From 77eccd0dfae353a64a2088d308bed3b373a4220f Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Tue, 1 Jun 2021 17:11:20 +0200 Subject: wait: use LIST_HEAD_INIT() to initialize wait_queue_head Replace the open-coded initialization with the right macro. Signed-off-by: Julian Wiedmann Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210601151120.329223-1-jwi@linux.ibm.com --- include/linux/wait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index fe10e8570a52..99c5f05718cd 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -56,7 +56,7 @@ struct task_struct; #define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .head = { &(name).head, &(name).head } } + .head = LIST_HEAD_INIT(name.head) } #define DECLARE_WAIT_QUEUE_HEAD(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name) -- cgit v1.2.3 From 18765447c3b7867b3f8cccde52dc9d822852e71b Mon Sep 17 00:00:00 2001 From: Hailong Liu Date: Sun, 6 Jun 2021 19:54:51 +0800 Subject: sched/sysctl: Move extern sysctl declarations to sched.h Since commit '8a99b6833c88(sched: Move SCHED_DEBUG sysctl to debugfs)', SCHED_DEBUG sysctls are moved to debugfs, so these extern sysctls in include/linux/sched/sysctl.h are no longer needed for sysctl.c, even some are no longer needed. So move those extern sysctls that needed by kernel/sched/debug.c to kernel/sched/sched.h, and remove others that are no longer needed. Signed-off-by: Hailong Liu Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210606115451.26745-1-liuhailongg6@163.com --- include/linux/sched/sysctl.h | 18 ------------------ kernel/sched/sched.h | 15 +++++++++++++++ 2 files changed, 15 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index db2c0f34aaaf..304f431178fd 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -28,30 +28,12 @@ enum { sysctl_hung_task_timeout_secs = 0 }; extern unsigned int sysctl_sched_child_runs_first; -extern unsigned int sysctl_sched_latency; -extern unsigned int sysctl_sched_min_granularity; -extern unsigned int sysctl_sched_wakeup_granularity; - enum sched_tunable_scaling { SCHED_TUNABLESCALING_NONE, SCHED_TUNABLESCALING_LOG, SCHED_TUNABLESCALING_LINEAR, SCHED_TUNABLESCALING_END, }; -extern unsigned int sysctl_sched_tunable_scaling; - -extern unsigned int sysctl_numa_balancing_scan_delay; -extern unsigned int sysctl_numa_balancing_scan_period_min; -extern unsigned int sysctl_numa_balancing_scan_period_max; -extern unsigned int sysctl_numa_balancing_scan_size; - -#ifdef CONFIG_SCHED_DEBUG -extern __read_mostly unsigned int sysctl_sched_migration_cost; -extern __read_mostly unsigned int sysctl_sched_nr_migrate; - -extern int sysctl_resched_latency_warn_ms; -extern int sysctl_resched_latency_warn_once; -#endif /* * control realtime throttling: diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c80d42e9589b..9a1c6aeb9165 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2385,6 +2385,21 @@ extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); extern const_debug unsigned int sysctl_sched_nr_migrate; extern const_debug unsigned int sysctl_sched_migration_cost; +#ifdef CONFIG_SCHED_DEBUG +extern unsigned int sysctl_sched_latency; +extern unsigned int sysctl_sched_min_granularity; +extern unsigned int sysctl_sched_wakeup_granularity; +extern int sysctl_resched_latency_warn_ms; +extern int sysctl_resched_latency_warn_once; + +extern unsigned int sysctl_sched_tunable_scaling; + +extern unsigned int sysctl_numa_balancing_scan_delay; +extern unsigned int sysctl_numa_balancing_scan_period_min; +extern unsigned int sysctl_numa_balancing_scan_period_max; +extern unsigned int sysctl_numa_balancing_scan_size; +#endif + #ifdef CONFIG_SCHED_HRTICK /* -- cgit v1.2.3 From fe21cb91ae7bca1ae7805454be80b6d03bec85f7 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 2 Jul 2021 16:48:21 +0530 Subject: net: core: Split out code to run generic XDP prog MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This helper can later be utilized in code that runs cpumap and devmap programs in generic redirect mode and adjust skb based on changes made to xdp_buff. When returning XDP_REDIRECT/XDP_TX, it invokes __skb_push, so whenever a generic redirect path invokes devmap/cpumap prog if set, it must __skb_pull again as we expect mac header to be pulled. It also drops the skb_reset_mac_len call after do_xdp_generic, as the mac_header and network_header are advanced by the same offset, so the difference (mac_len) remains constant. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Reviewed-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210702111825.491065-2-memxor@gmail.com --- include/linux/netdevice.h | 2 ++ net/core/dev.c | 84 ++++++++++++++++++++++++++++++----------------- 2 files changed, 55 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eaf5bb008aa9..42f6f866d5f3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3984,6 +3984,8 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); } +u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog); void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index c253c2aafe97..93e80c36cc97 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4744,45 +4744,18 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) return rxqueue; } -static u32 netif_receive_generic_xdp(struct sk_buff *skb, - struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) +u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) { void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; - u32 metalen, act = XDP_DROP; bool orig_bcast, orig_host; u32 mac_len, frame_sz; __be16 orig_eth_type; struct ethhdr *eth; + u32 metalen, act; int off; - /* Reinjected packets coming from act_mirred or similar should - * not get XDP generic processing. - */ - if (skb_is_redirected(skb)) - return XDP_PASS; - - /* XDP packets must be linear and must have sufficient headroom - * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also - * native XDP provides, thus we need to do it here as well. - */ - if (skb_cloned(skb) || skb_is_nonlinear(skb) || - skb_headroom(skb) < XDP_PACKET_HEADROOM) { - int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); - int troom = skb->tail + skb->data_len - skb->end; - - /* In case we have to go down the path and also linearize, - * then lets do the pskb_expand_head() work just once here. - */ - if (pskb_expand_head(skb, - hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, - troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) - goto do_drop; - if (skb_linearize(skb)) - goto do_drop; - } - /* The XDP program wants to see the packet starting at the MAC * header. */ @@ -4837,6 +4810,13 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, skb->protocol = eth_type_trans(skb, skb->dev); } + /* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull + * before calling us again on redirect path. We do not call do_redirect + * as we leave that up to the caller. + * + * Caller is responsible for managing lifetime of skb (i.e. calling + * kfree_skb in response to actions it cannot handle/XDP_DROP). + */ switch (act) { case XDP_REDIRECT: case XDP_TX: @@ -4847,6 +4827,49 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, if (metalen) skb_metadata_set(skb, metalen); break; + } + + return act; +} + +static u32 netif_receive_generic_xdp(struct sk_buff *skb, + struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) +{ + u32 act = XDP_DROP; + + /* Reinjected packets coming from act_mirred or similar should + * not get XDP generic processing. + */ + if (skb_is_redirected(skb)) + return XDP_PASS; + + /* XDP packets must be linear and must have sufficient headroom + * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also + * native XDP provides, thus we need to do it here as well. + */ + if (skb_cloned(skb) || skb_is_nonlinear(skb) || + skb_headroom(skb) < XDP_PACKET_HEADROOM) { + int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); + int troom = skb->tail + skb->data_len - skb->end; + + /* In case we have to go down the path and also linearize, + * then lets do the pskb_expand_head() work just once here. + */ + if (pskb_expand_head(skb, + hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, + troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) + goto do_drop; + if (skb_linearize(skb)) + goto do_drop; + } + + act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog); + switch (act) { + case XDP_REDIRECT: + case XDP_TX: + case XDP_PASS: + break; default: bpf_warn_invalid_xdp_action(act); fallthrough; @@ -5312,7 +5335,6 @@ another_round: ret = NET_RX_DROP; goto out; } - skb_reset_mac_len(skb); } if (eth_type_vlan(skb->protocol)) { -- cgit v1.2.3 From cb0f80039fb7ec9981a74d22019daaa85ff51a3d Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 2 Jul 2021 16:48:22 +0530 Subject: bitops: Add non-atomic bitops for pointers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cpumap needs to set, clear, and test the lowest bit in skb pointer in various places. To make these checks less noisy, add pointer friendly bitop macros that also do some typechecking to sanitize the argument. These wrap the non-atomic bitops __set_bit, __clear_bit, and test_bit but for pointer arguments. Pointer's address has to be passed in and it is treated as an unsigned long *, since width and representation of pointer and unsigned long match on targets Linux supports. They are prefixed with double underscore to indicate lack of atomicity. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Reviewed-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210702111825.491065-3-memxor@gmail.com --- include/linux/bitops.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/typecheck.h | 9 +++++++++ 2 files changed, 59 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 26bf15e6cd35..5e62e2383b7f 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -4,6 +4,7 @@ #include #include +#include #include @@ -253,6 +254,55 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, __clear_bit(nr, addr); } +/** + * __ptr_set_bit - Set bit in a pointer's value + * @nr: the bit to set + * @addr: the address of the pointer variable + * + * Example: + * void *p = foo(); + * __ptr_set_bit(bit, &p); + */ +#define __ptr_set_bit(nr, addr) \ + ({ \ + typecheck_pointer(*(addr)); \ + __set_bit(nr, (unsigned long *)(addr)); \ + }) + +/** + * __ptr_clear_bit - Clear bit in a pointer's value + * @nr: the bit to clear + * @addr: the address of the pointer variable + * + * Example: + * void *p = foo(); + * __ptr_clear_bit(bit, &p); + */ +#define __ptr_clear_bit(nr, addr) \ + ({ \ + typecheck_pointer(*(addr)); \ + __clear_bit(nr, (unsigned long *)(addr)); \ + }) + +/** + * __ptr_test_bit - Test bit in a pointer's value + * @nr: the bit to test + * @addr: the address of the pointer variable + * + * Example: + * void *p = foo(); + * if (__ptr_test_bit(bit, &p)) { + * ... + * } else { + * ... + * } + */ +#define __ptr_test_bit(nr, addr) \ + ({ \ + typecheck_pointer(*(addr)); \ + test_bit(nr, (unsigned long *)(addr)); \ + }) + #ifdef __KERNEL__ #ifndef set_mask_bits diff --git a/include/linux/typecheck.h b/include/linux/typecheck.h index 20d310331eb5..46b15e2aaefb 100644 --- a/include/linux/typecheck.h +++ b/include/linux/typecheck.h @@ -22,4 +22,13 @@ (void)__tmp; \ }) +/* + * Check at compile time that something is a pointer type. + */ +#define typecheck_pointer(x) \ +({ typeof(x) __dummy; \ + (void)sizeof(*__dummy); \ + 1; \ +}) + #endif /* TYPECHECK_H_INCLUDED */ -- cgit v1.2.3 From 11941f8a85362f612df61f4aaab0e41b64d2111d Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 2 Jul 2021 16:48:23 +0530 Subject: bpf: cpumap: Implement generic cpumap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This change implements CPUMAP redirect support for generic XDP programs. The idea is to reuse the cpu map entry's queue that is used to push native xdp frames for redirecting skb to a different CPU. This will match native XDP behavior (in that RPS is invoked again for packet reinjected into networking stack). To be able to determine whether the incoming skb is from the driver or cpumap, we reuse skb->redirected bit that skips generic XDP processing when it is set. To always make use of this, CONFIG_NET_REDIRECT guard on it has been lifted and it is always available. >From the redirect side, we add the skb to ptr_ring with its lowest bit set to 1. This should be safe as skb is not 1-byte aligned. This allows kthread to discern between xdp_frames and sk_buff. On consumption of the ptr_ring item, the lowest bit is unset. In the end, the skb is simply added to the list that kthread is anyway going to maintain for xdp_frames converted to skb, and then received again by using netif_receive_skb_list. Bulking optimization for generic cpumap is left as an exercise for a future patch for now. Since cpumap entry progs are now supported, also remove check in generic_xdp_install for the cpumap. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Reviewed-by: Toke Høiland-Jørgensen Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/20210702111825.491065-4-memxor@gmail.com --- include/linux/bpf.h | 9 +++- include/linux/skbuff.h | 10 +---- kernel/bpf/cpumap.c | 116 +++++++++++++++++++++++++++++++++++++++++-------- net/core/dev.c | 3 +- net/core/filter.c | 6 ++- 5 files changed, 114 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f309fc1509f2..095aaa104c56 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1513,7 +1513,8 @@ bool dev_map_can_have_prog(struct bpf_map *map); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); -bool cpu_map_prog_allowed(struct bpf_map *map); +int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, + struct sk_buff *skb); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) @@ -1710,6 +1711,12 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, return 0; } +static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, + struct sk_buff *skb) +{ + return -EOPNOTSUPP; +} + static inline bool cpu_map_prog_allowed(struct bpf_map *map) { return false; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b2db9cd9a73f..f19190820e63 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -863,8 +863,8 @@ struct sk_buff { __u8 tc_skip_classify:1; __u8 tc_at_ingress:1; #endif -#ifdef CONFIG_NET_REDIRECT __u8 redirected:1; +#ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif #ifdef CONFIG_TLS_DEVICE @@ -4664,17 +4664,13 @@ static inline __wsum lco_csum(struct sk_buff *skb) static inline bool skb_is_redirected(const struct sk_buff *skb) { -#ifdef CONFIG_NET_REDIRECT return skb->redirected; -#else - return false; -#endif } static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) { -#ifdef CONFIG_NET_REDIRECT skb->redirected = 1; +#ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) skb->tstamp = 0; @@ -4683,9 +4679,7 @@ static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) static inline void skb_reset_redirect(struct sk_buff *skb) { -#ifdef CONFIG_NET_REDIRECT skb->redirected = 0; -#endif } static inline bool skb_csum_is_sctp(struct sk_buff *skb) diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 480e936c54d0..585b2b77ccc4 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -16,6 +16,7 @@ * netstack, and assigning dedicated CPUs for this stage. This * basically allows for 10G wirespeed pre-filtering via bpf. */ +#include #include #include #include @@ -168,6 +169,46 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) } } +static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, + struct list_head *listp, + struct xdp_cpumap_stats *stats) +{ + struct sk_buff *skb, *tmp; + struct xdp_buff xdp; + u32 act; + int err; + + list_for_each_entry_safe(skb, tmp, listp, list) { + act = bpf_prog_run_generic_xdp(skb, &xdp, rcpu->prog); + switch (act) { + case XDP_PASS: + break; + case XDP_REDIRECT: + skb_list_del_init(skb); + err = xdp_do_generic_redirect(skb->dev, skb, &xdp, + rcpu->prog); + if (unlikely(err)) { + kfree_skb(skb); + stats->drop++; + } else { + stats->redirect++; + } + return; + default: + bpf_warn_invalid_xdp_action(act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(skb->dev, rcpu->prog, act); + fallthrough; + case XDP_DROP: + skb_list_del_init(skb); + kfree_skb(skb); + stats->drop++; + return; + } + } +} + static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, void **frames, int n, struct xdp_cpumap_stats *stats) @@ -176,11 +217,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, struct xdp_buff xdp; int i, nframes = 0; - if (!rcpu->prog) - return n; - - rcu_read_lock_bh(); - xdp_set_return_frame_no_direct(); xdp.rxq = &rxq; @@ -227,17 +263,37 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, } } + xdp_clear_return_frame_no_direct(); + + return nframes; +} + +#define CPUMAP_BATCH 8 + +static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, + int xdp_n, struct xdp_cpumap_stats *stats, + struct list_head *list) +{ + int nframes; + + if (!rcpu->prog) + return xdp_n; + + rcu_read_lock_bh(); + + nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, xdp_n, stats); + if (stats->redirect) - xdp_do_flush_map(); + xdp_do_flush(); - xdp_clear_return_frame_no_direct(); + if (unlikely(!list_empty(list))) + cpu_map_bpf_prog_run_skb(rcpu, list, stats); rcu_read_unlock_bh(); /* resched point, may call do_softirq() */ return nframes; } -#define CPUMAP_BATCH 8 static int cpu_map_kthread_run(void *data) { @@ -254,9 +310,9 @@ static int cpu_map_kthread_run(void *data) struct xdp_cpumap_stats stats = {}; /* zero stats */ unsigned int kmem_alloc_drops = 0, sched = 0; gfp_t gfp = __GFP_ZERO | GFP_ATOMIC; + int i, n, m, nframes, xdp_n; void *frames[CPUMAP_BATCH]; void *skbs[CPUMAP_BATCH]; - int i, n, m, nframes; LIST_HEAD(list); /* Release CPU reschedule checks */ @@ -280,9 +336,20 @@ static int cpu_map_kthread_run(void *data) */ n = __ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH); - for (i = 0; i < n; i++) { + for (i = 0, xdp_n = 0; i < n; i++) { void *f = frames[i]; - struct page *page = virt_to_page(f); + struct page *page; + + if (unlikely(__ptr_test_bit(0, &f))) { + struct sk_buff *skb = f; + + __ptr_clear_bit(0, &skb); + list_add_tail(&skb->list, &list); + continue; + } + + frames[xdp_n++] = f; + page = virt_to_page(f); /* Bring struct page memory area to curr CPU. Read by * build_skb_around via page_is_pfmemalloc(), and when @@ -292,7 +359,7 @@ static int cpu_map_kthread_run(void *data) } /* Support running another XDP prog on this CPU */ - nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, n, &stats); + nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list); if (nframes) { m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs); if (unlikely(m == 0)) { @@ -330,12 +397,6 @@ static int cpu_map_kthread_run(void *data) return 0; } -bool cpu_map_prog_allowed(struct bpf_map *map) -{ - return map->map_type == BPF_MAP_TYPE_CPUMAP && - map->value_size != offsetofend(struct bpf_cpumap_val, qsize); -} - static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd) { struct bpf_prog *prog; @@ -701,6 +762,25 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, return 0; } +int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, + struct sk_buff *skb) +{ + int ret; + + __skb_pull(skb, skb->mac_len); + skb_set_redirected(skb, false); + __ptr_set_bit(0, &skb); + + ret = ptr_ring_produce(rcpu->queue, skb); + if (ret < 0) + goto trace; + + wake_up_process(rcpu->kthread); +trace: + trace_xdp_cpumap_enqueue(rcpu->map_id, !ret, !!ret, rcpu->cpu); + return ret; +} + void __cpu_map_flush(void) { struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list); diff --git a/net/core/dev.c b/net/core/dev.c index 93e80c36cc97..4c51d1f81633 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5669,8 +5669,7 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) * have a bpf_prog installed on an entry */ for (i = 0; i < new->aux->used_map_cnt; i++) { - if (dev_map_can_have_prog(new->aux->used_maps[i]) || - cpu_map_prog_allowed(new->aux->used_maps[i])) { + if (dev_map_can_have_prog(new->aux->used_maps[i])) { mutex_unlock(&new->aux->used_maps_mutex); return -EINVAL; } diff --git a/net/core/filter.c b/net/core/filter.c index f2c15b2a057a..3b4986e96e9c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4040,8 +4040,12 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, goto err; consume_skb(skb); break; + case BPF_MAP_TYPE_CPUMAP: + err = cpu_map_generic_redirect(fwd, skb); + if (unlikely(err)) + goto err; + break; default: - /* TODO: Handle BPF_MAP_TYPE_CPUMAP */ err = -EBADRQC; goto err; } -- cgit v1.2.3 From 2ea5eabaf04a1829383aefe98ac38a2e5ae2d698 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 2 Jul 2021 16:48:24 +0530 Subject: bpf: devmap: Implement devmap prog execution for generic XDP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This lifts the restriction on running devmap BPF progs in generic redirect mode. To match native XDP behavior, it is invoked right before generic_xdp_tx is called, and only supports XDP_PASS/XDP_ABORTED/ XDP_DROP actions. We also return 0 even if devmap program drops the packet, as semantically redirect has already succeeded and the devmap prog is the last point before TX of the packet to device where it can deliver a verdict on the packet. This also means it must take care of freeing the skb, as xdp_do_generic_redirect callers only do that in case an error is returned. Since devmap entry prog is supported, remove the check in generic_xdp_install entirely. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Reviewed-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210702111825.491065-5-memxor@gmail.com --- include/linux/bpf.h | 1 - kernel/bpf/devmap.c | 49 +++++++++++++++++++++++++++++++++++++++---------- net/core/dev.c | 18 ------------------ 3 files changed, 39 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 095aaa104c56..4afbff308ca3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1508,7 +1508,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress); -bool dev_map_can_have_prog(struct bpf_map *map); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 2546dafd6672..fa26eac5e4b6 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -322,16 +322,6 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, return -ENOENT; } -bool dev_map_can_have_prog(struct bpf_map *map) -{ - if ((map->map_type == BPF_MAP_TYPE_DEVMAP || - map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) && - map->value_size != offsetofend(struct bpf_devmap_val, ifindex)) - return true; - - return false; -} - static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, struct net_device *dev) @@ -499,6 +489,37 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, return 0; } +static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst) +{ + struct xdp_txq_info txq = { .dev = dst->dev }; + struct xdp_buff xdp; + u32 act; + + if (!dst->xdp_prog) + return XDP_PASS; + + __skb_pull(skb, skb->mac_len); + xdp.txq = &txq; + + act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog); + switch (act) { + case XDP_PASS: + __skb_push(skb, skb->mac_len); + break; + default: + bpf_warn_invalid_xdp_action(act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(dst->dev, dst->xdp_prog, act); + fallthrough; + case XDP_DROP: + kfree_skb(skb); + break; + } + + return act; +} + int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, struct net_device *dev_rx) { @@ -614,6 +635,14 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; + + /* Redirect has already succeeded semantically at this point, so we just + * return 0 even if packet is dropped. Helper below takes care of + * freeing skb. + */ + if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS) + return 0; + skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); diff --git a/net/core/dev.c b/net/core/dev.c index 4c51d1f81633..71f7175cad9a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5660,24 +5660,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) struct bpf_prog *new = xdp->prog; int ret = 0; - if (new) { - u32 i; - - mutex_lock(&new->aux->used_maps_mutex); - - /* generic XDP does not work with DEVMAPs that can - * have a bpf_prog installed on an entry - */ - for (i = 0; i < new->aux->used_map_cnt; i++) { - if (dev_map_can_have_prog(new->aux->used_maps[i])) { - mutex_unlock(&new->aux->used_maps_mutex); - return -EINVAL; - } - } - - mutex_unlock(&new->aux->used_maps_mutex); - } - switch (xdp->command) { case XDP_SETUP_PROG: rcu_assign_pointer(dev->xdp_prog, new); -- cgit v1.2.3 From 0238bcf80e972f2ce25d767e54f89a9e49773f6e Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 5 Jul 2021 22:42:47 +0300 Subject: ASoC: ti: davinci-mcasp: Add support for the OMAP4 version of McASP There is a single McASP on OMAP4 (and OMAP5) which is configured to only support DIT playback mode on a single serializer. Add 0x200 offset to DAT port address as the TRM suggests it. Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20210705194249.2385-4-peter.ujfalusi@gmail.com Signed-off-by: Mark Brown --- include/linux/platform_data/davinci_asp.h | 1 + sound/soc/ti/Kconfig | 1 + sound/soc/ti/davinci-mcasp.c | 26 +++++++++++++++++++++++--- 3 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h index 5d1fb0d78a22..76b13ef67562 100644 --- a/include/linux/platform_data/davinci_asp.h +++ b/include/linux/platform_data/davinci_asp.h @@ -96,6 +96,7 @@ enum { MCASP_VERSION_2, /* DA8xx/OMAPL1x */ MCASP_VERSION_3, /* TI81xx/AM33xx */ MCASP_VERSION_4, /* DRA7xxx */ + MCASP_VERSION_OMAP, /* OMAP4/5 */ }; enum mcbsp_clk_input_pin { diff --git a/sound/soc/ti/Kconfig b/sound/soc/ti/Kconfig index 698d7bc84dcf..1d9fe3fca193 100644 --- a/sound/soc/ti/Kconfig +++ b/sound/soc/ti/Kconfig @@ -35,6 +35,7 @@ config SND_SOC_DAVINCI_MCASP various Texas Instruments SoCs like: - daVinci devices - Sitara line of SoCs (AM335x, AM438x, etc) + - OMAP4 - DRA7x devices - Keystone devices - K3 devices (am654, j721e) diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c index 64ec6d485834..56a19eeec5c7 100644 --- a/sound/soc/ti/davinci-mcasp.c +++ b/sound/soc/ti/davinci-mcasp.c @@ -1794,6 +1794,12 @@ static struct davinci_mcasp_pdata dra7_mcasp_pdata = { .version = MCASP_VERSION_4, }; +static struct davinci_mcasp_pdata omap_mcasp_pdata = { + .tx_dma_offset = 0x200, + .rx_dma_offset = 0, + .version = MCASP_VERSION_OMAP, +}; + static const struct of_device_id mcasp_dt_ids[] = { { .compatible = "ti,dm646x-mcasp-audio", @@ -1811,6 +1817,10 @@ static const struct of_device_id mcasp_dt_ids[] = { .compatible = "ti,dra7-mcasp-audio", .data = &dra7_mcasp_pdata, }, + { + .compatible = "ti,omap4-mcasp-audio", + .data = &omap_mcasp_pdata, + }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, mcasp_dt_ids); @@ -2350,10 +2360,17 @@ static int davinci_mcasp_probe(struct platform_device *pdev) dma_data = &mcasp->dma_data[SNDRV_PCM_STREAM_PLAYBACK]; dma_data->filter_data = "tx"; - if (dat) + if (dat) { dma_data->addr = dat->start; - else + /* + * According to the TRM there should be 0x200 offset added to + * the DAT port address + */ + if (mcasp->version == MCASP_VERSION_OMAP) + dma_data->addr += davinci_mcasp_txdma_offset(mcasp->pdata); + } else { dma_data->addr = mem->start + davinci_mcasp_txdma_offset(mcasp->pdata); + } /* RX is not valid in DIT mode */ @@ -2418,7 +2435,10 @@ static int davinci_mcasp_probe(struct platform_device *pdev) ret = edma_pcm_platform_register(&pdev->dev); break; case PCM_SDMA: - ret = sdma_pcm_platform_register(&pdev->dev, "tx", "rx"); + if (mcasp->op_mode == DAVINCI_MCASP_IIS_MODE) + ret = sdma_pcm_platform_register(&pdev->dev, "tx", "rx"); + else + ret = sdma_pcm_platform_register(&pdev->dev, "tx", NULL); break; case PCM_UDMA: ret = udma_pcm_platform_register(&pdev->dev); -- cgit v1.2.3 From 4ff75a29976590bc7afe3ed75d547c1f2a924c75 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 25 Jun 2021 15:23:22 +0300 Subject: regulator: devres: remove devm_regulator_unregister() function This API hook isn't used anywhere and most-likely exists because of the general principle of C APIs, where if an API function does an allocation/registration, it must also have an equivalent deallocation/deregistration counterpart. For devm_ functions this isn't all that true (for all cases), as the idea of these function is to provide an auto-cleanup logic on drivers/system de-init. Removing this also discourages any weird logic that could be created with such an API function. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210625122324.327585-3-aardelean@deviqon.com Signed-off-by: Mark Brown --- drivers/regulator/devres.c | 29 ----------------------------- include/linux/regulator/driver.h | 1 - 2 files changed, 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/devres.c b/drivers/regulator/devres.c index a8de0aa88bad..79e2571113b6 100644 --- a/drivers/regulator/devres.c +++ b/drivers/regulator/devres.c @@ -205,35 +205,6 @@ struct regulator_dev *devm_regulator_register(struct device *dev, } EXPORT_SYMBOL_GPL(devm_regulator_register); -static int devm_rdev_match(struct device *dev, void *res, void *data) -{ - struct regulator_dev **r = res; - if (!r || !*r) { - WARN_ON(!r || !*r); - return 0; - } - return *r == data; -} - -/** - * devm_regulator_unregister - Resource managed regulator_unregister() - * @dev: device to supply - * @rdev: regulator to free - * - * Unregister a regulator registered with devm_regulator_register(). - * Normally this function will not need to be called and the resource - * management code will ensure that the resource is freed. - */ -void devm_regulator_unregister(struct device *dev, struct regulator_dev *rdev) -{ - int rc; - - rc = devres_release(dev, devm_rdev_release, devm_rdev_match, rdev); - if (rc != 0) - WARN_ON(rc); -} -EXPORT_SYMBOL_GPL(devm_regulator_unregister); - struct regulator_supply_alias_match { struct device *dev; const char *id; diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 4aec20387857..5447a6b33fa0 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -645,7 +645,6 @@ devm_regulator_register(struct device *dev, const struct regulator_desc *regulator_desc, const struct regulator_config *config); void regulator_unregister(struct regulator_dev *rdev); -void devm_regulator_unregister(struct device *dev, struct regulator_dev *rdev); int regulator_notifier_call_chain(struct regulator_dev *rdev, unsigned long event, void *data); -- cgit v1.2.3 From eed43b96ede9c3f018ad24149de83f24b86ad729 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 25 Jun 2021 15:23:23 +0300 Subject: regulator: devres: remove devm_regulator_bulk_unregister_supply_alias() This API hook isn't used anywhere and most-likely exists because of the general principle of C APIs, where if an API function does an allocation/registration, it must also have an equivalent deallocation/deregistration counterpart. For devm_ functions this isn't all that true (for all cases), as the idea of these function is to provide an auto-cleanup logic on drivers/system de-init. Removing this also discourages any weird logic that could be created with such an API function. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210625122324.327585-4-aardelean@deviqon.com Signed-off-by: Mark Brown --- drivers/regulator/devres.c | 24 ------------------------ include/linux/regulator/consumer.h | 8 -------- 2 files changed, 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/devres.c b/drivers/regulator/devres.c index 79e2571113b6..6c657b29a6e1 100644 --- a/drivers/regulator/devres.c +++ b/drivers/regulator/devres.c @@ -344,30 +344,6 @@ err: } EXPORT_SYMBOL_GPL(devm_regulator_bulk_register_supply_alias); -/** - * devm_regulator_bulk_unregister_supply_alias - Managed unregister - * multiple aliases - * - * @dev: device to supply - * @id: list of supply names or regulator IDs - * @num_id: number of aliases to unregister - * - * Unregister aliases registered with - * devm_regulator_bulk_register_supply_alias(). Normally this function - * will not need to be called and the resource management code - * will ensure that the resource is freed. - */ -void devm_regulator_bulk_unregister_supply_alias(struct device *dev, - const char *const *id, - int num_id) -{ - int i; - - for (i = 0; i < num_id; ++i) - devm_regulator_unregister_supply_alias(dev, id[i]); -} -EXPORT_SYMBOL_GPL(devm_regulator_bulk_unregister_supply_alias); - struct regulator_notifier_match { struct regulator *regulator; struct notifier_block *nb; diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index f72ca73631be..98518b3f2828 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -230,9 +230,6 @@ int devm_regulator_bulk_register_supply_alias(struct device *dev, struct device *alias_dev, const char *const *alias_id, int num_id); -void devm_regulator_bulk_unregister_supply_alias(struct device *dev, - const char *const *id, - int num_id); /* regulator output control and status */ int __must_check regulator_enable(struct regulator *regulator); @@ -422,11 +419,6 @@ static inline int devm_regulator_bulk_register_supply_alias(struct device *dev, return 0; } -static inline void devm_regulator_bulk_unregister_supply_alias( - struct device *dev, const char *const *id, int num_id) -{ -} - static inline int regulator_enable(struct regulator *regulator) { return 0; -- cgit v1.2.3 From 4d9f4d1de3ceb84fa6ce68177a26b8fac6a71290 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 25 Jun 2021 15:23:24 +0300 Subject: regulator: devres: unexport devm_regulator_unregister_supply_alias() This API hook isn't used anywhere outside of the regulator devres code. This function is needed for the devm_regulator_bulk_register_supply_alias() function on the error path, to cleanup any previously registered supply aliases. This change makes the devm_regulator_unregister_supply_alias() local to the regulator core framework, to avoid it being used in any weird logic. It's also removing the doc-string for devm_regulator_unregister_supply_alias(), since it doesn't need to be documented anymore, as no other external consumer should use it. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210625122324.327585-5-aardelean@deviqon.com Signed-off-by: Mark Brown --- drivers/regulator/devres.c | 16 ++-------------- include/linux/regulator/consumer.h | 7 ------- 2 files changed, 2 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/devres.c b/drivers/regulator/devres.c index 6c657b29a6e1..9113233f41cd 100644 --- a/drivers/regulator/devres.c +++ b/drivers/regulator/devres.c @@ -267,19 +267,8 @@ int devm_regulator_register_supply_alias(struct device *dev, const char *id, } EXPORT_SYMBOL_GPL(devm_regulator_register_supply_alias); -/** - * devm_regulator_unregister_supply_alias - Resource managed - * regulator_unregister_supply_alias() - * - * @dev: device to supply - * @id: supply name or regulator ID - * - * Unregister an alias registered with - * devm_regulator_register_supply_alias(). Normally this function - * will not need to be called and the resource management code - * will ensure that the resource is freed. - */ -void devm_regulator_unregister_supply_alias(struct device *dev, const char *id) +static void devm_regulator_unregister_supply_alias(struct device *dev, + const char *id) { struct regulator_supply_alias_match match; int rc; @@ -292,7 +281,6 @@ void devm_regulator_unregister_supply_alias(struct device *dev, const char *id) if (rc != 0) WARN_ON(rc); } -EXPORT_SYMBOL_GPL(devm_regulator_unregister_supply_alias); /** * devm_regulator_bulk_register_supply_alias - Managed register diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 98518b3f2828..bbf6590a6dec 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -222,8 +222,6 @@ void regulator_bulk_unregister_supply_alias(struct device *dev, int devm_regulator_register_supply_alias(struct device *dev, const char *id, struct device *alias_dev, const char *alias_id); -void devm_regulator_unregister_supply_alias(struct device *dev, - const char *id); int devm_regulator_bulk_register_supply_alias(struct device *dev, const char *const *id, @@ -405,11 +403,6 @@ static inline int devm_regulator_register_supply_alias(struct device *dev, return 0; } -static inline void devm_regulator_unregister_supply_alias(struct device *dev, - const char *id) -{ -} - static inline int devm_regulator_bulk_register_supply_alias(struct device *dev, const char *const *id, struct device *alias_dev, -- cgit v1.2.3 From 6eb891cf73bd2ecc877e9916951a19f3e4f3c493 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Tue, 6 Jul 2021 14:45:39 +0800 Subject: regulator: rt5033: Use linear ranges to map all voltage selection Instead of linear mapping, Use linear range to map all voltage selection. Signed-off-by: ChiYuan Huang Reviewed-by: Axel Lin Acked-by: Lee Jones Link: https://lore.kernel.org/r/1625553939-9109-1-git-send-email-u0084500@gmail.com Signed-off-by: Mark Brown --- drivers/regulator/rt5033-regulator.c | 21 +++++++++++++++------ include/linux/mfd/rt5033-private.h | 4 ++-- 2 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/rt5033-regulator.c b/drivers/regulator/rt5033-regulator.c index 0e7311629165..da4cf5a6acc2 100644 --- a/drivers/regulator/rt5033-regulator.c +++ b/drivers/regulator/rt5033-regulator.c @@ -13,6 +13,16 @@ #include #include +static const struct linear_range rt5033_buck_ranges[] = { + REGULATOR_LINEAR_RANGE(1000000, 0, 20, 100000), + REGULATOR_LINEAR_RANGE(3000000, 21, 31, 0), +}; + +static const struct linear_range rt5033_ldo_ranges[] = { + REGULATOR_LINEAR_RANGE(1200000, 0, 18, 100000), + REGULATOR_LINEAR_RANGE(3000000, 19, 31, 0), +}; + static const struct regulator_ops rt5033_safe_ldo_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, @@ -24,8 +34,7 @@ static const struct regulator_ops rt5033_buck_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, - .list_voltage = regulator_list_voltage_linear, - .map_voltage = regulator_map_voltage_linear, + .list_voltage = regulator_list_voltage_linear_range, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = regulator_set_voltage_sel_regmap, }; @@ -40,8 +49,8 @@ static const struct regulator_desc rt5033_supported_regulators[] = { .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, .n_voltages = RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM, - .min_uV = RT5033_REGULATOR_BUCK_VOLTAGE_MIN, - .uV_step = RT5033_REGULATOR_BUCK_VOLTAGE_STEP, + .linear_ranges = rt5033_buck_ranges, + .n_linear_ranges = ARRAY_SIZE(rt5033_buck_ranges), .enable_reg = RT5033_REG_CTRL, .enable_mask = RT5033_CTRL_EN_BUCK_MASK, .vsel_reg = RT5033_REG_BUCK_CTRL, @@ -56,8 +65,8 @@ static const struct regulator_desc rt5033_supported_regulators[] = { .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, .n_voltages = RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM, - .min_uV = RT5033_REGULATOR_LDO_VOLTAGE_MIN, - .uV_step = RT5033_REGULATOR_LDO_VOLTAGE_STEP, + .linear_ranges = rt5033_ldo_ranges, + .n_linear_ranges = ARRAY_SIZE(rt5033_ldo_ranges), .enable_reg = RT5033_REG_CTRL, .enable_mask = RT5033_CTRL_EN_LDO_MASK, .vsel_reg = RT5033_REG_LDO_CTRL, diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h index 40a0c2dfb80f..2d1895c3efbf 100644 --- a/include/linux/mfd/rt5033-private.h +++ b/include/linux/mfd/rt5033-private.h @@ -200,13 +200,13 @@ enum rt5033_reg { #define RT5033_REGULATOR_BUCK_VOLTAGE_MIN 1000000U #define RT5033_REGULATOR_BUCK_VOLTAGE_MAX 3000000U #define RT5033_REGULATOR_BUCK_VOLTAGE_STEP 100000U -#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 21 +#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 32 /* RT5033 regulator LDO output voltage uV */ #define RT5033_REGULATOR_LDO_VOLTAGE_MIN 1200000U #define RT5033_REGULATOR_LDO_VOLTAGE_MAX 3000000U #define RT5033_REGULATOR_LDO_VOLTAGE_STEP 100000U -#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 19 +#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 32 /* RT5033 regulator SAFE LDO output voltage uV */ #define RT5033_REGULATOR_SAFE_LDO_VOLTAGE 4900000U -- cgit v1.2.3 From 78bbb7c345ab630cfe8b272c6179bf8b19a6c8aa Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 27 Jun 2021 18:54:22 -0700 Subject: regulator: machine.h: fix kernel-doc "bad line" Fix warning caused by a blank/empty line: ../include/linux/regulator/machine.h:115: warning: bad line: Signed-off-by: Randy Dunlap Link: https://lore.kernel.org/r/20210628015422.8845-1-rdunlap@infradead.org Signed-off-by: Mark Brown --- include/linux/regulator/machine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 68b4a514a410..621b7f4a3639 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -112,7 +112,7 @@ struct notification_limit { * @over_voltage_limits: Limits for acting on over voltage. * @under_voltage_limits: Limits for acting on under voltage. * @temp_limits: Limits for acting on over temperature. - + * * @max_spread: Max possible spread between coupled regulators * @max_uV_step: Max possible step change in voltage * @valid_modes_mask: Mask of modes which may be configured by consumers. -- cgit v1.2.3 From 8dd591ad0104593f315b6b2ab636a18c002f7d86 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 28 Jun 2021 14:05:20 -0700 Subject: spi: : add missing struct kernel-doc entry Fix kernel-doc warning in spi.h by adding the missing kernel-doc entry and also correct the original comment so that they both indicate the correct polarity of the flag. ../include/linux/spi/spi.h:673: warning: Function parameter or member 'devm_allocated' not described in 'spi_controller' Fixes: 794aaf01444d ("spi: Fix use-after-free with devm_spi_alloc_*") Signed-off-by: Randy Dunlap Cc: William A. Kennington III Cc: Mark Brown Cc: linux-spi@vger.kernel.org Cc: Lukas Wunner Reviewed-by: Lukas Wunner Link: https://lore.kernel.org/r/20210628210520.5712-1-rdunlap@infradead.org Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 97b8d12b5f2b..3a81b5d1c3cb 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -339,6 +339,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @max_speed_hz: Highest supported transfer speed * @flags: other constraints relevant to this driver * @slave: indicates that this is an SPI slave controller + * @devm_allocated: whether the allocation of this struct is devres-managed * @max_transfer_size: function that returns the max transfer size for * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. * @max_message_size: function that returns the max message size for @@ -511,7 +512,7 @@ struct spi_controller { #define SPI_MASTER_GPIO_SS BIT(5) /* GPIO CS must select slave */ - /* flag indicating this is a non-devres managed controller */ + /* flag indicating if the allocation of this struct is devres-managed */ bool devm_allocated; /* flag indicating this is an SPI slave controller */ -- cgit v1.2.3 From ce7d0008c2356626f69f37ef1afce8fbc83fe142 Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Sat, 10 Jul 2021 02:13:10 -0700 Subject: usb: gadget: udc: core: Introduce check_config to verify USB configuration Some UDCs may have constraints on how many high bandwidth endpoints it can support in a certain configuration. This API allows for the composite driver to pass down the total number of endpoints to the UDC so it can verify it has the required resources to support the configuration. Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/1625908395-5498-2-git-send-email-wcheng@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/core.c | 19 +++++++++++++++++++ include/linux/usb/gadget.h | 4 ++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index b7f0b1ebaaa8..14fdf918ecfe 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1003,6 +1003,25 @@ int usb_gadget_ep_match_desc(struct usb_gadget *gadget, } EXPORT_SYMBOL_GPL(usb_gadget_ep_match_desc); +/** + * usb_gadget_check_config - checks if the UDC can support the binded + * configuration + * @gadget: controller to check the USB configuration + * + * Ensure that a UDC is able to support the requested resources by a + * configuration, and that there are no resource limitations, such as + * internal memory allocated to all requested endpoints. + * + * Returns zero on success, else a negative errno. + */ +int usb_gadget_check_config(struct usb_gadget *gadget) +{ + if (gadget->ops->check_config) + return gadget->ops->check_config(gadget); + return 0; +} +EXPORT_SYMBOL_GPL(usb_gadget_check_config); + /* ------------------------------------------------------------------------- */ static void usb_gadget_state_work(struct work_struct *work) diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 75c7538e350a..776851e57741 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -329,6 +329,7 @@ struct usb_gadget_ops { struct usb_ep *(*match_ep)(struct usb_gadget *, struct usb_endpoint_descriptor *, struct usb_ss_ep_comp_descriptor *); + int (*check_config)(struct usb_gadget *gadget); }; /** @@ -608,6 +609,7 @@ int usb_gadget_connect(struct usb_gadget *gadget); int usb_gadget_disconnect(struct usb_gadget *gadget); int usb_gadget_deactivate(struct usb_gadget *gadget); int usb_gadget_activate(struct usb_gadget *gadget); +int usb_gadget_check_config(struct usb_gadget *gadget); #else static inline int usb_gadget_frame_number(struct usb_gadget *gadget) { return 0; } @@ -631,6 +633,8 @@ static inline int usb_gadget_deactivate(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_activate(struct usb_gadget *gadget) { return 0; } +static inline int usb_gadget_check_config(struct usb_gadget *gadget) +{ return 0; } #endif /* CONFIG_USB_GADGET */ /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From fe794e39548308e77e570fdf645d516554b3f873 Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Sat, 10 Jul 2021 02:13:13 -0700 Subject: of: Add stub for of_add_property() If building with OF Kconfig disabled, this can lead to errors for drivers utilizing of_add_property(). Add a stub for the add API, as it exists for the remove variant as well, and to avoid compliation issues. Also, export this API so that it can be used by modules. Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/1625908395-5498-5-git-send-email-wcheng@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- drivers/of/base.c | 1 + include/linux/of.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/drivers/of/base.c b/drivers/of/base.c index 48e941f99558..5883d63c7714 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1821,6 +1821,7 @@ int of_add_property(struct device_node *np, struct property *prop) return rc; } +EXPORT_SYMBOL_GPL(of_add_property); int __of_remove_property(struct device_node *np, struct property *prop) { diff --git a/include/linux/of.h b/include/linux/of.h index 9c2e71e202d1..0e786b60bd5d 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -946,6 +946,11 @@ static inline int of_machine_is_compatible(const char *compat) return 0; } +static inline int of_add_property(struct device_node *np, struct property *prop) +{ + return 0; +} + static inline int of_remove_property(struct device_node *np, struct property *prop) { return 0; -- cgit v1.2.3 From b48c7236b13cb5ef1b5fdf744aa8841df0f7b43a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 29 Jun 2021 15:11:44 -0500 Subject: exit/bdflush: Remove the deprecated bdflush system call The bdflush system call has been deprecated for a very long time. Recently Michael Schmitz tested[1] and found that the last known caller of of the bdflush system call is unaffected by it's removal. Since the code is not needed delete it. [1] https://lkml.kernel.org/r/36123b5d-daa0-6c2b-f2d4-a942f069fd54@gmail.com Link: https://lkml.kernel.org/r/87sg10quue.fsf_-_@disp2133 Tested-by: Michael Schmitz Acked-by: Geert Uytterhoeven Reviewed-by: Arnd Bergmann Acked-by: Cyril Hrubis Signed-off-by: "Eric W. Biederman" --- arch/alpha/kernel/syscalls/syscall.tbl | 2 +- arch/arm/tools/syscall.tbl | 2 +- arch/arm64/include/asm/unistd32.h | 2 +- arch/ia64/kernel/syscalls/syscall.tbl | 2 +- arch/m68k/kernel/syscalls/syscall.tbl | 2 +- arch/microblaze/kernel/syscalls/syscall.tbl | 2 +- arch/mips/kernel/syscalls/syscall_o32.tbl | 2 +- arch/parisc/kernel/syscalls/syscall.tbl | 2 +- arch/powerpc/kernel/syscalls/syscall.tbl | 2 +- arch/s390/kernel/syscalls/syscall.tbl | 2 +- arch/sh/kernel/syscalls/syscall.tbl | 2 +- arch/sparc/kernel/syscalls/syscall.tbl | 2 +- arch/x86/entry/syscalls/syscall_32.tbl | 2 +- arch/xtensa/kernel/syscalls/syscall.tbl | 2 +- fs/buffer.c | 27 ---------------------- include/linux/syscalls.h | 1 - include/uapi/linux/capability.h | 1 - kernel/sys_ni.c | 1 - tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 2 +- tools/perf/arch/s390/entry/syscalls/syscall.tbl | 2 +- 20 files changed, 16 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index a17687ed4b51..7ac22e007d52 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -230,7 +230,7 @@ 259 common osf_swapctl sys_ni_syscall 260 common osf_memcntl sys_ni_syscall 261 common osf_fdatasync sys_ni_syscall -300 common bdflush sys_bdflush +300 common bdflush sys_ni_syscall 301 common sethae sys_sethae 302 common mount sys_mount 303 common old_adjtimex sys_old_adjtimex diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index c5df1179fc5d..f8a2d5aa17b7 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -147,7 +147,7 @@ 131 common quotactl sys_quotactl 132 common getpgid sys_getpgid 133 common fchdir sys_fchdir -134 common bdflush sys_bdflush +134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs 136 common personality sys_personality # 137 was sys_afs_syscall diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 99ffcafc736c..03d4ca47d253 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -279,7 +279,7 @@ __SYSCALL(__NR_getpgid, sys_getpgid) #define __NR_fchdir 133 __SYSCALL(__NR_fchdir, sys_fchdir) #define __NR_bdflush 134 -__SYSCALL(__NR_bdflush, sys_bdflush) +__SYSCALL(__NR_bdflush, sys_ni_syscall) #define __NR_sysfs 135 __SYSCALL(__NR_sysfs, sys_sysfs) #define __NR_personality 136 diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 6d07742c57b8..4b20224b14d9 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -123,7 +123,7 @@ # 1135 was get_kernel_syms # 1136 was query_module 113 common quotactl sys_quotactl -114 common bdflush sys_bdflush +114 common bdflush sys_ni_syscall 115 common sysfs sys_sysfs 116 common personality sys_personality 117 common afs_syscall sys_ni_syscall diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 541bc1b3a8f9..3ec1291c268d 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -141,7 +141,7 @@ 131 common quotactl sys_quotactl 132 common getpgid sys_getpgid 133 common fchdir sys_fchdir -134 common bdflush sys_bdflush +134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs 136 common personality sys_personality # 137 was afs_syscall diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index a176faca2927..9be3ace12938 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -141,7 +141,7 @@ 131 common quotactl sys_quotactl 132 common getpgid sys_getpgid 133 common fchdir sys_fchdir -134 common bdflush sys_bdflush +134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs 136 common personality sys_personality 137 common afs_syscall sys_ni_syscall diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 253f2cd70b6b..fae35882a165 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -145,7 +145,7 @@ 131 o32 quotactl sys_quotactl 132 o32 getpgid sys_getpgid 133 o32 fchdir sys_fchdir -134 o32 bdflush sys_bdflush +134 o32 bdflush sys_ni_syscall 135 o32 sysfs sys_sysfs 136 o32 personality sys_personality sys_32_personality 137 o32 afs_syscall sys_ni_syscall diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index e26187b9ab87..eaf0603ae781 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -147,7 +147,7 @@ 131 common quotactl sys_quotactl 132 common getpgid sys_getpgid 133 common fchdir sys_fchdir -134 common bdflush sys_bdflush +134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs 136 32 personality parisc_personality 136 64 personality sys_personality diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index aef2a290e71a..6f3953f2a0d5 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -176,7 +176,7 @@ 131 nospu quotactl sys_quotactl 132 common getpgid sys_getpgid 133 common fchdir sys_fchdir -134 common bdflush sys_bdflush +134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs 136 32 personality sys_personality ppc64_personality 136 64 personality ppc64_personality diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 64d51ab5a8b4..aa705e1bd0dc 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -122,7 +122,7 @@ 131 common quotactl sys_quotactl sys_quotactl 132 common getpgid sys_getpgid sys_getpgid 133 common fchdir sys_fchdir sys_fchdir -134 common bdflush sys_bdflush sys_bdflush +134 common bdflush sys_ni_syscall sys_ni_syscall 135 common sysfs sys_sysfs sys_sysfs 136 common personality sys_s390_personality sys_s390_personality 137 common afs_syscall - - diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index e0a70be77d84..7bbd6700ae4b 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -141,7 +141,7 @@ 131 common quotactl sys_quotactl 132 common getpgid sys_getpgid 133 common fchdir sys_fchdir -134 common bdflush sys_bdflush +134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs 136 common personality sys_personality # 137 was afs_syscall diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 603f5a821502..f520e9cd2c78 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -270,7 +270,7 @@ 222 common delete_module sys_delete_module 223 common get_kernel_syms sys_ni_syscall 224 common getpgid sys_getpgid -225 common bdflush sys_bdflush +225 common bdflush sys_ni_syscall 226 common sysfs sys_sysfs 227 common afs_syscall sys_nis_syscall 228 common setfsuid sys_setfsuid16 diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ce763a12311c..a5beae6daf20 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -145,7 +145,7 @@ 131 i386 quotactl sys_quotactl 132 i386 getpgid sys_getpgid 133 i386 fchdir sys_fchdir -134 i386 bdflush sys_bdflush +134 i386 bdflush sys_ni_syscall 135 i386 sysfs sys_sysfs 136 i386 personality sys_personality 137 i386 afs_syscall diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 235d67d6ceb4..b3d1bc8a9095 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -223,7 +223,7 @@ # 205 was old nfsservctl 205 common nfsservctl sys_ni_syscall 206 common _sysctl sys_ni_syscall -207 common bdflush sys_bdflush +207 common bdflush sys_ni_syscall 208 common uname sys_newuname 209 common sysinfo sys_sysinfo 210 common init_module sys_init_module diff --git a/fs/buffer.c b/fs/buffer.c index 6290c3afdba4..32718ee13b08 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3267,33 +3267,6 @@ out: } EXPORT_SYMBOL(try_to_free_buffers); -/* - * There are no bdflush tunables left. But distributions are - * still running obsolete flush daemons, so we terminate them here. - * - * Use of bdflush() is deprecated and will be removed in a future kernel. - * The `flush-X' kernel threads fully replace bdflush daemons and this call. - */ -SYSCALL_DEFINE2(bdflush, int, func, long, data) -{ - static int msg_count; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (msg_count < 5) { - msg_count++; - printk(KERN_INFO - "warning: process `%s' used the obsolete bdflush" - " system call\n", current->comm); - printk(KERN_INFO "Fix your initscripts?\n"); - } - - if (func == 1) - do_exit(0); - return 0; -} - /* * Buffer-head allocation */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 69c9a7010081..2b47584eb843 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1158,7 +1158,6 @@ asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf); asmlinkage long sys_vfork(void); asmlinkage long sys_recv(int, void __user *, size_t, unsigned); asmlinkage long sys_send(int, void __user *, size_t, unsigned); -asmlinkage long sys_bdflush(int func, long data); asmlinkage long sys_oldumount(char __user *name); asmlinkage long sys_uselib(const char __user *library); asmlinkage long sys_sysfs(int option, diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 2ddb4226cd23..463d1ba2232a 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -243,7 +243,6 @@ struct vfs_ns_cap_data { /* Allow examination and configuration of disk quotas */ /* Allow setting the domainname */ /* Allow setting the hostname */ -/* Allow calling bdflush() */ /* Allow mount() and umount(), setting up new smb connection */ /* Allow some autofs root ioctls */ /* Allow nfsservctl */ diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 30971b1dd4a9..cb6f98f5c97a 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -416,7 +416,6 @@ COND_SYSCALL(epoll_wait); COND_SYSCALL(recv); COND_SYSCALL_COMPAT(recv); COND_SYSCALL(send); -COND_SYSCALL(bdflush); COND_SYSCALL(uselib); /* optional: time32 */ diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index aef2a290e71a..6f3953f2a0d5 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -176,7 +176,7 @@ 131 nospu quotactl sys_quotactl 132 common getpgid sys_getpgid 133 common fchdir sys_fchdir -134 common bdflush sys_bdflush +134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs 136 32 personality sys_personality ppc64_personality 136 64 personality ppc64_personality diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 64d51ab5a8b4..8d619ec86dcc 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -122,7 +122,7 @@ 131 common quotactl sys_quotactl sys_quotactl 132 common getpgid sys_getpgid sys_getpgid 133 common fchdir sys_fchdir sys_fchdir -134 common bdflush sys_bdflush sys_bdflush +134 common bdflush - - 135 common sysfs sys_sysfs sys_sysfs 136 common personality sys_s390_personality sys_s390_personality 137 common afs_syscall - - -- cgit v1.2.3 From 730633f0b7f951726e87f912a6323641f674ae34 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 28 Jan 2021 19:19:45 +0100 Subject: mm: Protect operations adding pages to page cache with invalidate_lock Currently, serializing operations such as page fault, read, or readahead against hole punching is rather difficult. The basic race scheme is like: fallocate(FALLOC_FL_PUNCH_HOLE) read / fault / .. truncate_inode_pages_range() Now the problem is in this way read / page fault / readahead can instantiate pages in page cache with potentially stale data (if blocks get quickly reused). Avoiding this race is not simple - page locks do not work because we want to make sure there are *no* pages in given range. inode->i_rwsem does not work because page fault happens under mmap_sem which ranks below inode->i_rwsem. Also using it for reads makes the performance for mixed read-write workloads suffer. So create a new rw_semaphore in the address_space - invalidate_lock - that protects adding of pages to page cache for page faults / reads / readahead. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- Documentation/filesystems/locking.rst | 62 +++++++++++++++------- fs/inode.c | 2 + include/linux/fs.h | 33 ++++++++++++ mm/filemap.c | 97 ++++++++++++++++++++++++++++------- mm/readahead.c | 2 + mm/rmap.c | 37 ++++++------- mm/truncate.c | 3 +- 7 files changed, 180 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index cdf15492c699..38a3097b6f1c 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -271,19 +271,19 @@ prototypes:: locking rules: All except set_page_dirty and freepage may block -====================== ======================== ========= -ops PageLocked(page) i_rwsem -====================== ======================== ========= +====================== ======================== ========= =============== +ops PageLocked(page) i_rwsem invalidate_lock +====================== ======================== ========= =============== writepage: yes, unlocks (see below) -readpage: yes, unlocks +readpage: yes, unlocks shared writepages: set_page_dirty no -readahead: yes, unlocks -readpages: no +readahead: yes, unlocks shared +readpages: no shared write_begin: locks the page exclusive write_end: yes, unlocks exclusive bmap: -invalidatepage: yes +invalidatepage: yes exclusive releasepage: yes freepage: yes direct_IO: @@ -378,7 +378,10 @@ keep it that way and don't breed new callers. ->invalidatepage() is called when the filesystem must attempt to drop some or all of the buffers from the page when it is being truncated. It returns zero on success. If ->invalidatepage is zero, the kernel uses -block_invalidatepage() instead. +block_invalidatepage() instead. The filesystem must exclusively acquire +invalidate_lock before invalidating page cache in truncate / hole punch path +(and thus calling into ->invalidatepage) to block races between page cache +invalidation and page cache filling functions (fault, read, ...). ->releasepage() is called when the kernel is about to try to drop the buffers from the page in preparation for freeing it. It returns zero to @@ -573,6 +576,25 @@ in sys_read() and friends. the lease within the individual filesystem to record the result of the operation +->fallocate implementation must be really careful to maintain page cache +consistency when punching holes or performing other operations that invalidate +page cache contents. Usually the filesystem needs to call +truncate_inode_pages_range() to invalidate relevant range of the page cache. +However the filesystem usually also needs to update its internal (and on disk) +view of file offset -> disk block mapping. Until this update is finished, the +filesystem needs to block page faults and reads from reloading now-stale page +cache contents from the disk. Since VFS acquires mapping->invalidate_lock in +shared mode when loading pages from disk (filemap_fault(), filemap_read(), +readahead paths), the fallocate implementation must take the invalidate_lock to +prevent reloading. + +->copy_file_range and ->remap_file_range implementations need to serialize +against modifications of file data while the operation is running. For +blocking changes through write(2) and similar operations inode->i_rwsem can be +used. To block changes to file contents via a memory mapping during the +operation, the filesystem must take mapping->invalidate_lock to coordinate +with ->page_mkwrite. + dquot_operations ================ @@ -630,11 +652,11 @@ pfn_mkwrite: yes access: yes ============= ========= =========================== -->fault() is called when a previously not present pte is about -to be faulted in. The filesystem must find and return the page associated -with the passed in "pgoff" in the vm_fault structure. If it is possible that -the page may be truncated and/or invalidated, then the filesystem must lock -the page, then ensure it is not already truncated (the page lock will block +->fault() is called when a previously not present pte is about to be faulted +in. The filesystem must find and return the page associated with the passed in +"pgoff" in the vm_fault structure. If it is possible that the page may be +truncated and/or invalidated, then the filesystem must lock invalidate_lock, +then ensure the page is not already truncated (invalidate_lock will block subsequent truncate), and then return with VM_FAULT_LOCKED, and the page locked. The VM will unlock the page. @@ -647,12 +669,14 @@ page table entry. Pointer to entry associated with the page is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". -->page_mkwrite() is called when a previously read-only pte is -about to become writeable. The filesystem again must ensure that there are -no truncate/invalidate races, and then return with the page locked. If -the page has been truncated, the filesystem should not look up a new page -like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which -will cause the VM to retry the fault. +->page_mkwrite() is called when a previously read-only pte is about to become +writeable. The filesystem again must ensure that there are no +truncate/invalidate races or races with operations such as ->remap_file_range +or ->copy_file_range, and then return with the page locked. Usually +mapping->invalidate_lock is suitable for proper serialization. If the page has +been truncated, the filesystem should not look up a new page like the ->fault() +handler, but simply return with VM_FAULT_NOPAGE, which will cause the VM to +retry the fault. ->pfn_mkwrite() is the same as page_mkwrite but when the pte is VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is diff --git a/fs/inode.c b/fs/inode.c index c93500d84264..84c528cd1955 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -190,6 +190,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->private_data = NULL; mapping->writeback_index = 0; + __init_rwsem(&mapping->invalidate_lock, "mapping.invalidate_lock", + &sb->s_type->invalidate_lock_key); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..90a80de37ad4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -436,6 +436,10 @@ int pagecache_write_end(struct file *, struct address_space *mapping, * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. + * @invalidate_lock: Guards coherency between page cache contents and + * file offset->disk block mappings in the filesystem during invalidates. + * It is also used to block modification of page cache contents through + * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). @@ -453,6 +457,7 @@ int pagecache_write_end(struct file *, struct address_space *mapping, struct address_space { struct inode *host; struct xarray i_pages; + struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS @@ -814,6 +819,33 @@ static inline void inode_lock_shared_nested(struct inode *inode, unsigned subcla down_read_nested(&inode->i_rwsem, subclass); } +static inline void filemap_invalidate_lock(struct address_space *mapping) +{ + down_write(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_unlock(struct address_space *mapping) +{ + up_write(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_lock_shared(struct address_space *mapping) +{ + down_read(&mapping->invalidate_lock); +} + +static inline int filemap_invalidate_trylock_shared( + struct address_space *mapping) +{ + return down_read_trylock(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_unlock_shared( + struct address_space *mapping) +{ + up_read(&mapping->invalidate_lock); +} + void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); @@ -2487,6 +2519,7 @@ struct file_system_type { struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; + struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; diff --git a/mm/filemap.c b/mm/filemap.c index acf20eca2fa4..f7f9b87d2cd0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -77,7 +77,8 @@ * ->i_pages lock * * ->i_rwsem - * ->i_mmap_rwsem (truncate->unmap_mapping_range) + * ->invalidate_lock (acquired by fs in truncate path) + * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem @@ -85,7 +86,8 @@ * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock - * ->lock_page (access_process_vm) + * ->invalidate_lock (filemap_fault) + * ->lock_page (filemap_fault, access_process_vm) * * ->i_rwsem (generic_perform_write) * ->mmap_lock (fault_in_pages_readable->do_page_fault) @@ -2368,20 +2370,30 @@ static int filemap_update_page(struct kiocb *iocb, { int error; + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!filemap_invalidate_trylock_shared(mapping)) + return -EAGAIN; + } else { + filemap_invalidate_lock_shared(mapping); + } + if (!trylock_page(page)) { + error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) - return -EAGAIN; + goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { + filemap_invalidate_unlock_shared(mapping); put_and_wait_on_page_locked(page, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } error = __lock_page_async(page, iocb->ki_waitq); if (error) - return error; + goto unlock_mapping; } + error = AOP_TRUNCATED_PAGE; if (!page->mapping) - goto truncated; + goto unlock; error = 0; if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page)) @@ -2392,15 +2404,13 @@ static int filemap_update_page(struct kiocb *iocb, goto unlock; error = filemap_read_page(iocb->ki_filp, mapping, page); - if (error == AOP_TRUNCATED_PAGE) - put_page(page); - return error; -truncated: - unlock_page(page); - put_page(page); - return AOP_TRUNCATED_PAGE; + goto unlock_mapping; unlock: unlock_page(page); +unlock_mapping: + filemap_invalidate_unlock_shared(mapping); + if (error == AOP_TRUNCATED_PAGE) + put_page(page); return error; } @@ -2415,6 +2425,19 @@ static int filemap_create_page(struct file *file, if (!page) return -ENOMEM; + /* + * Protect against truncate / hole punch. Grabbing invalidate_lock here + * assures we cannot instantiate and bring uptodate new pagecache pages + * after evicting page cache during truncate and before actually + * freeing blocks. Note that we could release invalidate_lock after + * inserting the page into page cache as the locked page would then be + * enough to synchronize with hole punching. But there are code paths + * such as filemap_update_page() filling in partially uptodate pages or + * ->readpages() that need to hold invalidate_lock while mapping blocks + * for IO so let's hold the lock here as well to keep locking rules + * simple. + */ + filemap_invalidate_lock_shared(mapping); error = add_to_page_cache_lru(page, mapping, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) @@ -2426,9 +2449,11 @@ static int filemap_create_page(struct file *file, if (error) goto error; + filemap_invalidate_unlock_shared(mapping); pagevec_add(pvec, page); return 0; error: + filemap_invalidate_unlock_shared(mapping); put_page(page); return error; } @@ -2967,6 +2992,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) pgoff_t max_off; struct page *page; vm_fault_t ret = 0; + bool mapping_locked = false; max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) @@ -2976,25 +3002,39 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) * Do we have something in the page cache already? */ page = find_get_page(mapping, offset); - if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) { + if (likely(page)) { /* - * We found the page, so try async readahead before - * waiting for the lock. + * We found the page, so try async readahead before waiting for + * the lock. */ - fpin = do_async_mmap_readahead(vmf, page); - } else if (!page) { + if (!(vmf->flags & FAULT_FLAG_TRIED)) + fpin = do_async_mmap_readahead(vmf, page); + if (unlikely(!PageUptodate(page))) { + filemap_invalidate_lock_shared(mapping); + mapping_locked = true; + } + } else { /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: + /* + * See comment in filemap_create_page() why we need + * invalidate_lock + */ + if (!mapping_locked) { + filemap_invalidate_lock_shared(mapping); + mapping_locked = true; + } page = pagecache_get_page(mapping, offset, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (!page) { if (fpin) goto out_retry; + filemap_invalidate_unlock_shared(mapping); return VM_FAULT_OOM; } } @@ -3014,8 +3054,20 @@ retry_find: * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. */ - if (unlikely(!PageUptodate(page))) + if (unlikely(!PageUptodate(page))) { + /* + * The page was in cache and uptodate and now it is not. + * Strange but possible since we didn't hold the page lock all + * the time. Let's drop everything get the invalidate lock and + * try again. + */ + if (!mapping_locked) { + unlock_page(page); + put_page(page); + goto retry_find; + } goto page_not_uptodate; + } /* * We've made it this far and we had to drop our mmap_lock, now is the @@ -3026,6 +3078,8 @@ retry_find: unlock_page(page); goto out_retry; } + if (mapping_locked) + filemap_invalidate_unlock_shared(mapping); /* * Found the page and have a reference on it. @@ -3056,6 +3110,7 @@ page_not_uptodate: if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; + filemap_invalidate_unlock_shared(mapping); return VM_FAULT_SIGBUS; @@ -3067,6 +3122,8 @@ out_retry: */ if (page) put_page(page); + if (mapping_locked) + filemap_invalidate_unlock_shared(mapping); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; @@ -3437,6 +3494,8 @@ out: * * If the page does not get brought uptodate, return -EIO. * + * The function expects mapping->invalidate_lock to be already held. + * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page(struct address_space *mapping, @@ -3460,6 +3519,8 @@ EXPORT_SYMBOL(read_cache_page); * * If the page does not get brought uptodate, return -EIO. * + * The function expects mapping->invalidate_lock to be already held. + * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, diff --git a/mm/readahead.c b/mm/readahead.c index d589f147f4c2..41b75d76d36e 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -192,6 +192,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, */ unsigned int nofs = memalloc_nofs_save(); + filemap_invalidate_lock_shared(mapping); /* * Preallocate as many pages as we will need. */ @@ -236,6 +237,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, * will then handle the error. */ read_pages(ractl, &page_pool, false); + filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); diff --git a/mm/rmap.c b/mm/rmap.c index a8b01929ab2e..86471aacc54a 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -22,24 +22,25 @@ * * inode->i_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock - * page->flags PG_locked (lock_page) * (see hugetlbfs below) - * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share) - * mapping->i_mmap_rwsem - * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) - * anon_vma->rwsem - * mm->page_table_lock or pte_lock - * swap_lock (in swap_duplicate, swap_info_get) - * mmlist_lock (in mmput, drain_mmlist and others) - * mapping->private_lock (in __set_page_dirty_buffers) - * lock_page_memcg move_lock (in __set_page_dirty_buffers) - * i_pages lock (widely used) - * lruvec->lru_lock (in lock_page_lruvec_irq) - * inode->i_lock (in set_page_dirty's __mark_inode_dirty) - * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) - * sb_lock (within inode_lock in fs/fs-writeback.c) - * i_pages lock (widely used, in set_page_dirty, - * in arch-dependent flush_dcache_mmap_lock, - * within bdi.wb->list_lock in __sync_single_inode) + * mapping->invalidate_lock (in filemap_fault) + * page->flags PG_locked (lock_page) * (see hugetlbfs below) + * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share) + * mapping->i_mmap_rwsem + * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) + * anon_vma->rwsem + * mm->page_table_lock or pte_lock + * swap_lock (in swap_duplicate, swap_info_get) + * mmlist_lock (in mmput, drain_mmlist and others) + * mapping->private_lock (in __set_page_dirty_buffers) + * lock_page_memcg move_lock (in __set_page_dirty_buffers) + * i_pages lock (widely used) + * lruvec->lru_lock (in lock_page_lruvec_irq) + * inode->i_lock (in set_page_dirty's __mark_inode_dirty) + * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) + * sb_lock (within inode_lock in fs/fs-writeback.c) + * i_pages lock (widely used, in set_page_dirty, + * in arch-dependent flush_dcache_mmap_lock, + * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock diff --git a/mm/truncate.c b/mm/truncate.c index 0f9becee9789..44ad5e515140 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -412,7 +412,8 @@ EXPORT_SYMBOL(truncate_inode_pages_range); * @mapping: mapping to truncate * @lstart: offset from which to truncate * - * Called under (and serialised by) inode->i_rwsem. + * Called under (and serialised by) inode->i_rwsem and + * mapping->invalidate_lock. * * Note: When this function returns, there can be a page in the process of * deletion (inside __delete_from_page_cache()) in the specified range. Thus -- cgit v1.2.3 From a1867f85e06edacd82956d3422caa2b9074f4321 Mon Sep 17 00:00:00 2001 From: Min Li Date: Fri, 18 Jun 2021 12:37:12 -0400 Subject: mfd: Add Renesas Synchronization Management Unit (SMU) support Add support for ClockMatrix(TM) and 82P33xxx families of timing and synchronization devices. The access interface can be either SPI or I2C. Currently, it will create 2 types of MFD devices, which are to be used by the corresponding rsmu character device driver and the PTP hardware clock driver, respectively. Signed-off-by: Min Li Signed-off-by: Lee Jones --- drivers/mfd/Kconfig | 28 ++ drivers/mfd/Makefile | 5 + drivers/mfd/rsmu.h | 16 + drivers/mfd/rsmu_core.c | 88 +++++ drivers/mfd/rsmu_i2c.c | 203 +++++++++++ drivers/mfd/rsmu_spi.c | 273 +++++++++++++++ include/linux/mfd/idt82p33_reg.h | 112 ++++++ include/linux/mfd/idt8a340_reg.h | 729 +++++++++++++++++++++++++++++++++++++++ include/linux/mfd/rsmu.h | 36 ++ 9 files changed, 1490 insertions(+) create mode 100644 drivers/mfd/rsmu.h create mode 100644 drivers/mfd/rsmu_core.c create mode 100644 drivers/mfd/rsmu_i2c.c create mode 100644 drivers/mfd/rsmu_spi.c create mode 100644 include/linux/mfd/idt82p33_reg.h create mode 100644 include/linux/mfd/idt8a340_reg.h create mode 100644 include/linux/mfd/rsmu.h (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 6a3fd2d75f96..578db280dedf 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -2183,5 +2183,33 @@ config MFD_INTEL_M10_BMC additional drivers must be enabled in order to use the functionality of the device. +config MFD_RSMU_I2C + tristate "Renesas Synchronization Management Unit with I2C" + depends on I2C && OF + select MFD_CORE + select REGMAP_I2C + help + Support for the Renesas Synchronization Management Unit, such as + Clockmatrix and 82P33XXX series. This option supports I2C as + the control interface. + + This driver provides common support for accessing the device. + Additional drivers must be enabled in order to use the functionality + of the device. + +config MFD_RSMU_SPI + tristate "Renesas Synchronization Management Unit with SPI" + depends on SPI && OF + select MFD_CORE + select REGMAP_SPI + help + Support for the Renesas Synchronization Management Unit, such as + Clockmatrix and 82P33XXX series. This option supports SPI as + the control interface. + + This driver provides common support for accessing the device. + Additional drivers must be enabled in order to use the functionality + of the device. + endmenu endif diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 8116c19d5fd4..54e37704f74b 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -272,3 +272,8 @@ obj-$(CONFIG_MFD_INTEL_M10_BMC) += intel-m10-bmc.o obj-$(CONFIG_MFD_ATC260X) += atc260x-core.o obj-$(CONFIG_MFD_ATC260X_I2C) += atc260x-i2c.o + +rsmu-i2c-objs := rsmu_core.o rsmu_i2c.o +rsmu-spi-objs := rsmu_core.o rsmu_spi.o +obj-$(CONFIG_MFD_RSMU_I2C) += rsmu-i2c.o +obj-$(CONFIG_MFD_RSMU_SPI) += rsmu-spi.o diff --git a/drivers/mfd/rsmu.h b/drivers/mfd/rsmu.h new file mode 100644 index 000000000000..bb88597d189f --- /dev/null +++ b/drivers/mfd/rsmu.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Renesas Synchronization Management Unit (SMU) devices. + * + * Copyright (C) 2021 Integrated Device Technology, Inc., a Renesas Company. + */ + +#ifndef __RSMU_MFD_H +#define __RSMU_MFD_H + +#include + +int rsmu_core_init(struct rsmu_ddata *rsmu); +void rsmu_core_exit(struct rsmu_ddata *rsmu); + +#endif /* __RSMU_MFD_H */ diff --git a/drivers/mfd/rsmu_core.c b/drivers/mfd/rsmu_core.c new file mode 100644 index 000000000000..29437fd0bd5b --- /dev/null +++ b/drivers/mfd/rsmu_core.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Core driver for Renesas Synchronization Management Unit (SMU) devices. + * + * Copyright (C) 2021 Integrated Device Technology, Inc., a Renesas Company. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rsmu.h" + +enum { + RSMU_PHC = 0, + RSMU_CDEV = 1, + RSMU_N_DEVS = 2, +}; + +static struct mfd_cell rsmu_cm_devs[] = { + [RSMU_PHC] = { + .name = "8a3400x-phc", + }, + [RSMU_CDEV] = { + .name = "8a3400x-cdev", + }, +}; + +static struct mfd_cell rsmu_sabre_devs[] = { + [RSMU_PHC] = { + .name = "82p33x1x-phc", + }, + [RSMU_CDEV] = { + .name = "82p33x1x-cdev", + }, +}; + +static struct mfd_cell rsmu_sl_devs[] = { + [RSMU_PHC] = { + .name = "8v19n85x-phc", + }, + [RSMU_CDEV] = { + .name = "8v19n85x-cdev", + }, +}; + +int rsmu_core_init(struct rsmu_ddata *rsmu) +{ + struct mfd_cell *cells; + int ret; + + switch (rsmu->type) { + case RSMU_CM: + cells = rsmu_cm_devs; + break; + case RSMU_SABRE: + cells = rsmu_sabre_devs; + break; + case RSMU_SL: + cells = rsmu_sl_devs; + break; + default: + dev_err(rsmu->dev, "Unsupported RSMU device type: %d\n", rsmu->type); + return -ENODEV; + } + + mutex_init(&rsmu->lock); + + ret = devm_mfd_add_devices(rsmu->dev, PLATFORM_DEVID_AUTO, cells, + RSMU_N_DEVS, NULL, 0, NULL); + if (ret < 0) + dev_err(rsmu->dev, "Failed to register sub-devices: %d\n", ret); + + return ret; +} + +void rsmu_core_exit(struct rsmu_ddata *rsmu) +{ + mutex_destroy(&rsmu->lock); +} + +MODULE_DESCRIPTION("Renesas SMU core driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mfd/rsmu_i2c.c b/drivers/mfd/rsmu_i2c.c new file mode 100644 index 000000000000..dc001c9791c1 --- /dev/null +++ b/drivers/mfd/rsmu_i2c.c @@ -0,0 +1,203 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * I2C driver for Renesas Synchronization Management Unit (SMU) devices. + * + * Copyright (C) 2021 Integrated Device Technology, Inc., a Renesas Company. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rsmu.h" + +/* + * 16-bit register address: the lower 8 bits of the register address come + * from the offset addr byte and the upper 8 bits come from the page register. + */ +#define RSMU_CM_PAGE_ADDR 0xFD +#define RSMU_CM_PAGE_WINDOW 256 + +/* + * 15-bit register address: the lower 7 bits of the register address come + * from the offset addr byte and the upper 8 bits come from the page register. + */ +#define RSMU_SABRE_PAGE_ADDR 0x7F +#define RSMU_SABRE_PAGE_WINDOW 128 + +static const struct regmap_range_cfg rsmu_cm_range_cfg[] = { + { + .range_min = 0, + .range_max = 0xD000, + .selector_reg = RSMU_CM_PAGE_ADDR, + .selector_mask = 0xFF, + .selector_shift = 0, + .window_start = 0, + .window_len = RSMU_CM_PAGE_WINDOW, + } +}; + +static const struct regmap_range_cfg rsmu_sabre_range_cfg[] = { + { + .range_min = 0, + .range_max = 0x400, + .selector_reg = RSMU_SABRE_PAGE_ADDR, + .selector_mask = 0xFF, + .selector_shift = 0, + .window_start = 0, + .window_len = RSMU_SABRE_PAGE_WINDOW, + } +}; + +static bool rsmu_cm_volatile_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case RSMU_CM_PAGE_ADDR: + return false; + default: + return true; + } +} + +static bool rsmu_sabre_volatile_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case RSMU_SABRE_PAGE_ADDR: + return false; + default: + return true; + } +} + +static const struct regmap_config rsmu_cm_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 0xD000, + .ranges = rsmu_cm_range_cfg, + .num_ranges = ARRAY_SIZE(rsmu_cm_range_cfg), + .volatile_reg = rsmu_cm_volatile_reg, + .cache_type = REGCACHE_RBTREE, + .can_multi_write = true, +}; + +static const struct regmap_config rsmu_sabre_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x400, + .ranges = rsmu_sabre_range_cfg, + .num_ranges = ARRAY_SIZE(rsmu_sabre_range_cfg), + .volatile_reg = rsmu_sabre_volatile_reg, + .cache_type = REGCACHE_RBTREE, + .can_multi_write = true, +}; + +static const struct regmap_config rsmu_sl_regmap_config = { + .reg_bits = 16, + .val_bits = 8, + .reg_format_endian = REGMAP_ENDIAN_BIG, + .max_register = 0x339, + .cache_type = REGCACHE_NONE, + .can_multi_write = true, +}; + +static int rsmu_i2c_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + const struct regmap_config *cfg; + struct rsmu_ddata *rsmu; + int ret; + + rsmu = devm_kzalloc(&client->dev, sizeof(*rsmu), GFP_KERNEL); + if (!rsmu) + return -ENOMEM; + + i2c_set_clientdata(client, rsmu); + + rsmu->dev = &client->dev; + rsmu->type = (enum rsmu_type)id->driver_data; + + switch (rsmu->type) { + case RSMU_CM: + cfg = &rsmu_cm_regmap_config; + break; + case RSMU_SABRE: + cfg = &rsmu_sabre_regmap_config; + break; + case RSMU_SL: + cfg = &rsmu_sl_regmap_config; + break; + default: + dev_err(rsmu->dev, "Unsupported RSMU device type: %d\n", rsmu->type); + return -ENODEV; + } + rsmu->regmap = devm_regmap_init_i2c(client, cfg); + if (IS_ERR(rsmu->regmap)) { + ret = PTR_ERR(rsmu->regmap); + dev_err(rsmu->dev, "Failed to allocate register map: %d\n", ret); + return ret; + } + + return rsmu_core_init(rsmu); +} + +static int rsmu_i2c_remove(struct i2c_client *client) +{ + struct rsmu_ddata *rsmu = i2c_get_clientdata(client); + + rsmu_core_exit(rsmu); + + return 0; +} + +static const struct i2c_device_id rsmu_i2c_id[] = { + { "8a34000", RSMU_CM }, + { "8a34001", RSMU_CM }, + { "82p33810", RSMU_SABRE }, + { "82p33811", RSMU_SABRE }, + { "8v19n850", RSMU_SL }, + { "8v19n851", RSMU_SL }, + {} +}; +MODULE_DEVICE_TABLE(i2c, rsmu_i2c_id); + +static const struct of_device_id rsmu_i2c_of_match[] = { + { .compatible = "idt,8a34000", .data = (void *)RSMU_CM }, + { .compatible = "idt,8a34001", .data = (void *)RSMU_CM }, + { .compatible = "idt,82p33810", .data = (void *)RSMU_SABRE }, + { .compatible = "idt,82p33811", .data = (void *)RSMU_SABRE }, + { .compatible = "idt,8v19n850", .data = (void *)RSMU_SL }, + { .compatible = "idt,8v19n851", .data = (void *)RSMU_SL }, + {} +}; +MODULE_DEVICE_TABLE(of, rsmu_i2c_of_match); + +static struct i2c_driver rsmu_i2c_driver = { + .driver = { + .name = "rsmu-i2c", + .of_match_table = of_match_ptr(rsmu_i2c_of_match), + }, + .probe = rsmu_i2c_probe, + .remove = rsmu_i2c_remove, + .id_table = rsmu_i2c_id, +}; + +static int __init rsmu_i2c_init(void) +{ + return i2c_add_driver(&rsmu_i2c_driver); +} +subsys_initcall(rsmu_i2c_init); + +static void __exit rsmu_i2c_exit(void) +{ + i2c_del_driver(&rsmu_i2c_driver); +} +module_exit(rsmu_i2c_exit); + +MODULE_DESCRIPTION("Renesas SMU I2C driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mfd/rsmu_spi.c b/drivers/mfd/rsmu_spi.c new file mode 100644 index 000000000000..fec2b4ec477c --- /dev/null +++ b/drivers/mfd/rsmu_spi.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * SPI driver for Renesas Synchronization Management Unit (SMU) devices. + * + * Copyright (C) 2021 Integrated Device Technology, Inc., a Renesas Company. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rsmu.h" + +#define RSMU_CM_PAGE_ADDR 0x7C +#define RSMU_SABRE_PAGE_ADDR 0x7F +#define RSMU_HIGHER_ADDR_MASK 0xFF80 +#define RSMU_HIGHER_ADDR_SHIFT 7 +#define RSMU_LOWER_ADDR_MASK 0x7F + +static int rsmu_read_device(struct rsmu_ddata *rsmu, u8 reg, u8 *buf, u16 bytes) +{ + struct spi_device *client = to_spi_device(rsmu->dev); + struct spi_transfer xfer = {0}; + struct spi_message msg; + u8 cmd[256] = {0}; + u8 rsp[256] = {0}; + int ret; + + cmd[0] = reg | 0x80; + xfer.rx_buf = rsp; + xfer.len = bytes + 1; + xfer.tx_buf = cmd; + xfer.bits_per_word = client->bits_per_word; + xfer.speed_hz = client->max_speed_hz; + + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + /* + * 4-wire SPI is a shift register, so for every byte you send, + * you get one back at the same time. Example read from 0xC024, + * which has value of 0x2D + * + * MOSI: + * 7C 00 C0 #Set page register + * A4 00 #MSB is set, so this is read command + * MISO: + * XX 2D #XX is a dummy byte from sending A4 and we + * need to throw it away + */ + ret = spi_sync(client, &msg); + if (ret >= 0) + memcpy(buf, &rsp[1], xfer.len-1); + + return ret; +} + +static int rsmu_write_device(struct rsmu_ddata *rsmu, u8 reg, u8 *buf, u16 bytes) +{ + struct spi_device *client = to_spi_device(rsmu->dev); + struct spi_transfer xfer = {0}; + struct spi_message msg; + u8 cmd[256] = {0}; + + cmd[0] = reg; + memcpy(&cmd[1], buf, bytes); + + xfer.len = bytes + 1; + xfer.tx_buf = cmd; + xfer.bits_per_word = client->bits_per_word; + xfer.speed_hz = client->max_speed_hz; + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + return spi_sync(client, &msg); +} + +/* + * 1-byte (1B) offset addressing: + * 16-bit register address: the lower 7 bits of the register address come + * from the offset addr byte and the upper 9 bits come from the page register. + */ +static int rsmu_write_page_register(struct rsmu_ddata *rsmu, u16 reg) +{ + u8 page_reg; + u8 buf[2]; + u16 bytes; + u16 page; + int err; + + switch (rsmu->type) { + case RSMU_CM: + page_reg = RSMU_CM_PAGE_ADDR; + page = reg & RSMU_HIGHER_ADDR_MASK; + buf[0] = (u8)(page & 0xff); + buf[1] = (u8)((page >> 8) & 0xff); + bytes = 2; + break; + case RSMU_SABRE: + page_reg = RSMU_SABRE_PAGE_ADDR; + page = reg >> RSMU_HIGHER_ADDR_SHIFT; + buf[0] = (u8)(page & 0xff); + bytes = 1; + break; + default: + dev_err(rsmu->dev, "Unsupported RSMU device type: %d\n", rsmu->type); + return -ENODEV; + } + + /* Simply return if we are on the same page */ + if (rsmu->page == page) + return 0; + + err = rsmu_write_device(rsmu, page_reg, buf, bytes); + if (err) + dev_err(rsmu->dev, "Failed to set page offset 0x%x\n", page); + else + /* Remember the last page */ + rsmu->page = page; + + return err; +} + +static int rsmu_reg_read(void *context, unsigned int reg, unsigned int *val) +{ + struct rsmu_ddata *rsmu = spi_get_drvdata((struct spi_device *)context); + u8 addr = (u8)(reg & RSMU_LOWER_ADDR_MASK); + int err; + + err = rsmu_write_page_register(rsmu, reg); + if (err) + return err; + + err = rsmu_read_device(rsmu, addr, (u8 *)val, 1); + if (err) + dev_err(rsmu->dev, "Failed to read offset address 0x%x\n", addr); + + return err; +} + +static int rsmu_reg_write(void *context, unsigned int reg, unsigned int val) +{ + struct rsmu_ddata *rsmu = spi_get_drvdata((struct spi_device *)context); + u8 addr = (u8)(reg & RSMU_LOWER_ADDR_MASK); + u8 data = (u8)val; + int err; + + err = rsmu_write_page_register(rsmu, reg); + if (err) + return err; + + err = rsmu_write_device(rsmu, addr, &data, 1); + if (err) + dev_err(rsmu->dev, + "Failed to write offset address 0x%x\n", addr); + + return err; +} + +static const struct regmap_config rsmu_cm_regmap_config = { + .reg_bits = 16, + .val_bits = 8, + .max_register = 0xD000, + .reg_read = rsmu_reg_read, + .reg_write = rsmu_reg_write, + .cache_type = REGCACHE_NONE, +}; + +static const struct regmap_config rsmu_sabre_regmap_config = { + .reg_bits = 16, + .val_bits = 8, + .max_register = 0x400, + .reg_read = rsmu_reg_read, + .reg_write = rsmu_reg_write, + .cache_type = REGCACHE_NONE, +}; + +static int rsmu_spi_probe(struct spi_device *client) +{ + const struct spi_device_id *id = spi_get_device_id(client); + const struct regmap_config *cfg; + struct rsmu_ddata *rsmu; + int ret; + + rsmu = devm_kzalloc(&client->dev, sizeof(*rsmu), GFP_KERNEL); + if (!rsmu) + return -ENOMEM; + + spi_set_drvdata(client, rsmu); + + rsmu->dev = &client->dev; + rsmu->type = (enum rsmu_type)id->driver_data; + + /* Initialize regmap */ + switch (rsmu->type) { + case RSMU_CM: + cfg = &rsmu_cm_regmap_config; + break; + case RSMU_SABRE: + cfg = &rsmu_sabre_regmap_config; + break; + default: + dev_err(rsmu->dev, "Unsupported RSMU device type: %d\n", rsmu->type); + return -ENODEV; + } + + rsmu->regmap = devm_regmap_init(&client->dev, NULL, client, cfg); + if (IS_ERR(rsmu->regmap)) { + ret = PTR_ERR(rsmu->regmap); + dev_err(rsmu->dev, "Failed to allocate register map: %d\n", ret); + return ret; + } + + return rsmu_core_init(rsmu); +} + +static int rsmu_spi_remove(struct spi_device *client) +{ + struct rsmu_ddata *rsmu = spi_get_drvdata(client); + + rsmu_core_exit(rsmu); + + return 0; +} + +static const struct spi_device_id rsmu_spi_id[] = { + { "8a34000", RSMU_CM }, + { "8a34001", RSMU_CM }, + { "82p33810", RSMU_SABRE }, + { "82p33811", RSMU_SABRE }, + {} +}; +MODULE_DEVICE_TABLE(spi, rsmu_spi_id); + +static const struct of_device_id rsmu_spi_of_match[] = { + { .compatible = "idt,8a34000", .data = (void *)RSMU_CM }, + { .compatible = "idt,8a34001", .data = (void *)RSMU_CM }, + { .compatible = "idt,82p33810", .data = (void *)RSMU_SABRE }, + { .compatible = "idt,82p33811", .data = (void *)RSMU_SABRE }, + {} +}; +MODULE_DEVICE_TABLE(of, rsmu_spi_of_match); + +static struct spi_driver rsmu_spi_driver = { + .driver = { + .name = "rsmu-spi", + .of_match_table = of_match_ptr(rsmu_spi_of_match), + }, + .probe = rsmu_spi_probe, + .remove = rsmu_spi_remove, + .id_table = rsmu_spi_id, +}; + +static int __init rsmu_spi_init(void) +{ + return spi_register_driver(&rsmu_spi_driver); +} +subsys_initcall(rsmu_spi_init); + +static void __exit rsmu_spi_exit(void) +{ + spi_unregister_driver(&rsmu_spi_driver); +} +module_exit(rsmu_spi_exit); + +MODULE_DESCRIPTION("Renesas SMU SPI driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/idt82p33_reg.h b/include/linux/mfd/idt82p33_reg.h new file mode 100644 index 000000000000..129a6c078221 --- /dev/null +++ b/include/linux/mfd/idt82p33_reg.h @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Register Map - Based on AN888_SMUforIEEE_SynchEther_82P33xxx_RevH.pdf + * + * Copyright (C) 2021 Integrated Device Technology, Inc., a Renesas Company. + */ +#ifndef HAVE_IDT82P33_REG +#define HAVE_IDT82P33_REG + +/* Register address */ +#define DPLL1_TOD_CNFG 0x134 +#define DPLL2_TOD_CNFG 0x1B4 + +#define DPLL1_TOD_STS 0x10B +#define DPLL2_TOD_STS 0x18B + +#define DPLL1_TOD_TRIGGER 0x115 +#define DPLL2_TOD_TRIGGER 0x195 + +#define DPLL1_OPERATING_MODE_CNFG 0x120 +#define DPLL2_OPERATING_MODE_CNFG 0x1A0 + +#define DPLL1_HOLDOVER_FREQ_CNFG 0x12C +#define DPLL2_HOLDOVER_FREQ_CNFG 0x1AC + +#define DPLL1_PHASE_OFFSET_CNFG 0x143 +#define DPLL2_PHASE_OFFSET_CNFG 0x1C3 + +#define DPLL1_SYNC_EDGE_CNFG 0x140 +#define DPLL2_SYNC_EDGE_CNFG 0x1C0 + +#define DPLL1_INPUT_MODE_CNFG 0x116 +#define DPLL2_INPUT_MODE_CNFG 0x196 + +#define DPLL1_OPERATING_STS 0x102 +#define DPLL2_OPERATING_STS 0x182 + +#define DPLL1_CURRENT_FREQ_STS 0x103 +#define DPLL2_CURRENT_FREQ_STS 0x183 + +#define REG_SOFT_RESET 0X381 + +#define OUT_MUX_CNFG(outn) REG_ADDR(0x6, (0xC * (outn))) + +/* Register bit definitions */ +#define SYNC_TOD BIT(1) +#define PH_OFFSET_EN BIT(7) +#define SQUELCH_ENABLE BIT(5) + +/* Bit definitions for the DPLL_MODE register */ +#define PLL_MODE_SHIFT (0) +#define PLL_MODE_MASK (0x1F) +#define COMBO_MODE_EN BIT(5) +#define COMBO_MODE_SHIFT (6) +#define COMBO_MODE_MASK (0x3) + +/* Bit definitions for DPLL_OPERATING_STS register */ +#define OPERATING_STS_MASK (0x7) +#define OPERATING_STS_SHIFT (0x0) + +/* Bit definitions for DPLL_TOD_TRIGGER register */ +#define READ_TRIGGER_MASK (0xF) +#define READ_TRIGGER_SHIFT (0x0) +#define WRITE_TRIGGER_MASK (0xF0) +#define WRITE_TRIGGER_SHIFT (0x4) + +/* Bit definitions for REG_SOFT_RESET register */ +#define SOFT_RESET_EN BIT(7) + +enum pll_mode { + PLL_MODE_MIN = 0, + PLL_MODE_AUTOMATIC = PLL_MODE_MIN, + PLL_MODE_FORCE_FREERUN = 1, + PLL_MODE_FORCE_HOLDOVER = 2, + PLL_MODE_FORCE_LOCKED = 4, + PLL_MODE_FORCE_PRE_LOCKED2 = 5, + PLL_MODE_FORCE_PRE_LOCKED = 6, + PLL_MODE_FORCE_LOST_PHASE = 7, + PLL_MODE_DCO = 10, + PLL_MODE_WPH = 18, + PLL_MODE_MAX = PLL_MODE_WPH, +}; + +enum hw_tod_trig_sel { + HW_TOD_TRIG_SEL_MIN = 0, + HW_TOD_TRIG_SEL_NO_WRITE = HW_TOD_TRIG_SEL_MIN, + HW_TOD_TRIG_SEL_NO_READ = HW_TOD_TRIG_SEL_MIN, + HW_TOD_TRIG_SEL_SYNC_SEL = 1, + HW_TOD_TRIG_SEL_IN12 = 2, + HW_TOD_TRIG_SEL_IN13 = 3, + HW_TOD_TRIG_SEL_IN14 = 4, + HW_TOD_TRIG_SEL_TOD_PPS = 5, + HW_TOD_TRIG_SEL_TIMER_INTERVAL = 6, + HW_TOD_TRIG_SEL_MSB_PHASE_OFFSET_CNFG = 7, + HW_TOD_TRIG_SEL_MSB_HOLDOVER_FREQ_CNFG = 8, + HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG = 9, + HW_TOD_RD_TRIG_SEL_LSB_TOD_STS = HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, + WR_TRIG_SEL_MAX = HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, +}; + +/** @brief Enumerated type listing DPLL operational modes */ +enum dpll_state { + DPLL_STATE_FREERUN = 1, + DPLL_STATE_HOLDOVER = 2, + DPLL_STATE_LOCKED = 4, + DPLL_STATE_PRELOCKED2 = 5, + DPLL_STATE_PRELOCKED = 6, + DPLL_STATE_LOSTPHASE = 7, + DPLL_STATE_MAX +}; + +#endif diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h new file mode 100644 index 000000000000..92d763230bdf --- /dev/null +++ b/include/linux/mfd/idt8a340_reg.h @@ -0,0 +1,729 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Based on 5.2.0, Family Programming Guide (Sept 30, 2020) + * + * Copyright (C) 2021 Integrated Device Technology, Inc., a Renesas Company. + */ +#ifndef HAVE_IDT8A340_REG +#define HAVE_IDT8A340_REG + +#define PAGE_ADDR_BASE 0x0000 +#define PAGE_ADDR 0x00fc + +#define HW_REVISION 0x8180 +#define REV_ID 0x007a + +#define HW_DPLL_0 (0x8a00) +#define HW_DPLL_1 (0x8b00) +#define HW_DPLL_2 (0x8c00) +#define HW_DPLL_3 (0x8d00) +#define HW_DPLL_4 (0x8e00) +#define HW_DPLL_5 (0x8f00) +#define HW_DPLL_6 (0x9000) +#define HW_DPLL_7 (0x9100) + +#define HW_DPLL_TOD_SW_TRIG_ADDR__0 (0x080) +#define HW_DPLL_TOD_CTRL_1 (0x089) +#define HW_DPLL_TOD_CTRL_2 (0x08A) +#define HW_DPLL_TOD_OVR__0 (0x098) +#define HW_DPLL_TOD_OUT_0__0 (0x0B0) + +#define HW_Q0_Q1_CH_SYNC_CTRL_0 (0xa740) +#define HW_Q0_Q1_CH_SYNC_CTRL_1 (0xa741) +#define HW_Q2_Q3_CH_SYNC_CTRL_0 (0xa742) +#define HW_Q2_Q3_CH_SYNC_CTRL_1 (0xa743) +#define HW_Q4_Q5_CH_SYNC_CTRL_0 (0xa744) +#define HW_Q4_Q5_CH_SYNC_CTRL_1 (0xa745) +#define HW_Q6_Q7_CH_SYNC_CTRL_0 (0xa746) +#define HW_Q6_Q7_CH_SYNC_CTRL_1 (0xa747) +#define HW_Q8_CH_SYNC_CTRL_0 (0xa748) +#define HW_Q8_CH_SYNC_CTRL_1 (0xa749) +#define HW_Q9_CH_SYNC_CTRL_0 (0xa74a) +#define HW_Q9_CH_SYNC_CTRL_1 (0xa74b) +#define HW_Q10_CH_SYNC_CTRL_0 (0xa74c) +#define HW_Q10_CH_SYNC_CTRL_1 (0xa74d) +#define HW_Q11_CH_SYNC_CTRL_0 (0xa74e) +#define HW_Q11_CH_SYNC_CTRL_1 (0xa74f) + +#define SYNC_SOURCE_DPLL0_TOD_PPS 0x14 +#define SYNC_SOURCE_DPLL1_TOD_PPS 0x15 +#define SYNC_SOURCE_DPLL2_TOD_PPS 0x16 +#define SYNC_SOURCE_DPLL3_TOD_PPS 0x17 + +#define SYNCTRL1_MASTER_SYNC_RST BIT(7) +#define SYNCTRL1_MASTER_SYNC_TRIG BIT(5) +#define SYNCTRL1_TOD_SYNC_TRIG BIT(4) +#define SYNCTRL1_FBDIV_FRAME_SYNC_TRIG BIT(3) +#define SYNCTRL1_FBDIV_SYNC_TRIG BIT(2) +#define SYNCTRL1_Q1_DIV_SYNC_TRIG BIT(1) +#define SYNCTRL1_Q0_DIV_SYNC_TRIG BIT(0) + +#define HW_Q8_CTRL_SPARE (0xa7d4) +#define HW_Q11_CTRL_SPARE (0xa7ec) + +/** + * Select FOD5 as sync_trigger for Q8 divider. + * Transition from logic zero to one + * sets trigger to sync Q8 divider. + * + * Unused when FOD4 is driving Q8 divider (normal operation). + */ +#define Q9_TO_Q8_SYNC_TRIG BIT(1) + +/** + * Enable FOD5 as driver for clock and sync for Q8 divider. + * Enable fanout buffer for FOD5. + * + * Unused when FOD4 is driving Q8 divider (normal operation). + */ +#define Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) + +/** + * Select FOD6 as sync_trigger for Q11 divider. + * Transition from logic zero to one + * sets trigger to sync Q11 divider. + * + * Unused when FOD7 is driving Q11 divider (normal operation). + */ +#define Q10_TO_Q11_SYNC_TRIG BIT(1) + +/** + * Enable FOD6 as driver for clock and sync for Q11 divider. + * Enable fanout buffer for FOD6. + * + * Unused when FOD7 is driving Q11 divider (normal operation). + */ +#define Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) + +#define RESET_CTRL 0xc000 +#define SM_RESET 0x0012 +#define SM_RESET_V520 0x0013 +#define SM_RESET_CMD 0x5A + +#define GENERAL_STATUS 0xc014 +#define BOOT_STATUS 0x0000 +#define HW_REV_ID 0x000A +#define BOND_ID 0x000B +#define HW_CSR_ID 0x000C +#define HW_IRQ_ID 0x000E +#define MAJ_REL 0x0010 +#define MIN_REL 0x0011 +#define HOTFIX_REL 0x0012 +#define PIPELINE_ID 0x0014 +#define BUILD_ID 0x0018 +#define JTAG_DEVICE_ID 0x001c +#define PRODUCT_ID 0x001e +#define OTP_SCSR_CONFIG_SELECT 0x0022 + +#define STATUS 0xc03c +#define DPLL0_STATUS 0x0018 +#define DPLL1_STATUS 0x0019 +#define DPLL2_STATUS 0x001a +#define DPLL3_STATUS 0x001b +#define DPLL4_STATUS 0x001c +#define DPLL5_STATUS 0x001d +#define DPLL6_STATUS 0x001e +#define DPLL7_STATUS 0x001f +#define DPLL_SYS_STATUS 0x0020 +#define DPLL_SYS_APLL_STATUS 0x0021 +#define DPLL0_FILTER_STATUS 0x0044 +#define DPLL1_FILTER_STATUS 0x004c +#define DPLL2_FILTER_STATUS 0x0054 +#define DPLL3_FILTER_STATUS 0x005c +#define DPLL4_FILTER_STATUS 0x0064 +#define DPLL5_FILTER_STATUS 0x006c +#define DPLL6_FILTER_STATUS 0x0074 +#define DPLL7_FILTER_STATUS 0x007c +#define DPLLSYS_FILTER_STATUS 0x0084 +#define USER_GPIO0_TO_7_STATUS 0x008a +#define USER_GPIO8_TO_15_STATUS 0x008b + +#define GPIO_USER_CONTROL 0xc160 +#define GPIO0_TO_7_OUT 0x0000 +#define GPIO8_TO_15_OUT 0x0001 +#define GPIO0_TO_7_OUT_V520 0x0002 +#define GPIO8_TO_15_OUT_V520 0x0003 + +#define STICKY_STATUS_CLEAR 0xc164 + +#define GPIO_TOD_NOTIFICATION_CLEAR 0xc16c + +#define ALERT_CFG 0xc188 + +#define SYS_DPLL_XO 0xc194 + +#define SYS_APLL 0xc19c + +#define INPUT_0 0xc1b0 +#define INPUT_1 0xc1c0 +#define INPUT_2 0xc1d0 +#define INPUT_3 0xc200 +#define INPUT_4 0xc210 +#define INPUT_5 0xc220 +#define INPUT_6 0xc230 +#define INPUT_7 0xc240 +#define INPUT_8 0xc250 +#define INPUT_9 0xc260 +#define INPUT_10 0xc280 +#define INPUT_11 0xc290 +#define INPUT_12 0xc2a0 +#define INPUT_13 0xc2b0 +#define INPUT_14 0xc2c0 +#define INPUT_15 0xc2d0 + +#define REF_MON_0 0xc2e0 +#define REF_MON_1 0xc2ec +#define REF_MON_2 0xc300 +#define REF_MON_3 0xc30c +#define REF_MON_4 0xc318 +#define REF_MON_5 0xc324 +#define REF_MON_6 0xc330 +#define REF_MON_7 0xc33c +#define REF_MON_8 0xc348 +#define REF_MON_9 0xc354 +#define REF_MON_10 0xc360 +#define REF_MON_11 0xc36c +#define REF_MON_12 0xc380 +#define REF_MON_13 0xc38c +#define REF_MON_14 0xc398 +#define REF_MON_15 0xc3a4 + +#define DPLL_0 0xc3b0 +#define DPLL_CTRL_REG_0 0x0002 +#define DPLL_CTRL_REG_1 0x0003 +#define DPLL_CTRL_REG_2 0x0004 +#define DPLL_TOD_SYNC_CFG 0x0031 +#define DPLL_COMBO_SLAVE_CFG_0 0x0032 +#define DPLL_COMBO_SLAVE_CFG_1 0x0033 +#define DPLL_SLAVE_REF_CFG 0x0034 +#define DPLL_REF_MODE 0x0035 +#define DPLL_PHASE_MEASUREMENT_CFG 0x0036 +#define DPLL_MODE 0x0037 +#define DPLL_MODE_V520 0x003B +#define DPLL_1 0xc400 +#define DPLL_2 0xc438 +#define DPLL_2_V520 0xc43c +#define DPLL_3 0xc480 +#define DPLL_4 0xc4b8 +#define DPLL_4_V520 0xc4bc +#define DPLL_5 0xc500 +#define DPLL_6 0xc538 +#define DPLL_6_V520 0xc53c +#define DPLL_7 0xc580 +#define SYS_DPLL 0xc5b8 +#define SYS_DPLL_V520 0xc5bc + +#define DPLL_CTRL_0 0xc600 +#define DPLL_CTRL_DPLL_MANU_REF_CFG 0x0001 +#define DPLL_CTRL_DPLL_FOD_FREQ 0x001c +#define DPLL_CTRL_COMBO_MASTER_CFG 0x003a +#define DPLL_CTRL_1 0xc63c +#define DPLL_CTRL_2 0xc680 +#define DPLL_CTRL_3 0xc6bc +#define DPLL_CTRL_4 0xc700 +#define DPLL_CTRL_5 0xc73c +#define DPLL_CTRL_6 0xc780 +#define DPLL_CTRL_7 0xc7bc +#define SYS_DPLL_CTRL 0xc800 + +#define DPLL_PHASE_0 0xc818 +/* Signed 42-bit FFO in units of 2^(-53) */ +#define DPLL_WR_PHASE 0x0000 +#define DPLL_PHASE_1 0xc81c +#define DPLL_PHASE_2 0xc820 +#define DPLL_PHASE_3 0xc824 +#define DPLL_PHASE_4 0xc828 +#define DPLL_PHASE_5 0xc82c +#define DPLL_PHASE_6 0xc830 +#define DPLL_PHASE_7 0xc834 + +#define DPLL_FREQ_0 0xc838 +/* Signed 42-bit FFO in units of 2^(-53) */ +#define DPLL_WR_FREQ 0x0000 +#define DPLL_FREQ_1 0xc840 +#define DPLL_FREQ_2 0xc848 +#define DPLL_FREQ_3 0xc850 +#define DPLL_FREQ_4 0xc858 +#define DPLL_FREQ_5 0xc860 +#define DPLL_FREQ_6 0xc868 +#define DPLL_FREQ_7 0xc870 + +#define DPLL_PHASE_PULL_IN_0 0xc880 +#define PULL_IN_OFFSET 0x0000 /* Signed 32 bit */ +#define PULL_IN_SLOPE_LIMIT 0x0004 /* Unsigned 24 bit */ +#define PULL_IN_CTRL 0x0007 +#define DPLL_PHASE_PULL_IN_1 0xc888 +#define DPLL_PHASE_PULL_IN_2 0xc890 +#define DPLL_PHASE_PULL_IN_3 0xc898 +#define DPLL_PHASE_PULL_IN_4 0xc8a0 +#define DPLL_PHASE_PULL_IN_5 0xc8a8 +#define DPLL_PHASE_PULL_IN_6 0xc8b0 +#define DPLL_PHASE_PULL_IN_7 0xc8b8 + +#define GPIO_CFG 0xc8c0 +#define GPIO_CFG_GBL 0x0000 +#define GPIO_0 0xc8c2 +#define GPIO_DCO_INC_DEC 0x0000 +#define GPIO_OUT_CTRL_0 0x0001 +#define GPIO_OUT_CTRL_1 0x0002 +#define GPIO_TOD_TRIG 0x0003 +#define GPIO_DPLL_INDICATOR 0x0004 +#define GPIO_LOS_INDICATOR 0x0005 +#define GPIO_REF_INPUT_DSQ_0 0x0006 +#define GPIO_REF_INPUT_DSQ_1 0x0007 +#define GPIO_REF_INPUT_DSQ_2 0x0008 +#define GPIO_REF_INPUT_DSQ_3 0x0009 +#define GPIO_MAN_CLK_SEL_0 0x000a +#define GPIO_MAN_CLK_SEL_1 0x000b +#define GPIO_MAN_CLK_SEL_2 0x000c +#define GPIO_SLAVE 0x000d +#define GPIO_ALERT_OUT_CFG 0x000e +#define GPIO_TOD_NOTIFICATION_CFG 0x000f +#define GPIO_CTRL 0x0010 +#define GPIO_CTRL_V520 0x0011 +#define GPIO_1 0xc8d4 +#define GPIO_2 0xc8e6 +#define GPIO_3 0xc900 +#define GPIO_4 0xc912 +#define GPIO_5 0xc924 +#define GPIO_6 0xc936 +#define GPIO_7 0xc948 +#define GPIO_8 0xc95a +#define GPIO_9 0xc980 +#define GPIO_10 0xc992 +#define GPIO_11 0xc9a4 +#define GPIO_12 0xc9b6 +#define GPIO_13 0xc9c8 +#define GPIO_14 0xc9da +#define GPIO_15 0xca00 + +#define OUT_DIV_MUX 0xca12 +#define OUTPUT_0 0xca14 +#define OUTPUT_0_V520 0xca20 +/* FOD frequency output divider value */ +#define OUT_DIV 0x0000 +#define OUT_DUTY_CYCLE_HIGH 0x0004 +#define OUT_CTRL_0 0x0008 +#define OUT_CTRL_1 0x0009 +/* Phase adjustment in FOD cycles */ +#define OUT_PHASE_ADJ 0x000c +#define OUTPUT_1 0xca24 +#define OUTPUT_1_V520 0xca30 +#define OUTPUT_2 0xca34 +#define OUTPUT_2_V520 0xca40 +#define OUTPUT_3 0xca44 +#define OUTPUT_3_V520 0xca50 +#define OUTPUT_4 0xca54 +#define OUTPUT_4_V520 0xca60 +#define OUTPUT_5 0xca64 +#define OUTPUT_5_V520 0xca80 +#define OUTPUT_6 0xca80 +#define OUTPUT_6_V520 0xca90 +#define OUTPUT_7 0xca90 +#define OUTPUT_7_V520 0xcaa0 +#define OUTPUT_8 0xcaa0 +#define OUTPUT_8_V520 0xcab0 +#define OUTPUT_9 0xcab0 +#define OUTPUT_9_V520 0xcac0 +#define OUTPUT_10 0xcac0 +#define OUTPUT_10_V520 0xcad0 +#define OUTPUT_11 0xcad0 +#define OUTPUT_11_V520 0xcae0 + +#define SERIAL 0xcae0 +#define SERIAL_V520 0xcaf0 + +#define PWM_ENCODER_0 0xcb00 +#define PWM_ENCODER_1 0xcb08 +#define PWM_ENCODER_2 0xcb10 +#define PWM_ENCODER_3 0xcb18 +#define PWM_ENCODER_4 0xcb20 +#define PWM_ENCODER_5 0xcb28 +#define PWM_ENCODER_6 0xcb30 +#define PWM_ENCODER_7 0xcb38 +#define PWM_DECODER_0 0xcb40 +#define PWM_DECODER_1 0xcb48 +#define PWM_DECODER_1_V520 0xcb4a +#define PWM_DECODER_2 0xcb50 +#define PWM_DECODER_2_V520 0xcb54 +#define PWM_DECODER_3 0xcb58 +#define PWM_DECODER_3_V520 0xcb5e +#define PWM_DECODER_4 0xcb60 +#define PWM_DECODER_4_V520 0xcb68 +#define PWM_DECODER_5 0xcb68 +#define PWM_DECODER_5_V520 0xcb80 +#define PWM_DECODER_6 0xcb70 +#define PWM_DECODER_6_V520 0xcb8a +#define PWM_DECODER_7 0xcb80 +#define PWM_DECODER_7_V520 0xcb94 +#define PWM_DECODER_8 0xcb88 +#define PWM_DECODER_8_V520 0xcb9e +#define PWM_DECODER_9 0xcb90 +#define PWM_DECODER_9_V520 0xcba8 +#define PWM_DECODER_10 0xcb98 +#define PWM_DECODER_10_V520 0xcbb2 +#define PWM_DECODER_11 0xcba0 +#define PWM_DECODER_11_V520 0xcbbc +#define PWM_DECODER_12 0xcba8 +#define PWM_DECODER_12_V520 0xcbc6 +#define PWM_DECODER_13 0xcbb0 +#define PWM_DECODER_13_V520 0xcbd0 +#define PWM_DECODER_14 0xcbb8 +#define PWM_DECODER_14_V520 0xcbda +#define PWM_DECODER_15 0xcbc0 +#define PWM_DECODER_15_V520 0xcbe4 +#define PWM_USER_DATA 0xcbc8 +#define PWM_USER_DATA_V520 0xcbf0 + +#define TOD_0 0xcbcc +#define TOD_0_V520 0xcc00 +/* Enable TOD counter, output channel sync and even-PPS mode */ +#define TOD_CFG 0x0000 +#define TOD_CFG_V520 0x0001 +#define TOD_1 0xcbce +#define TOD_1_V520 0xcc02 +#define TOD_2 0xcbd0 +#define TOD_2_V520 0xcc04 +#define TOD_3 0xcbd2 +#define TOD_3_V520 0xcc06 + +#define TOD_WRITE_0 0xcc00 +#define TOD_WRITE_0_V520 0xcc10 +/* 8-bit subns, 32-bit ns, 48-bit seconds */ +#define TOD_WRITE 0x0000 +/* Counter increments after TOD write is completed */ +#define TOD_WRITE_COUNTER 0x000c +/* TOD write trigger configuration */ +#define TOD_WRITE_SELECT_CFG_0 0x000d +/* TOD write trigger selection */ +#define TOD_WRITE_CMD 0x000f +#define TOD_WRITE_1 0xcc10 +#define TOD_WRITE_1_V520 0xcc20 +#define TOD_WRITE_2 0xcc20 +#define TOD_WRITE_2_V520 0xcc30 +#define TOD_WRITE_3 0xcc30 +#define TOD_WRITE_3_V520 0xcc40 + +#define TOD_READ_PRIMARY_0 0xcc40 +#define TOD_READ_PRIMARY_0_V520 0xcc50 +/* 8-bit subns, 32-bit ns, 48-bit seconds */ +#define TOD_READ_PRIMARY 0x0000 +/* Counter increments after TOD write is completed */ +#define TOD_READ_PRIMARY_COUNTER 0x000b +/* Read trigger configuration */ +#define TOD_READ_PRIMARY_SEL_CFG_0 0x000c +/* Read trigger selection */ +#define TOD_READ_PRIMARY_CMD 0x000e +#define TOD_READ_PRIMARY_CMD_V520 0x000f +#define TOD_READ_PRIMARY_1 0xcc50 +#define TOD_READ_PRIMARY_1_V520 0xcc60 +#define TOD_READ_PRIMARY_2 0xcc60 +#define TOD_READ_PRIMARY_2_V520 0xcc80 +#define TOD_READ_PRIMARY_3 0xcc80 +#define TOD_READ_PRIMARY_3_V520 0xcc90 + +#define TOD_READ_SECONDARY_0 0xcc90 +#define TOD_READ_SECONDARY_0_V520 0xcca0 +#define TOD_READ_SECONDARY_1 0xcca0 +#define TOD_READ_SECONDARY_1_V520 0xccb0 +#define TOD_READ_SECONDARY_2 0xccb0 +#define TOD_READ_SECONDARY_2_V520 0xccc0 +#define TOD_READ_SECONDARY_3 0xccc0 +#define TOD_READ_SECONDARY_3_V520 0xccd0 + +#define OUTPUT_TDC_CFG 0xccd0 +#define OUTPUT_TDC_CFG_V520 0xcce0 +#define OUTPUT_TDC_0 0xcd00 +#define OUTPUT_TDC_1 0xcd08 +#define OUTPUT_TDC_2 0xcd10 +#define OUTPUT_TDC_3 0xcd18 +#define INPUT_TDC 0xcd20 + +#define SCRATCH 0xcf50 +#define SCRATCH_V520 0xcf4c + +#define EEPROM 0xcf68 +#define EEPROM_V520 0xcf64 + +#define OTP 0xcf70 + +#define BYTE 0xcf80 + +/* Bit definitions for the MAJ_REL register */ +#define MAJOR_SHIFT (1) +#define MAJOR_MASK (0x7f) +#define PR_BUILD BIT(0) + +/* Bit definitions for the USER_GPIO0_TO_7_STATUS register */ +#define GPIO0_LEVEL BIT(0) +#define GPIO1_LEVEL BIT(1) +#define GPIO2_LEVEL BIT(2) +#define GPIO3_LEVEL BIT(3) +#define GPIO4_LEVEL BIT(4) +#define GPIO5_LEVEL BIT(5) +#define GPIO6_LEVEL BIT(6) +#define GPIO7_LEVEL BIT(7) + +/* Bit definitions for the USER_GPIO8_TO_15_STATUS register */ +#define GPIO8_LEVEL BIT(0) +#define GPIO9_LEVEL BIT(1) +#define GPIO10_LEVEL BIT(2) +#define GPIO11_LEVEL BIT(3) +#define GPIO12_LEVEL BIT(4) +#define GPIO13_LEVEL BIT(5) +#define GPIO14_LEVEL BIT(6) +#define GPIO15_LEVEL BIT(7) + +/* Bit definitions for the GPIO0_TO_7_OUT register */ +#define GPIO0_DRIVE_LEVEL BIT(0) +#define GPIO1_DRIVE_LEVEL BIT(1) +#define GPIO2_DRIVE_LEVEL BIT(2) +#define GPIO3_DRIVE_LEVEL BIT(3) +#define GPIO4_DRIVE_LEVEL BIT(4) +#define GPIO5_DRIVE_LEVEL BIT(5) +#define GPIO6_DRIVE_LEVEL BIT(6) +#define GPIO7_DRIVE_LEVEL BIT(7) + +/* Bit definitions for the GPIO8_TO_15_OUT register */ +#define GPIO8_DRIVE_LEVEL BIT(0) +#define GPIO9_DRIVE_LEVEL BIT(1) +#define GPIO10_DRIVE_LEVEL BIT(2) +#define GPIO11_DRIVE_LEVEL BIT(3) +#define GPIO12_DRIVE_LEVEL BIT(4) +#define GPIO13_DRIVE_LEVEL BIT(5) +#define GPIO14_DRIVE_LEVEL BIT(6) +#define GPIO15_DRIVE_LEVEL BIT(7) + +/* Bit definitions for the DPLL_TOD_SYNC_CFG register */ +#define TOD_SYNC_SOURCE_SHIFT (1) +#define TOD_SYNC_SOURCE_MASK (0x3) +#define TOD_SYNC_EN BIT(0) + +/* Bit definitions for the DPLL_MODE register */ +#define WRITE_TIMER_MODE BIT(6) +#define PLL_MODE_SHIFT (3) +#define PLL_MODE_MASK (0x7) +#define STATE_MODE_SHIFT (0) +#define STATE_MODE_MASK (0x7) + +/* Bit definitions for the GPIO_CFG_GBL register */ +#define SUPPLY_MODE_SHIFT (0) +#define SUPPLY_MODE_MASK (0x3) + +/* Bit definitions for the GPIO_DCO_INC_DEC register */ +#define INCDEC_DPLL_INDEX_SHIFT (0) +#define INCDEC_DPLL_INDEX_MASK (0x7) + +/* Bit definitions for the GPIO_OUT_CTRL_0 register */ +#define CTRL_OUT_0 BIT(0) +#define CTRL_OUT_1 BIT(1) +#define CTRL_OUT_2 BIT(2) +#define CTRL_OUT_3 BIT(3) +#define CTRL_OUT_4 BIT(4) +#define CTRL_OUT_5 BIT(5) +#define CTRL_OUT_6 BIT(6) +#define CTRL_OUT_7 BIT(7) + +/* Bit definitions for the GPIO_OUT_CTRL_1 register */ +#define CTRL_OUT_8 BIT(0) +#define CTRL_OUT_9 BIT(1) +#define CTRL_OUT_10 BIT(2) +#define CTRL_OUT_11 BIT(3) +#define CTRL_OUT_12 BIT(4) +#define CTRL_OUT_13 BIT(5) +#define CTRL_OUT_14 BIT(6) +#define CTRL_OUT_15 BIT(7) + +/* Bit definitions for the GPIO_TOD_TRIG register */ +#define TOD_TRIG_0 BIT(0) +#define TOD_TRIG_1 BIT(1) +#define TOD_TRIG_2 BIT(2) +#define TOD_TRIG_3 BIT(3) + +/* Bit definitions for the GPIO_DPLL_INDICATOR register */ +#define IND_DPLL_INDEX_SHIFT (0) +#define IND_DPLL_INDEX_MASK (0x7) + +/* Bit definitions for the GPIO_LOS_INDICATOR register */ +#define REFMON_INDEX_SHIFT (0) +#define REFMON_INDEX_MASK (0xf) +/* Active level of LOS indicator, 0=low 1=high */ +#define ACTIVE_LEVEL BIT(4) + +/* Bit definitions for the GPIO_REF_INPUT_DSQ_0 register */ +#define DSQ_INP_0 BIT(0) +#define DSQ_INP_1 BIT(1) +#define DSQ_INP_2 BIT(2) +#define DSQ_INP_3 BIT(3) +#define DSQ_INP_4 BIT(4) +#define DSQ_INP_5 BIT(5) +#define DSQ_INP_6 BIT(6) +#define DSQ_INP_7 BIT(7) + +/* Bit definitions for the GPIO_REF_INPUT_DSQ_1 register */ +#define DSQ_INP_8 BIT(0) +#define DSQ_INP_9 BIT(1) +#define DSQ_INP_10 BIT(2) +#define DSQ_INP_11 BIT(3) +#define DSQ_INP_12 BIT(4) +#define DSQ_INP_13 BIT(5) +#define DSQ_INP_14 BIT(6) +#define DSQ_INP_15 BIT(7) + +/* Bit definitions for the GPIO_REF_INPUT_DSQ_2 register */ +#define DSQ_DPLL_0 BIT(0) +#define DSQ_DPLL_1 BIT(1) +#define DSQ_DPLL_2 BIT(2) +#define DSQ_DPLL_3 BIT(3) +#define DSQ_DPLL_4 BIT(4) +#define DSQ_DPLL_5 BIT(5) +#define DSQ_DPLL_6 BIT(6) +#define DSQ_DPLL_7 BIT(7) + +/* Bit definitions for the GPIO_REF_INPUT_DSQ_3 register */ +#define DSQ_DPLL_SYS BIT(0) +#define GPIO_DSQ_LEVEL BIT(1) + +/* Bit definitions for the GPIO_TOD_NOTIFICATION_CFG register */ +#define DPLL_TOD_SHIFT (0) +#define DPLL_TOD_MASK (0x3) +#define TOD_READ_SECONDARY BIT(2) +#define GPIO_ASSERT_LEVEL BIT(3) + +/* Bit definitions for the GPIO_CTRL register */ +#define GPIO_FUNCTION_EN BIT(0) +#define GPIO_CMOS_OD_MODE BIT(1) +#define GPIO_CONTROL_DIR BIT(2) +#define GPIO_PU_PD_MODE BIT(3) +#define GPIO_FUNCTION_SHIFT (4) +#define GPIO_FUNCTION_MASK (0xf) + +/* Bit definitions for the OUT_CTRL_1 register */ +#define OUT_SYNC_DISABLE BIT(7) +#define SQUELCH_VALUE BIT(6) +#define SQUELCH_DISABLE BIT(5) +#define PAD_VDDO_SHIFT (2) +#define PAD_VDDO_MASK (0x7) +#define PAD_CMOSDRV_SHIFT (0) +#define PAD_CMOSDRV_MASK (0x3) + +/* Bit definitions for the TOD_CFG register */ +#define TOD_EVEN_PPS_MODE BIT(2) +#define TOD_OUT_SYNC_ENABLE BIT(1) +#define TOD_ENABLE BIT(0) + +/* Bit definitions for the TOD_WRITE_SELECT_CFG_0 register */ +#define WR_PWM_DECODER_INDEX_SHIFT (4) +#define WR_PWM_DECODER_INDEX_MASK (0xf) +#define WR_REF_INDEX_SHIFT (0) +#define WR_REF_INDEX_MASK (0xf) + +/* Bit definitions for the TOD_WRITE_CMD register */ +#define TOD_WRITE_SELECTION_SHIFT (0) +#define TOD_WRITE_SELECTION_MASK (0xf) +/* 4.8.7 */ +#define TOD_WRITE_TYPE_SHIFT (4) +#define TOD_WRITE_TYPE_MASK (0x3) + +/* Bit definitions for the TOD_READ_PRIMARY_SEL_CFG_0 register */ +#define RD_PWM_DECODER_INDEX_SHIFT (4) +#define RD_PWM_DECODER_INDEX_MASK (0xf) +#define RD_REF_INDEX_SHIFT (0) +#define RD_REF_INDEX_MASK (0xf) + +/* Bit definitions for the TOD_READ_PRIMARY_CMD register */ +#define TOD_READ_TRIGGER_MODE BIT(4) +#define TOD_READ_TRIGGER_SHIFT (0) +#define TOD_READ_TRIGGER_MASK (0xf) + +/* Bit definitions for the DPLL_CTRL_COMBO_MASTER_CFG register */ +#define COMBO_MASTER_HOLD BIT(0) + +/* Bit definitions for DPLL_SYS_STATUS register */ +#define DPLL_SYS_STATE_MASK (0xf) + +/* Bit definitions for SYS_APLL_STATUS register */ +#define SYS_APLL_LOSS_LOCK_LIVE_MASK BIT(0) +#define SYS_APLL_LOSS_LOCK_LIVE_LOCKED 0 +#define SYS_APLL_LOSS_LOCK_LIVE_UNLOCKED 1 + +/* Bit definitions for the DPLL0_STATUS register */ +#define DPLL_STATE_MASK (0xf) +#define DPLL_STATE_SHIFT (0x0) + +/* Values of DPLL_N.DPLL_MODE.PLL_MODE */ +enum pll_mode { + PLL_MODE_MIN = 0, + PLL_MODE_NORMAL = PLL_MODE_MIN, + PLL_MODE_WRITE_PHASE = 1, + PLL_MODE_WRITE_FREQUENCY = 2, + PLL_MODE_GPIO_INC_DEC = 3, + PLL_MODE_SYNTHESIS = 4, + PLL_MODE_PHASE_MEASUREMENT = 5, + PLL_MODE_DISABLED = 6, + PLL_MODE_MAX = PLL_MODE_DISABLED, +}; + +enum hw_tod_write_trig_sel { + HW_TOD_WR_TRIG_SEL_MIN = 0, + HW_TOD_WR_TRIG_SEL_MSB = HW_TOD_WR_TRIG_SEL_MIN, + HW_TOD_WR_TRIG_SEL_RESERVED = 1, + HW_TOD_WR_TRIG_SEL_TOD_PPS = 2, + HW_TOD_WR_TRIG_SEL_IRIGB_PPS = 3, + HW_TOD_WR_TRIG_SEL_PWM_PPS = 4, + HW_TOD_WR_TRIG_SEL_GPIO = 5, + HW_TOD_WR_TRIG_SEL_FOD_SYNC = 6, + WR_TRIG_SEL_MAX = HW_TOD_WR_TRIG_SEL_FOD_SYNC, +}; + +enum scsr_read_trig_sel { + /* CANCEL CURRENT TOD READ; MODULE BECOMES IDLE - NO TRIGGER OCCURS */ + SCSR_TOD_READ_TRIG_SEL_DISABLE = 0, + /* TRIGGER IMMEDIATELY */ + SCSR_TOD_READ_TRIG_SEL_IMMEDIATE = 1, + /* TRIGGER ON RISING EDGE OF INTERNAL TOD PPS SIGNAL */ + SCSR_TOD_READ_TRIG_SEL_TODPPS = 2, + /* TRGGER ON RISING EDGE OF SELECTED REFERENCE INPUT */ + SCSR_TOD_READ_TRIG_SEL_REFCLK = 3, + /* TRIGGER ON RISING EDGE OF SELECTED PWM DECODER 1PPS OUTPUT */ + SCSR_TOD_READ_TRIG_SEL_PWMPPS = 4, + SCSR_TOD_READ_TRIG_SEL_RESERVED = 5, + /* TRIGGER WHEN WRITE FREQUENCY EVENT OCCURS */ + SCSR_TOD_READ_TRIG_SEL_WRITEFREQUENCYEVENT = 6, + /* TRIGGER ON SELECTED GPIO */ + SCSR_TOD_READ_TRIG_SEL_GPIO = 7, + SCSR_TOD_READ_TRIG_SEL_MAX = SCSR_TOD_READ_TRIG_SEL_GPIO, +}; + +/* Values STATUS.DPLL_SYS_STATUS.DPLL_SYS_STATE */ +enum dpll_state { + DPLL_STATE_MIN = 0, + DPLL_STATE_FREERUN = DPLL_STATE_MIN, + DPLL_STATE_LOCKACQ = 1, + DPLL_STATE_LOCKREC = 2, + DPLL_STATE_LOCKED = 3, + DPLL_STATE_HOLDOVER = 4, + DPLL_STATE_OPEN_LOOP = 5, + DPLL_STATE_MAX = DPLL_STATE_OPEN_LOOP, +}; + +/* 4.8.7 only */ +enum scsr_tod_write_trig_sel { + SCSR_TOD_WR_TRIG_SEL_DISABLE = 0, + SCSR_TOD_WR_TRIG_SEL_IMMEDIATE = 1, + SCSR_TOD_WR_TRIG_SEL_REFCLK = 2, + SCSR_TOD_WR_TRIG_SEL_PWMPPS = 3, + SCSR_TOD_WR_TRIG_SEL_TODPPS = 4, + SCSR_TOD_WR_TRIG_SEL_SYNCFOD = 5, + SCSR_TOD_WR_TRIG_SEL_GPIO = 6, + SCSR_TOD_WR_TRIG_SEL_MAX = SCSR_TOD_WR_TRIG_SEL_GPIO, +}; + +/* 4.8.7 only */ +enum scsr_tod_write_type_sel { + SCSR_TOD_WR_TYPE_SEL_ABSOLUTE = 0, + SCSR_TOD_WR_TYPE_SEL_DELTA_PLUS = 1, + SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS = 2, + SCSR_TOD_WR_TYPE_SEL_MAX = SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS, +}; +#endif diff --git a/include/linux/mfd/rsmu.h b/include/linux/mfd/rsmu.h new file mode 100644 index 000000000000..6870de608233 --- /dev/null +++ b/include/linux/mfd/rsmu.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Core interface for Renesas Synchronization Management Unit (SMU) devices. + * + * Copyright (C) 2021 Integrated Device Technology, Inc., a Renesas Company. + */ + +#ifndef __LINUX_MFD_RSMU_H +#define __LINUX_MFD_RSMU_H + +/* The supported devices are ClockMatrix, Sabre and SnowLotus */ +enum rsmu_type { + RSMU_CM = 0x34000, + RSMU_SABRE = 0x33810, + RSMU_SL = 0x19850, +}; + +/** + * + * struct rsmu_ddata - device data structure for sub devices. + * + * @dev: i2c/spi device. + * @regmap: i2c/spi bus access. + * @lock: mutex used by sub devices to make sure a series of + * bus access requests are not interrupted. + * @type: RSMU device type. + * @page: i2c/spi bus driver internal use only. + */ +struct rsmu_ddata { + struct device *dev; + struct regmap *regmap; + struct mutex lock; + enum rsmu_type type; + u16 page; +}; +#endif /* __LINUX_MFD_RSMU_H */ -- cgit v1.2.3 From 7506ae6a7033f617ca5fea53e356fb1f7bd98010 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 24 May 2021 13:02:30 +0200 Subject: mm: Add functions to lock invalidate_lock for two mappings Some operations such as reflinking blocks among files will need to lock invalidate_lock for two mappings. Add helper functions to do that. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/fs.h | 6 ++++++ mm/filemap.c | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 90a80de37ad4..894ff2451793 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -849,6 +849,12 @@ static inline void filemap_invalidate_unlock_shared( void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); +void filemap_invalidate_lock_two(struct address_space *mapping1, + struct address_space *mapping2); +void filemap_invalidate_unlock_two(struct address_space *mapping1, + struct address_space *mapping2); + + /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic diff --git a/mm/filemap.c b/mm/filemap.c index f7f9b87d2cd0..0fad08331cf4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1009,6 +1009,44 @@ struct page *__page_cache_alloc(gfp_t gfp) EXPORT_SYMBOL(__page_cache_alloc); #endif +/* + * filemap_invalidate_lock_two - lock invalidate_lock for two mappings + * + * Lock exclusively invalidate_lock of any passed mapping that is not NULL. + * + * @mapping1: the first mapping to lock + * @mapping2: the second mapping to lock + */ +void filemap_invalidate_lock_two(struct address_space *mapping1, + struct address_space *mapping2) +{ + if (mapping1 > mapping2) + swap(mapping1, mapping2); + if (mapping1) + down_write(&mapping1->invalidate_lock); + if (mapping2 && mapping1 != mapping2) + down_write_nested(&mapping2->invalidate_lock, 1); +} +EXPORT_SYMBOL(filemap_invalidate_lock_two); + +/* + * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings + * + * Unlock exclusive invalidate_lock of any passed mapping that is not NULL. + * + * @mapping1: the first mapping to unlock + * @mapping2: the second mapping to unlock + */ +void filemap_invalidate_unlock_two(struct address_space *mapping1, + struct address_space *mapping2) +{ + if (mapping1) + up_write(&mapping1->invalidate_lock); + if (mapping2 && mapping1 != mapping2) + up_write(&mapping2->invalidate_lock); +} +EXPORT_SYMBOL(filemap_invalidate_unlock_two); + /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of -- cgit v1.2.3 From 69031f500865ee3eee19566a1b9c40a189817eaa Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:34 +0800 Subject: swiotlb: Set dev->dma_io_tlb_mem to the swiotlb pool used Always have the pointer to the swiotlb pool used in struct device. This could help simplify the code for other pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- drivers/base/core.c | 4 ++++ include/linux/device.h | 4 ++++ kernel/dma/swiotlb.c | 8 ++++---- 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index cadcade65825..ea5b85354526 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include /* for dma_default_coherent */ @@ -2846,6 +2847,9 @@ void device_initialize(struct device *dev) defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) dev->dma_coherent = dma_default_coherent; #endif +#ifdef CONFIG_SWIOTLB + dev->dma_io_tlb_mem = io_tlb_default_mem; +#endif } EXPORT_SYMBOL_GPL(device_initialize); diff --git a/include/linux/device.h b/include/linux/device.h index 59940f1744c1..2a22875238a6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -423,6 +423,7 @@ struct dev_links_info { * @dma_pools: Dma pools (if dma'ble device). * @dma_mem: Internal for coherent mem override. * @cma_area: Contiguous memory area for dma allocations + * @dma_io_tlb_mem: Pointer to the swiotlb pool used. Not for driver use. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. * @fwnode: Associated device node supplied by platform firmware. @@ -531,6 +532,9 @@ struct device { #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ +#endif +#ifdef CONFIG_SWIOTLB + struct io_tlb_mem *dma_io_tlb_mem; #endif /* arch specific additions */ struct dev_archdata archdata; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index ae6a151d0a41..33d413beddd4 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -348,7 +348,7 @@ static unsigned int swiotlb_align_offset(struct device *dev, u64 addr) static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT; phys_addr_t orig_addr = mem->slots[index].orig_addr; size_t alloc_size = mem->slots[index].alloc_size; @@ -429,7 +429,7 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index) static int find_slots(struct device *dev, phys_addr_t orig_addr, size_t alloc_size) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned long boundary_mask = dma_get_seg_boundary(dev); dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(dev, mem->start) & boundary_mask; @@ -506,7 +506,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, size_t mapping_size, size_t alloc_size, enum dma_data_direction dir, unsigned long attrs) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned int offset = swiotlb_align_offset(dev, orig_addr); unsigned int i; int index; @@ -557,7 +557,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, size_t mapping_size, enum dma_data_direction dir, unsigned long attrs) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = hwdev->dma_io_tlb_mem; unsigned long flags; unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr); int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; -- cgit v1.2.3 From 7fd856aa7f4261ddac62ea59d8383fef22a0690e Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:35 +0800 Subject: swiotlb: Update is_swiotlb_buffer to add a struct device argument Update is_swiotlb_buffer to add a struct device argument. This will be useful later to allow for different pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- drivers/iommu/dma-iommu.c | 12 ++++++------ drivers/xen/swiotlb-xen.c | 2 +- include/linux/swiotlb.h | 7 ++++--- kernel/dma/direct.c | 6 +++--- kernel/dma/direct.h | 6 +++--- 5 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 98ba927aee1a..4e34e8b26579 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -506,7 +506,7 @@ static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr, __iommu_dma_unmap(dev, dma_addr, size); - if (unlikely(is_swiotlb_buffer(phys))) + if (unlikely(is_swiotlb_buffer(dev, phys))) swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } @@ -577,7 +577,7 @@ static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys, } iova = __iommu_dma_map(dev, phys, aligned_size, prot, dma_mask); - if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(phys)) + if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(dev, phys)) swiotlb_tbl_unmap_single(dev, phys, org_size, dir, attrs); return iova; } @@ -783,7 +783,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_cpu(phys, size, dir); - if (is_swiotlb_buffer(phys)) + if (is_swiotlb_buffer(dev, phys)) swiotlb_sync_single_for_cpu(dev, phys, size, dir); } @@ -796,7 +796,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev, return; phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle); - if (is_swiotlb_buffer(phys)) + if (is_swiotlb_buffer(dev, phys)) swiotlb_sync_single_for_device(dev, phys, size, dir); if (!dev_is_dma_coherent(dev)) @@ -817,7 +817,7 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir); - if (is_swiotlb_buffer(sg_phys(sg))) + if (is_swiotlb_buffer(dev, sg_phys(sg))) swiotlb_sync_single_for_cpu(dev, sg_phys(sg), sg->length, dir); } @@ -834,7 +834,7 @@ static void iommu_dma_sync_sg_for_device(struct device *dev, return; for_each_sg(sgl, sg, nelems, i) { - if (is_swiotlb_buffer(sg_phys(sg))) + if (is_swiotlb_buffer(dev, sg_phys(sg))) swiotlb_sync_single_for_device(dev, sg_phys(sg), sg->length, dir); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 24d11861ac7d..0c4fb34f11ab 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -100,7 +100,7 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr) * in our domain. Therefore _only_ check address within our domain. */ if (pfn_valid(PFN_DOWN(paddr))) - return is_swiotlb_buffer(paddr); + return is_swiotlb_buffer(dev, paddr); return 0; } diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 216854a5e513..d1f3d95881cd 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -2,6 +2,7 @@ #ifndef __LINUX_SWIOTLB_H #define __LINUX_SWIOTLB_H +#include #include #include #include @@ -101,9 +102,9 @@ struct io_tlb_mem { }; extern struct io_tlb_mem *io_tlb_default_mem; -static inline bool is_swiotlb_buffer(phys_addr_t paddr) +static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; return mem && paddr >= mem->start && paddr < mem->end; } @@ -115,7 +116,7 @@ bool is_swiotlb_active(void); void __init swiotlb_adjust_size(unsigned long size); #else #define swiotlb_force SWIOTLB_NO_FORCE -static inline bool is_swiotlb_buffer(phys_addr_t paddr) +static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index f737e3347059..84c9feb5474a 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -343,7 +343,7 @@ void dma_direct_sync_sg_for_device(struct device *dev, for_each_sg(sgl, sg, nents, i) { phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg)); - if (unlikely(is_swiotlb_buffer(paddr))) + if (unlikely(is_swiotlb_buffer(dev, paddr))) swiotlb_sync_single_for_device(dev, paddr, sg->length, dir); @@ -369,7 +369,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev, if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_cpu(paddr, sg->length, dir); - if (unlikely(is_swiotlb_buffer(paddr))) + if (unlikely(is_swiotlb_buffer(dev, paddr))) swiotlb_sync_single_for_cpu(dev, paddr, sg->length, dir); @@ -504,7 +504,7 @@ size_t dma_direct_max_mapping_size(struct device *dev) bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr) { return !dev_is_dma_coherent(dev) || - is_swiotlb_buffer(dma_to_phys(dev, dma_addr)); + is_swiotlb_buffer(dev, dma_to_phys(dev, dma_addr)); } /** diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 50afc05b6f1d..13e9e7158d94 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -56,7 +56,7 @@ static inline void dma_direct_sync_single_for_device(struct device *dev, { phys_addr_t paddr = dma_to_phys(dev, addr); - if (unlikely(is_swiotlb_buffer(paddr))) + if (unlikely(is_swiotlb_buffer(dev, paddr))) swiotlb_sync_single_for_device(dev, paddr, size, dir); if (!dev_is_dma_coherent(dev)) @@ -73,7 +73,7 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev, arch_sync_dma_for_cpu_all(); } - if (unlikely(is_swiotlb_buffer(paddr))) + if (unlikely(is_swiotlb_buffer(dev, paddr))) swiotlb_sync_single_for_cpu(dev, paddr, size, dir); if (dir == DMA_FROM_DEVICE) @@ -113,7 +113,7 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) dma_direct_sync_single_for_cpu(dev, addr, size, dir); - if (unlikely(is_swiotlb_buffer(phys))) + if (unlikely(is_swiotlb_buffer(dev, phys))) swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } #endif /* _KERNEL_DMA_DIRECT_H */ -- cgit v1.2.3 From 6f2beb268a5d35504a636c4a3b7aaa76ec32d96c Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:36 +0800 Subject: swiotlb: Update is_swiotlb_active to add a struct device argument Update is_swiotlb_active to add a struct device argument. This will be useful later to allow for different pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- drivers/gpu/drm/i915/gem/i915_gem_internal.c | 2 +- drivers/gpu/drm/nouveau/nouveau_ttm.c | 2 +- drivers/pci/xen-pcifront.c | 2 +- include/linux/swiotlb.h | 4 ++-- kernel/dma/direct.c | 2 +- kernel/dma/swiotlb.c | 4 ++-- 6 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index ce6b664b10aa..89a894354263 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -42,7 +42,7 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) max_order = MAX_ORDER; #ifdef CONFIG_SWIOTLB - if (is_swiotlb_active()) { + if (is_swiotlb_active(obj->base.dev->dev)) { unsigned int max_segment; max_segment = swiotlb_max_segment(); diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c index f4c2e46b6fe1..2ca9d9a9e5d5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -276,7 +276,7 @@ nouveau_ttm_init(struct nouveau_drm *drm) } #if IS_ENABLED(CONFIG_SWIOTLB) && IS_ENABLED(CONFIG_X86) - need_swiotlb = is_swiotlb_active(); + need_swiotlb = is_swiotlb_active(dev->dev); #endif ret = ttm_device_init(&drm->ttm.bdev, &nouveau_bo_driver, drm->dev->dev, diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index b7a8f3a1921f..0d56985bfe81 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -693,7 +693,7 @@ static int pcifront_connect_and_init_dma(struct pcifront_device *pdev) spin_unlock(&pcifront_dev_lock); - if (!err && !is_swiotlb_active()) { + if (!err && !is_swiotlb_active(&pdev->xdev->dev)) { err = pci_xen_swiotlb_init_late(); if (err) dev_err(&pdev->xdev->dev, "Could not setup SWIOTLB!\n"); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index d1f3d95881cd..dd1c30a83058 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -112,7 +112,7 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); -bool is_swiotlb_active(void); +bool is_swiotlb_active(struct device *dev); void __init swiotlb_adjust_size(unsigned long size); #else #define swiotlb_force SWIOTLB_NO_FORCE @@ -132,7 +132,7 @@ static inline size_t swiotlb_max_mapping_size(struct device *dev) return SIZE_MAX; } -static inline bool is_swiotlb_active(void) +static inline bool is_swiotlb_active(struct device *dev) { return false; } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 84c9feb5474a..7a88c34d0867 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -495,7 +495,7 @@ int dma_direct_supported(struct device *dev, u64 mask) size_t dma_direct_max_mapping_size(struct device *dev) { /* If SWIOTLB is active, use its maximum mapping size */ - if (is_swiotlb_active() && + if (is_swiotlb_active(dev) && (dma_addressing_limited(dev) || swiotlb_force == SWIOTLB_FORCE)) return swiotlb_max_mapping_size(dev); return SIZE_MAX; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 33d413beddd4..d8677d6637dd 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -662,9 +662,9 @@ size_t swiotlb_max_mapping_size(struct device *dev) return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE; } -bool is_swiotlb_active(void) +bool is_swiotlb_active(struct device *dev) { - return io_tlb_default_mem != NULL; + return dev->dma_io_tlb_mem != NULL; } EXPORT_SYMBOL_GPL(is_swiotlb_active); -- cgit v1.2.3 From 903cd0f315fe426c6a64c54ed389de0becb663dc Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Thu, 24 Jun 2021 23:55:20 +0800 Subject: swiotlb: Use is_swiotlb_force_bounce for swiotlb data bouncing Propagate the swiotlb_force into io_tlb_default_mem->force_bounce and use it to determine whether to bounce the data or not. This will be useful later to allow for different pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk [v2: Includes Will's fix] --- drivers/xen/swiotlb-xen.c | 2 +- include/linux/swiotlb.h | 13 +++++++++++++ kernel/dma/direct.c | 2 +- kernel/dma/direct.h | 2 +- kernel/dma/swiotlb.c | 4 ++++ 5 files changed, 20 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 0c4fb34f11ab..785ec7e8be01 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -374,7 +374,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, if (dma_capable(dev, dev_addr, size, true) && !range_straddles_page_boundary(phys, size) && !xen_arch_need_swiotlb(dev, phys, dev_addr) && - swiotlb_force != SWIOTLB_FORCE) + !is_swiotlb_force_bounce(dev)) goto done; /* diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index dd1c30a83058..da348671b0d5 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -84,6 +84,7 @@ extern enum swiotlb_force swiotlb_force; * unmap calls. * @debugfs: The dentry to debugfs. * @late_alloc: %true if allocated using the page allocator + * @force_bounce: %true if swiotlb bouncing is forced */ struct io_tlb_mem { phys_addr_t start; @@ -94,6 +95,7 @@ struct io_tlb_mem { spinlock_t lock; struct dentry *debugfs; bool late_alloc; + bool force_bounce; struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; @@ -109,6 +111,13 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) return mem && paddr >= mem->start && paddr < mem->end; } +static inline bool is_swiotlb_force_bounce(struct device *dev) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + + return mem && mem->force_bounce; +} + void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); @@ -120,6 +129,10 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; } +static inline bool is_swiotlb_force_bounce(struct device *dev) +{ + return false; +} static inline void swiotlb_exit(void) { } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 7a88c34d0867..a92465b4eb12 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -496,7 +496,7 @@ size_t dma_direct_max_mapping_size(struct device *dev) { /* If SWIOTLB is active, use its maximum mapping size */ if (is_swiotlb_active(dev) && - (dma_addressing_limited(dev) || swiotlb_force == SWIOTLB_FORCE)) + (dma_addressing_limited(dev) || is_swiotlb_force_bounce(dev))) return swiotlb_max_mapping_size(dev); return SIZE_MAX; } diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 13e9e7158d94..4632b0f4f72e 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -87,7 +87,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dma_addr = phys_to_dma(dev, phys); - if (unlikely(swiotlb_force == SWIOTLB_FORCE)) + if (is_swiotlb_force_bounce(dev)) return swiotlb_map(dev, phys, size, dir, attrs); if (unlikely(!dma_capable(dev, dma_addr, size, true))) { diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index d8677d6637dd..04319dd22d28 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -179,6 +179,10 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, mem->end = mem->start + bytes; mem->index = 0; mem->late_alloc = late_alloc; + + if (swiotlb_force == SWIOTLB_FORCE) + mem->force_bounce = true; + spin_lock_init(&mem->lock); for (i = 0; i < mem->nslabs; i++) { mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i); -- cgit v1.2.3 From f4111e39a52aa5d5136d890bbd1aa87c1c8fe3bc Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:40 +0800 Subject: swiotlb: Add restricted DMA alloc/free support Add the functions, swiotlb_{alloc,free} and is_swiotlb_for_alloc to support the memory allocation from restricted DMA pool. The restricted DMA pool is preferred if available. Note that since coherent allocation needs remapping, one must set up another device coherent pool by shared-dma-pool and use dma_alloc_from_dev_coherent instead for atomic coherent allocation. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 26 ++++++++++++++++++++++++++ kernel/dma/direct.c | 49 +++++++++++++++++++++++++++++++++++++------------ kernel/dma/swiotlb.c | 38 ++++++++++++++++++++++++++++++++++++-- 3 files changed, 99 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index da348671b0d5..3b9454d1e498 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -85,6 +85,7 @@ extern enum swiotlb_force swiotlb_force; * @debugfs: The dentry to debugfs. * @late_alloc: %true if allocated using the page allocator * @force_bounce: %true if swiotlb bouncing is forced + * @for_alloc: %true if the pool is used for memory allocation */ struct io_tlb_mem { phys_addr_t start; @@ -96,6 +97,7 @@ struct io_tlb_mem { struct dentry *debugfs; bool late_alloc; bool force_bounce; + bool for_alloc; struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; @@ -158,4 +160,28 @@ static inline void swiotlb_adjust_size(unsigned long size) extern void swiotlb_print_info(void); extern void swiotlb_set_max_segment(unsigned int); +#ifdef CONFIG_DMA_RESTRICTED_POOL +struct page *swiotlb_alloc(struct device *dev, size_t size); +bool swiotlb_free(struct device *dev, struct page *page, size_t size); + +static inline bool is_swiotlb_for_alloc(struct device *dev) +{ + return dev->dma_io_tlb_mem->for_alloc; +} +#else +static inline struct page *swiotlb_alloc(struct device *dev, size_t size) +{ + return NULL; +} +static inline bool swiotlb_free(struct device *dev, struct page *page, + size_t size) +{ + return false; +} +static inline bool is_swiotlb_for_alloc(struct device *dev) +{ + return false; +} +#endif /* CONFIG_DMA_RESTRICTED_POOL */ + #endif /* __LINUX_SWIOTLB_H */ diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index a92465b4eb12..2de33e5d302b 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -75,6 +75,15 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit); } +static void __dma_direct_free_pages(struct device *dev, struct page *page, + size_t size) +{ + if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) && + swiotlb_free(dev, page, size)) + return; + dma_free_contiguous(dev, page, size); +} + static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp_t gfp) { @@ -86,6 +95,16 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, &phys_limit); + if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) && + is_swiotlb_for_alloc(dev)) { + page = swiotlb_alloc(dev, size); + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + __dma_direct_free_pages(dev, page, size); + return NULL; + } + return page; + } + page = dma_alloc_contiguous(dev, size, gfp); if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { dma_free_contiguous(dev, page, size); @@ -142,7 +161,7 @@ void *dma_direct_alloc(struct device *dev, size_t size, gfp |= __GFP_NOWARN; if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && - !force_dma_unencrypted(dev)) { + !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) { page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO); if (!page) return NULL; @@ -155,18 +174,23 @@ void *dma_direct_alloc(struct device *dev, size_t size, } if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) && - !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && - !dev_is_dma_coherent(dev)) + !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) && + !is_swiotlb_for_alloc(dev)) return arch_dma_alloc(dev, size, dma_handle, gfp, attrs); /* * Remapping or decrypting memory may block. If either is required and * we can't block, allocate the memory from the atomic pools. + * If restricted DMA (i.e., is_swiotlb_for_alloc) is required, one must + * set up another device coherent pool by shared-dma-pool and use + * dma_alloc_from_dev_coherent instead. */ if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) && !gfpflags_allow_blocking(gfp) && (force_dma_unencrypted(dev) || - (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev)))) + (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && + !dev_is_dma_coherent(dev))) && + !is_swiotlb_for_alloc(dev)) return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp); /* we always manually zero the memory once we are done */ @@ -237,7 +261,7 @@ out_encrypt_pages: return NULL; } out_free_pages: - dma_free_contiguous(dev, page, size); + __dma_direct_free_pages(dev, page, size); return NULL; } @@ -247,15 +271,15 @@ void dma_direct_free(struct device *dev, size_t size, unsigned int page_order = get_order(size); if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && - !force_dma_unencrypted(dev)) { + !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) { /* cpu_addr is a struct page cookie, not a kernel address */ dma_free_contiguous(dev, cpu_addr, size); return; } if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) && - !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && - !dev_is_dma_coherent(dev)) { + !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) && + !is_swiotlb_for_alloc(dev)) { arch_dma_free(dev, size, cpu_addr, dma_addr, attrs); return; } @@ -273,7 +297,7 @@ void dma_direct_free(struct device *dev, size_t size, else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED)) arch_dma_clear_uncached(cpu_addr, size); - dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size); + __dma_direct_free_pages(dev, dma_direct_to_page(dev, dma_addr), size); } struct page *dma_direct_alloc_pages(struct device *dev, size_t size, @@ -283,7 +307,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size, void *ret; if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) && - force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp)) + force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp) && + !is_swiotlb_for_alloc(dev)) return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp); page = __dma_direct_alloc_pages(dev, size, gfp); @@ -310,7 +335,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size, *dma_handle = phys_to_dma_direct(dev, page_to_phys(page)); return page; out_free_pages: - dma_free_contiguous(dev, page, size); + __dma_direct_free_pages(dev, page, size); return NULL; } @@ -329,7 +354,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, if (force_dma_unencrypted(dev)) set_memory_encrypted((unsigned long)vaddr, 1 << page_order); - dma_free_contiguous(dev, page, size); + __dma_direct_free_pages(dev, page, size); } #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 23b6df3a6ab7..44fc3d10f017 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -462,8 +462,9 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, index = wrap = wrap_index(mem, ALIGN(mem->index, stride)); do { - if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) != - (orig_addr & iotlb_align_mask)) { + if (orig_addr && + (slot_addr(tbl_dma_addr, index) & iotlb_align_mask) != + (orig_addr & iotlb_align_mask)) { index = wrap_index(mem, index + 1); continue; } @@ -702,3 +703,36 @@ static int __init swiotlb_create_default_debugfs(void) late_initcall(swiotlb_create_default_debugfs); #endif + +#ifdef CONFIG_DMA_RESTRICTED_POOL +struct page *swiotlb_alloc(struct device *dev, size_t size) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + phys_addr_t tlb_addr; + int index; + + if (!mem) + return NULL; + + index = swiotlb_find_slots(dev, 0, size); + if (index == -1) + return NULL; + + tlb_addr = slot_addr(mem->start, index); + + return pfn_to_page(PFN_DOWN(tlb_addr)); +} + +bool swiotlb_free(struct device *dev, struct page *page, size_t size) +{ + phys_addr_t tlb_addr = page_to_phys(page); + + if (!is_swiotlb_buffer(dev, tlb_addr)) + return false; + + swiotlb_release_slots(dev, tlb_addr); + + return true; +} + +#endif /* CONFIG_DMA_RESTRICTED_POOL */ -- cgit v1.2.3 From 0b84e4f8b793eb4045fd64f6f514165a7974cd16 Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:41 +0800 Subject: swiotlb: Add restricted DMA pool initialization Add the initialization function to create restricted DMA pools from matching reserved-memory nodes. Regardless of swiotlb setting, the restricted DMA pool is preferred if available. The restricted DMA pools provide a basic level of protection against the DMA overwriting buffer contents at unexpected times. However, to protect against general data leakage and system memory corruption, the system needs to provide a way to lock down the memory access, e.g., MPU. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 3 +- kernel/dma/Kconfig | 14 +++++++++ kernel/dma/swiotlb.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 92 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 3b9454d1e498..39284ff2a6cd 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -73,7 +73,8 @@ extern enum swiotlb_force swiotlb_force; * range check to see if the memory was in fact allocated by this * API. * @nslabs: The number of IO TLB blocks (in groups of 64) between @start and - * @end. This is command line adjustable via setup_io_tlb_npages. + * @end. For default swiotlb, this is command line adjustable via + * setup_io_tlb_npages. * @used: The number of used IO TLB block. * @list: The free list describing the number of free entries available * from each index. diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 77b405508743..3e961dc39634 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -80,6 +80,20 @@ config SWIOTLB bool select NEED_DMA_MAP_STATE +config DMA_RESTRICTED_POOL + bool "DMA Restricted Pool" + depends on OF && OF_RESERVED_MEM + select SWIOTLB + help + This enables support for restricted DMA pools which provide a level of + DMA memory protection on systems with limited hardware protection + capabilities, such as those lacking an IOMMU. + + For more information see + + and . + If unsure, say "n". + # # Should be selected if we can mmap non-coherent mappings to userspace. # The only thing that is really required is a way to set an uncached bit diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 44fc3d10f017..0ffbaae9fba2 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -39,6 +39,13 @@ #ifdef CONFIG_DEBUG_FS #include #endif +#ifdef CONFIG_DMA_RESTRICTED_POOL +#include +#include +#include +#include +#include +#endif #include #include @@ -735,4 +742,73 @@ bool swiotlb_free(struct device *dev, struct page *page, size_t size) return true; } +static int rmem_swiotlb_device_init(struct reserved_mem *rmem, + struct device *dev) +{ + struct io_tlb_mem *mem = rmem->priv; + unsigned long nslabs = rmem->size >> IO_TLB_SHIFT; + + /* + * Since multiple devices can share the same pool, the private data, + * io_tlb_mem struct, will be initialized by the first device attached + * to it. + */ + if (!mem) { + mem = kzalloc(struct_size(mem, slots, nslabs), GFP_KERNEL); + if (!mem) + return -ENOMEM; + + set_memory_decrypted((unsigned long)phys_to_virt(rmem->base), + rmem->size >> PAGE_SHIFT); + swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false); + mem->force_bounce = true; + mem->for_alloc = true; + + rmem->priv = mem; + + if (IS_ENABLED(CONFIG_DEBUG_FS)) { + mem->debugfs = + debugfs_create_dir(rmem->name, debugfs_dir); + swiotlb_create_debugfs_files(mem); + } + } + + dev->dma_io_tlb_mem = mem; + + return 0; +} + +static void rmem_swiotlb_device_release(struct reserved_mem *rmem, + struct device *dev) +{ + dev->dma_io_tlb_mem = io_tlb_default_mem; +} + +static const struct reserved_mem_ops rmem_swiotlb_ops = { + .device_init = rmem_swiotlb_device_init, + .device_release = rmem_swiotlb_device_release, +}; + +static int __init rmem_swiotlb_setup(struct reserved_mem *rmem) +{ + unsigned long node = rmem->fdt_node; + + if (of_get_flat_dt_prop(node, "reusable", NULL) || + of_get_flat_dt_prop(node, "linux,cma-default", NULL) || + of_get_flat_dt_prop(node, "linux,dma-default", NULL) || + of_get_flat_dt_prop(node, "no-map", NULL)) + return -EINVAL; + + if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) { + pr_err("Restricted DMA pool must be accessible within the linear mapping."); + return -EINVAL; + } + + rmem->ops = &rmem_swiotlb_ops; + pr_info("Reserved memory: created restricted DMA pool at %pa, size %ld MiB\n", + &rmem->base, (unsigned long)rmem->size / SZ_1M); + return 0; +} + +RESERVEDMEM_OF_DECLARE(dma, "restricted-dma-pool", rmem_swiotlb_setup); #endif /* CONFIG_DMA_RESTRICTED_POOL */ -- cgit v1.2.3 From fe364a7d95c24e07e9b3f2ab917f01d6d8330bba Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 12 Jul 2021 14:39:40 +0300 Subject: dmaengine: dw: Program xBAR hardware for Elkhart Lake Intel Elkhart Lake PSE DMA implementation is integrated with crossbar IP in order to serve more hardware than there are DMA request lines available. Due to this, program xBAR hardware to make flexible support of PSE peripheral. The Device-to-Device has not been tested and it's not supported by DMA Engine, but it's left in the code for the sake of documenting hardware features. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210712113940.42753-1-andriy.shevchenko@linux.intel.com Signed-off-by: Vinod Koul --- drivers/dma/dw/idma32.c | 138 ++++++++++++++++++++++++++++++++++- drivers/dma/dw/internal.h | 16 ++++ drivers/dma/dw/pci.c | 6 +- drivers/dma/dw/platform.c | 6 +- include/linux/platform_data/dma-dw.h | 3 + 5 files changed, 160 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/dw/idma32.c b/drivers/dma/dw/idma32.c index 3ce44de25d33..58f4078d83fe 100644 --- a/drivers/dma/dw/idma32.c +++ b/drivers/dma/dw/idma32.c @@ -1,15 +1,144 @@ // SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2013,2018 Intel Corporation +// Copyright (C) 2013,2018,2020-2021 Intel Corporation #include #include #include +#include +#include #include #include #include "internal.h" -static void idma32_initialize_chan(struct dw_dma_chan *dwc) +#define DMA_CTL_CH(x) (0x1000 + (x) * 4) +#define DMA_SRC_ADDR_FILLIN(x) (0x1100 + (x) * 4) +#define DMA_DST_ADDR_FILLIN(x) (0x1200 + (x) * 4) +#define DMA_XBAR_SEL(x) (0x1300 + (x) * 4) +#define DMA_REGACCESS_CHID_CFG (0x1400) + +#define CTL_CH_TRANSFER_MODE_MASK GENMASK(1, 0) +#define CTL_CH_TRANSFER_MODE_S2S 0 +#define CTL_CH_TRANSFER_MODE_S2D 1 +#define CTL_CH_TRANSFER_MODE_D2S 2 +#define CTL_CH_TRANSFER_MODE_D2D 3 +#define CTL_CH_RD_RS_MASK GENMASK(4, 3) +#define CTL_CH_WR_RS_MASK GENMASK(6, 5) +#define CTL_CH_RD_NON_SNOOP_BIT BIT(8) +#define CTL_CH_WR_NON_SNOOP_BIT BIT(9) + +#define XBAR_SEL_DEVID_MASK GENMASK(15, 0) +#define XBAR_SEL_RX_TX_BIT BIT(16) +#define XBAR_SEL_RX_TX_SHIFT 16 + +#define REGACCESS_CHID_MASK GENMASK(2, 0) + +static unsigned int idma32_get_slave_devfn(struct dw_dma_chan *dwc) +{ + struct device *slave = dwc->chan.slave; + + if (!slave || !dev_is_pci(slave)) + return 0; + + return to_pci_dev(slave)->devfn; +} + +static void idma32_initialize_chan_xbar(struct dw_dma_chan *dwc) +{ + struct dw_dma *dw = to_dw_dma(dwc->chan.device); + void __iomem *misc = __dw_regs(dw); + u32 cfghi = 0, cfglo = 0; + u8 dst_id, src_id; + u32 value; + + /* DMA Channel ID Configuration register must be programmed first */ + value = readl(misc + DMA_REGACCESS_CHID_CFG); + + value &= ~REGACCESS_CHID_MASK; + value |= dwc->chan.chan_id; + + writel(value, misc + DMA_REGACCESS_CHID_CFG); + + /* Configure channel attributes */ + value = readl(misc + DMA_CTL_CH(dwc->chan.chan_id)); + + value &= ~(CTL_CH_RD_NON_SNOOP_BIT | CTL_CH_WR_NON_SNOOP_BIT); + value &= ~(CTL_CH_RD_RS_MASK | CTL_CH_WR_RS_MASK); + value &= ~CTL_CH_TRANSFER_MODE_MASK; + + switch (dwc->direction) { + case DMA_MEM_TO_DEV: + value |= CTL_CH_TRANSFER_MODE_D2S; + value |= CTL_CH_WR_NON_SNOOP_BIT; + break; + case DMA_DEV_TO_MEM: + value |= CTL_CH_TRANSFER_MODE_S2D; + value |= CTL_CH_RD_NON_SNOOP_BIT; + break; + default: + /* + * Memory-to-Memory and Device-to-Device are ignored for now. + * + * For Memory-to-Memory transfers we would need to set mode + * and disable snooping on both sides. + */ + return; + } + + writel(value, misc + DMA_CTL_CH(dwc->chan.chan_id)); + + /* Configure crossbar selection */ + value = readl(misc + DMA_XBAR_SEL(dwc->chan.chan_id)); + + /* DEVFN selection */ + value &= ~XBAR_SEL_DEVID_MASK; + value |= idma32_get_slave_devfn(dwc); + + switch (dwc->direction) { + case DMA_MEM_TO_DEV: + value |= XBAR_SEL_RX_TX_BIT; + break; + case DMA_DEV_TO_MEM: + value &= ~XBAR_SEL_RX_TX_BIT; + break; + default: + /* Memory-to-Memory and Device-to-Device are ignored for now */ + return; + } + + writel(value, misc + DMA_XBAR_SEL(dwc->chan.chan_id)); + + /* Configure DMA channel low and high registers */ + switch (dwc->direction) { + case DMA_MEM_TO_DEV: + dst_id = dwc->chan.chan_id; + src_id = dwc->dws.src_id; + break; + case DMA_DEV_TO_MEM: + dst_id = dwc->dws.dst_id; + src_id = dwc->chan.chan_id; + break; + default: + /* Memory-to-Memory and Device-to-Device are ignored for now */ + return; + } + + /* Set default burst alignment */ + cfglo |= IDMA32C_CFGL_DST_BURST_ALIGN | IDMA32C_CFGL_SRC_BURST_ALIGN; + + /* Low 4 bits of the request lines */ + cfghi |= IDMA32C_CFGH_DST_PER(dst_id & 0xf); + cfghi |= IDMA32C_CFGH_SRC_PER(src_id & 0xf); + + /* Request line extension (2 bits) */ + cfghi |= IDMA32C_CFGH_DST_PER_EXT(dst_id >> 4 & 0x3); + cfghi |= IDMA32C_CFGH_SRC_PER_EXT(src_id >> 4 & 0x3); + + channel_writel(dwc, CFG_LO, cfglo); + channel_writel(dwc, CFG_HI, cfghi); +} + +static void idma32_initialize_chan_generic(struct dw_dma_chan *dwc) { u32 cfghi = 0; u32 cfglo = 0; @@ -134,7 +263,10 @@ int idma32_dma_probe(struct dw_dma_chip *chip) return -ENOMEM; /* Channel operations */ - dw->initialize_chan = idma32_initialize_chan; + if (chip->pdata->quirks & DW_DMA_QUIRK_XBAR_PRESENT) + dw->initialize_chan = idma32_initialize_chan_xbar; + else + dw->initialize_chan = idma32_initialize_chan_generic; dw->suspend_chan = idma32_suspend_chan; dw->resume_chan = idma32_resume_chan; dw->prepare_ctllo = idma32_prepare_ctllo; diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h index 2e1c52eefdeb..563ce73488db 100644 --- a/drivers/dma/dw/internal.h +++ b/drivers/dma/dw/internal.h @@ -74,4 +74,20 @@ static __maybe_unused const struct dw_dma_chip_pdata idma32_chip_pdata = { .remove = idma32_dma_remove, }; +static const struct dw_dma_platform_data xbar_pdata = { + .nr_channels = 8, + .chan_allocation_order = CHAN_ALLOCATION_ASCENDING, + .chan_priority = CHAN_PRIORITY_ASCENDING, + .block_size = 131071, + .nr_masters = 1, + .data_width = {4}, + .quirks = DW_DMA_QUIRK_XBAR_PRESENT, +}; + +static __maybe_unused const struct dw_dma_chip_pdata xbar_chip_pdata = { + .pdata = &xbar_pdata, + .probe = idma32_dma_probe, + .remove = idma32_dma_remove, +}; + #endif /* _DMA_DW_INTERNAL_H */ diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index 1142aa6f8c4a..26a3f926da02 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -120,9 +120,9 @@ static const struct pci_device_id dw_pci_id_table[] = { { PCI_VDEVICE(INTEL, 0x22c0), (kernel_ulong_t)&dw_dma_chip_pdata }, /* Elkhart Lake iDMA 32-bit (PSE DMA) */ - { PCI_VDEVICE(INTEL, 0x4bb4), (kernel_ulong_t)&idma32_chip_pdata }, - { PCI_VDEVICE(INTEL, 0x4bb5), (kernel_ulong_t)&idma32_chip_pdata }, - { PCI_VDEVICE(INTEL, 0x4bb6), (kernel_ulong_t)&idma32_chip_pdata }, + { PCI_VDEVICE(INTEL, 0x4bb4), (kernel_ulong_t)&xbar_chip_pdata }, + { PCI_VDEVICE(INTEL, 0x4bb5), (kernel_ulong_t)&xbar_chip_pdata }, + { PCI_VDEVICE(INTEL, 0x4bb6), (kernel_ulong_t)&xbar_chip_pdata }, /* Haswell */ { PCI_VDEVICE(INTEL, 0x9c60), (kernel_ulong_t)&dw_dma_chip_pdata }, diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index 0585d749d935..246118955877 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -149,9 +149,9 @@ static const struct acpi_device_id dw_dma_acpi_id_table[] = { { "808622C0", (kernel_ulong_t)&dw_dma_chip_pdata }, /* Elkhart Lake iDMA 32-bit (PSE DMA) */ - { "80864BB4", (kernel_ulong_t)&idma32_chip_pdata }, - { "80864BB5", (kernel_ulong_t)&idma32_chip_pdata }, - { "80864BB6", (kernel_ulong_t)&idma32_chip_pdata }, + { "80864BB4", (kernel_ulong_t)&xbar_chip_pdata }, + { "80864BB5", (kernel_ulong_t)&xbar_chip_pdata }, + { "80864BB6", (kernel_ulong_t)&xbar_chip_pdata }, { } }; diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index b34a094b2258..b11b0c8bc5da 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -52,6 +52,7 @@ struct dw_dma_slave { * @max_burst: Maximum value of burst transaction size supported by hardware * per channel (in units of CTL.SRC_TR_WIDTH/CTL.DST_TR_WIDTH). * @protctl: Protection control signals setting per channel. + * @quirks: Optional platform quirks. */ struct dw_dma_platform_data { unsigned int nr_channels; @@ -71,6 +72,8 @@ struct dw_dma_platform_data { #define CHAN_PROTCTL_CACHEABLE BIT(2) #define CHAN_PROTCTL_MASK GENMASK(2, 0) unsigned char protctl; +#define DW_DMA_QUIRK_XBAR_PRESENT BIT(0) + unsigned int quirks; }; #endif /* _PLATFORM_DATA_DMA_DW_H */ -- cgit v1.2.3 From f84d866ab43fcc27b417c86357d6534f157a3d89 Mon Sep 17 00:00:00 2001 From: Mason Zhang Date: Tue, 13 Jul 2021 19:40:49 +0800 Subject: spi: mediatek: add tick_delay support This patch support tick_delay setting, some users need use high-speed spi speed, which can use tick_delay to tuning spi clk timing. Signed-off-by: Mason Zhang Link: https://lore.kernel.org/r/20210713114048.29509-1-mason.zhang@mediatek.com Signed-off-by: Mark Brown --- drivers/spi/spi-mt65xx.c | 11 ++++++++++- include/linux/platform_data/spi-mt65xx.h | 1 + 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 097625d7915e..b34fbc913fd6 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -42,8 +42,9 @@ #define SPI_CFG1_CS_IDLE_OFFSET 0 #define SPI_CFG1_PACKET_LOOP_OFFSET 8 #define SPI_CFG1_PACKET_LENGTH_OFFSET 16 -#define SPI_CFG1_GET_TICK_DLY_OFFSET 30 +#define SPI_CFG1_GET_TICK_DLY_OFFSET 29 +#define SPI_CFG1_GET_TICK_DLY_MASK 0xe0000000 #define SPI_CFG1_CS_IDLE_MASK 0xff #define SPI_CFG1_PACKET_LOOP_MASK 0xff00 #define SPI_CFG1_PACKET_LENGTH_MASK 0x3ff0000 @@ -152,6 +153,7 @@ static const struct mtk_spi_compatible mt6893_compat = { */ static const struct mtk_chip_config mtk_default_chip_info = { .sample_sel = 0, + .tick_delay = 0, }; static const struct of_device_id mtk_spi_of_match[] = { @@ -275,6 +277,13 @@ static int mtk_spi_prepare_message(struct spi_master *master, writel(mdata->pad_sel[spi->chip_select], mdata->base + SPI_PAD_SEL_REG); + /* tick delay */ + reg_val = readl(mdata->base + SPI_CFG1_REG); + reg_val &= ~SPI_CFG1_GET_TICK_DLY_MASK; + reg_val |= ((chip_config->tick_delay & 0x7) + << SPI_CFG1_GET_TICK_DLY_OFFSET); + writel(reg_val, mdata->base + SPI_CFG1_REG); + return 0; } diff --git a/include/linux/platform_data/spi-mt65xx.h b/include/linux/platform_data/spi-mt65xx.h index 65fd5ffd257c..f0db674f07b8 100644 --- a/include/linux/platform_data/spi-mt65xx.h +++ b/include/linux/platform_data/spi-mt65xx.h @@ -12,5 +12,6 @@ /* Board specific platform_data */ struct mtk_chip_config { u32 sample_sel; + u32 tick_delay; }; #endif -- cgit v1.2.3 From 5c2c85315948c42c6c0258cf9bad596acaa79043 Mon Sep 17 00:00:00 2001 From: Richard Laing Date: Thu, 15 Jul 2021 09:18:05 +1200 Subject: bus: mhi: pci-generic: configurable network interface MRU The MRU value used by the MHI MBIM network interface affects the throughput performance of the interface. Different modem models use different default MRU sizes based on their bandwidth capabilities. Large values generally result in higher throughput for larger packet sizes. In addition if the MRU used by the MHI device is larger than that specified in the MHI net device the data is fragmented and needs to be re-assembled which generates a (single) warning message about the fragmented packets. Setting the MRU on both ends avoids the extra processing to re-assemble the packets. This patch allows the documented MRU for a modem to be automatically set as the MHI net device MRU avoiding fragmentation and improving throughput performance. Signed-off-by: Richard Laing Signed-off-by: David S. Miller --- drivers/bus/mhi/pci_generic.c | 6 +++++- drivers/net/mhi/net.c | 1 + drivers/net/mhi/proto_mbim.c | 4 +++- include/linux/mhi.h | 2 ++ 4 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/mhi/pci_generic.c b/drivers/bus/mhi/pci_generic.c index ca3bc40427f8..19413daa0917 100644 --- a/drivers/bus/mhi/pci_generic.c +++ b/drivers/bus/mhi/pci_generic.c @@ -32,6 +32,7 @@ * @edl: emergency download mode firmware path (if any) * @bar_num: PCI base address register to use for MHI MMIO register space * @dma_data_width: DMA transfer word size (32 or 64 bits) + * @mru_default: default MRU size for MBIM network packets */ struct mhi_pci_dev_info { const struct mhi_controller_config *config; @@ -40,6 +41,7 @@ struct mhi_pci_dev_info { const char *edl; unsigned int bar_num; unsigned int dma_data_width; + unsigned int mru_default; }; #define MHI_CHANNEL_CONFIG_UL(ch_num, ch_name, el_count, ev_ring) \ @@ -251,7 +253,8 @@ static const struct mhi_pci_dev_info mhi_qcom_sdx55_info = { .edl = "qcom/sdx55m/edl.mbn", .config = &modem_qcom_v1_mhiv_config, .bar_num = MHI_PCI_DEFAULT_BAR_NUM, - .dma_data_width = 32 + .dma_data_width = 32, + .mru_default = 32768 }; static const struct mhi_pci_dev_info mhi_qcom_sdx24_info = { @@ -643,6 +646,7 @@ static int mhi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) mhi_cntrl->wake_get = mhi_pci_wake_get_nop; mhi_cntrl->wake_put = mhi_pci_wake_put_nop; mhi_cntrl->wake_toggle = mhi_pci_wake_toggle_nop; + mhi_cntrl->mru = info->mru_default; err = mhi_pci_claim(mhi_cntrl, info->bar_num, DMA_BIT_MASK(info->dma_data_width)); if (err) diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index e60e38c1f09d..a5a2aa19bb91 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -329,6 +329,7 @@ static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id, mhi_netdev->mdev = mhi_dev; mhi_netdev->skbagg_head = NULL; mhi_netdev->proto = info->proto; + mhi_netdev->mru = mhi_dev->mhi_cntrl->mru; INIT_DELAYED_WORK(&mhi_netdev->rx_refill, mhi_net_rx_refill_work); u64_stats_init(&mhi_netdev->stats.rx_syncp); diff --git a/drivers/net/mhi/proto_mbim.c b/drivers/net/mhi/proto_mbim.c index bf1ad863237d..f1cc7f35bb85 100644 --- a/drivers/net/mhi/proto_mbim.c +++ b/drivers/net/mhi/proto_mbim.c @@ -292,7 +292,9 @@ static int mbim_init(struct mhi_net_dev *mhi_netdev) ndev->needed_headroom = sizeof(struct mbim_tx_hdr); ndev->mtu = MHI_MBIM_DEFAULT_MTU; - mhi_netdev->mru = MHI_MBIM_DEFAULT_MRU; + + if (!mhi_netdev->mru) + mhi_netdev->mru = MHI_MBIM_DEFAULT_MRU; return 0; } diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 944aa3aa3035..beb918328eef 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -356,6 +356,7 @@ struct mhi_controller_config { * @fbc_download: MHI host needs to do complete image transfer (optional) * @wake_set: Device wakeup set flag * @irq_flags: irq flags passed to request_irq (optional) + * @mru: the default MRU for the MHI device * * Fields marked as (required) need to be populated by the controller driver * before calling mhi_register_controller(). For the fields marked as (optional) @@ -448,6 +449,7 @@ struct mhi_controller { bool fbc_download; bool wake_set; unsigned long irq_flags; + u32 mru; }; /** -- cgit v1.2.3 From e48bf29cf9d6d60d810e2af71e54b71a324094e0 Mon Sep 17 00:00:00 2001 From: Ye Xiang Date: Sun, 13 Jun 2021 11:25:07 +0800 Subject: HID: intel-ish-hid: use async resume function ISH IPC driver uses asynchronous workqueue to do resume now, but there is a potential timing issue: when child devices resume before bus driver, it will cause child devices resume failed and cannot be recovered until reboot. The current implementation in this case do wait for IPC to resume but fail to accommodate for a case when there is no ISH reboot and soft resume is taking time. This issue is apparent on Tiger Lake platform with 5.11.13 kernel when doing suspend to idle then resume(s0ix) test. To resolve this issue, we change ISHTP HID client to use asynchronous resume callback too. In the asynchronous resume callback, it waits for the ISHTP resume done event, and then notify ISHTP HID client link ready. Signed-off-by: Ye Xiang Acked-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina --- drivers/hid/intel-ish-hid/ishtp-hid-client.c | 15 +++++++++++++- drivers/hid/intel-ish-hid/ishtp-hid.h | 1 + drivers/hid/intel-ish-hid/ishtp/bus.c | 29 +++++++++++++++++++++------- include/linux/intel-ish-client-if.h | 2 ++ 4 files changed, 39 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index 6b1fa971b33e..91bf4d01e91a 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -784,6 +784,17 @@ static void hid_ishtp_cl_reset_handler(struct work_struct *work) } } +static void hid_ishtp_cl_resume_handler(struct work_struct *work) +{ + struct ishtp_cl_data *client_data = container_of(work, struct ishtp_cl_data, resume_work); + struct ishtp_cl *hid_ishtp_cl = client_data->hid_ishtp_cl; + + if (ishtp_wait_resume(ishtp_get_ishtp_device(hid_ishtp_cl))) { + client_data->suspended = false; + wake_up_interruptible(&client_data->ishtp_resume_wait); + } +} + ishtp_print_log ishtp_hid_print_trace; /** @@ -822,6 +833,8 @@ static int hid_ishtp_cl_probe(struct ishtp_cl_device *cl_device) init_waitqueue_head(&client_data->ishtp_resume_wait); INIT_WORK(&client_data->work, hid_ishtp_cl_reset_handler); + INIT_WORK(&client_data->resume_work, hid_ishtp_cl_resume_handler); + ishtp_hid_print_trace = ishtp_trace_callback(cl_device); @@ -921,7 +934,7 @@ static int hid_ishtp_cl_resume(struct device *device) hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__, hid_ishtp_cl); - client_data->suspended = false; + schedule_work(&client_data->resume_work); return 0; } diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.h b/drivers/hid/intel-ish-hid/ishtp-hid.h index f88443a7d935..6a5cc11aefd8 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid.h +++ b/drivers/hid/intel-ish-hid/ishtp-hid.h @@ -135,6 +135,7 @@ struct ishtp_cl_data { int multi_packet_cnt; struct work_struct work; + struct work_struct resume_work; struct ishtp_cl_device *cl_device; }; diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index f0802b047ed8..aa2c51624012 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -314,13 +314,6 @@ static int ishtp_cl_device_resume(struct device *dev) if (!device) return 0; - /* - * When ISH needs hard reset, it is done asynchrnously, hence bus - * resume will be called before full ISH resume - */ - if (device->ishtp_dev->resume_flag) - return 0; - driver = to_ishtp_cl_driver(dev->driver); if (driver && driver->driver.pm) { if (driver->driver.pm->resume) @@ -849,6 +842,28 @@ struct device *ishtp_device(struct ishtp_cl_device *device) } EXPORT_SYMBOL(ishtp_device); +/** + * ishtp_wait_resume() - Wait for IPC resume + * + * Wait for IPC resume + * + * Return: resume complete or not + */ +bool ishtp_wait_resume(struct ishtp_device *dev) +{ + /* 50ms to get resume response */ + #define WAIT_FOR_RESUME_ACK_MS 50 + + /* Waiting to get resume response */ + if (dev->resume_flag) + wait_event_interruptible_timeout(dev->resume_wait, + !dev->resume_flag, + msecs_to_jiffies(WAIT_FOR_RESUME_ACK_MS)); + + return (!dev->resume_flag); +} +EXPORT_SYMBOL_GPL(ishtp_wait_resume); + /** * ishtp_get_pci_device() - Return PCI device dev pointer * This interface is used to return PCI device pointer diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 25e2b4e80502..aee8ff4739b1 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -81,6 +81,8 @@ int ishtp_register_event_cb(struct ishtp_cl_device *device, /* Get the device * from ishtp device instance */ struct device *ishtp_device(struct ishtp_cl_device *cl_device); +/* wait for IPC resume */ +bool ishtp_wait_resume(struct ishtp_device *dev); /* Trace interface for clients */ ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device); /* Get device pointer of PCI device for DMA acces */ -- cgit v1.2.3 From b00628b1c7d595ae5b544e059c27b1f5828314b4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 14 Jul 2021 17:54:09 -0700 Subject: bpf: Introduce bpf timers. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce 'struct bpf_timer { __u64 :64; __u64 :64; };' that can be embedded in hash/array/lru maps as a regular field and helpers to operate on it: // Initialize the timer. // First 4 bits of 'flags' specify clockid. // Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, int flags); // Configure the timer to call 'callback_fn' static function. long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn); // Arm the timer to expire 'nsec' nanoseconds from the current time. long bpf_timer_start(struct bpf_timer *timer, u64 nsec, u64 flags); // Cancel the timer and wait for callback_fn to finish if it was running. long bpf_timer_cancel(struct bpf_timer *timer); Here is how BPF program might look like: struct map_elem { int counter; struct bpf_timer timer; }; struct { __uint(type, BPF_MAP_TYPE_HASH); __uint(max_entries, 1000); __type(key, int); __type(value, struct map_elem); } hmap SEC(".maps"); static int timer_cb(void *map, int *key, struct map_elem *val); /* val points to particular map element that contains bpf_timer. */ SEC("fentry/bpf_fentry_test1") int BPF_PROG(test1, int a) { struct map_elem *val; int key = 0; val = bpf_map_lookup_elem(&hmap, &key); if (val) { bpf_timer_init(&val->timer, &hmap, CLOCK_REALTIME); bpf_timer_set_callback(&val->timer, timer_cb); bpf_timer_start(&val->timer, 1000 /* call timer_cb2 in 1 usec */, 0); } } This patch adds helper implementations that rely on hrtimers to call bpf functions as timers expire. The following patches add necessary safety checks. Only programs with CAP_BPF are allowed to use bpf_timer. The amount of timers used by the program is constrained by the memcg recorded at map creation time. The bpf_timer_init() helper needs explicit 'map' argument because inner maps are dynamic and not known at load time. While the bpf_timer_set_callback() is receiving hidden 'aux->prog' argument supplied by the verifier. The prog pointer is needed to do refcnting of bpf program to make sure that program doesn't get freed while the timer is armed. This approach relies on "user refcnt" scheme used in prog_array that stores bpf programs for bpf_tail_call. The bpf_timer_set_callback() will increment the prog refcnt which is paired with bpf_timer_cancel() that will drop the prog refcnt. The ops->map_release_uref is responsible for cancelling the timers and dropping prog refcnt when user space reference to a map reaches zero. This uref approach is done to make sure that Ctrl-C of user space process will not leave timers running forever unless the user space explicitly pinned a map that contained timers in bpffs. bpf_timer_init() and bpf_timer_set_callback() will return -EPERM if map doesn't have user references (is not held by open file descriptor from user space and not pinned in bpffs). The bpf_map_delete_elem() and bpf_map_update_elem() operations cancel and free the timer if given map element had it allocated. "bpftool map update" command can be used to cancel timers. The 'struct bpf_timer' is explicitly __attribute__((aligned(8))) because '__u64 :64' has 1 byte alignment of 8 byte padding. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210715005417.78572-4-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 3 + include/uapi/linux/bpf.h | 73 ++++++++++ kernel/bpf/helpers.c | 324 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 109 ++++++++++++++ kernel/trace/bpf_trace.c | 2 +- scripts/bpf_doc.py | 2 + tools/include/uapi/linux/bpf.h | 73 ++++++++++ 7 files changed, 585 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4afbff308ca3..125240b7cefb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -168,6 +168,7 @@ struct bpf_map { u32 max_entries; u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ + int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; @@ -221,6 +222,7 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); +void bpf_timer_cancel_and_free(void *timer); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; @@ -314,6 +316,7 @@ enum bpf_arg_type { ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ + ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ __BPF_ARG_TYPE_MAX, }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bafb6282032b..3544ec5234f0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4777,6 +4777,70 @@ union bpf_attr { * Execute close syscall for given FD. * Return * A syscall result. + * + * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags) + * Description + * Initialize the timer. + * First 4 bits of *flags* specify clockid. + * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. + * All other bits of *flags* are reserved. + * The verifier will reject the program if *timer* is not from + * the same *map*. + * Return + * 0 on success. + * **-EBUSY** if *timer* is already initialized. + * **-EINVAL** if invalid *flags* are passed. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn) + * Description + * Configure the timer to call *callback_fn* static function. + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags) + * Description + * Set timer expiration N nanoseconds from the current time. The + * configured callback will be invoked in soft irq context on some cpu + * and will not repeat unless another bpf_timer_start() is made. + * In such case the next invocation can migrate to a different cpu. + * Since struct bpf_timer is a field inside map element the map + * owns the timer. The bpf_timer_set_callback() will increment refcnt + * of BPF program to make sure that callback_fn code stays valid. + * When user space reference to a map reaches zero all timers + * in a map are cancelled and corresponding program's refcnts are + * decremented. This is done to make sure that Ctrl-C of a user + * process doesn't leave any timers running. If map is pinned in + * bpffs the callback_fn can re-arm itself indefinitely. + * bpf_map_update/delete_elem() helpers and user space sys_bpf commands + * cancel and free the timer in the given map element. + * The map can contain timers that invoke callback_fn-s from different + * programs. The same callback_fn can serve different timers from + * different maps if key/value layout matches across maps. + * Every bpf_timer_set_callback() can have different callback_fn. + * + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier + * or invalid *flags* are passed. + * + * long bpf_timer_cancel(struct bpf_timer *timer) + * Description + * Cancel the timer and wait for callback_fn to finish if it was running. + * Return + * 0 if the timer was not active. + * 1 if the timer was active. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its + * own timer which would have led to a deadlock otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4948,6 +5012,10 @@ union bpf_attr { FN(sys_bpf), \ FN(btf_find_by_name_kind), \ FN(sys_close), \ + FN(timer_init), \ + FN(timer_set_callback), \ + FN(timer_start), \ + FN(timer_cancel), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -6074,6 +6142,11 @@ struct bpf_spin_lock { __u32 val; }; +struct bpf_timer { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 38be3cfc2f58..74b16593983d 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -999,6 +999,322 @@ const struct bpf_func_proto bpf_snprintf_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +/* BPF map elements can contain 'struct bpf_timer'. + * Such map owns all of its BPF timers. + * 'struct bpf_timer' is allocated as part of map element allocation + * and it's zero initialized. + * That space is used to keep 'struct bpf_timer_kern'. + * bpf_timer_init() allocates 'struct bpf_hrtimer', inits hrtimer, and + * remembers 'struct bpf_map *' pointer it's part of. + * bpf_timer_set_callback() increments prog refcnt and assign bpf callback_fn. + * bpf_timer_start() arms the timer. + * If user space reference to a map goes to zero at this point + * ops->map_release_uref callback is responsible for cancelling the timers, + * freeing their memory, and decrementing prog's refcnts. + * bpf_timer_cancel() cancels the timer and decrements prog's refcnt. + * Inner maps can contain bpf timers as well. ops->map_release_uref is + * freeing the timers when inner map is replaced or deleted by user space. + */ +struct bpf_hrtimer { + struct hrtimer timer; + struct bpf_map *map; + struct bpf_prog *prog; + void __rcu *callback_fn; + void *value; +}; + +/* the actual struct hidden inside uapi struct bpf_timer */ +struct bpf_timer_kern { + struct bpf_hrtimer *timer; + /* bpf_spin_lock is used here instead of spinlock_t to make + * sure that it always fits into space resereved by struct bpf_timer + * regardless of LOCKDEP and spinlock debug flags. + */ + struct bpf_spin_lock lock; +} __attribute__((aligned(8))); + +static DEFINE_PER_CPU(struct bpf_hrtimer *, hrtimer_running); + +static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) +{ + struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer); + struct bpf_map *map = t->map; + void *value = t->value; + void *callback_fn; + void *key; + u32 idx; + int ret; + + callback_fn = rcu_dereference_check(t->callback_fn, rcu_read_lock_bh_held()); + if (!callback_fn) + goto out; + + /* bpf_timer_cb() runs in hrtimer_run_softirq. It doesn't migrate and + * cannot be preempted by another bpf_timer_cb() on the same cpu. + * Remember the timer this callback is servicing to prevent + * deadlock if callback_fn() calls bpf_timer_cancel() or + * bpf_map_delete_elem() on the same timer. + */ + this_cpu_write(hrtimer_running, t); + if (map->map_type == BPF_MAP_TYPE_ARRAY) { + struct bpf_array *array = container_of(map, struct bpf_array, map); + + /* compute the key */ + idx = ((char *)value - array->value) / array->elem_size; + key = &idx; + } else { /* hash or lru */ + key = value - round_up(map->key_size, 8); + } + + ret = BPF_CAST_CALL(callback_fn)((u64)(long)map, + (u64)(long)key, + (u64)(long)value, 0, 0); + WARN_ON(ret != 0); /* Next patch moves this check into the verifier */ + + this_cpu_write(hrtimer_running, NULL); +out: + return HRTIMER_NORESTART; +} + +BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map, + u64, flags) +{ + clockid_t clockid = flags & (MAX_CLOCKS - 1); + struct bpf_hrtimer *t; + int ret = 0; + + BUILD_BUG_ON(MAX_CLOCKS != 16); + BUILD_BUG_ON(sizeof(struct bpf_timer_kern) > sizeof(struct bpf_timer)); + BUILD_BUG_ON(__alignof__(struct bpf_timer_kern) != __alignof__(struct bpf_timer)); + + if (in_nmi()) + return -EOPNOTSUPP; + + if (flags >= MAX_CLOCKS || + /* similar to timerfd except _ALARM variants are not supported */ + (clockid != CLOCK_MONOTONIC && + clockid != CLOCK_REALTIME && + clockid != CLOCK_BOOTTIME)) + return -EINVAL; + __bpf_spin_lock_irqsave(&timer->lock); + t = timer->timer; + if (t) { + ret = -EBUSY; + goto out; + } + if (!atomic64_read(&map->usercnt)) { + /* maps with timers must be either held by user space + * or pinned in bpffs. + */ + ret = -EPERM; + goto out; + } + /* allocate hrtimer via map_kmalloc to use memcg accounting */ + t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node); + if (!t) { + ret = -ENOMEM; + goto out; + } + t->value = (void *)timer - map->timer_off; + t->map = map; + t->prog = NULL; + rcu_assign_pointer(t->callback_fn, NULL); + hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT); + t->timer.function = bpf_timer_cb; + timer->timer = t; +out: + __bpf_spin_unlock_irqrestore(&timer->lock); + return ret; +} + +static const struct bpf_func_proto bpf_timer_init_proto = { + .func = bpf_timer_init, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_timer_set_callback, struct bpf_timer_kern *, timer, void *, callback_fn, + struct bpf_prog_aux *, aux) +{ + struct bpf_prog *prev, *prog = aux->prog; + struct bpf_hrtimer *t; + int ret = 0; + + if (in_nmi()) + return -EOPNOTSUPP; + __bpf_spin_lock_irqsave(&timer->lock); + t = timer->timer; + if (!t) { + ret = -EINVAL; + goto out; + } + if (!atomic64_read(&t->map->usercnt)) { + /* maps with timers must be either held by user space + * or pinned in bpffs. Otherwise timer might still be + * running even when bpf prog is detached and user space + * is gone, since map_release_uref won't ever be called. + */ + ret = -EPERM; + goto out; + } + prev = t->prog; + if (prev != prog) { + /* Bump prog refcnt once. Every bpf_timer_set_callback() + * can pick different callback_fn-s within the same prog. + */ + prog = bpf_prog_inc_not_zero(prog); + if (IS_ERR(prog)) { + ret = PTR_ERR(prog); + goto out; + } + if (prev) + /* Drop prev prog refcnt when swapping with new prog */ + bpf_prog_put(prev); + t->prog = prog; + } + rcu_assign_pointer(t->callback_fn, callback_fn); +out: + __bpf_spin_unlock_irqrestore(&timer->lock); + return ret; +} + +static const struct bpf_func_proto bpf_timer_set_callback_proto = { + .func = bpf_timer_set_callback, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, + .arg2_type = ARG_PTR_TO_FUNC, +}; + +BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, flags) +{ + struct bpf_hrtimer *t; + int ret = 0; + + if (in_nmi()) + return -EOPNOTSUPP; + if (flags) + return -EINVAL; + __bpf_spin_lock_irqsave(&timer->lock); + t = timer->timer; + if (!t || !t->prog) { + ret = -EINVAL; + goto out; + } + hrtimer_start(&t->timer, ns_to_ktime(nsecs), HRTIMER_MODE_REL_SOFT); +out: + __bpf_spin_unlock_irqrestore(&timer->lock); + return ret; +} + +static const struct bpf_func_proto bpf_timer_start_proto = { + .func = bpf_timer_start, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + +static void drop_prog_refcnt(struct bpf_hrtimer *t) +{ + struct bpf_prog *prog = t->prog; + + if (prog) { + bpf_prog_put(prog); + t->prog = NULL; + rcu_assign_pointer(t->callback_fn, NULL); + } +} + +BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer) +{ + struct bpf_hrtimer *t; + int ret = 0; + + if (in_nmi()) + return -EOPNOTSUPP; + __bpf_spin_lock_irqsave(&timer->lock); + t = timer->timer; + if (!t) { + ret = -EINVAL; + goto out; + } + if (this_cpu_read(hrtimer_running) == t) { + /* If bpf callback_fn is trying to bpf_timer_cancel() + * its own timer the hrtimer_cancel() will deadlock + * since it waits for callback_fn to finish + */ + ret = -EDEADLK; + goto out; + } + drop_prog_refcnt(t); +out: + __bpf_spin_unlock_irqrestore(&timer->lock); + /* Cancel the timer and wait for associated callback to finish + * if it was running. + */ + ret = ret ?: hrtimer_cancel(&t->timer); + return ret; +} + +static const struct bpf_func_proto bpf_timer_cancel_proto = { + .func = bpf_timer_cancel, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_TIMER, +}; + +/* This function is called by map_delete/update_elem for individual element and + * by ops->map_release_uref when the user space reference to a map reaches zero. + */ +void bpf_timer_cancel_and_free(void *val) +{ + struct bpf_timer_kern *timer = val; + struct bpf_hrtimer *t; + + /* Performance optimization: read timer->timer without lock first. */ + if (!READ_ONCE(timer->timer)) + return; + + __bpf_spin_lock_irqsave(&timer->lock); + /* re-read it under lock */ + t = timer->timer; + if (!t) + goto out; + drop_prog_refcnt(t); + /* The subsequent bpf_timer_start/cancel() helpers won't be able to use + * this timer, since it won't be initialized. + */ + timer->timer = NULL; +out: + __bpf_spin_unlock_irqrestore(&timer->lock); + if (!t) + return; + /* Cancel the timer and wait for callback to complete if it was running. + * If hrtimer_cancel() can be safely called it's safe to call kfree(t) + * right after for both preallocated and non-preallocated maps. + * The timer->timer = NULL was already done and no code path can + * see address 't' anymore. + * + * Check that bpf_map_delete/update_elem() wasn't called from timer + * callback_fn. In such case don't call hrtimer_cancel() (since it will + * deadlock) and don't call hrtimer_try_to_cancel() (since it will just + * return -1). Though callback_fn is still running on this cpu it's + * safe to do kfree(t) because bpf_timer_cb() read everything it needed + * from 't'. The bpf subprog callback_fn won't be able to access 't', + * since timer->timer = NULL was already done. The timer will be + * effectively cancelled because bpf_timer_cb() will return + * HRTIMER_NORESTART. + */ + if (this_cpu_read(hrtimer_running) != t) + hrtimer_cancel(&t->timer); + kfree(t); +} + const struct bpf_func_proto bpf_get_current_task_proto __weak; const struct bpf_func_proto bpf_probe_read_user_proto __weak; const struct bpf_func_proto bpf_probe_read_user_str_proto __weak; @@ -1065,6 +1381,14 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_per_cpu_ptr_proto; case BPF_FUNC_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; + case BPF_FUNC_timer_init: + return &bpf_timer_init_proto; + case BPF_FUNC_timer_set_callback: + return &bpf_timer_set_callback_proto; + case BPF_FUNC_timer_start: + return &bpf_timer_start_proto; + case BPF_FUNC_timer_cancel: + return &bpf_timer_cancel_proto; default: break; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3dbb3b40b754..e8645c819803 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4656,6 +4656,38 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, return 0; } +static int process_timer_func(struct bpf_verifier_env *env, int regno, + struct bpf_call_arg_meta *meta) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + bool is_const = tnum_is_const(reg->var_off); + struct bpf_map *map = reg->map_ptr; + u64 val = reg->var_off.value; + + if (!is_const) { + verbose(env, + "R%d doesn't have constant offset. bpf_timer has to be at the constant offset\n", + regno); + return -EINVAL; + } + if (!map->btf) { + verbose(env, "map '%s' has to have BTF in order to use bpf_timer\n", + map->name); + return -EINVAL; + } + if (val) { + /* This restriction will be removed in the next patch */ + verbose(env, "bpf_timer field can only be first in the map value element\n"); + return -EINVAL; + } + if (meta->map_ptr) { + verbose(env, "verifier bug. Two map pointers in a timer helper\n"); + return -EFAULT; + } + meta->map_ptr = map; + return 0; +} + static bool arg_type_is_mem_ptr(enum bpf_arg_type type) { return type == ARG_PTR_TO_MEM || @@ -4788,6 +4820,7 @@ static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_PER static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } }; static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } }; static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } }; +static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_MAP_KEY] = &map_key_value_types, @@ -4819,6 +4852,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_FUNC] = &func_ptr_types, [ARG_PTR_TO_STACK_OR_NULL] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, + [ARG_PTR_TO_TIMER] = &timer_types, }; static int check_reg_type(struct bpf_verifier_env *env, u32 regno, @@ -4948,6 +4982,10 @@ skip_type_check: if (arg_type == ARG_CONST_MAP_PTR) { /* bpf_map_xxx(map_ptr) call: remember that map_ptr */ + if (meta->map_ptr && meta->map_ptr != reg->map_ptr) { + verbose(env, "Map pointer doesn't match bpf_timer.\n"); + return -EINVAL; + } meta->map_ptr = reg->map_ptr; } else if (arg_type == ARG_PTR_TO_MAP_KEY) { /* bpf_map_xxx(..., map_ptr, ..., key) call: @@ -5000,6 +5038,9 @@ skip_type_check: verbose(env, "verifier internal error\n"); return -EFAULT; } + } else if (arg_type == ARG_PTR_TO_TIMER) { + if (process_timer_func(env, regno, meta)) + return -EACCES; } else if (arg_type == ARG_PTR_TO_FUNC) { meta->subprogno = reg->subprogno; } else if (arg_type_is_mem_ptr(arg_type)) { @@ -5742,6 +5783,34 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env, return 0; } +static int set_timer_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + struct bpf_map *map_ptr = caller->regs[BPF_REG_1].map_ptr; + + /* bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn); + * callback_fn(struct bpf_map *map, void *key, void *value); + */ + callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; + __mark_reg_known_zero(&callee->regs[BPF_REG_1]); + callee->regs[BPF_REG_1].map_ptr = map_ptr; + + callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; + __mark_reg_known_zero(&callee->regs[BPF_REG_2]); + callee->regs[BPF_REG_2].map_ptr = map_ptr; + + callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; + __mark_reg_known_zero(&callee->regs[BPF_REG_3]); + callee->regs[BPF_REG_3].map_ptr = map_ptr; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + return 0; +} + static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; @@ -6069,6 +6138,13 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } + if (func_id == BPF_FUNC_timer_set_callback) { + err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, + set_timer_callback_state); + if (err < 0) + return -EINVAL; + } + if (func_id == BPF_FUNC_snprintf) { err = check_bpf_snprintf_call(env, regs); if (err < 0) @@ -12591,6 +12667,39 @@ static int do_misc_fixups(struct bpf_verifier_env *env) continue; } + if (insn->imm == BPF_FUNC_timer_set_callback) { + /* The verifier will process callback_fn as many times as necessary + * with different maps and the register states prepared by + * set_timer_callback_state will be accurate. + * + * The following use case is valid: + * map1 is shared by prog1, prog2, prog3. + * prog1 calls bpf_timer_init for some map1 elements + * prog2 calls bpf_timer_set_callback for some map1 elements. + * Those that were not bpf_timer_init-ed will return -EINVAL. + * prog3 calls bpf_timer_start for some map1 elements. + * Those that were not both bpf_timer_init-ed and + * bpf_timer_set_callback-ed will return -EINVAL. + */ + struct bpf_insn ld_addrs[2] = { + BPF_LD_IMM64(BPF_REG_3, (long)prog->aux), + }; + + insn_buf[0] = ld_addrs[0]; + insn_buf[1] = ld_addrs[1]; + insn_buf[2] = *insn; + cnt = 3; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto patch_call_imm; + } + /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup * and other inlining handlers are currently limited to 64 bit * only. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 64bd2d84367f..6c77d25137e0 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1059,7 +1059,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_snprintf: return &bpf_snprintf_proto; default: - return NULL; + return bpf_base_func_proto(func_id); } } diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index 2d94025b38e9..00ac7b79cddb 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -547,6 +547,7 @@ class PrinterHelpers(Printer): 'struct inode', 'struct socket', 'struct file', + 'struct bpf_timer', ] known_types = { '...', @@ -594,6 +595,7 @@ class PrinterHelpers(Printer): 'struct inode', 'struct socket', 'struct file', + 'struct bpf_timer', } mapped_types = { 'u8': '__u8', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bafb6282032b..3544ec5234f0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4777,6 +4777,70 @@ union bpf_attr { * Execute close syscall for given FD. * Return * A syscall result. + * + * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags) + * Description + * Initialize the timer. + * First 4 bits of *flags* specify clockid. + * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. + * All other bits of *flags* are reserved. + * The verifier will reject the program if *timer* is not from + * the same *map*. + * Return + * 0 on success. + * **-EBUSY** if *timer* is already initialized. + * **-EINVAL** if invalid *flags* are passed. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn) + * Description + * Configure the timer to call *callback_fn* static function. + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags) + * Description + * Set timer expiration N nanoseconds from the current time. The + * configured callback will be invoked in soft irq context on some cpu + * and will not repeat unless another bpf_timer_start() is made. + * In such case the next invocation can migrate to a different cpu. + * Since struct bpf_timer is a field inside map element the map + * owns the timer. The bpf_timer_set_callback() will increment refcnt + * of BPF program to make sure that callback_fn code stays valid. + * When user space reference to a map reaches zero all timers + * in a map are cancelled and corresponding program's refcnts are + * decremented. This is done to make sure that Ctrl-C of a user + * process doesn't leave any timers running. If map is pinned in + * bpffs the callback_fn can re-arm itself indefinitely. + * bpf_map_update/delete_elem() helpers and user space sys_bpf commands + * cancel and free the timer in the given map element. + * The map can contain timers that invoke callback_fn-s from different + * programs. The same callback_fn can serve different timers from + * different maps if key/value layout matches across maps. + * Every bpf_timer_set_callback() can have different callback_fn. + * + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier + * or invalid *flags* are passed. + * + * long bpf_timer_cancel(struct bpf_timer *timer) + * Description + * Cancel the timer and wait for callback_fn to finish if it was running. + * Return + * 0 if the timer was not active. + * 1 if the timer was active. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its + * own timer which would have led to a deadlock otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4948,6 +5012,10 @@ union bpf_attr { FN(sys_bpf), \ FN(btf_find_by_name_kind), \ FN(sys_close), \ + FN(timer_init), \ + FN(timer_set_callback), \ + FN(timer_start), \ + FN(timer_cancel), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -6074,6 +6142,11 @@ struct bpf_spin_lock { __u32 val; }; +struct bpf_timer { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. -- cgit v1.2.3 From 68134668c17f31f51930478f75495b552a411550 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 14 Jul 2021 17:54:10 -0700 Subject: bpf: Add map side support for bpf timers. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Restrict bpf timers to array, hash (both preallocated and kmalloced), and lru map types. The per-cpu maps with timers don't make sense, since 'struct bpf_timer' is a part of map value. bpf timers in per-cpu maps would mean that the number of timers depends on number of possible cpus and timers would not be accessible from all cpus. lpm map support can be added in the future. The timers in inner maps are supported. The bpf_map_update/delete_elem() helpers and sys_bpf commands cancel and free bpf_timer in a given map element. Similar to 'struct bpf_spin_lock' BTF is required and it is used to validate that map element indeed contains 'struct bpf_timer'. Make check_and_init_map_value() init both bpf_spin_lock and bpf_timer when map element data is reused in preallocated htab and lru maps. Teach copy_map_value() to support both bpf_spin_lock and bpf_timer in a single map element. There could be one of each, but not more than one. Due to 'one bpf_timer in one element' restriction do not support timers in global data, since global data is a map of single element, but from bpf program side it's seen as many global variables and restriction of single global timer would be odd. The sys_bpf map_freeze and sys_mmap syscalls are not allowed on maps with timers, since user space could have corrupted mmap element and crashed the kernel. The maps with timers cannot be readonly. Due to these restrictions search for bpf_timer in datasec BTF in case it was placed in the global data to report clear error. The previous patch allowed 'struct bpf_timer' as a first field in a map element only. Relax this restriction. Refactor lru map to s/bpf_lru_push_free/htab_lru_push_free/ to cancel and free the timer when lru map deletes an element as a part of it eviction algorithm. Make sure that bpf program cannot access 'struct bpf_timer' via direct load/store. The timer operation are done through helpers only. This is similar to 'struct bpf_spin_lock'. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Acked-by: Martin KaFai Lau Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210715005417.78572-5-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 44 ++++++++++++++----- include/linux/btf.h | 1 + kernel/bpf/arraymap.c | 21 +++++++++ kernel/bpf/btf.c | 77 +++++++++++++++++++++++++++------ kernel/bpf/hashtab.c | 105 +++++++++++++++++++++++++++++++++++++++------ kernel/bpf/local_storage.c | 4 +- kernel/bpf/map_in_map.c | 2 + kernel/bpf/syscall.c | 21 +++++++-- kernel/bpf/verifier.c | 30 +++++++++++-- 9 files changed, 259 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 125240b7cefb..a9a4a480a6d0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -198,24 +198,46 @@ static inline bool map_value_has_spin_lock(const struct bpf_map *map) return map->spin_lock_off >= 0; } -static inline void check_and_init_map_lock(struct bpf_map *map, void *dst) +static inline bool map_value_has_timer(const struct bpf_map *map) { - if (likely(!map_value_has_spin_lock(map))) - return; - *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = - (struct bpf_spin_lock){}; + return map->timer_off >= 0; } -/* copy everything but bpf_spin_lock */ +static inline void check_and_init_map_value(struct bpf_map *map, void *dst) +{ + if (unlikely(map_value_has_spin_lock(map))) + *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = + (struct bpf_spin_lock){}; + if (unlikely(map_value_has_timer(map))) + *(struct bpf_timer *)(dst + map->timer_off) = + (struct bpf_timer){}; +} + +/* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { + u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0; + if (unlikely(map_value_has_spin_lock(map))) { - u32 off = map->spin_lock_off; + s_off = map->spin_lock_off; + s_sz = sizeof(struct bpf_spin_lock); + } else if (unlikely(map_value_has_timer(map))) { + t_off = map->timer_off; + t_sz = sizeof(struct bpf_timer); + } - memcpy(dst, src, off); - memcpy(dst + off + sizeof(struct bpf_spin_lock), - src + off + sizeof(struct bpf_spin_lock), - map->value_size - off - sizeof(struct bpf_spin_lock)); + if (unlikely(s_sz || t_sz)) { + if (s_off < t_off || !s_sz) { + swap(s_off, t_off); + swap(s_sz, t_sz); + } + memcpy(dst, src, t_off); + memcpy(dst + t_off + t_sz, + src + t_off + t_sz, + s_off - t_off - t_sz); + memcpy(dst + s_off + s_sz, + src + s_off + s_sz, + map->value_size - s_off - s_sz); } else { memcpy(dst, src, map->value_size); } diff --git a/include/linux/btf.h b/include/linux/btf.h index 94a0c976c90f..214fde93214b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -99,6 +99,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); +int btf_find_timer(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 3c4105603f9d..cebd4fb06d19 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -287,6 +287,12 @@ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key return 0; } +static void check_and_free_timer_in_array(struct bpf_array *arr, void *val) +{ + if (unlikely(map_value_has_timer(&arr->map))) + bpf_timer_cancel_and_free(val + arr->map.timer_off); +} + /* Called from syscall or from eBPF program */ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) @@ -321,6 +327,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, copy_map_value_locked(map, val, value, false); else copy_map_value(map, val, value); + check_and_free_timer_in_array(array, val); } return 0; } @@ -374,6 +381,19 @@ static void *array_map_vmalloc_addr(struct bpf_array *array) return (void *)round_down((unsigned long)array, PAGE_SIZE); } +static void array_map_free_timers(struct bpf_map *map) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + int i; + + if (likely(!map_value_has_timer(map))) + return; + + for (i = 0; i < array->map.max_entries; i++) + bpf_timer_cancel_and_free(array->value + array->elem_size * i + + map->timer_off); +} + /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void array_map_free(struct bpf_map *map) { @@ -668,6 +688,7 @@ const struct bpf_map_ops array_map_ops = { .map_alloc = array_map_alloc, .map_free = array_map_free, .map_get_next_key = array_map_get_next_key, + .map_release_uref = array_map_free_timers, .map_lookup_elem = array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index cb4b72997d9b..7780131f710e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3046,43 +3046,92 @@ static void btf_struct_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } -/* find 'struct bpf_spin_lock' in map value. - * return >= 0 offset if found - * and < 0 in case of error - */ -int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t) +static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, + const char *name, int sz, int align) { const struct btf_member *member; u32 i, off = -ENOENT; - if (!__btf_type_is_struct(t)) - return -EINVAL; - for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); if (!__btf_type_is_struct(member_type)) continue; - if (member_type->size != sizeof(struct bpf_spin_lock)) + if (member_type->size != sz) continue; - if (strcmp(__btf_name_by_offset(btf, member_type->name_off), - "bpf_spin_lock")) + if (strcmp(__btf_name_by_offset(btf, member_type->name_off), name)) continue; if (off != -ENOENT) - /* only one 'struct bpf_spin_lock' is allowed */ + /* only one such field is allowed */ return -E2BIG; off = btf_member_bit_offset(t, member); if (off % 8) /* valid C code cannot generate such BTF */ return -EINVAL; off /= 8; - if (off % __alignof__(struct bpf_spin_lock)) - /* valid struct bpf_spin_lock will be 4 byte aligned */ + if (off % align) + return -EINVAL; + } + return off; +} + +static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, + const char *name, int sz, int align) +{ + const struct btf_var_secinfo *vsi; + u32 i, off = -ENOENT; + + for_each_vsi(i, t, vsi) { + const struct btf_type *var = btf_type_by_id(btf, vsi->type); + const struct btf_type *var_type = btf_type_by_id(btf, var->type); + + if (!__btf_type_is_struct(var_type)) + continue; + if (var_type->size != sz) + continue; + if (vsi->size != sz) + continue; + if (strcmp(__btf_name_by_offset(btf, var_type->name_off), name)) + continue; + if (off != -ENOENT) + /* only one such field is allowed */ + return -E2BIG; + off = vsi->offset; + if (off % align) return -EINVAL; } return off; } +static int btf_find_field(const struct btf *btf, const struct btf_type *t, + const char *name, int sz, int align) +{ + + if (__btf_type_is_struct(t)) + return btf_find_struct_field(btf, t, name, sz, align); + else if (btf_type_is_datasec(t)) + return btf_find_datasec_var(btf, t, name, sz, align); + return -EINVAL; +} + +/* find 'struct bpf_spin_lock' in map value. + * return >= 0 offset if found + * and < 0 in case of error + */ +int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t) +{ + return btf_find_field(btf, t, "bpf_spin_lock", + sizeof(struct bpf_spin_lock), + __alignof__(struct bpf_spin_lock)); +} + +int btf_find_timer(const struct btf *btf, const struct btf_type *t) +{ + return btf_find_field(btf, t, "bpf_timer", + sizeof(struct bpf_timer), + __alignof__(struct bpf_timer)); +} + static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 72c58cc516a3..6dc3fae46a56 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -228,6 +228,32 @@ static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i) return (struct htab_elem *) (htab->elems + i * (u64)htab->elem_size); } +static bool htab_has_extra_elems(struct bpf_htab *htab) +{ + return !htab_is_percpu(htab) && !htab_is_lru(htab); +} + +static void htab_free_prealloced_timers(struct bpf_htab *htab) +{ + u32 num_entries = htab->map.max_entries; + int i; + + if (likely(!map_value_has_timer(&htab->map))) + return; + if (htab_has_extra_elems(htab)) + num_entries += num_possible_cpus(); + + for (i = 0; i < num_entries; i++) { + struct htab_elem *elem; + + elem = get_htab_elem(htab, i); + bpf_timer_cancel_and_free(elem->key + + round_up(htab->map.key_size, 8) + + htab->map.timer_off); + cond_resched(); + } +} + static void htab_free_elems(struct bpf_htab *htab) { int i; @@ -265,8 +291,12 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, struct htab_elem *l; if (node) { + u32 key_size = htab->map.key_size; + l = container_of(node, struct htab_elem, lru_node); - memcpy(l->key, key, htab->map.key_size); + memcpy(l->key, key, key_size); + check_and_init_map_value(&htab->map, + l->key + round_up(key_size, 8)); return l; } @@ -278,7 +308,7 @@ static int prealloc_init(struct bpf_htab *htab) u32 num_entries = htab->map.max_entries; int err = -ENOMEM, i; - if (!htab_is_percpu(htab) && !htab_is_lru(htab)) + if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); htab->elems = bpf_map_area_alloc((u64)htab->elem_size * num_entries, @@ -695,6 +725,14 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map, return insn - insn_buf; } +static void check_and_free_timer(struct bpf_htab *htab, struct htab_elem *elem) +{ + if (unlikely(map_value_has_timer(&htab->map))) + bpf_timer_cancel_and_free(elem->key + + round_up(htab->map.key_size, 8) + + htab->map.timer_off); +} + /* It is called from the bpf_lru_list when the LRU needs to delete * older elements from the htab. */ @@ -719,6 +757,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { hlist_nulls_del_rcu(&l->hash_node); + check_and_free_timer(htab, l); break; } @@ -790,6 +829,7 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); + check_and_free_timer(htab, l); kfree(l); } @@ -817,6 +857,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { + check_and_free_timer(htab, l); __pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); @@ -920,8 +961,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new = ERR_PTR(-ENOMEM); goto dec_count; } - check_and_init_map_lock(&htab->map, - l_new->key + round_up(key_size, 8)); + check_and_init_map_value(&htab->map, + l_new->key + round_up(key_size, 8)); } memcpy(l_new->key, key, key_size); @@ -1062,6 +1103,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, hlist_nulls_del_rcu(&l_old->hash_node); if (!htab_is_prealloc(htab)) free_htab_elem(htab, l_old); + else + check_and_free_timer(htab, l_old); } ret = 0; err: @@ -1069,6 +1112,12 @@ err: return ret; } +static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem) +{ + check_and_free_timer(htab, elem); + bpf_lru_push_free(&htab->lru, &elem->lru_node); +} + static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { @@ -1102,7 +1151,8 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, l_new = prealloc_lru_pop(htab, key, hash); if (!l_new) return -ENOMEM; - memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size); + copy_map_value(&htab->map, + l_new->key + round_up(map->key_size, 8), value); ret = htab_lock_bucket(htab, b, hash, &flags); if (ret) @@ -1128,9 +1178,9 @@ err: htab_unlock_bucket(htab, b, hash, flags); if (ret) - bpf_lru_push_free(&htab->lru, &l_new->lru_node); + htab_lru_push_free(htab, l_new); else if (l_old) - bpf_lru_push_free(&htab->lru, &l_old->lru_node); + htab_lru_push_free(htab, l_old); return ret; } @@ -1339,7 +1389,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) htab_unlock_bucket(htab, b, hash, flags); if (l) - bpf_lru_push_free(&htab->lru, &l->lru_node); + htab_lru_push_free(htab, l); return ret; } @@ -1359,6 +1409,35 @@ static void delete_all_elements(struct bpf_htab *htab) } } +static void htab_free_malloced_timers(struct bpf_htab *htab) +{ + int i; + + rcu_read_lock(); + for (i = 0; i < htab->n_buckets; i++) { + struct hlist_nulls_head *head = select_bucket(htab, i); + struct hlist_nulls_node *n; + struct htab_elem *l; + + hlist_nulls_for_each_entry(l, n, head, hash_node) + check_and_free_timer(htab, l); + cond_resched_rcu(); + } + rcu_read_unlock(); +} + +static void htab_map_free_timers(struct bpf_map *map) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + + if (likely(!map_value_has_timer(&htab->map))) + return; + if (!htab_is_prealloc(htab)) + htab_free_malloced_timers(htab); + else + htab_free_prealloced_timers(htab); +} + /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void htab_map_free(struct bpf_map *map) { @@ -1456,7 +1535,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, else copy_map_value(map, value, l->key + roundup_key_size); - check_and_init_map_lock(map, value); + check_and_init_map_value(map, value); } hlist_nulls_del_rcu(&l->hash_node); @@ -1467,7 +1546,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, htab_unlock_bucket(htab, b, hash, bflags); if (is_lru_map && l) - bpf_lru_push_free(&htab->lru, &l->lru_node); + htab_lru_push_free(htab, l); return ret; } @@ -1645,7 +1724,7 @@ again_nocopy: true); else copy_map_value(map, dst_val, value); - check_and_init_map_lock(map, dst_val); + check_and_init_map_value(map, dst_val); } if (do_delete) { hlist_nulls_del_rcu(&l->hash_node); @@ -1672,7 +1751,7 @@ again_nocopy: while (node_to_free) { l = node_to_free; node_to_free = node_to_free->batch_flink; - bpf_lru_push_free(&htab->lru, &l->lru_node); + htab_lru_push_free(htab, l); } next_batch: @@ -2034,6 +2113,7 @@ const struct bpf_map_ops htab_map_ops = { .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, + .map_release_uref = htab_map_free_timers, .map_lookup_elem = htab_map_lookup_elem, .map_lookup_and_delete_elem = htab_map_lookup_and_delete_elem, .map_update_elem = htab_map_update_elem, @@ -2055,6 +2135,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, + .map_release_uref = htab_map_free_timers, .map_lookup_elem = htab_lru_map_lookup_elem, .map_lookup_and_delete_elem = htab_lru_map_lookup_and_delete_elem, .map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys, diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index bd11db9774c3..95d70a08325d 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -173,7 +173,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key, return -ENOMEM; memcpy(&new->data[0], value, map->value_size); - check_and_init_map_lock(map, new->data); + check_and_init_map_value(map, new->data); new = xchg(&storage->buf, new); kfree_rcu(new, rcu); @@ -509,7 +509,7 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, map->numa_node); if (!storage->buf) goto enomem; - check_and_init_map_lock(map, storage->buf->data); + check_and_init_map_value(map, storage->buf->data); } else { storage->percpu_buf = bpf_map_alloc_percpu(map, size, 8, gfp); if (!storage->percpu_buf) diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 39ab0b68cade..890dfe14e731 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -50,6 +50,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) inner_map_meta->map_flags = inner_map->map_flags; inner_map_meta->max_entries = inner_map->max_entries; inner_map_meta->spin_lock_off = inner_map->spin_lock_off; + inner_map_meta->timer_off = inner_map->timer_off; /* Misc members not needed in bpf_map_meta_equal() check. */ inner_map_meta->ops = inner_map->ops; @@ -75,6 +76,7 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, return meta0->map_type == meta1->map_type && meta0->key_size == meta1->key_size && meta0->value_size == meta1->value_size && + meta0->timer_off == meta1->timer_off && meta0->map_flags == meta1->map_flags; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5d1fee634be8..9a2068e39d23 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -260,8 +260,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, copy_map_value_locked(map, value, ptr, true); else copy_map_value(map, value, ptr); - /* mask lock, since value wasn't zero inited */ - check_and_init_map_lock(map, value); + /* mask lock and timer, since value wasn't zero inited */ + check_and_init_map_value(map, value); } rcu_read_unlock(); } @@ -623,7 +623,8 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) struct bpf_map *map = filp->private_data; int err; - if (!map->ops->map_mmap || map_value_has_spin_lock(map)) + if (!map->ops->map_mmap || map_value_has_spin_lock(map) || + map_value_has_timer(map)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) @@ -793,6 +794,16 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, } } + map->timer_off = btf_find_timer(btf, value_type); + if (map_value_has_timer(map)) { + if (map->map_flags & BPF_F_RDONLY_PROG) + return -EACCES; + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY) + return -EOPNOTSUPP; + } + if (map->ops->map_check_btf) ret = map->ops->map_check_btf(map, btf, key_type, value_type); @@ -844,6 +855,7 @@ static int map_create(union bpf_attr *attr) mutex_init(&map->freeze_mutex); map->spin_lock_off = -EINVAL; + map->timer_off = -EINVAL; if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, * the bpf_prog.o must have BTF to begin with @@ -1591,7 +1603,8 @@ static int map_freeze(const union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || + map_value_has_timer(map)) { fdput(f); return -ENOTSUPP; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e8645c819803..12b50f46a7c1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3241,6 +3241,15 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, return -EACCES; } } + if (map_value_has_timer(map)) { + u32 t = map->timer_off; + + if (reg->smin_value + off < t + sizeof(struct bpf_timer) && + t < reg->umax_value + off + size) { + verbose(env, "bpf_timer cannot be accessed directly by load/store\n"); + return -EACCES; + } + } return err; } @@ -4675,9 +4684,24 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno, map->name); return -EINVAL; } - if (val) { - /* This restriction will be removed in the next patch */ - verbose(env, "bpf_timer field can only be first in the map value element\n"); + if (!map_value_has_timer(map)) { + if (map->timer_off == -E2BIG) + verbose(env, + "map '%s' has more than one 'struct bpf_timer'\n", + map->name); + else if (map->timer_off == -ENOENT) + verbose(env, + "map '%s' doesn't have 'struct bpf_timer'\n", + map->name); + else + verbose(env, + "map '%s' is not a struct type or bpf_timer is mangled\n", + map->name); + return -EINVAL; + } + if (map->timer_off != val + reg->off) { + verbose(env, "off %lld doesn't point to 'struct bpf_timer' that is at %d\n", + val + reg->off, map->timer_off); return -EINVAL; } if (meta->map_ptr) { -- cgit v1.2.3 From 3e8ce29850f1839d0603f925b30be9d8a4329917 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 14 Jul 2021 17:54:11 -0700 Subject: bpf: Prevent pointer mismatch in bpf_timer_init. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit bpf_timer_init() arguments are: 1. pointer to a timer (which is embedded in map element). 2. pointer to a map. Make sure that pointer to a timer actually belongs to that map. Use map_uid (which is unique id of inner map) to reject: inner_map1 = bpf_map_lookup_elem(outer_map, key1) inner_map2 = bpf_map_lookup_elem(outer_map, key2) if (inner_map1 && inner_map2) { timer = bpf_map_lookup_elem(inner_map1); if (timer) // mismatch would have been allowed bpf_timer_init(timer, inner_map2); } Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210715005417.78572-6-alexei.starovoitov@gmail.com --- include/linux/bpf_verifier.h | 9 ++++++++- kernel/bpf/verifier.c | 31 ++++++++++++++++++++++++++++--- 2 files changed, 36 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e774ecc1cd1f..5d3169b57e6e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -53,7 +53,14 @@ struct bpf_reg_state { /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL */ - struct bpf_map *map_ptr; + struct { + struct bpf_map *map_ptr; + /* To distinguish map lookups from outer map + * the map_uid is non-zero for registers + * pointing to inner maps. + */ + u32 map_uid; + }; /* for PTR_TO_BTF_ID */ struct { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 12b50f46a7c1..8df2671c3d33 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -255,6 +255,7 @@ struct bpf_call_arg_meta { int mem_size; u64 msize_max_value; int ref_obj_id; + int map_uid; int func_id; struct btf *btf; u32 btf_id; @@ -1135,6 +1136,10 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) if (map->inner_map_meta) { reg->type = CONST_PTR_TO_MAP; reg->map_ptr = map->inner_map_meta; + /* transfer reg's id which is unique for every map_lookup_elem + * as UID of the inner map. + */ + reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || @@ -4708,6 +4713,7 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno, verbose(env, "verifier bug. Two map pointers in a timer helper\n"); return -EFAULT; } + meta->map_uid = reg->map_uid; meta->map_ptr = map; return 0; } @@ -5006,11 +5012,29 @@ skip_type_check: if (arg_type == ARG_CONST_MAP_PTR) { /* bpf_map_xxx(map_ptr) call: remember that map_ptr */ - if (meta->map_ptr && meta->map_ptr != reg->map_ptr) { - verbose(env, "Map pointer doesn't match bpf_timer.\n"); - return -EINVAL; + if (meta->map_ptr) { + /* Use map_uid (which is unique id of inner map) to reject: + * inner_map1 = bpf_map_lookup_elem(outer_map, key1) + * inner_map2 = bpf_map_lookup_elem(outer_map, key2) + * if (inner_map1 && inner_map2) { + * timer = bpf_map_lookup_elem(inner_map1); + * if (timer) + * // mismatch would have been allowed + * bpf_timer_init(timer, inner_map2); + * } + * + * Comparing map_ptr is enough to distinguish normal and outer maps. + */ + if (meta->map_ptr != reg->map_ptr || + meta->map_uid != reg->map_uid) { + verbose(env, + "timer pointer in R1 map_uid=%d doesn't match map pointer in R2 map_uid=%d\n", + meta->map_uid, reg->map_uid); + return -EINVAL; + } } meta->map_ptr = reg->map_ptr; + meta->map_uid = reg->map_uid; } else if (arg_type == ARG_PTR_TO_MAP_KEY) { /* bpf_map_xxx(..., map_ptr, ..., key) call: * check that [key, key + map->key_size) are within @@ -6204,6 +6228,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; + regs[BPF_REG_0].map_uid = meta.map_uid; if (fn->ret_type == RET_PTR_TO_MAP_VALUE) { regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; if (map_value_has_spin_lock(meta.map_ptr)) -- cgit v1.2.3 From bfc6bb74e4f16ab264fa73398a7a79d7d2afac2e Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 14 Jul 2021 17:54:14 -0700 Subject: bpf: Implement verifier support for validation of async callbacks. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit bpf_for_each_map_elem() and bpf_timer_set_callback() helpers are relying on PTR_TO_FUNC infra in the verifier to validate addresses to subprograms and pass them into the helpers as function callbacks. In case of bpf_for_each_map_elem() the callback is invoked synchronously and the verifier treats it as a normal subprogram call by adding another bpf_func_state and new frame in __check_func_call(). bpf_timer_set_callback() doesn't invoke the callback directly. The subprogram will be called asynchronously from bpf_timer_cb(). Teach the verifier to validate such async callbacks as special kind of jump by pushing verifier state into stack and let pop_stack() process it. Special care needs to be taken during state pruning. The call insn doing bpf_timer_set_callback has to be a prune_point. Otherwise short timer callbacks might not have prune points in front of bpf_timer_set_callback() which means is_state_visited() will be called after this call insn is processed in __check_func_call(). Which means that another async_cb state will be pushed to be walked later and the verifier will eventually hit BPF_COMPLEXITY_LIMIT_JMP_SEQ limit. Since push_async_cb() looks like another push_stack() branch the infinite loop detection will trigger false positive. To recognize this case mark such states as in_async_callback_fn. To distinguish infinite loop in async callback vs the same callback called with different arguments for different map and timer add async_entry_cnt to bpf_func_state. Enforce return zero from async callbacks. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210715005417.78572-9-alexei.starovoitov@gmail.com --- include/linux/bpf_verifier.h | 9 +++- kernel/bpf/helpers.c | 8 ++- kernel/bpf/verifier.c | 123 +++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 131 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5d3169b57e6e..242d0b1a0772 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -208,12 +208,19 @@ struct bpf_func_state { * zero == main subprog */ u32 subprogno; + /* Every bpf_timer_start will increment async_entry_cnt. + * It's used to distinguish: + * void foo(void) { for(;;); } + * void foo(void) { bpf_timer_set_callback(,foo); } + */ + u32 async_entry_cnt; + bool in_callback_fn; + bool in_async_callback_fn; /* The following fields should be last. See copy_func_state() */ int acquired_refs; struct bpf_reference_state *refs; int allocated_stack; - bool in_callback_fn; struct bpf_stack_state *stack; }; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 74b16593983d..9fe846ec6bd1 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1043,7 +1043,6 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) void *callback_fn; void *key; u32 idx; - int ret; callback_fn = rcu_dereference_check(t->callback_fn, rcu_read_lock_bh_held()); if (!callback_fn) @@ -1066,10 +1065,9 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) key = value - round_up(map->key_size, 8); } - ret = BPF_CAST_CALL(callback_fn)((u64)(long)map, - (u64)(long)key, - (u64)(long)value, 0, 0); - WARN_ON(ret != 0); /* Next patch moves this check into the verifier */ + BPF_CAST_CALL(callback_fn)((u64)(long)map, (u64)(long)key, + (u64)(long)value, 0, 0); + /* The verifier checked that return value is zero. */ this_cpu_write(hrtimer_running, NULL); out: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1cb1b35e69b7..ab06256bf6c8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -735,6 +735,10 @@ static void print_verifier_state(struct bpf_verifier_env *env, if (state->refs[i].id) verbose(env, ",%d", state->refs[i].id); } + if (state->in_callback_fn) + verbose(env, " cb"); + if (state->in_async_callback_fn) + verbose(env, " async_cb"); verbose(env, "\n"); } @@ -1527,6 +1531,54 @@ static void init_func_state(struct bpf_verifier_env *env, init_reg_state(env, state); } +/* Similar to push_stack(), but for async callbacks */ +static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env, + int insn_idx, int prev_insn_idx, + int subprog) +{ + struct bpf_verifier_stack_elem *elem; + struct bpf_func_state *frame; + + elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); + if (!elem) + goto err; + + elem->insn_idx = insn_idx; + elem->prev_insn_idx = prev_insn_idx; + elem->next = env->head; + elem->log_pos = env->log.len_used; + env->head = elem; + env->stack_size++; + if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { + verbose(env, + "The sequence of %d jumps is too complex for async cb.\n", + env->stack_size); + goto err; + } + /* Unlike push_stack() do not copy_verifier_state(). + * The caller state doesn't matter. + * This is async callback. It starts in a fresh stack. + * Initialize it similar to do_check_common(). + */ + elem->st.branches = 1; + frame = kzalloc(sizeof(*frame), GFP_KERNEL); + if (!frame) + goto err; + init_func_state(env, frame, + BPF_MAIN_FUNC /* callsite */, + 0 /* frameno within this callchain */, + subprog /* subprog number within this prog */); + elem->st.frame[0] = frame; + return &elem->st; +err: + free_verifier_state(env->cur_state, true); + env->cur_state = NULL; + /* pop all elements and return */ + while (!pop_stack(env, NULL, NULL, false)); + return NULL; +} + + enum reg_arg_type { SRC_OP, /* register is used as source operand */ DST_OP, /* register is used as destination operand */ @@ -5704,6 +5756,30 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn } } + if (insn->code == (BPF_JMP | BPF_CALL) && + insn->imm == BPF_FUNC_timer_set_callback) { + struct bpf_verifier_state *async_cb; + + /* there is no real recursion here. timer callbacks are async */ + async_cb = push_async_cb(env, env->subprog_info[subprog].start, + *insn_idx, subprog); + if (!async_cb) + return -EFAULT; + callee = async_cb->frame[0]; + callee->async_entry_cnt = caller->async_entry_cnt + 1; + + /* Convert bpf_timer_set_callback() args into timer callback args */ + err = set_callee_state_cb(env, caller, callee, *insn_idx); + if (err) + return err; + + clear_caller_saved_regs(env, caller->regs); + mark_reg_unknown(env, caller->regs, BPF_REG_0); + caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; + /* continue with next insn after call */ + return 0; + } + callee = kzalloc(sizeof(*callee), GFP_KERNEL); if (!callee) return -ENOMEM; @@ -5856,6 +5932,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + callee->in_async_callback_fn = true; return 0; } @@ -9224,7 +9301,8 @@ static int check_return_code(struct bpf_verifier_env *env) struct tnum range = tnum_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; - const bool is_subprog = env->cur_state->frame[0]->subprogno; + struct bpf_func_state *frame = env->cur_state->frame[0]; + const bool is_subprog = frame->subprogno; /* LSM and struct_ops func-ptr's return type could be "void" */ if (!is_subprog && @@ -9249,6 +9327,22 @@ static int check_return_code(struct bpf_verifier_env *env) } reg = cur_regs(env) + BPF_REG_0; + + if (frame->in_async_callback_fn) { + /* enforce return zero from async callbacks like timer */ + if (reg->type != SCALAR_VALUE) { + verbose(env, "In async callback the register R0 is not a known value (%s)\n", + reg_type_str[reg->type]); + return -EINVAL; + } + + if (!tnum_in(tnum_const(0), reg->var_off)) { + verbose_invalid_scalar(env, reg, &range, "async callback", "R0"); + return -EINVAL; + } + return 0; + } + if (is_subprog) { if (reg->type != SCALAR_VALUE) { verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", @@ -9496,6 +9590,13 @@ static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env) return DONE_EXPLORING; case BPF_CALL: + if (insns[t].imm == BPF_FUNC_timer_set_callback) + /* Mark this call insn to trigger is_state_visited() check + * before call itself is processed by __check_func_call(). + * Otherwise new async state will be pushed for further + * exploration. + */ + init_explored_state(env, t); return visit_func_call_insn(t, insn_cnt, insns, env, insns[t].src_reg == BPF_PSEUDO_CALL); @@ -10503,9 +10604,25 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) states_cnt++; if (sl->state.insn_idx != insn_idx) goto next; + if (sl->state.branches) { - if (states_maybe_looping(&sl->state, cur) && - states_equal(env, &sl->state, cur)) { + struct bpf_func_state *frame = sl->state.frame[sl->state.curframe]; + + if (frame->in_async_callback_fn && + frame->async_entry_cnt != cur->frame[cur->curframe]->async_entry_cnt) { + /* Different async_entry_cnt means that the verifier is + * processing another entry into async callback. + * Seeing the same state is not an indication of infinite + * loop or infinite recursion. + * But finding the same state doesn't mean that it's safe + * to stop processing the current state. The previous state + * hasn't yet reached bpf_exit, since state.branches > 0. + * Checking in_async_callback_fn alone is not enough either. + * Since the verifier still needs to catch infinite loops + * inside async callbacks. + */ + } else if (states_maybe_looping(&sl->state, cur) && + states_equal(env, &sl->state, cur)) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); return -EINVAL; -- cgit v1.2.3 From 7ddc80a476c2d599246028af5808d15f9e24c109 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 14 Jul 2021 17:54:15 -0700 Subject: bpf: Teach stack depth check about async callbacks. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Teach max stack depth checking algorithm about async callbacks that don't increase bpf program stack size. Also add sanity check that bpf_tail_call didn't sneak into async cb. It's impossible, since PTR_TO_CTX is not available in async cb, hence the program cannot contain bpf_tail_call(ctx,...); Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210715005417.78572-10-alexei.starovoitov@gmail.com --- include/linux/bpf_verifier.h | 1 + kernel/bpf/verifier.c | 18 +++++++++++++++--- 2 files changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 242d0b1a0772..b847e1ccd10f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -406,6 +406,7 @@ struct bpf_subprog_info { bool has_tail_call; bool tail_call_reachable; bool has_ld_abs; + bool is_async_cb; }; /* single container for all structs diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ab06256bf6c8..344ee67265cc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3709,6 +3709,8 @@ process_func: continue_func: subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { + int next_insn; + if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i)) continue; /* remember insn and function to return to */ @@ -3716,13 +3718,22 @@ continue_func: ret_prog[frame] = idx; /* find the callee */ - i = i + insn[i].imm + 1; - idx = find_subprog(env, i); + next_insn = i + insn[i].imm + 1; + idx = find_subprog(env, next_insn); if (idx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", - i); + next_insn); return -EFAULT; } + if (subprog[idx].is_async_cb) { + if (subprog[idx].has_tail_call) { + verbose(env, "verifier bug. subprog has tail_call and async cb\n"); + return -EFAULT; + } + /* async callbacks don't increase bpf prog stack size */ + continue; + } + i = next_insn; if (subprog[idx].has_tail_call) tail_call_reachable = true; @@ -5761,6 +5772,7 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn struct bpf_verifier_state *async_cb; /* there is no real recursion here. timer callbacks are async */ + env->subprog_info[subprog].is_async_cb = true; async_cb = push_async_cb(env, env->subprog_info[subprog].start, *insn_idx, subprog); if (!async_cb) -- cgit v1.2.3 From 7ed012969bbcdbd7aef5778a061681e6cbc4b402 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 14 Jul 2021 17:01:59 +0200 Subject: Compiler Attributes: fix __has_attribute(__no_sanitize_coverage__) for GCC 4 Fix __has_attribute(__no_sanitize_coverage__) for GCC 4 by defining __GCC4_has_attribute___no_sanitize_coverage__. Fixes: 540540d06e9d ("kcov: add __no_sanitize_coverage to fix noinstr for all architectures") Reported-by: Geert Uytterhoeven Signed-off-by: Marco Elver Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 183ddd5fd072..7b1fa5c30169 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -36,6 +36,7 @@ # define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) # define __GCC4_has_attribute___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___no_sanitize_coverage__ 0 # define __GCC4_has_attribute___fallthrough__ 0 #endif -- cgit v1.2.3 From 7e6f3cd89f04a0a577002d5696288b482109d25c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 14 Jul 2021 11:43:53 +0200 Subject: bpf, x86: Store caller's ip in trampoline stack Storing caller's ip in trampoline's stack. Trampoline programs can reach the IP in (ctx - 8) address, so there's no change in program's arguments interface. The IP address is takes from [fp + 8], which is return address from the initial 'call fentry' call to trampoline. This IP address will be returned via bpf_get_func_ip helper helper, which is added in following patches. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210714094400.396467-2-jolsa@kernel.org --- arch/x86/net/bpf_jit_comp.c | 19 +++++++++++++++++++ include/linux/bpf.h | 5 +++++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index e835164189f1..c320b3ce7b58 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1951,6 +1951,9 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (flags & BPF_TRAMP_F_CALL_ORIG) stack_size += 8; /* room for return value of orig_call */ + if (flags & BPF_TRAMP_F_IP_ARG) + stack_size += 8; /* room for IP address argument */ + if (flags & BPF_TRAMP_F_SKIP_FRAME) /* skip patched call instruction and point orig_call to actual * body of the kernel function. @@ -1964,6 +1967,22 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ EMIT1(0x53); /* push rbx */ + if (flags & BPF_TRAMP_F_IP_ARG) { + /* Store IP address of the traced function: + * mov rax, QWORD PTR [rbp + 8] + * sub rax, X86_PATCH_SIZE + * mov QWORD PTR [rbp - stack_size], rax + */ + emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8); + EMIT4(0x48, 0x83, 0xe8, X86_PATCH_SIZE); + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -stack_size); + + /* Continue with stack_size for regs storage, stack will + * be correctly restored with 'leave' instruction. + */ + stack_size -= 8; + } + save_regs(m, &prog, nr_args, stack_size); if (flags & BPF_TRAMP_F_CALL_ORIG) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a9a4a480a6d0..94d77dc7ce35 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -579,6 +579,11 @@ struct btf_func_model { */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) +/* Store IP address of the caller on the trampoline stack, + * so it's available for trampoline's programs. + */ +#define BPF_TRAMP_F_IP_ARG BIT(3) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ -- cgit v1.2.3 From 1e37392cccdea94da635e3c6d16b21865806f619 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 14 Jul 2021 11:43:54 +0200 Subject: bpf: Enable BPF_TRAMP_F_IP_ARG for trampolines with call_get_func_ip Enabling BPF_TRAMP_F_IP_ARG for trampolines that actually need it. The BPF_TRAMP_F_IP_ARG adds extra 3 instructions to trampoline code and is used only by programs with bpf_get_func_ip helper, which is added in following patch and sets call_get_func_ip bit. This patch ensures that BPF_TRAMP_F_IP_ARG flag is used only for trampolines that have programs with call_get_func_ip set. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210714094400.396467-3-jolsa@kernel.org --- include/linux/filter.h | 3 ++- kernel/bpf/trampoline.c | 12 +++++++++--- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 472f97074da0..ba36989f711a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -559,7 +559,8 @@ struct bpf_prog { kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ - call_get_stack:1; /* Do we call bpf_get_stack() or bpf_get_stackid() */ + call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ + call_get_func_ip:1; /* Do we call get_func_ip() */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 28a3630c48ee..b2535acfe9db 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -172,7 +172,7 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) } static struct bpf_tramp_progs * -bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total) +bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_arg) { const struct bpf_prog_aux *aux; struct bpf_tramp_progs *tprogs; @@ -189,8 +189,10 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total) *total += tr->progs_cnt[kind]; progs = tprogs[kind].progs; - hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist) + hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist) { + *ip_arg |= aux->prog->call_get_func_ip; *progs++ = aux->prog; + } } return tprogs; } @@ -333,9 +335,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) struct bpf_tramp_image *im; struct bpf_tramp_progs *tprogs; u32 flags = BPF_TRAMP_F_RESTORE_REGS; + bool ip_arg = false; int err, total; - tprogs = bpf_trampoline_get_progs(tr, &total); + tprogs = bpf_trampoline_get_progs(tr, &total, &ip_arg); if (IS_ERR(tprogs)) return PTR_ERR(tprogs); @@ -357,6 +360,9 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs) flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; + if (ip_arg) + flags |= BPF_TRAMP_F_IP_ARG; + err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE, &tr->func.model, flags, tprogs, tr->func.addr); -- cgit v1.2.3 From 17edea21b38d047a10c189296c58aea9875d0d0a Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 4 Jul 2021 12:02:42 -0700 Subject: sock_map: Relax config dependency to CONFIG_NET Currently sock_map still has Kconfig dependency on CONFIG_INET, but there is no actual functional dependency on it after we introduce ->psock_update_sk_prot(). We have to extend it to CONFIG_NET now as we are going to support AF_UNIX. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210704190252.11866-2-xiyou.wangcong@gmail.com --- include/linux/bpf.h | 38 ++++++++++++++++++++------------------ kernel/bpf/Kconfig | 2 +- net/core/Makefile | 2 -- 3 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 94d77dc7ce35..d25c16c365e5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1887,6 +1887,12 @@ void bpf_map_offload_map_free(struct bpf_map *map); int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); + +int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); +int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); +void sock_map_unhash(struct sock *sk); +void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1919,24 +1925,6 @@ static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, { return -ENOTSUPP; } -#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ - -#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) -int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); -int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); -int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); -void sock_map_unhash(struct sock *sk); -void sock_map_close(struct sock *sk, long timeout); - -void bpf_sk_reuseport_detach(struct sock *sk); -int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, - void *value); -int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags); -#else -static inline void bpf_sk_reuseport_detach(struct sock *sk) -{ -} #ifdef CONFIG_BPF_SYSCALL static inline int sock_map_get_from_fd(const union bpf_attr *attr, @@ -1956,7 +1944,21 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } +#endif /* CONFIG_BPF_SYSCALL */ +#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ +#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) +void bpf_sk_reuseport_detach(struct sock *sk); +int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, + void *value); +int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags); +#else +static inline void bpf_sk_reuseport_detach(struct sock *sk) +{ +} + +#ifdef CONFIG_BPF_SYSCALL static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig index bd04f4a44c01..a82d6de86522 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -29,7 +29,7 @@ config BPF_SYSCALL select IRQ_WORK select TASKS_TRACE_RCU select BINARY_PRINTF - select NET_SOCK_MSG if INET + select NET_SOCK_MSG if NET default n help Enable the bpf() system call that allows to manipulate BPF programs diff --git a/net/core/Makefile b/net/core/Makefile index f7f16650fe9e..35ced6201814 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -33,8 +33,6 @@ obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o -ifeq ($(CONFIG_INET),y) obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o obj-$(CONFIG_BPF_SYSCALL) += sock_map.o -endif obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o -- cgit v1.2.3 From 56d629af09b9d4db9792257165844287ecce0a98 Mon Sep 17 00:00:00 2001 From: Daisuke Nojiri Date: Wed, 16 Jun 2021 11:51:24 -0700 Subject: power: supply: PCHG: Peripheral device charger This patch adds a driver for PCHG (Peripheral CHarGer). PCHG is a framework managing power supplies for peripheral devices. This driver creates a sysfs node for each peripheral charge port: /sys/class/power_supply/peripheral where is the index of a charge port. For example, when a stylus is connected to a NFC/WLC port, the node returns: /sys/class/power_supply/peripheral0/ capacity=50 charge_type=Standard scope=Device status=Charging type=Battery Signed-off-by: Daisuke Nojiri Signed-off-by: Sebastian Reichel --- drivers/power/supply/Kconfig | 10 + drivers/power/supply/Makefile | 1 + drivers/power/supply/cros_peripheral_charger.c | 386 +++++++++++++++++++++++++ include/linux/platform_data/cros_ec_commands.h | 67 +++++ 4 files changed, 464 insertions(+) create mode 100644 drivers/power/supply/cros_peripheral_charger.c (limited to 'include/linux') diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index 11f5368e810e..47b7d2111c4e 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -736,6 +736,16 @@ config CHARGER_CROS_USBPD what is connected to USB PD ports from the EC and converts that into power_supply properties. +config CHARGER_CROS_PCHG + tristate "ChromeOS EC based peripheral charger" + depends on MFD_CROS_EC_DEV + default MFD_CROS_EC_DEV + help + Say Y here to enable ChromeOS EC based peripheral charge driver. + This driver gets various information about the devices connected to + the peripheral charge ports from the EC and converts that into + power_supply properties. + config CHARGER_SC2731 tristate "Spreadtrum SC2731 charger driver" depends on MFD_SC27XX_PMIC || COMPILE_TEST diff --git a/drivers/power/supply/Makefile b/drivers/power/supply/Makefile index dde138bc1591..2fd629dd7068 100644 --- a/drivers/power/supply/Makefile +++ b/drivers/power/supply/Makefile @@ -93,6 +93,7 @@ obj-$(CONFIG_CHARGER_TPS65217) += tps65217_charger.o obj-$(CONFIG_AXP288_FUEL_GAUGE) += axp288_fuel_gauge.o obj-$(CONFIG_AXP288_CHARGER) += axp288_charger.o obj-$(CONFIG_CHARGER_CROS_USBPD) += cros_usbpd-charger.o +obj-$(CONFIG_CHARGER_CROS_PCHG) += cros_peripheral_charger.o obj-$(CONFIG_CHARGER_SC2731) += sc2731_charger.o obj-$(CONFIG_FUEL_GAUGE_SC27XX) += sc27xx_fuel_gauge.o obj-$(CONFIG_CHARGER_UCS1002) += ucs1002_power.o diff --git a/drivers/power/supply/cros_peripheral_charger.c b/drivers/power/supply/cros_peripheral_charger.c new file mode 100644 index 000000000000..305f10dfc06d --- /dev/null +++ b/drivers/power/supply/cros_peripheral_charger.c @@ -0,0 +1,386 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Power supply driver for ChromeOS EC based Peripheral Device Charger. + * + * Copyright 2020 Google LLC. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRV_NAME "cros-ec-pchg" +#define PCHG_DIR_PREFIX "peripheral" +#define PCHG_DIR_NAME PCHG_DIR_PREFIX "%d" +#define PCHG_DIR_NAME_LENGTH \ + sizeof(PCHG_DIR_PREFIX __stringify(EC_PCHG_MAX_PORTS)) +#define PCHG_CACHE_UPDATE_DELAY msecs_to_jiffies(500) + +struct port_data { + int port_number; + char name[PCHG_DIR_NAME_LENGTH]; + struct power_supply *psy; + struct power_supply_desc psy_desc; + int psy_status; + int battery_percentage; + int charge_type; + struct charger_data *charger; + unsigned long last_update; +}; + +struct charger_data { + struct device *dev; + struct cros_ec_dev *ec_dev; + struct cros_ec_device *ec_device; + int num_registered_psy; + struct port_data *ports[EC_PCHG_MAX_PORTS]; + struct notifier_block notifier; +}; + +static enum power_supply_property cros_pchg_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_CHARGE_TYPE, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_SCOPE, +}; + +static int cros_pchg_ec_command(const struct charger_data *charger, + unsigned int version, + unsigned int command, + const void *outdata, + unsigned int outsize, + void *indata, + unsigned int insize) +{ + struct cros_ec_dev *ec_dev = charger->ec_dev; + struct cros_ec_command *msg; + int ret; + + msg = kzalloc(sizeof(*msg) + max(outsize, insize), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->version = version; + msg->command = ec_dev->cmd_offset + command; + msg->outsize = outsize; + msg->insize = insize; + + if (outsize) + memcpy(msg->data, outdata, outsize); + + ret = cros_ec_cmd_xfer_status(charger->ec_device, msg); + if (ret >= 0 && insize) + memcpy(indata, msg->data, insize); + + kfree(msg); + return ret; +} + +static const unsigned int pchg_cmd_version = 1; + +static bool cros_pchg_cmd_ver_check(const struct charger_data *charger) +{ + struct ec_params_get_cmd_versions_v1 req; + struct ec_response_get_cmd_versions rsp; + int ret; + + req.cmd = EC_CMD_PCHG; + ret = cros_pchg_ec_command(charger, 1, EC_CMD_GET_CMD_VERSIONS, + &req, sizeof(req), &rsp, sizeof(rsp)); + if (ret < 0) { + dev_warn(charger->dev, + "Unable to get versions of EC_CMD_PCHG (err:%d)\n", + ret); + return false; + } + + return !!(rsp.version_mask & BIT(pchg_cmd_version)); +} + +static int cros_pchg_port_count(const struct charger_data *charger) +{ + struct ec_response_pchg_count rsp; + int ret; + + ret = cros_pchg_ec_command(charger, 0, EC_CMD_PCHG_COUNT, + NULL, 0, &rsp, sizeof(rsp)); + if (ret < 0) { + dev_warn(charger->dev, + "Unable to get number or ports (err:%d)\n", ret); + return ret; + } + + return rsp.port_count; +} + +static int cros_pchg_get_status(struct port_data *port) +{ + struct charger_data *charger = port->charger; + struct ec_params_pchg req; + struct ec_response_pchg rsp; + struct device *dev = charger->dev; + int old_status = port->psy_status; + int old_percentage = port->battery_percentage; + int ret; + + req.port = port->port_number; + ret = cros_pchg_ec_command(charger, pchg_cmd_version, EC_CMD_PCHG, + &req, sizeof(req), &rsp, sizeof(rsp)); + if (ret < 0) { + dev_err(dev, "Unable to get port.%d status (err:%d)\n", + port->port_number, ret); + return ret; + } + + switch (rsp.state) { + case PCHG_STATE_RESET: + case PCHG_STATE_INITIALIZED: + case PCHG_STATE_ENABLED: + default: + port->psy_status = POWER_SUPPLY_STATUS_UNKNOWN; + port->charge_type = POWER_SUPPLY_CHARGE_TYPE_NONE; + break; + case PCHG_STATE_DETECTED: + port->psy_status = POWER_SUPPLY_STATUS_CHARGING; + port->charge_type = POWER_SUPPLY_CHARGE_TYPE_TRICKLE; + break; + case PCHG_STATE_CHARGING: + port->psy_status = POWER_SUPPLY_STATUS_CHARGING; + port->charge_type = POWER_SUPPLY_CHARGE_TYPE_STANDARD; + break; + case PCHG_STATE_FULL: + port->psy_status = POWER_SUPPLY_STATUS_FULL; + port->charge_type = POWER_SUPPLY_CHARGE_TYPE_NONE; + break; + } + + port->battery_percentage = rsp.battery_percentage; + + if (port->psy_status != old_status || + port->battery_percentage != old_percentage) + power_supply_changed(port->psy); + + dev_dbg(dev, + "Port %d: state=%d battery=%d%%\n", + port->port_number, rsp.state, rsp.battery_percentage); + + return 0; +} + +static int cros_pchg_get_port_status(struct port_data *port, bool ratelimit) +{ + int ret; + + if (ratelimit && + time_is_after_jiffies(port->last_update + PCHG_CACHE_UPDATE_DELAY)) + return 0; + + ret = cros_pchg_get_status(port); + if (ret < 0) + return ret; + + port->last_update = jiffies; + + return ret; +} + +static int cros_pchg_get_prop(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct port_data *port = power_supply_get_drvdata(psy); + + switch (psp) { + case POWER_SUPPLY_PROP_STATUS: + case POWER_SUPPLY_PROP_CAPACITY: + case POWER_SUPPLY_PROP_CHARGE_TYPE: + cros_pchg_get_port_status(port, true); + break; + default: + break; + } + + switch (psp) { + case POWER_SUPPLY_PROP_STATUS: + val->intval = port->psy_status; + break; + case POWER_SUPPLY_PROP_CAPACITY: + val->intval = port->battery_percentage; + break; + case POWER_SUPPLY_PROP_CHARGE_TYPE: + val->intval = port->charge_type; + break; + case POWER_SUPPLY_PROP_SCOPE: + val->intval = POWER_SUPPLY_SCOPE_DEVICE; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int cros_pchg_event(const struct charger_data *charger, + unsigned long host_event) +{ + int i; + + for (i = 0; i < charger->num_registered_psy; i++) + cros_pchg_get_port_status(charger->ports[i], false); + + return NOTIFY_OK; +} + +static u32 cros_get_device_event(const struct charger_data *charger) +{ + struct ec_params_device_event req; + struct ec_response_device_event rsp; + struct device *dev = charger->dev; + int ret; + + req.param = EC_DEVICE_EVENT_PARAM_GET_CURRENT_EVENTS; + ret = cros_pchg_ec_command(charger, 0, EC_CMD_DEVICE_EVENT, + &req, sizeof(req), &rsp, sizeof(rsp)); + if (ret < 0) { + dev_warn(dev, "Unable to get device events (err:%d)\n", ret); + return 0; + } + + return rsp.event_mask; +} + +static int cros_ec_notify(struct notifier_block *nb, + unsigned long queued_during_suspend, + void *data) +{ + struct cros_ec_device *ec_dev = (struct cros_ec_device *)data; + u32 host_event = cros_ec_get_host_event(ec_dev); + struct charger_data *charger = + container_of(nb, struct charger_data, notifier); + u32 device_event_mask; + + if (!host_event) + return NOTIFY_DONE; + + if (!(host_event & EC_HOST_EVENT_MASK(EC_HOST_EVENT_DEVICE))) + return NOTIFY_DONE; + + /* + * todo: Retrieve device event mask in common place + * (e.g. cros_ec_proto.c). + */ + device_event_mask = cros_get_device_event(charger); + if (!(device_event_mask & EC_DEVICE_EVENT_MASK(EC_DEVICE_EVENT_WLC))) + return NOTIFY_DONE; + + return cros_pchg_event(charger, host_event); +} + +static int cros_pchg_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cros_ec_dev *ec_dev = dev_get_drvdata(dev->parent); + struct cros_ec_device *ec_device = ec_dev->ec_dev; + struct power_supply_desc *psy_desc; + struct charger_data *charger; + struct power_supply *psy; + struct port_data *port; + struct notifier_block *nb; + int num_ports; + int ret; + int i; + + charger = devm_kzalloc(dev, sizeof(*charger), GFP_KERNEL); + if (!charger) + return -ENOMEM; + + charger->dev = dev; + charger->ec_dev = ec_dev; + charger->ec_device = ec_device; + + ret = cros_pchg_port_count(charger); + if (ret <= 0) { + /* + * This feature is enabled by the EC and the kernel driver is + * included by default for CrOS devices. Don't need to be loud + * since this error can be normal. + */ + dev_info(dev, "No peripheral charge ports (err:%d)\n", ret); + return -ENODEV; + } + + if (!cros_pchg_cmd_ver_check(charger)) { + dev_err(dev, "EC_CMD_PCHG version %d isn't available.\n", + pchg_cmd_version); + return -EOPNOTSUPP; + } + + num_ports = ret; + if (num_ports > EC_PCHG_MAX_PORTS) { + dev_err(dev, "Too many peripheral charge ports (%d)\n", + num_ports); + return -ENOBUFS; + } + + dev_info(dev, "%d peripheral charge ports found\n", num_ports); + + for (i = 0; i < num_ports; i++) { + struct power_supply_config psy_cfg = {}; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + port->charger = charger; + port->port_number = i; + snprintf(port->name, sizeof(port->name), PCHG_DIR_NAME, i); + + psy_desc = &port->psy_desc; + psy_desc->name = port->name; + psy_desc->type = POWER_SUPPLY_TYPE_BATTERY; + psy_desc->get_property = cros_pchg_get_prop; + psy_desc->external_power_changed = NULL; + psy_desc->properties = cros_pchg_props; + psy_desc->num_properties = ARRAY_SIZE(cros_pchg_props); + psy_cfg.drv_data = port; + + psy = devm_power_supply_register(dev, psy_desc, &psy_cfg); + if (IS_ERR(psy)) + return dev_err_probe(dev, PTR_ERR(psy), + "Failed to register power supply\n"); + port->psy = psy; + + charger->ports[charger->num_registered_psy++] = port; + } + + if (!charger->num_registered_psy) + return -ENODEV; + + nb = &charger->notifier; + nb->notifier_call = cros_ec_notify; + ret = blocking_notifier_chain_register(&ec_dev->ec_dev->event_notifier, + nb); + if (ret < 0) + dev_err(dev, "Failed to register notifier (err:%d)\n", ret); + + return 0; +} + +static struct platform_driver cros_pchg_driver = { + .driver = { + .name = DRV_NAME, + }, + .probe = cros_pchg_probe +}; + +module_platform_driver(cros_pchg_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("ChromeOS EC peripheral device charger"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 45f53afc46e2..271bd87bff0a 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4228,6 +4228,7 @@ enum ec_device_event { EC_DEVICE_EVENT_TRACKPAD, EC_DEVICE_EVENT_DSP, EC_DEVICE_EVENT_WIFI, + EC_DEVICE_EVENT_WLC, }; enum ec_device_event_param { @@ -5460,6 +5461,72 @@ struct ec_response_rollback_info { /* Issue AP reset */ #define EC_CMD_AP_RESET 0x0125 +/** + * Get the number of peripheral charge ports + */ +#define EC_CMD_PCHG_COUNT 0x0134 + +#define EC_PCHG_MAX_PORTS 8 + +struct ec_response_pchg_count { + uint8_t port_count; +} __ec_align1; + +/** + * Get the status of a peripheral charge port + */ +#define EC_CMD_PCHG 0x0135 + +struct ec_params_pchg { + uint8_t port; +} __ec_align1; + +struct ec_response_pchg { + uint32_t error; /* enum pchg_error */ + uint8_t state; /* enum pchg_state state */ + uint8_t battery_percentage; + uint8_t unused0; + uint8_t unused1; + /* Fields added in version 1 */ + uint32_t fw_version; + uint32_t dropped_event_count; +} __ec_align2; + +enum pchg_state { + /* Charger is reset and not initialized. */ + PCHG_STATE_RESET = 0, + /* Charger is initialized or disabled. */ + PCHG_STATE_INITIALIZED, + /* Charger is enabled and ready to detect a device. */ + PCHG_STATE_ENABLED, + /* Device is in proximity. */ + PCHG_STATE_DETECTED, + /* Device is being charged. */ + PCHG_STATE_CHARGING, + /* Device is fully charged. It implies DETECTED (& not charging). */ + PCHG_STATE_FULL, + /* In download (a.k.a. firmware update) mode */ + PCHG_STATE_DOWNLOAD, + /* In download mode. Ready for receiving data. */ + PCHG_STATE_DOWNLOADING, + /* Device is ready for data communication. */ + PCHG_STATE_CONNECTED, + /* Put no more entry below */ + PCHG_STATE_COUNT, +}; + +#define EC_PCHG_STATE_TEXT { \ + [PCHG_STATE_RESET] = "RESET", \ + [PCHG_STATE_INITIALIZED] = "INITIALIZED", \ + [PCHG_STATE_ENABLED] = "ENABLED", \ + [PCHG_STATE_DETECTED] = "DETECTED", \ + [PCHG_STATE_CHARGING] = "CHARGING", \ + [PCHG_STATE_FULL] = "FULL", \ + [PCHG_STATE_DOWNLOAD] = "DOWNLOAD", \ + [PCHG_STATE_DOWNLOADING] = "DOWNLOADING", \ + [PCHG_STATE_CONNECTED] = "CONNECTED", \ + } + /*****************************************************************************/ /* Voltage regulator controls */ -- cgit v1.2.3 From e042aa532c84d18ff13291d00620502ce7a38dda Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 16 Jul 2021 09:18:21 +0000 Subject: bpf: Fix pointer arithmetic mask tightening under state pruning In 7fedb63a8307 ("bpf: Tighten speculative pointer arithmetic mask") we narrowed the offset mask for unprivileged pointer arithmetic in order to mitigate a corner case where in the speculative domain it is possible to advance, for example, the map value pointer by up to value_size-1 out-of- bounds in order to leak kernel memory via side-channel to user space. The verifier's state pruning for scalars leaves one corner case open where in the first verification path R_x holds an unknown scalar with an aux->alu_limit of e.g. 7, and in a second verification path that same register R_x, here denoted as R_x', holds an unknown scalar which has tighter bounds and would thus satisfy range_within(R_x, R_x') as well as tnum_in(R_x, R_x') for state pruning, yielding an aux->alu_limit of 3: Given the second path fits the register constraints for pruning, the final generated mask from aux->alu_limit will remain at 7. While technically not wrong for the non-speculative domain, it would however be possible to craft similar cases where the mask would be too wide as in 7fedb63a8307. One way to fix it is to detect the presence of unknown scalar map pointer arithmetic and force a deeper search on unknown scalars to ensure that we do not run into a masking mismatch. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + kernel/bpf/verifier.c | 27 +++++++++++++++++---------- 2 files changed, 18 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e774ecc1cd1f..7ba7e800d472 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -414,6 +414,7 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ + bool explore_alu_limits; bool allow_ptr_leaks; bool allow_uninit_stack; bool allow_ptr_to_map_access; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8a7a28b4cfb9..657062cb4d85 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6561,6 +6561,12 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; alu_state |= ptr_is_dst_reg ? BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + + /* Limit pruning on unknown scalars to enable deep search for + * potential masking differences from other program paths. + */ + if (!off_is_imm) + env->explore_alu_limits = true; } err = update_alu_sanitation_state(aux, alu_state, alu_limit); @@ -9936,8 +9942,8 @@ next: } /* Returns true if (rold safe implies rcur safe) */ -static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, - struct bpf_id_pair *idmap) +static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, + struct bpf_reg_state *rcur, struct bpf_id_pair *idmap) { bool equal; @@ -9963,6 +9969,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; switch (rold->type) { case SCALAR_VALUE: + if (env->explore_alu_limits) + return false; if (rcur->type == SCALAR_VALUE) { if (!rold->precise && !rcur->precise) return true; @@ -10053,9 +10061,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; } -static bool stacksafe(struct bpf_func_state *old, - struct bpf_func_state *cur, - struct bpf_id_pair *idmap) +static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, + struct bpf_func_state *cur, struct bpf_id_pair *idmap) { int i, spi; @@ -10100,9 +10107,8 @@ static bool stacksafe(struct bpf_func_state *old, continue; if (old->stack[spi].slot_type[0] != STACK_SPILL) continue; - if (!regsafe(&old->stack[spi].spilled_ptr, - &cur->stack[spi].spilled_ptr, - idmap)) + if (!regsafe(env, &old->stack[spi].spilled_ptr, + &cur->stack[spi].spilled_ptr, idmap)) /* when explored and current stack slot are both storing * spilled registers, check that stored pointers types * are the same as well. @@ -10159,10 +10165,11 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch)); for (i = 0; i < MAX_BPF_REG; i++) - if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch)) + if (!regsafe(env, &old->regs[i], &cur->regs[i], + env->idmap_scratch)) return false; - if (!stacksafe(old, cur, env->idmap_scratch)) + if (!stacksafe(env, old, cur, env->idmap_scratch)) return false; if (!refsafe(old, cur)) -- cgit v1.2.3 From e3d18cee258b898017b298b5b93f8134dd62aee3 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 13 Jul 2021 11:52:51 +0100 Subject: locking/atomic: centralize generated headers The generated atomic headers are only intended to be included directly by , but are spread across include/linux/ and include/asm-generic/, where people mnay be encouraged to include them. This patch centralizes them under include/linux/atomic/. Other than the header guards and hashes, there is no change to any of the generated headers as a result of this patch. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210713105253.7615-4-mark.rutland@arm.com --- include/asm-generic/atomic-instrumented.h | 1337 --------------- include/asm-generic/atomic-long.h | 1014 ------------ include/linux/atomic-arch-fallback.h | 2361 --------------------------- include/linux/atomic.h | 7 +- include/linux/atomic/atomic-arch-fallback.h | 2361 +++++++++++++++++++++++++++ include/linux/atomic/atomic-instrumented.h | 1337 +++++++++++++++ include/linux/atomic/atomic-long.h | 1014 ++++++++++++ scripts/atomic/check-atomics.sh | 6 +- scripts/atomic/gen-atomic-instrumented.sh | 6 +- scripts/atomic/gen-atomic-long.sh | 6 +- scripts/atomic/gen-atomics.sh | 6 +- 11 files changed, 4727 insertions(+), 4728 deletions(-) delete mode 100644 include/asm-generic/atomic-instrumented.h delete mode 100644 include/asm-generic/atomic-long.h delete mode 100644 include/linux/atomic-arch-fallback.h create mode 100644 include/linux/atomic/atomic-arch-fallback.h create mode 100644 include/linux/atomic/atomic-instrumented.h create mode 100644 include/linux/atomic/atomic-long.h (limited to 'include/linux') diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h deleted file mode 100644 index bc45af52c93b..000000000000 --- a/include/asm-generic/atomic-instrumented.h +++ /dev/null @@ -1,1337 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -// Generated by scripts/atomic/gen-atomic-instrumented.sh -// DO NOT MODIFY THIS FILE DIRECTLY - -/* - * This file provides wrappers with KASAN instrumentation for atomic operations. - * To use this functionality an arch's atomic.h file needs to define all - * atomic operations with arch_ prefix (e.g. arch_atomic_read()) and include - * this file at the end. This file provides atomic_read() that forwards to - * arch_atomic_read() for actual atomic operation. - * Note: if an arch atomic operation is implemented by means of other atomic - * operations (e.g. atomic_read()/atomic_cmpxchg() loop), then it needs to use - * arch_ variants (i.e. arch_atomic_read()/arch_atomic_cmpxchg()) to avoid - * double instrumentation. - */ -#ifndef _ASM_GENERIC_ATOMIC_INSTRUMENTED_H -#define _ASM_GENERIC_ATOMIC_INSTRUMENTED_H - -#include -#include -#include - -static __always_inline int -atomic_read(const atomic_t *v) -{ - instrument_atomic_read(v, sizeof(*v)); - return arch_atomic_read(v); -} - -static __always_inline int -atomic_read_acquire(const atomic_t *v) -{ - instrument_atomic_read(v, sizeof(*v)); - return arch_atomic_read_acquire(v); -} - -static __always_inline void -atomic_set(atomic_t *v, int i) -{ - instrument_atomic_write(v, sizeof(*v)); - arch_atomic_set(v, i); -} - -static __always_inline void -atomic_set_release(atomic_t *v, int i) -{ - instrument_atomic_write(v, sizeof(*v)); - arch_atomic_set_release(v, i); -} - -static __always_inline void -atomic_add(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic_add(i, v); -} - -static __always_inline int -atomic_add_return(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_add_return(i, v); -} - -static __always_inline int -atomic_add_return_acquire(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_add_return_acquire(i, v); -} - -static __always_inline int -atomic_add_return_release(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_add_return_release(i, v); -} - -static __always_inline int -atomic_add_return_relaxed(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_add_return_relaxed(i, v); -} - -static __always_inline int -atomic_fetch_add(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_add(i, v); -} - -static __always_inline int -atomic_fetch_add_acquire(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_add_acquire(i, v); -} - -static __always_inline int -atomic_fetch_add_release(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_add_release(i, v); -} - -static __always_inline int -atomic_fetch_add_relaxed(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_add_relaxed(i, v); -} - -static __always_inline void -atomic_sub(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic_sub(i, v); -} - -static __always_inline int -atomic_sub_return(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_sub_return(i, v); -} - -static __always_inline int -atomic_sub_return_acquire(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_sub_return_acquire(i, v); -} - -static __always_inline int -atomic_sub_return_release(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_sub_return_release(i, v); -} - -static __always_inline int -atomic_sub_return_relaxed(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_sub_return_relaxed(i, v); -} - -static __always_inline int -atomic_fetch_sub(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_sub(i, v); -} - -static __always_inline int -atomic_fetch_sub_acquire(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_sub_acquire(i, v); -} - -static __always_inline int -atomic_fetch_sub_release(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_sub_release(i, v); -} - -static __always_inline int -atomic_fetch_sub_relaxed(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_sub_relaxed(i, v); -} - -static __always_inline void -atomic_inc(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic_inc(v); -} - -static __always_inline int -atomic_inc_return(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_inc_return(v); -} - -static __always_inline int -atomic_inc_return_acquire(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_inc_return_acquire(v); -} - -static __always_inline int -atomic_inc_return_release(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_inc_return_release(v); -} - -static __always_inline int -atomic_inc_return_relaxed(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_inc_return_relaxed(v); -} - -static __always_inline int -atomic_fetch_inc(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_inc(v); -} - -static __always_inline int -atomic_fetch_inc_acquire(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_inc_acquire(v); -} - -static __always_inline int -atomic_fetch_inc_release(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_inc_release(v); -} - -static __always_inline int -atomic_fetch_inc_relaxed(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_inc_relaxed(v); -} - -static __always_inline void -atomic_dec(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic_dec(v); -} - -static __always_inline int -atomic_dec_return(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_dec_return(v); -} - -static __always_inline int -atomic_dec_return_acquire(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_dec_return_acquire(v); -} - -static __always_inline int -atomic_dec_return_release(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_dec_return_release(v); -} - -static __always_inline int -atomic_dec_return_relaxed(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_dec_return_relaxed(v); -} - -static __always_inline int -atomic_fetch_dec(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_dec(v); -} - -static __always_inline int -atomic_fetch_dec_acquire(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_dec_acquire(v); -} - -static __always_inline int -atomic_fetch_dec_release(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_dec_release(v); -} - -static __always_inline int -atomic_fetch_dec_relaxed(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_dec_relaxed(v); -} - -static __always_inline void -atomic_and(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic_and(i, v); -} - -static __always_inline int -atomic_fetch_and(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_and(i, v); -} - -static __always_inline int -atomic_fetch_and_acquire(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_and_acquire(i, v); -} - -static __always_inline int -atomic_fetch_and_release(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_and_release(i, v); -} - -static __always_inline int -atomic_fetch_and_relaxed(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_and_relaxed(i, v); -} - -static __always_inline void -atomic_andnot(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic_andnot(i, v); -} - -static __always_inline int -atomic_fetch_andnot(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_andnot(i, v); -} - -static __always_inline int -atomic_fetch_andnot_acquire(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_andnot_acquire(i, v); -} - -static __always_inline int -atomic_fetch_andnot_release(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_andnot_release(i, v); -} - -static __always_inline int -atomic_fetch_andnot_relaxed(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_andnot_relaxed(i, v); -} - -static __always_inline void -atomic_or(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic_or(i, v); -} - -static __always_inline int -atomic_fetch_or(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_or(i, v); -} - -static __always_inline int -atomic_fetch_or_acquire(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_or_acquire(i, v); -} - -static __always_inline int -atomic_fetch_or_release(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_or_release(i, v); -} - -static __always_inline int -atomic_fetch_or_relaxed(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_or_relaxed(i, v); -} - -static __always_inline void -atomic_xor(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic_xor(i, v); -} - -static __always_inline int -atomic_fetch_xor(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_xor(i, v); -} - -static __always_inline int -atomic_fetch_xor_acquire(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_xor_acquire(i, v); -} - -static __always_inline int -atomic_fetch_xor_release(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_xor_release(i, v); -} - -static __always_inline int -atomic_fetch_xor_relaxed(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_xor_relaxed(i, v); -} - -static __always_inline int -atomic_xchg(atomic_t *v, int i) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_xchg(v, i); -} - -static __always_inline int -atomic_xchg_acquire(atomic_t *v, int i) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_xchg_acquire(v, i); -} - -static __always_inline int -atomic_xchg_release(atomic_t *v, int i) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_xchg_release(v, i); -} - -static __always_inline int -atomic_xchg_relaxed(atomic_t *v, int i) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_xchg_relaxed(v, i); -} - -static __always_inline int -atomic_cmpxchg(atomic_t *v, int old, int new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_cmpxchg(v, old, new); -} - -static __always_inline int -atomic_cmpxchg_acquire(atomic_t *v, int old, int new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_cmpxchg_acquire(v, old, new); -} - -static __always_inline int -atomic_cmpxchg_release(atomic_t *v, int old, int new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_cmpxchg_release(v, old, new); -} - -static __always_inline int -atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_cmpxchg_relaxed(v, old, new); -} - -static __always_inline bool -atomic_try_cmpxchg(atomic_t *v, int *old, int new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); - return arch_atomic_try_cmpxchg(v, old, new); -} - -static __always_inline bool -atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); - return arch_atomic_try_cmpxchg_acquire(v, old, new); -} - -static __always_inline bool -atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); - return arch_atomic_try_cmpxchg_release(v, old, new); -} - -static __always_inline bool -atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); - return arch_atomic_try_cmpxchg_relaxed(v, old, new); -} - -static __always_inline bool -atomic_sub_and_test(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_sub_and_test(i, v); -} - -static __always_inline bool -atomic_dec_and_test(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_dec_and_test(v); -} - -static __always_inline bool -atomic_inc_and_test(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_inc_and_test(v); -} - -static __always_inline bool -atomic_add_negative(int i, atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_add_negative(i, v); -} - -static __always_inline int -atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_fetch_add_unless(v, a, u); -} - -static __always_inline bool -atomic_add_unless(atomic_t *v, int a, int u) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_add_unless(v, a, u); -} - -static __always_inline bool -atomic_inc_not_zero(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_inc_not_zero(v); -} - -static __always_inline bool -atomic_inc_unless_negative(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_inc_unless_negative(v); -} - -static __always_inline bool -atomic_dec_unless_positive(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_dec_unless_positive(v); -} - -static __always_inline int -atomic_dec_if_positive(atomic_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic_dec_if_positive(v); -} - -static __always_inline s64 -atomic64_read(const atomic64_t *v) -{ - instrument_atomic_read(v, sizeof(*v)); - return arch_atomic64_read(v); -} - -static __always_inline s64 -atomic64_read_acquire(const atomic64_t *v) -{ - instrument_atomic_read(v, sizeof(*v)); - return arch_atomic64_read_acquire(v); -} - -static __always_inline void -atomic64_set(atomic64_t *v, s64 i) -{ - instrument_atomic_write(v, sizeof(*v)); - arch_atomic64_set(v, i); -} - -static __always_inline void -atomic64_set_release(atomic64_t *v, s64 i) -{ - instrument_atomic_write(v, sizeof(*v)); - arch_atomic64_set_release(v, i); -} - -static __always_inline void -atomic64_add(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic64_add(i, v); -} - -static __always_inline s64 -atomic64_add_return(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_add_return(i, v); -} - -static __always_inline s64 -atomic64_add_return_acquire(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_add_return_acquire(i, v); -} - -static __always_inline s64 -atomic64_add_return_release(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_add_return_release(i, v); -} - -static __always_inline s64 -atomic64_add_return_relaxed(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_add_return_relaxed(i, v); -} - -static __always_inline s64 -atomic64_fetch_add(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_add(i, v); -} - -static __always_inline s64 -atomic64_fetch_add_acquire(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_add_acquire(i, v); -} - -static __always_inline s64 -atomic64_fetch_add_release(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_add_release(i, v); -} - -static __always_inline s64 -atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_add_relaxed(i, v); -} - -static __always_inline void -atomic64_sub(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic64_sub(i, v); -} - -static __always_inline s64 -atomic64_sub_return(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_sub_return(i, v); -} - -static __always_inline s64 -atomic64_sub_return_acquire(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_sub_return_acquire(i, v); -} - -static __always_inline s64 -atomic64_sub_return_release(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_sub_return_release(i, v); -} - -static __always_inline s64 -atomic64_sub_return_relaxed(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_sub_return_relaxed(i, v); -} - -static __always_inline s64 -atomic64_fetch_sub(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_sub(i, v); -} - -static __always_inline s64 -atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_sub_acquire(i, v); -} - -static __always_inline s64 -atomic64_fetch_sub_release(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_sub_release(i, v); -} - -static __always_inline s64 -atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_sub_relaxed(i, v); -} - -static __always_inline void -atomic64_inc(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic64_inc(v); -} - -static __always_inline s64 -atomic64_inc_return(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_inc_return(v); -} - -static __always_inline s64 -atomic64_inc_return_acquire(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_inc_return_acquire(v); -} - -static __always_inline s64 -atomic64_inc_return_release(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_inc_return_release(v); -} - -static __always_inline s64 -atomic64_inc_return_relaxed(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_inc_return_relaxed(v); -} - -static __always_inline s64 -atomic64_fetch_inc(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_inc(v); -} - -static __always_inline s64 -atomic64_fetch_inc_acquire(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_inc_acquire(v); -} - -static __always_inline s64 -atomic64_fetch_inc_release(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_inc_release(v); -} - -static __always_inline s64 -atomic64_fetch_inc_relaxed(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_inc_relaxed(v); -} - -static __always_inline void -atomic64_dec(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic64_dec(v); -} - -static __always_inline s64 -atomic64_dec_return(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_dec_return(v); -} - -static __always_inline s64 -atomic64_dec_return_acquire(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_dec_return_acquire(v); -} - -static __always_inline s64 -atomic64_dec_return_release(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_dec_return_release(v); -} - -static __always_inline s64 -atomic64_dec_return_relaxed(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_dec_return_relaxed(v); -} - -static __always_inline s64 -atomic64_fetch_dec(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_dec(v); -} - -static __always_inline s64 -atomic64_fetch_dec_acquire(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_dec_acquire(v); -} - -static __always_inline s64 -atomic64_fetch_dec_release(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_dec_release(v); -} - -static __always_inline s64 -atomic64_fetch_dec_relaxed(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_dec_relaxed(v); -} - -static __always_inline void -atomic64_and(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic64_and(i, v); -} - -static __always_inline s64 -atomic64_fetch_and(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_and(i, v); -} - -static __always_inline s64 -atomic64_fetch_and_acquire(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_and_acquire(i, v); -} - -static __always_inline s64 -atomic64_fetch_and_release(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_and_release(i, v); -} - -static __always_inline s64 -atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_and_relaxed(i, v); -} - -static __always_inline void -atomic64_andnot(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic64_andnot(i, v); -} - -static __always_inline s64 -atomic64_fetch_andnot(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_andnot(i, v); -} - -static __always_inline s64 -atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_andnot_acquire(i, v); -} - -static __always_inline s64 -atomic64_fetch_andnot_release(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_andnot_release(i, v); -} - -static __always_inline s64 -atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_andnot_relaxed(i, v); -} - -static __always_inline void -atomic64_or(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic64_or(i, v); -} - -static __always_inline s64 -atomic64_fetch_or(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_or(i, v); -} - -static __always_inline s64 -atomic64_fetch_or_acquire(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_or_acquire(i, v); -} - -static __always_inline s64 -atomic64_fetch_or_release(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_or_release(i, v); -} - -static __always_inline s64 -atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_or_relaxed(i, v); -} - -static __always_inline void -atomic64_xor(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - arch_atomic64_xor(i, v); -} - -static __always_inline s64 -atomic64_fetch_xor(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_xor(i, v); -} - -static __always_inline s64 -atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_xor_acquire(i, v); -} - -static __always_inline s64 -atomic64_fetch_xor_release(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_xor_release(i, v); -} - -static __always_inline s64 -atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_xor_relaxed(i, v); -} - -static __always_inline s64 -atomic64_xchg(atomic64_t *v, s64 i) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_xchg(v, i); -} - -static __always_inline s64 -atomic64_xchg_acquire(atomic64_t *v, s64 i) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_xchg_acquire(v, i); -} - -static __always_inline s64 -atomic64_xchg_release(atomic64_t *v, s64 i) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_xchg_release(v, i); -} - -static __always_inline s64 -atomic64_xchg_relaxed(atomic64_t *v, s64 i) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_xchg_relaxed(v, i); -} - -static __always_inline s64 -atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_cmpxchg(v, old, new); -} - -static __always_inline s64 -atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_cmpxchg_acquire(v, old, new); -} - -static __always_inline s64 -atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_cmpxchg_release(v, old, new); -} - -static __always_inline s64 -atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_cmpxchg_relaxed(v, old, new); -} - -static __always_inline bool -atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); - return arch_atomic64_try_cmpxchg(v, old, new); -} - -static __always_inline bool -atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); - return arch_atomic64_try_cmpxchg_acquire(v, old, new); -} - -static __always_inline bool -atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); - return arch_atomic64_try_cmpxchg_release(v, old, new); -} - -static __always_inline bool -atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) -{ - instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); - return arch_atomic64_try_cmpxchg_relaxed(v, old, new); -} - -static __always_inline bool -atomic64_sub_and_test(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_sub_and_test(i, v); -} - -static __always_inline bool -atomic64_dec_and_test(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_dec_and_test(v); -} - -static __always_inline bool -atomic64_inc_and_test(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_inc_and_test(v); -} - -static __always_inline bool -atomic64_add_negative(s64 i, atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_add_negative(i, v); -} - -static __always_inline s64 -atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_fetch_add_unless(v, a, u); -} - -static __always_inline bool -atomic64_add_unless(atomic64_t *v, s64 a, s64 u) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_add_unless(v, a, u); -} - -static __always_inline bool -atomic64_inc_not_zero(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_inc_not_zero(v); -} - -static __always_inline bool -atomic64_inc_unless_negative(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_inc_unless_negative(v); -} - -static __always_inline bool -atomic64_dec_unless_positive(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_dec_unless_positive(v); -} - -static __always_inline s64 -atomic64_dec_if_positive(atomic64_t *v) -{ - instrument_atomic_read_write(v, sizeof(*v)); - return arch_atomic64_dec_if_positive(v); -} - -#define xchg(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_xchg(__ai_ptr, __VA_ARGS__); \ -}) - -#define xchg_acquire(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_xchg_acquire(__ai_ptr, __VA_ARGS__); \ -}) - -#define xchg_release(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_xchg_release(__ai_ptr, __VA_ARGS__); \ -}) - -#define xchg_relaxed(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_xchg_relaxed(__ai_ptr, __VA_ARGS__); \ -}) - -#define cmpxchg(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg(__ai_ptr, __VA_ARGS__); \ -}) - -#define cmpxchg_acquire(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \ -}) - -#define cmpxchg_release(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ -}) - -#define cmpxchg_relaxed(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \ -}) - -#define cmpxchg64(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \ -}) - -#define cmpxchg64_acquire(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \ -}) - -#define cmpxchg64_release(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ -}) - -#define cmpxchg64_relaxed(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \ -}) - -#define try_cmpxchg(ptr, oldp, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ - arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ -}) - -#define try_cmpxchg_acquire(ptr, oldp, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ - arch_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ -}) - -#define try_cmpxchg_release(ptr, oldp, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ - arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ -}) - -#define try_cmpxchg_relaxed(ptr, oldp, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ - arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ -}) - -#define cmpxchg_local(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg_local(__ai_ptr, __VA_ARGS__); \ -}) - -#define cmpxchg64_local(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \ -}) - -#define sync_cmpxchg(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ -}) - -#define cmpxchg_double(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ - arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \ -}) - - -#define cmpxchg_double_local(ptr, ...) \ -({ \ - typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ - arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \ -}) - -#endif /* _ASM_GENERIC_ATOMIC_INSTRUMENTED_H */ -// 1d7c3a25aca5c7fb031c307be4c3d24c7b48fcd5 diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h deleted file mode 100644 index 073cf40f431b..000000000000 --- a/include/asm-generic/atomic-long.h +++ /dev/null @@ -1,1014 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -// Generated by scripts/atomic/gen-atomic-long.sh -// DO NOT MODIFY THIS FILE DIRECTLY - -#ifndef _ASM_GENERIC_ATOMIC_LONG_H -#define _ASM_GENERIC_ATOMIC_LONG_H - -#include -#include - -#ifdef CONFIG_64BIT -typedef atomic64_t atomic_long_t; -#define ATOMIC_LONG_INIT(i) ATOMIC64_INIT(i) -#define atomic_long_cond_read_acquire atomic64_cond_read_acquire -#define atomic_long_cond_read_relaxed atomic64_cond_read_relaxed -#else -typedef atomic_t atomic_long_t; -#define ATOMIC_LONG_INIT(i) ATOMIC_INIT(i) -#define atomic_long_cond_read_acquire atomic_cond_read_acquire -#define atomic_long_cond_read_relaxed atomic_cond_read_relaxed -#endif - -#ifdef CONFIG_64BIT - -static __always_inline long -atomic_long_read(const atomic_long_t *v) -{ - return atomic64_read(v); -} - -static __always_inline long -atomic_long_read_acquire(const atomic_long_t *v) -{ - return atomic64_read_acquire(v); -} - -static __always_inline void -atomic_long_set(atomic_long_t *v, long i) -{ - atomic64_set(v, i); -} - -static __always_inline void -atomic_long_set_release(atomic_long_t *v, long i) -{ - atomic64_set_release(v, i); -} - -static __always_inline void -atomic_long_add(long i, atomic_long_t *v) -{ - atomic64_add(i, v); -} - -static __always_inline long -atomic_long_add_return(long i, atomic_long_t *v) -{ - return atomic64_add_return(i, v); -} - -static __always_inline long -atomic_long_add_return_acquire(long i, atomic_long_t *v) -{ - return atomic64_add_return_acquire(i, v); -} - -static __always_inline long -atomic_long_add_return_release(long i, atomic_long_t *v) -{ - return atomic64_add_return_release(i, v); -} - -static __always_inline long -atomic_long_add_return_relaxed(long i, atomic_long_t *v) -{ - return atomic64_add_return_relaxed(i, v); -} - -static __always_inline long -atomic_long_fetch_add(long i, atomic_long_t *v) -{ - return atomic64_fetch_add(i, v); -} - -static __always_inline long -atomic_long_fetch_add_acquire(long i, atomic_long_t *v) -{ - return atomic64_fetch_add_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_add_release(long i, atomic_long_t *v) -{ - return atomic64_fetch_add_release(i, v); -} - -static __always_inline long -atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) -{ - return atomic64_fetch_add_relaxed(i, v); -} - -static __always_inline void -atomic_long_sub(long i, atomic_long_t *v) -{ - atomic64_sub(i, v); -} - -static __always_inline long -atomic_long_sub_return(long i, atomic_long_t *v) -{ - return atomic64_sub_return(i, v); -} - -static __always_inline long -atomic_long_sub_return_acquire(long i, atomic_long_t *v) -{ - return atomic64_sub_return_acquire(i, v); -} - -static __always_inline long -atomic_long_sub_return_release(long i, atomic_long_t *v) -{ - return atomic64_sub_return_release(i, v); -} - -static __always_inline long -atomic_long_sub_return_relaxed(long i, atomic_long_t *v) -{ - return atomic64_sub_return_relaxed(i, v); -} - -static __always_inline long -atomic_long_fetch_sub(long i, atomic_long_t *v) -{ - return atomic64_fetch_sub(i, v); -} - -static __always_inline long -atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) -{ - return atomic64_fetch_sub_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_sub_release(long i, atomic_long_t *v) -{ - return atomic64_fetch_sub_release(i, v); -} - -static __always_inline long -atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) -{ - return atomic64_fetch_sub_relaxed(i, v); -} - -static __always_inline void -atomic_long_inc(atomic_long_t *v) -{ - atomic64_inc(v); -} - -static __always_inline long -atomic_long_inc_return(atomic_long_t *v) -{ - return atomic64_inc_return(v); -} - -static __always_inline long -atomic_long_inc_return_acquire(atomic_long_t *v) -{ - return atomic64_inc_return_acquire(v); -} - -static __always_inline long -atomic_long_inc_return_release(atomic_long_t *v) -{ - return atomic64_inc_return_release(v); -} - -static __always_inline long -atomic_long_inc_return_relaxed(atomic_long_t *v) -{ - return atomic64_inc_return_relaxed(v); -} - -static __always_inline long -atomic_long_fetch_inc(atomic_long_t *v) -{ - return atomic64_fetch_inc(v); -} - -static __always_inline long -atomic_long_fetch_inc_acquire(atomic_long_t *v) -{ - return atomic64_fetch_inc_acquire(v); -} - -static __always_inline long -atomic_long_fetch_inc_release(atomic_long_t *v) -{ - return atomic64_fetch_inc_release(v); -} - -static __always_inline long -atomic_long_fetch_inc_relaxed(atomic_long_t *v) -{ - return atomic64_fetch_inc_relaxed(v); -} - -static __always_inline void -atomic_long_dec(atomic_long_t *v) -{ - atomic64_dec(v); -} - -static __always_inline long -atomic_long_dec_return(atomic_long_t *v) -{ - return atomic64_dec_return(v); -} - -static __always_inline long -atomic_long_dec_return_acquire(atomic_long_t *v) -{ - return atomic64_dec_return_acquire(v); -} - -static __always_inline long -atomic_long_dec_return_release(atomic_long_t *v) -{ - return atomic64_dec_return_release(v); -} - -static __always_inline long -atomic_long_dec_return_relaxed(atomic_long_t *v) -{ - return atomic64_dec_return_relaxed(v); -} - -static __always_inline long -atomic_long_fetch_dec(atomic_long_t *v) -{ - return atomic64_fetch_dec(v); -} - -static __always_inline long -atomic_long_fetch_dec_acquire(atomic_long_t *v) -{ - return atomic64_fetch_dec_acquire(v); -} - -static __always_inline long -atomic_long_fetch_dec_release(atomic_long_t *v) -{ - return atomic64_fetch_dec_release(v); -} - -static __always_inline long -atomic_long_fetch_dec_relaxed(atomic_long_t *v) -{ - return atomic64_fetch_dec_relaxed(v); -} - -static __always_inline void -atomic_long_and(long i, atomic_long_t *v) -{ - atomic64_and(i, v); -} - -static __always_inline long -atomic_long_fetch_and(long i, atomic_long_t *v) -{ - return atomic64_fetch_and(i, v); -} - -static __always_inline long -atomic_long_fetch_and_acquire(long i, atomic_long_t *v) -{ - return atomic64_fetch_and_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_and_release(long i, atomic_long_t *v) -{ - return atomic64_fetch_and_release(i, v); -} - -static __always_inline long -atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) -{ - return atomic64_fetch_and_relaxed(i, v); -} - -static __always_inline void -atomic_long_andnot(long i, atomic_long_t *v) -{ - atomic64_andnot(i, v); -} - -static __always_inline long -atomic_long_fetch_andnot(long i, atomic_long_t *v) -{ - return atomic64_fetch_andnot(i, v); -} - -static __always_inline long -atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) -{ - return atomic64_fetch_andnot_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_andnot_release(long i, atomic_long_t *v) -{ - return atomic64_fetch_andnot_release(i, v); -} - -static __always_inline long -atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) -{ - return atomic64_fetch_andnot_relaxed(i, v); -} - -static __always_inline void -atomic_long_or(long i, atomic_long_t *v) -{ - atomic64_or(i, v); -} - -static __always_inline long -atomic_long_fetch_or(long i, atomic_long_t *v) -{ - return atomic64_fetch_or(i, v); -} - -static __always_inline long -atomic_long_fetch_or_acquire(long i, atomic_long_t *v) -{ - return atomic64_fetch_or_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_or_release(long i, atomic_long_t *v) -{ - return atomic64_fetch_or_release(i, v); -} - -static __always_inline long -atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) -{ - return atomic64_fetch_or_relaxed(i, v); -} - -static __always_inline void -atomic_long_xor(long i, atomic_long_t *v) -{ - atomic64_xor(i, v); -} - -static __always_inline long -atomic_long_fetch_xor(long i, atomic_long_t *v) -{ - return atomic64_fetch_xor(i, v); -} - -static __always_inline long -atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) -{ - return atomic64_fetch_xor_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_xor_release(long i, atomic_long_t *v) -{ - return atomic64_fetch_xor_release(i, v); -} - -static __always_inline long -atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) -{ - return atomic64_fetch_xor_relaxed(i, v); -} - -static __always_inline long -atomic_long_xchg(atomic_long_t *v, long i) -{ - return atomic64_xchg(v, i); -} - -static __always_inline long -atomic_long_xchg_acquire(atomic_long_t *v, long i) -{ - return atomic64_xchg_acquire(v, i); -} - -static __always_inline long -atomic_long_xchg_release(atomic_long_t *v, long i) -{ - return atomic64_xchg_release(v, i); -} - -static __always_inline long -atomic_long_xchg_relaxed(atomic_long_t *v, long i) -{ - return atomic64_xchg_relaxed(v, i); -} - -static __always_inline long -atomic_long_cmpxchg(atomic_long_t *v, long old, long new) -{ - return atomic64_cmpxchg(v, old, new); -} - -static __always_inline long -atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) -{ - return atomic64_cmpxchg_acquire(v, old, new); -} - -static __always_inline long -atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) -{ - return atomic64_cmpxchg_release(v, old, new); -} - -static __always_inline long -atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) -{ - return atomic64_cmpxchg_relaxed(v, old, new); -} - -static __always_inline bool -atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) -{ - return atomic64_try_cmpxchg(v, (s64 *)old, new); -} - -static __always_inline bool -atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) -{ - return atomic64_try_cmpxchg_acquire(v, (s64 *)old, new); -} - -static __always_inline bool -atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) -{ - return atomic64_try_cmpxchg_release(v, (s64 *)old, new); -} - -static __always_inline bool -atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) -{ - return atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new); -} - -static __always_inline bool -atomic_long_sub_and_test(long i, atomic_long_t *v) -{ - return atomic64_sub_and_test(i, v); -} - -static __always_inline bool -atomic_long_dec_and_test(atomic_long_t *v) -{ - return atomic64_dec_and_test(v); -} - -static __always_inline bool -atomic_long_inc_and_test(atomic_long_t *v) -{ - return atomic64_inc_and_test(v); -} - -static __always_inline bool -atomic_long_add_negative(long i, atomic_long_t *v) -{ - return atomic64_add_negative(i, v); -} - -static __always_inline long -atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) -{ - return atomic64_fetch_add_unless(v, a, u); -} - -static __always_inline bool -atomic_long_add_unless(atomic_long_t *v, long a, long u) -{ - return atomic64_add_unless(v, a, u); -} - -static __always_inline bool -atomic_long_inc_not_zero(atomic_long_t *v) -{ - return atomic64_inc_not_zero(v); -} - -static __always_inline bool -atomic_long_inc_unless_negative(atomic_long_t *v) -{ - return atomic64_inc_unless_negative(v); -} - -static __always_inline bool -atomic_long_dec_unless_positive(atomic_long_t *v) -{ - return atomic64_dec_unless_positive(v); -} - -static __always_inline long -atomic_long_dec_if_positive(atomic_long_t *v) -{ - return atomic64_dec_if_positive(v); -} - -#else /* CONFIG_64BIT */ - -static __always_inline long -atomic_long_read(const atomic_long_t *v) -{ - return atomic_read(v); -} - -static __always_inline long -atomic_long_read_acquire(const atomic_long_t *v) -{ - return atomic_read_acquire(v); -} - -static __always_inline void -atomic_long_set(atomic_long_t *v, long i) -{ - atomic_set(v, i); -} - -static __always_inline void -atomic_long_set_release(atomic_long_t *v, long i) -{ - atomic_set_release(v, i); -} - -static __always_inline void -atomic_long_add(long i, atomic_long_t *v) -{ - atomic_add(i, v); -} - -static __always_inline long -atomic_long_add_return(long i, atomic_long_t *v) -{ - return atomic_add_return(i, v); -} - -static __always_inline long -atomic_long_add_return_acquire(long i, atomic_long_t *v) -{ - return atomic_add_return_acquire(i, v); -} - -static __always_inline long -atomic_long_add_return_release(long i, atomic_long_t *v) -{ - return atomic_add_return_release(i, v); -} - -static __always_inline long -atomic_long_add_return_relaxed(long i, atomic_long_t *v) -{ - return atomic_add_return_relaxed(i, v); -} - -static __always_inline long -atomic_long_fetch_add(long i, atomic_long_t *v) -{ - return atomic_fetch_add(i, v); -} - -static __always_inline long -atomic_long_fetch_add_acquire(long i, atomic_long_t *v) -{ - return atomic_fetch_add_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_add_release(long i, atomic_long_t *v) -{ - return atomic_fetch_add_release(i, v); -} - -static __always_inline long -atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) -{ - return atomic_fetch_add_relaxed(i, v); -} - -static __always_inline void -atomic_long_sub(long i, atomic_long_t *v) -{ - atomic_sub(i, v); -} - -static __always_inline long -atomic_long_sub_return(long i, atomic_long_t *v) -{ - return atomic_sub_return(i, v); -} - -static __always_inline long -atomic_long_sub_return_acquire(long i, atomic_long_t *v) -{ - return atomic_sub_return_acquire(i, v); -} - -static __always_inline long -atomic_long_sub_return_release(long i, atomic_long_t *v) -{ - return atomic_sub_return_release(i, v); -} - -static __always_inline long -atomic_long_sub_return_relaxed(long i, atomic_long_t *v) -{ - return atomic_sub_return_relaxed(i, v); -} - -static __always_inline long -atomic_long_fetch_sub(long i, atomic_long_t *v) -{ - return atomic_fetch_sub(i, v); -} - -static __always_inline long -atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) -{ - return atomic_fetch_sub_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_sub_release(long i, atomic_long_t *v) -{ - return atomic_fetch_sub_release(i, v); -} - -static __always_inline long -atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) -{ - return atomic_fetch_sub_relaxed(i, v); -} - -static __always_inline void -atomic_long_inc(atomic_long_t *v) -{ - atomic_inc(v); -} - -static __always_inline long -atomic_long_inc_return(atomic_long_t *v) -{ - return atomic_inc_return(v); -} - -static __always_inline long -atomic_long_inc_return_acquire(atomic_long_t *v) -{ - return atomic_inc_return_acquire(v); -} - -static __always_inline long -atomic_long_inc_return_release(atomic_long_t *v) -{ - return atomic_inc_return_release(v); -} - -static __always_inline long -atomic_long_inc_return_relaxed(atomic_long_t *v) -{ - return atomic_inc_return_relaxed(v); -} - -static __always_inline long -atomic_long_fetch_inc(atomic_long_t *v) -{ - return atomic_fetch_inc(v); -} - -static __always_inline long -atomic_long_fetch_inc_acquire(atomic_long_t *v) -{ - return atomic_fetch_inc_acquire(v); -} - -static __always_inline long -atomic_long_fetch_inc_release(atomic_long_t *v) -{ - return atomic_fetch_inc_release(v); -} - -static __always_inline long -atomic_long_fetch_inc_relaxed(atomic_long_t *v) -{ - return atomic_fetch_inc_relaxed(v); -} - -static __always_inline void -atomic_long_dec(atomic_long_t *v) -{ - atomic_dec(v); -} - -static __always_inline long -atomic_long_dec_return(atomic_long_t *v) -{ - return atomic_dec_return(v); -} - -static __always_inline long -atomic_long_dec_return_acquire(atomic_long_t *v) -{ - return atomic_dec_return_acquire(v); -} - -static __always_inline long -atomic_long_dec_return_release(atomic_long_t *v) -{ - return atomic_dec_return_release(v); -} - -static __always_inline long -atomic_long_dec_return_relaxed(atomic_long_t *v) -{ - return atomic_dec_return_relaxed(v); -} - -static __always_inline long -atomic_long_fetch_dec(atomic_long_t *v) -{ - return atomic_fetch_dec(v); -} - -static __always_inline long -atomic_long_fetch_dec_acquire(atomic_long_t *v) -{ - return atomic_fetch_dec_acquire(v); -} - -static __always_inline long -atomic_long_fetch_dec_release(atomic_long_t *v) -{ - return atomic_fetch_dec_release(v); -} - -static __always_inline long -atomic_long_fetch_dec_relaxed(atomic_long_t *v) -{ - return atomic_fetch_dec_relaxed(v); -} - -static __always_inline void -atomic_long_and(long i, atomic_long_t *v) -{ - atomic_and(i, v); -} - -static __always_inline long -atomic_long_fetch_and(long i, atomic_long_t *v) -{ - return atomic_fetch_and(i, v); -} - -static __always_inline long -atomic_long_fetch_and_acquire(long i, atomic_long_t *v) -{ - return atomic_fetch_and_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_and_release(long i, atomic_long_t *v) -{ - return atomic_fetch_and_release(i, v); -} - -static __always_inline long -atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) -{ - return atomic_fetch_and_relaxed(i, v); -} - -static __always_inline void -atomic_long_andnot(long i, atomic_long_t *v) -{ - atomic_andnot(i, v); -} - -static __always_inline long -atomic_long_fetch_andnot(long i, atomic_long_t *v) -{ - return atomic_fetch_andnot(i, v); -} - -static __always_inline long -atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) -{ - return atomic_fetch_andnot_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_andnot_release(long i, atomic_long_t *v) -{ - return atomic_fetch_andnot_release(i, v); -} - -static __always_inline long -atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) -{ - return atomic_fetch_andnot_relaxed(i, v); -} - -static __always_inline void -atomic_long_or(long i, atomic_long_t *v) -{ - atomic_or(i, v); -} - -static __always_inline long -atomic_long_fetch_or(long i, atomic_long_t *v) -{ - return atomic_fetch_or(i, v); -} - -static __always_inline long -atomic_long_fetch_or_acquire(long i, atomic_long_t *v) -{ - return atomic_fetch_or_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_or_release(long i, atomic_long_t *v) -{ - return atomic_fetch_or_release(i, v); -} - -static __always_inline long -atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) -{ - return atomic_fetch_or_relaxed(i, v); -} - -static __always_inline void -atomic_long_xor(long i, atomic_long_t *v) -{ - atomic_xor(i, v); -} - -static __always_inline long -atomic_long_fetch_xor(long i, atomic_long_t *v) -{ - return atomic_fetch_xor(i, v); -} - -static __always_inline long -atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) -{ - return atomic_fetch_xor_acquire(i, v); -} - -static __always_inline long -atomic_long_fetch_xor_release(long i, atomic_long_t *v) -{ - return atomic_fetch_xor_release(i, v); -} - -static __always_inline long -atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) -{ - return atomic_fetch_xor_relaxed(i, v); -} - -static __always_inline long -atomic_long_xchg(atomic_long_t *v, long i) -{ - return atomic_xchg(v, i); -} - -static __always_inline long -atomic_long_xchg_acquire(atomic_long_t *v, long i) -{ - return atomic_xchg_acquire(v, i); -} - -static __always_inline long -atomic_long_xchg_release(atomic_long_t *v, long i) -{ - return atomic_xchg_release(v, i); -} - -static __always_inline long -atomic_long_xchg_relaxed(atomic_long_t *v, long i) -{ - return atomic_xchg_relaxed(v, i); -} - -static __always_inline long -atomic_long_cmpxchg(atomic_long_t *v, long old, long new) -{ - return atomic_cmpxchg(v, old, new); -} - -static __always_inline long -atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) -{ - return atomic_cmpxchg_acquire(v, old, new); -} - -static __always_inline long -atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) -{ - return atomic_cmpxchg_release(v, old, new); -} - -static __always_inline long -atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) -{ - return atomic_cmpxchg_relaxed(v, old, new); -} - -static __always_inline bool -atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) -{ - return atomic_try_cmpxchg(v, (int *)old, new); -} - -static __always_inline bool -atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) -{ - return atomic_try_cmpxchg_acquire(v, (int *)old, new); -} - -static __always_inline bool -atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) -{ - return atomic_try_cmpxchg_release(v, (int *)old, new); -} - -static __always_inline bool -atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) -{ - return atomic_try_cmpxchg_relaxed(v, (int *)old, new); -} - -static __always_inline bool -atomic_long_sub_and_test(long i, atomic_long_t *v) -{ - return atomic_sub_and_test(i, v); -} - -static __always_inline bool -atomic_long_dec_and_test(atomic_long_t *v) -{ - return atomic_dec_and_test(v); -} - -static __always_inline bool -atomic_long_inc_and_test(atomic_long_t *v) -{ - return atomic_inc_and_test(v); -} - -static __always_inline bool -atomic_long_add_negative(long i, atomic_long_t *v) -{ - return atomic_add_negative(i, v); -} - -static __always_inline long -atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) -{ - return atomic_fetch_add_unless(v, a, u); -} - -static __always_inline bool -atomic_long_add_unless(atomic_long_t *v, long a, long u) -{ - return atomic_add_unless(v, a, u); -} - -static __always_inline bool -atomic_long_inc_not_zero(atomic_long_t *v) -{ - return atomic_inc_not_zero(v); -} - -static __always_inline bool -atomic_long_inc_unless_negative(atomic_long_t *v) -{ - return atomic_inc_unless_negative(v); -} - -static __always_inline bool -atomic_long_dec_unless_positive(atomic_long_t *v) -{ - return atomic_dec_unless_positive(v); -} - -static __always_inline long -atomic_long_dec_if_positive(atomic_long_t *v) -{ - return atomic_dec_if_positive(v); -} - -#endif /* CONFIG_64BIT */ -#endif /* _ASM_GENERIC_ATOMIC_LONG_H */ -// a624200981f552b2c6be4f32fe44da8289f30d87 diff --git a/include/linux/atomic-arch-fallback.h b/include/linux/atomic-arch-fallback.h deleted file mode 100644 index a3dba31df01e..000000000000 --- a/include/linux/atomic-arch-fallback.h +++ /dev/null @@ -1,2361 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -// Generated by scripts/atomic/gen-atomic-fallback.sh -// DO NOT MODIFY THIS FILE DIRECTLY - -#ifndef _LINUX_ATOMIC_FALLBACK_H -#define _LINUX_ATOMIC_FALLBACK_H - -#include - -#ifndef arch_xchg_relaxed -#define arch_xchg_acquire arch_xchg -#define arch_xchg_release arch_xchg -#define arch_xchg_relaxed arch_xchg -#else /* arch_xchg_relaxed */ - -#ifndef arch_xchg_acquire -#define arch_xchg_acquire(...) \ - __atomic_op_acquire(arch_xchg, __VA_ARGS__) -#endif - -#ifndef arch_xchg_release -#define arch_xchg_release(...) \ - __atomic_op_release(arch_xchg, __VA_ARGS__) -#endif - -#ifndef arch_xchg -#define arch_xchg(...) \ - __atomic_op_fence(arch_xchg, __VA_ARGS__) -#endif - -#endif /* arch_xchg_relaxed */ - -#ifndef arch_cmpxchg_relaxed -#define arch_cmpxchg_acquire arch_cmpxchg -#define arch_cmpxchg_release arch_cmpxchg -#define arch_cmpxchg_relaxed arch_cmpxchg -#else /* arch_cmpxchg_relaxed */ - -#ifndef arch_cmpxchg_acquire -#define arch_cmpxchg_acquire(...) \ - __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) -#endif - -#ifndef arch_cmpxchg_release -#define arch_cmpxchg_release(...) \ - __atomic_op_release(arch_cmpxchg, __VA_ARGS__) -#endif - -#ifndef arch_cmpxchg -#define arch_cmpxchg(...) \ - __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) -#endif - -#endif /* arch_cmpxchg_relaxed */ - -#ifndef arch_cmpxchg64_relaxed -#define arch_cmpxchg64_acquire arch_cmpxchg64 -#define arch_cmpxchg64_release arch_cmpxchg64 -#define arch_cmpxchg64_relaxed arch_cmpxchg64 -#else /* arch_cmpxchg64_relaxed */ - -#ifndef arch_cmpxchg64_acquire -#define arch_cmpxchg64_acquire(...) \ - __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) -#endif - -#ifndef arch_cmpxchg64_release -#define arch_cmpxchg64_release(...) \ - __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) -#endif - -#ifndef arch_cmpxchg64 -#define arch_cmpxchg64(...) \ - __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) -#endif - -#endif /* arch_cmpxchg64_relaxed */ - -#ifndef arch_try_cmpxchg_relaxed -#ifdef arch_try_cmpxchg -#define arch_try_cmpxchg_acquire arch_try_cmpxchg -#define arch_try_cmpxchg_release arch_try_cmpxchg -#define arch_try_cmpxchg_relaxed arch_try_cmpxchg -#endif /* arch_try_cmpxchg */ - -#ifndef arch_try_cmpxchg -#define arch_try_cmpxchg(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = arch_cmpxchg((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* arch_try_cmpxchg */ - -#ifndef arch_try_cmpxchg_acquire -#define arch_try_cmpxchg_acquire(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = arch_cmpxchg_acquire((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* arch_try_cmpxchg_acquire */ - -#ifndef arch_try_cmpxchg_release -#define arch_try_cmpxchg_release(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = arch_cmpxchg_release((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* arch_try_cmpxchg_release */ - -#ifndef arch_try_cmpxchg_relaxed -#define arch_try_cmpxchg_relaxed(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = arch_cmpxchg_relaxed((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* arch_try_cmpxchg_relaxed */ - -#else /* arch_try_cmpxchg_relaxed */ - -#ifndef arch_try_cmpxchg_acquire -#define arch_try_cmpxchg_acquire(...) \ - __atomic_op_acquire(arch_try_cmpxchg, __VA_ARGS__) -#endif - -#ifndef arch_try_cmpxchg_release -#define arch_try_cmpxchg_release(...) \ - __atomic_op_release(arch_try_cmpxchg, __VA_ARGS__) -#endif - -#ifndef arch_try_cmpxchg -#define arch_try_cmpxchg(...) \ - __atomic_op_fence(arch_try_cmpxchg, __VA_ARGS__) -#endif - -#endif /* arch_try_cmpxchg_relaxed */ - -#ifndef arch_atomic_read_acquire -static __always_inline int -arch_atomic_read_acquire(const atomic_t *v) -{ - return smp_load_acquire(&(v)->counter); -} -#define arch_atomic_read_acquire arch_atomic_read_acquire -#endif - -#ifndef arch_atomic_set_release -static __always_inline void -arch_atomic_set_release(atomic_t *v, int i) -{ - smp_store_release(&(v)->counter, i); -} -#define arch_atomic_set_release arch_atomic_set_release -#endif - -#ifndef arch_atomic_add_return_relaxed -#define arch_atomic_add_return_acquire arch_atomic_add_return -#define arch_atomic_add_return_release arch_atomic_add_return -#define arch_atomic_add_return_relaxed arch_atomic_add_return -#else /* arch_atomic_add_return_relaxed */ - -#ifndef arch_atomic_add_return_acquire -static __always_inline int -arch_atomic_add_return_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_add_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_add_return_acquire arch_atomic_add_return_acquire -#endif - -#ifndef arch_atomic_add_return_release -static __always_inline int -arch_atomic_add_return_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_add_return_relaxed(i, v); -} -#define arch_atomic_add_return_release arch_atomic_add_return_release -#endif - -#ifndef arch_atomic_add_return -static __always_inline int -arch_atomic_add_return(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_add_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_add_return arch_atomic_add_return -#endif - -#endif /* arch_atomic_add_return_relaxed */ - -#ifndef arch_atomic_fetch_add_relaxed -#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add -#define arch_atomic_fetch_add_release arch_atomic_fetch_add -#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add -#else /* arch_atomic_fetch_add_relaxed */ - -#ifndef arch_atomic_fetch_add_acquire -static __always_inline int -arch_atomic_fetch_add_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_add_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire -#endif - -#ifndef arch_atomic_fetch_add_release -static __always_inline int -arch_atomic_fetch_add_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_add_relaxed(i, v); -} -#define arch_atomic_fetch_add_release arch_atomic_fetch_add_release -#endif - -#ifndef arch_atomic_fetch_add -static __always_inline int -arch_atomic_fetch_add(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_add_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_add arch_atomic_fetch_add -#endif - -#endif /* arch_atomic_fetch_add_relaxed */ - -#ifndef arch_atomic_sub_return_relaxed -#define arch_atomic_sub_return_acquire arch_atomic_sub_return -#define arch_atomic_sub_return_release arch_atomic_sub_return -#define arch_atomic_sub_return_relaxed arch_atomic_sub_return -#else /* arch_atomic_sub_return_relaxed */ - -#ifndef arch_atomic_sub_return_acquire -static __always_inline int -arch_atomic_sub_return_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_sub_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire -#endif - -#ifndef arch_atomic_sub_return_release -static __always_inline int -arch_atomic_sub_return_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_sub_return_relaxed(i, v); -} -#define arch_atomic_sub_return_release arch_atomic_sub_return_release -#endif - -#ifndef arch_atomic_sub_return -static __always_inline int -arch_atomic_sub_return(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_sub_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_sub_return arch_atomic_sub_return -#endif - -#endif /* arch_atomic_sub_return_relaxed */ - -#ifndef arch_atomic_fetch_sub_relaxed -#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub -#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub -#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub -#else /* arch_atomic_fetch_sub_relaxed */ - -#ifndef arch_atomic_fetch_sub_acquire -static __always_inline int -arch_atomic_fetch_sub_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_sub_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire -#endif - -#ifndef arch_atomic_fetch_sub_release -static __always_inline int -arch_atomic_fetch_sub_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_sub_relaxed(i, v); -} -#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release -#endif - -#ifndef arch_atomic_fetch_sub -static __always_inline int -arch_atomic_fetch_sub(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_sub_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_sub arch_atomic_fetch_sub -#endif - -#endif /* arch_atomic_fetch_sub_relaxed */ - -#ifndef arch_atomic_inc -static __always_inline void -arch_atomic_inc(atomic_t *v) -{ - arch_atomic_add(1, v); -} -#define arch_atomic_inc arch_atomic_inc -#endif - -#ifndef arch_atomic_inc_return_relaxed -#ifdef arch_atomic_inc_return -#define arch_atomic_inc_return_acquire arch_atomic_inc_return -#define arch_atomic_inc_return_release arch_atomic_inc_return -#define arch_atomic_inc_return_relaxed arch_atomic_inc_return -#endif /* arch_atomic_inc_return */ - -#ifndef arch_atomic_inc_return -static __always_inline int -arch_atomic_inc_return(atomic_t *v) -{ - return arch_atomic_add_return(1, v); -} -#define arch_atomic_inc_return arch_atomic_inc_return -#endif - -#ifndef arch_atomic_inc_return_acquire -static __always_inline int -arch_atomic_inc_return_acquire(atomic_t *v) -{ - return arch_atomic_add_return_acquire(1, v); -} -#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire -#endif - -#ifndef arch_atomic_inc_return_release -static __always_inline int -arch_atomic_inc_return_release(atomic_t *v) -{ - return arch_atomic_add_return_release(1, v); -} -#define arch_atomic_inc_return_release arch_atomic_inc_return_release -#endif - -#ifndef arch_atomic_inc_return_relaxed -static __always_inline int -arch_atomic_inc_return_relaxed(atomic_t *v) -{ - return arch_atomic_add_return_relaxed(1, v); -} -#define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed -#endif - -#else /* arch_atomic_inc_return_relaxed */ - -#ifndef arch_atomic_inc_return_acquire -static __always_inline int -arch_atomic_inc_return_acquire(atomic_t *v) -{ - int ret = arch_atomic_inc_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire -#endif - -#ifndef arch_atomic_inc_return_release -static __always_inline int -arch_atomic_inc_return_release(atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_inc_return_relaxed(v); -} -#define arch_atomic_inc_return_release arch_atomic_inc_return_release -#endif - -#ifndef arch_atomic_inc_return -static __always_inline int -arch_atomic_inc_return(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_inc_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_inc_return arch_atomic_inc_return -#endif - -#endif /* arch_atomic_inc_return_relaxed */ - -#ifndef arch_atomic_fetch_inc_relaxed -#ifdef arch_atomic_fetch_inc -#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc -#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc -#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc -#endif /* arch_atomic_fetch_inc */ - -#ifndef arch_atomic_fetch_inc -static __always_inline int -arch_atomic_fetch_inc(atomic_t *v) -{ - return arch_atomic_fetch_add(1, v); -} -#define arch_atomic_fetch_inc arch_atomic_fetch_inc -#endif - -#ifndef arch_atomic_fetch_inc_acquire -static __always_inline int -arch_atomic_fetch_inc_acquire(atomic_t *v) -{ - return arch_atomic_fetch_add_acquire(1, v); -} -#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire -#endif - -#ifndef arch_atomic_fetch_inc_release -static __always_inline int -arch_atomic_fetch_inc_release(atomic_t *v) -{ - return arch_atomic_fetch_add_release(1, v); -} -#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release -#endif - -#ifndef arch_atomic_fetch_inc_relaxed -static __always_inline int -arch_atomic_fetch_inc_relaxed(atomic_t *v) -{ - return arch_atomic_fetch_add_relaxed(1, v); -} -#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc_relaxed -#endif - -#else /* arch_atomic_fetch_inc_relaxed */ - -#ifndef arch_atomic_fetch_inc_acquire -static __always_inline int -arch_atomic_fetch_inc_acquire(atomic_t *v) -{ - int ret = arch_atomic_fetch_inc_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire -#endif - -#ifndef arch_atomic_fetch_inc_release -static __always_inline int -arch_atomic_fetch_inc_release(atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_inc_relaxed(v); -} -#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release -#endif - -#ifndef arch_atomic_fetch_inc -static __always_inline int -arch_atomic_fetch_inc(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_inc_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_inc arch_atomic_fetch_inc -#endif - -#endif /* arch_atomic_fetch_inc_relaxed */ - -#ifndef arch_atomic_dec -static __always_inline void -arch_atomic_dec(atomic_t *v) -{ - arch_atomic_sub(1, v); -} -#define arch_atomic_dec arch_atomic_dec -#endif - -#ifndef arch_atomic_dec_return_relaxed -#ifdef arch_atomic_dec_return -#define arch_atomic_dec_return_acquire arch_atomic_dec_return -#define arch_atomic_dec_return_release arch_atomic_dec_return -#define arch_atomic_dec_return_relaxed arch_atomic_dec_return -#endif /* arch_atomic_dec_return */ - -#ifndef arch_atomic_dec_return -static __always_inline int -arch_atomic_dec_return(atomic_t *v) -{ - return arch_atomic_sub_return(1, v); -} -#define arch_atomic_dec_return arch_atomic_dec_return -#endif - -#ifndef arch_atomic_dec_return_acquire -static __always_inline int -arch_atomic_dec_return_acquire(atomic_t *v) -{ - return arch_atomic_sub_return_acquire(1, v); -} -#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire -#endif - -#ifndef arch_atomic_dec_return_release -static __always_inline int -arch_atomic_dec_return_release(atomic_t *v) -{ - return arch_atomic_sub_return_release(1, v); -} -#define arch_atomic_dec_return_release arch_atomic_dec_return_release -#endif - -#ifndef arch_atomic_dec_return_relaxed -static __always_inline int -arch_atomic_dec_return_relaxed(atomic_t *v) -{ - return arch_atomic_sub_return_relaxed(1, v); -} -#define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed -#endif - -#else /* arch_atomic_dec_return_relaxed */ - -#ifndef arch_atomic_dec_return_acquire -static __always_inline int -arch_atomic_dec_return_acquire(atomic_t *v) -{ - int ret = arch_atomic_dec_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire -#endif - -#ifndef arch_atomic_dec_return_release -static __always_inline int -arch_atomic_dec_return_release(atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_dec_return_relaxed(v); -} -#define arch_atomic_dec_return_release arch_atomic_dec_return_release -#endif - -#ifndef arch_atomic_dec_return -static __always_inline int -arch_atomic_dec_return(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_dec_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_dec_return arch_atomic_dec_return -#endif - -#endif /* arch_atomic_dec_return_relaxed */ - -#ifndef arch_atomic_fetch_dec_relaxed -#ifdef arch_atomic_fetch_dec -#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec -#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec -#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec -#endif /* arch_atomic_fetch_dec */ - -#ifndef arch_atomic_fetch_dec -static __always_inline int -arch_atomic_fetch_dec(atomic_t *v) -{ - return arch_atomic_fetch_sub(1, v); -} -#define arch_atomic_fetch_dec arch_atomic_fetch_dec -#endif - -#ifndef arch_atomic_fetch_dec_acquire -static __always_inline int -arch_atomic_fetch_dec_acquire(atomic_t *v) -{ - return arch_atomic_fetch_sub_acquire(1, v); -} -#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire -#endif - -#ifndef arch_atomic_fetch_dec_release -static __always_inline int -arch_atomic_fetch_dec_release(atomic_t *v) -{ - return arch_atomic_fetch_sub_release(1, v); -} -#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release -#endif - -#ifndef arch_atomic_fetch_dec_relaxed -static __always_inline int -arch_atomic_fetch_dec_relaxed(atomic_t *v) -{ - return arch_atomic_fetch_sub_relaxed(1, v); -} -#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec_relaxed -#endif - -#else /* arch_atomic_fetch_dec_relaxed */ - -#ifndef arch_atomic_fetch_dec_acquire -static __always_inline int -arch_atomic_fetch_dec_acquire(atomic_t *v) -{ - int ret = arch_atomic_fetch_dec_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire -#endif - -#ifndef arch_atomic_fetch_dec_release -static __always_inline int -arch_atomic_fetch_dec_release(atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_dec_relaxed(v); -} -#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release -#endif - -#ifndef arch_atomic_fetch_dec -static __always_inline int -arch_atomic_fetch_dec(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_dec_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_dec arch_atomic_fetch_dec -#endif - -#endif /* arch_atomic_fetch_dec_relaxed */ - -#ifndef arch_atomic_fetch_and_relaxed -#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and -#define arch_atomic_fetch_and_release arch_atomic_fetch_and -#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and -#else /* arch_atomic_fetch_and_relaxed */ - -#ifndef arch_atomic_fetch_and_acquire -static __always_inline int -arch_atomic_fetch_and_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_and_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire -#endif - -#ifndef arch_atomic_fetch_and_release -static __always_inline int -arch_atomic_fetch_and_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_and_relaxed(i, v); -} -#define arch_atomic_fetch_and_release arch_atomic_fetch_and_release -#endif - -#ifndef arch_atomic_fetch_and -static __always_inline int -arch_atomic_fetch_and(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_and_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_and arch_atomic_fetch_and -#endif - -#endif /* arch_atomic_fetch_and_relaxed */ - -#ifndef arch_atomic_andnot -static __always_inline void -arch_atomic_andnot(int i, atomic_t *v) -{ - arch_atomic_and(~i, v); -} -#define arch_atomic_andnot arch_atomic_andnot -#endif - -#ifndef arch_atomic_fetch_andnot_relaxed -#ifdef arch_atomic_fetch_andnot -#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot -#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot -#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot -#endif /* arch_atomic_fetch_andnot */ - -#ifndef arch_atomic_fetch_andnot -static __always_inline int -arch_atomic_fetch_andnot(int i, atomic_t *v) -{ - return arch_atomic_fetch_and(~i, v); -} -#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot -#endif - -#ifndef arch_atomic_fetch_andnot_acquire -static __always_inline int -arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) -{ - return arch_atomic_fetch_and_acquire(~i, v); -} -#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire -#endif - -#ifndef arch_atomic_fetch_andnot_release -static __always_inline int -arch_atomic_fetch_andnot_release(int i, atomic_t *v) -{ - return arch_atomic_fetch_and_release(~i, v); -} -#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release -#endif - -#ifndef arch_atomic_fetch_andnot_relaxed -static __always_inline int -arch_atomic_fetch_andnot_relaxed(int i, atomic_t *v) -{ - return arch_atomic_fetch_and_relaxed(~i, v); -} -#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed -#endif - -#else /* arch_atomic_fetch_andnot_relaxed */ - -#ifndef arch_atomic_fetch_andnot_acquire -static __always_inline int -arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_andnot_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire -#endif - -#ifndef arch_atomic_fetch_andnot_release -static __always_inline int -arch_atomic_fetch_andnot_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_andnot_relaxed(i, v); -} -#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release -#endif - -#ifndef arch_atomic_fetch_andnot -static __always_inline int -arch_atomic_fetch_andnot(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_andnot_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot -#endif - -#endif /* arch_atomic_fetch_andnot_relaxed */ - -#ifndef arch_atomic_fetch_or_relaxed -#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or -#define arch_atomic_fetch_or_release arch_atomic_fetch_or -#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or -#else /* arch_atomic_fetch_or_relaxed */ - -#ifndef arch_atomic_fetch_or_acquire -static __always_inline int -arch_atomic_fetch_or_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_or_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire -#endif - -#ifndef arch_atomic_fetch_or_release -static __always_inline int -arch_atomic_fetch_or_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_or_relaxed(i, v); -} -#define arch_atomic_fetch_or_release arch_atomic_fetch_or_release -#endif - -#ifndef arch_atomic_fetch_or -static __always_inline int -arch_atomic_fetch_or(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_or_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_or arch_atomic_fetch_or -#endif - -#endif /* arch_atomic_fetch_or_relaxed */ - -#ifndef arch_atomic_fetch_xor_relaxed -#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor -#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor -#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor -#else /* arch_atomic_fetch_xor_relaxed */ - -#ifndef arch_atomic_fetch_xor_acquire -static __always_inline int -arch_atomic_fetch_xor_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_xor_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire -#endif - -#ifndef arch_atomic_fetch_xor_release -static __always_inline int -arch_atomic_fetch_xor_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_xor_relaxed(i, v); -} -#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release -#endif - -#ifndef arch_atomic_fetch_xor -static __always_inline int -arch_atomic_fetch_xor(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_xor_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_xor arch_atomic_fetch_xor -#endif - -#endif /* arch_atomic_fetch_xor_relaxed */ - -#ifndef arch_atomic_xchg_relaxed -#define arch_atomic_xchg_acquire arch_atomic_xchg -#define arch_atomic_xchg_release arch_atomic_xchg -#define arch_atomic_xchg_relaxed arch_atomic_xchg -#else /* arch_atomic_xchg_relaxed */ - -#ifndef arch_atomic_xchg_acquire -static __always_inline int -arch_atomic_xchg_acquire(atomic_t *v, int i) -{ - int ret = arch_atomic_xchg_relaxed(v, i); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_xchg_acquire arch_atomic_xchg_acquire -#endif - -#ifndef arch_atomic_xchg_release -static __always_inline int -arch_atomic_xchg_release(atomic_t *v, int i) -{ - __atomic_release_fence(); - return arch_atomic_xchg_relaxed(v, i); -} -#define arch_atomic_xchg_release arch_atomic_xchg_release -#endif - -#ifndef arch_atomic_xchg -static __always_inline int -arch_atomic_xchg(atomic_t *v, int i) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_xchg_relaxed(v, i); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_xchg arch_atomic_xchg -#endif - -#endif /* arch_atomic_xchg_relaxed */ - -#ifndef arch_atomic_cmpxchg_relaxed -#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg -#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg -#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg -#else /* arch_atomic_cmpxchg_relaxed */ - -#ifndef arch_atomic_cmpxchg_acquire -static __always_inline int -arch_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) -{ - int ret = arch_atomic_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire -#endif - -#ifndef arch_atomic_cmpxchg_release -static __always_inline int -arch_atomic_cmpxchg_release(atomic_t *v, int old, int new) -{ - __atomic_release_fence(); - return arch_atomic_cmpxchg_relaxed(v, old, new); -} -#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release -#endif - -#ifndef arch_atomic_cmpxchg -static __always_inline int -arch_atomic_cmpxchg(atomic_t *v, int old, int new) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_cmpxchg arch_atomic_cmpxchg -#endif - -#endif /* arch_atomic_cmpxchg_relaxed */ - -#ifndef arch_atomic_try_cmpxchg_relaxed -#ifdef arch_atomic_try_cmpxchg -#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg -#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg -#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg -#endif /* arch_atomic_try_cmpxchg */ - -#ifndef arch_atomic_try_cmpxchg -static __always_inline bool -arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = arch_atomic_cmpxchg(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg -#endif - -#ifndef arch_atomic_try_cmpxchg_acquire -static __always_inline bool -arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = arch_atomic_cmpxchg_acquire(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire -#endif - -#ifndef arch_atomic_try_cmpxchg_release -static __always_inline bool -arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = arch_atomic_cmpxchg_release(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release -#endif - -#ifndef arch_atomic_try_cmpxchg_relaxed -static __always_inline bool -arch_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = arch_atomic_cmpxchg_relaxed(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg_relaxed -#endif - -#else /* arch_atomic_try_cmpxchg_relaxed */ - -#ifndef arch_atomic_try_cmpxchg_acquire -static __always_inline bool -arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) -{ - bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire -#endif - -#ifndef arch_atomic_try_cmpxchg_release -static __always_inline bool -arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) -{ - __atomic_release_fence(); - return arch_atomic_try_cmpxchg_relaxed(v, old, new); -} -#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release -#endif - -#ifndef arch_atomic_try_cmpxchg -static __always_inline bool -arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) -{ - bool ret; - __atomic_pre_full_fence(); - ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg -#endif - -#endif /* arch_atomic_try_cmpxchg_relaxed */ - -#ifndef arch_atomic_sub_and_test -/** - * arch_atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -arch_atomic_sub_and_test(int i, atomic_t *v) -{ - return arch_atomic_sub_return(i, v) == 0; -} -#define arch_atomic_sub_and_test arch_atomic_sub_and_test -#endif - -#ifndef arch_atomic_dec_and_test -/** - * arch_atomic_dec_and_test - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static __always_inline bool -arch_atomic_dec_and_test(atomic_t *v) -{ - return arch_atomic_dec_return(v) == 0; -} -#define arch_atomic_dec_and_test arch_atomic_dec_and_test -#endif - -#ifndef arch_atomic_inc_and_test -/** - * arch_atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -arch_atomic_inc_and_test(atomic_t *v) -{ - return arch_atomic_inc_return(v) == 0; -} -#define arch_atomic_inc_and_test arch_atomic_inc_and_test -#endif - -#ifndef arch_atomic_add_negative -/** - * arch_atomic_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer of type atomic_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static __always_inline bool -arch_atomic_add_negative(int i, atomic_t *v) -{ - return arch_atomic_add_return(i, v) < 0; -} -#define arch_atomic_add_negative arch_atomic_add_negative -#endif - -#ifndef arch_atomic_fetch_add_unless -/** - * arch_atomic_fetch_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns original value of @v - */ -static __always_inline int -arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); - - return c; -} -#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless -#endif - -#ifndef arch_atomic_add_unless -/** - * arch_atomic_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, if @v was not already @u. - * Returns true if the addition was done. - */ -static __always_inline bool -arch_atomic_add_unless(atomic_t *v, int a, int u) -{ - return arch_atomic_fetch_add_unless(v, a, u) != u; -} -#define arch_atomic_add_unless arch_atomic_add_unless -#endif - -#ifndef arch_atomic_inc_not_zero -/** - * arch_atomic_inc_not_zero - increment unless the number is zero - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1, if @v is non-zero. - * Returns true if the increment was done. - */ -static __always_inline bool -arch_atomic_inc_not_zero(atomic_t *v) -{ - return arch_atomic_add_unless(v, 1, 0); -} -#define arch_atomic_inc_not_zero arch_atomic_inc_not_zero -#endif - -#ifndef arch_atomic_inc_unless_negative -static __always_inline bool -arch_atomic_inc_unless_negative(atomic_t *v) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c < 0)) - return false; - } while (!arch_atomic_try_cmpxchg(v, &c, c + 1)); - - return true; -} -#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative -#endif - -#ifndef arch_atomic_dec_unless_positive -static __always_inline bool -arch_atomic_dec_unless_positive(atomic_t *v) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c > 0)) - return false; - } while (!arch_atomic_try_cmpxchg(v, &c, c - 1)); - - return true; -} -#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive -#endif - -#ifndef arch_atomic_dec_if_positive -static __always_inline int -arch_atomic_dec_if_positive(atomic_t *v) -{ - int dec, c = arch_atomic_read(v); - - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!arch_atomic_try_cmpxchg(v, &c, dec)); - - return dec; -} -#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive -#endif - -#ifdef CONFIG_GENERIC_ATOMIC64 -#include -#endif - -#ifndef arch_atomic64_read_acquire -static __always_inline s64 -arch_atomic64_read_acquire(const atomic64_t *v) -{ - return smp_load_acquire(&(v)->counter); -} -#define arch_atomic64_read_acquire arch_atomic64_read_acquire -#endif - -#ifndef arch_atomic64_set_release -static __always_inline void -arch_atomic64_set_release(atomic64_t *v, s64 i) -{ - smp_store_release(&(v)->counter, i); -} -#define arch_atomic64_set_release arch_atomic64_set_release -#endif - -#ifndef arch_atomic64_add_return_relaxed -#define arch_atomic64_add_return_acquire arch_atomic64_add_return -#define arch_atomic64_add_return_release arch_atomic64_add_return -#define arch_atomic64_add_return_relaxed arch_atomic64_add_return -#else /* arch_atomic64_add_return_relaxed */ - -#ifndef arch_atomic64_add_return_acquire -static __always_inline s64 -arch_atomic64_add_return_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_add_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire -#endif - -#ifndef arch_atomic64_add_return_release -static __always_inline s64 -arch_atomic64_add_return_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_add_return_relaxed(i, v); -} -#define arch_atomic64_add_return_release arch_atomic64_add_return_release -#endif - -#ifndef arch_atomic64_add_return -static __always_inline s64 -arch_atomic64_add_return(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_add_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_add_return arch_atomic64_add_return -#endif - -#endif /* arch_atomic64_add_return_relaxed */ - -#ifndef arch_atomic64_fetch_add_relaxed -#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add -#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add -#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add -#else /* arch_atomic64_fetch_add_relaxed */ - -#ifndef arch_atomic64_fetch_add_acquire -static __always_inline s64 -arch_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_add_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire -#endif - -#ifndef arch_atomic64_fetch_add_release -static __always_inline s64 -arch_atomic64_fetch_add_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_add_relaxed(i, v); -} -#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release -#endif - -#ifndef arch_atomic64_fetch_add -static __always_inline s64 -arch_atomic64_fetch_add(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_add_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_add arch_atomic64_fetch_add -#endif - -#endif /* arch_atomic64_fetch_add_relaxed */ - -#ifndef arch_atomic64_sub_return_relaxed -#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return -#define arch_atomic64_sub_return_release arch_atomic64_sub_return -#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return -#else /* arch_atomic64_sub_return_relaxed */ - -#ifndef arch_atomic64_sub_return_acquire -static __always_inline s64 -arch_atomic64_sub_return_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_sub_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire -#endif - -#ifndef arch_atomic64_sub_return_release -static __always_inline s64 -arch_atomic64_sub_return_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_sub_return_relaxed(i, v); -} -#define arch_atomic64_sub_return_release arch_atomic64_sub_return_release -#endif - -#ifndef arch_atomic64_sub_return -static __always_inline s64 -arch_atomic64_sub_return(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_sub_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_sub_return arch_atomic64_sub_return -#endif - -#endif /* arch_atomic64_sub_return_relaxed */ - -#ifndef arch_atomic64_fetch_sub_relaxed -#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub -#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub -#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub -#else /* arch_atomic64_fetch_sub_relaxed */ - -#ifndef arch_atomic64_fetch_sub_acquire -static __always_inline s64 -arch_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire -#endif - -#ifndef arch_atomic64_fetch_sub_release -static __always_inline s64 -arch_atomic64_fetch_sub_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_sub_relaxed(i, v); -} -#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release -#endif - -#ifndef arch_atomic64_fetch_sub -static __always_inline s64 -arch_atomic64_fetch_sub(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_sub_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub -#endif - -#endif /* arch_atomic64_fetch_sub_relaxed */ - -#ifndef arch_atomic64_inc -static __always_inline void -arch_atomic64_inc(atomic64_t *v) -{ - arch_atomic64_add(1, v); -} -#define arch_atomic64_inc arch_atomic64_inc -#endif - -#ifndef arch_atomic64_inc_return_relaxed -#ifdef arch_atomic64_inc_return -#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return -#define arch_atomic64_inc_return_release arch_atomic64_inc_return -#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return -#endif /* arch_atomic64_inc_return */ - -#ifndef arch_atomic64_inc_return -static __always_inline s64 -arch_atomic64_inc_return(atomic64_t *v) -{ - return arch_atomic64_add_return(1, v); -} -#define arch_atomic64_inc_return arch_atomic64_inc_return -#endif - -#ifndef arch_atomic64_inc_return_acquire -static __always_inline s64 -arch_atomic64_inc_return_acquire(atomic64_t *v) -{ - return arch_atomic64_add_return_acquire(1, v); -} -#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire -#endif - -#ifndef arch_atomic64_inc_return_release -static __always_inline s64 -arch_atomic64_inc_return_release(atomic64_t *v) -{ - return arch_atomic64_add_return_release(1, v); -} -#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release -#endif - -#ifndef arch_atomic64_inc_return_relaxed -static __always_inline s64 -arch_atomic64_inc_return_relaxed(atomic64_t *v) -{ - return arch_atomic64_add_return_relaxed(1, v); -} -#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed -#endif - -#else /* arch_atomic64_inc_return_relaxed */ - -#ifndef arch_atomic64_inc_return_acquire -static __always_inline s64 -arch_atomic64_inc_return_acquire(atomic64_t *v) -{ - s64 ret = arch_atomic64_inc_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire -#endif - -#ifndef arch_atomic64_inc_return_release -static __always_inline s64 -arch_atomic64_inc_return_release(atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_inc_return_relaxed(v); -} -#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release -#endif - -#ifndef arch_atomic64_inc_return -static __always_inline s64 -arch_atomic64_inc_return(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_inc_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_inc_return arch_atomic64_inc_return -#endif - -#endif /* arch_atomic64_inc_return_relaxed */ - -#ifndef arch_atomic64_fetch_inc_relaxed -#ifdef arch_atomic64_fetch_inc -#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc -#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc -#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc -#endif /* arch_atomic64_fetch_inc */ - -#ifndef arch_atomic64_fetch_inc -static __always_inline s64 -arch_atomic64_fetch_inc(atomic64_t *v) -{ - return arch_atomic64_fetch_add(1, v); -} -#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc -#endif - -#ifndef arch_atomic64_fetch_inc_acquire -static __always_inline s64 -arch_atomic64_fetch_inc_acquire(atomic64_t *v) -{ - return arch_atomic64_fetch_add_acquire(1, v); -} -#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire -#endif - -#ifndef arch_atomic64_fetch_inc_release -static __always_inline s64 -arch_atomic64_fetch_inc_release(atomic64_t *v) -{ - return arch_atomic64_fetch_add_release(1, v); -} -#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release -#endif - -#ifndef arch_atomic64_fetch_inc_relaxed -static __always_inline s64 -arch_atomic64_fetch_inc_relaxed(atomic64_t *v) -{ - return arch_atomic64_fetch_add_relaxed(1, v); -} -#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc_relaxed -#endif - -#else /* arch_atomic64_fetch_inc_relaxed */ - -#ifndef arch_atomic64_fetch_inc_acquire -static __always_inline s64 -arch_atomic64_fetch_inc_acquire(atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_inc_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire -#endif - -#ifndef arch_atomic64_fetch_inc_release -static __always_inline s64 -arch_atomic64_fetch_inc_release(atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_inc_relaxed(v); -} -#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release -#endif - -#ifndef arch_atomic64_fetch_inc -static __always_inline s64 -arch_atomic64_fetch_inc(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_inc_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc -#endif - -#endif /* arch_atomic64_fetch_inc_relaxed */ - -#ifndef arch_atomic64_dec -static __always_inline void -arch_atomic64_dec(atomic64_t *v) -{ - arch_atomic64_sub(1, v); -} -#define arch_atomic64_dec arch_atomic64_dec -#endif - -#ifndef arch_atomic64_dec_return_relaxed -#ifdef arch_atomic64_dec_return -#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return -#define arch_atomic64_dec_return_release arch_atomic64_dec_return -#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return -#endif /* arch_atomic64_dec_return */ - -#ifndef arch_atomic64_dec_return -static __always_inline s64 -arch_atomic64_dec_return(atomic64_t *v) -{ - return arch_atomic64_sub_return(1, v); -} -#define arch_atomic64_dec_return arch_atomic64_dec_return -#endif - -#ifndef arch_atomic64_dec_return_acquire -static __always_inline s64 -arch_atomic64_dec_return_acquire(atomic64_t *v) -{ - return arch_atomic64_sub_return_acquire(1, v); -} -#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire -#endif - -#ifndef arch_atomic64_dec_return_release -static __always_inline s64 -arch_atomic64_dec_return_release(atomic64_t *v) -{ - return arch_atomic64_sub_return_release(1, v); -} -#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release -#endif - -#ifndef arch_atomic64_dec_return_relaxed -static __always_inline s64 -arch_atomic64_dec_return_relaxed(atomic64_t *v) -{ - return arch_atomic64_sub_return_relaxed(1, v); -} -#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed -#endif - -#else /* arch_atomic64_dec_return_relaxed */ - -#ifndef arch_atomic64_dec_return_acquire -static __always_inline s64 -arch_atomic64_dec_return_acquire(atomic64_t *v) -{ - s64 ret = arch_atomic64_dec_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire -#endif - -#ifndef arch_atomic64_dec_return_release -static __always_inline s64 -arch_atomic64_dec_return_release(atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_dec_return_relaxed(v); -} -#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release -#endif - -#ifndef arch_atomic64_dec_return -static __always_inline s64 -arch_atomic64_dec_return(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_dec_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_dec_return arch_atomic64_dec_return -#endif - -#endif /* arch_atomic64_dec_return_relaxed */ - -#ifndef arch_atomic64_fetch_dec_relaxed -#ifdef arch_atomic64_fetch_dec -#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec -#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec -#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec -#endif /* arch_atomic64_fetch_dec */ - -#ifndef arch_atomic64_fetch_dec -static __always_inline s64 -arch_atomic64_fetch_dec(atomic64_t *v) -{ - return arch_atomic64_fetch_sub(1, v); -} -#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec -#endif - -#ifndef arch_atomic64_fetch_dec_acquire -static __always_inline s64 -arch_atomic64_fetch_dec_acquire(atomic64_t *v) -{ - return arch_atomic64_fetch_sub_acquire(1, v); -} -#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire -#endif - -#ifndef arch_atomic64_fetch_dec_release -static __always_inline s64 -arch_atomic64_fetch_dec_release(atomic64_t *v) -{ - return arch_atomic64_fetch_sub_release(1, v); -} -#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release -#endif - -#ifndef arch_atomic64_fetch_dec_relaxed -static __always_inline s64 -arch_atomic64_fetch_dec_relaxed(atomic64_t *v) -{ - return arch_atomic64_fetch_sub_relaxed(1, v); -} -#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec_relaxed -#endif - -#else /* arch_atomic64_fetch_dec_relaxed */ - -#ifndef arch_atomic64_fetch_dec_acquire -static __always_inline s64 -arch_atomic64_fetch_dec_acquire(atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_dec_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire -#endif - -#ifndef arch_atomic64_fetch_dec_release -static __always_inline s64 -arch_atomic64_fetch_dec_release(atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_dec_relaxed(v); -} -#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release -#endif - -#ifndef arch_atomic64_fetch_dec -static __always_inline s64 -arch_atomic64_fetch_dec(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_dec_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec -#endif - -#endif /* arch_atomic64_fetch_dec_relaxed */ - -#ifndef arch_atomic64_fetch_and_relaxed -#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and -#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and -#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and -#else /* arch_atomic64_fetch_and_relaxed */ - -#ifndef arch_atomic64_fetch_and_acquire -static __always_inline s64 -arch_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_and_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire -#endif - -#ifndef arch_atomic64_fetch_and_release -static __always_inline s64 -arch_atomic64_fetch_and_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_and_relaxed(i, v); -} -#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release -#endif - -#ifndef arch_atomic64_fetch_and -static __always_inline s64 -arch_atomic64_fetch_and(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_and_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_and arch_atomic64_fetch_and -#endif - -#endif /* arch_atomic64_fetch_and_relaxed */ - -#ifndef arch_atomic64_andnot -static __always_inline void -arch_atomic64_andnot(s64 i, atomic64_t *v) -{ - arch_atomic64_and(~i, v); -} -#define arch_atomic64_andnot arch_atomic64_andnot -#endif - -#ifndef arch_atomic64_fetch_andnot_relaxed -#ifdef arch_atomic64_fetch_andnot -#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot -#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot -#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot -#endif /* arch_atomic64_fetch_andnot */ - -#ifndef arch_atomic64_fetch_andnot -static __always_inline s64 -arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) -{ - return arch_atomic64_fetch_and(~i, v); -} -#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot -#endif - -#ifndef arch_atomic64_fetch_andnot_acquire -static __always_inline s64 -arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) -{ - return arch_atomic64_fetch_and_acquire(~i, v); -} -#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire -#endif - -#ifndef arch_atomic64_fetch_andnot_release -static __always_inline s64 -arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) -{ - return arch_atomic64_fetch_and_release(~i, v); -} -#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release -#endif - -#ifndef arch_atomic64_fetch_andnot_relaxed -static __always_inline s64 -arch_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) -{ - return arch_atomic64_fetch_and_relaxed(~i, v); -} -#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed -#endif - -#else /* arch_atomic64_fetch_andnot_relaxed */ - -#ifndef arch_atomic64_fetch_andnot_acquire -static __always_inline s64 -arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire -#endif - -#ifndef arch_atomic64_fetch_andnot_release -static __always_inline s64 -arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_andnot_relaxed(i, v); -} -#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release -#endif - -#ifndef arch_atomic64_fetch_andnot -static __always_inline s64 -arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_andnot_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot -#endif - -#endif /* arch_atomic64_fetch_andnot_relaxed */ - -#ifndef arch_atomic64_fetch_or_relaxed -#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or -#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or -#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or -#else /* arch_atomic64_fetch_or_relaxed */ - -#ifndef arch_atomic64_fetch_or_acquire -static __always_inline s64 -arch_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_or_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire -#endif - -#ifndef arch_atomic64_fetch_or_release -static __always_inline s64 -arch_atomic64_fetch_or_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_or_relaxed(i, v); -} -#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release -#endif - -#ifndef arch_atomic64_fetch_or -static __always_inline s64 -arch_atomic64_fetch_or(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_or_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_or arch_atomic64_fetch_or -#endif - -#endif /* arch_atomic64_fetch_or_relaxed */ - -#ifndef arch_atomic64_fetch_xor_relaxed -#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor -#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor -#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor -#else /* arch_atomic64_fetch_xor_relaxed */ - -#ifndef arch_atomic64_fetch_xor_acquire -static __always_inline s64 -arch_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire -#endif - -#ifndef arch_atomic64_fetch_xor_release -static __always_inline s64 -arch_atomic64_fetch_xor_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_xor_relaxed(i, v); -} -#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release -#endif - -#ifndef arch_atomic64_fetch_xor -static __always_inline s64 -arch_atomic64_fetch_xor(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_xor_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor -#endif - -#endif /* arch_atomic64_fetch_xor_relaxed */ - -#ifndef arch_atomic64_xchg_relaxed -#define arch_atomic64_xchg_acquire arch_atomic64_xchg -#define arch_atomic64_xchg_release arch_atomic64_xchg -#define arch_atomic64_xchg_relaxed arch_atomic64_xchg -#else /* arch_atomic64_xchg_relaxed */ - -#ifndef arch_atomic64_xchg_acquire -static __always_inline s64 -arch_atomic64_xchg_acquire(atomic64_t *v, s64 i) -{ - s64 ret = arch_atomic64_xchg_relaxed(v, i); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_xchg_acquire arch_atomic64_xchg_acquire -#endif - -#ifndef arch_atomic64_xchg_release -static __always_inline s64 -arch_atomic64_xchg_release(atomic64_t *v, s64 i) -{ - __atomic_release_fence(); - return arch_atomic64_xchg_relaxed(v, i); -} -#define arch_atomic64_xchg_release arch_atomic64_xchg_release -#endif - -#ifndef arch_atomic64_xchg -static __always_inline s64 -arch_atomic64_xchg(atomic64_t *v, s64 i) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_xchg_relaxed(v, i); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_xchg arch_atomic64_xchg -#endif - -#endif /* arch_atomic64_xchg_relaxed */ - -#ifndef arch_atomic64_cmpxchg_relaxed -#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg -#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg -#define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg -#else /* arch_atomic64_cmpxchg_relaxed */ - -#ifndef arch_atomic64_cmpxchg_acquire -static __always_inline s64 -arch_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) -{ - s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg_acquire -#endif - -#ifndef arch_atomic64_cmpxchg_release -static __always_inline s64 -arch_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) -{ - __atomic_release_fence(); - return arch_atomic64_cmpxchg_relaxed(v, old, new); -} -#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg_release -#endif - -#ifndef arch_atomic64_cmpxchg -static __always_inline s64 -arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg -#endif - -#endif /* arch_atomic64_cmpxchg_relaxed */ - -#ifndef arch_atomic64_try_cmpxchg_relaxed -#ifdef arch_atomic64_try_cmpxchg -#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg -#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg -#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg -#endif /* arch_atomic64_try_cmpxchg */ - -#ifndef arch_atomic64_try_cmpxchg -static __always_inline bool -arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = arch_atomic64_cmpxchg(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg -#endif - -#ifndef arch_atomic64_try_cmpxchg_acquire -static __always_inline bool -arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = arch_atomic64_cmpxchg_acquire(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire -#endif - -#ifndef arch_atomic64_try_cmpxchg_release -static __always_inline bool -arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = arch_atomic64_cmpxchg_release(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release -#endif - -#ifndef arch_atomic64_try_cmpxchg_relaxed -static __always_inline bool -arch_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = arch_atomic64_cmpxchg_relaxed(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg_relaxed -#endif - -#else /* arch_atomic64_try_cmpxchg_relaxed */ - -#ifndef arch_atomic64_try_cmpxchg_acquire -static __always_inline bool -arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) -{ - bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire -#endif - -#ifndef arch_atomic64_try_cmpxchg_release -static __always_inline bool -arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) -{ - __atomic_release_fence(); - return arch_atomic64_try_cmpxchg_relaxed(v, old, new); -} -#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release -#endif - -#ifndef arch_atomic64_try_cmpxchg -static __always_inline bool -arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) -{ - bool ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg -#endif - -#endif /* arch_atomic64_try_cmpxchg_relaxed */ - -#ifndef arch_atomic64_sub_and_test -/** - * arch_atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -arch_atomic64_sub_and_test(s64 i, atomic64_t *v) -{ - return arch_atomic64_sub_return(i, v) == 0; -} -#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test -#endif - -#ifndef arch_atomic64_dec_and_test -/** - * arch_atomic64_dec_and_test - decrement and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static __always_inline bool -arch_atomic64_dec_and_test(atomic64_t *v) -{ - return arch_atomic64_dec_return(v) == 0; -} -#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test -#endif - -#ifndef arch_atomic64_inc_and_test -/** - * arch_atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -arch_atomic64_inc_and_test(atomic64_t *v) -{ - return arch_atomic64_inc_return(v) == 0; -} -#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test -#endif - -#ifndef arch_atomic64_add_negative -/** - * arch_atomic64_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer of type atomic64_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static __always_inline bool -arch_atomic64_add_negative(s64 i, atomic64_t *v) -{ - return arch_atomic64_add_return(i, v) < 0; -} -#define arch_atomic64_add_negative arch_atomic64_add_negative -#endif - -#ifndef arch_atomic64_fetch_add_unless -/** - * arch_atomic64_fetch_add_unless - add unless the number is already a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns original value of @v - */ -static __always_inline s64 -arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) -{ - s64 c = arch_atomic64_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); - - return c; -} -#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless -#endif - -#ifndef arch_atomic64_add_unless -/** - * arch_atomic64_add_unless - add unless the number is already a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, if @v was not already @u. - * Returns true if the addition was done. - */ -static __always_inline bool -arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) -{ - return arch_atomic64_fetch_add_unless(v, a, u) != u; -} -#define arch_atomic64_add_unless arch_atomic64_add_unless -#endif - -#ifndef arch_atomic64_inc_not_zero -/** - * arch_atomic64_inc_not_zero - increment unless the number is zero - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1, if @v is non-zero. - * Returns true if the increment was done. - */ -static __always_inline bool -arch_atomic64_inc_not_zero(atomic64_t *v) -{ - return arch_atomic64_add_unless(v, 1, 0); -} -#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero -#endif - -#ifndef arch_atomic64_inc_unless_negative -static __always_inline bool -arch_atomic64_inc_unless_negative(atomic64_t *v) -{ - s64 c = arch_atomic64_read(v); - - do { - if (unlikely(c < 0)) - return false; - } while (!arch_atomic64_try_cmpxchg(v, &c, c + 1)); - - return true; -} -#define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative -#endif - -#ifndef arch_atomic64_dec_unless_positive -static __always_inline bool -arch_atomic64_dec_unless_positive(atomic64_t *v) -{ - s64 c = arch_atomic64_read(v); - - do { - if (unlikely(c > 0)) - return false; - } while (!arch_atomic64_try_cmpxchg(v, &c, c - 1)); - - return true; -} -#define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive -#endif - -#ifndef arch_atomic64_dec_if_positive -static __always_inline s64 -arch_atomic64_dec_if_positive(atomic64_t *v) -{ - s64 dec, c = arch_atomic64_read(v); - - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); - - return dec; -} -#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive -#endif - -#endif /* _LINUX_ATOMIC_FALLBACK_H */ -// cca554917d7ea73d5e3e7397dd70c484cad9b2c4 diff --git a/include/linux/atomic.h b/include/linux/atomic.h index ed1d3ffd5b9d..1896a58b5aba 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -77,9 +77,8 @@ __ret; \ }) -#include -#include - -#include +#include +#include +#include #endif /* _LINUX_ATOMIC_H */ diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h new file mode 100644 index 000000000000..a3dba31df01e --- /dev/null +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -0,0 +1,2361 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-fallback.sh +// DO NOT MODIFY THIS FILE DIRECTLY + +#ifndef _LINUX_ATOMIC_FALLBACK_H +#define _LINUX_ATOMIC_FALLBACK_H + +#include + +#ifndef arch_xchg_relaxed +#define arch_xchg_acquire arch_xchg +#define arch_xchg_release arch_xchg +#define arch_xchg_relaxed arch_xchg +#else /* arch_xchg_relaxed */ + +#ifndef arch_xchg_acquire +#define arch_xchg_acquire(...) \ + __atomic_op_acquire(arch_xchg, __VA_ARGS__) +#endif + +#ifndef arch_xchg_release +#define arch_xchg_release(...) \ + __atomic_op_release(arch_xchg, __VA_ARGS__) +#endif + +#ifndef arch_xchg +#define arch_xchg(...) \ + __atomic_op_fence(arch_xchg, __VA_ARGS__) +#endif + +#endif /* arch_xchg_relaxed */ + +#ifndef arch_cmpxchg_relaxed +#define arch_cmpxchg_acquire arch_cmpxchg +#define arch_cmpxchg_release arch_cmpxchg +#define arch_cmpxchg_relaxed arch_cmpxchg +#else /* arch_cmpxchg_relaxed */ + +#ifndef arch_cmpxchg_acquire +#define arch_cmpxchg_acquire(...) \ + __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg_release +#define arch_cmpxchg_release(...) \ + __atomic_op_release(arch_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg +#define arch_cmpxchg(...) \ + __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) +#endif + +#endif /* arch_cmpxchg_relaxed */ + +#ifndef arch_cmpxchg64_relaxed +#define arch_cmpxchg64_acquire arch_cmpxchg64 +#define arch_cmpxchg64_release arch_cmpxchg64 +#define arch_cmpxchg64_relaxed arch_cmpxchg64 +#else /* arch_cmpxchg64_relaxed */ + +#ifndef arch_cmpxchg64_acquire +#define arch_cmpxchg64_acquire(...) \ + __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg64_release +#define arch_cmpxchg64_release(...) \ + __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg64 +#define arch_cmpxchg64(...) \ + __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) +#endif + +#endif /* arch_cmpxchg64_relaxed */ + +#ifndef arch_try_cmpxchg_relaxed +#ifdef arch_try_cmpxchg +#define arch_try_cmpxchg_acquire arch_try_cmpxchg +#define arch_try_cmpxchg_release arch_try_cmpxchg +#define arch_try_cmpxchg_relaxed arch_try_cmpxchg +#endif /* arch_try_cmpxchg */ + +#ifndef arch_try_cmpxchg +#define arch_try_cmpxchg(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg */ + +#ifndef arch_try_cmpxchg_acquire +#define arch_try_cmpxchg_acquire(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg_acquire((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg_acquire */ + +#ifndef arch_try_cmpxchg_release +#define arch_try_cmpxchg_release(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg_release((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg_release */ + +#ifndef arch_try_cmpxchg_relaxed +#define arch_try_cmpxchg_relaxed(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg_relaxed((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg_relaxed */ + +#else /* arch_try_cmpxchg_relaxed */ + +#ifndef arch_try_cmpxchg_acquire +#define arch_try_cmpxchg_acquire(...) \ + __atomic_op_acquire(arch_try_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg_release +#define arch_try_cmpxchg_release(...) \ + __atomic_op_release(arch_try_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg +#define arch_try_cmpxchg(...) \ + __atomic_op_fence(arch_try_cmpxchg, __VA_ARGS__) +#endif + +#endif /* arch_try_cmpxchg_relaxed */ + +#ifndef arch_atomic_read_acquire +static __always_inline int +arch_atomic_read_acquire(const atomic_t *v) +{ + return smp_load_acquire(&(v)->counter); +} +#define arch_atomic_read_acquire arch_atomic_read_acquire +#endif + +#ifndef arch_atomic_set_release +static __always_inline void +arch_atomic_set_release(atomic_t *v, int i) +{ + smp_store_release(&(v)->counter, i); +} +#define arch_atomic_set_release arch_atomic_set_release +#endif + +#ifndef arch_atomic_add_return_relaxed +#define arch_atomic_add_return_acquire arch_atomic_add_return +#define arch_atomic_add_return_release arch_atomic_add_return +#define arch_atomic_add_return_relaxed arch_atomic_add_return +#else /* arch_atomic_add_return_relaxed */ + +#ifndef arch_atomic_add_return_acquire +static __always_inline int +arch_atomic_add_return_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_add_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_add_return_acquire arch_atomic_add_return_acquire +#endif + +#ifndef arch_atomic_add_return_release +static __always_inline int +arch_atomic_add_return_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_add_return_relaxed(i, v); +} +#define arch_atomic_add_return_release arch_atomic_add_return_release +#endif + +#ifndef arch_atomic_add_return +static __always_inline int +arch_atomic_add_return(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_add_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_add_return arch_atomic_add_return +#endif + +#endif /* arch_atomic_add_return_relaxed */ + +#ifndef arch_atomic_fetch_add_relaxed +#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add +#define arch_atomic_fetch_add_release arch_atomic_fetch_add +#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add +#else /* arch_atomic_fetch_add_relaxed */ + +#ifndef arch_atomic_fetch_add_acquire +static __always_inline int +arch_atomic_fetch_add_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_add_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire +#endif + +#ifndef arch_atomic_fetch_add_release +static __always_inline int +arch_atomic_fetch_add_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_add_relaxed(i, v); +} +#define arch_atomic_fetch_add_release arch_atomic_fetch_add_release +#endif + +#ifndef arch_atomic_fetch_add +static __always_inline int +arch_atomic_fetch_add(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_add_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_add arch_atomic_fetch_add +#endif + +#endif /* arch_atomic_fetch_add_relaxed */ + +#ifndef arch_atomic_sub_return_relaxed +#define arch_atomic_sub_return_acquire arch_atomic_sub_return +#define arch_atomic_sub_return_release arch_atomic_sub_return +#define arch_atomic_sub_return_relaxed arch_atomic_sub_return +#else /* arch_atomic_sub_return_relaxed */ + +#ifndef arch_atomic_sub_return_acquire +static __always_inline int +arch_atomic_sub_return_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_sub_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire +#endif + +#ifndef arch_atomic_sub_return_release +static __always_inline int +arch_atomic_sub_return_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_sub_return_relaxed(i, v); +} +#define arch_atomic_sub_return_release arch_atomic_sub_return_release +#endif + +#ifndef arch_atomic_sub_return +static __always_inline int +arch_atomic_sub_return(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_sub_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_sub_return arch_atomic_sub_return +#endif + +#endif /* arch_atomic_sub_return_relaxed */ + +#ifndef arch_atomic_fetch_sub_relaxed +#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub +#else /* arch_atomic_fetch_sub_relaxed */ + +#ifndef arch_atomic_fetch_sub_acquire +static __always_inline int +arch_atomic_fetch_sub_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_sub_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire +#endif + +#ifndef arch_atomic_fetch_sub_release +static __always_inline int +arch_atomic_fetch_sub_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_sub_relaxed(i, v); +} +#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release +#endif + +#ifndef arch_atomic_fetch_sub +static __always_inline int +arch_atomic_fetch_sub(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_sub_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_sub arch_atomic_fetch_sub +#endif + +#endif /* arch_atomic_fetch_sub_relaxed */ + +#ifndef arch_atomic_inc +static __always_inline void +arch_atomic_inc(atomic_t *v) +{ + arch_atomic_add(1, v); +} +#define arch_atomic_inc arch_atomic_inc +#endif + +#ifndef arch_atomic_inc_return_relaxed +#ifdef arch_atomic_inc_return +#define arch_atomic_inc_return_acquire arch_atomic_inc_return +#define arch_atomic_inc_return_release arch_atomic_inc_return +#define arch_atomic_inc_return_relaxed arch_atomic_inc_return +#endif /* arch_atomic_inc_return */ + +#ifndef arch_atomic_inc_return +static __always_inline int +arch_atomic_inc_return(atomic_t *v) +{ + return arch_atomic_add_return(1, v); +} +#define arch_atomic_inc_return arch_atomic_inc_return +#endif + +#ifndef arch_atomic_inc_return_acquire +static __always_inline int +arch_atomic_inc_return_acquire(atomic_t *v) +{ + return arch_atomic_add_return_acquire(1, v); +} +#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire +#endif + +#ifndef arch_atomic_inc_return_release +static __always_inline int +arch_atomic_inc_return_release(atomic_t *v) +{ + return arch_atomic_add_return_release(1, v); +} +#define arch_atomic_inc_return_release arch_atomic_inc_return_release +#endif + +#ifndef arch_atomic_inc_return_relaxed +static __always_inline int +arch_atomic_inc_return_relaxed(atomic_t *v) +{ + return arch_atomic_add_return_relaxed(1, v); +} +#define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed +#endif + +#else /* arch_atomic_inc_return_relaxed */ + +#ifndef arch_atomic_inc_return_acquire +static __always_inline int +arch_atomic_inc_return_acquire(atomic_t *v) +{ + int ret = arch_atomic_inc_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire +#endif + +#ifndef arch_atomic_inc_return_release +static __always_inline int +arch_atomic_inc_return_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_inc_return_relaxed(v); +} +#define arch_atomic_inc_return_release arch_atomic_inc_return_release +#endif + +#ifndef arch_atomic_inc_return +static __always_inline int +arch_atomic_inc_return(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_inc_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_inc_return arch_atomic_inc_return +#endif + +#endif /* arch_atomic_inc_return_relaxed */ + +#ifndef arch_atomic_fetch_inc_relaxed +#ifdef arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc +#endif /* arch_atomic_fetch_inc */ + +#ifndef arch_atomic_fetch_inc +static __always_inline int +arch_atomic_fetch_inc(atomic_t *v) +{ + return arch_atomic_fetch_add(1, v); +} +#define arch_atomic_fetch_inc arch_atomic_fetch_inc +#endif + +#ifndef arch_atomic_fetch_inc_acquire +static __always_inline int +arch_atomic_fetch_inc_acquire(atomic_t *v) +{ + return arch_atomic_fetch_add_acquire(1, v); +} +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire +#endif + +#ifndef arch_atomic_fetch_inc_release +static __always_inline int +arch_atomic_fetch_inc_release(atomic_t *v) +{ + return arch_atomic_fetch_add_release(1, v); +} +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release +#endif + +#ifndef arch_atomic_fetch_inc_relaxed +static __always_inline int +arch_atomic_fetch_inc_relaxed(atomic_t *v) +{ + return arch_atomic_fetch_add_relaxed(1, v); +} +#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc_relaxed +#endif + +#else /* arch_atomic_fetch_inc_relaxed */ + +#ifndef arch_atomic_fetch_inc_acquire +static __always_inline int +arch_atomic_fetch_inc_acquire(atomic_t *v) +{ + int ret = arch_atomic_fetch_inc_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire +#endif + +#ifndef arch_atomic_fetch_inc_release +static __always_inline int +arch_atomic_fetch_inc_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_inc_relaxed(v); +} +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release +#endif + +#ifndef arch_atomic_fetch_inc +static __always_inline int +arch_atomic_fetch_inc(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_inc_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_inc arch_atomic_fetch_inc +#endif + +#endif /* arch_atomic_fetch_inc_relaxed */ + +#ifndef arch_atomic_dec +static __always_inline void +arch_atomic_dec(atomic_t *v) +{ + arch_atomic_sub(1, v); +} +#define arch_atomic_dec arch_atomic_dec +#endif + +#ifndef arch_atomic_dec_return_relaxed +#ifdef arch_atomic_dec_return +#define arch_atomic_dec_return_acquire arch_atomic_dec_return +#define arch_atomic_dec_return_release arch_atomic_dec_return +#define arch_atomic_dec_return_relaxed arch_atomic_dec_return +#endif /* arch_atomic_dec_return */ + +#ifndef arch_atomic_dec_return +static __always_inline int +arch_atomic_dec_return(atomic_t *v) +{ + return arch_atomic_sub_return(1, v); +} +#define arch_atomic_dec_return arch_atomic_dec_return +#endif + +#ifndef arch_atomic_dec_return_acquire +static __always_inline int +arch_atomic_dec_return_acquire(atomic_t *v) +{ + return arch_atomic_sub_return_acquire(1, v); +} +#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire +#endif + +#ifndef arch_atomic_dec_return_release +static __always_inline int +arch_atomic_dec_return_release(atomic_t *v) +{ + return arch_atomic_sub_return_release(1, v); +} +#define arch_atomic_dec_return_release arch_atomic_dec_return_release +#endif + +#ifndef arch_atomic_dec_return_relaxed +static __always_inline int +arch_atomic_dec_return_relaxed(atomic_t *v) +{ + return arch_atomic_sub_return_relaxed(1, v); +} +#define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed +#endif + +#else /* arch_atomic_dec_return_relaxed */ + +#ifndef arch_atomic_dec_return_acquire +static __always_inline int +arch_atomic_dec_return_acquire(atomic_t *v) +{ + int ret = arch_atomic_dec_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire +#endif + +#ifndef arch_atomic_dec_return_release +static __always_inline int +arch_atomic_dec_return_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_dec_return_relaxed(v); +} +#define arch_atomic_dec_return_release arch_atomic_dec_return_release +#endif + +#ifndef arch_atomic_dec_return +static __always_inline int +arch_atomic_dec_return(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_dec_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_dec_return arch_atomic_dec_return +#endif + +#endif /* arch_atomic_dec_return_relaxed */ + +#ifndef arch_atomic_fetch_dec_relaxed +#ifdef arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec +#endif /* arch_atomic_fetch_dec */ + +#ifndef arch_atomic_fetch_dec +static __always_inline int +arch_atomic_fetch_dec(atomic_t *v) +{ + return arch_atomic_fetch_sub(1, v); +} +#define arch_atomic_fetch_dec arch_atomic_fetch_dec +#endif + +#ifndef arch_atomic_fetch_dec_acquire +static __always_inline int +arch_atomic_fetch_dec_acquire(atomic_t *v) +{ + return arch_atomic_fetch_sub_acquire(1, v); +} +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire +#endif + +#ifndef arch_atomic_fetch_dec_release +static __always_inline int +arch_atomic_fetch_dec_release(atomic_t *v) +{ + return arch_atomic_fetch_sub_release(1, v); +} +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release +#endif + +#ifndef arch_atomic_fetch_dec_relaxed +static __always_inline int +arch_atomic_fetch_dec_relaxed(atomic_t *v) +{ + return arch_atomic_fetch_sub_relaxed(1, v); +} +#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec_relaxed +#endif + +#else /* arch_atomic_fetch_dec_relaxed */ + +#ifndef arch_atomic_fetch_dec_acquire +static __always_inline int +arch_atomic_fetch_dec_acquire(atomic_t *v) +{ + int ret = arch_atomic_fetch_dec_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire +#endif + +#ifndef arch_atomic_fetch_dec_release +static __always_inline int +arch_atomic_fetch_dec_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_dec_relaxed(v); +} +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release +#endif + +#ifndef arch_atomic_fetch_dec +static __always_inline int +arch_atomic_fetch_dec(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_dec_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_dec arch_atomic_fetch_dec +#endif + +#endif /* arch_atomic_fetch_dec_relaxed */ + +#ifndef arch_atomic_fetch_and_relaxed +#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and +#define arch_atomic_fetch_and_release arch_atomic_fetch_and +#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and +#else /* arch_atomic_fetch_and_relaxed */ + +#ifndef arch_atomic_fetch_and_acquire +static __always_inline int +arch_atomic_fetch_and_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_and_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire +#endif + +#ifndef arch_atomic_fetch_and_release +static __always_inline int +arch_atomic_fetch_and_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_and_relaxed(i, v); +} +#define arch_atomic_fetch_and_release arch_atomic_fetch_and_release +#endif + +#ifndef arch_atomic_fetch_and +static __always_inline int +arch_atomic_fetch_and(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_and_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_and arch_atomic_fetch_and +#endif + +#endif /* arch_atomic_fetch_and_relaxed */ + +#ifndef arch_atomic_andnot +static __always_inline void +arch_atomic_andnot(int i, atomic_t *v) +{ + arch_atomic_and(~i, v); +} +#define arch_atomic_andnot arch_atomic_andnot +#endif + +#ifndef arch_atomic_fetch_andnot_relaxed +#ifdef arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot +#endif /* arch_atomic_fetch_andnot */ + +#ifndef arch_atomic_fetch_andnot +static __always_inline int +arch_atomic_fetch_andnot(int i, atomic_t *v) +{ + return arch_atomic_fetch_and(~i, v); +} +#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot +#endif + +#ifndef arch_atomic_fetch_andnot_acquire +static __always_inline int +arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_acquire(~i, v); +} +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire +#endif + +#ifndef arch_atomic_fetch_andnot_release +static __always_inline int +arch_atomic_fetch_andnot_release(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_release(~i, v); +} +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release +#endif + +#ifndef arch_atomic_fetch_andnot_relaxed +static __always_inline int +arch_atomic_fetch_andnot_relaxed(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_relaxed(~i, v); +} +#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed +#endif + +#else /* arch_atomic_fetch_andnot_relaxed */ + +#ifndef arch_atomic_fetch_andnot_acquire +static __always_inline int +arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_andnot_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire +#endif + +#ifndef arch_atomic_fetch_andnot_release +static __always_inline int +arch_atomic_fetch_andnot_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_andnot_relaxed(i, v); +} +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release +#endif + +#ifndef arch_atomic_fetch_andnot +static __always_inline int +arch_atomic_fetch_andnot(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_andnot_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot +#endif + +#endif /* arch_atomic_fetch_andnot_relaxed */ + +#ifndef arch_atomic_fetch_or_relaxed +#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or +#define arch_atomic_fetch_or_release arch_atomic_fetch_or +#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or +#else /* arch_atomic_fetch_or_relaxed */ + +#ifndef arch_atomic_fetch_or_acquire +static __always_inline int +arch_atomic_fetch_or_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_or_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire +#endif + +#ifndef arch_atomic_fetch_or_release +static __always_inline int +arch_atomic_fetch_or_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_or_relaxed(i, v); +} +#define arch_atomic_fetch_or_release arch_atomic_fetch_or_release +#endif + +#ifndef arch_atomic_fetch_or +static __always_inline int +arch_atomic_fetch_or(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_or_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_or arch_atomic_fetch_or +#endif + +#endif /* arch_atomic_fetch_or_relaxed */ + +#ifndef arch_atomic_fetch_xor_relaxed +#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor +#else /* arch_atomic_fetch_xor_relaxed */ + +#ifndef arch_atomic_fetch_xor_acquire +static __always_inline int +arch_atomic_fetch_xor_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_xor_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire +#endif + +#ifndef arch_atomic_fetch_xor_release +static __always_inline int +arch_atomic_fetch_xor_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_xor_relaxed(i, v); +} +#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release +#endif + +#ifndef arch_atomic_fetch_xor +static __always_inline int +arch_atomic_fetch_xor(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_xor_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_xor arch_atomic_fetch_xor +#endif + +#endif /* arch_atomic_fetch_xor_relaxed */ + +#ifndef arch_atomic_xchg_relaxed +#define arch_atomic_xchg_acquire arch_atomic_xchg +#define arch_atomic_xchg_release arch_atomic_xchg +#define arch_atomic_xchg_relaxed arch_atomic_xchg +#else /* arch_atomic_xchg_relaxed */ + +#ifndef arch_atomic_xchg_acquire +static __always_inline int +arch_atomic_xchg_acquire(atomic_t *v, int i) +{ + int ret = arch_atomic_xchg_relaxed(v, i); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_xchg_acquire arch_atomic_xchg_acquire +#endif + +#ifndef arch_atomic_xchg_release +static __always_inline int +arch_atomic_xchg_release(atomic_t *v, int i) +{ + __atomic_release_fence(); + return arch_atomic_xchg_relaxed(v, i); +} +#define arch_atomic_xchg_release arch_atomic_xchg_release +#endif + +#ifndef arch_atomic_xchg +static __always_inline int +arch_atomic_xchg(atomic_t *v, int i) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_xchg_relaxed(v, i); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_xchg arch_atomic_xchg +#endif + +#endif /* arch_atomic_xchg_relaxed */ + +#ifndef arch_atomic_cmpxchg_relaxed +#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg +#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg +#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg +#else /* arch_atomic_cmpxchg_relaxed */ + +#ifndef arch_atomic_cmpxchg_acquire +static __always_inline int +arch_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) +{ + int ret = arch_atomic_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire +#endif + +#ifndef arch_atomic_cmpxchg_release +static __always_inline int +arch_atomic_cmpxchg_release(atomic_t *v, int old, int new) +{ + __atomic_release_fence(); + return arch_atomic_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release +#endif + +#ifndef arch_atomic_cmpxchg +static __always_inline int +arch_atomic_cmpxchg(atomic_t *v, int old, int new) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_cmpxchg arch_atomic_cmpxchg +#endif + +#endif /* arch_atomic_cmpxchg_relaxed */ + +#ifndef arch_atomic_try_cmpxchg_relaxed +#ifdef arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg +#endif /* arch_atomic_try_cmpxchg */ + +#ifndef arch_atomic_try_cmpxchg +static __always_inline bool +arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg +#endif + +#ifndef arch_atomic_try_cmpxchg_acquire +static __always_inline bool +arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_acquire(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic_try_cmpxchg_release +static __always_inline bool +arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_release(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release +#endif + +#ifndef arch_atomic_try_cmpxchg_relaxed +static __always_inline bool +arch_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_relaxed(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg_relaxed +#endif + +#else /* arch_atomic_try_cmpxchg_relaxed */ + +#ifndef arch_atomic_try_cmpxchg_acquire +static __always_inline bool +arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic_try_cmpxchg_release +static __always_inline bool +arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + __atomic_release_fence(); + return arch_atomic_try_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release +#endif + +#ifndef arch_atomic_try_cmpxchg +static __always_inline bool +arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg +#endif + +#endif /* arch_atomic_try_cmpxchg_relaxed */ + +#ifndef arch_atomic_sub_and_test +/** + * arch_atomic_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic_sub_and_test(int i, atomic_t *v) +{ + return arch_atomic_sub_return(i, v) == 0; +} +#define arch_atomic_sub_and_test arch_atomic_sub_and_test +#endif + +#ifndef arch_atomic_dec_and_test +/** + * arch_atomic_dec_and_test - decrement and test + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static __always_inline bool +arch_atomic_dec_and_test(atomic_t *v) +{ + return arch_atomic_dec_return(v) == 0; +} +#define arch_atomic_dec_and_test arch_atomic_dec_and_test +#endif + +#ifndef arch_atomic_inc_and_test +/** + * arch_atomic_inc_and_test - increment and test + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic_inc_and_test(atomic_t *v) +{ + return arch_atomic_inc_return(v) == 0; +} +#define arch_atomic_inc_and_test arch_atomic_inc_and_test +#endif + +#ifndef arch_atomic_add_negative +/** + * arch_atomic_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic_add_negative(int i, atomic_t *v) +{ + return arch_atomic_add_return(i, v) < 0; +} +#define arch_atomic_add_negative arch_atomic_add_negative +#endif + +#ifndef arch_atomic_fetch_add_unless +/** + * arch_atomic_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns original value of @v + */ +static __always_inline int +arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); + + return c; +} +#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless +#endif + +#ifndef arch_atomic_add_unless +/** + * arch_atomic_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static __always_inline bool +arch_atomic_add_unless(atomic_t *v, int a, int u) +{ + return arch_atomic_fetch_add_unless(v, a, u) != u; +} +#define arch_atomic_add_unless arch_atomic_add_unless +#endif + +#ifndef arch_atomic_inc_not_zero +/** + * arch_atomic_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +static __always_inline bool +arch_atomic_inc_not_zero(atomic_t *v) +{ + return arch_atomic_add_unless(v, 1, 0); +} +#define arch_atomic_inc_not_zero arch_atomic_inc_not_zero +#endif + +#ifndef arch_atomic_inc_unless_negative +static __always_inline bool +arch_atomic_inc_unless_negative(atomic_t *v) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!arch_atomic_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative +#endif + +#ifndef arch_atomic_dec_unless_positive +static __always_inline bool +arch_atomic_dec_unless_positive(atomic_t *v) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!arch_atomic_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive +#endif + +#ifndef arch_atomic_dec_if_positive +static __always_inline int +arch_atomic_dec_if_positive(atomic_t *v) +{ + int dec, c = arch_atomic_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!arch_atomic_try_cmpxchg(v, &c, dec)); + + return dec; +} +#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive +#endif + +#ifdef CONFIG_GENERIC_ATOMIC64 +#include +#endif + +#ifndef arch_atomic64_read_acquire +static __always_inline s64 +arch_atomic64_read_acquire(const atomic64_t *v) +{ + return smp_load_acquire(&(v)->counter); +} +#define arch_atomic64_read_acquire arch_atomic64_read_acquire +#endif + +#ifndef arch_atomic64_set_release +static __always_inline void +arch_atomic64_set_release(atomic64_t *v, s64 i) +{ + smp_store_release(&(v)->counter, i); +} +#define arch_atomic64_set_release arch_atomic64_set_release +#endif + +#ifndef arch_atomic64_add_return_relaxed +#define arch_atomic64_add_return_acquire arch_atomic64_add_return +#define arch_atomic64_add_return_release arch_atomic64_add_return +#define arch_atomic64_add_return_relaxed arch_atomic64_add_return +#else /* arch_atomic64_add_return_relaxed */ + +#ifndef arch_atomic64_add_return_acquire +static __always_inline s64 +arch_atomic64_add_return_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_add_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire +#endif + +#ifndef arch_atomic64_add_return_release +static __always_inline s64 +arch_atomic64_add_return_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_add_return_relaxed(i, v); +} +#define arch_atomic64_add_return_release arch_atomic64_add_return_release +#endif + +#ifndef arch_atomic64_add_return +static __always_inline s64 +arch_atomic64_add_return(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_add_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_add_return arch_atomic64_add_return +#endif + +#endif /* arch_atomic64_add_return_relaxed */ + +#ifndef arch_atomic64_fetch_add_relaxed +#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add +#else /* arch_atomic64_fetch_add_relaxed */ + +#ifndef arch_atomic64_fetch_add_acquire +static __always_inline s64 +arch_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_add_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire +#endif + +#ifndef arch_atomic64_fetch_add_release +static __always_inline s64 +arch_atomic64_fetch_add_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_add_relaxed(i, v); +} +#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release +#endif + +#ifndef arch_atomic64_fetch_add +static __always_inline s64 +arch_atomic64_fetch_add(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_add_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_add arch_atomic64_fetch_add +#endif + +#endif /* arch_atomic64_fetch_add_relaxed */ + +#ifndef arch_atomic64_sub_return_relaxed +#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return +#define arch_atomic64_sub_return_release arch_atomic64_sub_return +#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return +#else /* arch_atomic64_sub_return_relaxed */ + +#ifndef arch_atomic64_sub_return_acquire +static __always_inline s64 +arch_atomic64_sub_return_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_sub_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire +#endif + +#ifndef arch_atomic64_sub_return_release +static __always_inline s64 +arch_atomic64_sub_return_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_sub_return_relaxed(i, v); +} +#define arch_atomic64_sub_return_release arch_atomic64_sub_return_release +#endif + +#ifndef arch_atomic64_sub_return +static __always_inline s64 +arch_atomic64_sub_return(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_sub_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_sub_return arch_atomic64_sub_return +#endif + +#endif /* arch_atomic64_sub_return_relaxed */ + +#ifndef arch_atomic64_fetch_sub_relaxed +#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub +#else /* arch_atomic64_fetch_sub_relaxed */ + +#ifndef arch_atomic64_fetch_sub_acquire +static __always_inline s64 +arch_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire +#endif + +#ifndef arch_atomic64_fetch_sub_release +static __always_inline s64 +arch_atomic64_fetch_sub_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_sub_relaxed(i, v); +} +#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release +#endif + +#ifndef arch_atomic64_fetch_sub +static __always_inline s64 +arch_atomic64_fetch_sub(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_sub_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub +#endif + +#endif /* arch_atomic64_fetch_sub_relaxed */ + +#ifndef arch_atomic64_inc +static __always_inline void +arch_atomic64_inc(atomic64_t *v) +{ + arch_atomic64_add(1, v); +} +#define arch_atomic64_inc arch_atomic64_inc +#endif + +#ifndef arch_atomic64_inc_return_relaxed +#ifdef arch_atomic64_inc_return +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return +#define arch_atomic64_inc_return_release arch_atomic64_inc_return +#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return +#endif /* arch_atomic64_inc_return */ + +#ifndef arch_atomic64_inc_return +static __always_inline s64 +arch_atomic64_inc_return(atomic64_t *v) +{ + return arch_atomic64_add_return(1, v); +} +#define arch_atomic64_inc_return arch_atomic64_inc_return +#endif + +#ifndef arch_atomic64_inc_return_acquire +static __always_inline s64 +arch_atomic64_inc_return_acquire(atomic64_t *v) +{ + return arch_atomic64_add_return_acquire(1, v); +} +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire +#endif + +#ifndef arch_atomic64_inc_return_release +static __always_inline s64 +arch_atomic64_inc_return_release(atomic64_t *v) +{ + return arch_atomic64_add_return_release(1, v); +} +#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release +#endif + +#ifndef arch_atomic64_inc_return_relaxed +static __always_inline s64 +arch_atomic64_inc_return_relaxed(atomic64_t *v) +{ + return arch_atomic64_add_return_relaxed(1, v); +} +#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed +#endif + +#else /* arch_atomic64_inc_return_relaxed */ + +#ifndef arch_atomic64_inc_return_acquire +static __always_inline s64 +arch_atomic64_inc_return_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_inc_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire +#endif + +#ifndef arch_atomic64_inc_return_release +static __always_inline s64 +arch_atomic64_inc_return_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_inc_return_relaxed(v); +} +#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release +#endif + +#ifndef arch_atomic64_inc_return +static __always_inline s64 +arch_atomic64_inc_return(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_inc_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_inc_return arch_atomic64_inc_return +#endif + +#endif /* arch_atomic64_inc_return_relaxed */ + +#ifndef arch_atomic64_fetch_inc_relaxed +#ifdef arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc +#endif /* arch_atomic64_fetch_inc */ + +#ifndef arch_atomic64_fetch_inc +static __always_inline s64 +arch_atomic64_fetch_inc(atomic64_t *v) +{ + return arch_atomic64_fetch_add(1, v); +} +#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc +#endif + +#ifndef arch_atomic64_fetch_inc_acquire +static __always_inline s64 +arch_atomic64_fetch_inc_acquire(atomic64_t *v) +{ + return arch_atomic64_fetch_add_acquire(1, v); +} +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire +#endif + +#ifndef arch_atomic64_fetch_inc_release +static __always_inline s64 +arch_atomic64_fetch_inc_release(atomic64_t *v) +{ + return arch_atomic64_fetch_add_release(1, v); +} +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release +#endif + +#ifndef arch_atomic64_fetch_inc_relaxed +static __always_inline s64 +arch_atomic64_fetch_inc_relaxed(atomic64_t *v) +{ + return arch_atomic64_fetch_add_relaxed(1, v); +} +#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc_relaxed +#endif + +#else /* arch_atomic64_fetch_inc_relaxed */ + +#ifndef arch_atomic64_fetch_inc_acquire +static __always_inline s64 +arch_atomic64_fetch_inc_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_inc_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire +#endif + +#ifndef arch_atomic64_fetch_inc_release +static __always_inline s64 +arch_atomic64_fetch_inc_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_inc_relaxed(v); +} +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release +#endif + +#ifndef arch_atomic64_fetch_inc +static __always_inline s64 +arch_atomic64_fetch_inc(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_inc_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc +#endif + +#endif /* arch_atomic64_fetch_inc_relaxed */ + +#ifndef arch_atomic64_dec +static __always_inline void +arch_atomic64_dec(atomic64_t *v) +{ + arch_atomic64_sub(1, v); +} +#define arch_atomic64_dec arch_atomic64_dec +#endif + +#ifndef arch_atomic64_dec_return_relaxed +#ifdef arch_atomic64_dec_return +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return +#define arch_atomic64_dec_return_release arch_atomic64_dec_return +#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return +#endif /* arch_atomic64_dec_return */ + +#ifndef arch_atomic64_dec_return +static __always_inline s64 +arch_atomic64_dec_return(atomic64_t *v) +{ + return arch_atomic64_sub_return(1, v); +} +#define arch_atomic64_dec_return arch_atomic64_dec_return +#endif + +#ifndef arch_atomic64_dec_return_acquire +static __always_inline s64 +arch_atomic64_dec_return_acquire(atomic64_t *v) +{ + return arch_atomic64_sub_return_acquire(1, v); +} +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire +#endif + +#ifndef arch_atomic64_dec_return_release +static __always_inline s64 +arch_atomic64_dec_return_release(atomic64_t *v) +{ + return arch_atomic64_sub_return_release(1, v); +} +#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release +#endif + +#ifndef arch_atomic64_dec_return_relaxed +static __always_inline s64 +arch_atomic64_dec_return_relaxed(atomic64_t *v) +{ + return arch_atomic64_sub_return_relaxed(1, v); +} +#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed +#endif + +#else /* arch_atomic64_dec_return_relaxed */ + +#ifndef arch_atomic64_dec_return_acquire +static __always_inline s64 +arch_atomic64_dec_return_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_dec_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire +#endif + +#ifndef arch_atomic64_dec_return_release +static __always_inline s64 +arch_atomic64_dec_return_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_dec_return_relaxed(v); +} +#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release +#endif + +#ifndef arch_atomic64_dec_return +static __always_inline s64 +arch_atomic64_dec_return(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_dec_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_dec_return arch_atomic64_dec_return +#endif + +#endif /* arch_atomic64_dec_return_relaxed */ + +#ifndef arch_atomic64_fetch_dec_relaxed +#ifdef arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec +#endif /* arch_atomic64_fetch_dec */ + +#ifndef arch_atomic64_fetch_dec +static __always_inline s64 +arch_atomic64_fetch_dec(atomic64_t *v) +{ + return arch_atomic64_fetch_sub(1, v); +} +#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec +#endif + +#ifndef arch_atomic64_fetch_dec_acquire +static __always_inline s64 +arch_atomic64_fetch_dec_acquire(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_acquire(1, v); +} +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire +#endif + +#ifndef arch_atomic64_fetch_dec_release +static __always_inline s64 +arch_atomic64_fetch_dec_release(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_release(1, v); +} +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release +#endif + +#ifndef arch_atomic64_fetch_dec_relaxed +static __always_inline s64 +arch_atomic64_fetch_dec_relaxed(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_relaxed(1, v); +} +#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec_relaxed +#endif + +#else /* arch_atomic64_fetch_dec_relaxed */ + +#ifndef arch_atomic64_fetch_dec_acquire +static __always_inline s64 +arch_atomic64_fetch_dec_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_dec_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire +#endif + +#ifndef arch_atomic64_fetch_dec_release +static __always_inline s64 +arch_atomic64_fetch_dec_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_dec_relaxed(v); +} +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release +#endif + +#ifndef arch_atomic64_fetch_dec +static __always_inline s64 +arch_atomic64_fetch_dec(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_dec_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec +#endif + +#endif /* arch_atomic64_fetch_dec_relaxed */ + +#ifndef arch_atomic64_fetch_and_relaxed +#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and +#else /* arch_atomic64_fetch_and_relaxed */ + +#ifndef arch_atomic64_fetch_and_acquire +static __always_inline s64 +arch_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_and_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire +#endif + +#ifndef arch_atomic64_fetch_and_release +static __always_inline s64 +arch_atomic64_fetch_and_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_and_relaxed(i, v); +} +#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release +#endif + +#ifndef arch_atomic64_fetch_and +static __always_inline s64 +arch_atomic64_fetch_and(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_and_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_and arch_atomic64_fetch_and +#endif + +#endif /* arch_atomic64_fetch_and_relaxed */ + +#ifndef arch_atomic64_andnot +static __always_inline void +arch_atomic64_andnot(s64 i, atomic64_t *v) +{ + arch_atomic64_and(~i, v); +} +#define arch_atomic64_andnot arch_atomic64_andnot +#endif + +#ifndef arch_atomic64_fetch_andnot_relaxed +#ifdef arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot +#endif /* arch_atomic64_fetch_andnot */ + +#ifndef arch_atomic64_fetch_andnot +static __always_inline s64 +arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and(~i, v); +} +#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot +#endif + +#ifndef arch_atomic64_fetch_andnot_acquire +static __always_inline s64 +arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_acquire(~i, v); +} +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire +#endif + +#ifndef arch_atomic64_fetch_andnot_release +static __always_inline s64 +arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_release(~i, v); +} +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release +#endif + +#ifndef arch_atomic64_fetch_andnot_relaxed +static __always_inline s64 +arch_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_relaxed(~i, v); +} +#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed +#endif + +#else /* arch_atomic64_fetch_andnot_relaxed */ + +#ifndef arch_atomic64_fetch_andnot_acquire +static __always_inline s64 +arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire +#endif + +#ifndef arch_atomic64_fetch_andnot_release +static __always_inline s64 +arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_andnot_relaxed(i, v); +} +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release +#endif + +#ifndef arch_atomic64_fetch_andnot +static __always_inline s64 +arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_andnot_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot +#endif + +#endif /* arch_atomic64_fetch_andnot_relaxed */ + +#ifndef arch_atomic64_fetch_or_relaxed +#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or +#else /* arch_atomic64_fetch_or_relaxed */ + +#ifndef arch_atomic64_fetch_or_acquire +static __always_inline s64 +arch_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_or_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire +#endif + +#ifndef arch_atomic64_fetch_or_release +static __always_inline s64 +arch_atomic64_fetch_or_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_or_relaxed(i, v); +} +#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release +#endif + +#ifndef arch_atomic64_fetch_or +static __always_inline s64 +arch_atomic64_fetch_or(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_or_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_or arch_atomic64_fetch_or +#endif + +#endif /* arch_atomic64_fetch_or_relaxed */ + +#ifndef arch_atomic64_fetch_xor_relaxed +#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor +#else /* arch_atomic64_fetch_xor_relaxed */ + +#ifndef arch_atomic64_fetch_xor_acquire +static __always_inline s64 +arch_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire +#endif + +#ifndef arch_atomic64_fetch_xor_release +static __always_inline s64 +arch_atomic64_fetch_xor_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_xor_relaxed(i, v); +} +#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release +#endif + +#ifndef arch_atomic64_fetch_xor +static __always_inline s64 +arch_atomic64_fetch_xor(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_xor_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor +#endif + +#endif /* arch_atomic64_fetch_xor_relaxed */ + +#ifndef arch_atomic64_xchg_relaxed +#define arch_atomic64_xchg_acquire arch_atomic64_xchg +#define arch_atomic64_xchg_release arch_atomic64_xchg +#define arch_atomic64_xchg_relaxed arch_atomic64_xchg +#else /* arch_atomic64_xchg_relaxed */ + +#ifndef arch_atomic64_xchg_acquire +static __always_inline s64 +arch_atomic64_xchg_acquire(atomic64_t *v, s64 i) +{ + s64 ret = arch_atomic64_xchg_relaxed(v, i); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_xchg_acquire arch_atomic64_xchg_acquire +#endif + +#ifndef arch_atomic64_xchg_release +static __always_inline s64 +arch_atomic64_xchg_release(atomic64_t *v, s64 i) +{ + __atomic_release_fence(); + return arch_atomic64_xchg_relaxed(v, i); +} +#define arch_atomic64_xchg_release arch_atomic64_xchg_release +#endif + +#ifndef arch_atomic64_xchg +static __always_inline s64 +arch_atomic64_xchg(atomic64_t *v, s64 i) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_xchg_relaxed(v, i); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_xchg arch_atomic64_xchg +#endif + +#endif /* arch_atomic64_xchg_relaxed */ + +#ifndef arch_atomic64_cmpxchg_relaxed +#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg +#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg +#define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg +#else /* arch_atomic64_cmpxchg_relaxed */ + +#ifndef arch_atomic64_cmpxchg_acquire +static __always_inline s64 +arch_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) +{ + s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_cmpxchg_release +static __always_inline s64 +arch_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) +{ + __atomic_release_fence(); + return arch_atomic64_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg_release +#endif + +#ifndef arch_atomic64_cmpxchg +static __always_inline s64 +arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg +#endif + +#endif /* arch_atomic64_cmpxchg_relaxed */ + +#ifndef arch_atomic64_try_cmpxchg_relaxed +#ifdef arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg +#endif /* arch_atomic64_try_cmpxchg */ + +#ifndef arch_atomic64_try_cmpxchg +static __always_inline bool +arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg +#endif + +#ifndef arch_atomic64_try_cmpxchg_acquire +static __always_inline bool +arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_acquire(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_try_cmpxchg_release +static __always_inline bool +arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_release(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release +#endif + +#ifndef arch_atomic64_try_cmpxchg_relaxed +static __always_inline bool +arch_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_relaxed(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg_relaxed +#endif + +#else /* arch_atomic64_try_cmpxchg_relaxed */ + +#ifndef arch_atomic64_try_cmpxchg_acquire +static __always_inline bool +arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_try_cmpxchg_release +static __always_inline bool +arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + __atomic_release_fence(); + return arch_atomic64_try_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release +#endif + +#ifndef arch_atomic64_try_cmpxchg +static __always_inline bool +arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg +#endif + +#endif /* arch_atomic64_try_cmpxchg_relaxed */ + +#ifndef arch_atomic64_sub_and_test +/** + * arch_atomic64_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic64_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic64_sub_and_test(s64 i, atomic64_t *v) +{ + return arch_atomic64_sub_return(i, v) == 0; +} +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test +#endif + +#ifndef arch_atomic64_dec_and_test +/** + * arch_atomic64_dec_and_test - decrement and test + * @v: pointer of type atomic64_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static __always_inline bool +arch_atomic64_dec_and_test(atomic64_t *v) +{ + return arch_atomic64_dec_return(v) == 0; +} +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test +#endif + +#ifndef arch_atomic64_inc_and_test +/** + * arch_atomic64_inc_and_test - increment and test + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic64_inc_and_test(atomic64_t *v) +{ + return arch_atomic64_inc_return(v) == 0; +} +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test +#endif + +#ifndef arch_atomic64_add_negative +/** + * arch_atomic64_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic64_add_negative(s64 i, atomic64_t *v) +{ + return arch_atomic64_add_return(i, v) < 0; +} +#define arch_atomic64_add_negative arch_atomic64_add_negative +#endif + +#ifndef arch_atomic64_fetch_add_unless +/** + * arch_atomic64_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns original value of @v + */ +static __always_inline s64 +arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); + + return c; +} +#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless +#endif + +#ifndef arch_atomic64_add_unless +/** + * arch_atomic64_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static __always_inline bool +arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +{ + return arch_atomic64_fetch_add_unless(v, a, u) != u; +} +#define arch_atomic64_add_unless arch_atomic64_add_unless +#endif + +#ifndef arch_atomic64_inc_not_zero +/** + * arch_atomic64_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +static __always_inline bool +arch_atomic64_inc_not_zero(atomic64_t *v) +{ + return arch_atomic64_add_unless(v, 1, 0); +} +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero +#endif + +#ifndef arch_atomic64_inc_unless_negative +static __always_inline bool +arch_atomic64_inc_unless_negative(atomic64_t *v) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!arch_atomic64_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative +#endif + +#ifndef arch_atomic64_dec_unless_positive +static __always_inline bool +arch_atomic64_dec_unless_positive(atomic64_t *v) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!arch_atomic64_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive +#endif + +#ifndef arch_atomic64_dec_if_positive +static __always_inline s64 +arch_atomic64_dec_if_positive(atomic64_t *v) +{ + s64 dec, c = arch_atomic64_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); + + return dec; +} +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive +#endif + +#endif /* _LINUX_ATOMIC_FALLBACK_H */ +// cca554917d7ea73d5e3e7397dd70c484cad9b2c4 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h new file mode 100644 index 000000000000..f6fe36c428df --- /dev/null +++ b/include/linux/atomic/atomic-instrumented.h @@ -0,0 +1,1337 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-instrumented.sh +// DO NOT MODIFY THIS FILE DIRECTLY + +/* + * This file provides wrappers with KASAN instrumentation for atomic operations. + * To use this functionality an arch's atomic.h file needs to define all + * atomic operations with arch_ prefix (e.g. arch_atomic_read()) and include + * this file at the end. This file provides atomic_read() that forwards to + * arch_atomic_read() for actual atomic operation. + * Note: if an arch atomic operation is implemented by means of other atomic + * operations (e.g. atomic_read()/atomic_cmpxchg() loop), then it needs to use + * arch_ variants (i.e. arch_atomic_read()/arch_atomic_cmpxchg()) to avoid + * double instrumentation. + */ +#ifndef _LINUX_ATOMIC_INSTRUMENTED_H +#define _LINUX_ATOMIC_INSTRUMENTED_H + +#include +#include +#include + +static __always_inline int +atomic_read(const atomic_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic_read(v); +} + +static __always_inline int +atomic_read_acquire(const atomic_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic_read_acquire(v); +} + +static __always_inline void +atomic_set(atomic_t *v, int i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic_set(v, i); +} + +static __always_inline void +atomic_set_release(atomic_t *v, int i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic_set_release(v, i); +} + +static __always_inline void +atomic_add(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_add(i, v); +} + +static __always_inline int +atomic_add_return(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_return(i, v); +} + +static __always_inline int +atomic_add_return_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_return_acquire(i, v); +} + +static __always_inline int +atomic_add_return_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_return_release(i, v); +} + +static __always_inline int +atomic_add_return_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_return_relaxed(i, v); +} + +static __always_inline int +atomic_fetch_add(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_add(i, v); +} + +static __always_inline int +atomic_fetch_add_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_add_acquire(i, v); +} + +static __always_inline int +atomic_fetch_add_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_add_release(i, v); +} + +static __always_inline int +atomic_fetch_add_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_add_relaxed(i, v); +} + +static __always_inline void +atomic_sub(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_sub(i, v); +} + +static __always_inline int +atomic_sub_return(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_sub_return(i, v); +} + +static __always_inline int +atomic_sub_return_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_sub_return_acquire(i, v); +} + +static __always_inline int +atomic_sub_return_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_sub_return_release(i, v); +} + +static __always_inline int +atomic_sub_return_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_sub_return_relaxed(i, v); +} + +static __always_inline int +atomic_fetch_sub(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_sub(i, v); +} + +static __always_inline int +atomic_fetch_sub_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_sub_acquire(i, v); +} + +static __always_inline int +atomic_fetch_sub_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_sub_release(i, v); +} + +static __always_inline int +atomic_fetch_sub_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_sub_relaxed(i, v); +} + +static __always_inline void +atomic_inc(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_inc(v); +} + +static __always_inline int +atomic_inc_return(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_return(v); +} + +static __always_inline int +atomic_inc_return_acquire(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_return_acquire(v); +} + +static __always_inline int +atomic_inc_return_release(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_return_release(v); +} + +static __always_inline int +atomic_inc_return_relaxed(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_return_relaxed(v); +} + +static __always_inline int +atomic_fetch_inc(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_inc(v); +} + +static __always_inline int +atomic_fetch_inc_acquire(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_inc_acquire(v); +} + +static __always_inline int +atomic_fetch_inc_release(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_inc_release(v); +} + +static __always_inline int +atomic_fetch_inc_relaxed(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_inc_relaxed(v); +} + +static __always_inline void +atomic_dec(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_dec(v); +} + +static __always_inline int +atomic_dec_return(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_return(v); +} + +static __always_inline int +atomic_dec_return_acquire(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_return_acquire(v); +} + +static __always_inline int +atomic_dec_return_release(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_return_release(v); +} + +static __always_inline int +atomic_dec_return_relaxed(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_return_relaxed(v); +} + +static __always_inline int +atomic_fetch_dec(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_dec(v); +} + +static __always_inline int +atomic_fetch_dec_acquire(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_dec_acquire(v); +} + +static __always_inline int +atomic_fetch_dec_release(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_dec_release(v); +} + +static __always_inline int +atomic_fetch_dec_relaxed(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_dec_relaxed(v); +} + +static __always_inline void +atomic_and(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_and(i, v); +} + +static __always_inline int +atomic_fetch_and(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_and(i, v); +} + +static __always_inline int +atomic_fetch_and_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_and_acquire(i, v); +} + +static __always_inline int +atomic_fetch_and_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_and_release(i, v); +} + +static __always_inline int +atomic_fetch_and_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_and_relaxed(i, v); +} + +static __always_inline void +atomic_andnot(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_andnot(i, v); +} + +static __always_inline int +atomic_fetch_andnot(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot(i, v); +} + +static __always_inline int +atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot_acquire(i, v); +} + +static __always_inline int +atomic_fetch_andnot_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot_release(i, v); +} + +static __always_inline int +atomic_fetch_andnot_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot_relaxed(i, v); +} + +static __always_inline void +atomic_or(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_or(i, v); +} + +static __always_inline int +atomic_fetch_or(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_or(i, v); +} + +static __always_inline int +atomic_fetch_or_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_or_acquire(i, v); +} + +static __always_inline int +atomic_fetch_or_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_or_release(i, v); +} + +static __always_inline int +atomic_fetch_or_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_or_relaxed(i, v); +} + +static __always_inline void +atomic_xor(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_xor(i, v); +} + +static __always_inline int +atomic_fetch_xor(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_xor(i, v); +} + +static __always_inline int +atomic_fetch_xor_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_xor_acquire(i, v); +} + +static __always_inline int +atomic_fetch_xor_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_xor_release(i, v); +} + +static __always_inline int +atomic_fetch_xor_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_xor_relaxed(i, v); +} + +static __always_inline int +atomic_xchg(atomic_t *v, int i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_xchg(v, i); +} + +static __always_inline int +atomic_xchg_acquire(atomic_t *v, int i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_xchg_acquire(v, i); +} + +static __always_inline int +atomic_xchg_release(atomic_t *v, int i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_xchg_release(v, i); +} + +static __always_inline int +atomic_xchg_relaxed(atomic_t *v, int i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_xchg_relaxed(v, i); +} + +static __always_inline int +atomic_cmpxchg(atomic_t *v, int old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_cmpxchg(v, old, new); +} + +static __always_inline int +atomic_cmpxchg_acquire(atomic_t *v, int old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_cmpxchg_acquire(v, old, new); +} + +static __always_inline int +atomic_cmpxchg_release(atomic_t *v, int old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_cmpxchg_release(v, old, new); +} + +static __always_inline int +atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg(v, old, new); +} + +static __always_inline bool +atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg_acquire(v, old, new); +} + +static __always_inline bool +atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg_release(v, old, new); +} + +static __always_inline bool +atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_sub_and_test(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_sub_and_test(i, v); +} + +static __always_inline bool +atomic_dec_and_test(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_and_test(v); +} + +static __always_inline bool +atomic_inc_and_test(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_and_test(v); +} + +static __always_inline bool +atomic_add_negative(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_negative(i, v); +} + +static __always_inline int +atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_add_unless(v, a, u); +} + +static __always_inline bool +atomic_add_unless(atomic_t *v, int a, int u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_unless(v, a, u); +} + +static __always_inline bool +atomic_inc_not_zero(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_not_zero(v); +} + +static __always_inline bool +atomic_inc_unless_negative(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_unless_negative(v); +} + +static __always_inline bool +atomic_dec_unless_positive(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_unless_positive(v); +} + +static __always_inline int +atomic_dec_if_positive(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_if_positive(v); +} + +static __always_inline s64 +atomic64_read(const atomic64_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic64_read(v); +} + +static __always_inline s64 +atomic64_read_acquire(const atomic64_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic64_read_acquire(v); +} + +static __always_inline void +atomic64_set(atomic64_t *v, s64 i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic64_set(v, i); +} + +static __always_inline void +atomic64_set_release(atomic64_t *v, s64 i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic64_set_release(v, i); +} + +static __always_inline void +atomic64_add(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_add(i, v); +} + +static __always_inline s64 +atomic64_add_return(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_return(i, v); +} + +static __always_inline s64 +atomic64_add_return_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_return_acquire(i, v); +} + +static __always_inline s64 +atomic64_add_return_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_return_release(i, v); +} + +static __always_inline s64 +atomic64_add_return_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_return_relaxed(i, v); +} + +static __always_inline s64 +atomic64_fetch_add(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_add(i, v); +} + +static __always_inline s64 +atomic64_fetch_add_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_add_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_relaxed(i, v); +} + +static __always_inline void +atomic64_sub(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_sub(i, v); +} + +static __always_inline s64 +atomic64_sub_return(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_sub_return(i, v); +} + +static __always_inline s64 +atomic64_sub_return_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_sub_return_acquire(i, v); +} + +static __always_inline s64 +atomic64_sub_return_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_sub_return_release(i, v); +} + +static __always_inline s64 +atomic64_sub_return_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_sub_return_relaxed(i, v); +} + +static __always_inline s64 +atomic64_fetch_sub(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_sub(i, v); +} + +static __always_inline s64 +atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_sub_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_sub_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_sub_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_sub_relaxed(i, v); +} + +static __always_inline void +atomic64_inc(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_inc(v); +} + +static __always_inline s64 +atomic64_inc_return(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_return(v); +} + +static __always_inline s64 +atomic64_inc_return_acquire(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_return_acquire(v); +} + +static __always_inline s64 +atomic64_inc_return_release(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_return_release(v); +} + +static __always_inline s64 +atomic64_inc_return_relaxed(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_return_relaxed(v); +} + +static __always_inline s64 +atomic64_fetch_inc(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_inc(v); +} + +static __always_inline s64 +atomic64_fetch_inc_acquire(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_inc_acquire(v); +} + +static __always_inline s64 +atomic64_fetch_inc_release(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_inc_release(v); +} + +static __always_inline s64 +atomic64_fetch_inc_relaxed(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_inc_relaxed(v); +} + +static __always_inline void +atomic64_dec(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_dec(v); +} + +static __always_inline s64 +atomic64_dec_return(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_return(v); +} + +static __always_inline s64 +atomic64_dec_return_acquire(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_return_acquire(v); +} + +static __always_inline s64 +atomic64_dec_return_release(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_return_release(v); +} + +static __always_inline s64 +atomic64_dec_return_relaxed(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_return_relaxed(v); +} + +static __always_inline s64 +atomic64_fetch_dec(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec(v); +} + +static __always_inline s64 +atomic64_fetch_dec_acquire(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec_acquire(v); +} + +static __always_inline s64 +atomic64_fetch_dec_release(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec_release(v); +} + +static __always_inline s64 +atomic64_fetch_dec_relaxed(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec_relaxed(v); +} + +static __always_inline void +atomic64_and(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_and(i, v); +} + +static __always_inline s64 +atomic64_fetch_and(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_and(i, v); +} + +static __always_inline s64 +atomic64_fetch_and_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_and_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_and_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_and_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_and_relaxed(i, v); +} + +static __always_inline void +atomic64_andnot(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_andnot(i, v); +} + +static __always_inline s64 +atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_andnot(i, v); +} + +static __always_inline s64 +atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_andnot_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_andnot_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_andnot_relaxed(i, v); +} + +static __always_inline void +atomic64_or(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_or(i, v); +} + +static __always_inline s64 +atomic64_fetch_or(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_or(i, v); +} + +static __always_inline s64 +atomic64_fetch_or_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_or_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_or_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_or_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_or_relaxed(i, v); +} + +static __always_inline void +atomic64_xor(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_xor(i, v); +} + +static __always_inline s64 +atomic64_fetch_xor(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_xor(i, v); +} + +static __always_inline s64 +atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_xor_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_xor_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_xor_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_xor_relaxed(i, v); +} + +static __always_inline s64 +atomic64_xchg(atomic64_t *v, s64 i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_xchg(v, i); +} + +static __always_inline s64 +atomic64_xchg_acquire(atomic64_t *v, s64 i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_xchg_acquire(v, i); +} + +static __always_inline s64 +atomic64_xchg_release(atomic64_t *v, s64 i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_xchg_release(v, i); +} + +static __always_inline s64 +atomic64_xchg_relaxed(atomic64_t *v, s64 i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_xchg_relaxed(v, i); +} + +static __always_inline s64 +atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_cmpxchg(v, old, new); +} + +static __always_inline s64 +atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_cmpxchg_acquire(v, old, new); +} + +static __always_inline s64 +atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_cmpxchg_release(v, old, new); +} + +static __always_inline s64 +atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg(v, old, new); +} + +static __always_inline bool +atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg_acquire(v, old, new); +} + +static __always_inline bool +atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg_release(v, old, new); +} + +static __always_inline bool +atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic64_sub_and_test(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_sub_and_test(i, v); +} + +static __always_inline bool +atomic64_dec_and_test(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_and_test(v); +} + +static __always_inline bool +atomic64_inc_and_test(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_and_test(v); +} + +static __always_inline bool +atomic64_add_negative(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_negative(i, v); +} + +static __always_inline s64 +atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_unless(v, a, u); +} + +static __always_inline bool +atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_unless(v, a, u); +} + +static __always_inline bool +atomic64_inc_not_zero(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_not_zero(v); +} + +static __always_inline bool +atomic64_inc_unless_negative(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_unless_negative(v); +} + +static __always_inline bool +atomic64_dec_unless_positive(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_unless_positive(v); +} + +static __always_inline s64 +atomic64_dec_if_positive(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_if_positive(v); +} + +#define xchg(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg(__ai_ptr, __VA_ARGS__); \ +}) + +#define xchg_acquire(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg_acquire(__ai_ptr, __VA_ARGS__); \ +}) + +#define xchg_release(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg_release(__ai_ptr, __VA_ARGS__); \ +}) + +#define xchg_relaxed(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg_relaxed(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg_acquire(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg_release(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg_relaxed(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg64(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg64_acquire(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg64_release(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg64_relaxed(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \ +}) + +#define try_cmpxchg(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg_acquire(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg_release(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg_relaxed(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define cmpxchg_local(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_local(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg64_local(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \ +}) + +#define sync_cmpxchg(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg_double(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \ +}) + + +#define cmpxchg_double_local(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \ +}) + +#endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ +// 5edd72f105b6f54b7e9492d794abee88e6912d29 diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h new file mode 100644 index 000000000000..e40e480e175f --- /dev/null +++ b/include/linux/atomic/atomic-long.h @@ -0,0 +1,1014 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-long.sh +// DO NOT MODIFY THIS FILE DIRECTLY + +#ifndef _LINUX_ATOMIC_LONG_H +#define _LINUX_ATOMIC_LONG_H + +#include +#include + +#ifdef CONFIG_64BIT +typedef atomic64_t atomic_long_t; +#define ATOMIC_LONG_INIT(i) ATOMIC64_INIT(i) +#define atomic_long_cond_read_acquire atomic64_cond_read_acquire +#define atomic_long_cond_read_relaxed atomic64_cond_read_relaxed +#else +typedef atomic_t atomic_long_t; +#define ATOMIC_LONG_INIT(i) ATOMIC_INIT(i) +#define atomic_long_cond_read_acquire atomic_cond_read_acquire +#define atomic_long_cond_read_relaxed atomic_cond_read_relaxed +#endif + +#ifdef CONFIG_64BIT + +static __always_inline long +atomic_long_read(const atomic_long_t *v) +{ + return atomic64_read(v); +} + +static __always_inline long +atomic_long_read_acquire(const atomic_long_t *v) +{ + return atomic64_read_acquire(v); +} + +static __always_inline void +atomic_long_set(atomic_long_t *v, long i) +{ + atomic64_set(v, i); +} + +static __always_inline void +atomic_long_set_release(atomic_long_t *v, long i) +{ + atomic64_set_release(v, i); +} + +static __always_inline void +atomic_long_add(long i, atomic_long_t *v) +{ + atomic64_add(i, v); +} + +static __always_inline long +atomic_long_add_return(long i, atomic_long_t *v) +{ + return atomic64_add_return(i, v); +} + +static __always_inline long +atomic_long_add_return_acquire(long i, atomic_long_t *v) +{ + return atomic64_add_return_acquire(i, v); +} + +static __always_inline long +atomic_long_add_return_release(long i, atomic_long_t *v) +{ + return atomic64_add_return_release(i, v); +} + +static __always_inline long +atomic_long_add_return_relaxed(long i, atomic_long_t *v) +{ + return atomic64_add_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_add(long i, atomic_long_t *v) +{ + return atomic64_fetch_add(i, v); +} + +static __always_inline long +atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_add_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_add_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_add_release(i, v); +} + +static __always_inline long +atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_add_relaxed(i, v); +} + +static __always_inline void +atomic_long_sub(long i, atomic_long_t *v) +{ + atomic64_sub(i, v); +} + +static __always_inline long +atomic_long_sub_return(long i, atomic_long_t *v) +{ + return atomic64_sub_return(i, v); +} + +static __always_inline long +atomic_long_sub_return_acquire(long i, atomic_long_t *v) +{ + return atomic64_sub_return_acquire(i, v); +} + +static __always_inline long +atomic_long_sub_return_release(long i, atomic_long_t *v) +{ + return atomic64_sub_return_release(i, v); +} + +static __always_inline long +atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +{ + return atomic64_sub_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_sub(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub_release(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub_relaxed(i, v); +} + +static __always_inline void +atomic_long_inc(atomic_long_t *v) +{ + atomic64_inc(v); +} + +static __always_inline long +atomic_long_inc_return(atomic_long_t *v) +{ + return atomic64_inc_return(v); +} + +static __always_inline long +atomic_long_inc_return_acquire(atomic_long_t *v) +{ + return atomic64_inc_return_acquire(v); +} + +static __always_inline long +atomic_long_inc_return_release(atomic_long_t *v) +{ + return atomic64_inc_return_release(v); +} + +static __always_inline long +atomic_long_inc_return_relaxed(atomic_long_t *v) +{ + return atomic64_inc_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_inc(atomic_long_t *v) +{ + return atomic64_fetch_inc(v); +} + +static __always_inline long +atomic_long_fetch_inc_acquire(atomic_long_t *v) +{ + return atomic64_fetch_inc_acquire(v); +} + +static __always_inline long +atomic_long_fetch_inc_release(atomic_long_t *v) +{ + return atomic64_fetch_inc_release(v); +} + +static __always_inline long +atomic_long_fetch_inc_relaxed(atomic_long_t *v) +{ + return atomic64_fetch_inc_relaxed(v); +} + +static __always_inline void +atomic_long_dec(atomic_long_t *v) +{ + atomic64_dec(v); +} + +static __always_inline long +atomic_long_dec_return(atomic_long_t *v) +{ + return atomic64_dec_return(v); +} + +static __always_inline long +atomic_long_dec_return_acquire(atomic_long_t *v) +{ + return atomic64_dec_return_acquire(v); +} + +static __always_inline long +atomic_long_dec_return_release(atomic_long_t *v) +{ + return atomic64_dec_return_release(v); +} + +static __always_inline long +atomic_long_dec_return_relaxed(atomic_long_t *v) +{ + return atomic64_dec_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_dec(atomic_long_t *v) +{ + return atomic64_fetch_dec(v); +} + +static __always_inline long +atomic_long_fetch_dec_acquire(atomic_long_t *v) +{ + return atomic64_fetch_dec_acquire(v); +} + +static __always_inline long +atomic_long_fetch_dec_release(atomic_long_t *v) +{ + return atomic64_fetch_dec_release(v); +} + +static __always_inline long +atomic_long_fetch_dec_relaxed(atomic_long_t *v) +{ + return atomic64_fetch_dec_relaxed(v); +} + +static __always_inline void +atomic_long_and(long i, atomic_long_t *v) +{ + atomic64_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and(long i, atomic_long_t *v) +{ + return atomic64_fetch_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_and_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_and_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_and_release(i, v); +} + +static __always_inline long +atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_and_relaxed(i, v); +} + +static __always_inline void +atomic_long_andnot(long i, atomic_long_t *v) +{ + atomic64_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot_release(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot_relaxed(i, v); +} + +static __always_inline void +atomic_long_or(long i, atomic_long_t *v) +{ + atomic64_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or(long i, atomic_long_t *v) +{ + return atomic64_fetch_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_or_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_or_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_or_release(i, v); +} + +static __always_inline long +atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_or_relaxed(i, v); +} + +static __always_inline void +atomic_long_xor(long i, atomic_long_t *v) +{ + atomic64_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor_release(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor_relaxed(i, v); +} + +static __always_inline long +atomic_long_xchg(atomic_long_t *v, long i) +{ + return atomic64_xchg(v, i); +} + +static __always_inline long +atomic_long_xchg_acquire(atomic_long_t *v, long i) +{ + return atomic64_xchg_acquire(v, i); +} + +static __always_inline long +atomic_long_xchg_release(atomic_long_t *v, long i) +{ + return atomic64_xchg_release(v, i); +} + +static __always_inline long +atomic_long_xchg_relaxed(atomic_long_t *v, long i) +{ + return atomic64_xchg_relaxed(v, i); +} + +static __always_inline long +atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg_acquire(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg_release(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg(v, (s64 *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg_acquire(v, (s64 *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg_release(v, (s64 *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new); +} + +static __always_inline bool +atomic_long_sub_and_test(long i, atomic_long_t *v) +{ + return atomic64_sub_and_test(i, v); +} + +static __always_inline bool +atomic_long_dec_and_test(atomic_long_t *v) +{ + return atomic64_dec_and_test(v); +} + +static __always_inline bool +atomic_long_inc_and_test(atomic_long_t *v) +{ + return atomic64_inc_and_test(v); +} + +static __always_inline bool +atomic_long_add_negative(long i, atomic_long_t *v) +{ + return atomic64_add_negative(i, v); +} + +static __always_inline long +atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic64_fetch_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic64_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_inc_not_zero(atomic_long_t *v) +{ + return atomic64_inc_not_zero(v); +} + +static __always_inline bool +atomic_long_inc_unless_negative(atomic_long_t *v) +{ + return atomic64_inc_unless_negative(v); +} + +static __always_inline bool +atomic_long_dec_unless_positive(atomic_long_t *v) +{ + return atomic64_dec_unless_positive(v); +} + +static __always_inline long +atomic_long_dec_if_positive(atomic_long_t *v) +{ + return atomic64_dec_if_positive(v); +} + +#else /* CONFIG_64BIT */ + +static __always_inline long +atomic_long_read(const atomic_long_t *v) +{ + return atomic_read(v); +} + +static __always_inline long +atomic_long_read_acquire(const atomic_long_t *v) +{ + return atomic_read_acquire(v); +} + +static __always_inline void +atomic_long_set(atomic_long_t *v, long i) +{ + atomic_set(v, i); +} + +static __always_inline void +atomic_long_set_release(atomic_long_t *v, long i) +{ + atomic_set_release(v, i); +} + +static __always_inline void +atomic_long_add(long i, atomic_long_t *v) +{ + atomic_add(i, v); +} + +static __always_inline long +atomic_long_add_return(long i, atomic_long_t *v) +{ + return atomic_add_return(i, v); +} + +static __always_inline long +atomic_long_add_return_acquire(long i, atomic_long_t *v) +{ + return atomic_add_return_acquire(i, v); +} + +static __always_inline long +atomic_long_add_return_release(long i, atomic_long_t *v) +{ + return atomic_add_return_release(i, v); +} + +static __always_inline long +atomic_long_add_return_relaxed(long i, atomic_long_t *v) +{ + return atomic_add_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_add(long i, atomic_long_t *v) +{ + return atomic_fetch_add(i, v); +} + +static __always_inline long +atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_add_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_add_release(long i, atomic_long_t *v) +{ + return atomic_fetch_add_release(i, v); +} + +static __always_inline long +atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_add_relaxed(i, v); +} + +static __always_inline void +atomic_long_sub(long i, atomic_long_t *v) +{ + atomic_sub(i, v); +} + +static __always_inline long +atomic_long_sub_return(long i, atomic_long_t *v) +{ + return atomic_sub_return(i, v); +} + +static __always_inline long +atomic_long_sub_return_acquire(long i, atomic_long_t *v) +{ + return atomic_sub_return_acquire(i, v); +} + +static __always_inline long +atomic_long_sub_return_release(long i, atomic_long_t *v) +{ + return atomic_sub_return_release(i, v); +} + +static __always_inline long +atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +{ + return atomic_sub_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_sub(long i, atomic_long_t *v) +{ + return atomic_fetch_sub(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_sub_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_release(long i, atomic_long_t *v) +{ + return atomic_fetch_sub_release(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_sub_relaxed(i, v); +} + +static __always_inline void +atomic_long_inc(atomic_long_t *v) +{ + atomic_inc(v); +} + +static __always_inline long +atomic_long_inc_return(atomic_long_t *v) +{ + return atomic_inc_return(v); +} + +static __always_inline long +atomic_long_inc_return_acquire(atomic_long_t *v) +{ + return atomic_inc_return_acquire(v); +} + +static __always_inline long +atomic_long_inc_return_release(atomic_long_t *v) +{ + return atomic_inc_return_release(v); +} + +static __always_inline long +atomic_long_inc_return_relaxed(atomic_long_t *v) +{ + return atomic_inc_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_inc(atomic_long_t *v) +{ + return atomic_fetch_inc(v); +} + +static __always_inline long +atomic_long_fetch_inc_acquire(atomic_long_t *v) +{ + return atomic_fetch_inc_acquire(v); +} + +static __always_inline long +atomic_long_fetch_inc_release(atomic_long_t *v) +{ + return atomic_fetch_inc_release(v); +} + +static __always_inline long +atomic_long_fetch_inc_relaxed(atomic_long_t *v) +{ + return atomic_fetch_inc_relaxed(v); +} + +static __always_inline void +atomic_long_dec(atomic_long_t *v) +{ + atomic_dec(v); +} + +static __always_inline long +atomic_long_dec_return(atomic_long_t *v) +{ + return atomic_dec_return(v); +} + +static __always_inline long +atomic_long_dec_return_acquire(atomic_long_t *v) +{ + return atomic_dec_return_acquire(v); +} + +static __always_inline long +atomic_long_dec_return_release(atomic_long_t *v) +{ + return atomic_dec_return_release(v); +} + +static __always_inline long +atomic_long_dec_return_relaxed(atomic_long_t *v) +{ + return atomic_dec_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_dec(atomic_long_t *v) +{ + return atomic_fetch_dec(v); +} + +static __always_inline long +atomic_long_fetch_dec_acquire(atomic_long_t *v) +{ + return atomic_fetch_dec_acquire(v); +} + +static __always_inline long +atomic_long_fetch_dec_release(atomic_long_t *v) +{ + return atomic_fetch_dec_release(v); +} + +static __always_inline long +atomic_long_fetch_dec_relaxed(atomic_long_t *v) +{ + return atomic_fetch_dec_relaxed(v); +} + +static __always_inline void +atomic_long_and(long i, atomic_long_t *v) +{ + atomic_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and(long i, atomic_long_t *v) +{ + return atomic_fetch_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_and_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_and_release(long i, atomic_long_t *v) +{ + return atomic_fetch_and_release(i, v); +} + +static __always_inline long +atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_and_relaxed(i, v); +} + +static __always_inline void +atomic_long_andnot(long i, atomic_long_t *v) +{ + atomic_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot_release(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot_relaxed(i, v); +} + +static __always_inline void +atomic_long_or(long i, atomic_long_t *v) +{ + atomic_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or(long i, atomic_long_t *v) +{ + return atomic_fetch_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_or_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_or_release(long i, atomic_long_t *v) +{ + return atomic_fetch_or_release(i, v); +} + +static __always_inline long +atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_or_relaxed(i, v); +} + +static __always_inline void +atomic_long_xor(long i, atomic_long_t *v) +{ + atomic_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor(long i, atomic_long_t *v) +{ + return atomic_fetch_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_xor_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_release(long i, atomic_long_t *v) +{ + return atomic_fetch_xor_release(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_xor_relaxed(i, v); +} + +static __always_inline long +atomic_long_xchg(atomic_long_t *v, long i) +{ + return atomic_xchg(v, i); +} + +static __always_inline long +atomic_long_xchg_acquire(atomic_long_t *v, long i) +{ + return atomic_xchg_acquire(v, i); +} + +static __always_inline long +atomic_long_xchg_release(atomic_long_t *v, long i) +{ + return atomic_xchg_release(v, i); +} + +static __always_inline long +atomic_long_xchg_relaxed(atomic_long_t *v, long i) +{ + return atomic_xchg_relaxed(v, i); +} + +static __always_inline long +atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +{ + return atomic_cmpxchg(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +{ + return atomic_cmpxchg_acquire(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +{ + return atomic_cmpxchg_release(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +{ + return atomic_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg(v, (int *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg_acquire(v, (int *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg_release(v, (int *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg_relaxed(v, (int *)old, new); +} + +static __always_inline bool +atomic_long_sub_and_test(long i, atomic_long_t *v) +{ + return atomic_sub_and_test(i, v); +} + +static __always_inline bool +atomic_long_dec_and_test(atomic_long_t *v) +{ + return atomic_dec_and_test(v); +} + +static __always_inline bool +atomic_long_inc_and_test(atomic_long_t *v) +{ + return atomic_inc_and_test(v); +} + +static __always_inline bool +atomic_long_add_negative(long i, atomic_long_t *v) +{ + return atomic_add_negative(i, v); +} + +static __always_inline long +atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic_fetch_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_inc_not_zero(atomic_long_t *v) +{ + return atomic_inc_not_zero(v); +} + +static __always_inline bool +atomic_long_inc_unless_negative(atomic_long_t *v) +{ + return atomic_inc_unless_negative(v); +} + +static __always_inline bool +atomic_long_dec_unless_positive(atomic_long_t *v) +{ + return atomic_dec_unless_positive(v); +} + +static __always_inline long +atomic_long_dec_if_positive(atomic_long_t *v) +{ + return atomic_dec_if_positive(v); +} + +#endif /* CONFIG_64BIT */ +#endif /* _LINUX_ATOMIC_LONG_H */ +// c5552b5d78a0c7584dfd03cba985e78a1a86bbed diff --git a/scripts/atomic/check-atomics.sh b/scripts/atomic/check-atomics.sh index 9c7fbd4bcbce..0e7bab3eb0d1 100755 --- a/scripts/atomic/check-atomics.sh +++ b/scripts/atomic/check-atomics.sh @@ -14,9 +14,9 @@ if [ $? -ne 0 ]; then fi cat < #include @@ -158,5 +158,5 @@ gen_xchg "cmpxchg_double_local" "2 * " cat < #include @@ -98,5 +98,5 @@ done cat < ${LINUXDIR}/include/${header} -- cgit v1.2.3 From 67d1b0de258ad066e1fc85d0ceaa75e107fb45bb Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 13 Jul 2021 11:52:52 +0100 Subject: locking/atomic: add arch_atomic_long*() Now that all architectures provide arch_{atomic,atomic64}_*(), we can build arch_atomic_long_*() atop these, which can be safely used in noinstr code. The regular atomic_long_*() wrappers are built atop these, as we do for {atomic,atomic64}_*() atop arch_{atomic,atomic64}_*(). We don't provide arch_* versions of the cond_read*() variants, as we don't have arch_* versions of the underlying atomic/atomic64 functions (nor the smp_cond_load*() helpers these are typically based on). Note that the headers in this patch under include/linux/atomic/ are generated by the scripts in scripts/atomic/. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210713105253.7615-5-mark.rutland@arm.com --- include/linux/atomic.h | 2 +- include/linux/atomic/atomic-instrumented.h | 580 ++++++++++++++++++++++++- include/linux/atomic/atomic-long.h | 658 ++++++++++++++--------------- scripts/atomic/gen-atomic-instrumented.sh | 5 + scripts/atomic/gen-atomic-long.sh | 4 +- 5 files changed, 916 insertions(+), 333 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 1896a58b5aba..8dd57c3a99e9 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -78,7 +78,7 @@ }) #include -#include #include +#include #endif /* _LINUX_ATOMIC_H */ diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index f6fe36c428df..a0f654370da3 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1177,6 +1177,584 @@ atomic64_dec_if_positive(atomic64_t *v) return arch_atomic64_dec_if_positive(v); } +static __always_inline long +atomic_long_read(const atomic_long_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic_long_read(v); +} + +static __always_inline long +atomic_long_read_acquire(const atomic_long_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic_long_read_acquire(v); +} + +static __always_inline void +atomic_long_set(atomic_long_t *v, long i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic_long_set(v, i); +} + +static __always_inline void +atomic_long_set_release(atomic_long_t *v, long i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic_long_set_release(v, i); +} + +static __always_inline void +atomic_long_add(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_add(i, v); +} + +static __always_inline long +atomic_long_add_return(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_return(i, v); +} + +static __always_inline long +atomic_long_add_return_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_return_acquire(i, v); +} + +static __always_inline long +atomic_long_add_return_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_return_release(i, v); +} + +static __always_inline long +atomic_long_add_return_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_add(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_add(i, v); +} + +static __always_inline long +atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_add_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_add_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_add_release(i, v); +} + +static __always_inline long +atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_add_relaxed(i, v); +} + +static __always_inline void +atomic_long_sub(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_sub(i, v); +} + +static __always_inline long +atomic_long_sub_return(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_sub_return(i, v); +} + +static __always_inline long +atomic_long_sub_return_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_sub_return_acquire(i, v); +} + +static __always_inline long +atomic_long_sub_return_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_sub_return_release(i, v); +} + +static __always_inline long +atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_sub_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_sub(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_sub(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_sub_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_sub_release(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_sub_relaxed(i, v); +} + +static __always_inline void +atomic_long_inc(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_inc(v); +} + +static __always_inline long +atomic_long_inc_return(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_return(v); +} + +static __always_inline long +atomic_long_inc_return_acquire(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_return_acquire(v); +} + +static __always_inline long +atomic_long_inc_return_release(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_return_release(v); +} + +static __always_inline long +atomic_long_inc_return_relaxed(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_inc(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_inc(v); +} + +static __always_inline long +atomic_long_fetch_inc_acquire(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_inc_acquire(v); +} + +static __always_inline long +atomic_long_fetch_inc_release(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_inc_release(v); +} + +static __always_inline long +atomic_long_fetch_inc_relaxed(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_inc_relaxed(v); +} + +static __always_inline void +atomic_long_dec(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_dec(v); +} + +static __always_inline long +atomic_long_dec_return(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_return(v); +} + +static __always_inline long +atomic_long_dec_return_acquire(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_return_acquire(v); +} + +static __always_inline long +atomic_long_dec_return_release(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_return_release(v); +} + +static __always_inline long +atomic_long_dec_return_relaxed(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_dec(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_dec(v); +} + +static __always_inline long +atomic_long_fetch_dec_acquire(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_dec_acquire(v); +} + +static __always_inline long +atomic_long_fetch_dec_release(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_dec_release(v); +} + +static __always_inline long +atomic_long_fetch_dec_relaxed(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_dec_relaxed(v); +} + +static __always_inline void +atomic_long_and(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_and_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_and_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_and_release(i, v); +} + +static __always_inline long +atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_and_relaxed(i, v); +} + +static __always_inline void +atomic_long_andnot(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_andnot_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_andnot_release(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_andnot_relaxed(i, v); +} + +static __always_inline void +atomic_long_or(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_or_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_or_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_or_release(i, v); +} + +static __always_inline long +atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_or_relaxed(i, v); +} + +static __always_inline void +atomic_long_xor(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_xor_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_xor_release(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_xor_relaxed(i, v); +} + +static __always_inline long +atomic_long_xchg(atomic_long_t *v, long i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_xchg(v, i); +} + +static __always_inline long +atomic_long_xchg_acquire(atomic_long_t *v, long i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_xchg_acquire(v, i); +} + +static __always_inline long +atomic_long_xchg_release(atomic_long_t *v, long i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_xchg_release(v, i); +} + +static __always_inline long +atomic_long_xchg_relaxed(atomic_long_t *v, long i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_xchg_relaxed(v, i); +} + +static __always_inline long +atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_cmpxchg(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_cmpxchg_acquire(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_cmpxchg_release(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_long_try_cmpxchg(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_long_try_cmpxchg_acquire(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_long_try_cmpxchg_release(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_long_try_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_long_sub_and_test(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_sub_and_test(i, v); +} + +static __always_inline bool +atomic_long_dec_and_test(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_and_test(v); +} + +static __always_inline bool +atomic_long_inc_and_test(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_and_test(v); +} + +static __always_inline bool +atomic_long_add_negative(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_negative(i, v); +} + +static __always_inline long +atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_add_unless(atomic_long_t *v, long a, long u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_inc_not_zero(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_not_zero(v); +} + +static __always_inline bool +atomic_long_inc_unless_negative(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_unless_negative(v); +} + +static __always_inline bool +atomic_long_dec_unless_positive(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_unless_positive(v); +} + +static __always_inline long +atomic_long_dec_if_positive(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_if_positive(v); +} + #define xchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ @@ -1334,4 +1912,4 @@ atomic64_dec_if_positive(atomic64_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 5edd72f105b6f54b7e9492d794abee88e6912d29 +// 2a9553f0a9d5619f19151092df5cabbbf16ce835 diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index e40e480e175f..800b8c35992d 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -24,991 +24,991 @@ typedef atomic_t atomic_long_t; #ifdef CONFIG_64BIT static __always_inline long -atomic_long_read(const atomic_long_t *v) +arch_atomic_long_read(const atomic_long_t *v) { - return atomic64_read(v); + return arch_atomic64_read(v); } static __always_inline long -atomic_long_read_acquire(const atomic_long_t *v) +arch_atomic_long_read_acquire(const atomic_long_t *v) { - return atomic64_read_acquire(v); + return arch_atomic64_read_acquire(v); } static __always_inline void -atomic_long_set(atomic_long_t *v, long i) +arch_atomic_long_set(atomic_long_t *v, long i) { - atomic64_set(v, i); + arch_atomic64_set(v, i); } static __always_inline void -atomic_long_set_release(atomic_long_t *v, long i) +arch_atomic_long_set_release(atomic_long_t *v, long i) { - atomic64_set_release(v, i); + arch_atomic64_set_release(v, i); } static __always_inline void -atomic_long_add(long i, atomic_long_t *v) +arch_atomic_long_add(long i, atomic_long_t *v) { - atomic64_add(i, v); + arch_atomic64_add(i, v); } static __always_inline long -atomic_long_add_return(long i, atomic_long_t *v) +arch_atomic_long_add_return(long i, atomic_long_t *v) { - return atomic64_add_return(i, v); + return arch_atomic64_add_return(i, v); } static __always_inline long -atomic_long_add_return_acquire(long i, atomic_long_t *v) +arch_atomic_long_add_return_acquire(long i, atomic_long_t *v) { - return atomic64_add_return_acquire(i, v); + return arch_atomic64_add_return_acquire(i, v); } static __always_inline long -atomic_long_add_return_release(long i, atomic_long_t *v) +arch_atomic_long_add_return_release(long i, atomic_long_t *v) { - return atomic64_add_return_release(i, v); + return arch_atomic64_add_return_release(i, v); } static __always_inline long -atomic_long_add_return_relaxed(long i, atomic_long_t *v) +arch_atomic_long_add_return_relaxed(long i, atomic_long_t *v) { - return atomic64_add_return_relaxed(i, v); + return arch_atomic64_add_return_relaxed(i, v); } static __always_inline long -atomic_long_fetch_add(long i, atomic_long_t *v) +arch_atomic_long_fetch_add(long i, atomic_long_t *v) { - return atomic64_fetch_add(i, v); + return arch_atomic64_fetch_add(i, v); } static __always_inline long -atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_add_acquire(i, v); + return arch_atomic64_fetch_add_acquire(i, v); } static __always_inline long -atomic_long_fetch_add_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_release(long i, atomic_long_t *v) { - return atomic64_fetch_add_release(i, v); + return arch_atomic64_fetch_add_release(i, v); } static __always_inline long -atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_add_relaxed(i, v); + return arch_atomic64_fetch_add_relaxed(i, v); } static __always_inline void -atomic_long_sub(long i, atomic_long_t *v) +arch_atomic_long_sub(long i, atomic_long_t *v) { - atomic64_sub(i, v); + arch_atomic64_sub(i, v); } static __always_inline long -atomic_long_sub_return(long i, atomic_long_t *v) +arch_atomic_long_sub_return(long i, atomic_long_t *v) { - return atomic64_sub_return(i, v); + return arch_atomic64_sub_return(i, v); } static __always_inline long -atomic_long_sub_return_acquire(long i, atomic_long_t *v) +arch_atomic_long_sub_return_acquire(long i, atomic_long_t *v) { - return atomic64_sub_return_acquire(i, v); + return arch_atomic64_sub_return_acquire(i, v); } static __always_inline long -atomic_long_sub_return_release(long i, atomic_long_t *v) +arch_atomic_long_sub_return_release(long i, atomic_long_t *v) { - return atomic64_sub_return_release(i, v); + return arch_atomic64_sub_return_release(i, v); } static __always_inline long -atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +arch_atomic_long_sub_return_relaxed(long i, atomic_long_t *v) { - return atomic64_sub_return_relaxed(i, v); + return arch_atomic64_sub_return_relaxed(i, v); } static __always_inline long -atomic_long_fetch_sub(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub(long i, atomic_long_t *v) { - return atomic64_fetch_sub(i, v); + return arch_atomic64_fetch_sub(i, v); } static __always_inline long -atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_sub_acquire(i, v); + return arch_atomic64_fetch_sub_acquire(i, v); } static __always_inline long -atomic_long_fetch_sub_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_release(long i, atomic_long_t *v) { - return atomic64_fetch_sub_release(i, v); + return arch_atomic64_fetch_sub_release(i, v); } static __always_inline long -atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_sub_relaxed(i, v); + return arch_atomic64_fetch_sub_relaxed(i, v); } static __always_inline void -atomic_long_inc(atomic_long_t *v) +arch_atomic_long_inc(atomic_long_t *v) { - atomic64_inc(v); + arch_atomic64_inc(v); } static __always_inline long -atomic_long_inc_return(atomic_long_t *v) +arch_atomic_long_inc_return(atomic_long_t *v) { - return atomic64_inc_return(v); + return arch_atomic64_inc_return(v); } static __always_inline long -atomic_long_inc_return_acquire(atomic_long_t *v) +arch_atomic_long_inc_return_acquire(atomic_long_t *v) { - return atomic64_inc_return_acquire(v); + return arch_atomic64_inc_return_acquire(v); } static __always_inline long -atomic_long_inc_return_release(atomic_long_t *v) +arch_atomic_long_inc_return_release(atomic_long_t *v) { - return atomic64_inc_return_release(v); + return arch_atomic64_inc_return_release(v); } static __always_inline long -atomic_long_inc_return_relaxed(atomic_long_t *v) +arch_atomic_long_inc_return_relaxed(atomic_long_t *v) { - return atomic64_inc_return_relaxed(v); + return arch_atomic64_inc_return_relaxed(v); } static __always_inline long -atomic_long_fetch_inc(atomic_long_t *v) +arch_atomic_long_fetch_inc(atomic_long_t *v) { - return atomic64_fetch_inc(v); + return arch_atomic64_fetch_inc(v); } static __always_inline long -atomic_long_fetch_inc_acquire(atomic_long_t *v) +arch_atomic_long_fetch_inc_acquire(atomic_long_t *v) { - return atomic64_fetch_inc_acquire(v); + return arch_atomic64_fetch_inc_acquire(v); } static __always_inline long -atomic_long_fetch_inc_release(atomic_long_t *v) +arch_atomic_long_fetch_inc_release(atomic_long_t *v) { - return atomic64_fetch_inc_release(v); + return arch_atomic64_fetch_inc_release(v); } static __always_inline long -atomic_long_fetch_inc_relaxed(atomic_long_t *v) +arch_atomic_long_fetch_inc_relaxed(atomic_long_t *v) { - return atomic64_fetch_inc_relaxed(v); + return arch_atomic64_fetch_inc_relaxed(v); } static __always_inline void -atomic_long_dec(atomic_long_t *v) +arch_atomic_long_dec(atomic_long_t *v) { - atomic64_dec(v); + arch_atomic64_dec(v); } static __always_inline long -atomic_long_dec_return(atomic_long_t *v) +arch_atomic_long_dec_return(atomic_long_t *v) { - return atomic64_dec_return(v); + return arch_atomic64_dec_return(v); } static __always_inline long -atomic_long_dec_return_acquire(atomic_long_t *v) +arch_atomic_long_dec_return_acquire(atomic_long_t *v) { - return atomic64_dec_return_acquire(v); + return arch_atomic64_dec_return_acquire(v); } static __always_inline long -atomic_long_dec_return_release(atomic_long_t *v) +arch_atomic_long_dec_return_release(atomic_long_t *v) { - return atomic64_dec_return_release(v); + return arch_atomic64_dec_return_release(v); } static __always_inline long -atomic_long_dec_return_relaxed(atomic_long_t *v) +arch_atomic_long_dec_return_relaxed(atomic_long_t *v) { - return atomic64_dec_return_relaxed(v); + return arch_atomic64_dec_return_relaxed(v); } static __always_inline long -atomic_long_fetch_dec(atomic_long_t *v) +arch_atomic_long_fetch_dec(atomic_long_t *v) { - return atomic64_fetch_dec(v); + return arch_atomic64_fetch_dec(v); } static __always_inline long -atomic_long_fetch_dec_acquire(atomic_long_t *v) +arch_atomic_long_fetch_dec_acquire(atomic_long_t *v) { - return atomic64_fetch_dec_acquire(v); + return arch_atomic64_fetch_dec_acquire(v); } static __always_inline long -atomic_long_fetch_dec_release(atomic_long_t *v) +arch_atomic_long_fetch_dec_release(atomic_long_t *v) { - return atomic64_fetch_dec_release(v); + return arch_atomic64_fetch_dec_release(v); } static __always_inline long -atomic_long_fetch_dec_relaxed(atomic_long_t *v) +arch_atomic_long_fetch_dec_relaxed(atomic_long_t *v) { - return atomic64_fetch_dec_relaxed(v); + return arch_atomic64_fetch_dec_relaxed(v); } static __always_inline void -atomic_long_and(long i, atomic_long_t *v) +arch_atomic_long_and(long i, atomic_long_t *v) { - atomic64_and(i, v); + arch_atomic64_and(i, v); } static __always_inline long -atomic_long_fetch_and(long i, atomic_long_t *v) +arch_atomic_long_fetch_and(long i, atomic_long_t *v) { - return atomic64_fetch_and(i, v); + return arch_atomic64_fetch_and(i, v); } static __always_inline long -atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_and_acquire(i, v); + return arch_atomic64_fetch_and_acquire(i, v); } static __always_inline long -atomic_long_fetch_and_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_release(long i, atomic_long_t *v) { - return atomic64_fetch_and_release(i, v); + return arch_atomic64_fetch_and_release(i, v); } static __always_inline long -atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_and_relaxed(i, v); + return arch_atomic64_fetch_and_relaxed(i, v); } static __always_inline void -atomic_long_andnot(long i, atomic_long_t *v) +arch_atomic_long_andnot(long i, atomic_long_t *v) { - atomic64_andnot(i, v); + arch_atomic64_andnot(i, v); } static __always_inline long -atomic_long_fetch_andnot(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot(long i, atomic_long_t *v) { - return atomic64_fetch_andnot(i, v); + return arch_atomic64_fetch_andnot(i, v); } static __always_inline long -atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_andnot_acquire(i, v); + return arch_atomic64_fetch_andnot_acquire(i, v); } static __always_inline long -atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { - return atomic64_fetch_andnot_release(i, v); + return arch_atomic64_fetch_andnot_release(i, v); } static __always_inline long -atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_andnot_relaxed(i, v); + return arch_atomic64_fetch_andnot_relaxed(i, v); } static __always_inline void -atomic_long_or(long i, atomic_long_t *v) +arch_atomic_long_or(long i, atomic_long_t *v) { - atomic64_or(i, v); + arch_atomic64_or(i, v); } static __always_inline long -atomic_long_fetch_or(long i, atomic_long_t *v) +arch_atomic_long_fetch_or(long i, atomic_long_t *v) { - return atomic64_fetch_or(i, v); + return arch_atomic64_fetch_or(i, v); } static __always_inline long -atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_or_acquire(i, v); + return arch_atomic64_fetch_or_acquire(i, v); } static __always_inline long -atomic_long_fetch_or_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_release(long i, atomic_long_t *v) { - return atomic64_fetch_or_release(i, v); + return arch_atomic64_fetch_or_release(i, v); } static __always_inline long -atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_or_relaxed(i, v); + return arch_atomic64_fetch_or_relaxed(i, v); } static __always_inline void -atomic_long_xor(long i, atomic_long_t *v) +arch_atomic_long_xor(long i, atomic_long_t *v) { - atomic64_xor(i, v); + arch_atomic64_xor(i, v); } static __always_inline long -atomic_long_fetch_xor(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor(long i, atomic_long_t *v) { - return atomic64_fetch_xor(i, v); + return arch_atomic64_fetch_xor(i, v); } static __always_inline long -atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_xor_acquire(i, v); + return arch_atomic64_fetch_xor_acquire(i, v); } static __always_inline long -atomic_long_fetch_xor_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_release(long i, atomic_long_t *v) { - return atomic64_fetch_xor_release(i, v); + return arch_atomic64_fetch_xor_release(i, v); } static __always_inline long -atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_xor_relaxed(i, v); + return arch_atomic64_fetch_xor_relaxed(i, v); } static __always_inline long -atomic_long_xchg(atomic_long_t *v, long i) +arch_atomic_long_xchg(atomic_long_t *v, long i) { - return atomic64_xchg(v, i); + return arch_atomic64_xchg(v, i); } static __always_inline long -atomic_long_xchg_acquire(atomic_long_t *v, long i) +arch_atomic_long_xchg_acquire(atomic_long_t *v, long i) { - return atomic64_xchg_acquire(v, i); + return arch_atomic64_xchg_acquire(v, i); } static __always_inline long -atomic_long_xchg_release(atomic_long_t *v, long i) +arch_atomic_long_xchg_release(atomic_long_t *v, long i) { - return atomic64_xchg_release(v, i); + return arch_atomic64_xchg_release(v, i); } static __always_inline long -atomic_long_xchg_relaxed(atomic_long_t *v, long i) +arch_atomic_long_xchg_relaxed(atomic_long_t *v, long i) { - return atomic64_xchg_relaxed(v, i); + return arch_atomic64_xchg_relaxed(v, i); } static __always_inline long -atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { - return atomic64_cmpxchg(v, old, new); + return arch_atomic64_cmpxchg(v, old, new); } static __always_inline long -atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) { - return atomic64_cmpxchg_acquire(v, old, new); + return arch_atomic64_cmpxchg_acquire(v, old, new); } static __always_inline long -atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { - return atomic64_cmpxchg_release(v, old, new); + return arch_atomic64_cmpxchg_release(v, old, new); } static __always_inline long -atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) { - return atomic64_cmpxchg_relaxed(v, old, new); + return arch_atomic64_cmpxchg_relaxed(v, old, new); } static __always_inline bool -atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { - return atomic64_try_cmpxchg(v, (s64 *)old, new); + return arch_atomic64_try_cmpxchg(v, (s64 *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { - return atomic64_try_cmpxchg_acquire(v, (s64 *)old, new); + return arch_atomic64_try_cmpxchg_acquire(v, (s64 *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { - return atomic64_try_cmpxchg_release(v, (s64 *)old, new); + return arch_atomic64_try_cmpxchg_release(v, (s64 *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { - return atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new); + return arch_atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new); } static __always_inline bool -atomic_long_sub_and_test(long i, atomic_long_t *v) +arch_atomic_long_sub_and_test(long i, atomic_long_t *v) { - return atomic64_sub_and_test(i, v); + return arch_atomic64_sub_and_test(i, v); } static __always_inline bool -atomic_long_dec_and_test(atomic_long_t *v) +arch_atomic_long_dec_and_test(atomic_long_t *v) { - return atomic64_dec_and_test(v); + return arch_atomic64_dec_and_test(v); } static __always_inline bool -atomic_long_inc_and_test(atomic_long_t *v) +arch_atomic_long_inc_and_test(atomic_long_t *v) { - return atomic64_inc_and_test(v); + return arch_atomic64_inc_and_test(v); } static __always_inline bool -atomic_long_add_negative(long i, atomic_long_t *v) +arch_atomic_long_add_negative(long i, atomic_long_t *v) { - return atomic64_add_negative(i, v); + return arch_atomic64_add_negative(i, v); } static __always_inline long -atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { - return atomic64_fetch_add_unless(v, a, u); + return arch_atomic64_fetch_add_unless(v, a, u); } static __always_inline bool -atomic_long_add_unless(atomic_long_t *v, long a, long u) +arch_atomic_long_add_unless(atomic_long_t *v, long a, long u) { - return atomic64_add_unless(v, a, u); + return arch_atomic64_add_unless(v, a, u); } static __always_inline bool -atomic_long_inc_not_zero(atomic_long_t *v) +arch_atomic_long_inc_not_zero(atomic_long_t *v) { - return atomic64_inc_not_zero(v); + return arch_atomic64_inc_not_zero(v); } static __always_inline bool -atomic_long_inc_unless_negative(atomic_long_t *v) +arch_atomic_long_inc_unless_negative(atomic_long_t *v) { - return atomic64_inc_unless_negative(v); + return arch_atomic64_inc_unless_negative(v); } static __always_inline bool -atomic_long_dec_unless_positive(atomic_long_t *v) +arch_atomic_long_dec_unless_positive(atomic_long_t *v) { - return atomic64_dec_unless_positive(v); + return arch_atomic64_dec_unless_positive(v); } static __always_inline long -atomic_long_dec_if_positive(atomic_long_t *v) +arch_atomic_long_dec_if_positive(atomic_long_t *v) { - return atomic64_dec_if_positive(v); + return arch_atomic64_dec_if_positive(v); } #else /* CONFIG_64BIT */ static __always_inline long -atomic_long_read(const atomic_long_t *v) +arch_atomic_long_read(const atomic_long_t *v) { - return atomic_read(v); + return arch_atomic_read(v); } static __always_inline long -atomic_long_read_acquire(const atomic_long_t *v) +arch_atomic_long_read_acquire(const atomic_long_t *v) { - return atomic_read_acquire(v); + return arch_atomic_read_acquire(v); } static __always_inline void -atomic_long_set(atomic_long_t *v, long i) +arch_atomic_long_set(atomic_long_t *v, long i) { - atomic_set(v, i); + arch_atomic_set(v, i); } static __always_inline void -atomic_long_set_release(atomic_long_t *v, long i) +arch_atomic_long_set_release(atomic_long_t *v, long i) { - atomic_set_release(v, i); + arch_atomic_set_release(v, i); } static __always_inline void -atomic_long_add(long i, atomic_long_t *v) +arch_atomic_long_add(long i, atomic_long_t *v) { - atomic_add(i, v); + arch_atomic_add(i, v); } static __always_inline long -atomic_long_add_return(long i, atomic_long_t *v) +arch_atomic_long_add_return(long i, atomic_long_t *v) { - return atomic_add_return(i, v); + return arch_atomic_add_return(i, v); } static __always_inline long -atomic_long_add_return_acquire(long i, atomic_long_t *v) +arch_atomic_long_add_return_acquire(long i, atomic_long_t *v) { - return atomic_add_return_acquire(i, v); + return arch_atomic_add_return_acquire(i, v); } static __always_inline long -atomic_long_add_return_release(long i, atomic_long_t *v) +arch_atomic_long_add_return_release(long i, atomic_long_t *v) { - return atomic_add_return_release(i, v); + return arch_atomic_add_return_release(i, v); } static __always_inline long -atomic_long_add_return_relaxed(long i, atomic_long_t *v) +arch_atomic_long_add_return_relaxed(long i, atomic_long_t *v) { - return atomic_add_return_relaxed(i, v); + return arch_atomic_add_return_relaxed(i, v); } static __always_inline long -atomic_long_fetch_add(long i, atomic_long_t *v) +arch_atomic_long_fetch_add(long i, atomic_long_t *v) { - return atomic_fetch_add(i, v); + return arch_atomic_fetch_add(i, v); } static __always_inline long -atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_acquire(long i, atomic_long_t *v) { - return atomic_fetch_add_acquire(i, v); + return arch_atomic_fetch_add_acquire(i, v); } static __always_inline long -atomic_long_fetch_add_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_release(long i, atomic_long_t *v) { - return atomic_fetch_add_release(i, v); + return arch_atomic_fetch_add_release(i, v); } static __always_inline long -atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_add_relaxed(i, v); + return arch_atomic_fetch_add_relaxed(i, v); } static __always_inline void -atomic_long_sub(long i, atomic_long_t *v) +arch_atomic_long_sub(long i, atomic_long_t *v) { - atomic_sub(i, v); + arch_atomic_sub(i, v); } static __always_inline long -atomic_long_sub_return(long i, atomic_long_t *v) +arch_atomic_long_sub_return(long i, atomic_long_t *v) { - return atomic_sub_return(i, v); + return arch_atomic_sub_return(i, v); } static __always_inline long -atomic_long_sub_return_acquire(long i, atomic_long_t *v) +arch_atomic_long_sub_return_acquire(long i, atomic_long_t *v) { - return atomic_sub_return_acquire(i, v); + return arch_atomic_sub_return_acquire(i, v); } static __always_inline long -atomic_long_sub_return_release(long i, atomic_long_t *v) +arch_atomic_long_sub_return_release(long i, atomic_long_t *v) { - return atomic_sub_return_release(i, v); + return arch_atomic_sub_return_release(i, v); } static __always_inline long -atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +arch_atomic_long_sub_return_relaxed(long i, atomic_long_t *v) { - return atomic_sub_return_relaxed(i, v); + return arch_atomic_sub_return_relaxed(i, v); } static __always_inline long -atomic_long_fetch_sub(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub(long i, atomic_long_t *v) { - return atomic_fetch_sub(i, v); + return arch_atomic_fetch_sub(i, v); } static __always_inline long -atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) { - return atomic_fetch_sub_acquire(i, v); + return arch_atomic_fetch_sub_acquire(i, v); } static __always_inline long -atomic_long_fetch_sub_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_release(long i, atomic_long_t *v) { - return atomic_fetch_sub_release(i, v); + return arch_atomic_fetch_sub_release(i, v); } static __always_inline long -atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_sub_relaxed(i, v); + return arch_atomic_fetch_sub_relaxed(i, v); } static __always_inline void -atomic_long_inc(atomic_long_t *v) +arch_atomic_long_inc(atomic_long_t *v) { - atomic_inc(v); + arch_atomic_inc(v); } static __always_inline long -atomic_long_inc_return(atomic_long_t *v) +arch_atomic_long_inc_return(atomic_long_t *v) { - return atomic_inc_return(v); + return arch_atomic_inc_return(v); } static __always_inline long -atomic_long_inc_return_acquire(atomic_long_t *v) +arch_atomic_long_inc_return_acquire(atomic_long_t *v) { - return atomic_inc_return_acquire(v); + return arch_atomic_inc_return_acquire(v); } static __always_inline long -atomic_long_inc_return_release(atomic_long_t *v) +arch_atomic_long_inc_return_release(atomic_long_t *v) { - return atomic_inc_return_release(v); + return arch_atomic_inc_return_release(v); } static __always_inline long -atomic_long_inc_return_relaxed(atomic_long_t *v) +arch_atomic_long_inc_return_relaxed(atomic_long_t *v) { - return atomic_inc_return_relaxed(v); + return arch_atomic_inc_return_relaxed(v); } static __always_inline long -atomic_long_fetch_inc(atomic_long_t *v) +arch_atomic_long_fetch_inc(atomic_long_t *v) { - return atomic_fetch_inc(v); + return arch_atomic_fetch_inc(v); } static __always_inline long -atomic_long_fetch_inc_acquire(atomic_long_t *v) +arch_atomic_long_fetch_inc_acquire(atomic_long_t *v) { - return atomic_fetch_inc_acquire(v); + return arch_atomic_fetch_inc_acquire(v); } static __always_inline long -atomic_long_fetch_inc_release(atomic_long_t *v) +arch_atomic_long_fetch_inc_release(atomic_long_t *v) { - return atomic_fetch_inc_release(v); + return arch_atomic_fetch_inc_release(v); } static __always_inline long -atomic_long_fetch_inc_relaxed(atomic_long_t *v) +arch_atomic_long_fetch_inc_relaxed(atomic_long_t *v) { - return atomic_fetch_inc_relaxed(v); + return arch_atomic_fetch_inc_relaxed(v); } static __always_inline void -atomic_long_dec(atomic_long_t *v) +arch_atomic_long_dec(atomic_long_t *v) { - atomic_dec(v); + arch_atomic_dec(v); } static __always_inline long -atomic_long_dec_return(atomic_long_t *v) +arch_atomic_long_dec_return(atomic_long_t *v) { - return atomic_dec_return(v); + return arch_atomic_dec_return(v); } static __always_inline long -atomic_long_dec_return_acquire(atomic_long_t *v) +arch_atomic_long_dec_return_acquire(atomic_long_t *v) { - return atomic_dec_return_acquire(v); + return arch_atomic_dec_return_acquire(v); } static __always_inline long -atomic_long_dec_return_release(atomic_long_t *v) +arch_atomic_long_dec_return_release(atomic_long_t *v) { - return atomic_dec_return_release(v); + return arch_atomic_dec_return_release(v); } static __always_inline long -atomic_long_dec_return_relaxed(atomic_long_t *v) +arch_atomic_long_dec_return_relaxed(atomic_long_t *v) { - return atomic_dec_return_relaxed(v); + return arch_atomic_dec_return_relaxed(v); } static __always_inline long -atomic_long_fetch_dec(atomic_long_t *v) +arch_atomic_long_fetch_dec(atomic_long_t *v) { - return atomic_fetch_dec(v); + return arch_atomic_fetch_dec(v); } static __always_inline long -atomic_long_fetch_dec_acquire(atomic_long_t *v) +arch_atomic_long_fetch_dec_acquire(atomic_long_t *v) { - return atomic_fetch_dec_acquire(v); + return arch_atomic_fetch_dec_acquire(v); } static __always_inline long -atomic_long_fetch_dec_release(atomic_long_t *v) +arch_atomic_long_fetch_dec_release(atomic_long_t *v) { - return atomic_fetch_dec_release(v); + return arch_atomic_fetch_dec_release(v); } static __always_inline long -atomic_long_fetch_dec_relaxed(atomic_long_t *v) +arch_atomic_long_fetch_dec_relaxed(atomic_long_t *v) { - return atomic_fetch_dec_relaxed(v); + return arch_atomic_fetch_dec_relaxed(v); } static __always_inline void -atomic_long_and(long i, atomic_long_t *v) +arch_atomic_long_and(long i, atomic_long_t *v) { - atomic_and(i, v); + arch_atomic_and(i, v); } static __always_inline long -atomic_long_fetch_and(long i, atomic_long_t *v) +arch_atomic_long_fetch_and(long i, atomic_long_t *v) { - return atomic_fetch_and(i, v); + return arch_atomic_fetch_and(i, v); } static __always_inline long -atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_acquire(long i, atomic_long_t *v) { - return atomic_fetch_and_acquire(i, v); + return arch_atomic_fetch_and_acquire(i, v); } static __always_inline long -atomic_long_fetch_and_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_release(long i, atomic_long_t *v) { - return atomic_fetch_and_release(i, v); + return arch_atomic_fetch_and_release(i, v); } static __always_inline long -atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_and_relaxed(i, v); + return arch_atomic_fetch_and_relaxed(i, v); } static __always_inline void -atomic_long_andnot(long i, atomic_long_t *v) +arch_atomic_long_andnot(long i, atomic_long_t *v) { - atomic_andnot(i, v); + arch_atomic_andnot(i, v); } static __always_inline long -atomic_long_fetch_andnot(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot(long i, atomic_long_t *v) { - return atomic_fetch_andnot(i, v); + return arch_atomic_fetch_andnot(i, v); } static __always_inline long -atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) { - return atomic_fetch_andnot_acquire(i, v); + return arch_atomic_fetch_andnot_acquire(i, v); } static __always_inline long -atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { - return atomic_fetch_andnot_release(i, v); + return arch_atomic_fetch_andnot_release(i, v); } static __always_inline long -atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_andnot_relaxed(i, v); + return arch_atomic_fetch_andnot_relaxed(i, v); } static __always_inline void -atomic_long_or(long i, atomic_long_t *v) +arch_atomic_long_or(long i, atomic_long_t *v) { - atomic_or(i, v); + arch_atomic_or(i, v); } static __always_inline long -atomic_long_fetch_or(long i, atomic_long_t *v) +arch_atomic_long_fetch_or(long i, atomic_long_t *v) { - return atomic_fetch_or(i, v); + return arch_atomic_fetch_or(i, v); } static __always_inline long -atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_acquire(long i, atomic_long_t *v) { - return atomic_fetch_or_acquire(i, v); + return arch_atomic_fetch_or_acquire(i, v); } static __always_inline long -atomic_long_fetch_or_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_release(long i, atomic_long_t *v) { - return atomic_fetch_or_release(i, v); + return arch_atomic_fetch_or_release(i, v); } static __always_inline long -atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_or_relaxed(i, v); + return arch_atomic_fetch_or_relaxed(i, v); } static __always_inline void -atomic_long_xor(long i, atomic_long_t *v) +arch_atomic_long_xor(long i, atomic_long_t *v) { - atomic_xor(i, v); + arch_atomic_xor(i, v); } static __always_inline long -atomic_long_fetch_xor(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor(long i, atomic_long_t *v) { - return atomic_fetch_xor(i, v); + return arch_atomic_fetch_xor(i, v); } static __always_inline long -atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) { - return atomic_fetch_xor_acquire(i, v); + return arch_atomic_fetch_xor_acquire(i, v); } static __always_inline long -atomic_long_fetch_xor_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_release(long i, atomic_long_t *v) { - return atomic_fetch_xor_release(i, v); + return arch_atomic_fetch_xor_release(i, v); } static __always_inline long -atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_xor_relaxed(i, v); + return arch_atomic_fetch_xor_relaxed(i, v); } static __always_inline long -atomic_long_xchg(atomic_long_t *v, long i) +arch_atomic_long_xchg(atomic_long_t *v, long i) { - return atomic_xchg(v, i); + return arch_atomic_xchg(v, i); } static __always_inline long -atomic_long_xchg_acquire(atomic_long_t *v, long i) +arch_atomic_long_xchg_acquire(atomic_long_t *v, long i) { - return atomic_xchg_acquire(v, i); + return arch_atomic_xchg_acquire(v, i); } static __always_inline long -atomic_long_xchg_release(atomic_long_t *v, long i) +arch_atomic_long_xchg_release(atomic_long_t *v, long i) { - return atomic_xchg_release(v, i); + return arch_atomic_xchg_release(v, i); } static __always_inline long -atomic_long_xchg_relaxed(atomic_long_t *v, long i) +arch_atomic_long_xchg_relaxed(atomic_long_t *v, long i) { - return atomic_xchg_relaxed(v, i); + return arch_atomic_xchg_relaxed(v, i); } static __always_inline long -atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { - return atomic_cmpxchg(v, old, new); + return arch_atomic_cmpxchg(v, old, new); } static __always_inline long -atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) { - return atomic_cmpxchg_acquire(v, old, new); + return arch_atomic_cmpxchg_acquire(v, old, new); } static __always_inline long -atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { - return atomic_cmpxchg_release(v, old, new); + return arch_atomic_cmpxchg_release(v, old, new); } static __always_inline long -atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) { - return atomic_cmpxchg_relaxed(v, old, new); + return arch_atomic_cmpxchg_relaxed(v, old, new); } static __always_inline bool -atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { - return atomic_try_cmpxchg(v, (int *)old, new); + return arch_atomic_try_cmpxchg(v, (int *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { - return atomic_try_cmpxchg_acquire(v, (int *)old, new); + return arch_atomic_try_cmpxchg_acquire(v, (int *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { - return atomic_try_cmpxchg_release(v, (int *)old, new); + return arch_atomic_try_cmpxchg_release(v, (int *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { - return atomic_try_cmpxchg_relaxed(v, (int *)old, new); + return arch_atomic_try_cmpxchg_relaxed(v, (int *)old, new); } static __always_inline bool -atomic_long_sub_and_test(long i, atomic_long_t *v) +arch_atomic_long_sub_and_test(long i, atomic_long_t *v) { - return atomic_sub_and_test(i, v); + return arch_atomic_sub_and_test(i, v); } static __always_inline bool -atomic_long_dec_and_test(atomic_long_t *v) +arch_atomic_long_dec_and_test(atomic_long_t *v) { - return atomic_dec_and_test(v); + return arch_atomic_dec_and_test(v); } static __always_inline bool -atomic_long_inc_and_test(atomic_long_t *v) +arch_atomic_long_inc_and_test(atomic_long_t *v) { - return atomic_inc_and_test(v); + return arch_atomic_inc_and_test(v); } static __always_inline bool -atomic_long_add_negative(long i, atomic_long_t *v) +arch_atomic_long_add_negative(long i, atomic_long_t *v) { - return atomic_add_negative(i, v); + return arch_atomic_add_negative(i, v); } static __always_inline long -atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { - return atomic_fetch_add_unless(v, a, u); + return arch_atomic_fetch_add_unless(v, a, u); } static __always_inline bool -atomic_long_add_unless(atomic_long_t *v, long a, long u) +arch_atomic_long_add_unless(atomic_long_t *v, long a, long u) { - return atomic_add_unless(v, a, u); + return arch_atomic_add_unless(v, a, u); } static __always_inline bool -atomic_long_inc_not_zero(atomic_long_t *v) +arch_atomic_long_inc_not_zero(atomic_long_t *v) { - return atomic_inc_not_zero(v); + return arch_atomic_inc_not_zero(v); } static __always_inline bool -atomic_long_inc_unless_negative(atomic_long_t *v) +arch_atomic_long_inc_unless_negative(atomic_long_t *v) { - return atomic_inc_unless_negative(v); + return arch_atomic_inc_unless_negative(v); } static __always_inline bool -atomic_long_dec_unless_positive(atomic_long_t *v) +arch_atomic_long_dec_unless_positive(atomic_long_t *v) { - return atomic_dec_unless_positive(v); + return arch_atomic_dec_unless_positive(v); } static __always_inline long -atomic_long_dec_if_positive(atomic_long_t *v) +arch_atomic_long_dec_if_positive(atomic_long_t *v) { - return atomic_dec_if_positive(v); + return arch_atomic_dec_if_positive(v); } #endif /* CONFIG_64BIT */ #endif /* _LINUX_ATOMIC_LONG_H */ -// c5552b5d78a0c7584dfd03cba985e78a1a86bbed +// e8f0e08ff072b74d180eabe2ad001282b38c2c88 diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh index 6fc1ab772e40..035ceb4ee85c 100755 --- a/scripts/atomic/gen-atomic-instrumented.sh +++ b/scripts/atomic/gen-atomic-instrumented.sh @@ -138,6 +138,11 @@ grep '^[a-z]' "$1" | while read name meta args; do gen_proto "${meta}" "${name}" "atomic64" "s64" ${args} done +grep '^[a-z]' "$1" | while read name meta args; do + gen_proto "${meta}" "${name}" "atomic_long" "long" ${args} +done + + for xchg in "xchg" "cmpxchg" "cmpxchg64" "try_cmpxchg"; do for order in "" "_acquire" "_release" "_relaxed"; do gen_xchg "${xchg}${order}" "" diff --git a/scripts/atomic/gen-atomic-long.sh b/scripts/atomic/gen-atomic-long.sh index db69572609df..eda89cea6e1d 100755 --- a/scripts/atomic/gen-atomic-long.sh +++ b/scripts/atomic/gen-atomic-long.sh @@ -47,9 +47,9 @@ gen_proto_order_variant() cat < Date: Mon, 5 Jul 2021 20:42:04 +0800 Subject: ACPI: Add LoongArch support for ACPI_PROCESSOR/ACPI_NUMA We are preparing to add new Loongson (based on LoongArch, not MIPS) support. LoongArch use ACPI other than DT as its boot protocol, so add its support for ACPI_PROCESSOR/ACPI_NUMA. Signed-off-by: Huacai Chen Signed-off-by: Rafael J. Wysocki --- drivers/acpi/Kconfig | 4 ++-- drivers/acpi/numa/Kconfig | 2 +- drivers/acpi/numa/srat.c | 2 +- include/linux/acpi.h | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 9d872ea477a6..9efd27e8af21 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -280,9 +280,9 @@ config ACPI_CPPC_LIB config ACPI_PROCESSOR tristate "Processor" - depends on X86 || IA64 || ARM64 + depends on X86 || IA64 || ARM64 || LOONGARCH select ACPI_PROCESSOR_IDLE - select ACPI_CPU_FREQ_PSS if X86 || IA64 + select ACPI_CPU_FREQ_PSS if X86 || IA64 || LOONGARCH default y help This driver adds support for the ACPI Processor package. It is required diff --git a/drivers/acpi/numa/Kconfig b/drivers/acpi/numa/Kconfig index fcf2e556d69d..39b1f34c21df 100644 --- a/drivers/acpi/numa/Kconfig +++ b/drivers/acpi/numa/Kconfig @@ -2,7 +2,7 @@ config ACPI_NUMA bool "NUMA support" depends on NUMA - depends on (X86 || IA64 || ARM64) + depends on (X86 || IA64 || ARM64 || LOONGARCH) default y if IA64 || ARM64 config ACPI_HMAT diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 6021a1013442..b8795fc49097 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -206,7 +206,7 @@ int __init srat_disabled(void) return acpi_numa < 0; } -#if defined(CONFIG_X86) || defined(CONFIG_ARM64) +#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) /* * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for * I/O localities since SRAT does not list them. I/O localities are diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 72e4f7fd268c..3e4805619fe0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -249,7 +249,7 @@ void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); /* the following numa functions are architecture-dependent */ void acpi_numa_slit_init (struct acpi_table_slit *slit); -#if defined(CONFIG_X86) || defined(CONFIG_IA64) +#if defined(CONFIG_X86) || defined(CONFIG_IA64) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else static inline void -- cgit v1.2.3 From d0b8e398319e5b09f3cb26ee8288ce356646fca6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 12 Jul 2021 19:25:55 +0200 Subject: ACPI: glue: Eliminate acpi_platform_notify() Get rid of acpi_platform_notify() which is redundant and make device_platform_notify() in the driver core call acpi_device_notify() and acpi_device_notify_remove() directly. No functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Andy Shevchenko --- drivers/acpi/glue.c | 19 ++----------------- drivers/base/core.c | 7 ++++--- include/linux/acpi.h | 10 ++++------ 3 files changed, 10 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index dbdd86c80793..7a33a6d985f8 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -285,7 +285,7 @@ int acpi_unbind_one(struct device *dev) } EXPORT_SYMBOL_GPL(acpi_unbind_one); -static void acpi_device_notify(struct device *dev) +void acpi_device_notify(struct device *dev) { struct acpi_bus_type *type = acpi_get_bus_type(dev); struct acpi_device *adev; @@ -324,7 +324,7 @@ err: dev_dbg(dev, "No ACPI support\n"); } -static void acpi_device_notify_remove(struct device *dev) +void acpi_device_notify_remove(struct device *dev) { struct acpi_device *adev = ACPI_COMPANION(dev); struct acpi_bus_type *type; @@ -340,18 +340,3 @@ static void acpi_device_notify_remove(struct device *dev) acpi_unbind_one(dev); } - -int acpi_platform_notify(struct device *dev, enum kobject_action action) -{ - switch (action) { - case KOBJ_ADD: - acpi_device_notify(dev); - break; - case KOBJ_REMOVE: - acpi_device_notify_remove(dev); - break; - default: - break; - } - return 0; -} diff --git a/drivers/base/core.c b/drivers/base/core.c index cadcade65825..1521915c0330 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2005,9 +2005,10 @@ device_platform_notify(struct device *dev, enum kobject_action action) { int ret; - ret = acpi_platform_notify(dev, action); - if (ret) - return ret; + if (action == KOBJ_ADD) + acpi_device_notify(dev); + else if (action == KOBJ_REMOVE) + acpi_device_notify_remove(dev); ret = software_node_notify(dev, action); if (ret) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 72e4f7fd268c..fdbf6d7d928a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1380,13 +1380,11 @@ static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level) #endif #ifdef CONFIG_ACPI -extern int acpi_platform_notify(struct device *dev, enum kobject_action action); +extern void acpi_device_notify(struct device *dev); +extern void acpi_device_notify_remove(struct device *dev); #else -static inline int -acpi_platform_notify(struct device *dev, enum kobject_action action) -{ - return 0; -} +static inline void acpi_device_notify(struct device *dev) { } +static inline void acpi_device_notify_remove(struct device *dev) { } #endif #endif /*_LINUX_ACPI_H*/ -- cgit v1.2.3 From 384f5a857baeba88cf013b36999a97b471e4bd9c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 12 Jul 2021 19:27:12 +0200 Subject: software nodes: Split software_node_notify() Split software_node_notify_remove) out of software_node_notify() and make device_platform_notify() call the latter on device addition and the former on device removal. While at it, put the headers of the above functions into base.h, because they don't need to be present in a global header file. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Greg Kroah-Hartman Reviewed-by: Heikki Krogerus Reviewed-by: Andy Shevchenko --- drivers/base/base.h | 3 +++ drivers/base/core.c | 9 ++++--- drivers/base/swnode.c | 61 +++++++++++++++++++++++++----------------------- include/linux/property.h | 2 -- 4 files changed, 39 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/base.h b/drivers/base/base.h index 404db83ee5ec..2882af26392a 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -202,3 +202,6 @@ int devtmpfs_delete_node(struct device *dev); static inline int devtmpfs_create_node(struct device *dev) { return 0; } static inline int devtmpfs_delete_node(struct device *dev) { return 0; } #endif + +void software_node_notify(struct device *dev); +void software_node_notify_remove(struct device *dev); diff --git a/drivers/base/core.c b/drivers/base/core.c index 1521915c0330..6cf9c500fe93 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2003,16 +2003,15 @@ static inline int device_is_not_partition(struct device *dev) static int device_platform_notify(struct device *dev, enum kobject_action action) { - int ret; - if (action == KOBJ_ADD) acpi_device_notify(dev); else if (action == KOBJ_REMOVE) acpi_device_notify_remove(dev); - ret = software_node_notify(dev, action); - if (ret) - return ret; + if (action == KOBJ_ADD) + software_node_notify(dev); + else if (action == KOBJ_REMOVE) + software_node_notify_remove(dev); if (platform_notify && action == KOBJ_ADD) platform_notify(dev); diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index d1f1a8240120..7bd0f3cfb7eb 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -11,6 +11,8 @@ #include #include +#include "base.h" + struct swnode { struct kobject kobj; struct fwnode_handle fwnode; @@ -1053,7 +1055,7 @@ int device_add_software_node(struct device *dev, const struct software_node *nod * balance. */ if (device_is_registered(dev)) - software_node_notify(dev, KOBJ_ADD); + software_node_notify(dev); return 0; } @@ -1074,7 +1076,8 @@ void device_remove_software_node(struct device *dev) return; if (device_is_registered(dev)) - software_node_notify(dev, KOBJ_REMOVE); + software_node_notify_remove(dev); + set_secondary_fwnode(dev, NULL); kobject_put(&swnode->kobj); } @@ -1117,44 +1120,44 @@ int device_create_managed_software_node(struct device *dev, } EXPORT_SYMBOL_GPL(device_create_managed_software_node); -int software_node_notify(struct device *dev, unsigned long action) +void software_node_notify(struct device *dev) { struct swnode *swnode; int ret; swnode = dev_to_swnode(dev); if (!swnode) - return 0; + return; - switch (action) { - case KOBJ_ADD: - ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node"); - if (ret) - break; + ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node"); + if (ret) + return; - ret = sysfs_create_link(&swnode->kobj, &dev->kobj, - dev_name(dev)); - if (ret) { - sysfs_remove_link(&dev->kobj, "software_node"); - break; - } - kobject_get(&swnode->kobj); - break; - case KOBJ_REMOVE: - sysfs_remove_link(&swnode->kobj, dev_name(dev)); + ret = sysfs_create_link(&swnode->kobj, &dev->kobj, dev_name(dev)); + if (ret) { sysfs_remove_link(&dev->kobj, "software_node"); - kobject_put(&swnode->kobj); - - if (swnode->managed) { - set_secondary_fwnode(dev, NULL); - kobject_put(&swnode->kobj); - } - break; - default: - break; + return; } - return 0; + kobject_get(&swnode->kobj); +} + +void software_node_notify_remove(struct device *dev) +{ + struct swnode *swnode; + + swnode = dev_to_swnode(dev); + if (!swnode) + return; + + sysfs_remove_link(&swnode->kobj, dev_name(dev)); + sysfs_remove_link(&dev->kobj, "software_node"); + kobject_put(&swnode->kobj); + + if (swnode->managed) { + set_secondary_fwnode(dev, NULL); + kobject_put(&swnode->kobj); + } } static int __init software_node_init(void) diff --git a/include/linux/property.h b/include/linux/property.h index 073e680c35e2..357513a977e5 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -484,8 +484,6 @@ void software_node_unregister_node_group(const struct software_node **node_group int software_node_register(const struct software_node *node); void software_node_unregister(const struct software_node *node); -int software_node_notify(struct device *dev, unsigned long action); - struct fwnode_handle * fwnode_create_software_node(const struct property_entry *properties, const struct fwnode_handle *parent); -- cgit v1.2.3 From c7603cfa04e7c3a435b31d065f7cbdc829428f6e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 12 Jul 2021 16:06:15 -0700 Subject: bpf: Add ambient BPF runtime context stored in current b910eaaaa4b8 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper") fixed the problem with cgroup-local storage use in BPF by pre-allocating per-CPU array of 8 cgroup storage pointers to accommodate possible BPF program preemptions and nested executions. While this seems to work good in practice, it introduces new and unnecessary failure mode in which not all BPF programs might be executed if we fail to find an unused slot for cgroup storage, however unlikely it is. It might also not be so unlikely when/if we allow sleepable cgroup BPF programs in the future. Further, the way that cgroup storage is implemented as ambiently-available property during entire BPF program execution is a convenient way to pass extra information to BPF program and helpers without requiring user code to pass around extra arguments explicitly. So it would be good to have a generic solution that can allow implementing this without arbitrary restrictions. Ideally, such solution would work for both preemptable and sleepable BPF programs in exactly the same way. This patch introduces such solution, bpf_run_ctx. It adds one pointer field (bpf_ctx) to task_struct. This field is maintained by BPF_PROG_RUN family of macros in such a way that it always stays valid throughout BPF program execution. BPF program preemption is handled by remembering previous current->bpf_ctx value locally while executing nested BPF program and restoring old value after nested BPF program finishes. This is handled by two helper functions, bpf_set_run_ctx() and bpf_reset_run_ctx(), which are supposed to be used before and after BPF program runs, respectively. Restoring old value of the pointer handles preemption, while bpf_run_ctx pointer being a property of current task_struct naturally solves this problem for sleepable BPF programs by "following" BPF program execution as it is scheduled in and out of CPU. It would even allow CPU migration of BPF programs, even though it's not currently allowed by BPF infra. This patch cleans up cgroup local storage handling as a first application. The design itself is generic, though, with bpf_run_ctx being an empty struct that is supposed to be embedded into a specific struct for a given BPF program type (bpf_cg_run_ctx in this case). Follow up patches are planned that will expand this mechanism for other uses within tracing BPF programs. To verify that this change doesn't revert the fix to the original cgroup storage issue, I ran the same repro as in the original report ([0]) and didn't get any problems. Replacing bpf_reset_run_ctx(old_run_ctx) with bpf_reset_run_ctx(NULL) triggers the issue pretty quickly (so repro does work). [0] https://lore.kernel.org/bpf/YEEvBUiJl2pJkxTd@krava/ Fixes: b910eaaaa4b8 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210712230615.3525979-1-andrii@kernel.org --- include/linux/bpf-cgroup.h | 54 ---------------------------------------------- include/linux/bpf.h | 54 +++++++++++++++++++++++++++++----------------- include/linux/sched.h | 3 +++ kernel/bpf/helpers.c | 16 +++++--------- kernel/bpf/local_storage.c | 3 --- kernel/fork.c | 1 + net/bpf/test_run.c | 23 ++++++++++---------- 7 files changed, 54 insertions(+), 100 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8b77d08d4b47..a74cd1c3bd87 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -27,19 +27,6 @@ struct task_struct; extern struct static_key_false cgroup_bpf_enabled_key[MAX_BPF_ATTACH_TYPE]; #define cgroup_bpf_enabled(type) static_branch_unlikely(&cgroup_bpf_enabled_key[type]) -#define BPF_CGROUP_STORAGE_NEST_MAX 8 - -struct bpf_cgroup_storage_info { - struct task_struct *task; - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; -}; - -/* For each cpu, permit maximum BPF_CGROUP_STORAGE_NEST_MAX number of tasks - * to use bpf cgroup storage simultaneously. - */ -DECLARE_PER_CPU(struct bpf_cgroup_storage_info, - bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); - #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -172,44 +159,6 @@ static inline enum bpf_cgroup_storage_type cgroup_storage_type( return BPF_CGROUP_STORAGE_SHARED; } -static inline int bpf_cgroup_storage_set(struct bpf_cgroup_storage - *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) -{ - enum bpf_cgroup_storage_type stype; - int i, err = 0; - - preempt_disable(); - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != NULL)) - continue; - - this_cpu_write(bpf_cgroup_storage_info[i].task, current); - for_each_cgroup_storage_type(stype) - this_cpu_write(bpf_cgroup_storage_info[i].storage[stype], - storage[stype]); - goto out; - } - err = -EBUSY; - WARN_ON_ONCE(1); - -out: - preempt_enable(); - return err; -} - -static inline void bpf_cgroup_storage_unset(void) -{ - int i; - - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) - continue; - - this_cpu_write(bpf_cgroup_storage_info[i].task, NULL); - return; - } -} - struct bpf_cgroup_storage * cgroup_storage_lookup(struct bpf_cgroup_storage_map *map, void *key, bool locked); @@ -487,9 +436,6 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } -static inline int bpf_cgroup_storage_set( - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { return 0; } -static inline void bpf_cgroup_storage_unset(void) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0edff8f5177e..978ebd16ae60 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1142,38 +1142,40 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *include_prog, struct bpf_prog_array **new_array); +struct bpf_run_ctx {}; + +struct bpf_cg_run_ctx { + struct bpf_run_ctx run_ctx; + struct bpf_prog_array_item *prog_item; +}; + /* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ #define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) /* BPF program asks to set CN on the packet. */ #define BPF_RET_SET_CN (1 << 0) -/* For BPF_PROG_RUN_ARRAY_FLAGS and __BPF_PROG_RUN_ARRAY, - * if bpf_cgroup_storage_set() failed, the rest of programs - * will not execute. This should be a really rare scenario - * as it requires BPF_CGROUP_STORAGE_NEST_MAX number of - * preemptions all between bpf_cgroup_storage_set() and - * bpf_cgroup_storage_unset() on the same cpu. - */ #define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags) \ ({ \ struct bpf_prog_array_item *_item; \ struct bpf_prog *_prog; \ struct bpf_prog_array *_array; \ + struct bpf_run_ctx *old_run_ctx; \ + struct bpf_cg_run_ctx run_ctx; \ u32 _ret = 1; \ u32 func_ret; \ migrate_disable(); \ rcu_read_lock(); \ _array = rcu_dereference(array); \ _item = &_array->items[0]; \ + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); \ while ((_prog = READ_ONCE(_item->prog))) { \ - if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ - break; \ + run_ctx.prog_item = _item; \ func_ret = func(_prog, ctx); \ _ret &= (func_ret & 1); \ - *(ret_flags) |= (func_ret >> 1); \ - bpf_cgroup_storage_unset(); \ + *(ret_flags) |= (func_ret >> 1); \ _item++; \ } \ + bpf_reset_run_ctx(old_run_ctx); \ rcu_read_unlock(); \ migrate_enable(); \ _ret; \ @@ -1184,6 +1186,8 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog_array_item *_item; \ struct bpf_prog *_prog; \ struct bpf_prog_array *_array; \ + struct bpf_run_ctx *old_run_ctx; \ + struct bpf_cg_run_ctx run_ctx; \ u32 _ret = 1; \ migrate_disable(); \ rcu_read_lock(); \ @@ -1191,17 +1195,13 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, if (unlikely(check_non_null && !_array))\ goto _out; \ _item = &_array->items[0]; \ - while ((_prog = READ_ONCE(_item->prog))) { \ - if (!set_cg_storage) { \ - _ret &= func(_prog, ctx); \ - } else { \ - if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ - break; \ - _ret &= func(_prog, ctx); \ - bpf_cgroup_storage_unset(); \ - } \ + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);\ + while ((_prog = READ_ONCE(_item->prog))) { \ + run_ctx.prog_item = _item; \ + _ret &= func(_prog, ctx); \ _item++; \ } \ + bpf_reset_run_ctx(old_run_ctx); \ _out: \ rcu_read_unlock(); \ migrate_enable(); \ @@ -1284,6 +1284,20 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } +static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) +{ + struct bpf_run_ctx *old_ctx; + + old_ctx = current->bpf_ctx; + current->bpf_ctx = new_ctx; + return old_ctx; +} + +static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) +{ + current->bpf_ctx = old_ctx; +} + extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; diff --git a/include/linux/sched.h b/include/linux/sched.h index ec8d07d88641..c64119aa2e60 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -42,6 +42,7 @@ struct backing_dev_info; struct bio_list; struct blk_plug; struct bpf_local_storage; +struct bpf_run_ctx; struct capture_control; struct cfs_rq; struct fs_struct; @@ -1379,6 +1380,8 @@ struct task_struct { #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; + /* Used for BPF run context */ + struct bpf_run_ctx *bpf_ctx; #endif #ifdef CONFIG_GCC_PLUGIN_STACKLEAK diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9fe846ec6bd1..15746f779fe1 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -393,8 +393,6 @@ const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { }; #ifdef CONFIG_CGROUP_BPF -DECLARE_PER_CPU(struct bpf_cgroup_storage_info, - bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { @@ -403,17 +401,13 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) * verifier checks that its value is correct. */ enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); - struct bpf_cgroup_storage *storage = NULL; + struct bpf_cgroup_storage *storage; + struct bpf_cg_run_ctx *ctx; void *ptr; - int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) - continue; - - storage = this_cpu_read(bpf_cgroup_storage_info[i].storage[stype]); - break; - } + /* get current cgroup storage from BPF run context */ + ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); + storage = ctx->prog_item->cgroup_storage[stype]; if (stype == BPF_CGROUP_STORAGE_SHARED) ptr = &READ_ONCE(storage->buf)->data[0]; diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 95d70a08325d..362e81481594 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -11,9 +11,6 @@ #ifdef CONFIG_CGROUP_BPF -DEFINE_PER_CPU(struct bpf_cgroup_storage_info, - bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); - #include "../cgroup/cgroup-internal.h" #define LOCAL_STORAGE_CREATE_FLAG_MASK \ diff --git a/kernel/fork.c b/kernel/fork.c index bc94b2cc5995..e8b41e212110 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2083,6 +2083,7 @@ static __latent_entropy struct task_struct *copy_process( #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); + p->bpf_ctx = NULL; #endif /* Perform scheduler related setup. Assign this task to a CPU. */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index cda8375bbbaf..8d46e2962786 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -88,17 +88,19 @@ reset: static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time, bool xdp) { - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { NULL }; + struct bpf_prog_array_item item = {.prog = prog}; + struct bpf_run_ctx *old_ctx; + struct bpf_cg_run_ctx run_ctx; struct bpf_test_timer t = { NO_MIGRATE }; enum bpf_cgroup_storage_type stype; int ret; for_each_cgroup_storage_type(stype) { - storage[stype] = bpf_cgroup_storage_alloc(prog, stype); - if (IS_ERR(storage[stype])) { - storage[stype] = NULL; + item.cgroup_storage[stype] = bpf_cgroup_storage_alloc(prog, stype); + if (IS_ERR(item.cgroup_storage[stype])) { + item.cgroup_storage[stype] = NULL; for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); + bpf_cgroup_storage_free(item.cgroup_storage[stype]); return -ENOMEM; } } @@ -107,22 +109,19 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, repeat = 1; bpf_test_timer_enter(&t); + old_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); do { - ret = bpf_cgroup_storage_set(storage); - if (ret) - break; - + run_ctx.prog_item = &item; if (xdp) *retval = bpf_prog_run_xdp(prog, ctx); else *retval = BPF_PROG_RUN(prog, ctx); - - bpf_cgroup_storage_unset(); } while (bpf_test_timer_continue(&t, repeat, &ret, time)); + bpf_reset_run_ctx(old_ctx); bpf_test_timer_leave(&t); for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); + bpf_cgroup_storage_free(item.cgroup_storage[stype]); return ret; } -- cgit v1.2.3 From 96cd2dd65bb0b94c908f2df32bba7350fc1b954e Mon Sep 17 00:00:00 2001 From: Lior Nahmanson Date: Mon, 28 Dec 2020 10:38:12 +0200 Subject: net/mlx5: Add DCS caps & fields support This fields will be needed when adding a support for DCS offload max_dci_stream_channels - maximum DCI stream channels supported per DCI. max_dci_errored_streams - maximum DCI error stream channels supported per DCI before a DCI move to error state. Signed-off-by: Lior Nahmanson Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b0009aa3647f..3dd6641e942c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1651,7 +1651,13 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_geneve_tlv_option_data_len[0x5]; u8 reserved_at_570[0x10]; - u8 reserved_at_580[0x33]; + u8 reserved_at_580[0xb]; + u8 log_max_dci_stream_channels[0x5]; + u8 reserved_at_590[0x3]; + u8 log_max_dci_errored_streams[0x5]; + u8 reserved_at_598[0x8]; + + u8 reserved_at_5a0[0x13]; u8 log_max_dek[0x5]; u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; @@ -3020,10 +3026,12 @@ struct mlx5_ifc_qpc_bits { u8 reserved_at_3c0[0x8]; u8 next_send_psn[0x18]; - u8 reserved_at_3e0[0x8]; + u8 reserved_at_3e0[0x3]; + u8 log_num_dci_stream_channels[0x5]; u8 cqn_snd[0x18]; - u8 reserved_at_400[0x8]; + u8 reserved_at_400[0x3]; + u8 log_num_dci_errored_streams[0x5]; u8 deth_sqpn[0x18]; u8 reserved_at_420[0x20]; -- cgit v1.2.3 From 337015573718b161891a3473d25f59273f2e626b Mon Sep 17 00:00:00 2001 From: Chris Down Date: Tue, 15 Jun 2021 17:52:53 +0100 Subject: printk: Userspace format indexing support We have a number of systems industry-wide that have a subset of their functionality that works as follows: 1. Receive a message from local kmsg, serial console, or netconsole; 2. Apply a set of rules to classify the message; 3. Do something based on this classification (like scheduling a remediation for the machine), rinse, and repeat. As a couple of examples of places we have this implemented just inside Facebook, although this isn't a Facebook-specific problem, we have this inside our netconsole processing (for alarm classification), and as part of our machine health checking. We use these messages to determine fairly important metrics around production health, and it's important that we get them right. While for some kinds of issues we have counters, tracepoints, or metrics with a stable interface which can reliably indicate the issue, in order to react to production issues quickly we need to work with the interface which most kernel developers naturally use when developing: printk. Most production issues come from unexpected phenomena, and as such usually the code in question doesn't have easily usable tracepoints or other counters available for the specific problem being mitigated. We have a number of lines of monitoring defence against problems in production (host metrics, process metrics, service metrics, etc), and where it's not feasible to reliably monitor at another level, this kind of pragmatic netconsole monitoring is essential. As one would expect, monitoring using printk is rather brittle for a number of reasons -- most notably that the message might disappear entirely in a new version of the kernel, or that the message may change in some way that the regex or other classification methods start to silently fail. One factor that makes this even harder is that, under normal operation, many of these messages are never expected to be hit. For example, there may be a rare hardware bug which one wants to detect if it was to ever happen again, but its recurrence is not likely or anticipated. This precludes using something like checking whether the printk in question was printed somewhere fleetwide recently to determine whether the message in question is still present or not, since we don't anticipate that it should be printed anywhere, but still need to monitor for its future presence in the long-term. This class of issue has happened on a number of occasions, causing unhealthy machines with hardware issues to remain in production for longer than ideal. As a recent example, some monitoring around blk_update_request fell out of date and caused semi-broken machines to remain in production for longer than would be desirable. Searching through the codebase to find the message is also extremely fragile, because many of the messages are further constructed beyond their callsite (eg. btrfs_printk and other module-specific wrappers, each with their own functionality). Even if they aren't, guessing the format and formulation of the underlying message based on the aesthetics of the message emitted is not a recipe for success at scale, and our previous issues with fleetwide machine health checking demonstrate as much. This provides a solution to the issue of silently changed or deleted printks: we record pointers to all printk format strings known at compile time into a new .printk_index section, both in vmlinux and modules. At runtime, this can then be iterated by looking at /printk/index/, which emits the following format, both readable by humans and able to be parsed by machines: $ head -1 vmlinux; shuf -n 5 vmlinux # filename:line function "format" <5> block/blk-settings.c:661 disk_stack_limits "%s: Warning: Device %s is misaligned\n" <4> kernel/trace/trace.c:8296 trace_create_file "Could not create tracefs '%s' entry\n" <6> arch/x86/kernel/hpet.c:144 _hpet_print_config "hpet: %s(%d):\n" <6> init/do_mounts.c:605 prepare_namespace "Waiting for root device %s...\n" <6> drivers/acpi/osl.c:1410 acpi_no_auto_serialize_setup "ACPI: auto-serialization disabled\n" This mitigates the majority of cases where we have a highly-specific printk which we want to match on, as we can now enumerate and check whether the format changed or the printk callsite disappeared entirely in userspace. This allows us to catch changes to printks we monitor earlier and decide what to do about it before it becomes problematic. There is no additional runtime cost for printk callers or printk itself, and the assembly generated is exactly the same. Signed-off-by: Chris Down Cc: Petr Mladek Cc: Jessica Yu Cc: Sergey Senozhatsky Cc: John Ogness Cc: Steven Rostedt Cc: Greg Kroah-Hartman Cc: Johannes Weiner Cc: Kees Cook Reviewed-by: Petr Mladek Tested-by: Petr Mladek Reported-by: kernel test robot Acked-by: Andy Shevchenko Acked-by: Jessica Yu # for module.{c,h} Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/e42070983637ac5e384f17fbdbe86d19c7b212a5.1623775748.git.chris@chrisdown.name --- MAINTAINERS | 5 + arch/arm/kernel/entry-v7m.S | 2 +- arch/arm/lib/backtrace-clang.S | 2 +- arch/arm/lib/backtrace.S | 2 +- arch/arm/mach-rpc/io-acorn.S | 2 +- arch/arm/vfp/vfphw.S | 6 +- arch/ia64/include/uapi/asm/cmpxchg.h | 4 +- arch/openrisc/kernel/entry.S | 6 +- arch/powerpc/kernel/head_fsl_booke.S | 2 +- arch/um/include/shared/user.h | 3 +- arch/x86/kernel/head_32.S | 2 +- include/asm-generic/vmlinux.lds.h | 13 +++ include/linux/module.h | 5 + include/linux/printk.h | 95 ++++++++++++++++- init/Kconfig | 14 +++ kernel/module.c | 5 + kernel/printk/Makefile | 1 + kernel/printk/index.c | 195 +++++++++++++++++++++++++++++++++++ kernel/printk/printk.c | 13 ++- 19 files changed, 353 insertions(+), 24 deletions(-) create mode 100644 kernel/printk/index.c (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index a61f4f3b78a9..a19a104e0cc4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14918,6 +14918,11 @@ S: Maintained F: include/linux/printk.h F: kernel/printk/ +PRINTK INDEXING +R: Chris Down +S: Maintained +F: kernel/printk/index.c + PRISM54 WIRELESS DRIVER M: Luis Chamberlain L: linux-wireless@vger.kernel.org diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S index d0e898608d30..7bde93c10962 100644 --- a/arch/arm/kernel/entry-v7m.S +++ b/arch/arm/kernel/entry-v7m.S @@ -23,7 +23,7 @@ __invalid_entry: adr r0, strerr mrs r1, ipsr mov r2, lr - bl printk + bl _printk #endif mov r0, sp bl show_regs diff --git a/arch/arm/lib/backtrace-clang.S b/arch/arm/lib/backtrace-clang.S index 6174c45f53a5..5b2cdb1003e3 100644 --- a/arch/arm/lib/backtrace-clang.S +++ b/arch/arm/lib/backtrace-clang.S @@ -202,7 +202,7 @@ finished_setup: 1006: adr r0, .Lbad mov r1, loglvl mov r2, frame - bl printk + bl _printk no_frame: ldmfd sp!, {r4 - r9, fp, pc} ENDPROC(c_backtrace) .pushsection __ex_table,"a" diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S index 872f658638d9..e8408f22d4dc 100644 --- a/arch/arm/lib/backtrace.S +++ b/arch/arm/lib/backtrace.S @@ -103,7 +103,7 @@ for_each_frame: tst frame, mask @ Check for address exceptions 1006: adr r0, .Lbad mov r1, loglvl mov r2, frame - bl printk + bl _printk no_frame: ldmfd sp!, {r4 - r9, pc} ENDPROC(c_backtrace) diff --git a/arch/arm/mach-rpc/io-acorn.S b/arch/arm/mach-rpc/io-acorn.S index b9082a2a2a01..aa9bf0d771c0 100644 --- a/arch/arm/mach-rpc/io-acorn.S +++ b/arch/arm/mach-rpc/io-acorn.S @@ -25,4 +25,4 @@ ENTRY(insl) ENTRY(outsl) adr r0, .Liosl_warning mov r1, lr - b printk + b _printk diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index d5837bf05a9a..6f7926c9c179 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -23,7 +23,7 @@ #ifdef DEBUG stmfd sp!, {r0-r3, ip, lr} ldr r0, =1f - bl printk + bl _printk ldmfd sp!, {r0-r3, ip, lr} .pushsection .rodata, "a" @@ -38,7 +38,7 @@ stmfd sp!, {r0-r3, ip, lr} mov r1, \arg ldr r0, =1f - bl printk + bl _printk ldmfd sp!, {r0-r3, ip, lr} .pushsection .rodata, "a" @@ -55,7 +55,7 @@ mov r2, \arg2 mov r1, \arg1 ldr r0, =1f - bl printk + bl _printk ldmfd sp!, {r0-r3, ip, lr} .pushsection .rodata, "a" diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h index 926c6cb1e029..2c2f3cfeaa77 100644 --- a/arch/ia64/include/uapi/asm/cmpxchg.h +++ b/arch/ia64/include/uapi/asm/cmpxchg.h @@ -143,9 +143,9 @@ extern long ia64_cmpxchg_called_with_bad_pointer(void); do { \ if (_cmpxchg_bugcheck_count-- <= 0) { \ void *ip; \ - extern int printk(const char *fmt, ...); \ + extern int _printk(const char *fmt, ...); \ ip = (void *) ia64_getreg(_IA64_REG_IP); \ - printk("CMPXCHG_BUGCHECK: stuck at %p on word %p\n", ip, (v));\ + _printk("CMPXCHG_BUGCHECK: stuck at %p on word %p\n", ip, (v));\ break; \ } \ } while (0) diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index bc657e55c15f..947613f61d4a 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -551,7 +551,7 @@ EXCEPTION_ENTRY(_external_irq_handler) l.movhi r3,hi(42f) l.ori r3,r3,lo(42f) l.sw 0x0(r1),r3 - l.jal printk + l.jal _printk l.sw 0x4(r1),r4 l.addi r1,r1,0x8 @@ -681,8 +681,8 @@ _syscall_debug: l.sw -4(r1),r27 l.sw -8(r1),r11 l.addi r1,r1,-8 - l.movhi r27,hi(printk) - l.ori r27,r27,lo(printk) + l.movhi r27,hi(_printk) + l.ori r27,r27,lo(_printk) l.jalr r27 l.nop l.addi r1,r1,8 diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 0f9642f36b49..9a2f4265e6d2 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -858,7 +858,7 @@ KernelSPE: ori r3,r3,87f@l mr r4,r2 /* current */ lwz r5,_NIP(r1) - bl printk + bl _printk #endif b interrupt_return #ifdef CONFIG_PRINTK diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h index e793e4212f0a..dd4badffdeb3 100644 --- a/arch/um/include/shared/user.h +++ b/arch/um/include/shared/user.h @@ -38,7 +38,8 @@ extern void panic(const char *fmt, ...) #define UM_KERN_CONT KERN_CONT #ifdef UML_CONFIG_PRINTK -extern int printk(const char *fmt, ...) +#define printk(...) _printk(__VA_ARGS__) +extern int _printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); #else static inline int printk(const char *fmt, ...) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 67f590425d90..d8c64dab0efe 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -432,7 +432,7 @@ SYM_FUNC_START(early_ignore_irq) pushl 32(%esp) pushl 40(%esp) pushl $int_msg - call printk + call _printk call dump_stack diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 17325416e2de..ddb2ff158321 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -483,6 +483,8 @@ \ TRACEDATA \ \ + PRINTK_INDEX \ + \ /* Kernel symbol table: Normal symbols */ \ __ksymtab : AT(ADDR(__ksymtab) - LOAD_OFFSET) { \ __start___ksymtab = .; \ @@ -893,6 +895,17 @@ #define TRACEDATA #endif +#ifdef CONFIG_PRINTK_INDEX +#define PRINTK_INDEX \ + .printk_index : AT(ADDR(.printk_index) - LOAD_OFFSET) { \ + __start_printk_index = .; \ + *(.printk_index) \ + __stop_printk_index = .; \ + } +#else +#define PRINTK_INDEX +#endif + #define NOTES \ .notes : AT(ADDR(.notes) - LOAD_OFFSET) { \ __start_notes = .; \ diff --git a/include/linux/module.h b/include/linux/module.h index 8a298d820dbc..c9f1200b2312 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -511,6 +511,11 @@ struct module { struct klp_modinfo *klp_info; #endif +#ifdef CONFIG_PRINTK_INDEX + unsigned int printk_index_size; + struct pi_entry **printk_index_start; +#endif + #ifdef CONFIG_MODULE_UNLOAD /* What modules depend on me? */ struct list_head source_list; diff --git a/include/linux/printk.h b/include/linux/printk.h index e834d78f0478..2651b82ed352 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -174,12 +174,12 @@ asmlinkage __printf(1, 0) int vprintk(const char *fmt, va_list args); asmlinkage __printf(1, 2) __cold -int printk(const char *fmt, ...); +int _printk(const char *fmt, ...); /* * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ -__printf(1, 2) __cold int printk_deferred(const char *fmt, ...); +__printf(1, 2) __cold int _printk_deferred(const char *fmt, ...); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -218,12 +218,12 @@ int vprintk(const char *s, va_list args) return 0; } static inline __printf(1, 2) __cold -int printk(const char *s, ...) +int _printk(const char *s, ...) { return 0; } static inline __printf(1, 2) __cold -int printk_deferred(const char *s, ...) +int _printk_deferred(const char *s, ...) { return 0; } @@ -348,6 +348,93 @@ extern int kptr_restrict; #define pr_fmt(fmt) fmt #endif +struct module; + +#ifdef CONFIG_PRINTK_INDEX +struct pi_entry { + const char *fmt; + const char *func; + const char *file; + unsigned int line; + + /* + * While printk and pr_* have the level stored in the string at compile + * time, some subsystems dynamically add it at runtime through the + * format string. For these dynamic cases, we allow the subsystem to + * tell us the level at compile time. + * + * NULL indicates that the level, if any, is stored in fmt. + */ + const char *level; + + /* + * The format string used by various subsystem specific printk() + * wrappers to prefix the message. + * + * Note that the static prefix defined by the pr_fmt() macro is stored + * directly in the message format (@fmt), not here. + */ + const char *subsys_fmt_prefix; +} __packed; + +#define __printk_index_emit(_fmt, _level, _subsys_fmt_prefix) \ + do { \ + if (__builtin_constant_p(_fmt) && __builtin_constant_p(_level)) { \ + /* + * We check __builtin_constant_p multiple times here + * for the same input because GCC will produce an error + * if we try to assign a static variable to fmt if it + * is not a constant, even with the outer if statement. + */ \ + static const struct pi_entry _entry \ + __used = { \ + .fmt = __builtin_constant_p(_fmt) ? (_fmt) : NULL, \ + .func = __func__, \ + .file = __FILE__, \ + .line = __LINE__, \ + .level = __builtin_constant_p(_level) ? (_level) : NULL, \ + .subsys_fmt_prefix = _subsys_fmt_prefix,\ + }; \ + static const struct pi_entry *_entry_ptr \ + __used __section(".printk_index") = &_entry; \ + } \ + } while (0) + +#else /* !CONFIG_PRINTK_INDEX */ +#define __printk_index_emit(...) do {} while (0) +#endif /* CONFIG_PRINTK_INDEX */ + +/* + * Some subsystems have their own custom printk that applies a va_format to a + * generic format, for example, to include a device number or other metadata + * alongside the format supplied by the caller. + * + * In order to store these in the way they would be emitted by the printk + * infrastructure, the subsystem provides us with the start, fixed string, and + * any subsequent text in the format string. + * + * We take a variable argument list as pr_fmt/dev_fmt/etc are sometimes passed + * as multiple arguments (eg: `"%s: ", "blah"`), and we must only take the + * first one. + * + * subsys_fmt_prefix must be known at compile time, or compilation will fail + * (since this is a mistake). If fmt or level is not known at compile time, no + * index entry will be made (since this can legitimately happen). + */ +#define printk_index_subsys_emit(subsys_fmt_prefix, level, fmt, ...) \ + __printk_index_emit(fmt, level, subsys_fmt_prefix) + +#define printk_index_wrap(_p_func, _fmt, ...) \ + ({ \ + __printk_index_emit(_fmt, NULL, NULL); \ + _p_func(_fmt, ##__VA_ARGS__); \ + }) + + +#define printk(fmt, ...) printk_index_wrap(_printk, fmt, ##__VA_ARGS__) +#define printk_deferred(fmt, ...) \ + printk_index_wrap(_printk_deferred, fmt, ##__VA_ARGS__) + /** * pr_emerg - Print an emergency-level message * @fmt: format string diff --git a/init/Kconfig b/init/Kconfig index bb0d6e6262b1..ccffa7ae5ccc 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -775,6 +775,20 @@ config PRINTK_SAFE_LOG_BUF_SHIFT 13 => 8 KB for each CPU 12 => 4 KB for each CPU +config PRINTK_INDEX + bool "Printk indexing debugfs interface" + depends on PRINTK && DEBUG_FS + help + Add support for indexing of all printk formats known at compile time + at /printk/index/. + + This can be used as part of maintaining daemons which monitor + /dev/kmsg, as it permits auditing the printk formats present in a + kernel, allowing detection of cases where monitored printks are + changed or no longer present. + + There is no additional runtime cost to printk with this enabled. + # # Architectures with an unreliable sched_clock() should select this: # diff --git a/kernel/module.c b/kernel/module.c index ed13917ea5f3..40ec9a030eec 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3355,6 +3355,11 @@ static int find_module_sections(struct module *mod, struct load_info *info) sizeof(unsigned long), &mod->num_kprobe_blacklist); #endif +#ifdef CONFIG_PRINTK_INDEX + mod->printk_index_start = section_objs(info, ".printk_index", + sizeof(*mod->printk_index_start), + &mod->printk_index_size); +#endif #ifdef CONFIG_HAVE_STATIC_CALL_INLINE mod->static_call_sites = section_objs(info, ".static_call_sites", sizeof(*mod->static_call_sites), diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile index eee3dc9b60a9..d118739874c0 100644 --- a/kernel/printk/Makefile +++ b/kernel/printk/Makefile @@ -3,3 +3,4 @@ obj-y = printk.o obj-$(CONFIG_PRINTK) += printk_safe.o obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o obj-$(CONFIG_PRINTK) += printk_ringbuffer.o +obj-$(CONFIG_PRINTK_INDEX) += index.o diff --git a/kernel/printk/index.c b/kernel/printk/index.c new file mode 100644 index 000000000000..ca062f5e1779 --- /dev/null +++ b/kernel/printk/index.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Userspace indexing of printk formats + */ + +#include +#include +#include +#include +#include + +#include "internal.h" + +extern struct pi_entry *__start_printk_index[]; +extern struct pi_entry *__stop_printk_index[]; + +/* The base dir for module formats, typically debugfs/printk/index/ */ +static struct dentry *dfs_index; + +static struct pi_entry *pi_get_entry(const struct module *mod, loff_t pos) +{ + struct pi_entry **entries; + unsigned int nr_entries; + +#ifdef CONFIG_MODULES + if (mod) { + entries = mod->printk_index_start; + nr_entries = mod->printk_index_size; + } +#endif + + if (!mod) { + /* vmlinux, comes from linker symbols */ + entries = __start_printk_index; + nr_entries = __stop_printk_index - __start_printk_index; + } + + if (pos >= nr_entries) + return NULL; + + return entries[pos]; +} + +static void *pi_next(struct seq_file *s, void *v, loff_t *pos) +{ + const struct module *mod = s->file->f_inode->i_private; + struct pi_entry *entry = pi_get_entry(mod, *pos); + + (*pos)++; + + return entry; +} + +static void *pi_start(struct seq_file *s, loff_t *pos) +{ + /* + * Make show() print the header line. Do not update *pos because + * pi_next() still has to return the entry at index 0 later. + */ + if (*pos == 0) + return SEQ_START_TOKEN; + + return pi_next(s, NULL, pos); +} + +/* + * We need both ESCAPE_ANY and explicit characters from ESCAPE_SPECIAL in @only + * because otherwise ESCAPE_NAP will cause double quotes and backslashes to be + * ignored for quoting. + */ +#define seq_escape_printf_format(s, src) \ + seq_escape_str(s, src, ESCAPE_ANY | ESCAPE_NAP | ESCAPE_APPEND, "\"\\") + +static int pi_show(struct seq_file *s, void *v) +{ + const struct pi_entry *entry = v; + int level = LOGLEVEL_DEFAULT; + enum printk_info_flags flags = 0; + u16 prefix_len = 0; + + if (v == SEQ_START_TOKEN) { + seq_puts(s, "# filename:line function \"format\"\n"); + return 0; + } + + if (!entry->fmt) + return 0; + + if (entry->level) + printk_parse_prefix(entry->level, &level, &flags); + else + prefix_len = printk_parse_prefix(entry->fmt, &level, &flags); + + + if (flags & LOG_CONT) { + /* + * LOGLEVEL_DEFAULT here means "use the same level as the + * message we're continuing from", not the default message + * loglevel, so don't display it as such. + */ + if (level == LOGLEVEL_DEFAULT) + seq_puts(s, ""); + else + seq_printf(s, "<%d,c>", level); + } else + seq_printf(s, "<%d>", level); + + seq_printf(s, " %s:%d %s \"", entry->file, entry->line, entry->func); + if (entry->subsys_fmt_prefix) + seq_escape_printf_format(s, entry->subsys_fmt_prefix); + seq_escape_printf_format(s, entry->fmt + prefix_len); + seq_puts(s, "\"\n"); + + return 0; +} + +static void pi_stop(struct seq_file *p, void *v) { } + +static const struct seq_operations dfs_index_sops = { + .start = pi_start, + .next = pi_next, + .show = pi_show, + .stop = pi_stop, +}; + +DEFINE_SEQ_ATTRIBUTE(dfs_index); + +#ifdef CONFIG_MODULES +static const char *pi_get_module_name(struct module *mod) +{ + return mod ? mod->name : "vmlinux"; +} +#else +static const char *pi_get_module_name(struct module *mod) +{ + return "vmlinux"; +} +#endif + +void pi_create_file(struct module *mod) +{ + debugfs_create_file(pi_get_module_name(mod), 0444, dfs_index, + mod, &dfs_index_fops); +} + +void pi_remove_file(struct module *mod) +{ + debugfs_remove(debugfs_lookup(pi_get_module_name(mod), dfs_index)); +} + +#ifdef CONFIG_MODULES +static int pi_module_notify(struct notifier_block *nb, unsigned long op, + void *data) +{ + struct module *mod = data; + + switch (op) { + case MODULE_STATE_COMING: + pi_create_file(mod); + break; + case MODULE_STATE_GOING: + pi_remove_file(mod); + break; + default: /* we don't care about other module states */ + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block module_printk_fmts_nb = { + .notifier_call = pi_module_notify, +}; + +static void __init pi_setup_module_notifier(void) +{ + register_module_notifier(&module_printk_fmts_nb); +} +#else +static inline void __init pi_setup_module_notifier(void) { } +#endif + +static int __init pi_init(void) +{ + struct dentry *dfs_root = debugfs_create_dir("printk", NULL); + + dfs_index = debugfs_create_dir("index", dfs_root); + pi_setup_module_notifier(); + pi_create_file(NULL); + + return 0; +} + +/* debugfs comes up on core and must be initialised first */ +postcore_initcall(pi_init); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 03956c3eb745..765f7af6ce56 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2184,10 +2184,13 @@ int vprintk_default(const char *fmt, va_list args) EXPORT_SYMBOL_GPL(vprintk_default); /** - * printk - print a kernel message + * _printk - print a kernel message * @fmt: format string * - * This is printk(). It can be called from any context. We want it to work. + * This is _printk(). It can be called from any context. We want it to work. + * + * If printk indexing is enabled, _printk() is called from printk_index_wrap. + * Otherwise, printk is simply #defined to _printk. * * We try to grab the console_lock. If we succeed, it's easy - we log the * output and call the console drivers. If we fail to get the semaphore, we @@ -2204,7 +2207,7 @@ EXPORT_SYMBOL_GPL(vprintk_default); * * See the vsnprintf() documentation for format string extensions over C99. */ -asmlinkage __visible int printk(const char *fmt, ...) +asmlinkage __visible int _printk(const char *fmt, ...) { va_list args; int r; @@ -2215,7 +2218,7 @@ asmlinkage __visible int printk(const char *fmt, ...) return r; } -EXPORT_SYMBOL(printk); +EXPORT_SYMBOL(_printk); #else /* CONFIG_PRINTK */ @@ -3200,7 +3203,7 @@ int vprintk_deferred(const char *fmt, va_list args) return r; } -int printk_deferred(const char *fmt, ...) +int _printk_deferred(const char *fmt, ...) { va_list args; int r; -- cgit v1.2.3 From ad7d61f159db73974f1b0352f21afe04b0bbd920 Mon Sep 17 00:00:00 2001 From: Chris Down Date: Tue, 15 Jun 2021 17:52:56 +0100 Subject: printk: index: Add indexing support to dev_printk While for most kinds of issues we have counters, tracepoints, or metrics with a stable interface which can reliably be used to indicate issues, in order to react to production issues quickly we sometimes need to work with the interface which most kernel developers naturally use when developing: printk, and printk-esques like dev_printk. dev_printk is by far the most likely custom subsystem printk to benefit from the printk indexing infrastructure, since niche device issues brought about by production changes, firmware upgrades, and the like are one of the most common things that we need printk infrastructure's assistance to monitor. Often these errors were never expected to practically manifest in reality, and exhibit in code without extensive (or any) metrics present. As such, there are typically very few options for issue detection available to those with large fleets at the time the incident happens, and we thus benefit strongly from monitoring netconsole in these instances. As such, add the infrastructure for dev_printk to be indexed in the printk index. Even on a minimal kernel config, the coverage of the base kernel's printk index is significantly improved: Before: [root@ktst ~]# wc -l /sys/kernel/debug/printk/index/vmlinux 4497 /sys/kernel/debug/printk/index/vmlinux After: [root@ktst ~]# wc -l /sys/kernel/debug/printk/index/vmlinux 5573 /sys/kernel/debug/printk/index/vmlinux In terms of implementation, in order to trivially disambiguate them, dev_printk is now a macro which wraps _dev_printk. Signed-off-by: Chris Down Cc: Petr Mladek Cc: Greg Kroah-Hartman Cc: Rasmus Villemoes Reviewed-by: Petr Mladek Tested-by: Petr Mladek Acked-by: Andy Shevchenko Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/959c7aed1017cb2c9de922e0a820d397e29c6a5a.1623775748.git.chris@chrisdown.name --- drivers/base/core.c | 6 ++--- include/linux/dev_printk.h | 66 ++++++++++++++++++++++++++++++++++------------ 2 files changed, 52 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index cadcade65825..613497f45224 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4579,8 +4579,8 @@ static void __dev_printk(const char *level, const struct device *dev, printk("%s(NULL device *): %pV", level, vaf); } -void dev_printk(const char *level, const struct device *dev, - const char *fmt, ...) +void _dev_printk(const char *level, const struct device *dev, + const char *fmt, ...) { struct va_format vaf; va_list args; @@ -4594,7 +4594,7 @@ void dev_printk(const char *level, const struct device *dev, va_end(args); } -EXPORT_SYMBOL(dev_printk); +EXPORT_SYMBOL(_dev_printk); #define define_dev_printk_level(func, kern_level) \ void func(const struct device *dev, const char *fmt, ...) \ diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 82d3d46005a1..8904063d4c9f 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -38,8 +38,8 @@ __printf(3, 4) __cold int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...); __printf(3, 4) __cold -void dev_printk(const char *level, const struct device *dev, - const char *fmt, ...); +void _dev_printk(const char *level, const struct device *dev, + const char *fmt, ...); __printf(2, 3) __cold void _dev_emerg(const struct device *dev, const char *fmt, ...); __printf(2, 3) __cold @@ -69,7 +69,7 @@ static inline void __dev_printk(const char *level, const struct device *dev, struct va_format *vaf) {} static inline __printf(3, 4) -void dev_printk(const char *level, const struct device *dev, +void _dev_printk(const char *level, const struct device *dev, const char *fmt, ...) {} @@ -97,25 +97,57 @@ void _dev_info(const struct device *dev, const char *fmt, ...) #endif +/* + * Need to take variadic arguments even though we don't use them, as dev_fmt() + * may only just have been expanded and may result in multiple arguments. + */ +#define dev_printk_index_emit(level, fmt, ...) \ + printk_index_subsys_emit("%s %s: ", level, fmt) + +#define dev_printk_index_wrap(_p_func, level, dev, fmt, ...) \ + ({ \ + dev_printk_index_emit(level, fmt); \ + _p_func(dev, fmt, ##__VA_ARGS__); \ + }) + +/* + * Some callsites directly call dev_printk rather than going through the + * dev_ infrastructure, so we need to emit here as well as inside those + * level-specific macros. Only one index entry will be produced, either way, + * since dev_printk's `fmt` isn't known at compile time if going through the + * dev_ macros. + * + * dev_fmt() isn't called for dev_printk when used directly, as it's used by + * the dev_ macros internally which already have dev_fmt() processed. + * + * We also can't use dev_printk_index_wrap directly, because we have a separate + * level to process. + */ +#define dev_printk(level, dev, fmt, ...) \ + ({ \ + dev_printk_index_emit(level, fmt); \ + _dev_printk(level, dev, fmt, ##__VA_ARGS__); \ + }) + /* * #defines for all the dev_ macros to prefix with whatever * possible use of #define dev_fmt(fmt) ... */ -#define dev_emerg(dev, fmt, ...) \ - _dev_emerg(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_crit(dev, fmt, ...) \ - _dev_crit(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_alert(dev, fmt, ...) \ - _dev_alert(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_err(dev, fmt, ...) \ - _dev_err(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_warn(dev, fmt, ...) \ - _dev_warn(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_notice(dev, fmt, ...) \ - _dev_notice(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_info(dev, fmt, ...) \ - _dev_info(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_emerg(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_emerg, KERN_EMERG, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_crit(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_crit, KERN_CRIT, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_alert(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_alert, KERN_ALERT, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_err(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_err, KERN_ERR, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_warn(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_warn, KERN_WARNING, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_notice(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_notice, KERN_NOTICE, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_info(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_info, KERN_INFO, dev, dev_fmt(fmt), ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -- cgit v1.2.3 From ec03f18cc222bb7bec074ce7845c157d1c5195f6 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Mon, 19 Jul 2021 11:03:17 +0300 Subject: clk: at91: add register definition for sama7g5's master clock Add register definitions for SAMA7G5's master clock. These would be also used by architecture specific power saving code. Signed-off-by: Claudiu Beznea Signed-off-by: Nicolas Ferre Link: https://lore.kernel.org/r/20210719080317.1045832-3-claudiu.beznea@microchip.com --- include/linux/clk/at91_pmc.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index a4f82e836a7c..ccb3f034bfa9 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -137,6 +137,32 @@ #define AT91_PMC_PLLADIV2_ON (1 << 12) #define AT91_PMC_H32MXDIV BIT(24) +#define AT91_PMC_MCR_V2 0x30 /* Master Clock Register [SAMA7G5 only] */ +#define AT91_PMC_MCR_V2_ID_MSK (0xF) +#define AT91_PMC_MCR_V2_ID(_id) ((_id) & AT91_PMC_MCR_V2_ID_MSK) +#define AT91_PMC_MCR_V2_CMD (1 << 7) +#define AT91_PMC_MCR_V2_DIV (7 << 8) +#define AT91_PMC_MCR_V2_DIV1 (0 << 8) +#define AT91_PMC_MCR_V2_DIV2 (1 << 8) +#define AT91_PMC_MCR_V2_DIV4 (2 << 8) +#define AT91_PMC_MCR_V2_DIV8 (3 << 8) +#define AT91_PMC_MCR_V2_DIV16 (4 << 8) +#define AT91_PMC_MCR_V2_DIV32 (5 << 8) +#define AT91_PMC_MCR_V2_DIV64 (6 << 8) +#define AT91_PMC_MCR_V2_DIV3 (7 << 8) +#define AT91_PMC_MCR_V2_CSS (0x1F << 16) +#define AT91_PMC_MCR_V2_CSS_MD_SLCK (0 << 16) +#define AT91_PMC_MCR_V2_CSS_TD_SLCK (1 << 16) +#define AT91_PMC_MCR_V2_CSS_MAINCK (2 << 16) +#define AT91_PMC_MCR_V2_CSS_MCK0 (3 << 16) +#define AT91_PMC_MCR_V2_CSS_SYSPLL (5 << 16) +#define AT91_PMC_MCR_V2_CSS_DDRPLL (6 << 16) +#define AT91_PMC_MCR_V2_CSS_IMGPLL (7 << 16) +#define AT91_PMC_MCR_V2_CSS_BAUDPLL (8 << 16) +#define AT91_PMC_MCR_V2_CSS_AUDIOPLL (9 << 16) +#define AT91_PMC_MCR_V2_CSS_ETHPLL (10 << 16) +#define AT91_PMC_MCR_V2_EN (1 << 28) + #define AT91_PMC_XTALF 0x34 /* Main XTAL Frequency Register [SAMA7G5 only] */ #define AT91_PMC_USB 0x38 /* USB Clock Register [some SAM9 only] */ -- cgit v1.2.3 From d6371c76e20d7d3f61b05fd67b596af4d14a8886 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 19 Jul 2021 09:51:34 +0100 Subject: bpf: Fix OOB read when printing XDP link fdinfo We got the following UBSAN report on one of our testing machines: ================================================================================ UBSAN: array-index-out-of-bounds in kernel/bpf/syscall.c:2389:24 index 6 is out of range for type 'char *[6]' CPU: 43 PID: 930921 Comm: systemd-coredum Tainted: G O 5.10.48-cloudflare-kasan-2021.7.0 #1 Hardware name: Call Trace: dump_stack+0x7d/0xa3 ubsan_epilogue+0x5/0x40 __ubsan_handle_out_of_bounds.cold+0x43/0x48 ? seq_printf+0x17d/0x250 bpf_link_show_fdinfo+0x329/0x380 ? bpf_map_value_size+0xe0/0xe0 ? put_files_struct+0x20/0x2d0 ? __kasan_kmalloc.constprop.0+0xc2/0xd0 seq_show+0x3f7/0x540 seq_read_iter+0x3f8/0x1040 seq_read+0x329/0x500 ? seq_read_iter+0x1040/0x1040 ? __fsnotify_parent+0x80/0x820 ? __fsnotify_update_child_dentry_flags+0x380/0x380 vfs_read+0x123/0x460 ksys_read+0xed/0x1c0 ? __x64_sys_pwrite64+0x1f0/0x1f0 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ================================================================================ ================================================================================ UBSAN: object-size-mismatch in kernel/bpf/syscall.c:2384:2 From the report, we can infer that some array access in bpf_link_show_fdinfo at index 6 is out of bounds. The obvious candidate is bpf_link_type_strs[BPF_LINK_TYPE_XDP] with BPF_LINK_TYPE_XDP == 6. It turns out that BPF_LINK_TYPE_XDP is missing from bpf_types.h and therefore doesn't have an entry in bpf_link_type_strs: pos: 0 flags: 02000000 mnt_id: 13 link_type: (null) link_id: 4 prog_tag: bcf7977d3b93787c prog_id: 4 ifindex: 1 Fixes: aa8d3a716b59 ("bpf, xdp: Add bpf_link-based XDP attachment API") Signed-off-by: Lorenz Bauer Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210719085134.43325-2-lmb@cloudflare.com --- include/linux/bpf_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a9db1eae6796..ae3ac3a2018c 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -134,4 +134,5 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) #ifdef CONFIG_NET BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) +BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #endif -- cgit v1.2.3 From 0fac6aa098edf91ba65370da03811d9aba5715a9 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:42 +0300 Subject: net: dsa: sja1105: delete the best_effort_vlan_filtering mode Simply put, the best-effort VLAN filtering mode relied on VLAN retagging from a bridge VLAN towards a tag_8021q sub-VLAN in order to be able to decode the source port in the tagger, but the VLAN retagging implementation inside the sja1105 chips is not the best and we were relying on marginal operating conditions. The most notable limitation of the best-effort VLAN filtering mode is its incapacity to treat this case properly: ip link add br0 type bridge vlan_filtering 1 ip link set swp2 master br0 ip link set swp4 master br0 bridge vlan del dev swp4 vid 1 bridge vlan add dev swp4 vid 1 pvid When sending an untagged packet through swp2, the expectation is for it to be forwarded to swp4 as egress-tagged (so it will contain VLAN ID 1 on egress). But the switch will send it as egress-untagged. There was an attempt to fix this here: https://patchwork.kernel.org/project/netdevbpf/patch/20210407201452.1703261-2-olteanv@gmail.com/ but it failed miserably because it broke PTP RX timestamping, in a way that cannot be corrected due to hardware issues related to VLAN retagging. So with either PTP broken or pushing VLAN headers on egress for untagged packets being broken, the sad reality is that the best-effort VLAN filtering code is broken. Delete it. Note that this means there will be a temporary loss of functionality in this driver until it is replaced with something better (network stack RX/TX capability for "mode 2" as described in Documentation/networking/dsa/sja1105.rst, the "port under VLAN-aware bridge" case). We simply cannot keep this code until that driver rework is done, it is super bloated and tangled with tag_8021q. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105.h | 13 +- drivers/net/dsa/sja1105/sja1105_devlink.c | 114 +------ drivers/net/dsa/sja1105/sja1105_main.c | 482 ++---------------------------- drivers/net/dsa/sja1105/sja1105_vl.c | 14 +- include/linux/dsa/8021q.h | 9 +- include/linux/dsa/sja1105.h | 1 - net/dsa/tag_8021q.c | 77 +---- net/dsa/tag_ocelot_8021q.c | 4 +- net/dsa/tag_sja1105.c | 28 +- 9 files changed, 42 insertions(+), 700 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 221c7abdef0e..869b19c08fc0 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -234,19 +234,13 @@ struct sja1105_bridge_vlan { bool untagged; }; -enum sja1105_vlan_state { - SJA1105_VLAN_UNAWARE, - SJA1105_VLAN_BEST_EFFORT, - SJA1105_VLAN_FILTERING_FULL, -}; - struct sja1105_private { struct sja1105_static_config static_config; bool rgmii_rx_delay[SJA1105_MAX_NUM_PORTS]; bool rgmii_tx_delay[SJA1105_MAX_NUM_PORTS]; phy_interface_t phy_mode[SJA1105_MAX_NUM_PORTS]; bool fixed_link[SJA1105_MAX_NUM_PORTS]; - bool best_effort_vlan_filtering; + bool vlan_aware; unsigned long learn_ena; unsigned long ucast_egress_floods; unsigned long bcast_egress_floods; @@ -264,7 +258,6 @@ struct sja1105_private { */ struct mutex mgmt_lock; struct dsa_8021q_context *dsa_8021q_ctx; - enum sja1105_vlan_state vlan_state; struct devlink_region **regions; struct sja1105_cbs_entry *cbs; struct mii_bus *mdio_base_t1; @@ -311,10 +304,6 @@ int sja1110_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val); /* From sja1105_devlink.c */ int sja1105_devlink_setup(struct dsa_switch *ds); void sja1105_devlink_teardown(struct dsa_switch *ds); -int sja1105_devlink_param_get(struct dsa_switch *ds, u32 id, - struct devlink_param_gset_ctx *ctx); -int sja1105_devlink_param_set(struct dsa_switch *ds, u32 id, - struct devlink_param_gset_ctx *ctx); int sja1105_devlink_info_get(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c index b6a4a16b8c7e..05c7f4ca3b1a 100644 --- a/drivers/net/dsa/sja1105/sja1105_devlink.c +++ b/drivers/net/dsa/sja1105/sja1105_devlink.c @@ -115,105 +115,6 @@ static void sja1105_teardown_devlink_regions(struct dsa_switch *ds) kfree(priv->regions); } -static int sja1105_best_effort_vlan_filtering_get(struct sja1105_private *priv, - bool *be_vlan) -{ - *be_vlan = priv->best_effort_vlan_filtering; - - return 0; -} - -static int sja1105_best_effort_vlan_filtering_set(struct sja1105_private *priv, - bool be_vlan) -{ - struct dsa_switch *ds = priv->ds; - bool vlan_filtering; - int port; - int rc; - - priv->best_effort_vlan_filtering = be_vlan; - - rtnl_lock(); - for (port = 0; port < ds->num_ports; port++) { - struct dsa_port *dp; - - if (!dsa_is_user_port(ds, port)) - continue; - - dp = dsa_to_port(ds, port); - vlan_filtering = dsa_port_is_vlan_filtering(dp); - - rc = sja1105_vlan_filtering(ds, port, vlan_filtering, NULL); - if (rc) - break; - } - rtnl_unlock(); - - return rc; -} - -enum sja1105_devlink_param_id { - SJA1105_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, - SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING, -}; - -int sja1105_devlink_param_get(struct dsa_switch *ds, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct sja1105_private *priv = ds->priv; - int err; - - switch (id) { - case SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING: - err = sja1105_best_effort_vlan_filtering_get(priv, - &ctx->val.vbool); - break; - default: - err = -EOPNOTSUPP; - break; - } - - return err; -} - -int sja1105_devlink_param_set(struct dsa_switch *ds, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct sja1105_private *priv = ds->priv; - int err; - - switch (id) { - case SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING: - err = sja1105_best_effort_vlan_filtering_set(priv, - ctx->val.vbool); - break; - default: - err = -EOPNOTSUPP; - break; - } - - return err; -} - -static const struct devlink_param sja1105_devlink_params[] = { - DSA_DEVLINK_PARAM_DRIVER(SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING, - "best_effort_vlan_filtering", - DEVLINK_PARAM_TYPE_BOOL, - BIT(DEVLINK_PARAM_CMODE_RUNTIME)), -}; - -static int sja1105_setup_devlink_params(struct dsa_switch *ds) -{ - return dsa_devlink_params_register(ds, sja1105_devlink_params, - ARRAY_SIZE(sja1105_devlink_params)); -} - -static void sja1105_teardown_devlink_params(struct dsa_switch *ds) -{ - dsa_devlink_params_unregister(ds, sja1105_devlink_params, - ARRAY_SIZE(sja1105_devlink_params)); -} - int sja1105_devlink_info_get(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack) @@ -233,23 +134,10 @@ int sja1105_devlink_info_get(struct dsa_switch *ds, int sja1105_devlink_setup(struct dsa_switch *ds) { - int rc; - - rc = sja1105_setup_devlink_params(ds); - if (rc) - return rc; - - rc = sja1105_setup_devlink_regions(ds); - if (rc < 0) { - sja1105_teardown_devlink_params(ds); - return rc; - } - - return 0; + return sja1105_setup_devlink_regions(ds); } void sja1105_devlink_teardown(struct dsa_switch *ds) { - sja1105_teardown_devlink_params(ds); sja1105_teardown_devlink_regions(ds); } diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index ced8c9cb29c2..4514ac468cc8 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -545,18 +545,11 @@ void sja1105_frame_memory_partitioning(struct sja1105_private *priv) { struct sja1105_l2_forwarding_params_entry *l2_fwd_params; struct sja1105_vl_forwarding_params_entry *vl_fwd_params; - int max_mem = priv->info->max_frame_mem; struct sja1105_table *table; - /* VLAN retagging is implemented using a loopback port that consumes - * frame buffers. That leaves less for us. - */ - if (priv->vlan_state == SJA1105_VLAN_BEST_EFFORT) - max_mem -= SJA1105_FRAME_MEMORY_RETAGGING_OVERHEAD; - table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING_PARAMS]; l2_fwd_params = table->entries; - l2_fwd_params->part_spc[0] = max_mem; + l2_fwd_params->part_spc[0] = SJA1105_MAX_FRAME_MEMORY; /* If we have any critical-traffic virtual links, we need to reserve * some frame buffer memory for them. At the moment, hardcode the value @@ -1416,7 +1409,7 @@ int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port, l2_lookup.vlanid = vid; l2_lookup.iotag = SJA1105_S_TAG; l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0); - if (priv->vlan_state != SJA1105_VLAN_UNAWARE) { + if (priv->vlan_aware) { l2_lookup.mask_vlanid = VLAN_VID_MASK; l2_lookup.mask_iotag = BIT(0); } else { @@ -1479,7 +1472,7 @@ int sja1105pqrs_fdb_del(struct dsa_switch *ds, int port, l2_lookup.vlanid = vid; l2_lookup.iotag = SJA1105_S_TAG; l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0); - if (priv->vlan_state != SJA1105_VLAN_UNAWARE) { + if (priv->vlan_aware) { l2_lookup.mask_vlanid = VLAN_VID_MASK; l2_lookup.mask_iotag = BIT(0); } else { @@ -1525,7 +1518,7 @@ static int sja1105_fdb_add(struct dsa_switch *ds, int port, * for what gets printed in 'bridge fdb show'. In the case of zero, * no VID gets printed at all. */ - if (priv->vlan_state != SJA1105_VLAN_FILTERING_FULL) + if (!priv->vlan_aware) vid = 0; return priv->info->fdb_add_cmd(ds, port, addr, vid); @@ -1536,7 +1529,7 @@ static int sja1105_fdb_del(struct dsa_switch *ds, int port, { struct sja1105_private *priv = ds->priv; - if (priv->vlan_state != SJA1105_VLAN_FILTERING_FULL) + if (!priv->vlan_aware) vid = 0; return priv->info->fdb_del_cmd(ds, port, addr, vid); @@ -1581,7 +1574,7 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port, u64_to_ether_addr(l2_lookup.macaddr, macaddr); /* We need to hide the dsa_8021q VLANs from the user. */ - if (priv->vlan_state == SJA1105_VLAN_UNAWARE) + if (!priv->vlan_aware) l2_lookup.vlanid = 0; cb(macaddr, l2_lookup.vlanid, l2_lookup.lockeds, data); } @@ -2085,57 +2078,6 @@ sja1105_get_tag_protocol(struct dsa_switch *ds, int port, return priv->info->tag_proto; } -static int sja1105_find_free_subvlan(u16 *subvlan_map, bool pvid) -{ - int subvlan; - - if (pvid) - return 0; - - for (subvlan = 1; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) - if (subvlan_map[subvlan] == VLAN_N_VID) - return subvlan; - - return -1; -} - -static int sja1105_find_subvlan(u16 *subvlan_map, u16 vid) -{ - int subvlan; - - for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) - if (subvlan_map[subvlan] == vid) - return subvlan; - - return -1; -} - -static int sja1105_find_committed_subvlan(struct sja1105_private *priv, - int port, u16 vid) -{ - struct sja1105_port *sp = &priv->ports[port]; - - return sja1105_find_subvlan(sp->subvlan_map, vid); -} - -static void sja1105_init_subvlan_map(u16 *subvlan_map) -{ - int subvlan; - - for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) - subvlan_map[subvlan] = VLAN_N_VID; -} - -static void sja1105_commit_subvlan_map(struct sja1105_private *priv, int port, - u16 *subvlan_map) -{ - struct sja1105_port *sp = &priv->ports[port]; - int subvlan; - - for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) - sp->subvlan_map[subvlan] = subvlan_map[subvlan]; -} - static int sja1105_is_vlan_configured(struct sja1105_private *priv, u16 vid) { struct sja1105_vlan_lookup_entry *vlan; @@ -2152,29 +2094,9 @@ static int sja1105_is_vlan_configured(struct sja1105_private *priv, u16 vid) return -1; } -static int -sja1105_find_retagging_entry(struct sja1105_retagging_entry *retagging, - int count, int from_port, u16 from_vid, - u16 to_vid) -{ - int i; - - for (i = 0; i < count; i++) - if (retagging[i].ing_port == BIT(from_port) && - retagging[i].vlan_ing == from_vid && - retagging[i].vlan_egr == to_vid) - return i; - - /* Return an invalid entry index if not found */ - return -1; -} - static int sja1105_commit_vlans(struct sja1105_private *priv, - struct sja1105_vlan_lookup_entry *new_vlan, - struct sja1105_retagging_entry *new_retagging, - int num_retagging) + struct sja1105_vlan_lookup_entry *new_vlan) { - struct sja1105_retagging_entry *retagging; struct sja1105_vlan_lookup_entry *vlan; struct sja1105_table *table; int num_vlans = 0; @@ -2234,50 +2156,9 @@ static int sja1105_commit_vlans(struct sja1105_private *priv, vlan[k++] = new_vlan[i]; } - /* VLAN Retagging Table */ - table = &priv->static_config.tables[BLK_IDX_RETAGGING]; - retagging = table->entries; - - for (i = 0; i < table->entry_count; i++) { - rc = sja1105_dynamic_config_write(priv, BLK_IDX_RETAGGING, - i, &retagging[i], false); - if (rc) - return rc; - } - - if (table->entry_count) - kfree(table->entries); - - table->entries = kcalloc(num_retagging, table->ops->unpacked_entry_size, - GFP_KERNEL); - if (!table->entries) - return -ENOMEM; - - table->entry_count = num_retagging; - retagging = table->entries; - - for (i = 0; i < num_retagging; i++) { - retagging[i] = new_retagging[i]; - - /* Update entry */ - rc = sja1105_dynamic_config_write(priv, BLK_IDX_RETAGGING, - i, &retagging[i], true); - if (rc < 0) - return rc; - } - return 0; } -struct sja1105_crosschip_vlan { - struct list_head list; - u16 vid; - bool untagged; - int port; - int other_port; - struct dsa_8021q_context *other_ctx; -}; - struct sja1105_crosschip_switch { struct list_head list; struct dsa_8021q_context *other_ctx; @@ -2289,7 +2170,7 @@ static int sja1105_commit_pvid(struct sja1105_private *priv) struct list_head *vlan_list; int rc = 0; - if (priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) + if (priv->vlan_aware) vlan_list = &priv->bridge_vlans; else vlan_list = &priv->dsa_8021q_vlans; @@ -2311,7 +2192,7 @@ sja1105_build_bridge_vlans(struct sja1105_private *priv, { struct sja1105_bridge_vlan *v; - if (priv->vlan_state == SJA1105_VLAN_UNAWARE) + if (!priv->vlan_aware) return 0; list_for_each_entry(v, &priv->bridge_vlans, list) { @@ -2334,9 +2215,6 @@ sja1105_build_dsa_8021q_vlans(struct sja1105_private *priv, { struct sja1105_bridge_vlan *v; - if (priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) - return 0; - list_for_each_entry(v, &priv->dsa_8021q_vlans, list) { int match = v->vid; @@ -2351,267 +2229,6 @@ sja1105_build_dsa_8021q_vlans(struct sja1105_private *priv, return 0; } -static int sja1105_build_subvlans(struct sja1105_private *priv, - u16 subvlan_map[][DSA_8021Q_N_SUBVLAN], - struct sja1105_vlan_lookup_entry *new_vlan, - struct sja1105_retagging_entry *new_retagging, - int *num_retagging) -{ - struct sja1105_bridge_vlan *v; - int k = *num_retagging; - - if (priv->vlan_state != SJA1105_VLAN_BEST_EFFORT) - return 0; - - list_for_each_entry(v, &priv->bridge_vlans, list) { - int upstream = dsa_upstream_port(priv->ds, v->port); - int match, subvlan; - u16 rx_vid; - - /* Only sub-VLANs on user ports need to be applied. - * Bridge VLANs also include VLANs added automatically - * by DSA on the CPU port. - */ - if (!dsa_is_user_port(priv->ds, v->port)) - continue; - - subvlan = sja1105_find_subvlan(subvlan_map[v->port], - v->vid); - if (subvlan < 0) { - subvlan = sja1105_find_free_subvlan(subvlan_map[v->port], - v->pvid); - if (subvlan < 0) { - dev_err(priv->ds->dev, "No more free subvlans\n"); - return -ENOSPC; - } - } - - rx_vid = dsa_8021q_rx_vid_subvlan(priv->ds, v->port, subvlan); - - /* @v->vid on @v->port needs to be retagged to @rx_vid - * on @upstream. Assume @v->vid on @v->port and on - * @upstream was already configured by the previous - * iteration over bridge_vlans. - */ - match = rx_vid; - new_vlan[match].vlanid = rx_vid; - new_vlan[match].vmemb_port |= BIT(v->port); - new_vlan[match].vmemb_port |= BIT(upstream); - new_vlan[match].vlan_bc |= BIT(v->port); - new_vlan[match].vlan_bc |= BIT(upstream); - /* The "untagged" flag is set the same as for the - * original VLAN - */ - if (!v->untagged) - new_vlan[match].tag_port |= BIT(v->port); - /* But it's always tagged towards the CPU */ - new_vlan[match].tag_port |= BIT(upstream); - new_vlan[match].type_entry = SJA1110_VLAN_D_TAG; - - /* The Retagging Table generates packet *clones* with - * the new VLAN. This is a very odd hardware quirk - * which we need to suppress by dropping the original - * packet. - * Deny egress of the original VLAN towards the CPU - * port. This will force the switch to drop it, and - * we'll see only the retagged packets. - */ - match = v->vid; - new_vlan[match].vlan_bc &= ~BIT(upstream); - - /* And the retagging itself */ - new_retagging[k].vlan_ing = v->vid; - new_retagging[k].vlan_egr = rx_vid; - new_retagging[k].ing_port = BIT(v->port); - new_retagging[k].egr_port = BIT(upstream); - if (k++ == SJA1105_MAX_RETAGGING_COUNT) { - dev_err(priv->ds->dev, "No more retagging rules\n"); - return -ENOSPC; - } - - subvlan_map[v->port][subvlan] = v->vid; - } - - *num_retagging = k; - - return 0; -} - -/* Sadly, in crosschip scenarios where the CPU port is also the link to another - * switch, we should retag backwards (the dsa_8021q vid to the original vid) on - * the CPU port of neighbour switches. - */ -static int -sja1105_build_crosschip_subvlans(struct sja1105_private *priv, - struct sja1105_vlan_lookup_entry *new_vlan, - struct sja1105_retagging_entry *new_retagging, - int *num_retagging) -{ - struct sja1105_crosschip_vlan *tmp, *pos; - struct dsa_8021q_crosschip_link *c; - struct sja1105_bridge_vlan *v, *w; - struct list_head crosschip_vlans; - int k = *num_retagging; - int rc = 0; - - if (priv->vlan_state != SJA1105_VLAN_BEST_EFFORT) - return 0; - - INIT_LIST_HEAD(&crosschip_vlans); - - list_for_each_entry(c, &priv->dsa_8021q_ctx->crosschip_links, list) { - struct sja1105_private *other_priv = c->other_ctx->ds->priv; - - if (other_priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) - continue; - - /* Crosschip links are also added to the CPU ports. - * Ignore those. - */ - if (!dsa_is_user_port(priv->ds, c->port)) - continue; - if (!dsa_is_user_port(c->other_ctx->ds, c->other_port)) - continue; - - /* Search for VLANs on the remote port */ - list_for_each_entry(v, &other_priv->bridge_vlans, list) { - bool already_added = false; - bool we_have_it = false; - - if (v->port != c->other_port) - continue; - - /* If @v is a pvid on @other_ds, it does not need - * re-retagging, because its SVL field is 0 and we - * already allow that, via the dsa_8021q crosschip - * links. - */ - if (v->pvid) - continue; - - /* Search for the VLAN on our local port */ - list_for_each_entry(w, &priv->bridge_vlans, list) { - if (w->port == c->port && w->vid == v->vid) { - we_have_it = true; - break; - } - } - - if (!we_have_it) - continue; - - list_for_each_entry(tmp, &crosschip_vlans, list) { - if (tmp->vid == v->vid && - tmp->untagged == v->untagged && - tmp->port == c->port && - tmp->other_port == v->port && - tmp->other_ctx == c->other_ctx) { - already_added = true; - break; - } - } - - if (already_added) - continue; - - tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); - if (!tmp) { - dev_err(priv->ds->dev, "Failed to allocate memory\n"); - rc = -ENOMEM; - goto out; - } - tmp->vid = v->vid; - tmp->port = c->port; - tmp->other_port = v->port; - tmp->other_ctx = c->other_ctx; - tmp->untagged = v->untagged; - list_add(&tmp->list, &crosschip_vlans); - } - } - - list_for_each_entry(tmp, &crosschip_vlans, list) { - struct sja1105_private *other_priv = tmp->other_ctx->ds->priv; - int upstream = dsa_upstream_port(priv->ds, tmp->port); - int match, subvlan; - u16 rx_vid; - - subvlan = sja1105_find_committed_subvlan(other_priv, - tmp->other_port, - tmp->vid); - /* If this happens, it's a bug. The neighbour switch does not - * have a subvlan for tmp->vid on tmp->other_port, but it - * should, since we already checked for its vlan_state. - */ - if (WARN_ON(subvlan < 0)) { - rc = -EINVAL; - goto out; - } - - rx_vid = dsa_8021q_rx_vid_subvlan(tmp->other_ctx->ds, - tmp->other_port, - subvlan); - - /* The @rx_vid retagged from @tmp->vid on - * {@tmp->other_ds, @tmp->other_port} needs to be - * re-retagged to @tmp->vid on the way back to us. - * - * Assume the original @tmp->vid is already configured - * on this local switch, otherwise we wouldn't be - * retagging its subvlan on the other switch in the - * first place. We just need to add a reverse retagging - * rule for @rx_vid and install @rx_vid on our ports. - */ - match = rx_vid; - new_vlan[match].vlanid = rx_vid; - new_vlan[match].vmemb_port |= BIT(tmp->port); - new_vlan[match].vmemb_port |= BIT(upstream); - /* The "untagged" flag is set the same as for the - * original VLAN. And towards the CPU, it doesn't - * really matter, because @rx_vid will only receive - * traffic on that port. For consistency with other dsa_8021q - * VLANs, we'll keep the CPU port tagged. - */ - if (!tmp->untagged) - new_vlan[match].tag_port |= BIT(tmp->port); - new_vlan[match].tag_port |= BIT(upstream); - new_vlan[match].type_entry = SJA1110_VLAN_D_TAG; - /* Deny egress of @rx_vid towards our front-panel port. - * This will force the switch to drop it, and we'll see - * only the re-retagged packets (having the original, - * pre-initial-retagging, VLAN @tmp->vid). - */ - new_vlan[match].vlan_bc &= ~BIT(tmp->port); - - /* On reverse retagging, the same ingress VLAN goes to multiple - * ports. So we have an opportunity to create composite rules - * to not waste the limited space in the retagging table. - */ - k = sja1105_find_retagging_entry(new_retagging, *num_retagging, - upstream, rx_vid, tmp->vid); - if (k < 0) { - if (*num_retagging == SJA1105_MAX_RETAGGING_COUNT) { - dev_err(priv->ds->dev, "No more retagging rules\n"); - rc = -ENOSPC; - goto out; - } - k = (*num_retagging)++; - } - /* And the retagging itself */ - new_retagging[k].vlan_ing = rx_vid; - new_retagging[k].vlan_egr = tmp->vid; - new_retagging[k].ing_port = BIT(upstream); - new_retagging[k].egr_port |= BIT(tmp->port); - } - -out: - list_for_each_entry_safe(tmp, pos, &crosschip_vlans, list) { - list_del(&tmp->list); - kfree(tmp); - } - - return rc; -} - static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify); static int sja1105_notify_crosschip_switches(struct sja1105_private *priv) @@ -2665,12 +2282,9 @@ out: static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify) { - u16 subvlan_map[SJA1105_MAX_NUM_PORTS][DSA_8021Q_N_SUBVLAN]; - struct sja1105_retagging_entry *new_retagging; struct sja1105_vlan_lookup_entry *new_vlan; struct sja1105_table *table; - int i, num_retagging = 0; - int rc; + int rc, i; table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP]; new_vlan = kcalloc(VLAN_N_VID, @@ -2679,22 +2293,10 @@ static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify) return -ENOMEM; table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP]; - new_retagging = kcalloc(SJA1105_MAX_RETAGGING_COUNT, - table->ops->unpacked_entry_size, GFP_KERNEL); - if (!new_retagging) { - kfree(new_vlan); - return -ENOMEM; - } for (i = 0; i < VLAN_N_VID; i++) new_vlan[i].vlanid = VLAN_N_VID; - for (i = 0; i < SJA1105_MAX_RETAGGING_COUNT; i++) - new_retagging[i].vlan_ing = VLAN_N_VID; - - for (i = 0; i < priv->ds->num_ports; i++) - sja1105_init_subvlan_map(subvlan_map[i]); - /* Bridge VLANs */ rc = sja1105_build_bridge_vlans(priv, new_vlan); if (rc) @@ -2709,22 +2311,7 @@ static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify) if (rc) goto out; - /* Private VLANs necessary for dsa_8021q operation, which we need to - * determine on our own: - * - Sub-VLANs - * - Sub-VLANs of crosschip switches - */ - rc = sja1105_build_subvlans(priv, subvlan_map, new_vlan, new_retagging, - &num_retagging); - if (rc) - goto out; - - rc = sja1105_build_crosschip_subvlans(priv, new_vlan, new_retagging, - &num_retagging); - if (rc) - goto out; - - rc = sja1105_commit_vlans(priv, new_vlan, new_retagging, num_retagging); + rc = sja1105_commit_vlans(priv, new_vlan); if (rc) goto out; @@ -2732,9 +2319,6 @@ static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify) if (rc) goto out; - for (i = 0; i < priv->ds->num_ports; i++) - sja1105_commit_subvlan_map(priv, i, subvlan_map[i]); - if (notify) { rc = sja1105_notify_crosschip_switches(priv); if (rc) @@ -2743,7 +2327,6 @@ static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify) out: kfree(new_vlan); - kfree(new_retagging); return rc; } @@ -2758,10 +2341,8 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, struct sja1105_l2_lookup_params_entry *l2_lookup_params; struct sja1105_general_params_entry *general_params; struct sja1105_private *priv = ds->priv; - enum sja1105_vlan_state state; struct sja1105_table *table; struct sja1105_rule *rule; - bool want_tagging; u16 tpid, tpid2; int rc; @@ -2792,19 +2373,10 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, sp->xmit_tpid = ETH_P_SJA1105; } - if (!enabled) - state = SJA1105_VLAN_UNAWARE; - else if (priv->best_effort_vlan_filtering) - state = SJA1105_VLAN_BEST_EFFORT; - else - state = SJA1105_VLAN_FILTERING_FULL; - - if (priv->vlan_state == state) + if (priv->vlan_aware == enabled) return 0; - priv->vlan_state = state; - want_tagging = (state == SJA1105_VLAN_UNAWARE || - state == SJA1105_VLAN_BEST_EFFORT); + priv->vlan_aware = enabled; table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; general_params = table->entries; @@ -2818,8 +2390,6 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, general_params->incl_srcpt1 = enabled; general_params->incl_srcpt0 = enabled; - want_tagging = priv->best_effort_vlan_filtering || !enabled; - /* VLAN filtering => independent VLAN learning. * No VLAN filtering (or best effort) => shared VLAN learning. * @@ -2840,9 +2410,7 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, */ table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS]; l2_lookup_params = table->entries; - l2_lookup_params->shared_learn = want_tagging; - - sja1105_frame_memory_partitioning(priv); + l2_lookup_params->shared_learn = !priv->vlan_aware; rc = sja1105_build_vlan_table(priv, false); if (rc) @@ -2852,12 +2420,7 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, if (rc) NL_SET_ERR_MSG_MOD(extack, "Failed to change VLAN Ethertype"); - /* Switch port identification based on 802.1Q is only passable - * if we are not under a vlan_filtering bridge. So make sure - * the two configurations are mutually exclusive (of course, the - * user may know better, i.e. best_effort_vlan_filtering). - */ - return sja1105_setup_8021q_tagging(ds, want_tagging); + return rc; } /* Returns number of VLANs added (0 or 1) on success, @@ -2927,12 +2490,9 @@ static int sja1105_vlan_add(struct dsa_switch *ds, int port, bool vlan_table_changed = false; int rc; - /* If the user wants best-effort VLAN filtering (aka vlan_filtering - * bridge plus tagging), be sure to at least deny alterations to the - * configuration done by dsa_8021q. + /* Be sure to deny alterations to the configuration done by tag_8021q. */ - if (priv->vlan_state != SJA1105_VLAN_FILTERING_FULL && - vid_is_dsa_8021q(vlan->vid)) { + if (vid_is_dsa_8021q(vlan->vid)) { NL_SET_ERR_MSG_MOD(extack, "Range 1024-3071 reserved for dsa_8021q operation"); return -EBUSY; @@ -3086,8 +2646,6 @@ static int sja1105_setup(struct dsa_switch *ds) ds->mtu_enforcement_ingress = true; - priv->best_effort_vlan_filtering = true; - rc = sja1105_devlink_setup(ds); if (rc < 0) goto out_static_config_free; @@ -3604,8 +3162,6 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .cls_flower_stats = sja1105_cls_flower_stats, .crosschip_bridge_join = sja1105_crosschip_bridge_join, .crosschip_bridge_leave = sja1105_crosschip_bridge_leave, - .devlink_param_get = sja1105_devlink_param_get, - .devlink_param_set = sja1105_devlink_param_set, .devlink_info_get = sja1105_devlink_info_get, }; @@ -3785,7 +3341,6 @@ static int sja1105_probe(struct spi_device *spi) struct sja1105_port *sp = &priv->ports[port]; struct dsa_port *dp = dsa_to_port(ds, port); struct net_device *slave; - int subvlan; if (!dsa_is_user_port(ds, port)) continue; @@ -3806,9 +3361,6 @@ static int sja1105_probe(struct spi_device *spi) } skb_queue_head_init(&sp->xmit_queue); sp->xmit_tpid = ETH_P_SJA1105; - - for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) - sp->subvlan_map[subvlan] = VLAN_N_VID; } return 0; diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c index f6e13e6c6a18..ec7b65daec20 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.c +++ b/drivers/net/dsa/sja1105/sja1105_vl.c @@ -496,14 +496,11 @@ int sja1105_vl_redirect(struct sja1105_private *priv, int port, struct sja1105_rule *rule = sja1105_rule_find(priv, cookie); int rc; - if (priv->vlan_state == SJA1105_VLAN_UNAWARE && - key->type != SJA1105_KEY_VLAN_UNAWARE_VL) { + if (!priv->vlan_aware && key->type != SJA1105_KEY_VLAN_UNAWARE_VL) { NL_SET_ERR_MSG_MOD(extack, "Can only redirect based on DMAC"); return -EOPNOTSUPP; - } else if ((priv->vlan_state == SJA1105_VLAN_BEST_EFFORT || - priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) && - key->type != SJA1105_KEY_VLAN_AWARE_VL) { + } else if (priv->vlan_aware && key->type != SJA1105_KEY_VLAN_AWARE_VL) { NL_SET_ERR_MSG_MOD(extack, "Can only redirect based on {DMAC, VID, PCP}"); return -EOPNOTSUPP; @@ -595,14 +592,11 @@ int sja1105_vl_gate(struct sja1105_private *priv, int port, return -ERANGE; } - if (priv->vlan_state == SJA1105_VLAN_UNAWARE && - key->type != SJA1105_KEY_VLAN_UNAWARE_VL) { + if (!priv->vlan_aware && key->type != SJA1105_KEY_VLAN_UNAWARE_VL) { NL_SET_ERR_MSG_MOD(extack, "Can only gate based on DMAC"); return -EOPNOTSUPP; - } else if ((priv->vlan_state == SJA1105_VLAN_BEST_EFFORT || - priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) && - key->type != SJA1105_KEY_VLAN_AWARE_VL) { + } else if (priv->vlan_aware && key->type != SJA1105_KEY_VLAN_AWARE_VL) { NL_SET_ERR_MSG_MOD(extack, "Can only gate based on {DMAC, VID, PCP}"); return -EOPNOTSUPP; diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 1587961f1a7b..608607f904a5 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -35,8 +35,6 @@ struct dsa_8021q_context { __be16 proto; }; -#define DSA_8021Q_N_SUBVLAN 8 - int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, @@ -50,21 +48,16 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); -void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, - int *subvlan); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan); - int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); -u16 dsa_8021q_rx_subvlan(u16 vid); - bool vid_is_dsa_8021q_rxvlan(u16 vid); bool vid_is_dsa_8021q_txvlan(u16 vid); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index b6089b88314c..0eadc7ac44ec 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -59,7 +59,6 @@ struct sja1105_skb_cb { ((struct sja1105_skb_cb *)((skb)->cb)) struct sja1105_port { - u16 subvlan_map[DSA_8021Q_N_SUBVLAN]; struct kthread_worker *xmit_worker; struct kthread_work xmit_work; struct sk_buff_head xmit_queue; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 4aa29f90ecea..d657864969d4 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -17,7 +17,7 @@ * * | 11 | 10 | 9 | 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 | * +-----------+-----+-----------------+-----------+-----------------------+ - * | DIR | SVL | SWITCH_ID | SUBVLAN | PORT | + * | DIR | RSV | SWITCH_ID | RSV | PORT | * +-----------+-----+-----------------+-----------+-----------------------+ * * DIR - VID[11:10]: @@ -27,24 +27,13 @@ * These values make the special VIDs of 0, 1 and 4095 to be left * unused by this coding scheme. * - * SVL/SUBVLAN - { VID[9], VID[5:4] }: - * Sub-VLAN encoding. Valid only when DIR indicates an RX VLAN. - * * 0 (0b000): Field does not encode a sub-VLAN, either because - * received traffic is untagged, PVID-tagged or because a second - * VLAN tag is present after this tag and not inside of it. - * * 1 (0b001): Received traffic is tagged with a VID value private - * to the host. This field encodes the index in the host's lookup - * table through which the value of the ingress VLAN ID can be - * recovered. - * * 2 (0b010): Field encodes a sub-VLAN. - * ... - * * 7 (0b111): Field encodes a sub-VLAN. - * When DIR indicates a TX VLAN, SUBVLAN must be transmitted as zero - * (by the host) and ignored on receive (by the switch). - * * SWITCH_ID - VID[8:6]: * Index of switch within DSA tree. Must be between 0 and 7. * + * RSV - VID[5:4]: + * To be used for further expansion of PORT or for other purposes. + * Must be transmitted as zero and ignored on receive. + * * PORT - VID[3:0]: * Index of switch port. Must be between 0 and 15. */ @@ -61,18 +50,6 @@ #define DSA_8021Q_SWITCH_ID(x) (((x) << DSA_8021Q_SWITCH_ID_SHIFT) & \ DSA_8021Q_SWITCH_ID_MASK) -#define DSA_8021Q_SUBVLAN_HI_SHIFT 9 -#define DSA_8021Q_SUBVLAN_HI_MASK GENMASK(9, 9) -#define DSA_8021Q_SUBVLAN_LO_SHIFT 4 -#define DSA_8021Q_SUBVLAN_LO_MASK GENMASK(5, 4) -#define DSA_8021Q_SUBVLAN_HI(x) (((x) & GENMASK(2, 2)) >> 2) -#define DSA_8021Q_SUBVLAN_LO(x) ((x) & GENMASK(1, 0)) -#define DSA_8021Q_SUBVLAN(x) \ - (((DSA_8021Q_SUBVLAN_LO(x) << DSA_8021Q_SUBVLAN_LO_SHIFT) & \ - DSA_8021Q_SUBVLAN_LO_MASK) | \ - ((DSA_8021Q_SUBVLAN_HI(x) << DSA_8021Q_SUBVLAN_HI_SHIFT) & \ - DSA_8021Q_SUBVLAN_HI_MASK)) - #define DSA_8021Q_PORT_SHIFT 0 #define DSA_8021Q_PORT_MASK GENMASK(3, 0) #define DSA_8021Q_PORT(x) (((x) << DSA_8021Q_PORT_SHIFT) & \ @@ -98,13 +75,6 @@ u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) } EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid); -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan) -{ - return DSA_8021Q_DIR_RX | DSA_8021Q_SWITCH_ID(ds->index) | - DSA_8021Q_PORT(port) | DSA_8021Q_SUBVLAN(subvlan); -} -EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid_subvlan); - /* Returns the decoded switch ID from the RX VID. */ int dsa_8021q_rx_switch_id(u16 vid) { @@ -119,20 +89,6 @@ int dsa_8021q_rx_source_port(u16 vid) } EXPORT_SYMBOL_GPL(dsa_8021q_rx_source_port); -/* Returns the decoded subvlan from the RX VID. */ -u16 dsa_8021q_rx_subvlan(u16 vid) -{ - u16 svl_hi, svl_lo; - - svl_hi = (vid & DSA_8021Q_SUBVLAN_HI_MASK) >> - DSA_8021Q_SUBVLAN_HI_SHIFT; - svl_lo = (vid & DSA_8021Q_SUBVLAN_LO_MASK) >> - DSA_8021Q_SUBVLAN_LO_SHIFT; - - return (svl_hi << 2) | svl_lo; -} -EXPORT_SYMBOL_GPL(dsa_8021q_rx_subvlan); - bool vid_is_dsa_8021q_rxvlan(u16 vid) { return (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_RX; @@ -227,7 +183,7 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port, u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port); u16 tx_vid = dsa_8021q_tx_vid(ctx->ds, port); struct net_device *master; - int i, err, subvlan; + int i, err; /* The CPU port is implicitly configured by * configuring the front-panel ports @@ -275,18 +231,11 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port, return err; } - /* Add to the master's RX filter not only @rx_vid, but in fact - * the entire subvlan range, just in case this DSA switch might - * want to use sub-VLANs. - */ - for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) { - u16 vid = dsa_8021q_rx_vid_subvlan(ctx->ds, port, subvlan); - - if (enabled) - vlan_vid_add(master, ctx->proto, vid); - else - vlan_vid_del(master, ctx->proto, vid); - } + /* Add @rx_vid to the master's RX filter. */ + if (enabled) + vlan_vid_add(master, ctx->proto, rx_vid); + else + vlan_vid_del(master, ctx->proto, rx_vid); /* Finally apply the TX VID on this port and on the CPU port */ err = dsa_8021q_vid_apply(ctx, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED, @@ -471,8 +420,7 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, } EXPORT_SYMBOL_GPL(dsa_8021q_xmit); -void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, - int *subvlan) +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id) { u16 vid, tci; @@ -489,7 +437,6 @@ void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, *source_port = dsa_8021q_rx_source_port(vid); *switch_id = dsa_8021q_rx_switch_id(vid); - *subvlan = dsa_8021q_rx_subvlan(vid); skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } EXPORT_SYMBOL_GPL(dsa_8021q_rcv); diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 85ac85c3af8c..d0781b058610 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -41,9 +41,9 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { - int src_port, switch_id, subvlan; + int src_port, switch_id; - dsa_8021q_rcv(skb, &src_port, &switch_id, &subvlan); + dsa_8021q_rcv(skb, &src_port, &switch_id); skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); if (!skb->dev) diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 9c2df9ece01b..7c92c329a092 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -358,20 +358,6 @@ static struct sk_buff return skb; } -static void sja1105_decode_subvlan(struct sk_buff *skb, u16 subvlan) -{ - struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_port *sp = dp->priv; - u16 vid = sp->subvlan_map[subvlan]; - u16 vlan_tci; - - if (vid == VLAN_N_VID) - return; - - vlan_tci = (skb->priority << VLAN_PRIO_SHIFT) | vid; - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); -} - static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) { u16 tpid = ntohs(eth_hdr(skb)->h_proto); @@ -389,8 +375,8 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { - int source_port, switch_id, subvlan = 0; struct sja1105_meta meta = {0}; + int source_port, switch_id; struct ethhdr *hdr; bool is_link_local; bool is_meta; @@ -403,7 +389,7 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, if (sja1105_skb_has_tag_8021q(skb)) { /* Normal traffic path. */ - dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); + dsa_8021q_rcv(skb, &source_port, &switch_id); } else if (is_link_local) { /* Management traffic path. Switch embeds the switch ID and * port ID into bytes of the destination MAC, courtesy of @@ -428,9 +414,6 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, return NULL; } - if (subvlan) - sja1105_decode_subvlan(skb, subvlan); - return sja1105_rcv_meta_state_machine(skb, &meta, is_link_local, is_meta); } @@ -538,7 +521,7 @@ static struct sk_buff *sja1110_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { - int source_port = -1, switch_id = -1, subvlan = 0; + int source_port = -1, switch_id = -1; skb->offload_fwd_mark = 1; @@ -551,7 +534,7 @@ static struct sk_buff *sja1110_rcv(struct sk_buff *skb, /* Packets with in-band control extensions might still have RX VLANs */ if (likely(sja1105_skb_has_tag_8021q(skb))) - dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); + dsa_8021q_rcv(skb, &source_port, &switch_id); skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); if (!skb->dev) { @@ -561,9 +544,6 @@ static struct sk_buff *sja1110_rcv(struct sk_buff *skb, return NULL; } - if (subvlan) - sja1105_decode_subvlan(skb, subvlan); - return skb; } -- cgit v1.2.3 From 8afbea187d31e4e9beb83b7a316d16b7879c2799 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:45 +0300 Subject: net: dsa: tag_8021q: remove struct packet_type declaration This is no longer necessary since tag_8021q doesn't register itself as a full-blown tagger anymore. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 608607f904a5..5f01dea7d5b6 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -11,7 +11,6 @@ struct dsa_switch; struct sk_buff; struct net_device; -struct packet_type; struct dsa_8021q_context; struct dsa_8021q_crosschip_link { -- cgit v1.2.3 From cedf467064b6b8764fdb2ee6b9e3d18bc81a9d8f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:46 +0300 Subject: net: dsa: tag_8021q: create dsa_tag_8021q_{register,unregister} helpers In preparation of moving tag_8021q to core DSA, move all initialization and teardown related to tag_8021q which is currently done by drivers in 2 functions called "register" and "unregister". These will gather more functionality in future patches, which will better justify the chosen naming scheme. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 12 ++++-------- drivers/net/dsa/sja1105/sja1105_main.c | 18 +++++++++--------- include/linux/dsa/8021q.h | 6 ++++++ net/dsa/tag_8021q.c | 33 +++++++++++++++++++++++++++++++++ 4 files changed, 52 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index a2a15919b960..b52cc381cdc1 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -425,15 +425,11 @@ static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu) ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_MC); ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_BC); - felix->dsa_8021q_ctx = kzalloc(sizeof(*felix->dsa_8021q_ctx), - GFP_KERNEL); + felix->dsa_8021q_ctx = dsa_tag_8021q_register(ds, &felix_tag_8021q_ops, + htons(ETH_P_8021AD)); if (!felix->dsa_8021q_ctx) return -ENOMEM; - felix->dsa_8021q_ctx->ops = &felix_tag_8021q_ops; - felix->dsa_8021q_ctx->proto = htons(ETH_P_8021AD); - felix->dsa_8021q_ctx->ds = ds; - err = dsa_8021q_setup(felix->dsa_8021q_ctx, true); if (err) goto out_free_dsa_8021_ctx; @@ -447,7 +443,7 @@ static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu) out_teardown_dsa_8021q: dsa_8021q_setup(felix->dsa_8021q_ctx, false); out_free_dsa_8021_ctx: - kfree(felix->dsa_8021q_ctx); + dsa_tag_8021q_unregister(felix->dsa_8021q_ctx); return err; } @@ -466,7 +462,7 @@ static void felix_teardown_tag_8021q(struct dsa_switch *ds, int cpu) if (err) dev_err(ds->dev, "dsa_8021q_setup returned %d", err); - kfree(felix->dsa_8021q_ctx); + dsa_tag_8021q_unregister(felix->dsa_8021q_ctx); for (port = 0; port < ds->num_ports; port++) { if (dsa_is_unused_port(ds, port)) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 4514ac468cc8..689f46797d1c 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -3306,16 +3306,11 @@ static int sja1105_probe(struct spi_device *spi) mutex_init(&priv->ptp_data.lock); mutex_init(&priv->mgmt_lock); - priv->dsa_8021q_ctx = devm_kzalloc(dev, sizeof(*priv->dsa_8021q_ctx), - GFP_KERNEL); + priv->dsa_8021q_ctx = dsa_tag_8021q_register(ds, &sja1105_dsa_8021q_ops, + htons(ETH_P_8021Q)); if (!priv->dsa_8021q_ctx) return -ENOMEM; - priv->dsa_8021q_ctx->ops = &sja1105_dsa_8021q_ops; - priv->dsa_8021q_ctx->proto = htons(ETH_P_8021Q); - priv->dsa_8021q_ctx->ds = ds; - - INIT_LIST_HEAD(&priv->dsa_8021q_ctx->crosschip_links); INIT_LIST_HEAD(&priv->bridge_vlans); INIT_LIST_HEAD(&priv->dsa_8021q_vlans); @@ -3324,7 +3319,7 @@ static int sja1105_probe(struct spi_device *spi) rc = dsa_register_switch(priv->ds); if (rc) - return rc; + goto out_tag_8021q_unregister; if (IS_ENABLED(CONFIG_NET_SCH_CBS)) { priv->cbs = devm_kcalloc(dev, priv->info->num_cbs_shapers, @@ -3377,6 +3372,8 @@ out_destroy_workers: out_unregister_switch: dsa_unregister_switch(ds); +out_tag_8021q_unregister: + dsa_tag_8021q_unregister(priv->dsa_8021q_ctx); return rc; } @@ -3384,8 +3381,11 @@ out_unregister_switch: static int sja1105_remove(struct spi_device *spi) { struct sja1105_private *priv = spi_get_drvdata(spi); + struct dsa_switch *ds = priv->ds; + + dsa_unregister_switch(ds); + dsa_tag_8021q_unregister(priv->dsa_8021q_ctx); - dsa_unregister_switch(priv->ds); return 0; } diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 5f01dea7d5b6..9945898a90c3 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -34,6 +34,12 @@ struct dsa_8021q_context { __be16 proto; }; +struct dsa_8021q_context *dsa_tag_8021q_register(struct dsa_switch *ds, + const struct dsa_8021q_ops *ops, + __be16 proto); + +void dsa_tag_8021q_unregister(struct dsa_8021q_context *ctx); + int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 3a25b7b1ba50..73966ca23ac3 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -410,6 +410,39 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, } EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_leave); +struct dsa_8021q_context *dsa_tag_8021q_register(struct dsa_switch *ds, + const struct dsa_8021q_ops *ops, + __be16 proto) +{ + struct dsa_8021q_context *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; + + ctx->ops = ops; + ctx->proto = proto; + ctx->ds = ds; + + INIT_LIST_HEAD(&ctx->crosschip_links); + + return ctx; +} +EXPORT_SYMBOL_GPL(dsa_tag_8021q_register); + +void dsa_tag_8021q_unregister(struct dsa_8021q_context *ctx) +{ + struct dsa_8021q_crosschip_link *c, *n; + + list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) { + list_del(&c->list); + kfree(c); + } + + kfree(ctx); +} +EXPORT_SYMBOL_GPL(dsa_tag_8021q_unregister); + struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci) { -- cgit v1.2.3 From d7b1fd520d5d4271f4ab9b1671afbdcd868039d3 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:48 +0300 Subject: net: dsa: let the core manage the tag_8021q context The basic problem description is as follows: Be there 3 switches in a daisy chain topology: | sw0p0 sw0p1 sw0p2 sw0p3 sw0p4 [ user ] [ user ] [ user ] [ dsa ] [ cpu ] | +---------+ | sw1p0 sw1p1 sw1p2 sw1p3 sw1p4 [ user ] [ user ] [ user ] [ dsa ] [ dsa ] | +---------+ | sw2p0 sw2p1 sw2p2 sw2p3 sw2p4 [ user ] [ user ] [ user ] [ user ] [ dsa ] The CPU will not be able to ping through the user ports of the bottom-most switch (like for example sw2p0), simply because tag_8021q was not coded up for this scenario - it has always assumed DSA switch trees with a single switch. To add support for the topology above, we must admit that the RX VLAN of sw2p0 must be added on some ports of switches 0 and 1 as well. This is in fact a textbook example of thing that can use the cross-chip notifier framework that DSA has set up in switch.c. There is only one problem: core DSA (switch.c) is not able right now to make the connection between a struct dsa_switch *ds and a struct dsa_8021q_context *ctx. Right now, it is drivers who call into tag_8021q.c and always provide a struct dsa_8021q_context *ctx pointer, and tag_8021q.c calls them back with the .tag_8021q_vlan_{add,del} methods. But with cross-chip notifiers, it is possible for tag_8021q to call drivers without drivers having ever asked for anything. A good example is right above: when sw2p0 wants to set itself up for tag_8021q, the .tag_8021q_vlan_add method needs to be called for switches 1 and 0, so that they transport sw2p0's VLANs towards the CPU without dropping them. So instead of letting drivers manage the tag_8021q context, add a tag_8021q_ctx pointer inside of struct dsa_switch, which will be populated when dsa_tag_8021q_register() returns success. The patch is fairly long-winded because we are partly reverting commit 5899ee367ab3 ("net: dsa: tag_8021q: add a context structure") which made the driver-facing tag_8021q API use "ctx" instead of "ds". Now that we can access "ctx" directly from "ds", this is no longer needed. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 22 +++---- drivers/net/dsa/ocelot/felix.h | 1 - drivers/net/dsa/sja1105/sja1105.h | 1 - drivers/net/dsa/sja1105/sja1105_main.c | 40 +++++------- include/linux/dsa/8021q.h | 18 +++--- include/net/dsa.h | 3 + net/dsa/tag_8021q.c | 114 ++++++++++++++++++--------------- 7 files changed, 99 insertions(+), 100 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index b52cc381cdc1..9e4ae15aa4fb 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -425,14 +425,14 @@ static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu) ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_MC); ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_BC); - felix->dsa_8021q_ctx = dsa_tag_8021q_register(ds, &felix_tag_8021q_ops, - htons(ETH_P_8021AD)); - if (!felix->dsa_8021q_ctx) - return -ENOMEM; + err = dsa_tag_8021q_register(ds, &felix_tag_8021q_ops, + htons(ETH_P_8021AD)); + if (err) + return err; - err = dsa_8021q_setup(felix->dsa_8021q_ctx, true); + err = dsa_8021q_setup(ds, true); if (err) - goto out_free_dsa_8021_ctx; + goto out_tag_8021q_unregister; err = felix_setup_mmio_filtering(felix); if (err) @@ -441,9 +441,9 @@ static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu) return 0; out_teardown_dsa_8021q: - dsa_8021q_setup(felix->dsa_8021q_ctx, false); -out_free_dsa_8021_ctx: - dsa_tag_8021q_unregister(felix->dsa_8021q_ctx); + dsa_8021q_setup(ds, false); +out_tag_8021q_unregister: + dsa_tag_8021q_unregister(ds); return err; } @@ -458,11 +458,11 @@ static void felix_teardown_tag_8021q(struct dsa_switch *ds, int cpu) dev_err(ds->dev, "felix_teardown_mmio_filtering returned %d", err); - err = dsa_8021q_setup(felix->dsa_8021q_ctx, false); + err = dsa_8021q_setup(ds, false); if (err) dev_err(ds->dev, "dsa_8021q_setup returned %d", err); - dsa_tag_8021q_unregister(felix->dsa_8021q_ctx); + dsa_tag_8021q_unregister(ds); for (port = 0; port < ds->num_ports; port++) { if (dsa_is_unused_port(ds, port)) diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 4d96cad815d5..9da3c6a94c6e 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -60,7 +60,6 @@ struct felix { struct lynx_pcs **pcs; resource_size_t switch_base; resource_size_t imdio_base; - struct dsa_8021q_context *dsa_8021q_ctx; enum dsa_tag_protocol tag_proto; }; diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 869b19c08fc0..068be8afd322 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -257,7 +257,6 @@ struct sja1105_private { * the switch doesn't confuse them with one another. */ struct mutex mgmt_lock; - struct dsa_8021q_context *dsa_8021q_ctx; struct devlink_region **regions; struct sja1105_cbs_entry *cbs; struct mii_bus *mdio_base_t1; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 689f46797d1c..ac4254690a8d 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1995,8 +1995,6 @@ static int sja1105_crosschip_bridge_join(struct dsa_switch *ds, int other_port, struct net_device *br) { struct dsa_switch *other_ds = dsa_switch_find(tree_index, sw_index); - struct sja1105_private *other_priv = other_ds->priv; - struct sja1105_private *priv = ds->priv; int port, rc; if (other_ds->ops != &sja1105_switch_ops) @@ -2008,17 +2006,13 @@ static int sja1105_crosschip_bridge_join(struct dsa_switch *ds, if (dsa_to_port(ds, port)->bridge_dev != br) continue; - rc = dsa_8021q_crosschip_bridge_join(priv->dsa_8021q_ctx, - port, - other_priv->dsa_8021q_ctx, + rc = dsa_8021q_crosschip_bridge_join(ds, port, other_ds, other_port); if (rc) return rc; - rc = dsa_8021q_crosschip_bridge_join(other_priv->dsa_8021q_ctx, - other_port, - priv->dsa_8021q_ctx, - port); + rc = dsa_8021q_crosschip_bridge_join(other_ds, other_port, + ds, port); if (rc) return rc; } @@ -2032,8 +2026,6 @@ static void sja1105_crosschip_bridge_leave(struct dsa_switch *ds, struct net_device *br) { struct dsa_switch *other_ds = dsa_switch_find(tree_index, sw_index); - struct sja1105_private *other_priv = other_ds->priv; - struct sja1105_private *priv = ds->priv; int port; if (other_ds->ops != &sja1105_switch_ops) @@ -2045,22 +2037,19 @@ static void sja1105_crosschip_bridge_leave(struct dsa_switch *ds, if (dsa_to_port(ds, port)->bridge_dev != br) continue; - dsa_8021q_crosschip_bridge_leave(priv->dsa_8021q_ctx, port, - other_priv->dsa_8021q_ctx, + dsa_8021q_crosschip_bridge_leave(ds, port, other_ds, other_port); - dsa_8021q_crosschip_bridge_leave(other_priv->dsa_8021q_ctx, - other_port, - priv->dsa_8021q_ctx, port); + dsa_8021q_crosschip_bridge_leave(other_ds, other_port, + ds, port); } } static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled) { - struct sja1105_private *priv = ds->priv; int rc; - rc = dsa_8021q_setup(priv->dsa_8021q_ctx, enabled); + rc = dsa_8021q_setup(ds, enabled); if (rc) return rc; @@ -2233,6 +2222,7 @@ static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify); static int sja1105_notify_crosschip_switches(struct sja1105_private *priv) { + struct dsa_8021q_context *ctx = priv->ds->tag_8021q_ctx; struct sja1105_crosschip_switch *s, *pos; struct list_head crosschip_switches; struct dsa_8021q_crosschip_link *c; @@ -2240,7 +2230,7 @@ static int sja1105_notify_crosschip_switches(struct sja1105_private *priv) INIT_LIST_HEAD(&crosschip_switches); - list_for_each_entry(c, &priv->dsa_8021q_ctx->crosschip_links, list) { + list_for_each_entry(c, &ctx->crosschip_links, list) { bool already_added = false; list_for_each_entry(s, &crosschip_switches, list) { @@ -3306,10 +3296,10 @@ static int sja1105_probe(struct spi_device *spi) mutex_init(&priv->ptp_data.lock); mutex_init(&priv->mgmt_lock); - priv->dsa_8021q_ctx = dsa_tag_8021q_register(ds, &sja1105_dsa_8021q_ops, - htons(ETH_P_8021Q)); - if (!priv->dsa_8021q_ctx) - return -ENOMEM; + rc = dsa_tag_8021q_register(ds, &sja1105_dsa_8021q_ops, + htons(ETH_P_8021Q)); + if (rc) + return rc; INIT_LIST_HEAD(&priv->bridge_vlans); INIT_LIST_HEAD(&priv->dsa_8021q_vlans); @@ -3373,7 +3363,7 @@ out_destroy_workers: out_unregister_switch: dsa_unregister_switch(ds); out_tag_8021q_unregister: - dsa_tag_8021q_unregister(priv->dsa_8021q_ctx); + dsa_tag_8021q_unregister(ds); return rc; } @@ -3384,7 +3374,7 @@ static int sja1105_remove(struct spi_device *spi) struct dsa_switch *ds = priv->ds; dsa_unregister_switch(ds); - dsa_tag_8021q_unregister(priv->dsa_8021q_ctx); + dsa_tag_8021q_unregister(ds); return 0; } diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 9945898a90c3..77939c0c8dd5 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -34,20 +34,20 @@ struct dsa_8021q_context { __be16 proto; }; -struct dsa_8021q_context *dsa_tag_8021q_register(struct dsa_switch *ds, - const struct dsa_8021q_ops *ops, - __be16 proto); +int dsa_tag_8021q_register(struct dsa_switch *ds, + const struct dsa_8021q_ops *ops, + __be16 proto); -void dsa_tag_8021q_unregister(struct dsa_8021q_context *ctx); +void dsa_tag_8021q_unregister(struct dsa_switch *ds); -int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); +int dsa_8021q_setup(struct dsa_switch *ds, bool enabled); -int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, +int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, int other_port); -int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, +int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, int other_port); struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, diff --git a/include/net/dsa.h b/include/net/dsa.h index 33f40c1ec379..e213572f6341 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -352,6 +352,9 @@ struct dsa_switch { unsigned int ageing_time_min; unsigned int ageing_time_max; + /* Storage for drivers using tag_8021q */ + struct dsa_8021q_context *tag_8021q_ctx; + /* devlink used to represent this switch device */ struct devlink *devlink; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 16eb2c7bcc8d..de46a551a486 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -113,10 +113,11 @@ EXPORT_SYMBOL_GPL(vid_is_dsa_8021q); * user explicitly configured this @vid through the bridge core, then the @vid * is installed again, but this time with the flags from the bridge layer. */ -static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid, +static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid, u16 flags, bool enabled) { - struct dsa_port *dp = dsa_to_port(ctx->ds, port); + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_port *dp = dsa_to_port(ds, port); if (enabled) return ctx->ops->vlan_add(ctx->ds, dp->index, vid, flags); @@ -176,29 +177,29 @@ static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid, * +-+-----+-+-----+-+-----+-+-----+-+ +-+-----+-+-----+-+-----+-+-----+-+ * swp0 swp1 swp2 swp3 swp0 swp1 swp2 swp3 */ -static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port, - bool enabled) +static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled) { - int upstream = dsa_upstream_port(ctx->ds, port); - u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port); - u16 tx_vid = dsa_8021q_tx_vid(ctx->ds, port); + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + int upstream = dsa_upstream_port(ds, port); + u16 rx_vid = dsa_8021q_rx_vid(ds, port); + u16 tx_vid = dsa_8021q_tx_vid(ds, port); struct net_device *master; int i, err; /* The CPU port is implicitly configured by * configuring the front-panel ports */ - if (!dsa_is_user_port(ctx->ds, port)) + if (!dsa_is_user_port(ds, port)) return 0; - master = dsa_to_port(ctx->ds, port)->cpu_dp->master; + master = dsa_to_port(ds, port)->cpu_dp->master; /* Add this user port's RX VID to the membership list of all others * (including itself). This is so that bridging will not be hindered. * L2 forwarding rules still take precedence when there are no VLAN * restrictions, so there are no concerns about leaking traffic. */ - for (i = 0; i < ctx->ds->num_ports; i++) { + for (i = 0; i < ds->num_ports; i++) { u16 flags; if (i == upstream) @@ -211,9 +212,9 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port, /* The RX VID is a regular VLAN on all others */ flags = BRIDGE_VLAN_INFO_UNTAGGED; - err = dsa_8021q_vid_apply(ctx, i, rx_vid, flags, enabled); + err = dsa_8021q_vid_apply(ds, i, rx_vid, flags, enabled); if (err) { - dev_err(ctx->ds->dev, + dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %pe\n", rx_vid, port, ERR_PTR(err)); return err; @@ -223,9 +224,9 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port, /* CPU port needs to see this port's RX VID * as tagged egress. */ - err = dsa_8021q_vid_apply(ctx, upstream, rx_vid, 0, enabled); + err = dsa_8021q_vid_apply(ds, upstream, rx_vid, 0, enabled); if (err) { - dev_err(ctx->ds->dev, + dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %pe\n", rx_vid, port, ERR_PTR(err)); return err; @@ -238,17 +239,17 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port, vlan_vid_del(master, ctx->proto, rx_vid); /* Finally apply the TX VID on this port and on the CPU port */ - err = dsa_8021q_vid_apply(ctx, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED, + err = dsa_8021q_vid_apply(ds, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED, enabled); if (err) { - dev_err(ctx->ds->dev, + dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %pe\n", tx_vid, port, ERR_PTR(err)); return err; } - err = dsa_8021q_vid_apply(ctx, upstream, tx_vid, 0, enabled); + err = dsa_8021q_vid_apply(ds, upstream, tx_vid, 0, enabled); if (err) { - dev_err(ctx->ds->dev, + dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %pe\n", tx_vid, upstream, ERR_PTR(err)); return err; @@ -257,16 +258,16 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port, return err; } -int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) +int dsa_8021q_setup(struct dsa_switch *ds, bool enabled) { int err, port; ASSERT_RTNL(); - for (port = 0; port < ctx->ds->num_ports; port++) { - err = dsa_8021q_setup_port(ctx, port, enabled); + for (port = 0; port < ds->num_ports; port++) { + err = dsa_8021q_setup_port(ds, port, enabled); if (err < 0) { - dev_err(ctx->ds->dev, + dev_err(ds->dev, "Failed to setup VLAN tagging for port %d: %pe\n", port, ERR_PTR(err)); return err; @@ -277,24 +278,25 @@ int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) } EXPORT_SYMBOL_GPL(dsa_8021q_setup); -static int dsa_8021q_crosschip_link_apply(struct dsa_8021q_context *ctx, - int port, - struct dsa_8021q_context *other_ctx, +static int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, int other_port, bool enabled) { - u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port); + u16 rx_vid = dsa_8021q_rx_vid(ds, port); /* @rx_vid of local @ds port @port goes to @other_port of * @other_ds */ - return dsa_8021q_vid_apply(other_ctx, other_port, rx_vid, + return dsa_8021q_vid_apply(other_ds, other_port, rx_vid, BRIDGE_VLAN_INFO_UNTAGGED, enabled); } -static int dsa_8021q_crosschip_link_add(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, +static int dsa_8021q_crosschip_link_add(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, int other_port) { + struct dsa_8021q_context *other_ctx = other_ds->tag_8021q_ctx; + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_8021q_crosschip_link *c; list_for_each_entry(c, &ctx->crosschip_links, list) { @@ -305,9 +307,9 @@ static int dsa_8021q_crosschip_link_add(struct dsa_8021q_context *ctx, int port, } } - dev_dbg(ctx->ds->dev, + dev_dbg(ds->dev, "adding crosschip link from port %d to %s port %d\n", - port, dev_name(other_ctx->ds->dev), other_port); + port, dev_name(other_ds->dev), other_port); c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) @@ -323,7 +325,7 @@ static int dsa_8021q_crosschip_link_add(struct dsa_8021q_context *ctx, int port, return 0; } -static void dsa_8021q_crosschip_link_del(struct dsa_8021q_context *ctx, +static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds, struct dsa_8021q_crosschip_link *c, bool *keep) { @@ -332,7 +334,7 @@ static void dsa_8021q_crosschip_link_del(struct dsa_8021q_context *ctx, if (*keep) return; - dev_dbg(ctx->ds->dev, + dev_dbg(ds->dev, "deleting crosschip link from port %d to %s port %d\n", c->port, dev_name(c->other_ctx->ds->dev), c->other_port); @@ -347,8 +349,8 @@ static void dsa_8021q_crosschip_link_del(struct dsa_8021q_context *ctx, * or untagged: it doesn't matter, since it should never egress a frame having * our @rx_vid. */ -int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, +int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, int other_port) { /* @other_upstream is how @other_ds reaches us. If we are part @@ -356,49 +358,50 @@ int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, * our CPU ports. If we're part of the same tree though, we should * probably use dsa_towards_port. */ - int other_upstream = dsa_upstream_port(other_ctx->ds, other_port); + int other_upstream = dsa_upstream_port(other_ds, other_port); int err; - err = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_port); + err = dsa_8021q_crosschip_link_add(ds, port, other_ds, other_port); if (err) return err; - err = dsa_8021q_crosschip_link_apply(ctx, port, other_ctx, + err = dsa_8021q_crosschip_link_apply(ds, port, other_ds, other_port, true); if (err) return err; - err = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_upstream); + err = dsa_8021q_crosschip_link_add(ds, port, other_ds, other_upstream); if (err) return err; - return dsa_8021q_crosschip_link_apply(ctx, port, other_ctx, + return dsa_8021q_crosschip_link_apply(ds, port, other_ds, other_upstream, true); } EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_join); -int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, +int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, int other_port) { - int other_upstream = dsa_upstream_port(other_ctx->ds, other_port); + struct dsa_8021q_context *other_ctx = other_ds->tag_8021q_ctx; + int other_upstream = dsa_upstream_port(other_ds, other_port); + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_8021q_crosschip_link *c, *n; list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) { if (c->port == port && c->other_ctx == other_ctx && (c->other_port == other_port || c->other_port == other_upstream)) { - struct dsa_8021q_context *other_ctx = c->other_ctx; int other_port = c->other_port; bool keep; int err; - dsa_8021q_crosschip_link_del(ctx, c, &keep); + dsa_8021q_crosschip_link_del(ds, c, &keep); if (keep) continue; - err = dsa_8021q_crosschip_link_apply(ctx, port, - other_ctx, + err = dsa_8021q_crosschip_link_apply(ds, port, + other_ds, other_port, false); if (err) @@ -410,15 +413,15 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, } EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_leave); -struct dsa_8021q_context *dsa_tag_8021q_register(struct dsa_switch *ds, - const struct dsa_8021q_ops *ops, - __be16 proto) +int dsa_tag_8021q_register(struct dsa_switch *ds, + const struct dsa_8021q_ops *ops, + __be16 proto) { struct dsa_8021q_context *ctx; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) - return NULL; + return -ENOMEM; ctx->ops = ops; ctx->proto = proto; @@ -426,12 +429,15 @@ struct dsa_8021q_context *dsa_tag_8021q_register(struct dsa_switch *ds, INIT_LIST_HEAD(&ctx->crosschip_links); - return ctx; + ds->tag_8021q_ctx = ctx; + + return 0; } EXPORT_SYMBOL_GPL(dsa_tag_8021q_register); -void dsa_tag_8021q_unregister(struct dsa_8021q_context *ctx) +void dsa_tag_8021q_unregister(struct dsa_switch *ds) { + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_8021q_crosschip_link *c, *n; list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) { @@ -439,6 +445,8 @@ void dsa_tag_8021q_unregister(struct dsa_8021q_context *ctx) kfree(c); } + ds->tag_8021q_ctx = NULL; + kfree(ctx); } EXPORT_SYMBOL_GPL(dsa_tag_8021q_unregister); -- cgit v1.2.3 From 5da11eb407340233a6111c563419e19685a062a4 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:49 +0300 Subject: net: dsa: make tag_8021q operations part of the core Make tag_8021q a more central element of DSA and move the 2 driver specific operations outside of struct dsa_8021q_context (which is supposed to hold dynamic data and not really constant function pointers). Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 10 +++------- drivers/net/dsa/sja1105/sja1105_main.c | 10 +++------- include/linux/dsa/8021q.h | 10 +--------- include/net/dsa.h | 7 +++++++ net/dsa/tag_8021q.c | 10 +++------- 5 files changed, 17 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 9e4ae15aa4fb..b6ab28d2f155 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -231,11 +231,6 @@ static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid) return 0; } -static const struct dsa_8021q_ops felix_tag_8021q_ops = { - .vlan_add = felix_tag_8021q_vlan_add, - .vlan_del = felix_tag_8021q_vlan_del, -}; - /* Alternatively to using the NPI functionality, that same hardware MAC * connected internally to the enetc or fman DSA master can be configured to * use the software-defined tag_8021q frame format. As far as the hardware is @@ -425,8 +420,7 @@ static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu) ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_MC); ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_BC); - err = dsa_tag_8021q_register(ds, &felix_tag_8021q_ops, - htons(ETH_P_8021AD)); + err = dsa_tag_8021q_register(ds, htons(ETH_P_8021AD)); if (err) return err; @@ -1675,6 +1669,8 @@ const struct dsa_switch_ops felix_switch_ops = { .port_mrp_del = felix_mrp_del, .port_mrp_add_ring_role = felix_mrp_add_ring_role, .port_mrp_del_ring_role = felix_mrp_del_ring_role, + .tag_8021q_vlan_add = felix_tag_8021q_vlan_add, + .tag_8021q_vlan_del = felix_tag_8021q_vlan_del, }; struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index ac4254690a8d..0c04f6caccdf 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2543,11 +2543,6 @@ static int sja1105_dsa_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid) return sja1105_build_vlan_table(priv, true); } -static const struct dsa_8021q_ops sja1105_dsa_8021q_ops = { - .vlan_add = sja1105_dsa_8021q_vlan_add, - .vlan_del = sja1105_dsa_8021q_vlan_del, -}; - /* The programming model for the SJA1105 switch is "all-at-once" via static * configuration tables. Some of these can be dynamically modified at runtime, * but not the xMII mode parameters table. @@ -3153,6 +3148,8 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .crosschip_bridge_join = sja1105_crosschip_bridge_join, .crosschip_bridge_leave = sja1105_crosschip_bridge_leave, .devlink_info_get = sja1105_devlink_info_get, + .tag_8021q_vlan_add = sja1105_dsa_8021q_vlan_add, + .tag_8021q_vlan_del = sja1105_dsa_8021q_vlan_del, }; static const struct of_device_id sja1105_dt_ids[]; @@ -3296,8 +3293,7 @@ static int sja1105_probe(struct spi_device *spi) mutex_init(&priv->ptp_data.lock); mutex_init(&priv->mgmt_lock); - rc = dsa_tag_8021q_register(ds, &sja1105_dsa_8021q_ops, - htons(ETH_P_8021Q)); + rc = dsa_tag_8021q_register(ds, htons(ETH_P_8021Q)); if (rc) return rc; diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 77939c0c8dd5..0bda08fb2f16 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -21,22 +21,14 @@ struct dsa_8021q_crosschip_link { refcount_t refcount; }; -struct dsa_8021q_ops { - int (*vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); - int (*vlan_del)(struct dsa_switch *ds, int port, u16 vid); -}; - struct dsa_8021q_context { - const struct dsa_8021q_ops *ops; struct dsa_switch *ds; struct list_head crosschip_links; /* EtherType of RX VID, used for filtering on master interface */ __be16 proto; }; -int dsa_tag_8021q_register(struct dsa_switch *ds, - const struct dsa_8021q_ops *ops, - __be16 proto); +int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); diff --git a/include/net/dsa.h b/include/net/dsa.h index e213572f6341..9e5593885357 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -872,6 +872,13 @@ struct dsa_switch_ops { const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); + + /* + * tag_8021q operations + */ + int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, + u16 flags); + int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index de46a551a486..4a11c5004783 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -116,13 +116,12 @@ EXPORT_SYMBOL_GPL(vid_is_dsa_8021q); static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid, u16 flags, bool enabled) { - struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_port *dp = dsa_to_port(ds, port); if (enabled) - return ctx->ops->vlan_add(ctx->ds, dp->index, vid, flags); + return ds->ops->tag_8021q_vlan_add(ds, dp->index, vid, flags); - return ctx->ops->vlan_del(ctx->ds, dp->index, vid); + return ds->ops->tag_8021q_vlan_del(ds, dp->index, vid); } /* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single @@ -413,9 +412,7 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, } EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_leave); -int dsa_tag_8021q_register(struct dsa_switch *ds, - const struct dsa_8021q_ops *ops, - __be16 proto) +int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto) { struct dsa_8021q_context *ctx; @@ -423,7 +420,6 @@ int dsa_tag_8021q_register(struct dsa_switch *ds, if (!ctx) return -ENOMEM; - ctx->ops = ops; ctx->proto = proto; ctx->ds = ds; -- cgit v1.2.3 From 328621f6131f667c5c328bb72d45442fd76efb81 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:50 +0300 Subject: net: dsa: tag_8021q: absorb dsa_8021q_setup into dsa_tag_8021q_{,un}register Right now, setting up tag_8021q is a 2-step operation for a driver, first the context structure needs to be created, then the VLANs need to be installed on the ports. A similar thing is true for teardown. Merge the 2 steps into the register/unregister methods, to be as transparent as possible for the driver as to what tag_8021q does behind the scenes. This also gets rid of the funny "bool setup == true means setup, == false means teardown" API that tag_8021q used to expose. Note that dsa_tag_8021q_register() must be called at least in the .setup() driver method and never earlier (like in the driver probe function). This is because the DSA switch tree is not initialized at probe time, and the cross-chip notifiers will not work. For symmetry with .setup(), the unregister method should be put in .teardown(). Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 12 +----------- drivers/net/dsa/sja1105/sja1105_main.c | 32 ++++++-------------------------- include/linux/dsa/8021q.h | 2 -- net/dsa/tag_8021q.c | 11 ++++++++--- 4 files changed, 15 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index b6ab28d2f155..583a22d901b3 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -424,18 +424,12 @@ static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu) if (err) return err; - err = dsa_8021q_setup(ds, true); - if (err) - goto out_tag_8021q_unregister; - err = felix_setup_mmio_filtering(felix); if (err) - goto out_teardown_dsa_8021q; + goto out_tag_8021q_unregister; return 0; -out_teardown_dsa_8021q: - dsa_8021q_setup(ds, false); out_tag_8021q_unregister: dsa_tag_8021q_unregister(ds); return err; @@ -452,10 +446,6 @@ static void felix_teardown_tag_8021q(struct dsa_switch *ds, int cpu) dev_err(ds->dev, "felix_teardown_mmio_filtering returned %d", err); - err = dsa_8021q_setup(ds, false); - if (err) - dev_err(ds->dev, "dsa_8021q_setup returned %d", err); - dsa_tag_8021q_unregister(ds); for (port = 0; port < ds->num_ports; port++) { diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 0c04f6caccdf..6b56c1ada3ee 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2045,19 +2045,6 @@ static void sja1105_crosschip_bridge_leave(struct dsa_switch *ds, } } -static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled) -{ - int rc; - - rc = dsa_8021q_setup(ds, enabled); - if (rc) - return rc; - - dev_info(ds->dev, "%s switch tagging\n", - enabled ? "Enabled" : "Disabled"); - return 0; -} - static enum dsa_tag_protocol sja1105_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) @@ -2635,12 +2622,8 @@ static int sja1105_setup(struct dsa_switch *ds) if (rc < 0) goto out_static_config_free; - /* The DSA/switchdev model brings up switch ports in standalone mode by - * default, and that means vlan_filtering is 0 since they're not under - * a bridge, so it's safe to set up switch tagging at this time. - */ rtnl_lock(); - rc = sja1105_setup_8021q_tagging(ds, true); + rc = dsa_tag_8021q_register(ds, htons(ETH_P_8021Q)); rtnl_unlock(); if (rc) goto out_devlink_teardown; @@ -2665,6 +2648,10 @@ static void sja1105_teardown(struct dsa_switch *ds) struct sja1105_bridge_vlan *v, *n; int port; + rtnl_lock(); + dsa_tag_8021q_unregister(ds); + rtnl_unlock(); + for (port = 0; port < ds->num_ports; port++) { struct sja1105_port *sp = &priv->ports[port]; @@ -3293,10 +3280,6 @@ static int sja1105_probe(struct spi_device *spi) mutex_init(&priv->ptp_data.lock); mutex_init(&priv->mgmt_lock); - rc = dsa_tag_8021q_register(ds, htons(ETH_P_8021Q)); - if (rc) - return rc; - INIT_LIST_HEAD(&priv->bridge_vlans); INIT_LIST_HEAD(&priv->dsa_8021q_vlans); @@ -3305,7 +3288,7 @@ static int sja1105_probe(struct spi_device *spi) rc = dsa_register_switch(priv->ds); if (rc) - goto out_tag_8021q_unregister; + return rc; if (IS_ENABLED(CONFIG_NET_SCH_CBS)) { priv->cbs = devm_kcalloc(dev, priv->info->num_cbs_shapers, @@ -3358,8 +3341,6 @@ out_destroy_workers: out_unregister_switch: dsa_unregister_switch(ds); -out_tag_8021q_unregister: - dsa_tag_8021q_unregister(ds); return rc; } @@ -3370,7 +3351,6 @@ static int sja1105_remove(struct spi_device *spi) struct dsa_switch *ds = priv->ds; dsa_unregister_switch(ds); - dsa_tag_8021q_unregister(ds); return 0; } diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 0bda08fb2f16..9cf2c99eb668 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -32,8 +32,6 @@ int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); -int dsa_8021q_setup(struct dsa_switch *ds, bool enabled); - int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, int other_port); diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 4a11c5004783..9785c8497039 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -257,7 +257,7 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled) return err; } -int dsa_8021q_setup(struct dsa_switch *ds, bool enabled) +static int dsa_8021q_setup(struct dsa_switch *ds, bool enabled) { int err, port; @@ -275,7 +275,6 @@ int dsa_8021q_setup(struct dsa_switch *ds, bool enabled) return 0; } -EXPORT_SYMBOL_GPL(dsa_8021q_setup); static int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, @@ -427,7 +426,7 @@ int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto) ds->tag_8021q_ctx = ctx; - return 0; + return dsa_8021q_setup(ds, true); } EXPORT_SYMBOL_GPL(dsa_tag_8021q_register); @@ -435,6 +434,12 @@ void dsa_tag_8021q_unregister(struct dsa_switch *ds) { struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_8021q_crosschip_link *c, *n; + int err; + + err = dsa_8021q_setup(ds, false); + if (err) + dev_err(ds->dev, "failed to tear down tag_8021q VLANs: %pe\n", + ERR_PTR(err)); list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) { list_del(&c->list); -- cgit v1.2.3 From c64b9c05045a21a5258f6dbd81d94a2a22ff73a2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:52 +0300 Subject: net: dsa: tag_8021q: add proper cross-chip notifier support The big problem which mandates cross-chip notifiers for tag_8021q is this: | sw0p0 sw0p1 sw0p2 sw0p3 sw0p4 [ user ] [ user ] [ user ] [ dsa ] [ cpu ] | +---------+ | sw1p0 sw1p1 sw1p2 sw1p3 sw1p4 [ user ] [ user ] [ user ] [ dsa ] [ dsa ] | +---------+ | sw2p0 sw2p1 sw2p2 sw2p3 sw2p4 [ user ] [ user ] [ user ] [ dsa ] [ dsa ] When the user runs: ip link add br0 type bridge ip link set sw0p0 master br0 ip link set sw2p0 master br0 It doesn't work. This is because dsa_8021q_crosschip_bridge_join() assumes that "ds" and "other_ds" are at most 1 hop away from each other, so it is sufficient to add the RX VLAN of {ds, port} into {other_ds, other_port} and vice versa and presto, the cross-chip link works. When there is another switch in the middle, such as in this case switch 1 with its DSA links sw1p3 and sw1p4, somebody needs to tell it about these VLANs too. Which is exactly why the problem is quadratic: when a port joins a bridge, for each port in the tree that's already in that same bridge we notify a tag_8021q VLAN addition of that port's RX VLAN to the entire tree. It is a very complicated web of VLANs. It must be mentioned that currently we install tag_8021q VLANs on too many ports (DSA links - to be precise, on all of them). For example, when sw2p0 joins br0, and assuming sw1p0 was part of br0 too, we add the RX VLAN of sw2p0 on the DSA links of switch 0 too, even though there isn't any port of switch 0 that is a member of br0 (at least yet). In theory we could notify only the switches which sit in between the port joining the bridge and the port reacting to that bridge_join event. But in practice that is impossible, because of the way 'link' properties are described in the device tree. The DSA bindings require DT writers to list out not only the real/physical DSA links, but in fact the entire routing table, like for example switch 0 above will have: sw0p3: port@3 { link = <&sw1p4 &sw2p4>; }; This was done because: /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ but it is a perfect example of a situation where too much information is actively detrimential, because we are now in the position where we cannot distinguish a real DSA link from one that is put there to avoid the 'complex tree walking'. And because DT is ABI, there is not much we can change. And because we do not know which DSA links are real and which ones aren't, we can't really know if DSA switch A is in the data path between switches B and C, in the general case. So this is why tag_8021q RX VLANs are added on all DSA links, and probably why it will never change. On the other hand, at least the number of additions/deletions is well balanced, and this means that once we implement reference counting at the cross-chip notifier level a la fdb/mdb, there is absolutely zero need for a struct dsa_8021q_crosschip_link, it's all self-managing. In fact, with the tag_8021q notifiers emitted from the bridge join notifiers, it becomes so generic that sja1105 does not need to do anything anymore, we can just delete its implementation of the .crosschip_bridge_{join,leave} methods. Among other things we can simply delete is the home-grown implementation of sja1105_notify_crosschip_switches(). The reason why that is wrong is because it is not quadratic - it only covers remote switches to which we have a cross-chip bridging link and that does not cover in-between switches. This deletion is part of the same patch because sja1105 used to poke deep inside the guts of the tag_8021q context in order to do that. Because the cross-chip links went away, so needs the sja1105 code. Last but not least, dsa_8021q_setup_port() is simplified (and also renamed). Because our TAG_8021Q_VLAN_ADD notifier is designed to react on the CPU port too, the four dsa_8021q_vid_apply() calls: - 1 for RX VLAN on user port - 1 for the user port's RX VLAN on the CPU port - 1 for TX VLAN on user port - 1 for the user port's TX VLAN on the CPU port now get squashed into only 2 notifier calls via dsa_port_tag_8021q_vlan_add. And because the notifiers to add and to delete a tag_8021q VLAN are distinct, now we finally break up the port setup and teardown into separate functions instead of relying on a "bool enabled" flag which tells us what to do. Arguably it should have been this way from the get go. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 132 +---------- include/linux/dsa/8021q.h | 16 +- net/dsa/dsa_priv.h | 16 ++ net/dsa/port.c | 28 +++ net/dsa/switch.c | 6 + net/dsa/tag_8021q.c | 398 ++++++++++++++++----------------- 6 files changed, 256 insertions(+), 340 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 6b56c1ada3ee..6618abba23b3 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1990,61 +1990,6 @@ static int sja1105_pvid_apply(struct sja1105_private *priv, int port, u16 pvid) &mac[port], true); } -static int sja1105_crosschip_bridge_join(struct dsa_switch *ds, - int tree_index, int sw_index, - int other_port, struct net_device *br) -{ - struct dsa_switch *other_ds = dsa_switch_find(tree_index, sw_index); - int port, rc; - - if (other_ds->ops != &sja1105_switch_ops) - return 0; - - for (port = 0; port < ds->num_ports; port++) { - if (!dsa_is_user_port(ds, port)) - continue; - if (dsa_to_port(ds, port)->bridge_dev != br) - continue; - - rc = dsa_8021q_crosschip_bridge_join(ds, port, other_ds, - other_port); - if (rc) - return rc; - - rc = dsa_8021q_crosschip_bridge_join(other_ds, other_port, - ds, port); - if (rc) - return rc; - } - - return 0; -} - -static void sja1105_crosschip_bridge_leave(struct dsa_switch *ds, - int tree_index, int sw_index, - int other_port, - struct net_device *br) -{ - struct dsa_switch *other_ds = dsa_switch_find(tree_index, sw_index); - int port; - - if (other_ds->ops != &sja1105_switch_ops) - return; - - for (port = 0; port < ds->num_ports; port++) { - if (!dsa_is_user_port(ds, port)) - continue; - if (dsa_to_port(ds, port)->bridge_dev != br) - continue; - - dsa_8021q_crosschip_bridge_leave(ds, port, other_ds, - other_port); - - dsa_8021q_crosschip_bridge_leave(other_ds, other_port, - ds, port); - } -} - static enum dsa_tag_protocol sja1105_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) @@ -2135,11 +2080,6 @@ static int sja1105_commit_vlans(struct sja1105_private *priv, return 0; } -struct sja1105_crosschip_switch { - struct list_head list; - struct dsa_8021q_context *other_ctx; -}; - static int sja1105_commit_pvid(struct sja1105_private *priv) { struct sja1105_bridge_vlan *v; @@ -2205,59 +2145,7 @@ sja1105_build_dsa_8021q_vlans(struct sja1105_private *priv, return 0; } -static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify); - -static int sja1105_notify_crosschip_switches(struct sja1105_private *priv) -{ - struct dsa_8021q_context *ctx = priv->ds->tag_8021q_ctx; - struct sja1105_crosschip_switch *s, *pos; - struct list_head crosschip_switches; - struct dsa_8021q_crosschip_link *c; - int rc = 0; - - INIT_LIST_HEAD(&crosschip_switches); - - list_for_each_entry(c, &ctx->crosschip_links, list) { - bool already_added = false; - - list_for_each_entry(s, &crosschip_switches, list) { - if (s->other_ctx == c->other_ctx) { - already_added = true; - break; - } - } - - if (already_added) - continue; - - s = kzalloc(sizeof(*s), GFP_KERNEL); - if (!s) { - dev_err(priv->ds->dev, "Failed to allocate memory\n"); - rc = -ENOMEM; - goto out; - } - s->other_ctx = c->other_ctx; - list_add(&s->list, &crosschip_switches); - } - - list_for_each_entry(s, &crosschip_switches, list) { - struct sja1105_private *other_priv = s->other_ctx->ds->priv; - - rc = sja1105_build_vlan_table(other_priv, false); - if (rc) - goto out; - } - -out: - list_for_each_entry_safe(s, pos, &crosschip_switches, list) { - list_del(&s->list); - kfree(s); - } - - return rc; -} - -static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify) +static int sja1105_build_vlan_table(struct sja1105_private *priv) { struct sja1105_vlan_lookup_entry *new_vlan; struct sja1105_table *table; @@ -2296,12 +2184,6 @@ static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify) if (rc) goto out; - if (notify) { - rc = sja1105_notify_crosschip_switches(priv); - if (rc) - goto out; - } - out: kfree(new_vlan); @@ -2389,7 +2271,7 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, l2_lookup_params = table->entries; l2_lookup_params->shared_learn = !priv->vlan_aware; - rc = sja1105_build_vlan_table(priv, false); + rc = sja1105_build_vlan_table(priv); if (rc) return rc; @@ -2485,7 +2367,7 @@ static int sja1105_vlan_add(struct dsa_switch *ds, int port, if (!vlan_table_changed) return 0; - return sja1105_build_vlan_table(priv, true); + return sja1105_build_vlan_table(priv); } static int sja1105_vlan_del(struct dsa_switch *ds, int port, @@ -2502,7 +2384,7 @@ static int sja1105_vlan_del(struct dsa_switch *ds, int port, if (!vlan_table_changed) return 0; - return sja1105_build_vlan_table(priv, true); + return sja1105_build_vlan_table(priv); } static int sja1105_dsa_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, @@ -2515,7 +2397,7 @@ static int sja1105_dsa_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, if (rc <= 0) return rc; - return sja1105_build_vlan_table(priv, true); + return sja1105_build_vlan_table(priv); } static int sja1105_dsa_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid) @@ -2527,7 +2409,7 @@ static int sja1105_dsa_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid) if (!rc) return 0; - return sja1105_build_vlan_table(priv, true); + return sja1105_build_vlan_table(priv); } /* The programming model for the SJA1105 switch is "all-at-once" via static @@ -3132,8 +3014,6 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .cls_flower_add = sja1105_cls_flower_add, .cls_flower_del = sja1105_cls_flower_del, .cls_flower_stats = sja1105_cls_flower_stats, - .crosschip_bridge_join = sja1105_crosschip_bridge_join, - .crosschip_bridge_leave = sja1105_crosschip_bridge_leave, .devlink_info_get = sja1105_devlink_info_get, .tag_8021q_vlan_add = sja1105_dsa_8021q_vlan_add, .tag_8021q_vlan_del = sja1105_dsa_8021q_vlan_del, diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 9cf2c99eb668..ec5abfcdefd1 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -11,19 +11,17 @@ struct dsa_switch; struct sk_buff; struct net_device; -struct dsa_8021q_context; -struct dsa_8021q_crosschip_link { +struct dsa_tag_8021q_vlan { struct list_head list; int port; - struct dsa_8021q_context *other_ctx; - int other_port; + u16 vid; refcount_t refcount; }; struct dsa_8021q_context { struct dsa_switch *ds; - struct list_head crosschip_links; + struct list_head vlans; /* EtherType of RX VID, used for filtering on master interface */ __be16 proto; }; @@ -32,14 +30,6 @@ int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); -int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port); - -int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port); - struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 28c4d1107b6d..efd6bca78d2f 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -39,6 +39,8 @@ enum { DSA_NOTIFIER_MRP_DEL, DSA_NOTIFIER_MRP_ADD_RING_ROLE, DSA_NOTIFIER_MRP_DEL_RING_ROLE, + DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, + DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, }; /* DSA_NOTIFIER_AGEING_TIME */ @@ -113,6 +115,14 @@ struct dsa_notifier_mrp_ring_role_info { int port; }; +/* DSA_NOTIFIER_TAG_8021Q_VLAN_* */ +struct dsa_notifier_tag_8021q_vlan_info { + int tree_index; + int sw_index; + int port; + u16 vid; +}; + struct dsa_switchdev_event_work { struct dsa_switch *ds; int port; @@ -253,6 +263,8 @@ int dsa_port_link_register_of(struct dsa_port *dp); void dsa_port_link_unregister_of(struct dsa_port *dp); int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr); void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); +int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid); +void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid); extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, @@ -391,6 +403,10 @@ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, struct dsa_notifier_bridge_info *info); int dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, struct dsa_notifier_bridge_info *info); +int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info); +int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info); extern struct list_head dsa_tree_list; diff --git a/net/dsa/port.c b/net/dsa/port.c index 28b45b7e66df..982e18771d76 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1217,3 +1217,31 @@ void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr) if (err) pr_err("DSA: failed to notify DSA_NOTIFIER_HSR_LEAVE\n"); } + +int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid) +{ + struct dsa_notifier_tag_8021q_vlan_info info = { + .tree_index = dp->ds->dst->index, + .sw_index = dp->ds->index, + .port = dp->index, + .vid = vid, + }; + + return dsa_broadcast(DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, &info); +} + +void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid) +{ + struct dsa_notifier_tag_8021q_vlan_info info = { + .tree_index = dp->ds->dst->index, + .sw_index = dp->ds->index, + .port = dp->index, + .vid = vid, + }; + int err; + + err = dsa_broadcast(DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, &info); + if (err) + pr_err("DSA: failed to notify tag_8021q VLAN deletion: %pe\n", + ERR_PTR(err)); +} diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 38560de99b80..fd1a1c6bf9cf 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -734,6 +734,12 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_MRP_DEL_RING_ROLE: err = dsa_switch_mrp_del_ring_role(ds, info); break; + case DSA_NOTIFIER_TAG_8021Q_VLAN_ADD: + err = dsa_switch_tag_8021q_vlan_add(ds, info); + break; + case DSA_NOTIFIER_TAG_8021Q_VLAN_DEL: + err = dsa_switch_tag_8021q_vlan_del(ds, info); + break; default: err = -EOPNOTSUPP; break; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 0946169033a5..51dcde7db26b 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -107,21 +107,152 @@ bool vid_is_dsa_8021q(u16 vid) } EXPORT_SYMBOL_GPL(vid_is_dsa_8021q); -/* If @enabled is true, installs @vid with @flags into the switch port's HW - * filter. - * If @enabled is false, deletes @vid (ignores @flags) from the port. Had the - * user explicitly configured this @vid through the bridge core, then the @vid - * is installed again, but this time with the flags from the bridge layer. - */ -static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid, - u16 flags, bool enabled) +static struct dsa_tag_8021q_vlan * +dsa_tag_8021q_vlan_find(struct dsa_8021q_context *ctx, int port, u16 vid) +{ + struct dsa_tag_8021q_vlan *v; + + list_for_each_entry(v, &ctx->vlans, list) + if (v->vid == vid && v->port == port) + return v; + + return NULL; +} + +static int dsa_switch_do_tag_8021q_vlan_add(struct dsa_switch *ds, int port, + u16 vid, u16 flags) { + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_tag_8021q_vlan *v; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->tag_8021q_vlan_add(ds, port, vid, flags); + + v = dsa_tag_8021q_vlan_find(ctx, port, vid); + if (v) { + refcount_inc(&v->refcount); + return 0; + } + + v = kzalloc(sizeof(*v), GFP_KERNEL); + if (!v) + return -ENOMEM; + + err = ds->ops->tag_8021q_vlan_add(ds, port, vid, flags); + if (err) { + kfree(v); + return err; + } + + v->vid = vid; + v->port = port; + refcount_set(&v->refcount, 1); + list_add_tail(&v->list, &ctx->vlans); + + return 0; +} + +static int dsa_switch_do_tag_8021q_vlan_del(struct dsa_switch *ds, int port, + u16 vid) +{ + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_tag_8021q_vlan *v; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->tag_8021q_vlan_del(ds, port, vid); + + v = dsa_tag_8021q_vlan_find(ctx, port, vid); + if (!v) + return -ENOENT; + + if (!refcount_dec_and_test(&v->refcount)) + return 0; + + err = ds->ops->tag_8021q_vlan_del(ds, port, vid); + if (err) { + refcount_inc(&v->refcount); + return err; + } + + list_del(&v->list); + kfree(v); + + return 0; +} - if (enabled) - return ds->ops->tag_8021q_vlan_add(ds, dp->index, vid, flags); +static bool +dsa_switch_tag_8021q_vlan_match(struct dsa_switch *ds, int port, + struct dsa_notifier_tag_8021q_vlan_info *info) +{ + if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) + return true; + + if (ds->dst->index == info->tree_index && ds->index == info->sw_index) + return port == info->port; + + return false; +} + +int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info) +{ + int port, err; + + /* Since we use dsa_broadcast(), there might be other switches in other + * trees which don't support tag_8021q, so don't return an error. + * Or they might even support tag_8021q but have not registered yet to + * use it (maybe they use another tagger currently). + */ + if (!ds->ops->tag_8021q_vlan_add || !ds->tag_8021q_ctx) + return 0; - return ds->ops->tag_8021q_vlan_del(ds, dp->index, vid); + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_tag_8021q_vlan_match(ds, port, info)) { + u16 flags = 0; + + if (dsa_is_user_port(ds, port)) + flags |= BRIDGE_VLAN_INFO_UNTAGGED; + + if (vid_is_dsa_8021q_rxvlan(info->vid) && + dsa_8021q_rx_switch_id(info->vid) == ds->index && + dsa_8021q_rx_source_port(info->vid) == port) + flags |= BRIDGE_VLAN_INFO_PVID; + + err = dsa_switch_do_tag_8021q_vlan_add(ds, port, + info->vid, + flags); + if (err) + return err; + } + } + + return 0; +} + +int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info) +{ + int port, err; + + if (!ds->ops->tag_8021q_vlan_del || !ds->tag_8021q_ctx) + return 0; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_tag_8021q_vlan_match(ds, port, info)) { + err = dsa_switch_do_tag_8021q_vlan_del(ds, port, + info->vid); + if (err) + return err; + } + } + + return 0; } /* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single @@ -192,6 +323,7 @@ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, struct dsa_notifier_bridge_info *info) { struct dsa_switch *targeted_ds; + struct dsa_port *targeted_dp; u16 targeted_rx_vid; int err, port; @@ -199,23 +331,23 @@ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, return 0; targeted_ds = dsa_switch_find(info->tree_index, info->sw_index); + targeted_dp = dsa_to_port(targeted_ds, info->port); targeted_rx_vid = dsa_8021q_rx_vid(targeted_ds, info->port); for (port = 0; port < ds->num_ports; port++) { + struct dsa_port *dp = dsa_to_port(ds, port); u16 rx_vid = dsa_8021q_rx_vid(ds, port); if (!dsa_tag_8021q_bridge_match(ds, port, info)) continue; /* Install the RX VID of the targeted port in our VLAN table */ - err = dsa_8021q_vid_apply(ds, port, targeted_rx_vid, - BRIDGE_VLAN_INFO_UNTAGGED, true); + err = dsa_port_tag_8021q_vlan_add(dp, targeted_rx_vid); if (err) return err; /* Install our RX VID into the targeted port's VLAN table */ - err = dsa_8021q_vid_apply(targeted_ds, info->port, rx_vid, - BRIDGE_VLAN_INFO_UNTAGGED, true); + err = dsa_port_tag_8021q_vlan_add(targeted_dp, rx_vid); if (err) return err; } @@ -227,46 +359,39 @@ int dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, struct dsa_notifier_bridge_info *info) { struct dsa_switch *targeted_ds; + struct dsa_port *targeted_dp; u16 targeted_rx_vid; - int err, port; + int port; if (!ds->tag_8021q_ctx) return 0; targeted_ds = dsa_switch_find(info->tree_index, info->sw_index); + targeted_dp = dsa_to_port(targeted_ds, info->port); targeted_rx_vid = dsa_8021q_rx_vid(targeted_ds, info->port); for (port = 0; port < ds->num_ports; port++) { + struct dsa_port *dp = dsa_to_port(ds, port); u16 rx_vid = dsa_8021q_rx_vid(ds, port); if (!dsa_tag_8021q_bridge_match(ds, port, info)) continue; /* Remove the RX VID of the targeted port from our VLAN table */ - err = dsa_8021q_vid_apply(ds, port, targeted_rx_vid, - BRIDGE_VLAN_INFO_UNTAGGED, false); - if (err) - dev_err(ds->dev, - "port %d failed to delete tag_8021q VLAN: %pe\n", - port, ERR_PTR(err)); + dsa_port_tag_8021q_vlan_del(dp, targeted_rx_vid); /* Remove our RX VID from the targeted port's VLAN table */ - err = dsa_8021q_vid_apply(targeted_ds, info->port, rx_vid, - BRIDGE_VLAN_INFO_UNTAGGED, false); - if (err) - dev_err(targeted_ds->dev, - "port %d failed to delete tag_8021q VLAN: %pe\n", - info->port, ERR_PTR(err)); + dsa_port_tag_8021q_vlan_del(targeted_dp, rx_vid); } return 0; } /* Set up a port's tag_8021q RX and TX VLAN for standalone mode operation */ -static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled) +static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) { struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; - int upstream = dsa_upstream_port(ds, port); + struct dsa_port *dp = dsa_to_port(ds, port); u16 rx_vid = dsa_8021q_rx_vid(ds, port); u16 tx_vid = dsa_8021q_tx_vid(ds, port); struct net_device *master; @@ -275,29 +400,17 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled) /* The CPU port is implicitly configured by * configuring the front-panel ports */ - if (!dsa_is_user_port(ds, port)) + if (!dsa_port_is_user(dp)) return 0; - master = dsa_to_port(ds, port)->cpu_dp->master; + master = dp->cpu_dp->master; /* Add this user port's RX VID to the membership list of all others * (including itself). This is so that bridging will not be hindered. * L2 forwarding rules still take precedence when there are no VLAN * restrictions, so there are no concerns about leaking traffic. */ - err = dsa_8021q_vid_apply(ds, port, rx_vid, BRIDGE_VLAN_INFO_UNTAGGED | - BRIDGE_VLAN_INFO_PVID, enabled); - if (err) { - dev_err(ds->dev, - "Failed to apply RX VID %d to port %d: %pe\n", - rx_vid, port, ERR_PTR(err)); - return err; - } - - /* CPU port needs to see this port's RX VID - * as tagged egress. - */ - err = dsa_8021q_vid_apply(ds, upstream, rx_vid, 0, enabled); + err = dsa_port_tag_8021q_vlan_add(dp, rx_vid); if (err) { dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %pe\n", @@ -306,39 +419,51 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled) } /* Add @rx_vid to the master's RX filter. */ - if (enabled) - vlan_vid_add(master, ctx->proto, rx_vid); - else - vlan_vid_del(master, ctx->proto, rx_vid); + vlan_vid_add(master, ctx->proto, rx_vid); /* Finally apply the TX VID on this port and on the CPU port */ - err = dsa_8021q_vid_apply(ds, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED, - enabled); + err = dsa_port_tag_8021q_vlan_add(dp, tx_vid); if (err) { dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %pe\n", tx_vid, port, ERR_PTR(err)); return err; } - err = dsa_8021q_vid_apply(ds, upstream, tx_vid, 0, enabled); - if (err) { - dev_err(ds->dev, - "Failed to apply TX VID %d on port %d: %pe\n", - tx_vid, upstream, ERR_PTR(err)); - return err; - } return err; } -static int dsa_8021q_setup(struct dsa_switch *ds, bool enabled) +static void dsa_tag_8021q_port_teardown(struct dsa_switch *ds, int port) +{ + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_port *dp = dsa_to_port(ds, port); + u16 rx_vid = dsa_8021q_rx_vid(ds, port); + u16 tx_vid = dsa_8021q_tx_vid(ds, port); + struct net_device *master; + + /* The CPU port is implicitly configured by + * configuring the front-panel ports + */ + if (!dsa_port_is_user(dp)) + return; + + master = dp->cpu_dp->master; + + dsa_port_tag_8021q_vlan_del(dp, rx_vid); + + vlan_vid_del(master, ctx->proto, rx_vid); + + dsa_port_tag_8021q_vlan_del(dp, tx_vid); +} + +static int dsa_tag_8021q_setup(struct dsa_switch *ds) { int err, port; ASSERT_RTNL(); for (port = 0; port < ds->num_ports; port++) { - err = dsa_8021q_setup_port(ds, port, enabled); + err = dsa_tag_8021q_port_setup(ds, port); if (err < 0) { dev_err(ds->dev, "Failed to setup VLAN tagging for port %d: %pe\n", @@ -350,140 +475,15 @@ static int dsa_8021q_setup(struct dsa_switch *ds, bool enabled) return 0; } -static int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, bool enabled) +static void dsa_tag_8021q_teardown(struct dsa_switch *ds) { - u16 rx_vid = dsa_8021q_rx_vid(ds, port); + int port; - /* @rx_vid of local @ds port @port goes to @other_port of - * @other_ds - */ - return dsa_8021q_vid_apply(other_ds, other_port, rx_vid, - BRIDGE_VLAN_INFO_UNTAGGED, enabled); -} - -static int dsa_8021q_crosschip_link_add(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port) -{ - struct dsa_8021q_context *other_ctx = other_ds->tag_8021q_ctx; - struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; - struct dsa_8021q_crosschip_link *c; - - list_for_each_entry(c, &ctx->crosschip_links, list) { - if (c->port == port && c->other_ctx == other_ctx && - c->other_port == other_port) { - refcount_inc(&c->refcount); - return 0; - } - } - - dev_dbg(ds->dev, - "adding crosschip link from port %d to %s port %d\n", - port, dev_name(other_ds->dev), other_port); - - c = kzalloc(sizeof(*c), GFP_KERNEL); - if (!c) - return -ENOMEM; - - c->port = port; - c->other_ctx = other_ctx; - c->other_port = other_port; - refcount_set(&c->refcount, 1); - - list_add(&c->list, &ctx->crosschip_links); - - return 0; -} - -static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds, - struct dsa_8021q_crosschip_link *c, - bool *keep) -{ - *keep = !refcount_dec_and_test(&c->refcount); - - if (*keep) - return; - - dev_dbg(ds->dev, - "deleting crosschip link from port %d to %s port %d\n", - c->port, dev_name(c->other_ctx->ds->dev), c->other_port); - - list_del(&c->list); - kfree(c); -} - -/* Make traffic from local port @port be received by remote port @other_port. - * This means that our @rx_vid needs to be installed on @other_ds's upstream - * and user ports. The user ports should be egress-untagged so that they can - * pop the dsa_8021q VLAN. But the @other_upstream can be either egress-tagged - * or untagged: it doesn't matter, since it should never egress a frame having - * our @rx_vid. - */ -int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port) -{ - /* @other_upstream is how @other_ds reaches us. If we are part - * of disjoint trees, then we are probably connected through - * our CPU ports. If we're part of the same tree though, we should - * probably use dsa_towards_port. - */ - int other_upstream = dsa_upstream_port(other_ds, other_port); - int err; - - err = dsa_8021q_crosschip_link_add(ds, port, other_ds, other_port); - if (err) - return err; - - err = dsa_8021q_crosschip_link_apply(ds, port, other_ds, - other_port, true); - if (err) - return err; - - err = dsa_8021q_crosschip_link_add(ds, port, other_ds, other_upstream); - if (err) - return err; - - return dsa_8021q_crosschip_link_apply(ds, port, other_ds, - other_upstream, true); -} -EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_join); - -int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port) -{ - struct dsa_8021q_context *other_ctx = other_ds->tag_8021q_ctx; - int other_upstream = dsa_upstream_port(other_ds, other_port); - struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; - struct dsa_8021q_crosschip_link *c, *n; - - list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) { - if (c->port == port && c->other_ctx == other_ctx && - (c->other_port == other_port || - c->other_port == other_upstream)) { - int other_port = c->other_port; - bool keep; - int err; - - dsa_8021q_crosschip_link_del(ds, c, &keep); - if (keep) - continue; - - err = dsa_8021q_crosschip_link_apply(ds, port, - other_ds, - other_port, - false); - if (err) - return err; - } - } + ASSERT_RTNL(); - return 0; + for (port = 0; port < ds->num_ports; port++) + dsa_tag_8021q_port_teardown(ds, port); } -EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_leave); int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto) { @@ -496,28 +496,24 @@ int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto) ctx->proto = proto; ctx->ds = ds; - INIT_LIST_HEAD(&ctx->crosschip_links); + INIT_LIST_HEAD(&ctx->vlans); ds->tag_8021q_ctx = ctx; - return dsa_8021q_setup(ds, true); + return dsa_tag_8021q_setup(ds); } EXPORT_SYMBOL_GPL(dsa_tag_8021q_register); void dsa_tag_8021q_unregister(struct dsa_switch *ds) { struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; - struct dsa_8021q_crosschip_link *c, *n; - int err; + struct dsa_tag_8021q_vlan *v, *n; - err = dsa_8021q_setup(ds, false); - if (err) - dev_err(ds->dev, "failed to tear down tag_8021q VLANs: %pe\n", - ERR_PTR(err)); + dsa_tag_8021q_teardown(ds); - list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) { - list_del(&c->list); - kfree(c); + list_for_each_entry_safe(v, n, &ctx->vlans, list) { + list_del(&v->list); + kfree(v); } ds->tag_8021q_ctx = NULL; -- cgit v1.2.3 From 8b72b301b442907742c1af1b8fcb52e351a2aac1 Mon Sep 17 00:00:00 2001 From: Xu Liang Date: Mon, 19 Jul 2021 13:32:11 +0800 Subject: net: phy: add API to read 802.3-c45 IDs Add API to read 802.3-c45 IDs so that C22/C45 mixed device can use C45 APIs without failing ID checks. Signed-off-by: Xu Liang Acked-by: Hauke Mehrtens Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 14 ++++++++++++++ include/linux/phy.h | 1 + 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 5d5f9a9ee768..107aa6d7bc6b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -968,6 +968,20 @@ void phy_device_remove(struct phy_device *phydev) } EXPORT_SYMBOL(phy_device_remove); +/** + * phy_get_c45_ids - Read 802.3-c45 IDs for phy device. + * @phydev: phy_device structure to read 802.3-c45 IDs + * + * Returns zero on success, %-EIO on bus access error, or %-ENODEV if + * the "devices in package" is invalid. + */ +int phy_get_c45_ids(struct phy_device *phydev) +{ + return get_phy_c45_ids(phydev->mdio.bus, phydev->mdio.addr, + &phydev->c45_ids); +} +EXPORT_SYMBOL(phy_get_c45_ids); + /** * phy_find_first - finds the first PHY device on the bus * @bus: the target MII bus diff --git a/include/linux/phy.h b/include/linux/phy.h index 3b80dc3ed68b..736e1d1a47c4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1431,6 +1431,7 @@ static inline int phy_device_register(struct phy_device *phy) static inline void phy_device_free(struct phy_device *phydev) { } #endif /* CONFIG_PHYLIB */ void phy_device_remove(struct phy_device *phydev); +int phy_get_c45_ids(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); -- cgit v1.2.3 From e1ca90b7cc5cb5d3a38321cbb65ad36a59fcb574 Mon Sep 17 00:00:00 2001 From: Naveen Krishna Chatradhi Date: Wed, 30 Jun 2021 20:58:24 +0530 Subject: EDAC/mc: Add new HBM2 memory type Add a new entry to 'enum mem_type' and a new string to 'edac_mem_types[]' for HBM2 (High Bandwidth Memory Gen 2) new memory type. Reviewed-by: Yazen Ghannam Signed-off-by: Muralidhara M K Signed-off-by: Naveen Krishna Chatradhi Signed-off-by: Tony Luck Link: https://lore.kernel.org/r/20210630152828.162659-4-nchatrad@amd.com --- drivers/edac/edac_mc.c | 1 + include/linux/edac.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index f6d462d0be2d..2c5975674723 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -166,6 +166,7 @@ const char * const edac_mem_types[] = { [MEM_DDR5] = "Unbuffered-DDR5", [MEM_NVDIMM] = "Non-volatile-RAM", [MEM_WIO2] = "Wide-IO-2", + [MEM_HBM2] = "High-bandwidth-memory-Gen2", }; EXPORT_SYMBOL_GPL(edac_mem_types); diff --git a/include/linux/edac.h b/include/linux/edac.h index 76d3562d3006..4207d06996a4 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -184,6 +184,7 @@ static inline char *mc_event_error_type(const unsigned int err_type) * @MEM_DDR5: Unbuffered DDR5 RAM * @MEM_NVDIMM: Non-volatile RAM * @MEM_WIO2: Wide I/O 2. + * @MEM_HBM2: High bandwidth Memory Gen 2. */ enum mem_type { MEM_EMPTY = 0, @@ -212,6 +213,7 @@ enum mem_type { MEM_DDR5, MEM_NVDIMM, MEM_WIO2, + MEM_HBM2, }; #define MEM_FLAG_EMPTY BIT(MEM_EMPTY) @@ -239,6 +241,7 @@ enum mem_type { #define MEM_FLAG_DDR5 BIT(MEM_DDR5) #define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) #define MEM_FLAG_WIO2 BIT(MEM_WIO2) +#define MEM_FLAG_HBM2 BIT(MEM_HBM2) /** * enum edac_type - Error Detection and Correction capabilities and mode -- cgit v1.2.3 From fed31a4dd3adb5455df7c704de2abb639a1dc1c0 Mon Sep 17 00:00:00 2001 From: Zhouyi Zhou Date: Tue, 13 Jul 2021 08:56:45 +0800 Subject: rcu: Fix macro name CONFIG_TASKS_RCU_TRACE This commit fixes several typos where CONFIG_TASKS_RCU_TRACE should instead be CONFIG_TASKS_TRACE_RCU. Among other things, these typos could cause CONFIG_TASKS_TRACE_RCU_READ_MB=y kernels to suffer from memory-ordering bugs that could result in false-positive quiescent states and too-short grace periods. Signed-off-by: Zhouyi Zhou Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 +- kernel/rcu/tree_plugin.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index d9680b798b21..955c82b4737c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -167,7 +167,7 @@ void synchronize_rcu_tasks(void); # define synchronize_rcu_tasks synchronize_rcu # endif -# ifdef CONFIG_TASKS_RCU_TRACE +# ifdef CONFIG_TASKS_TRACE_RCU # define rcu_tasks_trace_qs(t) \ do { \ if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index de1dc3bb7f70..6ce104242b23 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2982,17 +2982,17 @@ static void noinstr rcu_dynticks_task_exit(void) /* Turn on heavyweight RCU tasks trace readers on idle/user entry. */ static void rcu_dynticks_task_trace_enter(void) { -#ifdef CONFIG_TASKS_RCU_TRACE +#ifdef CONFIG_TASKS_TRACE_RCU if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) current->trc_reader_special.b.need_mb = true; -#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */ +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } /* Turn off heavyweight RCU tasks trace readers on idle/user exit. */ static void rcu_dynticks_task_trace_exit(void) { -#ifdef CONFIG_TASKS_RCU_TRACE +#ifdef CONFIG_TASKS_TRACE_RCU if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) current->trc_reader_special.b.need_mb = false; -#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */ +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } -- cgit v1.2.3 From dc7019b7d0e188d4093b34bd0747ed0d668c63bf Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Mon, 14 Jun 2021 17:33:14 -0500 Subject: tee: add tee_shm_alloc_kernel_buf() Adds a new function tee_shm_alloc_kernel_buf() to allocate shared memory from a kernel driver. This function can later be made more lightweight by unnecessary dma-buf export. Cc: stable@vger.kernel.org Reviewed-by: Tyler Hicks Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/tee_shm.c | 18 ++++++++++++++++++ include/linux/tee_drv.h | 1 + 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index 00472f5ce22e..c65e44707cd6 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -193,6 +193,24 @@ err_dev_put: } EXPORT_SYMBOL_GPL(tee_shm_alloc); +/** + * tee_shm_alloc_kernel_buf() - Allocate shared memory for kernel buffer + * @ctx: Context that allocates the shared memory + * @size: Requested size of shared memory + * + * The returned memory registered in secure world and is suitable to be + * passed as a memory buffer in parameter argument to + * tee_client_invoke_func(). The memory allocated is later freed with a + * call to tee_shm_free(). + * + * @returns a pointer to 'struct tee_shm' + */ +struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size) +{ + return tee_shm_alloc(ctx, size, TEE_SHM_MAPPED | TEE_SHM_DMA_BUF); +} +EXPORT_SYMBOL_GPL(tee_shm_alloc_kernel_buf); + struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr, size_t length, u32 flags) { diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 54269e47ac9a..8990f7628387 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -332,6 +332,7 @@ void *tee_get_drvdata(struct tee_device *teedev); * @returns a pointer to 'struct tee_shm' */ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags); +struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); /** * tee_shm_register() - Register shared memory buffer -- cgit v1.2.3 From 376e4199e327a5cf29b8ec8fb0f64f3d8b429819 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Mon, 14 Jun 2021 17:33:15 -0500 Subject: tee: Correct inappropriate usage of TEE_SHM_DMA_BUF flag Currently TEE_SHM_DMA_BUF flag has been inappropriately used to not register shared memory allocated for private usage by underlying TEE driver: OP-TEE in this case. So rather add a new flag as TEE_SHM_PRIV that can be utilized by underlying TEE drivers for private allocation and usage of shared memory. With this corrected, allow tee_shm_alloc_kernel_buf() to allocate a shared memory region without the backing of dma-buf. Cc: stable@vger.kernel.org Signed-off-by: Sumit Garg Co-developed-by: Tyler Hicks Signed-off-by: Tyler Hicks Reviewed-by: Jens Wiklander Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/optee/call.c | 2 +- drivers/tee/optee/core.c | 3 ++- drivers/tee/optee/rpc.c | 5 +++-- drivers/tee/optee/shm_pool.c | 8 ++++++-- drivers/tee/tee_shm.c | 4 ++-- include/linux/tee_drv.h | 1 + 6 files changed, 15 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c index 387e94768182..945f03da0223 100644 --- a/drivers/tee/optee/call.c +++ b/drivers/tee/optee/call.c @@ -184,7 +184,7 @@ static struct tee_shm *get_msg_arg(struct tee_context *ctx, size_t num_params, struct optee_msg_arg *ma; shm = tee_shm_alloc(ctx, OPTEE_MSG_GET_ARG_SIZE(num_params), - TEE_SHM_MAPPED); + TEE_SHM_MAPPED | TEE_SHM_PRIV); if (IS_ERR(shm)) return shm; diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c index 651d49b53d3b..5ce13b099d7d 100644 --- a/drivers/tee/optee/core.c +++ b/drivers/tee/optee/core.c @@ -278,7 +278,8 @@ static void optee_release(struct tee_context *ctx) if (!ctxdata) return; - shm = tee_shm_alloc(ctx, sizeof(struct optee_msg_arg), TEE_SHM_MAPPED); + shm = tee_shm_alloc(ctx, sizeof(struct optee_msg_arg), + TEE_SHM_MAPPED | TEE_SHM_PRIV); if (!IS_ERR(shm)) { arg = tee_shm_get_va(shm, 0); /* diff --git a/drivers/tee/optee/rpc.c b/drivers/tee/optee/rpc.c index 1849180b0278..efbaff7ad7e5 100644 --- a/drivers/tee/optee/rpc.c +++ b/drivers/tee/optee/rpc.c @@ -314,7 +314,7 @@ static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx, shm = cmd_alloc_suppl(ctx, sz); break; case OPTEE_RPC_SHM_TYPE_KERNEL: - shm = tee_shm_alloc(ctx, sz, TEE_SHM_MAPPED); + shm = tee_shm_alloc(ctx, sz, TEE_SHM_MAPPED | TEE_SHM_PRIV); break; default: arg->ret = TEEC_ERROR_BAD_PARAMETERS; @@ -502,7 +502,8 @@ void optee_handle_rpc(struct tee_context *ctx, struct optee_rpc_param *param, switch (OPTEE_SMC_RETURN_GET_RPC_FUNC(param->a0)) { case OPTEE_SMC_RPC_FUNC_ALLOC: - shm = tee_shm_alloc(ctx, param->a1, TEE_SHM_MAPPED); + shm = tee_shm_alloc(ctx, param->a1, + TEE_SHM_MAPPED | TEE_SHM_PRIV); if (!IS_ERR(shm) && !tee_shm_get_pa(shm, 0, &pa)) { reg_pair_from_64(¶m->a1, ¶m->a2, pa); reg_pair_from_64(¶m->a4, ¶m->a5, diff --git a/drivers/tee/optee/shm_pool.c b/drivers/tee/optee/shm_pool.c index da06ce9b9313..c41a9a501a6e 100644 --- a/drivers/tee/optee/shm_pool.c +++ b/drivers/tee/optee/shm_pool.c @@ -27,7 +27,11 @@ static int pool_op_alloc(struct tee_shm_pool_mgr *poolm, shm->paddr = page_to_phys(page); shm->size = PAGE_SIZE << order; - if (shm->flags & TEE_SHM_DMA_BUF) { + /* + * Shared memory private to the OP-TEE driver doesn't need + * to be registered with OP-TEE. + */ + if (!(shm->flags & TEE_SHM_PRIV)) { unsigned int nr_pages = 1 << order, i; struct page **pages; @@ -60,7 +64,7 @@ err: static void pool_op_free(struct tee_shm_pool_mgr *poolm, struct tee_shm *shm) { - if (shm->flags & TEE_SHM_DMA_BUF) + if (!(shm->flags & TEE_SHM_PRIV)) optee_shm_unregister(shm->ctx, shm); free_pages((unsigned long)shm->kaddr, get_order(shm->size)); diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index c65e44707cd6..8a9384a64f3e 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -117,7 +117,7 @@ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags) return ERR_PTR(-EINVAL); } - if ((flags & ~(TEE_SHM_MAPPED | TEE_SHM_DMA_BUF))) { + if ((flags & ~(TEE_SHM_MAPPED | TEE_SHM_DMA_BUF | TEE_SHM_PRIV))) { dev_err(teedev->dev.parent, "invalid shm flags 0x%x", flags); return ERR_PTR(-EINVAL); } @@ -207,7 +207,7 @@ EXPORT_SYMBOL_GPL(tee_shm_alloc); */ struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size) { - return tee_shm_alloc(ctx, size, TEE_SHM_MAPPED | TEE_SHM_DMA_BUF); + return tee_shm_alloc(ctx, size, TEE_SHM_MAPPED); } EXPORT_SYMBOL_GPL(tee_shm_alloc_kernel_buf); diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 8990f7628387..3ebfea0781f1 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -27,6 +27,7 @@ #define TEE_SHM_USER_MAPPED BIT(4) /* Memory mapped in user space */ #define TEE_SHM_POOL BIT(5) /* Memory allocated from pool */ #define TEE_SHM_KERNEL_MAPPED BIT(6) /* Memory mapped in kernel space */ +#define TEE_SHM_PRIV BIT(7) /* Memory private to TEE driver */ struct device; struct tee_device; -- cgit v1.2.3 From b48f8939b9ff593ebed20433bb53c51199920412 Mon Sep 17 00:00:00 2001 From: Ruslan Bilovol Date: Mon, 12 Jul 2021 14:55:26 +0200 Subject: usb: audio-v2: add ability to define feature unit descriptor Similar to UAC1 spec, UAC2 feature unit descriptor has variable size. Current audio-v2 feature unit descriptor structure is used for parsing descriptors, but can't be used to define your own descriptor. Add a new macro similar to what audio v1 already has. Signed-off-by: Ruslan Bilovol Signed-off-by: Pavel Hofman Link: https://lore.kernel.org/r/20210712125529.76070-2-pavel.hofman@ivitera.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/audio-v2.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index ead8c9a47c6a..8fc2abd7aecb 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -156,6 +156,20 @@ struct uac2_feature_unit_descriptor { __u8 bmaControls[]; /* variable length */ } __attribute__((packed)); +#define UAC2_DT_FEATURE_UNIT_SIZE(ch) (6 + ((ch) + 1) * 4) + +/* As above, but more useful for defining your own descriptors: */ +#define DECLARE_UAC2_FEATURE_UNIT_DESCRIPTOR(ch) \ +struct uac2_feature_unit_descriptor_##ch { \ + __u8 bLength; \ + __u8 bDescriptorType; \ + __u8 bDescriptorSubtype; \ + __u8 bUnitID; \ + __u8 bSourceID; \ + __le32 bmaControls[ch + 1]; \ + __u8 iFeature; \ +} __packed + /* 4.7.2.10 Effect Unit Descriptor */ struct uac2_effect_unit_descriptor { -- cgit v1.2.3 From f81d992182570d56db642344fa89a7e1777dbc80 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 17 Jul 2021 11:58:13 +0200 Subject: staging: hi6421-spmi-pmic: rename GPIO IRQ OF node Instead of using the standard name ("gpios"), use "interrupts". Suggested-by: Rob Herring Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/8b2cad1e9b9904c6a2aaea8786d5e5a39f09ac19.1626515862.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/staging/hikey9xx/hi6421-spmi-pmic.c | 18 ++++++------------ .../staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml | 8 +++----- include/linux/mfd/hi6421-spmi-pmic.h | 1 - 3 files changed, 9 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c index dd7ff63214d3..61cbd2e62f68 100644 --- a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c +++ b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c @@ -218,6 +218,7 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *sdev) struct device *dev = &sdev->dev; struct device_node *np = dev->of_node; struct hi6421_spmi_pmic *ddata; + struct platform_device *pdev; unsigned int virq; int ret, i; @@ -233,21 +234,14 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *sdev) ddata->dev = dev; - ddata->gpio = of_get_gpio(np, 0); - if (ddata->gpio < 0) - return ddata->gpio; + pdev = container_of(dev, struct platform_device, dev); - if (!gpio_is_valid(ddata->gpio)) - return -EINVAL; - - ret = devm_gpio_request_one(dev, ddata->gpio, GPIOF_IN, "pmic"); - if (ret < 0) { - dev_err(dev, "Failed to request gpio%d\n", ddata->gpio); - return ret; + ddata->irq = platform_get_irq(pdev, 0); + if (ddata->irq < 0) { + dev_err(dev, "Error %d when getting IRQs\n", ddata->irq); + return ddata->irq; } - ddata->irq = gpio_to_irq(ddata->gpio); - hi6421_spmi_pmic_irq_init(ddata); ddata->irqs = devm_kzalloc(dev, PMIC_IRQ_LIST_MAX * sizeof(int), GFP_KERNEL); diff --git a/drivers/staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml b/drivers/staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml index 8e355cddd437..5a3b1cbfd639 100644 --- a/drivers/staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml +++ b/drivers/staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml @@ -34,9 +34,7 @@ properties: interrupt-controller: true - gpios: - maxItems: 1 - description: GPIO used for IRQs + interrupts: true regulators: type: object @@ -63,7 +61,6 @@ additionalProperties: false examples: - | - /* pmic properties */ pmic: pmic@0 { compatible = "hisilicon,hi6421-spmi"; @@ -71,7 +68,8 @@ examples: #interrupt-cells = <2>; interrupt-controller; - gpios = <&gpio28 0 0>; + interrupt-parent = <&gpio28>; + interrupts = <0 0>; regulators { #address-cells = <1>; diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index 2660226138b8..254430c897d6 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -22,7 +22,6 @@ struct hi6421_spmi_pmic { spinlock_t lock; struct irq_domain *domain; int irq; - int gpio; unsigned int *irqs; struct regmap *regmap; }; -- cgit v1.2.3 From bb3b6552a5b0679b55c43d49621597e54668f089 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 17 Jul 2021 11:58:15 +0200 Subject: staging: hikey9xx: split hi6421v600 irq into a separate driver Per MFD subsystem requirements, split the IRQ part of the driver into a separate one with just the IRQ handling code and the powerkey support. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/709e01c9ffafe6cd0ecb23336b44f9bcde2b5bc2.1626515862.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/Kconfig | 10 + drivers/misc/Makefile | 1 + drivers/misc/hi6421v600-irq.c | 307 +++++++++++++++++++++ drivers/staging/hikey9xx/hi6421-spmi-pmic.c | 239 +--------------- .../hikey9xx/hisilicon,hi6421-spmi-pmic.yaml | 2 +- include/linux/mfd/hi6421-spmi-pmic.h | 4 - 6 files changed, 322 insertions(+), 241 deletions(-) create mode 100644 drivers/misc/hi6421v600-irq.c (limited to 'include/linux') diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index f4fb5c52b863..29294c52d5af 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -208,6 +208,16 @@ config CS5535_CLOCK_EVENT_SRC MFGPTs have a better resolution and max interval than the generic PIT, and are suitable for use as high-res timers. +config HI6421V600_IRQ + tristate "HiSilicon Hi6421v600 IRQ and powerkey" + depends on OF + depends on SPMI + select MFD_CORE + select REGMAP_SPMI + help + This driver provides IRQ handling for Hi6421v600, used on + some Kirin chipsets, like the one at Hikey 970. + config HP_ILO tristate "Channel interface driver for the HP iLO processor" depends on PCI diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index e92a56d4442f..f91cab8c3d55 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -57,3 +57,4 @@ obj-$(CONFIG_HABANA_AI) += habanalabs/ obj-$(CONFIG_UACCE) += uacce/ obj-$(CONFIG_XILINX_SDFEC) += xilinx_sdfec.o obj-$(CONFIG_HISI_HIKEY_USB) += hisi_hikey_usb.o +obj-$(CONFIG_HI6421V600_IRQ) += hi6421v600-irq.o diff --git a/drivers/misc/hi6421v600-irq.c b/drivers/misc/hi6421v600-irq.c new file mode 100644 index 000000000000..08535e97ff43 --- /dev/null +++ b/drivers/misc/hi6421v600-irq.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Device driver for irqs in HISI PMIC IC + * + * Copyright (c) 2013 Linaro Ltd. + * Copyright (c) 2011 Hisilicon. + * Copyright (c) 2020-2021 Huawei Technologies Co., Ltd. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct hi6421v600_irq { + struct device *dev; + struct irq_domain *domain; + int irq; + unsigned int *irqs; + struct regmap *regmap; + + /* Protect IRQ mask changes */ + spinlock_t lock; +}; + +enum hi6421v600_irq_list { + OTMP = 0, + VBUS_CONNECT, + VBUS_DISCONNECT, + ALARMON_R, + HOLD_6S, + HOLD_1S, + POWERKEY_UP, + POWERKEY_DOWN, + OCP_SCP_R, + COUL_R, + SIM0_HPD_R, + SIM0_HPD_F, + SIM1_HPD_R, + SIM1_HPD_F, + + PMIC_IRQ_LIST_MAX +}; + +#define HISI_IRQ_BANK_SIZE 2 + +/* + * IRQ number for the power key button and mask for both UP and DOWN IRQs + */ +#define HISI_POWERKEY_IRQ_NUM 0 +#define HISI_IRQ_POWERKEY_UP_DOWN (BIT(POWERKEY_DOWN) | BIT(POWERKEY_UP)) + +/* + * Registers for IRQ address and IRQ mask bits + * + * Please notice that we need to regmap a larger region, as other + * registers are used by the irqs. + * See drivers/irq/hi6421-irq.c. + */ +#define SOC_PMIC_IRQ_MASK_0_ADDR 0x0202 +#define SOC_PMIC_IRQ0_ADDR 0x0212 + +/* + * The IRQs are mapped as: + * + * ====================== ============= ============ ===== + * IRQ MASK REGISTER IRQ REGISTER BIT + * ====================== ============= ============ ===== + * OTMP 0x0202 0x212 bit 0 + * VBUS_CONNECT 0x0202 0x212 bit 1 + * VBUS_DISCONNECT 0x0202 0x212 bit 2 + * ALARMON_R 0x0202 0x212 bit 3 + * HOLD_6S 0x0202 0x212 bit 4 + * HOLD_1S 0x0202 0x212 bit 5 + * POWERKEY_UP 0x0202 0x212 bit 6 + * POWERKEY_DOWN 0x0202 0x212 bit 7 + * + * OCP_SCP_R 0x0203 0x213 bit 0 + * COUL_R 0x0203 0x213 bit 1 + * SIM0_HPD_R 0x0203 0x213 bit 2 + * SIM0_HPD_F 0x0203 0x213 bit 3 + * SIM1_HPD_R 0x0203 0x213 bit 4 + * SIM1_HPD_F 0x0203 0x213 bit 5 + * ====================== ============= ============ ===== + * + * Each mask register contains 8 bits. The ancillary macros below + * convert a number from 0 to 14 into a register address and a bit mask + */ +#define HISI_IRQ_MASK_REG(irq_data) (SOC_PMIC_IRQ_MASK_0_ADDR + \ + (irqd_to_hwirq(irq_data) / BITS_PER_BYTE)) +#define HISI_IRQ_MASK_BIT(irq_data) BIT(irqd_to_hwirq(irq_data) & (BITS_PER_BYTE - 1)) +#define HISI_8BITS_MASK 0xff + +static irqreturn_t hi6421v600_irq_handler(int irq, void *__priv) +{ + struct hi6421v600_irq *priv = __priv; + unsigned long pending; + unsigned int in; + int i, offset; + + for (i = 0; i < HISI_IRQ_BANK_SIZE; i++) { + regmap_read(priv->regmap, SOC_PMIC_IRQ0_ADDR + i, &in); + + /* Mark pending IRQs as handled */ + regmap_write(priv->regmap, SOC_PMIC_IRQ0_ADDR + i, in); + + pending = in & HISI_8BITS_MASK; + + if (i == HISI_POWERKEY_IRQ_NUM && + (pending & HISI_IRQ_POWERKEY_UP_DOWN) == HISI_IRQ_POWERKEY_UP_DOWN) { + /* + * If both powerkey down and up IRQs are received, + * handle them at the right order + */ + generic_handle_irq(priv->irqs[POWERKEY_DOWN]); + generic_handle_irq(priv->irqs[POWERKEY_UP]); + pending &= ~HISI_IRQ_POWERKEY_UP_DOWN; + } + + if (!pending) + continue; + + for_each_set_bit(offset, &pending, BITS_PER_BYTE) { + generic_handle_irq(priv->irqs[offset + i * BITS_PER_BYTE]); + } + } + + return IRQ_HANDLED; +} + +static void hi6421v600_irq_mask(struct irq_data *d) +{ + struct hi6421v600_irq *priv = irq_data_get_irq_chip_data(d); + unsigned long flags; + unsigned int data; + u32 offset; + + offset = HISI_IRQ_MASK_REG(d); + + spin_lock_irqsave(&priv->lock, flags); + + regmap_read(priv->regmap, offset, &data); + data |= HISI_IRQ_MASK_BIT(d); + regmap_write(priv->regmap, offset, data); + + spin_unlock_irqrestore(&priv->lock, flags); +} + +static void hi6421v600_irq_unmask(struct irq_data *d) +{ + struct hi6421v600_irq *priv = irq_data_get_irq_chip_data(d); + u32 data, offset; + unsigned long flags; + + offset = HISI_IRQ_MASK_REG(d); + + spin_lock_irqsave(&priv->lock, flags); + + regmap_read(priv->regmap, offset, &data); + data &= ~HISI_IRQ_MASK_BIT(d); + regmap_write(priv->regmap, offset, data); + + spin_unlock_irqrestore(&priv->lock, flags); +} + +static struct irq_chip hi6421v600_pmu_irqchip = { + .name = "hi6421v600-irq", + .irq_mask = hi6421v600_irq_mask, + .irq_unmask = hi6421v600_irq_unmask, + .irq_disable = hi6421v600_irq_mask, + .irq_enable = hi6421v600_irq_unmask, +}; + +static int hi6421v600_irq_map(struct irq_domain *d, unsigned int virq, + irq_hw_number_t hw) +{ + struct hi6421v600_irq *priv = d->host_data; + + irq_set_chip_and_handler_name(virq, &hi6421v600_pmu_irqchip, + handle_simple_irq, "hi6421v600"); + irq_set_chip_data(virq, priv); + irq_set_irq_type(virq, IRQ_TYPE_NONE); + + return 0; +} + +static const struct irq_domain_ops hi6421v600_domain_ops = { + .map = hi6421v600_irq_map, + .xlate = irq_domain_xlate_twocell, +}; + +static void hi6421v600_irq_init(struct hi6421v600_irq *priv) +{ + int i; + unsigned int pending; + + /* Mask all IRQs */ + for (i = 0; i < HISI_IRQ_BANK_SIZE; i++) + regmap_write(priv->regmap, SOC_PMIC_IRQ_MASK_0_ADDR + i, + HISI_8BITS_MASK); + + /* Mark all IRQs as handled */ + for (i = 0; i < HISI_IRQ_BANK_SIZE; i++) { + regmap_read(priv->regmap, SOC_PMIC_IRQ0_ADDR + i, &pending); + regmap_write(priv->regmap, SOC_PMIC_IRQ0_ADDR + i, + HISI_8BITS_MASK); + } +} + +static int hi6421v600_irq_probe(struct platform_device *pdev) +{ + struct device *pmic_dev = pdev->dev.parent; + struct device_node *np = pmic_dev->of_node; + struct platform_device *pmic_pdev; + struct device *dev = &pdev->dev; + struct hi6421v600_irq *priv; + struct hi6421_spmi_pmic *pmic; + unsigned int virq; + int i, ret; + + /* + * This driver is meant to be called by hi6421-spmi-core, + * which should first set drvdata. If this doesn't happen, hit + * a warn on and return. + */ + pmic = dev_get_drvdata(pmic_dev); + if (WARN_ON(!pmic)) + return -ENODEV; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->dev = dev; + priv->regmap = pmic->regmap; + + spin_lock_init(&priv->lock); + + pmic_pdev = container_of(pmic_dev, struct platform_device, dev); + + priv->irq = platform_get_irq(pmic_pdev, 0); + if (priv->irq < 0) { + dev_err(dev, "Error %d when getting IRQs\n", priv->irq); + return priv->irq; + } + + platform_set_drvdata(pdev, priv); + + hi6421v600_irq_init(priv); + + priv->irqs = devm_kzalloc(dev, PMIC_IRQ_LIST_MAX * sizeof(int), GFP_KERNEL); + if (!priv->irqs) + return -ENOMEM; + + priv->domain = irq_domain_add_simple(np, PMIC_IRQ_LIST_MAX, 0, + &hi6421v600_domain_ops, priv); + if (!priv->domain) { + dev_err(dev, "Failed to create IRQ domain\n"); + return -ENODEV; + } + + for (i = 0; i < PMIC_IRQ_LIST_MAX; i++) { + virq = irq_create_mapping(priv->domain, i); + if (!virq) { + dev_err(dev, "Failed to map H/W IRQ\n"); + return -ENODEV; + } + priv->irqs[i] = virq; + } + + ret = devm_request_threaded_irq(dev, + priv->irq, hi6421v600_irq_handler, + NULL, + IRQF_TRIGGER_LOW | IRQF_SHARED | IRQF_NO_SUSPEND, + "pmic", priv); + if (ret < 0) { + dev_err(dev, "Failed to start IRQ handling thread: error %d\n", + ret); + return ret; + } + + return 0; +} + +static const struct platform_device_id hi6421v600_irq_table[] = { + { .name = "hi6421v600-irq" }, + {}, +}; +MODULE_DEVICE_TABLE(platform, hi6421v600_irq_table); + +static struct platform_driver hi6421v600_irq_driver = { + .id_table = hi6421v600_irq_table, + .driver = { + .name = "hi6421v600-irq", + }, + .probe = hi6421v600_irq_probe, +}; +module_platform_driver(hi6421v600_irq_driver); + +MODULE_DESCRIPTION("HiSilicon Hi6421v600 IRQ driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c index 0ffd8b7fecf5..4f136826681b 100644 --- a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c +++ b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c @@ -7,205 +7,19 @@ * Copyright (c) 2020-2021 Huawei Technologies Co., Ltd. */ -#include -#include -#include #include #include #include -#include #include +#include #include #include -enum hi6421_spmi_pmic_irq_list { - OTMP = 0, - VBUS_CONNECT, - VBUS_DISCONNECT, - ALARMON_R, - HOLD_6S, - HOLD_1S, - POWERKEY_UP, - POWERKEY_DOWN, - OCP_SCP_R, - COUL_R, - SIM0_HPD_R, - SIM0_HPD_F, - SIM1_HPD_R, - SIM1_HPD_F, - - PMIC_IRQ_LIST_MAX -}; - -#define HISI_IRQ_BANK_SIZE 2 - -/* - * IRQ number for the power key button and mask for both UP and DOWN IRQs - */ -#define HISI_POWERKEY_IRQ_NUM 0 -#define HISI_IRQ_POWERKEY_UP_DOWN (BIT(POWERKEY_DOWN) | BIT(POWERKEY_UP)) - -/* - * Registers for IRQ address and IRQ mask bits - * - * Please notice that we need to regmap a larger region, as other - * registers are used by the regulators. - * See drivers/regulator/hi6421-regulator.c. - */ -#define SOC_PMIC_IRQ_MASK_0_ADDR 0x0202 -#define SOC_PMIC_IRQ0_ADDR 0x0212 - -/* - * The IRQs are mapped as: - * - * ====================== ============= ============ ===== - * IRQ MASK REGISTER IRQ REGISTER BIT - * ====================== ============= ============ ===== - * OTMP 0x0202 0x212 bit 0 - * VBUS_CONNECT 0x0202 0x212 bit 1 - * VBUS_DISCONNECT 0x0202 0x212 bit 2 - * ALARMON_R 0x0202 0x212 bit 3 - * HOLD_6S 0x0202 0x212 bit 4 - * HOLD_1S 0x0202 0x212 bit 5 - * POWERKEY_UP 0x0202 0x212 bit 6 - * POWERKEY_DOWN 0x0202 0x212 bit 7 - * - * OCP_SCP_R 0x0203 0x213 bit 0 - * COUL_R 0x0203 0x213 bit 1 - * SIM0_HPD_R 0x0203 0x213 bit 2 - * SIM0_HPD_F 0x0203 0x213 bit 3 - * SIM1_HPD_R 0x0203 0x213 bit 4 - * SIM1_HPD_F 0x0203 0x213 bit 5 - * ====================== ============= ============ ===== - * - * Each mask register contains 8 bits. The ancillary macros below - * convert a number from 0 to 14 into a register address and a bit mask - */ -#define HISI_IRQ_MASK_REG(irq_data) (SOC_PMIC_IRQ_MASK_0_ADDR + \ - (irqd_to_hwirq(irq_data) / BITS_PER_BYTE)) -#define HISI_IRQ_MASK_BIT(irq_data) BIT(irqd_to_hwirq(irq_data) & (BITS_PER_BYTE - 1)) -#define HISI_8BITS_MASK 0xff - static const struct mfd_cell hi6421v600_devs[] = { + { .name = "hi6421v600-irq", }, { .name = "hi6421v600-regulator", }, }; -static irqreturn_t hi6421_spmi_irq_handler(int irq, void *priv) -{ - struct hi6421_spmi_pmic *ddata = (struct hi6421_spmi_pmic *)priv; - unsigned long pending; - unsigned int in; - int i, offset; - - for (i = 0; i < HISI_IRQ_BANK_SIZE; i++) { - regmap_read(ddata->regmap, SOC_PMIC_IRQ0_ADDR + i, &in); - - /* Mark pending IRQs as handled */ - regmap_write(ddata->regmap, SOC_PMIC_IRQ0_ADDR + i, in); - - pending = in & HISI_8BITS_MASK; - - if (i == HISI_POWERKEY_IRQ_NUM && - (pending & HISI_IRQ_POWERKEY_UP_DOWN) == HISI_IRQ_POWERKEY_UP_DOWN) { - /* - * If both powerkey down and up IRQs are received, - * handle them at the right order - */ - generic_handle_irq(ddata->irqs[POWERKEY_DOWN]); - generic_handle_irq(ddata->irqs[POWERKEY_UP]); - pending &= ~HISI_IRQ_POWERKEY_UP_DOWN; - } - - if (!pending) - continue; - - for_each_set_bit(offset, &pending, BITS_PER_BYTE) { - generic_handle_irq(ddata->irqs[offset + i * BITS_PER_BYTE]); - } - } - - return IRQ_HANDLED; -} - -static void hi6421_spmi_irq_mask(struct irq_data *d) -{ - struct hi6421_spmi_pmic *ddata = irq_data_get_irq_chip_data(d); - unsigned long flags; - unsigned int data; - u32 offset; - - offset = HISI_IRQ_MASK_REG(d); - - spin_lock_irqsave(&ddata->lock, flags); - - regmap_read(ddata->regmap, offset, &data); - data |= HISI_IRQ_MASK_BIT(d); - regmap_write(ddata->regmap, offset, data); - - spin_unlock_irqrestore(&ddata->lock, flags); -} - -static void hi6421_spmi_irq_unmask(struct irq_data *d) -{ - struct hi6421_spmi_pmic *ddata = irq_data_get_irq_chip_data(d); - u32 data, offset; - unsigned long flags; - - offset = HISI_IRQ_MASK_REG(d); - - spin_lock_irqsave(&ddata->lock, flags); - - regmap_read(ddata->regmap, offset, &data); - data &= ~HISI_IRQ_MASK_BIT(d); - regmap_write(ddata->regmap, offset, data); - - spin_unlock_irqrestore(&ddata->lock, flags); -} - -static struct irq_chip hi6421_spmi_pmu_irqchip = { - .name = "hi6421v600-irq", - .irq_mask = hi6421_spmi_irq_mask, - .irq_unmask = hi6421_spmi_irq_unmask, - .irq_disable = hi6421_spmi_irq_mask, - .irq_enable = hi6421_spmi_irq_unmask, -}; - -static int hi6421_spmi_irq_map(struct irq_domain *d, unsigned int virq, - irq_hw_number_t hw) -{ - struct hi6421_spmi_pmic *ddata = d->host_data; - - irq_set_chip_and_handler_name(virq, &hi6421_spmi_pmu_irqchip, - handle_simple_irq, "hi6421v600"); - irq_set_chip_data(virq, ddata); - irq_set_irq_type(virq, IRQ_TYPE_NONE); - - return 0; -} - -static const struct irq_domain_ops hi6421_spmi_domain_ops = { - .map = hi6421_spmi_irq_map, - .xlate = irq_domain_xlate_twocell, -}; - -static void hi6421_spmi_pmic_irq_init(struct hi6421_spmi_pmic *ddata) -{ - int i; - unsigned int pending; - - /* Mask all IRQs */ - for (i = 0; i < HISI_IRQ_BANK_SIZE; i++) - regmap_write(ddata->regmap, SOC_PMIC_IRQ_MASK_0_ADDR + i, - HISI_8BITS_MASK); - - /* Mark all IRQs as handled */ - for (i = 0; i < HISI_IRQ_BANK_SIZE; i++) { - regmap_read(ddata->regmap, SOC_PMIC_IRQ0_ADDR + i, &pending); - regmap_write(ddata->regmap, SOC_PMIC_IRQ0_ADDR + i, - HISI_8BITS_MASK); - } -} - static const struct regmap_config regmap_config = { .reg_bits = 16, .val_bits = BITS_PER_BYTE, @@ -216,12 +30,8 @@ static const struct regmap_config regmap_config = { static int hi6421_spmi_pmic_probe(struct spmi_device *sdev) { struct device *dev = &sdev->dev; - struct device_node *np = dev->of_node; + int ret; struct hi6421_spmi_pmic *ddata; - struct platform_device *pdev; - unsigned int virq; - int ret, i; - ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL); if (!ddata) return -ENOMEM; @@ -230,51 +40,8 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *sdev) if (IS_ERR(ddata->regmap)) return PTR_ERR(ddata->regmap); - spin_lock_init(&ddata->lock); - ddata->dev = dev; - pdev = container_of(dev, struct platform_device, dev); - - ddata->irq = platform_get_irq(pdev, 0); - if (ddata->irq < 0) { - dev_err(dev, "Error %d when getting IRQs\n", ddata->irq); - return ddata->irq; - } - - hi6421_spmi_pmic_irq_init(ddata); - - ddata->irqs = devm_kzalloc(dev, PMIC_IRQ_LIST_MAX * sizeof(int), GFP_KERNEL); - if (!ddata->irqs) - return -ENOMEM; - - ddata->domain = irq_domain_add_simple(np, PMIC_IRQ_LIST_MAX, 0, - &hi6421_spmi_domain_ops, ddata); - if (!ddata->domain) { - dev_err(dev, "Failed to create IRQ domain\n"); - return -ENODEV; - } - - for (i = 0; i < PMIC_IRQ_LIST_MAX; i++) { - virq = irq_create_mapping(ddata->domain, i); - if (!virq) { - dev_err(dev, "Failed to map H/W IRQ\n"); - return -ENODEV; - } - ddata->irqs[i] = virq; - } - - ret = devm_request_threaded_irq(dev, - ddata->irq, hi6421_spmi_irq_handler, - NULL, - IRQF_TRIGGER_LOW | IRQF_SHARED | IRQF_NO_SUSPEND, - "pmic", ddata); - if (ret < 0) { - dev_err(dev, "Failed to start IRQ handling thread: error %d\n", - ret); - return ret; - } - dev_set_drvdata(&sdev->dev, ddata); ret = devm_mfd_add_devices(&sdev->dev, PLATFORM_DEVID_NONE, diff --git a/drivers/staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml b/drivers/staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml index 5a3b1cbfd639..63f49080001d 100644 --- a/drivers/staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml +++ b/drivers/staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml @@ -63,7 +63,7 @@ examples: - | pmic: pmic@0 { - compatible = "hisilicon,hi6421-spmi"; + compatible = "hisilicon,hi6421v600-spmi"; reg = <0 0>; #interrupt-cells = <2>; diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index 254430c897d6..e5b8dbf828b6 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -19,10 +19,6 @@ struct hi6421_spmi_pmic { struct resource *res; struct device *dev; void __iomem *regs; - spinlock_t lock; - struct irq_domain *domain; - int irq; - unsigned int *irqs; struct regmap *regmap; }; -- cgit v1.2.3 From dde0a31863d6a7b05ca7cb5d138586e71afc5e50 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Tue, 13 Jul 2021 21:35:18 +0200 Subject: PCI: endpoint: Make struct pci_epf_driver::remove return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of pci_epf_device_remove() (because there is only little it can do when a device disappears) and there are no pci_epf_drivers with a remove callback. So make it impossible for future drivers to return an unused error code by changing the remove prototype to return void. The real motivation for this change is the quest to make struct bus_type::remove return void, too. Acked-by: Kishon Vijay Abraham I Acked-by: Bjorn Helgaas Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210713193522.1770306-2-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/pci/endpoint/pci-epf-core.c | 5 ++--- include/linux/pci-epf.h | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index e9289d10f822..4b9ad96bf1b2 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -389,15 +389,14 @@ static int pci_epf_device_probe(struct device *dev) static int pci_epf_device_remove(struct device *dev) { - int ret = 0; struct pci_epf *epf = to_pci_epf(dev); struct pci_epf_driver *driver = to_pci_epf_driver(dev->driver); if (driver->remove) - ret = driver->remove(epf); + driver->remove(epf); epf->driver = NULL; - return ret; + return 0; } static struct bus_type pci_epf_bus_type = { diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 2debc27ba95e..8292420426f3 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -85,7 +85,7 @@ struct pci_epf_ops { */ struct pci_epf_driver { int (*probe)(struct pci_epf *epf); - int (*remove)(struct pci_epf *epf); + void (*remove)(struct pci_epf *epf); struct device_driver driver; struct pci_epf_ops *ops; -- cgit v1.2.3 From fc7a6209d5710618eb4f72a77cd81b8d694ecf89 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Tue, 13 Jul 2021 21:35:22 +0200 Subject: bus: Make remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of this callback because there is only little it can do when a device disappears. This is the final bit of a long lasting cleanup quest where several buses were converted to also return void from their remove callback. Additionally some resource leaks were fixed that were caused by drivers returning an error code in the expectation that the driver won't go away. With struct bus_type::remove returning void it's prevented that newly implemented buses return an ignored error code and so don't anticipate wrong expectations for driver authors. Reviewed-by: Tom Rix (For fpga) Reviewed-by: Mathieu Poirier Reviewed-by: Cornelia Huck (For drivers/s390 and drivers/vfio) Acked-by: Russell King (Oracle) (For ARM, Amba and related parts) Acked-by: Mark Brown Acked-by: Chen-Yu Tsai (for sunxi-rsb) Acked-by: Pali Rohár Acked-by: Mauro Carvalho Chehab (for media) Acked-by: Hans de Goede (For drivers/platform) Acked-by: Alexandre Belloni Acked-By: Vinod Koul Acked-by: Juergen Gross (For xen) Acked-by: Lee Jones (For mfd) Acked-by: Johannes Thumshirn (For mcb) Acked-by: Johan Hovold Acked-by: Srinivas Kandagatla (For slimbus) Acked-by: Kirti Wankhede (For vfio) Acked-by: Maximilian Luz Acked-by: Heikki Krogerus (For ulpi and typec) Acked-by: Samuel Iglesias Gonsálvez (For ipack) Acked-by: Geoff Levand (For ps3) Acked-by: Yehezkel Bernat (For thunderbolt) Acked-by: Alexander Shishkin (For intel_th) Acked-by: Dominik Brodowski (For pcmcia) Acked-by: Rafael J. Wysocki (For ACPI) Acked-by: Bjorn Andersson (rpmsg and apr) Acked-by: Srinivas Pandruvada (For intel-ish-hid) Acked-by: Dan Williams (For CXL, DAX, and NVDIMM) Acked-by: William Breathitt Gray (For isa) Acked-by: Stefan Richter (For firewire) Acked-by: Benjamin Tissoires (For hid) Acked-by: Thorsten Scherer (For siox) Acked-by: Sven Van Asbroeck (For anybuss) Acked-by: Ulf Hansson (For MMC) Acked-by: Wolfram Sang # for I2C Acked-by: Sudeep Holla Acked-by: Geert Uytterhoeven Acked-by: Dmitry Torokhov Acked-by: Finn Thain Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210713193522.1770306-6-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- arch/arm/common/locomo.c | 3 +-- arch/arm/common/sa1111.c | 4 +--- arch/arm/mach-rpc/ecard.c | 4 +--- arch/mips/sgi-ip22/ip22-gio.c | 3 +-- arch/parisc/kernel/drivers.c | 5 ++--- arch/powerpc/platforms/ps3/system-bus.c | 3 +-- arch/powerpc/platforms/pseries/ibmebus.c | 3 +-- arch/powerpc/platforms/pseries/vio.c | 3 +-- arch/sparc/kernel/vio.c | 4 +--- drivers/acpi/bus.c | 3 +-- drivers/amba/bus.c | 4 +--- drivers/base/auxiliary.c | 4 +--- drivers/base/isa.c | 4 +--- drivers/base/platform.c | 4 +--- drivers/bcma/main.c | 6 ++---- drivers/bus/sunxi-rsb.c | 4 +--- drivers/cxl/core.c | 3 +-- drivers/dax/bus.c | 4 +--- drivers/dma/idxd/sysfs.c | 4 +--- drivers/firewire/core-device.c | 4 +--- drivers/firmware/arm_scmi/bus.c | 4 +--- drivers/firmware/google/coreboot_table.c | 4 +--- drivers/fpga/dfl.c | 4 +--- drivers/hid/hid-core.c | 4 +--- drivers/hid/intel-ish-hid/ishtp/bus.c | 4 +--- drivers/hv/vmbus_drv.c | 5 +---- drivers/hwtracing/intel_th/core.c | 4 +--- drivers/i2c/i2c-core-base.c | 5 +---- drivers/i3c/master.c | 4 +--- drivers/input/gameport/gameport.c | 3 +-- drivers/input/serio/serio.c | 3 +-- drivers/ipack/ipack.c | 4 +--- drivers/macintosh/macio_asic.c | 4 +--- drivers/mcb/mcb-core.c | 4 +--- drivers/media/pci/bt8xx/bttv-gpio.c | 3 +-- drivers/memstick/core/memstick.c | 3 +-- drivers/mfd/mcp-core.c | 3 +-- drivers/misc/mei/bus.c | 4 +--- drivers/misc/tifm_core.c | 3 +-- drivers/mmc/core/bus.c | 4 +--- drivers/mmc/core/sdio_bus.c | 4 +--- drivers/net/netdevsim/bus.c | 3 +-- drivers/ntb/core.c | 4 +--- drivers/ntb/ntb_transport.c | 4 +--- drivers/nubus/bus.c | 6 ++---- drivers/nvdimm/bus.c | 3 +-- drivers/pci/endpoint/pci-epf-core.c | 4 +--- drivers/pci/pci-driver.c | 3 +-- drivers/pcmcia/ds.c | 4 +--- drivers/platform/surface/aggregator/bus.c | 4 +--- drivers/platform/x86/wmi.c | 4 +--- drivers/pnp/driver.c | 3 +-- drivers/rapidio/rio-driver.c | 4 +--- drivers/rpmsg/rpmsg_core.c | 7 ++----- drivers/s390/cio/ccwgroup.c | 4 +--- drivers/s390/cio/css.c | 4 +--- drivers/s390/cio/device.c | 4 +--- drivers/s390/cio/scm.c | 4 +--- drivers/s390/crypto/ap_bus.c | 4 +--- drivers/scsi/scsi_debug.c | 3 +-- drivers/sh/superhyway/superhyway.c | 8 ++------ drivers/siox/siox-core.c | 4 +--- drivers/slimbus/core.c | 4 +--- drivers/soc/qcom/apr.c | 4 +--- drivers/spi/spi.c | 4 +--- drivers/spmi/spmi.c | 3 +-- drivers/ssb/main.c | 4 +--- drivers/staging/fieldbus/anybuss/host.c | 4 +--- drivers/staging/greybus/gbphy.c | 4 +--- drivers/target/loopback/tcm_loop.c | 5 ++--- drivers/thunderbolt/domain.c | 4 +--- drivers/tty/serdev/core.c | 4 +--- drivers/usb/common/ulpi.c | 4 +--- drivers/usb/serial/bus.c | 4 +--- drivers/usb/typec/bus.c | 4 +--- drivers/vdpa/vdpa.c | 4 +--- drivers/vfio/mdev/mdev_driver.c | 4 +--- drivers/virtio/virtio.c | 3 +-- drivers/vlynq/vlynq.c | 4 +--- drivers/vme/vme.c | 4 +--- drivers/xen/xenbus/xenbus.h | 2 +- drivers/xen/xenbus/xenbus_probe.c | 4 +--- drivers/zorro/zorro-driver.c | 3 +-- include/linux/device/bus.h | 2 +- sound/ac97/bus.c | 6 ++---- sound/aoa/soundbus/core.c | 4 +--- 86 files changed, 93 insertions(+), 243 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c index e45f4e4e06b6..24d21ba63030 100644 --- a/arch/arm/common/locomo.c +++ b/arch/arm/common/locomo.c @@ -834,14 +834,13 @@ static int locomo_bus_probe(struct device *dev) return ret; } -static int locomo_bus_remove(struct device *dev) +static void locomo_bus_remove(struct device *dev) { struct locomo_dev *ldev = LOCOMO_DEV(dev); struct locomo_driver *drv = LOCOMO_DRV(dev->driver); if (drv->remove) drv->remove(ldev); - return 0; } struct bus_type locomo_bus_type = { diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index ff5e0d04cb89..092a2ebc0c28 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -1364,15 +1364,13 @@ static int sa1111_bus_probe(struct device *dev) return ret; } -static int sa1111_bus_remove(struct device *dev) +static void sa1111_bus_remove(struct device *dev) { struct sa1111_dev *sadev = to_sa1111_device(dev); struct sa1111_driver *drv = SA1111_DRV(dev->driver); if (drv->remove) drv->remove(sadev); - - return 0; } struct bus_type sa1111_bus_type = { diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index 827b50f1c73e..53813f9464a2 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -1052,7 +1052,7 @@ static int ecard_drv_probe(struct device *dev) return ret; } -static int ecard_drv_remove(struct device *dev) +static void ecard_drv_remove(struct device *dev) { struct expansion_card *ec = ECARD_DEV(dev); struct ecard_driver *drv = ECARD_DRV(dev->driver); @@ -1067,8 +1067,6 @@ static int ecard_drv_remove(struct device *dev) ec->ops = &ecard_default_ops; barrier(); ec->irq_data = NULL; - - return 0; } /* diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c index de0768a49ee8..dfc52f661ad0 100644 --- a/arch/mips/sgi-ip22/ip22-gio.c +++ b/arch/mips/sgi-ip22/ip22-gio.c @@ -143,14 +143,13 @@ static int gio_device_probe(struct device *dev) return error; } -static int gio_device_remove(struct device *dev) +static void gio_device_remove(struct device *dev) { struct gio_device *gio_dev = to_gio_device(dev); struct gio_driver *drv = to_gio_driver(dev->driver); if (dev->driver && drv->remove) drv->remove(gio_dev); - return 0; } static void gio_device_shutdown(struct device *dev) diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index 80fa0650736b..776d624a7207 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -133,14 +133,13 @@ static int parisc_driver_probe(struct device *dev) return rc; } -static int __exit parisc_driver_remove(struct device *dev) +static void __exit parisc_driver_remove(struct device *dev) { struct parisc_device *pa_dev = to_parisc_device(dev); struct parisc_driver *pa_drv = to_parisc_driver(dev->driver); + if (pa_drv->remove) pa_drv->remove(pa_dev); - - return 0; } diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index 1a5665875165..cc5774c64fae 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -381,7 +381,7 @@ static int ps3_system_bus_probe(struct device *_dev) return result; } -static int ps3_system_bus_remove(struct device *_dev) +static void ps3_system_bus_remove(struct device *_dev) { struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev); struct ps3_system_bus_driver *drv; @@ -399,7 +399,6 @@ static int ps3_system_bus_remove(struct device *_dev) __func__, __LINE__, drv->core.name); pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev_name(&dev->core)); - return 0; } static void ps3_system_bus_shutdown(struct device *_dev) diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index c6c79ef55e13..7ee3ed7d6cc2 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -366,14 +366,13 @@ static int ibmebus_bus_device_probe(struct device *dev) return error; } -static int ibmebus_bus_device_remove(struct device *dev) +static void ibmebus_bus_device_remove(struct device *dev) { struct platform_device *of_dev = to_platform_device(dev); struct platform_driver *drv = to_platform_driver(dev->driver); if (dev->driver && drv->remove) drv->remove(of_dev); - return 0; } static void ibmebus_bus_device_shutdown(struct device *dev) diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index e00f3725ec96..58283cecbd52 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1257,7 +1257,7 @@ static int vio_bus_probe(struct device *dev) } /* convert from struct device to struct vio_dev and pass to driver. */ -static int vio_bus_remove(struct device *dev) +static void vio_bus_remove(struct device *dev) { struct vio_dev *viodev = to_vio_dev(dev); struct vio_driver *viodrv = to_vio_driver(dev->driver); @@ -1276,7 +1276,6 @@ static int vio_bus_remove(struct device *dev) vio_cmo_bus_remove(viodev); put_device(devptr); - return 0; } static void vio_bus_shutdown(struct device *dev) diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index 348a88691219..01122a208f94 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -93,7 +93,7 @@ static int vio_device_probe(struct device *dev) return drv->probe(vdev, id); } -static int vio_device_remove(struct device *dev) +static void vio_device_remove(struct device *dev) { struct vio_dev *vdev = to_vio_dev(dev); struct vio_driver *drv = to_vio_driver(dev->driver); @@ -107,8 +107,6 @@ static int vio_device_remove(struct device *dev) drv->remove(vdev); } - - return 0; } static ssize_t devspec_show(struct device *dev, diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index f854bcb8d010..b941555cb5e4 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1019,7 +1019,7 @@ static int acpi_device_probe(struct device *dev) return 0; } -static int acpi_device_remove(struct device *dev) +static void acpi_device_remove(struct device *dev) { struct acpi_device *acpi_dev = to_acpi_device(dev); struct acpi_driver *acpi_drv = acpi_dev->driver; @@ -1034,7 +1034,6 @@ static int acpi_device_remove(struct device *dev) acpi_dev->driver_data = NULL; put_device(dev); - return 0; } struct bus_type acpi_bus_type = { diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 939ca220bf78..962041148482 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -219,7 +219,7 @@ static int amba_probe(struct device *dev) return ret; } -static int amba_remove(struct device *dev) +static void amba_remove(struct device *dev) { struct amba_device *pcdev = to_amba_device(dev); struct amba_driver *drv = to_amba_driver(dev->driver); @@ -236,8 +236,6 @@ static int amba_remove(struct device *dev) amba_put_disable_pclk(pcdev); dev_pm_domain_detach(dev, true); - - return 0; } static void amba_shutdown(struct device *dev) diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c index adc199dfba3c..0c86f5bed9f4 100644 --- a/drivers/base/auxiliary.c +++ b/drivers/base/auxiliary.c @@ -79,7 +79,7 @@ static int auxiliary_bus_probe(struct device *dev) return ret; } -static int auxiliary_bus_remove(struct device *dev) +static void auxiliary_bus_remove(struct device *dev) { struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver); struct auxiliary_device *auxdev = to_auxiliary_dev(dev); @@ -87,8 +87,6 @@ static int auxiliary_bus_remove(struct device *dev) if (auxdrv->remove) auxdrv->remove(auxdev); dev_pm_domain_detach(dev, true); - - return 0; } static void auxiliary_bus_shutdown(struct device *dev) diff --git a/drivers/base/isa.c b/drivers/base/isa.c index aa4737667026..55e3ee2da98f 100644 --- a/drivers/base/isa.c +++ b/drivers/base/isa.c @@ -46,14 +46,12 @@ static int isa_bus_probe(struct device *dev) return 0; } -static int isa_bus_remove(struct device *dev) +static void isa_bus_remove(struct device *dev) { struct isa_driver *isa_driver = dev->platform_data; if (isa_driver && isa_driver->remove) isa_driver->remove(dev, to_isa_dev(dev)->id); - - return 0; } static void isa_bus_shutdown(struct device *dev) diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 8640578f45e9..a94b7f454881 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1438,7 +1438,7 @@ out: return ret; } -static int platform_remove(struct device *_dev) +static void platform_remove(struct device *_dev) { struct platform_driver *drv = to_platform_driver(_dev->driver); struct platform_device *dev = to_platform_device(_dev); @@ -1450,8 +1450,6 @@ static int platform_remove(struct device *_dev) dev_warn(_dev, "remove callback returned a non-zero value. This will be ignored.\n"); } dev_pm_domain_detach(_dev, true); - - return 0; } static void platform_shutdown(struct device *_dev) diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index 6535614a7dc1..e076630d17bd 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -27,7 +27,7 @@ static DEFINE_MUTEX(bcma_buses_mutex); static int bcma_bus_match(struct device *dev, struct device_driver *drv); static int bcma_device_probe(struct device *dev); -static int bcma_device_remove(struct device *dev); +static void bcma_device_remove(struct device *dev); static int bcma_device_uevent(struct device *dev, struct kobj_uevent_env *env); static ssize_t manuf_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -614,7 +614,7 @@ static int bcma_device_probe(struct device *dev) return err; } -static int bcma_device_remove(struct device *dev) +static void bcma_device_remove(struct device *dev) { struct bcma_device *core = container_of(dev, struct bcma_device, dev); struct bcma_driver *adrv = container_of(dev->driver, struct bcma_driver, @@ -623,8 +623,6 @@ static int bcma_device_remove(struct device *dev) if (adrv->remove) adrv->remove(core); put_device(dev); - - return 0; } static int bcma_device_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index d46db132d085..6f225dddc74f 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -169,13 +169,11 @@ static int sunxi_rsb_device_probe(struct device *dev) return drv->probe(rdev); } -static int sunxi_rsb_device_remove(struct device *dev) +static void sunxi_rsb_device_remove(struct device *dev) { const struct sunxi_rsb_driver *drv = to_sunxi_rsb_driver(dev->driver); drv->remove(to_sunxi_rsb_device(dev)); - - return 0; } static struct bus_type sunxi_rsb_bus = { diff --git a/drivers/cxl/core.c b/drivers/cxl/core.c index a2e4d54fc7bc..2b90b7c3b9d7 100644 --- a/drivers/cxl/core.c +++ b/drivers/cxl/core.c @@ -1034,13 +1034,12 @@ static int cxl_bus_probe(struct device *dev) return to_cxl_drv(dev->driver)->probe(dev); } -static int cxl_bus_remove(struct device *dev) +static void cxl_bus_remove(struct device *dev) { struct cxl_driver *cxl_drv = to_cxl_drv(dev->driver); if (cxl_drv->remove) cxl_drv->remove(dev); - return 0; } struct bus_type cxl_bus_type = { diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 5aee26e1bbd6..6cc4da4c713d 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -172,15 +172,13 @@ static int dax_bus_probe(struct device *dev) return 0; } -static int dax_bus_remove(struct device *dev) +static void dax_bus_remove(struct device *dev) { struct dax_device_driver *dax_drv = to_dax_drv(dev->driver); struct dev_dax *dev_dax = to_dev_dax(dev); if (dax_drv->remove) dax_drv->remove(dev_dax); - - return 0; } static struct bus_type dax_bus_type = { diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 0460d58e3941..5a017c62c752 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -260,7 +260,7 @@ static void disable_wq(struct idxd_wq *wq) dev_info(dev, "wq %s disabled\n", dev_name(&wq->conf_dev)); } -static int idxd_config_bus_remove(struct device *dev) +static void idxd_config_bus_remove(struct device *dev) { int rc; @@ -305,8 +305,6 @@ static int idxd_config_bus_remove(struct device *dev) dev_info(dev, "Device %s disabled\n", dev_name(dev)); } - - return 0; } static void idxd_config_bus_shutdown(struct device *dev) diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 68216988391f..90ed8fdaba75 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -187,14 +187,12 @@ static int fw_unit_probe(struct device *dev) return driver->probe(fw_unit(dev), unit_match(dev, dev->driver)); } -static int fw_unit_remove(struct device *dev) +static void fw_unit_remove(struct device *dev) { struct fw_driver *driver = container_of(dev->driver, struct fw_driver, driver); driver->remove(fw_unit(dev)); - - return 0; } static int get_modalias(struct fw_unit *unit, char *buffer, size_t buffer_size) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 6c7e24935eca..f6fe723ab869 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -111,15 +111,13 @@ static int scmi_dev_probe(struct device *dev) return scmi_drv->probe(scmi_dev); } -static int scmi_dev_remove(struct device *dev) +static void scmi_dev_remove(struct device *dev) { struct scmi_driver *scmi_drv = to_scmi_driver(dev->driver); struct scmi_device *scmi_dev = to_scmi_dev(dev); if (scmi_drv->remove) scmi_drv->remove(scmi_dev); - - return 0; } static struct bus_type scmi_bus_type = { diff --git a/drivers/firmware/google/coreboot_table.c b/drivers/firmware/google/coreboot_table.c index dc83ea118c67..c52bcaa9def6 100644 --- a/drivers/firmware/google/coreboot_table.c +++ b/drivers/firmware/google/coreboot_table.c @@ -44,15 +44,13 @@ static int coreboot_bus_probe(struct device *dev) return ret; } -static int coreboot_bus_remove(struct device *dev) +static void coreboot_bus_remove(struct device *dev) { struct coreboot_device *device = CB_DEV(dev); struct coreboot_driver *driver = CB_DRV(dev->driver); if (driver->remove) driver->remove(device); - - return 0; } static struct bus_type coreboot_bus_type = { diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index 511b20ff35a3..1ae6779a0dd6 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -284,15 +284,13 @@ static int dfl_bus_probe(struct device *dev) return ddrv->probe(ddev); } -static int dfl_bus_remove(struct device *dev) +static void dfl_bus_remove(struct device *dev) { struct dfl_driver *ddrv = to_dfl_drv(dev->driver); struct dfl_device *ddev = to_dfl_dev(dev); if (ddrv->remove) ddrv->remove(ddev); - - return 0; } static int dfl_bus_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 7db332139f7d..dbed2524fd47 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2302,7 +2302,7 @@ end: return ret; } -static int hid_device_remove(struct device *dev) +static void hid_device_remove(struct device *dev) { struct hid_device *hdev = to_hid_device(dev); struct hid_driver *hdrv; @@ -2322,8 +2322,6 @@ static int hid_device_remove(struct device *dev) if (!hdev->io_started) up(&hdev->driver_input_lock); - - return 0; } static ssize_t modalias_show(struct device *dev, struct device_attribute *a, diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index f0802b047ed8..8a51bd9cd093 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -255,7 +255,7 @@ static int ishtp_cl_bus_match(struct device *dev, struct device_driver *drv) * * Return: Return value from driver remove() call. */ -static int ishtp_cl_device_remove(struct device *dev) +static void ishtp_cl_device_remove(struct device *dev) { struct ishtp_cl_device *device = to_ishtp_cl_device(dev); struct ishtp_cl_driver *driver = to_ishtp_cl_driver(dev->driver); @@ -267,8 +267,6 @@ static int ishtp_cl_device_remove(struct device *dev) if (driver->remove) driver->remove(device); - - return 0; } /** diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 57bbbaa4e8f7..392c1ac4f819 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -922,7 +922,7 @@ static int vmbus_probe(struct device *child_device) /* * vmbus_remove - Remove a vmbus device */ -static int vmbus_remove(struct device *child_device) +static void vmbus_remove(struct device *child_device) { struct hv_driver *drv; struct hv_device *dev = device_to_hv_device(child_device); @@ -932,11 +932,8 @@ static int vmbus_remove(struct device *child_device) if (drv->remove) drv->remove(dev); } - - return 0; } - /* * vmbus_shutdown - Shutdown a vmbus device */ diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 66eed2dff818..7e753a75d23b 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -95,7 +95,7 @@ out_pm: static void intel_th_device_remove(struct intel_th_device *thdev); -static int intel_th_remove(struct device *dev) +static void intel_th_remove(struct device *dev) { struct intel_th_driver *thdrv = to_intel_th_driver(dev->driver); struct intel_th_device *thdev = to_intel_th_device(dev); @@ -164,8 +164,6 @@ static int intel_th_remove(struct device *dev) pm_runtime_disable(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); - - return 0; } static struct bus_type intel_th_bus = { diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 84f12bf90644..54964fbe3f03 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -601,7 +601,7 @@ put_sync_adapter: return status; } -static int i2c_device_remove(struct device *dev) +static void i2c_device_remove(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); struct i2c_adapter *adap; @@ -631,9 +631,6 @@ static int i2c_device_remove(struct device *dev) client->irq = 0; if (client->flags & I2C_CLIENT_HOST_NOTIFY) pm_runtime_put(&client->adapter->dev); - - /* return always 0 because there is WIP to make remove-functions void */ - return 0; } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index e2e12a5585e5..c3b4c677b442 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -322,7 +322,7 @@ static int i3c_device_probe(struct device *dev) return driver->probe(i3cdev); } -static int i3c_device_remove(struct device *dev) +static void i3c_device_remove(struct device *dev) { struct i3c_device *i3cdev = dev_to_i3cdev(dev); struct i3c_driver *driver = drv_to_i3cdrv(dev->driver); @@ -331,8 +331,6 @@ static int i3c_device_remove(struct device *dev) driver->remove(i3cdev); i3c_device_free_ibi(i3cdev); - - return 0; } struct bus_type i3c_bus_type = { diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c index 61fa7e724172..db58a01b23d3 100644 --- a/drivers/input/gameport/gameport.c +++ b/drivers/input/gameport/gameport.c @@ -697,13 +697,12 @@ static int gameport_driver_probe(struct device *dev) return gameport->drv ? 0 : -ENODEV; } -static int gameport_driver_remove(struct device *dev) +static void gameport_driver_remove(struct device *dev) { struct gameport *gameport = to_gameport_port(dev); struct gameport_driver *drv = to_gameport_driver(dev->driver); drv->disconnect(gameport); - return 0; } static void gameport_attach_driver(struct gameport_driver *drv) diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c index 29f491082926..ec117be3d8d8 100644 --- a/drivers/input/serio/serio.c +++ b/drivers/input/serio/serio.c @@ -778,12 +778,11 @@ static int serio_driver_probe(struct device *dev) return serio_connect_driver(serio, drv); } -static int serio_driver_remove(struct device *dev) +static void serio_driver_remove(struct device *dev) { struct serio *serio = to_serio_port(dev); serio_disconnect_driver(serio); - return 0; } static void serio_cleanup(struct serio *serio) diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c index 7de9605cac4f..b1c3198355e7 100644 --- a/drivers/ipack/ipack.c +++ b/drivers/ipack/ipack.c @@ -67,15 +67,13 @@ static int ipack_bus_probe(struct device *device) return drv->ops->probe(dev); } -static int ipack_bus_remove(struct device *device) +static void ipack_bus_remove(struct device *device) { struct ipack_device *dev = to_ipack_dev(device); struct ipack_driver *drv = to_ipack_driver(device->driver); if (drv->ops->remove) drv->ops->remove(dev); - - return 0; } static int ipack_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 49af60bdac92..c1fdf2896021 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -88,7 +88,7 @@ static int macio_device_probe(struct device *dev) return error; } -static int macio_device_remove(struct device *dev) +static void macio_device_remove(struct device *dev) { struct macio_dev * macio_dev = to_macio_device(dev); struct macio_driver * drv = to_macio_driver(dev->driver); @@ -96,8 +96,6 @@ static int macio_device_remove(struct device *dev) if (dev->driver && drv->remove) drv->remove(macio_dev); macio_dev_put(macio_dev); - - return 0; } static void macio_device_shutdown(struct device *dev) diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c index 38fbb3b59873..edf4ee6eff25 100644 --- a/drivers/mcb/mcb-core.c +++ b/drivers/mcb/mcb-core.c @@ -77,7 +77,7 @@ static int mcb_probe(struct device *dev) return ret; } -static int mcb_remove(struct device *dev) +static void mcb_remove(struct device *dev) { struct mcb_driver *mdrv = to_mcb_driver(dev->driver); struct mcb_device *mdev = to_mcb_device(dev); @@ -89,8 +89,6 @@ static int mcb_remove(struct device *dev) module_put(carrier_mod); put_device(&mdev->dev); - - return 0; } static void mcb_shutdown(struct device *dev) diff --git a/drivers/media/pci/bt8xx/bttv-gpio.c b/drivers/media/pci/bt8xx/bttv-gpio.c index b730225ca887..a2b18e2bed1b 100644 --- a/drivers/media/pci/bt8xx/bttv-gpio.c +++ b/drivers/media/pci/bt8xx/bttv-gpio.c @@ -46,14 +46,13 @@ static int bttv_sub_probe(struct device *dev) return sub->probe ? sub->probe(sdev) : -ENODEV; } -static int bttv_sub_remove(struct device *dev) +static void bttv_sub_remove(struct device *dev) { struct bttv_sub_device *sdev = to_bttv_sub_dev(dev); struct bttv_sub_driver *sub = to_bttv_sub_drv(dev->driver); if (sub->remove) sub->remove(sdev); - return 0; } struct bus_type bttv_sub_bus_type = { diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index bb1065990aeb..660df7d269fa 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -91,7 +91,7 @@ static int memstick_device_probe(struct device *dev) return rc; } -static int memstick_device_remove(struct device *dev) +static void memstick_device_remove(struct device *dev) { struct memstick_dev *card = container_of(dev, struct memstick_dev, dev); @@ -105,7 +105,6 @@ static int memstick_device_remove(struct device *dev) } put_device(dev); - return 0; } #ifdef CONFIG_PM diff --git a/drivers/mfd/mcp-core.c b/drivers/mfd/mcp-core.c index eff9423e90f5..2fa592c37c6f 100644 --- a/drivers/mfd/mcp-core.c +++ b/drivers/mfd/mcp-core.c @@ -33,13 +33,12 @@ static int mcp_bus_probe(struct device *dev) return drv->probe(mcp); } -static int mcp_bus_remove(struct device *dev) +static void mcp_bus_remove(struct device *dev) { struct mcp *mcp = to_mcp(dev); struct mcp_driver *drv = to_mcp_driver(dev->driver); drv->remove(mcp); - return 0; } static struct bus_type mcp_bus_type = { diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 935acc6bbf3c..3bf2bb4fd152 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -884,7 +884,7 @@ static int mei_cl_device_probe(struct device *dev) * * Return: 0 on success; < 0 otherwise */ -static int mei_cl_device_remove(struct device *dev) +static void mei_cl_device_remove(struct device *dev) { struct mei_cl_device *cldev = to_mei_cl_device(dev); struct mei_cl_driver *cldrv = to_mei_cl_driver(dev->driver); @@ -896,8 +896,6 @@ static int mei_cl_device_remove(struct device *dev) mei_cl_bus_module_put(cldev); module_put(THIS_MODULE); - - return 0; } static ssize_t name_show(struct device *dev, struct device_attribute *a, diff --git a/drivers/misc/tifm_core.c b/drivers/misc/tifm_core.c index 667e574a7df2..52656fc87e99 100644 --- a/drivers/misc/tifm_core.c +++ b/drivers/misc/tifm_core.c @@ -87,7 +87,7 @@ static void tifm_dummy_event(struct tifm_dev *sock) return; } -static int tifm_device_remove(struct device *dev) +static void tifm_device_remove(struct device *dev) { struct tifm_dev *sock = container_of(dev, struct tifm_dev, dev); struct tifm_driver *drv = container_of(dev->driver, struct tifm_driver, @@ -101,7 +101,6 @@ static int tifm_device_remove(struct device *dev) } put_device(dev); - return 0; } #ifdef CONFIG_PM diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c index 4383c262b3f5..f6b7a9c5bbff 100644 --- a/drivers/mmc/core/bus.c +++ b/drivers/mmc/core/bus.c @@ -140,14 +140,12 @@ static int mmc_bus_probe(struct device *dev) return drv->probe(card); } -static int mmc_bus_remove(struct device *dev) +static void mmc_bus_remove(struct device *dev) { struct mmc_driver *drv = to_mmc_driver(dev->driver); struct mmc_card *card = mmc_dev_to_card(dev); drv->remove(card); - - return 0; } static void mmc_bus_shutdown(struct device *dev) diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index 3d709029e07c..fda03b35c14a 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -203,7 +203,7 @@ disable_runtimepm: return ret; } -static int sdio_bus_remove(struct device *dev) +static void sdio_bus_remove(struct device *dev) { struct sdio_driver *drv = to_sdio_driver(dev->driver); struct sdio_func *func = dev_to_sdio_func(dev); @@ -232,8 +232,6 @@ static int sdio_bus_remove(struct device *dev) pm_runtime_put_sync(dev); dev_pm_domain_detach(dev, false); - - return 0; } static const struct dev_pm_ops sdio_bus_pm_ops = { diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c index ccec29970d5b..14b154929533 100644 --- a/drivers/net/netdevsim/bus.c +++ b/drivers/net/netdevsim/bus.c @@ -370,12 +370,11 @@ static int nsim_bus_probe(struct device *dev) return nsim_dev_probe(nsim_bus_dev); } -static int nsim_bus_remove(struct device *dev) +static void nsim_bus_remove(struct device *dev) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); nsim_dev_remove(nsim_bus_dev); - return 0; } static int nsim_num_vf(struct device *dev) diff --git a/drivers/ntb/core.c b/drivers/ntb/core.c index f8f75a504a58..27dd93deff6e 100644 --- a/drivers/ntb/core.c +++ b/drivers/ntb/core.c @@ -271,7 +271,7 @@ static int ntb_probe(struct device *dev) return rc; } -static int ntb_remove(struct device *dev) +static void ntb_remove(struct device *dev) { struct ntb_dev *ntb; struct ntb_client *client; @@ -283,8 +283,6 @@ static int ntb_remove(struct device *dev) client->ops.remove(client, ntb); put_device(dev); } - - return 0; } static void ntb_dev_release(struct device *dev) diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 4a02561cfb96..a9b97ebc71ac 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -304,7 +304,7 @@ static int ntb_transport_bus_probe(struct device *dev) return rc; } -static int ntb_transport_bus_remove(struct device *dev) +static void ntb_transport_bus_remove(struct device *dev) { const struct ntb_transport_client *client; @@ -312,8 +312,6 @@ static int ntb_transport_bus_remove(struct device *dev) client->remove(dev); put_device(dev); - - return 0; } static struct bus_type ntb_transport_bus = { diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c index ad3d17c42e23..d9d04f27f89b 100644 --- a/drivers/nubus/bus.c +++ b/drivers/nubus/bus.c @@ -29,14 +29,12 @@ static int nubus_device_probe(struct device *dev) return err; } -static int nubus_device_remove(struct device *dev) +static void nubus_device_remove(struct device *dev) { struct nubus_driver *ndrv = to_nubus_driver(dev->driver); - int err = -ENODEV; if (dev->driver && ndrv->remove) - err = ndrv->remove(to_nubus_board(dev)); - return err; + ndrv->remove(to_nubus_board(dev)); } struct bus_type nubus_bus_type = { diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index e6aa87043a95..9dc7f3edd42b 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -108,7 +108,7 @@ static int nvdimm_bus_probe(struct device *dev) return rc; } -static int nvdimm_bus_remove(struct device *dev) +static void nvdimm_bus_remove(struct device *dev) { struct nd_device_driver *nd_drv = to_nd_device_driver(dev->driver); struct module *provider = to_bus_provider(dev); @@ -123,7 +123,6 @@ static int nvdimm_bus_remove(struct device *dev) dev_dbg(&nvdimm_bus->dev, "%s.remove(%s)\n", dev->driver->name, dev_name(dev)); module_put(provider); - return 0; } static void nvdimm_bus_shutdown(struct device *dev) diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 4b9ad96bf1b2..502eb79cd551 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -387,7 +387,7 @@ static int pci_epf_device_probe(struct device *dev) return driver->probe(epf); } -static int pci_epf_device_remove(struct device *dev) +static void pci_epf_device_remove(struct device *dev) { struct pci_epf *epf = to_pci_epf(dev); struct pci_epf_driver *driver = to_pci_epf_driver(dev->driver); @@ -395,8 +395,6 @@ static int pci_epf_device_remove(struct device *dev) if (driver->remove) driver->remove(epf); epf->driver = NULL; - - return 0; } static struct bus_type pci_epf_bus_type = { diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 3a72352aa5cf..a0615395500a 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -440,7 +440,7 @@ static int pci_device_probe(struct device *dev) return error; } -static int pci_device_remove(struct device *dev) +static void pci_device_remove(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct pci_driver *drv = pci_dev->driver; @@ -476,7 +476,6 @@ static int pci_device_remove(struct device *dev) */ pci_dev_put(pci_dev); - return 0; } static void pci_device_shutdown(struct device *dev) diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c index bd81aa64d011..5bd1b80424e7 100644 --- a/drivers/pcmcia/ds.c +++ b/drivers/pcmcia/ds.c @@ -350,7 +350,7 @@ static void pcmcia_card_remove(struct pcmcia_socket *s, struct pcmcia_device *le return; } -static int pcmcia_device_remove(struct device *dev) +static void pcmcia_device_remove(struct device *dev) { struct pcmcia_device *p_dev; struct pcmcia_driver *p_drv; @@ -389,8 +389,6 @@ static int pcmcia_device_remove(struct device *dev) /* references from pcmcia_device_probe */ pcmcia_put_dev(p_dev); module_put(p_drv->owner); - - return 0; } diff --git a/drivers/platform/surface/aggregator/bus.c b/drivers/platform/surface/aggregator/bus.c index 0169677c243e..0a40dd9c94ed 100644 --- a/drivers/platform/surface/aggregator/bus.c +++ b/drivers/platform/surface/aggregator/bus.c @@ -316,14 +316,12 @@ static int ssam_bus_probe(struct device *dev) ->probe(to_ssam_device(dev)); } -static int ssam_bus_remove(struct device *dev) +static void ssam_bus_remove(struct device *dev) { struct ssam_device_driver *sdrv = to_ssam_device_driver(dev->driver); if (sdrv->remove) sdrv->remove(to_ssam_device(dev)); - - return 0; } struct bus_type ssam_bus_type = { diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 62e0d56a3332..a76313006bdc 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -980,7 +980,7 @@ probe_failure: return ret; } -static int wmi_dev_remove(struct device *dev) +static void wmi_dev_remove(struct device *dev) { struct wmi_block *wblock = dev_to_wblock(dev); struct wmi_driver *wdriver = @@ -997,8 +997,6 @@ static int wmi_dev_remove(struct device *dev) if (ACPI_FAILURE(wmi_method_enable(wblock, 0))) dev_warn(dev, "failed to disable device\n"); - - return 0; } static struct class wmi_bus_class = { diff --git a/drivers/pnp/driver.c b/drivers/pnp/driver.c index c29d590c5e4f..cc6757dfa3f1 100644 --- a/drivers/pnp/driver.c +++ b/drivers/pnp/driver.c @@ -123,7 +123,7 @@ fail: return error; } -static int pnp_device_remove(struct device *dev) +static void pnp_device_remove(struct device *dev) { struct pnp_dev *pnp_dev = to_pnp_dev(dev); struct pnp_driver *drv = pnp_dev->driver; @@ -139,7 +139,6 @@ static int pnp_device_remove(struct device *dev) pnp_disable_dev(pnp_dev); pnp_device_detach(pnp_dev); - return 0; } static void pnp_device_shutdown(struct device *dev) diff --git a/drivers/rapidio/rio-driver.c b/drivers/rapidio/rio-driver.c index 72874153972e..a72bb0a40fcf 100644 --- a/drivers/rapidio/rio-driver.c +++ b/drivers/rapidio/rio-driver.c @@ -112,7 +112,7 @@ static int rio_device_probe(struct device *dev) * driver, then run the driver remove() method. Then update * the reference count. */ -static int rio_device_remove(struct device *dev) +static void rio_device_remove(struct device *dev) { struct rio_dev *rdev = to_rio_dev(dev); struct rio_driver *rdrv = rdev->driver; @@ -124,8 +124,6 @@ static int rio_device_remove(struct device *dev) } rio_dev_put(rdev); - - return 0; } static void rio_device_shutdown(struct device *dev) diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index c1404d3dae2c..9151836190ce 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -530,14 +530,13 @@ out: return err; } -static int rpmsg_dev_remove(struct device *dev) +static void rpmsg_dev_remove(struct device *dev) { struct rpmsg_device *rpdev = to_rpmsg_device(dev); struct rpmsg_driver *rpdrv = to_rpmsg_driver(rpdev->dev.driver); - int err = 0; if (rpdev->ops->announce_destroy) - err = rpdev->ops->announce_destroy(rpdev); + rpdev->ops->announce_destroy(rpdev); if (rpdrv->remove) rpdrv->remove(rpdev); @@ -546,8 +545,6 @@ static int rpmsg_dev_remove(struct device *dev) if (rpdev->ept) rpmsg_destroy_ept(rpdev->ept); - - return err; } static struct bus_type rpmsg_bus = { diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index a6aeab1ea0ae..382c5b5f8cd3 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -439,15 +439,13 @@ module_exit(cleanup_ccwgroup); /************************** driver stuff ******************************/ -static int ccwgroup_remove(struct device *dev) +static void ccwgroup_remove(struct device *dev) { struct ccwgroup_device *gdev = to_ccwgroupdev(dev); struct ccwgroup_driver *gdrv = to_ccwgroupdrv(dev->driver); if (gdrv->remove) gdrv->remove(gdev); - - return 0; } static void ccwgroup_shutdown(struct device *dev) diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 092fd1ea5799..ebc321edba51 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -1371,7 +1371,7 @@ static int css_probe(struct device *dev) return ret; } -static int css_remove(struct device *dev) +static void css_remove(struct device *dev) { struct subchannel *sch; @@ -1379,8 +1379,6 @@ static int css_remove(struct device *dev) if (sch->driver->remove) sch->driver->remove(sch); sch->driver = NULL; - - return 0; } static void css_shutdown(struct device *dev) diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index cd5d2d4d8e46..adf33b653d87 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1741,7 +1741,7 @@ ccw_device_probe (struct device *dev) return 0; } -static int ccw_device_remove(struct device *dev) +static void ccw_device_remove(struct device *dev) { struct ccw_device *cdev = to_ccwdev(dev); struct ccw_driver *cdrv = cdev->drv; @@ -1775,8 +1775,6 @@ static int ccw_device_remove(struct device *dev) spin_unlock_irq(cdev->ccwlock); io_subchannel_quiesce(sch); __disable_cmf(cdev); - - return 0; } static void ccw_device_shutdown(struct device *dev) diff --git a/drivers/s390/cio/scm.c b/drivers/s390/cio/scm.c index b31711307e5a..b6b4589c70bd 100644 --- a/drivers/s390/cio/scm.c +++ b/drivers/s390/cio/scm.c @@ -28,15 +28,13 @@ static int scmdev_probe(struct device *dev) return scmdrv->probe ? scmdrv->probe(scmdev) : -ENODEV; } -static int scmdev_remove(struct device *dev) +static void scmdev_remove(struct device *dev) { struct scm_device *scmdev = to_scm_dev(dev); struct scm_driver *scmdrv = to_scm_drv(dev->driver); if (scmdrv->remove) scmdrv->remove(scmdev); - - return 0; } static int scmdev_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 8d3a1d84a757..0992edcaf1af 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -901,7 +901,7 @@ out: return rc; } -static int ap_device_remove(struct device *dev) +static void ap_device_remove(struct device *dev) { struct ap_device *ap_dev = to_ap_dev(dev); struct ap_driver *ap_drv = ap_dev->drv; @@ -926,8 +926,6 @@ static int ap_device_remove(struct device *dev) ap_dev->drv = NULL; put_device(dev); - - return 0; } struct ap_queue *ap_get_qdev(ap_qid_t qid) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 5b3a20a140f9..58f69366bdcc 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -7674,7 +7674,7 @@ static int sdebug_driver_probe(struct device *dev) return error; } -static int sdebug_driver_remove(struct device *dev) +static void sdebug_driver_remove(struct device *dev) { struct sdebug_host_info *sdbg_host; struct sdebug_dev_info *sdbg_devinfo, *tmp; @@ -7691,7 +7691,6 @@ static int sdebug_driver_remove(struct device *dev) } scsi_host_put(sdbg_host->shost); - return 0; } static int pseudo_lld_bus_match(struct device *dev, diff --git a/drivers/sh/superhyway/superhyway.c b/drivers/sh/superhyway/superhyway.c index 348836b90605..c0ab904c76ec 100644 --- a/drivers/sh/superhyway/superhyway.c +++ b/drivers/sh/superhyway/superhyway.c @@ -150,17 +150,13 @@ static int superhyway_device_probe(struct device *dev) return -ENODEV; } -static int superhyway_device_remove(struct device *dev) +static void superhyway_device_remove(struct device *dev) { struct superhyway_device *shyway_dev = to_superhyway_device(dev); struct superhyway_driver *shyway_drv = to_superhyway_driver(dev->driver); - if (shyway_drv && shyway_drv->remove) { + if (shyway_drv && shyway_drv->remove) shyway_drv->remove(shyway_dev); - return 0; - } - - return -ENODEV; } /** diff --git a/drivers/siox/siox-core.c b/drivers/siox/siox-core.c index 1794ff0106bc..7c4f32d76966 100644 --- a/drivers/siox/siox-core.c +++ b/drivers/siox/siox-core.c @@ -520,7 +520,7 @@ static int siox_probe(struct device *dev) return sdriver->probe(sdevice); } -static int siox_remove(struct device *dev) +static void siox_remove(struct device *dev) { struct siox_driver *sdriver = container_of(dev->driver, struct siox_driver, driver); @@ -528,8 +528,6 @@ static int siox_remove(struct device *dev) if (sdriver->remove) sdriver->remove(sdevice); - - return 0; } static void siox_shutdown(struct device *dev) diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index 1d2bc181da05..78480e332ab8 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -81,7 +81,7 @@ static int slim_device_probe(struct device *dev) return ret; } -static int slim_device_remove(struct device *dev) +static void slim_device_remove(struct device *dev) { struct slim_device *sbdev = to_slim_device(dev); struct slim_driver *sbdrv; @@ -91,8 +91,6 @@ static int slim_device_remove(struct device *dev) if (sbdrv->remove) sbdrv->remove(sbdev); } - - return 0; } static int slim_device_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index 7abfc8c4fdc7..475a57b435b2 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -217,7 +217,7 @@ static int apr_device_probe(struct device *dev) return adrv->probe(adev); } -static int apr_device_remove(struct device *dev) +static void apr_device_remove(struct device *dev) { struct apr_device *adev = to_apr_device(dev); struct apr_driver *adrv; @@ -231,8 +231,6 @@ static int apr_device_remove(struct device *dev) idr_remove(&apr->svcs_idr, adev->svc_id); spin_unlock(&apr->svcs_lock); } - - return 0; } static int apr_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index c99181165321..ad2b558dc9cb 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -405,7 +405,7 @@ static int spi_probe(struct device *dev) return ret; } -static int spi_remove(struct device *dev) +static void spi_remove(struct device *dev) { const struct spi_driver *sdrv = to_spi_driver(dev->driver); @@ -420,8 +420,6 @@ static int spi_remove(struct device *dev) } dev_pm_domain_detach(dev, true); - - return 0; } static void spi_shutdown(struct device *dev) diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c index 51f5aeb65b3b..b37ead9e2fad 100644 --- a/drivers/spmi/spmi.c +++ b/drivers/spmi/spmi.c @@ -345,7 +345,7 @@ fail_probe: return err; } -static int spmi_drv_remove(struct device *dev) +static void spmi_drv_remove(struct device *dev) { const struct spmi_driver *sdrv = to_spmi_driver(dev->driver); @@ -356,7 +356,6 @@ static int spmi_drv_remove(struct device *dev) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); pm_runtime_put_noidle(dev); - return 0; } static void spmi_drv_shutdown(struct device *dev) diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index 3a29b5570f9f..8a93c83cb6f8 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -283,7 +283,7 @@ static void ssb_device_shutdown(struct device *dev) ssb_drv->shutdown(ssb_dev); } -static int ssb_device_remove(struct device *dev) +static void ssb_device_remove(struct device *dev) { struct ssb_device *ssb_dev = dev_to_ssb_dev(dev); struct ssb_driver *ssb_drv = drv_to_ssb_drv(dev->driver); @@ -291,8 +291,6 @@ static int ssb_device_remove(struct device *dev) if (ssb_drv && ssb_drv->remove) ssb_drv->remove(ssb_dev); ssb_device_put(ssb_dev); - - return 0; } static int ssb_device_probe(struct device *dev) diff --git a/drivers/staging/fieldbus/anybuss/host.c b/drivers/staging/fieldbus/anybuss/host.c index 0f730efe9a6d..8a75f6642c78 100644 --- a/drivers/staging/fieldbus/anybuss/host.c +++ b/drivers/staging/fieldbus/anybuss/host.c @@ -1186,15 +1186,13 @@ static int anybus_bus_probe(struct device *dev) return adrv->probe(adev); } -static int anybus_bus_remove(struct device *dev) +static void anybus_bus_remove(struct device *dev) { struct anybuss_client_driver *adrv = to_anybuss_client_driver(dev->driver); if (adrv->remove) adrv->remove(to_anybuss_client(dev)); - - return 0; } static struct bus_type anybus_bus = { diff --git a/drivers/staging/greybus/gbphy.c b/drivers/staging/greybus/gbphy.c index 13d319860da5..5a5c17a4519b 100644 --- a/drivers/staging/greybus/gbphy.c +++ b/drivers/staging/greybus/gbphy.c @@ -169,7 +169,7 @@ static int gbphy_dev_probe(struct device *dev) return ret; } -static int gbphy_dev_remove(struct device *dev) +static void gbphy_dev_remove(struct device *dev) { struct gbphy_driver *gbphy_drv = to_gbphy_driver(dev->driver); struct gbphy_device *gbphy_dev = to_gbphy_dev(dev); @@ -180,8 +180,6 @@ static int gbphy_dev_remove(struct device *dev) pm_runtime_set_suspended(dev); pm_runtime_put_noidle(dev); pm_runtime_dont_use_autosuspend(dev); - - return 0; } static struct bus_type gbphy_bus_type = { diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 6d0b0e67e79e..cbb2118fb35e 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -81,7 +81,7 @@ static int tcm_loop_show_info(struct seq_file *m, struct Scsi_Host *host) } static int tcm_loop_driver_probe(struct device *); -static int tcm_loop_driver_remove(struct device *); +static void tcm_loop_driver_remove(struct device *); static int pseudo_lld_bus_match(struct device *dev, struct device_driver *dev_driver) @@ -363,7 +363,7 @@ static int tcm_loop_driver_probe(struct device *dev) return 0; } -static int tcm_loop_driver_remove(struct device *dev) +static void tcm_loop_driver_remove(struct device *dev) { struct tcm_loop_hba *tl_hba; struct Scsi_Host *sh; @@ -373,7 +373,6 @@ static int tcm_loop_driver_remove(struct device *dev) scsi_remove_host(sh); scsi_host_put(sh); - return 0; } static void tcm_loop_release_adapter(struct device *dev) diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c index a062befcb3b2..7018d959f775 100644 --- a/drivers/thunderbolt/domain.c +++ b/drivers/thunderbolt/domain.c @@ -86,7 +86,7 @@ static int tb_service_probe(struct device *dev) return driver->probe(svc, id); } -static int tb_service_remove(struct device *dev) +static void tb_service_remove(struct device *dev) { struct tb_service *svc = tb_to_service(dev); struct tb_service_driver *driver; @@ -94,8 +94,6 @@ static int tb_service_remove(struct device *dev) driver = container_of(dev->driver, struct tb_service_driver, driver); if (driver->remove) driver->remove(svc); - - return 0; } static void tb_service_shutdown(struct device *dev) diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c index 9cdfcfe07e87..92498961fd92 100644 --- a/drivers/tty/serdev/core.c +++ b/drivers/tty/serdev/core.c @@ -421,15 +421,13 @@ static int serdev_drv_probe(struct device *dev) return ret; } -static int serdev_drv_remove(struct device *dev) +static void serdev_drv_remove(struct device *dev) { const struct serdev_device_driver *sdrv = to_serdev_device_driver(dev->driver); if (sdrv->remove) sdrv->remove(to_serdev_device(dev)); dev_pm_domain_detach(dev, true); - - return 0; } static struct bus_type serdev_bus_type = { diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index 7e13b74e60e5..4169cf40a03b 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -78,14 +78,12 @@ static int ulpi_probe(struct device *dev) return drv->probe(to_ulpi_dev(dev)); } -static int ulpi_remove(struct device *dev) +static void ulpi_remove(struct device *dev) { struct ulpi_driver *drv = to_ulpi_driver(dev->driver); if (drv->remove) drv->remove(to_ulpi_dev(dev)); - - return 0; } static struct bus_type ulpi_bus = { diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c index 7133818a58b9..9e38142acd38 100644 --- a/drivers/usb/serial/bus.c +++ b/drivers/usb/serial/bus.c @@ -74,7 +74,7 @@ err_autopm_put: return retval; } -static int usb_serial_device_remove(struct device *dev) +static void usb_serial_device_remove(struct device *dev) { struct usb_serial_port *port = to_usb_serial_port(dev); struct usb_serial_driver *driver; @@ -101,8 +101,6 @@ static int usb_serial_device_remove(struct device *dev) if (!autopm_err) usb_autopm_put_interface(port->serial->interface); - - return 0; } static ssize_t new_id_store(struct device_driver *driver, diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index 7f3c9a8e2bf0..78e0e78954f2 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -382,7 +382,7 @@ static int typec_probe(struct device *dev) return ret; } -static int typec_remove(struct device *dev) +static void typec_remove(struct device *dev) { struct typec_altmode_driver *drv = to_altmode_driver(dev->driver); struct typec_altmode *adev = to_typec_altmode(dev); @@ -400,8 +400,6 @@ static int typec_remove(struct device *dev) adev->desc = NULL; adev->ops = NULL; - - return 0; } struct bus_type typec_bus = { diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index bb3f1d1f0422..3fc4525fc05c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -34,15 +34,13 @@ static int vdpa_dev_probe(struct device *d) return ret; } -static int vdpa_dev_remove(struct device *d) +static void vdpa_dev_remove(struct device *d) { struct vdpa_device *vdev = dev_to_vdpa(d); struct vdpa_driver *drv = drv_to_vdpa(vdev->dev.driver); if (drv && drv->remove) drv->remove(vdev); - - return 0; } static struct bus_type vdpa_bus = { diff --git a/drivers/vfio/mdev/mdev_driver.c b/drivers/vfio/mdev/mdev_driver.c index c368ec824e2b..e2cb1ff56f6c 100644 --- a/drivers/vfio/mdev/mdev_driver.c +++ b/drivers/vfio/mdev/mdev_driver.c @@ -57,7 +57,7 @@ static int mdev_probe(struct device *dev) return ret; } -static int mdev_remove(struct device *dev) +static void mdev_remove(struct device *dev) { struct mdev_driver *drv = container_of(dev->driver, struct mdev_driver, driver); @@ -67,8 +67,6 @@ static int mdev_remove(struct device *dev) drv->remove(mdev); mdev_detach_iommu(mdev); - - return 0; } static int mdev_match(struct device *dev, struct device_driver *drv) diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 4b15c00c0a0a..2a6055c0d4d3 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -278,7 +278,7 @@ err: } -static int virtio_dev_remove(struct device *_d) +static void virtio_dev_remove(struct device *_d) { struct virtio_device *dev = dev_to_virtio(_d); struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); @@ -292,7 +292,6 @@ static int virtio_dev_remove(struct device *_d) /* Acknowledge the device's existence again. */ virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); - return 0; } static struct bus_type virtio_bus = { diff --git a/drivers/vlynq/vlynq.c b/drivers/vlynq/vlynq.c index e966981c0215..4af6615808cc 100644 --- a/drivers/vlynq/vlynq.c +++ b/drivers/vlynq/vlynq.c @@ -342,14 +342,12 @@ static int vlynq_device_probe(struct device *dev) return result; } -static int vlynq_device_remove(struct device *dev) +static void vlynq_device_remove(struct device *dev) { struct vlynq_driver *drv = to_vlynq_driver(dev->driver); if (drv->remove) drv->remove(to_vlynq_device(dev)); - - return 0; } int __vlynq_register_driver(struct vlynq_driver *driver, struct module *owner) diff --git a/drivers/vme/vme.c b/drivers/vme/vme.c index 1b15afea28ee..8dba20186be3 100644 --- a/drivers/vme/vme.c +++ b/drivers/vme/vme.c @@ -1990,7 +1990,7 @@ static int vme_bus_probe(struct device *dev) return -ENODEV; } -static int vme_bus_remove(struct device *dev) +static void vme_bus_remove(struct device *dev) { struct vme_driver *driver; struct vme_dev *vdev = dev_to_vme_dev(dev); @@ -1998,8 +1998,6 @@ static int vme_bus_remove(struct device *dev) driver = dev->platform_data; if (driver->remove) driver->remove(vdev); - - return 0; } struct bus_type vme_bus_type = { diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 2a93b7c9c159..2754bdfadcb8 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -106,7 +106,7 @@ void xs_request_exit(struct xb_req_data *req); int xenbus_match(struct device *_dev, struct device_driver *_drv); int xenbus_dev_probe(struct device *_dev); -int xenbus_dev_remove(struct device *_dev); +void xenbus_dev_remove(struct device *_dev); int xenbus_register_driver_common(struct xenbus_driver *drv, struct xen_bus_type *bus, struct module *owner, diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 33d09b3f6211..bd003ca8acbe 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -325,7 +325,7 @@ fail: } EXPORT_SYMBOL_GPL(xenbus_dev_probe); -int xenbus_dev_remove(struct device *_dev) +void xenbus_dev_remove(struct device *_dev) { struct xenbus_device *dev = to_xenbus_device(_dev); struct xenbus_driver *drv = to_xenbus_driver(_dev->driver); @@ -355,8 +355,6 @@ int xenbus_dev_remove(struct device *_dev) if (!drv->allow_rebind || xenbus_read_driver_state(dev->nodename) == XenbusStateClosing) xenbus_switch_state(dev, XenbusStateClosed); - - return 0; } EXPORT_SYMBOL_GPL(xenbus_dev_remove); diff --git a/drivers/zorro/zorro-driver.c b/drivers/zorro/zorro-driver.c index 0dd7cbcec2b0..c18524bb8b2a 100644 --- a/drivers/zorro/zorro-driver.c +++ b/drivers/zorro/zorro-driver.c @@ -62,7 +62,7 @@ static int zorro_device_probe(struct device *dev) } -static int zorro_device_remove(struct device *dev) +static void zorro_device_remove(struct device *dev) { struct zorro_dev *z = to_zorro_dev(dev); struct zorro_driver *drv = to_zorro_driver(dev->driver); @@ -72,7 +72,6 @@ static int zorro_device_remove(struct device *dev) drv->remove(z); z->driver = NULL; } - return 0; } diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 1ea5e1d1545b..062777a45a74 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -91,7 +91,7 @@ struct bus_type { int (*uevent)(struct device *dev, struct kobj_uevent_env *env); int (*probe)(struct device *dev); void (*sync_state)(struct device *dev); - int (*remove)(struct device *dev); + void (*remove)(struct device *dev); void (*shutdown)(struct device *dev); int (*online)(struct device *dev); diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c index 6ddf646cda65..0d31a6d71468 100644 --- a/sound/ac97/bus.c +++ b/sound/ac97/bus.c @@ -514,7 +514,7 @@ static int ac97_bus_probe(struct device *dev) return ret; } -static int ac97_bus_remove(struct device *dev) +static void ac97_bus_remove(struct device *dev) { struct ac97_codec_device *adev = to_ac97_device(dev); struct ac97_codec_driver *adrv = to_ac97_driver(dev->driver); @@ -522,7 +522,7 @@ static int ac97_bus_remove(struct device *dev) ret = pm_runtime_resume_and_get(dev); if (ret < 0) - return ret; + return; ret = adrv->remove(adev); pm_runtime_put_noidle(dev); @@ -530,8 +530,6 @@ static int ac97_bus_remove(struct device *dev) ac97_put_disable_clk(adev); pm_runtime_disable(dev); - - return ret; } static struct bus_type ac97_bus_type = { diff --git a/sound/aoa/soundbus/core.c b/sound/aoa/soundbus/core.c index 002fb5bf220b..c9579d97fbab 100644 --- a/sound/aoa/soundbus/core.c +++ b/sound/aoa/soundbus/core.c @@ -104,7 +104,7 @@ static int soundbus_uevent(struct device *dev, struct kobj_uevent_env *env) return retval; } -static int soundbus_device_remove(struct device *dev) +static void soundbus_device_remove(struct device *dev) { struct soundbus_dev * soundbus_dev = to_soundbus_device(dev); struct soundbus_driver * drv = to_soundbus_driver(dev->driver); @@ -112,8 +112,6 @@ static int soundbus_device_remove(struct device *dev) if (dev->driver && drv->remove) drv->remove(soundbus_dev); soundbus_dev_put(soundbus_dev); - - return 0; } static void soundbus_device_shutdown(struct device *dev) -- cgit v1.2.3 From 853a9ae29e978d37f5dfa72622a68c9ae3d7fa89 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 14 Jul 2021 10:04:27 +0200 Subject: serial: 8250: fix handle_irq locking The 8250 handle_irq callback is not just called from the interrupt handler but also from a timer callback when polling (e.g. for ports without an interrupt line). Consequently the callback must explicitly disable interrupts to avoid a potential deadlock with another interrupt in polled mode. Add back an irqrestore-version of the sysrq port-unlock helper and use it in the 8250 callbacks that need it. Fixes: 75f4e830fa9c ("serial: do not restore interrupt state in sysrq helper") Cc: stable@vger.kernel.org # 5.13 Cc: Joel Stanley Cc: Andrew Jeffery Reported-by: kernel test robot Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210714080427.28164-1-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_aspeed_vuart.c | 5 +++-- drivers/tty/serial/8250/8250_fsl.c | 5 +++-- drivers/tty/serial/8250/8250_port.c | 5 +++-- include/linux/serial_core.h | 24 ++++++++++++++++++++++++ 4 files changed, 33 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c index 4caab8714e2c..2350fb3bb5e4 100644 --- a/drivers/tty/serial/8250/8250_aspeed_vuart.c +++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c @@ -329,6 +329,7 @@ static int aspeed_vuart_handle_irq(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int iir, lsr; + unsigned long flags; unsigned int space, count; iir = serial_port_in(port, UART_IIR); @@ -336,7 +337,7 @@ static int aspeed_vuart_handle_irq(struct uart_port *port) if (iir & UART_IIR_NO_INT) return 0; - spin_lock(&port->lock); + spin_lock_irqsave(&port->lock, flags); lsr = serial_port_in(port, UART_LSR); @@ -370,7 +371,7 @@ static int aspeed_vuart_handle_irq(struct uart_port *port) if (lsr & UART_LSR_THRE) serial8250_tx_chars(up); - uart_unlock_and_check_sysrq(port); + uart_unlock_and_check_sysrq_irqrestore(port, flags); return 1; } diff --git a/drivers/tty/serial/8250/8250_fsl.c b/drivers/tty/serial/8250/8250_fsl.c index 4e75d2e4f87c..fc65a2293ce9 100644 --- a/drivers/tty/serial/8250/8250_fsl.c +++ b/drivers/tty/serial/8250/8250_fsl.c @@ -30,10 +30,11 @@ struct fsl8250_data { int fsl8250_handle_irq(struct uart_port *port) { unsigned char lsr, orig_lsr; + unsigned long flags; unsigned int iir; struct uart_8250_port *up = up_to_u8250p(port); - spin_lock(&up->port.lock); + spin_lock_irqsave(&up->port.lock, flags); iir = port->serial_in(port, UART_IIR); if (iir & UART_IIR_NO_INT) { @@ -82,7 +83,7 @@ int fsl8250_handle_irq(struct uart_port *port) up->lsr_saved_flags = orig_lsr; - uart_unlock_and_check_sysrq(&up->port); + uart_unlock_and_check_sysrq_irqrestore(&up->port, flags); return 1; } diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 2e7000f79b03..1da29a219842 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1899,11 +1899,12 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) unsigned char status; struct uart_8250_port *up = up_to_u8250p(port); bool skip_rx = false; + unsigned long flags; if (iir & UART_IIR_NO_INT) return 0; - spin_lock(&port->lock); + spin_lock_irqsave(&port->lock, flags); status = serial_port_in(port, UART_LSR); @@ -1929,7 +1930,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) (up->ier & UART_IER_THRI)) serial8250_tx_chars(up); - uart_unlock_and_check_sysrq(port); + uart_unlock_and_check_sysrq_irqrestore(port, flags); return 1; } diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 52d7fb92a69d..c58cc142d23f 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -518,6 +518,25 @@ static inline void uart_unlock_and_check_sysrq(struct uart_port *port) if (sysrq_ch) handle_sysrq(sysrq_ch); } + +static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, + unsigned long flags) +{ + int sysrq_ch; + + if (!port->has_sysrq) { + spin_unlock_irqrestore(&port->lock, flags); + return; + } + + sysrq_ch = port->sysrq_ch; + port->sysrq_ch = 0; + + spin_unlock_irqrestore(&port->lock, flags); + + if (sysrq_ch) + handle_sysrq(sysrq_ch); +} #else /* CONFIG_MAGIC_SYSRQ_SERIAL */ static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) { @@ -531,6 +550,11 @@ static inline void uart_unlock_and_check_sysrq(struct uart_port *port) { spin_unlock(&port->lock); } +static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, + unsigned long flags) +{ + spin_unlock_irqrestore(&port->lock, flags); +} #endif /* CONFIG_MAGIC_SYSRQ_SERIAL */ /* -- cgit v1.2.3 From 2b9fc773c31bb7cb7529757382013a8158bf7e9c Mon Sep 17 00:00:00 2001 From: Nava kishore Manne Date: Sat, 26 Jun 2021 21:22:44 +0530 Subject: drivers: firmware: Add PDI load API support This patch adds load PDI API support to enable full/partial PDI loading from linux. Programmable Device Image (PDI) is combination of headers, images and bitstream files to be loaded. Reviewed-by: Moritz Fischer Signed-off-by: Nava kishore Manne Link: https://lore.kernel.org/r/20210626155248.5004-2-nava.manne@xilinx.com Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/xilinx/zynqmp.c | 17 +++++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 10 ++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 15b138326ecc..2db571da9ad8 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -1011,6 +1011,23 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, } EXPORT_SYMBOL_GPL(zynqmp_pm_set_requirement); +/** + * zynqmp_pm_load_pdi - Load and process PDI + * @src: Source device where PDI is located + * @address: PDI src address + * + * This function provides support to load PDI from linux + * + * Return: Returns status, either success or error+reason + */ +int zynqmp_pm_load_pdi(const u32 src, const u64 address) +{ + return zynqmp_pm_invoke_fn(PM_LOAD_PDI, src, + lower_32_bits(address), + upper_32_bits(address), 0, NULL); +} +EXPORT_SYMBOL_GPL(zynqmp_pm_load_pdi); + /** * zynqmp_pm_aes - Access AES hardware to encrypt/decrypt the data using * AES-GCM core. diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 9d1a5c175065..56b426fe020c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -52,6 +52,10 @@ #define ZYNQMP_PM_CAPABILITY_WAKEUP 0x4U #define ZYNQMP_PM_CAPABILITY_UNUSABLE 0x8U +/* Loader commands */ +#define PM_LOAD_PDI 0x701 +#define PDI_SRC_DDR 0xF + /* * Firmware FPGA Manager flags * XILINX_ZYNQMP_PM_FPGA_FULL: FPGA full reconfiguration @@ -411,6 +415,7 @@ int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param, u32 *value); int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param, u32 value); +int zynqmp_pm_load_pdi(const u32 src, const u64 address); #else static inline int zynqmp_pm_get_api_version(u32 *version) { @@ -622,6 +627,11 @@ static inline int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param, { return -ENODEV; } + +static inline int zynqmp_pm_load_pdi(const u32 src, const u64 address) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 9ee11f0fff205b4b3df9750bff5e94f97c71b6a0 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Tue, 20 Jul 2021 21:42:57 +0200 Subject: ipv6: ioam: Data plane support for Pre-allocated Trace Implement support for processing the IOAM Pre-allocated Trace with IPv6, see [1] and [2]. Introduce a new IPv6 Hop-by-Hop TLV option, see IANA [3]. A new per-interface sysctl is introduced. The value is a boolean to accept (=1) or ignore (=0, by default) IPv6 IOAM options on ingress for an interface: - net.ipv6.conf.XXX.ioam6_enabled Two other sysctls are introduced to define IOAM IDs, represented by an integer. They are respectively per-namespace and per-interface: - net.ipv6.ioam6_id - net.ipv6.conf.XXX.ioam6_id The value of the first one represents the IOAM ID of the node itself (u32; max and default value = U32_MAX>>8, due to hop limit concatenation) while the other represents the IOAM ID of an interface (u16; max and default value = U16_MAX). Each "ioam6_id" sysctl has a "_wide" equivalent: - net.ipv6.ioam6_id_wide - net.ipv6.conf.XXX.ioam6_id_wide The value of the first one represents the wide IOAM ID of the node itself (u64; max and default value = U64_MAX>>8, due to hop limit concatenation) while the other represents the wide IOAM ID of an interface (u32; max and default value = U32_MAX). The use of short and wide equivalents is not exclusive, a deployment could choose to leverage both. For example, net.ipv6.conf.XXX.ioam6_id (short format) could be an identifier for a physical interface, whereas net.ipv6.conf.XXX.ioam6_id_wide (wide format) could be an identifier for a logical sub-interface. Documentation about new sysctls is provided at the end of this patchset. Two relativistic hash tables are used: one for IOAM namespaces, the other for IOAM schemas. A namespace can only have a single active schema and a schema can only be attached to a single namespace (1:1 relationship). [1] https://tools.ietf.org/html/draft-ietf-ippm-ioam-ipv6-options [2] https://tools.ietf.org/html/draft-ietf-ippm-ioam-data [3] https://www.iana.org/assignments/ipv6-parameters/ipv6-parameters.xhtml#ipv6-parameters-2 Signed-off-by: Justin Iurman Signed-off-by: David S. Miller --- include/linux/ioam6.h | 13 ++ include/linux/ipv6.h | 3 + include/net/ioam6.h | 64 +++++++++ include/net/netns/ipv6.h | 3 + include/uapi/linux/in6.h | 1 + include/uapi/linux/ioam6.h | 9 ++ include/uapi/linux/ipv6.h | 3 + net/ipv6/Makefile | 2 +- net/ipv6/addrconf.c | 37 +++++ net/ipv6/af_inet6.c | 10 ++ net/ipv6/exthdrs.c | 61 +++++++++ net/ipv6/ioam6.c | 333 +++++++++++++++++++++++++++++++++++++++++++++ net/ipv6/sysctl_net_ipv6.c | 19 +++ 13 files changed, 557 insertions(+), 1 deletion(-) create mode 100644 include/linux/ioam6.h create mode 100644 include/net/ioam6.h create mode 100644 net/ipv6/ioam6.c (limited to 'include/linux') diff --git a/include/linux/ioam6.h b/include/linux/ioam6.h new file mode 100644 index 000000000000..94a24b36998f --- /dev/null +++ b/include/linux/ioam6.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * IPv6 IOAM + * + * Author: + * Justin Iurman + */ +#ifndef _LINUX_IOAM6_H +#define _LINUX_IOAM6_H + +#include + +#endif /* _LINUX_IOAM6_H */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 70b2ad3b9884..ef4a69865737 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -76,6 +76,9 @@ struct ipv6_devconf { __s32 disable_policy; __s32 ndisc_tclass; __s32 rpl_seg_enabled; + __u32 ioam6_id; + __u32 ioam6_id_wide; + __u8 ioam6_enabled; struct ctl_table_header *sysctl_header; }; diff --git a/include/net/ioam6.h b/include/net/ioam6.h new file mode 100644 index 000000000000..772b91ee2e87 --- /dev/null +++ b/include/net/ioam6.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * IPv6 IOAM implementation + * + * Author: + * Justin Iurman + */ + +#ifndef _NET_IOAM6_H +#define _NET_IOAM6_H + +#include +#include +#include +#include + +struct ioam6_namespace { + struct rhash_head head; + struct rcu_head rcu; + + struct ioam6_schema __rcu *schema; + + __be16 id; + __be32 data; + __be64 data_wide; +}; + +struct ioam6_schema { + struct rhash_head head; + struct rcu_head rcu; + + struct ioam6_namespace __rcu *ns; + + u32 id; + int len; + __be32 hdr; + + u8 data[0]; +}; + +struct ioam6_pernet_data { + struct mutex lock; + struct rhashtable namespaces; + struct rhashtable schemas; +}; + +static inline struct ioam6_pernet_data *ioam6_pernet(struct net *net) +{ +#if IS_ENABLED(CONFIG_IPV6) + return net->ipv6.ioam6_data; +#else + return NULL; +#endif +} + +struct ioam6_namespace *ioam6_namespace(struct net *net, __be16 id); +void ioam6_fill_trace_data(struct sk_buff *skb, + struct ioam6_namespace *ns, + struct ioam6_trace_hdr *trace); + +int ioam6_init(void); +void ioam6_exit(void); + +#endif /* _NET_IOAM6_H */ diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index bde0b7adb4a3..a4b550380316 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -51,6 +51,8 @@ struct netns_sysctl_ipv6 { int max_dst_opts_len; int max_hbh_opts_len; int seg6_flowlabel; + u32 ioam6_id; + u64 ioam6_id_wide; bool skip_notify_on_dev_down; u8 fib_notify_on_flag_change; }; @@ -110,6 +112,7 @@ struct netns_ipv6 { spinlock_t lock; u32 seq; } ip6addrlbl_table; + struct ioam6_pernet_data *ioam6_data; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 5ad396a57eb3..c4c53a9ab959 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -145,6 +145,7 @@ struct in6_flowlabel_req { #define IPV6_TLV_PADN 1 #define IPV6_TLV_ROUTERALERT 5 #define IPV6_TLV_CALIPSO 7 /* RFC 5570 */ +#define IPV6_TLV_IOAM 49 /* TEMPORARY IANA allocation for IOAM */ #define IPV6_TLV_JUMBO 194 #define IPV6_TLV_HAO 201 /* home address option */ diff --git a/include/uapi/linux/ioam6.h b/include/uapi/linux/ioam6.h index 2177e4e49566..23ba6e85582f 100644 --- a/include/uapi/linux/ioam6.h +++ b/include/uapi/linux/ioam6.h @@ -12,6 +12,15 @@ #include #include +#define IOAM6_U16_UNAVAILABLE U16_MAX +#define IOAM6_U32_UNAVAILABLE U32_MAX +#define IOAM6_U64_UNAVAILABLE U64_MAX + +#define IOAM6_DEFAULT_ID (IOAM6_U32_UNAVAILABLE >> 8) +#define IOAM6_DEFAULT_ID_WIDE (IOAM6_U64_UNAVAILABLE >> 8) +#define IOAM6_DEFAULT_IF_ID IOAM6_U16_UNAVAILABLE +#define IOAM6_DEFAULT_IF_ID_WIDE IOAM6_U32_UNAVAILABLE + /* * IPv6 IOAM Option Header */ diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 70603775fe91..b243a53fa985 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -190,6 +190,9 @@ enum { DEVCONF_NDISC_TCLASS, DEVCONF_RPL_SEG_ENABLED, DEVCONF_RA_DEFRTR_METRIC, + DEVCONF_IOAM6_ENABLED, + DEVCONF_IOAM6_ID, + DEVCONF_IOAM6_ID_WIDE, DEVCONF_MAX }; diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index cf7b47bdb9b3..b7ef10d417d6 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -10,7 +10,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \ - udp_offload.o seg6.o fib6_notifier.o rpl.o + udp_offload.o seg6.o fib6_notifier.o rpl.o ioam6.o ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index bc330fffb4a8..1802287977f1 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -89,12 +89,15 @@ #include #include #include +#include #define INFINITY_LIFE_TIME 0xFFFFFFFF #define IPV6_MAX_STRLEN \ sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255") +static u32 ioam6_if_id_max = U16_MAX; + static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; @@ -237,6 +240,9 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, .disable_policy = 0, .rpl_seg_enabled = 0, + .ioam6_enabled = 0, + .ioam6_id = IOAM6_DEFAULT_IF_ID, + .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -293,6 +299,9 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, .disable_policy = 0, .rpl_seg_enabled = 0, + .ioam6_enabled = 0, + .ioam6_id = IOAM6_DEFAULT_IF_ID, + .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -5524,6 +5533,9 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass; array[DEVCONF_RPL_SEG_ENABLED] = cnf->rpl_seg_enabled; + array[DEVCONF_IOAM6_ENABLED] = cnf->ioam6_enabled; + array[DEVCONF_IOAM6_ID] = cnf->ioam6_id; + array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; } static inline size_t inet6_ifla6_size(void) @@ -6930,6 +6942,31 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "ioam6_enabled", + .data = &ipv6_devconf.ioam6_enabled, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = (void *)SYSCTL_ZERO, + .extra2 = (void *)SYSCTL_ONE, + }, + { + .procname = "ioam6_id", + .data = &ipv6_devconf.ioam6_id, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = (void *)SYSCTL_ZERO, + .extra2 = (void *)&ioam6_if_id_max, + }, + { + .procname = "ioam6_id_wide", + .data = &ipv6_devconf.ioam6_id_wide, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_douintvec, + }, { /* sentinel */ } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 2389ff702f51..d92c90d97763 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -62,6 +62,7 @@ #include #include #include +#include #include #include @@ -961,6 +962,9 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.fib_notify_on_flag_change = 0; atomic_set(&net->ipv6.fib6_sernum, 1); + net->ipv6.sysctl.ioam6_id = IOAM6_DEFAULT_ID; + net->ipv6.sysctl.ioam6_id_wide = IOAM6_DEFAULT_ID_WIDE; + err = ipv6_init_mibs(net); if (err) return err; @@ -1191,6 +1195,10 @@ static int __init inet6_init(void) if (err) goto rpl_fail; + err = ioam6_init(); + if (err) + goto ioam6_fail; + err = igmp6_late_init(); if (err) goto igmp6_late_err; @@ -1213,6 +1221,8 @@ sysctl_fail: igmp6_late_cleanup(); #endif igmp6_late_err: + ioam6_exit(); +ioam6_fail: rpl_exit(); rpl_fail: seg6_exit(); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 26882e165c9e..d897faa4e9e6 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -49,6 +49,9 @@ #include #endif #include +#include +#include +#include #include @@ -928,6 +931,60 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) return false; } +/* IOAM */ + +static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) +{ + struct ioam6_trace_hdr *trace; + struct ioam6_namespace *ns; + struct ioam6_hdr *hdr; + + /* Bad alignment (must be 4n-aligned) */ + if (optoff & 3) + goto drop; + + /* Ignore if IOAM is not enabled on ingress */ + if (!__in6_dev_get(skb->dev)->cnf.ioam6_enabled) + goto ignore; + + /* Truncated Option header */ + hdr = (struct ioam6_hdr *)(skb_network_header(skb) + optoff); + if (hdr->opt_len < 2) + goto drop; + + switch (hdr->type) { + case IOAM6_TYPE_PREALLOC: + /* Truncated Pre-allocated Trace header */ + if (hdr->opt_len < 2 + sizeof(*trace)) + goto drop; + + /* Malformed Pre-allocated Trace header */ + trace = (struct ioam6_trace_hdr *)((u8 *)hdr + sizeof(*hdr)); + if (hdr->opt_len < 2 + sizeof(*trace) + trace->remlen * 4) + goto drop; + + /* Ignore if the IOAM namespace is unknown */ + ns = ioam6_namespace(ipv6_skb_net(skb), trace->namespace_id); + if (!ns) + goto ignore; + + if (!skb_valid_dst(skb)) + ip6_route_input(skb); + + ioam6_fill_trace_data(skb, ns, trace); + break; + default: + break; + } + +ignore: + return true; + +drop: + kfree_skb(skb); + return false; +} + /* Jumbo payload */ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) @@ -999,6 +1056,10 @@ static const struct tlvtype_proc tlvprochopopt_lst[] = { .type = IPV6_TLV_ROUTERALERT, .func = ipv6_hop_ra, }, + { + .type = IPV6_TLV_IOAM, + .func = ipv6_hop_ioam, + }, { .type = IPV6_TLV_JUMBO, .func = ipv6_hop_jumbo, diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c new file mode 100644 index 000000000000..ba629e1b9408 --- /dev/null +++ b/net/ipv6/ioam6.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * IPv6 IOAM implementation + * + * Author: + * Justin Iurman + */ + +#include +#include +#include +#include +#include +#include + +#include +#include + +static void ioam6_ns_release(struct ioam6_namespace *ns) +{ + kfree_rcu(ns, rcu); +} + +static void ioam6_sc_release(struct ioam6_schema *sc) +{ + kfree_rcu(sc, rcu); +} + +static void ioam6_free_ns(void *ptr, void *arg) +{ + struct ioam6_namespace *ns = (struct ioam6_namespace *)ptr; + + if (ns) + ioam6_ns_release(ns); +} + +static void ioam6_free_sc(void *ptr, void *arg) +{ + struct ioam6_schema *sc = (struct ioam6_schema *)ptr; + + if (sc) + ioam6_sc_release(sc); +} + +static int ioam6_ns_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) +{ + const struct ioam6_namespace *ns = obj; + + return (ns->id != *(__be16 *)arg->key); +} + +static int ioam6_sc_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) +{ + const struct ioam6_schema *sc = obj; + + return (sc->id != *(u32 *)arg->key); +} + +static const struct rhashtable_params rht_ns_params = { + .key_len = sizeof(__be16), + .key_offset = offsetof(struct ioam6_namespace, id), + .head_offset = offsetof(struct ioam6_namespace, head), + .automatic_shrinking = true, + .obj_cmpfn = ioam6_ns_cmpfn, +}; + +static const struct rhashtable_params rht_sc_params = { + .key_len = sizeof(u32), + .key_offset = offsetof(struct ioam6_schema, id), + .head_offset = offsetof(struct ioam6_schema, head), + .automatic_shrinking = true, + .obj_cmpfn = ioam6_sc_cmpfn, +}; + +struct ioam6_namespace *ioam6_namespace(struct net *net, __be16 id) +{ + struct ioam6_pernet_data *nsdata = ioam6_pernet(net); + + return rhashtable_lookup_fast(&nsdata->namespaces, &id, rht_ns_params); +} + +static void __ioam6_fill_trace_data(struct sk_buff *skb, + struct ioam6_namespace *ns, + struct ioam6_trace_hdr *trace, + struct ioam6_schema *sc, + u8 sclen) +{ + struct __kernel_sock_timeval ts; + u64 raw64; + u32 raw32; + u16 raw16; + u8 *data; + u8 byte; + + data = trace->data + trace->remlen * 4 - trace->nodelen * 4 - sclen * 4; + + /* hop_lim and node_id */ + if (trace->type.bit0) { + byte = ipv6_hdr(skb)->hop_limit; + if (skb->dev) + byte--; + + raw32 = dev_net(skb->dev)->ipv6.sysctl.ioam6_id; + + *(__be32 *)data = cpu_to_be32((byte << 24) | raw32); + data += sizeof(__be32); + } + + /* ingress_if_id and egress_if_id */ + if (trace->type.bit1) { + if (!skb->dev) + raw16 = IOAM6_U16_UNAVAILABLE; + else + raw16 = (__force u16)__in6_dev_get(skb->dev)->cnf.ioam6_id; + + *(__be16 *)data = cpu_to_be16(raw16); + data += sizeof(__be16); + + if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) + raw16 = IOAM6_U16_UNAVAILABLE; + else + raw16 = (__force u16)__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id; + + *(__be16 *)data = cpu_to_be16(raw16); + data += sizeof(__be16); + } + + /* timestamp seconds */ + if (trace->type.bit2) { + if (!skb->tstamp) + __net_timestamp(skb); + + skb_get_new_timestamp(skb, &ts); + + *(__be32 *)data = cpu_to_be32((u32)ts.tv_sec); + data += sizeof(__be32); + } + + /* timestamp subseconds */ + if (trace->type.bit3) { + if (!skb->tstamp) + __net_timestamp(skb); + + if (!trace->type.bit2) + skb_get_new_timestamp(skb, &ts); + + *(__be32 *)data = cpu_to_be32((u32)ts.tv_usec); + data += sizeof(__be32); + } + + /* transit delay */ + if (trace->type.bit4) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* namespace data */ + if (trace->type.bit5) { + *(__be32 *)data = ns->data; + data += sizeof(__be32); + } + + /* queue depth */ + if (trace->type.bit6) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* checksum complement */ + if (trace->type.bit7) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* hop_lim and node_id (wide) */ + if (trace->type.bit8) { + byte = ipv6_hdr(skb)->hop_limit; + if (skb->dev) + byte--; + + raw64 = dev_net(skb->dev)->ipv6.sysctl.ioam6_id_wide; + + *(__be64 *)data = cpu_to_be64(((u64)byte << 56) | raw64); + data += sizeof(__be64); + } + + /* ingress_if_id and egress_if_id (wide) */ + if (trace->type.bit9) { + if (!skb->dev) + raw32 = IOAM6_U32_UNAVAILABLE; + else + raw32 = __in6_dev_get(skb->dev)->cnf.ioam6_id_wide; + + *(__be32 *)data = cpu_to_be32(raw32); + data += sizeof(__be32); + + if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) + raw32 = IOAM6_U32_UNAVAILABLE; + else + raw32 = __in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id_wide; + + *(__be32 *)data = cpu_to_be32(raw32); + data += sizeof(__be32); + } + + /* namespace data (wide) */ + if (trace->type.bit10) { + *(__be64 *)data = ns->data_wide; + data += sizeof(__be64); + } + + /* buffer occupancy */ + if (trace->type.bit11) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* opaque state snapshot */ + if (trace->type.bit22) { + if (!sc) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE >> 8); + } else { + *(__be32 *)data = sc->hdr; + data += sizeof(__be32); + + memcpy(data, sc->data, sc->len); + } + } +} + +/* called with rcu_read_lock() */ +void ioam6_fill_trace_data(struct sk_buff *skb, + struct ioam6_namespace *ns, + struct ioam6_trace_hdr *trace) +{ + struct ioam6_schema *sc; + u8 sclen = 0; + + /* Skip if Overflow flag is set OR + * if an unknown type (bit 12-21) is set + */ + if (trace->overflow || + trace->type.bit12 | trace->type.bit13 | trace->type.bit14 | + trace->type.bit15 | trace->type.bit16 | trace->type.bit17 | + trace->type.bit18 | trace->type.bit19 | trace->type.bit20 | + trace->type.bit21) { + return; + } + + /* NodeLen does not include Opaque State Snapshot length. We need to + * take it into account if the corresponding bit is set (bit 22) and + * if the current IOAM namespace has an active schema attached to it + */ + sc = rcu_dereference(ns->schema); + if (trace->type.bit22) { + sclen = sizeof_field(struct ioam6_schema, hdr) / 4; + + if (sc) + sclen += sc->len / 4; + } + + /* If there is no space remaining, we set the Overflow flag and we + * skip without filling the trace + */ + if (!trace->remlen || trace->remlen < trace->nodelen + sclen) { + trace->overflow = 1; + return; + } + + __ioam6_fill_trace_data(skb, ns, trace, sc, sclen); + trace->remlen -= trace->nodelen + sclen; +} + +static int __net_init ioam6_net_init(struct net *net) +{ + struct ioam6_pernet_data *nsdata; + int err = -ENOMEM; + + nsdata = kzalloc(sizeof(*nsdata), GFP_KERNEL); + if (!nsdata) + goto out; + + mutex_init(&nsdata->lock); + net->ipv6.ioam6_data = nsdata; + + err = rhashtable_init(&nsdata->namespaces, &rht_ns_params); + if (err) + goto free_nsdata; + + err = rhashtable_init(&nsdata->schemas, &rht_sc_params); + if (err) + goto free_rht_ns; + +out: + return err; +free_rht_ns: + rhashtable_destroy(&nsdata->namespaces); +free_nsdata: + kfree(nsdata); + net->ipv6.ioam6_data = NULL; + goto out; +} + +static void __net_exit ioam6_net_exit(struct net *net) +{ + struct ioam6_pernet_data *nsdata = ioam6_pernet(net); + + rhashtable_free_and_destroy(&nsdata->namespaces, ioam6_free_ns, NULL); + rhashtable_free_and_destroy(&nsdata->schemas, ioam6_free_sc, NULL); + + kfree(nsdata); +} + +static struct pernet_operations ioam6_net_ops = { + .init = ioam6_net_init, + .exit = ioam6_net_exit, +}; + +int __init ioam6_init(void) +{ + int err = register_pernet_subsys(&ioam6_net_ops); + + if (err) + return err; + + pr_info("In-situ OAM (IOAM) with IPv6\n"); + return 0; +} + +void ioam6_exit(void) +{ + unregister_pernet_subsys(&ioam6_net_ops); +} diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index d7cf26f730d7..d53dd142bf87 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -21,6 +21,7 @@ #ifdef CONFIG_NETLABEL #include #endif +#include static int two = 2; static int three = 3; @@ -28,6 +29,8 @@ static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; static u32 rt6_multipath_hash_fields_all_mask = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; +static u32 ioam6_id_max = IOAM6_DEFAULT_ID; +static u64 ioam6_id_wide_max = IOAM6_DEFAULT_ID_WIDE; static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -196,6 +199,22 @@ static struct ctl_table ipv6_table_template[] = { .extra1 = SYSCTL_ZERO, .extra2 = &two, }, + { + .procname = "ioam6_id", + .data = &init_net.ipv6.sysctl.ioam6_id, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra2 = &ioam6_id_max, + }, + { + .procname = "ioam6_id_wide", + .data = &init_net.ipv6.sysctl.ioam6_id_wide, + .maxlen = sizeof(u64), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + .extra2 = &ioam6_id_wide_max, + }, { } }; -- cgit v1.2.3 From 8c6f6fa6772696be0c047a711858084b38763728 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Tue, 20 Jul 2021 21:42:58 +0200 Subject: ipv6: ioam: IOAM Generic Netlink API Add Generic Netlink commands to allow userspace to configure IOAM namespaces and schemas. The target is iproute2 and the patch is ready. It will be posted as soon as this patchset is merged. Here is an overview: $ ip ioam Usage: ip ioam { COMMAND | help } ip ioam namespace show ip ioam namespace add ID [ data DATA32 ] [ wide DATA64 ] ip ioam namespace del ID ip ioam schema show ip ioam schema add ID DATA ip ioam schema del ID ip ioam namespace set ID schema { ID | none } Signed-off-by: Justin Iurman Signed-off-by: David S. Miller --- include/linux/ioam6_genl.h | 13 + include/uapi/linux/ioam6_genl.h | 52 ++++ net/ipv6/ioam6.c | 561 +++++++++++++++++++++++++++++++++++++++- 3 files changed, 624 insertions(+), 2 deletions(-) create mode 100644 include/linux/ioam6_genl.h create mode 100644 include/uapi/linux/ioam6_genl.h (limited to 'include/linux') diff --git a/include/linux/ioam6_genl.h b/include/linux/ioam6_genl.h new file mode 100644 index 000000000000..176e67919de3 --- /dev/null +++ b/include/linux/ioam6_genl.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * IPv6 IOAM Generic Netlink API + * + * Author: + * Justin Iurman + */ +#ifndef _LINUX_IOAM6_GENL_H +#define _LINUX_IOAM6_GENL_H + +#include + +#endif /* _LINUX_IOAM6_GENL_H */ diff --git a/include/uapi/linux/ioam6_genl.h b/include/uapi/linux/ioam6_genl.h new file mode 100644 index 000000000000..ca4b22833754 --- /dev/null +++ b/include/uapi/linux/ioam6_genl.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * IPv6 IOAM Generic Netlink API + * + * Author: + * Justin Iurman + */ + +#ifndef _UAPI_LINUX_IOAM6_GENL_H +#define _UAPI_LINUX_IOAM6_GENL_H + +#define IOAM6_GENL_NAME "IOAM6" +#define IOAM6_GENL_VERSION 0x1 + +enum { + IOAM6_ATTR_UNSPEC, + + IOAM6_ATTR_NS_ID, /* u16 */ + IOAM6_ATTR_NS_DATA, /* u32 */ + IOAM6_ATTR_NS_DATA_WIDE,/* u64 */ + +#define IOAM6_MAX_SCHEMA_DATA_LEN (255 * 4) + IOAM6_ATTR_SC_ID, /* u32 */ + IOAM6_ATTR_SC_DATA, /* Binary */ + IOAM6_ATTR_SC_NONE, /* Flag */ + + IOAM6_ATTR_PAD, + + __IOAM6_ATTR_MAX, +}; + +#define IOAM6_ATTR_MAX (__IOAM6_ATTR_MAX - 1) + +enum { + IOAM6_CMD_UNSPEC, + + IOAM6_CMD_ADD_NAMESPACE, + IOAM6_CMD_DEL_NAMESPACE, + IOAM6_CMD_DUMP_NAMESPACES, + + IOAM6_CMD_ADD_SCHEMA, + IOAM6_CMD_DEL_SCHEMA, + IOAM6_CMD_DUMP_SCHEMAS, + + IOAM6_CMD_NS_SET_SCHEMA, + + __IOAM6_CMD_MAX, +}; + +#define IOAM6_CMD_MAX (__IOAM6_CMD_MAX - 1) + +#endif /* _UAPI_LINUX_IOAM6_GENL_H */ diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c index ba629e1b9408..ba59671f32b8 100644 --- a/net/ipv6/ioam6.c +++ b/net/ipv6/ioam6.c @@ -11,9 +11,11 @@ #include #include #include +#include #include #include +#include #include static void ioam6_ns_release(struct ioam6_namespace *ns) @@ -72,6 +74,552 @@ static const struct rhashtable_params rht_sc_params = { .obj_cmpfn = ioam6_sc_cmpfn, }; +static struct genl_family ioam6_genl_family; + +static const struct nla_policy ioam6_genl_policy_addns[] = { + [IOAM6_ATTR_NS_ID] = { .type = NLA_U16 }, + [IOAM6_ATTR_NS_DATA] = { .type = NLA_U32 }, + [IOAM6_ATTR_NS_DATA_WIDE] = { .type = NLA_U64 }, +}; + +static const struct nla_policy ioam6_genl_policy_delns[] = { + [IOAM6_ATTR_NS_ID] = { .type = NLA_U16 }, +}; + +static const struct nla_policy ioam6_genl_policy_addsc[] = { + [IOAM6_ATTR_SC_ID] = { .type = NLA_U32 }, + [IOAM6_ATTR_SC_DATA] = { .type = NLA_BINARY, + .len = IOAM6_MAX_SCHEMA_DATA_LEN }, +}; + +static const struct nla_policy ioam6_genl_policy_delsc[] = { + [IOAM6_ATTR_SC_ID] = { .type = NLA_U32 }, +}; + +static const struct nla_policy ioam6_genl_policy_ns_sc[] = { + [IOAM6_ATTR_NS_ID] = { .type = NLA_U16 }, + [IOAM6_ATTR_SC_ID] = { .type = NLA_U32 }, + [IOAM6_ATTR_SC_NONE] = { .type = NLA_FLAG }, +}; + +static int ioam6_genl_addns(struct sk_buff *skb, struct genl_info *info) +{ + struct ioam6_pernet_data *nsdata; + struct ioam6_namespace *ns; + u64 data64; + u32 data32; + __be16 id; + int err; + + if (!info->attrs[IOAM6_ATTR_NS_ID]) + return -EINVAL; + + id = cpu_to_be16(nla_get_u16(info->attrs[IOAM6_ATTR_NS_ID])); + nsdata = ioam6_pernet(genl_info_net(info)); + + mutex_lock(&nsdata->lock); + + ns = rhashtable_lookup_fast(&nsdata->namespaces, &id, rht_ns_params); + if (ns) { + err = -EEXIST; + goto out_unlock; + } + + ns = kzalloc(sizeof(*ns), GFP_KERNEL); + if (!ns) { + err = -ENOMEM; + goto out_unlock; + } + + ns->id = id; + + if (!info->attrs[IOAM6_ATTR_NS_DATA]) + data32 = IOAM6_U32_UNAVAILABLE; + else + data32 = nla_get_u32(info->attrs[IOAM6_ATTR_NS_DATA]); + + if (!info->attrs[IOAM6_ATTR_NS_DATA_WIDE]) + data64 = IOAM6_U64_UNAVAILABLE; + else + data64 = nla_get_u64(info->attrs[IOAM6_ATTR_NS_DATA_WIDE]); + + ns->data = cpu_to_be32(data32); + ns->data_wide = cpu_to_be64(data64); + + err = rhashtable_lookup_insert_fast(&nsdata->namespaces, &ns->head, + rht_ns_params); + if (err) + kfree(ns); + +out_unlock: + mutex_unlock(&nsdata->lock); + return err; +} + +static int ioam6_genl_delns(struct sk_buff *skb, struct genl_info *info) +{ + struct ioam6_pernet_data *nsdata; + struct ioam6_namespace *ns; + struct ioam6_schema *sc; + __be16 id; + int err; + + if (!info->attrs[IOAM6_ATTR_NS_ID]) + return -EINVAL; + + id = cpu_to_be16(nla_get_u16(info->attrs[IOAM6_ATTR_NS_ID])); + nsdata = ioam6_pernet(genl_info_net(info)); + + mutex_lock(&nsdata->lock); + + ns = rhashtable_lookup_fast(&nsdata->namespaces, &id, rht_ns_params); + if (!ns) { + err = -ENOENT; + goto out_unlock; + } + + sc = rcu_dereference_protected(ns->schema, + lockdep_is_held(&nsdata->lock)); + + err = rhashtable_remove_fast(&nsdata->namespaces, &ns->head, + rht_ns_params); + if (err) + goto out_unlock; + + if (sc) + rcu_assign_pointer(sc->ns, NULL); + + ioam6_ns_release(ns); + +out_unlock: + mutex_unlock(&nsdata->lock); + return err; +} + +static int __ioam6_genl_dumpns_element(struct ioam6_namespace *ns, + u32 portid, + u32 seq, + u32 flags, + struct sk_buff *skb, + u8 cmd) +{ + struct ioam6_schema *sc; + u64 data64; + u32 data32; + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &ioam6_genl_family, flags, cmd); + if (!hdr) + return -ENOMEM; + + data32 = be32_to_cpu(ns->data); + data64 = be64_to_cpu(ns->data_wide); + + if (nla_put_u16(skb, IOAM6_ATTR_NS_ID, be16_to_cpu(ns->id)) || + (data32 != IOAM6_U32_UNAVAILABLE && + nla_put_u32(skb, IOAM6_ATTR_NS_DATA, data32)) || + (data64 != IOAM6_U64_UNAVAILABLE && + nla_put_u64_64bit(skb, IOAM6_ATTR_NS_DATA_WIDE, + data64, IOAM6_ATTR_PAD))) + goto nla_put_failure; + + rcu_read_lock(); + + sc = rcu_dereference(ns->schema); + if (sc && nla_put_u32(skb, IOAM6_ATTR_SC_ID, sc->id)) { + rcu_read_unlock(); + goto nla_put_failure; + } + + rcu_read_unlock(); + + genlmsg_end(skb, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int ioam6_genl_dumpns_start(struct netlink_callback *cb) +{ + struct ioam6_pernet_data *nsdata = ioam6_pernet(sock_net(cb->skb->sk)); + struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; + + if (!iter) { + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + cb->args[0] = (long)iter; + } + + rhashtable_walk_enter(&nsdata->namespaces, iter); + + return 0; +} + +static int ioam6_genl_dumpns_done(struct netlink_callback *cb) +{ + struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; + + rhashtable_walk_exit(iter); + kfree(iter); + + return 0; +} + +static int ioam6_genl_dumpns(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct rhashtable_iter *iter; + struct ioam6_namespace *ns; + int err; + + iter = (struct rhashtable_iter *)cb->args[0]; + rhashtable_walk_start(iter); + + for (;;) { + ns = rhashtable_walk_next(iter); + + if (IS_ERR(ns)) { + if (PTR_ERR(ns) == -EAGAIN) + continue; + err = PTR_ERR(ns); + goto done; + } else if (!ns) { + break; + } + + err = __ioam6_genl_dumpns_element(ns, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, + skb, + IOAM6_CMD_DUMP_NAMESPACES); + if (err) + goto done; + } + + err = skb->len; + +done: + rhashtable_walk_stop(iter); + return err; +} + +static int ioam6_genl_addsc(struct sk_buff *skb, struct genl_info *info) +{ + struct ioam6_pernet_data *nsdata; + int len, len_aligned, err; + struct ioam6_schema *sc; + u32 id; + + if (!info->attrs[IOAM6_ATTR_SC_ID] || !info->attrs[IOAM6_ATTR_SC_DATA]) + return -EINVAL; + + id = nla_get_u32(info->attrs[IOAM6_ATTR_SC_ID]); + nsdata = ioam6_pernet(genl_info_net(info)); + + mutex_lock(&nsdata->lock); + + sc = rhashtable_lookup_fast(&nsdata->schemas, &id, rht_sc_params); + if (sc) { + err = -EEXIST; + goto out_unlock; + } + + len = nla_len(info->attrs[IOAM6_ATTR_SC_DATA]); + len_aligned = ALIGN(len, 4); + + sc = kzalloc(sizeof(*sc) + len_aligned, GFP_KERNEL); + if (!sc) { + err = -ENOMEM; + goto out_unlock; + } + + sc->id = id; + sc->len = len_aligned; + sc->hdr = cpu_to_be32(sc->id | ((u8)(sc->len / 4) << 24)); + nla_memcpy(sc->data, info->attrs[IOAM6_ATTR_SC_DATA], len); + + err = rhashtable_lookup_insert_fast(&nsdata->schemas, &sc->head, + rht_sc_params); + if (err) + goto free_sc; + +out_unlock: + mutex_unlock(&nsdata->lock); + return err; +free_sc: + kfree(sc); + goto out_unlock; +} + +static int ioam6_genl_delsc(struct sk_buff *skb, struct genl_info *info) +{ + struct ioam6_pernet_data *nsdata; + struct ioam6_namespace *ns; + struct ioam6_schema *sc; + int err; + u32 id; + + if (!info->attrs[IOAM6_ATTR_SC_ID]) + return -EINVAL; + + id = nla_get_u32(info->attrs[IOAM6_ATTR_SC_ID]); + nsdata = ioam6_pernet(genl_info_net(info)); + + mutex_lock(&nsdata->lock); + + sc = rhashtable_lookup_fast(&nsdata->schemas, &id, rht_sc_params); + if (!sc) { + err = -ENOENT; + goto out_unlock; + } + + ns = rcu_dereference_protected(sc->ns, lockdep_is_held(&nsdata->lock)); + + err = rhashtable_remove_fast(&nsdata->schemas, &sc->head, + rht_sc_params); + if (err) + goto out_unlock; + + if (ns) + rcu_assign_pointer(ns->schema, NULL); + + ioam6_sc_release(sc); + +out_unlock: + mutex_unlock(&nsdata->lock); + return err; +} + +static int __ioam6_genl_dumpsc_element(struct ioam6_schema *sc, + u32 portid, u32 seq, u32 flags, + struct sk_buff *skb, u8 cmd) +{ + struct ioam6_namespace *ns; + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &ioam6_genl_family, flags, cmd); + if (!hdr) + return -ENOMEM; + + if (nla_put_u32(skb, IOAM6_ATTR_SC_ID, sc->id) || + nla_put(skb, IOAM6_ATTR_SC_DATA, sc->len, sc->data)) + goto nla_put_failure; + + rcu_read_lock(); + + ns = rcu_dereference(sc->ns); + if (ns && nla_put_u16(skb, IOAM6_ATTR_NS_ID, be16_to_cpu(ns->id))) { + rcu_read_unlock(); + goto nla_put_failure; + } + + rcu_read_unlock(); + + genlmsg_end(skb, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int ioam6_genl_dumpsc_start(struct netlink_callback *cb) +{ + struct ioam6_pernet_data *nsdata = ioam6_pernet(sock_net(cb->skb->sk)); + struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; + + if (!iter) { + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + cb->args[0] = (long)iter; + } + + rhashtable_walk_enter(&nsdata->schemas, iter); + + return 0; +} + +static int ioam6_genl_dumpsc_done(struct netlink_callback *cb) +{ + struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; + + rhashtable_walk_exit(iter); + kfree(iter); + + return 0; +} + +static int ioam6_genl_dumpsc(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct rhashtable_iter *iter; + struct ioam6_schema *sc; + int err; + + iter = (struct rhashtable_iter *)cb->args[0]; + rhashtable_walk_start(iter); + + for (;;) { + sc = rhashtable_walk_next(iter); + + if (IS_ERR(sc)) { + if (PTR_ERR(sc) == -EAGAIN) + continue; + err = PTR_ERR(sc); + goto done; + } else if (!sc) { + break; + } + + err = __ioam6_genl_dumpsc_element(sc, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, + skb, + IOAM6_CMD_DUMP_SCHEMAS); + if (err) + goto done; + } + + err = skb->len; + +done: + rhashtable_walk_stop(iter); + return err; +} + +static int ioam6_genl_ns_set_schema(struct sk_buff *skb, struct genl_info *info) +{ + struct ioam6_namespace *ns, *ns_ref; + struct ioam6_schema *sc, *sc_ref; + struct ioam6_pernet_data *nsdata; + __be16 ns_id; + u32 sc_id; + int err; + + if (!info->attrs[IOAM6_ATTR_NS_ID] || + (!info->attrs[IOAM6_ATTR_SC_ID] && + !info->attrs[IOAM6_ATTR_SC_NONE])) + return -EINVAL; + + ns_id = cpu_to_be16(nla_get_u16(info->attrs[IOAM6_ATTR_NS_ID])); + nsdata = ioam6_pernet(genl_info_net(info)); + + mutex_lock(&nsdata->lock); + + ns = rhashtable_lookup_fast(&nsdata->namespaces, &ns_id, rht_ns_params); + if (!ns) { + err = -ENOENT; + goto out_unlock; + } + + if (info->attrs[IOAM6_ATTR_SC_NONE]) { + sc = NULL; + } else { + sc_id = nla_get_u32(info->attrs[IOAM6_ATTR_SC_ID]); + sc = rhashtable_lookup_fast(&nsdata->schemas, &sc_id, + rht_sc_params); + if (!sc) { + err = -ENOENT; + goto out_unlock; + } + } + + sc_ref = rcu_dereference_protected(ns->schema, + lockdep_is_held(&nsdata->lock)); + if (sc_ref) + rcu_assign_pointer(sc_ref->ns, NULL); + rcu_assign_pointer(ns->schema, sc); + + if (sc) { + ns_ref = rcu_dereference_protected(sc->ns, + lockdep_is_held(&nsdata->lock)); + if (ns_ref) + rcu_assign_pointer(ns_ref->schema, NULL); + rcu_assign_pointer(sc->ns, ns); + } + + err = 0; + +out_unlock: + mutex_unlock(&nsdata->lock); + return err; +} + +static const struct genl_ops ioam6_genl_ops[] = { + { + .cmd = IOAM6_CMD_ADD_NAMESPACE, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = ioam6_genl_addns, + .flags = GENL_ADMIN_PERM, + .policy = ioam6_genl_policy_addns, + .maxattr = ARRAY_SIZE(ioam6_genl_policy_addns) - 1, + }, + { + .cmd = IOAM6_CMD_DEL_NAMESPACE, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = ioam6_genl_delns, + .flags = GENL_ADMIN_PERM, + .policy = ioam6_genl_policy_delns, + .maxattr = ARRAY_SIZE(ioam6_genl_policy_delns) - 1, + }, + { + .cmd = IOAM6_CMD_DUMP_NAMESPACES, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .start = ioam6_genl_dumpns_start, + .dumpit = ioam6_genl_dumpns, + .done = ioam6_genl_dumpns_done, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = IOAM6_CMD_ADD_SCHEMA, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = ioam6_genl_addsc, + .flags = GENL_ADMIN_PERM, + .policy = ioam6_genl_policy_addsc, + .maxattr = ARRAY_SIZE(ioam6_genl_policy_addsc) - 1, + }, + { + .cmd = IOAM6_CMD_DEL_SCHEMA, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = ioam6_genl_delsc, + .flags = GENL_ADMIN_PERM, + .policy = ioam6_genl_policy_delsc, + .maxattr = ARRAY_SIZE(ioam6_genl_policy_delsc) - 1, + }, + { + .cmd = IOAM6_CMD_DUMP_SCHEMAS, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .start = ioam6_genl_dumpsc_start, + .dumpit = ioam6_genl_dumpsc, + .done = ioam6_genl_dumpsc_done, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = IOAM6_CMD_NS_SET_SCHEMA, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = ioam6_genl_ns_set_schema, + .flags = GENL_ADMIN_PERM, + .policy = ioam6_genl_policy_ns_sc, + .maxattr = ARRAY_SIZE(ioam6_genl_policy_ns_sc) - 1, + }, +}; + +static struct genl_family ioam6_genl_family __ro_after_init = { + .name = IOAM6_GENL_NAME, + .version = IOAM6_GENL_VERSION, + .netnsok = true, + .parallel_ops = true, + .ops = ioam6_genl_ops, + .n_ops = ARRAY_SIZE(ioam6_genl_ops), + .module = THIS_MODULE, +}; + struct ioam6_namespace *ioam6_namespace(struct net *net, __be16 id) { struct ioam6_pernet_data *nsdata = ioam6_pernet(net); @@ -319,15 +867,24 @@ static struct pernet_operations ioam6_net_ops = { int __init ioam6_init(void) { int err = register_pernet_subsys(&ioam6_net_ops); + if (err) + goto out; + err = genl_register_family(&ioam6_genl_family); if (err) - return err; + goto out_unregister_pernet_subsys; pr_info("In-situ OAM (IOAM) with IPv6\n"); - return 0; + +out: + return err; +out_unregister_pernet_subsys: + unregister_pernet_subsys(&ioam6_net_ops); + goto out; } void ioam6_exit(void) { + genl_unregister_family(&ioam6_genl_family); unregister_pernet_subsys(&ioam6_net_ops); } -- cgit v1.2.3 From 3edede08ff37c6a9370510508d5eeb54890baf47 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Tue, 20 Jul 2021 21:42:59 +0200 Subject: ipv6: ioam: Support for IOAM injection with lwtunnels Add support for the IOAM inline insertion (only for the host-to-host use case) which is per-route configured with lightweight tunnels. The target is iproute2 and the patch is ready. It will be posted as soon as this patchset is merged. Here is an overview: $ ip -6 ro ad fc00::1/128 encap ioam6 trace type 0x800000 ns 1 size 12 dev eth0 This example configures an IOAM Pre-allocated Trace option attached to the fc00::1/128 prefix. The IOAM namespace (ns) is 1, the size of the pre-allocated trace data block is 12 octets (size) and only the first IOAM data (bit 0: hop_limit + node id) is included in the trace (type) represented as a bitfield. The reason why the in-transit (IPv6-in-IPv6 encapsulation) use case is not implemented is explained on the patchset cover. Signed-off-by: Justin Iurman Signed-off-by: David S. Miller --- include/linux/ioam6_iptunnel.h | 13 ++ include/net/ioam6.h | 3 + include/uapi/linux/ioam6.h | 1 + include/uapi/linux/ioam6_iptunnel.h | 20 +++ include/uapi/linux/lwtunnel.h | 1 + net/core/lwtunnel.c | 2 + net/ipv6/Kconfig | 11 ++ net/ipv6/Makefile | 1 + net/ipv6/ioam6.c | 44 ++++-- net/ipv6/ioam6_iptunnel.c | 274 ++++++++++++++++++++++++++++++++++++ 10 files changed, 358 insertions(+), 12 deletions(-) create mode 100644 include/linux/ioam6_iptunnel.h create mode 100644 include/uapi/linux/ioam6_iptunnel.h create mode 100644 net/ipv6/ioam6_iptunnel.c (limited to 'include/linux') diff --git a/include/linux/ioam6_iptunnel.h b/include/linux/ioam6_iptunnel.h new file mode 100644 index 000000000000..07d9dfedd29d --- /dev/null +++ b/include/linux/ioam6_iptunnel.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * IPv6 IOAM Lightweight Tunnel API + * + * Author: + * Justin Iurman + */ +#ifndef _LINUX_IOAM6_IPTUNNEL_H +#define _LINUX_IOAM6_IPTUNNEL_H + +#include + +#endif /* _LINUX_IOAM6_IPTUNNEL_H */ diff --git a/include/net/ioam6.h b/include/net/ioam6.h index 772b91ee2e87..3c2993bc48c8 100644 --- a/include/net/ioam6.h +++ b/include/net/ioam6.h @@ -61,4 +61,7 @@ void ioam6_fill_trace_data(struct sk_buff *skb, int ioam6_init(void); void ioam6_exit(void); +int ioam6_iptunnel_init(void); +void ioam6_iptunnel_exit(void); + #endif /* _NET_IOAM6_H */ diff --git a/include/uapi/linux/ioam6.h b/include/uapi/linux/ioam6.h index 23ba6e85582f..ac4de376f0ce 100644 --- a/include/uapi/linux/ioam6.h +++ b/include/uapi/linux/ioam6.h @@ -126,6 +126,7 @@ struct ioam6_trace_hdr { #error "Please fix " #endif +#define IOAM6_TRACE_DATA_SIZE_MAX 244 __u8 data[0]; } __attribute__((packed)); diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h new file mode 100644 index 000000000000..bae14636a8c8 --- /dev/null +++ b/include/uapi/linux/ioam6_iptunnel.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * IPv6 IOAM Lightweight Tunnel API + * + * Author: + * Justin Iurman + */ + +#ifndef _UAPI_LINUX_IOAM6_IPTUNNEL_H +#define _UAPI_LINUX_IOAM6_IPTUNNEL_H + +enum { + IOAM6_IPTUNNEL_UNSPEC, + IOAM6_IPTUNNEL_TRACE, /* struct ioam6_trace_hdr */ + __IOAM6_IPTUNNEL_MAX, +}; + +#define IOAM6_IPTUNNEL_MAX (__IOAM6_IPTUNNEL_MAX - 1) + +#endif /* _UAPI_LINUX_IOAM6_IPTUNNEL_H */ diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index 568a4303ccce..2e206919125c 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -14,6 +14,7 @@ enum lwtunnel_encap_types { LWTUNNEL_ENCAP_BPF, LWTUNNEL_ENCAP_SEG6_LOCAL, LWTUNNEL_ENCAP_RPL, + LWTUNNEL_ENCAP_IOAM6, __LWTUNNEL_ENCAP_MAX, }; diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 8ec7d13d2860..d0ae987d2de9 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -43,6 +43,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) return "SEG6LOCAL"; case LWTUNNEL_ENCAP_RPL: return "RPL"; + case LWTUNNEL_ENCAP_IOAM6: + return "IOAM6"; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: case LWTUNNEL_ENCAP_NONE: diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 747f56e0c636..e504204bca92 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -328,4 +328,15 @@ config IPV6_RPL_LWTUNNEL If unsure, say N. +config IPV6_IOAM6_LWTUNNEL + bool "IPv6: IOAM Pre-allocated Trace insertion support" + depends on IPV6 + select LWTUNNEL + help + Support for the inline insertion of IOAM Pre-allocated + Trace Header (only on locally generated packets), using + the lightweight tunnels mechanism. + + If unsure, say N. + endif # IPV6 diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index b7ef10d417d6..1bc7e143217b 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -27,6 +27,7 @@ ipv6-$(CONFIG_NETLABEL) += calipso.o ipv6-$(CONFIG_IPV6_SEG6_LWTUNNEL) += seg6_iptunnel.o seg6_local.o ipv6-$(CONFIG_IPV6_SEG6_HMAC) += seg6_hmac.o ipv6-$(CONFIG_IPV6_RPL_LWTUNNEL) += rpl_iptunnel.o +ipv6-$(CONFIG_IPV6_IOAM6_LWTUNNEL) += ioam6_iptunnel.o ipv6-objs += $(ipv6-y) diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c index ba59671f32b8..5e8961004832 100644 --- a/net/ipv6/ioam6.c +++ b/net/ipv6/ioam6.c @@ -648,7 +648,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (skb->dev) byte--; - raw32 = dev_net(skb->dev)->ipv6.sysctl.ioam6_id; + raw32 = dev_net(skb_dst(skb)->dev)->ipv6.sysctl.ioam6_id; *(__be32 *)data = cpu_to_be32((byte << 24) | raw32); data += sizeof(__be32); @@ -675,24 +675,31 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, /* timestamp seconds */ if (trace->type.bit2) { - if (!skb->tstamp) - __net_timestamp(skb); - - skb_get_new_timestamp(skb, &ts); + if (!skb->dev) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + } else { + if (!skb->tstamp) + __net_timestamp(skb); - *(__be32 *)data = cpu_to_be32((u32)ts.tv_sec); + skb_get_new_timestamp(skb, &ts); + *(__be32 *)data = cpu_to_be32((u32)ts.tv_sec); + } data += sizeof(__be32); } /* timestamp subseconds */ if (trace->type.bit3) { - if (!skb->tstamp) - __net_timestamp(skb); + if (!skb->dev) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + } else { + if (!skb->tstamp) + __net_timestamp(skb); - if (!trace->type.bit2) - skb_get_new_timestamp(skb, &ts); + if (!trace->type.bit2) + skb_get_new_timestamp(skb, &ts); - *(__be32 *)data = cpu_to_be32((u32)ts.tv_usec); + *(__be32 *)data = cpu_to_be32((u32)ts.tv_usec); + } data += sizeof(__be32); } @@ -726,7 +733,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (skb->dev) byte--; - raw64 = dev_net(skb->dev)->ipv6.sysctl.ioam6_id_wide; + raw64 = dev_net(skb_dst(skb)->dev)->ipv6.sysctl.ioam6_id_wide; *(__be64 *)data = cpu_to_be64(((u64)byte << 56) | raw64); data += sizeof(__be64); @@ -874,10 +881,20 @@ int __init ioam6_init(void) if (err) goto out_unregister_pernet_subsys; +#ifdef CONFIG_IPV6_IOAM6_LWTUNNEL + err = ioam6_iptunnel_init(); + if (err) + goto out_unregister_genl; +#endif + pr_info("In-situ OAM (IOAM) with IPv6\n"); out: return err; +#ifdef CONFIG_IPV6_IOAM6_LWTUNNEL +out_unregister_genl: + genl_unregister_family(&ioam6_genl_family); +#endif out_unregister_pernet_subsys: unregister_pernet_subsys(&ioam6_net_ops); goto out; @@ -885,6 +902,9 @@ out_unregister_pernet_subsys: void ioam6_exit(void) { +#ifdef CONFIG_IPV6_IOAM6_LWTUNNEL + ioam6_iptunnel_exit(); +#endif genl_unregister_family(&ioam6_genl_family); unregister_pernet_subsys(&ioam6_net_ops); } diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c new file mode 100644 index 000000000000..f9ee04541c17 --- /dev/null +++ b/net/ipv6/ioam6_iptunnel.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * IPv6 IOAM Lightweight Tunnel implementation + * + * Author: + * Justin Iurman + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define IOAM6_MASK_SHORT_FIELDS 0xff100000 +#define IOAM6_MASK_WIDE_FIELDS 0xe00000 + +struct ioam6_lwt_encap { + struct ipv6_hopopt_hdr eh; + u8 pad[2]; /* 2-octet padding for 4n-alignment */ + struct ioam6_hdr ioamh; + struct ioam6_trace_hdr traceh; +} __packed; + +struct ioam6_lwt { + struct ioam6_lwt_encap tuninfo; +}; + +static struct ioam6_lwt *ioam6_lwt_state(struct lwtunnel_state *lwt) +{ + return (struct ioam6_lwt *)lwt->data; +} + +static struct ioam6_lwt_encap *ioam6_lwt_info(struct lwtunnel_state *lwt) +{ + return &ioam6_lwt_state(lwt)->tuninfo; +} + +static struct ioam6_trace_hdr *ioam6_trace(struct lwtunnel_state *lwt) +{ + return &(ioam6_lwt_state(lwt)->tuninfo.traceh); +} + +static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = { + [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)), +}; + +static int nla_put_ioam6_trace(struct sk_buff *skb, int attrtype, + struct ioam6_trace_hdr *trace) +{ + struct ioam6_trace_hdr *data; + struct nlattr *nla; + int len; + + len = sizeof(*trace); + + nla = nla_reserve(skb, attrtype, len); + if (!nla) + return -EMSGSIZE; + + data = nla_data(nla); + memcpy(data, trace, len); + + return 0; +} + +static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace) +{ + u32 fields; + + if (!trace->type_be32 || !trace->remlen || + trace->remlen > IOAM6_TRACE_DATA_SIZE_MAX / 4) + return false; + + trace->nodelen = 0; + fields = be32_to_cpu(trace->type_be32); + + trace->nodelen += hweight32(fields & IOAM6_MASK_SHORT_FIELDS) + * (sizeof(__be32) / 4); + trace->nodelen += hweight32(fields & IOAM6_MASK_WIDE_FIELDS) + * (sizeof(__be64) / 4); + + return true; +} + +static int ioam6_build_state(struct net *net, struct nlattr *nla, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IOAM6_IPTUNNEL_MAX + 1]; + struct ioam6_lwt_encap *tuninfo; + struct ioam6_trace_hdr *trace; + struct lwtunnel_state *s; + int len_aligned; + int len, err; + + if (family != AF_INET6) + return -EINVAL; + + err = nla_parse_nested(tb, IOAM6_IPTUNNEL_MAX, nla, + ioam6_iptunnel_policy, extack); + if (err < 0) + return err; + + if (!tb[IOAM6_IPTUNNEL_TRACE]) { + NL_SET_ERR_MSG(extack, "missing trace"); + return -EINVAL; + } + + trace = nla_data(tb[IOAM6_IPTUNNEL_TRACE]); + if (!ioam6_validate_trace_hdr(trace)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_TRACE], + "invalid trace validation"); + return -EINVAL; + } + + len = sizeof(*tuninfo) + trace->remlen * 4; + len_aligned = ALIGN(len, 8); + + s = lwtunnel_state_alloc(len_aligned); + if (!s) + return -ENOMEM; + + tuninfo = ioam6_lwt_info(s); + tuninfo->eh.hdrlen = (len_aligned >> 3) - 1; + tuninfo->pad[0] = IPV6_TLV_PADN; + tuninfo->ioamh.type = IOAM6_TYPE_PREALLOC; + tuninfo->ioamh.opt_type = IPV6_TLV_IOAM; + tuninfo->ioamh.opt_len = sizeof(tuninfo->ioamh) - 2 + sizeof(*trace) + + trace->remlen * 4; + + memcpy(&tuninfo->traceh, trace, sizeof(*trace)); + + len = len_aligned - len; + if (len == 1) { + tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PAD1; + } else if (len > 0) { + tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PADN; + tuninfo->traceh.data[trace->remlen * 4 + 1] = len - 2; + } + + s->type = LWTUNNEL_ENCAP_IOAM6; + s->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + + *ts = s; + + return 0; +} + +static int ioam6_do_inline(struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo) +{ + struct ioam6_trace_hdr *trace; + struct ipv6hdr *oldhdr, *hdr; + struct ioam6_namespace *ns; + int hdrlen, err; + + hdrlen = (tuninfo->eh.hdrlen + 1) << 3; + + err = skb_cow_head(skb, hdrlen + skb->mac_len); + if (unlikely(err)) + return err; + + oldhdr = ipv6_hdr(skb); + skb_pull(skb, sizeof(*oldhdr)); + skb_postpull_rcsum(skb, skb_network_header(skb), sizeof(*oldhdr)); + + skb_push(skb, sizeof(*oldhdr) + hdrlen); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + + hdr = ipv6_hdr(skb); + memmove(hdr, oldhdr, sizeof(*oldhdr)); + tuninfo->eh.nexthdr = hdr->nexthdr; + + skb_set_transport_header(skb, sizeof(*hdr)); + skb_postpush_rcsum(skb, hdr, sizeof(*hdr) + hdrlen); + + memcpy(skb_transport_header(skb), (u8 *)tuninfo, hdrlen); + + hdr->nexthdr = NEXTHDR_HOP; + hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr)); + + trace = (struct ioam6_trace_hdr *)(skb_transport_header(skb) + + sizeof(struct ipv6_hopopt_hdr) + 2 + + sizeof(struct ioam6_hdr)); + + ns = ioam6_namespace(dev_net(skb_dst(skb)->dev), trace->namespace_id); + if (ns) + ioam6_fill_trace_data(skb, ns, trace); + + return 0; +} + +static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct lwtunnel_state *lwt = skb_dst(skb)->lwtstate; + int err = -EINVAL; + + if (skb->protocol != htons(ETH_P_IPV6)) + goto drop; + + /* Only for packets we send and + * that do not contain a Hop-by-Hop yet + */ + if (skb->dev || ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP) + goto out; + + err = ioam6_do_inline(skb, ioam6_lwt_info(lwt)); + if (unlikely(err)) + goto drop; + + err = skb_cow_head(skb, LL_RESERVED_SPACE(skb_dst(skb)->dev)); + if (unlikely(err)) + goto drop; + +out: + return lwt->orig_output(net, sk, skb); + +drop: + kfree_skb(skb); + return err; +} + +static int ioam6_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct ioam6_trace_hdr *trace = ioam6_trace(lwtstate); + + if (nla_put_ioam6_trace(skb, IOAM6_IPTUNNEL_TRACE, trace)) + return -EMSGSIZE; + + return 0; +} + +static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + struct ioam6_trace_hdr *trace = ioam6_trace(lwtstate); + + return nla_total_size(sizeof(*trace)); +} + +static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + struct ioam6_trace_hdr *a_hdr = ioam6_trace(a); + struct ioam6_trace_hdr *b_hdr = ioam6_trace(b); + + return (a_hdr->namespace_id != b_hdr->namespace_id); +} + +static const struct lwtunnel_encap_ops ioam6_iptun_ops = { + .build_state = ioam6_build_state, + .output = ioam6_output, + .fill_encap = ioam6_fill_encap_info, + .get_encap_size = ioam6_encap_nlsize, + .cmp_encap = ioam6_encap_cmp, + .owner = THIS_MODULE, +}; + +int __init ioam6_iptunnel_init(void) +{ + return lwtunnel_encap_add_ops(&ioam6_iptun_ops, LWTUNNEL_ENCAP_IOAM6); +} + +void ioam6_iptunnel_exit(void) +{ + lwtunnel_encap_del_ops(&ioam6_iptun_ops, LWTUNNEL_ENCAP_IOAM6); +} -- cgit v1.2.3 From 1e7107c5ef44431bc1ebbd4c353f1d7c22e5f2ec Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 16 Jun 2021 08:51:57 -0400 Subject: cgroup1: fix leaked context root causing sporadic NULL deref in LTP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Richard reported sporadic (roughly one in 10 or so) null dereferences and other strange behaviour for a set of automated LTP tests. Things like: BUG: kernel NULL pointer dereference, address: 0000000000000008 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 1516 Comm: umount Not tainted 5.10.0-yocto-standard #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:kernfs_sop_show_path+0x1b/0x60 ...or these others: RIP: 0010:do_mkdirat+0x6a/0xf0 RIP: 0010:d_alloc_parallel+0x98/0x510 RIP: 0010:do_readlinkat+0x86/0x120 There were other less common instances of some kind of a general scribble but the common theme was mount and cgroup and a dubious dentry triggering the NULL dereference. I was only able to reproduce it under qemu by replicating Richard's setup as closely as possible - I never did get it to happen on bare metal, even while keeping everything else the same. In commit 71d883c37e8d ("cgroup_do_mount(): massage calling conventions") we see this as a part of the overall change: -------------- struct cgroup_subsys *ss; - struct dentry *dentry; [...] - dentry = cgroup_do_mount(&cgroup_fs_type, fc->sb_flags, root, - CGROUP_SUPER_MAGIC, ns); [...] - if (percpu_ref_is_dying(&root->cgrp.self.refcnt)) { - struct super_block *sb = dentry->d_sb; - dput(dentry); + ret = cgroup_do_mount(fc, CGROUP_SUPER_MAGIC, ns); + if (!ret && percpu_ref_is_dying(&root->cgrp.self.refcnt)) { + struct super_block *sb = fc->root->d_sb; + dput(fc->root); deactivate_locked_super(sb); msleep(10); return restart_syscall(); } -------------- In changing from the local "*dentry" variable to using fc->root, we now export/leave that dentry pointer in the file context after doing the dput() in the unlikely "is_dying" case. With LTP doing a crazy amount of back to back mount/unmount [testcases/bin/cgroup_regression_5_1.sh] the unlikely becomes slightly likely and then bad things happen. A fix would be to not leave the stale reference in fc->root as follows: --------------                 dput(fc->root); + fc->root = NULL;                 deactivate_locked_super(sb); -------------- ...but then we are just open-coding a duplicate of fc_drop_locked() so we simply use that instead. Cc: Al Viro Cc: Tejun Heo Cc: Zefan Li Cc: Johannes Weiner Cc: stable@vger.kernel.org # v5.1+ Reported-by: Richard Purdie Fixes: 71d883c37e8d ("cgroup_do_mount(): massage calling conventions") Signed-off-by: Paul Gortmaker Signed-off-by: Tejun Heo --- fs/internal.h | 1 - include/linux/fs_context.h | 1 + kernel/cgroup/cgroup-v1.c | 4 +--- 3 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/internal.h b/fs/internal.h index 3ce8edbaa3ca..82e8eb32ff3d 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -61,7 +61,6 @@ extern void __init chrdev_init(void); */ extern const struct fs_context_operations legacy_fs_context_ops; extern int parse_monolithic_mount_data(struct fs_context *, void *); -extern void fc_drop_locked(struct fs_context *); extern void vfs_clean_context(struct fs_context *fc); extern int finish_clean_context(struct fs_context *fc); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index e2bc16300c82..6b54982fc5f3 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -141,6 +141,7 @@ extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); +extern void fc_drop_locked(struct fs_context *fc); /* * sget() wrappers to be called from the ->get_tree() op. diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 8d6bf56ed77a..de2c432dee20 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1221,9 +1221,7 @@ int cgroup1_get_tree(struct fs_context *fc) ret = cgroup_do_get_tree(fc); if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { - struct super_block *sb = fc->root->d_sb; - dput(fc->root); - deactivate_locked_super(sb); + fc_drop_locked(fc); ret = 1; } -- cgit v1.2.3 From 580e3137318edb39d2c6efa5dad51e3fbd7e2536 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Wed, 19 May 2021 09:30:56 -0700 Subject: fpga: fix spelling mistakes Run the fpga subsystem through aspell. Signed-off-by: Tom Rix Reviewed-by: Fernando Pacheco Signed-off-by: Moritz Fischer --- Documentation/fpga/dfl.rst | 4 ++-- drivers/fpga/altera-cvp.c | 2 +- drivers/fpga/dfl-fme-pr.c | 2 +- drivers/fpga/dfl-n3000-nios.c | 2 +- drivers/fpga/dfl.h | 2 +- drivers/fpga/fpga-bridge.c | 4 ++-- drivers/fpga/zynq-fpga.c | 6 +++--- include/linux/fpga/fpga-mgr.h | 2 +- 8 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/Documentation/fpga/dfl.rst b/Documentation/fpga/dfl.rst index 75df90d1e54c..ef9eec71f6f3 100644 --- a/Documentation/fpga/dfl.rst +++ b/Documentation/fpga/dfl.rst @@ -10,7 +10,7 @@ Authors: - Xu Yilun The Device Feature List (DFL) FPGA framework (and drivers according to -this framework) hides the very details of low layer hardwares and provides +this framework) hides the very details of low layer hardware and provides unified interfaces to userspace. Applications could use these interfaces to configure, enumerate, open and access FPGA accelerators on platforms which implement the DFL in the device memory. Besides this, the DFL framework @@ -205,7 +205,7 @@ given Device Feature Lists and create platform devices for feature devices also abstracts operations for the private features and exposes common ops to feature device drivers. -The FPGA DFL Device could be different hardwares, e.g. PCIe device, platform +The FPGA DFL Device could be different hardware, e.g. PCIe device, platform device and etc. Its driver module is always loaded first once the device is created by the system. This driver plays an infrastructural role in the driver architecture. It locates the DFLs in the device memory, handles them diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c index 4e0edb60bfba..ccf4546eff29 100644 --- a/drivers/fpga/altera-cvp.c +++ b/drivers/fpga/altera-cvp.c @@ -346,7 +346,7 @@ static int altera_cvp_write_init(struct fpga_manager *mgr, } if (val & VSE_CVP_STATUS_CFG_RDY) { - dev_warn(&mgr->dev, "CvP already started, teardown first\n"); + dev_warn(&mgr->dev, "CvP already started, tear down first\n"); ret = altera_cvp_teardown(mgr, info); if (ret) return ret; diff --git a/drivers/fpga/dfl-fme-pr.c b/drivers/fpga/dfl-fme-pr.c index 1194c0e850e0..d61ce9a18879 100644 --- a/drivers/fpga/dfl-fme-pr.c +++ b/drivers/fpga/dfl-fme-pr.c @@ -148,7 +148,7 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg) /* * it allows userspace to reset the PR region's logic by disabling and - * reenabling the bridge to clear things out between accleration runs. + * reenabling the bridge to clear things out between acceleration runs. * so no need to hold the bridges after partial reconfiguration. */ if (region->get_bridges) diff --git a/drivers/fpga/dfl-n3000-nios.c b/drivers/fpga/dfl-n3000-nios.c index 7a95366f6516..9ddf1d1d392f 100644 --- a/drivers/fpga/dfl-n3000-nios.c +++ b/drivers/fpga/dfl-n3000-nios.c @@ -461,7 +461,7 @@ static int n3000_nios_poll_stat_timeout(void __iomem *base, u64 *v) * We don't use the time based timeout here for performance. * * The regbus read/write is on the critical path of Intel PAC N3000 - * image programing. The time based timeout checking will add too much + * image programming. The time based timeout checking will add too much * overhead on it. Usually the state changes in 1 or 2 loops on the * test server, and we set 10000 times loop here for safety. */ diff --git a/drivers/fpga/dfl.h b/drivers/fpga/dfl.h index 2b82c96ba56c..dac9c3d45e6c 100644 --- a/drivers/fpga/dfl.h +++ b/drivers/fpga/dfl.h @@ -232,7 +232,7 @@ struct dfl_feature_irq_ctx { * @id: sub feature id. * @resource_index: each sub feature has one mmio resource for its registers. * this index is used to find its mmio resource from the - * feature dev (platform device)'s reources. + * feature dev (platform device)'s resources. * @ioaddr: mapped mmio resource address. * @irq_ctx: interrupt context list. * @nr_irqs: number of interrupt contexts. diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c index 2bfb2ff86930..b09f68f8e1b0 100644 --- a/drivers/fpga/fpga-bridge.c +++ b/drivers/fpga/fpga-bridge.c @@ -230,7 +230,7 @@ EXPORT_SYMBOL_GPL(fpga_bridges_put); * * Get an exclusive reference to the bridge and and it to the list. * - * Return 0 for success, error code from of_fpga_bridge_get() othewise. + * Return 0 for success, error code from of_fpga_bridge_get() otherwise. */ int of_fpga_bridge_get_to_list(struct device_node *np, struct fpga_image_info *info, @@ -260,7 +260,7 @@ EXPORT_SYMBOL_GPL(of_fpga_bridge_get_to_list); * * Get an exclusive reference to the bridge and and it to the list. * - * Return 0 for success, error code from fpga_bridge_get() othewise. + * Return 0 for success, error code from fpga_bridge_get() otherwise. */ int fpga_bridge_get_to_list(struct device *dev, struct fpga_image_info *info, diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c index 07fa8d9ec675..9b75bd4f93d8 100644 --- a/drivers/fpga/zynq-fpga.c +++ b/drivers/fpga/zynq-fpga.c @@ -192,7 +192,7 @@ static void zynq_step_dma(struct zynq_fpga_priv *priv) /* Once the first transfer is queued we can turn on the ISR, future * calls to zynq_step_dma will happen from the ISR context. The - * dma_lock spinlock guarentees this handover is done coherently, the + * dma_lock spinlock guarantees this handover is done coherently, the * ISR enable is put at the end to avoid another CPU spinning in the * ISR on this lock. */ @@ -267,7 +267,7 @@ static int zynq_fpga_ops_write_init(struct fpga_manager *mgr, ctrl = zynq_fpga_read(priv, CTRL_OFFSET); if (!(ctrl & CTRL_SEC_EN_MASK)) { dev_err(&mgr->dev, - "System not secure, can't use crypted bitstreams\n"); + "System not secure, can't use encrypted bitstreams\n"); err = -EINVAL; goto out_err; } @@ -344,7 +344,7 @@ static int zynq_fpga_ops_write_init(struct fpga_manager *mgr, /* set configuration register with following options: * - enable PCAP interface - * - set throughput for maximum speed (if bistream not crypted) + * - set throughput for maximum speed (if bistream not encrypted) * - set CPU in user mode */ ctrl = zynq_fpga_read(priv, CTRL_OFFSET); diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index ec2cd8bfceb0..474c1f506307 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -110,7 +110,7 @@ struct fpga_image_info { * @initial_header_size: Maximum number of bytes that should be passed into write_init * @state: returns an enum value of the FPGA's state * @status: returns status of the FPGA, including reconfiguration error code - * @write_init: prepare the FPGA to receive confuration data + * @write_init: prepare the FPGA to receive configuration data * @write: write count bytes of configuration data to the FPGA * @write_sg: write the scatter list of configuration data to the FPGA * @write_complete: set FPGA to operating state after writing is done -- cgit v1.2.3 From 2f5dc00f7a3ea669fd387ce79ffca92bff361550 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 21 Jul 2021 19:24:01 +0300 Subject: net: bridge: switchdev: let drivers inform which bridge ports are offloaded On reception of an skb, the bridge checks if it was marked as 'already forwarded in hardware' (checks if skb->offload_fwd_mark == 1), and if it is, it assigns the source hardware domain of that skb based on the hardware domain of the ingress port. Then during forwarding, it enforces that the egress port must have a different hardware domain than the ingress one (this is done in nbp_switchdev_allowed_egress). Non-switchdev drivers don't report any physical switch id (neither through devlink nor .ndo_get_port_parent_id), therefore the bridge assigns them a hardware domain of 0, and packets coming from them will always have skb->offload_fwd_mark = 0. So there aren't any restrictions. Problems appear due to the fact that DSA would like to perform software fallback for bonding and team interfaces that the physical switch cannot offload. +-- br0 ---+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 There, it is desirable that the presence of swp3 and swp4 under a non-offloaded LAG does not preclude us from doing hardware bridging beteen swp0, swp1 and swp2. The bandwidth of the CPU is often times high enough that software bridging between {swp0,swp1,swp2} and bond0 is not impractical. But this creates an impossible paradox given the current way in which port hardware domains are assigned. When the driver receives a packet from swp0 (say, due to flooding), it must set skb->offload_fwd_mark to something. - If we set it to 0, then the bridge will forward it towards swp1, swp2 and bond0. But the switch has already forwarded it towards swp1 and swp2 (not to bond0, remember, that isn't offloaded, so as far as the switch is concerned, ports swp3 and swp4 are not looking up the FDB, and the entire bond0 is a destination that is strictly behind the CPU). But we don't want duplicated traffic towards swp1 and swp2, so it's not ok to set skb->offload_fwd_mark = 0. - If we set it to 1, then the bridge will not forward the skb towards the ports with the same switchdev mark, i.e. not to swp1, swp2 and bond0. Towards swp1 and swp2 that's ok, but towards bond0? It should have forwarded the skb there. So the real issue is that bond0 will be assigned the same hardware domain as {swp0,swp1,swp2}, because the function that assigns hardware domains to bridge ports, nbp_switchdev_add(), recurses through bond0's lower interfaces until it finds something that implements devlink (calls dev_get_port_parent_id with bool recurse = true). This is a problem because the fact that bond0 can be offloaded by swp3 and swp4 in our example is merely an assumption. A solution is to give the bridge explicit hints as to what hardware domain it should use for each port. Currently, the bridging offload is very 'silent': a driver registers a netdevice notifier, which is put on the netns's notifier chain, and which sniffs around for NETDEV_CHANGEUPPER events where the upper is a bridge, and the lower is an interface it knows about (one registered by this driver, normally). Then, from within that notifier, it does a bunch of stuff behind the bridge's back, without the bridge necessarily knowing that there's somebody offloading that port. It looks like this: ip link set swp0 master br0 | v br_add_if() calls netdev_master_upper_dev_link() | v call_netdevice_notifiers | v dsa_slave_netdevice_event | v oh, hey! it's for me! | v .port_bridge_join What we do to solve the conundrum is to be less silent, and change the switchdev drivers to present themselves to the bridge. Something like this: ip link set swp0 master br0 | v br_add_if() calls netdev_master_upper_dev_link() | v bridge: Aye! I'll use this call_netdevice_notifiers ^ ppid as the | | hardware domain for v | this port, and zero dsa_slave_netdevice_event | if I got nothing. | | v | oh, hey! it's for me! | | | v | .port_bridge_join | | | +------------------------+ switchdev_bridge_port_offload(swp0, swp0) Then stacked interfaces (like bond0 on top of swp3/swp4) would be treated differently in DSA, depending on whether we can or cannot offload them. The offload case: ip link set bond0 master br0 | v br_add_if() calls netdev_master_upper_dev_link() | v bridge: Aye! I'll use this call_netdevice_notifiers ^ ppid as the | | switchdev mark for v | bond0. dsa_slave_netdevice_event | Coincidentally (or not), | | bond0 and swp0, swp1, swp2 v | all have the same switchdev hmm, it's not quite for me, | mark now, since the ASIC but my driver has already | is able to forward towards called .port_lag_join | all these ports in hw. for it, because I have | a port with dp->lag_dev == bond0. | | | v | .port_bridge_join | for swp3 and swp4 | | | +------------------------+ switchdev_bridge_port_offload(bond0, swp3) switchdev_bridge_port_offload(bond0, swp4) And the non-offload case: ip link set bond0 master br0 | v br_add_if() calls netdev_master_upper_dev_link() | v bridge waiting: call_netdevice_notifiers ^ huh, switchdev_bridge_port_offload | | wasn't called, okay, I'll use a v | hwdom of zero for this one. dsa_slave_netdevice_event : Then packets received on swp0 will | : not be software-forwarded towards v : swp1, but they will towards bond0. it's not for me, but bond0 is an upper of swp3 and swp4, but their dp->lag_dev is NULL because they couldn't offload it. Basically we can draw the conclusion that the lowers of a bridge port can come and go, so depending on the configuration of lowers for a bridge port, it can dynamically toggle between offloaded and unoffloaded. Therefore, we need an equivalent switchdev_bridge_port_unoffload too. This patch changes the way any switchdev driver interacts with the bridge. From now on, everybody needs to call switchdev_bridge_port_offload and switchdev_bridge_port_unoffload, otherwise the bridge will treat the port as non-offloaded and allow software flooding to other ports from the same ASIC. Note that these functions lay the ground for a more complex handshake between switchdev drivers and the bridge in the future. For drivers that will request a replay of the switchdev objects when they offload and unoffload a bridge port (DSA, dpaa2-switch, ocelot), we place the call to switchdev_bridge_port_unoffload() strategically inside the NETDEV_PRECHANGEUPPER notifier's code path, and not inside NETDEV_CHANGEUPPER. This is because the switchdev object replay helpers need the netdev adjacency lists to be valid, and that is only true in NETDEV_PRECHANGEUPPER. Cc: Vadym Kochan Cc: Taras Chornyi Cc: Ioana Ciornei Cc: Lars Povlsen Cc: Steen Hegelund Cc: UNGLinuxDriver@microchip.com Cc: Claudiu Manoil Cc: Alexandre Belloni Cc: Grygorii Strashko Signed-off-by: Vladimir Oltean Tested-by: Ioana Ciornei # dpaa2-switch: regression Acked-by: Ioana Ciornei # dpaa2-switch Tested-by: Horatiu Vultur # ocelot-switch Signed-off-by: David S. Miller --- .../net/ethernet/freescale/dpaa2/dpaa2-switch.c | 13 ++++ .../net/ethernet/marvell/prestera/prestera_main.c | 3 +- .../ethernet/marvell/prestera/prestera_switchdev.c | 11 ++- .../ethernet/marvell/prestera/prestera_switchdev.h | 3 +- .../ethernet/mellanox/mlxsw/spectrum_switchdev.c | 24 +++++-- .../ethernet/microchip/sparx5/sparx5_switchdev.c | 23 +++++- drivers/net/ethernet/mscc/ocelot_net.c | 71 +++++++++++++++++++ drivers/net/ethernet/rocker/rocker.h | 3 +- drivers/net/ethernet/rocker/rocker_main.c | 9 ++- drivers/net/ethernet/rocker/rocker_ofdpa.c | 18 +++-- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 17 ++++- drivers/net/ethernet/ti/cpsw_new.c | 15 +++- include/linux/if_bridge.h | 21 ++++++ net/bridge/br_if.c | 13 +--- net/bridge/br_private.h | 13 +--- net/bridge/br_switchdev.c | 82 ++++++++++++++++++---- net/dsa/port.c | 16 ++++- 17 files changed, 298 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 23798feb40b2..9b090da3e460 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1930,8 +1930,13 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, if (err) goto err_egress_flood; + err = switchdev_bridge_port_offload(netdev, netdev, extack); + if (err) + goto err_switchdev_offload; + return 0; +err_switchdev_offload: err_egress_flood: dpaa2_switch_port_set_fdb(port_priv, NULL); return err; @@ -1957,6 +1962,11 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo return dpaa2_switch_port_vlan_add(arg, vlan_proto, vid); } +static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev) +{ + switchdev_bridge_port_unoffload(netdev); +} + static int dpaa2_switch_port_bridge_leave(struct net_device *netdev) { struct ethsw_port_priv *port_priv = netdev_priv(netdev); @@ -2078,6 +2088,9 @@ static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb, if (err) goto out; + if (!info->linking) + dpaa2_switch_port_pre_bridge_leave(netdev); + break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 226f4ff29f6e..7c569c1abefc 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -746,7 +746,8 @@ static int prestera_netdev_port_event(struct net_device *lower, case NETDEV_CHANGEUPPER: if (netif_is_bridge_master(upper)) { if (info->linking) - return prestera_bridge_port_join(upper, port); + return prestera_bridge_port_join(upper, port, + extack); else prestera_bridge_port_leave(upper, port); } else if (netif_is_lag_master(upper)) { diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index 0b3e8f2db294..8cf3fe3b7e58 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -480,7 +480,8 @@ err_port_flood_set: } int prestera_bridge_port_join(struct net_device *br_dev, - struct prestera_port *port) + struct prestera_port *port, + struct netlink_ext_ack *extack) { struct prestera_switchdev *swdev = port->sw->swdev; struct prestera_bridge_port *br_port; @@ -500,6 +501,10 @@ int prestera_bridge_port_join(struct net_device *br_dev, goto err_brport_create; } + err = switchdev_bridge_port_offload(br_port->dev, port->dev, extack); + if (err) + goto err_switchdev_offload; + if (bridge->vlan_enabled) return 0; @@ -510,6 +515,8 @@ int prestera_bridge_port_join(struct net_device *br_dev, return 0; err_port_join: + switchdev_bridge_port_unoffload(br_port->dev); +err_switchdev_offload: prestera_bridge_port_put(br_port); err_brport_create: prestera_bridge_put(bridge); @@ -584,6 +591,8 @@ void prestera_bridge_port_leave(struct net_device *br_dev, else prestera_bridge_1d_port_leave(br_port); + switchdev_bridge_port_unoffload(br_port->dev); + prestera_hw_port_learning_set(port, false); prestera_hw_port_flood_set(port, BR_FLOOD | BR_MCAST_FLOOD, 0); prestera_port_vid_stp_set(port, PRESTERA_VID_ALL, BR_STATE_FORWARDING); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h index a91bc35d235f..0e93fda3d9a5 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h @@ -8,7 +8,8 @@ int prestera_switchdev_init(struct prestera_switch *sw); void prestera_switchdev_fini(struct prestera_switch *sw); int prestera_bridge_port_join(struct net_device *br_dev, - struct prestera_port *port); + struct prestera_port *port, + struct netlink_ext_ack *extack); void prestera_bridge_port_leave(struct net_device *br_dev, struct prestera_port *port); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 61911fed6aeb..c52317de1f35 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -335,14 +335,16 @@ mlxsw_sp_bridge_port_find(struct mlxsw_sp_bridge *bridge, static struct mlxsw_sp_bridge_port * mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device, - struct net_device *brport_dev) + struct net_device *brport_dev, + struct netlink_ext_ack *extack) { struct mlxsw_sp_bridge_port *bridge_port; struct mlxsw_sp_port *mlxsw_sp_port; + int err; bridge_port = kzalloc(sizeof(*bridge_port), GFP_KERNEL); if (!bridge_port) - return NULL; + return ERR_PTR(-ENOMEM); mlxsw_sp_port = mlxsw_sp_port_dev_lower_find(brport_dev); bridge_port->lagged = mlxsw_sp_port->lagged; @@ -359,12 +361,23 @@ mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device, list_add(&bridge_port->list, &bridge_device->ports_list); bridge_port->ref_count = 1; + err = switchdev_bridge_port_offload(brport_dev, mlxsw_sp_port->dev, + extack); + if (err) + goto err_switchdev_offload; + return bridge_port; + +err_switchdev_offload: + list_del(&bridge_port->list); + kfree(bridge_port); + return ERR_PTR(err); } static void mlxsw_sp_bridge_port_destroy(struct mlxsw_sp_bridge_port *bridge_port) { + switchdev_bridge_port_unoffload(bridge_port->dev); list_del(&bridge_port->list); WARN_ON(!list_empty(&bridge_port->vlans_list)); kfree(bridge_port); @@ -390,9 +403,10 @@ mlxsw_sp_bridge_port_get(struct mlxsw_sp_bridge *bridge, if (IS_ERR(bridge_device)) return ERR_CAST(bridge_device); - bridge_port = mlxsw_sp_bridge_port_create(bridge_device, brport_dev); - if (!bridge_port) { - err = -ENOMEM; + bridge_port = mlxsw_sp_bridge_port_create(bridge_device, brport_dev, + extack); + if (IS_ERR(bridge_port)) { + err = PTR_ERR(bridge_port); goto err_bridge_port_create; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c index a72e3b3b596e..e4fb573563d0 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c @@ -93,9 +93,12 @@ static int sparx5_port_attr_set(struct net_device *dev, const void *ctx, } static int sparx5_port_bridge_join(struct sparx5_port *port, - struct net_device *bridge) + struct net_device *bridge, + struct netlink_ext_ack *extack) { struct sparx5 *sparx5 = port->sparx5; + struct net_device *ndev = port->ndev; + int err; if (bitmap_empty(sparx5->bridge_mask, SPX5_PORTS)) /* First bridged port */ @@ -109,12 +112,20 @@ static int sparx5_port_bridge_join(struct sparx5_port *port, set_bit(port->portno, sparx5->bridge_mask); + err = switchdev_bridge_port_offload(ndev, ndev, extack); + if (err) + goto err_switchdev_offload; + /* Port enters in bridge mode therefor don't need to copy to CPU * frames for multicast in case the bridge is not requesting them */ - __dev_mc_unsync(port->ndev, sparx5_mc_unsync); + __dev_mc_unsync(ndev, sparx5_mc_unsync); return 0; + +err_switchdev_offload: + clear_bit(port->portno, sparx5->bridge_mask); + return err; } static void sparx5_port_bridge_leave(struct sparx5_port *port, @@ -122,6 +133,8 @@ static void sparx5_port_bridge_leave(struct sparx5_port *port, { struct sparx5 *sparx5 = port->sparx5; + switchdev_bridge_port_unoffload(port->ndev); + clear_bit(port->portno, sparx5->bridge_mask); if (bitmap_empty(sparx5->bridge_mask, SPX5_PORTS)) sparx5->hw_bridge_dev = NULL; @@ -139,11 +152,15 @@ static int sparx5_port_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct sparx5_port *port = netdev_priv(dev); + struct netlink_ext_ack *extack; int err = 0; + extack = netdev_notifier_info_to_extack(&info->info); + if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) - err = sparx5_port_bridge_join(port, info->upper_dev); + err = sparx5_port_bridge_join(port, info->upper_dev, + extack); else sparx5_port_bridge_leave(port, info->upper_dev); diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index e9d260d84bf3..76b7b9536bf7 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -1216,6 +1216,10 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev, ocelot_port_bridge_join(ocelot, port, bridge); + err = switchdev_bridge_port_offload(brport_dev, dev, extack); + if (err) + goto err_switchdev_offload; + err = ocelot_switchdev_sync(ocelot, port, brport_dev, bridge, extack); if (err) goto err_switchdev_sync; @@ -1223,10 +1227,17 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev, return 0; err_switchdev_sync: + switchdev_bridge_port_unoffload(brport_dev); +err_switchdev_offload: ocelot_port_bridge_leave(ocelot, port, bridge); return err; } +static void ocelot_netdevice_pre_bridge_leave(struct net_device *brport_dev) +{ + switchdev_bridge_port_unoffload(brport_dev); +} + static int ocelot_netdevice_bridge_leave(struct net_device *dev, struct net_device *brport_dev, struct net_device *bridge) @@ -1279,6 +1290,18 @@ err_bridge_join: return err; } +static void ocelot_netdevice_pre_lag_leave(struct net_device *dev, + struct net_device *bond) +{ + struct net_device *bridge_dev; + + bridge_dev = netdev_master_upper_dev_get(bond); + if (!bridge_dev || !netif_is_bridge_master(bridge_dev)) + return; + + ocelot_netdevice_pre_bridge_leave(bond); +} + static int ocelot_netdevice_lag_leave(struct net_device *dev, struct net_device *bond) { @@ -1355,6 +1378,43 @@ ocelot_netdevice_lag_changeupper(struct net_device *dev, return NOTIFY_DONE; } +static int +ocelot_netdevice_prechangeupper(struct net_device *dev, + struct net_device *brport_dev, + struct netdev_notifier_changeupper_info *info) +{ + if (netif_is_bridge_master(info->upper_dev) && !info->linking) + ocelot_netdevice_pre_bridge_leave(brport_dev); + + if (netif_is_lag_master(info->upper_dev) && !info->linking) + ocelot_netdevice_pre_lag_leave(dev, info->upper_dev); + + return NOTIFY_DONE; +} + +static int +ocelot_netdevice_lag_prechangeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct net_device *lower; + struct list_head *iter; + int err = NOTIFY_DONE; + + netdev_for_each_lower_dev(dev, lower, iter) { + struct ocelot_port_private *priv = netdev_priv(lower); + struct ocelot_port *ocelot_port = &priv->port; + + if (ocelot_port->bond != dev) + return NOTIFY_OK; + + err = ocelot_netdevice_prechangeupper(dev, lower, info); + if (err) + return err; + } + + return NOTIFY_DONE; +} + static int ocelot_netdevice_changelowerstate(struct net_device *dev, struct netdev_lag_lower_state_info *info) @@ -1382,6 +1442,17 @@ static int ocelot_netdevice_event(struct notifier_block *unused, struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { + case NETDEV_PRECHANGEUPPER: { + struct netdev_notifier_changeupper_info *info = ptr; + + if (ocelot_netdevice_dev_check(dev)) + return ocelot_netdevice_prechangeupper(dev, dev, info); + + if (netif_is_lag_master(dev)) + return ocelot_netdevice_lag_prechangeupper(dev, info); + + break; + } case NETDEV_CHANGEUPPER: { struct netdev_notifier_changeupper_info *info = ptr; diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h index 315a6e5c0f59..e75814a4654f 100644 --- a/drivers/net/ethernet/rocker/rocker.h +++ b/drivers/net/ethernet/rocker/rocker.h @@ -119,7 +119,8 @@ struct rocker_world_ops { int (*port_obj_fdb_del)(struct rocker_port *rocker_port, u16 vid, const unsigned char *addr); int (*port_master_linked)(struct rocker_port *rocker_port, - struct net_device *master); + struct net_device *master, + struct netlink_ext_ack *extack); int (*port_master_unlinked)(struct rocker_port *rocker_port, struct net_device *master); int (*port_neigh_update)(struct rocker_port *rocker_port, diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index a46633606cae..53d407a5dbf7 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -1670,13 +1670,14 @@ rocker_world_port_fdb_del(struct rocker_port *rocker_port, } static int rocker_world_port_master_linked(struct rocker_port *rocker_port, - struct net_device *master) + struct net_device *master, + struct netlink_ext_ack *extack) { struct rocker_world_ops *wops = rocker_port->rocker->wops; if (!wops->port_master_linked) return -EOPNOTSUPP; - return wops->port_master_linked(rocker_port, master); + return wops->port_master_linked(rocker_port, master, extack); } static int rocker_world_port_master_unlinked(struct rocker_port *rocker_port, @@ -3107,6 +3108,7 @@ struct rocker_port *rocker_port_dev_lower_find(struct net_device *dev, static int rocker_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { + struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *info; struct rocker_port *rocker_port; @@ -3123,7 +3125,8 @@ static int rocker_netdevice_event(struct notifier_block *unused, rocker_port = netdev_priv(dev); if (info->linking) { err = rocker_world_port_master_linked(rocker_port, - info->upper_dev); + info->upper_dev, + extack); if (err) netdev_warn(dev, "failed to reflect master linked (err %d)\n", err); diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 967a634ee9ac..84dcaf8687a0 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -2571,8 +2571,10 @@ static int ofdpa_port_obj_fdb_del(struct rocker_port *rocker_port, } static int ofdpa_port_bridge_join(struct ofdpa_port *ofdpa_port, - struct net_device *bridge) + struct net_device *bridge, + struct netlink_ext_ack *extack) { + struct net_device *dev = ofdpa_port->dev; int err; /* Port is joining bridge, so the internal VLAN for the @@ -2592,13 +2594,20 @@ static int ofdpa_port_bridge_join(struct ofdpa_port *ofdpa_port, ofdpa_port->bridge_dev = bridge; - return ofdpa_port_vlan_add(ofdpa_port, OFDPA_UNTAGGED_VID, 0); + err = ofdpa_port_vlan_add(ofdpa_port, OFDPA_UNTAGGED_VID, 0); + if (err) + return err; + + return switchdev_bridge_port_offload(dev, dev, extack); } static int ofdpa_port_bridge_leave(struct ofdpa_port *ofdpa_port) { + struct net_device *dev = ofdpa_port->dev; int err; + switchdev_bridge_port_unoffload(dev); + err = ofdpa_port_vlan_del(ofdpa_port, OFDPA_UNTAGGED_VID, 0); if (err) return err; @@ -2637,13 +2646,14 @@ static int ofdpa_port_ovs_changed(struct ofdpa_port *ofdpa_port, } static int ofdpa_port_master_linked(struct rocker_port *rocker_port, - struct net_device *master) + struct net_device *master, + struct netlink_ext_ack *extack) { struct ofdpa_port *ofdpa_port = rocker_port->wpriv; int err = 0; if (netif_is_bridge_master(master)) - err = ofdpa_port_bridge_join(ofdpa_port, master); + err = ofdpa_port_bridge_join(ofdpa_port, master, extack); else if (netif_is_ovs_master(master)) err = ofdpa_port_ovs_changed(ofdpa_port, master); return err; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 718539cdd2f2..8b9596eb808e 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -2077,10 +2078,13 @@ bool am65_cpsw_port_dev_check(const struct net_device *ndev) return false; } -static int am65_cpsw_netdevice_port_link(struct net_device *ndev, struct net_device *br_ndev) +static int am65_cpsw_netdevice_port_link(struct net_device *ndev, + struct net_device *br_ndev, + struct netlink_ext_ack *extack) { struct am65_cpsw_common *common = am65_ndev_to_common(ndev); struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(ndev); + int err; if (!common->br_members) { common->hw_bridge_dev = br_ndev; @@ -2092,6 +2096,10 @@ static int am65_cpsw_netdevice_port_link(struct net_device *ndev, struct net_dev return -EOPNOTSUPP; } + err = switchdev_bridge_port_offload(ndev, ndev, extack); + if (err) + return err; + common->br_members |= BIT(priv->port->port_id); am65_cpsw_port_offload_fwd_mark_update(common); @@ -2104,6 +2112,8 @@ static void am65_cpsw_netdevice_port_unlink(struct net_device *ndev) struct am65_cpsw_common *common = am65_ndev_to_common(ndev); struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(ndev); + switchdev_bridge_port_unoffload(ndev); + common->br_members &= ~BIT(priv->port->port_id); am65_cpsw_port_offload_fwd_mark_update(common); @@ -2116,6 +2126,7 @@ static void am65_cpsw_netdevice_port_unlink(struct net_device *ndev) static int am65_cpsw_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { + struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *info; int ret = NOTIFY_DONE; @@ -2129,7 +2140,9 @@ static int am65_cpsw_netdevice_event(struct notifier_block *unused, if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) - ret = am65_cpsw_netdevice_port_link(ndev, info->upper_dev); + ret = am65_cpsw_netdevice_port_link(ndev, + info->upper_dev, + extack); else am65_cpsw_netdevice_port_unlink(ndev); } diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 57d279fdcc9f..bf9cadfb11b5 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -1499,10 +1500,12 @@ static void cpsw_port_offload_fwd_mark_update(struct cpsw_common *cpsw) } static int cpsw_netdevice_port_link(struct net_device *ndev, - struct net_device *br_ndev) + struct net_device *br_ndev, + struct netlink_ext_ack *extack) { struct cpsw_priv *priv = netdev_priv(ndev); struct cpsw_common *cpsw = priv->cpsw; + int err; if (!cpsw->br_members) { cpsw->hw_bridge_dev = br_ndev; @@ -1514,6 +1517,10 @@ static int cpsw_netdevice_port_link(struct net_device *ndev, return -EOPNOTSUPP; } + err = switchdev_bridge_port_offload(ndev, ndev, extack); + if (err) + return err; + cpsw->br_members |= BIT(priv->emac_port); cpsw_port_offload_fwd_mark_update(cpsw); @@ -1526,6 +1533,8 @@ static void cpsw_netdevice_port_unlink(struct net_device *ndev) struct cpsw_priv *priv = netdev_priv(ndev); struct cpsw_common *cpsw = priv->cpsw; + switchdev_bridge_port_unoffload(ndev); + cpsw->br_members &= ~BIT(priv->emac_port); cpsw_port_offload_fwd_mark_update(cpsw); @@ -1538,6 +1547,7 @@ static void cpsw_netdevice_port_unlink(struct net_device *ndev) static int cpsw_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { + struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *info; int ret = NOTIFY_DONE; @@ -1552,7 +1562,8 @@ static int cpsw_netdevice_event(struct notifier_block *unused, if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) ret = cpsw_netdevice_port_link(ndev, - info->upper_dev); + info->upper_dev, + extack); else cpsw_netdevice_port_unlink(ndev); } diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index b651c5e32a28..ce413eca527e 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -206,4 +206,25 @@ static inline int br_fdb_replay(const struct net_device *br_dev, } #endif +#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_NET_SWITCHDEV) + +int switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, + struct netlink_ext_ack *extack); +void switchdev_bridge_port_unoffload(struct net_device *brport_dev); + +#else + +static inline int switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, + struct netlink_ext_ack *extack) +{ + return -EINVAL; +} + +static inline void switchdev_bridge_port_unoffload(struct net_device *brport_dev) +{ +} +#endif + #endif diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index c0df50e4abbb..86f6d7e93ea8 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -349,7 +349,6 @@ static void del_nbp(struct net_bridge_port *p) nbp_backup_clear(p); nbp_update_port_count(br); - nbp_switchdev_del(p); netdev_upper_dev_unlink(dev, br->dev); @@ -644,10 +643,6 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, if (err) goto err5; - err = nbp_switchdev_add(p); - if (err) - goto err6; - dev_disable_lro(dev); list_add_rcu(&p->list, &br->port_list); @@ -685,13 +680,13 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, */ err = dev_pre_changeaddr_notify(br->dev, dev->dev_addr, extack); if (err) - goto err7; + goto err6; } err = nbp_vlan_init(p, extack); if (err) { netdev_err(dev, "failed to initialize vlan filtering on this port\n"); - goto err7; + goto err6; } spin_lock_bh(&br->lock); @@ -714,14 +709,12 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, return 0; -err7: +err6: if (fdb_synced) br_fdb_unsync_static(br, p); list_del_rcu(&p->list); br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); - nbp_switchdev_del(p); -err6: netdev_upper_dev_unlink(dev, br->dev); err5: dev->priv_flags &= ~IFF_BRIDGE_PORT; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d0e6ae25a4e4..fbf73a5256d0 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -392,6 +392,8 @@ struct net_bridge_port { * hardware domain. */ int hwdom; + int offload_count; + struct netdev_phys_item_id ppid; #endif u16 group_fwd_mask; u16 backup_redirected_cnt; @@ -1857,8 +1859,6 @@ void br_switchdev_fdb_notify(struct net_bridge *br, int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags, struct netlink_ext_ack *extack); int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid); -int nbp_switchdev_add(struct net_bridge_port *p); -void nbp_switchdev_del(struct net_bridge_port *p); void br_switchdev_init(struct net_bridge *br); static inline void br_switchdev_frame_unmark(struct sk_buff *skb) @@ -1907,15 +1907,6 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb) { } -static inline int nbp_switchdev_add(struct net_bridge_port *p) -{ - return 0; -} - -static inline void nbp_switchdev_del(struct net_bridge_port *p) -{ -} - static inline void br_switchdev_init(struct net_bridge *br) { } diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index f3120f13c293..39f0787fde01 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -133,7 +133,7 @@ static int nbp_switchdev_hwdom_set(struct net_bridge_port *joining) /* joining is yet to be added to the port list. */ list_for_each_entry(p, &br->port_list, list) { - if (netdev_port_same_parent_id(joining->dev, p->dev)) { + if (netdev_phys_item_id_same(&joining->ppid, &p->ppid)) { joining->hwdom = p->hwdom; return 0; } @@ -162,27 +162,85 @@ static void nbp_switchdev_hwdom_put(struct net_bridge_port *leaving) clear_bit(leaving->hwdom, &br->busy_hwdoms); } -int nbp_switchdev_add(struct net_bridge_port *p) +static int nbp_switchdev_add(struct net_bridge_port *p, + struct netdev_phys_item_id ppid, + struct netlink_ext_ack *extack) { - struct netdev_phys_item_id ppid = { }; - int err; + if (p->offload_count) { + /* Prevent unsupported configurations such as a bridge port + * which is a bonding interface, and the member ports are from + * different hardware switches. + */ + if (!netdev_phys_item_id_same(&p->ppid, &ppid)) { + NL_SET_ERR_MSG_MOD(extack, + "Same bridge port cannot be offloaded by two physical switches"); + return -EBUSY; + } - ASSERT_RTNL(); + /* Tolerate drivers that call switchdev_bridge_port_offload() + * more than once for the same bridge port, such as when the + * bridge port is an offloaded bonding/team interface. + */ + p->offload_count++; - err = dev_get_port_parent_id(p->dev, &ppid, true); - if (err) { - if (err == -EOPNOTSUPP) - return 0; - return err; + return 0; } + p->ppid = ppid; + p->offload_count = 1; + return nbp_switchdev_hwdom_set(p); } -void nbp_switchdev_del(struct net_bridge_port *p) +static void nbp_switchdev_del(struct net_bridge_port *p) { - ASSERT_RTNL(); + if (WARN_ON(!p->offload_count)) + return; + + p->offload_count--; + + if (p->offload_count) + return; if (p->hwdom) nbp_switchdev_hwdom_put(p); } + +/* Let the bridge know that this port is offloaded, so that it can assign a + * switchdev hardware domain to it. + */ +int switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, + struct netlink_ext_ack *extack) +{ + struct netdev_phys_item_id ppid; + struct net_bridge_port *p; + int err; + + ASSERT_RTNL(); + + p = br_port_get_rtnl(brport_dev); + if (!p) + return -ENODEV; + + err = dev_get_port_parent_id(dev, &ppid, false); + if (err) + return err; + + return nbp_switchdev_add(p, ppid, extack); +} +EXPORT_SYMBOL_GPL(switchdev_bridge_port_offload); + +void switchdev_bridge_port_unoffload(struct net_device *brport_dev) +{ + struct net_bridge_port *p; + + ASSERT_RTNL(); + + p = br_port_get_rtnl(brport_dev); + if (!p) + return; + + nbp_switchdev_del(p); +} +EXPORT_SYMBOL_GPL(switchdev_bridge_port_unoffload); diff --git a/net/dsa/port.c b/net/dsa/port.c index 982e18771d76..7accda066149 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -292,6 +292,8 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, .port = dp->index, .br = br, }; + struct net_device *dev = dp->slave; + struct net_device *brport_dev; int err; /* Here the interface is already bridged. Reflect the current @@ -299,16 +301,24 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, */ dp->bridge_dev = br; + brport_dev = dsa_port_to_bridge_port(dp); + err = dsa_broadcast(DSA_NOTIFIER_BRIDGE_JOIN, &info); if (err) goto out_rollback; - err = dsa_port_switchdev_sync(dp, extack); + err = switchdev_bridge_port_offload(brport_dev, dev, extack); if (err) goto out_rollback_unbridge; + err = dsa_port_switchdev_sync(dp, extack); + if (err) + goto out_rollback_unoffload; + return 0; +out_rollback_unoffload: + switchdev_bridge_port_unoffload(brport_dev); out_rollback_unbridge: dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); out_rollback: @@ -319,6 +329,10 @@ out_rollback: int dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br, struct netlink_ext_ack *extack) { + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + + switchdev_bridge_port_unoffload(brport_dev); + return dsa_port_switchdev_unsync_objs(dp, br, extack); } -- cgit v1.2.3 From 4e51bf44a03af6fa19a39a36ea8fedfacb8ccadf Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 21 Jul 2021 19:24:03 +0300 Subject: net: bridge: move the switchdev object replay helpers to "push" mode Starting with commit 4f2673b3a2b6 ("net: bridge: add helper to replay port and host-joined mdb entries"), DSA has introduced some bridge helpers that replay switchdev events (FDB/MDB/VLAN additions and deletions) that can be lost by the switchdev drivers in a variety of circumstances: - an IP multicast group was host-joined on the bridge itself before any switchdev port joined the bridge, leading to the host MDB entries missing in the hardware database. - during the bridge creation process, the MAC address of the bridge was added to the FDB as an entry pointing towards the bridge device itself, but with no switchdev ports being part of the bridge yet, this local FDB entry would remain unknown to the switchdev hardware database. - a VLAN/FDB/MDB was added to a bridge port that is a LAG interface, before any switchdev port joined that LAG, leading to the hardware database missing those entries. - a switchdev port left a LAG that is a bridge port, while the LAG remained part of the bridge, and all FDB/MDB/VLAN entries remained installed in the hardware database of the switchdev port. Also, since commit 0d2cfbd41c4a ("net: bridge: ignore switchdev events for LAG ports which didn't request replay"), DSA introduced a method, based on a const void *ctx, to ensure that two switchdev ports under the same LAG that is a bridge port do not see the same MDB/VLAN entry being replayed twice by the bridge, once for every bridge port that joins the LAG. With so many ordering corner cases being possible, it seems unreasonable to expect a switchdev driver writer to get it right from the first try. Therefore, now that DSA has experimented with the bridge replay helpers for a little bit, we can move the code to the bridge driver where it is more readily available to all switchdev drivers. To convert the switchdev object replay helpers from "pull mode" (where the driver asks for them) to a "push mode" (where the bridge offers them automatically), the biggest problem is that the bridge needs to be aware when a switchdev port joins and leaves, even when the switchdev is only indirectly a bridge port (for example when the bridge port is a LAG upper of the switchdev). Luckily, we already have a hook for that, in the form of the newly introduced switchdev_bridge_port_offload() and switchdev_bridge_port_unoffload() calls. These offer a natural place for hooking the object addition and deletion replays. Extend the above 2 functions with: - pointers to the switchdev atomic notifier (for FDB replays) and the blocking notifier (for MDB and VLAN replays). - the "const void *ctx" argument required for drivers to be able to disambiguate between which port is targeted, when multiple ports are lowers of the same LAG that is a bridge port. Most of the drivers pass NULL to this argument, except the ones that support LAG offload and have the proper context check already in place in the switchdev blocking notifier handler. Also unexport the replay helpers, since nobody except the bridge calls them directly now. Note that: (a) we abuse the terminology slightly, because FDB entries are not "switchdev objects", but we count them as objects nonetheless. With no direct way to prove it, I think they are not modeled as switchdev objects because those can only be installed by the bridge to the hardware (as opposed to FDB entries which can be propagated in the other direction too). This is merely an abuse of terms, FDB entries are replayed too, despite not being objects. (b) the bridge does not attempt to sync port attributes to newly joined ports, just the countable stuff (the objects). The reason for this is simple: no universal and symmetric way to sync and unsync them is known. For example, VLAN filtering: what to do on unsync, disable or leave it enabled? Similarly, STP state, ageing timer, etc etc. What a switchdev port does when it becomes standalone again is not really up to the bridge's competence, and the driver should deal with it. On the other hand, replaying deletions of switchdev objects can be seen a matter of cleanup and therefore be treated by the bridge, hence this patch. We make the replay helpers opt-in for drivers, because they might not bring immediate benefits for them: - nbp_vlan_init() is called _after_ netdev_master_upper_dev_link(), so br_vlan_replay() should not do anything for the new drivers on which we call it. The existing drivers where there was even a slight possibility for there to exist a VLAN on a bridge port before they join it are already guarded against this: mlxsw and prestera deny joining LAG interfaces that are members of a bridge. - br_fdb_replay() should now notify of local FDB entries, but I patched all drivers except DSA to ignore these new entries in commit 2c4eca3ef716 ("net: bridge: switchdev: include local flag in FDB notifications"). Driver authors can lift this restriction as they wish, and when they do, they can also opt into the FDB replay functionality. - br_mdb_replay() should fix a real issue which is described in commit 4f2673b3a2b6 ("net: bridge: add helper to replay port and host-joined mdb entries"). However most drivers do not offload the SWITCHDEV_OBJ_ID_HOST_MDB to see this issue: only cpsw and am65_cpsw offload this switchdev object, and I don't completely understand the way in which they offload this switchdev object anyway. So I'll leave it up to these drivers' respective maintainers to opt into br_mdb_replay(). So most of the drivers pass NULL notifier blocks for the replay helpers, except: - dpaa2-switch which was already acked/regression-tested with the helpers enabled (and there isn't much of a downside in having them) - ocelot which already had replay logic in "pull" mode - DSA which already had replay logic in "pull" mode An important observation is that the drivers which don't currently request bridge event replays don't even have the switchdev_bridge_port_{offload,unoffload} calls placed in proper places right now. This was done to avoid unnecessary rework for drivers which might never even add support for this. For driver writers who wish to add replay support, this can be used as a tentative placement guide: https://patchwork.kernel.org/project/netdevbpf/patch/20210720134655.892334-11-vladimir.oltean@nxp.com/ Cc: Vadym Kochan Cc: Taras Chornyi Cc: Ioana Ciornei Cc: Lars Povlsen Cc: Steen Hegelund Cc: UNGLinuxDriver@microchip.com Cc: Claudiu Manoil Cc: Alexandre Belloni Cc: Grygorii Strashko Signed-off-by: Vladimir Oltean Acked-by: Ioana Ciornei # dpaa2-switch Signed-off-by: David S. Miller --- .../net/ethernet/freescale/dpaa2/dpaa2-switch.c | 12 +++- .../ethernet/marvell/prestera/prestera_switchdev.c | 7 +- .../ethernet/mellanox/mlxsw/spectrum_switchdev.c | 4 +- .../ethernet/microchip/sparx5/sparx5_switchdev.c | 5 +- drivers/net/ethernet/mscc/ocelot_net.c | 45 +++++------- drivers/net/ethernet/rocker/rocker_ofdpa.c | 5 +- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 5 +- drivers/net/ethernet/ti/cpsw_new.c | 5 +- include/linux/if_bridge.h | 54 +++++--------- net/bridge/br_fdb.c | 1 - net/bridge/br_mdb.c | 1 - net/bridge/br_private.h | 25 +++++++ net/bridge/br_switchdev.c | 75 ++++++++++++++++++- net/bridge/br_vlan.c | 1 - net/dsa/dsa_priv.h | 6 +- net/dsa/port.c | 84 +++++----------------- net/dsa/slave.c | 10 +-- 17 files changed, 182 insertions(+), 163 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 9b090da3e460..2138239facfd 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1889,6 +1889,9 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev, return notifier_from_errno(err); } +static struct notifier_block dpaa2_switch_port_switchdev_nb; +static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb; + static int dpaa2_switch_port_bridge_join(struct net_device *netdev, struct net_device *upper_dev, struct netlink_ext_ack *extack) @@ -1930,7 +1933,10 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, if (err) goto err_egress_flood; - err = switchdev_bridge_port_offload(netdev, netdev, extack); + err = switchdev_bridge_port_offload(netdev, netdev, NULL, + &dpaa2_switch_port_switchdev_nb, + &dpaa2_switch_port_switchdev_blocking_nb, + extack); if (err) goto err_switchdev_offload; @@ -1964,7 +1970,9 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev) { - switchdev_bridge_port_unoffload(netdev); + switchdev_bridge_port_unoffload(netdev, NULL, + &dpaa2_switch_port_switchdev_nb, + &dpaa2_switch_port_switchdev_blocking_nb); } static int dpaa2_switch_port_bridge_leave(struct net_device *netdev) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index 8cf3fe3b7e58..7fe1287228e5 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -501,7 +501,8 @@ int prestera_bridge_port_join(struct net_device *br_dev, goto err_brport_create; } - err = switchdev_bridge_port_offload(br_port->dev, port->dev, extack); + err = switchdev_bridge_port_offload(br_port->dev, port->dev, NULL, + NULL, NULL, extack); if (err) goto err_switchdev_offload; @@ -515,7 +516,7 @@ int prestera_bridge_port_join(struct net_device *br_dev, return 0; err_port_join: - switchdev_bridge_port_unoffload(br_port->dev); + switchdev_bridge_port_unoffload(br_port->dev, NULL, NULL, NULL); err_switchdev_offload: prestera_bridge_port_put(br_port); err_brport_create: @@ -591,7 +592,7 @@ void prestera_bridge_port_leave(struct net_device *br_dev, else prestera_bridge_1d_port_leave(br_port); - switchdev_bridge_port_unoffload(br_port->dev); + switchdev_bridge_port_unoffload(br_port->dev, NULL, NULL, NULL); prestera_hw_port_learning_set(port, false); prestera_hw_port_flood_set(port, BR_FLOOD | BR_MCAST_FLOOD, 0); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index c52317de1f35..0a53f1d8e7e1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -362,7 +362,7 @@ mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device, bridge_port->ref_count = 1; err = switchdev_bridge_port_offload(brport_dev, mlxsw_sp_port->dev, - extack); + NULL, NULL, NULL, extack); if (err) goto err_switchdev_offload; @@ -377,7 +377,7 @@ err_switchdev_offload: static void mlxsw_sp_bridge_port_destroy(struct mlxsw_sp_bridge_port *bridge_port) { - switchdev_bridge_port_unoffload(bridge_port->dev); + switchdev_bridge_port_unoffload(bridge_port->dev, NULL, NULL, NULL); list_del(&bridge_port->list); WARN_ON(!list_empty(&bridge_port->vlans_list)); kfree(bridge_port); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c index e4fb573563d0..807dc45cfae4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c @@ -112,7 +112,8 @@ static int sparx5_port_bridge_join(struct sparx5_port *port, set_bit(port->portno, sparx5->bridge_mask); - err = switchdev_bridge_port_offload(ndev, ndev, extack); + err = switchdev_bridge_port_offload(ndev, ndev, NULL, NULL, NULL, + extack); if (err) goto err_switchdev_offload; @@ -133,7 +134,7 @@ static void sparx5_port_bridge_leave(struct sparx5_port *port, { struct sparx5 *sparx5 = port->sparx5; - switchdev_bridge_port_unoffload(port->ndev); + switchdev_bridge_port_unoffload(port->ndev, NULL, NULL, NULL); clear_bit(port->portno, sparx5->bridge_mask); if (bitmap_empty(sparx5->bridge_mask, SPX5_PORTS)) diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 76b7b9536bf7..3558ee8d9212 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -1154,38 +1154,19 @@ static int ocelot_switchdev_sync(struct ocelot *ocelot, int port, struct net_device *bridge_dev, struct netlink_ext_ack *extack) { - struct ocelot_port *ocelot_port = ocelot->ports[port]; - struct ocelot_port_private *priv; clock_t ageing_time; u8 stp_state; - int err; - - priv = container_of(ocelot_port, struct ocelot_port_private, port); ocelot_inherit_brport_flags(ocelot, port, brport_dev); stp_state = br_port_get_stp_state(brport_dev); ocelot_bridge_stp_state_set(ocelot, port, stp_state); - err = ocelot_port_vlan_filtering(ocelot, port, - br_vlan_enabled(bridge_dev)); - if (err) - return err; - ageing_time = br_get_ageing_time(bridge_dev); ocelot_port_attr_ageing_set(ocelot, port, ageing_time); - err = br_mdb_replay(bridge_dev, brport_dev, priv, true, - &ocelot_switchdev_blocking_nb, extack); - if (err && err != -EOPNOTSUPP) - return err; - - err = br_vlan_replay(bridge_dev, brport_dev, priv, true, - &ocelot_switchdev_blocking_nb, extack); - if (err && err != -EOPNOTSUPP) - return err; - - return 0; + return ocelot_port_vlan_filtering(ocelot, port, + br_vlan_enabled(bridge_dev)); } static int ocelot_switchdev_unsync(struct ocelot *ocelot, int port) @@ -1216,7 +1197,10 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev, ocelot_port_bridge_join(ocelot, port, bridge); - err = switchdev_bridge_port_offload(brport_dev, dev, extack); + err = switchdev_bridge_port_offload(brport_dev, dev, priv, + &ocelot_netdevice_nb, + &ocelot_switchdev_blocking_nb, + extack); if (err) goto err_switchdev_offload; @@ -1227,15 +1211,22 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev, return 0; err_switchdev_sync: - switchdev_bridge_port_unoffload(brport_dev); + switchdev_bridge_port_unoffload(brport_dev, priv, + &ocelot_netdevice_nb, + &ocelot_switchdev_blocking_nb); err_switchdev_offload: ocelot_port_bridge_leave(ocelot, port, bridge); return err; } -static void ocelot_netdevice_pre_bridge_leave(struct net_device *brport_dev) +static void ocelot_netdevice_pre_bridge_leave(struct net_device *dev, + struct net_device *brport_dev) { - switchdev_bridge_port_unoffload(brport_dev); + struct ocelot_port_private *priv = netdev_priv(dev); + + switchdev_bridge_port_unoffload(brport_dev, priv, + &ocelot_netdevice_nb, + &ocelot_switchdev_blocking_nb); } static int ocelot_netdevice_bridge_leave(struct net_device *dev, @@ -1299,7 +1290,7 @@ static void ocelot_netdevice_pre_lag_leave(struct net_device *dev, if (!bridge_dev || !netif_is_bridge_master(bridge_dev)) return; - ocelot_netdevice_pre_bridge_leave(bond); + ocelot_netdevice_pre_bridge_leave(dev, bond); } static int ocelot_netdevice_lag_leave(struct net_device *dev, @@ -1384,7 +1375,7 @@ ocelot_netdevice_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { if (netif_is_bridge_master(info->upper_dev) && !info->linking) - ocelot_netdevice_pre_bridge_leave(brport_dev); + ocelot_netdevice_pre_bridge_leave(dev, brport_dev); if (netif_is_lag_master(info->upper_dev) && !info->linking) ocelot_netdevice_pre_lag_leave(dev, info->upper_dev); diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 84dcaf8687a0..03df6a24d0ba 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -2598,7 +2598,8 @@ static int ofdpa_port_bridge_join(struct ofdpa_port *ofdpa_port, if (err) return err; - return switchdev_bridge_port_offload(dev, dev, extack); + return switchdev_bridge_port_offload(dev, dev, NULL, NULL, NULL, + extack); } static int ofdpa_port_bridge_leave(struct ofdpa_port *ofdpa_port) @@ -2606,7 +2607,7 @@ static int ofdpa_port_bridge_leave(struct ofdpa_port *ofdpa_port) struct net_device *dev = ofdpa_port->dev; int err; - switchdev_bridge_port_unoffload(dev); + switchdev_bridge_port_unoffload(dev, NULL, NULL, NULL); err = ofdpa_port_vlan_del(ofdpa_port, OFDPA_UNTAGGED_VID, 0); if (err) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 8b9596eb808e..b285606f963d 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2096,7 +2096,8 @@ static int am65_cpsw_netdevice_port_link(struct net_device *ndev, return -EOPNOTSUPP; } - err = switchdev_bridge_port_offload(ndev, ndev, extack); + err = switchdev_bridge_port_offload(ndev, ndev, NULL, NULL, NULL, + extack); if (err) return err; @@ -2112,7 +2113,7 @@ static void am65_cpsw_netdevice_port_unlink(struct net_device *ndev) struct am65_cpsw_common *common = am65_ndev_to_common(ndev); struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(ndev); - switchdev_bridge_port_unoffload(ndev); + switchdev_bridge_port_unoffload(ndev, NULL, NULL, NULL); common->br_members &= ~BIT(priv->port->port_id); diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index bf9cadfb11b5..31030f73840d 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1517,7 +1517,8 @@ static int cpsw_netdevice_port_link(struct net_device *ndev, return -EOPNOTSUPP; } - err = switchdev_bridge_port_offload(ndev, ndev, extack); + err = switchdev_bridge_port_offload(ndev, ndev, NULL, NULL, NULL, + extack); if (err) return err; @@ -1533,7 +1534,7 @@ static void cpsw_netdevice_port_unlink(struct net_device *ndev) struct cpsw_priv *priv = netdev_priv(ndev); struct cpsw_common *cpsw = priv->cpsw; - switchdev_bridge_port_unoffload(ndev); + switchdev_bridge_port_unoffload(ndev, NULL, NULL, NULL); cpsw->br_members &= ~BIT(priv->emac_port); diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index ce413eca527e..bbf680093823 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -70,9 +70,6 @@ bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); bool br_multicast_has_router_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); bool br_multicast_router(const struct net_device *dev); -int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -104,13 +101,6 @@ static inline bool br_multicast_router(const struct net_device *dev) { return false; } -static inline int br_mdb_replay(const struct net_device *br_dev, - const struct net_device *dev, const void *ctx, - bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack) -{ - return -EOPNOTSUPP; -} #endif #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) @@ -120,9 +110,6 @@ int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid); int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); -int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -149,14 +136,6 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, { return -EINVAL; } - -static inline int br_vlan_replay(struct net_device *br_dev, - struct net_device *dev, const void *ctx, - bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack) -{ - return -EOPNOTSUPP; -} #endif #if IS_ENABLED(CONFIG_BRIDGE) @@ -167,8 +146,6 @@ void br_fdb_clear_offload(const struct net_device *dev, u16 vid); bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); u8 br_port_get_stp_state(const struct net_device *dev); clock_t br_get_ageing_time(const struct net_device *br_dev); -int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb); #else static inline struct net_device * br_fdb_find_port(const struct net_device *br_dev, @@ -197,32 +174,37 @@ static inline clock_t br_get_ageing_time(const struct net_device *br_dev) { return 0; } - -static inline int br_fdb_replay(const struct net_device *br_dev, - const struct net_device *dev, const void *ctx, - bool adding, struct notifier_block *nb) -{ - return -EOPNOTSUPP; -} #endif #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_NET_SWITCHDEV) int switchdev_bridge_port_offload(struct net_device *brport_dev, - struct net_device *dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, struct netlink_ext_ack *extack); -void switchdev_bridge_port_unoffload(struct net_device *brport_dev); +void switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb); #else -static inline int switchdev_bridge_port_offload(struct net_device *brport_dev, - struct net_device *dev, - struct netlink_ext_ack *extack) +static inline int +switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + struct netlink_ext_ack *extack) { return -EINVAL; } -static inline void switchdev_bridge_port_unoffload(struct net_device *brport_dev) +static inline void +switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) { } #endif diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 47f190b6bfa3..7747442e6572 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -795,7 +795,6 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, return err; } -EXPORT_SYMBOL_GPL(br_fdb_replay); static void fdb_notify(struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, int type, diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index e58f1a4ac962..73a8915b0148 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -689,7 +689,6 @@ out_free_mdb: return err; } -EXPORT_SYMBOL_GPL(br_mdb_replay); static void br_mdb_switchdev_host_port(struct net_device *dev, struct net_device *lower_dev, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index fbf73a5256d0..2f32d330b648 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -769,6 +769,8 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, bool swdev_notify); void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, bool offloaded); +int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, + const void *ctx, bool adding, struct notifier_block *nb); /* br_forward.c */ enum br_pkt_type { @@ -929,6 +931,10 @@ int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on, struct netlink_ext_ack *extack); bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan, bool on); +int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack); + static inline bool br_group_is_l2(const struct br_ip *group) { return group->proto == 0; @@ -1307,6 +1313,14 @@ static inline bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan, { return false; } + +static inline int br_mdb_replay(struct net_device *br_dev, + struct net_device *dev, const void *ctx, + bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} #endif /* br_vlan.c */ @@ -1358,6 +1372,9 @@ void br_vlan_notify(const struct net_bridge *br, const struct net_bridge_port *p, u16 vid, u16 vid_range, int cmd); +int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack); bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end); @@ -1603,6 +1620,14 @@ static inline bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, { return true; } + +static inline int br_vlan_replay(struct net_device *br_dev, + struct net_device *dev, const void *ctx, + bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} #endif /* br_vlan_options.c */ diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 39f0787fde01..6bfff28ede23 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -206,11 +206,62 @@ static void nbp_switchdev_del(struct net_bridge_port *p) nbp_switchdev_hwdom_put(p); } +static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + struct netlink_ext_ack *extack) +{ + struct net_device *br_dev = p->br->dev; + struct net_device *dev = p->dev; + int err; + + err = br_vlan_replay(br_dev, dev, ctx, true, blocking_nb, extack); + if (err && err != -EOPNOTSUPP) + return err; + + err = br_mdb_replay(br_dev, dev, ctx, true, blocking_nb, extack); + if (err && err != -EOPNOTSUPP) + return err; + + /* Forwarding and termination FDB entries on the port */ + err = br_fdb_replay(br_dev, dev, ctx, true, atomic_nb); + if (err && err != -EOPNOTSUPP) + return err; + + /* Termination FDB entries on the bridge itself */ + err = br_fdb_replay(br_dev, br_dev, ctx, true, atomic_nb); + if (err && err != -EOPNOTSUPP) + return err; + + return 0; +} + +static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) +{ + struct net_device *br_dev = p->br->dev; + struct net_device *dev = p->dev; + + br_vlan_replay(br_dev, dev, ctx, false, blocking_nb, NULL); + + br_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); + + /* Forwarding and termination FDB entries on the port */ + br_fdb_replay(br_dev, dev, ctx, false, atomic_nb); + + /* Termination FDB entries on the bridge itself */ + br_fdb_replay(br_dev, br_dev, ctx, false, atomic_nb); +} + /* Let the bridge know that this port is offloaded, so that it can assign a * switchdev hardware domain to it. */ int switchdev_bridge_port_offload(struct net_device *brport_dev, - struct net_device *dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, struct netlink_ext_ack *extack) { struct netdev_phys_item_id ppid; @@ -227,11 +278,27 @@ int switchdev_bridge_port_offload(struct net_device *brport_dev, if (err) return err; - return nbp_switchdev_add(p, ppid, extack); + err = nbp_switchdev_add(p, ppid, extack); + if (err) + return err; + + err = nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack); + if (err) + goto out_switchdev_del; + + return 0; + +out_switchdev_del: + nbp_switchdev_del(p); + + return err; } EXPORT_SYMBOL_GPL(switchdev_bridge_port_offload); -void switchdev_bridge_port_unoffload(struct net_device *brport_dev) +void switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) { struct net_bridge_port *p; @@ -241,6 +308,8 @@ void switchdev_bridge_port_unoffload(struct net_device *brport_dev) if (!p) return; + nbp_switchdev_unsync_objs(p, ctx, atomic_nb, blocking_nb); + nbp_switchdev_del(p); } EXPORT_SYMBOL_GPL(switchdev_bridge_port_unoffload); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 45ef07f682f1..382ab992badf 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1905,7 +1905,6 @@ int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, return err; } -EXPORT_SYMBOL_GPL(br_vlan_replay); /* check if v_curr can enter a range ending in range_end */ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 4d3ab9e6183a..78c70f5bdab5 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -204,16 +204,14 @@ void dsa_port_disable_rt(struct dsa_port *dp); void dsa_port_disable(struct dsa_port *dp); int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, struct netlink_ext_ack *extack); -int dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br, - struct netlink_ext_ack *extack); +void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br); void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); int dsa_port_lag_change(struct dsa_port *dp, struct netdev_lag_lower_state_info *linfo); int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev, struct netdev_lag_upper_info *uinfo, struct netlink_ext_ack *extack); -int dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev, - struct netlink_ext_ack *extack); +void dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, struct netlink_ext_ack *extack); diff --git a/net/dsa/port.c b/net/dsa/port.c index 7accda066149..d81c283b7358 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -167,8 +167,8 @@ static void dsa_port_clear_brport_flags(struct dsa_port *dp) } } -static int dsa_port_switchdev_sync(struct dsa_port *dp, - struct netlink_ext_ack *extack) +static int dsa_port_switchdev_sync_attrs(struct dsa_port *dp, + struct netlink_ext_ack *extack) { struct net_device *brport_dev = dsa_port_to_bridge_port(dp); struct net_device *br = dp->bridge_dev; @@ -194,59 +194,6 @@ static int dsa_port_switchdev_sync(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - err = br_mdb_replay(br, brport_dev, dp, true, - &dsa_slave_switchdev_blocking_notifier, extack); - if (err && err != -EOPNOTSUPP) - return err; - - /* Forwarding and termination FDB entries on the port */ - err = br_fdb_replay(br, brport_dev, dp, true, - &dsa_slave_switchdev_notifier); - if (err && err != -EOPNOTSUPP) - return err; - - /* Termination FDB entries on the bridge itself */ - err = br_fdb_replay(br, br, dp, true, &dsa_slave_switchdev_notifier); - if (err && err != -EOPNOTSUPP) - return err; - - err = br_vlan_replay(br, brport_dev, dp, true, - &dsa_slave_switchdev_blocking_notifier, extack); - if (err && err != -EOPNOTSUPP) - return err; - - return 0; -} - -static int dsa_port_switchdev_unsync_objs(struct dsa_port *dp, - struct net_device *br, - struct netlink_ext_ack *extack) -{ - struct net_device *brport_dev = dsa_port_to_bridge_port(dp); - int err; - - /* Delete the switchdev objects left on this port */ - err = br_mdb_replay(br, brport_dev, dp, false, - &dsa_slave_switchdev_blocking_notifier, extack); - if (err && err != -EOPNOTSUPP) - return err; - - /* Forwarding and termination FDB entries on the port */ - err = br_fdb_replay(br, brport_dev, dp, false, - &dsa_slave_switchdev_notifier); - if (err && err != -EOPNOTSUPP) - return err; - - /* Termination FDB entries on the bridge itself */ - err = br_fdb_replay(br, br, dp, false, &dsa_slave_switchdev_notifier); - if (err && err != -EOPNOTSUPP) - return err; - - err = br_vlan_replay(br, brport_dev, dp, false, - &dsa_slave_switchdev_blocking_notifier, extack); - if (err && err != -EOPNOTSUPP) - return err; - return 0; } @@ -307,18 +254,23 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, if (err) goto out_rollback; - err = switchdev_bridge_port_offload(brport_dev, dev, extack); + err = switchdev_bridge_port_offload(brport_dev, dev, dp, + &dsa_slave_switchdev_notifier, + &dsa_slave_switchdev_blocking_notifier, + extack); if (err) goto out_rollback_unbridge; - err = dsa_port_switchdev_sync(dp, extack); + err = dsa_port_switchdev_sync_attrs(dp, extack); if (err) goto out_rollback_unoffload; return 0; out_rollback_unoffload: - switchdev_bridge_port_unoffload(brport_dev); + switchdev_bridge_port_unoffload(brport_dev, dp, + &dsa_slave_switchdev_notifier, + &dsa_slave_switchdev_blocking_notifier); out_rollback_unbridge: dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); out_rollback: @@ -326,14 +278,13 @@ out_rollback: return err; } -int dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br, - struct netlink_ext_ack *extack) +void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br) { struct net_device *brport_dev = dsa_port_to_bridge_port(dp); - switchdev_bridge_port_unoffload(brport_dev); - - return dsa_port_switchdev_unsync_objs(dp, br, extack); + switchdev_bridge_port_unoffload(brport_dev, dp, + &dsa_slave_switchdev_notifier, + &dsa_slave_switchdev_blocking_notifier); } void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) @@ -423,13 +374,10 @@ err_lag_join: return err; } -int dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag, - struct netlink_ext_ack *extack) +void dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag) { if (dp->bridge_dev) - return dsa_port_pre_bridge_leave(dp, dp->bridge_dev, extack); - - return 0; + dsa_port_pre_bridge_leave(dp, dp->bridge_dev); } void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 22ce11cd770e..8105f642572b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2052,20 +2052,16 @@ static int dsa_slave_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct netlink_ext_ack *extack; - int err = 0; - - extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_bridge_master(info->upper_dev) && !info->linking) - err = dsa_port_pre_bridge_leave(dp, info->upper_dev, extack); + dsa_port_pre_bridge_leave(dp, info->upper_dev); else if (netif_is_lag_master(info->upper_dev) && !info->linking) - err = dsa_port_pre_lag_leave(dp, info->upper_dev, extack); + dsa_port_pre_lag_leave(dp, info->upper_dev); /* dsa_port_pre_hsr_leave is not yet necessary since hsr cannot be * meaningfully enslaved to a bridge yet */ - return notifier_from_errno(err); + return NOTIFY_DONE; } static int -- cgit v1.2.3 From 63fb60c2fcc94d595a184fa187bdfb25e5ecd4a2 Mon Sep 17 00:00:00 2001 From: Sonia Sharma Date: Wed, 21 Jul 2021 14:41:03 -0700 Subject: hv: hyperv.h: Remove unused inline functions There are some unused inline functions in hyper.h. Remove those unused functions. Signed-off-by: Sonia Sharma Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1626903663-23615-1-git-send-email-sosha@linux.microsoft.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2e859d2f9609..ddc8713ce57b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -538,12 +538,6 @@ struct vmbus_channel_rescind_offer { u32 child_relid; } __packed; -static inline u32 -hv_ringbuffer_pending_size(const struct hv_ring_buffer_info *rbi) -{ - return rbi->ring_buffer->pending_send_sz; -} - /* * Request Offer -- no parameters, SynIC message contains the partition ID * Set Snoop -- no parameters, SynIC message contains the partition ID @@ -1092,16 +1086,6 @@ static inline void set_channel_pending_send_size(struct vmbus_channel *c, c->outbound.ring_buffer->pending_send_sz = size; } -static inline void set_low_latency_mode(struct vmbus_channel *c) -{ - c->low_latency = true; -} - -static inline void clear_low_latency_mode(struct vmbus_channel *c) -{ - c->low_latency = false; -} - void vmbus_onmessage(struct vmbus_channel_message_header *hdr); int vmbus_request_offers(void); -- cgit v1.2.3 From 1a33b18b3bd9748c9c712a23e788bf1f1c4a7025 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 22 Jul 2021 16:28:58 +0200 Subject: compat: make linux/compat.h available everywhere Parts of linux/compat.h are under an #ifdef, but we end up using more of those over time, moving things around bit by bit. To get it over with once and for all, make all of this file uncondititonal now so it can be accessed everywhere. There are only a few types left that are in asm/compat.h but not yet in the asm-generic version, so add those in the process. This requires providing a few more types in asm-generic/compat.h that were not already there. The only tricky one is compat_sigset_t, which needs a little help on 32-bit architectures and for x86. Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Signed-off-by: David S. Miller --- arch/arm64/include/asm/compat.h | 14 +++----------- arch/mips/include/asm/compat.h | 24 +++++++++++------------- arch/parisc/include/asm/compat.h | 14 +++----------- arch/powerpc/include/asm/compat.h | 11 ----------- arch/s390/include/asm/compat.h | 14 +++----------- arch/sparc/include/asm/compat.h | 14 +++----------- arch/x86/include/asm/compat.h | 14 +++----------- arch/x86/include/asm/signal.h | 1 + include/asm-generic/compat.h | 17 +++++++++++++++++ include/linux/compat.h | 32 +++++++++++++++----------------- 10 files changed, 59 insertions(+), 96 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 23a9fb73c04f..79c1a750e357 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -5,6 +5,9 @@ #ifndef __ASM_COMPAT_H #define __ASM_COMPAT_H +#define compat_mode_t compat_mode_t +typedef u16 compat_mode_t; + #include #ifdef CONFIG_COMPAT @@ -27,13 +30,9 @@ typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; typedef u16 __compat_uid16_t; typedef u16 __compat_gid16_t; -typedef u32 __compat_uid32_t; -typedef u32 __compat_gid32_t; -typedef u16 compat_mode_t; typedef u32 compat_dev_t; typedef s32 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { @@ -103,13 +102,6 @@ struct compat_statfs { #define COMPAT_RLIM_INFINITY 0xffffffff -typedef u32 compat_old_sigset_t; - -#define _COMPAT_NSIG 64 -#define _COMPAT_NSIG_BPW 32 - -typedef u32 compat_sigset_word; - #define COMPAT_OFF_T_MAX 0x7fffffff #define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current))) diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 65975712a22d..53f015a1b0a7 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -9,20 +9,25 @@ #include #include +typedef s32 __compat_uid_t; +typedef s32 __compat_gid_t; +typedef __compat_uid_t __compat_uid32_t; +typedef __compat_gid_t __compat_gid32_t; +#define __compat_uid32_t __compat_uid32_t +#define __compat_gid32_t __compat_gid32_t + +#define _COMPAT_NSIG 128 /* Don't ask !$@#% ... */ +#define _COMPAT_NSIG_BPW 32 +typedef u32 compat_sigset_word; + #include #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "mips\0\0\0" -typedef s32 __compat_uid_t; -typedef s32 __compat_gid_t; -typedef __compat_uid_t __compat_uid32_t; -typedef __compat_gid_t __compat_gid32_t; -typedef u32 compat_mode_t; typedef u32 compat_dev_t; typedef u32 compat_nlink_t; typedef s32 compat_ipc_pid_t; -typedef s32 compat_caddr_t; typedef struct { s32 val[2]; } compat_fsid_t; @@ -89,13 +94,6 @@ struct compat_statfs { #define COMPAT_RLIM_INFINITY 0x7fffffffUL -typedef u32 compat_old_sigset_t; /* at least 32 bits */ - -#define _COMPAT_NSIG 128 /* Don't ask !$@#% ... */ -#define _COMPAT_NSIG_BPW 32 - -typedef u32 compat_sigset_word; - #define COMPAT_OFF_T_MAX 0x7fffffff static inline void __user *arch_compat_alloc_user_space(long len) diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 1a609d38f667..b5d90e82b65d 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -8,6 +8,9 @@ #include #include +#define compat_mode_t compat_mode_t +typedef u16 compat_mode_t; + #include #define COMPAT_USER_HZ 100 @@ -15,13 +18,9 @@ typedef u32 __compat_uid_t; typedef u32 __compat_gid_t; -typedef u32 __compat_uid32_t; -typedef u32 __compat_gid32_t; -typedef u16 compat_mode_t; typedef u32 compat_dev_t; typedef u16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef u32 compat_caddr_t; struct compat_stat { compat_dev_t st_dev; /* dev_t is 32 bits on parisc */ @@ -96,13 +95,6 @@ struct compat_sigcontext { #define COMPAT_RLIM_INFINITY 0xffffffff -typedef u32 compat_old_sigset_t; /* at least 32 bits */ - -#define _COMPAT_NSIG 64 -#define _COMPAT_NSIG_BPW 32 - -typedef u32 compat_sigset_word; - #define COMPAT_OFF_T_MAX 0x7fffffff struct compat_ipc64_perm { diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 9191fc29e6ed..e33dcf134cdd 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -19,13 +19,9 @@ typedef u32 __compat_uid_t; typedef u32 __compat_gid_t; -typedef u32 __compat_uid32_t; -typedef u32 __compat_gid32_t; -typedef u32 compat_mode_t; typedef u32 compat_dev_t; typedef s16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { @@ -85,13 +81,6 @@ struct compat_statfs { #define COMPAT_RLIM_INFINITY 0xffffffff -typedef u32 compat_old_sigset_t; - -#define _COMPAT_NSIG 64 -#define _COMPAT_NSIG_BPW 32 - -typedef u32 compat_sigset_word; - #define COMPAT_OFF_T_MAX 0x7fffffff static inline void __user *arch_compat_alloc_user_space(long len) diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index ea5b9c34b7be..8d49505b4a43 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -9,6 +9,9 @@ #include #include +#define compat_mode_t compat_mode_t +typedef u16 compat_mode_t; + #include #define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p( \ @@ -55,13 +58,9 @@ typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; -typedef u32 __compat_uid32_t; -typedef u32 __compat_gid32_t; -typedef u16 compat_mode_t; typedef u16 compat_dev_t; typedef u16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; typedef struct { @@ -155,13 +154,6 @@ struct compat_statfs64 { #define COMPAT_RLIM_INFINITY 0xffffffff -typedef u32 compat_old_sigset_t; /* at least 32 bits */ - -#define _COMPAT_NSIG 64 -#define _COMPAT_NSIG_BPW 32 - -typedef u32 compat_sigset_word; - #define COMPAT_OFF_T_MAX 0x7fffffff /* diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index b85842cda99f..8b63410e830f 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -6,6 +6,9 @@ */ #include +#define compat_mode_t compat_mode_t +typedef u16 compat_mode_t; + #include #define COMPAT_USER_HZ 100 @@ -13,13 +16,9 @@ typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; -typedef u32 __compat_uid32_t; -typedef u32 __compat_gid32_t; -typedef u16 compat_mode_t; typedef u16 compat_dev_t; typedef s16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { @@ -115,13 +114,6 @@ struct compat_statfs { #define COMPAT_RLIM_INFINITY 0x7fffffff -typedef u32 compat_old_sigset_t; - -#define _COMPAT_NSIG 64 -#define _COMPAT_NSIG_BPW 32 - -typedef u32 compat_sigset_word; - #define COMPAT_OFF_T_MAX 0x7fffffff #ifdef CONFIG_COMPAT diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index be09c7eac89f..4ae01cdb99de 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -12,6 +12,9 @@ #include #include +#define compat_mode_t compat_mode_t +typedef u16 compat_mode_t; + #include #define COMPAT_USER_HZ 100 @@ -19,13 +22,9 @@ typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; -typedef u32 __compat_uid32_t; -typedef u32 __compat_gid32_t; -typedef u16 compat_mode_t; typedef u16 compat_dev_t; typedef u16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { @@ -92,13 +91,6 @@ struct compat_statfs { #define COMPAT_RLIM_INFINITY 0xffffffff -typedef u32 compat_old_sigset_t; /* at least 32 bits */ - -#define _COMPAT_NSIG 64 -#define _COMPAT_NSIG_BPW 32 - -typedef u32 compat_sigset_word; - #define COMPAT_OFF_T_MAX 0x7fffffff struct compat_ipc64_perm { diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 6fd8410a3910..2dfb5fea13af 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -29,6 +29,7 @@ typedef struct { #define SA_X32_ABI 0x01000000u #ifndef CONFIG_COMPAT +#define compat_sigset_t compat_sigset_t typedef sigset_t compat_sigset_t; #endif diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index 30f7b18a36f9..d46c0201cc34 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -20,7 +20,18 @@ typedef u16 compat_ushort_t; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u32 compat_uptr_t; +typedef u32 compat_caddr_t; typedef u32 compat_aio_context_t; +typedef u32 compat_old_sigset_t; + +#ifndef __compat_uid32_t +typedef u32 __compat_uid32_t; +typedef u32 __compat_gid32_t; +#endif + +#ifndef compat_mode_t +typedef u32 compat_mode_t; +#endif #ifdef CONFIG_COMPAT_FOR_U64_ALIGNMENT typedef s64 __attribute__((aligned(4))) compat_s64; @@ -30,4 +41,10 @@ typedef s64 compat_s64; typedef u64 compat_u64; #endif +#ifndef _COMPAT_NSIG +typedef u32 compat_sigset_word; +#define _COMPAT_NSIG _NSIG +#define _COMPAT_NSIG_BPW 32 +#endif + #endif diff --git a/include/linux/compat.h b/include/linux/compat.h index c270124e4402..8e0598c7d1d1 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -20,11 +20,8 @@ #include #include - -#ifdef CONFIG_COMPAT #include #include -#endif #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER /* @@ -95,8 +92,6 @@ struct compat_iovec { compat_size_t iov_len; }; -#ifdef CONFIG_COMPAT - #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() #endif @@ -131,9 +126,11 @@ struct compat_tms { #define _COMPAT_NSIG_WORDS (_COMPAT_NSIG / _COMPAT_NSIG_BPW) +#ifndef compat_sigset_t typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; +#endif int set_compat_user_sigmask(const compat_sigset_t __user *umask, size_t sigsetsize); @@ -384,6 +381,7 @@ struct compat_keyctl_kdf_params { __u32 __spare[8]; }; +struct compat_stat; struct compat_statfs; struct compat_statfs64; struct compat_old_linux_dirent; @@ -428,7 +426,7 @@ put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, unsigned int size) { /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ -#ifdef __BIG_ENDIAN +#if defined(__BIG_ENDIAN) && defined(CONFIG_64BIT) compat_sigset_t v; switch (_NSIG_WORDS) { case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; @@ -929,17 +927,6 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ - -/* - * For most but not all architectures, "am I in a compat syscall?" and - * "am I a compat task?" are the same question. For architectures on which - * they aren't the same question, arch code can override in_compat_syscall. - */ - -#ifndef in_compat_syscall -static inline bool in_compat_syscall(void) { return is_compat_task(); } -#endif - /** * ns_to_old_timeval32 - Compat version of ns_to_timeval * @nsec: the nanoseconds value to be converted @@ -969,6 +956,17 @@ int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user * buf); +#ifdef CONFIG_COMPAT + +/* + * For most but not all architectures, "am I in a compat syscall?" and + * "am I a compat task?" are the same question. For architectures on which + * they aren't the same question, arch code can override in_compat_syscall. + */ +#ifndef in_compat_syscall +static inline bool in_compat_syscall(void) { return is_compat_task(); } +#endif + #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) -- cgit v1.2.3 From dd98d2895de6485c884a9cb42de69fed02826fa4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 22 Jul 2021 16:28:59 +0200 Subject: ethtool: improve compat ioctl handling The ethtool compat ioctl handling is hidden away in net/socket.c, which introduces a couple of minor oddities: - The implementation may end up diverging, as seen in the RXNFC extension in commit 84a1d9c48200 ("net: ethtool: extend RXNFC API to support RSS spreading of filter matches") that does not work in compat mode. - Most architectures do not need the compat handling at all because u64 and compat_u64 have the same alignment. - On x86, the conversion is done for both x32 and i386 user space, but it's actually wrong to do it for x32 and cannot work there. - On 32-bit Arm, it never worked for compat oabi user space, since that needs to do the same conversion but does not. - It would be nice to get rid of both compat_alloc_user_space() and copy_in_user() throughout the kernel. None of these actually seems to be a serious problem that real users are likely to encounter, but fixing all of them actually leads to code that is both shorter and more readable. Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/ethtool.h | 4 -- net/ethtool/ioctl.c | 136 ++++++++++++++++++++++++++++++++++++++++++------ net/socket.c | 125 +------------------------------------------- 3 files changed, 121 insertions(+), 144 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 232daaec56e4..4711b96dae0c 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -17,8 +17,6 @@ #include #include -#ifdef CONFIG_COMPAT - struct compat_ethtool_rx_flow_spec { u32 flow_type; union ethtool_flow_union h_u; @@ -38,8 +36,6 @@ struct compat_ethtool_rxnfc { u32 rule_locs[]; }; -#endif /* CONFIG_COMPAT */ - #include /** diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index baa5d10043cb..6134b180f59f 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -7,6 +7,7 @@ * the information ethtool needs. */ +#include #include #include #include @@ -807,6 +808,120 @@ out: return ret; } +static noinline_for_stack int +ethtool_rxnfc_copy_from_compat(struct ethtool_rxnfc *rxnfc, + const struct compat_ethtool_rxnfc __user *useraddr, + size_t size) +{ + struct compat_ethtool_rxnfc crxnfc = {}; + + /* We expect there to be holes between fs.m_ext and + * fs.ring_cookie and at the end of fs, but nowhere else. + * On non-x86, no conversion should be needed. + */ + BUILD_BUG_ON(!IS_ENABLED(CONFIG_X86_64) && + sizeof(struct compat_ethtool_rxnfc) != + sizeof(struct ethtool_rxnfc)); + BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) + + sizeof(useraddr->fs.m_ext) != + offsetof(struct ethtool_rxnfc, fs.m_ext) + + sizeof(rxnfc->fs.m_ext)); + BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.location) - + offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) != + offsetof(struct ethtool_rxnfc, fs.location) - + offsetof(struct ethtool_rxnfc, fs.ring_cookie)); + + if (copy_from_user(&crxnfc, useraddr, min(size, sizeof(crxnfc)))) + return -EFAULT; + + *rxnfc = (struct ethtool_rxnfc) { + .cmd = crxnfc.cmd, + .flow_type = crxnfc.flow_type, + .data = crxnfc.data, + .fs = { + .flow_type = crxnfc.fs.flow_type, + .h_u = crxnfc.fs.h_u, + .h_ext = crxnfc.fs.h_ext, + .m_u = crxnfc.fs.m_u, + .m_ext = crxnfc.fs.m_ext, + .ring_cookie = crxnfc.fs.ring_cookie, + .location = crxnfc.fs.location, + }, + .rule_cnt = crxnfc.rule_cnt, + }; + + return 0; +} + +static int ethtool_rxnfc_copy_from_user(struct ethtool_rxnfc *rxnfc, + const void __user *useraddr, + size_t size) +{ + if (compat_need_64bit_alignment_fixup()) + return ethtool_rxnfc_copy_from_compat(rxnfc, useraddr, size); + + if (copy_from_user(rxnfc, useraddr, size)) + return -EFAULT; + + return 0; +} + +static int ethtool_rxnfc_copy_to_compat(void __user *useraddr, + const struct ethtool_rxnfc *rxnfc, + size_t size, const u32 *rule_buf) +{ + struct compat_ethtool_rxnfc crxnfc; + + memset(&crxnfc, 0, sizeof(crxnfc)); + crxnfc = (struct compat_ethtool_rxnfc) { + .cmd = rxnfc->cmd, + .flow_type = rxnfc->flow_type, + .data = rxnfc->data, + .fs = { + .flow_type = rxnfc->fs.flow_type, + .h_u = rxnfc->fs.h_u, + .h_ext = rxnfc->fs.h_ext, + .m_u = rxnfc->fs.m_u, + .m_ext = rxnfc->fs.m_ext, + .ring_cookie = rxnfc->fs.ring_cookie, + .location = rxnfc->fs.location, + }, + .rule_cnt = rxnfc->rule_cnt, + }; + + if (copy_to_user(useraddr, &crxnfc, min(size, sizeof(crxnfc)))) + return -EFAULT; + + return 0; +} + +static int ethtool_rxnfc_copy_to_user(void __user *useraddr, + const struct ethtool_rxnfc *rxnfc, + size_t size, const u32 *rule_buf) +{ + int ret; + + if (compat_need_64bit_alignment_fixup()) { + ret = ethtool_rxnfc_copy_to_compat(useraddr, rxnfc, size, + rule_buf); + useraddr += offsetof(struct compat_ethtool_rxnfc, rule_locs); + } else { + ret = copy_to_user(useraddr, &rxnfc, size); + useraddr += offsetof(struct ethtool_rxnfc, rule_locs); + } + + if (ret) + return -EFAULT; + + if (rule_buf) { + if (copy_to_user(useraddr, rule_buf, + rxnfc->rule_cnt * sizeof(u32))) + return -EFAULT; + } + + return 0; +} + static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, u32 cmd, void __user *useraddr) { @@ -825,7 +940,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, info_size = (offsetof(struct ethtool_rxnfc, data) + sizeof(info.data)); - if (copy_from_user(&info, useraddr, info_size)) + if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size)) return -EFAULT; rc = dev->ethtool_ops->set_rxnfc(dev, &info); @@ -833,7 +948,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, return rc; if (cmd == ETHTOOL_SRXCLSRLINS && - copy_to_user(useraddr, &info, info_size)) + ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, NULL)) return -EFAULT; return 0; @@ -859,7 +974,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, info_size = (offsetof(struct ethtool_rxnfc, data) + sizeof(info.data)); - if (copy_from_user(&info, useraddr, info_size)) + if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size)) return -EFAULT; /* If FLOW_RSS was requested then user-space must be using the @@ -867,7 +982,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, */ if (cmd == ETHTOOL_GRXFH && info.flow_type & FLOW_RSS) { info_size = sizeof(info); - if (copy_from_user(&info, useraddr, info_size)) + if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size)) return -EFAULT; /* Since malicious users may modify the original data, * we need to check whether FLOW_RSS is still requested. @@ -893,18 +1008,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, if (ret < 0) goto err_out; - ret = -EFAULT; - if (copy_to_user(useraddr, &info, info_size)) - goto err_out; - - if (rule_buf) { - useraddr += offsetof(struct ethtool_rxnfc, rule_locs); - if (copy_to_user(useraddr, rule_buf, - info.rule_cnt * sizeof(u32))) - goto err_out; - } - ret = 0; - + ret = ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, rule_buf); err_out: kfree(rule_buf); diff --git a/net/socket.c b/net/socket.c index 0b2dad3bdf7f..ec63cf6de33e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3152,128 +3152,6 @@ static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc3 return 0; } -static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) -{ - struct compat_ethtool_rxnfc __user *compat_rxnfc; - bool convert_in = false, convert_out = false; - size_t buf_size = 0; - struct ethtool_rxnfc __user *rxnfc = NULL; - struct ifreq ifr; - u32 rule_cnt = 0, actual_rule_cnt; - u32 ethcmd; - u32 data; - int ret; - - if (get_user(data, &ifr32->ifr_ifru.ifru_data)) - return -EFAULT; - - compat_rxnfc = compat_ptr(data); - - if (get_user(ethcmd, &compat_rxnfc->cmd)) - return -EFAULT; - - /* Most ethtool structures are defined without padding. - * Unfortunately struct ethtool_rxnfc is an exception. - */ - switch (ethcmd) { - default: - break; - case ETHTOOL_GRXCLSRLALL: - /* Buffer size is variable */ - if (get_user(rule_cnt, &compat_rxnfc->rule_cnt)) - return -EFAULT; - if (rule_cnt > KMALLOC_MAX_SIZE / sizeof(u32)) - return -ENOMEM; - buf_size += rule_cnt * sizeof(u32); - fallthrough; - case ETHTOOL_GRXRINGS: - case ETHTOOL_GRXCLSRLCNT: - case ETHTOOL_GRXCLSRULE: - case ETHTOOL_SRXCLSRLINS: - convert_out = true; - fallthrough; - case ETHTOOL_SRXCLSRLDEL: - buf_size += sizeof(struct ethtool_rxnfc); - convert_in = true; - rxnfc = compat_alloc_user_space(buf_size); - break; - } - - if (copy_from_user(&ifr.ifr_name, &ifr32->ifr_name, IFNAMSIZ)) - return -EFAULT; - - ifr.ifr_data = convert_in ? rxnfc : (void __user *)compat_rxnfc; - - if (convert_in) { - /* We expect there to be holes between fs.m_ext and - * fs.ring_cookie and at the end of fs, but nowhere else. - */ - BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) + - sizeof(compat_rxnfc->fs.m_ext) != - offsetof(struct ethtool_rxnfc, fs.m_ext) + - sizeof(rxnfc->fs.m_ext)); - BUILD_BUG_ON( - offsetof(struct compat_ethtool_rxnfc, fs.location) - - offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) != - offsetof(struct ethtool_rxnfc, fs.location) - - offsetof(struct ethtool_rxnfc, fs.ring_cookie)); - - if (copy_in_user(rxnfc, compat_rxnfc, - (void __user *)(&rxnfc->fs.m_ext + 1) - - (void __user *)rxnfc) || - copy_in_user(&rxnfc->fs.ring_cookie, - &compat_rxnfc->fs.ring_cookie, - (void __user *)(&rxnfc->fs.location + 1) - - (void __user *)&rxnfc->fs.ring_cookie)) - return -EFAULT; - if (ethcmd == ETHTOOL_GRXCLSRLALL) { - if (put_user(rule_cnt, &rxnfc->rule_cnt)) - return -EFAULT; - } else if (copy_in_user(&rxnfc->rule_cnt, - &compat_rxnfc->rule_cnt, - sizeof(rxnfc->rule_cnt))) - return -EFAULT; - } - - ret = dev_ioctl(net, SIOCETHTOOL, &ifr, NULL); - if (ret) - return ret; - - if (convert_out) { - if (copy_in_user(compat_rxnfc, rxnfc, - (const void __user *)(&rxnfc->fs.m_ext + 1) - - (const void __user *)rxnfc) || - copy_in_user(&compat_rxnfc->fs.ring_cookie, - &rxnfc->fs.ring_cookie, - (const void __user *)(&rxnfc->fs.location + 1) - - (const void __user *)&rxnfc->fs.ring_cookie) || - copy_in_user(&compat_rxnfc->rule_cnt, &rxnfc->rule_cnt, - sizeof(rxnfc->rule_cnt))) - return -EFAULT; - - if (ethcmd == ETHTOOL_GRXCLSRLALL) { - /* As an optimisation, we only copy the actual - * number of rules that the underlying - * function returned. Since Mallory might - * change the rule count in user memory, we - * check that it is less than the rule count - * originally given (as the user buffer size), - * which has been range-checked. - */ - if (get_user(actual_rule_cnt, &rxnfc->rule_cnt)) - return -EFAULT; - if (actual_rule_cnt < rule_cnt) - rule_cnt = actual_rule_cnt; - if (copy_in_user(&compat_rxnfc->rule_locs[0], - &rxnfc->rule_locs[0], - rule_cnt * sizeof(u32))) - return -EFAULT; - } - } - - return 0; -} - static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) { compat_uptr_t uptr32; @@ -3428,8 +3306,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, return old_bridge_ioctl(argp); case SIOCGIFCONF: return compat_dev_ifconf(net, argp); - case SIOCETHTOOL: - return ethtool_ioctl(net, argp); case SIOCWANDEV: return compat_siocwandev(net, argp); case SIOCGIFMAP: @@ -3442,6 +3318,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !COMPAT_USE_64BIT_TIME); + case SIOCETHTOOL: case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: -- cgit v1.2.3 From b0e99d03778b2418aec20db99d97d19d25d198b6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 22 Jul 2021 16:29:01 +0200 Subject: net: socket: remove register_gifconf Since dynamic registration of the gifconf() helper is only used for IPv4, and this can not be in a loadable module, this can be simplified noticeably by turning it into a direct function call as a preparation for cleaning up the compat handling. Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 9 +++++++++ include/linux/netdevice.h | 8 -------- net/core/dev_ioctl.c | 43 ++++++++++--------------------------------- net/ipv4/devinet.c | 4 +--- 4 files changed, 20 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 53aa0343bf69..67e042932681 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -178,6 +178,15 @@ static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); +#ifdef CONFIG_INET +int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); +#else +static inline int inet_gifconf(struct net_device *dev, char __user *buf, + int len, int size) +{ + return 0; +} +#endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 42f6f866d5f3..6630a9f0b0f0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3289,14 +3289,6 @@ static inline bool dev_has_header(const struct net_device *dev) return dev->header_ops && dev->header_ops->create; } -typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, - int len, int size); -int register_gifconf(unsigned int family, gifconf_func_t *gifconf); -static inline int unregister_gifconf(unsigned int family) -{ - return register_gifconf(family, NULL); -} - #ifdef CONFIG_NET_FLOW_LIMIT #define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ struct sd_flow_limit { diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 62f45da7ecfe..c22c3dc15ce9 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include @@ -25,26 +26,6 @@ static int dev_ifname(struct net *net, struct ifreq *ifr) return netdev_get_name(net, ifr->ifr_name, ifr->ifr_ifindex); } -static gifconf_func_t *gifconf_list[NPROTO]; - -/** - * register_gifconf - register a SIOCGIF handler - * @family: Address family - * @gifconf: Function handler - * - * Register protocol dependent address dumping routines. The handler - * that is passed must not be freed or reused until it has been replaced - * by another handler. - */ -int register_gifconf(unsigned int family, gifconf_func_t *gifconf) -{ - if (family >= NPROTO) - return -EINVAL; - gifconf_list[family] = gifconf; - return 0; -} -EXPORT_SYMBOL(register_gifconf); - /* * Perform a SIOCGIFCONF call. This structure will change * size eventually, and there is nothing I can do about it. @@ -72,19 +53,15 @@ int dev_ifconf(struct net *net, struct ifconf *ifc, int size) total = 0; for_each_netdev(net, dev) { - for (i = 0; i < NPROTO; i++) { - if (gifconf_list[i]) { - int done; - if (!pos) - done = gifconf_list[i](dev, NULL, 0, size); - else - done = gifconf_list[i](dev, pos + total, - len - total, size); - if (done < 0) - return -EFAULT; - total += done; - } - } + int done; + if (!pos) + done = inet_gifconf(dev, NULL, 0, size); + else + done = inet_gifconf(dev, pos + total, + len - total, size); + if (done < 0) + return -EFAULT; + total += done; } /* diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 94b648d9eaff..c82aded8da7d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1243,7 +1243,7 @@ out: return ret; } -static int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) +int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { struct in_device *in_dev = __in_dev_get_rtnl(dev); const struct in_ifaddr *ifa; @@ -2766,8 +2766,6 @@ void __init devinet_init(void) INIT_HLIST_HEAD(&inet_addr_lst[i]); register_pernet_subsys(&devinet_ops); - - register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0); -- cgit v1.2.3 From 876f0bf9d0d5189dca9341c8e8e8686b09db8398 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 22 Jul 2021 16:29:02 +0200 Subject: net: socket: simplify dev_ifconf handling The dev_ifconf() calling conventions make compat handling more complicated than necessary, simplify this by moving the in_compat_syscall() check into the function. Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/dev_ioctl.c | 55 ++++++++++++++++++++++--------------------- net/socket.c | 59 +++++++++++------------------------------------ 3 files changed, 44 insertions(+), 72 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6630a9f0b0f0..da2c273c7e0a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4008,7 +4008,7 @@ void netdev_rx_handler_unregister(struct net_device *dev); bool dev_valid_name(const char *name); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_copyout); -int dev_ifconf(struct net *net, struct ifconf *, int); +int dev_ifconf(struct net *net, struct ifconf __user *ifc); int dev_ethtool(struct net *net, struct ifreq *); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index c22c3dc15ce9..950e2fe5d56a 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -31,48 +31,51 @@ static int dev_ifname(struct net *net, struct ifreq *ifr) * size eventually, and there is nothing I can do about it. * Thus we will need a 'compatibility mode'. */ - -int dev_ifconf(struct net *net, struct ifconf *ifc, int size) +int dev_ifconf(struct net *net, struct ifconf __user *uifc) { struct net_device *dev; - char __user *pos; - int len; - int total; - int i; + void __user *pos; + size_t size; + int len, total = 0, done; - /* - * Fetch the caller's info block. - */ + /* both the ifconf and the ifreq structures are slightly different */ + if (in_compat_syscall()) { + struct compat_ifconf ifc32; + + if (copy_from_user(&ifc32, uifc, sizeof(struct compat_ifconf))) + return -EFAULT; - pos = ifc->ifc_buf; - len = ifc->ifc_len; + pos = compat_ptr(ifc32.ifcbuf); + len = ifc32.ifc_len; + size = sizeof(struct compat_ifreq); + } else { + struct ifconf ifc; - /* - * Loop over the interfaces, and write an info block for each. - */ + if (copy_from_user(&ifc, uifc, sizeof(struct ifconf))) + return -EFAULT; - total = 0; + pos = ifc.ifc_buf; + len = ifc.ifc_len; + size = sizeof(struct ifreq); + } + + /* Loop over the interfaces, and write an info block for each. */ + rtnl_lock(); for_each_netdev(net, dev) { - int done; if (!pos) done = inet_gifconf(dev, NULL, 0, size); else done = inet_gifconf(dev, pos + total, len - total, size); - if (done < 0) + if (done < 0) { + rtnl_unlock(); return -EFAULT; + } total += done; } + rtnl_unlock(); - /* - * All done. Write the updated control block back to the caller. - */ - ifc->ifc_len = total; - - /* - * Both BSD and Solaris return 0 here, so we do too. - */ - return 0; + return put_user(total, &uifc->ifc_len); } static int dev_getifmap(struct net_device *dev, struct ifreq *ifr) diff --git a/net/socket.c b/net/socket.c index 62005a12ec70..ecdb7913a3bd 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1088,6 +1088,8 @@ EXPORT_SYMBOL(vlan_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, unsigned int cmd, unsigned long arg) { + struct ifreq ifr; + bool need_copyout; int err; void __user *argp = (void __user *)arg; @@ -1100,25 +1102,13 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, if (err != -ENOIOCTLCMD) return err; - if (cmd == SIOCGIFCONF) { - struct ifconf ifc; - if (copy_from_user(&ifc, argp, sizeof(struct ifconf))) - return -EFAULT; - rtnl_lock(); - err = dev_ifconf(net, &ifc, sizeof(struct ifreq)); - rtnl_unlock(); - if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf))) - err = -EFAULT; - } else { - struct ifreq ifr; - bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + return -EFAULT; + err = dev_ioctl(net, cmd, &ifr, &need_copyout); + if (!err && need_copyout) + if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; - err = dev_ioctl(net, cmd, &ifr, &need_copyout); - if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) - return -EFAULT; - } + return err; } @@ -1217,6 +1207,11 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) cmd == SIOCGSTAMP_NEW, false); break; + + case SIOCGIFCONF: + err = dev_ifconf(net, argp); + break; + default: err = sock_do_ioctl(net, sock, cmd, arg); break; @@ -3127,31 +3122,6 @@ void socket_seq_show(struct seq_file *seq) #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_COMPAT -static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32) -{ - struct compat_ifconf ifc32; - struct ifconf ifc; - int err; - - if (copy_from_user(&ifc32, uifc32, sizeof(struct compat_ifconf))) - return -EFAULT; - - ifc.ifc_len = ifc32.ifc_len; - ifc.ifc_req = compat_ptr(ifc32.ifcbuf); - - rtnl_lock(); - err = dev_ifconf(net, &ifc, sizeof(struct compat_ifreq)); - rtnl_unlock(); - if (err) - return err; - - ifc32.ifc_len = ifc.ifc_len; - if (copy_to_user(uifc32, &ifc32, sizeof(struct compat_ifconf))) - return -EFAULT; - - return 0; -} - static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) { compat_uptr_t uptr32; @@ -3270,8 +3240,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCSIFBR: case SIOCGIFBR: return old_bridge_ioctl(argp); - case SIOCGIFCONF: - return compat_dev_ifconf(net, argp); case SIOCWANDEV: return compat_siocwandev(net, argp); case SIOCGSTAMP_OLD: @@ -3299,6 +3267,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCGSKNS: case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: + case SIOCGIFCONF: return sock_ioctl(file, cmd, arg); case SIOCGIFFLAGS: -- cgit v1.2.3 From 29c4964822aad42c960d9edf67fb8209f1886baa Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 22 Jul 2021 16:29:03 +0200 Subject: net: socket: rework compat_ifreq_ioctl() compat_ifreq_ioctl() is one of the last users of copy_in_user() and compat_alloc_user_space(), as it attempts to convert the 'struct ifreq' arguments from 32-bit to 64-bit format as used by dev_ioctl() and a couple of socket family specific interpretations. The current implementation works correctly when calling dev_ioctl(), inet_ioctl(), ieee802154_sock_ioctl(), atalk_ioctl(), qrtr_ioctl() and packet_ioctl(). The ioctl handlers for x25, netrom, rose and x25 do not interpret the arguments and only block the corresponding commands, so they do not care. For af_inet6 and af_decnet however, the compat conversion is slightly incorrect, as it will copy more data than the native handler accesses, both of them use a structure that is shorter than ifreq. Replace the copy_in_user() conversion with a pair of accessor functions to read and write the ifreq data in place with the correct length where needed, while leaving the other ones to copy the (already compatible) structures directly. Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 + net/appletalk/ddp.c | 4 +- net/ieee802154/socket.c | 4 +- net/ipv4/af_inet.c | 6 +-- net/qrtr/qrtr.c | 4 +- net/socket.c | 103 +++++++++++++++++++++++++++++----------------- 6 files changed, 76 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index da2c273c7e0a..c871dc223dfa 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4006,6 +4006,8 @@ int netdev_rx_handler_register(struct net_device *dev, void netdev_rx_handler_unregister(struct net_device *dev); bool dev_valid_name(const char *name); +int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg); +int put_user_ifreq(struct ifreq *ifr, void __user *arg); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf __user *ifc); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 8ade5a4ceaf5..bf5736c1d458 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -666,7 +666,7 @@ static int atif_ioctl(int cmd, void __user *arg) struct rtentry rtdef; int add_route; - if (copy_from_user(&atreq, arg, sizeof(atreq))) + if (get_user_ifreq(&atreq, NULL, arg)) return -EFAULT; dev = __dev_get_by_name(&init_net, atreq.ifr_name); @@ -865,7 +865,7 @@ static int atif_ioctl(int cmd, void __user *arg) return 0; } - return copy_to_user(arg, &atreq, sizeof(atreq)) ? -EFAULT : 0; + return put_user_ifreq(&atreq, arg); } static int atrtr_ioctl_addrt(struct rtentry *rt) diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index a45a0401adc5..f5077de3619e 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -129,7 +129,7 @@ static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg, int ret = -ENOIOCTLCMD; struct net_device *dev; - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + if (get_user_ifreq(&ifr, NULL, arg)) return -EFAULT; ifr.ifr_name[IFNAMSIZ-1] = 0; @@ -143,7 +143,7 @@ static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg, if (dev->type == ARPHRD_IEEE802154 && dev->netdev_ops->ndo_do_ioctl) ret = dev->netdev_ops->ndo_do_ioctl(dev, &ifr, cmd); - if (!ret && copy_to_user(arg, &ifr, sizeof(struct ifreq))) + if (!ret && put_user_ifreq(&ifr, arg)) ret = -EFAULT; dev_put(dev); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 54648181dd56..0e4d758c2585 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -953,10 +953,10 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCGIFNETMASK: case SIOCGIFDSTADDR: case SIOCGIFPFLAGS: - if (copy_from_user(&ifr, p, sizeof(struct ifreq))) + if (get_user_ifreq(&ifr, NULL, p)) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); - if (!err && copy_to_user(p, &ifr, sizeof(struct ifreq))) + if (!err && put_user_ifreq(&ifr, p)) err = -EFAULT; break; @@ -966,7 +966,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCSIFDSTADDR: case SIOCSIFPFLAGS: case SIOCSIFFLAGS: - if (copy_from_user(&ifr, p, sizeof(struct ifreq))) + if (get_user_ifreq(&ifr, NULL, p)) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); break; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index e6f4a6202f82..e71847877248 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -1153,14 +1153,14 @@ static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) rc = put_user(len, (int __user *)argp); break; case SIOCGIFADDR: - if (copy_from_user(&ifr, argp, sizeof(ifr))) { + if (get_user_ifreq(&ifr, NULL, argp)) { rc = -EFAULT; break; } sq = (struct sockaddr_qrtr *)&ifr.ifr_addr; *sq = ipc->us; - if (copy_to_user(argp, &ifr, sizeof(ifr))) { + if (put_user_ifreq(&ifr, argp)) { rc = -EFAULT; break; } diff --git a/net/socket.c b/net/socket.c index ecdb7913a3bd..84de89c1ee9d 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3121,6 +3121,54 @@ void socket_seq_show(struct seq_file *seq) } #endif /* CONFIG_PROC_FS */ +/* Handle the fact that while struct ifreq has the same *layout* on + * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, + * which are handled elsewhere, it still has different *size* due to + * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, + * resulting in struct ifreq being 32 and 40 bytes respectively). + * As a result, if the struct happens to be at the end of a page and + * the next page isn't readable/writable, we get a fault. To prevent + * that, copy back and forth to the full size. + */ +int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg) +{ + if (in_compat_syscall()) { + struct compat_ifreq *ifr32 = (struct compat_ifreq *)ifr; + + memset(ifr, 0, sizeof(*ifr)); + if (copy_from_user(ifr32, arg, sizeof(*ifr32))) + return -EFAULT; + + if (ifrdata) + *ifrdata = compat_ptr(ifr32->ifr_data); + + return 0; + } + + if (copy_from_user(ifr, arg, sizeof(*ifr))) + return -EFAULT; + + if (ifrdata) + *ifrdata = ifr->ifr_data; + + return 0; +} +EXPORT_SYMBOL(get_user_ifreq); + +int put_user_ifreq(struct ifreq *ifr, void __user *arg) +{ + size_t size = sizeof(*ifr); + + if (in_compat_syscall()) + size = sizeof(struct compat_ifreq); + + if (copy_to_user(arg, ifr, size)) + return -EFAULT; + + return 0; +} +EXPORT_SYMBOL(put_user_ifreq); + #ifdef CONFIG_COMPAT static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) { @@ -3129,7 +3177,7 @@ static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32 void __user *saved; int err; - if (copy_from_user(&ifr, uifr32, sizeof(struct compat_ifreq))) + if (get_user_ifreq(&ifr, NULL, uifr32)) return -EFAULT; if (get_user(uptr32, &uifr32->ifr_settings.ifs_ifsu)) @@ -3141,7 +3189,7 @@ static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32 err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL); if (!err) { ifr.ifr_settings.ifs_ifsu.raw_hdlc = saved; - if (copy_to_user(uifr32, &ifr, sizeof(struct compat_ifreq))) + if (put_user_ifreq(&ifr, uifr32)) err = -EFAULT; } return err; @@ -3165,49 +3213,28 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, static int compat_ifreq_ioctl(struct net *net, struct socket *sock, unsigned int cmd, + unsigned long arg, struct compat_ifreq __user *uifr32) { - struct ifreq __user *uifr; + struct ifreq ifr; + bool need_copyout; int err; - /* Handle the fact that while struct ifreq has the same *layout* on - * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, - * which are handled elsewhere, it still has different *size* due to - * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, - * resulting in struct ifreq being 32 and 40 bytes respectively). - * As a result, if the struct happens to be at the end of a page and - * the next page isn't readable/writable, we get a fault. To prevent - * that, copy back and forth to the full size. + err = sock->ops->ioctl(sock, cmd, arg); + + /* If this ioctl is unknown try to hand it down + * to the NIC driver. */ + if (err != -ENOIOCTLCMD) + return err; - uifr = compat_alloc_user_space(sizeof(*uifr)); - if (copy_in_user(uifr, uifr32, sizeof(*uifr32))) + if (get_user_ifreq(&ifr, NULL, uifr32)) return -EFAULT; + err = dev_ioctl(net, cmd, &ifr, &need_copyout); + if (!err && need_copyout) + if (put_user_ifreq(&ifr, uifr32)) + return -EFAULT; - err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr); - - if (!err) { - switch (cmd) { - case SIOCGIFFLAGS: - case SIOCGIFMETRIC: - case SIOCGIFMTU: - case SIOCGIFMEM: - case SIOCGIFHWADDR: - case SIOCGIFINDEX: - case SIOCGIFADDR: - case SIOCGIFBRDADDR: - case SIOCGIFDSTADDR: - case SIOCGIFNETMASK: - case SIOCGIFPFLAGS: - case SIOCGIFTXQLEN: - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCGIFNAME: - if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) - err = -EFAULT; - break; - } - } return err; } @@ -3310,7 +3337,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - return compat_ifreq_ioctl(net, sock, cmd, argp); + return compat_ifreq_ioctl(net, sock, cmd, arg, argp); case SIOCSARP: case SIOCGARP: -- cgit v1.2.3 From 5d1ef2ce13a9098b4e0d31c50e4c79763a57b444 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 23 Jul 2021 10:53:02 +0200 Subject: ima: Introduce ima_get_current_hash_algo() Buffer measurements, unlike file measurements, are not accessible after the measurement is done, as buffers are not suitable for use with the integrity_iint_cache structure (there is no index, for files it is the inode number). In the subsequent patches, the measurement (digest) will be returned directly by the functions that perform the buffer measurement, ima_measure_critical_data() and process_buffer_measurement(). A caller of those functions also needs to know the algorithm used to calculate the digest. Instead of adding the algorithm as a new parameter to the functions, this patch provides it separately with the new function ima_get_current_hash_algo(). Since the hash algorithm does not change after the IMA setup phase, there is no risk of races (obtaining a digest calculated with a different algorithm than the one returned). Signed-off-by: Roberto Sassu Reviewed-by: Lakshmi Ramasubramanian [zohar@linux.ibm.com: annotate ima_hash_algo as __ro_after_init] Signed-off-by: Mimi Zohar --- include/linux/ima.h | 7 +++++++ security/integrity/ima/ima_main.c | 7 ++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 61d5723ec303..81e830d01ced 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -11,9 +11,11 @@ #include #include #include +#include struct linux_binprm; #ifdef CONFIG_IMA +extern enum hash_algo ima_get_current_hash_algo(void); extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask); extern void ima_post_create_tmpfile(struct user_namespace *mnt_userns, @@ -64,6 +66,11 @@ static inline const char * const *arch_get_ima_policy(void) #endif #else +static inline enum hash_algo ima_get_current_hash_algo(void) +{ + return HASH_ALGO__LAST; +} + static inline int ima_bprm_check(struct linux_binprm *bprm) { return 0; diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 287b90509006..634e4709d8af 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -35,7 +35,7 @@ int ima_appraise = IMA_APPRAISE_ENFORCE; int ima_appraise; #endif -int ima_hash_algo = HASH_ALGO_SHA1; +int __ro_after_init ima_hash_algo = HASH_ALGO_SHA1; static int hash_setup_done; static struct notifier_block ima_lsm_policy_notifier = { @@ -76,6 +76,11 @@ out: } __setup("ima_hash=", hash_setup); +enum hash_algo ima_get_current_hash_algo(void) +{ + return ima_hash_algo; +} + /* Prevent mmap'ing a file execute that is already mmap'ed write */ static int mmap_violation_check(enum ima_hooks func, struct file *file, char **pathbuf, const char **pathname, -- cgit v1.2.3 From ce5bb5a86e5ebcd3c2e40e6dd1382027b5d43caf Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 23 Jul 2021 10:53:03 +0200 Subject: ima: Return int in the functions to measure a buffer ima_measure_critical_data() and process_buffer_measurement() currently don't return a result as, unlike appraisal-related functions, the result is not used by callers to deny an operation. Measurement-related functions instead rely on the audit subsystem to notify the system administrator when an error occurs. However, ima_measure_critical_data() and process_buffer_measurement() are a special case, as these are the only functions that can return a buffer measurement (for files, there is ima_file_hash()). In a subsequent patch, they will be modified to return the calculated digest. In preparation to return the result of the digest calculation, this patch modifies the return type from void to int, and returns 0 if the buffer has been successfully measured, a negative value otherwise. Given that the result of the measurement is still not necessary, this patch does not modify the behavior of existing callers by processing the returned value. For those, the return value is ignored. Signed-off-by: Roberto Sassu Reviewed-by: Lakshmi Ramasubramanian Acked-by: Paul Moore (for the SELinux bits) Signed-off-by: Mimi Zohar --- include/linux/ima.h | 15 +++++++++------ security/integrity/ima/ima.h | 10 +++++----- security/integrity/ima/ima_main.c | 40 ++++++++++++++++++++++----------------- 3 files changed, 37 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 81e830d01ced..60492263aa64 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -35,10 +35,10 @@ extern void ima_post_path_mknod(struct user_namespace *mnt_userns, extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); -extern void ima_measure_critical_data(const char *event_label, - const char *event_name, - const void *buf, size_t buf_len, - bool hash); +extern int ima_measure_critical_data(const char *event_label, + const char *event_name, + const void *buf, size_t buf_len, + bool hash); #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM extern void ima_appraise_parse_cmdline(void); @@ -144,10 +144,13 @@ static inline int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) {} -static inline void ima_measure_critical_data(const char *event_label, +static inline int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, - bool hash) {} + bool hash) +{ + return -ENOENT; +} #endif /* CONFIG_IMA */ diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index f0e448ed1f9f..03db221324c3 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -264,11 +264,11 @@ void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig, int pcr, struct ima_template_desc *template_desc); -void process_buffer_measurement(struct user_namespace *mnt_userns, - struct inode *inode, const void *buf, int size, - const char *eventname, enum ima_hooks func, - int pcr, const char *func_data, - bool buf_hash); +int process_buffer_measurement(struct user_namespace *mnt_userns, + struct inode *inode, const void *buf, int size, + const char *eventname, enum ima_hooks func, + int pcr, const char *func_data, + bool buf_hash); void ima_audit_measurement(struct integrity_iint_cache *iint, const unsigned char *filename); int ima_alloc_init_template(struct ima_event_data *event_data, diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 634e4709d8af..c814738caaca 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -827,7 +827,7 @@ int ima_post_load_data(char *buf, loff_t size, return 0; } -/* +/** * process_buffer_measurement - Measure the buffer or the buffer data hash * @mnt_userns: user namespace of the mount the inode was found from * @inode: inode associated with the object being measured (NULL for KEY_CHECK) @@ -840,12 +840,15 @@ int ima_post_load_data(char *buf, loff_t size, * @buf_hash: measure buffer data hash * * Based on policy, either the buffer data or buffer data hash is measured + * + * Return: 0 if the buffer has been successfully measured, a negative value + * otherwise. */ -void process_buffer_measurement(struct user_namespace *mnt_userns, - struct inode *inode, const void *buf, int size, - const char *eventname, enum ima_hooks func, - int pcr, const char *func_data, - bool buf_hash) +int process_buffer_measurement(struct user_namespace *mnt_userns, + struct inode *inode, const void *buf, int size, + const char *eventname, enum ima_hooks func, + int pcr, const char *func_data, + bool buf_hash) { int ret = 0; const char *audit_cause = "ENOMEM"; @@ -867,7 +870,7 @@ void process_buffer_measurement(struct user_namespace *mnt_userns, u32 secid; if (!ima_policy_flag) - return; + return -ENOENT; template = ima_template_desc_buf(); if (!template) { @@ -889,7 +892,7 @@ void process_buffer_measurement(struct user_namespace *mnt_userns, secid, 0, func, &pcr, &template, func_data); if (!(action & IMA_MEASURE)) - return; + return -ENOENT; } if (!pcr) @@ -937,7 +940,7 @@ out: func_measure_str(func), audit_cause, ret, 0, ret); - return; + return ret; } /** @@ -977,18 +980,21 @@ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) * and extend the pcr. Examples of critical data could be various data * structures, policies, and states stored in kernel memory that can * impact the integrity of the system. + * + * Return: 0 if the buffer has been successfully measured, a negative value + * otherwise. */ -void ima_measure_critical_data(const char *event_label, - const char *event_name, - const void *buf, size_t buf_len, - bool hash) +int ima_measure_critical_data(const char *event_label, + const char *event_name, + const void *buf, size_t buf_len, + bool hash) { if (!event_name || !event_label || !buf || !buf_len) - return; + return -ENOPARAM; - process_buffer_measurement(&init_user_ns, NULL, buf, buf_len, event_name, - CRITICAL_DATA, 0, event_label, - hash); + return process_buffer_measurement(&init_user_ns, NULL, buf, buf_len, + event_name, CRITICAL_DATA, 0, + event_label, hash); } static int __init init_ima(void) -- cgit v1.2.3 From ca3c9bdb101d9b9eb3ed8a85cc0fe55915ba49de Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 23 Jul 2021 10:53:04 +0200 Subject: ima: Add digest and digest_len params to the functions to measure a buffer This patch performs the final modification necessary to pass the buffer measurement to callers, so that they provide a functionality similar to ima_file_hash(). It adds the 'digest' and 'digest_len' parameters to ima_measure_critical_data() and process_buffer_measurement(). These functions calculate the digest even if there is no suitable rule in the IMA policy and, in this case, they simply return 1 before generating a new measurement entry. Signed-off-by: Roberto Sassu Reviewed-by: Lakshmi Ramasubramanian Signed-off-by: Mimi Zohar --- include/linux/ima.h | 5 ++-- security/integrity/ima/ima.h | 2 +- security/integrity/ima/ima_appraise.c | 2 +- security/integrity/ima/ima_asymmetric_keys.c | 2 +- security/integrity/ima/ima_init.c | 3 ++- security/integrity/ima/ima_main.c | 36 ++++++++++++++++++++-------- security/integrity/ima/ima_queue_keys.c | 2 +- security/selinux/ima.c | 6 +++-- 8 files changed, 39 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 60492263aa64..b6ab66a546ae 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -38,7 +38,7 @@ extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); extern int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, - bool hash); + bool hash, u8 *digest, size_t digest_len); #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM extern void ima_appraise_parse_cmdline(void); @@ -147,7 +147,8 @@ static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) { static inline int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, - bool hash) + bool hash, u8 *digest, + size_t digest_len) { return -ENOENT; } diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 03db221324c3..2f4c20b16ad7 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -268,7 +268,7 @@ int process_buffer_measurement(struct user_namespace *mnt_userns, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, - bool buf_hash); + bool buf_hash, u8 *digest, size_t digest_len); void ima_audit_measurement(struct integrity_iint_cache *iint, const unsigned char *filename); int ima_alloc_init_template(struct ima_event_data *event_data, diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index ef9dcfce45d4..63bec42c353f 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -357,7 +357,7 @@ int ima_check_blacklist(struct integrity_iint_cache *iint, if ((rc == -EPERM) && (iint->flags & IMA_MEASURE)) process_buffer_measurement(&init_user_ns, NULL, digest, digestsize, "blacklisted-hash", NONE, - pcr, NULL, false); + pcr, NULL, false, NULL, 0); } return rc; diff --git a/security/integrity/ima/ima_asymmetric_keys.c b/security/integrity/ima/ima_asymmetric_keys.c index c985418698a4..f6aa0b47a772 100644 --- a/security/integrity/ima/ima_asymmetric_keys.c +++ b/security/integrity/ima/ima_asymmetric_keys.c @@ -62,5 +62,5 @@ void ima_post_key_create_or_update(struct key *keyring, struct key *key, */ process_buffer_measurement(&init_user_ns, NULL, payload, payload_len, keyring->description, KEY_CHECK, 0, - keyring->description, false); + keyring->description, false, NULL, 0); } diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c index 5076a7d9d23e..b26fa67476b4 100644 --- a/security/integrity/ima/ima_init.c +++ b/security/integrity/ima/ima_init.c @@ -154,7 +154,8 @@ int __init ima_init(void) ima_init_key_queue(); ima_measure_critical_data("kernel_info", "kernel_version", - UTS_RELEASE, strlen(UTS_RELEASE), false); + UTS_RELEASE, strlen(UTS_RELEASE), false, + NULL, 0); return rc; } diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index c814738caaca..1cba6beb5a60 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -838,17 +838,20 @@ int ima_post_load_data(char *buf, loff_t size, * @pcr: pcr to extend the measurement * @func_data: func specific data, may be NULL * @buf_hash: measure buffer data hash + * @digest: buffer digest will be written to + * @digest_len: buffer length * * Based on policy, either the buffer data or buffer data hash is measured * - * Return: 0 if the buffer has been successfully measured, a negative value - * otherwise. + * Return: 0 if the buffer has been successfully measured, 1 if the digest + * has been written to the passed location but not added to a measurement entry, + * a negative value otherwise. */ int process_buffer_measurement(struct user_namespace *mnt_userns, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, - bool buf_hash) + bool buf_hash, u8 *digest, size_t digest_len) { int ret = 0; const char *audit_cause = "ENOMEM"; @@ -869,7 +872,10 @@ int process_buffer_measurement(struct user_namespace *mnt_userns, int action = 0; u32 secid; - if (!ima_policy_flag) + if (digest && digest_len < digest_hash_len) + return -EINVAL; + + if (!ima_policy_flag && !digest) return -ENOENT; template = ima_template_desc_buf(); @@ -891,7 +897,7 @@ int process_buffer_measurement(struct user_namespace *mnt_userns, action = ima_get_action(mnt_userns, inode, current_cred(), secid, 0, func, &pcr, &template, func_data); - if (!(action & IMA_MEASURE)) + if (!(action & IMA_MEASURE) && !digest) return -ENOENT; } @@ -922,6 +928,12 @@ int process_buffer_measurement(struct user_namespace *mnt_userns, event_data.buf_len = digest_hash_len; } + if (digest) + memcpy(digest, iint.ima_hash->digest, digest_hash_len); + + if (!ima_policy_flag || (func && !(action & IMA_MEASURE))) + return 1; + ret = ima_alloc_init_template(&event_data, &entry, template); if (ret < 0) { audit_cause = "alloc_entry"; @@ -964,7 +976,7 @@ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) process_buffer_measurement(file_mnt_user_ns(f.file), file_inode(f.file), buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, - NULL, false); + NULL, false, NULL, 0); fdput(f); } @@ -975,26 +987,30 @@ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) * @buf: pointer to buffer data * @buf_len: length of buffer data (in bytes) * @hash: measure buffer data hash + * @digest: buffer digest will be written to + * @digest_len: buffer length * * Measure data critical to the integrity of the kernel into the IMA log * and extend the pcr. Examples of critical data could be various data * structures, policies, and states stored in kernel memory that can * impact the integrity of the system. * - * Return: 0 if the buffer has been successfully measured, a negative value - * otherwise. + * Return: 0 if the buffer has been successfully measured, 1 if the digest + * has been written to the passed location but not added to a measurement entry, + * a negative value otherwise. */ int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, - bool hash) + bool hash, u8 *digest, size_t digest_len) { if (!event_name || !event_label || !buf || !buf_len) return -ENOPARAM; return process_buffer_measurement(&init_user_ns, NULL, buf, buf_len, event_name, CRITICAL_DATA, 0, - event_label, hash); + event_label, hash, digest, + digest_len); } static int __init init_ima(void) diff --git a/security/integrity/ima/ima_queue_keys.c b/security/integrity/ima/ima_queue_keys.c index 979ef6c71f3d..93056c03bf5a 100644 --- a/security/integrity/ima/ima_queue_keys.c +++ b/security/integrity/ima/ima_queue_keys.c @@ -165,7 +165,7 @@ void ima_process_queued_keys(void) entry->keyring_name, KEY_CHECK, 0, entry->keyring_name, - false); + false, NULL, 0); list_del(&entry->list); ima_free_key_entry(entry); } diff --git a/security/selinux/ima.c b/security/selinux/ima.c index 34d421861bfc..727c4e43219d 100644 --- a/security/selinux/ima.c +++ b/security/selinux/ima.c @@ -86,7 +86,8 @@ void selinux_ima_measure_state_locked(struct selinux_state *state) } ima_measure_critical_data("selinux", "selinux-state", - state_str, strlen(state_str), false); + state_str, strlen(state_str), false, + NULL, 0); kfree(state_str); @@ -103,7 +104,8 @@ void selinux_ima_measure_state_locked(struct selinux_state *state) } ima_measure_critical_data("selinux", "selinux-policy-hash", - policy, policy_len, true); + policy, policy_len, true, + NULL, 0); vfree(policy); } -- cgit v1.2.3 From 472111920f1c5fbe103022a4b05bfb37128a2a29 Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Thu, 22 Jul 2021 18:55:38 +0300 Subject: net: bridge: switchdev: allow the TX data plane forwarding to be offloaded Allow switchdevs to forward frames from the CPU in accordance with the bridge configuration in the same way as is done between bridge ports. This means that the bridge will only send a single skb towards one of the ports under the switchdev's control, and expects the driver to deliver the packet to all eligible ports in its domain. Primarily this improves the performance of multicast flows with multiple subscribers, as it allows the hardware to perform the frame replication. The basic flow between the driver and the bridge is as follows: - When joining a bridge port, the switchdev driver calls switchdev_bridge_port_offload() with tx_fwd_offload = true. - The bridge sends offloadable skbs to one of the ports under the switchdev's control using skb->offload_fwd_mark = true. - The switchdev driver checks the skb->offload_fwd_mark field and lets its FDB lookup select the destination port mask for this packet. v1->v2: - convert br_input_skb_cb::fwd_hwdoms to a plain unsigned long - introduce a static key "br_switchdev_fwd_offload_used" to minimize the impact of the newly introduced feature on all the setups which don't have hardware that can make use of it - introduce a check for nbp->flags & BR_FWD_OFFLOAD to optimize cache line access - reorder nbp_switchdev_frame_mark_accel() and br_handle_vlan() in __br_forward() - do not strip VLAN on egress if forwarding offload on VLAN-aware bridge is being used - propagate errors from .ndo_dfwd_add_station() if not EOPNOTSUPP v2->v3: - replace the solution based on .ndo_dfwd_add_station with a solution based on switchdev_bridge_port_offload - rename BR_FWD_OFFLOAD to BR_TX_FWD_OFFLOAD v3->v4: rebase v4->v5: - make sure the static key is decremented on bridge port unoffload - more function and variable renaming and comments for them: br_switchdev_fwd_offload_used to br_switchdev_tx_fwd_offload br_switchdev_accels_skb to br_switchdev_frame_uses_tx_fwd_offload nbp_switchdev_frame_mark_tx_fwd to nbp_switchdev_frame_mark_tx_fwd_to_hwdom nbp_switchdev_frame_mark_accel to nbp_switchdev_frame_mark_tx_fwd_offload fwd_accel to tx_fwd_offload Signed-off-by: Tobias Waldekranz Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- .../net/ethernet/freescale/dpaa2/dpaa2-switch.c | 2 +- .../ethernet/marvell/prestera/prestera_switchdev.c | 2 +- .../ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 +- .../ethernet/microchip/sparx5/sparx5_switchdev.c | 2 +- drivers/net/ethernet/mscc/ocelot_net.c | 2 +- drivers/net/ethernet/rocker/rocker_ofdpa.c | 2 +- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +- drivers/net/ethernet/ti/cpsw_new.c | 2 +- include/linux/if_bridge.h | 3 + net/bridge/br_forward.c | 9 +++ net/bridge/br_private.h | 31 ++++++++++ net/bridge/br_switchdev.c | 68 ++++++++++++++++++++-- net/bridge/br_vlan.c | 10 +++- net/dsa/port.c | 2 +- 14 files changed, 125 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 3d021edb78e6..c233e8786e19 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1936,7 +1936,7 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, err = switchdev_bridge_port_offload(netdev, netdev, NULL, &dpaa2_switch_port_switchdev_nb, &dpaa2_switch_port_switchdev_blocking_nb, - extack); + false, extack); if (err) goto err_switchdev_offload; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index 7fe1287228e5..be01ec8284e6 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -502,7 +502,7 @@ int prestera_bridge_port_join(struct net_device *br_dev, } err = switchdev_bridge_port_offload(br_port->dev, port->dev, NULL, - NULL, NULL, extack); + NULL, NULL, false, extack); if (err) goto err_switchdev_offload; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 0a53f1d8e7e1..f5d0d392efbf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -362,7 +362,7 @@ mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device, bridge_port->ref_count = 1; err = switchdev_bridge_port_offload(brport_dev, mlxsw_sp_port->dev, - NULL, NULL, NULL, extack); + NULL, NULL, NULL, false, extack); if (err) goto err_switchdev_offload; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c index 807dc45cfae4..649ca609884a 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c @@ -113,7 +113,7 @@ static int sparx5_port_bridge_join(struct sparx5_port *port, set_bit(port->portno, sparx5->bridge_mask); err = switchdev_bridge_port_offload(ndev, ndev, NULL, NULL, NULL, - extack); + false, extack); if (err) goto err_switchdev_offload; diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 3558ee8d9212..c52f175df389 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -1200,7 +1200,7 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev, err = switchdev_bridge_port_offload(brport_dev, dev, priv, &ocelot_netdevice_nb, &ocelot_switchdev_blocking_nb, - extack); + false, extack); if (err) goto err_switchdev_offload; diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 03df6a24d0ba..b82e169b7836 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -2599,7 +2599,7 @@ static int ofdpa_port_bridge_join(struct ofdpa_port *ofdpa_port, return err; return switchdev_bridge_port_offload(dev, dev, NULL, NULL, NULL, - extack); + false, extack); } static int ofdpa_port_bridge_leave(struct ofdpa_port *ofdpa_port) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index b285606f963d..229e2f09d605 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2097,7 +2097,7 @@ static int am65_cpsw_netdevice_port_link(struct net_device *ndev, } err = switchdev_bridge_port_offload(ndev, ndev, NULL, NULL, NULL, - extack); + false, extack); if (err) return err; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 31030f73840d..4448a91cce54 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1518,7 +1518,7 @@ static int cpsw_netdevice_port_link(struct net_device *ndev, } err = switchdev_bridge_port_offload(ndev, ndev, NULL, NULL, NULL, - extack); + false, extack); if (err) return err; diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index bbf680093823..f0b4ffbd8582 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -57,6 +57,7 @@ struct br_ip_list { #define BR_MRP_AWARE BIT(17) #define BR_MRP_LOST_CONT BIT(18) #define BR_MRP_LOST_IN_CONT BIT(19) +#define BR_TX_FWD_OFFLOAD BIT(20) #define BR_DEFAULT_AGEING_TIME (300 * HZ) @@ -182,6 +183,7 @@ int switchdev_bridge_port_offload(struct net_device *brport_dev, struct net_device *dev, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, + bool tx_fwd_offload, struct netlink_ext_ack *extack); void switchdev_bridge_port_unoffload(struct net_device *brport_dev, const void *ctx, @@ -195,6 +197,7 @@ switchdev_bridge_port_offload(struct net_device *brport_dev, struct net_device *dev, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, + bool tx_fwd_offload, struct netlink_ext_ack *extack) { return -EINVAL; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index bfdbaf3015b9..bc14b1b384e9 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -48,6 +48,8 @@ int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb skb_set_network_header(skb, depth); } + skb->offload_fwd_mark = br_switchdev_frame_uses_tx_fwd_offload(skb); + dev_queue_xmit(skb); return 0; @@ -76,6 +78,11 @@ static void __br_forward(const struct net_bridge_port *to, struct net *net; int br_hook; + /* Mark the skb for forwarding offload early so that br_handle_vlan() + * can know whether to pop the VLAN header on egress or keep it. + */ + nbp_switchdev_frame_mark_tx_fwd_offload(to, skb); + vg = nbp_vlan_group_rcu(to); skb = br_handle_vlan(to->br, to, vg, skb); if (!skb) @@ -174,6 +181,8 @@ static struct net_bridge_port *maybe_deliver( if (!should_deliver(p, skb)) return prev; + nbp_switchdev_frame_mark_tx_fwd_to_hwdom(p, skb); + if (!prev) goto out; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2f32d330b648..86ca617fec7a 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -552,12 +552,20 @@ struct br_input_skb_cb { #endif #ifdef CONFIG_NET_SWITCHDEV + /* Set if TX data plane offloading is used towards at least one + * hardware domain. + */ + u8 tx_fwd_offload:1; /* The switchdev hardware domain from which this packet was received. * If skb->offload_fwd_mark was set, then this packet was already * forwarded by hardware to the other ports in the source hardware * domain, otherwise it wasn't. */ int src_hwdom; + /* Bit mask of hardware domains towards this packet has already been + * transmitted using the TX data plane offload. + */ + unsigned long fwd_hwdoms; #endif }; @@ -1871,6 +1879,12 @@ static inline void br_sysfs_delbr(struct net_device *dev) { return; } /* br_switchdev.c */ #ifdef CONFIG_NET_SWITCHDEV +bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb); + +void nbp_switchdev_frame_mark_tx_fwd_offload(const struct net_bridge_port *p, + struct sk_buff *skb); +void nbp_switchdev_frame_mark_tx_fwd_to_hwdom(const struct net_bridge_port *p, + struct sk_buff *skb); void nbp_switchdev_frame_mark(const struct net_bridge_port *p, struct sk_buff *skb); bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, @@ -1891,6 +1905,23 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb) skb->offload_fwd_mark = 0; } #else +static inline bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb) +{ + return false; +} + +static inline void +nbp_switchdev_frame_mark_tx_fwd_offload(const struct net_bridge_port *p, + struct sk_buff *skb) +{ +} + +static inline void +nbp_switchdev_frame_mark_tx_fwd_to_hwdom(const struct net_bridge_port *p, + struct sk_buff *skb) +{ +} + static inline void nbp_switchdev_frame_mark(const struct net_bridge_port *p, struct sk_buff *skb) { diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 6bfff28ede23..96ce069d0c8c 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -8,6 +8,46 @@ #include "br_private.h" +static struct static_key_false br_switchdev_tx_fwd_offload; + +static bool nbp_switchdev_can_offload_tx_fwd(const struct net_bridge_port *p, + const struct sk_buff *skb) +{ + if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload)) + return false; + + return (p->flags & BR_TX_FWD_OFFLOAD) && + (p->hwdom != BR_INPUT_SKB_CB(skb)->src_hwdom); +} + +bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb) +{ + if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload)) + return false; + + return BR_INPUT_SKB_CB(skb)->tx_fwd_offload; +} + +/* Mark the frame for TX forwarding offload if this egress port supports it */ +void nbp_switchdev_frame_mark_tx_fwd_offload(const struct net_bridge_port *p, + struct sk_buff *skb) +{ + if (nbp_switchdev_can_offload_tx_fwd(p, skb)) + BR_INPUT_SKB_CB(skb)->tx_fwd_offload = true; +} + +/* Lazily adds the hwdom of the egress bridge port to the bit mask of hwdoms + * that the skb has been already forwarded to, to avoid further cloning to + * other ports in the same hwdom by making nbp_switchdev_allowed_egress() + * return false. + */ +void nbp_switchdev_frame_mark_tx_fwd_to_hwdom(const struct net_bridge_port *p, + struct sk_buff *skb) +{ + if (nbp_switchdev_can_offload_tx_fwd(p, skb)) + set_bit(p->hwdom, &BR_INPUT_SKB_CB(skb)->fwd_hwdoms); +} + void nbp_switchdev_frame_mark(const struct net_bridge_port *p, struct sk_buff *skb) { @@ -18,8 +58,10 @@ void nbp_switchdev_frame_mark(const struct net_bridge_port *p, bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, const struct sk_buff *skb) { - return !skb->offload_fwd_mark || - BR_INPUT_SKB_CB(skb)->src_hwdom != p->hwdom; + struct br_input_skb_cb *cb = BR_INPUT_SKB_CB(skb); + + return !test_bit(p->hwdom, &cb->fwd_hwdoms) && + (!skb->offload_fwd_mark || cb->src_hwdom != p->hwdom); } /* Flags that can be offloaded to hardware */ @@ -164,8 +206,11 @@ static void nbp_switchdev_hwdom_put(struct net_bridge_port *leaving) static int nbp_switchdev_add(struct net_bridge_port *p, struct netdev_phys_item_id ppid, + bool tx_fwd_offload, struct netlink_ext_ack *extack) { + int err; + if (p->offload_count) { /* Prevent unsupported configurations such as a bridge port * which is a bonding interface, and the member ports are from @@ -189,7 +234,16 @@ static int nbp_switchdev_add(struct net_bridge_port *p, p->ppid = ppid; p->offload_count = 1; - return nbp_switchdev_hwdom_set(p); + err = nbp_switchdev_hwdom_set(p); + if (err) + return err; + + if (tx_fwd_offload) { + p->flags |= BR_TX_FWD_OFFLOAD; + static_branch_inc(&br_switchdev_tx_fwd_offload); + } + + return 0; } static void nbp_switchdev_del(struct net_bridge_port *p) @@ -204,6 +258,11 @@ static void nbp_switchdev_del(struct net_bridge_port *p) if (p->hwdom) nbp_switchdev_hwdom_put(p); + + if (p->flags & BR_TX_FWD_OFFLOAD) { + p->flags &= ~BR_TX_FWD_OFFLOAD; + static_branch_dec(&br_switchdev_tx_fwd_offload); + } } static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx, @@ -262,6 +321,7 @@ int switchdev_bridge_port_offload(struct net_device *brport_dev, struct net_device *dev, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, + bool tx_fwd_offload, struct netlink_ext_ack *extack) { struct netdev_phys_item_id ppid; @@ -278,7 +338,7 @@ int switchdev_bridge_port_offload(struct net_device *brport_dev, if (err) return err; - err = nbp_switchdev_add(p, ppid, extack); + err = nbp_switchdev_add(p, ppid, tx_fwd_offload, extack); if (err) return err; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 382ab992badf..325600361487 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -465,7 +465,15 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, u64_stats_update_end(&stats->syncp); } - if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) + /* If the skb will be sent using forwarding offload, the assumption is + * that the switchdev will inject the packet into hardware together + * with the bridge VLAN, so that it can be forwarded according to that + * VLAN. The switchdev should deal with popping the VLAN header in + * hardware on each egress port as appropriate. So only strip the VLAN + * header if forwarding offload is not being used. + */ + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED && + !br_switchdev_frame_uses_tx_fwd_offload(skb)) __vlan_hwaccel_clear_tag(skb); if (p && (p->flags & BR_VLAN_TUNNEL) && diff --git a/net/dsa/port.c b/net/dsa/port.c index d81c283b7358..f2704f101ccf 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -257,7 +257,7 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, err = switchdev_bridge_port_offload(brport_dev, dev, dp, &dsa_slave_switchdev_notifier, &dsa_slave_switchdev_blocking_notifier, - extack); + false, extack); if (err) goto out_rollback_unbridge; -- cgit v1.2.3 From 2c9f7eaf08659fa23d25b93a446f74306b3abea8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 28 May 2021 13:38:19 -0500 Subject: signal/sparc: si_trapno is only used with SIGILL ILL_ILLTRP While reviewing the signal handlers on sparc it became clear that si_trapno is only set to a non-zero value when sending SIGILL with si_code ILL_ILLTRP. Add force_sig_fault_trapno and send SIGILL ILL_ILLTRP with it. Remove the define of __ARCH_SI_TRAPNO and remove the always zero si_trapno parameter from send_sig_fault and force_sig_fault. v1: https://lkml.kernel.org/r/m1eeers7q7.fsf_-_@fess.ebiederm.org v2: https://lkml.kernel.org/r/20210505141101.11519-7-ebiederm@xmission.com Link: https://lkml.kernel.org/r/87mtqnxx89.fsf_-_@disp2133 Signed-off-by: "Eric W. Biederman" --- arch/sparc/include/uapi/asm/siginfo.h | 3 --- arch/sparc/kernel/process_64.c | 2 +- arch/sparc/kernel/sys_sparc_32.c | 2 +- arch/sparc/kernel/sys_sparc_64.c | 2 +- arch/sparc/kernel/traps_32.c | 22 +++++++++--------- arch/sparc/kernel/traps_64.c | 44 +++++++++++++++-------------------- arch/sparc/kernel/unaligned_32.c | 2 +- arch/sparc/mm/fault_32.c | 2 +- arch/sparc/mm/fault_64.c | 2 +- include/linux/sched/signal.h | 1 + kernel/signal.c | 19 +++++++++++++++ 11 files changed, 56 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/arch/sparc/include/uapi/asm/siginfo.h b/arch/sparc/include/uapi/asm/siginfo.h index 68bdde4c2a2e..0e7c27522aed 100644 --- a/arch/sparc/include/uapi/asm/siginfo.h +++ b/arch/sparc/include/uapi/asm/siginfo.h @@ -8,9 +8,6 @@ #endif /* defined(__sparc__) && defined(__arch64__) */ - -#define __ARCH_SI_TRAPNO - #include diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index d33c58a58d4f..547b06b49ce3 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -518,7 +518,7 @@ void synchronize_user_stack(void) static void stack_unaligned(unsigned long sp) { - force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *) sp, 0); + force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *) sp); } static const char uwfault32[] = KERN_INFO \ diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index be77538bc038..082a551897ed 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -151,7 +151,7 @@ sparc_breakpoint (struct pt_regs *regs) #ifdef DEBUG_SPARC_BREAKPOINT printk ("TRAP: Entering kernel PC=%x, nPC=%x\n", regs->pc, regs->npc); #endif - force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc, 0); + force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc); #ifdef DEBUG_SPARC_BREAKPOINT printk ("TRAP: Returning to space: PC=%x nPC=%x\n", regs->pc, regs->npc); diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 6b92fadb6ec7..1e9a9e016237 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -514,7 +514,7 @@ asmlinkage void sparc_breakpoint(struct pt_regs *regs) #ifdef DEBUG_SPARC_BREAKPOINT printk ("TRAP: Entering kernel PC=%lx, nPC=%lx\n", regs->tpc, regs->tnpc); #endif - force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->tpc, 0); + force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->tpc); #ifdef DEBUG_SPARC_BREAKPOINT printk ("TRAP: Returning to space: PC=%lx nPC=%lx\n", regs->tpc, regs->tnpc); #endif diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c index 247a0d9683b2..5630e5a395e0 100644 --- a/arch/sparc/kernel/traps_32.c +++ b/arch/sparc/kernel/traps_32.c @@ -102,8 +102,8 @@ void do_hw_interrupt(struct pt_regs *regs, unsigned long type) if(regs->psr & PSR_PS) die_if_kernel("Kernel bad trap", regs); - force_sig_fault(SIGILL, ILL_ILLTRP, - (void __user *)regs->pc, type - 0x80); + force_sig_fault_trapno(SIGILL, ILL_ILLTRP, + (void __user *)regs->pc, type - 0x80); } void do_illegal_instruction(struct pt_regs *regs, unsigned long pc, unsigned long npc, @@ -116,7 +116,7 @@ void do_illegal_instruction(struct pt_regs *regs, unsigned long pc, unsigned lon regs->pc, *(unsigned long *)regs->pc); #endif - send_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)pc, 0, current); + send_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)pc, current); } void do_priv_instruction(struct pt_regs *regs, unsigned long pc, unsigned long npc, @@ -124,7 +124,7 @@ void do_priv_instruction(struct pt_regs *regs, unsigned long pc, unsigned long n { if(psr & PSR_PS) die_if_kernel("Penguin instruction from Penguin mode??!?!", regs); - send_sig_fault(SIGILL, ILL_PRVOPC, (void __user *)pc, 0, current); + send_sig_fault(SIGILL, ILL_PRVOPC, (void __user *)pc, current); } /* XXX User may want to be allowed to do this. XXX */ @@ -145,7 +145,7 @@ void do_memaccess_unaligned(struct pt_regs *regs, unsigned long pc, unsigned lon #endif send_sig_fault(SIGBUS, BUS_ADRALN, /* FIXME: Should dig out mna address */ (void *)0, - 0, current); + current); } static unsigned long init_fsr = 0x0UL; @@ -291,7 +291,7 @@ void do_fpe_trap(struct pt_regs *regs, unsigned long pc, unsigned long npc, else if (fsr & 0x01) code = FPE_FLTRES; } - send_sig_fault(SIGFPE, code, (void __user *)pc, 0, fpt); + send_sig_fault(SIGFPE, code, (void __user *)pc, fpt); #ifndef CONFIG_SMP last_task_used_math = NULL; #endif @@ -305,7 +305,7 @@ void handle_tag_overflow(struct pt_regs *regs, unsigned long pc, unsigned long n { if(psr & PSR_PS) die_if_kernel("Penguin overflow trap from kernel mode", regs); - send_sig_fault(SIGEMT, EMT_TAGOVF, (void __user *)pc, 0, current); + send_sig_fault(SIGEMT, EMT_TAGOVF, (void __user *)pc, current); } void handle_watchpoint(struct pt_regs *regs, unsigned long pc, unsigned long npc, @@ -327,13 +327,13 @@ void handle_reg_access(struct pt_regs *regs, unsigned long pc, unsigned long npc printk("Register Access Exception at PC %08lx NPC %08lx PSR %08lx\n", pc, npc, psr); #endif - force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)pc, 0); + force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)pc); } void handle_cp_disabled(struct pt_regs *regs, unsigned long pc, unsigned long npc, unsigned long psr) { - send_sig_fault(SIGILL, ILL_COPROC, (void __user *)pc, 0, current); + send_sig_fault(SIGILL, ILL_COPROC, (void __user *)pc, current); } void handle_cp_exception(struct pt_regs *regs, unsigned long pc, unsigned long npc, @@ -343,13 +343,13 @@ void handle_cp_exception(struct pt_regs *regs, unsigned long pc, unsigned long n printk("Co-Processor Exception at PC %08lx NPC %08lx PSR %08lx\n", pc, npc, psr); #endif - send_sig_fault(SIGILL, ILL_COPROC, (void __user *)pc, 0, current); + send_sig_fault(SIGILL, ILL_COPROC, (void __user *)pc, current); } void handle_hw_divzero(struct pt_regs *regs, unsigned long pc, unsigned long npc, unsigned long psr) { - send_sig_fault(SIGFPE, FPE_INTDIV, (void __user *)pc, 0, current); + send_sig_fault(SIGFPE, FPE_INTDIV, (void __user *)pc, current); } #ifdef CONFIG_DEBUG_BUGVERBOSE diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index a850dccd78ea..6863025ed56d 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -107,8 +107,8 @@ void bad_trap(struct pt_regs *regs, long lvl) regs->tpc &= 0xffffffff; regs->tnpc &= 0xffffffff; } - force_sig_fault(SIGILL, ILL_ILLTRP, - (void __user *)regs->tpc, lvl); + force_sig_fault_trapno(SIGILL, ILL_ILLTRP, + (void __user *)regs->tpc, lvl); } void bad_trap_tl1(struct pt_regs *regs, long lvl) @@ -201,8 +201,7 @@ void spitfire_insn_access_exception(struct pt_regs *regs, unsigned long sfsr, un regs->tpc &= 0xffffffff; regs->tnpc &= 0xffffffff; } - force_sig_fault(SIGSEGV, SEGV_MAPERR, - (void __user *)regs->tpc, 0); + force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)regs->tpc); out: exception_exit(prev_state); } @@ -237,7 +236,7 @@ void sun4v_insn_access_exception(struct pt_regs *regs, unsigned long addr, unsig regs->tpc &= 0xffffffff; regs->tnpc &= 0xffffffff; } - force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *) addr, 0); + force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *) addr); } void sun4v_insn_access_exception_tl1(struct pt_regs *regs, unsigned long addr, unsigned long type_ctx) @@ -321,7 +320,7 @@ void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, un if (is_no_fault_exception(regs)) return; - force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)sfar, 0); + force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)sfar); out: exception_exit(prev_state); } @@ -385,13 +384,13 @@ void sun4v_data_access_exception(struct pt_regs *regs, unsigned long addr, unsig */ switch (type) { case HV_FAULT_TYPE_INV_ASI: - force_sig_fault(SIGILL, ILL_ILLADR, (void __user *)addr, 0); + force_sig_fault(SIGILL, ILL_ILLADR, (void __user *)addr); break; case HV_FAULT_TYPE_MCD_DIS: - force_sig_fault(SIGSEGV, SEGV_ACCADI, (void __user *)addr, 0); + force_sig_fault(SIGSEGV, SEGV_ACCADI, (void __user *)addr); break; default: - force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)addr, 0); + force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)addr); break; } } @@ -568,7 +567,7 @@ static void spitfire_ue_log(unsigned long afsr, unsigned long afar, unsigned lon regs->tpc &= 0xffffffff; regs->tnpc &= 0xffffffff; } - force_sig_fault(SIGBUS, BUS_OBJERR, (void *)0, 0); + force_sig_fault(SIGBUS, BUS_OBJERR, (void *)0); } void spitfire_access_error(struct pt_regs *regs, unsigned long status_encoded, unsigned long afar) @@ -2069,8 +2068,7 @@ void do_mcd_err(struct pt_regs *regs, struct sun4v_error_entry ent) /* Send SIGSEGV to the userspace process with the right signal * code */ - force_sig_fault(SIGSEGV, SEGV_ADIDERR, (void __user *)ent.err_raddr, - 0); + force_sig_fault(SIGSEGV, SEGV_ADIDERR, (void __user *)ent.err_raddr); } /* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate. @@ -2184,7 +2182,7 @@ bool sun4v_nonresum_error_user_handled(struct pt_regs *regs, } if (attrs & SUN4V_ERR_ATTRS_PIO) { force_sig_fault(SIGBUS, BUS_ADRERR, - (void __user *)sun4v_get_vaddr(regs), 0); + (void __user *)sun4v_get_vaddr(regs)); return true; } @@ -2340,8 +2338,7 @@ static void do_fpe_common(struct pt_regs *regs) else if (fsr & 0x01) code = FPE_FLTRES; } - force_sig_fault(SIGFPE, code, - (void __user *)regs->tpc, 0); + force_sig_fault(SIGFPE, code, (void __user *)regs->tpc); } } @@ -2395,8 +2392,7 @@ void do_tof(struct pt_regs *regs) regs->tpc &= 0xffffffff; regs->tnpc &= 0xffffffff; } - force_sig_fault(SIGEMT, EMT_TAGOVF, - (void __user *)regs->tpc, 0); + force_sig_fault(SIGEMT, EMT_TAGOVF, (void __user *)regs->tpc); out: exception_exit(prev_state); } @@ -2415,8 +2411,7 @@ void do_div0(struct pt_regs *regs) regs->tpc &= 0xffffffff; regs->tnpc &= 0xffffffff; } - force_sig_fault(SIGFPE, FPE_INTDIV, - (void __user *)regs->tpc, 0); + force_sig_fault(SIGFPE, FPE_INTDIV, (void __user *)regs->tpc); out: exception_exit(prev_state); } @@ -2612,7 +2607,7 @@ void do_illegal_instruction(struct pt_regs *regs) } } } - force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)pc, 0); + force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)pc); out: exception_exit(prev_state); } @@ -2632,7 +2627,7 @@ void mem_address_unaligned(struct pt_regs *regs, unsigned long sfar, unsigned lo if (is_no_fault_exception(regs)) return; - force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)sfar, 0); + force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)sfar); out: exception_exit(prev_state); } @@ -2650,7 +2645,7 @@ void sun4v_do_mna(struct pt_regs *regs, unsigned long addr, unsigned long type_c if (is_no_fault_exception(regs)) return; - force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *) addr, 0); + force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *) addr); } /* sun4v_mem_corrupt_detect_precise() - Handle precise exception on an ADI @@ -2697,7 +2692,7 @@ void sun4v_mem_corrupt_detect_precise(struct pt_regs *regs, unsigned long addr, regs->tpc &= 0xffffffff; regs->tnpc &= 0xffffffff; } - force_sig_fault(SIGSEGV, SEGV_ADIPERR, (void __user *)addr, 0); + force_sig_fault(SIGSEGV, SEGV_ADIPERR, (void __user *)addr); } void do_privop(struct pt_regs *regs) @@ -2712,8 +2707,7 @@ void do_privop(struct pt_regs *regs) regs->tpc &= 0xffffffff; regs->tnpc &= 0xffffffff; } - force_sig_fault(SIGILL, ILL_PRVOPC, - (void __user *)regs->tpc, 0); + force_sig_fault(SIGILL, ILL_PRVOPC, (void __user *)regs->tpc); out: exception_exit(prev_state); } diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c index ef5c5207c9ff..455f0258c745 100644 --- a/arch/sparc/kernel/unaligned_32.c +++ b/arch/sparc/kernel/unaligned_32.c @@ -278,5 +278,5 @@ asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn) { send_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)safe_compute_effective_address(regs, insn), - 0, current); + current); } diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index de2031c2b2d7..fa858626b85b 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -83,7 +83,7 @@ static void __do_fault_siginfo(int code, int sig, struct pt_regs *regs, show_signal_msg(regs, sig, code, addr, current); - force_sig_fault(sig, code, (void __user *) addr, 0); + force_sig_fault(sig, code, (void __user *) addr); } static unsigned long compute_si_addr(struct pt_regs *regs, int text_fault) diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 0a6bcc85fba7..9a9652a15fed 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -176,7 +176,7 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs, if (unlikely(show_unhandled_signals)) show_signal_msg(regs, sig, code, addr, current); - force_sig_fault(sig, code, (void __user *) addr, 0); + force_sig_fault(sig, code, (void __user *) addr); } static unsigned int get_fault_insn(struct pt_regs *regs, unsigned int insn) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index b9126fe06c3f..99a9ab2b169a 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -329,6 +329,7 @@ int force_sig_pkuerr(void __user *addr, u32 pkey); int force_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); +int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig); diff --git a/kernel/signal.c b/kernel/signal.c index a3229add4455..87a374225277 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1808,6 +1808,22 @@ int force_sig_ptrace_errno_trap(int errno, void __user *addr) return force_sig_info(&info); } +/* For the rare architectures that include trap information using + * si_trapno. + */ +int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = sig; + info.si_errno = 0; + info.si_code = code; + info.si_addr = addr; + info.si_trapno = trapno; + return force_sig_info(&info); +} + int kill_pgrp(struct pid *pid, int sig, int priv) { int ret; @@ -3243,6 +3259,9 @@ enum siginfo_layout siginfo_layout(unsigned sig, int si_code) #endif else if ((sig == SIGTRAP) && (si_code == TRAP_PERF)) layout = SIL_PERF_EVENT; + else if (IS_ENABLED(CONFIG_SPARC) && + (sig == SIGILL) && (si_code == ILL_ILLTRP)) + layout = SIL_FAULT_TRAPNO; #ifdef __ARCH_SI_TRAPNO else if (layout == SIL_FAULT) layout = SIL_FAULT_TRAPNO; -- cgit v1.2.3 From 7de5f68d497cbc700c4a28cc037dd61f00e452e8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 28 May 2021 14:15:51 -0500 Subject: signal/alpha: si_trapno is only used with SIGFPE and SIGTRAP TRAP_UNK While reviewing the signal handlers on alpha it became clear that si_trapno is only set to a non-zero value when sending SIGFPE and when sending SITGRAP with si_code TRAP_UNK. Add send_sig_fault_trapno and send SIGTRAP TRAP_UNK, and SIGFPE with it. Remove the define of __ARCH_SI_TRAPNO and remove the always zero si_trapno parameter from send_sig_fault and force_sig_fault. v1: https://lkml.kernel.org/r/m1eeers7q7.fsf_-_@fess.ebiederm.org v2: https://lkml.kernel.org/r/20210505141101.11519-7-ebiederm@xmission.com Link: https://lkml.kernel.org/r/87h7gvxx7l.fsf_-_@disp2133 Signed-off-by: "Eric W. Biederman" --- arch/alpha/include/uapi/asm/siginfo.h | 2 -- arch/alpha/kernel/osf_sys.c | 2 +- arch/alpha/kernel/signal.c | 4 ++-- arch/alpha/kernel/traps.c | 26 +++++++++++++------------- arch/alpha/mm/fault.c | 4 ++-- include/linux/sched/signal.h | 2 ++ kernel/signal.c | 21 +++++++++++++++++++++ 7 files changed, 41 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/uapi/asm/siginfo.h b/arch/alpha/include/uapi/asm/siginfo.h index 6e1a2af2f962..e08eae88182b 100644 --- a/arch/alpha/include/uapi/asm/siginfo.h +++ b/arch/alpha/include/uapi/asm/siginfo.h @@ -2,8 +2,6 @@ #ifndef _ALPHA_SIGINFO_H #define _ALPHA_SIGINFO_H -#define __ARCH_SI_TRAPNO - #include #endif diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index d5367a1c6300..bbdb1a9a5fd8 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -876,7 +876,7 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer, if (fex & IEEE_TRAP_ENABLE_DZE) si_code = FPE_FLTDIV; if (fex & IEEE_TRAP_ENABLE_INV) si_code = FPE_FLTINV; - send_sig_fault(SIGFPE, si_code, + send_sig_fault_trapno(SIGFPE, si_code, (void __user *)NULL, /* FIXME */ 0, current); } diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index 948b89789da8..bc077babafab 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -219,7 +219,7 @@ do_sigreturn(struct sigcontext __user *sc) /* Send SIGTRAP if we're single-stepping: */ if (ptrace_cancel_bpt (current)) { - send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *) regs->pc, 0, + send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *) regs->pc, current); } return; @@ -247,7 +247,7 @@ do_rt_sigreturn(struct rt_sigframe __user *frame) /* Send SIGTRAP if we're single-stepping: */ if (ptrace_cancel_bpt (current)) { - send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *) regs->pc, 0, + send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *) regs->pc, current); } return; diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 921d4b6e4d95..e9e3de18793b 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -227,7 +227,7 @@ do_entArith(unsigned long summary, unsigned long write_mask, } die_if_kernel("Arithmetic fault", regs, 0, NULL); - send_sig_fault(SIGFPE, si_code, (void __user *) regs->pc, 0, current); + send_sig_fault_trapno(SIGFPE, si_code, (void __user *) regs->pc, 0, current); } asmlinkage void @@ -268,13 +268,13 @@ do_entIF(unsigned long type, struct pt_regs *regs) regs->pc -= 4; /* make pc point to former bpt */ } - send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc, 0, + send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc, current); return; case 1: /* bugcheck */ - send_sig_fault(SIGTRAP, TRAP_UNK, (void __user *) regs->pc, 0, - current); + send_sig_fault_trapno(SIGTRAP, TRAP_UNK, + (void __user *) regs->pc, 0, current); return; case 2: /* gentrap */ @@ -335,8 +335,8 @@ do_entIF(unsigned long type, struct pt_regs *regs) break; } - send_sig_fault(signo, code, (void __user *) regs->pc, regs->r16, - current); + send_sig_fault_trapno(signo, code, (void __user *) regs->pc, + regs->r16, current); return; case 4: /* opDEC */ @@ -360,9 +360,9 @@ do_entIF(unsigned long type, struct pt_regs *regs) if (si_code == 0) return; if (si_code > 0) { - send_sig_fault(SIGFPE, si_code, - (void __user *) regs->pc, 0, - current); + send_sig_fault_trapno(SIGFPE, si_code, + (void __user *) regs->pc, + 0, current); return; } } @@ -387,7 +387,7 @@ do_entIF(unsigned long type, struct pt_regs *regs) ; } - send_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)regs->pc, 0, current); + send_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)regs->pc, current); } /* There is an ifdef in the PALcode in MILO that enables a @@ -402,7 +402,7 @@ do_entDbg(struct pt_regs *regs) { die_if_kernel("Instruction fault", regs, 0, NULL); - force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)regs->pc, 0); + force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)regs->pc); } @@ -964,12 +964,12 @@ give_sigsegv: si_code = SEGV_MAPERR; mmap_read_unlock(mm); } - send_sig_fault(SIGSEGV, si_code, va, 0, current); + send_sig_fault(SIGSEGV, si_code, va, current); return; give_sigbus: regs->pc -= 4; - send_sig_fault(SIGBUS, BUS_ADRALN, va, 0, current); + send_sig_fault(SIGBUS, BUS_ADRALN, va, current); return; } diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 09172f017efc..eee5102c3d88 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -219,13 +219,13 @@ retry: mmap_read_unlock(mm); /* Send a sigbus, regardless of whether we were in kernel or user mode. */ - force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *) address, 0); + force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *) address); if (!user_mode(regs)) goto no_context; return; do_sigsegv: - force_sig_fault(SIGSEGV, si_code, (void __user *) address, 0); + force_sig_fault(SIGSEGV, si_code, (void __user *) address); return; #ifdef CONFIG_ALPHA_LARGE_VMALLOC diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 99a9ab2b169a..6657184cef07 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -330,6 +330,8 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); +int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno, + struct task_struct *t); extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig); diff --git a/kernel/signal.c b/kernel/signal.c index 87a374225277..ae06a424aa72 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1824,6 +1824,23 @@ int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno) return force_sig_info(&info); } +/* For the rare architectures that include trap information using + * si_trapno. + */ +int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno, + struct task_struct *t) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = sig; + info.si_errno = 0; + info.si_code = code; + info.si_addr = addr; + info.si_trapno = trapno; + return send_sig_info(info.si_signo, &info, t); +} + int kill_pgrp(struct pid *pid, int sig, int priv) { int ret; @@ -3262,6 +3279,10 @@ enum siginfo_layout siginfo_layout(unsigned sig, int si_code) else if (IS_ENABLED(CONFIG_SPARC) && (sig == SIGILL) && (si_code == ILL_ILLTRP)) layout = SIL_FAULT_TRAPNO; + else if (IS_ENABLED(CONFIG_ALPHA) && + ((sig == SIGFPE) || + ((sig == SIGTRAP) && (si_code == TRAP_UNK)))) + layout = SIL_FAULT_TRAPNO; #ifdef __ARCH_SI_TRAPNO else if (layout == SIL_FAULT) layout = SIL_FAULT_TRAPNO; -- cgit v1.2.3 From c7fff9288dce1ee5fa9de8d656e09cc8e0e3281b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 30 Apr 2021 17:53:38 -0500 Subject: signal: Remove the generic __ARCH_SI_TRAPNO support Now that __ARCH_SI_TRAPNO is no longer set by any architecture remove all of the code it enabled from the kernel. On alpha and sparc a more explict approach of using send_sig_fault_trapno or force_sig_fault_trapno in the very limited circumstances where si_trapno was set to a non-zero value. The generic support that is being removed always set si_trapno on all fault signals. With only SIGILL ILL_ILLTRAP on sparc and SIGFPE and SIGTRAP TRAP_UNK on alpla providing si_trapno values asking all senders of fault signals to provide an si_trapno value does not make sense. Making si_trapno an ordinary extension of the fault siginfo layout has enabled the architecture generic implementation of SIGTRAP TRAP_PERF, and enables other faulting signals to grow architecture generic senders as well. v1: https://lkml.kernel.org/r/m18s4zs7nu.fsf_-_@fess.ebiederm.org v2: https://lkml.kernel.org/r/20210505141101.11519-8-ebiederm@xmission.com Link: https://lkml.kernel.org/r/87bl73xx6x.fsf_-_@disp2133 Signed-off-by: "Eric W. Biederman" --- arch/mips/include/uapi/asm/siginfo.h | 2 -- include/linux/sched/signal.h | 8 -------- kernel/signal.c | 14 -------------- 3 files changed, 24 deletions(-) (limited to 'include/linux') diff --git a/arch/mips/include/uapi/asm/siginfo.h b/arch/mips/include/uapi/asm/siginfo.h index c34c7eef0a1c..8cb8bd061a68 100644 --- a/arch/mips/include/uapi/asm/siginfo.h +++ b/arch/mips/include/uapi/asm/siginfo.h @@ -10,9 +10,7 @@ #ifndef _UAPI_ASM_SIGINFO_H #define _UAPI_ASM_SIGINFO_H - #define __ARCH_SIGEV_PREAMBLE_SIZE (sizeof(long) + 2*sizeof(int)) -#undef __ARCH_SI_TRAPNO /* exception code needs to fill this ... */ #define __ARCH_HAS_SWAPPED_SIGINFO diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 6657184cef07..928e0025d358 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -298,11 +298,6 @@ static inline void kernel_signal_stop(void) schedule(); } -#ifdef __ARCH_SI_TRAPNO -# define ___ARCH_SI_TRAPNO(_a1) , _a1 -#else -# define ___ARCH_SI_TRAPNO(_a1) -#endif #ifdef __ia64__ # define ___ARCH_SI_IA64(_a1, _a2, _a3) , _a1, _a2, _a3 #else @@ -310,14 +305,11 @@ static inline void kernel_signal_stop(void) #endif int force_sig_fault_to_task(int sig, int code, void __user *addr - ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t); int force_sig_fault(int sig, int code, void __user *addr - ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)); int send_sig_fault(int sig, int code, void __user *addr - ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t); diff --git a/kernel/signal.c b/kernel/signal.c index ae06a424aa72..2181423e562a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1666,7 +1666,6 @@ void force_sigsegv(int sig) } int force_sig_fault_to_task(int sig, int code, void __user *addr - ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t) { @@ -1677,9 +1676,6 @@ int force_sig_fault_to_task(int sig, int code, void __user *addr info.si_errno = 0; info.si_code = code; info.si_addr = addr; -#ifdef __ARCH_SI_TRAPNO - info.si_trapno = trapno; -#endif #ifdef __ia64__ info.si_imm = imm; info.si_flags = flags; @@ -1689,16 +1685,13 @@ int force_sig_fault_to_task(int sig, int code, void __user *addr } int force_sig_fault(int sig, int code, void __user *addr - ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)) { return force_sig_fault_to_task(sig, code, addr - ___ARCH_SI_TRAPNO(trapno) ___ARCH_SI_IA64(imm, flags, isr), current); } int send_sig_fault(int sig, int code, void __user *addr - ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t) { @@ -1709,9 +1702,6 @@ int send_sig_fault(int sig, int code, void __user *addr info.si_errno = 0; info.si_code = code; info.si_addr = addr; -#ifdef __ARCH_SI_TRAPNO - info.si_trapno = trapno; -#endif #ifdef __ia64__ info.si_imm = imm; info.si_flags = flags; @@ -3283,10 +3273,6 @@ enum siginfo_layout siginfo_layout(unsigned sig, int si_code) ((sig == SIGFPE) || ((sig == SIGTRAP) && (si_code == TRAP_UNK)))) layout = SIL_FAULT_TRAPNO; -#ifdef __ARCH_SI_TRAPNO - else if (layout == SIL_FAULT) - layout = SIL_FAULT_TRAPNO; -#endif } else if (si_code <= NSIGPOLL) layout = SIL_POLL; -- cgit v1.2.3 From f4ac73023449e6f2f74f69e38f4840c83edfa840 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 30 Apr 2021 17:58:56 -0500 Subject: signal: Rename SIL_PERF_EVENT SIL_FAULT_PERF_EVENT for consistency It helps to know which part of the siginfo structure the siginfo_layout value is talking about. v1: https://lkml.kernel.org/r/m18s4zs7nu.fsf_-_@fess.ebiederm.org v2: https://lkml.kernel.org/r/20210505141101.11519-9-ebiederm@xmission.com Link: https://lkml.kernel.org/r/87zgumw8cc.fsf_-_@disp2133 Acked-by: Marco Elver Signed-off-by: Eric W. Biederman --- fs/signalfd.c | 4 ++-- include/linux/signal.h | 2 +- kernel/signal.c | 10 +++++----- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/signalfd.c b/fs/signalfd.c index 167b5889db4b..040e1cf90528 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -114,10 +114,10 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, break; case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: - case SIL_PERF_EVENT: + case SIL_FAULT_PERF_EVENT: /* * Fall through to the SIL_FAULT case. SIL_FAULT_BNDERR, - * SIL_FAULT_PKUERR, and SIL_PERF_EVENT are only + * SIL_FAULT_PKUERR, and SIL_FAULT_PERF_EVENT are only * generated by faults that deliver them synchronously to * userspace. In case someone injects one of these signals * and signalfd catches it treat it as SIL_FAULT. diff --git a/include/linux/signal.h b/include/linux/signal.h index 3454c7ff0778..3f96a6374e4f 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -44,7 +44,7 @@ enum siginfo_layout { SIL_FAULT_MCEERR, SIL_FAULT_BNDERR, SIL_FAULT_PKUERR, - SIL_PERF_EVENT, + SIL_FAULT_PERF_EVENT, SIL_CHLD, SIL_RT, SIL_SYS, diff --git a/kernel/signal.c b/kernel/signal.c index 2181423e562a..332b21f2fe72 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1213,7 +1213,7 @@ static inline bool has_si_pid_and_uid(struct kernel_siginfo *info) case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: - case SIL_PERF_EVENT: + case SIL_FAULT_PERF_EVENT: case SIL_SYS: ret = false; break; @@ -2580,7 +2580,7 @@ static void hide_si_addr_tag_bits(struct ksignal *ksig) case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: - case SIL_PERF_EVENT: + case SIL_FAULT_PERF_EVENT: ksig->info.si_addr = arch_untagged_si_addr( ksig->info.si_addr, ksig->sig, ksig->info.si_code); break; @@ -3265,7 +3265,7 @@ enum siginfo_layout siginfo_layout(unsigned sig, int si_code) layout = SIL_FAULT_PKUERR; #endif else if ((sig == SIGTRAP) && (si_code == TRAP_PERF)) - layout = SIL_PERF_EVENT; + layout = SIL_FAULT_PERF_EVENT; else if (IS_ENABLED(CONFIG_SPARC) && (sig == SIGILL) && (si_code == ILL_ILLTRP)) layout = SIL_FAULT_TRAPNO; @@ -3394,7 +3394,7 @@ void copy_siginfo_to_external32(struct compat_siginfo *to, to->si_addr = ptr_to_compat(from->si_addr); to->si_pkey = from->si_pkey; break; - case SIL_PERF_EVENT: + case SIL_FAULT_PERF_EVENT: to->si_addr = ptr_to_compat(from->si_addr); to->si_perf_data = from->si_perf_data; to->si_perf_type = from->si_perf_type; @@ -3471,7 +3471,7 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, to->si_addr = compat_ptr(from->si_addr); to->si_pkey = from->si_pkey; break; - case SIL_PERF_EVENT: + case SIL_FAULT_PERF_EVENT: to->si_addr = compat_ptr(from->si_addr); to->si_perf_data = from->si_perf_data; to->si_perf_type = from->si_perf_type; -- cgit v1.2.3 From 3cee6fb8e69ecd79be891c89a94974c48a25a437 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 1 Jul 2021 13:06:19 -0700 Subject: bpf: tcp: Support bpf_(get|set)sockopt in bpf tcp iter This patch allows bpf tcp iter to call bpf_(get|set)sockopt. To allow a specific bpf iter (tcp here) to call a set of helpers, get_func_proto function pointer is added to bpf_iter_reg. The bpf iter is a tracing prog which currently requires CAP_PERFMON or CAP_SYS_ADMIN, so this patch does not impose other capability checks for bpf_(get|set)sockopt. Signed-off-by: Martin KaFai Lau Signed-off-by: Andrii Nakryiko Reviewed-by: Eric Dumazet Acked-by: Kuniyuki Iwashima Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210701200619.1036715-1-kafai@fb.com --- include/linux/bpf.h | 8 ++++++++ kernel/bpf/bpf_iter.c | 22 ++++++++++++++++++++++ kernel/trace/bpf_trace.c | 7 ++++++- net/core/filter.c | 34 ++++++++++++++++++++++++++++++++++ net/ipv4/tcp_ipv4.c | 15 +++++++++++++++ 5 files changed, 85 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 978ebd16ae60..c8cc09013210 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1442,6 +1442,9 @@ typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux, struct seq_file *seq); typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); +typedef const struct bpf_func_proto * +(*bpf_iter_get_func_proto_t)(enum bpf_func_id func_id, + const struct bpf_prog *prog); enum bpf_iter_feature { BPF_ITER_RESCHED = BIT(0), @@ -1454,6 +1457,7 @@ struct bpf_iter_reg { bpf_iter_detach_target_t detach_target; bpf_iter_show_fdinfo_t show_fdinfo; bpf_iter_fill_link_info_t fill_link_info; + bpf_iter_get_func_proto_t get_func_proto; u32 ctx_arg_info_size; u32 feature; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; @@ -1476,6 +1480,8 @@ struct bpf_iter__bpf_map_elem { int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); +const struct bpf_func_proto * +bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); @@ -2050,6 +2056,8 @@ extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; +extern const struct bpf_func_proto bpf_sk_setsockopt_proto; +extern const struct bpf_func_proto bpf_sk_getsockopt_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 2d4fbdbb194e..2e9d47bb40ff 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -360,6 +360,28 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog) return supported; } +const struct bpf_func_proto * +bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + const struct bpf_iter_target_info *tinfo; + const struct bpf_func_proto *fn = NULL; + + mutex_lock(&targets_mutex); + list_for_each_entry(tinfo, &targets, list) { + if (tinfo->btf_id == prog->aux->attach_btf_id) { + const struct bpf_iter_reg *reg_info; + + reg_info = tinfo->reg_info; + if (reg_info->get_func_proto) + fn = reg_info->get_func_proto(func_id, prog); + break; + } + } + mutex_unlock(&targets_mutex); + + return fn; +} + static void bpf_iter_link_release(struct bpf_link *link) { struct bpf_iter_link *iter_link = diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1f22ce1fa971..c5e0b6a64091 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1461,6 +1461,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) const struct bpf_func_proto * tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { + const struct bpf_func_proto *fn; + switch (func_id) { #ifdef CONFIG_NET case BPF_FUNC_skb_output: @@ -1501,7 +1503,10 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_d_path: return &bpf_d_path_proto; default: - return raw_tp_prog_func_proto(func_id, prog); + fn = raw_tp_prog_func_proto(func_id, prog); + if (!fn && prog->expected_attach_type == BPF_TRACE_ITER) + fn = bpf_iter_get_func_proto(func_id, prog); + return fn; } } diff --git a/net/core/filter.c b/net/core/filter.c index 3b4986e96e9c..faf29fd82276 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5016,6 +5016,40 @@ err_clear: return -EINVAL; } +BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level, + int, optname, char *, optval, int, optlen) +{ + return _bpf_setsockopt(sk, level, optname, optval, optlen); +} + +const struct bpf_func_proto bpf_sk_setsockopt_proto = { + .func = bpf_sk_setsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + +BPF_CALL_5(bpf_sk_getsockopt, struct sock *, sk, int, level, + int, optname, char *, optval, int, optlen) +{ + return _bpf_getsockopt(sk, level, optname, optval, optlen); +} + +const struct bpf_func_proto bpf_sk_getsockopt_proto = { + .func = bpf_sk_getsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_UNINIT_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 84ac0135d389..f9c6e47141fd 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3259,6 +3259,20 @@ static const struct bpf_iter_seq_info tcp_seq_info = { .seq_priv_size = sizeof(struct bpf_tcp_iter_state), }; +static const struct bpf_func_proto * +bpf_iter_tcp_get_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_setsockopt: + return &bpf_sk_setsockopt_proto; + case BPF_FUNC_getsockopt: + return &bpf_sk_getsockopt_proto; + default: + return NULL; + } +} + static struct bpf_iter_reg tcp_reg_info = { .target = "tcp", .ctx_arg_info_size = 1, @@ -3266,6 +3280,7 @@ static struct bpf_iter_reg tcp_reg_info = { { offsetof(struct bpf_iter__tcp, sk_common), PTR_TO_BTF_ID_OR_NULL }, }, + .get_func_proto = bpf_iter_tcp_get_func_proto, .seq_info = &tcp_seq_info, }; -- cgit v1.2.3 From 463e862ac63ef27fca423782536f6465abc3f180 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 20 Jul 2021 14:38:24 +0100 Subject: swiotlb: Convert io_default_tlb_mem to static allocation Since commit 69031f500865 ("swiotlb: Set dev->dma_io_tlb_mem to the swiotlb pool used"), 'struct device' may hold a copy of the global 'io_default_tlb_mem' pointer if the device is using swiotlb for DMA. A subsequent call to swiotlb_exit() will therefore leave dangling pointers behind in these device structures, resulting in KASAN splats such as: | BUG: KASAN: use-after-free in __iommu_dma_unmap_swiotlb+0x64/0xb0 | Read of size 8 at addr ffff8881d7830000 by task swapper/0/0 | | CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.12.0-rc3-debug #1 | Hardware name: HP HP Desktop M01-F1xxx/87D6, BIOS F.12 12/17/2020 | Call Trace: | | dump_stack+0x9c/0xcf | print_address_description.constprop.0+0x18/0x130 | kasan_report.cold+0x7f/0x111 | __iommu_dma_unmap_swiotlb+0x64/0xb0 | nvme_pci_complete_rq+0x73/0x130 | blk_complete_reqs+0x6f/0x80 | __do_softirq+0xfc/0x3be Convert 'io_default_tlb_mem' to a static structure, so that the per-device pointers remain valid after swiotlb_exit() has been invoked. All users are updated to reference the static structure directly, using the 'nslabs' field to determine whether swiotlb has been initialised. The 'slots' array is still allocated dynamically and referenced via a pointer rather than a flexible array member. Cc: Claire Chang Cc: Christoph Hellwig Cc: Robin Murphy Cc: Konrad Rzeszutek Wilk Fixes: 69031f500865 ("swiotlb: Set dev->dma_io_tlb_mem to the swiotlb pool used") Reported-by: Nathan Chancellor Tested-by: Nathan Chancellor Tested-by: Claire Chang Reviewed-by: Christoph Hellwig Signed-off-by: Will Deacon Signed-off-by: Konrad Rzeszutek Wilk --- drivers/base/core.c | 2 +- drivers/xen/swiotlb-xen.c | 4 +-- include/linux/swiotlb.h | 4 +-- kernel/dma/swiotlb.c | 66 ++++++++++++++++++++++++++--------------------- 4 files changed, 41 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index ea5b85354526..b49824001cfa 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2848,7 +2848,7 @@ void device_initialize(struct device *dev) dev->dma_coherent = dma_default_coherent; #endif #ifdef CONFIG_SWIOTLB - dev->dma_io_tlb_mem = io_tlb_default_mem; + dev->dma_io_tlb_mem = &io_tlb_default_mem; #endif } EXPORT_SYMBOL_GPL(device_initialize); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 785ec7e8be01..f06d9b4f1e0f 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -164,7 +164,7 @@ int __ref xen_swiotlb_init(void) int rc = -ENOMEM; char *start; - if (io_tlb_default_mem != NULL) { + if (io_tlb_default_mem.nslabs) { pr_warn("swiotlb buffer already initialized\n"); return -EEXIST; } @@ -547,7 +547,7 @@ xen_swiotlb_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, static int xen_swiotlb_dma_supported(struct device *hwdev, u64 mask) { - return xen_phys_to_dma(hwdev, io_tlb_default_mem->end - 1) <= mask; + return xen_phys_to_dma(hwdev, io_tlb_default_mem.end - 1) <= mask; } const struct dma_map_ops xen_swiotlb_dma_ops = { diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 39284ff2a6cd..b0cb2a9973f4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -103,9 +103,9 @@ struct io_tlb_mem { phys_addr_t orig_addr; size_t alloc_size; unsigned int list; - } slots[]; + } *slots; }; -extern struct io_tlb_mem *io_tlb_default_mem; +extern struct io_tlb_mem io_tlb_default_mem; static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index f1a9ae7fad8f..7948f274f9bb 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -70,7 +70,7 @@ enum swiotlb_force swiotlb_force; -struct io_tlb_mem *io_tlb_default_mem; +struct io_tlb_mem io_tlb_default_mem; /* * Max segment that we can provide which (if pages are contingous) will @@ -101,7 +101,7 @@ early_param("swiotlb", setup_io_tlb_npages); unsigned int swiotlb_max_segment(void) { - return io_tlb_default_mem ? max_segment : 0; + return io_tlb_default_mem.nslabs ? max_segment : 0; } EXPORT_SYMBOL_GPL(swiotlb_max_segment); @@ -134,9 +134,9 @@ void __init swiotlb_adjust_size(unsigned long size) void swiotlb_print_info(void) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = &io_tlb_default_mem; - if (!mem) { + if (!mem->nslabs) { pr_warn("No low mem\n"); return; } @@ -163,11 +163,11 @@ static inline unsigned long nr_slots(u64 val) */ void __init swiotlb_update_mem_attributes(void) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = &io_tlb_default_mem; void *vaddr; unsigned long bytes; - if (!mem || mem->late_alloc) + if (!mem->nslabs || mem->late_alloc) return; vaddr = phys_to_virt(mem->start); bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); @@ -201,25 +201,24 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) { - struct io_tlb_mem *mem; + struct io_tlb_mem *mem = &io_tlb_default_mem; size_t alloc_size; if (swiotlb_force == SWIOTLB_NO_FORCE) return 0; /* protect against double initialization */ - if (WARN_ON_ONCE(io_tlb_default_mem)) + if (WARN_ON_ONCE(mem->nslabs)) return -ENOMEM; - alloc_size = PAGE_ALIGN(struct_size(mem, slots, nslabs)); - mem = memblock_alloc(alloc_size, PAGE_SIZE); - if (!mem) + alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs)); + mem->slots = memblock_alloc(alloc_size, PAGE_SIZE); + if (!mem->slots) panic("%s: Failed to allocate %zu bytes align=0x%lx\n", __func__, alloc_size, PAGE_SIZE); swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false); - io_tlb_default_mem = mem; if (verbose) swiotlb_print_info(); swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT); @@ -304,26 +303,24 @@ swiotlb_late_init_with_default_size(size_t default_size) int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { - struct io_tlb_mem *mem; + struct io_tlb_mem *mem = &io_tlb_default_mem; unsigned long bytes = nslabs << IO_TLB_SHIFT; if (swiotlb_force == SWIOTLB_NO_FORCE) return 0; /* protect against double initialization */ - if (WARN_ON_ONCE(io_tlb_default_mem)) + if (WARN_ON_ONCE(mem->nslabs)) return -ENOMEM; - mem = (void *)__get_free_pages(GFP_KERNEL, - get_order(struct_size(mem, slots, nslabs))); - if (!mem) + mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(array_size(sizeof(*mem->slots), nslabs))); + if (!mem->slots) return -ENOMEM; - memset(mem, 0, sizeof(*mem)); set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true); - io_tlb_default_mem = mem; swiotlb_print_info(); swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT); return 0; @@ -331,18 +328,18 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) void __init swiotlb_exit(void) { - struct io_tlb_mem *mem = io_tlb_default_mem; size_t size; + struct io_tlb_mem *mem = &io_tlb_default_mem; - if (!mem) + if (!mem->nslabs) return; - size = struct_size(mem, slots, mem->nslabs); + size = array_size(sizeof(*mem->slots), mem->nslabs); if (mem->late_alloc) - free_pages((unsigned long)mem, get_order(size)); + free_pages((unsigned long)mem->slots, get_order(size)); else - memblock_free_late(__pa(mem), PAGE_ALIGN(size)); - io_tlb_default_mem = NULL; + memblock_free_late(__pa(mem->slots), PAGE_ALIGN(size)); + memset(mem, 0, sizeof(*mem)); } /* @@ -696,7 +693,9 @@ size_t swiotlb_max_mapping_size(struct device *dev) bool is_swiotlb_active(struct device *dev) { - return dev->dma_io_tlb_mem != NULL; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + + return mem && mem->nslabs; } EXPORT_SYMBOL_GPL(is_swiotlb_active); @@ -711,10 +710,10 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem) static int __init swiotlb_create_default_debugfs(void) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = &io_tlb_default_mem; debugfs_dir = debugfs_create_dir("swiotlb", NULL); - if (mem) { + if (mem->nslabs) { mem->debugfs = debugfs_dir; swiotlb_create_debugfs_files(mem); } @@ -783,10 +782,17 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem, * to it. */ if (!mem) { - mem = kzalloc(struct_size(mem, slots, nslabs), GFP_KERNEL); + mem = kzalloc(sizeof(*mem), GFP_KERNEL); if (!mem) return -ENOMEM; + mem->slots = kzalloc(array_size(sizeof(*mem->slots), nslabs), + GFP_KERNEL); + if (!mem->slots) { + kfree(mem); + return -ENOMEM; + } + set_memory_decrypted((unsigned long)phys_to_virt(rmem->base), rmem->size >> PAGE_SHIFT); swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false); @@ -806,7 +812,7 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem, static void rmem_swiotlb_device_release(struct reserved_mem *rmem, struct device *dev) { - dev->dma_io_tlb_mem = io_tlb_default_mem; + dev->dma_io_tlb_mem = &io_tlb_default_mem; } static const struct reserved_mem_ops rmem_swiotlb_ops = { -- cgit v1.2.3 From 616d5769345528b989294a242a5906b157a92837 Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Sun, 18 Jul 2021 14:54:13 +0300 Subject: IB/mlx5: Rename is_apu_thread_cq function to is_apu_cq is_apu_thread_cq() used to detect CQs which are attached to APU threads. This was extended to support other elements as well, so the function was renamed to is_apu_cq(). c_eqn_or_apu_element was extended from 8 bits to 32 bits, which wan't reflected when the APU support was first introduced. Acked-by: Michael S. Tsirkin # vdpa Signed-off-by: Tal Gilboa Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/cq.c | 2 +- drivers/infiniband/hw/mlx5/devx.c | 7 +++---- drivers/net/ethernet/mellanox/mlx5/core/cq.c | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 +- include/linux/mlx5/mlx5_ifc.h | 5 ++--- 8 files changed, 12 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 7abeb576b3c5..18b55d2eba40 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -997,7 +997,7 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD)); MLX5_SET(cqc, cqc, log_cq_size, ilog2(entries)); MLX5_SET(cqc, cqc, uar_page, index); - MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET64(cqc, cqc, dbr_addr, cq->db.dma); if (cq->create_flags & IB_UVERBS_CQ_FLAGS_IGNORE_OVERRUN) MLX5_SET(cqc, cqc, oi, 1); diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index eb9b0a2707f8..e994aefcc40f 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1437,11 +1437,10 @@ out: rcu_read_unlock(); } -static bool is_apu_thread_cq(struct mlx5_ib_dev *dev, const void *in) +static bool is_apu_cq(struct mlx5_ib_dev *dev, const void *in) { if (!MLX5_CAP_GEN(dev->mdev, apu) || - !MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), - apu_thread_cq)) + !MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), apu_cq)) return false; return true; @@ -1501,7 +1500,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( err = mlx5_core_create_dct(dev, &obj->core_dct, cmd_in, cmd_in_len, cmd_out, cmd_out_len); } else if (opcode == MLX5_CMD_OP_CREATE_CQ && - !is_apu_thread_cq(dev, cmd_in)) { + !is_apu_cq(dev, cmd_in)) { obj->flags |= DEVX_OBJ_FLAGS_CQ; obj->core_cq.comp = devx_cq_comp; err = mlx5_core_create_cq(dev->mdev, &obj->core_cq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index df3e4938ecdd..99ec278d0370 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -89,7 +89,8 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen) { - int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), c_eqn); + int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), + c_eqn_or_apu_element); u32 din[MLX5_ST_SZ_DW(destroy_cq_in)] = {}; struct mlx5_eq_comp *eq; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d09e65557e75..cd2042d11968 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1627,7 +1627,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas)); MLX5_SET(cqc, cqc, cq_period_mode, param->cq_period_mode); - MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index bd66ab2af5b5..9b2cca6d9620 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -454,7 +454,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); MLX5_SET(cqc, cqc, log_cq_size, ilog2(cq_size)); - MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET(cqc, cqc, uar_page, fdev->conn_res.uar->index); MLX5_SET(cqc, cqc, log_page_size, conn->cq.wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 12cf323a5943..754f89222858 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -790,7 +790,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); MLX5_SET(cqc, cqc, log_cq_size, ilog2(ncqe)); - MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET(cqc, cqc, uar_page, uar->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 2a31467f7ac5..de8e8a1e13e7 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -573,7 +573,7 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); MLX5_SET(cqc, cqc, log_cq_size, ilog2(num_ent)); MLX5_SET(cqc, cqc, uar_page, ndev->mvdev.res.uar->index); - MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET64(cqc, cqc, dbr_addr, vcq->db.dma); err = mlx5_core_create_cq(mdev, &vcq->mcq, in, inlen, out, sizeof(out)); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3dd6641e942c..0b413f365699 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3919,7 +3919,7 @@ struct mlx5_ifc_cqc_bits { u8 status[0x4]; u8 reserved_at_4[0x2]; u8 dbr_umem_valid[0x1]; - u8 apu_thread_cq[0x1]; + u8 apu_cq[0x1]; u8 cqe_sz[0x3]; u8 cc[0x1]; u8 reserved_at_c[0x1]; @@ -3945,8 +3945,7 @@ struct mlx5_ifc_cqc_bits { u8 cq_period[0xc]; u8 cq_max_count[0x10]; - u8 reserved_at_a0[0x18]; - u8 c_eqn[0x8]; + u8 c_eqn_or_apu_element[0x20]; u8 reserved_at_c0[0x3]; u8 log_page_size[0x5]; -- cgit v1.2.3 From c757096ea1033c46ab768709847f7776b7e92a92 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 9 Oct 2019 06:41:08 +0200 Subject: can: rx-offload: add skb queue for use during ISR Adding a skb to the skb_queue in rx-offload requires to take a lock. This commit avoids this by adding an unlocked skb queue that is appended at the end of the ISR. Having one lock at the end of the ISR should be OK as the HW is empty, not about to overflow. Link: https://lore.kernel.org/r/20210724204745.736053-2-mkl@pengutronix.de Tested-by: Oleksij Rempel Co-developed-by: Kurt Van Dijck Signed-off-by: Kurt Van Dijck Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/rx-offload.c | 67 +++++++++++++------------- drivers/net/can/flexcan.c | 3 ++ drivers/net/can/m_can/m_can.c | 3 ++ drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c | 6 ++- drivers/net/can/ti_hecc.c | 2 + include/linux/can/rx-offload.h | 2 + 6 files changed, 48 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev/rx-offload.c b/drivers/net/can/dev/rx-offload.c index ab2c1543786c..d0bdb6db3a57 100644 --- a/drivers/net/can/dev/rx-offload.c +++ b/drivers/net/can/dev/rx-offload.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2014 Protonic Holland, * David Jander - * Copyright (C) 2014-2017 Pengutronix, + * Copyright (C) 2014-2021 Pengutronix, * Marc Kleine-Budde */ @@ -174,10 +174,8 @@ can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n) int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 pending) { - struct sk_buff_head skb_queue; unsigned int i; - - __skb_queue_head_init(&skb_queue); + int received = 0; for (i = offload->mb_first; can_rx_offload_le(offload, i, offload->mb_last); @@ -191,26 +189,12 @@ int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, if (IS_ERR_OR_NULL(skb)) continue; - __skb_queue_add_sort(&skb_queue, skb, can_rx_offload_compare); - } - - if (!skb_queue_empty(&skb_queue)) { - unsigned long flags; - u32 queue_len; - - spin_lock_irqsave(&offload->skb_queue.lock, flags); - skb_queue_splice_tail(&skb_queue, &offload->skb_queue); - spin_unlock_irqrestore(&offload->skb_queue.lock, flags); - - queue_len = skb_queue_len(&offload->skb_queue); - if (queue_len > offload->skb_queue_len_max / 8) - netdev_dbg(offload->dev, "%s: queue_len=%d\n", - __func__, queue_len); - - can_rx_offload_schedule(offload); + __skb_queue_add_sort(&offload->skb_irq_queue, skb, + can_rx_offload_compare); + received++; } - return skb_queue_len(&skb_queue); + return received; } EXPORT_SYMBOL_GPL(can_rx_offload_irq_offload_timestamp); @@ -226,13 +210,10 @@ int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload) if (!skb) break; - skb_queue_tail(&offload->skb_queue, skb); + __skb_queue_tail(&offload->skb_irq_queue, skb); received++; } - if (received) - can_rx_offload_schedule(offload); - return received; } EXPORT_SYMBOL_GPL(can_rx_offload_irq_offload_fifo); @@ -241,7 +222,6 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload, struct sk_buff *skb, u32 timestamp) { struct can_rx_offload_cb *cb; - unsigned long flags; if (skb_queue_len(&offload->skb_queue) > offload->skb_queue_len_max) { @@ -252,11 +232,8 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload, cb = can_rx_offload_get_cb(skb); cb->timestamp = timestamp; - spin_lock_irqsave(&offload->skb_queue.lock, flags); - __skb_queue_add_sort(&offload->skb_queue, skb, can_rx_offload_compare); - spin_unlock_irqrestore(&offload->skb_queue.lock, flags); - - can_rx_offload_schedule(offload); + __skb_queue_add_sort(&offload->skb_irq_queue, skb, + can_rx_offload_compare); return 0; } @@ -295,13 +272,33 @@ int can_rx_offload_queue_tail(struct can_rx_offload *offload, return -ENOBUFS; } - skb_queue_tail(&offload->skb_queue, skb); - can_rx_offload_schedule(offload); + __skb_queue_tail(&offload->skb_irq_queue, skb); return 0; } EXPORT_SYMBOL_GPL(can_rx_offload_queue_tail); +void can_rx_offload_irq_finish(struct can_rx_offload *offload) +{ + unsigned long flags; + int queue_len; + + if (skb_queue_empty_lockless(&offload->skb_irq_queue)) + return; + + spin_lock_irqsave(&offload->skb_queue.lock, flags); + skb_queue_splice_tail_init(&offload->skb_irq_queue, &offload->skb_queue); + spin_unlock_irqrestore(&offload->skb_queue.lock, flags); + + queue_len = skb_queue_len(&offload->skb_queue); + if (queue_len > offload->skb_queue_len_max / 8) + netdev_dbg(offload->dev, "%s: queue_len=%d\n", + __func__, queue_len); + + can_rx_offload_schedule(offload); +} +EXPORT_SYMBOL_GPL(can_rx_offload_irq_finish); + static int can_rx_offload_init_queue(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight) @@ -312,6 +309,7 @@ static int can_rx_offload_init_queue(struct net_device *dev, offload->skb_queue_len_max = 2 << fls(weight); offload->skb_queue_len_max *= 4; skb_queue_head_init(&offload->skb_queue); + __skb_queue_head_init(&offload->skb_irq_queue); netif_napi_add(dev, &offload->napi, can_rx_offload_napi_poll, weight); @@ -373,5 +371,6 @@ void can_rx_offload_del(struct can_rx_offload *offload) { netif_napi_del(&offload->napi); skb_queue_purge(&offload->skb_queue); + __skb_queue_purge(&offload->skb_irq_queue); } EXPORT_SYMBOL_GPL(can_rx_offload_del); diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 57f3635ad8d7..d9dcf6a8412b 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1198,6 +1198,9 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id) } } + if (handled) + can_rx_offload_irq_finish(&priv->offload); + return handled; } diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index bba2a449ac70..18461982f7a1 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1058,6 +1058,9 @@ static irqreturn_t m_can_isr(int irq, void *dev_id) } } + if (cdev->is_peripheral) + can_rx_offload_irq_finish(&cdev->offload); + return IRQ_HANDLED; } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 47c3f408a799..f3b267ec22e0 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -2195,8 +2195,10 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id) FIELD_GET(MCP251XFD_REG_INT_IE_MASK, priv->regs_status.intf); - if (!(intf_pending)) + if (!(intf_pending)) { + can_rx_offload_irq_finish(&priv->offload); return handled; + } /* Some interrupts must be ACKed in the * MCP251XFD_REG_INT register. @@ -2296,6 +2298,8 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id) } while (1); out_fail: + can_rx_offload_irq_finish(&priv->offload); + netdev_err(priv->ndev, "IRQ handler returned %d (intf=0x%08x).\n", err, priv->regs_status.intf); mcp251xfd_dump(priv); diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 73245d8836a9..353062ead98f 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -786,6 +786,8 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) int_status = hecc_read(priv, HECC_CANGIF0); } + can_rx_offload_irq_finish(&priv->offload); + return IRQ_HANDLED; } diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 40882df7105e..d71c938e17d0 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -20,6 +20,7 @@ struct can_rx_offload { bool drop); struct sk_buff_head skb_queue; + struct sk_buff_head skb_irq_queue; u32 skb_queue_len_max; unsigned int mb_first; @@ -48,6 +49,7 @@ unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int *frame_len_ptr); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb); +void can_rx_offload_irq_finish(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); void can_rx_offload_enable(struct can_rx_offload *offload); -- cgit v1.2.3 From 1e0d8e507ea42dd37f52636db300de7ea7118012 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Fri, 7 May 2021 17:58:30 +0200 Subject: can: rx-offload: can_rx_offload_irq_finish(): directly call napi_schedule() Instead of calling can_rx_offload_schedule() call napi_schedule() directly. As this was the last use of can_rx_offload_schedule() remove this helper function. Link: https://lore.kernel.org/r/20210724204745.736053-3-mkl@pengutronix.de Tested-by: Oleksij Rempel Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/rx-offload.c | 2 +- include/linux/can/rx-offload.h | 5 ----- 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev/rx-offload.c b/drivers/net/can/dev/rx-offload.c index d0bdb6db3a57..82ade3aa5c13 100644 --- a/drivers/net/can/dev/rx-offload.c +++ b/drivers/net/can/dev/rx-offload.c @@ -295,7 +295,7 @@ void can_rx_offload_irq_finish(struct can_rx_offload *offload) netdev_dbg(offload->dev, "%s: queue_len=%d\n", __func__, queue_len); - can_rx_offload_schedule(offload); + napi_schedule(&offload->napi); } EXPORT_SYMBOL_GPL(can_rx_offload_irq_finish); diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index d71c938e17d0..516f64df0ebc 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -53,11 +53,6 @@ void can_rx_offload_irq_finish(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); void can_rx_offload_enable(struct can_rx_offload *offload); -static inline void can_rx_offload_schedule(struct can_rx_offload *offload) -{ - napi_schedule(&offload->napi); -} - static inline void can_rx_offload_disable(struct can_rx_offload *offload) { napi_disable(&offload->napi); -- cgit v1.2.3 From 30bfec4fec5902731c8823f51c5332e6f2b2312a Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 10 May 2021 22:51:39 +0200 Subject: can: rx-offload: can_rx_offload_threaded_irq_finish(): add new function to be called from threaded interrupt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After reading all CAN frames from the controller in the IRQ handler and storing them into a skb_queue, the driver calls napi_schedule(). In the napi poll function the skb from the skb_queue are then pushed into the networking stack. However if napi_schedule() is called from a threaded IRQ handler this triggers the following error: | NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!! To avoid this, create a new rx-offload function (can_rx_offload_threaded_irq_finish()) with a call to local_bh_disable()/local_bh_enable() around the napi_schedule() call. Convert all drivers that call can_rx_offload_irq_finish() from threaded IRQ context to can_rx_offload_threaded_irq_finish(). Link: https://lore.kernel.org/r/20210724204745.736053-4-mkl@pengutronix.de Suggested-by: Daniel Glöckner Tested-by: Oleksij Rempel Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/rx-offload.c | 23 +++++++++++++++++++++++ drivers/net/can/m_can/m_can.c | 2 +- drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c | 4 ++-- include/linux/can/rx-offload.h | 1 + 4 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev/rx-offload.c b/drivers/net/can/dev/rx-offload.c index 82ade3aa5c13..37b0cc65237b 100644 --- a/drivers/net/can/dev/rx-offload.c +++ b/drivers/net/can/dev/rx-offload.c @@ -299,6 +299,29 @@ void can_rx_offload_irq_finish(struct can_rx_offload *offload) } EXPORT_SYMBOL_GPL(can_rx_offload_irq_finish); +void can_rx_offload_threaded_irq_finish(struct can_rx_offload *offload) +{ + unsigned long flags; + int queue_len; + + if (skb_queue_empty_lockless(&offload->skb_irq_queue)) + return; + + spin_lock_irqsave(&offload->skb_queue.lock, flags); + skb_queue_splice_tail_init(&offload->skb_irq_queue, &offload->skb_queue); + spin_unlock_irqrestore(&offload->skb_queue.lock, flags); + + queue_len = skb_queue_len(&offload->skb_queue); + if (queue_len > offload->skb_queue_len_max / 8) + netdev_dbg(offload->dev, "%s: queue_len=%d\n", + __func__, queue_len); + + local_bh_disable(); + napi_schedule(&offload->napi); + local_bh_enable(); +} +EXPORT_SYMBOL_GPL(can_rx_offload_threaded_irq_finish); + static int can_rx_offload_init_queue(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 18461982f7a1..317cdc98c539 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1059,7 +1059,7 @@ static irqreturn_t m_can_isr(int irq, void *dev_id) } if (cdev->is_peripheral) - can_rx_offload_irq_finish(&cdev->offload); + can_rx_offload_threaded_irq_finish(&cdev->offload); return IRQ_HANDLED; } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index f3b267ec22e0..6962ab2749df 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -2196,7 +2196,7 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id) priv->regs_status.intf); if (!(intf_pending)) { - can_rx_offload_irq_finish(&priv->offload); + can_rx_offload_threaded_irq_finish(&priv->offload); return handled; } @@ -2298,7 +2298,7 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id) } while (1); out_fail: - can_rx_offload_irq_finish(&priv->offload); + can_rx_offload_threaded_irq_finish(&priv->offload); netdev_err(priv->ndev, "IRQ handler returned %d (intf=0x%08x).\n", err, priv->regs_status.intf); diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 516f64df0ebc..c11477620403 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -50,6 +50,7 @@ unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb); void can_rx_offload_irq_finish(struct can_rx_offload *offload); +void can_rx_offload_threaded_irq_finish(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); void can_rx_offload_enable(struct can_rx_offload *offload); -- cgit v1.2.3 From 8345a330738149389dc8883573c9264965922e08 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 16 Jun 2021 11:55:26 +0200 Subject: can: bittiming: fix documentation for struct can_tdc This patch fixes a typo in the documentation for struct can_tdc::tdcv. The number "0" refers to automatic mode not the letter "O". Further two grammar errors in the documentation for struct can_tdc are fixed. First grammar error: add a missing third person 's'. Second grammar error: replace "such as" by "such that". The intent is to give a condition, not an example. Fixes: 289ea9e4ae59 ("can: add new CAN FD bittiming parameters: Transmitter Delay Compensation (TDC)") Link: https://lore.kernel.org/r/20210616095922.2430415-1-mkl@pengutronix.de Link: https://lore.kernel.org/r/20210616124057.60723-1-mailhol.vincent@wanadoo.fr Co-developed-by: Vincent Mailhol Signed-off-by: Vincent Mailhol Acked-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- include/linux/can/bittiming.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index ae7a3411167c..9de6e9053e34 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -37,7 +37,7 @@ * quanta, from when the bit is sent on the TX pin to when it is * received on the RX pin of the transmitter. Possible options: * - * O: automatic mode. The controller dynamically measure @tdcv + * 0: automatic mode. The controller dynamically measures @tdcv * for each transmitted CAN FD frame. * * Other values: manual mode. Use the fixed provided value. @@ -45,7 +45,7 @@ * @tdco: Transmitter Delay Compensation Offset. Offset value, in time * quanta, defining the distance between the start of the bit * reception on the RX pin of the transceiver and the SSP - * position such as SSP = @tdcv + @tdco. + * position such that SSP = @tdcv + @tdco. * * If @tdco is zero, then TDC is disabled and both @tdcv and * @tdcf should be ignored. -- cgit v1.2.3 From 896e7f3e7424d6cc1436172740aa76ebb2c1b248 Mon Sep 17 00:00:00 2001 From: Angelo Dureghello Date: Fri, 2 Jul 2021 11:48:37 +0200 Subject: can: flexcan: add platform data header Add platform data header for flexcan. Link: https://lore.kernel.org/r/20210702094841.327679-1-angelo@kernel-space.org Signed-off-by: Angelo Dureghello Signed-off-by: Marc Kleine-Budde --- include/linux/can/platform/flexcan.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/linux/can/platform/flexcan.h (limited to 'include/linux') diff --git a/include/linux/can/platform/flexcan.h b/include/linux/can/platform/flexcan.h new file mode 100644 index 000000000000..1b536fb999de --- /dev/null +++ b/include/linux/can/platform/flexcan.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Angelo Dureghello + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _CAN_PLATFORM_FLEXCAN_H +#define _CAN_PLATFORM_FLEXCAN_H + +struct flexcan_platform_data { + u32 clock_frequency; + u8 clk_src; +}; + +#endif /* _CAN_PLATFORM_FLEXCAN_H */ -- cgit v1.2.3 From d18760560593e5af921f51a8c9b64b6109d634c2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 1 Jul 2021 23:53:46 -0700 Subject: fscrypt: add fscrypt_symlink_getattr() for computing st_size Add a helper function fscrypt_symlink_getattr() which will be called from the various filesystems' ->getattr() methods to read and decrypt the target of encrypted symlinks in order to report the correct st_size. Detailed explanation: As required by POSIX and as documented in various man pages, st_size for a symlink is supposed to be the length of the symlink target. Unfortunately, st_size has always been wrong for encrypted symlinks because st_size is populated from i_size from disk, which intentionally contains the length of the encrypted symlink target. That's slightly greater than the length of the decrypted symlink target (which is the symlink target that userspace usually sees), and usually won't match the length of the no-key encoded symlink target either. This hadn't been fixed yet because reporting the correct st_size would require reading the symlink target from disk and decrypting or encoding it, which historically has been considered too heavyweight to do in ->getattr(). Also historically, the wrong st_size had only broken a test (LTP lstat03) and there were no known complaints from real users. (This is probably because the st_size of symlinks isn't used too often, and when it is, typically it's for a hint for what buffer size to pass to readlink() -- which a slightly-too-large size still works for.) However, a couple things have changed now. First, there have recently been complaints about the current behavior from real users: - Breakage in rpmbuild: https://github.com/rpm-software-management/rpm/issues/1682 https://github.com/google/fscrypt/issues/305 - Breakage in toybox cpio: https://www.mail-archive.com/toybox@lists.landley.net/msg07193.html - Breakage in libgit2: https://issuetracker.google.com/issues/189629152 (on Android public issue tracker, requires login) Second, we now cache decrypted symlink targets in ->i_link. Therefore, taking the performance hit of reading and decrypting the symlink target in ->getattr() wouldn't be as big a deal as it used to be, since usually it will just save having to do the same thing later. Also note that eCryptfs ended up having to read and decrypt symlink targets in ->getattr() as well, to fix this same issue; see commit 3a60a1686f0d ("eCryptfs: Decrypt symlink target for stat size"). So, let's just bite the bullet, and read and decrypt the symlink target in ->getattr() in order to report the correct st_size. Add a function fscrypt_symlink_getattr() which the filesystems will call to do this. (Alternatively, we could store the decrypted size of symlinks on-disk. But there isn't a great place to do so, and encryption is meant to hide the original size to some extent; that property would be lost.) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210702065350.209646-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/crypto/hooks.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/fscrypt.h | 7 +++++++ 2 files changed, 51 insertions(+) (limited to 'include/linux') diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index a73b0376e6f3..af74599ae1cf 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -384,3 +384,47 @@ err_kfree: return ERR_PTR(err); } EXPORT_SYMBOL_GPL(fscrypt_get_symlink); + +/** + * fscrypt_symlink_getattr() - set the correct st_size for encrypted symlinks + * @path: the path for the encrypted symlink being queried + * @stat: the struct being filled with the symlink's attributes + * + * Override st_size of encrypted symlinks to be the length of the decrypted + * symlink target (or the no-key encoded symlink target, if the key is + * unavailable) rather than the length of the encrypted symlink target. This is + * necessary for st_size to match the symlink target that userspace actually + * sees. POSIX requires this, and some userspace programs depend on it. + * + * This requires reading the symlink target from disk if needed, setting up the + * inode's encryption key if possible, and then decrypting or encoding the + * symlink target. This makes lstat() more heavyweight than is normally the + * case. However, decrypted symlink targets will be cached in ->i_link, so + * usually the symlink won't have to be read and decrypted again later if/when + * it is actually followed, readlink() is called, or lstat() is called again. + * + * Return: 0 on success, -errno on failure + */ +int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat) +{ + struct dentry *dentry = path->dentry; + struct inode *inode = d_inode(dentry); + const char *link; + DEFINE_DELAYED_CALL(done); + + /* + * To get the symlink target that userspace will see (whether it's the + * decrypted target or the no-key encoded target), we can just get it in + * the same way the VFS does during path resolution and readlink(). + */ + link = READ_ONCE(inode->i_link); + if (!link) { + link = inode->i_op->get_link(dentry, inode, &done); + if (IS_ERR(link)) + return PTR_ERR(link); + } + stat->size = strlen(link); + do_delayed_call(&done); + return 0; +} +EXPORT_SYMBOL_GPL(fscrypt_symlink_getattr); diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 2ea1387bb497..b7bfd0cd4f3e 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -253,6 +253,7 @@ int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, unsigned int max_size, struct delayed_call *done); +int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat); static inline void fscrypt_set_ops(struct super_block *sb, const struct fscrypt_operations *s_cop) { @@ -583,6 +584,12 @@ static inline const char *fscrypt_get_symlink(struct inode *inode, return ERR_PTR(-EOPNOTSUPP); } +static inline int fscrypt_symlink_getattr(const struct path *path, + struct kstat *stat) +{ + return -EOPNOTSUPP; +} + static inline void fscrypt_set_ops(struct super_block *sb, const struct fscrypt_operations *s_cop) { -- cgit v1.2.3 From 7d9e2661f268585ca24ab4edbc1e2925b08374b2 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sun, 25 Jul 2021 15:16:00 -0600 Subject: printk: Move the printk() kerneldoc comment to its new home Commit 337015573718 ("printk: Userspace format indexing support") turned printk() into a macro, but left the kerneldoc comment for it with the (now) _printk() function, resulting in this docs-build warning: kernel/printk/printk.c:1: warning: 'printk' not found Move the kerneldoc comment back next to the (now) macro it's meant to describe and have the docs build find it there. Fixes: 337015573718b161 ("printk: Userspace format indexing support") Signed-off-by: Jonathan Corbet Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/87o8aqt7qn.fsf@meer.lwn.net --- Documentation/core-api/printk-basics.rst | 5 +---- include/linux/printk.h | 24 ++++++++++++++++++++++++ kernel/printk/printk.c | 24 ------------------------ 3 files changed, 25 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/printk-basics.rst b/Documentation/core-api/printk-basics.rst index 965e4281eddd..2dde24ca7d9f 100644 --- a/Documentation/core-api/printk-basics.rst +++ b/Documentation/core-api/printk-basics.rst @@ -107,9 +107,6 @@ also ``CONFIG_DYNAMIC_DEBUG`` in the case of pr_debug()) is defined. Function reference ================== -.. kernel-doc:: kernel/printk/printk.c - :functions: printk - .. kernel-doc:: include/linux/printk.h - :functions: pr_emerg pr_alert pr_crit pr_err pr_warn pr_notice pr_info + :functions: printk pr_emerg pr_alert pr_crit pr_err pr_warn pr_notice pr_info pr_fmt pr_debug pr_devel pr_cont diff --git a/include/linux/printk.h b/include/linux/printk.h index 2651b82ed352..c1e176403967 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -431,6 +431,30 @@ struct pi_entry { }) +/** + * printk - print a kernel message + * @fmt: format string + * + * This is printk(). It can be called from any context. We want it to work. + * + * If printk indexing is enabled, _printk() is called from printk_index_wrap. + * Otherwise, printk is simply #defined to _printk. + * + * We try to grab the console_lock. If we succeed, it's easy - we log the + * output and call the console drivers. If we fail to get the semaphore, we + * place the output into the log buffer and return. The current holder of + * the console_sem will notice the new output in console_unlock(); and will + * send it to the consoles before releasing the lock. + * + * One effect of this deferred printing is that code which calls printk() and + * then changes console_loglevel may break. This is because console_loglevel + * is inspected when the actual printing occurs. + * + * See also: + * printf(3) + * + * See the vsnprintf() documentation for format string extensions over C99. + */ #define printk(fmt, ...) printk_index_wrap(_printk, fmt, ##__VA_ARGS__) #define printk_deferred(fmt, ...) \ printk_index_wrap(_printk_deferred, fmt, ##__VA_ARGS__) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 765f7af6ce56..8030c670f0bc 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2183,30 +2183,6 @@ int vprintk_default(const char *fmt, va_list args) } EXPORT_SYMBOL_GPL(vprintk_default); -/** - * _printk - print a kernel message - * @fmt: format string - * - * This is _printk(). It can be called from any context. We want it to work. - * - * If printk indexing is enabled, _printk() is called from printk_index_wrap. - * Otherwise, printk is simply #defined to _printk. - * - * We try to grab the console_lock. If we succeed, it's easy - we log the - * output and call the console drivers. If we fail to get the semaphore, we - * place the output into the log buffer and return. The current holder of - * the console_sem will notice the new output in console_unlock(); and will - * send it to the consoles before releasing the lock. - * - * One effect of this deferred printing is that code which calls printk() and - * then changes console_loglevel may break. This is because console_loglevel - * is inspected when the actual printing occurs. - * - * See also: - * printf(3) - * - * See the vsnprintf() documentation for format string extensions over C99. - */ asmlinkage __visible int _printk(const char *fmt, ...) { va_list args; -- cgit v1.2.3 From 374c15594c4ee0dfcceb38852bd43be09070f402 Mon Sep 17 00:00:00 2001 From: "Isaac J. Manjarres" Date: Wed, 16 Jun 2021 06:38:42 -0700 Subject: iommu/io-pgtable: Introduce unmap_pages() as a page table op The io-pgtable code expects to operate on a single block or granule of memory that is supported by the IOMMU hardware when unmapping memory. This means that when a large buffer that consists of multiple such blocks is unmapped, the io-pgtable code will walk the page tables to the correct level to unmap each block, even for blocks that are virtually contiguous and at the same level, which can incur an overhead in performance. Introduce the unmap_pages() page table op to express to the io-pgtable code that it should unmap a number of blocks of the same size, instead of a single block. Doing so allows multiple blocks to be unmapped in one call to the io-pgtable code, reducing the number of page table walks, and indirect calls. Signed-off-by: Isaac J. Manjarres Suggested-by: Will Deacon Signed-off-by: Will Deacon Signed-off-by: Georgi Djakov Link: https://lore.kernel.org/r/1623850736-389584-2-git-send-email-quic_c_gdjako@quicinc.com Signed-off-by: Joerg Roedel --- include/linux/io-pgtable.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 4d40dfa75b55..9391c5fa71e6 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -144,6 +144,7 @@ struct io_pgtable_cfg { * * @map: Map a physically contiguous memory region. * @unmap: Unmap a physically contiguous memory region. + * @unmap_pages: Unmap a range of virtually contiguous pages of the same size. * @iova_to_phys: Translate iova to physical address. * * These functions map directly onto the iommu_ops member functions with @@ -154,6 +155,9 @@ struct io_pgtable_ops { phys_addr_t paddr, size_t size, int prot, gfp_t gfp); size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, size_t size, struct iommu_iotlb_gather *gather); + size_t (*unmap_pages)(struct io_pgtable_ops *ops, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *gather); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, unsigned long iova); }; -- cgit v1.2.3 From cacffb7f7b45ba7649eedea4c196c6e9f1863bf3 Mon Sep 17 00:00:00 2001 From: "Isaac J. Manjarres" Date: Wed, 16 Jun 2021 06:38:43 -0700 Subject: iommu: Add an unmap_pages() op for IOMMU drivers Add a callback for IOMMU drivers to provide a path for the IOMMU framework to call into an IOMMU driver, which can call into the io-pgtable code, to unmap a virtually contiguous range of pages of the same size. For IOMMU drivers that do not specify an unmap_pages() callback, the existing logic of unmapping memory one page block at a time will be used. Signed-off-by: Isaac J. Manjarres Suggested-by: Will Deacon Signed-off-by: Will Deacon Acked-by: Lu Baolu Signed-off-by: Georgi Djakov Link: https://lore.kernel.org/r/1623850736-389584-3-git-send-email-quic_c_gdjako@quicinc.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 32d448050bf7..25a844121be5 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -181,6 +181,7 @@ struct iommu_iotlb_gather { * @detach_dev: detach device from an iommu domain * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain + * @unmap_pages: unmap a number of pages of the same size from an iommu domain * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain * @iotlb_sync_map: Sync mappings created recently using @map to the hardware * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush @@ -231,6 +232,9 @@ struct iommu_ops { phys_addr_t paddr, size_t size, int prot, gfp_t gfp); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); + size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *iotlb_gather); void (*flush_iotlb_all)(struct iommu_domain *domain); void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova, size_t size); -- cgit v1.2.3 From ca073b55d16a83ba7e73cd313312abc68f07f293 Mon Sep 17 00:00:00 2001 From: "Isaac J. Manjarres" Date: Wed, 16 Jun 2021 06:38:44 -0700 Subject: iommu/io-pgtable: Introduce map_pages() as a page table op Mapping memory into io-pgtables follows the same semantics that unmapping memory used to follow (i.e. a buffer will be mapped one page block per call to the io-pgtable code). This means that it can be optimized in the same way that unmapping memory was, so add a map_pages() callback to the io-pgtable ops structure, so that a range of pages of the same size can be mapped within the same call. Signed-off-by: Isaac J. Manjarres Suggested-by: Will Deacon Signed-off-by: Georgi Djakov Link: https://lore.kernel.org/r/1623850736-389584-4-git-send-email-quic_c_gdjako@quicinc.com Signed-off-by: Joerg Roedel --- include/linux/io-pgtable.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 9391c5fa71e6..c43f3b899d2a 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -143,6 +143,7 @@ struct io_pgtable_cfg { * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers. * * @map: Map a physically contiguous memory region. + * @map_pages: Map a physically contiguous range of pages of the same size. * @unmap: Unmap a physically contiguous memory region. * @unmap_pages: Unmap a range of virtually contiguous pages of the same size. * @iova_to_phys: Translate iova to physical address. @@ -153,6 +154,9 @@ struct io_pgtable_cfg { struct io_pgtable_ops { int (*map)(struct io_pgtable_ops *ops, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp); + int (*map_pages)(struct io_pgtable_ops *ops, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped); size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, size_t size, struct iommu_iotlb_gather *gather); size_t (*unmap_pages)(struct io_pgtable_ops *ops, unsigned long iova, -- cgit v1.2.3 From 910c4406ccc9613de0a54abf910edc4bf8a575c0 Mon Sep 17 00:00:00 2001 From: "Isaac J. Manjarres" Date: Wed, 16 Jun 2021 06:38:45 -0700 Subject: iommu: Add a map_pages() op for IOMMU drivers Add a callback for IOMMU drivers to provide a path for the IOMMU framework to call into an IOMMU driver, which can call into the io-pgtable code, to map a physically contiguous rnage of pages of the same size. For IOMMU drivers that do not specify a map_pages() callback, the existing logic of mapping memory one page block at a time will be used. Signed-off-by: Isaac J. Manjarres Suggested-by: Will Deacon Acked-by: Lu Baolu Signed-off-by: Georgi Djakov Link: https://lore.kernel.org/r/1623850736-389584-5-git-send-email-quic_c_gdjako@quicinc.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 25a844121be5..d7989d4a7404 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -180,6 +180,8 @@ struct iommu_iotlb_gather { * @attach_dev: attach device to an iommu domain * @detach_dev: detach device from an iommu domain * @map: map a physically contiguous memory region to an iommu domain + * @map_pages: map a physically contiguous set of pages of the same size to + * an iommu domain. * @unmap: unmap a physically contiguous memory region from an iommu domain * @unmap_pages: unmap a number of pages of the same size from an iommu domain * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain @@ -230,6 +232,9 @@ struct iommu_ops { void (*detach_dev)(struct iommu_domain *domain, struct device *dev); int (*map)(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp); + int (*map_pages)(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova, -- cgit v1.2.3 From 308723e3580027f0cd7c86a5edfe6b5acb6863d2 Mon Sep 17 00:00:00 2001 From: John Garry Date: Mon, 12 Jul 2021 19:12:20 +0800 Subject: iommu: Remove mode argument from iommu_set_dma_strict() We only ever now set strict mode enabled in iommu_set_dma_strict(), so just remove the argument. Signed-off-by: John Garry Reviewed-by: Robin Murphy Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/1626088340-5838-7-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/init.c | 2 +- drivers/iommu/intel/iommu.c | 6 +++--- drivers/iommu/iommu.c | 5 ++--- include/linux/iommu.h | 2 +- 4 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 1e641cb6dddc..6e12a615117b 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3099,7 +3099,7 @@ static int __init parse_amd_iommu_options(char *str) for (; *str; ++str) { if (strncmp(str, "fullflush", 9) == 0) { pr_warn("amd_iommu=fullflush deprecated; use iommu.strict=1 instead\n"); - iommu_set_dma_strict(true); + iommu_set_dma_strict(); } if (strncmp(str, "force_enable", 12) == 0) amd_iommu_force_enable = true; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 6fd004a1a66d..da9afa730df1 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -454,7 +454,7 @@ static int __init intel_iommu_setup(char *str) iommu_dma_forcedac = true; } else if (!strncmp(str, "strict", 6)) { pr_warn("intel_iommu=strict deprecated; use iommu.strict=1 instead\n"); - iommu_set_dma_strict(true); + iommu_set_dma_strict(); } else if (!strncmp(str, "sp_off", 6)) { pr_info("Disable supported super page\n"); intel_iommu_superpage = 0; @@ -4394,7 +4394,7 @@ int __init intel_iommu_init(void) */ if (cap_caching_mode(iommu->cap)) { pr_info_once("IOMMU batching disallowed due to virtualization\n"); - iommu_set_dma_strict(true); + iommu_set_dma_strict(); } iommu_device_sysfs_add(&iommu->iommu, NULL, intel_iommu_groups, @@ -5712,7 +5712,7 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev) } else if (dmar_map_gfx) { /* we have to ensure the gfx device is idle before we flush */ pci_info(dev, "Disabling batched IOTLB flush on Ironlake\n"); - iommu_set_dma_strict(true); + iommu_set_dma_strict(); } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index bd9ccce387c5..eeea5e5c4d10 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -350,10 +350,9 @@ static int __init iommu_dma_setup(char *str) } early_param("iommu.strict", iommu_dma_setup); -void iommu_set_dma_strict(bool strict) +void iommu_set_dma_strict(void) { - if (strict || !(iommu_cmd_line & IOMMU_CMD_LINE_STRICT)) - iommu_dma_strict = strict; + iommu_dma_strict = true; } bool iommu_get_dma_strict(struct iommu_domain *domain) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d7989d4a7404..4997c78e2670 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -485,7 +485,7 @@ int iommu_enable_nesting(struct iommu_domain *domain); int iommu_set_pgtable_quirks(struct iommu_domain *domain, unsigned long quirks); -void iommu_set_dma_strict(bool val); +void iommu_set_dma_strict(void); bool iommu_get_dma_strict(struct iommu_domain *domain); extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, -- cgit v1.2.3 From 93d102f094be9beab28e5afb656c188b16a3793b Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 15 Jul 2021 21:39:56 +0206 Subject: printk: remove safe buffers With @logbuf_lock removed, the high level printk functions for storing messages are lockless. Messages can be stored from any context, so there is no need for the NMI and safe buffers anymore. Remove the NMI and safe buffers. Although the safe buffers are removed, the NMI and safe context tracking is still in place. In these contexts, store the message immediately but still use irq_work to defer the console printing. Since printk recursion tracking is in place, safe context tracking for most of printk is not needed. Remove it. Only safe context tracking relating to the console and console_owner locks is left in place. This is because the console and console_owner locks are needed for the actual printing. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210715193359.25946-4-john.ogness@linutronix.de --- arch/powerpc/kernel/traps.c | 1 - arch/powerpc/kernel/watchdog.c | 5 - include/linux/printk.h | 10 -- kernel/kexec_core.c | 1 - kernel/panic.c | 3 - kernel/printk/internal.h | 17 --- kernel/printk/printk.c | 120 ++++++--------- kernel/printk/printk_safe.c | 335 +---------------------------------------- lib/nmi_backtrace.c | 6 - 9 files changed, 48 insertions(+), 450 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index b4ab95c9e94a..2522800217d1 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -170,7 +170,6 @@ extern void panic_flush_kmsg_start(void) extern void panic_flush_kmsg_end(void) { - printk_safe_flush_on_panic(); kmsg_dump(KMSG_DUMP_PANIC); bust_spinlocks(0); debug_locks_off(); diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index c9a8f4781a10..dc17d8903d4f 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -183,11 +183,6 @@ static void watchdog_smp_panic(int cpu, u64 tb) wd_smp_unlock(&flags); - printk_safe_flush(); - /* - * printk_safe_flush() seems to require another print - * before anything actually goes out to console. - */ if (sysctl_hardlockup_all_cpu_backtrace) trigger_allbutself_cpu_backtrace(); diff --git a/include/linux/printk.h b/include/linux/printk.h index d796183f26c9..719d919f9b67 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -208,8 +208,6 @@ void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; -extern void printk_safe_flush(void); -extern void printk_safe_flush_on_panic(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -277,14 +275,6 @@ static inline void dump_stack_lvl(const char *log_lvl) static inline void dump_stack(void) { } - -static inline void printk_safe_flush(void) -{ -} - -static inline void printk_safe_flush_on_panic(void) -{ -} #endif #ifdef CONFIG_SMP diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index f099baee3578..69c6e9b7761c 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -978,7 +978,6 @@ void crash_kexec(struct pt_regs *regs) old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu); if (old_cpu == PANIC_CPU_INVALID) { /* This is the 1st CPU which comes here, so go ahead. */ - printk_safe_flush_on_panic(); __crash_kexec(regs); /* diff --git a/kernel/panic.c b/kernel/panic.c index 332736a72a58..1f0df42f8d0c 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -247,7 +247,6 @@ void panic(const char *fmt, ...) * Bypass the panic_cpu check and call __crash_kexec directly. */ if (!_crash_kexec_post_notifiers) { - printk_safe_flush_on_panic(); __crash_kexec(NULL); /* @@ -271,8 +270,6 @@ void panic(const char *fmt, ...) */ atomic_notifier_call_chain(&panic_notifier_list, 0, buf); - /* Call flush even twice. It tries harder with a single online CPU */ - printk_safe_flush_on_panic(); kmsg_dump(KMSG_DUMP_PANIC); /* diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 51615c909b2f..6cc35c5de890 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -22,7 +22,6 @@ __printf(1, 0) int vprintk_deferred(const char *fmt, va_list args); void __printk_safe_enter(void); void __printk_safe_exit(void); -void printk_safe_init(void); bool printk_percpu_data_ready(void); #define printk_safe_enter_irqsave(flags) \ @@ -37,18 +36,6 @@ bool printk_percpu_data_ready(void); local_irq_restore(flags); \ } while (0) -#define printk_safe_enter_irq() \ - do { \ - local_irq_disable(); \ - __printk_safe_enter(); \ - } while (0) - -#define printk_safe_exit_irq() \ - do { \ - __printk_safe_exit(); \ - local_irq_enable(); \ - } while (0) - void defer_console_output(void); #else @@ -61,9 +48,5 @@ void defer_console_output(void); #define printk_safe_enter_irqsave(flags) local_irq_save(flags) #define printk_safe_exit_irqrestore(flags) local_irq_restore(flags) -#define printk_safe_enter_irq() local_irq_disable() -#define printk_safe_exit_irq() local_irq_enable() - -static inline void printk_safe_init(void) { } static inline bool printk_percpu_data_ready(void) { return false; } #endif /* CONFIG_PRINTK */ diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 7fa0b4d91975..219ad710a9e8 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -732,27 +732,22 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, if (ret) return ret; - printk_safe_enter_irq(); if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; - printk_safe_exit_irq(); goto out; } - printk_safe_exit_irq(); ret = wait_event_interruptible(log_wait, prb_read_valid(prb, atomic64_read(&user->seq), r)); if (ret) goto out; - printk_safe_enter_irq(); } if (r->info->seq != atomic64_read(&user->seq)) { /* our last seen message is gone, return error and reset */ atomic64_set(&user->seq, r->info->seq); ret = -EPIPE; - printk_safe_exit_irq(); goto out; } @@ -762,7 +757,6 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, &r->info->dev_info); atomic64_set(&user->seq, r->info->seq + 1); - printk_safe_exit_irq(); if (len > count) { ret = -EINVAL; @@ -797,7 +791,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) if (offset) return -ESPIPE; - printk_safe_enter_irq(); switch (whence) { case SEEK_SET: /* the first record */ @@ -818,7 +811,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) default: ret = -EINVAL; } - printk_safe_exit_irq(); return ret; } @@ -833,7 +825,6 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait) poll_wait(file, &log_wait, wait); - printk_safe_enter_irq(); if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) { /* return error when data has vanished underneath us */ if (info.seq != atomic64_read(&user->seq)) @@ -841,7 +832,6 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait) else ret = EPOLLIN|EPOLLRDNORM; } - printk_safe_exit_irq(); return ret; } @@ -874,9 +864,7 @@ static int devkmsg_open(struct inode *inode, struct file *file) prb_rec_init_rd(&user->record, &user->info, &user->text_buf[0], sizeof(user->text_buf)); - printk_safe_enter_irq(); atomic64_set(&user->seq, prb_first_valid_seq(prb)); - printk_safe_exit_irq(); file->private_data = user; return 0; @@ -1042,9 +1030,6 @@ static inline void log_buf_add_cpu(void) {} static void __init set_percpu_data_ready(void) { - printk_safe_init(); - /* Make sure we set this flag only after printk_safe() init is done */ - barrier(); __printk_percpu_data_ready = true; } @@ -1082,6 +1067,7 @@ void __init setup_log_buf(int early) struct prb_desc *new_descs; struct printk_info info; struct printk_record r; + unsigned int text_size; size_t new_descs_size; size_t new_infos_size; unsigned long flags; @@ -1142,24 +1128,37 @@ void __init setup_log_buf(int early) new_descs, ilog2(new_descs_count), new_infos); - printk_safe_enter_irqsave(flags); + local_irq_save(flags); log_buf_len = new_log_buf_len; log_buf = new_log_buf; new_log_buf_len = 0; free = __LOG_BUF_LEN; - prb_for_each_record(0, &printk_rb_static, seq, &r) - free -= add_to_rb(&printk_rb_dynamic, &r); + prb_for_each_record(0, &printk_rb_static, seq, &r) { + text_size = add_to_rb(&printk_rb_dynamic, &r); + if (text_size > free) + free = 0; + else + free -= text_size; + } - /* - * This is early enough that everything is still running on the - * boot CPU and interrupts are disabled. So no new messages will - * appear during the transition to the dynamic buffer. - */ prb = &printk_rb_dynamic; - printk_safe_exit_irqrestore(flags); + local_irq_restore(flags); + + /* + * Copy any remaining messages that might have appeared from + * NMI context after copying but before switching to the + * dynamic buffer. + */ + prb_for_each_record(seq, &printk_rb_static, seq, &r) { + text_size = add_to_rb(&printk_rb_dynamic, &r); + if (text_size > free) + free = 0; + else + free -= text_size; + } if (seq != prb_next_seq(&printk_rb_static)) { pr_err("dropped %llu messages\n", @@ -1498,11 +1497,9 @@ static int syslog_print(char __user *buf, int size) size_t n; size_t skip; - printk_safe_enter_irq(); - raw_spin_lock(&syslog_lock); + raw_spin_lock_irq(&syslog_lock); if (!prb_read_valid(prb, syslog_seq, &r)) { - raw_spin_unlock(&syslog_lock); - printk_safe_exit_irq(); + raw_spin_unlock_irq(&syslog_lock); break; } if (r.info->seq != syslog_seq) { @@ -1531,8 +1528,7 @@ static int syslog_print(char __user *buf, int size) syslog_partial += n; } else n = 0; - raw_spin_unlock(&syslog_lock); - printk_safe_exit_irq(); + raw_spin_unlock_irq(&syslog_lock); if (!n) break; @@ -1566,7 +1562,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear) return -ENOMEM; time = printk_time; - printk_safe_enter_irq(); /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. @@ -1587,23 +1582,20 @@ static int syslog_print_all(char __user *buf, int size, bool clear) break; } - printk_safe_exit_irq(); if (copy_to_user(buf + len, text, textlen)) len = -EFAULT; else len += textlen; - printk_safe_enter_irq(); if (len < 0) break; } if (clear) { - raw_spin_lock(&syslog_lock); + raw_spin_lock_irq(&syslog_lock); latched_seq_write(&clear_seq, seq); - raw_spin_unlock(&syslog_lock); + raw_spin_unlock_irq(&syslog_lock); } - printk_safe_exit_irq(); kfree(text); return len; @@ -1611,11 +1603,9 @@ static int syslog_print_all(char __user *buf, int size, bool clear) static void syslog_clear(void) { - printk_safe_enter_irq(); - raw_spin_lock(&syslog_lock); + raw_spin_lock_irq(&syslog_lock); latched_seq_write(&clear_seq, prb_next_seq(prb)); - raw_spin_unlock(&syslog_lock); - printk_safe_exit_irq(); + raw_spin_unlock_irq(&syslog_lock); } /* Return a consistent copy of @syslog_seq. */ @@ -1703,12 +1693,10 @@ int do_syslog(int type, char __user *buf, int len, int source) break; /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: - printk_safe_enter_irq(); - raw_spin_lock(&syslog_lock); + raw_spin_lock_irq(&syslog_lock); if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) { /* No unread messages. */ - raw_spin_unlock(&syslog_lock); - printk_safe_exit_irq(); + raw_spin_unlock_irq(&syslog_lock); return 0; } if (info.seq != syslog_seq) { @@ -1736,8 +1724,7 @@ int do_syslog(int type, char __user *buf, int len, int source) } error -= syslog_partial; } - raw_spin_unlock(&syslog_lock); - printk_safe_exit_irq(); + raw_spin_unlock_irq(&syslog_lock); break; /* Size of the log buffer */ case SYSLOG_ACTION_SIZE_BUFFER: @@ -2219,7 +2206,6 @@ asmlinkage int vprintk_emit(int facility, int level, { int printed_len; bool in_sched = false; - unsigned long flags; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) @@ -2233,9 +2219,7 @@ asmlinkage int vprintk_emit(int facility, int level, boot_delay_msec(level); printk_delay(); - printk_safe_enter_irqsave(flags); printed_len = vprintk_store(facility, level, dev_info, fmt, args); - printk_safe_exit_irqrestore(flags); /* If called from the scheduler, we can not call up(). */ if (!in_sched) { @@ -2664,9 +2648,9 @@ again: for (;;) { size_t ext_len = 0; + int handover; size_t len; - printk_safe_enter_irqsave(flags); skip: if (!prb_read_valid(prb, console_seq, &r)) break; @@ -2716,19 +2700,22 @@ skip: * were to occur on another CPU, it may wait for this one to * finish. This task can not be preempted if there is a * waiter waiting to take over. + * + * Interrupts are disabled because the hand over to a waiter + * must not be interrupted until the hand over is completed + * (@console_waiter is cleared). */ + printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); stop_critical_timings(); /* don't trace print latency */ call_console_drivers(ext_text, ext_len, text, len); start_critical_timings(); - if (console_lock_spinning_disable_and_check()) { - printk_safe_exit_irqrestore(flags); - return; - } - + handover = console_lock_spinning_disable_and_check(); printk_safe_exit_irqrestore(flags); + if (handover) + return; if (do_cond_resched) cond_resched(); @@ -2745,8 +2732,6 @@ skip: * flush, no worries. */ retry = prb_read_valid(prb, console_seq, NULL); - printk_safe_exit_irqrestore(flags); - if (retry && console_trylock()) goto again; } @@ -2808,13 +2793,8 @@ void console_flush_on_panic(enum con_flush_mode mode) console_trylock(); console_may_schedule = 0; - if (mode == CONSOLE_REPLAY_ALL) { - unsigned long flags; - - printk_safe_enter_irqsave(flags); + if (mode == CONSOLE_REPLAY_ALL) console_seq = prb_first_valid_seq(prb); - printk_safe_exit_irqrestore(flags); - } console_unlock(); } @@ -3466,14 +3446,12 @@ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, struct printk_info info; unsigned int line_count; struct printk_record r; - unsigned long flags; size_t l = 0; bool ret = false; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; - printk_safe_enter_irqsave(flags); prb_rec_init_rd(&r, &info, line, size); /* Read text or count text lines? */ @@ -3494,7 +3472,6 @@ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, iter->cur_seq = r.info->seq + 1; ret = true; out: - printk_safe_exit_irqrestore(flags); if (len) *len = l; return ret; @@ -3526,7 +3503,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; struct printk_record r; - unsigned long flags; u64 seq; u64 next_seq; size_t len = 0; @@ -3539,7 +3515,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; - printk_safe_enter_irqsave(flags); if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) { if (info.seq != iter->cur_seq) { /* messages are gone, move to first available one */ @@ -3548,10 +3523,8 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, } /* last entry */ - if (iter->cur_seq >= iter->next_seq) { - printk_safe_exit_irqrestore(flags); + if (iter->cur_seq >= iter->next_seq) goto out; - } /* * Find first record that fits, including all following records, @@ -3583,7 +3556,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, iter->next_seq = next_seq; ret = true; - printk_safe_exit_irqrestore(flags); out: if (len_out) *len_out = len; @@ -3601,12 +3573,8 @@ EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); */ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) { - unsigned long flags; - - printk_safe_enter_irqsave(flags); iter->cur_seq = latched_seq_read_nolock(&clear_seq); iter->next_seq = prb_next_seq(prb); - printk_safe_exit_irqrestore(flags); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 94232186fccb..29c580dac93d 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -15,286 +15,9 @@ #include "internal.h" -/* - * In NMI and safe mode, printk() avoids taking locks. Instead, - * it uses an alternative implementation that temporary stores - * the strings into a per-CPU buffer. The content of the buffer - * is later flushed into the main ring buffer via IRQ work. - * - * The alternative implementation is chosen transparently - * by examining current printk() context mask stored in @printk_context - * per-CPU variable. - * - * The implementation allows to flush the strings also from another CPU. - * There are situations when we want to make sure that all buffers - * were handled or when IRQs are blocked. - */ - -#define SAFE_LOG_BUF_LEN ((1 << CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT) - \ - sizeof(atomic_t) - \ - sizeof(atomic_t) - \ - sizeof(struct irq_work)) - -struct printk_safe_seq_buf { - atomic_t len; /* length of written data */ - atomic_t message_lost; - struct irq_work work; /* IRQ work that flushes the buffer */ - unsigned char buffer[SAFE_LOG_BUF_LEN]; -}; - -static DEFINE_PER_CPU(struct printk_safe_seq_buf, safe_print_seq); static DEFINE_PER_CPU(int, printk_context); -static DEFINE_RAW_SPINLOCK(safe_read_lock); - -#ifdef CONFIG_PRINTK_NMI -static DEFINE_PER_CPU(struct printk_safe_seq_buf, nmi_print_seq); -#endif - -/* Get flushed in a more safe context. */ -static void queue_flush_work(struct printk_safe_seq_buf *s) -{ - if (printk_percpu_data_ready()) - irq_work_queue(&s->work); -} - -/* - * Add a message to per-CPU context-dependent buffer. NMI and printk-safe - * have dedicated buffers, because otherwise printk-safe preempted by - * NMI-printk would have overwritten the NMI messages. - * - * The messages are flushed from irq work (or from panic()), possibly, - * from other CPU, concurrently with printk_safe_log_store(). Should this - * happen, printk_safe_log_store() will notice the buffer->len mismatch - * and repeat the write. - */ -static __printf(2, 0) int printk_safe_log_store(struct printk_safe_seq_buf *s, - const char *fmt, va_list args) -{ - int add; - size_t len; - va_list ap; - -again: - len = atomic_read(&s->len); - - /* The trailing '\0' is not counted into len. */ - if (len >= sizeof(s->buffer) - 1) { - atomic_inc(&s->message_lost); - queue_flush_work(s); - return 0; - } - - /* - * Make sure that all old data have been read before the buffer - * was reset. This is not needed when we just append data. - */ - if (!len) - smp_rmb(); - - va_copy(ap, args); - add = vscnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, ap); - va_end(ap); - if (!add) - return 0; - - /* - * Do it once again if the buffer has been flushed in the meantime. - * Note that atomic_cmpxchg() is an implicit memory barrier that - * makes sure that the data were written before updating s->len. - */ - if (atomic_cmpxchg(&s->len, len, len + add) != len) - goto again; - - queue_flush_work(s); - return add; -} - -static inline void printk_safe_flush_line(const char *text, int len) -{ - /* - * Avoid any console drivers calls from here, because we may be - * in NMI or printk_safe context (when in panic). The messages - * must go only into the ring buffer at this stage. Consoles will - * get explicitly called later when a crashdump is not generated. - */ - printk_deferred("%.*s", len, text); -} - -/* printk part of the temporary buffer line by line */ -static int printk_safe_flush_buffer(const char *start, size_t len) -{ - const char *c, *end; - bool header; - - c = start; - end = start + len; - header = true; - - /* Print line by line. */ - while (c < end) { - if (*c == '\n') { - printk_safe_flush_line(start, c - start + 1); - start = ++c; - header = true; - continue; - } - - /* Handle continuous lines or missing new line. */ - if ((c + 1 < end) && printk_get_level(c)) { - if (header) { - c = printk_skip_level(c); - continue; - } - - printk_safe_flush_line(start, c - start); - start = c++; - header = true; - continue; - } - - header = false; - c++; - } - - /* Check if there was a partial line. Ignore pure header. */ - if (start < end && !header) { - static const char newline[] = KERN_CONT "\n"; - - printk_safe_flush_line(start, end - start); - printk_safe_flush_line(newline, strlen(newline)); - } - - return len; -} - -static void report_message_lost(struct printk_safe_seq_buf *s) -{ - int lost = atomic_xchg(&s->message_lost, 0); - - if (lost) - printk_deferred("Lost %d message(s)!\n", lost); -} - -/* - * Flush data from the associated per-CPU buffer. The function - * can be called either via IRQ work or independently. - */ -static void __printk_safe_flush(struct irq_work *work) -{ - struct printk_safe_seq_buf *s = - container_of(work, struct printk_safe_seq_buf, work); - unsigned long flags; - size_t len; - int i; - - /* - * The lock has two functions. First, one reader has to flush all - * available message to make the lockless synchronization with - * writers easier. Second, we do not want to mix messages from - * different CPUs. This is especially important when printing - * a backtrace. - */ - raw_spin_lock_irqsave(&safe_read_lock, flags); - - i = 0; -more: - len = atomic_read(&s->len); - - /* - * This is just a paranoid check that nobody has manipulated - * the buffer an unexpected way. If we printed something then - * @len must only increase. Also it should never overflow the - * buffer size. - */ - if ((i && i >= len) || len > sizeof(s->buffer)) { - const char *msg = "printk_safe_flush: internal error\n"; - - printk_safe_flush_line(msg, strlen(msg)); - len = 0; - } - - if (!len) - goto out; /* Someone else has already flushed the buffer. */ - - /* Make sure that data has been written up to the @len */ - smp_rmb(); - i += printk_safe_flush_buffer(s->buffer + i, len - i); - - /* - * Check that nothing has got added in the meantime and truncate - * the buffer. Note that atomic_cmpxchg() is an implicit memory - * barrier that makes sure that the data were copied before - * updating s->len. - */ - if (atomic_cmpxchg(&s->len, len, 0) != len) - goto more; - -out: - report_message_lost(s); - raw_spin_unlock_irqrestore(&safe_read_lock, flags); -} - -/** - * printk_safe_flush - flush all per-cpu nmi buffers. - * - * The buffers are flushed automatically via IRQ work. This function - * is useful only when someone wants to be sure that all buffers have - * been flushed at some point. - */ -void printk_safe_flush(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { -#ifdef CONFIG_PRINTK_NMI - __printk_safe_flush(&per_cpu(nmi_print_seq, cpu).work); -#endif - __printk_safe_flush(&per_cpu(safe_print_seq, cpu).work); - } -} - -/** - * printk_safe_flush_on_panic - flush all per-cpu nmi buffers when the system - * goes down. - * - * Similar to printk_safe_flush() but it can be called even in NMI context when - * the system goes down. It does the best effort to get NMI messages into - * the main ring buffer. - * - * Note that it could try harder when there is only one CPU online. - */ -void printk_safe_flush_on_panic(void) -{ - /* - * Make sure that we could access the safe buffers. - * Do not risk a double release when more CPUs are up. - */ - if (raw_spin_is_locked(&safe_read_lock)) { - if (num_online_cpus() > 1) - return; - - debug_locks_off(); - raw_spin_lock_init(&safe_read_lock); - } - - printk_safe_flush(); -} - #ifdef CONFIG_PRINTK_NMI -/* - * Safe printk() for NMI context. It uses a per-CPU buffer to - * store the message. NMIs are not nested, so there is always only - * one writer running. But the buffer might get flushed from another - * CPU, so we need to be careful. - */ -static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) -{ - struct printk_safe_seq_buf *s = this_cpu_ptr(&nmi_print_seq); - - return printk_safe_log_store(s, fmt, args); -} - void noinstr printk_nmi_enter(void) { this_cpu_add(printk_context, PRINTK_NMI_CONTEXT_OFFSET); @@ -309,9 +32,6 @@ void noinstr printk_nmi_exit(void) * Marks a code that might produce many messages in NMI context * and the risk of losing them is more critical than eventual * reordering. - * - * It has effect only when called in NMI context. Then printk() - * will store the messages into the main logbuf directly. */ void printk_nmi_direct_enter(void) { @@ -324,27 +44,8 @@ void printk_nmi_direct_exit(void) this_cpu_and(printk_context, ~PRINTK_NMI_DIRECT_CONTEXT_MASK); } -#else - -static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) -{ - return 0; -} - #endif /* CONFIG_PRINTK_NMI */ -/* - * Lock-less printk(), to avoid deadlocks should the printk() recurse - * into itself. It uses a per-CPU buffer to store the message, just like - * NMI. - */ -static __printf(1, 0) int vprintk_safe(const char *fmt, va_list args) -{ - struct printk_safe_seq_buf *s = this_cpu_ptr(&safe_print_seq); - - return printk_safe_log_store(s, fmt, args); -} - /* Can be preempted by NMI. */ void __printk_safe_enter(void) { @@ -369,46 +70,18 @@ asmlinkage int vprintk(const char *fmt, va_list args) * Use the main logbuf even in NMI. But avoid calling console * drivers that might have their own locks. */ - if ((this_cpu_read(printk_context) & PRINTK_NMI_DIRECT_CONTEXT_MASK)) { - unsigned long flags; + if (this_cpu_read(printk_context) & + (PRINTK_NMI_DIRECT_CONTEXT_MASK | + PRINTK_NMI_CONTEXT_MASK | + PRINTK_SAFE_CONTEXT_MASK)) { int len; - printk_safe_enter_irqsave(flags); len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args); - printk_safe_exit_irqrestore(flags); defer_console_output(); return len; } - /* Use extra buffer in NMI. */ - if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK) - return vprintk_nmi(fmt, args); - - /* Use extra buffer to prevent a recursion deadlock in safe mode. */ - if (this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK) - return vprintk_safe(fmt, args); - /* No obstacles. */ return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); - -void __init printk_safe_init(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct printk_safe_seq_buf *s; - - s = &per_cpu(safe_print_seq, cpu); - init_irq_work(&s->work, __printk_safe_flush); - -#ifdef CONFIG_PRINTK_NMI - s = &per_cpu(nmi_print_seq, cpu); - init_irq_work(&s->work, __printk_safe_flush); -#endif - } - - /* Flush pending messages that did not have scheduled IRQ works. */ - printk_safe_flush(); -} diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index dae233c5f597..9813a983d024 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -75,12 +75,6 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, touch_softlockup_watchdog(); } - /* - * Force flush any remote buffers that might be stuck in IRQ context - * and therefore could not run their irq_work. - */ - printk_safe_flush(); - clear_bit_unlock(0, &backtrace_flag); put_cpu(); } -- cgit v1.2.3 From 85e3e7fbbb720b9897fba9a99659e31cbd1c082e Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 15 Jul 2021 21:39:57 +0206 Subject: printk: remove NMI tracking All NMI contexts are handled the same as the safe context: store the message and defer printing. There is no need to have special NMI context tracking for this. Using in_nmi() is enough. There are several parts of the kernel that are manually calling into the printk NMI context tracking in order to cause general printk deferred printing: arch/arm/kernel/smp.c arch/powerpc/kexec/crash.c kernel/trace/trace.c For arm/kernel/smp.c and powerpc/kexec/crash.c, provide a new function pair printk_deferred_enter/exit that explicitly achieves the same objective. For ftrace, remove the printk context manipulation completely. It was added in commit 03fc7f9c99c1 ("printk/nmi: Prevent deadlock when accessing the main log buffer in NMI"). The purpose was to enforce storing messages directly into the ring buffer even in NMI context. It really should have only modified the behavior in NMI context. There is no need for a special behavior any longer. All messages are always stored directly now. The console deferring is handled transparently in vprintk(). Signed-off-by: John Ogness [pmladek@suse.com: Remove special handling in ftrace.c completely. Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210715193359.25946-5-john.ogness@linutronix.de --- arch/arm/kernel/smp.c | 4 ++-- arch/powerpc/kexec/crash.c | 2 +- include/linux/hardirq.h | 2 -- include/linux/printk.h | 31 +++++++++++++++++++------------ init/Kconfig | 5 ----- kernel/printk/internal.h | 8 -------- kernel/printk/printk_safe.c | 37 +------------------------------------ kernel/trace/trace.c | 2 -- 8 files changed, 23 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index c7bb168b0d97..842427ff2b3c 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -667,9 +667,9 @@ static void do_handle_IPI(int ipinr) break; case IPI_CPU_BACKTRACE: - printk_nmi_enter(); + printk_deferred_enter(); nmi_cpu_backtrace(get_irq_regs()); - printk_nmi_exit(); + printk_deferred_exit(); break; default: diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index 0196d0c211ac..1070378c8e35 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -313,7 +313,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs) int (*old_handler)(struct pt_regs *regs); /* Avoid hardlocking with irresponsive CPU holding logbuf_lock */ - printk_nmi_enter(); + printk_deferred_enter(); /* * This function is only called after the system diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 69bc86ea382c..76878b357ffa 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -116,7 +116,6 @@ extern void rcu_nmi_exit(void); do { \ lockdep_off(); \ arch_nmi_enter(); \ - printk_nmi_enter(); \ BUG_ON(in_nmi() == NMI_MASK); \ __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ } while (0) @@ -135,7 +134,6 @@ extern void rcu_nmi_exit(void); do { \ BUG_ON(!in_nmi()); \ __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ - printk_nmi_exit(); \ arch_nmi_exit(); \ lockdep_on(); \ } while (0) diff --git a/include/linux/printk.h b/include/linux/printk.h index 719d919f9b67..a1379df43251 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -149,18 +149,6 @@ static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } #endif -#ifdef CONFIG_PRINTK_NMI -extern void printk_nmi_enter(void); -extern void printk_nmi_exit(void); -extern void printk_nmi_direct_enter(void); -extern void printk_nmi_direct_exit(void); -#else -static inline void printk_nmi_enter(void) { } -static inline void printk_nmi_exit(void) { } -static inline void printk_nmi_direct_enter(void) { } -static inline void printk_nmi_direct_exit(void) { } -#endif /* PRINTK_NMI */ - struct dev_printk_info; #ifdef CONFIG_PRINTK @@ -180,6 +168,16 @@ int printk(const char *fmt, ...); */ __printf(1, 2) __cold int printk_deferred(const char *fmt, ...); +extern void __printk_safe_enter(void); +extern void __printk_safe_exit(void); +/* + * The printk_deferred_enter/exit macros are available only as a hack for + * some code paths that need to defer all printk console printing. Interrupts + * must be disabled for the deferred duration. + */ +#define printk_deferred_enter __printk_safe_enter +#define printk_deferred_exit __printk_safe_exit + /* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use @@ -224,6 +222,15 @@ int printk_deferred(const char *s, ...) { return 0; } + +static inline void printk_deferred_enter(void) +{ +} + +static inline void printk_deferred_exit(void) +{ +} + static inline int printk_ratelimit(void) { return 0; diff --git a/init/Kconfig b/init/Kconfig index a61c92066c2e..9c0510693543 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1506,11 +1506,6 @@ config PRINTK very difficult to diagnose system problems, saying N here is strongly discouraged. -config PRINTK_NMI - def_bool y - depends on PRINTK - depends on HAVE_NMI - config BUG bool "BUG() support" if EXPERT default y diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 6cc35c5de890..b6d310c72fc9 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -6,12 +6,6 @@ #ifdef CONFIG_PRINTK -#define PRINTK_SAFE_CONTEXT_MASK 0x007ffffff -#define PRINTK_NMI_DIRECT_CONTEXT_MASK 0x008000000 -#define PRINTK_NMI_CONTEXT_MASK 0xff0000000 - -#define PRINTK_NMI_CONTEXT_OFFSET 0x010000000 - __printf(4, 0) int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, @@ -19,8 +13,6 @@ int vprintk_store(int facility, int level, __printf(1, 0) int vprintk_default(const char *fmt, va_list args); __printf(1, 0) int vprintk_deferred(const char *fmt, va_list args); -void __printk_safe_enter(void); -void __printk_safe_exit(void); bool printk_percpu_data_ready(void); diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 29c580dac93d..ef0f9a2044da 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -4,12 +4,9 @@ */ #include -#include -#include #include #include #include -#include #include #include @@ -17,35 +14,6 @@ static DEFINE_PER_CPU(int, printk_context); -#ifdef CONFIG_PRINTK_NMI -void noinstr printk_nmi_enter(void) -{ - this_cpu_add(printk_context, PRINTK_NMI_CONTEXT_OFFSET); -} - -void noinstr printk_nmi_exit(void) -{ - this_cpu_sub(printk_context, PRINTK_NMI_CONTEXT_OFFSET); -} - -/* - * Marks a code that might produce many messages in NMI context - * and the risk of losing them is more critical than eventual - * reordering. - */ -void printk_nmi_direct_enter(void) -{ - if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK) - this_cpu_or(printk_context, PRINTK_NMI_DIRECT_CONTEXT_MASK); -} - -void printk_nmi_direct_exit(void) -{ - this_cpu_and(printk_context, ~PRINTK_NMI_DIRECT_CONTEXT_MASK); -} - -#endif /* CONFIG_PRINTK_NMI */ - /* Can be preempted by NMI. */ void __printk_safe_enter(void) { @@ -70,10 +38,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) * Use the main logbuf even in NMI. But avoid calling console * drivers that might have their own locks. */ - if (this_cpu_read(printk_context) & - (PRINTK_NMI_DIRECT_CONTEXT_MASK | - PRINTK_NMI_CONTEXT_MASK | - PRINTK_SAFE_CONTEXT_MASK)) { + if (this_cpu_read(printk_context) || in_nmi()) { int len; len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d23a09d3eb37..2f41311c61d7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9647,7 +9647,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) tracing_off(); local_irq_save(flags); - printk_nmi_direct_enter(); /* Simulate the iterator */ trace_init_global_iter(&iter); @@ -9729,7 +9728,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); } atomic_dec(&dump_running); - printk_nmi_direct_exit(); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(ftrace_dump); -- cgit v1.2.3 From 26ab7b384525ccfa678c518577f7f0d841209c8b Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Fri, 23 Apr 2021 20:34:48 +0300 Subject: net/mlx5e: Block LRO if firmware asks for tunneled LRO This commit does a cleanup in LRO configuration. LRO is a parameter of an RQ, but its state is changed by modifying a TIR related to the RQ. The current status: LRO for tunneled packets is not supported in the driver, inner TIRs may enable LRO on creation, but LRO status of inner TIRs isn't changed in mlx5e_modify_tirs_lro(). This is inconsistent, but as long as the firmware doesn't declare support for tunneled LRO, it works, because the same RQs are shared between the inner and outer TIRs. This commit does two fixes: 1. If the firmware has the tunneled LRO capability, LRO is blocked altogether, because it's not possible to block it for inner TIRs only, when the same RQs are shared between inner and outer TIRs, and the driver won't be able to handle tunneled LRO traffic. 2. mlx5e_modify_tirs_lro() is patched to modify LRO state for all TIRs, including inner ones, because all TIRs related to an RQ should agree on their LRO state. Fixes: 7b3722fa9ef6 ("net/mlx5e: Support RSS for GRE tunneled packets") Signed-off-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 +++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 3 ++- 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d09e65557e75..b651134b0f6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2576,6 +2576,14 @@ static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in); if (err) goto free_in; + + /* Verify inner tirs resources allocated */ + if (!priv->inner_indir_tir[0].tirn) + continue; + + err = mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in); + if (err) + goto free_in; } for (ix = 0; ix < priv->max_nch; ix++) { @@ -4808,7 +4816,14 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_enc_features |= NETIF_F_HW_VLAN_CTAG_TX; netdev->hw_enc_features |= NETIF_F_HW_VLAN_CTAG_RX; + /* Tunneled LRO is not supported in the driver, and the same RQs are + * shared between inner and outer TIRs, so the driver can't disable LRO + * for inner TIRs while having it enabled for outer TIRs. Due to this, + * block LRO altogether if the firmware declares tunneled LRO support. + */ if (!!MLX5_CAP_ETH(mdev, lro_cap) && + !MLX5_CAP_ETH(mdev, tunnel_lro_vxlan) && + !MLX5_CAP_ETH(mdev, tunnel_lro_gre) && mlx5e_check_fragmented_striding_rq_cap(mdev)) netdev->vlan_features |= NETIF_F_LRO; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b0009aa3647f..6bbae0c3bc0b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -921,7 +921,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 scatter_fcs[0x1]; u8 enhanced_multi_pkt_send_wqe[0x1]; u8 tunnel_lso_const_out_ip_id[0x1]; - u8 reserved_at_1c[0x2]; + u8 tunnel_lro_gre[0x1]; + u8 tunnel_lro_vxlan[0x1]; u8 tunnel_stateless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; -- cgit v1.2.3 From ee80dd2e89ecce9c5dd6f556b8f581c9e1cbb605 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 26 Jul 2021 19:55:29 +0300 Subject: net: bridge: add a helper for retrieving port VLANs from the data path Introduce a brother of br_vlan_get_info() which is protected by the RCU mechanism, as opposed to br_vlan_get_info() which relies on taking the write-side rtnl_mutex. This is needed for drivers which need to find out whether a bridge port has a VLAN configured or not. For example, certain DSA switches might not offer complete source port identification to the CPU on RX, just the VLAN in which the packet was received. Based on this VLAN, we cannot set an accurate skb->dev ingress port, but at least we can configure one that behaves the same as the correct one would (this is possible because DSA sets skb->offload_fwd_mark = 1). When we look at the bridge RX handler (br_handle_frame), we see that what matters regarding skb->dev is the VLAN ID and the port STP state. So we need to select an skb->dev that has the same bridge VLAN as the packet we're receiving, and is in the LEARNING or FORWARDING STP state. The latter is easy, but for the former, we should somehow keep a shadow list of the bridge VLANs on each port, and a lookup table between VLAN ID and the 'designated port for imprecise RX'. That is rather complicated to keep in sync properly (the designated port per VLAN needs to be updated on the addition and removal of a VLAN, as well as on the join/leave events of the bridge on that port). So, to avoid all that complexity, let's just iterate through our finite number of ports and ask the bridge, for each packet: "do you have this VLAN configured on this port?". Cc: Roopa Prabhu Cc: Nikolay Aleksandrov Cc: Ido Schimmel Cc: Jiri Pirko Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 8 ++++++++ net/bridge/br_vlan.c | 27 +++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index f0b4ffbd8582..b73b4ff749e1 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -111,6 +111,8 @@ int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid); int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); +int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -137,6 +139,12 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, { return -EINVAL; } + +static inline int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo) +{ + return -EINVAL; +} #endif #if IS_ENABLED(CONFIG_BRIDGE) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 805206f31795..8cfd035bbaf9 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1449,6 +1449,33 @@ int br_vlan_get_info(const struct net_device *dev, u16 vid, } EXPORT_SYMBOL_GPL(br_vlan_get_info); +int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + struct net_bridge_port *p; + + p = br_port_get_check_rcu(dev); + if (p) + vg = nbp_vlan_group_rcu(p); + else if (netif_is_bridge_master(dev)) + vg = br_vlan_group_rcu(netdev_priv(dev)); + else + return -EINVAL; + + v = br_vlan_find(vg, vid); + if (!v) + return -ENOENT; + + p_vinfo->vid = vid; + p_vinfo->flags = v->flags; + if (vid == br_get_pvid(vg)) + p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; + return 0; +} +EXPORT_SYMBOL_GPL(br_vlan_get_info_rcu); + static int br_vlan_is_bind_vlan_dev(const struct net_device *dev) { return is_vlan_dev(dev) && -- cgit v1.2.3 From b6ad86e6ad6c46e52cac218e62613c6c47cf7fa0 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 26 Jul 2021 19:55:35 +0300 Subject: net: dsa: sja1105: add bridge TX data plane offload based on tag_8021q The main desire for having this feature in sja1105 is to support network stack termination for traffic coming from a VLAN-aware bridge. For sja1105, offloading the bridge data plane means sending packets as-is, with the proper VLAN tag, to the chip. The chip will look up its FDB and forward them to the correct destination port. But we support bridge data plane offload even for VLAN-unaware bridges, and the implementation there is different. In fact, VLAN-unaware bridging is governed by tag_8021q, so it makes sense to have the .bridge_fwd_offload_add() implementation fully within tag_8021q. The key difference is that we only support 1 VLAN-aware bridge, but we support multiple VLAN-unaware bridges. So we need to make sure that the forwarding domain is not crossed by packets injected from the stack. For this, we introduce the concept of a tag_8021q TX VLAN for bridge forwarding offload. As opposed to the regular TX VLANs which contain only 2 ports (the user port and the CPU port), a bridge data plane TX VLAN is "multicast" (or "imprecise"): it contains all the ports that are part of a certain bridge, and the hardware will select where the packet goes within this "imprecise" forwarding domain. Each VLAN-unaware bridge has its own "imprecise" TX VLAN, so we make use of the unique "bridge_num" provided by DSA for the data plane offload. We use the same 3 bits from the tag_8021q VLAN ID format to encode this bridge number. Note that these 3 bit positions have been used before for sub-VLANs in best-effort VLAN filtering mode. The difference is that for best-effort, the sub-VLANs were only valid on RX (and it was documented that the sub-VLAN field needed to be transmitted as zero). Whereas for the bridge data plane offload, these 3 bits are only valid on TX. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 4 +++ include/linux/dsa/8021q.h | 10 +++++++ net/dsa/tag_8021q.c | 48 +++++++++++++++++++++++++++++++--- net/dsa/tag_sja1105.c | 31 ++++++++++++++++++++++ 4 files changed, 89 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index a6a671f0fca5..da042e211dda 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2367,6 +2367,8 @@ static int sja1105_setup(struct dsa_switch *ds) */ ds->vlan_filtering_is_global = true; ds->untag_bridge_pvid = true; + /* tag_8021q has 3 bits for the VBID, and the value 0 is reserved */ + ds->num_fwd_offloading_bridges = 7; /* Advertise the 8 egress queues */ ds->num_tx_queues = SJA1105_NUM_TC; @@ -2880,6 +2882,8 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .tag_8021q_vlan_add = sja1105_dsa_8021q_vlan_add, .tag_8021q_vlan_del = sja1105_dsa_8021q_vlan_del, .port_prechangeupper = sja1105_prechangeupper, + .port_bridge_tx_fwd_offload = dsa_tag_8021q_bridge_tx_fwd_offload, + .port_bridge_tx_fwd_unoffload = dsa_tag_8021q_bridge_tx_fwd_unoffload, }; static const struct of_device_id sja1105_dt_ids[]; diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index ec5abfcdefd1..c7fa4a3498fe 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -35,6 +35,16 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); +int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, + struct net_device *br, + int bridge_num); + +void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, + struct net_device *br, + int bridge_num); + +u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num); + u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 51dcde7db26b..654697ebb6f3 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -17,7 +17,7 @@ * * | 11 | 10 | 9 | 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 | * +-----------+-----+-----------------+-----------+-----------------------+ - * | DIR | RSV | SWITCH_ID | RSV | PORT | + * | DIR | VBID| SWITCH_ID | VBID | PORT | * +-----------+-----+-----------------+-----------+-----------------------+ * * DIR - VID[11:10]: @@ -30,9 +30,10 @@ * SWITCH_ID - VID[8:6]: * Index of switch within DSA tree. Must be between 0 and 7. * - * RSV - VID[5:4]: - * To be used for further expansion of PORT or for other purposes. - * Must be transmitted as zero and ignored on receive. + * VBID - { VID[9], VID[5:4] }: + * Virtual bridge ID. If between 1 and 7, packet targets the broadcast + * domain of a bridge. If transmitted as zero, packet targets a single + * port. Field only valid on transmit, must be ignored on receive. * * PORT - VID[3:0]: * Index of switch port. Must be between 0 and 15. @@ -50,11 +51,30 @@ #define DSA_8021Q_SWITCH_ID(x) (((x) << DSA_8021Q_SWITCH_ID_SHIFT) & \ DSA_8021Q_SWITCH_ID_MASK) +#define DSA_8021Q_VBID_HI_SHIFT 9 +#define DSA_8021Q_VBID_HI_MASK GENMASK(9, 9) +#define DSA_8021Q_VBID_LO_SHIFT 4 +#define DSA_8021Q_VBID_LO_MASK GENMASK(5, 4) +#define DSA_8021Q_VBID_HI(x) (((x) & GENMASK(2, 2)) >> 2) +#define DSA_8021Q_VBID_LO(x) ((x) & GENMASK(1, 0)) +#define DSA_8021Q_VBID(x) \ + (((DSA_8021Q_VBID_LO(x) << DSA_8021Q_VBID_LO_SHIFT) & \ + DSA_8021Q_VBID_LO_MASK) | \ + ((DSA_8021Q_VBID_HI(x) << DSA_8021Q_VBID_HI_SHIFT) & \ + DSA_8021Q_VBID_HI_MASK)) + #define DSA_8021Q_PORT_SHIFT 0 #define DSA_8021Q_PORT_MASK GENMASK(3, 0) #define DSA_8021Q_PORT(x) (((x) << DSA_8021Q_PORT_SHIFT) & \ DSA_8021Q_PORT_MASK) +u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num) +{ + /* The VBID value of 0 is reserved for precise TX */ + return DSA_8021Q_DIR_TX | DSA_8021Q_VBID(bridge_num + 1); +} +EXPORT_SYMBOL_GPL(dsa_8021q_bridge_tx_fwd_offload_vid); + /* Returns the VID to be inserted into the frame from xmit for switch steering * instructions on egress. Encodes switch ID and port ID. */ @@ -387,6 +407,26 @@ int dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, return 0; } +int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, + struct net_device *br, + int bridge_num) +{ + u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); + + return dsa_port_tag_8021q_vlan_add(dsa_to_port(ds, port), tx_vid); +} +EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_tx_fwd_offload); + +void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, + struct net_device *br, + int bridge_num) +{ + u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); + + dsa_port_tag_8021q_vlan_del(dsa_to_port(ds, port), tx_vid); +} +EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_tx_fwd_unoffload); + /* Set up a port's tag_8021q RX and TX VLAN for standalone mode operation */ static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) { diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index f142a933c5e2..cddee4b499d8 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -133,6 +133,31 @@ static u16 sja1105_xmit_tpid(struct sja1105_port *sp) return sp->xmit_tpid; } +static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + struct net_device *br = dp->bridge_dev; + u16 tx_vid; + + /* If the port is under a VLAN-aware bridge, just slide the + * VLAN-tagged packet into the FDB and hope for the best. + * This works because we support a single VLAN-aware bridge + * across the entire dst, and its VLANs cannot be shared with + * any standalone port. + */ + if (br_vlan_enabled(br)) + return skb; + + /* If the port is under a VLAN-unaware bridge, use an imprecise + * TX VLAN that targets the bridge's entire broadcast domain, + * instead of just the specific port. + */ + tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(dp->bridge_num); + + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), tx_vid); +} + static struct sk_buff *sja1105_xmit(struct sk_buff *skb, struct net_device *netdev) { @@ -141,6 +166,9 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + if (skb->offload_fwd_mark) + return sja1105_imprecise_xmit(skb, netdev); + /* Transmitting management traffic does not rely upon switch tagging, * but instead SPI-installed management routes. Part 2 of this * is the .port_deferred_xmit driver callback. @@ -165,6 +193,9 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb, __be16 *tx_header; int trailer_pos; + if (skb->offload_fwd_mark) + return sja1105_imprecise_xmit(skb, netdev); + /* Transmitting control packets is done using in-band control * extensions, while data packets are transmitted using * tag_8021q TX VLANs. -- cgit v1.2.3 From 895adbec302e92086359e6fd92611ac3be6d92c3 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Fri, 16 Jul 2021 17:28:18 +0800 Subject: kernfs: add a revision to identify directory node changes Add a revision counter to kernfs directory nodes so it can be used to detect if a directory node has changed during negative dentry revalidation. There's an assumption that sizeof(unsigned long) <= sizeof(pointer) on all architectures and as far as I know that assumption holds. So adding a revision counter to the struct kernfs_elem_dir variant of the kernfs_node type union won't increase the size of the kernfs_node struct. This is because struct kernfs_elem_dir is at least sizeof(pointer) smaller than the largest union variant. It's tempting to make the revision counter a u64 but that would increase the size of kernfs_node on archs where sizeof(pointer) is smaller than the revision counter. Reviewed-by: Miklos Szeredi Signed-off-by: Ian Kent Link: https://lore.kernel.org/r/162642769895.63632.8356662784964509867.stgit@web.messagingengine.com Signed-off-by: Greg Kroah-Hartman --- fs/kernfs/dir.c | 2 ++ fs/kernfs/kernfs-internal.h | 19 +++++++++++++++++++ include/linux/kernfs.h | 5 +++++ 3 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 33166ec90a11..b3d1bc0f317d 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -372,6 +372,7 @@ static int kernfs_link_sibling(struct kernfs_node *kn) /* successfully added, account subdir number */ if (kernfs_type(kn) == KERNFS_DIR) kn->parent->dir.subdirs++; + kernfs_inc_rev(kn->parent); return 0; } @@ -394,6 +395,7 @@ static bool kernfs_unlink_sibling(struct kernfs_node *kn) if (kernfs_type(kn) == KERNFS_DIR) kn->parent->dir.subdirs--; + kernfs_inc_rev(kn->parent); rb_erase(&kn->rb, &kn->parent->dir.children); RB_CLEAR_NODE(&kn->rb); diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index ccc3b44f6306..c2ae58f3b202 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -81,6 +81,25 @@ static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) return d_inode(dentry)->i_private; } +static inline void kernfs_set_rev(struct kernfs_node *parent, + struct dentry *dentry) +{ + dentry->d_time = parent->dir.rev; +} + +static inline void kernfs_inc_rev(struct kernfs_node *parent) +{ + parent->dir.rev++; +} + +static inline bool kernfs_dir_changed(struct kernfs_node *parent, + struct dentry *dentry) +{ + if (parent->dir.rev != dentry->d_time) + return true; + return false; +} + extern const struct super_operations kernfs_sops; extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 9e8ca8743c26..d68b4ad09573 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -98,6 +98,11 @@ struct kernfs_elem_dir { * better directly in kernfs_node but is here to save space. */ struct kernfs_root *root; + /* + * Monotonic revision counter, used to identify if a directory + * node has changed during negative dentry revalidation. + */ + unsigned long rev; }; struct kernfs_elem_symlink { -- cgit v1.2.3 From 7ba0273b2f34a55efe967d3c7381fb1da2ca195f Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Fri, 16 Jul 2021 17:28:29 +0800 Subject: kernfs: switch kernfs to use an rwsem The kernfs global lock restricts the ability to perform kernfs node lookup operations in parallel during path walks. Change the kernfs mutex to an rwsem so that, when opportunity arises, node searches can be done in parallel with path walk lookups. Reviewed-by: Miklos Szeredi Signed-off-by: Ian Kent Link: https://lore.kernel.org/r/162642770946.63632.2218304587223241374.stgit@web.messagingengine.com Signed-off-by: Greg Kroah-Hartman --- fs/kernfs/dir.c | 100 ++++++++++++++++++++++---------------------- fs/kernfs/file.c | 4 +- fs/kernfs/inode.c | 16 +++---- fs/kernfs/kernfs-internal.h | 5 ++- fs/kernfs/mount.c | 12 +++--- fs/kernfs/symlink.c | 4 +- include/linux/kernfs.h | 2 +- 7 files changed, 72 insertions(+), 71 deletions(-) (limited to 'include/linux') diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 0b21a8f961ac..4994723d6cf7 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -17,7 +17,7 @@ #include "kernfs-internal.h" -DEFINE_MUTEX(kernfs_mutex); +DECLARE_RWSEM(kernfs_rwsem); static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by rename_lock */ static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */ @@ -26,7 +26,7 @@ static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */ static bool kernfs_active(struct kernfs_node *kn) { - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held(&kernfs_rwsem); return atomic_read(&kn->active) >= 0; } @@ -340,7 +340,7 @@ static int kernfs_sd_compare(const struct kernfs_node *left, * @kn->parent->dir.children. * * Locking: - * mutex_lock(kernfs_mutex) + * kernfs_rwsem held exclusive * * RETURNS: * 0 on susccess -EEXIST on failure. @@ -386,7 +386,7 @@ static int kernfs_link_sibling(struct kernfs_node *kn) * removed, %false if @kn wasn't on the rbtree. * * Locking: - * mutex_lock(kernfs_mutex) + * kernfs_rwsem held exclusive */ static bool kernfs_unlink_sibling(struct kernfs_node *kn) { @@ -457,14 +457,14 @@ void kernfs_put_active(struct kernfs_node *kn) * return after draining is complete. */ static void kernfs_drain(struct kernfs_node *kn) - __releases(&kernfs_mutex) __acquires(&kernfs_mutex) + __releases(&kernfs_rwsem) __acquires(&kernfs_rwsem) { struct kernfs_root *root = kernfs_root(kn); - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held_write(&kernfs_rwsem); WARN_ON_ONCE(kernfs_active(kn)); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); if (kernfs_lockdep(kn)) { rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); @@ -483,7 +483,7 @@ static void kernfs_drain(struct kernfs_node *kn) kernfs_drain_open_files(kn); - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); } /** @@ -722,7 +722,7 @@ int kernfs_add_one(struct kernfs_node *kn) bool has_ns; int ret; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); @@ -753,7 +753,7 @@ int kernfs_add_one(struct kernfs_node *kn) ps_iattr->ia_mtime = ps_iattr->ia_ctime; } - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); /* * Activate the new node unless CREATE_DEACTIVATED is requested. @@ -767,7 +767,7 @@ int kernfs_add_one(struct kernfs_node *kn) return 0; out_unlock: - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return ret; } @@ -788,7 +788,7 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, bool has_ns = kernfs_ns_enabled(parent); unsigned int hash; - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held(&kernfs_rwsem); if (has_ns != (bool)ns) { WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", @@ -820,7 +820,7 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, size_t len; char *p, *name; - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held_read(&kernfs_rwsem); /* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */ spin_lock_irq(&kernfs_rename_lock); @@ -860,10 +860,10 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, { struct kernfs_node *kn; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); kernfs_get(kn); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return kn; } @@ -884,10 +884,10 @@ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, { struct kernfs_node *kn; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); kn = kernfs_walk_ns(parent, path, ns); kernfs_get(kn); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return kn; } @@ -1046,18 +1046,18 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) /* If the kernfs parent node has changed discard and * proceed to ->lookup. */ - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); spin_lock(&dentry->d_lock); parent = kernfs_dentry_node(dentry->d_parent); if (parent) { if (kernfs_dir_changed(parent, dentry)) { spin_unlock(&dentry->d_lock); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return 0; } } spin_unlock(&dentry->d_lock); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); /* The kernfs parent node hasn't changed, leave the * dentry negative and return success. @@ -1066,7 +1066,7 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) } kn = kernfs_dentry_node(dentry); - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); /* The kernfs node has been deactivated */ if (!kernfs_active(kn)) @@ -1085,10 +1085,10 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) kernfs_info(dentry->d_sb)->ns != kn->ns) goto out_bad; - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return 1; out_bad: - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return 0; } @@ -1106,7 +1106,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, struct inode *inode = NULL; const void *ns = NULL; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dir->i_sb)->ns; @@ -1122,7 +1122,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, kernfs_set_rev(parent, dentry); /* instantiate and hash (possibly negative) dentry */ ret = d_splice_alias(inode, dentry); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return ret; } @@ -1244,7 +1244,7 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, { struct rb_node *rbn; - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held_write(&kernfs_rwsem); /* if first iteration, visit leftmost descendant which may be root */ if (!pos) @@ -1280,7 +1280,7 @@ void kernfs_activate(struct kernfs_node *kn) { struct kernfs_node *pos; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) { @@ -1294,14 +1294,14 @@ void kernfs_activate(struct kernfs_node *kn) pos->flags |= KERNFS_ACTIVATED; } - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); } static void __kernfs_remove(struct kernfs_node *kn) { struct kernfs_node *pos; - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held_write(&kernfs_rwsem); /* * Short-circuit if non-root @kn has already finished removal. @@ -1324,7 +1324,7 @@ static void __kernfs_remove(struct kernfs_node *kn) pos = kernfs_leftmost_descendant(kn); /* - * kernfs_drain() drops kernfs_mutex temporarily and @pos's + * kernfs_drain() drops kernfs_rwsem temporarily and @pos's * base ref could have been put by someone else by the time * the function returns. Make sure it doesn't go away * underneath us. @@ -1371,9 +1371,9 @@ static void __kernfs_remove(struct kernfs_node *kn) */ void kernfs_remove(struct kernfs_node *kn) { - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); __kernfs_remove(kn); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); } /** @@ -1460,17 +1460,17 @@ bool kernfs_remove_self(struct kernfs_node *kn) { bool ret; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); kernfs_break_active_protection(kn); /* * SUICIDAL is used to arbitrate among competing invocations. Only * the first one will actually perform removal. When the removal * is complete, SUICIDED is set and the active ref is restored - * while holding kernfs_mutex. The ones which lost arbitration - * waits for SUICDED && drained which can happen only after the - * enclosing kernfs operation which executed the winning instance - * of kernfs_remove_self() finished. + * while kernfs_rwsem for held exclusive. The ones which lost + * arbitration waits for SUICIDED && drained which can happen only + * after the enclosing kernfs operation which executed the winning + * instance of kernfs_remove_self() finished. */ if (!(kn->flags & KERNFS_SUICIDAL)) { kn->flags |= KERNFS_SUICIDAL; @@ -1488,9 +1488,9 @@ bool kernfs_remove_self(struct kernfs_node *kn) atomic_read(&kn->active) == KN_DEACTIVATED_BIAS) break; - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); schedule(); - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); } finish_wait(waitq, &wait); WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb)); @@ -1498,12 +1498,12 @@ bool kernfs_remove_self(struct kernfs_node *kn) } /* - * This must be done while holding kernfs_mutex; otherwise, waiting - * for SUICIDED && deactivated could finish prematurely. + * This must be done while kernfs_rwsem held exclusive; otherwise, + * waiting for SUICIDED && deactivated could finish prematurely. */ kernfs_unbreak_active_protection(kn); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return ret; } @@ -1527,13 +1527,13 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, return -ENOENT; } - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); if (kn) __kernfs_remove(kn); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); if (kn) return 0; @@ -1559,7 +1559,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, if (!kn->parent) return -EINVAL; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); error = -ENOENT; if (!kernfs_active(kn) || !kernfs_active(new_parent) || @@ -1613,7 +1613,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, error = 0; out: - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return error; } @@ -1688,7 +1688,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit_dots(file, ctx)) return 0; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dentry->d_sb)->ns; @@ -1705,12 +1705,12 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) file->private_data = pos; kernfs_get(pos); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); if (!dir_emit(ctx, name, len, ino, type)) return 0; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); } - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); file->private_data = NULL; ctx->pos = INT_MAX; return 0; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index c75719312147..60e2a86c535e 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -860,7 +860,7 @@ repeat: spin_unlock_irq(&kernfs_notify_lock); /* kick fsnotify */ - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; @@ -898,7 +898,7 @@ repeat: iput(inode); } - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); kernfs_put(kn); goto repeat; } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 26f2aa3586f9..dad749f39518 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -100,9 +100,9 @@ int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { int ret; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); ret = __kernfs_setattr(kn, iattr); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return ret; } @@ -116,7 +116,7 @@ int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (!kn) return -EINVAL; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); error = setattr_prepare(&init_user_ns, dentry, iattr); if (error) goto out; @@ -129,7 +129,7 @@ int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, setattr_copy(&init_user_ns, inode, iattr); out: - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return error; } @@ -185,9 +185,9 @@ int kernfs_iop_getattr(struct user_namespace *mnt_userns, struct inode *inode = d_inode(path->dentry); struct kernfs_node *kn = inode->i_private; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); kernfs_refresh_inode(kn, inode); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); generic_fillattr(&init_user_ns, inode, stat); return 0; @@ -278,9 +278,9 @@ int kernfs_iop_permission(struct user_namespace *mnt_userns, kn = inode->i_private; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); kernfs_refresh_inode(kn, inode); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return generic_permission(&init_user_ns, inode, mask); } diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index c2ae58f3b202..f9cc912c31e1 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -69,7 +70,7 @@ struct kernfs_super_info { */ const void *ns; - /* anchored at kernfs_root->supers, protected by kernfs_mutex */ + /* anchored at kernfs_root->supers, protected by kernfs_rwsem */ struct list_head node; }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) @@ -121,7 +122,7 @@ int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); /* * dir.c */ -extern struct mutex kernfs_mutex; +extern struct rw_semaphore kernfs_rwsem; extern const struct dentry_operations kernfs_dops; extern const struct file_operations kernfs_dir_fops; extern const struct inode_operations kernfs_dir_iops; diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 9dc7e7a64e10..baa4155ba2ed 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -255,9 +255,9 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k sb->s_shrink.seeks = 0; /* get root inode, initialize and unlock it */ - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); inode = kernfs_get_inode(sb, info->root->kn); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); if (!inode) { pr_debug("kernfs: could not get root inode\n"); return -ENOMEM; @@ -344,9 +344,9 @@ int kernfs_get_tree(struct fs_context *fc) } sb->s_flags |= SB_ACTIVE; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); list_add(&info->node, &info->root->supers); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); } fc->root = dget(sb->s_root); @@ -372,9 +372,9 @@ void kernfs_kill_sb(struct super_block *sb) { struct kernfs_super_info *info = kernfs_info(sb); - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); list_del(&info->node); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); /* * Remove the superblock from fs_supers/s_instances diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 5432883d819f..c8f8e41b8411 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -116,9 +116,9 @@ static int kernfs_getlink(struct inode *inode, char *path) struct kernfs_node *target = kn->symlink.target_kn; int error; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); error = kernfs_get_target_path(parent, target, path); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return error; } diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index d68b4ad09573..1093abf7c28c 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -193,7 +193,7 @@ struct kernfs_root { u32 id_highbits; struct kernfs_syscall_ops *syscall_ops; - /* list of kernfs_super_info of this root, protected by kernfs_mutex */ + /* list of kernfs_super_info of this root, protected by kernfs_rwsem */ struct list_head supers; wait_queue_head_t deactivate_waitq; -- cgit v1.2.3 From 9acb9c48b9408bbb6ade90e3f3192ee38e2589b3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 20 Jul 2021 15:33:41 +0200 Subject: fs: remove generic_block_fiemap Remove the now unused generic_block_fiemap helper. Link: https://lore.kernel.org/r/20210720133341.405438-5-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/ioctl.c | 203 ------------------------------------------------- include/linux/fiemap.h | 4 - 2 files changed, 207 deletions(-) (limited to 'include/linux') diff --git a/fs/ioctl.c b/fs/ioctl.c index 1e2204fa9963..eea8267ae1f2 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -263,209 +263,6 @@ static long ioctl_file_clone_range(struct file *file, args.src_length, args.dest_offset); } -#ifdef CONFIG_BLOCK - -static inline sector_t logical_to_blk(struct inode *inode, loff_t offset) -{ - return (offset >> inode->i_blkbits); -} - -static inline loff_t blk_to_logical(struct inode *inode, sector_t blk) -{ - return (blk << inode->i_blkbits); -} - -/** - * __generic_block_fiemap - FIEMAP for block based inodes (no locking) - * @inode: the inode to map - * @fieinfo: the fiemap info struct that will be passed back to userspace - * @start: where to start mapping in the inode - * @len: how much space to map - * @get_block: the fs's get_block function - * - * This does FIEMAP for block based inodes. Basically it will just loop - * through get_block until we hit the number of extents we want to map, or we - * go past the end of the file and hit a hole. - * - * If it is possible to have data blocks beyond a hole past @inode->i_size, then - * please do not use this function, it will stop at the first unmapped block - * beyond i_size. - * - * If you use this function directly, you need to do your own locking. Use - * generic_block_fiemap if you want the locking done for you. - */ -static int __generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, loff_t start, - loff_t len, get_block_t *get_block) -{ - struct buffer_head map_bh; - sector_t start_blk, last_blk; - loff_t isize = i_size_read(inode); - u64 logical = 0, phys = 0, size = 0; - u32 flags = FIEMAP_EXTENT_MERGED; - bool past_eof = false, whole_file = false; - int ret = 0; - - ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_SYNC); - if (ret) - return ret; - - /* - * Either the i_mutex or other appropriate locking needs to be held - * since we expect isize to not change at all through the duration of - * this call. - */ - if (len >= isize) { - whole_file = true; - len = isize; - } - - /* - * Some filesystems can't deal with being asked to map less than - * blocksize, so make sure our len is at least block length. - */ - if (logical_to_blk(inode, len) == 0) - len = blk_to_logical(inode, 1); - - start_blk = logical_to_blk(inode, start); - last_blk = logical_to_blk(inode, start + len - 1); - - do { - /* - * we set b_size to the total size we want so it will map as - * many contiguous blocks as possible at once - */ - memset(&map_bh, 0, sizeof(struct buffer_head)); - map_bh.b_size = len; - - ret = get_block(inode, start_blk, &map_bh, 0); - if (ret) - break; - - /* HOLE */ - if (!buffer_mapped(&map_bh)) { - start_blk++; - - /* - * We want to handle the case where there is an - * allocated block at the front of the file, and then - * nothing but holes up to the end of the file properly, - * to make sure that extent at the front gets properly - * marked with FIEMAP_EXTENT_LAST - */ - if (!past_eof && - blk_to_logical(inode, start_blk) >= isize) - past_eof = 1; - - /* - * First hole after going past the EOF, this is our - * last extent - */ - if (past_eof && size) { - flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST; - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, - flags); - } else if (size) { - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, flags); - size = 0; - } - - /* if we have holes up to/past EOF then we're done */ - if (start_blk > last_blk || past_eof || ret) - break; - } else { - /* - * We have gone over the length of what we wanted to - * map, and it wasn't the entire file, so add the extent - * we got last time and exit. - * - * This is for the case where say we want to map all the - * way up to the second to the last block in a file, but - * the last block is a hole, making the second to last - * block FIEMAP_EXTENT_LAST. In this case we want to - * see if there is a hole after the second to last block - * so we can mark it properly. If we found data after - * we exceeded the length we were requesting, then we - * are good to go, just add the extent to the fieinfo - * and break - */ - if (start_blk > last_blk && !whole_file) { - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, - flags); - break; - } - - /* - * if size != 0 then we know we already have an extent - * to add, so add it. - */ - if (size) { - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, - flags); - if (ret) - break; - } - - logical = blk_to_logical(inode, start_blk); - phys = blk_to_logical(inode, map_bh.b_blocknr); - size = map_bh.b_size; - flags = FIEMAP_EXTENT_MERGED; - - start_blk += logical_to_blk(inode, size); - - /* - * If we are past the EOF, then we need to make sure as - * soon as we find a hole that the last extent we found - * is marked with FIEMAP_EXTENT_LAST - */ - if (!past_eof && logical + size >= isize) - past_eof = true; - } - cond_resched(); - if (fatal_signal_pending(current)) { - ret = -EINTR; - break; - } - - } while (1); - - /* If ret is 1 then we just hit the end of the extent array */ - if (ret == 1) - ret = 0; - - return ret; -} - -/** - * generic_block_fiemap - FIEMAP for block based inodes - * @inode: The inode to map - * @fieinfo: The mapping information - * @start: The initial block to map - * @len: The length of the extect to attempt to map - * @get_block: The block mapping function for the fs - * - * Calls __generic_block_fiemap to map the inode, after taking - * the inode's mutex lock. - */ - -int generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, u64 start, - u64 len, get_block_t *get_block) -{ - int ret; - inode_lock(inode); - ret = __generic_block_fiemap(inode, fieinfo, start, len, get_block); - inode_unlock(inode); - return ret; -} -EXPORT_SYMBOL(generic_block_fiemap); - -#endif /* CONFIG_BLOCK */ - /* * This provides compatibility with legacy XFS pre-allocation ioctls * which predate the fallocate syscall. diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h index 4e624c466583..c50882f19235 100644 --- a/include/linux/fiemap.h +++ b/include/linux/fiemap.h @@ -18,8 +18,4 @@ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, u64 phys, u64 len, u32 flags); -int generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, u64 start, u64 len, - get_block_t *get_block); - #endif /* _LINUX_FIEMAP_H 1 */ -- cgit v1.2.3 From 4d3d947866c2da405a6257158e42077fa3c95755 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 12:31:40 +0200 Subject: tty: move tty_driver related prototypes to tty_driver.h We already have tty_driver.h, so cleanup tty.h a bit by moving out tty_driver-related function prototypes into tty_driver.h. Note that tty.h already includes tty_driver.h. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723103147.18250-2-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 17 ----------------- include/linux/tty_driver.h | 17 +++++++++++++++++ 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 19dc1097e09c..1550c1d49baa 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -446,15 +446,6 @@ extern const char *tty_driver_name(const struct tty_struct *tty); extern void tty_wait_until_sent(struct tty_struct *tty, long timeout); extern void stop_tty(struct tty_struct *tty); extern void start_tty(struct tty_struct *tty); -extern int tty_register_driver(struct tty_driver *driver); -extern void tty_unregister_driver(struct tty_driver *driver); -extern struct device *tty_register_device(struct tty_driver *driver, - unsigned index, struct device *dev); -extern struct device *tty_register_device_attr(struct tty_driver *driver, - unsigned index, struct device *device, - void *drvdata, - const struct attribute_group **attr_grp); -extern void tty_unregister_device(struct tty_driver *driver, unsigned index); extern void tty_write_message(struct tty_struct *tty, char *msg); extern int tty_send_xchar(struct tty_struct *tty, char ch); extern int tty_put_char(struct tty_struct *tty, unsigned char c); @@ -691,12 +682,4 @@ extern void tty_lock_slave(struct tty_struct *tty); extern void tty_unlock_slave(struct tty_struct *tty); extern void tty_set_lock_subclass(struct tty_struct *tty); -#ifdef CONFIG_PROC_FS -extern void proc_tty_register_driver(struct tty_driver *); -extern void proc_tty_unregister_driver(struct tty_driver *); -#else -static inline void proc_tty_register_driver(struct tty_driver *d) {} -static inline void proc_tty_unregister_driver(struct tty_driver *d) {} -#endif - #endif diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 448f8ee6db6e..e15f8635aa36 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -434,4 +434,21 @@ static inline struct tty_driver *tty_driver_kref_get(struct tty_driver *d) /* serial subtype definitions */ #define SERIAL_TYPE_NORMAL 1 +int tty_register_driver(struct tty_driver *driver); +void tty_unregister_driver(struct tty_driver *driver); +struct device *tty_register_device(struct tty_driver *driver, unsigned index, + struct device *dev); +struct device *tty_register_device_attr(struct tty_driver *driver, + unsigned index, struct device *device, void *drvdata, + const struct attribute_group **attr_grp); +void tty_unregister_device(struct tty_driver *driver, unsigned index); + +#ifdef CONFIG_PROC_FS +void proc_tty_register_driver(struct tty_driver *); +void proc_tty_unregister_driver(struct tty_driver *); +#else +static inline void proc_tty_register_driver(struct tty_driver *d) {} +static inline void proc_tty_unregister_driver(struct tty_driver *d) {} +#endif + #endif /* #ifdef _LINUX_TTY_DRIVER_H */ -- cgit v1.2.3 From 890ebae627708cd530592b524efd5d26d9fdb2ec Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 12:31:41 +0200 Subject: tty: include kref.h in tty_driver.h We use kref in tty_driver.h, but do not include kref.h. It is currently included by linux/cdev.h -> linux/kobject.h -> linux/kref.h chain, so everything is in order only implicitly. So make this dependency explicit. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723103147.18250-3-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index e15f8635aa36..a798e7f8890a 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -233,6 +233,7 @@ #include #include +#include #include #include #include -- cgit v1.2.3 From a24bc667ac1f19cdda8a998cdaf7fbdd4fc0a040 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 12:31:42 +0200 Subject: tty: move ldisc prototypes to tty_ldisc.h We already have tty_ldisc.h, so cleanup tty.h a bit by moving out tty_ldisc-related function prototypes and a variable into tty_ldisc.h. They are implemented in tty_ldisc.c anyway. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723103147.18250-4-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 10 ---------- include/linux/tty_ldisc.h | 15 +++++++++++++++ 2 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 1550c1d49baa..7f088d43db45 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -493,13 +492,7 @@ extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); extern int tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b); extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); -extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *); -extern void tty_ldisc_deref(struct tty_ldisc *); -extern struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *); -extern const struct seq_operations tty_ldiscs_seq_ops; - extern void tty_wakeup(struct tty_struct *tty); -extern void tty_ldisc_flush(struct tty_struct *tty); extern int tty_mode_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); @@ -629,9 +622,6 @@ static inline int tty_port_users(struct tty_port *port) return port->count + port->blocked_open; } -extern int tty_register_ldisc(struct tty_ldisc_ops *new_ldisc); -extern void tty_unregister_ldisc(struct tty_ldisc_ops *ldisc); -extern int tty_set_ldisc(struct tty_struct *tty, int disc); extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, const char *f, int count); diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index fbe9de278629..62131bb9251f 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -2,6 +2,8 @@ #ifndef _LINUX_TTY_LDISC_H #define _LINUX_TTY_LDISC_H +struct tty_struct; + /* * This structure defines the interface between the tty line discipline * implementation and the tty routines. The following routines can be @@ -126,6 +128,7 @@ #include #include #include +#include /* * the semaphore definition @@ -220,4 +223,16 @@ struct tty_ldisc { #define MODULE_ALIAS_LDISC(ldisc) \ MODULE_ALIAS("tty-ldisc-" __stringify(ldisc)) +extern const struct seq_operations tty_ldiscs_seq_ops; + +struct tty_ldisc *tty_ldisc_ref(struct tty_struct *); +void tty_ldisc_deref(struct tty_ldisc *); +struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *); + +void tty_ldisc_flush(struct tty_struct *tty); + +int tty_register_ldisc(struct tty_ldisc_ops *new_ldisc); +void tty_unregister_ldisc(struct tty_ldisc_ops *ldisc); +int tty_set_ldisc(struct tty_struct *tty, int disc); + #endif /* _LINUX_TTY_LDISC_H */ -- cgit v1.2.3 From abca990183e933d8448a4791c2912b509a17e290 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 12:31:43 +0200 Subject: tty: include list & lockdep from tty_ldisc.h We use structs list_head and lockdep_map as non-pointers in tty_ldisc.h. So better have headers defining them explicitly included so that the structs are always defined. Not only implicitly via random include chains. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723103147.18250-5-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_ldisc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 62131bb9251f..b1d812e902aa 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -128,6 +128,8 @@ struct tty_struct; #include #include #include +#include +#include #include /* -- cgit v1.2.3 From 56eef46aa830824d5046a765d695a78bc0c34fed Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 12:31:44 +0200 Subject: tty: move tty_ldisc_receive_buf to tty_flip.h It's the only remaining tty_buffer.c prototype residing in tty.h. Move it along others to tty_flip.h. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723103147.18250-6-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 --- include/linux/tty_flip.h | 5 +++++ 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 7f088d43db45..fad53f69a8ca 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -622,9 +622,6 @@ static inline int tty_port_users(struct tty_port *port) return port->count + port->blocked_open; } -extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, - const char *f, int count); - /* n_tty.c */ extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops); #ifdef CONFIG_TTY diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 67d78dc553e1..615a2a87b2a7 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -4,6 +4,8 @@ #include +struct tty_ldisc; + extern int tty_buffer_set_limit(struct tty_port *port, int limit); extern unsigned int tty_buffer_space_avail(struct tty_port *port); extern int tty_buffer_request_room(struct tty_port *port, size_t size); @@ -39,6 +41,9 @@ static inline int tty_insert_flip_string(struct tty_port *port, return tty_insert_flip_string_fixed_flag(port, chars, TTY_NORMAL, size); } +int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, + const char *f, int count); + extern void tty_buffer_lock_exclusive(struct tty_port *port); extern void tty_buffer_unlock_exclusive(struct tty_port *port); -- cgit v1.2.3 From 8d29e0024437ae9184ae24f817ef0fda80b8cd3c Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 12:31:45 +0200 Subject: tty: move tty_buffer definitions to new tty_buffer.h tty.h is large enough currently. And I am slowly adding kernel-doc documentation, so it grows to unmaintainable long mess. To avoid this, split tty.h further into tty_buffer.h and move there tty_buffer-related declarations and function prototypes. Note that many of the tty_buffer.c function prototypes reside now in tty_flip.h. But we cannot move struct tty_buffer & friends because: * tty_insert_flip_char() in tty_flip.h needs both struct tty_port and struct tty_buffer defined. * struct tty_port in tty_port.h needs struct tty_buffer defined. So if we moved struct tty_buffer to tty_flip.h too, tty_flip.h would need tty_port.h and that would need tty_flip.h (to have tty_buffer) again. Hence we introduce new header tty_buffer.h here to break this circular dependency. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723103147.18250-7-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 49 +------------------------------------- include/linux/tty_buffer.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 60 insertions(+), 48 deletions(-) create mode 100644 include/linux/tty_buffer.h (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index fad53f69a8ca..b5f353797cec 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -30,54 +31,6 @@ */ #define __DISABLED_CHAR '\0' -struct tty_buffer { - union { - struct tty_buffer *next; - struct llist_node free; - }; - int used; - int size; - int commit; - int read; - int flags; - /* Data points here */ - unsigned long data[]; -}; - -/* Values for .flags field of tty_buffer */ -#define TTYB_NORMAL 1 /* buffer has no flags buffer */ - -static inline unsigned char *char_buf_ptr(struct tty_buffer *b, int ofs) -{ - return ((unsigned char *)b->data) + ofs; -} - -static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) -{ - return (char *)char_buf_ptr(b, ofs) + b->size; -} - -struct tty_bufhead { - struct tty_buffer *head; /* Queue head */ - struct work_struct work; - struct mutex lock; - atomic_t priority; - struct tty_buffer sentinel; - struct llist_head free; /* Free queue head */ - atomic_t mem_used; /* In-use buffers excluding free list */ - int mem_limit; - struct tty_buffer *tail; /* Active buffer */ -}; -/* - * When a break, frame error, or parity error happens, these codes are - * stuffed into the flags buffer. - */ -#define TTY_NORMAL 0 -#define TTY_BREAK 1 -#define TTY_FRAME 2 -#define TTY_PARITY 3 -#define TTY_OVERRUN 4 - #define INTR_CHAR(tty) ((tty)->termios.c_cc[VINTR]) #define QUIT_CHAR(tty) ((tty)->termios.c_cc[VQUIT]) #define ERASE_CHAR(tty) ((tty)->termios.c_cc[VERASE]) diff --git a/include/linux/tty_buffer.h b/include/linux/tty_buffer.h new file mode 100644 index 000000000000..3b9d77604291 --- /dev/null +++ b/include/linux/tty_buffer.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TTY_BUFFER_H +#define _LINUX_TTY_BUFFER_H + +#include +#include +#include +#include + +struct tty_buffer { + union { + struct tty_buffer *next; + struct llist_node free; + }; + int used; + int size; + int commit; + int read; + int flags; + /* Data points here */ + unsigned long data[]; +}; + +/* Values for .flags field of tty_buffer */ +#define TTYB_NORMAL 1 /* buffer has no flags buffer */ + +static inline unsigned char *char_buf_ptr(struct tty_buffer *b, int ofs) +{ + return ((unsigned char *)b->data) + ofs; +} + +static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) +{ + return (char *)char_buf_ptr(b, ofs) + b->size; +} + +struct tty_bufhead { + struct tty_buffer *head; /* Queue head */ + struct work_struct work; + struct mutex lock; + atomic_t priority; + struct tty_buffer sentinel; + struct llist_head free; /* Free queue head */ + atomic_t mem_used; /* In-use buffers excluding free list */ + int mem_limit; + struct tty_buffer *tail; /* Active buffer */ +}; + +/* + * When a break, frame error, or parity error happens, these codes are + * stuffed into the flags buffer. + */ +#define TTY_NORMAL 0 +#define TTY_BREAK 1 +#define TTY_FRAME 2 +#define TTY_PARITY 3 +#define TTY_OVERRUN 4 + +#endif -- cgit v1.2.3 From 67b94be44771ab99bdbd019e19314f268fa1ff8c Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 12:31:46 +0200 Subject: tty: move tty_port to new tty_port.h tty.h is long enough already. And I am slowly adding kernel-doc documentation, so it grows to unmaintainable long mess. To avoid this, split tty.h further into tty_port.h and move there tty_port-related declarations and function prototypes (those implemented in tty_port.c). Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723103147.18250-8-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 196 +------------------------------------------- include/linux/tty_port.h | 208 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 209 insertions(+), 195 deletions(-) create mode 100644 include/linux/tty_port.h (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index b5f353797cec..168e57e40bbb 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -116,85 +117,6 @@ struct device; struct signal_struct; - -/* - * Port level information. Each device keeps its own port level information - * so provide a common structure for those ports wanting to use common support - * routines. - * - * The tty port has a different lifetime to the tty so must be kept apart. - * In addition be careful as tty -> port mappings are valid for the life - * of the tty object but in many cases port -> tty mappings are valid only - * until a hangup so don't use the wrong path. - */ - -struct tty_port; - -struct tty_port_operations { - /* Return 1 if the carrier is raised */ - int (*carrier_raised)(struct tty_port *port); - /* Control the DTR line */ - void (*dtr_rts)(struct tty_port *port, int raise); - /* Called when the last close completes or a hangup finishes - IFF the port was initialized. Do not use to free resources. Called - under the port mutex to serialize against activate/shutdowns */ - void (*shutdown)(struct tty_port *port); - /* Called under the port mutex from tty_port_open, serialized using - the port mutex */ - /* FIXME: long term getting the tty argument *out* of this would be - good for consoles */ - int (*activate)(struct tty_port *port, struct tty_struct *tty); - /* Called on the final put of a port */ - void (*destruct)(struct tty_port *port); -}; - -struct tty_port_client_operations { - int (*receive_buf)(struct tty_port *port, const unsigned char *, const unsigned char *, size_t); - void (*write_wakeup)(struct tty_port *port); -}; - -extern const struct tty_port_client_operations tty_port_default_client_ops; - -struct tty_port { - struct tty_bufhead buf; /* Locked internally */ - struct tty_struct *tty; /* Back pointer */ - struct tty_struct *itty; /* internal back ptr */ - const struct tty_port_operations *ops; /* Port operations */ - const struct tty_port_client_operations *client_ops; /* Port client operations */ - spinlock_t lock; /* Lock protecting tty field */ - int blocked_open; /* Waiting to open */ - int count; /* Usage count */ - wait_queue_head_t open_wait; /* Open waiters */ - wait_queue_head_t delta_msr_wait; /* Modem status change */ - unsigned long flags; /* User TTY flags ASYNC_ */ - unsigned long iflags; /* Internal flags TTY_PORT_ */ - unsigned char console:1; /* port is a console */ - struct mutex mutex; /* Locking */ - struct mutex buf_mutex; /* Buffer alloc lock */ - unsigned char *xmit_buf; /* Optional buffer */ - unsigned int close_delay; /* Close port delay */ - unsigned int closing_wait; /* Delay for output */ - int drain_delay; /* Set to zero if no pure time - based drain is needed else - set to size of fifo */ - struct kref kref; /* Ref counter */ - void *client_data; -}; - -/* tty_port::iflags bits -- use atomic bit ops */ -#define TTY_PORT_INITIALIZED 0 /* device is initialized */ -#define TTY_PORT_SUSPENDED 1 /* device is suspended */ -#define TTY_PORT_ACTIVE 2 /* device is open */ - -/* - * uart drivers: use the uart_port::status field and the UPSTAT_* defines - * for s/w-based flow control steering and carrier detection status - */ -#define TTY_PORT_CTS_FLOW 3 /* h/w flow control enabled */ -#define TTY_PORT_CHECK_CD 4 /* carrier detect enabled */ -#define TTY_PORT_KOPENED 5 /* device exclusively opened by - kernel */ - struct tty_operations; /** @@ -459,122 +381,6 @@ extern int tty_standard_install(struct tty_driver *driver, extern struct mutex tty_mutex; -extern void tty_port_init(struct tty_port *port); -extern void tty_port_link_device(struct tty_port *port, - struct tty_driver *driver, unsigned index); -extern struct device *tty_port_register_device(struct tty_port *port, - struct tty_driver *driver, unsigned index, - struct device *device); -extern struct device *tty_port_register_device_attr(struct tty_port *port, - struct tty_driver *driver, unsigned index, - struct device *device, void *drvdata, - const struct attribute_group **attr_grp); -extern struct device *tty_port_register_device_serdev(struct tty_port *port, - struct tty_driver *driver, unsigned index, - struct device *device); -extern struct device *tty_port_register_device_attr_serdev(struct tty_port *port, - struct tty_driver *driver, unsigned index, - struct device *device, void *drvdata, - const struct attribute_group **attr_grp); -extern void tty_port_unregister_device(struct tty_port *port, - struct tty_driver *driver, unsigned index); -extern int tty_port_alloc_xmit_buf(struct tty_port *port); -extern void tty_port_free_xmit_buf(struct tty_port *port); -extern void tty_port_destroy(struct tty_port *port); -extern void tty_port_put(struct tty_port *port); - -static inline struct tty_port *tty_port_get(struct tty_port *port) -{ - if (port && kref_get_unless_zero(&port->kref)) - return port; - return NULL; -} - -/* If the cts flow control is enabled, return true. */ -static inline bool tty_port_cts_enabled(const struct tty_port *port) -{ - return test_bit(TTY_PORT_CTS_FLOW, &port->iflags); -} - -static inline void tty_port_set_cts_flow(struct tty_port *port, bool val) -{ - assign_bit(TTY_PORT_CTS_FLOW, &port->iflags, val); -} - -static inline bool tty_port_active(const struct tty_port *port) -{ - return test_bit(TTY_PORT_ACTIVE, &port->iflags); -} - -static inline void tty_port_set_active(struct tty_port *port, bool val) -{ - assign_bit(TTY_PORT_ACTIVE, &port->iflags, val); -} - -static inline bool tty_port_check_carrier(const struct tty_port *port) -{ - return test_bit(TTY_PORT_CHECK_CD, &port->iflags); -} - -static inline void tty_port_set_check_carrier(struct tty_port *port, bool val) -{ - assign_bit(TTY_PORT_CHECK_CD, &port->iflags, val); -} - -static inline bool tty_port_suspended(const struct tty_port *port) -{ - return test_bit(TTY_PORT_SUSPENDED, &port->iflags); -} - -static inline void tty_port_set_suspended(struct tty_port *port, bool val) -{ - assign_bit(TTY_PORT_SUSPENDED, &port->iflags, val); -} - -static inline bool tty_port_initialized(const struct tty_port *port) -{ - return test_bit(TTY_PORT_INITIALIZED, &port->iflags); -} - -static inline void tty_port_set_initialized(struct tty_port *port, bool val) -{ - assign_bit(TTY_PORT_INITIALIZED, &port->iflags, val); -} - -static inline bool tty_port_kopened(const struct tty_port *port) -{ - return test_bit(TTY_PORT_KOPENED, &port->iflags); -} - -static inline void tty_port_set_kopened(struct tty_port *port, bool val) -{ - assign_bit(TTY_PORT_KOPENED, &port->iflags, val); -} - -extern struct tty_struct *tty_port_tty_get(struct tty_port *port); -extern void tty_port_tty_set(struct tty_port *port, struct tty_struct *tty); -extern int tty_port_carrier_raised(struct tty_port *port); -extern void tty_port_raise_dtr_rts(struct tty_port *port); -extern void tty_port_lower_dtr_rts(struct tty_port *port); -extern void tty_port_hangup(struct tty_port *port); -extern void tty_port_tty_hangup(struct tty_port *port, bool check_clocal); -extern void tty_port_tty_wakeup(struct tty_port *port); -extern int tty_port_block_til_ready(struct tty_port *port, - struct tty_struct *tty, struct file *filp); -extern int tty_port_close_start(struct tty_port *port, - struct tty_struct *tty, struct file *filp); -extern void tty_port_close_end(struct tty_port *port, struct tty_struct *tty); -extern void tty_port_close(struct tty_port *port, - struct tty_struct *tty, struct file *filp); -extern int tty_port_install(struct tty_port *port, struct tty_driver *driver, - struct tty_struct *tty); -extern int tty_port_open(struct tty_port *port, - struct tty_struct *tty, struct file *filp); -static inline int tty_port_users(struct tty_port *port) -{ - return port->count + port->blocked_open; -} - /* n_tty.c */ extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops); #ifdef CONFIG_TTY diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h new file mode 100644 index 000000000000..6e86e9e118b6 --- /dev/null +++ b/include/linux/tty_port.h @@ -0,0 +1,208 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TTY_PORT_H +#define _LINUX_TTY_PORT_H + +#include +#include +#include +#include + +/* + * Port level information. Each device keeps its own port level information + * so provide a common structure for those ports wanting to use common support + * routines. + * + * The tty port has a different lifetime to the tty so must be kept apart. + * In addition be careful as tty -> port mappings are valid for the life + * of the tty object but in many cases port -> tty mappings are valid only + * until a hangup so don't use the wrong path. + */ + +struct attribute_group; +struct tty_driver; +struct tty_port; +struct tty_struct; + +struct tty_port_operations { + /* Return 1 if the carrier is raised */ + int (*carrier_raised)(struct tty_port *port); + /* Control the DTR line */ + void (*dtr_rts)(struct tty_port *port, int raise); + /* Called when the last close completes or a hangup finishes + IFF the port was initialized. Do not use to free resources. Called + under the port mutex to serialize against activate/shutdowns */ + void (*shutdown)(struct tty_port *port); + /* Called under the port mutex from tty_port_open, serialized using + the port mutex */ + /* FIXME: long term getting the tty argument *out* of this would be + good for consoles */ + int (*activate)(struct tty_port *port, struct tty_struct *tty); + /* Called on the final put of a port */ + void (*destruct)(struct tty_port *port); +}; + +struct tty_port_client_operations { + int (*receive_buf)(struct tty_port *port, const unsigned char *, const unsigned char *, size_t); + void (*write_wakeup)(struct tty_port *port); +}; + +extern const struct tty_port_client_operations tty_port_default_client_ops; + +struct tty_port { + struct tty_bufhead buf; /* Locked internally */ + struct tty_struct *tty; /* Back pointer */ + struct tty_struct *itty; /* internal back ptr */ + const struct tty_port_operations *ops; /* Port operations */ + const struct tty_port_client_operations *client_ops; /* Port client operations */ + spinlock_t lock; /* Lock protecting tty field */ + int blocked_open; /* Waiting to open */ + int count; /* Usage count */ + wait_queue_head_t open_wait; /* Open waiters */ + wait_queue_head_t delta_msr_wait; /* Modem status change */ + unsigned long flags; /* User TTY flags ASYNC_ */ + unsigned long iflags; /* Internal flags TTY_PORT_ */ + unsigned char console:1; /* port is a console */ + struct mutex mutex; /* Locking */ + struct mutex buf_mutex; /* Buffer alloc lock */ + unsigned char *xmit_buf; /* Optional buffer */ + unsigned int close_delay; /* Close port delay */ + unsigned int closing_wait; /* Delay for output */ + int drain_delay; /* Set to zero if no pure time + based drain is needed else + set to size of fifo */ + struct kref kref; /* Ref counter */ + void *client_data; +}; + +/* tty_port::iflags bits -- use atomic bit ops */ +#define TTY_PORT_INITIALIZED 0 /* device is initialized */ +#define TTY_PORT_SUSPENDED 1 /* device is suspended */ +#define TTY_PORT_ACTIVE 2 /* device is open */ + +/* + * uart drivers: use the uart_port::status field and the UPSTAT_* defines + * for s/w-based flow control steering and carrier detection status + */ +#define TTY_PORT_CTS_FLOW 3 /* h/w flow control enabled */ +#define TTY_PORT_CHECK_CD 4 /* carrier detect enabled */ +#define TTY_PORT_KOPENED 5 /* device exclusively opened by + kernel */ + +void tty_port_init(struct tty_port *port); +void tty_port_link_device(struct tty_port *port, struct tty_driver *driver, + unsigned index); +struct device *tty_port_register_device(struct tty_port *port, + struct tty_driver *driver, unsigned index, + struct device *device); +struct device *tty_port_register_device_attr(struct tty_port *port, + struct tty_driver *driver, unsigned index, + struct device *device, void *drvdata, + const struct attribute_group **attr_grp); +struct device *tty_port_register_device_serdev(struct tty_port *port, + struct tty_driver *driver, unsigned index, + struct device *device); +struct device *tty_port_register_device_attr_serdev(struct tty_port *port, + struct tty_driver *driver, unsigned index, + struct device *device, void *drvdata, + const struct attribute_group **attr_grp); +void tty_port_unregister_device(struct tty_port *port, + struct tty_driver *driver, unsigned index); +int tty_port_alloc_xmit_buf(struct tty_port *port); +void tty_port_free_xmit_buf(struct tty_port *port); +void tty_port_destroy(struct tty_port *port); +void tty_port_put(struct tty_port *port); + +static inline struct tty_port *tty_port_get(struct tty_port *port) +{ + if (port && kref_get_unless_zero(&port->kref)) + return port; + return NULL; +} + +/* If the cts flow control is enabled, return true. */ +static inline bool tty_port_cts_enabled(const struct tty_port *port) +{ + return test_bit(TTY_PORT_CTS_FLOW, &port->iflags); +} + +static inline void tty_port_set_cts_flow(struct tty_port *port, bool val) +{ + assign_bit(TTY_PORT_CTS_FLOW, &port->iflags, val); +} + +static inline bool tty_port_active(const struct tty_port *port) +{ + return test_bit(TTY_PORT_ACTIVE, &port->iflags); +} + +static inline void tty_port_set_active(struct tty_port *port, bool val) +{ + assign_bit(TTY_PORT_ACTIVE, &port->iflags, val); +} + +static inline bool tty_port_check_carrier(const struct tty_port *port) +{ + return test_bit(TTY_PORT_CHECK_CD, &port->iflags); +} + +static inline void tty_port_set_check_carrier(struct tty_port *port, bool val) +{ + assign_bit(TTY_PORT_CHECK_CD, &port->iflags, val); +} + +static inline bool tty_port_suspended(const struct tty_port *port) +{ + return test_bit(TTY_PORT_SUSPENDED, &port->iflags); +} + +static inline void tty_port_set_suspended(struct tty_port *port, bool val) +{ + assign_bit(TTY_PORT_SUSPENDED, &port->iflags, val); +} + +static inline bool tty_port_initialized(const struct tty_port *port) +{ + return test_bit(TTY_PORT_INITIALIZED, &port->iflags); +} + +static inline void tty_port_set_initialized(struct tty_port *port, bool val) +{ + assign_bit(TTY_PORT_INITIALIZED, &port->iflags, val); +} + +static inline bool tty_port_kopened(const struct tty_port *port) +{ + return test_bit(TTY_PORT_KOPENED, &port->iflags); +} + +static inline void tty_port_set_kopened(struct tty_port *port, bool val) +{ + assign_bit(TTY_PORT_KOPENED, &port->iflags, val); +} + +struct tty_struct *tty_port_tty_get(struct tty_port *port); +void tty_port_tty_set(struct tty_port *port, struct tty_struct *tty); +int tty_port_carrier_raised(struct tty_port *port); +void tty_port_raise_dtr_rts(struct tty_port *port); +void tty_port_lower_dtr_rts(struct tty_port *port); +void tty_port_hangup(struct tty_port *port); +void tty_port_tty_hangup(struct tty_port *port, bool check_clocal); +void tty_port_tty_wakeup(struct tty_port *port); +int tty_port_block_til_ready(struct tty_port *port, struct tty_struct *tty, + struct file *filp); +int tty_port_close_start(struct tty_port *port, struct tty_struct *tty, + struct file *filp); +void tty_port_close_end(struct tty_port *port, struct tty_struct *tty); +void tty_port_close(struct tty_port *port, struct tty_struct *tty, + struct file *filp); +int tty_port_install(struct tty_port *port, struct tty_driver *driver, + struct tty_struct *tty); +int tty_port_open(struct tty_port *port, struct tty_struct *tty, + struct file *filp); + +static inline int tty_port_users(struct tty_port *port) +{ + return port->count + port->blocked_open; +} + +#endif -- cgit v1.2.3 From 52c27f13b52cd7b7893de4fc11f1555d3917c3e6 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 12:31:47 +0200 Subject: tty: tty_flip.h needs only tty_buffer and tty_port tty_flip.h currently includes whole tty.h. In fact, it needs only tty_buffer and tty_port definitions. Provided, we separated tty_buffer and tty_port into separate headers in the previous patch, we can make tty_flip.h to include only much lighter tty_buffer.h and tty_port.h. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723103147.18250-9-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_flip.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 615a2a87b2a7..32284992b31a 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -2,7 +2,8 @@ #ifndef _LINUX_TTY_FLIP_H #define _LINUX_TTY_FLIP_H -#include +#include +#include struct tty_ldisc; -- cgit v1.2.3 From 56ec5880a28eae0f508e88e9e80d2e82a471c9be Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 09:43:14 +0200 Subject: tty: drop alloc_tty_driver Noone uses this deprecated function now. So we can remove it. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723074317.32690-6-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_driver.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index a798e7f8890a..c7746dee58a6 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -340,18 +340,6 @@ extern void tty_driver_kref_put(struct tty_driver *driver); #define tty_alloc_driver(lines, flags) \ __tty_alloc_driver(lines, THIS_MODULE, flags) -/* - * DEPRECATED Do not use this in new code, use tty_alloc_driver instead. - * (And change the return value checks.) - */ -static inline struct tty_driver *alloc_tty_driver(unsigned int lines) -{ - struct tty_driver *ret = tty_alloc_driver(lines, 0); - if (IS_ERR(ret)) - return NULL; - return ret; -} - static inline struct tty_driver *tty_driver_kref_get(struct tty_driver *d) { kref_get(&d->kref); -- cgit v1.2.3 From cb9ea618ee60313d9278b2ba75f56da2531c8cac Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 09:43:15 +0200 Subject: tty: make tty_set_operations an inline Since commit f34d7a5b7010 (tty: The big operations rework) in 2008, tty_set_operations() is a simple one-line assignment. There is no reason for this to be an exported function, hence move it to a header and make an inline from that. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723074317.32690-7-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 7 ------- include/linux/tty_driver.h | 8 ++++++-- 2 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 26debec26b4e..16e3fce6f88d 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -3438,13 +3438,6 @@ void tty_driver_kref_put(struct tty_driver *driver) } EXPORT_SYMBOL(tty_driver_kref_put); -void tty_set_operations(struct tty_driver *driver, - const struct tty_operations *op) -{ - driver->ops = op; -}; -EXPORT_SYMBOL(tty_set_operations); - void put_tty_driver(struct tty_driver *d) { tty_driver_kref_put(d); diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index c7746dee58a6..6092ce9180aa 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -330,8 +330,6 @@ extern struct list_head tty_drivers; extern struct tty_driver *__tty_alloc_driver(unsigned int lines, struct module *owner, unsigned long flags); extern void put_tty_driver(struct tty_driver *driver); -extern void tty_set_operations(struct tty_driver *driver, - const struct tty_operations *op); extern struct tty_driver *tty_find_polling_driver(char *name, int *line); extern void tty_driver_kref_put(struct tty_driver *driver); @@ -346,6 +344,12 @@ static inline struct tty_driver *tty_driver_kref_get(struct tty_driver *d) return d; } +static inline void tty_set_operations(struct tty_driver *driver, + const struct tty_operations *op) +{ + driver->ops = op; +} + /* tty driver magic number */ #define TTY_DRIVER_MAGIC 0x5402 -- cgit v1.2.3 From 9f90a4ddef4e4d3aa4229f6b117d4e57231457b3 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 23 Jul 2021 09:43:16 +0200 Subject: tty: drop put_tty_driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit put_tty_driver() is an alias for tty_driver_kref_put(). There is no need for two exported identical functions, therefore switch all users of old put_tty_driver() to new tty_driver_kref_put() and remove the former for good. Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Geert Uytterhoeven Cc: Jeff Dike Cc: Richard Weinberger Cc: Anton Ivanov Cc: Chris Zankel Cc: Max Filippov Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Samuel Iglesias Gonsalvez Cc: Jens Taprogge Cc: Karsten Keil Cc: Scott Branden Cc: Ulf Hansson Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: David Lin Cc: Johan Hovold Cc: Alex Elder Cc: Jiri Slaby Cc: Laurentiu Tudor Cc: Jiri Kosina Cc: David Sterba Cc: Shawn Guo Cc: Sascha Hauer Cc: Pengutronix Kernel Team Cc: Fabio Estevam Cc: NXP Linux Team Cc: Oliver Neukum Cc: Felipe Balbi Cc: Mathias Nyman Cc: Marcel Holtmann Cc: Johan Hedberg Cc: Luiz Augusto von Dentz Acked-by: Alex Elder Acked-by: Christian Borntraeger Acked-by: Max Filippov Acked-by: David Sterba Acked-by: Samuel Iglesias Gonsálvez Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210723074317.32690-8-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- arch/alpha/kernel/srmcons.c | 2 +- arch/m68k/emu/nfcon.c | 4 ++-- arch/um/drivers/line.c | 2 +- arch/xtensa/platforms/iss/console.c | 2 +- drivers/char/pcmcia/synclink_cs.c | 4 ++-- drivers/char/ttyprintk.c | 4 ++-- drivers/ipack/devices/ipoctal.c | 4 ++-- drivers/isdn/capi/capi.c | 4 ++-- drivers/misc/bcm-vk/bcm_vk_tty.c | 8 ++++---- drivers/mmc/core/sdio_uart.c | 4 ++-- drivers/net/usb/hso.c | 4 ++-- drivers/s390/char/con3215.c | 4 ++-- drivers/s390/char/sclp_tty.c | 8 ++++---- drivers/s390/char/sclp_vt220.c | 2 +- drivers/s390/char/tty3270.c | 4 ++-- drivers/staging/fwserial/fwserial.c | 8 ++++---- drivers/staging/gdm724x/gdm_tty.c | 4 ++-- drivers/staging/greybus/uart.c | 4 ++-- drivers/tty/amiserial.c | 8 ++++---- drivers/tty/ehv_bytechan.c | 6 +++--- drivers/tty/goldfish.c | 4 ++-- drivers/tty/hvc/hvc_console.c | 2 +- drivers/tty/hvc/hvcs.c | 4 ++-- drivers/tty/ipwireless/tty.c | 4 ++-- drivers/tty/mips_ejtag_fdc.c | 2 +- drivers/tty/moxa.c | 4 ++-- drivers/tty/mxser.c | 4 ++-- drivers/tty/n_gsm.c | 4 ++-- drivers/tty/nozomi.c | 4 ++-- drivers/tty/serial/kgdb_nmi.c | 4 ++-- drivers/tty/serial/serial_core.c | 4 ++-- drivers/tty/synclink_gt.c | 4 ++-- drivers/tty/tty_io.c | 6 ------ drivers/tty/ttynull.c | 4 ++-- drivers/tty/vcc.c | 4 ++-- drivers/usb/class/cdc-acm.c | 6 +++--- drivers/usb/gadget/function/u_serial.c | 4 ++-- drivers/usb/host/xhci-dbgtty.c | 4 ++-- drivers/usb/serial/usb-serial.c | 4 ++-- include/linux/tty_driver.h | 1 - net/bluetooth/rfcomm/tty.c | 4 ++-- 41 files changed, 82 insertions(+), 89 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c index d0a1b08d851d..90635ef5dafa 100644 --- a/arch/alpha/kernel/srmcons.c +++ b/arch/alpha/kernel/srmcons.c @@ -221,7 +221,7 @@ srmcons_init(void) tty_port_link_device(&srmcons_singleton.port, driver, 0); err = tty_register_driver(driver); if (err) { - put_tty_driver(driver); + tty_driver_kref_put(driver); tty_port_destroy(&srmcons_singleton.port); return err; } diff --git a/arch/m68k/emu/nfcon.c b/arch/m68k/emu/nfcon.c index b3b64d03bad6..557d60867f98 100644 --- a/arch/m68k/emu/nfcon.c +++ b/arch/m68k/emu/nfcon.c @@ -144,7 +144,7 @@ static int __init nfcon_init(void) res = tty_register_driver(driver); if (res) { pr_err("failed to register nfcon tty driver\n"); - put_tty_driver(driver); + tty_driver_kref_put(driver); tty_port_destroy(&nfcon_tty_port); return res; } @@ -161,7 +161,7 @@ static void __exit nfcon_exit(void) { unregister_console(&nf_console); tty_unregister_driver(nfcon_tty_driver); - put_tty_driver(nfcon_tty_driver); + tty_driver_kref_put(nfcon_tty_driver); tty_port_destroy(&nfcon_tty_port); } diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 0d8f4ee6335d..8febf95da96e 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -568,7 +568,7 @@ int register_lines(struct line_driver *line_driver, if (err) { printk(KERN_ERR "register_lines : can't register %s driver\n", line_driver->name); - put_tty_driver(driver); + tty_driver_kref_put(driver); for (i = 0; i < nlines; i++) tty_port_destroy(&lines[i].port); return err; diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 0b8a0565cdfd..81f988914d9a 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -178,7 +178,7 @@ static int __init rs_init(void) static __exit void rs_exit(void) { tty_unregister_driver(serial_driver); - put_tty_driver(serial_driver); + tty_driver_kref_put(serial_driver); tty_port_destroy(&serial_port); } diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c index 6eaefea0520e..fd78d5856841 100644 --- a/drivers/char/pcmcia/synclink_cs.c +++ b/drivers/char/pcmcia/synclink_cs.c @@ -2841,7 +2841,7 @@ static int __init synclink_cs_init(void) err_unreg_tty: tty_unregister_driver(serial_driver); err_put_tty: - put_tty_driver(serial_driver); + tty_driver_kref_put(serial_driver); err: return rc; } @@ -2850,7 +2850,7 @@ static void __exit synclink_cs_exit(void) { pcmcia_unregister_driver(&mgslpc_driver); tty_unregister_driver(serial_driver); - put_tty_driver(serial_driver); + tty_driver_kref_put(serial_driver); } module_init(synclink_cs_init); diff --git a/drivers/char/ttyprintk.c b/drivers/char/ttyprintk.c index 230b2c9b3e3c..adf941c47506 100644 --- a/drivers/char/ttyprintk.c +++ b/drivers/char/ttyprintk.c @@ -198,7 +198,7 @@ static int __init ttyprintk_init(void) return 0; error: - put_tty_driver(ttyprintk_driver); + tty_driver_kref_put(ttyprintk_driver); tty_port_destroy(&tpk_port.port); return ret; } @@ -206,7 +206,7 @@ error: static void __exit ttyprintk_exit(void) { tty_unregister_driver(ttyprintk_driver); - put_tty_driver(ttyprintk_driver); + tty_driver_kref_put(ttyprintk_driver); tty_port_destroy(&tpk_port.port); } diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c index be6d11f46e62..c14e65a5d38f 100644 --- a/drivers/ipack/devices/ipoctal.c +++ b/drivers/ipack/devices/ipoctal.c @@ -371,7 +371,7 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, res = tty_register_driver(tty); if (res) { dev_err(&ipoctal->dev->dev, "Can't register tty driver.\n"); - put_tty_driver(tty); + tty_driver_kref_put(tty); return res; } @@ -696,7 +696,7 @@ static void __ipoctal_remove(struct ipoctal *ipoctal) } tty_unregister_driver(ipoctal->tty_drv); - put_tty_driver(ipoctal->tty_drv); + tty_driver_kref_put(ipoctal->tty_drv); kfree(ipoctal); } diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c index 32abf4d15450..0f00be62438d 100644 --- a/drivers/isdn/capi/capi.c +++ b/drivers/isdn/capi/capi.c @@ -1290,7 +1290,7 @@ static int __init capinc_tty_init(void) err = tty_register_driver(drv); if (err) { - put_tty_driver(drv); + tty_driver_kref_put(drv); kfree(capiminors); printk(KERN_ERR "Couldn't register capi_nc driver\n"); return err; @@ -1302,7 +1302,7 @@ static int __init capinc_tty_init(void) static void __exit capinc_tty_exit(void) { tty_unregister_driver(capinc_tty_driver); - put_tty_driver(capinc_tty_driver); + tty_driver_kref_put(capinc_tty_driver); kfree(capiminors); } diff --git a/drivers/misc/bcm-vk/bcm_vk_tty.c b/drivers/misc/bcm-vk/bcm_vk_tty.c index dae9eeed84a2..1b6076a89ca6 100644 --- a/drivers/misc/bcm-vk/bcm_vk_tty.c +++ b/drivers/misc/bcm-vk/bcm_vk_tty.c @@ -249,7 +249,7 @@ int bcm_vk_tty_init(struct bcm_vk *vk, char *name) tty_drv->name = kstrdup(name, GFP_KERNEL); if (!tty_drv->name) { err = -ENOMEM; - goto err_put_tty_driver; + goto err_tty_driver_kref_put; } tty_drv->type = TTY_DRIVER_TYPE_SERIAL; tty_drv->subtype = SERIAL_TYPE_NORMAL; @@ -295,8 +295,8 @@ err_kfree_tty_name: kfree(tty_drv->name); tty_drv->name = NULL; -err_put_tty_driver: - put_tty_driver(tty_drv); +err_tty_driver_kref_put: + tty_driver_kref_put(tty_drv); return err; } @@ -317,7 +317,7 @@ void bcm_vk_tty_exit(struct bcm_vk *vk) kfree(vk->tty_drv->name); vk->tty_drv->name = NULL; - put_tty_driver(vk->tty_drv); + tty_driver_kref_put(vk->tty_drv); } void bcm_vk_tty_terminate_tty_user(struct bcm_vk *vk) diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c index 04a57832e486..04c0823e0359 100644 --- a/drivers/mmc/core/sdio_uart.c +++ b/drivers/mmc/core/sdio_uart.c @@ -1165,7 +1165,7 @@ static int __init sdio_uart_init(void) err2: tty_unregister_driver(tty_drv); err1: - put_tty_driver(tty_drv); + tty_driver_kref_put(tty_drv); return ret; } @@ -1173,7 +1173,7 @@ static void __exit sdio_uart_exit(void) { sdio_unregister_driver(&sdio_uart_driver); tty_unregister_driver(sdio_uart_tty_driver); - put_tty_driver(sdio_uart_tty_driver); + tty_driver_kref_put(sdio_uart_tty_driver); } module_init(sdio_uart_init); diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 6ecb6d7893a8..48192de045fc 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -3269,7 +3269,7 @@ static int __init hso_init(void) err_unreg_tty: tty_unregister_driver(tty_drv); err_free_tty: - put_tty_driver(tty_drv); + tty_driver_kref_put(tty_drv); return result; } @@ -3280,7 +3280,7 @@ static void __exit hso_exit(void) tty_unregister_driver(tty_drv); /* deregister the usb driver */ usb_deregister(&hso_driver); - put_tty_driver(tty_drv); + tty_driver_kref_put(tty_drv); } /* Module definitions */ diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index 3818a89aef5c..f356607835d8 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -1082,7 +1082,7 @@ static int __init tty3215_init(void) ret = ccw_driver_register(&raw3215_ccw_driver); if (ret) { - put_tty_driver(driver); + tty_driver_kref_put(driver); return ret; } /* @@ -1104,7 +1104,7 @@ static int __init tty3215_init(void) tty_set_operations(driver, &tty3215_ops); ret = tty_register_driver(driver); if (ret) { - put_tty_driver(driver); + tty_driver_kref_put(driver); return ret; } tty3215_driver = driver; diff --git a/drivers/s390/char/sclp_tty.c b/drivers/s390/char/sclp_tty.c index 48790f8fb3b1..971fbb52740b 100644 --- a/drivers/s390/char/sclp_tty.c +++ b/drivers/s390/char/sclp_tty.c @@ -509,14 +509,14 @@ sclp_tty_init(void) rc = sclp_rw_init(); if (rc) { - put_tty_driver(driver); + tty_driver_kref_put(driver); return rc; } /* Allocate pages for output buffering */ for (i = 0; i < MAX_KMEM_PAGES; i++) { page = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA); if (page == NULL) { - put_tty_driver(driver); + tty_driver_kref_put(driver); return -ENOMEM; } list_add_tail((struct list_head *) page, &sclp_tty_pages); @@ -532,7 +532,7 @@ sclp_tty_init(void) rc = sclp_register(&sclp_input_event); if (rc) { - put_tty_driver(driver); + tty_driver_kref_put(driver); return rc; } @@ -552,7 +552,7 @@ sclp_tty_init(void) tty_port_link_device(&sclp_port, driver, 0); rc = tty_register_driver(driver); if (rc) { - put_tty_driver(driver); + tty_driver_kref_put(driver); tty_port_destroy(&sclp_port); return rc; } diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c index c6a7ea32aa5c..29a6a0099f83 100644 --- a/drivers/s390/char/sclp_vt220.c +++ b/drivers/s390/char/sclp_vt220.c @@ -763,7 +763,7 @@ out_reg: out_init: __sclp_vt220_cleanup(); out_driver: - put_tty_driver(driver); + tty_driver_kref_put(driver); return rc; } __initcall(sclp_vt220_tty_init); diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c index adc33846bf8e..5c83f71c1d0e 100644 --- a/drivers/s390/char/tty3270.c +++ b/drivers/s390/char/tty3270.c @@ -1935,7 +1935,7 @@ static int __init tty3270_init(void) tty_set_operations(driver, &tty3270_ops); ret = tty_register_driver(driver); if (ret) { - put_tty_driver(driver); + tty_driver_kref_put(driver); return ret; } tty3270_driver = driver; @@ -1952,7 +1952,7 @@ tty3270_exit(void) driver = tty3270_driver; tty3270_driver = NULL; tty_unregister_driver(driver); - put_tty_driver(driver); + tty_driver_kref_put(driver); tty3270_del_views(); } diff --git a/drivers/staging/fwserial/fwserial.c b/drivers/staging/fwserial/fwserial.c index 38a280e876c2..e8fa7f53cd5e 100644 --- a/drivers/staging/fwserial/fwserial.c +++ b/drivers/staging/fwserial/fwserial.c @@ -2852,11 +2852,11 @@ unregister_loop: tty_unregister_driver(fwloop_driver); put_loop: if (create_loop_dev) - put_tty_driver(fwloop_driver); + tty_driver_kref_put(fwloop_driver); unregister_driver: tty_unregister_driver(fwtty_driver); put_tty: - put_tty_driver(fwtty_driver); + tty_driver_kref_put(fwtty_driver); remove_debugfs: debugfs_remove_recursive(fwserial_debugfs); @@ -2871,10 +2871,10 @@ static void __exit fwserial_exit(void) kmem_cache_destroy(fwtty_txn_cache); if (create_loop_dev) { tty_unregister_driver(fwloop_driver); - put_tty_driver(fwloop_driver); + tty_driver_kref_put(fwloop_driver); } tty_unregister_driver(fwtty_driver); - put_tty_driver(fwtty_driver); + tty_driver_kref_put(fwtty_driver); debugfs_remove_recursive(fwserial_debugfs); } diff --git a/drivers/staging/gdm724x/gdm_tty.c b/drivers/staging/gdm724x/gdm_tty.c index 918575417264..04df6f9f5403 100644 --- a/drivers/staging/gdm724x/gdm_tty.c +++ b/drivers/staging/gdm724x/gdm_tty.c @@ -299,7 +299,7 @@ int register_lte_tty_driver(void) ret = tty_register_driver(tty_driver); if (ret) { - put_tty_driver(tty_driver); + tty_driver_kref_put(tty_driver); return ret; } @@ -318,7 +318,7 @@ void unregister_lte_tty_driver(void) tty_driver = gdm_driver[i]; if (tty_driver) { tty_unregister_driver(tty_driver); - put_tty_driver(tty_driver); + tty_driver_kref_put(tty_driver); } } } diff --git a/drivers/staging/greybus/uart.c b/drivers/staging/greybus/uart.c index 73f01ed1e5b7..e6d860a9678e 100644 --- a/drivers/staging/greybus/uart.c +++ b/drivers/staging/greybus/uart.c @@ -973,7 +973,7 @@ static int gb_tty_init(void) return 0; fail_put_gb_tty: - put_tty_driver(gb_tty_driver); + tty_driver_kref_put(gb_tty_driver); fail_unregister_dev: return retval; } @@ -981,7 +981,7 @@ fail_unregister_dev: static void gb_tty_exit(void) { tty_unregister_driver(gb_tty_driver); - put_tty_driver(gb_tty_driver); + tty_driver_kref_put(gb_tty_driver); idr_destroy(&tty_minors); } diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c index 50f1a54ef35a..1e60dbef676c 100644 --- a/drivers/tty/amiserial.c +++ b/drivers/tty/amiserial.c @@ -1519,7 +1519,7 @@ static int __init amiga_serial_probe(struct platform_device *pdev) error = tty_register_driver(driver); if (error) - goto fail_put_tty_driver; + goto fail_tty_driver_kref_put; printk(KERN_INFO "ttyS0 is the amiga builtin serial port\n"); @@ -1566,9 +1566,9 @@ fail_free_irq: free_irq(IRQ_AMIGA_TBE, state); fail_unregister: tty_unregister_driver(driver); -fail_put_tty_driver: +fail_tty_driver_kref_put: tty_port_destroy(&state->tport); - put_tty_driver(driver); + tty_driver_kref_put(driver); return error; } @@ -1577,7 +1577,7 @@ static int __exit amiga_serial_remove(struct platform_device *pdev) struct serial_state *state = platform_get_drvdata(pdev); tty_unregister_driver(serial_driver); - put_tty_driver(serial_driver); + tty_driver_kref_put(serial_driver); tty_port_destroy(&state->tport); free_irq(IRQ_AMIGA_TBE, state); diff --git a/drivers/tty/ehv_bytechan.c b/drivers/tty/ehv_bytechan.c index f580a5de3c98..19d32cb6af84 100644 --- a/drivers/tty/ehv_bytechan.c +++ b/drivers/tty/ehv_bytechan.c @@ -791,7 +791,7 @@ static int __init ehv_bc_init(void) ret = tty_register_driver(driver); if (ret) { pr_err("ehv-bc: could not register tty driver (ret=%i)\n", ret); - goto err_put_tty_driver; + goto err_tty_driver_kref_put; } ehv_bc_driver = driver; @@ -808,8 +808,8 @@ static int __init ehv_bc_init(void) err_deregister_tty_driver: ehv_bc_driver = NULL; tty_unregister_driver(driver); -err_put_tty_driver: - put_tty_driver(driver); +err_tty_driver_kref_put: + tty_driver_kref_put(driver); err_free_bcs: kfree(bcs); diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c index 853083fcebb8..d24af649a8bb 100644 --- a/drivers/tty/goldfish.c +++ b/drivers/tty/goldfish.c @@ -274,7 +274,7 @@ static int goldfish_tty_create_driver(void) return 0; err_tty_register_driver_failed: - put_tty_driver(tty); + tty_driver_kref_put(tty); err_tty_alloc_driver_failed: kfree(goldfish_ttys); goldfish_ttys = NULL; @@ -285,7 +285,7 @@ err_alloc_goldfish_ttys_failed: static void goldfish_tty_delete_driver(void) { tty_unregister_driver(goldfish_tty_driver); - put_tty_driver(goldfish_tty_driver); + tty_driver_kref_put(goldfish_tty_driver); goldfish_tty_driver = NULL; kfree(goldfish_ttys); goldfish_ttys = NULL; diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index 9215dd4bd9f0..7b30d5a05e2f 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -1063,7 +1063,7 @@ stop_thread: kthread_stop(hvc_task); hvc_task = NULL; put_tty: - put_tty_driver(drv); + tty_driver_kref_put(drv); out: return err; } diff --git a/drivers/tty/hvc/hvcs.c b/drivers/tty/hvc/hvcs.c index 23aebc964201..245da1dfd818 100644 --- a/drivers/tty/hvc/hvcs.c +++ b/drivers/tty/hvc/hvcs.c @@ -1509,7 +1509,7 @@ buff_alloc_fail: register_fail: hvcs_free_index_list(); index_fail: - put_tty_driver(hvcs_tty_driver); + tty_driver_kref_put(hvcs_tty_driver); hvcs_tty_driver = NULL; mutex_unlock(&hvcs_init_mutex); return rc; @@ -1562,7 +1562,7 @@ static void __exit hvcs_module_exit(void) hvcs_free_index_list(); - put_tty_driver(hvcs_tty_driver); + tty_driver_kref_put(hvcs_tty_driver); printk(KERN_INFO "HVCS: driver module removed.\n"); } diff --git a/drivers/tty/ipwireless/tty.c b/drivers/tty/ipwireless/tty.c index d24404c222e0..9edd5ae17580 100644 --- a/drivers/tty/ipwireless/tty.c +++ b/drivers/tty/ipwireless/tty.c @@ -585,7 +585,7 @@ int ipwireless_tty_init(void) if (result) { printk(KERN_ERR IPWIRELESS_PCCARD_NAME ": failed to register tty driver\n"); - put_tty_driver(ipw_tty_driver); + tty_driver_kref_put(ipw_tty_driver); return result; } @@ -595,7 +595,7 @@ int ipwireless_tty_init(void) void ipwireless_tty_release(void) { tty_unregister_driver(ipw_tty_driver); - put_tty_driver(ipw_tty_driver); + tty_driver_kref_put(ipw_tty_driver); } int ipwireless_tty_is_modem(struct ipw_tty *tty) diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c index 3b5915b94fac..02c10a968de1 100644 --- a/drivers/tty/mips_ejtag_fdc.c +++ b/drivers/tty/mips_ejtag_fdc.c @@ -1042,7 +1042,7 @@ err_destroy_ports: dport = &priv->ports[nport]; tty_port_destroy(&dport->port); } - put_tty_driver(priv->driver); + tty_driver_kref_put(priv->driver); return ret; } diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c index 64b18177c790..776f78de0f82 100644 --- a/drivers/tty/moxa.c +++ b/drivers/tty/moxa.c @@ -1053,7 +1053,7 @@ static int __init moxa_init(void) if (tty_register_driver(moxaDriver)) { printk(KERN_ERR "can't register MOXA Smartio tty driver!\n"); - put_tty_driver(moxaDriver); + tty_driver_kref_put(moxaDriver); return -1; } @@ -1119,7 +1119,7 @@ static void __exit moxa_exit(void) del_timer_sync(&moxaTimer); tty_unregister_driver(moxaDriver); - put_tty_driver(moxaDriver); + tty_driver_kref_put(moxaDriver); } module_init(moxa_init); diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c index 650fc6fac88e..335e4e50d679 100644 --- a/drivers/tty/mxser.c +++ b/drivers/tty/mxser.c @@ -2008,7 +2008,7 @@ static int __init mxser_module_init(void) err_unr: tty_unregister_driver(mxvar_sdriver); err_put: - put_tty_driver(mxvar_sdriver); + tty_driver_kref_put(mxvar_sdriver); return retval; } @@ -2016,7 +2016,7 @@ static void __exit mxser_module_exit(void) { pci_unregister_driver(&mxser_driver); tty_unregister_driver(mxvar_sdriver); - put_tty_driver(mxvar_sdriver); + tty_driver_kref_put(mxvar_sdriver); } module_init(mxser_module_init); diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 0308669c21c6..1d92d2a84889 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -3279,7 +3279,7 @@ static int __init gsm_init(void) gsm_tty_driver->major, gsm_tty_driver->minor_start); return 0; err_put_driver: - put_tty_driver(gsm_tty_driver); + tty_driver_kref_put(gsm_tty_driver); err_unreg_ldisc: tty_unregister_ldisc(&tty_ldisc_packet); return status; @@ -3289,7 +3289,7 @@ static void __exit gsm_exit(void) { tty_unregister_ldisc(&tty_ldisc_packet); tty_unregister_driver(gsm_tty_driver); - put_tty_driver(gsm_tty_driver); + tty_driver_kref_put(gsm_tty_driver); } module_init(gsm_init); diff --git a/drivers/tty/nozomi.c b/drivers/tty/nozomi.c index f3eb0aaec79b..0454c78deee6 100644 --- a/drivers/tty/nozomi.c +++ b/drivers/tty/nozomi.c @@ -1857,7 +1857,7 @@ static __init int nozomi_init(void) unr_tty: tty_unregister_driver(ntty_driver); free_tty: - put_tty_driver(ntty_driver); + tty_driver_kref_put(ntty_driver); return ret; } @@ -1865,7 +1865,7 @@ static __exit void nozomi_exit(void) { pci_unregister_driver(&nozomi_driver); tty_unregister_driver(ntty_driver); - put_tty_driver(ntty_driver); + tty_driver_kref_put(ntty_driver); } module_init(nozomi_init); diff --git a/drivers/tty/serial/kgdb_nmi.c b/drivers/tty/serial/kgdb_nmi.c index 9209573a7e37..55c3c9db7462 100644 --- a/drivers/tty/serial/kgdb_nmi.c +++ b/drivers/tty/serial/kgdb_nmi.c @@ -355,7 +355,7 @@ int kgdb_register_nmi_console(void) return 0; err_drv_reg: - put_tty_driver(kgdb_nmi_tty_driver); + tty_driver_kref_put(kgdb_nmi_tty_driver); return ret; } EXPORT_SYMBOL_GPL(kgdb_register_nmi_console); @@ -373,7 +373,7 @@ int kgdb_unregister_nmi_console(void) return ret; tty_unregister_driver(kgdb_nmi_tty_driver); - put_tty_driver(kgdb_nmi_tty_driver); + tty_driver_kref_put(kgdb_nmi_tty_driver); return 0; } diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index eb1401b61a90..0e2e35ab64c7 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2568,7 +2568,7 @@ int uart_register_driver(struct uart_driver *drv) for (i = 0; i < drv->nr; i++) tty_port_destroy(&drv->state[i].port); - put_tty_driver(normal); + tty_driver_kref_put(normal); out_kfree: kfree(drv->state); out: @@ -2590,7 +2590,7 @@ void uart_unregister_driver(struct uart_driver *drv) unsigned int i; tty_unregister_driver(p); - put_tty_driver(p); + tty_driver_kref_put(p); for (i = 0; i < drv->nr; i++) tty_port_destroy(&drv->state[i].port); kfree(drv->state); diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c index 525f3a568c32..c89f7de38d12 100644 --- a/drivers/tty/synclink_gt.c +++ b/drivers/tty/synclink_gt.c @@ -3650,7 +3650,7 @@ static void slgt_cleanup(void) for (info=slgt_device_list ; info != NULL ; info=info->next_device) tty_unregister_device(serial_driver, info->line); tty_unregister_driver(serial_driver); - put_tty_driver(serial_driver); + tty_driver_kref_put(serial_driver); } /* reset devices */ @@ -3712,7 +3712,7 @@ static int __init slgt_init(void) tty_set_operations(serial_driver, &ops); if ((rc = tty_register_driver(serial_driver)) < 0) { DBGERR(("%s can't register serial driver\n", driver_name)); - put_tty_driver(serial_driver); + tty_driver_kref_put(serial_driver); serial_driver = NULL; goto error; } diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 16e3fce6f88d..e8532006e960 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -3438,12 +3438,6 @@ void tty_driver_kref_put(struct tty_driver *driver) } EXPORT_SYMBOL(tty_driver_kref_put); -void put_tty_driver(struct tty_driver *d) -{ - tty_driver_kref_put(d); -} -EXPORT_SYMBOL(put_tty_driver); - /* * Called by a tty driver to register itself. */ diff --git a/drivers/tty/ttynull.c b/drivers/tty/ttynull.c index af3311a24917..1d4438472442 100644 --- a/drivers/tty/ttynull.c +++ b/drivers/tty/ttynull.c @@ -84,7 +84,7 @@ static int __init ttynull_init(void) ret = tty_register_driver(driver); if (ret < 0) { - put_tty_driver(driver); + tty_driver_kref_put(driver); tty_port_destroy(&ttynull_port); return ret; } @@ -99,7 +99,7 @@ static void __exit ttynull_exit(void) { unregister_console(&ttynull_console); tty_unregister_driver(ttynull_driver); - put_tty_driver(ttynull_driver); + tty_driver_kref_put(ttynull_driver); tty_port_destroy(&ttynull_port); } diff --git a/drivers/tty/vcc.c b/drivers/tty/vcc.c index d06bcc3b4c07..e11383ae1e7e 100644 --- a/drivers/tty/vcc.c +++ b/drivers/tty/vcc.c @@ -1028,7 +1028,7 @@ static int vcc_tty_init(void) rv = tty_register_driver(vcc_tty_driver); if (rv) { pr_err("VCC: TTY driver registration failed\n"); - put_tty_driver(vcc_tty_driver); + tty_driver_kref_put(vcc_tty_driver); vcc_tty_driver = NULL; return rv; } @@ -1041,7 +1041,7 @@ static int vcc_tty_init(void) static void vcc_tty_exit(void) { tty_unregister_driver(vcc_tty_driver); - put_tty_driver(vcc_tty_driver); + tty_driver_kref_put(vcc_tty_driver); vccdbg("VCC: TTY driver unregistered\n"); vcc_tty_driver = NULL; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index c19b59583d9f..8bbd8e29e60d 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -2044,14 +2044,14 @@ static int __init acm_init(void) retval = tty_register_driver(acm_tty_driver); if (retval) { - put_tty_driver(acm_tty_driver); + tty_driver_kref_put(acm_tty_driver); return retval; } retval = usb_register(&acm_driver); if (retval) { tty_unregister_driver(acm_tty_driver); - put_tty_driver(acm_tty_driver); + tty_driver_kref_put(acm_tty_driver); return retval; } @@ -2064,7 +2064,7 @@ static void __exit acm_exit(void) { usb_deregister(&acm_driver); tty_unregister_driver(acm_tty_driver); - put_tty_driver(acm_tty_driver); + tty_driver_kref_put(acm_tty_driver); idr_destroy(&acm_minors); } diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 74289f68a2ab..72961c1beeef 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -1491,7 +1491,7 @@ static int userial_init(void) return status; fail: - put_tty_driver(driver); + tty_driver_kref_put(driver); return status; } module_init(userial_init); @@ -1499,7 +1499,7 @@ module_init(userial_init); static void userial_cleanup(void) { tty_unregister_driver(gs_tty_driver); - put_tty_driver(gs_tty_driver); + tty_driver_kref_put(gs_tty_driver); gs_tty_driver = NULL; } module_exit(userial_cleanup); diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c index bef104511352..6e784f2fc26d 100644 --- a/drivers/usb/host/xhci-dbgtty.c +++ b/drivers/usb/host/xhci-dbgtty.c @@ -541,7 +541,7 @@ static int dbc_tty_init(void) ret = tty_register_driver(dbc_tty_driver); if (ret) { pr_err("Can't register dbc tty driver\n"); - put_tty_driver(dbc_tty_driver); + tty_driver_kref_put(dbc_tty_driver); } return ret; } @@ -550,7 +550,7 @@ static void dbc_tty_exit(void) { if (dbc_tty_driver) { tty_unregister_driver(dbc_tty_driver); - put_tty_driver(dbc_tty_driver); + tty_driver_kref_put(dbc_tty_driver); dbc_tty_driver = NULL; } } diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index 2f7855da645f..090a78c948f2 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -1366,7 +1366,7 @@ exit_reg_driver: exit_bus: pr_err("%s - returning with error %d\n", __func__, result); - put_tty_driver(usb_serial_tty_driver); + tty_driver_kref_put(usb_serial_tty_driver); return result; } @@ -1378,7 +1378,7 @@ static void __exit usb_serial_exit(void) usb_serial_generic_deregister(); tty_unregister_driver(usb_serial_tty_driver); - put_tty_driver(usb_serial_tty_driver); + tty_driver_kref_put(usb_serial_tty_driver); bus_unregister(&usb_serial_bus_type); idr_destroy(&serial_minors); } diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 6092ce9180aa..c20431d8def8 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -329,7 +329,6 @@ extern struct list_head tty_drivers; extern struct tty_driver *__tty_alloc_driver(unsigned int lines, struct module *owner, unsigned long flags); -extern void put_tty_driver(struct tty_driver *driver); extern struct tty_driver *tty_find_polling_driver(char *name, int *line); extern void tty_driver_kref_put(struct tty_driver *driver); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 8ec0600cd927..ebd78fdbd6e8 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -1146,7 +1146,7 @@ int __init rfcomm_init_ttys(void) error = tty_register_driver(rfcomm_tty_driver); if (error) { BT_ERR("Can't register RFCOMM TTY driver"); - put_tty_driver(rfcomm_tty_driver); + tty_driver_kref_put(rfcomm_tty_driver); return error; } @@ -1158,5 +1158,5 @@ int __init rfcomm_init_ttys(void) void rfcomm_cleanup_ttys(void) { tty_unregister_driver(rfcomm_tty_driver); - put_tty_driver(rfcomm_tty_driver); + tty_driver_kref_put(rfcomm_tty_driver); } -- cgit v1.2.3 From 3df15d6f37246d2f12f53d915c41d806289d3d46 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 26 Jul 2021 15:43:22 +0200 Subject: vt: keyboard.c: make console an unsigned int The console variable is used everywhere in some fun pointer path and array indexes and for some reason isn't always declared as unsigned. This plays havoc with some static analysis tools so mark the variable as unsigned so we "know" we can not wrap the arrays backwards here. Cc: Jiri Slaby Cc: Andy Shevchenko Reported-by: Jordy Zomer Link: https://lore.kernel.org/r/20210726134322.2274919-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/keyboard.c | 30 +++++++++++++++--------------- include/linux/vt_kern.h | 30 +++++++++++++++--------------- 2 files changed, 30 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index e81c940a2ea1..c7fbbcdcc346 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -1171,7 +1171,7 @@ static inline unsigned char getleds(void) * * Check the status of a keyboard led flag and report it back */ -int vt_get_leds(int console, int flag) +int vt_get_leds(unsigned int console, int flag) { struct kbd_struct *kb = &kbd_table[console]; int ret; @@ -1193,7 +1193,7 @@ EXPORT_SYMBOL_GPL(vt_get_leds); * Set the LEDs on a console. This is a wrapper for the VT layer * so that we can keep kbd knowledge internal */ -void vt_set_led_state(int console, int leds) +void vt_set_led_state(unsigned int console, int leds) { struct kbd_struct *kb = &kbd_table[console]; setledstate(kb, leds); @@ -1212,7 +1212,7 @@ void vt_set_led_state(int console, int leds) * don't hold the lock. We probably need to split out an LED lock * but not during an -rc release! */ -void vt_kbd_con_start(int console) +void vt_kbd_con_start(unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; @@ -1229,7 +1229,7 @@ void vt_kbd_con_start(int console) * Handle console stop. This is a wrapper for the VT layer * so that we can keep kbd knowledge internal */ -void vt_kbd_con_stop(int console) +void vt_kbd_con_stop(unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; @@ -1825,7 +1825,7 @@ int vt_do_diacrit(unsigned int cmd, void __user *udp, int perm) * Update the keyboard mode bits while holding the correct locks. * Return 0 for success or an error code. */ -int vt_do_kdskbmode(int console, unsigned int arg) +int vt_do_kdskbmode(unsigned int console, unsigned int arg) { struct kbd_struct *kb = &kbd_table[console]; int ret = 0; @@ -1865,7 +1865,7 @@ int vt_do_kdskbmode(int console, unsigned int arg) * Update the keyboard meta bits while holding the correct locks. * Return 0 for success or an error code. */ -int vt_do_kdskbmeta(int console, unsigned int arg) +int vt_do_kdskbmeta(unsigned int console, unsigned int arg) { struct kbd_struct *kb = &kbd_table[console]; int ret = 0; @@ -2008,7 +2008,7 @@ out: } int vt_do_kdsk_ioctl(int cmd, struct kbentry __user *user_kbe, int perm, - int console) + unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; struct kbentry kbe; @@ -2097,7 +2097,7 @@ int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm) return ret; } -int vt_do_kdskled(int console, int cmd, unsigned long arg, int perm) +int vt_do_kdskled(unsigned int console, int cmd, unsigned long arg, int perm) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; @@ -2139,7 +2139,7 @@ int vt_do_kdskled(int console, int cmd, unsigned long arg, int perm) return -ENOIOCTLCMD; } -int vt_do_kdgkbmode(int console) +int vt_do_kdgkbmode(unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; /* This is a spot read so needs no locking */ @@ -2163,7 +2163,7 @@ int vt_do_kdgkbmode(int console) * * Report the meta flag status of this console */ -int vt_do_kdgkbmeta(int console) +int vt_do_kdgkbmeta(unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; /* Again a spot read so no locking */ @@ -2176,7 +2176,7 @@ int vt_do_kdgkbmeta(int console) * * Restore the unicode console state to its default */ -void vt_reset_unicode(int console) +void vt_reset_unicode(unsigned int console) { unsigned long flags; @@ -2204,7 +2204,7 @@ int vt_get_shift_state(void) * Reset the keyboard bits for a console as part of a general console * reset event */ -void vt_reset_keyboard(int console) +void vt_reset_keyboard(unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; @@ -2234,7 +2234,7 @@ void vt_reset_keyboard(int console) * caller must be sure that there are no synchronization needs */ -int vt_get_kbd_mode_bit(int console, int bit) +int vt_get_kbd_mode_bit(unsigned int console, int bit) { struct kbd_struct *kb = &kbd_table[console]; return vc_kbd_mode(kb, bit); @@ -2249,7 +2249,7 @@ int vt_get_kbd_mode_bit(int console, int bit) * caller must be sure that there are no synchronization needs */ -void vt_set_kbd_mode_bit(int console, int bit) +void vt_set_kbd_mode_bit(unsigned int console, int bit) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; @@ -2268,7 +2268,7 @@ void vt_set_kbd_mode_bit(int console, int bit) * caller must be sure that there are no synchronization needs */ -void vt_clr_kbd_mode_bit(int console, int bit) +void vt_clr_kbd_mode_bit(unsigned int console, int bit) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 0da94a6dee15..b5ab452fca5b 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -148,26 +148,26 @@ void hide_boot_cursor(bool hide); /* keyboard provided interfaces */ int vt_do_diacrit(unsigned int cmd, void __user *up, int eperm); -int vt_do_kdskbmode(int console, unsigned int arg); -int vt_do_kdskbmeta(int console, unsigned int arg); +int vt_do_kdskbmode(unsigned int console, unsigned int arg); +int vt_do_kdskbmeta(unsigned int console, unsigned int arg); int vt_do_kbkeycode_ioctl(int cmd, struct kbkeycode __user *user_kbkc, int perm); int vt_do_kdsk_ioctl(int cmd, struct kbentry __user *user_kbe, int perm, - int console); + unsigned int console); int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm); -int vt_do_kdskled(int console, int cmd, unsigned long arg, int perm); -int vt_do_kdgkbmode(int console); -int vt_do_kdgkbmeta(int console); -void vt_reset_unicode(int console); +int vt_do_kdskled(unsigned int console, int cmd, unsigned long arg, int perm); +int vt_do_kdgkbmode(unsigned int console); +int vt_do_kdgkbmeta(unsigned int console); +void vt_reset_unicode(unsigned int console); int vt_get_shift_state(void); -void vt_reset_keyboard(int console); -int vt_get_leds(int console, int flag); -int vt_get_kbd_mode_bit(int console, int bit); -void vt_set_kbd_mode_bit(int console, int bit); -void vt_clr_kbd_mode_bit(int console, int bit); -void vt_set_led_state(int console, int leds); -void vt_kbd_con_start(int console); -void vt_kbd_con_stop(int console); +void vt_reset_keyboard(unsigned int console); +int vt_get_leds(unsigned int console, int flag); +int vt_get_kbd_mode_bit(unsigned int console, int bit); +void vt_set_kbd_mode_bit(unsigned int console, int bit); +void vt_clr_kbd_mode_bit(unsigned int console, int bit); +void vt_set_led_state(unsigned int console, int leds); +void vt_kbd_con_start(unsigned int console); +void vt_kbd_con_stop(unsigned int console); void vc_scrolldelta_helper(struct vc_data *c, int lines, unsigned int rolled_over, void *_base, unsigned int size); -- cgit v1.2.3 From 2037f2991ddedded1ef4aaabe4caf11e306158dc Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Thu, 15 Jul 2021 17:07:50 +0800 Subject: usb: common: add helper to get role-switch-default-mode Add helper to get "role-switch-default-mode", and convert it to the corresponding enum usb_dr_mode Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/1626340078-29111-6-git-send-email-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/common/common.c | 20 ++++++++++++++++++++ include/linux/usb/otg.h | 1 + 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c index 347fb3d3894a..c9bdeb4ddcb5 100644 --- a/drivers/usb/common/common.c +++ b/drivers/usb/common/common.c @@ -200,6 +200,26 @@ enum usb_dr_mode usb_get_dr_mode(struct device *dev) } EXPORT_SYMBOL_GPL(usb_get_dr_mode); +/** + * usb_get_role_switch_default_mode - Get default mode for given device + * @dev: Pointer to the given device + * + * The function gets string from property 'role-switch-default-mode', + * and returns the corresponding enum usb_dr_mode. + */ +enum usb_dr_mode usb_get_role_switch_default_mode(struct device *dev) +{ + const char *str; + int ret; + + ret = device_property_read_string(dev, "role-switch-default-mode", &str); + if (ret < 0) + return USB_DR_MODE_UNKNOWN; + + return usb_get_dr_mode_from_string(str); +} +EXPORT_SYMBOL_GPL(usb_get_role_switch_default_mode); + /** * usb_decode_interval - Decode bInterval into the time expressed in 1us unit * @epd: The descriptor of the endpoint diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h index 7ceeecbb9e02..6475f880be37 100644 --- a/include/linux/usb/otg.h +++ b/include/linux/usb/otg.h @@ -128,5 +128,6 @@ enum usb_dr_mode { * and returns the corresponding enum usb_dr_mode */ extern enum usb_dr_mode usb_get_dr_mode(struct device *dev); +extern enum usb_dr_mode usb_get_role_switch_default_mode(struct device *dev); #endif /* __LINUX_USB_OTG_H */ -- cgit v1.2.3 From bf88fef0b6f1488abeca594d377991171c00e52a Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Sat, 17 Jul 2021 21:21:27 +0300 Subject: usb: otg-fsm: Fix hrtimer list corruption The HNP work can be re-scheduled while it's still in-fly. This results in re-initialization of the busy work, resetting the hrtimer's list node of the work and crashing kernel with null dereference within kernel/timer once work's timer is expired. It's very easy to trigger this problem by re-plugging USB cable quickly. Initialize HNP work only once to fix this trouble. Unable to handle kernel NULL pointer dereference at virtual address 00000126) ... PC is at __run_timers.part.0+0x150/0x228 LR is at __next_timer_interrupt+0x51/0x9c ... (__run_timers.part.0) from [] (run_timer_softirq+0x2f/0x50) (run_timer_softirq) from [] (__do_softirq+0xd5/0x2f0) (__do_softirq) from [] (irq_exit+0xab/0xb8) (irq_exit) from [] (handle_domain_irq+0x45/0x60) (handle_domain_irq) from [] (gic_handle_irq+0x6b/0x7c) (gic_handle_irq) from [] (__irq_svc+0x65/0xac) Cc: stable@vger.kernel.org Acked-by: Peter Chen Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20210717182134.30262-6-digetx@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/common/usb-otg-fsm.c | 6 +++++- include/linux/usb/otg-fsm.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c index 3740cf95560e..0697fde51d00 100644 --- a/drivers/usb/common/usb-otg-fsm.c +++ b/drivers/usb/common/usb-otg-fsm.c @@ -193,7 +193,11 @@ static void otg_start_hnp_polling(struct otg_fsm *fsm) if (!fsm->host_req_flag) return; - INIT_DELAYED_WORK(&fsm->hnp_polling_work, otg_hnp_polling_work); + if (!fsm->hnp_work_inited) { + INIT_DELAYED_WORK(&fsm->hnp_polling_work, otg_hnp_polling_work); + fsm->hnp_work_inited = true; + } + schedule_delayed_work(&fsm->hnp_polling_work, msecs_to_jiffies(T_HOST_REQ_POLL)); } diff --git a/include/linux/usb/otg-fsm.h b/include/linux/usb/otg-fsm.h index 3aee78dda16d..784659d4dc99 100644 --- a/include/linux/usb/otg-fsm.h +++ b/include/linux/usb/otg-fsm.h @@ -196,6 +196,7 @@ struct otg_fsm { struct mutex lock; u8 *host_req_flag; struct delayed_work hnp_polling_work; + bool hnp_work_inited; bool state_changed; }; -- cgit v1.2.3 From c25abcd625505f53b72dc156bac32b5120826742 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Mon, 12 Jul 2021 19:16:18 +0530 Subject: kdb: Get rid of redundant kdb_register_flags() Commit e4f291b3f7bb ("kdb: Simplify kdb commands registration") allowed registration of pre-allocated kdb commands with pointer to struct kdbtab_t. Lets switch other users as well to register pre- allocated kdb commands via: - Changing prototype for kdb_register() to pass a pointer to struct kdbtab_t instead. - Embed kdbtab_t structure in kdb_macro_t rather than individual params. With these changes kdb_register_flags() becomes redundant and hence removed. Also, since we have switched all users to register pre-allocated commands, "is_dynamic" flag in struct kdbtab_t becomes redundant and hence removed as well. Suggested-by: Daniel Thompson Signed-off-by: Sumit Garg Acked-by: Steven Rostedt (VMware) Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/20210712134620.276667-3-sumit.garg@linaro.org Signed-off-by: Daniel Thompson --- include/linux/kdb.h | 27 ++++--- kernel/debug/kdb/kdb_main.c | 167 +++++++++++++---------------------------- kernel/debug/kdb/kdb_private.h | 13 ---- kernel/trace/trace_kdb.c | 12 ++- samples/kdb/kdb_hello.c | 20 +++-- 5 files changed, 88 insertions(+), 151 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 0125a677b67f..de858edfb3b8 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -13,6 +13,8 @@ * Copyright (C) 2009 Jason Wessel */ +#include + /* Shifted versions of the command enable bits are be used if the command * has no arguments (see kdb_check_flags). This allows commands, such as * go, to have different permissions depending upon whether it is called @@ -64,6 +66,17 @@ typedef enum { typedef int (*kdb_func_t)(int, const char **); +/* The KDB shell command table */ +typedef struct _kdbtab { + char *cmd_name; /* Command name */ + kdb_func_t cmd_func; /* Function to execute command */ + char *cmd_usage; /* Usage String for this command */ + char *cmd_help; /* Help message for this command */ + short cmd_minlen; /* Minimum legal # cmd chars required */ + kdb_cmdflags_t cmd_flags; /* Command behaviour flags */ + struct list_head list_node; /* Command list */ +} kdbtab_t; + #ifdef CONFIG_KGDB_KDB #include #include @@ -193,19 +206,13 @@ static inline const char *kdb_walk_kallsyms(loff_t *pos) #endif /* ! CONFIG_KALLSYMS */ /* Dynamic kdb shell command registration */ -extern int kdb_register(char *, kdb_func_t, char *, char *, short); -extern int kdb_register_flags(char *, kdb_func_t, char *, char *, - short, kdb_cmdflags_t); -extern int kdb_unregister(char *); +extern int kdb_register(kdbtab_t *cmd); +extern void kdb_unregister(kdbtab_t *cmd); #else /* ! CONFIG_KGDB_KDB */ static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } static inline void kdb_init(int level) {} -static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, - char *help, short minlen) { return 0; } -static inline int kdb_register_flags(char *cmd, kdb_func_t func, char *usage, - char *help, short minlen, - kdb_cmdflags_t flags) { return 0; } -static inline int kdb_unregister(char *cmd) { return 0; } +static inline int kdb_register(kdbtab_t *cmd) { return 0; } +static inline void kdb_unregister(kdbtab_t *cmd) {} #endif /* CONFIG_KGDB_KDB */ enum { KDB_NOT_INITIALIZED, diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 5cf9867fa118..b2880fad26d4 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include #include @@ -657,9 +656,7 @@ static void kdb_cmderror(int diag) struct kdb_macro { int count; bool usable; - char *name; - char *usage; - char *help; + kdbtab_t cmd; char **command; }; static struct kdb_macro *kdb_macro; @@ -678,13 +675,7 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0) if (!s->count) s->usable = false; if (s->usable) - /* macros are always safe because when executed each - * internal command re-enters kdb_parse() and is - * safety checked individually. - */ - kdb_register_flags(s->name, kdb_exec_defcmd, s->usage, - s->help, 0, - KDB_ENABLE_ALWAYS_SAFE); + kdb_register(&s->cmd); return 0; } if (!s->usable) @@ -705,6 +696,8 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0) static int kdb_defcmd(int argc, const char **argv) { struct kdb_macro *save_kdb_macro = kdb_macro, *s; + kdbtab_t *mp; + if (defcmd_in_progress) { kdb_printf("kdb: nested defcmd detected, assuming missing " "endefcmd\n"); @@ -713,8 +706,8 @@ static int kdb_defcmd(int argc, const char **argv) if (argc == 0) { int i; for (s = kdb_macro; s < kdb_macro + kdb_macro_count; ++s) { - kdb_printf("defcmd %s \"%s\" \"%s\"\n", s->name, - s->usage, s->help); + kdb_printf("defcmd %s \"%s\" \"%s\"\n", s->cmd.cmd_name, + s->cmd.cmd_usage, s->cmd.cmd_help); for (i = 0; i < s->count; ++i) kdb_printf("%s", s->command[i]); kdb_printf("endefcmd\n"); @@ -736,31 +729,36 @@ static int kdb_defcmd(int argc, const char **argv) s = kdb_macro + kdb_macro_count; memset(s, 0, sizeof(*s)); s->usable = true; - s->name = kdb_strdup(argv[1], GFP_KDB); - if (!s->name) + + mp = &s->cmd; + mp->cmd_func = kdb_exec_defcmd; + mp->cmd_minlen = 0; + mp->cmd_flags = KDB_ENABLE_ALWAYS_SAFE; + mp->cmd_name = kdb_strdup(argv[1], GFP_KDB); + if (!mp->cmd_name) goto fail_name; - s->usage = kdb_strdup(argv[2], GFP_KDB); - if (!s->usage) + mp->cmd_usage = kdb_strdup(argv[2], GFP_KDB); + if (!mp->cmd_usage) goto fail_usage; - s->help = kdb_strdup(argv[3], GFP_KDB); - if (!s->help) + mp->cmd_help = kdb_strdup(argv[3], GFP_KDB); + if (!mp->cmd_help) goto fail_help; - if (s->usage[0] == '"') { - strcpy(s->usage, argv[2]+1); - s->usage[strlen(s->usage)-1] = '\0'; + if (mp->cmd_usage[0] == '"') { + strcpy(mp->cmd_usage, argv[2]+1); + mp->cmd_usage[strlen(mp->cmd_usage)-1] = '\0'; } - if (s->help[0] == '"') { - strcpy(s->help, argv[3]+1); - s->help[strlen(s->help)-1] = '\0'; + if (mp->cmd_help[0] == '"') { + strcpy(mp->cmd_help, argv[3]+1); + mp->cmd_help[strlen(mp->cmd_help)-1] = '\0'; } ++kdb_macro_count; defcmd_in_progress = true; kfree(save_kdb_macro); return 0; fail_help: - kfree(s->usage); + kfree(mp->cmd_usage); fail_usage: - kfree(s->name); + kfree(mp->cmd_name); fail_name: kfree(kdb_macro); fail_defcmd: @@ -785,7 +783,7 @@ static int kdb_exec_defcmd(int argc, const char **argv) if (argc != 0) return KDB_ARGCOUNT; for (s = kdb_macro, i = 0; i < kdb_macro_count; ++i, ++s) { - if (strcmp(s->name, argv[0]) == 0) + if (strcmp(s->cmd.cmd_name, argv[0]) == 0) break; } if (i == kdb_macro_count) { @@ -797,7 +795,7 @@ static int kdb_exec_defcmd(int argc, const char **argv) /* Recursive use of kdb_parse, do not use argv after * this point */ argv = NULL; - kdb_printf("[%s]kdb> %s\n", s->name, s->command[i]); + kdb_printf("[%s]kdb> %s\n", s->cmd.cmd_name, s->command[i]); ret = kdb_parse(s->command[i]); if (ret) return ret; @@ -2613,56 +2611,32 @@ static int kdb_grep_help(int argc, const char **argv) return 0; } -/* - * kdb_register_flags - This function is used to register a kernel - * debugger command. - * Inputs: - * cmd Command name - * func Function to execute the command - * usage A simple usage string showing arguments - * help A simple help string describing command - * repeat Does the command auto repeat on enter? - * Returns: - * zero for success, one if a duplicate command. +/** + * kdb_register() - This function is used to register a kernel debugger + * command. + * @cmd: pointer to kdb command + * + * Note that it's the job of the caller to keep the memory for the cmd + * allocated until unregister is called. */ -int kdb_register_flags(char *cmd, - kdb_func_t func, - char *usage, - char *help, - short minlen, - kdb_cmdflags_t flags) +int kdb_register(kdbtab_t *cmd) { kdbtab_t *kp; list_for_each_entry(kp, &kdb_cmds_head, list_node) { - if (strcmp(kp->cmd_name, cmd) == 0) { - kdb_printf("Duplicate kdb command registered: " - "%s, func %px help %s\n", cmd, func, help); + if (strcmp(kp->cmd_name, cmd->cmd_name) == 0) { + kdb_printf("Duplicate kdb cmd: %s, func %p help %s\n", + cmd->cmd_name, cmd->cmd_func, cmd->cmd_help); return 1; } } - kp = kmalloc(sizeof(*kp), GFP_KDB); - if (!kp) { - kdb_printf("Could not allocate new kdb_command table\n"); - return 1; - } - - kp->cmd_name = cmd; - kp->cmd_func = func; - kp->cmd_usage = usage; - kp->cmd_help = help; - kp->cmd_minlen = minlen; - kp->cmd_flags = flags; - kp->is_dynamic = true; - - list_add_tail(&kp->list_node, &kdb_cmds_head); - + list_add_tail(&cmd->list_node, &kdb_cmds_head); return 0; } -EXPORT_SYMBOL_GPL(kdb_register_flags); +EXPORT_SYMBOL_GPL(kdb_register); -/* +/** * kdb_register_table() - This function is used to register a kdb command * table. * @kp: pointer to kdb command table @@ -2676,55 +2650,15 @@ void kdb_register_table(kdbtab_t *kp, size_t len) } } -/* - * kdb_register - Compatibility register function for commands that do - * not need to specify a repeat state. Equivalent to - * kdb_register_flags with flags set to 0. - * Inputs: - * cmd Command name - * func Function to execute the command - * usage A simple usage string showing arguments - * help A simple help string describing command - * Returns: - * zero for success, one if a duplicate command. - */ -int kdb_register(char *cmd, - kdb_func_t func, - char *usage, - char *help, - short minlen) -{ - return kdb_register_flags(cmd, func, usage, help, minlen, 0); -} -EXPORT_SYMBOL_GPL(kdb_register); - -/* - * kdb_unregister - This function is used to unregister a kernel - * debugger command. It is generally called when a module which - * implements kdb commands is unloaded. - * Inputs: - * cmd Command name - * Returns: - * zero for success, one command not registered. +/** + * kdb_unregister() - This function is used to unregister a kernel debugger + * command. It is generally called when a module which + * implements kdb command is unloaded. + * @cmd: pointer to kdb command */ -int kdb_unregister(char *cmd) +void kdb_unregister(kdbtab_t *cmd) { - kdbtab_t *kp; - - /* - * find the command. - */ - list_for_each_entry(kp, &kdb_cmds_head, list_node) { - if (strcmp(kp->cmd_name, cmd) == 0) { - list_del(&kp->list_node); - if (kp->is_dynamic) - kfree(kp); - return 0; - } - } - - /* Couldn't find it. */ - return 1; + list_del(&cmd->list_node); } EXPORT_SYMBOL_GPL(kdb_unregister); @@ -2900,6 +2834,11 @@ static kdbtab_t maintab[] = { .cmd_func = kdb_defcmd, .cmd_usage = "name \"usage\" \"help\"", .cmd_help = "Define a set of commands, down to endefcmd", + /* + * Macros are always safe because when executed each + * internal command re-enters kdb_parse() and is safety + * checked individually. + */ .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, }, { .cmd_name = "kill", diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 8dbc840113c9..629590084a0d 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -164,19 +164,6 @@ typedef struct _kdb_bp { #ifdef CONFIG_KGDB_KDB extern kdb_bp_t kdb_breakpoints[/* KDB_MAXBPT */]; -/* The KDB shell command table */ -typedef struct _kdbtab { - char *cmd_name; /* Command name */ - kdb_func_t cmd_func; /* Function to execute command */ - char *cmd_usage; /* Usage String for this command */ - char *cmd_help; /* Help message for this command */ - short cmd_minlen; /* Minimum legal # command - * chars required */ - kdb_cmdflags_t cmd_flags; /* Command behaviour flags */ - struct list_head list_node; /* Command list */ - bool is_dynamic; /* Command table allocation type */ -} kdbtab_t; - extern void kdb_register_table(kdbtab_t *kp, size_t len); extern int kdb_bt(int, const char **); /* KDB display back trace */ diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index 9da76104f7a2..6c4f92c79e43 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -147,11 +147,17 @@ static int kdb_ftdump(int argc, const char **argv) return 0; } +static kdbtab_t ftdump_cmd = { + .cmd_name = "ftdump", + .cmd_func = kdb_ftdump, + .cmd_usage = "[skip_#entries] [cpu]", + .cmd_help = "Dump ftrace log; -skip dumps last #entries", + .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, +}; + static __init int kdb_ftrace_register(void) { - kdb_register_flags("ftdump", kdb_ftdump, "[skip_#entries] [cpu]", - "Dump ftrace log; -skip dumps last #entries", 0, - KDB_ENABLE_ALWAYS_SAFE); + kdb_register(&ftdump_cmd); return 0; } diff --git a/samples/kdb/kdb_hello.c b/samples/kdb/kdb_hello.c index c1c2fa0f62c2..9ad514a6648b 100644 --- a/samples/kdb/kdb_hello.c +++ b/samples/kdb/kdb_hello.c @@ -28,28 +28,26 @@ static int kdb_hello_cmd(int argc, const char **argv) return 0; } +static kdbtab_t hello_cmd = { + .cmd_name = "hello", + .cmd_func = kdb_hello_cmd, + .cmd_usage = "[string]", + .cmd_help = "Say Hello World or Hello [string]", +}; static int __init kdb_hello_cmd_init(void) { /* * Registration of a dynamically added kdb command is done with - * kdb_register() with the arguments being: - * 1: The name of the shell command - * 2: The function that processes the command - * 3: Description of the usage of any arguments - * 4: Descriptive text when you run help - * 5: Number of characters to complete the command - * 0 == type the whole command - * 1 == match both "g" and "go" for example + * kdb_register(). */ - kdb_register("hello", kdb_hello_cmd, "[string]", - "Say Hello World or Hello [string]", 0); + kdb_register(&hello_cmd); return 0; } static void __exit kdb_hello_cmd_exit(void) { - kdb_unregister("hello"); + kdb_unregister(&hello_cmd); } module_init(kdb_hello_cmd_init); -- cgit v1.2.3 From e868f0a3c4b9c1d7721f08b703142a876814a3f8 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Mon, 12 Jul 2021 19:16:20 +0530 Subject: kdb: Rename members of struct kdbtab_t Remove redundant prefix "cmd_" from name of members in struct kdbtab_t for better readibility. Suggested-by: Doug Anderson Signed-off-by: Sumit Garg Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/20210712134620.276667-5-sumit.garg@linaro.org Signed-off-by: Daniel Thompson --- include/linux/kdb.h | 12 +- kernel/debug/kdb/kdb_bp.c | 72 ++++---- kernel/debug/kdb/kdb_main.c | 404 ++++++++++++++++++++++---------------------- kernel/trace/trace_kdb.c | 10 +- samples/kdb/kdb_hello.c | 8 +- 5 files changed, 252 insertions(+), 254 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index de858edfb3b8..ea0f5e580fac 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -68,12 +68,12 @@ typedef int (*kdb_func_t)(int, const char **); /* The KDB shell command table */ typedef struct _kdbtab { - char *cmd_name; /* Command name */ - kdb_func_t cmd_func; /* Function to execute command */ - char *cmd_usage; /* Usage String for this command */ - char *cmd_help; /* Help message for this command */ - short cmd_minlen; /* Minimum legal # cmd chars required */ - kdb_cmdflags_t cmd_flags; /* Command behaviour flags */ + char *name; /* Command name */ + kdb_func_t func; /* Function to execute command */ + char *usage; /* Usage String for this command */ + char *help; /* Help message for this command */ + short minlen; /* Minimum legal # cmd chars required */ + kdb_cmdflags_t flags; /* Command behaviour flags */ struct list_head list_node; /* Command list */ } kdbtab_t; diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index 2168f8dacb99..372025cf1ca3 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -523,51 +523,51 @@ static int kdb_ss(int argc, const char **argv) } static kdbtab_t bptab[] = { - { .cmd_name = "bp", - .cmd_func = kdb_bp, - .cmd_usage = "[]", - .cmd_help = "Set/Display breakpoints", - .cmd_flags = KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS, + { .name = "bp", + .func = kdb_bp, + .usage = "[]", + .help = "Set/Display breakpoints", + .flags = KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS, }, - { .cmd_name = "bl", - .cmd_func = kdb_bp, - .cmd_usage = "[]", - .cmd_help = "Display breakpoints", - .cmd_flags = KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS, + { .name = "bl", + .func = kdb_bp, + .usage = "[]", + .help = "Display breakpoints", + .flags = KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS, }, - { .cmd_name = "bc", - .cmd_func = kdb_bc, - .cmd_usage = "", - .cmd_help = "Clear Breakpoint", - .cmd_flags = KDB_ENABLE_FLOW_CTRL, + { .name = "bc", + .func = kdb_bc, + .usage = "", + .help = "Clear Breakpoint", + .flags = KDB_ENABLE_FLOW_CTRL, }, - { .cmd_name = "be", - .cmd_func = kdb_bc, - .cmd_usage = "", - .cmd_help = "Enable Breakpoint", - .cmd_flags = KDB_ENABLE_FLOW_CTRL, + { .name = "be", + .func = kdb_bc, + .usage = "", + .help = "Enable Breakpoint", + .flags = KDB_ENABLE_FLOW_CTRL, }, - { .cmd_name = "bd", - .cmd_func = kdb_bc, - .cmd_usage = "", - .cmd_help = "Disable Breakpoint", - .cmd_flags = KDB_ENABLE_FLOW_CTRL, + { .name = "bd", + .func = kdb_bc, + .usage = "", + .help = "Disable Breakpoint", + .flags = KDB_ENABLE_FLOW_CTRL, }, - { .cmd_name = "ss", - .cmd_func = kdb_ss, - .cmd_usage = "", - .cmd_help = "Single Step", - .cmd_minlen = 1, - .cmd_flags = KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS, + { .name = "ss", + .func = kdb_ss, + .usage = "", + .help = "Single Step", + .minlen = 1, + .flags = KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS, }, }; static kdbtab_t bphcmd = { - .cmd_name = "bph", - .cmd_func = kdb_bp, - .cmd_usage = "[]", - .cmd_help = "[datar [length]|dataw [length]] Set hw brk", - .cmd_flags = KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS, + .name = "bph", + .func = kdb_bp, + .usage = "[]", + .help = "[datar [length]|dataw [length]] Set hw brk", + .flags = KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS, }; /* Initialize the breakpoint table and register breakpoint commands. */ diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 7c7a2ef834fc..fa6deda894a1 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -711,10 +711,9 @@ static int kdb_defcmd(int argc, const char **argv) struct kdb_macro_statement *kms; list_for_each_entry(kp, &kdb_cmds_head, list_node) { - if (kp->cmd_func == kdb_exec_defcmd) { + if (kp->func == kdb_exec_defcmd) { kdb_printf("defcmd %s \"%s\" \"%s\"\n", - kp->cmd_name, kp->cmd_usage, - kp->cmd_help); + kp->name, kp->usage, kp->help); kmp = container_of(kp, struct kdb_macro, cmd); list_for_each_entry(kms, &kmp->statements, list_node) @@ -735,34 +734,34 @@ static int kdb_defcmd(int argc, const char **argv) goto fail_defcmd; mp = &kdb_macro->cmd; - mp->cmd_func = kdb_exec_defcmd; - mp->cmd_minlen = 0; - mp->cmd_flags = KDB_ENABLE_ALWAYS_SAFE; - mp->cmd_name = kdb_strdup(argv[1], GFP_KDB); - if (!mp->cmd_name) + mp->func = kdb_exec_defcmd; + mp->minlen = 0; + mp->flags = KDB_ENABLE_ALWAYS_SAFE; + mp->name = kdb_strdup(argv[1], GFP_KDB); + if (!mp->name) goto fail_name; - mp->cmd_usage = kdb_strdup(argv[2], GFP_KDB); - if (!mp->cmd_usage) + mp->usage = kdb_strdup(argv[2], GFP_KDB); + if (!mp->usage) goto fail_usage; - mp->cmd_help = kdb_strdup(argv[3], GFP_KDB); - if (!mp->cmd_help) + mp->help = kdb_strdup(argv[3], GFP_KDB); + if (!mp->help) goto fail_help; - if (mp->cmd_usage[0] == '"') { - strcpy(mp->cmd_usage, argv[2]+1); - mp->cmd_usage[strlen(mp->cmd_usage)-1] = '\0'; + if (mp->usage[0] == '"') { + strcpy(mp->usage, argv[2]+1); + mp->usage[strlen(mp->usage)-1] = '\0'; } - if (mp->cmd_help[0] == '"') { - strcpy(mp->cmd_help, argv[3]+1); - mp->cmd_help[strlen(mp->cmd_help)-1] = '\0'; + if (mp->help[0] == '"') { + strcpy(mp->help, argv[3]+1); + mp->help[strlen(mp->help)-1] = '\0'; } INIT_LIST_HEAD(&kdb_macro->statements); defcmd_in_progress = true; return 0; fail_help: - kfree(mp->cmd_usage); + kfree(mp->usage); fail_usage: - kfree(mp->cmd_name); + kfree(mp->name); fail_name: kfree(kdb_macro); fail_defcmd: @@ -790,7 +789,7 @@ static int kdb_exec_defcmd(int argc, const char **argv) return KDB_ARGCOUNT; list_for_each_entry(kp, &kdb_cmds_head, list_node) { - if (strcmp(kp->cmd_name, argv[0]) == 0) + if (strcmp(kp->name, argv[0]) == 0) break; } if (list_entry_is_head(kp, &kdb_cmds_head, list_node)) { @@ -804,7 +803,7 @@ static int kdb_exec_defcmd(int argc, const char **argv) * Recursive use of kdb_parse, do not use argv after this point. */ argv = NULL; - kdb_printf("[%s]kdb> %s\n", kmp->cmd.cmd_name, kms->statement); + kdb_printf("[%s]kdb> %s\n", kmp->cmd.name, kms->statement); ret = kdb_parse(kms->statement); if (ret) return ret; @@ -1016,11 +1015,11 @@ int kdb_parse(const char *cmdstr) * If this command is allowed to be abbreviated, * check to see if this is it. */ - if (tp->cmd_minlen && (strlen(argv[0]) <= tp->cmd_minlen) && - (strncmp(argv[0], tp->cmd_name, tp->cmd_minlen) == 0)) + if (tp->minlen && (strlen(argv[0]) <= tp->minlen) && + (strncmp(argv[0], tp->name, tp->minlen) == 0)) break; - if (strcmp(argv[0], tp->cmd_name) == 0) + if (strcmp(argv[0], tp->name) == 0) break; } @@ -1031,8 +1030,7 @@ int kdb_parse(const char *cmdstr) */ if (list_entry_is_head(tp, &kdb_cmds_head, list_node)) { list_for_each_entry(tp, &kdb_cmds_head, list_node) { - if (strncmp(argv[0], tp->cmd_name, - strlen(tp->cmd_name)) == 0) + if (strncmp(argv[0], tp->name, strlen(tp->name)) == 0) break; } } @@ -1040,19 +1038,19 @@ int kdb_parse(const char *cmdstr) if (!list_entry_is_head(tp, &kdb_cmds_head, list_node)) { int result; - if (!kdb_check_flags(tp->cmd_flags, kdb_cmd_enabled, argc <= 1)) + if (!kdb_check_flags(tp->flags, kdb_cmd_enabled, argc <= 1)) return KDB_NOPERM; KDB_STATE_SET(CMD); - result = (*tp->cmd_func)(argc-1, (const char **)argv); + result = (*tp->func)(argc-1, (const char **)argv); if (result && ignore_errors && result > KDB_CMD_GO) result = 0; KDB_STATE_CLEAR(CMD); - if (tp->cmd_flags & KDB_REPEAT_WITH_ARGS) + if (tp->flags & KDB_REPEAT_WITH_ARGS) return result; - argc = tp->cmd_flags & KDB_REPEAT_NO_ARGS ? 1 : 0; + argc = tp->flags & KDB_REPEAT_NO_ARGS ? 1 : 0; if (argv[argc]) *(argv[argc]) = '\0'; return result; @@ -2419,12 +2417,12 @@ static int kdb_help(int argc, const char **argv) char *space = ""; if (KDB_FLAG(CMD_INTERRUPT)) return 0; - if (!kdb_check_flags(kt->cmd_flags, kdb_cmd_enabled, true)) + if (!kdb_check_flags(kt->flags, kdb_cmd_enabled, true)) continue; - if (strlen(kt->cmd_usage) > 20) + if (strlen(kt->usage) > 20) space = "\n "; - kdb_printf("%-15.15s %-20s%s%s\n", kt->cmd_name, - kt->cmd_usage, space, kt->cmd_help); + kdb_printf("%-15.15s %-20s%s%s\n", kt->name, + kt->usage, space, kt->help); } return 0; } @@ -2633,9 +2631,9 @@ int kdb_register(kdbtab_t *cmd) kdbtab_t *kp; list_for_each_entry(kp, &kdb_cmds_head, list_node) { - if (strcmp(kp->cmd_name, cmd->cmd_name) == 0) { + if (strcmp(kp->name, cmd->name) == 0) { kdb_printf("Duplicate kdb cmd: %s, func %p help %s\n", - cmd->cmd_name, cmd->cmd_func, cmd->cmd_help); + cmd->name, cmd->func, cmd->help); return 1; } } @@ -2672,218 +2670,218 @@ void kdb_unregister(kdbtab_t *cmd) EXPORT_SYMBOL_GPL(kdb_unregister); static kdbtab_t maintab[] = { - { .cmd_name = "md", - .cmd_func = kdb_md, - .cmd_usage = "", - .cmd_help = "Display Memory Contents, also mdWcN, e.g. md8c1", - .cmd_minlen = 1, - .cmd_flags = KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS, + { .name = "md", + .func = kdb_md, + .usage = "", + .help = "Display Memory Contents, also mdWcN, e.g. md8c1", + .minlen = 1, + .flags = KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS, }, - { .cmd_name = "mdr", - .cmd_func = kdb_md, - .cmd_usage = " ", - .cmd_help = "Display Raw Memory", - .cmd_flags = KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS, + { .name = "mdr", + .func = kdb_md, + .usage = " ", + .help = "Display Raw Memory", + .flags = KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS, }, - { .cmd_name = "mdp", - .cmd_func = kdb_md, - .cmd_usage = " ", - .cmd_help = "Display Physical Memory", - .cmd_flags = KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS, + { .name = "mdp", + .func = kdb_md, + .usage = " ", + .help = "Display Physical Memory", + .flags = KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS, }, - { .cmd_name = "mds", - .cmd_func = kdb_md, - .cmd_usage = "", - .cmd_help = "Display Memory Symbolically", - .cmd_flags = KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS, + { .name = "mds", + .func = kdb_md, + .usage = "", + .help = "Display Memory Symbolically", + .flags = KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS, }, - { .cmd_name = "mm", - .cmd_func = kdb_mm, - .cmd_usage = " ", - .cmd_help = "Modify Memory Contents", - .cmd_flags = KDB_ENABLE_MEM_WRITE | KDB_REPEAT_NO_ARGS, + { .name = "mm", + .func = kdb_mm, + .usage = " ", + .help = "Modify Memory Contents", + .flags = KDB_ENABLE_MEM_WRITE | KDB_REPEAT_NO_ARGS, }, - { .cmd_name = "go", - .cmd_func = kdb_go, - .cmd_usage = "[]", - .cmd_help = "Continue Execution", - .cmd_minlen = 1, - .cmd_flags = KDB_ENABLE_REG_WRITE | + { .name = "go", + .func = kdb_go, + .usage = "[]", + .help = "Continue Execution", + .minlen = 1, + .flags = KDB_ENABLE_REG_WRITE | KDB_ENABLE_ALWAYS_SAFE_NO_ARGS, }, - { .cmd_name = "rd", - .cmd_func = kdb_rd, - .cmd_usage = "", - .cmd_help = "Display Registers", - .cmd_flags = KDB_ENABLE_REG_READ, + { .name = "rd", + .func = kdb_rd, + .usage = "", + .help = "Display Registers", + .flags = KDB_ENABLE_REG_READ, }, - { .cmd_name = "rm", - .cmd_func = kdb_rm, - .cmd_usage = " ", - .cmd_help = "Modify Registers", - .cmd_flags = KDB_ENABLE_REG_WRITE, + { .name = "rm", + .func = kdb_rm, + .usage = " ", + .help = "Modify Registers", + .flags = KDB_ENABLE_REG_WRITE, }, - { .cmd_name = "ef", - .cmd_func = kdb_ef, - .cmd_usage = "", - .cmd_help = "Display exception frame", - .cmd_flags = KDB_ENABLE_MEM_READ, + { .name = "ef", + .func = kdb_ef, + .usage = "", + .help = "Display exception frame", + .flags = KDB_ENABLE_MEM_READ, }, - { .cmd_name = "bt", - .cmd_func = kdb_bt, - .cmd_usage = "[]", - .cmd_help = "Stack traceback", - .cmd_minlen = 1, - .cmd_flags = KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS, + { .name = "bt", + .func = kdb_bt, + .usage = "[]", + .help = "Stack traceback", + .minlen = 1, + .flags = KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS, }, - { .cmd_name = "btp", - .cmd_func = kdb_bt, - .cmd_usage = "", - .cmd_help = "Display stack for process ", - .cmd_flags = KDB_ENABLE_INSPECT, + { .name = "btp", + .func = kdb_bt, + .usage = "", + .help = "Display stack for process ", + .flags = KDB_ENABLE_INSPECT, }, - { .cmd_name = "bta", - .cmd_func = kdb_bt, - .cmd_usage = "[D|R|S|T|C|Z|E|U|I|M|A]", - .cmd_help = "Backtrace all processes matching state flag", - .cmd_flags = KDB_ENABLE_INSPECT, + { .name = "bta", + .func = kdb_bt, + .usage = "[D|R|S|T|C|Z|E|U|I|M|A]", + .help = "Backtrace all processes matching state flag", + .flags = KDB_ENABLE_INSPECT, }, - { .cmd_name = "btc", - .cmd_func = kdb_bt, - .cmd_usage = "", - .cmd_help = "Backtrace current process on each cpu", - .cmd_flags = KDB_ENABLE_INSPECT, + { .name = "btc", + .func = kdb_bt, + .usage = "", + .help = "Backtrace current process on each cpu", + .flags = KDB_ENABLE_INSPECT, }, - { .cmd_name = "btt", - .cmd_func = kdb_bt, - .cmd_usage = "", - .cmd_help = "Backtrace process given its struct task address", - .cmd_flags = KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS, + { .name = "btt", + .func = kdb_bt, + .usage = "", + .help = "Backtrace process given its struct task address", + .flags = KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS, }, - { .cmd_name = "env", - .cmd_func = kdb_env, - .cmd_usage = "", - .cmd_help = "Show environment variables", - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + { .name = "env", + .func = kdb_env, + .usage = "", + .help = "Show environment variables", + .flags = KDB_ENABLE_ALWAYS_SAFE, }, - { .cmd_name = "set", - .cmd_func = kdb_set, - .cmd_usage = "", - .cmd_help = "Set environment variables", - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + { .name = "set", + .func = kdb_set, + .usage = "", + .help = "Set environment variables", + .flags = KDB_ENABLE_ALWAYS_SAFE, }, - { .cmd_name = "help", - .cmd_func = kdb_help, - .cmd_usage = "", - .cmd_help = "Display Help Message", - .cmd_minlen = 1, - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + { .name = "help", + .func = kdb_help, + .usage = "", + .help = "Display Help Message", + .minlen = 1, + .flags = KDB_ENABLE_ALWAYS_SAFE, }, - { .cmd_name = "?", - .cmd_func = kdb_help, - .cmd_usage = "", - .cmd_help = "Display Help Message", - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + { .name = "?", + .func = kdb_help, + .usage = "", + .help = "Display Help Message", + .flags = KDB_ENABLE_ALWAYS_SAFE, }, - { .cmd_name = "cpu", - .cmd_func = kdb_cpu, - .cmd_usage = "", - .cmd_help = "Switch to new cpu", - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE_NO_ARGS, + { .name = "cpu", + .func = kdb_cpu, + .usage = "", + .help = "Switch to new cpu", + .flags = KDB_ENABLE_ALWAYS_SAFE_NO_ARGS, }, - { .cmd_name = "kgdb", - .cmd_func = kdb_kgdb, - .cmd_usage = "", - .cmd_help = "Enter kgdb mode", - .cmd_flags = 0, + { .name = "kgdb", + .func = kdb_kgdb, + .usage = "", + .help = "Enter kgdb mode", + .flags = 0, }, - { .cmd_name = "ps", - .cmd_func = kdb_ps, - .cmd_usage = "[|A]", - .cmd_help = "Display active task list", - .cmd_flags = KDB_ENABLE_INSPECT, + { .name = "ps", + .func = kdb_ps, + .usage = "[|A]", + .help = "Display active task list", + .flags = KDB_ENABLE_INSPECT, }, - { .cmd_name = "pid", - .cmd_func = kdb_pid, - .cmd_usage = "", - .cmd_help = "Switch to another task", - .cmd_flags = KDB_ENABLE_INSPECT, + { .name = "pid", + .func = kdb_pid, + .usage = "", + .help = "Switch to another task", + .flags = KDB_ENABLE_INSPECT, }, - { .cmd_name = "reboot", - .cmd_func = kdb_reboot, - .cmd_usage = "", - .cmd_help = "Reboot the machine immediately", - .cmd_flags = KDB_ENABLE_REBOOT, + { .name = "reboot", + .func = kdb_reboot, + .usage = "", + .help = "Reboot the machine immediately", + .flags = KDB_ENABLE_REBOOT, }, #if defined(CONFIG_MODULES) - { .cmd_name = "lsmod", - .cmd_func = kdb_lsmod, - .cmd_usage = "", - .cmd_help = "List loaded kernel modules", - .cmd_flags = KDB_ENABLE_INSPECT, + { .name = "lsmod", + .func = kdb_lsmod, + .usage = "", + .help = "List loaded kernel modules", + .flags = KDB_ENABLE_INSPECT, }, #endif #if defined(CONFIG_MAGIC_SYSRQ) - { .cmd_name = "sr", - .cmd_func = kdb_sr, - .cmd_usage = "", - .cmd_help = "Magic SysRq key", - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + { .name = "sr", + .func = kdb_sr, + .usage = "", + .help = "Magic SysRq key", + .flags = KDB_ENABLE_ALWAYS_SAFE, }, #endif #if defined(CONFIG_PRINTK) - { .cmd_name = "dmesg", - .cmd_func = kdb_dmesg, - .cmd_usage = "[lines]", - .cmd_help = "Display syslog buffer", - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + { .name = "dmesg", + .func = kdb_dmesg, + .usage = "[lines]", + .help = "Display syslog buffer", + .flags = KDB_ENABLE_ALWAYS_SAFE, }, #endif - { .cmd_name = "defcmd", - .cmd_func = kdb_defcmd, - .cmd_usage = "name \"usage\" \"help\"", - .cmd_help = "Define a set of commands, down to endefcmd", + { .name = "defcmd", + .func = kdb_defcmd, + .usage = "name \"usage\" \"help\"", + .help = "Define a set of commands, down to endefcmd", /* * Macros are always safe because when executed each * internal command re-enters kdb_parse() and is safety * checked individually. */ - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + .flags = KDB_ENABLE_ALWAYS_SAFE, }, - { .cmd_name = "kill", - .cmd_func = kdb_kill, - .cmd_usage = "<-signal> ", - .cmd_help = "Send a signal to a process", - .cmd_flags = KDB_ENABLE_SIGNAL, + { .name = "kill", + .func = kdb_kill, + .usage = "<-signal> ", + .help = "Send a signal to a process", + .flags = KDB_ENABLE_SIGNAL, }, - { .cmd_name = "summary", - .cmd_func = kdb_summary, - .cmd_usage = "", - .cmd_help = "Summarize the system", - .cmd_minlen = 4, - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + { .name = "summary", + .func = kdb_summary, + .usage = "", + .help = "Summarize the system", + .minlen = 4, + .flags = KDB_ENABLE_ALWAYS_SAFE, }, - { .cmd_name = "per_cpu", - .cmd_func = kdb_per_cpu, - .cmd_usage = " [] []", - .cmd_help = "Display per_cpu variables", - .cmd_minlen = 3, - .cmd_flags = KDB_ENABLE_MEM_READ, + { .name = "per_cpu", + .func = kdb_per_cpu, + .usage = " [] []", + .help = "Display per_cpu variables", + .minlen = 3, + .flags = KDB_ENABLE_MEM_READ, }, - { .cmd_name = "grephelp", - .cmd_func = kdb_grep_help, - .cmd_usage = "", - .cmd_help = "Display help on | grep", - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + { .name = "grephelp", + .func = kdb_grep_help, + .usage = "", + .help = "Display help on | grep", + .flags = KDB_ENABLE_ALWAYS_SAFE, }, }; static kdbtab_t nmicmd = { - .cmd_name = "disable_nmi", - .cmd_func = kdb_disable_nmi, - .cmd_usage = "", - .cmd_help = "Disable NMI entry to KDB", - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + .name = "disable_nmi", + .func = kdb_disable_nmi, + .usage = "", + .help = "Disable NMI entry to KDB", + .flags = KDB_ENABLE_ALWAYS_SAFE, }; /* Initialize the kdb command table. */ diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index 6c4f92c79e43..59857a1ee44c 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -148,11 +148,11 @@ static int kdb_ftdump(int argc, const char **argv) } static kdbtab_t ftdump_cmd = { - .cmd_name = "ftdump", - .cmd_func = kdb_ftdump, - .cmd_usage = "[skip_#entries] [cpu]", - .cmd_help = "Dump ftrace log; -skip dumps last #entries", - .cmd_flags = KDB_ENABLE_ALWAYS_SAFE, + .name = "ftdump", + .func = kdb_ftdump, + .usage = "[skip_#entries] [cpu]", + .help = "Dump ftrace log; -skip dumps last #entries", + .flags = KDB_ENABLE_ALWAYS_SAFE, }; static __init int kdb_ftrace_register(void) diff --git a/samples/kdb/kdb_hello.c b/samples/kdb/kdb_hello.c index 9ad514a6648b..82736e5a5e32 100644 --- a/samples/kdb/kdb_hello.c +++ b/samples/kdb/kdb_hello.c @@ -29,10 +29,10 @@ static int kdb_hello_cmd(int argc, const char **argv) } static kdbtab_t hello_cmd = { - .cmd_name = "hello", - .cmd_func = kdb_hello_cmd, - .cmd_usage = "[string]", - .cmd_help = "Say Hello World or Hello [string]", + .name = "hello", + .func = kdb_hello_cmd, + .usage = "[string]", + .help = "Say Hello World or Hello [string]", }; static int __init kdb_hello_cmd_init(void) -- cgit v1.2.3 From b9067f5dc4a07c8e24e01a1b277c6722d91be39e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Jul 2021 15:44:47 +0200 Subject: net: split out SIOCDEVPRIVATE handling from dev_ioctl SIOCDEVPRIVATE ioctl commands are mainly used in really old drivers, and they have a number of problems: - They hide behind the normal .ndo_do_ioctl function that is also used for other things in modern drivers, so it's hard to spot a driver that actually uses one of these - Since drivers use a number different calling conventions, it is impossible to support compat mode for them in a generic way. - With all drivers using the same 16 commands codes, there is no way to introspect the data being passed through things like strace. Add a new net_device_ops callback pointer, to address the first two of these. Separating them from .ndo_do_ioctl makes it easy to grep for drivers with a .ndo_siocdevprivate callback, and the unwieldy name hopefully makes it easier to spot in code review. By passing the ifreq structure and the ifr_data pointer separately, it is no longer necessary to overload these, and the driver can use either one for a given command. Cc: Cong Wang Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- Documentation/networking/netdevices.rst | 7 +++++++ include/linux/netdevice.h | 3 +++ net/core/dev_ioctl.c | 25 ++++++++++++++++++++++--- 3 files changed, 32 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst index 17bdcb746dcf..02f1faac839a 100644 --- a/Documentation/networking/netdevices.rst +++ b/Documentation/networking/netdevices.rst @@ -222,6 +222,13 @@ ndo_do_ioctl: Synchronization: rtnl_lock() semaphore. Context: process +ndo_siocdevprivate: + Synchronization: rtnl_lock() semaphore. + Context: process + + This is used to implement SIOCDEVPRIVATE ioctl helpers. + These should not be added to new drivers, so don't use. + ndo_get_stats: Synchronization: rtnl_lock() semaphore, dev_base_lock rwlock, or RCU. Context: atomic (can't sleep under rwlock or RCU) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c871dc223dfa..670e1a8e5928 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1361,6 +1361,9 @@ struct net_device_ops { int (*ndo_validate_addr)(struct net_device *dev); int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); + int (*ndo_siocdevprivate)(struct net_device *dev, + struct ifreq *ifr, + void __user *data, int cmd); int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); int (*ndo_change_mtu)(struct net_device *dev, diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 950e2fe5d56a..75e3e340d884 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -259,6 +259,23 @@ static int dev_do_ioctl(struct net_device *dev, return err; } +static int dev_siocdevprivate(struct net_device *dev, + struct ifreq *ifr, unsigned int cmd) +{ + const struct net_device_ops *ops = dev->netdev_ops; + void __user *data = ifr->ifr_data; + + if (ops->ndo_siocdevprivate) { + if (netif_device_present(dev)) + return ops->ndo_siocdevprivate(dev, ifr, data, cmd); + else + return -ENODEV; + } + + /* fall back to do_ioctl for drivers not yet converted */ + return dev_do_ioctl(dev, ifr, cmd); +} + /* * Perform the SIOCxIFxxx calls, inside rtnl_lock() */ @@ -336,9 +353,11 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) * Unknown or private ioctl */ default: - if ((cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15) || - cmd == SIOCBONDENSLAVE || + if (cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15) + return dev_siocdevprivate(dev, ifr, cmd); + + if (cmd == SIOCBONDENSLAVE || cmd == SIOCBONDRELEASE || cmd == SIOCBONDSETHWADDR || cmd == SIOCBONDSLAVEINFOQUERY || -- cgit v1.2.3 From 25ec92fbdd23a0a2bfd2bdf489e60ea4f0ae46d1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Jul 2021 15:45:04 +0200 Subject: hamradio: use ndo_siocdevprivate hamradio uses a set of private ioctls that do seem to work correctly in compat mode, as they only rely on the ifr_data pointer. Move them over to the ndo_siocdevprivate callback as a cleanup. Cc: Thomas Sailer Cc: Joerg Reuter Cc: Jean-Paul Roubelat Cc: linux-hams@vger.kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/hamradio/baycom_epp.c | 9 +++++---- drivers/net/hamradio/baycom_par.c | 12 ++++++------ drivers/net/hamradio/baycom_ser_fdx.c | 12 ++++++------ drivers/net/hamradio/baycom_ser_hdx.c | 12 ++++++------ drivers/net/hamradio/bpqether.c | 9 +++++---- drivers/net/hamradio/dmascc.c | 18 ++++++++---------- drivers/net/hamradio/hdlcdrv.c | 20 +++++++++++--------- drivers/net/hamradio/scc.c | 13 ++++++++----- drivers/net/hamradio/yam.c | 19 +++++++++---------- include/linux/hdlcdrv.h | 2 +- 10 files changed, 65 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 4435a1195194..775dcf4ebde5 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -1005,7 +1005,8 @@ static int baycom_setmode(struct baycom_state *bc, const char *modestr) /* --------------------------------------------------------------------- */ -static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int baycom_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd) { struct baycom_state *bc = netdev_priv(dev); struct hdlcdrv_ioctl hi; @@ -1013,7 +1014,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (cmd != SIOCDEVPRIVATE) return -ENOIOCTLCMD; - if (copy_from_user(&hi, ifr->ifr_data, sizeof(hi))) + if (copy_from_user(&hi, data, sizeof(hi))) return -EFAULT; switch (hi.cmd) { default: @@ -1104,7 +1105,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return HDLCDRV_PARMASK_IOBASE; } - if (copy_to_user(ifr->ifr_data, &hi, sizeof(hi))) + if (copy_to_user(data, &hi, sizeof(hi))) return -EFAULT; return 0; } @@ -1114,7 +1115,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static const struct net_device_ops baycom_netdev_ops = { .ndo_open = epp_open, .ndo_stop = epp_close, - .ndo_do_ioctl = baycom_ioctl, + .ndo_siocdevprivate = baycom_siocdevprivate, .ndo_start_xmit = baycom_send_packet, .ndo_set_mac_address = baycom_set_mac_address, }; diff --git a/drivers/net/hamradio/baycom_par.c b/drivers/net/hamradio/baycom_par.c index 6a3dc7b3f28a..fd7da5bb1fa5 100644 --- a/drivers/net/hamradio/baycom_par.c +++ b/drivers/net/hamradio/baycom_par.c @@ -380,7 +380,7 @@ static int par96_close(struct net_device *dev) * ===================== hdlcdrv driver interface ========================= */ -static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, +static int baycom_ioctl(struct net_device *dev, void __user *data, struct hdlcdrv_ioctl *hi, int cmd); /* --------------------------------------------------------------------- */ @@ -408,7 +408,7 @@ static int baycom_setmode(struct baycom_state *bc, const char *modestr) /* --------------------------------------------------------------------- */ -static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, +static int baycom_ioctl(struct net_device *dev, void __user *data, struct hdlcdrv_ioctl *hi, int cmd) { struct baycom_state *bc; @@ -428,7 +428,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, case HDLCDRVCTL_GETMODE: strcpy(hi->data.modename, bc->options ? "par96" : "picpar"); - if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl))) + if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl))) return -EFAULT; return 0; @@ -440,7 +440,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, case HDLCDRVCTL_MODELIST: strcpy(hi->data.modename, "par96,picpar"); - if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl))) + if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl))) return -EFAULT; return 0; @@ -449,7 +449,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, } - if (copy_from_user(&bi, ifr->ifr_data, sizeof(bi))) + if (copy_from_user(&bi, data, sizeof(bi))) return -EFAULT; switch (bi.cmd) { default: @@ -464,7 +464,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, #endif /* BAYCOM_DEBUG */ } - if (copy_to_user(ifr->ifr_data, &bi, sizeof(bi))) + if (copy_to_user(data, &bi, sizeof(bi))) return -EFAULT; return 0; diff --git a/drivers/net/hamradio/baycom_ser_fdx.c b/drivers/net/hamradio/baycom_ser_fdx.c index 04bb409707fc..646f605e358f 100644 --- a/drivers/net/hamradio/baycom_ser_fdx.c +++ b/drivers/net/hamradio/baycom_ser_fdx.c @@ -462,7 +462,7 @@ static int ser12_close(struct net_device *dev) /* --------------------------------------------------------------------- */ -static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, +static int baycom_ioctl(struct net_device *dev, void __user *data, struct hdlcdrv_ioctl *hi, int cmd); /* --------------------------------------------------------------------- */ @@ -497,7 +497,7 @@ static int baycom_setmode(struct baycom_state *bc, const char *modestr) /* --------------------------------------------------------------------- */ -static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, +static int baycom_ioctl(struct net_device *dev, void __user *data, struct hdlcdrv_ioctl *hi, int cmd) { struct baycom_state *bc; @@ -519,7 +519,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, sprintf(hi->data.modename, "ser%u", bc->baud / 100); if (bc->opt_dcd <= 0) strcat(hi->data.modename, (!bc->opt_dcd) ? "*" : "+"); - if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl))) + if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl))) return -EFAULT; return 0; @@ -531,7 +531,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, case HDLCDRVCTL_MODELIST: strcpy(hi->data.modename, "ser12,ser3,ser24"); - if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl))) + if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl))) return -EFAULT; return 0; @@ -540,7 +540,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, } - if (copy_from_user(&bi, ifr->ifr_data, sizeof(bi))) + if (copy_from_user(&bi, data, sizeof(bi))) return -EFAULT; switch (bi.cmd) { default: @@ -555,7 +555,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, #endif /* BAYCOM_DEBUG */ } - if (copy_to_user(ifr->ifr_data, &bi, sizeof(bi))) + if (copy_to_user(data, &bi, sizeof(bi))) return -EFAULT; return 0; diff --git a/drivers/net/hamradio/baycom_ser_hdx.c b/drivers/net/hamradio/baycom_ser_hdx.c index a1acb3a47bdb..5d1ab4840753 100644 --- a/drivers/net/hamradio/baycom_ser_hdx.c +++ b/drivers/net/hamradio/baycom_ser_hdx.c @@ -521,7 +521,7 @@ static int ser12_close(struct net_device *dev) /* --------------------------------------------------------------------- */ -static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, +static int baycom_ioctl(struct net_device *dev, void __user *data, struct hdlcdrv_ioctl *hi, int cmd); /* --------------------------------------------------------------------- */ @@ -551,7 +551,7 @@ static int baycom_setmode(struct baycom_state *bc, const char *modestr) /* --------------------------------------------------------------------- */ -static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, +static int baycom_ioctl(struct net_device *dev, void __user *data, struct hdlcdrv_ioctl *hi, int cmd) { struct baycom_state *bc; @@ -573,7 +573,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, strcpy(hi->data.modename, "ser12"); if (bc->opt_dcd <= 0) strcat(hi->data.modename, (!bc->opt_dcd) ? "*" : (bc->opt_dcd == -2) ? "@" : "+"); - if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl))) + if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl))) return -EFAULT; return 0; @@ -585,7 +585,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, case HDLCDRVCTL_MODELIST: strcpy(hi->data.modename, "ser12"); - if (copy_to_user(ifr->ifr_data, hi, sizeof(struct hdlcdrv_ioctl))) + if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl))) return -EFAULT; return 0; @@ -594,7 +594,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, } - if (copy_from_user(&bi, ifr->ifr_data, sizeof(bi))) + if (copy_from_user(&bi, data, sizeof(bi))) return -EFAULT; switch (bi.cmd) { default: @@ -609,7 +609,7 @@ static int baycom_ioctl(struct net_device *dev, struct ifreq *ifr, #endif /* BAYCOM_DEBUG */ } - if (copy_to_user(ifr->ifr_data, &bi, sizeof(bi))) + if (copy_to_user(data, &bi, sizeof(bi))) return -EFAULT; return 0; diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 0e623c2e8b2d..d967b0748773 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -314,9 +314,10 @@ static int bpq_set_mac_address(struct net_device *dev, void *addr) * source ethernet address (broadcast * or multicast: accept all) */ -static int bpq_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int bpq_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd) { - struct bpq_ethaddr __user *ethaddr = ifr->ifr_data; + struct bpq_ethaddr __user *ethaddr = data; struct bpqdev *bpq = netdev_priv(dev); struct bpq_req req; @@ -325,7 +326,7 @@ static int bpq_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCSBPQETHOPT: - if (copy_from_user(&req, ifr->ifr_data, sizeof(struct bpq_req))) + if (copy_from_user(&req, data, sizeof(struct bpq_req))) return -EFAULT; switch (req.cmd) { case SIOCGBPQETHPARAM: @@ -448,7 +449,7 @@ static const struct net_device_ops bpq_netdev_ops = { .ndo_stop = bpq_close, .ndo_start_xmit = bpq_xmit, .ndo_set_mac_address = bpq_set_mac_address, - .ndo_do_ioctl = bpq_ioctl, + .ndo_siocdevprivate = bpq_siocdevprivate, }; static void bpq_setup(struct net_device *dev) diff --git a/drivers/net/hamradio/dmascc.c b/drivers/net/hamradio/dmascc.c index c25c8c99c5c7..b50b7fafd8d6 100644 --- a/drivers/net/hamradio/dmascc.c +++ b/drivers/net/hamradio/dmascc.c @@ -225,7 +225,8 @@ static int read_scc_data(struct scc_priv *priv); static int scc_open(struct net_device *dev); static int scc_close(struct net_device *dev); -static int scc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); +static int scc_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd); static int scc_send_packet(struct sk_buff *skb, struct net_device *dev); static int scc_set_mac_address(struct net_device *dev, void *sa); @@ -432,7 +433,7 @@ static const struct net_device_ops scc_netdev_ops = { .ndo_open = scc_open, .ndo_stop = scc_close, .ndo_start_xmit = scc_send_packet, - .ndo_do_ioctl = scc_ioctl, + .ndo_siocdevprivate = scc_siocdevprivate, .ndo_set_mac_address = scc_set_mac_address, }; @@ -881,15 +882,13 @@ static int scc_close(struct net_device *dev) } -static int scc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int scc_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { struct scc_priv *priv = dev->ml_priv; switch (cmd) { case SIOCGSCCPARAM: - if (copy_to_user - (ifr->ifr_data, &priv->param, - sizeof(struct scc_param))) + if (copy_to_user(data, &priv->param, sizeof(struct scc_param))) return -EFAULT; return 0; case SIOCSSCCPARAM: @@ -897,13 +896,12 @@ static int scc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EPERM; if (netif_running(dev)) return -EAGAIN; - if (copy_from_user - (&priv->param, ifr->ifr_data, - sizeof(struct scc_param))) + if (copy_from_user(&priv->param, data, + sizeof(struct scc_param))) return -EFAULT; return 0; default: - return -EINVAL; + return -EOPNOTSUPP; } } diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c index cbaf1cdde7cb..5805cfc83854 100644 --- a/drivers/net/hamradio/hdlcdrv.c +++ b/drivers/net/hamradio/hdlcdrv.c @@ -483,23 +483,25 @@ static int hdlcdrv_close(struct net_device *dev) /* --------------------------------------------------------------------- */ -static int hdlcdrv_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int hdlcdrv_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd) { struct hdlcdrv_state *s = netdev_priv(dev); struct hdlcdrv_ioctl bi; - if (cmd != SIOCDEVPRIVATE) { - if (s->ops && s->ops->ioctl) - return s->ops->ioctl(dev, ifr, &bi, cmd); + if (cmd != SIOCDEVPRIVATE) return -ENOIOCTLCMD; - } - if (copy_from_user(&bi, ifr->ifr_data, sizeof(bi))) + + if (in_compat_syscall()) /* to be implemented */ + return -ENOIOCTLCMD; + + if (copy_from_user(&bi, data, sizeof(bi))) return -EFAULT; switch (bi.cmd) { default: if (s->ops && s->ops->ioctl) - return s->ops->ioctl(dev, ifr, &bi, cmd); + return s->ops->ioctl(dev, data, &bi, cmd); return -ENOIOCTLCMD; case HDLCDRVCTL_GETCHANNELPAR: @@ -605,7 +607,7 @@ static int hdlcdrv_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; } - if (copy_to_user(ifr->ifr_data, &bi, sizeof(bi))) + if (copy_to_user(data, &bi, sizeof(bi))) return -EFAULT; return 0; @@ -617,7 +619,7 @@ static const struct net_device_ops hdlcdrv_netdev = { .ndo_open = hdlcdrv_open, .ndo_stop = hdlcdrv_close, .ndo_start_xmit = hdlcdrv_send_packet, - .ndo_do_ioctl = hdlcdrv_ioctl, + .ndo_siocdevprivate = hdlcdrv_siocdevprivate, .ndo_set_mac_address = hdlcdrv_set_mac_address, }; diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index 3f1edd0526a4..e0bb131a33d7 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -210,7 +210,8 @@ static int scc_net_close(struct net_device *dev); static void scc_net_rx(struct scc_channel *scc, struct sk_buff *skb); static netdev_tx_t scc_net_tx(struct sk_buff *skb, struct net_device *dev); -static int scc_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); +static int scc_net_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd); static int scc_net_set_mac_address(struct net_device *dev, void *addr); static struct net_device_stats * scc_net_get_stats(struct net_device *dev); @@ -1550,7 +1551,7 @@ static const struct net_device_ops scc_netdev_ops = { .ndo_start_xmit = scc_net_tx, .ndo_set_mac_address = scc_net_set_mac_address, .ndo_get_stats = scc_net_get_stats, - .ndo_do_ioctl = scc_net_ioctl, + .ndo_siocdevprivate = scc_net_siocdevprivate, }; /* ----> Initialize device <----- */ @@ -1703,7 +1704,8 @@ static netdev_tx_t scc_net_tx(struct sk_buff *skb, struct net_device *dev) * SIOCSCCCAL - send calib. pattern arg: (struct scc_calibrate *) arg */ -static int scc_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int scc_net_siocdevprivate(struct net_device *dev, + struct ifreq *ifr, void __user *arg, int cmd) { struct scc_kiss_cmd kiss_cmd; struct scc_mem_config memcfg; @@ -1712,8 +1714,6 @@ static int scc_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) struct scc_channel *scc = (struct scc_channel *) dev->ml_priv; int chan; unsigned char device_name[IFNAMSIZ]; - void __user *arg = ifr->ifr_data; - if (!Driver_Initialized) { @@ -1722,6 +1722,9 @@ static int scc_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) int found = 1; if (!capable(CAP_SYS_RAWIO)) return -EPERM; + if (in_compat_syscall()) + return -EOPNOTSUPP; + if (!arg) return -EFAULT; if (Nchips >= SCC_MAXCHIPS) diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index d4911041596c..6ddacbdb224b 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -920,15 +920,15 @@ static int yam_close(struct net_device *dev) /* --------------------------------------------------------------------- */ -static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int yam_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { struct yam_port *yp = netdev_priv(dev); struct yamdrv_ioctl_cfg yi; struct yamdrv_ioctl_mcs *ym; int ioctl_cmd; - if (copy_from_user(&ioctl_cmd, ifr->ifr_data, sizeof(int))) - return -EFAULT; + if (copy_from_user(&ioctl_cmd, data, sizeof(int))) + return -EFAULT; if (yp->magic != YAM_MAGIC) return -EINVAL; @@ -947,8 +947,7 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCYAMSMCS: if (netif_running(dev)) return -EINVAL; /* Cannot change this parameter when up */ - ym = memdup_user(ifr->ifr_data, - sizeof(struct yamdrv_ioctl_mcs)); + ym = memdup_user(data, sizeof(struct yamdrv_ioctl_mcs)); if (IS_ERR(ym)) return PTR_ERR(ym); if (ym->cmd != SIOCYAMSMCS) @@ -965,8 +964,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCYAMSCFG: if (!capable(CAP_SYS_RAWIO)) return -EPERM; - if (copy_from_user(&yi, ifr->ifr_data, sizeof(struct yamdrv_ioctl_cfg))) - return -EFAULT; + if (copy_from_user(&yi, data, sizeof(struct yamdrv_ioctl_cfg))) + return -EFAULT; if (yi.cmd != SIOCYAMSCFG) return -EINVAL; @@ -1045,8 +1044,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) yi.cfg.txtail = yp->txtail; yi.cfg.persist = yp->pers; yi.cfg.slottime = yp->slot; - if (copy_to_user(ifr->ifr_data, &yi, sizeof(struct yamdrv_ioctl_cfg))) - return -EFAULT; + if (copy_to_user(data, &yi, sizeof(struct yamdrv_ioctl_cfg))) + return -EFAULT; break; default: @@ -1074,7 +1073,7 @@ static const struct net_device_ops yam_netdev_ops = { .ndo_open = yam_open, .ndo_stop = yam_close, .ndo_start_xmit = yam_send_packet, - .ndo_do_ioctl = yam_ioctl, + .ndo_siocdevprivate = yam_siocdevprivate, .ndo_set_mac_address = yam_set_mac_address, }; diff --git a/include/linux/hdlcdrv.h b/include/linux/hdlcdrv.h index d4d633a49d36..5d70c3f98f5b 100644 --- a/include/linux/hdlcdrv.h +++ b/include/linux/hdlcdrv.h @@ -79,7 +79,7 @@ struct hdlcdrv_ops { */ int (*open)(struct net_device *); int (*close)(struct net_device *); - int (*ioctl)(struct net_device *, struct ifreq *, + int (*ioctl)(struct net_device *, void __user *, struct hdlcdrv_ioctl *, int); }; -- cgit v1.2.3 From a554bf96b49db4c208e305ae92546422e9489380 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Jul 2021 15:45:12 +0200 Subject: dev_ioctl: pass SIOCDEVPRIVATE data separately The compat handlers for SIOCDEVPRIVATE are incorrect for any driver that passes data as part of struct ifreq rather than as an ifr_data pointer, or that passes data back this way, since the compat_ifr_data_ioctl() helper overwrites the ifr_data pointer and does not copy anything back out. Since all drivers using devprivate commands are now converted to the new .ndo_siocdevprivate callback, fix this by adding the missing piece and passing the pointer separately the whole way. This further unifies the native and compat logic for socket ioctls, as the new code now passes the correct pointer as well as the correct data for both native and compat ioctls. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- net/core/dev_ioctl.c | 22 ++++++++++--------- net/ethtool/ioctl.c | 3 +-- net/socket.c | 55 +++++++++++------------------------------------ 4 files changed, 28 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 670e1a8e5928..658d8cf57342 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4012,9 +4012,9 @@ bool dev_valid_name(const char *name); int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg); int put_user_ifreq(struct ifreq *ifr, void __user *arg); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, - bool *need_copyout); + void __user *data, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf __user *ifc); -int dev_ethtool(struct net *net, struct ifreq *); +int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 75e3e340d884..3ace1e4f6b80 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -259,11 +259,10 @@ static int dev_do_ioctl(struct net_device *dev, return err; } -static int dev_siocdevprivate(struct net_device *dev, - struct ifreq *ifr, unsigned int cmd) +static int dev_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, unsigned int cmd) { const struct net_device_ops *ops = dev->netdev_ops; - void __user *data = ifr->ifr_data; if (ops->ndo_siocdevprivate) { if (netif_device_present(dev)) @@ -273,13 +272,15 @@ static int dev_siocdevprivate(struct net_device *dev, } /* fall back to do_ioctl for drivers not yet converted */ + ifr->ifr_data = data; return dev_do_ioctl(dev, ifr, cmd); } /* * Perform the SIOCxIFxxx calls, inside rtnl_lock() */ -static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) +static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, + unsigned int cmd) { int err; struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); @@ -355,7 +356,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) default: if (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15) - return dev_siocdevprivate(dev, ifr, cmd); + return dev_siocdevprivate(dev, ifr, data, cmd); if (cmd == SIOCBONDENSLAVE || cmd == SIOCBONDRELEASE || @@ -424,7 +425,8 @@ EXPORT_SYMBOL(dev_load); * positive or a negative errno code on error. */ -int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_copyout) +int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, + void __user *data, bool *need_copyout) { int ret; char *colon; @@ -475,7 +477,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCETHTOOL: dev_load(net, ifr->ifr_name); rtnl_lock(); - ret = dev_ethtool(net, ifr); + ret = dev_ethtool(net, ifr, data); rtnl_unlock(); if (colon) *colon = ':'; @@ -494,7 +496,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_lock(); - ret = dev_ifsioc(net, ifr, cmd); + ret = dev_ifsioc(net, ifr, data, cmd); rtnl_unlock(); if (colon) *colon = ':'; @@ -540,7 +542,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCBONDINFOQUERY: dev_load(net, ifr->ifr_name); rtnl_lock(); - ret = dev_ifsioc(net, ifr, cmd); + ret = dev_ifsioc(net, ifr, data, cmd); rtnl_unlock(); if (need_copyout) *need_copyout = false; @@ -565,7 +567,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c cmd <= SIOCDEVPRIVATE + 15)) { dev_load(net, ifr->ifr_name); rtnl_lock(); - ret = dev_ifsioc(net, ifr, cmd); + ret = dev_ifsioc(net, ifr, data, cmd); rtnl_unlock(); return ret; } diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index af011534bcb2..b0fa2b00ad43 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2685,10 +2685,9 @@ static int ethtool_set_fecparam(struct net_device *dev, void __user *useraddr) /* The main entry point in this file. Called from net/core/dev_ioctl.c */ -int dev_ethtool(struct net *net, struct ifreq *ifr) +int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *useraddr) { struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); - void __user *useraddr = ifr->ifr_data; u32 ethcmd, sub_cmd; int rc; netdev_features_t old_features; diff --git a/net/socket.c b/net/socket.c index 84de89c1ee9d..ddce6327633e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1092,6 +1092,7 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, bool need_copyout; int err; void __user *argp = (void __user *)arg; + void __user *data; err = sock->ops->ioctl(sock, cmd, arg); @@ -1102,11 +1103,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, if (err != -ENOIOCTLCMD) return err; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (get_user_ifreq(&ifr, &data, argp)) return -EFAULT; - err = dev_ioctl(net, cmd, &ifr, &need_copyout); + err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) + if (put_user_ifreq(&ifr, argp)) return -EFAULT; return err; @@ -1130,12 +1131,13 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) net = sock_net(sk); if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) { struct ifreq ifr; + void __user *data; bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (get_user_ifreq(&ifr, &data, argp)) return -EFAULT; - err = dev_ioctl(net, cmd, &ifr, &need_copyout); + err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) + if (put_user_ifreq(&ifr, argp)) return -EFAULT; } else #ifdef CONFIG_WEXT_CORE @@ -3186,7 +3188,7 @@ static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32 saved = ifr.ifr_settings.ifs_ifsu.raw_hdlc; ifr.ifr_settings.ifs_ifsu.raw_hdlc = compat_ptr(uptr32); - err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL); + err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL, NULL); if (!err) { ifr.ifr_settings.ifs_ifsu.raw_hdlc = saved; if (put_user_ifreq(&ifr, uifr32)) @@ -3200,42 +3202,13 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct compat_ifreq __user *u_ifreq32) { struct ifreq ifreq; - u32 data32; + void __user *data; - if (copy_from_user(ifreq.ifr_name, u_ifreq32->ifr_name, IFNAMSIZ)) + if (get_user_ifreq(&ifreq, &data, u_ifreq32)) return -EFAULT; - if (get_user(data32, &u_ifreq32->ifr_data)) - return -EFAULT; - ifreq.ifr_data = compat_ptr(data32); + ifreq.ifr_data = data; - return dev_ioctl(net, cmd, &ifreq, NULL); -} - -static int compat_ifreq_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, - unsigned long arg, - struct compat_ifreq __user *uifr32) -{ - struct ifreq ifr; - bool need_copyout; - int err; - - err = sock->ops->ioctl(sock, cmd, arg); - - /* If this ioctl is unknown try to hand it down - * to the NIC driver. - */ - if (err != -ENOIOCTLCMD) - return err; - - if (get_user_ifreq(&ifr, NULL, uifr32)) - return -EFAULT; - err = dev_ioctl(net, cmd, &ifr, &need_copyout); - if (!err && need_copyout) - if (put_user_ifreq(&ifr, uifr32)) - return -EFAULT; - - return err; + return dev_ioctl(net, cmd, &ifreq, data, NULL); } /* Since old style bridge ioctl's endup using SIOCDEVPRIVATE @@ -3337,8 +3310,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - return compat_ifreq_ioctl(net, sock, cmd, arg, argp); - case SIOCSARP: case SIOCGARP: case SIOCDARP: -- cgit v1.2.3 From a76053707dbf0dc020a73b4d90cd952409ef3691 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Jul 2021 15:45:13 +0200 Subject: dev_ioctl: split out ndo_eth_ioctl Most users of ndo_do_ioctl are ethernet drivers that implement the MII commands SIOCGMIIPHY/SIOCGMIIREG/SIOCSMIIREG, or hardware timestamping with SIOCSHWTSTAMP/SIOCGHWTSTAMP. Separate these from the few drivers that use ndo_do_ioctl to implement SIOCBOND, SIOCBR and SIOCWANDEV commands. This is a purely cosmetic change intended to help readers find their way through the implementation. Cc: Doug Ledford Cc: Jason Gunthorpe Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Cc: Andrew Lunn Cc: Vivien Didelot Cc: Florian Fainelli Cc: Vladimir Oltean Cc: Leon Romanovsky Cc: linux-rdma@vger.kernel.org Signed-off-by: Arnd Bergmann Acked-by: Jason Gunthorpe Signed-off-by: David S. Miller --- Documentation/networking/netdevices.rst | 4 +++ Documentation/networking/timestamping.rst | 6 ++-- drivers/infiniband/ulp/ipoib/ipoib_main.c | 8 ++--- drivers/net/bonding/bond_main.c | 42 +++++++++++++++------- drivers/net/ethernet/3com/3c574_cs.c | 2 +- drivers/net/ethernet/3com/3c59x.c | 4 +-- drivers/net/ethernet/8390/ax88796.c | 2 +- drivers/net/ethernet/8390/axnet_cs.c | 2 +- drivers/net/ethernet/8390/pcnet_cs.c | 2 +- drivers/net/ethernet/actions/owl-emac.c | 6 ++-- drivers/net/ethernet/adaptec/starfire.c | 2 +- drivers/net/ethernet/agere/et131x.c | 2 +- drivers/net/ethernet/allwinner/sun4i-emac.c | 2 +- drivers/net/ethernet/amd/amd8111e.c | 2 +- drivers/net/ethernet/amd/au1000_eth.c | 2 +- drivers/net/ethernet/amd/pcnet32.c | 2 +- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 2 +- drivers/net/ethernet/aquantia/atlantic/aq_main.c | 2 +- drivers/net/ethernet/arc/emac_main.c | 2 +- drivers/net/ethernet/atheros/ag71xx.c | 2 +- drivers/net/ethernet/atheros/alx/main.c | 2 +- drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 2 +- drivers/net/ethernet/atheros/atl1e/atl1e_main.c | 2 +- drivers/net/ethernet/atheros/atlx/atl1.c | 2 +- drivers/net/ethernet/atheros/atlx/atl2.c | 2 +- drivers/net/ethernet/broadcom/b44.c | 2 +- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 4 +-- drivers/net/ethernet/broadcom/bgmac.c | 2 +- drivers/net/ethernet/broadcom/bnx2.c | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +- drivers/net/ethernet/broadcom/sb1250-mac.c | 2 +- drivers/net/ethernet/broadcom/tg3.c | 2 +- drivers/net/ethernet/cadence/macb_main.c | 4 +-- drivers/net/ethernet/cavium/liquidio/lio_main.c | 2 +- drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 2 +- drivers/net/ethernet/cavium/octeon/octeon_mgmt.c | 2 +- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 2 +- drivers/net/ethernet/chelsio/cxgb/cxgb2.c | 2 +- drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 2 +- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 2 +- .../net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c | 2 +- drivers/net/ethernet/cirrus/ep93xx_eth.c | 2 +- drivers/net/ethernet/davicom/dm9000.c | 2 +- drivers/net/ethernet/dec/tulip/tulip_core.c | 2 +- drivers/net/ethernet/dec/tulip/winbond-840.c | 2 +- drivers/net/ethernet/dlink/dl2k.c | 2 +- drivers/net/ethernet/dlink/sundance.c | 2 +- drivers/net/ethernet/dnet.c | 2 +- drivers/net/ethernet/ethoc.c | 2 +- drivers/net/ethernet/faraday/ftgmac100.c | 2 +- drivers/net/ethernet/faraday/ftmac100.c | 2 +- drivers/net/ethernet/fealnx.c | 2 +- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 2 +- drivers/net/ethernet/freescale/enetc/enetc_pf.c | 2 +- drivers/net/ethernet/freescale/enetc/enetc_vf.c | 2 +- drivers/net/ethernet/freescale/fec_main.c | 2 +- drivers/net/ethernet/freescale/fec_mpc52xx.c | 2 +- .../net/ethernet/freescale/fs_enet/fs_enet-main.c | 2 +- drivers/net/ethernet/freescale/gianfar.c | 2 +- drivers/net/ethernet/freescale/ucc_geth.c | 2 +- drivers/net/ethernet/hisilicon/hisi_femac.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +- drivers/net/ethernet/ibm/emac/core.c | 4 +-- drivers/net/ethernet/ibm/ibmveth.c | 2 +- drivers/net/ethernet/intel/e100.c | 2 +- drivers/net/ethernet/intel/e1000/e1000_main.c | 2 +- drivers/net/ethernet/intel/e1000e/netdev.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- drivers/net/ethernet/intel/ice/ice_main.c | 6 ++-- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/igbvf/netdev.c | 2 +- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/ethernet/jme.c | 2 +- drivers/net/ethernet/korina.c | 2 +- drivers/net/ethernet/lantiq_etop.c | 2 +- drivers/net/ethernet/marvell/mv643xx_eth.c | 2 +- drivers/net/ethernet/marvell/mvneta.c | 2 +- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +- .../net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 2 +- drivers/net/ethernet/marvell/pxa168_eth.c | 2 +- drivers/net/ethernet/marvell/skge.c | 2 +- drivers/net/ethernet/marvell/sky2.c | 4 +-- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 2 +- drivers/net/ethernet/mediatek/mtk_star_emac.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 2 +- .../ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c | 2 +- .../ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c | 4 +-- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +- drivers/net/ethernet/micrel/ks8851_common.c | 2 +- drivers/net/ethernet/micrel/ksz884x.c | 2 +- drivers/net/ethernet/microchip/lan743x_main.c | 2 +- drivers/net/ethernet/mscc/ocelot_net.c | 2 +- drivers/net/ethernet/natsemi/natsemi.c | 2 +- drivers/net/ethernet/neterion/s2io.c | 2 +- drivers/net/ethernet/neterion/vxge/vxge-main.c | 2 +- drivers/net/ethernet/nxp/lpc_eth.c | 2 +- .../net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 2 +- drivers/net/ethernet/packetengines/hamachi.c | 2 +- drivers/net/ethernet/packetengines/yellowfin.c | 2 +- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 4 +-- drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +- drivers/net/ethernet/qualcomm/emac/emac.c | 2 +- drivers/net/ethernet/rdc/r6040.c | 2 +- drivers/net/ethernet/realtek/8139cp.c | 2 +- drivers/net/ethernet/realtek/8139too.c | 2 +- drivers/net/ethernet/realtek/r8169_main.c | 2 +- drivers/net/ethernet/renesas/ravb_main.c | 2 +- drivers/net/ethernet/renesas/sh_eth.c | 4 +-- drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c | 2 +- drivers/net/ethernet/sfc/efx.c | 2 +- drivers/net/ethernet/sfc/falcon/efx.c | 2 +- drivers/net/ethernet/sgi/ioc3-eth.c | 2 +- drivers/net/ethernet/sgi/meth.c | 2 +- drivers/net/ethernet/sis/sis190.c | 2 +- drivers/net/ethernet/sis/sis900.c | 2 +- drivers/net/ethernet/smsc/epic100.c | 2 +- drivers/net/ethernet/smsc/smc91c92_cs.c | 2 +- drivers/net/ethernet/smsc/smsc911x.c | 2 +- drivers/net/ethernet/smsc/smsc9420.c | 2 +- drivers/net/ethernet/socionext/netsec.c | 2 +- drivers/net/ethernet/socionext/sni_ave.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- drivers/net/ethernet/sun/cassini.c | 2 +- drivers/net/ethernet/sun/niu.c | 2 +- drivers/net/ethernet/sun/sungem.c | 2 +- drivers/net/ethernet/synopsys/dwc-xlgmac-net.c | 2 +- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +- drivers/net/ethernet/ti/cpmac.c | 2 +- drivers/net/ethernet/ti/cpsw.c | 2 +- drivers/net/ethernet/ti/cpsw_new.c | 2 +- drivers/net/ethernet/ti/davinci_emac.c | 2 +- drivers/net/ethernet/ti/netcp_core.c | 2 +- drivers/net/ethernet/ti/tlan.c | 2 +- drivers/net/ethernet/toshiba/spider_net.c | 2 +- drivers/net/ethernet/toshiba/tc35815.c | 2 +- drivers/net/ethernet/tundra/tsi108_eth.c | 2 +- drivers/net/ethernet/via/via-rhine.c | 2 +- drivers/net/ethernet/via/via-velocity.c | 2 +- drivers/net/ethernet/xilinx/ll_temac_main.c | 2 +- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 2 +- drivers/net/ethernet/xilinx/xilinx_emaclite.c | 2 +- drivers/net/ethernet/xircom/xirc2ps_cs.c | 2 +- drivers/net/ethernet/xscale/ixp4xx_eth.c | 2 +- drivers/net/macvlan.c | 8 ++--- drivers/net/phy/phy.c | 4 +-- drivers/net/usb/asix_devices.c | 6 ++-- drivers/net/usb/ax88172a.c | 2 +- drivers/net/usb/ax88179_178a.c | 2 +- drivers/net/usb/dm9601.c | 2 +- drivers/net/usb/lan78xx.c | 2 +- drivers/net/usb/mcs7830.c | 2 +- drivers/net/usb/r8152.c | 2 +- drivers/net/usb/smsc75xx.c | 2 +- drivers/net/usb/smsc95xx.c | 2 +- drivers/net/usb/sr9700.c | 2 +- drivers/net/usb/sr9800.c | 2 +- drivers/s390/net/qeth_l2_main.c | 2 +- drivers/s390/net/qeth_l3_main.c | 4 +-- drivers/staging/octeon/ethernet.c | 12 +++---- include/linux/netdevice.h | 6 ++++ include/net/dsa.h | 14 ++++---- net/8021q/vlan_dev.c | 6 ++-- net/core/dev_ioctl.c | 38 ++++++++++++++------ net/dsa/master.c | 6 ++-- net/dsa/slave.c | 2 +- 172 files changed, 273 insertions(+), 231 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst index 02f1faac839a..f57f255f2397 100644 --- a/Documentation/networking/netdevices.rst +++ b/Documentation/networking/netdevices.rst @@ -229,6 +229,10 @@ ndo_siocdevprivate: This is used to implement SIOCDEVPRIVATE ioctl helpers. These should not be added to new drivers, so don't use. +ndo_eth_ioctl: + Synchronization: rtnl_lock() semaphore. + Context: process + ndo_get_stats: Synchronization: rtnl_lock() semaphore, dev_base_lock rwlock, or RCU. Context: atomic (can't sleep under rwlock or RCU) diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index 7db3985359bc..a722eb30e014 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -625,7 +625,7 @@ interfaces of a DSA switch to share the same PHC. By design, PTP timestamping with a DSA switch does not need any special handling in the driver for the host port it is attached to. However, when the host port also supports PTP timestamping, DSA will take care of intercepting -the ``.ndo_do_ioctl`` calls towards the host port, and block attempts to enable +the ``.ndo_eth_ioctl`` calls towards the host port, and block attempts to enable hardware timestamping on it. This is because the SO_TIMESTAMPING API does not allow the delivery of multiple hardware timestamps for the same packet, so anybody else except for the DSA switch port must be prevented from doing so. @@ -688,7 +688,7 @@ ethtool ioctl operations for them need to be mediated by their respective MAC driver. Therefore, as opposed to DSA switches, modifications need to be done to each individual MAC driver for PHY timestamping support. This entails: -- Checking, in ``.ndo_do_ioctl``, whether ``phy_has_hwtstamp(netdev->phydev)`` +- Checking, in ``.ndo_eth_ioctl``, whether ``phy_has_hwtstamp(netdev->phydev)`` is true or not. If it is, then the MAC driver should not process this request but instead pass it on to the PHY using ``phy_mii_ioctl()``. @@ -747,7 +747,7 @@ For example, a typical driver design for TX timestamping might be to split the transmission part into 2 portions: 1. "TX": checks whether PTP timestamping has been previously enabled through - the ``.ndo_do_ioctl`` ("``priv->hwtstamp_tx_enabled == true``") and the + the ``.ndo_eth_ioctl`` ("``priv->hwtstamp_tx_enabled == true``") and the current skb requires a TX timestamp ("``skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP``"). If this is true, it sets the "``skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS``" flag. Note: as diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index abf60f4d9203..0aa8629fdf62 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1745,10 +1745,10 @@ static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, { struct ipoib_dev_priv *priv = ipoib_priv(dev); - if (!priv->rn_ops->ndo_do_ioctl) + if (!priv->rn_ops->ndo_eth_ioctl) return -EOPNOTSUPP; - return priv->rn_ops->ndo_do_ioctl(dev, ifr, cmd); + return priv->rn_ops->ndo_eth_ioctl(dev, ifr, cmd); } static int ipoib_dev_init(struct net_device *dev) @@ -2078,7 +2078,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_set_vf_guid = ipoib_set_vf_guid, .ndo_set_mac_address = ipoib_set_mac, .ndo_get_stats64 = ipoib_get_stats, - .ndo_do_ioctl = ipoib_ioctl, + .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_ops_vf = { @@ -2093,7 +2093,7 @@ static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_get_stats64 = ipoib_get_stats, - .ndo_do_ioctl = ipoib_ioctl, + .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_default_pf = { diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 96864183f92e..23769e937c28 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -732,7 +732,7 @@ static int bond_check_dev_link(struct bonding *bond, BMSR_LSTATUS : 0; /* Ethtool can't be used, fallback to MII ioctls. */ - ioctl = slave_ops->ndo_do_ioctl; + ioctl = slave_ops->ndo_eth_ioctl; if (ioctl) { /* TODO: set pointer to correct ioctl on a per team member * bases to make this more efficient. that is, once @@ -756,7 +756,7 @@ static int bond_check_dev_link(struct bonding *bond, } } - /* If reporting, report that either there's no dev->do_ioctl, + /* If reporting, report that either there's no ndo_eth_ioctl, * or both SIOCGMIIREG and get_link failed (meaning that we * cannot report link status). If not reporting, pretend * we're ok. @@ -1733,7 +1733,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, if (!bond->params.use_carrier && slave_dev->ethtool_ops->get_link == NULL && - slave_ops->ndo_do_ioctl == NULL) { + slave_ops->ndo_eth_ioctl == NULL) { slave_warn(bond_dev, slave_dev, "no link monitoring support\n"); } @@ -3962,20 +3962,13 @@ static void bond_get_stats(struct net_device *bond_dev, rcu_read_unlock(); } -static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) +static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) { struct bonding *bond = netdev_priv(bond_dev); - struct net_device *slave_dev = NULL; - struct ifbond k_binfo; - struct ifbond __user *u_binfo = NULL; - struct ifslave k_sinfo; - struct ifslave __user *u_sinfo = NULL; struct mii_ioctl_data *mii = NULL; - struct bond_opt_value newval; - struct net *net; - int res = 0; + int res; - netdev_dbg(bond_dev, "bond_ioctl: cmd=%d\n", cmd); + netdev_dbg(bond_dev, "bond_eth_ioctl: cmd=%d\n", cmd); switch (cmd) { case SIOCGMIIPHY: @@ -4000,6 +3993,28 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd } return 0; + default: + res = -EOPNOTSUPP; + } + + return res; +} + +static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct net_device *slave_dev = NULL; + struct ifbond k_binfo; + struct ifbond __user *u_binfo = NULL; + struct ifslave k_sinfo; + struct ifslave __user *u_sinfo = NULL; + struct bond_opt_value newval; + struct net *net; + int res = 0; + + netdev_dbg(bond_dev, "bond_ioctl: cmd=%d\n", cmd); + + switch (cmd) { case SIOCBONDINFOQUERY: u_binfo = (struct ifbond __user *)ifr->ifr_data; @@ -4972,6 +4987,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_start_xmit = bond_start_xmit, .ndo_select_queue = bond_select_queue, .ndo_get_stats64 = bond_get_stats, + .ndo_eth_ioctl = bond_eth_ioctl, .ndo_do_ioctl = bond_do_ioctl, .ndo_siocdevprivate = bond_siocdevprivate, .ndo_change_rx_flags = bond_change_rx_flags, diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c index f66e7fb9a2bb..dd4d3c48b98d 100644 --- a/drivers/net/ethernet/3com/3c574_cs.c +++ b/drivers/net/ethernet/3com/3c574_cs.c @@ -252,7 +252,7 @@ static const struct net_device_ops el3_netdev_ops = { .ndo_start_xmit = el3_start_xmit, .ndo_tx_timeout = el3_tx_timeout, .ndo_get_stats = el3_get_stats, - .ndo_do_ioctl = el3_ioctl, + .ndo_eth_ioctl = el3_ioctl, .ndo_set_rx_mode = set_multicast_list, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 7d7d3ffe25c3..17c16333a412 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -1052,7 +1052,7 @@ static const struct net_device_ops boomrang_netdev_ops = { .ndo_tx_timeout = vortex_tx_timeout, .ndo_get_stats = vortex_get_stats, #ifdef CONFIG_PCI - .ndo_do_ioctl = vortex_ioctl, + .ndo_eth_ioctl = vortex_ioctl, #endif .ndo_set_rx_mode = set_rx_mode, .ndo_set_mac_address = eth_mac_addr, @@ -1069,7 +1069,7 @@ static const struct net_device_ops vortex_netdev_ops = { .ndo_tx_timeout = vortex_tx_timeout, .ndo_get_stats = vortex_get_stats, #ifdef CONFIG_PCI - .ndo_do_ioctl = vortex_ioctl, + .ndo_eth_ioctl = vortex_ioctl, #endif .ndo_set_rx_mode = set_rx_mode, .ndo_set_mac_address = eth_mac_addr, diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index 172947fc051a..9595dd1f32ca 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -635,7 +635,7 @@ static void ax_eeprom_register_write(struct eeprom_93cx6 *eeprom) static const struct net_device_ops ax_netdev_ops = { .ndo_open = ax_open, .ndo_stop = ax_close, - .ndo_do_ioctl = ax_ioctl, + .ndo_eth_ioctl = ax_ioctl, .ndo_start_xmit = ax_ei_start_xmit, .ndo_tx_timeout = ax_ei_tx_timeout, diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index 8c321dfc7b3b..3c370e686ec3 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -128,7 +128,7 @@ static inline struct axnet_dev *PRIV(struct net_device *dev) static const struct net_device_ops axnet_netdev_ops = { .ndo_open = axnet_open, .ndo_stop = axnet_close, - .ndo_do_ioctl = axnet_ioctl, + .ndo_eth_ioctl = axnet_ioctl, .ndo_start_xmit = axnet_start_xmit, .ndo_tx_timeout = axnet_tx_timeout, .ndo_get_stats = get_stats, diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index cac036706382..96ad72abd373 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -223,7 +223,7 @@ static const struct net_device_ops pcnet_netdev_ops = { .ndo_set_config = set_config, .ndo_start_xmit = ei_start_xmit, .ndo_get_stats = ei_get_stats, - .ndo_do_ioctl = ei_ioctl, + .ndo_eth_ioctl = ei_ioctl, .ndo_set_rx_mode = ei_set_multicast_list, .ndo_tx_timeout = ei_tx_timeout, .ndo_set_mac_address = eth_mac_addr, diff --git a/drivers/net/ethernet/actions/owl-emac.c b/drivers/net/ethernet/actions/owl-emac.c index b8e771c2bc40..c4ecf4fcadf8 100644 --- a/drivers/net/ethernet/actions/owl-emac.c +++ b/drivers/net/ethernet/actions/owl-emac.c @@ -1179,8 +1179,8 @@ static int owl_emac_ndo_set_mac_addr(struct net_device *netdev, void *addr) return owl_emac_setup_frame_xmit(netdev_priv(netdev)); } -static int owl_emac_ndo_do_ioctl(struct net_device *netdev, - struct ifreq *req, int cmd) +static int owl_emac_ndo_eth_ioctl(struct net_device *netdev, + struct ifreq *req, int cmd) { if (!netif_running(netdev)) return -EINVAL; @@ -1224,7 +1224,7 @@ static const struct net_device_ops owl_emac_netdev_ops = { .ndo_set_rx_mode = owl_emac_ndo_set_rx_mode, .ndo_set_mac_address = owl_emac_ndo_set_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = owl_emac_ndo_do_ioctl, + .ndo_eth_ioctl = owl_emac_ndo_eth_ioctl, .ndo_tx_timeout = owl_emac_ndo_tx_timeout, .ndo_get_stats = owl_emac_ndo_get_stats, }; diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index 7965e5e3c985..e0f6cc910bd2 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -625,7 +625,7 @@ static const struct net_device_ops netdev_ops = { .ndo_tx_timeout = tx_timeout, .ndo_get_stats = get_stats, .ndo_set_rx_mode = set_rx_mode, - .ndo_do_ioctl = netdev_ioctl, + .ndo_eth_ioctl = netdev_ioctl, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef VLAN_SUPPORT diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index 41f8821f792d..920633161174 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -3882,7 +3882,7 @@ static const struct net_device_ops et131x_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_get_stats = et131x_stats, - .ndo_do_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, }; static int et131x_pci_setup(struct pci_dev *pdev, diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index f99ae317c188..037baea1c738 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -774,7 +774,7 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_start_xmit = emac_start_xmit, .ndo_tx_timeout = emac_timeout, .ndo_set_rx_mode = emac_set_rx_mode, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = emac_set_mac_address, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 9cac5aa75a73..92e4246dc359 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -1729,7 +1729,7 @@ static const struct net_device_ops amd8111e_netdev_ops = { .ndo_set_rx_mode = amd8111e_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = amd8111e_set_mac_address, - .ndo_do_ioctl = amd8111e_ioctl, + .ndo_eth_ioctl = amd8111e_ioctl, .ndo_change_mtu = amd8111e_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = amd8111e_poll, diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index 19e195420e24..9c1636222b99 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -1051,7 +1051,7 @@ static const struct net_device_ops au1000_netdev_ops = { .ndo_stop = au1000_close, .ndo_start_xmit = au1000_tx, .ndo_set_rx_mode = au1000_multicast_list, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_tx_timeout = au1000_tx_timeout, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 4100ab07e6b7..70d76fdb9f56 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1572,7 +1572,7 @@ static const struct net_device_ops pcnet32_netdev_ops = { .ndo_tx_timeout = pcnet32_tx_timeout, .ndo_get_stats = pcnet32_get_stats, .ndo_set_rx_mode = pcnet32_set_multicast_list, - .ndo_do_ioctl = pcnet32_ioctl, + .ndo_eth_ioctl = pcnet32_ioctl, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 4f714f874c4f..17a585adfb49 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -2284,7 +2284,7 @@ static const struct net_device_ops xgbe_netdev_ops = { .ndo_set_rx_mode = xgbe_set_rx_mode, .ndo_set_mac_address = xgbe_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = xgbe_ioctl, + .ndo_eth_ioctl = xgbe_ioctl, .ndo_change_mtu = xgbe_change_mtu, .ndo_tx_timeout = xgbe_tx_timeout, .ndo_get_stats64 = xgbe_get_stats64, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index 4af0cd9530de..e22935ce9573 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -421,7 +421,7 @@ static const struct net_device_ops aq_ndev_ops = { .ndo_change_mtu = aq_ndev_change_mtu, .ndo_set_mac_address = aq_ndev_set_mac_address, .ndo_set_features = aq_ndev_set_features, - .ndo_do_ioctl = aq_ndev_ioctl, + .ndo_eth_ioctl = aq_ndev_ioctl, .ndo_vlan_rx_add_vid = aq_ndo_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = aq_ndo_vlan_rx_kill_vid, .ndo_setup_tc = aq_ndo_setup_tc, diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 67b8113a2b53..38c288ec9059 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -844,7 +844,7 @@ static const struct net_device_ops arc_emac_netdev_ops = { .ndo_set_mac_address = arc_emac_set_address, .ndo_get_stats = arc_emac_stats, .ndo_set_rx_mode = arc_emac_set_rx_mode, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = arc_emac_poll_controller, #endif diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 1ba81b1eb6fd..02ae98aabf91 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1851,7 +1851,7 @@ static const struct net_device_ops ag71xx_netdev_ops = { .ndo_open = ag71xx_open, .ndo_stop = ag71xx_stop, .ndo_start_xmit = ag71xx_hard_start_xmit, - .ndo_do_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_tx_timeout = ag71xx_tx_timeout, .ndo_change_mtu = ag71xx_change_mtu, .ndo_set_mac_address = eth_mac_addr, diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 11ef1fbe7aee..4ea157efca86 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1701,7 +1701,7 @@ static const struct net_device_ops alx_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = alx_set_mac_address, .ndo_change_mtu = alx_change_mtu, - .ndo_do_ioctl = alx_ioctl, + .ndo_eth_ioctl = alx_ioctl, .ndo_tx_timeout = alx_tx_timeout, .ndo_fix_features = alx_fix_features, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 1c6246a5dc22..3b51b172b317 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2609,7 +2609,7 @@ static const struct net_device_ops atl1c_netdev_ops = { .ndo_change_mtu = atl1c_change_mtu, .ndo_fix_features = atl1c_fix_features, .ndo_set_features = atl1c_set_features, - .ndo_do_ioctl = atl1c_ioctl, + .ndo_eth_ioctl = atl1c_ioctl, .ndo_tx_timeout = atl1c_tx_timeout, .ndo_get_stats = atl1c_get_stats, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 2eb0a2ab69f6..753973ac922e 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -2247,7 +2247,7 @@ static const struct net_device_ops atl1e_netdev_ops = { .ndo_fix_features = atl1e_fix_features, .ndo_set_features = atl1e_set_features, .ndo_change_mtu = atl1e_change_mtu, - .ndo_do_ioctl = atl1e_ioctl, + .ndo_eth_ioctl = atl1e_ioctl, .ndo_tx_timeout = atl1e_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = atl1e_netpoll, diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index c67201a13cf5..68f6c0bbd945 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -2885,7 +2885,7 @@ static const struct net_device_ops atl1_netdev_ops = { .ndo_change_mtu = atl1_change_mtu, .ndo_fix_features = atlx_fix_features, .ndo_set_features = atlx_set_features, - .ndo_do_ioctl = atlx_ioctl, + .ndo_eth_ioctl = atlx_ioctl, .ndo_tx_timeout = atlx_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = atl1_poll_controller, diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index 0cc0db04c27d..b69298ddb647 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -1293,7 +1293,7 @@ static const struct net_device_ops atl2_netdev_ops = { .ndo_change_mtu = atl2_change_mtu, .ndo_fix_features = atl2_fix_features, .ndo_set_features = atl2_set_features, - .ndo_do_ioctl = atl2_ioctl, + .ndo_eth_ioctl = atl2_ioctl, .ndo_tx_timeout = atl2_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = atl2_poll_controller, diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index ad2655efe423..fa784953c601 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -2198,7 +2198,7 @@ static const struct net_device_ops b44_netdev_ops = { .ndo_set_rx_mode = b44_set_rx_mode, .ndo_set_mac_address = b44_set_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = b44_ioctl, + .ndo_eth_ioctl = b44_ioctl, .ndo_tx_timeout = b44_tx_timeout, .ndo_change_mtu = b44_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 977f097fc7bf..5ec056a26cf8 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1699,7 +1699,7 @@ static const struct net_device_ops bcm_enet_ops = { .ndo_start_xmit = bcm_enet_start_xmit, .ndo_set_mac_address = bcm_enet_set_mac_address, .ndo_set_rx_mode = bcm_enet_set_multicast_list, - .ndo_do_ioctl = bcm_enet_ioctl, + .ndo_eth_ioctl = bcm_enet_ioctl, .ndo_change_mtu = bcm_enet_change_mtu, }; @@ -2446,7 +2446,7 @@ static const struct net_device_ops bcm_enetsw_ops = { .ndo_stop = bcm_enetsw_stop, .ndo_start_xmit = bcm_enet_start_xmit, .ndo_change_mtu = bcm_enet_change_mtu, - .ndo_do_ioctl = bcm_enetsw_ioctl, + .ndo_eth_ioctl = bcm_enetsw_ioctl, }; diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 075f6e146b29..fe4d99abd548 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1263,7 +1263,7 @@ static const struct net_device_ops bgmac_netdev_ops = { .ndo_set_rx_mode = bgmac_set_rx_mode, .ndo_set_mac_address = bgmac_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_change_mtu = bgmac_change_mtu, }; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index bee6cfad9fc6..89ee1c0e9c79 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -8546,7 +8546,7 @@ static const struct net_device_ops bnx2_netdev_ops = { .ndo_stop = bnx2_close, .ndo_get_stats64 = bnx2_get_stats64, .ndo_set_rx_mode = bnx2_set_rx_mode, - .ndo_do_ioctl = bnx2_ioctl, + .ndo_eth_ioctl = bnx2_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = bnx2_change_mac_addr, .ndo_change_mtu = bnx2_change_mtu, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 2acbc73dcd18..6d98134913cd 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13048,7 +13048,7 @@ static const struct net_device_ops bnx2x_netdev_ops = { .ndo_set_rx_mode = bnx2x_set_rx_mode, .ndo_set_mac_address = bnx2x_change_mac_addr, .ndo_validate_addr = bnx2x_validate_addr, - .ndo_do_ioctl = bnx2x_ioctl, + .ndo_eth_ioctl = bnx2x_ioctl, .ndo_change_mtu = bnx2x_change_mtu, .ndo_fix_features = bnx2x_fix_features, .ndo_set_features = bnx2x_set_features, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4db162cee911..e34c362a3c58 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12667,7 +12667,7 @@ static const struct net_device_ops bnxt_netdev_ops = { .ndo_stop = bnxt_close, .ndo_get_stats64 = bnxt_get_stats64, .ndo_set_rx_mode = bnxt_set_rx_mode, - .ndo_do_ioctl = bnxt_ioctl, + .ndo_eth_ioctl = bnxt_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = bnxt_change_mac_addr, .ndo_change_mtu = bnxt_change_mtu, diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index db74241935ab..63e2237e0cb4 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3659,7 +3659,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = { .ndo_tx_timeout = bcmgenet_timeout, .ndo_set_rx_mode = bcmgenet_set_rx_mode, .ndo_set_mac_address = bcmgenet_set_mac_addr, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_features = bcmgenet_set_features, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = bcmgenet_poll_controller, diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index 5b4568c2ad1c..f38f40eb966e 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -2136,7 +2136,7 @@ static const struct net_device_ops sbmac_netdev_ops = { .ndo_start_xmit = sbmac_start_tx, .ndo_set_rx_mode = sbmac_set_rx_mode, .ndo_tx_timeout = sbmac_tx_timeout, - .ndo_do_ioctl = sbmac_mii_ioctl, + .ndo_eth_ioctl = sbmac_mii_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index b0e49643f483..6f82eeaa4b9f 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -14290,7 +14290,7 @@ static const struct net_device_ops tg3_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = tg3_set_rx_mode, .ndo_set_mac_address = tg3_set_mac_addr, - .ndo_do_ioctl = tg3_ioctl, + .ndo_eth_ioctl = tg3_ioctl, .ndo_tx_timeout = tg3_tx_timeout, .ndo_change_mtu = tg3_change_mtu, .ndo_fix_features = tg3_fix_features, diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 7d2fe13a52f8..181ebc235925 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3664,7 +3664,7 @@ static const struct net_device_ops macb_netdev_ops = { .ndo_start_xmit = macb_start_xmit, .ndo_set_rx_mode = macb_set_rx_mode, .ndo_get_stats = macb_get_stats, - .ndo_do_ioctl = macb_ioctl, + .ndo_eth_ioctl = macb_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = macb_change_mtu, .ndo_set_mac_address = eth_mac_addr, @@ -4323,7 +4323,7 @@ static const struct net_device_ops at91ether_netdev_ops = { .ndo_get_stats = macb_get_stats, .ndo_set_rx_mode = macb_set_rx_mode, .ndo_set_mac_address = eth_mac_addr, - .ndo_do_ioctl = macb_ioctl, + .ndo_eth_ioctl = macb_ioctl, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = at91ether_poll_controller, diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 591229b96257..a4a5209a9386 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3223,7 +3223,7 @@ static const struct net_device_ops lionetdevops = { .ndo_vlan_rx_add_vid = liquidio_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = liquidio_vlan_rx_kill_vid, .ndo_change_mtu = liquidio_change_mtu, - .ndo_do_ioctl = liquidio_ioctl, + .ndo_eth_ioctl = liquidio_ioctl, .ndo_fix_features = liquidio_fix_features, .ndo_set_features = liquidio_set_features, .ndo_set_vf_mac = liquidio_set_vf_mac, diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index ffddb3126a32..3085dd455a17 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -1889,7 +1889,7 @@ static const struct net_device_ops lionetdevops = { .ndo_vlan_rx_add_vid = liquidio_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = liquidio_vlan_rx_kill_vid, .ndo_change_mtu = liquidio_change_mtu, - .ndo_do_ioctl = liquidio_ioctl, + .ndo_eth_ioctl = liquidio_ioctl, .ndo_fix_features = liquidio_fix_features, .ndo_set_features = liquidio_set_features, }; diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 48ff6fb0eed9..30463a6d1f8c 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -1373,7 +1373,7 @@ static const struct net_device_ops octeon_mgmt_ops = { .ndo_start_xmit = octeon_mgmt_xmit, .ndo_set_rx_mode = octeon_mgmt_set_rx_filtering, .ndo_set_mac_address = octeon_mgmt_set_mac_address, - .ndo_do_ioctl = octeon_mgmt_ioctl, + .ndo_eth_ioctl = octeon_mgmt_ioctl, .ndo_change_mtu = octeon_mgmt_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = octeon_mgmt_poll_controller, diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index e2b290135fd9..efaaa57d4ed5 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -2096,7 +2096,7 @@ static const struct net_device_ops nicvf_netdev_ops = { .ndo_fix_features = nicvf_fix_features, .ndo_set_features = nicvf_set_features, .ndo_bpf = nicvf_xdp, - .ndo_do_ioctl = nicvf_ioctl, + .ndo_eth_ioctl = nicvf_ioctl, .ndo_set_rx_mode = nicvf_set_rx_mode, }; diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c index 512da98019c6..e7575d41f4f5 100644 --- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c +++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c @@ -924,7 +924,7 @@ static const struct net_device_ops cxgb_netdev_ops = { .ndo_get_stats = t1_get_stats, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = t1_set_rxmode, - .ndo_do_ioctl = t1_ioctl, + .ndo_eth_ioctl = t1_ioctl, .ndo_change_mtu = t1_change_mtu, .ndo_set_mac_address = t1_set_mac_addr, .ndo_fix_features = t1_fix_features, diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index eae893d7d840..72af9d2a00ae 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -3184,7 +3184,7 @@ static const struct net_device_ops cxgb_netdev_ops = { .ndo_get_stats = cxgb_get_stats, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = cxgb_set_rxmode, - .ndo_do_ioctl = cxgb_ioctl, + .ndo_eth_ioctl = cxgb_ioctl, .ndo_siocdevprivate = cxgb_siocdevprivate, .ndo_change_mtu = cxgb_change_mtu, .ndo_set_mac_address = cxgb_set_mac_addr, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index dbf9a0e6601d..aa8573202c37 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3872,7 +3872,7 @@ static const struct net_device_ops cxgb4_netdev_ops = { .ndo_set_mac_address = cxgb_set_mac_addr, .ndo_set_features = cxgb_set_features, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = cxgb_ioctl, + .ndo_eth_ioctl = cxgb_ioctl, .ndo_change_mtu = cxgb_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = cxgb_netpoll, diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 2820a0bb971b..2842628ad2c5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2837,7 +2837,7 @@ static const struct net_device_ops cxgb4vf_netdev_ops = { .ndo_set_rx_mode = cxgb4vf_set_rxmode, .ndo_set_mac_address = cxgb4vf_set_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = cxgb4vf_do_ioctl, + .ndo_eth_ioctl = cxgb4vf_do_ioctl, .ndo_change_mtu = cxgb4vf_change_mtu, .ndo_fix_features = cxgb4vf_fix_features, .ndo_set_features = cxgb4vf_set_features, diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c index 9f5e5ec69991..072fac5f5d24 100644 --- a/drivers/net/ethernet/cirrus/ep93xx_eth.c +++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c @@ -733,7 +733,7 @@ static const struct net_device_ops ep93xx_netdev_ops = { .ndo_open = ep93xx_open, .ndo_stop = ep93xx_close, .ndo_start_xmit = ep93xx_xmit, - .ndo_do_ioctl = ep93xx_ioctl, + .ndo_eth_ioctl = ep93xx_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 2a8bf53c2f75..e842de6f6635 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1372,7 +1372,7 @@ static const struct net_device_ops dm9000_netdev_ops = { .ndo_start_xmit = dm9000_start_xmit, .ndo_tx_timeout = dm9000_timeout, .ndo_set_rx_mode = dm9000_hash_table, - .ndo_do_ioctl = dm9000_ioctl, + .ndo_eth_ioctl = dm9000_ioctl, .ndo_set_features = dm9000_set_features, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index c1dcd6ca1457..fcedd733bacb 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1271,7 +1271,7 @@ static const struct net_device_ops tulip_netdev_ops = { .ndo_tx_timeout = tulip_tx_timeout, .ndo_stop = tulip_close, .ndo_get_stats = tulip_get_stats, - .ndo_do_ioctl = private_ioctl, + .ndo_eth_ioctl = private_ioctl, .ndo_set_rx_mode = set_rx_mode, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index f6ff1f76eacb..07a48f6bf0fa 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -341,7 +341,7 @@ static const struct net_device_ops netdev_ops = { .ndo_start_xmit = start_tx, .ndo_get_stats = get_stats, .ndo_set_rx_mode = set_rx_mode, - .ndo_do_ioctl = netdev_ioctl, + .ndo_eth_ioctl = netdev_ioctl, .ndo_tx_timeout = tx_timeout, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 734acb834c98..202ecb132053 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -95,7 +95,7 @@ static const struct net_device_ops netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_set_rx_mode = set_multicast, - .ndo_do_ioctl = rio_ioctl, + .ndo_eth_ioctl = rio_ioctl, .ndo_tx_timeout = rio_tx_timeout, }; diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index ee0ca712dd1c..c36d186dffed 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -479,7 +479,7 @@ static const struct net_device_ops netdev_ops = { .ndo_start_xmit = start_tx, .ndo_get_stats = get_stats, .ndo_set_rx_mode = set_rx_mode, - .ndo_do_ioctl = netdev_ioctl, + .ndo_eth_ioctl = netdev_ioctl, .ndo_tx_timeout = tx_timeout, .ndo_change_mtu = change_mtu, .ndo_set_mac_address = sundance_set_mac_addr, diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index 48c6eb142dcc..6c51cf991dad 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -742,7 +742,7 @@ static const struct net_device_ops dnet_netdev_ops = { .ndo_stop = dnet_close, .ndo_get_stats = dnet_get_stats, .ndo_start_xmit = dnet_start_xmit, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index e1b43b07755b..ed1ed48e7483 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -1009,7 +1009,7 @@ static const struct ethtool_ops ethoc_ethtool_ops = { static const struct net_device_ops ethoc_netdev_ops = { .ndo_open = ethoc_open, .ndo_stop = ethoc_stop, - .ndo_do_ioctl = ethoc_ioctl, + .ndo_eth_ioctl = ethoc_ioctl, .ndo_set_mac_address = ethoc_set_mac_address, .ndo_set_rx_mode = ethoc_set_multicast_list, .ndo_change_mtu = ethoc_change_mtu, diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 11dbbfd38770..ff76e401a014 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1616,7 +1616,7 @@ static const struct net_device_ops ftgmac100_netdev_ops = { .ndo_start_xmit = ftgmac100_hard_start_xmit, .ndo_set_mac_address = ftgmac100_set_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_tx_timeout = ftgmac100_tx_timeout, .ndo_set_rx_mode = ftgmac100_set_rx_mode, .ndo_set_features = ftgmac100_set_features, diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c index 5a1a8f2ea63c..8a341e2d5833 100644 --- a/drivers/net/ethernet/faraday/ftmac100.c +++ b/drivers/net/ethernet/faraday/ftmac100.c @@ -1043,7 +1043,7 @@ static const struct net_device_ops ftmac100_netdev_ops = { .ndo_start_xmit = ftmac100_hard_start_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = ftmac100_do_ioctl, + .ndo_eth_ioctl = ftmac100_do_ioctl, }; /****************************************************************************** diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c index 0f141c14d72d..25c91b3c5fd3 100644 --- a/drivers/net/ethernet/fealnx.c +++ b/drivers/net/ethernet/fealnx.c @@ -463,7 +463,7 @@ static const struct net_device_ops netdev_ops = { .ndo_start_xmit = start_tx, .ndo_get_stats = get_stats, .ndo_set_rx_mode = set_rx_mode, - .ndo_do_ioctl = mii_ioctl, + .ndo_eth_ioctl = mii_ioctl, .ndo_tx_timeout = fealnx_tx_timeout, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index e6826561cf11..685d2d8a3b36 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -3157,7 +3157,7 @@ static const struct net_device_ops dpaa_ops = { .ndo_set_mac_address = dpaa_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = dpaa_set_rx_mode, - .ndo_do_ioctl = dpaa_ioctl, + .ndo_eth_ioctl = dpaa_ioctl, .ndo_setup_tc = dpaa_setup_tc, .ndo_change_mtu = dpaa_change_mtu, .ndo_bpf = dpaa_xdp, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 973352393bd4..f664021c3ad1 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -2594,7 +2594,7 @@ static const struct net_device_ops dpaa2_eth_ops = { .ndo_get_stats64 = dpaa2_eth_get_stats, .ndo_set_rx_mode = dpaa2_eth_set_rx_mode, .ndo_set_features = dpaa2_eth_set_features, - .ndo_do_ioctl = dpaa2_eth_ioctl, + .ndo_eth_ioctl = dpaa2_eth_ioctl, .ndo_change_mtu = dpaa2_eth_change_mtu, .ndo_bpf = dpaa2_eth_xdp, .ndo_xdp_xmit = dpaa2_eth_xdp_xmit, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index c84f6c226743..60d94e0a07d6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -735,7 +735,7 @@ static const struct net_device_ops enetc_ndev_ops = { .ndo_set_vf_vlan = enetc_pf_set_vf_vlan, .ndo_set_vf_spoofchk = enetc_pf_set_vf_spoofchk, .ndo_set_features = enetc_pf_set_features, - .ndo_do_ioctl = enetc_ioctl, + .ndo_eth_ioctl = enetc_ioctl, .ndo_setup_tc = enetc_setup_tc, .ndo_bpf = enetc_setup_bpf, .ndo_xdp_xmit = enetc_xdp_xmit, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index 03090ba7e226..1a9d1e8b772c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -99,7 +99,7 @@ static const struct net_device_ops enetc_ndev_ops = { .ndo_get_stats = enetc_get_stats, .ndo_set_mac_address = enetc_vf_set_mac_addr, .ndo_set_features = enetc_vf_set_features, - .ndo_do_ioctl = enetc_ioctl, + .ndo_eth_ioctl = enetc_ioctl, .ndo_setup_tc = enetc_setup_tc, }; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 8aea707a65a7..e361be85f26f 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3280,7 +3280,7 @@ static const struct net_device_ops fec_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = fec_timeout, .ndo_set_mac_address = fec_set_mac_address, - .ndo_do_ioctl = fec_enet_ioctl, + .ndo_eth_ioctl = fec_enet_ioctl, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = fec_poll_controller, #endif diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c index 02c47658a215..73ff359a15f1 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c @@ -792,7 +792,7 @@ static const struct net_device_ops mpc52xx_fec_netdev_ops = { .ndo_set_rx_mode = mpc52xx_fec_set_multicast_list, .ndo_set_mac_address = mpc52xx_fec_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_tx_timeout = mpc52xx_fec_tx_timeout, .ndo_get_stats = mpc52xx_fec_get_stats, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index 6ee325ad35c5..2db6e38a772e 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -900,7 +900,7 @@ static const struct net_device_ops fs_enet_netdev_ops = { .ndo_start_xmit = fs_enet_start_xmit, .ndo_tx_timeout = fs_timeout, .ndo_set_rx_mode = fs_set_multicast_list, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 9646483137c4..af6ad94bf24a 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -3184,7 +3184,7 @@ static const struct net_device_ops gfar_netdev_ops = { .ndo_set_features = gfar_set_features, .ndo_set_rx_mode = gfar_set_multi, .ndo_tx_timeout = gfar_timeout, - .ndo_do_ioctl = gfar_ioctl, + .ndo_eth_ioctl = gfar_ioctl, .ndo_get_stats64 = gfar_get_stats64, .ndo_change_carrier = fixed_phy_change_carrier, .ndo_set_mac_address = gfar_set_mac_addr, diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 0acfafb73db1..3eb288d10b0c 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3516,7 +3516,7 @@ static const struct net_device_ops ucc_geth_netdev_ops = { .ndo_set_mac_address = ucc_geth_set_mac_addr, .ndo_set_rx_mode = ucc_geth_set_multi, .ndo_tx_timeout = ucc_geth_timeout, - .ndo_do_ioctl = ucc_geth_ioctl, + .ndo_eth_ioctl = ucc_geth_ioctl, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ucc_netpoll, #endif diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c index 3c4db4a6b431..22bf914f2dbd 100644 --- a/drivers/net/ethernet/hisilicon/hisi_femac.c +++ b/drivers/net/ethernet/hisilicon/hisi_femac.c @@ -685,7 +685,7 @@ static const struct net_device_ops hisi_femac_netdev_ops = { .ndo_open = hisi_femac_net_open, .ndo_stop = hisi_femac_net_close, .ndo_start_xmit = hisi_femac_net_xmit, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_mac_address = hisi_femac_set_mac_address, .ndo_set_rx_mode = hisi_femac_net_set_rx_mode, }; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index ad534f9e41ab..343c605c4be8 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1945,7 +1945,7 @@ static const struct net_device_ops hns_nic_netdev_ops = { .ndo_tx_timeout = hns_nic_net_timeout, .ndo_set_mac_address = hns_nic_net_set_mac_address, .ndo_change_mtu = hns_nic_change_mtu, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_features = hns_nic_set_features, .ndo_fix_features = hns_nic_fix_features, .ndo_get_stats64 = hns_nic_get_stats64, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index cdb5f14fb6bc..cb8d5da3654f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2852,7 +2852,7 @@ static const struct net_device_ops hns3_nic_netdev_ops = { .ndo_start_xmit = hns3_nic_net_xmit, .ndo_tx_timeout = hns3_nic_net_timeout, .ndo_set_mac_address = hns3_nic_net_set_mac_address, - .ndo_do_ioctl = hns3_nic_do_ioctl, + .ndo_eth_ioctl = hns3_nic_do_ioctl, .ndo_change_mtu = hns3_nic_change_mtu, .ndo_set_features = hns3_nic_set_features, .ndo_features_check = hns3_features_check, diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 471be6ec7e8a..664a91af662d 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -3011,7 +3011,7 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_stop = emac_close, .ndo_get_stats = emac_stats, .ndo_set_rx_mode = emac_set_multicast_list, - .ndo_do_ioctl = emac_ioctl, + .ndo_eth_ioctl = emac_ioctl, .ndo_tx_timeout = emac_tx_timeout, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = emac_set_mac_address, @@ -3023,7 +3023,7 @@ static const struct net_device_ops emac_gige_netdev_ops = { .ndo_stop = emac_close, .ndo_get_stats = emac_stats, .ndo_set_rx_mode = emac_set_multicast_list, - .ndo_do_ioctl = emac_ioctl, + .ndo_eth_ioctl = emac_ioctl, .ndo_tx_timeout = emac_tx_timeout, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = emac_set_mac_address, diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 737ba85e409f..3d9b4f99d357 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1630,7 +1630,7 @@ static const struct net_device_ops ibmveth_netdev_ops = { .ndo_stop = ibmveth_close, .ndo_start_xmit = ibmveth_start_xmit, .ndo_set_rx_mode = ibmveth_set_multicast_list, - .ndo_do_ioctl = ibmveth_ioctl, + .ndo_eth_ioctl = ibmveth_ioctl, .ndo_change_mtu = ibmveth_change_mtu, .ndo_fix_features = ibmveth_fix_features, .ndo_set_features = ibmveth_set_features, diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 1ec924c556c5..373eb027b925 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2809,7 +2809,7 @@ static const struct net_device_ops e100_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = e100_set_multicast_list, .ndo_set_mac_address = e100_set_mac_address, - .ndo_do_ioctl = e100_do_ioctl, + .ndo_eth_ioctl = e100_do_ioctl, .ndo_tx_timeout = e100_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = e100_netpoll, diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index c2a109126c27..bed4f040face 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -832,7 +832,7 @@ static const struct net_device_ops e1000_netdev_ops = { .ndo_set_mac_address = e1000_set_mac, .ndo_tx_timeout = e1000_tx_timeout, .ndo_change_mtu = e1000_change_mtu, - .ndo_do_ioctl = e1000_ioctl, + .ndo_eth_ioctl = e1000_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_vlan_rx_add_vid = e1000_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = e1000_vlan_rx_kill_vid, diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 3c22b509fa79..900b3ab998bd 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7354,7 +7354,7 @@ static const struct net_device_ops e1000e_netdev_ops = { .ndo_set_rx_mode = e1000e_set_rx_mode, .ndo_set_mac_address = e1000_set_mac, .ndo_change_mtu = e1000_change_mtu, - .ndo_do_ioctl = e1000_ioctl, + .ndo_eth_ioctl = e1000_ioctl, .ndo_tx_timeout = e1000_tx_timeout, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 53c1fbeee62a..5b4012a09acb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13256,7 +13256,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = i40e_set_mac, .ndo_change_mtu = i40e_change_mtu, - .ndo_do_ioctl = i40e_ioctl, + .ndo_eth_ioctl = i40e_ioctl, .ndo_tx_timeout = i40e_tx_timeout, .ndo_vlan_rx_add_vid = i40e_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = i40e_vlan_rx_kill_vid, diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ef8d1815af56..33916ed9e874 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -6558,12 +6558,12 @@ event_after: } /** - * ice_do_ioctl - Access the hwtstamp interface + * ice_eth_ioctl - Access the hwtstamp interface * @netdev: network interface device structure * @ifr: interface request data * @cmd: ioctl command */ -static int ice_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +static int ice_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_pf *pf = np->vsi->back; @@ -7229,7 +7229,7 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_change_mtu = ice_change_mtu, .ndo_get_stats64 = ice_get_stats64, .ndo_set_tx_maxrate = ice_set_tx_maxrate, - .ndo_do_ioctl = ice_do_ioctl, + .ndo_eth_ioctl = ice_eth_ioctl, .ndo_set_vf_spoofchk = ice_set_vf_spoofchk, .ndo_set_vf_mac = ice_set_vf_mac, .ndo_get_vf_config = ice_get_vf_cfg, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 171a7a629b20..751de06019a0 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2991,7 +2991,7 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_set_rx_mode = igb_set_rx_mode, .ndo_set_mac_address = igb_set_mac, .ndo_change_mtu = igb_change_mtu, - .ndo_do_ioctl = igb_ioctl, + .ndo_eth_ioctl = igb_ioctl, .ndo_tx_timeout = igb_tx_timeout, .ndo_validate_addr = eth_validate_addr, .ndo_vlan_rx_add_vid = igb_vlan_rx_add_vid, diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 1bbe9862a758..d32e72d953c8 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2657,7 +2657,7 @@ static const struct net_device_ops igbvf_netdev_ops = { .ndo_set_rx_mode = igbvf_set_rx_mode, .ndo_set_mac_address = igbvf_set_mac, .ndo_change_mtu = igbvf_change_mtu, - .ndo_do_ioctl = igbvf_ioctl, + .ndo_eth_ioctl = igbvf_ioctl, .ndo_tx_timeout = igbvf_tx_timeout, .ndo_vlan_rx_add_vid = igbvf_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = igbvf_vlan_rx_kill_vid, diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 5c95bf82eaf7..b7aab35c1132 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6013,7 +6013,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_fix_features = igc_fix_features, .ndo_set_features = igc_set_features, .ndo_features_check = igc_features_check, - .ndo_do_ioctl = igc_ioctl, + .ndo_eth_ioctl = igc_ioctl, .ndo_setup_tc = igc_setup_tc, .ndo_bpf = igc_bpf, .ndo_xdp_xmit = igc_xdp_xmit, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 14aea40da50f..24e06ba6f5e9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10247,7 +10247,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_set_tx_maxrate = ixgbe_tx_maxrate, .ndo_vlan_rx_add_vid = ixgbe_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ixgbe_vlan_rx_kill_vid, - .ndo_do_ioctl = ixgbe_ioctl, + .ndo_eth_ioctl = ixgbe_ioctl, .ndo_set_vf_mac = ixgbe_ndo_set_vf_mac, .ndo_set_vf_vlan = ixgbe_ndo_set_vf_vlan, .ndo_set_vf_rate = ixgbe_ndo_set_vf_bw, diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index f1b9284e0bea..1251b74fe0e2 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -2901,7 +2901,7 @@ static const struct net_device_ops jme_netdev_ops = { .ndo_open = jme_open, .ndo_stop = jme_close, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = jme_ioctl, + .ndo_eth_ioctl = jme_ioctl, .ndo_start_xmit = jme_start_xmit, .ndo_set_mac_address = jme_set_macaddr, .ndo_set_rx_mode = jme_set_multi, diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index b30a45725374..3e9f324f1061 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -1272,7 +1272,7 @@ static const struct net_device_ops korina_netdev_ops = { .ndo_start_xmit = korina_send_packet, .ndo_set_rx_mode = korina_multicast_list, .ndo_tx_timeout = korina_tx_timeout, - .ndo_do_ioctl = korina_ioctl, + .ndo_eth_ioctl = korina_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 2d0c52f7106b..62f8c5212182 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -609,7 +609,7 @@ static const struct net_device_ops ltq_eth_netdev_ops = { .ndo_stop = ltq_etop_stop, .ndo_start_xmit = ltq_etop_tx, .ndo_change_mtu = ltq_etop_change_mtu, - .ndo_do_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_set_mac_address = ltq_etop_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = ltq_etop_set_multicast_list, diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index d207bfcaf31d..6502c5c2ebca 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -3060,7 +3060,7 @@ static const struct net_device_ops mv643xx_eth_netdev_ops = { .ndo_set_rx_mode = mv643xx_eth_set_rx_mode, .ndo_set_mac_address = mv643xx_eth_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = mv643xx_eth_ioctl, + .ndo_eth_ioctl = mv643xx_eth_ioctl, .ndo_change_mtu = mv643xx_eth_change_mtu, .ndo_set_features = mv643xx_eth_set_features, .ndo_tx_timeout = mv643xx_eth_tx_timeout, diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 975a1a77d445..ff8db311963c 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4994,7 +4994,7 @@ static const struct net_device_ops mvneta_netdev_ops = { .ndo_change_mtu = mvneta_change_mtu, .ndo_fix_features = mvneta_fix_features, .ndo_get_stats64 = mvneta_get_stats64, - .ndo_do_ioctl = mvneta_ioctl, + .ndo_eth_ioctl = mvneta_ioctl, .ndo_bpf = mvneta_xdp, .ndo_xdp_xmit = mvneta_xdp_xmit, .ndo_setup_tc = mvneta_setup_tc, diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 878fb17dea41..99bd8b8aa0e2 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5702,7 +5702,7 @@ static const struct net_device_ops mvpp2_netdev_ops = { .ndo_set_mac_address = mvpp2_set_mac_address, .ndo_change_mtu = mvpp2_change_mtu, .ndo_get_stats64 = mvpp2_get_stats64, - .ndo_do_ioctl = mvpp2_ioctl, + .ndo_eth_ioctl = mvpp2_ioctl, .ndo_vlan_rx_add_vid = mvpp2_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = mvpp2_vlan_rx_kill_vid, .ndo_set_features = mvpp2_set_features, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index f300b807a85b..3f03bbdd8d04 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -2326,7 +2326,7 @@ static const struct net_device_ops otx2_netdev_ops = { .ndo_set_features = otx2_set_features, .ndo_tx_timeout = otx2_tx_timeout, .ndo_get_stats64 = otx2_get_stats64, - .ndo_do_ioctl = otx2_ioctl, + .ndo_eth_ioctl = otx2_ioctl, .ndo_set_vf_mac = otx2_set_vf_mac, .ndo_set_vf_vlan = otx2_set_vf_vlan, .ndo_get_vf_config = otx2_get_vf_config, diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index 9b48ae4bac39..fab53c9b8380 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1377,7 +1377,7 @@ static const struct net_device_ops pxa168_eth_netdev_ops = { .ndo_set_rx_mode = pxa168_eth_set_rx_mode, .ndo_set_mac_address = pxa168_eth_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_change_mtu = pxa168_eth_change_mtu, .ndo_tx_timeout = pxa168_eth_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index d4bb27ba1419..150c06ee3627 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -3787,7 +3787,7 @@ static const struct net_device_ops skge_netdev_ops = { .ndo_open = skge_up, .ndo_stop = skge_down, .ndo_start_xmit = skge_xmit_frame, - .ndo_do_ioctl = skge_ioctl, + .ndo_eth_ioctl = skge_ioctl, .ndo_get_stats = skge_get_stats, .ndo_tx_timeout = skge_tx_timeout, .ndo_change_mtu = skge_change_mtu, diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 8b8bff59c8fe..743ca96527fa 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4693,7 +4693,7 @@ static const struct net_device_ops sky2_netdev_ops[2] = { .ndo_open = sky2_open, .ndo_stop = sky2_close, .ndo_start_xmit = sky2_xmit_frame, - .ndo_do_ioctl = sky2_ioctl, + .ndo_eth_ioctl = sky2_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = sky2_set_mac_address, .ndo_set_rx_mode = sky2_set_multicast, @@ -4710,7 +4710,7 @@ static const struct net_device_ops sky2_netdev_ops[2] = { .ndo_open = sky2_open, .ndo_stop = sky2_close, .ndo_start_xmit = sky2_xmit_frame, - .ndo_do_ioctl = sky2_ioctl, + .ndo_eth_ioctl = sky2_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = sky2_set_mac_address, .ndo_set_rx_mode = sky2_set_multicast, diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 64adfd24e134..398c23cec815 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2933,7 +2933,7 @@ static const struct net_device_ops mtk_netdev_ops = { .ndo_start_xmit = mtk_start_xmit, .ndo_set_mac_address = mtk_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = mtk_do_ioctl, + .ndo_eth_ioctl = mtk_do_ioctl, .ndo_change_mtu = mtk_change_mtu, .ndo_tx_timeout = mtk_tx_timeout, .ndo_get_stats64 = mtk_get_stats64, diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index 96d2891f1675..1d5dd2015453 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -1162,7 +1162,7 @@ static const struct net_device_ops mtk_star_netdev_ops = { .ndo_start_xmit = mtk_star_netdev_start_xmit, .ndo_get_stats64 = mtk_star_netdev_get_stats64, .ndo_set_rx_mode = mtk_star_set_rx_mode, - .ndo_do_ioctl = mtk_star_netdev_ioctl, + .ndo_eth_ioctl = mtk_star_netdev_ioctl, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 5d0c9c62382d..a2f61a87cef8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2828,7 +2828,7 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_set_mac_address = mlx4_en_set_mac, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = mlx4_en_change_mtu, - .ndo_do_ioctl = mlx4_en_ioctl, + .ndo_eth_ioctl = mlx4_en_ioctl, .ndo_tx_timeout = mlx4_en_tx_timeout, .ndo_vlan_rx_add_vid = mlx4_en_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = mlx4_en_vlan_rx_kill_vid, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b9a0459b58f1..b6c1e3124f96 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4417,7 +4417,7 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_set_features = mlx5e_set_features, .ndo_fix_features = mlx5e_fix_features, .ndo_change_mtu = mlx5e_change_nic_mtu, - .ndo_do_ioctl = mlx5e_ioctl, + .ndo_eth_ioctl = mlx5e_ioctl, .ndo_set_tx_maxrate = mlx5e_set_tx_maxrate, .ndo_features_check = mlx5e_features_check, .ndo_tx_timeout = mlx5e_tx_timeout, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 6535c636ae22..a126cbc6f0d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -50,7 +50,7 @@ static const struct net_device_ops mlx5i_netdev_ops = { .ndo_init = mlx5i_dev_init, .ndo_uninit = mlx5i_dev_cleanup, .ndo_change_mtu = mlx5i_change_mtu, - .ndo_do_ioctl = mlx5i_ioctl, + .ndo_eth_ioctl = mlx5i_ioctl, }; /* IPoIB mlx5 netdev profile */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 18ee21b06a00..5308f23702bc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -149,7 +149,7 @@ static const struct net_device_ops mlx5i_pkey_netdev_ops = { .ndo_get_stats64 = mlx5i_get_stats, .ndo_uninit = mlx5i_pkey_dev_cleanup, .ndo_change_mtu = mlx5i_pkey_change_mtu, - .ndo_do_ioctl = mlx5i_pkey_ioctl, + .ndo_eth_ioctl = mlx5i_pkey_ioctl, }; /* Child NDOs */ diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index a0a059e0154f..d22219613719 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -199,7 +199,7 @@ static int mlxbf_gige_stop(struct net_device *netdev) return 0; } -static int mlxbf_gige_do_ioctl(struct net_device *netdev, +static int mlxbf_gige_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) { if (!(netif_running(netdev))) @@ -253,7 +253,7 @@ static const struct net_device_ops mlxbf_gige_netdev_ops = { .ndo_start_xmit = mlxbf_gige_start_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = mlxbf_gige_do_ioctl, + .ndo_eth_ioctl = mlxbf_gige_eth_ioctl, .ndo_set_rx_mode = mlxbf_gige_set_rx_mode, .ndo_get_stats64 = mlxbf_gige_get_stats64, }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 88699e678544..081408e892d5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1207,7 +1207,7 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = { .ndo_vlan_rx_kill_vid = mlxsw_sp_port_kill_vid, .ndo_set_features = mlxsw_sp_set_features, .ndo_get_devlink_port = mlxsw_sp_port_get_devlink_port, - .ndo_do_ioctl = mlxsw_sp_port_ioctl, + .ndo_eth_ioctl = mlxsw_sp_port_ioctl, }; static int diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 831518466de2..3f69bb59ba49 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -689,7 +689,7 @@ static int ks8851_net_ioctl(struct net_device *dev, struct ifreq *req, int cmd) static const struct net_device_ops ks8851_netdev_ops = { .ndo_open = ks8851_net_open, .ndo_stop = ks8851_net_stop, - .ndo_do_ioctl = ks8851_net_ioctl, + .ndo_eth_ioctl = ks8851_net_ioctl, .ndo_start_xmit = ks8851_start_xmit, .ndo_set_mac_address = ks8851_set_mac_address, .ndo_set_rx_mode = ks8851_set_rx_mode, diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index 7945eb5e2fe8..a0ee155f9f51 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -6738,7 +6738,7 @@ static const struct net_device_ops netdev_ops = { .ndo_set_features = netdev_set_features, .ndo_set_mac_address = netdev_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = netdev_ioctl, + .ndo_eth_ioctl = netdev_ioctl, .ndo_set_rx_mode = netdev_set_rx_mode, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = netdev_netpoll, diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index dae10328c6cf..9e8561cdc32a 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -2655,7 +2655,7 @@ static const struct net_device_ops lan743x_netdev_ops = { .ndo_open = lan743x_netdev_open, .ndo_stop = lan743x_netdev_close, .ndo_start_xmit = lan743x_netdev_xmit_frame, - .ndo_do_ioctl = lan743x_netdev_ioctl, + .ndo_eth_ioctl = lan743x_netdev_ioctl, .ndo_set_rx_mode = lan743x_netdev_set_multicast, .ndo_change_mtu = lan743x_netdev_change_mtu, .ndo_get_stats64 = lan743x_netdev_get_stats64, diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index c52f175df389..de900ea70fd4 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -823,7 +823,7 @@ static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_vlan_rx_kill_vid = ocelot_vlan_rx_kill_vid, .ndo_set_features = ocelot_set_features, .ndo_setup_tc = ocelot_setup_tc, - .ndo_do_ioctl = ocelot_ioctl, + .ndo_eth_ioctl = ocelot_ioctl, .ndo_get_devlink_port = ocelot_get_devlink_port, }; diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index 51b4b25d15ad..bd9d026e609d 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -790,7 +790,7 @@ static const struct net_device_ops natsemi_netdev_ops = { .ndo_get_stats = get_stats, .ndo_set_rx_mode = set_rx_mode, .ndo_change_mtu = natsemi_change_mtu, - .ndo_do_ioctl = netdev_ioctl, + .ndo_eth_ioctl = netdev_ioctl, .ndo_tx_timeout = ns_tx_timeout, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 0b017d4f5c08..09c0e839cca5 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -7625,7 +7625,7 @@ static const struct net_device_ops s2io_netdev_ops = { .ndo_start_xmit = s2io_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = s2io_ndo_set_multicast, - .ndo_do_ioctl = s2io_ioctl, + .ndo_eth_ioctl = s2io_ioctl, .ndo_set_mac_address = s2io_set_mac_addr, .ndo_change_mtu = s2io_change_mtu, .ndo_set_features = s2io_set_features, diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 82eef4c72f01..20fb4ad29865 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -3339,7 +3339,7 @@ static const struct net_device_ops vxge_netdev_ops = { .ndo_start_xmit = vxge_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = vxge_set_multicast, - .ndo_do_ioctl = vxge_ioctl, + .ndo_eth_ioctl = vxge_ioctl, .ndo_set_mac_address = vxge_set_mac_addr, .ndo_change_mtu = vxge_change_mtu, .ndo_fix_features = vxge_fix_features, diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 64c6842bd452..d29fe562b3de 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1219,7 +1219,7 @@ static const struct net_device_ops lpc_netdev_ops = { .ndo_stop = lpc_eth_close, .ndo_start_xmit = lpc_eth_hard_start_xmit, .ndo_set_rx_mode = lpc_eth_set_multicast_list, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_mac_address = lpc_set_mac_address, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index e351f3d1608f..bc35d5703bd2 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -2333,7 +2333,7 @@ static const struct net_device_ops pch_gbe_netdev_ops = { .ndo_tx_timeout = pch_gbe_tx_timeout, .ndo_change_mtu = pch_gbe_change_mtu, .ndo_set_features = pch_gbe_set_features, - .ndo_do_ioctl = pch_gbe_ioctl, + .ndo_eth_ioctl = pch_gbe_ioctl, .ndo_set_rx_mode = pch_gbe_set_multi, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = pch_gbe_netpoll, diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c index 94823c5f7dff..1a6336a56d3d 100644 --- a/drivers/net/ethernet/packetengines/hamachi.c +++ b/drivers/net/ethernet/packetengines/hamachi.c @@ -573,7 +573,7 @@ static const struct net_device_ops hamachi_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_tx_timeout = hamachi_tx_timeout, - .ndo_do_ioctl = hamachi_ioctl, + .ndo_eth_ioctl = hamachi_ioctl, .ndo_siocdevprivate = hamachi_siocdevprivate, }; diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c index d1dd9bc1bc7f..f5cd8f51be7c 100644 --- a/drivers/net/ethernet/packetengines/yellowfin.c +++ b/drivers/net/ethernet/packetengines/yellowfin.c @@ -362,7 +362,7 @@ static const struct net_device_ops netdev_ops = { .ndo_set_rx_mode = set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_do_ioctl = netdev_ioctl, + .ndo_eth_ioctl = netdev_ioctl, .ndo_tx_timeout = yellowfin_tx_timeout, }; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index af3a5368529c..537c2907b91e 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2264,7 +2264,7 @@ static int ionic_stop(struct net_device *netdev) return 0; } -static int ionic_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +static int ionic_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) { struct ionic_lif *lif = netdev_priv(netdev); @@ -2526,7 +2526,7 @@ static int ionic_set_vf_link_state(struct net_device *netdev, int vf, int set) static const struct net_device_ops ionic_netdev_ops = { .ndo_open = ionic_open, .ndo_stop = ionic_stop, - .ndo_do_ioctl = ionic_do_ioctl, + .ndo_eth_ioctl = ionic_eth_ioctl, .ndo_start_xmit = ionic_start_xmit, .ndo_get_stats64 = ionic_get_stats64, .ndo_set_rx_mode = ionic_ndo_set_rx_mode, diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 01ac1e93d27a..173878696143 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -644,7 +644,7 @@ static const struct net_device_ops qede_netdev_ops = { .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = qede_change_mtu, - .ndo_do_ioctl = qede_ioctl, + .ndo_eth_ioctl = qede_ioctl, .ndo_tx_timeout = qede_tx_timeout, #ifdef CONFIG_QED_SRIOV .ndo_set_vf_mac = qede_set_vf_mac, diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index ad655f0a4965..9015a38eaced 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -377,7 +377,7 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_start_xmit = emac_start_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = emac_change_mtu, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_tx_timeout = emac_tx_timeout, .ndo_get_stats64 = emac_get_stats64, .ndo_set_features = emac_set_features, diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index 47e9998b62f0..4b2eca5e08e2 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -954,7 +954,7 @@ static const struct net_device_ops r6040_netdev_ops = { .ndo_set_rx_mode = r6040_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_do_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_tx_timeout = r6040_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = r6040_poll_controller, diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 9677e257e9a1..edc61906694f 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -1869,7 +1869,7 @@ static const struct net_device_ops cp_netdev_ops = { .ndo_set_mac_address = cp_set_mac_address, .ndo_set_rx_mode = cp_set_rx_mode, .ndo_get_stats = cp_get_stats, - .ndo_do_ioctl = cp_ioctl, + .ndo_eth_ioctl = cp_ioctl, .ndo_start_xmit = cp_start_xmit, .ndo_tx_timeout = cp_tx_timeout, .ndo_set_features = cp_set_features, diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index f0608f050050..2e6923cc653e 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -932,7 +932,7 @@ static const struct net_device_ops rtl8139_netdev_ops = { .ndo_set_mac_address = rtl8139_set_mac_address, .ndo_start_xmit = rtl8139_start_xmit, .ndo_set_rx_mode = rtl8139_set_rx_mode, - .ndo_do_ioctl = netdev_ioctl, + .ndo_eth_ioctl = netdev_ioctl, .ndo_tx_timeout = rtl8139_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = rtl8139_poll_controller, diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index c7af5bc3b8af..fa2dab6980bb 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4979,7 +4979,7 @@ static const struct net_device_ops rtl_netdev_ops = { .ndo_fix_features = rtl8169_fix_features, .ndo_set_features = rtl8169_set_features, .ndo_set_mac_address = rtl_set_mac_address, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_rx_mode = rtl_set_rx_mode, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = rtl8169_netpoll, diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 805397088850..f4dfe9f71d06 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1872,7 +1872,7 @@ static const struct net_device_ops ravb_netdev_ops = { .ndo_get_stats = ravb_get_stats, .ndo_set_rx_mode = ravb_set_rx_mode, .ndo_tx_timeout = ravb_tx_timeout, - .ndo_do_ioctl = ravb_do_ioctl, + .ndo_eth_ioctl = ravb_do_ioctl, .ndo_change_mtu = ravb_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 840478692a37..6c8ba916d1a6 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3141,7 +3141,7 @@ static const struct net_device_ops sh_eth_netdev_ops = { .ndo_get_stats = sh_eth_get_stats, .ndo_set_rx_mode = sh_eth_set_rx_mode, .ndo_tx_timeout = sh_eth_tx_timeout, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_change_mtu = sh_eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, @@ -3157,7 +3157,7 @@ static const struct net_device_ops sh_eth_netdev_ops_tsu = { .ndo_vlan_rx_add_vid = sh_eth_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = sh_eth_vlan_rx_kill_vid, .ndo_tx_timeout = sh_eth_tx_timeout, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_change_mtu = sh_eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 090bcd2fb758..6781aa636d58 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -1964,7 +1964,7 @@ static const struct net_device_ops sxgbe_netdev_ops = { .ndo_set_features = sxgbe_set_features, .ndo_set_rx_mode = sxgbe_set_rx_mode, .ndo_tx_timeout = sxgbe_tx_timeout, - .ndo_do_ioctl = sxgbe_ioctl, + .ndo_eth_ioctl = sxgbe_ioctl, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = sxgbe_poll_controller, #endif diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 37fcf2eb0741..a295e2621cf3 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -591,7 +591,7 @@ static const struct net_device_ops efx_netdev_ops = { .ndo_tx_timeout = efx_watchdog, .ndo_start_xmit = efx_hard_start_xmit, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = efx_ioctl, + .ndo_eth_ioctl = efx_ioctl, .ndo_change_mtu = efx_change_mtu, .ndo_set_mac_address = efx_set_mac_address, .ndo_set_rx_mode = efx_set_rx_mode, diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index 9ec752a43c75..c177ea0f301e 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -2219,7 +2219,7 @@ static const struct net_device_ops ef4_netdev_ops = { .ndo_tx_timeout = ef4_watchdog, .ndo_start_xmit = ef4_hard_start_xmit, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = ef4_ioctl, + .ndo_eth_ioctl = ef4_ioctl, .ndo_change_mtu = ef4_change_mtu, .ndo_set_mac_address = ef4_set_mac_address, .ndo_set_rx_mode = ef4_set_rx_mode, diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 2b29fd4cbdf4..062f7844c496 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -820,7 +820,7 @@ static const struct net_device_ops ioc3_netdev_ops = { .ndo_tx_timeout = ioc3_timeout, .ndo_get_stats = ioc3_get_stats, .ndo_set_rx_mode = ioc3_set_multicast_list, - .ndo_do_ioctl = ioc3_ioctl, + .ndo_eth_ioctl = ioc3_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ioc3_set_mac_address, }; diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c index 0c396ecd3389..efce834d8ee6 100644 --- a/drivers/net/ethernet/sgi/meth.c +++ b/drivers/net/ethernet/sgi/meth.c @@ -812,7 +812,7 @@ static const struct net_device_ops meth_netdev_ops = { .ndo_open = meth_open, .ndo_stop = meth_release, .ndo_start_xmit = meth_tx, - .ndo_do_ioctl = meth_ioctl, + .ndo_eth_ioctl = meth_ioctl, .ndo_tx_timeout = meth_tx_timeout, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c index 676b193833c0..3d1a18a01ce5 100644 --- a/drivers/net/ethernet/sis/sis190.c +++ b/drivers/net/ethernet/sis/sis190.c @@ -1841,7 +1841,7 @@ static int sis190_mac_addr(struct net_device *dev, void *p) static const struct net_device_ops sis190_netdev_ops = { .ndo_open = sis190_open, .ndo_stop = sis190_close, - .ndo_do_ioctl = sis190_ioctl, + .ndo_eth_ioctl = sis190_ioctl, .ndo_start_xmit = sis190_start_xmit, .ndo_tx_timeout = sis190_tx_timeout, .ndo_set_rx_mode = sis190_set_rx_mode, diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index ca9c00b7f588..ec6f7f993eb7 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -404,7 +404,7 @@ static const struct net_device_ops sis900_netdev_ops = { .ndo_set_rx_mode = set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_do_ioctl = mii_ioctl, + .ndo_eth_ioctl = mii_ioctl, .ndo_tx_timeout = sis900_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = sis900_poll, diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 51cd7dca91cd..44daf79a8f97 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -312,7 +312,7 @@ static const struct net_device_ops epic_netdev_ops = { .ndo_tx_timeout = epic_tx_timeout, .ndo_get_stats = epic_get_stats, .ndo_set_rx_mode = set_rx_mode, - .ndo_do_ioctl = netdev_ioctl, + .ndo_eth_ioctl = netdev_ioctl, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c index f2a50eb3c1e0..42fc37c7887a 100644 --- a/drivers/net/ethernet/smsc/smc91c92_cs.c +++ b/drivers/net/ethernet/smsc/smc91c92_cs.c @@ -294,7 +294,7 @@ static const struct net_device_ops smc_netdev_ops = { .ndo_tx_timeout = smc_tx_timeout, .ndo_set_config = s9k_config, .ndo_set_rx_mode = set_rx_mode, - .ndo_do_ioctl = smc_ioctl, + .ndo_eth_ioctl = smc_ioctl, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index 556a9790cdcf..199a97339280 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -2148,7 +2148,7 @@ static const struct net_device_ops smsc911x_netdev_ops = { .ndo_start_xmit = smsc911x_hard_start_xmit, .ndo_get_stats = smsc911x_get_stats, .ndo_set_rx_mode = smsc911x_set_multicast_list, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = smsc911x_set_mac_address, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index c1dab009415d..fdbd2a43e267 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -1482,7 +1482,7 @@ static const struct net_device_ops smsc9420_netdev_ops = { .ndo_start_xmit = smsc9420_hard_start_xmit, .ndo_get_stats = smsc9420_get_stats, .ndo_set_rx_mode = smsc9420_set_multicast_list, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 20d148c019d8..d15f7b3a3f10 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1831,7 +1831,7 @@ static const struct net_device_ops netsec_netdev_ops = { .ndo_set_features = netsec_netdev_set_features, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_xdp_xmit = netsec_xdp_xmit, .ndo_bpf = netsec_xdp, }; diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 5eb6bb4f7b6c..ae31ed93aaf0 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1543,7 +1543,7 @@ static const struct net_device_ops ave_netdev_ops = { .ndo_open = ave_open, .ndo_stop = ave_stop, .ndo_start_xmit = ave_start_xmit, - .ndo_do_ioctl = ave_ioctl, + .ndo_eth_ioctl = ave_ioctl, .ndo_set_rx_mode = ave_set_rx_mode, .ndo_get_stats64 = ave_get_stats64, .ndo_set_mac_address = ave_set_mac_address, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7b8404a21544..a2aa75cb184e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -6451,7 +6451,7 @@ static const struct net_device_ops stmmac_netdev_ops = { .ndo_set_features = stmmac_set_features, .ndo_set_rx_mode = stmmac_set_rx_mode, .ndo_tx_timeout = stmmac_tx_timeout, - .ndo_do_ioctl = stmmac_ioctl, + .ndo_eth_ioctl = stmmac_ioctl, .ndo_setup_tc = stmmac_setup_tc, .ndo_select_queue = stmmac_select_queue, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 981685c88308..287ae4c538aa 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -4876,7 +4876,7 @@ static const struct net_device_ops cas_netdev_ops = { .ndo_start_xmit = cas_start_xmit, .ndo_get_stats = cas_get_stats, .ndo_set_rx_mode = cas_set_multicast, - .ndo_do_ioctl = cas_ioctl, + .ndo_eth_ioctl = cas_ioctl, .ndo_tx_timeout = cas_tx_timeout, .ndo_change_mtu = cas_change_mtu, .ndo_set_mac_address = eth_mac_addr, diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 74e748662ec0..006fd4237725 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9667,7 +9667,7 @@ static const struct net_device_ops niu_netdev_ops = { .ndo_set_rx_mode = niu_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = niu_set_mac_addr, - .ndo_do_ioctl = niu_ioctl, + .ndo_eth_ioctl = niu_ioctl, .ndo_tx_timeout = niu_tx_timeout, .ndo_change_mtu = niu_change_mtu, }; diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index cfb9e21b18b7..d72018a60c0f 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -2831,7 +2831,7 @@ static const struct net_device_ops gem_netdev_ops = { .ndo_start_xmit = gem_start_xmit, .ndo_get_stats = gem_get_stats, .ndo_set_rx_mode = gem_set_multicast, - .ndo_do_ioctl = gem_ioctl, + .ndo_eth_ioctl = gem_ioctl, .ndo_tx_timeout = gem_tx_timeout, .ndo_change_mtu = gem_change_mtu, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c index 26d178f8616b..1db7104fef3a 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c @@ -933,7 +933,7 @@ static const struct net_device_ops xlgmac_netdev_ops = { .ndo_change_mtu = xlgmac_change_mtu, .ndo_set_mac_address = xlgmac_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = xlgmac_ioctl, + .ndo_eth_ioctl = xlgmac_ioctl, .ndo_vlan_rx_add_vid = xlgmac_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = xlgmac_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 229e2f09d605..dffb6839f0fa 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1480,7 +1480,7 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_tx_timeout = am65_cpsw_nuss_ndo_host_tx_timeout, .ndo_vlan_rx_add_vid = am65_cpsw_nuss_ndo_slave_add_vid, .ndo_vlan_rx_kill_vid = am65_cpsw_nuss_ndo_slave_kill_vid, - .ndo_do_ioctl = am65_cpsw_nuss_ndo_slave_ioctl, + .ndo_eth_ioctl = am65_cpsw_nuss_ndo_slave_ioctl, .ndo_setup_tc = am65_cpsw_qos_ndo_setup_tc, .ndo_get_devlink_port = am65_cpsw_ndo_get_devlink_port, }; diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index c20715107075..02d4e51f7306 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -1044,7 +1044,7 @@ static const struct net_device_ops cpmac_netdev_ops = { .ndo_start_xmit = cpmac_start_xmit, .ndo_tx_timeout = cpmac_tx_timeout, .ndo_set_rx_mode = cpmac_set_multicast_list, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, }; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index cbbd0f665796..abf9a2a6f7eb 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1159,7 +1159,7 @@ static const struct net_device_ops cpsw_netdev_ops = { .ndo_stop = cpsw_ndo_stop, .ndo_start_xmit = cpsw_ndo_start_xmit, .ndo_set_mac_address = cpsw_ndo_set_mac_address, - .ndo_do_ioctl = cpsw_ndo_ioctl, + .ndo_eth_ioctl = cpsw_ndo_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = cpsw_ndo_tx_timeout, .ndo_set_rx_mode = cpsw_ndo_set_rx_mode, diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 4448a91cce54..b4f55ff4e84f 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1128,7 +1128,7 @@ static const struct net_device_ops cpsw_netdev_ops = { .ndo_stop = cpsw_ndo_stop, .ndo_start_xmit = cpsw_ndo_start_xmit, .ndo_set_mac_address = cpsw_ndo_set_mac_address, - .ndo_do_ioctl = cpsw_ndo_ioctl, + .ndo_eth_ioctl = cpsw_ndo_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = cpsw_ndo_tx_timeout, .ndo_set_rx_mode = cpsw_ndo_set_rx_mode, diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index c674e34b6839..637796670746 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1670,7 +1670,7 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_start_xmit = emac_dev_xmit, .ndo_set_rx_mode = emac_dev_mcast_set, .ndo_set_mac_address = emac_dev_setmac_addr, - .ndo_do_ioctl = emac_devioctl, + .ndo_eth_ioctl = emac_devioctl, .ndo_tx_timeout = emac_dev_tx_timeout, .ndo_get_stats = emac_dev_getnetstats, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 97942b0e3897..eda2961c0fe2 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1944,7 +1944,7 @@ static const struct net_device_ops netcp_netdev_ops = { .ndo_stop = netcp_ndo_stop, .ndo_start_xmit = netcp_ndo_start_xmit, .ndo_set_rx_mode = netcp_set_rx_mode, - .ndo_do_ioctl = netcp_ndo_ioctl, + .ndo_eth_ioctl = netcp_ndo_ioctl, .ndo_get_stats64 = netcp_get_stats, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index e0cb713193ea..77c448ad67ce 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -749,7 +749,7 @@ static const struct net_device_ops tlan_netdev_ops = { .ndo_tx_timeout = tlan_tx_timeout, .ndo_get_stats = tlan_get_stats, .ndo_set_rx_mode = tlan_set_multicast_list, - .ndo_do_ioctl = tlan_ioctl, + .ndo_eth_ioctl = tlan_ioctl, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c index 226a76633e65..087f0af56c50 100644 --- a/drivers/net/ethernet/toshiba/spider_net.c +++ b/drivers/net/ethernet/toshiba/spider_net.c @@ -2214,7 +2214,7 @@ static const struct net_device_ops spider_net_ops = { .ndo_start_xmit = spider_net_xmit, .ndo_set_rx_mode = spider_net_set_multi, .ndo_set_mac_address = spider_net_set_mac, - .ndo_do_ioctl = spider_net_do_ioctl, + .ndo_eth_ioctl = spider_net_do_ioctl, .ndo_tx_timeout = spider_net_tx_timeout, .ndo_validate_addr = eth_validate_addr, /* HW VLAN */ diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index fedb2bf69261..52245ac60fc7 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -750,7 +750,7 @@ static const struct net_device_ops tc35815_netdev_ops = { .ndo_get_stats = tc35815_get_stats, .ndo_set_rx_mode = tc35815_set_multicast_list, .ndo_tx_timeout = tc35815_tx_timeout, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index c62f474b6d08..cf0917b29e30 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -1538,7 +1538,7 @@ static const struct net_device_ops tsi108_netdev_ops = { .ndo_start_xmit = tsi108_send_packet, .ndo_set_rx_mode = tsi108_set_rx_mode, .ndo_get_stats = tsi108_get_stats, - .ndo_do_ioctl = tsi108_do_ioctl, + .ndo_eth_ioctl = tsi108_do_ioctl, .ndo_set_mac_address = tsi108_set_mac, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 73ca597ebd1b..961b623b7880 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -884,7 +884,7 @@ static const struct net_device_ops rhine_netdev_ops = { .ndo_set_rx_mode = rhine_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, - .ndo_do_ioctl = netdev_ioctl, + .ndo_eth_ioctl = netdev_ioctl, .ndo_tx_timeout = rhine_tx_timeout, .ndo_vlan_rx_add_vid = rhine_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = rhine_vlan_rx_kill_vid, diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index 88426b5e410b..278f49518d3f 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -2637,7 +2637,7 @@ static const struct net_device_ops velocity_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_set_rx_mode = velocity_set_multi, .ndo_change_mtu = velocity_change_mtu, - .ndo_do_ioctl = velocity_ioctl, + .ndo_eth_ioctl = velocity_ioctl, .ndo_vlan_rx_add_vid = velocity_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = velocity_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 60a4f79b8fa1..db1994fb51c5 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1237,7 +1237,7 @@ static const struct net_device_ops temac_netdev_ops = { .ndo_set_rx_mode = temac_set_multicast_list, .ndo_set_mac_address = temac_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = temac_poll_controller, #endif diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 13cd799541aa..348c0ba5edcf 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1227,7 +1227,7 @@ static const struct net_device_ops axienet_netdev_ops = { .ndo_change_mtu = axienet_change_mtu, .ndo_set_mac_address = netdev_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = axienet_ioctl, + .ndo_eth_ioctl = axienet_ioctl, .ndo_set_rx_mode = axienet_set_multicast_list, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = axienet_poll_controller, diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index b06377fe7293..b780aad3550a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -1263,7 +1263,7 @@ static const struct net_device_ops xemaclite_netdev_ops = { .ndo_start_xmit = xemaclite_send, .ndo_set_mac_address = xemaclite_set_mac_address, .ndo_tx_timeout = xemaclite_tx_timeout, - .ndo_do_ioctl = xemaclite_ioctl, + .ndo_eth_ioctl = xemaclite_ioctl, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = xemaclite_poll_controller, #endif diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index 4f6db6f5c272..ae611e46da6a 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -464,7 +464,7 @@ static const struct net_device_ops netdev_ops = { .ndo_start_xmit = do_start_xmit, .ndo_tx_timeout = xirc_tx_timeout, .ndo_set_config = do_config, - .ndo_do_ioctl = do_ioctl, + .ndo_eth_ioctl = do_ioctl, .ndo_set_rx_mode = set_multicast_list, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c index 7ae754eadf22..ff50305d6e13 100644 --- a/drivers/net/ethernet/xscale/ixp4xx_eth.c +++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c @@ -1357,7 +1357,7 @@ static const struct net_device_ops ixp4xx_netdev_ops = { .ndo_stop = eth_close, .ndo_start_xmit = eth_xmit, .ndo_set_rx_mode = eth_set_mcast_list, - .ndo_do_ioctl = eth_ioctl, + .ndo_eth_ioctl = eth_ioctl, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 80de9768ecd4..35f46ad040b0 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -829,7 +829,7 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu) return 0; } -static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int macvlan_eth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct net_device *real_dev = macvlan_dev_real_dev(dev); const struct net_device_ops *ops = real_dev->netdev_ops; @@ -845,8 +845,8 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; fallthrough; case SIOCGHWTSTAMP: - if (netif_device_present(real_dev) && ops->ndo_do_ioctl) - err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd); + if (netif_device_present(real_dev) && ops->ndo_eth_ioctl) + err = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd); break; } @@ -1151,7 +1151,7 @@ static const struct net_device_ops macvlan_netdev_ops = { .ndo_stop = macvlan_stop, .ndo_start_xmit = macvlan_start_xmit, .ndo_change_mtu = macvlan_change_mtu, - .ndo_do_ioctl = macvlan_do_ioctl, + .ndo_eth_ioctl = macvlan_eth_ioctl, .ndo_fix_features = macvlan_fix_features, .ndo_change_rx_flags = macvlan_change_rx_flags, .ndo_set_mac_address = macvlan_set_mac_address, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 8eeb26d8aeb7..f124a8a58bd4 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -426,7 +426,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd) EXPORT_SYMBOL(phy_mii_ioctl); /** - * phy_do_ioctl - generic ndo_do_ioctl implementation + * phy_do_ioctl - generic ndo_eth_ioctl implementation * @dev: the net_device struct * @ifr: &struct ifreq for socket ioctl's * @cmd: ioctl cmd to execute @@ -441,7 +441,7 @@ int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) EXPORT_SYMBOL(phy_do_ioctl); /** - * phy_do_ioctl_running - generic ndo_do_ioctl implementation but test first + * phy_do_ioctl_running - generic ndo_eth_ioctl implementation but test first * * @dev: the net_device struct * @ifr: &struct ifreq for socket ioctl's diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 9b914765c2de..cb01897c7a5d 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -197,7 +197,7 @@ static const struct net_device_ops ax88172_netdev_ops = { .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = asix_ioctl, + .ndo_eth_ioctl = asix_ioctl, .ndo_set_rx_mode = ax88172_set_multicast, }; @@ -589,7 +589,7 @@ static const struct net_device_ops ax88772_netdev_ops = { .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = asix_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_rx_mode = asix_set_multicast, }; @@ -1095,7 +1095,7 @@ static const struct net_device_ops ax88178_netdev_ops = { .ndo_set_mac_address = asix_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = asix_set_multicast, - .ndo_do_ioctl = asix_ioctl, + .ndo_eth_ioctl = asix_ioctl, .ndo_change_mtu = ax88178_change_mtu, }; diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 530947d7477b..d9777d9a7c5d 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -109,7 +109,7 @@ static const struct net_device_ops ax88172a_netdev_ops = { .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = asix_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_rx_mode = asix_set_multicast, }; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index c1316718304d..f25448a08870 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1035,7 +1035,7 @@ static const struct net_device_ops ax88179_netdev_ops = { .ndo_change_mtu = ax88179_change_mtu, .ndo_set_mac_address = ax88179_set_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = ax88179_ioctl, + .ndo_eth_ioctl = ax88179_ioctl, .ndo_set_rx_mode = ax88179_set_multicast, .ndo_set_features = ax88179_set_features, }; diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 89cc61d7a675..907f98b1eefe 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -345,7 +345,7 @@ static const struct net_device_ops dm9601_netdev_ops = { .ndo_change_mtu = usbnet_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = dm9601_ioctl, + .ndo_eth_ioctl = dm9601_ioctl, .ndo_set_rx_mode = dm9601_set_multicast, .ndo_set_mac_address = dm9601_set_mac_address, }; diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 25489389ea49..13f86368b78a 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3601,7 +3601,7 @@ static const struct net_device_ops lan78xx_netdev_ops = { .ndo_change_mtu = lan78xx_change_mtu, .ndo_set_mac_address = lan78xx_set_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = phy_do_ioctl_running, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_rx_mode = lan78xx_set_multicast, .ndo_set_features = lan78xx_set_features, .ndo_vlan_rx_add_vid = lan78xx_vlan_rx_add_vid, diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index 2469bdcb1a04..66866bef25df 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -464,7 +464,7 @@ static const struct net_device_ops mcs7830_netdev_ops = { .ndo_change_mtu = usbnet_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = mcs7830_ioctl, + .ndo_eth_ioctl = mcs7830_ioctl, .ndo_set_rx_mode = mcs7830_set_multicast, .ndo_set_mac_address = mcs7830_set_mac_address, }; diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index e09b107b5c99..d7fbc81b518a 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9173,7 +9173,7 @@ static int rtl8152_change_mtu(struct net_device *dev, int new_mtu) static const struct net_device_ops rtl8152_netdev_ops = { .ndo_open = rtl8152_open, .ndo_stop = rtl8152_close, - .ndo_do_ioctl = rtl8152_ioctl, + .ndo_eth_ioctl = rtl8152_ioctl, .ndo_start_xmit = rtl8152_start_xmit, .ndo_tx_timeout = rtl8152_tx_timeout, .ndo_set_features = rtl8152_set_features, diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 13141dbfa3a8..76f7af161313 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -1439,7 +1439,7 @@ static const struct net_device_ops smsc75xx_netdev_ops = { .ndo_change_mtu = smsc75xx_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = smsc75xx_ioctl, + .ndo_eth_ioctl = smsc75xx_ioctl, .ndo_set_rx_mode = smsc75xx_set_multicast, .ndo_set_features = smsc75xx_set_features, }; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 4c8ee1cff4d4..7d953974eb9b 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1044,7 +1044,7 @@ static const struct net_device_ops smsc95xx_netdev_ops = { .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = smsc95xx_ioctl, + .ndo_eth_ioctl = smsc95xx_ioctl, .ndo_set_rx_mode = smsc95xx_set_multicast, .ndo_set_features = smsc95xx_set_features, }; diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index ce29261263cd..6516a37893e2 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -310,7 +310,7 @@ static const struct net_device_ops sr9700_netdev_ops = { .ndo_change_mtu = usbnet_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = sr9700_ioctl, + .ndo_eth_ioctl = sr9700_ioctl, .ndo_set_rx_mode = sr9700_set_multicast, .ndo_set_mac_address = sr9700_set_mac_address, }; diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index a822d81310d5..576401c8b1be 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -684,7 +684,7 @@ static const struct net_device_ops sr9800_netdev_ops = { .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = sr_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = sr_ioctl, + .ndo_eth_ioctl = sr_ioctl, .ndo_set_rx_mode = sr_set_multicast, }; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index d50d3cba238e..69afc0311dd1 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -836,7 +836,7 @@ static const struct net_device_ops qeth_l2_netdev_ops = { .ndo_select_queue = qeth_l2_select_queue, .ndo_validate_addr = qeth_l2_validate_addr, .ndo_set_rx_mode = qeth_l2_set_rx_mode, - .ndo_do_ioctl = qeth_do_ioctl, + .ndo_eth_ioctl = qeth_do_ioctl, .ndo_siocdevprivate = qeth_siocdevprivate, .ndo_set_mac_address = qeth_l2_set_mac_address, .ndo_vlan_rx_add_vid = qeth_l2_vlan_rx_add_vid, diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index d7a895372f19..3a523e700a5a 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1841,7 +1841,7 @@ static const struct net_device_ops qeth_l3_netdev_ops = { .ndo_select_queue = qeth_l3_iqd_select_queue, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l3_set_rx_mode, - .ndo_do_ioctl = qeth_do_ioctl, + .ndo_eth_ioctl = qeth_do_ioctl, .ndo_siocdevprivate = qeth_siocdevprivate, .ndo_fix_features = qeth_fix_features, .ndo_set_features = qeth_set_features, @@ -1857,7 +1857,7 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = { .ndo_select_queue = qeth_l3_osa_select_queue, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l3_set_rx_mode, - .ndo_do_ioctl = qeth_do_ioctl, + .ndo_eth_ioctl = qeth_do_ioctl, .ndo_siocdevprivate = qeth_siocdevprivate, .ndo_fix_features = qeth_fix_features, .ndo_set_features = qeth_set_features, diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c index dcbba9621b21..5d24c1b6663b 100644 --- a/drivers/staging/octeon/ethernet.c +++ b/drivers/staging/octeon/ethernet.c @@ -524,7 +524,7 @@ static const struct net_device_ops cvm_oct_npi_netdev_ops = { .ndo_start_xmit = cvm_oct_xmit, .ndo_set_rx_mode = cvm_oct_common_set_multicast_list, .ndo_set_mac_address = cvm_oct_common_set_mac_address, - .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_eth_ioctl = cvm_oct_ioctl, .ndo_change_mtu = cvm_oct_common_change_mtu, .ndo_get_stats = cvm_oct_common_get_stats, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -540,7 +540,7 @@ static const struct net_device_ops cvm_oct_xaui_netdev_ops = { .ndo_start_xmit = cvm_oct_xmit, .ndo_set_rx_mode = cvm_oct_common_set_multicast_list, .ndo_set_mac_address = cvm_oct_common_set_mac_address, - .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_eth_ioctl = cvm_oct_ioctl, .ndo_change_mtu = cvm_oct_common_change_mtu, .ndo_get_stats = cvm_oct_common_get_stats, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -556,7 +556,7 @@ static const struct net_device_ops cvm_oct_sgmii_netdev_ops = { .ndo_start_xmit = cvm_oct_xmit, .ndo_set_rx_mode = cvm_oct_common_set_multicast_list, .ndo_set_mac_address = cvm_oct_common_set_mac_address, - .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_eth_ioctl = cvm_oct_ioctl, .ndo_change_mtu = cvm_oct_common_change_mtu, .ndo_get_stats = cvm_oct_common_get_stats, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -570,7 +570,7 @@ static const struct net_device_ops cvm_oct_spi_netdev_ops = { .ndo_start_xmit = cvm_oct_xmit, .ndo_set_rx_mode = cvm_oct_common_set_multicast_list, .ndo_set_mac_address = cvm_oct_common_set_mac_address, - .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_eth_ioctl = cvm_oct_ioctl, .ndo_change_mtu = cvm_oct_common_change_mtu, .ndo_get_stats = cvm_oct_common_get_stats, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -586,7 +586,7 @@ static const struct net_device_ops cvm_oct_rgmii_netdev_ops = { .ndo_start_xmit = cvm_oct_xmit, .ndo_set_rx_mode = cvm_oct_common_set_multicast_list, .ndo_set_mac_address = cvm_oct_common_set_mac_address, - .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_eth_ioctl = cvm_oct_ioctl, .ndo_change_mtu = cvm_oct_common_change_mtu, .ndo_get_stats = cvm_oct_common_get_stats, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -599,7 +599,7 @@ static const struct net_device_ops cvm_oct_pow_netdev_ops = { .ndo_start_xmit = cvm_oct_xmit_pow, .ndo_set_rx_mode = cvm_oct_common_set_multicast_list, .ndo_set_mac_address = cvm_oct_common_set_mac_address, - .ndo_do_ioctl = cvm_oct_ioctl, + .ndo_eth_ioctl = cvm_oct_ioctl, .ndo_change_mtu = cvm_oct_common_change_mtu, .ndo_get_stats = cvm_oct_common_get_stats, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 658d8cf57342..b6e062a3b0d4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1090,6 +1090,10 @@ struct netdev_net_notifier { * the generic interface code. If not defined ioctls return * not supported error code. * + * * int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); + * Called for ethernet specific ioctls: SIOCGMIIPHY, SIOCGMIIREG, + * SIOCSMIIREG, SIOCSHWTSTAMP and SIOCGHWTSTAMP. + * * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); * Used to set network devices bus interface parameters. This interface * is retained for legacy reasons; new devices should use the bus @@ -1361,6 +1365,8 @@ struct net_device_ops { int (*ndo_validate_addr)(struct net_device *dev); int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); + int (*ndo_eth_ioctl)(struct net_device *dev, + struct ifreq *ifr, int cmd); int (*ndo_siocdevprivate)(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd); diff --git a/include/net/dsa.h b/include/net/dsa.h index 55fcac854058..2af6ee2f2bfb 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -106,8 +106,8 @@ struct dsa_device_ops { * function pointers. */ struct dsa_netdevice_ops { - int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, - int cmd); + int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, + int cmd); }; #define DSA_TAG_DRIVER_ALIAS "dsa_tag-" @@ -1019,8 +1019,8 @@ static inline int __dsa_netdevice_ops_check(struct net_device *dev) return 0; } -static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr, - int cmd) +static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, + int cmd) { const struct dsa_netdevice_ops *ops; int err; @@ -1031,11 +1031,11 @@ static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr, ops = dev->dsa_ptr->netdev_ops; - return ops->ndo_do_ioctl(dev, ifr, cmd); + return ops->ndo_eth_ioctl(dev, ifr, cmd); } #else -static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr, - int cmd) +static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, + int cmd) { return -EOPNOTSUPP; } diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index a0367b37512d..0c21d1fec852 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -372,8 +372,8 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGMIIREG: case SIOCSMIIREG: case SIOCGHWTSTAMP: - if (netif_device_present(real_dev) && ops->ndo_do_ioctl) - err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd); + if (netif_device_present(real_dev) && ops->ndo_eth_ioctl) + err = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd); break; } @@ -814,7 +814,7 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_set_mac_address = vlan_dev_set_mac_address, .ndo_set_rx_mode = vlan_dev_set_rx_mode, .ndo_change_rx_flags = vlan_dev_change_rx_flags, - .ndo_do_ioctl = vlan_dev_ioctl, + .ndo_eth_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, .ndo_get_stats64 = vlan_dev_get_stats64, #if IS_ENABLED(CONFIG_FCOE) diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 3ace1e4f6b80..8e30fe8b5645 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -239,19 +239,19 @@ static int net_hwtstamp_validate(struct ifreq *ifr) return 0; } -static int dev_do_ioctl(struct net_device *dev, - struct ifreq *ifr, unsigned int cmd) +static int dev_eth_ioctl(struct net_device *dev, + struct ifreq *ifr, unsigned int cmd) { const struct net_device_ops *ops = dev->netdev_ops; int err; - err = dsa_ndo_do_ioctl(dev, ifr, cmd); + err = dsa_ndo_eth_ioctl(dev, ifr, cmd); if (err == 0 || err != -EOPNOTSUPP) return err; - if (ops->ndo_do_ioctl) { + if (ops->ndo_eth_ioctl) { if (netif_device_present(dev)) - err = ops->ndo_do_ioctl(dev, ifr, cmd); + err = ops->ndo_eth_ioctl(dev, ifr, cmd); else err = -ENODEV; } @@ -259,6 +259,21 @@ static int dev_do_ioctl(struct net_device *dev, return err; } +static int dev_do_ioctl(struct net_device *dev, + struct ifreq *ifr, unsigned int cmd) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_do_ioctl) { + if (netif_device_present(dev)) + return ops->ndo_do_ioctl(dev, ifr, cmd); + else + return -ENODEV; + } + + return -EOPNOTSUPP; +} + static int dev_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, unsigned int cmd) { @@ -358,19 +373,20 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, cmd <= SIOCDEVPRIVATE + 15) return dev_siocdevprivate(dev, ifr, data, cmd); - if (cmd == SIOCBONDENSLAVE || + if (cmd == SIOCGMIIPHY || + cmd == SIOCGMIIREG || + cmd == SIOCSMIIREG || + cmd == SIOCSHWTSTAMP || + cmd == SIOCGHWTSTAMP) { + err = dev_eth_ioctl(dev, ifr, cmd); + } else if (cmd == SIOCBONDENSLAVE || cmd == SIOCBONDRELEASE || cmd == SIOCBONDSETHWADDR || cmd == SIOCBONDSLAVEINFOQUERY || cmd == SIOCBONDINFOQUERY || cmd == SIOCBONDCHANGEACTIVE || - cmd == SIOCGMIIPHY || - cmd == SIOCGMIIREG || - cmd == SIOCSMIIREG || cmd == SIOCBRADDIF || cmd == SIOCBRDELIF || - cmd == SIOCSHWTSTAMP || - cmd == SIOCGHWTSTAMP || cmd == SIOCWANDEV) { err = dev_do_ioctl(dev, ifr, cmd); } else diff --git a/net/dsa/master.c b/net/dsa/master.c index 3fc90e36772d..e8e19857621b 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -210,14 +210,14 @@ static int dsa_master_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; } - if (dev->netdev_ops->ndo_do_ioctl) - err = dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd); + if (dev->netdev_ops->ndo_eth_ioctl) + err = dev->netdev_ops->ndo_eth_ioctl(dev, ifr, cmd); return err; } static const struct dsa_netdevice_ops dsa_netdev_ops = { - .ndo_do_ioctl = dsa_master_ioctl, + .ndo_eth_ioctl = dsa_master_ioctl, }; static int dsa_master_ethtool_setup(struct net_device *dev) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 8c112d7d5b0a..6e1135d3ee33 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1687,7 +1687,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_set_rx_mode = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, .ndo_fdb_dump = dsa_slave_fdb_dump, - .ndo_do_ioctl = dsa_slave_ioctl, + .ndo_eth_ioctl = dsa_slave_ioctl, .ndo_get_iflink = dsa_slave_get_iflink, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = dsa_slave_netpoll_setup, -- cgit v1.2.3 From ad7eab2ab014748b062507b7ac69f8e856057717 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Jul 2021 15:45:14 +0200 Subject: net: split out ndo_siowandev ioctl In order to further reduce the scope of ndo_do_ioctl(), move out the SIOCWANDEV handling into a new network device operation function. Adjust the prototype to only pass the if_settings sub-structure in place of the ifreq, and remove the redundant 'cmd' argument in the process. Cc: Krzysztof Halasa Cc: "Jan \"Yenya\" Kasprzak" Cc: Kevin Curtis Cc: Zhao Qiang Cc: Martin Schiller Cc: Jiri Slaby Cc: linux-x25@vger.kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- Documentation/networking/netdevices.rst | 7 +++ drivers/char/pcmcia/synclink_cs.c | 23 ++++----- drivers/net/wan/c101.c | 19 +++---- drivers/net/wan/cosa.c | 2 +- drivers/net/wan/farsync.c | 92 +++++++++++++++------------------ drivers/net/wan/fsl_ucc_hdlc.c | 19 +++---- drivers/net/wan/hdlc.c | 9 ++-- drivers/net/wan/hdlc_cisco.c | 14 ++--- drivers/net/wan/hdlc_fr.c | 43 +++++++-------- drivers/net/wan/hdlc_ppp.c | 8 +-- drivers/net/wan/hdlc_raw.c | 14 ++--- drivers/net/wan/hdlc_raw_eth.c | 14 ++--- drivers/net/wan/hdlc_x25.c | 16 +++--- drivers/net/wan/hostess_sv11.c | 7 +-- drivers/net/wan/ixp4xx_hss.c | 19 +++---- drivers/net/wan/lmc/lmc.h | 2 +- drivers/net/wan/lmc/lmc_main.c | 10 +--- drivers/net/wan/lmc/lmc_proto.c | 7 --- drivers/net/wan/lmc/lmc_proto.h | 1 - drivers/net/wan/n2.c | 19 +++---- drivers/net/wan/pc300too.c | 29 +++++------ drivers/net/wan/pci200syn.c | 19 +++---- drivers/net/wan/sealevel.c | 10 +--- drivers/net/wan/wanxl.c | 21 ++++---- drivers/tty/synclink_gt.c | 19 +++---- include/linux/hdlc.h | 4 +- include/linux/netdevice.h | 2 + net/core/dev_ioctl.c | 20 ++++++- 28 files changed, 211 insertions(+), 258 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst index f57f255f2397..3c42b0b0be93 100644 --- a/Documentation/networking/netdevices.rst +++ b/Documentation/networking/netdevices.rst @@ -222,6 +222,13 @@ ndo_do_ioctl: Synchronization: rtnl_lock() semaphore. Context: process +ndo_siocwandev: + Synchronization: rtnl_lock() semaphore. + Context: process + + Used by the drivers/net/wan framework to handle + the SIOCWANDEV ioctl with the if_settings structure. + ndo_siocdevprivate: Synchronization: rtnl_lock() semaphore. Context: process diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c index 6eaefea0520e..5ac53dcb3a6a 100644 --- a/drivers/char/pcmcia/synclink_cs.c +++ b/drivers/char/pcmcia/synclink_cs.c @@ -4050,16 +4050,15 @@ static int hdlcdev_close(struct net_device *dev) * called by network layer to process IOCTL call to network device * * dev pointer to network device structure - * ifr pointer to network interface request structure - * cmd IOCTL command code + * ifs pointer to network interface settings structure * * returns 0 if success, otherwise error code */ -static int hdlcdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int hdlcdev_wan_ioctl(struct net_device *dev, struct if_settings *ifs) { const size_t size = sizeof(sync_serial_settings); sync_serial_settings new_line; - sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync; + sync_serial_settings __user *line = ifs->ifs_ifsu.sync; MGSLPC_INFO *info = dev_to_port(dev); unsigned int flags; @@ -4070,17 +4069,14 @@ static int hdlcdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (info->port.count) return -EBUSY; - if (cmd != SIOCWANDEV) - return hdlc_ioctl(dev, ifr, cmd); - memset(&new_line, 0, size); - switch(ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_IFACE: /* return current sync_serial_settings */ - ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_IFACE_SYNC_SERIAL; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } @@ -4148,9 +4144,8 @@ static int hdlcdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) tty_kref_put(tty); } return 0; - default: - return hdlc_ioctl(dev, ifr, cmd); + return hdlc_ioctl(dev, ifs); } } @@ -4225,7 +4220,7 @@ static const struct net_device_ops hdlcdev_ops = { .ndo_open = hdlcdev_open, .ndo_stop = hdlcdev_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = hdlcdev_ioctl, + .ndo_siocwandev = hdlcdev_wan_ioctl, .ndo_tx_timeout = hdlcdev_tx_timeout, }; diff --git a/drivers/net/wan/c101.c b/drivers/net/wan/c101.c index ca308230500d..8dd14d916c3a 100644 --- a/drivers/net/wan/c101.c +++ b/drivers/net/wan/c101.c @@ -228,21 +228,18 @@ static int c101_siocdevprivate(struct net_device *dev, struct ifreq *ifr, return -EOPNOTSUPP; } -static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int c101_ioctl(struct net_device *dev, struct if_settings *ifs) { const size_t size = sizeof(sync_serial_settings); sync_serial_settings new_line; - sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync; + sync_serial_settings __user *line = ifs->ifs_ifsu.sync; port_t *port = dev_to_port(dev); - if (cmd != SIOCWANDEV) - return hdlc_ioctl(dev, ifr, cmd); - - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_IFACE: - ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_IFACE_SYNC_SERIAL; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } if (copy_to_user(line, &port->settings, size)) @@ -270,7 +267,7 @@ static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; default: - return hdlc_ioctl(dev, ifr, cmd); + return hdlc_ioctl(dev, ifs); } } @@ -295,7 +292,7 @@ static const struct net_device_ops c101_ops = { .ndo_open = c101_open, .ndo_stop = c101_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = c101_ioctl, + .ndo_siocwandev = c101_ioctl, .ndo_siocdevprivate = c101_siocdevprivate, }; diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index 4c0e9cf02217..23d2954d9747 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -414,7 +414,7 @@ static const struct net_device_ops cosa_ops = { .ndo_open = cosa_net_open, .ndo_stop = cosa_net_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = hdlc_ioctl, + .ndo_siocwandev = hdlc_ioctl, .ndo_tx_timeout = cosa_net_timeout, }; diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index d0e3cab98645..6a212c085435 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -1784,16 +1784,15 @@ gather_conf_info(struct fst_card_info *card, struct fst_port_info *port, static int fst_set_iface(struct fst_card_info *card, struct fst_port_info *port, - struct ifreq *ifr) + struct if_settings *ifs) { sync_serial_settings sync; int i; - if (ifr->ifr_settings.size != sizeof(sync)) + if (ifs->size != sizeof(sync)) return -ENOMEM; - if (copy_from_user - (&sync, ifr->ifr_settings.ifs_ifsu.sync, sizeof(sync))) + if (copy_from_user(&sync, ifs->ifs_ifsu.sync, sizeof(sync))) return -EFAULT; if (sync.loopback) @@ -1801,7 +1800,7 @@ fst_set_iface(struct fst_card_info *card, struct fst_port_info *port, i = port->index; - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_IFACE_V35: FST_WRW(card, portConfig[i].lineInterface, V35); port->hwif = V35; @@ -1857,7 +1856,7 @@ fst_set_iface(struct fst_card_info *card, struct fst_port_info *port, static int fst_get_iface(struct fst_card_info *card, struct fst_port_info *port, - struct ifreq *ifr) + struct if_settings *ifs) { sync_serial_settings sync; int i; @@ -1868,29 +1867,29 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port, */ switch (port->hwif) { case E1: - ifr->ifr_settings.type = IF_IFACE_E1; + ifs->type = IF_IFACE_E1; break; case T1: - ifr->ifr_settings.type = IF_IFACE_T1; + ifs->type = IF_IFACE_T1; break; case V35: - ifr->ifr_settings.type = IF_IFACE_V35; + ifs->type = IF_IFACE_V35; break; case V24: - ifr->ifr_settings.type = IF_IFACE_V24; + ifs->type = IF_IFACE_V24; break; case X21D: - ifr->ifr_settings.type = IF_IFACE_X21D; + ifs->type = IF_IFACE_X21D; break; case X21: default: - ifr->ifr_settings.type = IF_IFACE_X21; + ifs->type = IF_IFACE_X21; break; } - if (ifr->ifr_settings.size == 0) + if (!ifs->size) return 0; /* only type requested */ - if (ifr->ifr_settings.size < sizeof(sync)) + if (ifs->size < sizeof(sync)) return -ENOMEM; i = port->index; @@ -1901,10 +1900,10 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port, INTCLK ? CLOCK_INT : CLOCK_EXT; sync.loopback = 0; - if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &sync, sizeof(sync))) + if (copy_to_user(ifs->ifs_ifsu.sync, &sync, sizeof(sync))) return -EFAULT; - ifr->ifr_settings.size = sizeof(sync); + ifs->size = sizeof(sync); return 0; } @@ -2020,12 +2019,12 @@ fst_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, } static int -fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +fst_ioctl(struct net_device *dev, struct if_settings *ifs) { struct fst_card_info *card; struct fst_port_info *port; - dbg(DBG_IOCTL, "ioctl: %x, %x\n", cmd, ifr->ifr_settings.type); + dbg(DBG_IOCTL, "SIOCDEVPRIVATE, %x\n", ifs->type); port = dev_to_port(dev); card = port->card; @@ -2033,42 +2032,35 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (!capable(CAP_NET_ADMIN)) return -EPERM; - switch (cmd) { - case SIOCWANDEV: - switch (ifr->ifr_settings.type) { - case IF_GET_IFACE: - return fst_get_iface(card, port, ifr); - - case IF_IFACE_SYNC_SERIAL: - case IF_IFACE_V35: - case IF_IFACE_V24: - case IF_IFACE_X21: - case IF_IFACE_X21D: - case IF_IFACE_T1: - case IF_IFACE_E1: - return fst_set_iface(card, port, ifr); - - case IF_PROTO_RAW: - port->mode = FST_RAW; - return 0; + switch (ifs->type) { + case IF_GET_IFACE: + return fst_get_iface(card, port, ifs); - case IF_GET_PROTO: - if (port->mode == FST_RAW) { - ifr->ifr_settings.type = IF_PROTO_RAW; - return 0; - } - return hdlc_ioctl(dev, ifr, cmd); + case IF_IFACE_SYNC_SERIAL: + case IF_IFACE_V35: + case IF_IFACE_V24: + case IF_IFACE_X21: + case IF_IFACE_X21D: + case IF_IFACE_T1: + case IF_IFACE_E1: + return fst_set_iface(card, port, ifs); - default: - port->mode = FST_GEN_HDLC; - dbg(DBG_IOCTL, "Passing this type to hdlc %x\n", - ifr->ifr_settings.type); - return hdlc_ioctl(dev, ifr, cmd); + case IF_PROTO_RAW: + port->mode = FST_RAW; + return 0; + + case IF_GET_PROTO: + if (port->mode == FST_RAW) { + ifs->type = IF_PROTO_RAW; + return 0; } + return hdlc_ioctl(dev, ifs); default: - /* Not one of ours. Pass through to HDLC package */ - return hdlc_ioctl(dev, ifr, cmd); + port->mode = FST_GEN_HDLC; + dbg(DBG_IOCTL, "Passing this type to hdlc %x\n", + ifs->type); + return hdlc_ioctl(dev, ifs); } } @@ -2328,7 +2320,7 @@ static const struct net_device_ops fst_ops = { .ndo_open = fst_open, .ndo_stop = fst_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = fst_ioctl, + .ndo_siocwandev = fst_ioctl, .ndo_siocdevprivate = fst_siocdevprivate, .ndo_tx_timeout = fst_tx_timeout, }; diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 39f05fabbfa4..cda1b4ce6b21 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -674,31 +674,28 @@ static irqreturn_t ucc_hdlc_irq_handler(int irq, void *dev_id) return IRQ_HANDLED; } -static int uhdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int uhdlc_ioctl(struct net_device *dev, struct if_settings *ifs) { const size_t size = sizeof(te1_settings); te1_settings line; struct ucc_hdlc_private *priv = netdev_priv(dev); - if (cmd != SIOCWANDEV) - return hdlc_ioctl(dev, ifr, cmd); - - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_IFACE: - ifr->ifr_settings.type = IF_IFACE_E1; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_IFACE_E1; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } memset(&line, 0, sizeof(line)); line.clock_type = priv->clocking; - if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &line, size)) + if (copy_to_user(ifs->ifs_ifsu.sync, &line, size)) return -EFAULT; return 0; default: - return hdlc_ioctl(dev, ifr, cmd); + return hdlc_ioctl(dev, ifs); } } @@ -1053,7 +1050,7 @@ static const struct net_device_ops uhdlc_ops = { .ndo_open = uhdlc_open, .ndo_stop = uhdlc_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = uhdlc_ioctl, + .ndo_siocwandev = uhdlc_ioctl, .ndo_tx_timeout = uhdlc_tx_timeout, }; diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index dd6312b69861..cbed10b1d862 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -196,16 +196,13 @@ void hdlc_close(struct net_device *dev) } EXPORT_SYMBOL(hdlc_close); -int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +int hdlc_ioctl(struct net_device *dev, struct if_settings *ifs) { struct hdlc_proto *proto = first_proto; int result; - if (cmd != SIOCWANDEV) - return -EINVAL; - if (dev_to_hdlc(dev)->proto) { - result = dev_to_hdlc(dev)->proto->ioctl(dev, ifr); + result = dev_to_hdlc(dev)->proto->ioctl(dev, ifs); if (result != -EINVAL) return result; } @@ -213,7 +210,7 @@ int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /* Not handled by currently attached protocol (if any) */ while (proto) { - result = proto->ioctl(dev, ifr); + result = proto->ioctl(dev, ifs); if (result != -EINVAL) return result; proto = proto->next; diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index c54fdae950fb..cdebe65a7e2d 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -56,7 +56,7 @@ struct cisco_state { u32 rxseq; /* RX sequence number */ }; -static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr); +static int cisco_ioctl(struct net_device *dev, struct if_settings *ifs); static inline struct cisco_state *state(hdlc_device *hdlc) { @@ -306,21 +306,21 @@ static const struct header_ops cisco_header_ops = { .create = cisco_hard_header, }; -static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr) +static int cisco_ioctl(struct net_device *dev, struct if_settings *ifs) { - cisco_proto __user *cisco_s = ifr->ifr_settings.ifs_ifsu.cisco; + cisco_proto __user *cisco_s = ifs->ifs_ifsu.cisco; const size_t size = sizeof(cisco_proto); cisco_proto new_settings; hdlc_device *hdlc = dev_to_hdlc(dev); int result; - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_PROTO: if (dev_to_hdlc(dev)->proto != &proto) return -EINVAL; - ifr->ifr_settings.type = IF_PROTO_CISCO; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_PROTO_CISCO; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } if (copy_to_user(cisco_s, &state(hdlc)->settings, size)) diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 2910ea25e51d..7637edce443e 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -146,7 +146,7 @@ struct frad_state { u8 rxseq; /* RX sequence number */ }; -static int fr_ioctl(struct net_device *dev, struct ifreq *ifr); +static int fr_ioctl(struct net_device *dev, struct if_settings *ifs); static inline u16 q922_to_dlci(u8 *hdr) { @@ -357,29 +357,26 @@ static int pvc_close(struct net_device *dev) return 0; } -static int pvc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int pvc_ioctl(struct net_device *dev, struct if_settings *ifs) { struct pvc_device *pvc = dev->ml_priv; fr_proto_pvc_info info; - if (cmd != SIOCWANDEV) - return -EOPNOTSUPP; - - if (ifr->ifr_settings.type == IF_GET_PROTO) { + if (ifs->type == IF_GET_PROTO) { if (dev->type == ARPHRD_ETHER) - ifr->ifr_settings.type = IF_PROTO_FR_ETH_PVC; + ifs->type = IF_PROTO_FR_ETH_PVC; else - ifr->ifr_settings.type = IF_PROTO_FR_PVC; + ifs->type = IF_PROTO_FR_PVC; - if (ifr->ifr_settings.size < sizeof(info)) { + if (ifs->size < sizeof(info)) { /* data size wanted */ - ifr->ifr_settings.size = sizeof(info); + ifs->size = sizeof(info); return -ENOBUFS; } info.dlci = pvc->dlci; memcpy(info.master, pvc->frad->name, IFNAMSIZ); - if (copy_to_user(ifr->ifr_settings.ifs_ifsu.fr_pvc_info, + if (copy_to_user(ifs->ifs_ifsu.fr_pvc_info, &info, sizeof(info))) return -EFAULT; return 0; @@ -1059,7 +1056,7 @@ static const struct net_device_ops pvc_ops = { .ndo_open = pvc_open, .ndo_stop = pvc_close, .ndo_start_xmit = pvc_xmit, - .ndo_do_ioctl = pvc_ioctl, + .ndo_siocwandev = pvc_ioctl, }; static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type) @@ -1182,22 +1179,22 @@ static struct hdlc_proto proto = { .module = THIS_MODULE, }; -static int fr_ioctl(struct net_device *dev, struct ifreq *ifr) +static int fr_ioctl(struct net_device *dev, struct if_settings *ifs) { - fr_proto __user *fr_s = ifr->ifr_settings.ifs_ifsu.fr; + fr_proto __user *fr_s = ifs->ifs_ifsu.fr; const size_t size = sizeof(fr_proto); fr_proto new_settings; hdlc_device *hdlc = dev_to_hdlc(dev); fr_proto_pvc pvc; int result; - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_PROTO: if (dev_to_hdlc(dev)->proto != &proto) /* Different proto */ return -EINVAL; - ifr->ifr_settings.type = IF_PROTO_FR; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_PROTO_FR; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } if (copy_to_user(fr_s, &state(hdlc)->settings, size)) @@ -1259,21 +1256,21 @@ static int fr_ioctl(struct net_device *dev, struct ifreq *ifr) if (!capable(CAP_NET_ADMIN)) return -EPERM; - if (copy_from_user(&pvc, ifr->ifr_settings.ifs_ifsu.fr_pvc, + if (copy_from_user(&pvc, ifs->ifs_ifsu.fr_pvc, sizeof(fr_proto_pvc))) return -EFAULT; if (pvc.dlci <= 0 || pvc.dlci >= 1024) return -EINVAL; /* Only 10 bits, DLCI 0 reserved */ - if (ifr->ifr_settings.type == IF_PROTO_FR_ADD_ETH_PVC || - ifr->ifr_settings.type == IF_PROTO_FR_DEL_ETH_PVC) + if (ifs->type == IF_PROTO_FR_ADD_ETH_PVC || + ifs->type == IF_PROTO_FR_DEL_ETH_PVC) result = ARPHRD_ETHER; /* bridged Ethernet device */ else result = ARPHRD_DLCI; - if (ifr->ifr_settings.type == IF_PROTO_FR_ADD_PVC || - ifr->ifr_settings.type == IF_PROTO_FR_ADD_ETH_PVC) + if (ifs->type == IF_PROTO_FR_ADD_PVC || + ifs->type == IF_PROTO_FR_ADD_ETH_PVC) return fr_add_pvc(dev, pvc.dlci, result); else return fr_del_pvc(hdlc, pvc.dlci, result); diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index b81ecf432a0c..37a3c989cba1 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -100,7 +100,7 @@ static const char *const event_names[EVENTS] = { static struct sk_buff_head tx_queue; /* used when holding the spin lock */ -static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr); +static int ppp_ioctl(struct net_device *dev, struct if_settings *ifs); static inline struct ppp *get_ppp(struct net_device *dev) { @@ -655,17 +655,17 @@ static const struct header_ops ppp_header_ops = { .create = ppp_hard_header, }; -static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr) +static int ppp_ioctl(struct net_device *dev, struct if_settings *ifs) { hdlc_device *hdlc = dev_to_hdlc(dev); struct ppp *ppp; int result; - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_PROTO: if (dev_to_hdlc(dev)->proto != &proto) return -EINVAL; - ifr->ifr_settings.type = IF_PROTO_PPP; + ifs->type = IF_PROTO_PPP; return 0; /* return protocol only, no settable parameters */ case IF_PROTO_PPP: diff --git a/drivers/net/wan/hdlc_raw.c b/drivers/net/wan/hdlc_raw.c index 54d28496fefd..4a2f068721bc 100644 --- a/drivers/net/wan/hdlc_raw.c +++ b/drivers/net/wan/hdlc_raw.c @@ -19,7 +19,7 @@ #include -static int raw_ioctl(struct net_device *dev, struct ifreq *ifr); +static int raw_ioctl(struct net_device *dev, struct if_settings *ifs); static __be16 raw_type_trans(struct sk_buff *skb, struct net_device *dev) { @@ -33,21 +33,21 @@ static struct hdlc_proto proto = { }; -static int raw_ioctl(struct net_device *dev, struct ifreq *ifr) +static int raw_ioctl(struct net_device *dev, struct if_settings *ifs) { - raw_hdlc_proto __user *raw_s = ifr->ifr_settings.ifs_ifsu.raw_hdlc; + raw_hdlc_proto __user *raw_s = ifs->ifs_ifsu.raw_hdlc; const size_t size = sizeof(raw_hdlc_proto); raw_hdlc_proto new_settings; hdlc_device *hdlc = dev_to_hdlc(dev); int result; - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_PROTO: if (dev_to_hdlc(dev)->proto != &proto) return -EINVAL; - ifr->ifr_settings.type = IF_PROTO_HDLC; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_PROTO_HDLC; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } if (copy_to_user(raw_s, hdlc->state, size)) diff --git a/drivers/net/wan/hdlc_raw_eth.c b/drivers/net/wan/hdlc_raw_eth.c index 927596276a07..0a66b7356405 100644 --- a/drivers/net/wan/hdlc_raw_eth.c +++ b/drivers/net/wan/hdlc_raw_eth.c @@ -20,7 +20,7 @@ #include #include -static int raw_eth_ioctl(struct net_device *dev, struct ifreq *ifr); +static int raw_eth_ioctl(struct net_device *dev, struct if_settings *ifs); static netdev_tx_t eth_tx(struct sk_buff *skb, struct net_device *dev) { @@ -48,22 +48,22 @@ static struct hdlc_proto proto = { }; -static int raw_eth_ioctl(struct net_device *dev, struct ifreq *ifr) +static int raw_eth_ioctl(struct net_device *dev, struct if_settings *ifs) { - raw_hdlc_proto __user *raw_s = ifr->ifr_settings.ifs_ifsu.raw_hdlc; + raw_hdlc_proto __user *raw_s = ifs->ifs_ifsu.raw_hdlc; const size_t size = sizeof(raw_hdlc_proto); raw_hdlc_proto new_settings; hdlc_device *hdlc = dev_to_hdlc(dev); unsigned int old_qlen; int result; - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_PROTO: if (dev_to_hdlc(dev)->proto != &proto) return -EINVAL; - ifr->ifr_settings.type = IF_PROTO_HDLC_ETH; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_PROTO_HDLC_ETH; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } if (copy_to_user(raw_s, hdlc->state, size)) diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index 9b7ebf8bd85c..f72c92c24003 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -29,7 +29,7 @@ struct x25_state { struct tasklet_struct rx_tasklet; }; -static int x25_ioctl(struct net_device *dev, struct ifreq *ifr); +static int x25_ioctl(struct net_device *dev, struct if_settings *ifs); static struct x25_state *state(hdlc_device *hdlc) { @@ -274,21 +274,21 @@ static struct hdlc_proto proto = { .module = THIS_MODULE, }; -static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) +static int x25_ioctl(struct net_device *dev, struct if_settings *ifs) { - x25_hdlc_proto __user *x25_s = ifr->ifr_settings.ifs_ifsu.x25; + x25_hdlc_proto __user *x25_s = ifs->ifs_ifsu.x25; const size_t size = sizeof(x25_hdlc_proto); hdlc_device *hdlc = dev_to_hdlc(dev); x25_hdlc_proto new_settings; int result; - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_PROTO: if (dev_to_hdlc(dev)->proto != &proto) return -EINVAL; - ifr->ifr_settings.type = IF_PROTO_X25; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_PROTO_X25; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } if (copy_to_user(x25_s, &state(hdlc)->settings, size)) @@ -303,7 +303,7 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) return -EBUSY; /* backward compatibility */ - if (ifr->ifr_settings.size == 0) { + if (ifs->size == 0) { new_settings.dce = 0; new_settings.modulo = 8; new_settings.window = 7; diff --git a/drivers/net/wan/hostess_sv11.c b/drivers/net/wan/hostess_sv11.c index fd61a7cc4fdf..15a754310fd7 100644 --- a/drivers/net/wan/hostess_sv11.c +++ b/drivers/net/wan/hostess_sv11.c @@ -142,11 +142,6 @@ static int hostess_close(struct net_device *d) return 0; } -static int hostess_ioctl(struct net_device *d, struct ifreq *ifr, int cmd) -{ - return hdlc_ioctl(d, ifr, cmd); -} - /* Passed network frames, fire them downwind. */ @@ -171,7 +166,7 @@ static const struct net_device_ops hostess_ops = { .ndo_open = hostess_open, .ndo_stop = hostess_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = hostess_ioctl, + .ndo_siocwandev = hdlc_ioctl, }; static struct z8530_dev *sv11_init(int iobase, int irq) diff --git a/drivers/net/wan/ixp4xx_hss.c b/drivers/net/wan/ixp4xx_hss.c index 2cebbfca0bd1..88a36a069311 100644 --- a/drivers/net/wan/ixp4xx_hss.c +++ b/drivers/net/wan/ixp4xx_hss.c @@ -1254,23 +1254,20 @@ static void find_best_clock(u32 timer_freq, u32 rate, u32 *best, u32 *reg) } } -static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int hss_hdlc_ioctl(struct net_device *dev, struct if_settings *ifs) { const size_t size = sizeof(sync_serial_settings); sync_serial_settings new_line; - sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync; + sync_serial_settings __user *line = ifs->ifs_ifsu.sync; struct port *port = dev_to_port(dev); unsigned long flags; int clk; - if (cmd != SIOCWANDEV) - return hdlc_ioctl(dev, ifr, cmd); - - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_IFACE: - ifr->ifr_settings.type = IF_IFACE_V35; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_IFACE_V35; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } memset(&new_line, 0, sizeof(new_line)); @@ -1323,7 +1320,7 @@ static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; default: - return hdlc_ioctl(dev, ifr, cmd); + return hdlc_ioctl(dev, ifs); } } @@ -1335,7 +1332,7 @@ static const struct net_device_ops hss_hdlc_ops = { .ndo_open = hss_hdlc_open, .ndo_stop = hss_hdlc_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = hss_hdlc_ioctl, + .ndo_siocwandev = hss_hdlc_ioctl, }; static int hss_init_one(struct platform_device *pdev) diff --git a/drivers/net/wan/lmc/lmc.h b/drivers/net/wan/lmc/lmc.h index 3bd541c868d5..d7d59b4595f9 100644 --- a/drivers/net/wan/lmc/lmc.h +++ b/drivers/net/wan/lmc/lmc.h @@ -19,7 +19,7 @@ void lmc_mii_writereg(lmc_softc_t * const, unsigned, unsigned, unsigned); void lmc_gpio_mkinput(lmc_softc_t * const sc, u32 bits); void lmc_gpio_mkoutput(lmc_softc_t * const sc, u32 bits); -int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); +int lmc_ioctl(struct net_device *dev, struct if_settings *ifs); extern lmc_media_t lmc_ds3_media; extern lmc_media_t lmc_ssi_media; diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c index 26a4ffbff73b..ed687bf6ec47 100644 --- a/drivers/net/wan/lmc/lmc_main.c +++ b/drivers/net/wan/lmc/lmc_main.c @@ -616,14 +616,6 @@ static int lmc_siocdevprivate(struct net_device *dev, struct ifreq *ifr, return ret; } -int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - if (cmd != SIOCWANDEV) - return -EOPNOTSUPP; - - return lmc_proto_ioctl(dev_to_sc(dev), ifr, cmd); -} - /* the watchdog process that cruises around */ static void lmc_watchdog(struct timer_list *t) /*fold00*/ @@ -794,7 +786,7 @@ static const struct net_device_ops lmc_ops = { .ndo_open = lmc_open, .ndo_stop = lmc_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = lmc_ioctl, + .ndo_siocwandev = hdlc_ioctl, .ndo_siocdevprivate = lmc_siocdevprivate, .ndo_tx_timeout = lmc_driver_timeout, .ndo_get_stats = lmc_get_stats, diff --git a/drivers/net/wan/lmc/lmc_proto.c b/drivers/net/wan/lmc/lmc_proto.c index 4e9cc83b615a..e5487616a816 100644 --- a/drivers/net/wan/lmc/lmc_proto.c +++ b/drivers/net/wan/lmc/lmc_proto.c @@ -58,13 +58,6 @@ void lmc_proto_attach(lmc_softc_t *sc) /*FOLD00*/ } } -int lmc_proto_ioctl(lmc_softc_t *sc, struct ifreq *ifr, int cmd) -{ - if (sc->if_type == LMC_PPP) - return hdlc_ioctl(sc->lmc_device, ifr, cmd); - return -EOPNOTSUPP; -} - int lmc_proto_open(lmc_softc_t *sc) { int ret = 0; diff --git a/drivers/net/wan/lmc/lmc_proto.h b/drivers/net/wan/lmc/lmc_proto.h index bb098e443776..e56e7072de44 100644 --- a/drivers/net/wan/lmc/lmc_proto.h +++ b/drivers/net/wan/lmc/lmc_proto.h @@ -5,7 +5,6 @@ #include void lmc_proto_attach(lmc_softc_t *sc); -int lmc_proto_ioctl(lmc_softc_t *sc, struct ifreq *ifr, int cmd); int lmc_proto_open(lmc_softc_t *sc); void lmc_proto_close(lmc_softc_t *sc); __be16 lmc_proto_type(lmc_softc_t *sc, struct sk_buff *skb); diff --git a/drivers/net/wan/n2.c b/drivers/net/wan/n2.c index 4122ca2cd07d..f3e80722ba1d 100644 --- a/drivers/net/wan/n2.c +++ b/drivers/net/wan/n2.c @@ -239,21 +239,18 @@ static int n2_siocdevprivate(struct net_device *dev, struct ifreq *ifr, return -EOPNOTSUPP; } -static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int n2_ioctl(struct net_device *dev, struct if_settings *ifs) { const size_t size = sizeof(sync_serial_settings); sync_serial_settings new_line; - sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync; + sync_serial_settings __user *line = ifs->ifs_ifsu.sync; port_t *port = dev_to_port(dev); - if (cmd != SIOCWANDEV) - return hdlc_ioctl(dev, ifr, cmd); - - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_IFACE: - ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_IFACE_SYNC_SERIAL; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } if (copy_to_user(line, &port->settings, size)) @@ -281,7 +278,7 @@ static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; default: - return hdlc_ioctl(dev, ifr, cmd); + return hdlc_ioctl(dev, ifs); } } @@ -317,7 +314,7 @@ static const struct net_device_ops n2_ops = { .ndo_open = n2_open, .ndo_stop = n2_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = n2_ioctl, + .ndo_siocwandev = n2_ioctl, .ndo_siocdevprivate = n2_siocdevprivate, }; diff --git a/drivers/net/wan/pc300too.c b/drivers/net/wan/pc300too.c index 8cdfd0056c81..4766446f0fa0 100644 --- a/drivers/net/wan/pc300too.c +++ b/drivers/net/wan/pc300too.c @@ -186,21 +186,18 @@ static int pc300_siocdevprivate(struct net_device *dev, struct ifreq *ifr, return -EOPNOTSUPP; } -static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int pc300_ioctl(struct net_device *dev, struct if_settings *ifs) { const size_t size = sizeof(sync_serial_settings); sync_serial_settings new_line; - sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync; + sync_serial_settings __user *line = ifs->ifs_ifsu.sync; int new_type; port_t *port = dev_to_port(dev); - if (cmd != SIOCWANDEV) - return hdlc_ioctl(dev, ifr, cmd); - - if (ifr->ifr_settings.type == IF_GET_IFACE) { - ifr->ifr_settings.type = port->iface; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + if (ifs->type == IF_GET_IFACE) { + ifs->type = port->iface; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } if (copy_to_user(line, &port->settings, size)) @@ -209,21 +206,21 @@ static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } if (port->card->type == PC300_X21 && - (ifr->ifr_settings.type == IF_IFACE_SYNC_SERIAL || - ifr->ifr_settings.type == IF_IFACE_X21)) + (ifs->type == IF_IFACE_SYNC_SERIAL || + ifs->type == IF_IFACE_X21)) new_type = IF_IFACE_X21; else if (port->card->type == PC300_RSV && - (ifr->ifr_settings.type == IF_IFACE_SYNC_SERIAL || - ifr->ifr_settings.type == IF_IFACE_V35)) + (ifs->type == IF_IFACE_SYNC_SERIAL || + ifs->type == IF_IFACE_V35)) new_type = IF_IFACE_V35; else if (port->card->type == PC300_RSV && - ifr->ifr_settings.type == IF_IFACE_V24) + ifs->type == IF_IFACE_V24) new_type = IF_IFACE_V24; else - return hdlc_ioctl(dev, ifr, cmd); + return hdlc_ioctl(dev, ifs); if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -278,7 +275,7 @@ static const struct net_device_ops pc300_ops = { .ndo_open = pc300_open, .ndo_stop = pc300_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = pc300_ioctl, + .ndo_siocwandev = pc300_ioctl, .ndo_siocdevprivate = pc300_siocdevprivate, }; diff --git a/drivers/net/wan/pci200syn.c b/drivers/net/wan/pci200syn.c index f4dc3dda25b7..ea86c7035653 100644 --- a/drivers/net/wan/pci200syn.c +++ b/drivers/net/wan/pci200syn.c @@ -179,21 +179,18 @@ static int pci200_siocdevprivate(struct net_device *dev, struct ifreq *ifr, return -EOPNOTSUPP; } -static int pci200_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int pci200_ioctl(struct net_device *dev, struct if_settings *ifs) { const size_t size = sizeof(sync_serial_settings); sync_serial_settings new_line; - sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync; + sync_serial_settings __user *line = ifs->ifs_ifsu.sync; port_t *port = dev_to_port(dev); - if (cmd != SIOCWANDEV) - return hdlc_ioctl(dev, ifr, cmd); - - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_IFACE: - ifr->ifr_settings.type = IF_IFACE_V35; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_IFACE_V35; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } if (copy_to_user(line, &port->settings, size)) @@ -223,7 +220,7 @@ static int pci200_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; default: - return hdlc_ioctl(dev, ifr, cmd); + return hdlc_ioctl(dev, ifs); } } @@ -259,7 +256,7 @@ static const struct net_device_ops pci200_ops = { .ndo_open = pci200_open, .ndo_stop = pci200_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = pci200_ioctl, + .ndo_siocwandev = pci200_ioctl, .ndo_siocdevprivate = pci200_siocdevprivate, }; diff --git a/drivers/net/wan/sealevel.c b/drivers/net/wan/sealevel.c index 4403e219ca03..eddd20aab691 100644 --- a/drivers/net/wan/sealevel.c +++ b/drivers/net/wan/sealevel.c @@ -124,14 +124,6 @@ static int sealevel_close(struct net_device *d) return 0; } -static int sealevel_ioctl(struct net_device *d, struct ifreq *ifr, int cmd) -{ - /* struct slvl_device *slvl=dev_to_chan(d); - * z8530_ioctl(d,&slvl->sync.chanA,ifr,cmd) - */ - return hdlc_ioctl(d, ifr, cmd); -} - /* Passed network frames, fire them downwind. */ static netdev_tx_t sealevel_queue_xmit(struct sk_buff *skb, @@ -152,7 +144,7 @@ static const struct net_device_ops sealevel_ops = { .ndo_open = sealevel_open, .ndo_stop = sealevel_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = sealevel_ioctl, + .ndo_siocwandev = hdlc_ioctl, }; static int slvl_setup(struct slvl_device *sv, int iobase, int irq) diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index f22e48415e6f..5a9e262188ef 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -343,20 +343,17 @@ static int wanxl_attach(struct net_device *dev, unsigned short encoding, return 0; } -static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int wanxl_ioctl(struct net_device *dev, struct if_settings *ifs) { const size_t size = sizeof(sync_serial_settings); sync_serial_settings line; struct port *port = dev_to_port(dev); - if (cmd != SIOCWANDEV) - return hdlc_ioctl(dev, ifr, cmd); - - switch (ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_IFACE: - ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_IFACE_SYNC_SERIAL; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } memset(&line, 0, sizeof(line)); @@ -364,7 +361,7 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) line.clock_rate = 0; line.loopback = 0; - if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &line, size)) + if (copy_to_user(ifs->ifs_ifsu.sync, &line, size)) return -EFAULT; return 0; @@ -374,7 +371,7 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (dev->flags & IFF_UP) return -EBUSY; - if (copy_from_user(&line, ifr->ifr_settings.ifs_ifsu.sync, + if (copy_from_user(&line, ifs->ifs_ifsu.sync, size)) return -EFAULT; @@ -389,7 +386,7 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; default: - return hdlc_ioctl(dev, ifr, cmd); + return hdlc_ioctl(dev, ifs); } } @@ -545,7 +542,7 @@ static const struct net_device_ops wanxl_ops = { .ndo_open = wanxl_open, .ndo_stop = wanxl_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = wanxl_ioctl, + .ndo_siocwandev = wanxl_ioctl, .ndo_get_stats = wanxl_get_stats, }; diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c index 5bb928b7873e..3e3b8873fa29 100644 --- a/drivers/tty/synclink_gt.c +++ b/drivers/tty/synclink_gt.c @@ -1524,11 +1524,11 @@ static int hdlcdev_close(struct net_device *dev) * * Return: 0 if success, otherwise error code */ -static int hdlcdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int hdlcdev_ioctl(struct net_device *dev, struct if_settings *ifs) { const size_t size = sizeof(sync_serial_settings); sync_serial_settings new_line; - sync_serial_settings __user *line = ifr->ifr_settings.ifs_ifsu.sync; + sync_serial_settings __user *line = ifs->ifs_ifsu.sync; struct slgt_info *info = dev_to_port(dev); unsigned int flags; @@ -1538,17 +1538,14 @@ static int hdlcdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (info->port.count) return -EBUSY; - if (cmd != SIOCWANDEV) - return hdlc_ioctl(dev, ifr, cmd); - memset(&new_line, 0, sizeof(new_line)); - switch(ifr->ifr_settings.type) { + switch (ifs->type) { case IF_GET_IFACE: /* return current sync_serial_settings */ - ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL; - if (ifr->ifr_settings.size < size) { - ifr->ifr_settings.size = size; /* data size wanted */ + ifs->type = IF_IFACE_SYNC_SERIAL; + if (ifs->size < size) { + ifs->size = size; /* data size wanted */ return -ENOBUFS; } @@ -1615,7 +1612,7 @@ static int hdlcdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; default: - return hdlc_ioctl(dev, ifr, cmd); + return hdlc_ioctl(dev, ifs); } } @@ -1688,7 +1685,7 @@ static const struct net_device_ops hdlcdev_ops = { .ndo_open = hdlcdev_open, .ndo_stop = hdlcdev_close, .ndo_start_xmit = hdlc_start_xmit, - .ndo_do_ioctl = hdlcdev_ioctl, + .ndo_siocwandev = hdlcdev_ioctl, .ndo_tx_timeout = hdlcdev_tx_timeout, }; diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h index cacc4dd27794..630a388035f1 100644 --- a/include/linux/hdlc.h +++ b/include/linux/hdlc.h @@ -22,7 +22,7 @@ struct hdlc_proto { void (*start)(struct net_device *dev); /* if open & DCD */ void (*stop)(struct net_device *dev); /* if open & !DCD */ void (*detach)(struct net_device *dev); - int (*ioctl)(struct net_device *dev, struct ifreq *ifr); + int (*ioctl)(struct net_device *dev, struct if_settings *ifs); __be16 (*type_trans)(struct sk_buff *skb, struct net_device *dev); int (*netif_rx)(struct sk_buff *skb); netdev_tx_t (*xmit)(struct sk_buff *skb, struct net_device *dev); @@ -54,7 +54,7 @@ typedef struct hdlc_device { /* Exported from hdlc module */ /* Called by hardware driver when a user requests HDLC service */ -int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); +int hdlc_ioctl(struct net_device *dev, struct if_settings *ifs); /* Must be used by hardware driver on module startup/exit */ #define register_hdlc_device(dev) register_netdev(dev) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b6e062a3b0d4..cc11382f76a3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1367,6 +1367,8 @@ struct net_device_ops { struct ifreq *ifr, int cmd); int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); + int (*ndo_siocwandev)(struct net_device *dev, + struct if_settings *ifs); int (*ndo_siocdevprivate)(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 8e30fe8b5645..e0586bc4d6c6 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -291,6 +291,20 @@ static int dev_siocdevprivate(struct net_device *dev, struct ifreq *ifr, return dev_do_ioctl(dev, ifr, cmd); } +static int dev_siocwandev(struct net_device *dev, struct if_settings *ifs) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_siocwandev) { + if (netif_device_present(dev)) + return ops->ndo_siocwandev(dev, ifs); + else + return -ENODEV; + } + + return -EOPNOTSUPP; +} + /* * Perform the SIOCxIFxxx calls, inside rtnl_lock() */ @@ -359,6 +373,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, ifr->ifr_newname[IFNAMSIZ-1] = '\0'; return dev_change_name(dev, ifr->ifr_newname); + case SIOCWANDEV: + return dev_siocwandev(dev, &ifr->ifr_settings); + case SIOCSHWTSTAMP: err = net_hwtstamp_validate(ifr); if (err) @@ -386,8 +403,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, cmd == SIOCBONDINFOQUERY || cmd == SIOCBONDCHANGEACTIVE || cmd == SIOCBRADDIF || - cmd == SIOCBRDELIF || - cmd == SIOCWANDEV) { + cmd == SIOCBRDELIF) { err = dev_do_ioctl(dev, ifr, cmd); } else err = -EINVAL; -- cgit v1.2.3 From ad2f99aedf8fa77f3ae647153284fa63c43d3055 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Jul 2021 15:45:16 +0200 Subject: net: bridge: move bridge ioctls out of .ndo_do_ioctl Working towards obsoleting the .ndo_do_ioctl operation entirely, stop passing the SIOCBRADDIF/SIOCBRDELIF device ioctl commands into this callback. My first attempt was to add another ndo_siocbr() callback, but as there is only a single driver that takes these commands and there is already a hook mechanism to call directly into this driver, extend this hook instead, and use it for both the deviceless and the device specific ioctl commands. Cc: Roopa Prabhu Cc: Nikolay Aleksandrov Cc: bridge@lists.linux-foundation.org Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 7 ++++++- net/bridge/br.c | 2 +- net/bridge/br_device.c | 1 - net/bridge/br_ioctl.c | 15 +++------------ net/bridge/br_private.h | 5 ++--- net/core/dev_ioctl.c | 11 ++++++++--- net/socket.c | 33 +++++++++++++++++++++++---------- 7 files changed, 43 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index b73b4ff749e1..21daed10322e 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -61,7 +61,12 @@ struct br_ip_list { #define BR_DEFAULT_AGEING_TIME (300 * HZ) -extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); +struct net_bridge; +void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br, + unsigned int cmd, struct ifreq *ifr, + void __user *uarg)); +int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd, + struct ifreq *ifr, void __user *uarg); #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING) int br_multicast_list_adjacent(struct net_device *dev, diff --git a/net/bridge/br.c b/net/bridge/br.c index 51f2e25c4cd6..8fb5dca5f8e0 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -359,7 +359,7 @@ static int __init br_init(void) if (err) goto err_out5; - brioctl_set(br_ioctl_deviceless_stub); + brioctl_set(br_ioctl_stub); #if IS_ENABLED(CONFIG_ATM_LANE) br_fdb_test_addr_hook = br_fdb_test_addr; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 1952bb433ca7..8d6bab244c4a 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -454,7 +454,6 @@ static const struct net_device_ops br_netdev_ops = { .ndo_set_rx_mode = br_dev_set_multicast_list, .ndo_change_rx_flags = br_dev_change_rx_flags, .ndo_change_mtu = br_change_mtu, - .ndo_do_ioctl = br_dev_ioctl, .ndo_siocdevprivate = br_dev_siocdevprivate, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = br_netpoll_setup, diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 9f924fe43641..46a24c20e405 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -366,7 +366,8 @@ static int old_deviceless(struct net *net, void __user *uarg) return -EOPNOTSUPP; } -int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *uarg) +int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd, + struct ifreq *ifr, void __user *uarg) { switch (cmd) { case SIOCGIFBR: @@ -390,21 +391,11 @@ int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *uar return br_del_bridge(net, buf); } - } - return -EOPNOTSUPP; -} - -int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) -{ - struct net_bridge *br = netdev_priv(dev); - switch (cmd) { case SIOCBRADDIF: case SIOCBRDELIF: - return add_del_if(br, rq->ifr_ifindex, cmd == SIOCBRADDIF); + return add_del_if(br, ifr->ifr_ifindex, cmd == SIOCBRADDIF); } - - br_debug(br, "Bridge does not support ioctl 0x%x\n", cmd); return -EOPNOTSUPP; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 572c28ae41b8..f2d34ea1ea37 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -851,11 +851,10 @@ br_port_get_check_rtnl(const struct net_device *dev) } /* br_ioctl.c */ -int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); int br_dev_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data, int cmd); -int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, - void __user *arg); +int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd, + struct ifreq *ifr, void __user *uarg); /* br_multicast.c */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 70a379cee5fd..3166f196b296 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -374,6 +375,12 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, case SIOCWANDEV: return dev_siocwandev(dev, &ifr->ifr_settings); + case SIOCBRADDIF: + case SIOCBRDELIF: + if (!netif_device_present(dev)) + return -ENODEV; + return br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL); + case SIOCSHWTSTAMP: err = net_hwtstamp_validate(ifr); if (err) @@ -399,9 +406,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, cmd == SIOCBONDSETHWADDR || cmd == SIOCBONDSLAVEINFOQUERY || cmd == SIOCBONDINFOQUERY || - cmd == SIOCBONDCHANGEACTIVE || - cmd == SIOCBRADDIF || - cmd == SIOCBRDELIF) { + cmd == SIOCBONDCHANGEACTIVE) { err = dev_do_ioctl(dev, ifr, cmd); } else err = -EINVAL; diff --git a/net/socket.c b/net/socket.c index 48471a219c1d..42665bd99ea4 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1064,9 +1064,13 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) */ static DEFINE_MUTEX(br_ioctl_mutex); -static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg); +static int (*br_ioctl_hook)(struct net *net, struct net_bridge *br, + unsigned int cmd, struct ifreq *ifr, + void __user *uarg); -void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *)) +void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br, + unsigned int cmd, struct ifreq *ifr, + void __user *uarg)) { mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; @@ -1074,6 +1078,22 @@ void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *)) } EXPORT_SYMBOL(brioctl_set); +int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd, + struct ifreq *ifr, void __user *uarg) +{ + int err = -ENOPKG; + + if (!br_ioctl_hook) + request_module("bridge"); + + mutex_lock(&br_ioctl_mutex); + if (br_ioctl_hook) + err = br_ioctl_hook(net, br, cmd, ifr, uarg); + mutex_unlock(&br_ioctl_mutex); + + return err; +} + static DEFINE_MUTEX(vlan_ioctl_mutex); static int (*vlan_ioctl_hook) (struct net *, void __user *arg); @@ -1162,14 +1182,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) case SIOCSIFBR: case SIOCBRADDBR: case SIOCBRDELBR: - err = -ENOPKG; - if (!br_ioctl_hook) - request_module("bridge"); - - mutex_lock(&br_ioctl_mutex); - if (br_ioctl_hook) - err = br_ioctl_hook(net, cmd, argp); - mutex_unlock(&br_ioctl_mutex); + err = br_ioctl_call(net, NULL, cmd, NULL, argp); break; case SIOCGIFVLAN: case SIOCSIFVLAN: -- cgit v1.2.3 From 3d9d00bd1885afa6b2c766cf9bab7b54b1a951ed Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Jul 2021 15:45:17 +0200 Subject: net: bonding: move ioctl handling to private ndo operation All other user triggered operations are gone from ndo_ioctl, so move the SIOCBOND family into a custom operation as well. The .ndo_ioctl() helper is no longer called by the dev_ioctl.c code now, but there are still a few definitions in obsolete wireless drivers as well as the appletalk and ieee802154 layers to call SIOCSIFADDR/SIOCGIFADDR helpers from inside the kernel. Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- Documentation/networking/netdevices.rst | 11 +++++++++++ drivers/net/bonding/bond_main.c | 2 +- include/linux/netdevice.h | 13 ++++++++++--- net/core/dev_ioctl.c | 8 ++++---- 4 files changed, 26 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst index 3c42b0b0be93..9e4cccb90b87 100644 --- a/Documentation/networking/netdevices.rst +++ b/Documentation/networking/netdevices.rst @@ -222,6 +222,17 @@ ndo_do_ioctl: Synchronization: rtnl_lock() semaphore. Context: process + This is only called by network subsystems internally, + not by user space calling ioctl as it was in before + linux-5.14. + +ndo_siocbond: + Synchronization: rtnl_lock() semaphore. + Context: process + + Used by the bonding driver for the SIOCBOND family of + ioctl commands. + ndo_siocwandev: Synchronization: rtnl_lock() semaphore. Context: process diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 23769e937c28..bec8ceaff98f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4988,7 +4988,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_select_queue = bond_select_queue, .ndo_get_stats64 = bond_get_stats, .ndo_eth_ioctl = bond_eth_ioctl, - .ndo_do_ioctl = bond_do_ioctl, + .ndo_siocbond = bond_do_ioctl, .ndo_siocdevprivate = bond_siocdevprivate, .ndo_change_rx_flags = bond_change_rx_flags, .ndo_set_rx_mode = bond_set_rx_mode, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cc11382f76a3..226bbee06730 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1086,9 +1086,14 @@ struct netdev_net_notifier { * Test if Media Access Control address is valid for the device. * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); - * Called when a user requests an ioctl which can't be handled by - * the generic interface code. If not defined ioctls return - * not supported error code. + * Old-style ioctl entry point. This is used internally by the + * appletalk and ieee802154 subsystems but is no longer called by + * the device ioctl handler. + * + * int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd); + * Used by the bonding driver for its device specific ioctls: + * SIOCBONDENSLAVE, SIOCBONDRELEASE, SIOCBONDSETHWADDR, SIOCBONDCHANGEACTIVE, + * SIOCBONDSLAVEINFOQUERY, and SIOCBONDINFOQUERY * * * int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); * Called for ethernet specific ioctls: SIOCGMIIPHY, SIOCGMIIREG, @@ -1367,6 +1372,8 @@ struct net_device_ops { struct ifreq *ifr, int cmd); int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); + int (*ndo_siocbond)(struct net_device *dev, + struct ifreq *ifr, int cmd); int (*ndo_siocwandev)(struct net_device *dev, struct if_settings *ifs); int (*ndo_siocdevprivate)(struct net_device *dev, diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 3166f196b296..4035bce06bf8 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -260,14 +260,14 @@ static int dev_eth_ioctl(struct net_device *dev, return err; } -static int dev_do_ioctl(struct net_device *dev, +static int dev_siocbond(struct net_device *dev, struct ifreq *ifr, unsigned int cmd) { const struct net_device_ops *ops = dev->netdev_ops; - if (ops->ndo_do_ioctl) { + if (ops->ndo_siocbond) { if (netif_device_present(dev)) - return ops->ndo_do_ioctl(dev, ifr, cmd); + return ops->ndo_siocbond(dev, ifr, cmd); else return -ENODEV; } @@ -407,7 +407,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, cmd == SIOCBONDSLAVEINFOQUERY || cmd == SIOCBONDINFOQUERY || cmd == SIOCBONDCHANGEACTIVE) { - err = dev_do_ioctl(dev, ifr, cmd); + err = dev_siocbond(dev, ifr, cmd); } else err = -EINVAL; -- cgit v1.2.3 From cf0a95659e659d36838e56cc439d3986dcb46870 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 22 Jul 2021 22:34:50 +0300 Subject: clk: x86: Rename clk-lpt to more specific clk-lpss-atom The LPT stands for Lynxpoint PCH. However the driver is used on a few Intel Atom SoCs. Rename it to reflect this in a way how another clock driver, i.e. clk-pmc-atom, is called. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210722193450.35321-1-andriy.shevchenko@linux.intel.com Acked-by: Rafael J. Wysocki Signed-off-by: Stephen Boyd --- drivers/acpi/acpi_lpss.c | 6 ++-- drivers/clk/x86/Makefile | 2 +- drivers/clk/x86/clk-lpss-atom.c | 47 ++++++++++++++++++++++++++++++ drivers/clk/x86/clk-lpt.c | 47 ------------------------------ include/linux/platform_data/x86/clk-lpss.h | 2 +- 5 files changed, 53 insertions(+), 51 deletions(-) create mode 100644 drivers/clk/x86/clk-lpss-atom.c delete mode 100644 drivers/clk/x86/clk-lpt.c (limited to 'include/linux') diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 894b7e6ae144..7f163074e4e4 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -385,7 +385,9 @@ static struct platform_device *lpss_clk_dev; static inline void lpt_register_clock_device(void) { - lpss_clk_dev = platform_device_register_simple("clk-lpt", -1, NULL, 0); + lpss_clk_dev = platform_device_register_simple("clk-lpss-atom", + PLATFORM_DEVID_NONE, + NULL, 0); } static int register_device_clock(struct acpi_device *adev, @@ -1337,7 +1339,7 @@ void __init acpi_lpss_init(void) const struct x86_cpu_id *id; int ret; - ret = lpt_clk_init(); + ret = lpss_atom_clk_init(); if (ret) return; diff --git a/drivers/clk/x86/Makefile b/drivers/clk/x86/Makefile index 18564efdc651..1244c4e568ff 100644 --- a/drivers/clk/x86/Makefile +++ b/drivers/clk/x86/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_PMC_ATOM) += clk-pmc-atom.o obj-$(CONFIG_X86_AMD_PLATFORM_DEVICE) += clk-fch.o -clk-x86-lpss-objs := clk-lpt.o +clk-x86-lpss-y := clk-lpss-atom.o obj-$(CONFIG_X86_INTEL_LPSS) += clk-x86-lpss.o obj-$(CONFIG_CLK_LGM_CGU) += clk-cgu.o clk-cgu-pll.o clk-lgm.o diff --git a/drivers/clk/x86/clk-lpss-atom.c b/drivers/clk/x86/clk-lpss-atom.c new file mode 100644 index 000000000000..aa9d0bb98f8b --- /dev/null +++ b/drivers/clk/x86/clk-lpss-atom.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Intel Low Power Subsystem clocks. + * + * Copyright (C) 2013, Intel Corporation + * Authors: Mika Westerberg + * Heikki Krogerus + */ + +#include +#include +#include +#include +#include + +static int lpss_atom_clk_probe(struct platform_device *pdev) +{ + struct lpss_clk_data *drvdata; + struct clk *clk; + + drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + /* LPSS free running clock */ + drvdata->name = "lpss_clk"; + clk = clk_register_fixed_rate(&pdev->dev, drvdata->name, NULL, + 0, 100000000); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + drvdata->clk = clk; + platform_set_drvdata(pdev, drvdata); + return 0; +} + +static struct platform_driver lpss_atom_clk_driver = { + .driver = { + .name = "clk-lpss-atom", + }, + .probe = lpss_atom_clk_probe, +}; + +int __init lpss_atom_clk_init(void) +{ + return platform_driver_register(&lpss_atom_clk_driver); +} diff --git a/drivers/clk/x86/clk-lpt.c b/drivers/clk/x86/clk-lpt.c deleted file mode 100644 index fbe9fd3ed948..000000000000 --- a/drivers/clk/x86/clk-lpt.c +++ /dev/null @@ -1,47 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Intel Low Power Subsystem clocks. - * - * Copyright (C) 2013, Intel Corporation - * Authors: Mika Westerberg - * Heikki Krogerus - */ - -#include -#include -#include -#include -#include - -static int lpt_clk_probe(struct platform_device *pdev) -{ - struct lpss_clk_data *drvdata; - struct clk *clk; - - drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; - - /* LPSS free running clock */ - drvdata->name = "lpss_clk"; - clk = clk_register_fixed_rate(&pdev->dev, drvdata->name, NULL, - 0, 100000000); - if (IS_ERR(clk)) - return PTR_ERR(clk); - - drvdata->clk = clk; - platform_set_drvdata(pdev, drvdata); - return 0; -} - -static struct platform_driver lpt_clk_driver = { - .driver = { - .name = "clk-lpt", - }, - .probe = lpt_clk_probe, -}; - -int __init lpt_clk_init(void) -{ - return platform_driver_register(&lpt_clk_driver); -} diff --git a/include/linux/platform_data/x86/clk-lpss.h b/include/linux/platform_data/x86/clk-lpss.h index 207e1a317800..41df326583f9 100644 --- a/include/linux/platform_data/x86/clk-lpss.h +++ b/include/linux/platform_data/x86/clk-lpss.h @@ -15,6 +15,6 @@ struct lpss_clk_data { struct clk *clk; }; -extern int lpt_clk_init(void); +extern int lpss_atom_clk_init(void); #endif /* __CLK_LPSS_H */ -- cgit v1.2.3 From 9635720b7c88592214562cb72605bdab6708006c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 27 Jul 2021 09:05:00 -0700 Subject: bpf, sockmap: Fix memleak on ingress msg enqueue If backlog handler is running during a tear down operation we may enqueue data on the ingress msg queue while tear down is trying to free it. sk_psock_backlog() sk_psock_handle_skb() skb_psock_skb_ingress() sk_psock_skb_ingress_enqueue() sk_psock_queue_msg(psock,msg) spin_lock(ingress_lock) sk_psock_zap_ingress() _sk_psock_purge_ingerss_msg() _sk_psock_purge_ingress_msg() -- free ingress_msg list -- spin_unlock(ingress_lock) spin_lock(ingress_lock) list_add_tail(msg,ingress_msg) <- entry on list with no one left to free it. spin_unlock(ingress_lock) To fix we only enqueue from backlog if the ENABLED bit is set. The tear down logic clears the bit with ingress_lock set so we wont enqueue the msg in the last step. Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Signed-off-by: John Fastabend Signed-off-by: Andrii Nakryiko Acked-by: Jakub Sitnicki Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210727160500.1713554-4-john.fastabend@gmail.com --- include/linux/skmsg.h | 54 +++++++++++++++++++++++++++++++++------------------ net/core/skmsg.c | 6 ------ 2 files changed, 35 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 96f319099744..14ab0c0bc924 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -285,11 +285,45 @@ static inline struct sk_psock *sk_psock(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } +static inline void sk_psock_set_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + set_bit(bit, &psock->state); +} + +static inline void sk_psock_clear_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + clear_bit(bit, &psock->state); +} + +static inline bool sk_psock_test_state(const struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + return test_bit(bit, &psock->state); +} + +static inline void sock_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + kfree_skb(skb); +} + +static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg) +{ + if (msg->skb) + sock_drop(psock->sk, msg->skb); + kfree(msg); +} + static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); - list_add_tail(&msg->list, &psock->ingress_msg); + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + list_add_tail(&msg->list, &psock->ingress_msg); + else + drop_sk_msg(psock, msg); spin_unlock_bh(&psock->ingress_lock); } @@ -406,24 +440,6 @@ static inline void sk_psock_restore_proto(struct sock *sk, psock->psock_update_sk_prot(sk, psock, true); } -static inline void sk_psock_set_state(struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - set_bit(bit, &psock->state); -} - -static inline void sk_psock_clear_state(struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - clear_bit(bit, &psock->state); -} - -static inline bool sk_psock_test_state(const struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - return test_bit(bit, &psock->state); -} - static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 036cdb33a94a..2d6249b28928 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -584,12 +584,6 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return sk_psock_skb_ingress(psock, skb); } -static void sock_drop(struct sock *sk, struct sk_buff *skb) -{ - sk_drops_add(sk, skb); - kfree_skb(skb); -} - static void sk_psock_skb_state(struct sk_psock *psock, struct sk_psock_work_state *state, struct sk_buff *skb, -- cgit v1.2.3 From 58e106e725eed59896b9141a1c9a917d2f67962a Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Mon, 26 Apr 2021 21:59:11 +0200 Subject: sched: Add task_work callback for paranoid L1D flush The upcoming paranoid L1D flush infrastructure allows to conditionally (opt-in) flush L1D in switch_mm() as a defense against potential new side channels or for paranoia reasons. As the flush makes only sense when a task runs on a non-SMT enabled core, because SMT siblings share L1, the switch_mm() logic will kill a task which is flagged for L1D flush when it is running on a SMT thread. Add a taskwork callback so switch_mm() can queue a SIG_KILL command which is invoked when the task tries to return to user space. Signed-off-by: Balbir Singh Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210108121056.21940-1-sblbir@amazon.com --- arch/Kconfig | 3 +++ include/linux/sched.h | 10 ++++++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 129df498a8e1..98db63496bab 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1282,6 +1282,9 @@ config ARCH_SPLIT_ARG64 config ARCH_HAS_ELFCORE_COMPAT bool +config ARCH_HAS_PARANOID_L1D_FLUSH + bool + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/include/linux/sched.h b/include/linux/sched.h index ec8d07d88641..c048e59d3fbd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1400,6 +1400,16 @@ struct task_struct { struct llist_head kretprobe_instances; #endif +#ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH + /* + * If L1D flush is supported on mm context switch + * then we use this callback head to queue kill work + * to kill tasks that are not running on SMT disabled + * cores + */ + struct callback_head l1d_flush_kill; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. -- cgit v1.2.3 From b2c943e52705b211d1aa0633c9196150cf30be47 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Tue, 27 Jul 2021 10:08:37 +0200 Subject: nubus: Make struct nubus_driver::remove return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The nubus core ignores the return value of the remove callback (in nubus_device_remove()) and all implementers return 0 anyway. So make it impossible for future drivers to return an unused error code by changing the remove prototype to return void. Signed-off-by: Uwe Kleine-König Acked-by: Finn Thain Link: https://lore.kernel.org/r/20210727080840.3550927-3-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/8390/mac8390.c | 3 +-- drivers/net/ethernet/natsemi/macsonic.c | 4 +--- include/linux/nubus.h | 2 +- 3 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c index 9aac7119d382..91b04abfd687 100644 --- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -428,13 +428,12 @@ out: return err; } -static int mac8390_device_remove(struct nubus_board *board) +static void mac8390_device_remove(struct nubus_board *board) { struct net_device *dev = nubus_get_drvdata(board); unregister_netdev(dev); free_netdev(dev); - return 0; } static struct nubus_driver mac8390_driver = { diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c index 2289e1fe3741..8709d700e15a 100644 --- a/drivers/net/ethernet/natsemi/macsonic.c +++ b/drivers/net/ethernet/natsemi/macsonic.c @@ -603,7 +603,7 @@ out: return err; } -static int mac_sonic_nubus_remove(struct nubus_board *board) +static void mac_sonic_nubus_remove(struct nubus_board *board) { struct net_device *ndev = nubus_get_drvdata(board); struct sonic_local *lp = netdev_priv(ndev); @@ -613,8 +613,6 @@ static int mac_sonic_nubus_remove(struct nubus_board *board) SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode), lp->descriptors, lp->descriptors_laddr); free_netdev(ndev); - - return 0; } static struct nubus_driver mac_sonic_nubus_driver = { diff --git a/include/linux/nubus.h b/include/linux/nubus.h index eba50b057f6f..392fc6c53e96 100644 --- a/include/linux/nubus.h +++ b/include/linux/nubus.h @@ -86,7 +86,7 @@ extern struct list_head nubus_func_rsrcs; struct nubus_driver { struct device_driver driver; int (*probe)(struct nubus_board *board); - int (*remove)(struct nubus_board *board); + void (*remove)(struct nubus_board *board); }; extern struct bus_type nubus_bus_type; -- cgit v1.2.3 From 147b589c5f446d602215577835356a96c40a4044 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Tue, 6 Jul 2021 22:21:56 +0800 Subject: remoteproc: fix kernel doc for struct rproc_ops The load_rsc_table was removed since the commit c1d35c1ab424 ("remoteproc: Rename "load_rsc_table" to "parse_fw"") but got added back again by mistake in the below commit: commit b1a17513a2d6 ("remoteproc: add vendor resources handling"). The patch fixed a small code indent issue which not worth a separate patch. Fixes: b1a17513a2d6 ("remoteproc: add vendor resources handling") Signed-off-by: Dong Aisheng Link: https://lore.kernel.org/r/20210706142156.952794-2-aisheng.dong@nxp.com Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index a5b37bc10865..83c09ac36b13 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -369,9 +369,8 @@ enum rsc_handling_status { * @da_to_va: optional platform hook to perform address translations * @parse_fw: parse firmware to extract information (e.g. resource table) * @handle_rsc: optional platform hook to handle vendor resources. Should return - * RSC_HANDLED if resource was handled, RSC_IGNORED if not handled and a - * negative value on error - * @load_rsc_table: load resource table from firmware image + * RSC_HANDLED if resource was handled, RSC_IGNORED if not handled + * and a negative value on error * @find_loaded_rsc_table: find the loaded resource table from firmware image * @get_loaded_rsc_table: get resource table installed in memory * by external entity -- cgit v1.2.3 From f5e81d1117501546b7be050c5fbafa6efd2c722c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 13 Jul 2021 08:18:31 +0000 Subject: bpf: Introduce BPF nospec instruction for mitigating Spectre v4 In case of JITs, each of the JIT backends compiles the BPF nospec instruction /either/ to a machine instruction which emits a speculation barrier /or/ to /no/ machine instruction in case the underlying architecture is not affected by Speculative Store Bypass or has different mitigations in place already. This covers both x86 and (implicitly) arm64: In case of x86, we use 'lfence' instruction for mitigation. In case of arm64, we rely on the firmware mitigation as controlled via the ssbd kernel parameter. Whenever the mitigation is enabled, it works for all of the kernel code with no need to provide any additional instructions here (hence only comment in arm64 JIT). Other archs can follow as needed. The BPF nospec instruction is specifically targeting Spectre v4 since i) we don't use a serialization barrier for the Spectre v1 case, and ii) mitigation instructions for v1 and v4 might be different on some archs. The BPF nospec is required for a future commit, where the BPF verifier does annotate intermediate BPF programs with speculation barriers. Co-developed-by: Piotr Krysiuk Co-developed-by: Benedict Schlueter Signed-off-by: Daniel Borkmann Signed-off-by: Piotr Krysiuk Signed-off-by: Benedict Schlueter Acked-by: Alexei Starovoitov --- arch/arm/net/bpf_jit_32.c | 3 +++ arch/arm64/net/bpf_jit_comp.c | 13 +++++++++++++ arch/mips/net/ebpf_jit.c | 3 +++ arch/powerpc/net/bpf_jit_comp32.c | 6 ++++++ arch/powerpc/net/bpf_jit_comp64.c | 6 ++++++ arch/riscv/net/bpf_jit_comp32.c | 4 ++++ arch/riscv/net/bpf_jit_comp64.c | 4 ++++ arch/s390/net/bpf_jit_comp.c | 5 +++++ arch/sparc/net/bpf_jit_comp_64.c | 3 +++ arch/x86/net/bpf_jit_comp.c | 7 +++++++ arch/x86/net/bpf_jit_comp32.c | 6 ++++++ include/linux/filter.h | 15 +++++++++++++++ kernel/bpf/core.c | 19 ++++++++++++++++++- kernel/bpf/disasm.c | 16 +++++++++------- 14 files changed, 102 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 897634d0a67c..a951276f0547 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1602,6 +1602,9 @@ exit: rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx); emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code)); break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index dccf98a37283..41c23f474ea6 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -823,6 +823,19 @@ emit_cond_jmp: return ret; break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + /* + * Nothing required here. + * + * In case of arm64, we rely on the firmware mitigation of + * Speculative Store Bypass as controlled via the ssbd kernel + * parameter. Whenever the mitigation is enabled, it works + * for all of the kernel code with no need to provide any + * additional instructions. + */ + break; + /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 939dd06764bc..3a73e9375712 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -1355,6 +1355,9 @@ jeq_common: } break; + case BPF_ST | BPF_NOSPEC: /* speculation barrier */ + break; + case BPF_ST | BPF_B | BPF_MEM: case BPF_ST | BPF_H | BPF_MEM: case BPF_ST | BPF_W | BPF_MEM: diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 34bb1583fc0c..beb12cbc8c29 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -737,6 +737,12 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * } break; + /* + * BPF_ST NOSPEC (speculation barrier) + */ + case BPF_ST | BPF_NOSPEC: + break; + /* * BPF_ST(X) */ diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index de8595880fee..b87a63dba9c8 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -627,6 +627,12 @@ emit_clear: } break; + /* + * BPF_ST NOSPEC (speculation barrier) + */ + case BPF_ST | BPF_NOSPEC: + break; + /* * BPF_ST(X) */ diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index 81de865f4c7c..e6497424cbf6 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -1251,6 +1251,10 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, return -1; break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + case BPF_ST | BPF_MEM | BPF_B: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_W: diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 87e3bf5b9086..3af4131c22c7 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -939,6 +939,10 @@ out_be: emit_ld(rd, 0, RV_REG_T1, ctx); break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_B: emit_imm(RV_REG_T1, imm, ctx); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 2ae419f5115a..88419263a89a 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1153,6 +1153,11 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, break; } break; + /* + * BPF_NOSPEC (speculation barrier) + */ + case BPF_ST | BPF_NOSPEC: + break; /* * BPF_ST(X) */ diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 4b8d3c65d266..9a2f20cbd48b 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1287,6 +1287,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) return 1; break; } + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 4b951458c9fc..16d76f814e9b 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1219,6 +1219,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + if (boot_cpu_has(X86_FEATURE_XMM2)) + /* Emit 'lfence' */ + EMIT3(0x0F, 0xAE, 0xE8); + break; + /* ST: *(u8*)(dst_reg + off) = imm */ case BPF_ST | BPF_MEM | BPF_B: if (is_ereg(dst_reg)) diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 3da88ded6ee3..3bfda5f502cb 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1886,6 +1886,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, i++; break; } + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + if (boot_cpu_has(X86_FEATURE_XMM2)) + /* Emit 'lfence' */ + EMIT3(0x0F, 0xAE, 0xE8); + break; /* ST: *(u8*)(dst_reg + off) = imm */ case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: diff --git a/include/linux/filter.h b/include/linux/filter.h index 472f97074da0..83b896044e79 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -73,6 +73,11 @@ struct ctl_table_header; /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 +/* unused opcode to mark speculation barrier for mitigating + * Speculative Store Bypass + */ +#define BPF_NOSPEC 0xc0 + /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. @@ -390,6 +395,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = 0, \ .imm = 0 }) +/* Speculation barrier */ + +#define BPF_ST_NOSPEC() \ + ((struct bpf_insn) { \ + .code = BPF_ST | BPF_NOSPEC, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = 0 }) + /* Internal classic blocks for direct assignment */ #define __BPF_STMT(CODE, K) \ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9b1577498373..b1a5fc04492b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -32,6 +32,8 @@ #include #include #include + +#include #include /* Registers */ @@ -1377,6 +1379,7 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, + [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC, [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, @@ -1621,7 +1624,21 @@ out: COND_JMP(s, JSGE, >=) COND_JMP(s, JSLE, <=) #undef COND_JMP - /* STX and ST and LDX*/ + /* ST, STX and LDX*/ + ST_NOSPEC: + /* Speculation barrier for mitigating Speculative Store Bypass. + * In case of arm64, we rely on the firmware mitigation as + * controlled via the ssbd kernel parameter. Whenever the + * mitigation is enabled, it works for all of the kernel code + * with no need to provide any additional instructions here. + * In case of x86, we use 'lfence' insn for mitigation. We + * reuse preexisting logic from Spectre v1 mitigation that + * happens to produce the required code on x86 for v4 as well. + */ +#ifdef CONFIG_X86 + barrier_nospec(); +#endif + CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index bbfc6bb79240..ca3cd9aaa6ce 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -206,15 +206,17 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, verbose(cbs->private_data, "BUG_%02x\n", insn->code); } } else if (class == BPF_ST) { - if (BPF_MODE(insn->code) != BPF_MEM) { + if (BPF_MODE(insn->code) == BPF_MEM) { + verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) { + verbose(cbs->private_data, "(%02x) nospec\n", insn->code); + } else { verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); - return; } - verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->imm); } else if (class == BPF_LDX) { if (BPF_MODE(insn->code) != BPF_MEM) { verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code); -- cgit v1.2.3 From 2039f26f3aca5b0e419b98f65dd36481337b86ee Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 13 Jul 2021 08:18:31 +0000 Subject: bpf: Fix leakage due to insufficient speculative store bypass mitigation Spectre v4 gadgets make use of memory disambiguation, which is a set of techniques that execute memory access instructions, that is, loads and stores, out of program order; Intel's optimization manual, section 2.4.4.5: A load instruction micro-op may depend on a preceding store. Many microarchitectures block loads until all preceding store addresses are known. The memory disambiguator predicts which loads will not depend on any previous stores. When the disambiguator predicts that a load does not have such a dependency, the load takes its data from the L1 data cache. Eventually, the prediction is verified. If an actual conflict is detected, the load and all succeeding instructions are re-executed. af86ca4e3088 ("bpf: Prevent memory disambiguation attack") tried to mitigate this attack by sanitizing the memory locations through preemptive "fast" (low latency) stores of zero prior to the actual "slow" (high latency) store of a pointer value such that upon dependency misprediction the CPU then speculatively executes the load of the pointer value and retrieves the zero value instead of the attacker controlled scalar value previously stored at that location, meaning, subsequent access in the speculative domain is then redirected to the "zero page". The sanitized preemptive store of zero prior to the actual "slow" store is done through a simple ST instruction based on r10 (frame pointer) with relative offset to the stack location that the verifier has been tracking on the original used register for STX, which does not have to be r10. Thus, there are no memory dependencies for this store, since it's only using r10 and immediate constant of zero; hence af86ca4e3088 /assumed/ a low latency operation. However, a recent attack demonstrated that this mitigation is not sufficient since the preemptive store of zero could also be turned into a "slow" store and is thus bypassed as well: [...] // r2 = oob address (e.g. scalar) // r7 = pointer to map value 31: (7b) *(u64 *)(r10 -16) = r2 // r9 will remain "fast" register, r10 will become "slow" register below 32: (bf) r9 = r10 // JIT maps BPF reg to x86 reg: // r9 -> r15 (callee saved) // r10 -> rbp // train store forward prediction to break dependency link between both r9 // and r10 by evicting them from the predictor's LRU table. 33: (61) r0 = *(u32 *)(r7 +24576) 34: (63) *(u32 *)(r7 +29696) = r0 35: (61) r0 = *(u32 *)(r7 +24580) 36: (63) *(u32 *)(r7 +29700) = r0 37: (61) r0 = *(u32 *)(r7 +24584) 38: (63) *(u32 *)(r7 +29704) = r0 39: (61) r0 = *(u32 *)(r7 +24588) 40: (63) *(u32 *)(r7 +29708) = r0 [...] 543: (61) r0 = *(u32 *)(r7 +25596) 544: (63) *(u32 *)(r7 +30716) = r0 // prepare call to bpf_ringbuf_output() helper. the latter will cause rbp // to spill to stack memory while r13/r14/r15 (all callee saved regs) remain // in hardware registers. rbp becomes slow due to push/pop latency. below is // disasm of bpf_ringbuf_output() helper for better visual context: // // ffffffff8117ee20: 41 54 push r12 // ffffffff8117ee22: 55 push rbp // ffffffff8117ee23: 53 push rbx // ffffffff8117ee24: 48 f7 c1 fc ff ff ff test rcx,0xfffffffffffffffc // ffffffff8117ee2b: 0f 85 af 00 00 00 jne ffffffff8117eee0 <-- jump taken // [...] // ffffffff8117eee0: 49 c7 c4 ea ff ff ff mov r12,0xffffffffffffffea // ffffffff8117eee7: 5b pop rbx // ffffffff8117eee8: 5d pop rbp // ffffffff8117eee9: 4c 89 e0 mov rax,r12 // ffffffff8117eeec: 41 5c pop r12 // ffffffff8117eeee: c3 ret 545: (18) r1 = map[id:4] 547: (bf) r2 = r7 548: (b7) r3 = 0 549: (b7) r4 = 4 550: (85) call bpf_ringbuf_output#194288 // instruction 551 inserted by verifier \ 551: (7a) *(u64 *)(r10 -16) = 0 | /both/ are now slow stores here // storing map value pointer r7 at fp-16 | since value of r10 is "slow". 552: (7b) *(u64 *)(r10 -16) = r7 / // following "fast" read to the same memory location, but due to dependency // misprediction it will speculatively execute before insn 551/552 completes. 553: (79) r2 = *(u64 *)(r9 -16) // in speculative domain contains attacker controlled r2. in non-speculative // domain this contains r7, and thus accesses r7 +0 below. 554: (71) r3 = *(u8 *)(r2 +0) // leak r3 As can be seen, the current speculative store bypass mitigation which the verifier inserts at line 551 is insufficient since /both/, the write of the zero sanitation as well as the map value pointer are a high latency instruction due to prior memory access via push/pop of r10 (rbp) in contrast to the low latency read in line 553 as r9 (r15) which stays in hardware registers. Thus, architecturally, fp-16 is r7, however, microarchitecturally, fp-16 can still be r2. Initial thoughts to address this issue was to track spilled pointer loads from stack and enforce their load via LDX through r10 as well so that /both/ the preemptive store of zero /as well as/ the load use the /same/ register such that a dependency is created between the store and load. However, this option is not sufficient either since it can be bypassed as well under speculation. An updated attack with pointer spill/fills now _all_ based on r10 would look as follows: [...] // r2 = oob address (e.g. scalar) // r7 = pointer to map value [...] // longer store forward prediction training sequence than before. 2062: (61) r0 = *(u32 *)(r7 +25588) 2063: (63) *(u32 *)(r7 +30708) = r0 2064: (61) r0 = *(u32 *)(r7 +25592) 2065: (63) *(u32 *)(r7 +30712) = r0 2066: (61) r0 = *(u32 *)(r7 +25596) 2067: (63) *(u32 *)(r7 +30716) = r0 // store the speculative load address (scalar) this time after the store // forward prediction training. 2068: (7b) *(u64 *)(r10 -16) = r2 // preoccupy the CPU store port by running sequence of dummy stores. 2069: (63) *(u32 *)(r7 +29696) = r0 2070: (63) *(u32 *)(r7 +29700) = r0 2071: (63) *(u32 *)(r7 +29704) = r0 2072: (63) *(u32 *)(r7 +29708) = r0 2073: (63) *(u32 *)(r7 +29712) = r0 2074: (63) *(u32 *)(r7 +29716) = r0 2075: (63) *(u32 *)(r7 +29720) = r0 2076: (63) *(u32 *)(r7 +29724) = r0 2077: (63) *(u32 *)(r7 +29728) = r0 2078: (63) *(u32 *)(r7 +29732) = r0 2079: (63) *(u32 *)(r7 +29736) = r0 2080: (63) *(u32 *)(r7 +29740) = r0 2081: (63) *(u32 *)(r7 +29744) = r0 2082: (63) *(u32 *)(r7 +29748) = r0 2083: (63) *(u32 *)(r7 +29752) = r0 2084: (63) *(u32 *)(r7 +29756) = r0 2085: (63) *(u32 *)(r7 +29760) = r0 2086: (63) *(u32 *)(r7 +29764) = r0 2087: (63) *(u32 *)(r7 +29768) = r0 2088: (63) *(u32 *)(r7 +29772) = r0 2089: (63) *(u32 *)(r7 +29776) = r0 2090: (63) *(u32 *)(r7 +29780) = r0 2091: (63) *(u32 *)(r7 +29784) = r0 2092: (63) *(u32 *)(r7 +29788) = r0 2093: (63) *(u32 *)(r7 +29792) = r0 2094: (63) *(u32 *)(r7 +29796) = r0 2095: (63) *(u32 *)(r7 +29800) = r0 2096: (63) *(u32 *)(r7 +29804) = r0 2097: (63) *(u32 *)(r7 +29808) = r0 2098: (63) *(u32 *)(r7 +29812) = r0 // overwrite scalar with dummy pointer; same as before, also including the // sanitation store with 0 from the current mitigation by the verifier. 2099: (7a) *(u64 *)(r10 -16) = 0 | /both/ are now slow stores here 2100: (7b) *(u64 *)(r10 -16) = r7 | since store unit is still busy. // load from stack intended to bypass stores. 2101: (79) r2 = *(u64 *)(r10 -16) 2102: (71) r3 = *(u8 *)(r2 +0) // leak r3 [...] Looking at the CPU microarchitecture, the scheduler might issue loads (such as seen in line 2101) before stores (line 2099,2100) because the load execution units become available while the store execution unit is still busy with the sequence of dummy stores (line 2069-2098). And so the load may use the prior stored scalar from r2 at address r10 -16 for speculation. The updated attack may work less reliable on CPU microarchitectures where loads and stores share execution resources. This concludes that the sanitizing with zero stores from af86ca4e3088 ("bpf: Prevent memory disambiguation attack") is insufficient. Moreover, the detection of stack reuse from af86ca4e3088 where previously data (STACK_MISC) has been written to a given stack slot where a pointer value is now to be stored does not have sufficient coverage as precondition for the mitigation either; for several reasons outlined as follows: 1) Stack content from prior program runs could still be preserved and is therefore not "random", best example is to split a speculative store bypass attack between tail calls, program A would prepare and store the oob address at a given stack slot and then tail call into program B which does the "slow" store of a pointer to the stack with subsequent "fast" read. From program B PoV such stack slot type is STACK_INVALID, and therefore also must be subject to mitigation. 2) The STACK_SPILL must not be coupled to register_is_const(&stack->spilled_ptr) condition, for example, the previous content of that memory location could also be a pointer to map or map value. Without the fix, a speculative store bypass is not mitigated in such precondition and can then lead to a type confusion in the speculative domain leaking kernel memory near these pointer types. While brainstorming on various alternative mitigation possibilities, we also stumbled upon a retrospective from Chrome developers [0]: [...] For variant 4, we implemented a mitigation to zero the unused memory of the heap prior to allocation, which cost about 1% when done concurrently and 4% for scavenging. Variant 4 defeats everything we could think of. We explored more mitigations for variant 4 but the threat proved to be more pervasive and dangerous than we anticipated. For example, stack slots used by the register allocator in the optimizing compiler could be subject to type confusion, leading to pointer crafting. Mitigating type confusion for stack slots alone would have required a complete redesign of the backend of the optimizing compiler, perhaps man years of work, without a guarantee of completeness. [...] From BPF side, the problem space is reduced, however, options are rather limited. One idea that has been explored was to xor-obfuscate pointer spills to the BPF stack: [...] // preoccupy the CPU store port by running sequence of dummy stores. [...] 2106: (63) *(u32 *)(r7 +29796) = r0 2107: (63) *(u32 *)(r7 +29800) = r0 2108: (63) *(u32 *)(r7 +29804) = r0 2109: (63) *(u32 *)(r7 +29808) = r0 2110: (63) *(u32 *)(r7 +29812) = r0 // overwrite scalar with dummy pointer; xored with random 'secret' value // of 943576462 before store ... 2111: (b4) w11 = 943576462 2112: (af) r11 ^= r7 2113: (7b) *(u64 *)(r10 -16) = r11 2114: (79) r11 = *(u64 *)(r10 -16) 2115: (b4) w2 = 943576462 2116: (af) r2 ^= r11 // ... and restored with the same 'secret' value with the help of AX reg. 2117: (71) r3 = *(u8 *)(r2 +0) [...] While the above would not prevent speculation, it would make data leakage infeasible by directing it to random locations. In order to be effective and prevent type confusion under speculation, such random secret would have to be regenerated for each store. The additional complexity involved for a tracking mechanism that prevents jumps such that restoring spilled pointers would not get corrupted is not worth the gain for unprivileged. Hence, the fix in here eventually opted for emitting a non-public BPF_ST | BPF_NOSPEC instruction which the x86 JIT translates into a lfence opcode. Inserting the latter in between the store and load instruction is one of the mitigations options [1]. The x86 instruction manual notes: [...] An LFENCE that follows an instruction that stores to memory might complete before the data being stored have become globally visible. [...] The latter meaning that the preceding store instruction finished execution and the store is at minimum guaranteed to be in the CPU's store queue, but it's not guaranteed to be in that CPU's L1 cache at that point (globally visible). The latter would only be guaranteed via sfence. So the load which is guaranteed to execute after the lfence for that local CPU would have to rely on store-to-load forwarding. [2], in section 2.3 on store buffers says: [...] For every store operation that is added to the ROB, an entry is allocated in the store buffer. This entry requires both the virtual and physical address of the target. Only if there is no free entry in the store buffer, the frontend stalls until there is an empty slot available in the store buffer again. Otherwise, the CPU can immediately continue adding subsequent instructions to the ROB and execute them out of order. On Intel CPUs, the store buffer has up to 56 entries. [...] One small upside on the fix is that it lifts constraints from af86ca4e3088 where the sanitize_stack_off relative to r10 must be the same when coming from different paths. The BPF_ST | BPF_NOSPEC gets emitted after a BPF_STX or BPF_ST instruction. This happens either when we store a pointer or data value to the BPF stack for the first time, or upon later pointer spills. The former needs to be enforced since otherwise stale stack data could be leaked under speculation as outlined earlier. For non-x86 JITs the BPF_ST | BPF_NOSPEC mapping is currently optimized away, but others could emit a speculation barrier as well if necessary. For real-world unprivileged programs e.g. generated by LLVM, pointer spill/fill is only generated upon register pressure and LLVM only tries to do that for pointers which are not used often. The program main impact will be the initial BPF_ST | BPF_NOSPEC sanitation for the STACK_INVALID case when the first write to a stack slot occurs e.g. upon map lookup. In future we might refine ways to mitigate the latter cost. [0] https://arxiv.org/pdf/1902.05178.pdf [1] https://msrc-blog.microsoft.com/2018/05/21/analysis-and-mitigation-of-speculative-store-bypass-cve-2018-3639/ [2] https://arxiv.org/pdf/1905.05725.pdf Fixes: af86ca4e3088 ("bpf: Prevent memory disambiguation attack") Fixes: f7cf25b2026d ("bpf: track spill/fill of constants") Co-developed-by: Piotr Krysiuk Co-developed-by: Benedict Schlueter Signed-off-by: Daniel Borkmann Signed-off-by: Piotr Krysiuk Signed-off-by: Benedict Schlueter Acked-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 +- kernel/bpf/verifier.c | 87 ++++++++++++++++---------------------------- 2 files changed, 33 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7ba7e800d472..828d08afeee0 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -340,8 +340,8 @@ struct bpf_insn_aux_data { }; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ - int sanitize_stack_off; /* stack slot to be cleared */ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ + bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */ bool zext_dst; /* this insn zero extends dst reg */ u8 alu_state; /* used in combination with alu_limit */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 657062cb4d85..f9bda5476ea5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2610,6 +2610,19 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, cur = env->cur_state->frame[env->cur_state->curframe]; if (value_regno >= 0) reg = &cur->regs[value_regno]; + if (!env->bypass_spec_v4) { + bool sanitize = reg && is_spillable_regtype(reg->type); + + for (i = 0; i < size; i++) { + if (state->stack[spi].slot_type[i] == STACK_INVALID) { + sanitize = true; + break; + } + } + + if (sanitize) + env->insn_aux_data[insn_idx].sanitize_stack_spill = true; + } if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { @@ -2632,47 +2645,10 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "invalid size of register spill\n"); return -EACCES; } - if (state != cur && reg->type == PTR_TO_STACK) { verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - - if (!env->bypass_spec_v4) { - bool sanitize = false; - - if (state->stack[spi].slot_type[0] == STACK_SPILL && - register_is_const(&state->stack[spi].spilled_ptr)) - sanitize = true; - for (i = 0; i < BPF_REG_SIZE; i++) - if (state->stack[spi].slot_type[i] == STACK_MISC) { - sanitize = true; - break; - } - if (sanitize) { - int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off; - int soff = (-spi - 1) * BPF_REG_SIZE; - - /* detected reuse of integer stack slot with a pointer - * which means either llvm is reusing stack slot or - * an attacker is trying to exploit CVE-2018-3639 - * (speculative store bypass) - * Have to sanitize that slot with preemptive - * store of zero. - */ - if (*poff && *poff != soff) { - /* disallow programs where single insn stores - * into two different stack slots, since verifier - * cannot sanitize them - */ - verbose(env, - "insn %d cannot access two stack slots fp%d and fp%d", - insn_idx, *poff, soff); - return -EINVAL; - } - *poff = soff; - } - } save_register_state(state, spi, reg); } else { u8 type = STACK_MISC; @@ -11913,35 +11889,33 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { bpf_convert_ctx_access_t convert_ctx_access; + bool ctx_access; if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || - insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) + insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) { type = BPF_READ; - else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || - insn->code == (BPF_STX | BPF_MEM | BPF_H) || - insn->code == (BPF_STX | BPF_MEM | BPF_W) || - insn->code == (BPF_STX | BPF_MEM | BPF_DW)) + ctx_access = true; + } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || + insn->code == (BPF_STX | BPF_MEM | BPF_H) || + insn->code == (BPF_STX | BPF_MEM | BPF_W) || + insn->code == (BPF_STX | BPF_MEM | BPF_DW) || + insn->code == (BPF_ST | BPF_MEM | BPF_B) || + insn->code == (BPF_ST | BPF_MEM | BPF_H) || + insn->code == (BPF_ST | BPF_MEM | BPF_W) || + insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; - else + ctx_access = BPF_CLASS(insn->code) == BPF_STX; + } else { continue; + } if (type == BPF_WRITE && - env->insn_aux_data[i + delta].sanitize_stack_off) { + env->insn_aux_data[i + delta].sanitize_stack_spill) { struct bpf_insn patch[] = { - /* Sanitize suspicious stack slot with zero. - * There are no memory dependencies for this store, - * since it's only using frame pointer and immediate - * constant of zero - */ - BPF_ST_MEM(BPF_DW, BPF_REG_FP, - env->insn_aux_data[i + delta].sanitize_stack_off, - 0), - /* the original STX instruction will immediately - * overwrite the same stack slot with appropriate value - */ *insn, + BPF_ST_NOSPEC(), }; cnt = ARRAY_SIZE(patch); @@ -11955,6 +11929,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } + if (!ctx_access) + continue; + switch (env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) -- cgit v1.2.3 From fb1ba406c451045f1063ace70086b4645d4e9d54 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 24 Jul 2021 09:20:18 +0200 Subject: scsi: scsi_ioctl: Remove scsi_cmd_blk_ioctl() Open code scsi_cmd_blk_ioctl() in its two callers. Link: https://lore.kernel.org/r/20210724072033.1284840-10-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- block/scsi_ioctl.c | 13 ------------- drivers/scsi/sd.c | 5 ++++- drivers/scsi/sr.c | 8 ++++++-- include/linux/blkdev.h | 2 -- 4 files changed, 10 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index d247431a6853..f8138438c56f 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -854,19 +854,6 @@ int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd) } EXPORT_SYMBOL(scsi_verify_blk_ioctl); -int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode, - unsigned int cmd, void __user *arg) -{ - int ret; - - ret = scsi_verify_blk_ioctl(bd, cmd); - if (ret < 0) - return ret; - - return scsi_cmd_ioctl(bd->bd_disk->queue, bd->bd_disk, mode, cmd, arg); -} -EXPORT_SYMBOL(scsi_cmd_blk_ioctl); - /** * scsi_req_init - initialize certain fields of a scsi_request structure * @req: Pointer to a scsi_request structure. diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 0b87ca01efff..d65bfe505e08 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1583,7 +1583,10 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, case SCSI_IOCTL_GET_BUS_NUMBER: break; default: - error = scsi_cmd_blk_ioctl(bdev, mode, cmd, p); + error = scsi_verify_blk_ioctl(bdev, cmd); + if (error < 0) + return error; + error = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, p); if (error != -ENOTTY) return error; } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 7948416f40d5..b903e54c57fd 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -556,7 +556,8 @@ static void sr_block_release(struct gendisk *disk, fmode_t mode) static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { - struct scsi_cd *cd = scsi_cd(bdev->bd_disk); + struct gendisk *disk = bdev->bd_disk; + struct scsi_cd *cd = scsi_cd(disk); struct scsi_device *sdev = cd->device; void __user *argp = (void __user *)arg; int ret; @@ -579,7 +580,10 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case SCSI_IOCTL_GET_BUS_NUMBER: break; default: - ret = scsi_cmd_blk_ioctl(bdev, mode, cmd, argp); + ret = scsi_verify_blk_ioctl(bdev, cmd); + if (ret < 0) + goto put; + ret = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, argp); if (ret != -ENOTTY) goto put; ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3177181c4326..19aa3d5429c0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -889,8 +889,6 @@ extern blk_status_t blk_insert_cloned_request(struct request_queue *q, int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_queue_split(struct bio **); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); -extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, - unsigned int, void __user *); extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, unsigned int, void __user *); extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, -- cgit v1.2.3 From 4f07bfc56157ebc689ef54879e90c48a47294083 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 24 Jul 2021 09:20:19 +0200 Subject: scsi: scsi_ioctl: Remove scsi_verify_blk_ioctl() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Manually verify that the device is not a partition and the caller has admin privіleges at the beginning of the sr ioctl method and open code the trivial check for sd as well. Link: https://lore.kernel.org/r/20210724072033.1284840-11-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- block/scsi_ioctl.c | 12 ------------ drivers/scsi/sd.c | 8 ++------ drivers/scsi/sr.c | 6 +++--- include/linux/blkdev.h | 1 - 4 files changed, 5 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index f8138438c56f..ca7b84452d9d 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -842,18 +842,6 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod } EXPORT_SYMBOL(scsi_cmd_ioctl); -int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd) -{ - if (bd && !bdev_is_partition(bd)) - return 0; - - if (capable(CAP_SYS_RAWIO)) - return 0; - - return -ENOIOCTLCMD; -} -EXPORT_SYMBOL(scsi_verify_blk_ioctl); - /** * scsi_req_init - initialize certain fields of a scsi_request structure * @req: Pointer to a scsi_request structure. diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index d65bfe505e08..bcc4b1339e21 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1555,9 +1555,8 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, SCSI_LOG_IOCTL(1, sd_printk(KERN_INFO, sdkp, "sd_ioctl: disk=%s, " "cmd=0x%x\n", disk->disk_name, cmd)); - error = scsi_verify_blk_ioctl(bdev, cmd); - if (error < 0) - return error; + if (bdev_is_partition(bdev) && !capable(CAP_SYS_RAWIO)) + return -ENOIOCTLCMD; /* * If we are in the middle of error recovery, don't let anyone @@ -1583,9 +1582,6 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, case SCSI_IOCTL_GET_BUS_NUMBER: break; default: - error = scsi_verify_blk_ioctl(bdev, cmd); - if (error < 0) - return error; error = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, p); if (error != -ENOTTY) return error; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index b903e54c57fd..e6eadba4d638 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -562,6 +562,9 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, void __user *argp = (void __user *)arg; int ret; + if (bdev_is_partition(bdev) && !capable(CAP_SYS_RAWIO)) + return -ENOIOCTLCMD; + mutex_lock(&cd->lock); ret = scsi_ioctl_block_when_processing_errors(sdev, cmd, @@ -580,9 +583,6 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case SCSI_IOCTL_GET_BUS_NUMBER: break; default: - ret = scsi_verify_blk_ioctl(bdev, cmd); - if (ret < 0) - goto put; ret = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, argp); if (ret != -ENOTTY) goto put; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 19aa3d5429c0..e2b972a85012 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -888,7 +888,6 @@ extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_queue_split(struct bio **); -extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, unsigned int, void __user *); extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, -- cgit v1.2.3 From 547e2f7093b19a993d76c249b4c3ec8af8127d09 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 24 Jul 2021 09:20:21 +0200 Subject: scsi: block: Add a queue_max_bytes() helper Return the max_sectors value in bytes. Lifted from scsi_ioctl.c. Link: https://lore.kernel.org/r/20210724072033.1284840-13-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- block/scsi_ioctl.c | 13 ++----------- include/linux/blkdev.h | 5 +++++ 2 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index ca7b84452d9d..c3871529e283 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -68,18 +68,9 @@ static int sg_set_timeout(struct request_queue *q, int __user *p) return err; } -static int max_sectors_bytes(struct request_queue *q) -{ - unsigned int max_sectors = queue_max_sectors(q); - - max_sectors = min_t(unsigned int, max_sectors, INT_MAX >> 9); - - return max_sectors << 9; -} - static int sg_get_reserved_size(struct request_queue *q, int __user *p) { - int val = min_t(int, q->sg_reserved_size, max_sectors_bytes(q)); + int val = min(q->sg_reserved_size, queue_max_bytes(q)); return put_user(val, p); } @@ -94,7 +85,7 @@ static int sg_set_reserved_size(struct request_queue *q, int __user *p) if (size < 0) return -EINVAL; - q->sg_reserved_size = min(size, max_sectors_bytes(q)); + q->sg_reserved_size = min_t(unsigned int, size, queue_max_bytes(q)); return 0; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e2b972a85012..9971796819ef 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1373,6 +1373,11 @@ static inline unsigned int queue_max_sectors(const struct request_queue *q) return q->limits.max_sectors; } +static inline unsigned int queue_max_bytes(struct request_queue *q) +{ + return min_t(unsigned int, queue_max_sectors(q), INT_MAX >> 9) << 9; +} + static inline unsigned int queue_max_hw_sectors(const struct request_queue *q) { return q->limits.max_hw_sectors; -- cgit v1.2.3 From 78011042684dfbb50f7060f4623793f7a5c74a01 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 24 Jul 2021 09:20:23 +0200 Subject: scsi: bsg: Move bsg_scsi_ops to drivers/scsi/ Move the SCSI-specific bsg code in the SCSI midlayer instead of in the common bsg code. This just keeps the common bsg code block/ and also allows building it as a module. Link: https://lore.kernel.org/r/20210724072033.1284840-15-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- block/Kconfig | 23 ++---------- block/Makefile | 2 +- block/bsg.c | 95 +---------------------------------------------- drivers/scsi/Kconfig | 13 +++++++ drivers/scsi/Makefile | 1 + drivers/scsi/scsi_bsg.c | 95 +++++++++++++++++++++++++++++++++++++++++++++++ drivers/scsi/scsi_priv.h | 10 +++++ drivers/scsi/scsi_sysfs.c | 2 +- include/linux/blkdev.h | 2 +- include/linux/bsg.h | 11 ++---- 10 files changed, 129 insertions(+), 125 deletions(-) create mode 100644 drivers/scsi/scsi_bsg.c (limited to 'include/linux') diff --git a/block/Kconfig b/block/Kconfig index fd732aede922..88aa88241795 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -35,29 +35,12 @@ config BLK_SCSI_REQUEST config BLK_CGROUP_RWSTAT bool -config BLK_DEV_BSG - bool "Block layer SG support v4" - default y - select BLK_SCSI_REQUEST - help - Saying Y here will enable generic SG (SCSI generic) v4 support - for any block device. - - Unlike SG v3 (aka block/scsi_ioctl.c drivers/scsi/sg.c), SG v4 - can handle complicated SCSI commands: tagged variable length cdbs - with bidirectional data transfers and generic request/response - protocols (e.g. Task Management Functions and SMP in Serial - Attached SCSI). - - This option is required by recent UDEV versions to properly - access device serial numbers, etc. - - If unsure, say Y. +config BLK_DEV_BSG_COMMON + tristate config BLK_DEV_BSGLIB bool "Block layer SG support v4 helper lib" - select BLK_DEV_BSG - select BLK_SCSI_REQUEST + select BLK_DEV_BSG_COMMON help Subsystems will normally enable this if needed. Users will not normally need to manually enable this. diff --git a/block/Makefile b/block/Makefile index bfbe4e13ca1e..f37d532c8da5 100644 --- a/block/Makefile +++ b/block/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \ obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_SCSI_REQUEST) += scsi_ioctl.o -obj-$(CONFIG_BLK_DEV_BSG) += bsg.o +obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o obj-$(CONFIG_BLK_CGROUP_RWSTAT) += blk-cgroup-rwstat.o diff --git a/block/bsg.c b/block/bsg.c index df21df106d3b..3dbfd2c6aef3 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -15,9 +15,6 @@ #include #include -#include -#include -#include #include #define BSG_DESCRIPTION "Block layer SCSI generic (bsg) driver" @@ -54,86 +51,6 @@ static inline struct hlist_head *bsg_dev_idx_hash(int index) #define uptr64(val) ((void __user *)(uintptr_t)(val)) -static int bsg_scsi_check_proto(struct sg_io_v4 *hdr) -{ - if (hdr->protocol != BSG_PROTOCOL_SCSI || - hdr->subprotocol != BSG_SUB_PROTOCOL_SCSI_CMD) - return -EINVAL; - return 0; -} - -static int bsg_scsi_fill_hdr(struct request *rq, struct sg_io_v4 *hdr, - fmode_t mode) -{ - struct scsi_request *sreq = scsi_req(rq); - - if (hdr->dout_xfer_len && hdr->din_xfer_len) { - pr_warn_once("BIDI support in bsg has been removed.\n"); - return -EOPNOTSUPP; - } - - sreq->cmd_len = hdr->request_len; - if (sreq->cmd_len > BLK_MAX_CDB) { - sreq->cmd = kzalloc(sreq->cmd_len, GFP_KERNEL); - if (!sreq->cmd) - return -ENOMEM; - } - - if (copy_from_user(sreq->cmd, uptr64(hdr->request), sreq->cmd_len)) - return -EFAULT; - if (blk_verify_command(sreq->cmd, mode)) - return -EPERM; - return 0; -} - -static int bsg_scsi_complete_rq(struct request *rq, struct sg_io_v4 *hdr) -{ - struct scsi_request *sreq = scsi_req(rq); - int ret = 0; - - /* - * fill in all the output members - */ - hdr->device_status = sreq->result & 0xff; - hdr->transport_status = host_byte(sreq->result); - hdr->driver_status = 0; - if (scsi_status_is_check_condition(sreq->result)) - hdr->driver_status = DRIVER_SENSE; - hdr->info = 0; - if (hdr->device_status || hdr->transport_status || hdr->driver_status) - hdr->info |= SG_INFO_CHECK; - hdr->response_len = 0; - - if (sreq->sense_len && hdr->response) { - int len = min_t(unsigned int, hdr->max_response_len, - sreq->sense_len); - - if (copy_to_user(uptr64(hdr->response), sreq->sense, len)) - ret = -EFAULT; - else - hdr->response_len = len; - } - - if (rq_data_dir(rq) == READ) - hdr->din_resid = sreq->resid_len; - else - hdr->dout_resid = sreq->resid_len; - - return ret; -} - -static void bsg_scsi_free_rq(struct request *rq) -{ - scsi_req_free_cmd(scsi_req(rq)); -} - -static const struct bsg_ops bsg_scsi_ops = { - .check_proto = bsg_scsi_check_proto, - .fill_hdr = bsg_scsi_fill_hdr, - .complete_rq = bsg_scsi_complete_rq, - .free_rq = bsg_scsi_free_rq, -}; - static int bsg_sg_io(struct request_queue *q, fmode_t mode, void __user *uarg) { struct request *rq; @@ -487,17 +404,7 @@ unlock: mutex_unlock(&bsg_mutex); return ret; } - -int bsg_scsi_register_queue(struct request_queue *q, struct device *parent) -{ - if (!blk_queue_scsi_passthrough(q)) { - WARN_ONCE(true, "Attempt to register a non-SCSI queue\n"); - return -EINVAL; - } - - return bsg_register_queue(q, parent, dev_name(parent), &bsg_scsi_ops); -} -EXPORT_SYMBOL_GPL(bsg_scsi_register_queue); +EXPORT_SYMBOL_GPL(bsg_register_queue); static struct cdev bsg_cdev; diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 8f44d433e06e..86ecab196dfd 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -20,6 +20,7 @@ config SCSI select SCSI_DMA if HAS_DMA select SG_POOL select BLK_SCSI_REQUEST + select BLK_DEV_BSG_COMMON if BLK_DEV_BSG help If you want to use a SCSI hard disk, SCSI tape drive, SCSI CD-ROM or any other SCSI device under Linux, say Y and make sure that you know @@ -140,6 +141,18 @@ config CHR_DEV_SG If unsure, say N. +config BLK_DEV_BSG + bool "/dev/bsg support (SG v4)" + depends on SCSI + default y + help + Saying Y here will enable generic SG (SCSI generic) v4 support + for any SCSI device. + + This option is required by UDEV to access device serial numbers, etc. + + If unsure, say Y. + config CHR_DEV_SCH tristate "SCSI media changer support" depends on SCSI diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index 1748d1ec1338..240b831b5a11 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -168,6 +168,7 @@ scsi_mod-$(CONFIG_BLK_DEBUG_FS) += scsi_debugfs.o scsi_mod-y += scsi_trace.o scsi_logging.o scsi_mod-$(CONFIG_PM) += scsi_pm.o scsi_mod-$(CONFIG_SCSI_DH) += scsi_dh.o +scsi_mod-$(CONFIG_BLK_DEV_BSG) += scsi_bsg.o hv_storvsc-y := storvsc_drv.o diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c new file mode 100644 index 000000000000..3bdb28940460 --- /dev/null +++ b/drivers/scsi/scsi_bsg.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include "scsi_priv.h" + +#define uptr64(val) ((void __user *)(uintptr_t)(val)) + +static int scsi_bsg_check_proto(struct sg_io_v4 *hdr) +{ + if (hdr->protocol != BSG_PROTOCOL_SCSI || + hdr->subprotocol != BSG_SUB_PROTOCOL_SCSI_CMD) + return -EINVAL; + return 0; +} + +static int scsi_bsg_fill_hdr(struct request *rq, struct sg_io_v4 *hdr, + fmode_t mode) +{ + struct scsi_request *sreq = scsi_req(rq); + + if (hdr->dout_xfer_len && hdr->din_xfer_len) { + pr_warn_once("BIDI support in bsg has been removed.\n"); + return -EOPNOTSUPP; + } + + sreq->cmd_len = hdr->request_len; + if (sreq->cmd_len > BLK_MAX_CDB) { + sreq->cmd = kzalloc(sreq->cmd_len, GFP_KERNEL); + if (!sreq->cmd) + return -ENOMEM; + } + + if (copy_from_user(sreq->cmd, uptr64(hdr->request), sreq->cmd_len)) + return -EFAULT; + if (blk_verify_command(sreq->cmd, mode)) + return -EPERM; + return 0; +} + +static int scsi_bsg_complete_rq(struct request *rq, struct sg_io_v4 *hdr) +{ + struct scsi_request *sreq = scsi_req(rq); + int ret = 0; + + /* + * fill in all the output members + */ + hdr->device_status = sreq->result & 0xff; + hdr->transport_status = host_byte(sreq->result); + hdr->driver_status = 0; + if (scsi_status_is_check_condition(sreq->result)) + hdr->driver_status = DRIVER_SENSE; + hdr->info = 0; + if (hdr->device_status || hdr->transport_status || hdr->driver_status) + hdr->info |= SG_INFO_CHECK; + hdr->response_len = 0; + + if (sreq->sense_len && hdr->response) { + int len = min_t(unsigned int, hdr->max_response_len, + sreq->sense_len); + + if (copy_to_user(uptr64(hdr->response), sreq->sense, len)) + ret = -EFAULT; + else + hdr->response_len = len; + } + + if (rq_data_dir(rq) == READ) + hdr->din_resid = sreq->resid_len; + else + hdr->dout_resid = sreq->resid_len; + + return ret; +} + +static void scsi_bsg_free_rq(struct request *rq) +{ + scsi_req_free_cmd(scsi_req(rq)); +} + +static const struct bsg_ops scsi_bsg_ops = { + .check_proto = scsi_bsg_check_proto, + .fill_hdr = scsi_bsg_fill_hdr, + .complete_rq = scsi_bsg_complete_rq, + .free_rq = scsi_bsg_free_rq, +}; + +int scsi_bsg_register_queue(struct request_queue *q, struct device *parent) +{ + return bsg_register_queue(q, parent, dev_name(parent), &scsi_bsg_ops); +} diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index eae2235f79b5..0a0db35bab04 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -180,6 +180,16 @@ static inline void scsi_dh_add_device(struct scsi_device *sdev) { } static inline void scsi_dh_release_device(struct scsi_device *sdev) { } #endif +#ifdef CONFIG_BLK_DEV_BSG +int scsi_bsg_register_queue(struct request_queue *q, struct device *parent); +#else +static inline int scsi_bsg_register_queue(struct request_queue *q, + struct device *parent) +{ + return 0; +} +#endif + extern int scsi_device_max_queue_depth(struct scsi_device *sdev); /* diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 32489d25158f..4ff9ac3296d8 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1366,7 +1366,7 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) transport_add_device(&sdev->sdev_gendev); sdev->is_visible = 1; - error = bsg_scsi_register_queue(rq, &sdev->sdev_gendev); + error = scsi_bsg_register_queue(rq, &sdev->sdev_gendev); if (error) /* we're treating error on bsg register as non-fatal, * so pretend nothing went wrong */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9971796819ef..d36b67bd7267 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -537,7 +537,7 @@ struct request_queue { int mq_freeze_depth; -#if defined(CONFIG_BLK_DEV_BSG) +#if IS_ENABLED(CONFIG_BLK_DEV_BSG_COMMON) struct bsg_class_device bsg_dev; #endif diff --git a/include/linux/bsg.h b/include/linux/bsg.h index dac37b6e00ec..b887da20bd41 100644 --- a/include/linux/bsg.h +++ b/include/linux/bsg.h @@ -5,8 +5,9 @@ #include struct request; +struct request_queue; -#ifdef CONFIG_BLK_DEV_BSG +#ifdef CONFIG_BLK_DEV_BSG_COMMON struct bsg_ops { int (*check_proto)(struct sg_io_v4 *hdr); int (*fill_hdr)(struct request *rq, struct sg_io_v4 *hdr, @@ -24,16 +25,10 @@ struct bsg_class_device { int bsg_register_queue(struct request_queue *q, struct device *parent, const char *name, const struct bsg_ops *ops); -int bsg_scsi_register_queue(struct request_queue *q, struct device *parent); void bsg_unregister_queue(struct request_queue *q); #else -static inline int bsg_scsi_register_queue(struct request_queue *q, - struct device *parent) -{ - return 0; -} static inline void bsg_unregister_queue(struct request_queue *q) { } -#endif /* CONFIG_BLK_DEV_BSG */ +#endif /* CONFIG_BLK_DEV_BSG_COMMON */ #endif /* _LINUX_BSG_H */ -- cgit v1.2.3 From 7353dc06c9a8e37c80da7ff986e6ef5123bec8ce Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 24 Jul 2021 09:20:26 +0200 Subject: scsi: scsi_ioctl: Simplify SCSI passthrough permission checking Remove the separate command filter structure and just use a switch statement (which also cought two duplicate commands), return a bool and give the function a sensible name. Link: https://lore.kernel.org/r/20210724072033.1284840-18-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- block/scsi_ioctl.c | 219 ++++++++++++++++++++++-------------------------- drivers/scsi/scsi_bsg.c | 2 +- drivers/scsi/sg.c | 5 +- include/linux/blkdev.h | 2 +- 4 files changed, 104 insertions(+), 124 deletions(-) (limited to 'include/linux') diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 4d023f2f43f0..3642e145108a 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -22,13 +22,6 @@ #include #include -struct blk_cmd_filter { - unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; - unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; -}; - -static struct blk_cmd_filter blk_default_cmd_filter; - static int sg_get_version(int __user *p) { static const int sg_version_num = 30527; @@ -80,115 +73,108 @@ static int sg_emulated_host(struct request_queue *q, int __user *p) return put_user(1, p); } -static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter) -{ - /* Basic read-only commands */ - __set_bit(TEST_UNIT_READY, filter->read_ok); - __set_bit(REQUEST_SENSE, filter->read_ok); - __set_bit(READ_6, filter->read_ok); - __set_bit(READ_10, filter->read_ok); - __set_bit(READ_12, filter->read_ok); - __set_bit(READ_16, filter->read_ok); - __set_bit(READ_BUFFER, filter->read_ok); - __set_bit(READ_DEFECT_DATA, filter->read_ok); - __set_bit(READ_CAPACITY, filter->read_ok); - __set_bit(READ_LONG, filter->read_ok); - __set_bit(INQUIRY, filter->read_ok); - __set_bit(MODE_SENSE, filter->read_ok); - __set_bit(MODE_SENSE_10, filter->read_ok); - __set_bit(LOG_SENSE, filter->read_ok); - __set_bit(START_STOP, filter->read_ok); - __set_bit(GPCMD_VERIFY_10, filter->read_ok); - __set_bit(VERIFY_16, filter->read_ok); - __set_bit(REPORT_LUNS, filter->read_ok); - __set_bit(SERVICE_ACTION_IN_16, filter->read_ok); - __set_bit(RECEIVE_DIAGNOSTIC, filter->read_ok); - __set_bit(MAINTENANCE_IN, filter->read_ok); - __set_bit(GPCMD_READ_BUFFER_CAPACITY, filter->read_ok); - - /* Audio CD commands */ - __set_bit(GPCMD_PLAY_CD, filter->read_ok); - __set_bit(GPCMD_PLAY_AUDIO_10, filter->read_ok); - __set_bit(GPCMD_PLAY_AUDIO_MSF, filter->read_ok); - __set_bit(GPCMD_PLAY_AUDIO_TI, filter->read_ok); - __set_bit(GPCMD_PAUSE_RESUME, filter->read_ok); - - /* CD/DVD data reading */ - __set_bit(GPCMD_READ_CD, filter->read_ok); - __set_bit(GPCMD_READ_CD_MSF, filter->read_ok); - __set_bit(GPCMD_READ_DISC_INFO, filter->read_ok); - __set_bit(GPCMD_READ_CDVD_CAPACITY, filter->read_ok); - __set_bit(GPCMD_READ_DVD_STRUCTURE, filter->read_ok); - __set_bit(GPCMD_READ_HEADER, filter->read_ok); - __set_bit(GPCMD_READ_TRACK_RZONE_INFO, filter->read_ok); - __set_bit(GPCMD_READ_SUBCHANNEL, filter->read_ok); - __set_bit(GPCMD_READ_TOC_PMA_ATIP, filter->read_ok); - __set_bit(GPCMD_REPORT_KEY, filter->read_ok); - __set_bit(GPCMD_SCAN, filter->read_ok); - __set_bit(GPCMD_GET_CONFIGURATION, filter->read_ok); - __set_bit(GPCMD_READ_FORMAT_CAPACITIES, filter->read_ok); - __set_bit(GPCMD_GET_EVENT_STATUS_NOTIFICATION, filter->read_ok); - __set_bit(GPCMD_GET_PERFORMANCE, filter->read_ok); - __set_bit(GPCMD_SEEK, filter->read_ok); - __set_bit(GPCMD_STOP_PLAY_SCAN, filter->read_ok); - - /* Basic writing commands */ - __set_bit(WRITE_6, filter->write_ok); - __set_bit(WRITE_10, filter->write_ok); - __set_bit(WRITE_VERIFY, filter->write_ok); - __set_bit(WRITE_12, filter->write_ok); - __set_bit(WRITE_VERIFY_12, filter->write_ok); - __set_bit(WRITE_16, filter->write_ok); - __set_bit(WRITE_LONG, filter->write_ok); - __set_bit(WRITE_LONG_2, filter->write_ok); - __set_bit(WRITE_SAME, filter->write_ok); - __set_bit(WRITE_SAME_16, filter->write_ok); - __set_bit(WRITE_SAME_32, filter->write_ok); - __set_bit(ERASE, filter->write_ok); - __set_bit(GPCMD_MODE_SELECT_10, filter->write_ok); - __set_bit(MODE_SELECT, filter->write_ok); - __set_bit(LOG_SELECT, filter->write_ok); - __set_bit(GPCMD_BLANK, filter->write_ok); - __set_bit(GPCMD_CLOSE_TRACK, filter->write_ok); - __set_bit(GPCMD_FLUSH_CACHE, filter->write_ok); - __set_bit(GPCMD_FORMAT_UNIT, filter->write_ok); - __set_bit(GPCMD_REPAIR_RZONE_TRACK, filter->write_ok); - __set_bit(GPCMD_RESERVE_RZONE_TRACK, filter->write_ok); - __set_bit(GPCMD_SEND_DVD_STRUCTURE, filter->write_ok); - __set_bit(GPCMD_SEND_EVENT, filter->write_ok); - __set_bit(GPCMD_SEND_KEY, filter->write_ok); - __set_bit(GPCMD_SEND_OPC, filter->write_ok); - __set_bit(GPCMD_SEND_CUE_SHEET, filter->write_ok); - __set_bit(GPCMD_SET_SPEED, filter->write_ok); - __set_bit(GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL, filter->write_ok); - __set_bit(GPCMD_LOAD_UNLOAD, filter->write_ok); - __set_bit(GPCMD_SET_STREAMING, filter->write_ok); - __set_bit(GPCMD_SET_READ_AHEAD, filter->write_ok); - - /* ZBC Commands */ - __set_bit(ZBC_OUT, filter->write_ok); - __set_bit(ZBC_IN, filter->read_ok); -} - -int blk_verify_command(unsigned char *cmd, fmode_t mode) +/* + * Check if the given command is allowed. + * + * For unprivileged users only a small set of whitelisted command is allowed so + * that they can't format the drive or update the firmware. + */ +bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode) { - struct blk_cmd_filter *filter = &blk_default_cmd_filter; - /* root can do any command. */ if (capable(CAP_SYS_RAWIO)) - return 0; + return true; /* Anybody who can open the device can do a read-safe command */ - if (test_bit(cmd[0], filter->read_ok)) - return 0; - - /* Write-safe commands require a writable open */ - if (test_bit(cmd[0], filter->write_ok) && (mode & FMODE_WRITE)) - return 0; - - return -EPERM; + switch (cmd[0]) { + /* Basic read-only commands */ + case TEST_UNIT_READY: + case REQUEST_SENSE: + case READ_6: + case READ_10: + case READ_12: + case READ_16: + case READ_BUFFER: + case READ_DEFECT_DATA: + case READ_CAPACITY: /* also GPCMD_READ_CDVD_CAPACITY */ + case READ_LONG: + case INQUIRY: + case MODE_SENSE: + case MODE_SENSE_10: + case LOG_SENSE: + case START_STOP: + case GPCMD_VERIFY_10: + case VERIFY_16: + case REPORT_LUNS: + case SERVICE_ACTION_IN_16: + case RECEIVE_DIAGNOSTIC: + case MAINTENANCE_IN: /* also GPCMD_SEND_KEY, which is a write command */ + case GPCMD_READ_BUFFER_CAPACITY: + /* Audio CD commands */ + case GPCMD_PLAY_CD: + case GPCMD_PLAY_AUDIO_10: + case GPCMD_PLAY_AUDIO_MSF: + case GPCMD_PLAY_AUDIO_TI: + case GPCMD_PAUSE_RESUME: + /* CD/DVD data reading */ + case GPCMD_READ_CD: + case GPCMD_READ_CD_MSF: + case GPCMD_READ_DISC_INFO: + case GPCMD_READ_DVD_STRUCTURE: + case GPCMD_READ_HEADER: + case GPCMD_READ_TRACK_RZONE_INFO: + case GPCMD_READ_SUBCHANNEL: + case GPCMD_READ_TOC_PMA_ATIP: + case GPCMD_REPORT_KEY: + case GPCMD_SCAN: + case GPCMD_GET_CONFIGURATION: + case GPCMD_READ_FORMAT_CAPACITIES: + case GPCMD_GET_EVENT_STATUS_NOTIFICATION: + case GPCMD_GET_PERFORMANCE: + case GPCMD_SEEK: + case GPCMD_STOP_PLAY_SCAN: + /* ZBC */ + case ZBC_IN: + return true; + /* Basic writing commands */ + case WRITE_6: + case WRITE_10: + case WRITE_VERIFY: + case WRITE_12: + case WRITE_VERIFY_12: + case WRITE_16: + case WRITE_LONG: + case WRITE_LONG_2: + case WRITE_SAME: + case WRITE_SAME_16: + case WRITE_SAME_32: + case ERASE: + case GPCMD_MODE_SELECT_10: + case MODE_SELECT: + case LOG_SELECT: + case GPCMD_BLANK: + case GPCMD_CLOSE_TRACK: + case GPCMD_FLUSH_CACHE: + case GPCMD_FORMAT_UNIT: + case GPCMD_REPAIR_RZONE_TRACK: + case GPCMD_RESERVE_RZONE_TRACK: + case GPCMD_SEND_DVD_STRUCTURE: + case GPCMD_SEND_EVENT: + case GPCMD_SEND_OPC: + case GPCMD_SEND_CUE_SHEET: + case GPCMD_SET_SPEED: + case GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL: + case GPCMD_LOAD_UNLOAD: + case GPCMD_SET_STREAMING: + case GPCMD_SET_READ_AHEAD: + /* ZBC */ + case ZBC_OUT: + return (mode & FMODE_WRITE); + default: + return false; + } } -EXPORT_SYMBOL(blk_verify_command); +EXPORT_SYMBOL(scsi_cmd_allowed); static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq, struct sg_io_hdr *hdr, fmode_t mode) @@ -197,7 +183,7 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq, if (copy_from_user(req->cmd, hdr->cmdp, hdr->cmd_len)) return -EFAULT; - if (blk_verify_command(req->cmd, mode)) + if (!scsi_cmd_allowed(req->cmd, mode)) return -EPERM; /* @@ -428,8 +414,8 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len)) goto error; - err = blk_verify_command(req->cmd, mode); - if (err) + err = -EPERM; + if (!scsi_cmd_allowed(req->cmd, mode)) goto error; /* default. possible overriden later */ @@ -808,10 +794,3 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod return err; } EXPORT_SYMBOL(scsi_cmd_ioctl); - -static int __init blk_scsi_ioctl_init(void) -{ - blk_set_cmd_filter_defaults(&blk_default_cmd_filter); - return 0; -} -fs_initcall(blk_scsi_ioctl_init); diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c index 3bdb28940460..68f60316adf1 100644 --- a/drivers/scsi/scsi_bsg.c +++ b/drivers/scsi/scsi_bsg.c @@ -36,7 +36,7 @@ static int scsi_bsg_fill_hdr(struct request *rq, struct sg_io_v4 *hdr, if (copy_from_user(sreq->cmd, uptr64(hdr->request), sreq->cmd_len)) return -EFAULT; - if (blk_verify_command(sreq->cmd, mode)) + if (!scsi_cmd_allowed(sreq->cmd, mode)) return -EPERM; return 0; } diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 6cb1e4b6eac2..c86fa4476334 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -238,8 +238,9 @@ static int sg_allow_access(struct file *filp, unsigned char *cmd) if (sfp->parentdp->device->type == TYPE_SCANNER) return 0; - - return blk_verify_command(cmd, filp->f_mode); + if (!scsi_cmd_allowed(cmd, filp->f_mode)) + return -EPERM; + return 0; } static int diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d36b67bd7267..e28679e63373 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1343,7 +1343,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, gfp_mask, 0); } -extern int blk_verify_command(unsigned char *cmd, fmode_t mode); +bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode); static inline bool bdev_is_partition(struct block_device *bdev) { -- cgit v1.2.3 From f2542a3be3277a65c766fa6e86b930d3d839f79e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 24 Jul 2021 09:20:27 +0200 Subject: scsi: scsi_ioctl: Move the "block layer" SCSI ioctl handling to drivers/scsi Merge the ioctl handling in block/scsi_ioctl.c into its only caller in drivers/scsi/scsi_ioctl.c. Link: https://lore.kernel.org/r/20210724072033.1284840-19-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- block/Makefile | 1 - block/scsi_ioctl.c | 796 ---------------------------------------------- drivers/scsi/scsi_ioctl.c | 740 +++++++++++++++++++++++++++++++++++++++++- include/linux/blkdev.h | 11 - include/scsi/scsi_ioctl.h | 6 + 5 files changed, 741 insertions(+), 813 deletions(-) delete mode 100644 block/scsi_ioctl.c (limited to 'include/linux') diff --git a/block/Makefile b/block/Makefile index f37d532c8da5..640afba070fd 100644 --- a/block/Makefile +++ b/block/Makefile @@ -12,7 +12,6 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \ disk-events.o obj-$(CONFIG_BOUNCE) += bounce.o -obj-$(CONFIG_BLK_SCSI_REQUEST) += scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c deleted file mode 100644 index 3642e145108a..000000000000 --- a/block/scsi_ioctl.c +++ /dev/null @@ -1,796 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2001 Jens Axboe - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -static int sg_get_version(int __user *p) -{ - static const int sg_version_num = 30527; - return put_user(sg_version_num, p); -} - -static int sg_get_timeout(struct request_queue *q) -{ - return jiffies_to_clock_t(q->sg_timeout); -} - -static int sg_set_timeout(struct request_queue *q, int __user *p) -{ - int timeout, err = get_user(timeout, p); - - if (!err) - q->sg_timeout = clock_t_to_jiffies(timeout); - - return err; -} - -static int sg_get_reserved_size(struct request_queue *q, int __user *p) -{ - int val = min(q->sg_reserved_size, queue_max_bytes(q)); - - return put_user(val, p); -} - -static int sg_set_reserved_size(struct request_queue *q, int __user *p) -{ - int size, err = get_user(size, p); - - if (err) - return err; - - if (size < 0) - return -EINVAL; - - q->sg_reserved_size = min_t(unsigned int, size, queue_max_bytes(q)); - return 0; -} - -/* - * will always return that we are ATAPI even for a real SCSI drive, I'm not - * so sure this is worth doing anything about (why would you care??) - */ -static int sg_emulated_host(struct request_queue *q, int __user *p) -{ - return put_user(1, p); -} - -/* - * Check if the given command is allowed. - * - * For unprivileged users only a small set of whitelisted command is allowed so - * that they can't format the drive or update the firmware. - */ -bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode) -{ - /* root can do any command. */ - if (capable(CAP_SYS_RAWIO)) - return true; - - /* Anybody who can open the device can do a read-safe command */ - switch (cmd[0]) { - /* Basic read-only commands */ - case TEST_UNIT_READY: - case REQUEST_SENSE: - case READ_6: - case READ_10: - case READ_12: - case READ_16: - case READ_BUFFER: - case READ_DEFECT_DATA: - case READ_CAPACITY: /* also GPCMD_READ_CDVD_CAPACITY */ - case READ_LONG: - case INQUIRY: - case MODE_SENSE: - case MODE_SENSE_10: - case LOG_SENSE: - case START_STOP: - case GPCMD_VERIFY_10: - case VERIFY_16: - case REPORT_LUNS: - case SERVICE_ACTION_IN_16: - case RECEIVE_DIAGNOSTIC: - case MAINTENANCE_IN: /* also GPCMD_SEND_KEY, which is a write command */ - case GPCMD_READ_BUFFER_CAPACITY: - /* Audio CD commands */ - case GPCMD_PLAY_CD: - case GPCMD_PLAY_AUDIO_10: - case GPCMD_PLAY_AUDIO_MSF: - case GPCMD_PLAY_AUDIO_TI: - case GPCMD_PAUSE_RESUME: - /* CD/DVD data reading */ - case GPCMD_READ_CD: - case GPCMD_READ_CD_MSF: - case GPCMD_READ_DISC_INFO: - case GPCMD_READ_DVD_STRUCTURE: - case GPCMD_READ_HEADER: - case GPCMD_READ_TRACK_RZONE_INFO: - case GPCMD_READ_SUBCHANNEL: - case GPCMD_READ_TOC_PMA_ATIP: - case GPCMD_REPORT_KEY: - case GPCMD_SCAN: - case GPCMD_GET_CONFIGURATION: - case GPCMD_READ_FORMAT_CAPACITIES: - case GPCMD_GET_EVENT_STATUS_NOTIFICATION: - case GPCMD_GET_PERFORMANCE: - case GPCMD_SEEK: - case GPCMD_STOP_PLAY_SCAN: - /* ZBC */ - case ZBC_IN: - return true; - /* Basic writing commands */ - case WRITE_6: - case WRITE_10: - case WRITE_VERIFY: - case WRITE_12: - case WRITE_VERIFY_12: - case WRITE_16: - case WRITE_LONG: - case WRITE_LONG_2: - case WRITE_SAME: - case WRITE_SAME_16: - case WRITE_SAME_32: - case ERASE: - case GPCMD_MODE_SELECT_10: - case MODE_SELECT: - case LOG_SELECT: - case GPCMD_BLANK: - case GPCMD_CLOSE_TRACK: - case GPCMD_FLUSH_CACHE: - case GPCMD_FORMAT_UNIT: - case GPCMD_REPAIR_RZONE_TRACK: - case GPCMD_RESERVE_RZONE_TRACK: - case GPCMD_SEND_DVD_STRUCTURE: - case GPCMD_SEND_EVENT: - case GPCMD_SEND_OPC: - case GPCMD_SEND_CUE_SHEET: - case GPCMD_SET_SPEED: - case GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL: - case GPCMD_LOAD_UNLOAD: - case GPCMD_SET_STREAMING: - case GPCMD_SET_READ_AHEAD: - /* ZBC */ - case ZBC_OUT: - return (mode & FMODE_WRITE); - default: - return false; - } -} -EXPORT_SYMBOL(scsi_cmd_allowed); - -static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq, - struct sg_io_hdr *hdr, fmode_t mode) -{ - struct scsi_request *req = scsi_req(rq); - - if (copy_from_user(req->cmd, hdr->cmdp, hdr->cmd_len)) - return -EFAULT; - if (!scsi_cmd_allowed(req->cmd, mode)) - return -EPERM; - - /* - * fill in request structure - */ - req->cmd_len = hdr->cmd_len; - - rq->timeout = msecs_to_jiffies(hdr->timeout); - if (!rq->timeout) - rq->timeout = q->sg_timeout; - if (!rq->timeout) - rq->timeout = BLK_DEFAULT_SG_TIMEOUT; - if (rq->timeout < BLK_MIN_SG_TIMEOUT) - rq->timeout = BLK_MIN_SG_TIMEOUT; - - return 0; -} - -static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr, - struct bio *bio) -{ - struct scsi_request *req = scsi_req(rq); - int r, ret = 0; - - /* - * fill in all the output members - */ - hdr->status = req->result & 0xff; - hdr->masked_status = status_byte(req->result); - hdr->msg_status = COMMAND_COMPLETE; - hdr->host_status = host_byte(req->result); - hdr->driver_status = 0; - if (scsi_status_is_check_condition(hdr->status)) - hdr->driver_status = DRIVER_SENSE; - hdr->info = 0; - if (hdr->masked_status || hdr->host_status || hdr->driver_status) - hdr->info |= SG_INFO_CHECK; - hdr->resid = req->resid_len; - hdr->sb_len_wr = 0; - - if (req->sense_len && hdr->sbp) { - int len = min((unsigned int) hdr->mx_sb_len, req->sense_len); - - if (!copy_to_user(hdr->sbp, req->sense, len)) - hdr->sb_len_wr = len; - else - ret = -EFAULT; - } - - r = blk_rq_unmap_user(bio); - if (!ret) - ret = r; - - return ret; -} - -static int sg_io(struct request_queue *q, struct gendisk *bd_disk, - struct sg_io_hdr *hdr, fmode_t mode) -{ - unsigned long start_time; - ssize_t ret = 0; - int writing = 0; - int at_head = 0; - struct request *rq; - struct scsi_request *req; - struct bio *bio; - - if (hdr->interface_id != 'S') - return -EINVAL; - - if (hdr->dxfer_len > (queue_max_hw_sectors(q) << 9)) - return -EIO; - - if (hdr->dxfer_len) - switch (hdr->dxfer_direction) { - default: - return -EINVAL; - case SG_DXFER_TO_DEV: - writing = 1; - break; - case SG_DXFER_TO_FROM_DEV: - case SG_DXFER_FROM_DEV: - break; - } - if (hdr->flags & SG_FLAG_Q_AT_HEAD) - at_head = 1; - - ret = -ENOMEM; - rq = blk_get_request(q, writing ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); - if (IS_ERR(rq)) - return PTR_ERR(rq); - req = scsi_req(rq); - - if (hdr->cmd_len > BLK_MAX_CDB) { - req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL); - if (!req->cmd) - goto out_put_request; - } - - ret = blk_fill_sghdr_rq(q, rq, hdr, mode); - if (ret < 0) - goto out_free_cdb; - - ret = 0; - if (hdr->iovec_count) { - struct iov_iter i; - struct iovec *iov = NULL; - - ret = import_iovec(rq_data_dir(rq), hdr->dxferp, - hdr->iovec_count, 0, &iov, &i); - if (ret < 0) - goto out_free_cdb; - - /* SG_IO howto says that the shorter of the two wins */ - iov_iter_truncate(&i, hdr->dxfer_len); - - ret = blk_rq_map_user_iov(q, rq, NULL, &i, GFP_KERNEL); - kfree(iov); - } else if (hdr->dxfer_len) - ret = blk_rq_map_user(q, rq, NULL, hdr->dxferp, hdr->dxfer_len, - GFP_KERNEL); - - if (ret) - goto out_free_cdb; - - bio = rq->bio; - req->retries = 0; - - start_time = jiffies; - - blk_execute_rq(bd_disk, rq, at_head); - - hdr->duration = jiffies_to_msecs(jiffies - start_time); - - ret = blk_complete_sghdr_rq(rq, hdr, bio); - -out_free_cdb: - scsi_req_free_cmd(req); -out_put_request: - blk_put_request(rq); - return ret; -} - -/** - * sg_scsi_ioctl -- handle deprecated SCSI_IOCTL_SEND_COMMAND ioctl - * @q: request queue to send scsi commands down - * @disk: gendisk to operate on (option) - * @mode: mode used to open the file through which the ioctl has been - * submitted - * @sic: userspace structure describing the command to perform - * - * Send down the scsi command described by @sic to the device below - * the request queue @q. If @file is non-NULL it's used to perform - * fine-grained permission checks that allow users to send down - * non-destructive SCSI commands. If the caller has a struct gendisk - * available it should be passed in as @disk to allow the low level - * driver to use the information contained in it. A non-NULL @disk - * is only allowed if the caller knows that the low level driver doesn't - * need it (e.g. in the scsi subsystem). - * - * Notes: - * - This interface is deprecated - users should use the SG_IO - * interface instead, as this is a more flexible approach to - * performing SCSI commands on a device. - * - The SCSI command length is determined by examining the 1st byte - * of the given command. There is no way to override this. - * - Data transfers are limited to PAGE_SIZE - * - The length (x + y) must be at least OMAX_SB_LEN bytes long to - * accommodate the sense buffer when an error occurs. - * The sense buffer is truncated to OMAX_SB_LEN (16) bytes so that - * old code will not be surprised. - * - If a Unix error occurs (e.g. ENOMEM) then the user will receive - * a negative return and the Unix error code in 'errno'. - * If the SCSI command succeeds then 0 is returned. - * Positive numbers returned are the compacted SCSI error codes (4 - * bytes in one int) where the lowest byte is the SCSI status. - */ -int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, - struct scsi_ioctl_command __user *sic) -{ - enum { OMAX_SB_LEN = 16 }; /* For backward compatibility */ - struct request *rq; - struct scsi_request *req; - int err; - unsigned int in_len, out_len, bytes, opcode, cmdlen; - char *buffer = NULL; - - if (!sic) - return -EINVAL; - - /* - * get in an out lengths, verify they don't exceed a page worth of data - */ - if (get_user(in_len, &sic->inlen)) - return -EFAULT; - if (get_user(out_len, &sic->outlen)) - return -EFAULT; - if (in_len > PAGE_SIZE || out_len > PAGE_SIZE) - return -EINVAL; - if (get_user(opcode, sic->data)) - return -EFAULT; - - bytes = max(in_len, out_len); - if (bytes) { - buffer = kzalloc(bytes, GFP_NOIO | GFP_USER | __GFP_NOWARN); - if (!buffer) - return -ENOMEM; - - } - - rq = blk_get_request(q, in_len ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); - if (IS_ERR(rq)) { - err = PTR_ERR(rq); - goto error_free_buffer; - } - req = scsi_req(rq); - - cmdlen = COMMAND_SIZE(opcode); - - /* - * get command and data to send to device, if any - */ - err = -EFAULT; - req->cmd_len = cmdlen; - if (copy_from_user(req->cmd, sic->data, cmdlen)) - goto error; - - if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len)) - goto error; - - err = -EPERM; - if (!scsi_cmd_allowed(req->cmd, mode)) - goto error; - - /* default. possible overriden later */ - req->retries = 5; - - switch (opcode) { - case SEND_DIAGNOSTIC: - case FORMAT_UNIT: - rq->timeout = FORMAT_UNIT_TIMEOUT; - req->retries = 1; - break; - case START_STOP: - rq->timeout = START_STOP_TIMEOUT; - break; - case MOVE_MEDIUM: - rq->timeout = MOVE_MEDIUM_TIMEOUT; - break; - case READ_ELEMENT_STATUS: - rq->timeout = READ_ELEMENT_STATUS_TIMEOUT; - break; - case READ_DEFECT_DATA: - rq->timeout = READ_DEFECT_DATA_TIMEOUT; - req->retries = 1; - break; - default: - rq->timeout = BLK_DEFAULT_SG_TIMEOUT; - break; - } - - if (bytes) { - err = blk_rq_map_kern(q, rq, buffer, bytes, GFP_NOIO); - if (err) - goto error; - } - - blk_execute_rq(disk, rq, 0); - - err = req->result & 0xff; /* only 8 bit SCSI status */ - if (err) { - if (req->sense_len && req->sense) { - bytes = (OMAX_SB_LEN > req->sense_len) ? - req->sense_len : OMAX_SB_LEN; - if (copy_to_user(sic->data, req->sense, bytes)) - err = -EFAULT; - } - } else { - if (copy_to_user(sic->data, buffer, out_len)) - err = -EFAULT; - } - -error: - blk_put_request(rq); - -error_free_buffer: - kfree(buffer); - - return err; -} -EXPORT_SYMBOL_GPL(sg_scsi_ioctl); - -/* Send basic block requests */ -static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk, - int cmd, int data) -{ - struct request *rq; - int err; - - rq = blk_get_request(q, REQ_OP_DRV_OUT, 0); - if (IS_ERR(rq)) - return PTR_ERR(rq); - rq->timeout = BLK_DEFAULT_SG_TIMEOUT; - scsi_req(rq)->cmd[0] = cmd; - scsi_req(rq)->cmd[4] = data; - scsi_req(rq)->cmd_len = 6; - blk_execute_rq(bd_disk, rq, 0); - err = scsi_req(rq)->result ? -EIO : 0; - blk_put_request(rq); - - return err; -} - -static inline int blk_send_start_stop(struct request_queue *q, - struct gendisk *bd_disk, int data) -{ - return __blk_send_generic(q, bd_disk, GPCMD_START_STOP_UNIT, data); -} - -int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp) -{ -#ifdef CONFIG_COMPAT - if (in_compat_syscall()) { - struct compat_sg_io_hdr hdr32 = { - .interface_id = hdr->interface_id, - .dxfer_direction = hdr->dxfer_direction, - .cmd_len = hdr->cmd_len, - .mx_sb_len = hdr->mx_sb_len, - .iovec_count = hdr->iovec_count, - .dxfer_len = hdr->dxfer_len, - .dxferp = (uintptr_t)hdr->dxferp, - .cmdp = (uintptr_t)hdr->cmdp, - .sbp = (uintptr_t)hdr->sbp, - .timeout = hdr->timeout, - .flags = hdr->flags, - .pack_id = hdr->pack_id, - .usr_ptr = (uintptr_t)hdr->usr_ptr, - .status = hdr->status, - .masked_status = hdr->masked_status, - .msg_status = hdr->msg_status, - .sb_len_wr = hdr->sb_len_wr, - .host_status = hdr->host_status, - .driver_status = hdr->driver_status, - .resid = hdr->resid, - .duration = hdr->duration, - .info = hdr->info, - }; - - if (copy_to_user(argp, &hdr32, sizeof(hdr32))) - return -EFAULT; - - return 0; - } -#endif - - if (copy_to_user(argp, hdr, sizeof(*hdr))) - return -EFAULT; - - return 0; -} -EXPORT_SYMBOL(put_sg_io_hdr); - -int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp) -{ -#ifdef CONFIG_COMPAT - struct compat_sg_io_hdr hdr32; - - if (in_compat_syscall()) { - if (copy_from_user(&hdr32, argp, sizeof(hdr32))) - return -EFAULT; - - *hdr = (struct sg_io_hdr) { - .interface_id = hdr32.interface_id, - .dxfer_direction = hdr32.dxfer_direction, - .cmd_len = hdr32.cmd_len, - .mx_sb_len = hdr32.mx_sb_len, - .iovec_count = hdr32.iovec_count, - .dxfer_len = hdr32.dxfer_len, - .dxferp = compat_ptr(hdr32.dxferp), - .cmdp = compat_ptr(hdr32.cmdp), - .sbp = compat_ptr(hdr32.sbp), - .timeout = hdr32.timeout, - .flags = hdr32.flags, - .pack_id = hdr32.pack_id, - .usr_ptr = compat_ptr(hdr32.usr_ptr), - .status = hdr32.status, - .masked_status = hdr32.masked_status, - .msg_status = hdr32.msg_status, - .sb_len_wr = hdr32.sb_len_wr, - .host_status = hdr32.host_status, - .driver_status = hdr32.driver_status, - .resid = hdr32.resid, - .duration = hdr32.duration, - .info = hdr32.info, - }; - - return 0; - } -#endif - - if (copy_from_user(hdr, argp, sizeof(*hdr))) - return -EFAULT; - - return 0; -} -EXPORT_SYMBOL(get_sg_io_hdr); - -#ifdef CONFIG_COMPAT -struct compat_cdrom_generic_command { - unsigned char cmd[CDROM_PACKET_SIZE]; - compat_caddr_t buffer; - compat_uint_t buflen; - compat_int_t stat; - compat_caddr_t sense; - unsigned char data_direction; - unsigned char pad[3]; - compat_int_t quiet; - compat_int_t timeout; - compat_caddr_t unused; -}; -#endif - -static int scsi_get_cdrom_generic_arg(struct cdrom_generic_command *cgc, - const void __user *arg) -{ -#ifdef CONFIG_COMPAT - if (in_compat_syscall()) { - struct compat_cdrom_generic_command cgc32; - - if (copy_from_user(&cgc32, arg, sizeof(cgc32))) - return -EFAULT; - - *cgc = (struct cdrom_generic_command) { - .buffer = compat_ptr(cgc32.buffer), - .buflen = cgc32.buflen, - .stat = cgc32.stat, - .sense = compat_ptr(cgc32.sense), - .data_direction = cgc32.data_direction, - .quiet = cgc32.quiet, - .timeout = cgc32.timeout, - .unused = compat_ptr(cgc32.unused), - }; - memcpy(&cgc->cmd, &cgc32.cmd, CDROM_PACKET_SIZE); - return 0; - } -#endif - if (copy_from_user(cgc, arg, sizeof(*cgc))) - return -EFAULT; - - return 0; -} - -static int scsi_put_cdrom_generic_arg(const struct cdrom_generic_command *cgc, - void __user *arg) -{ -#ifdef CONFIG_COMPAT - if (in_compat_syscall()) { - struct compat_cdrom_generic_command cgc32 = { - .buffer = (uintptr_t)(cgc->buffer), - .buflen = cgc->buflen, - .stat = cgc->stat, - .sense = (uintptr_t)(cgc->sense), - .data_direction = cgc->data_direction, - .quiet = cgc->quiet, - .timeout = cgc->timeout, - .unused = (uintptr_t)(cgc->unused), - }; - memcpy(&cgc32.cmd, &cgc->cmd, CDROM_PACKET_SIZE); - - if (copy_to_user(arg, &cgc32, sizeof(cgc32))) - return -EFAULT; - - return 0; - } -#endif - if (copy_to_user(arg, cgc, sizeof(*cgc))) - return -EFAULT; - - return 0; -} - -static int scsi_cdrom_send_packet(struct request_queue *q, - struct gendisk *bd_disk, - fmode_t mode, void __user *arg) -{ - struct cdrom_generic_command cgc; - struct sg_io_hdr hdr; - int err; - - err = scsi_get_cdrom_generic_arg(&cgc, arg); - if (err) - return err; - - cgc.timeout = clock_t_to_jiffies(cgc.timeout); - memset(&hdr, 0, sizeof(hdr)); - hdr.interface_id = 'S'; - hdr.cmd_len = sizeof(cgc.cmd); - hdr.dxfer_len = cgc.buflen; - switch (cgc.data_direction) { - case CGC_DATA_UNKNOWN: - hdr.dxfer_direction = SG_DXFER_UNKNOWN; - break; - case CGC_DATA_WRITE: - hdr.dxfer_direction = SG_DXFER_TO_DEV; - break; - case CGC_DATA_READ: - hdr.dxfer_direction = SG_DXFER_FROM_DEV; - break; - case CGC_DATA_NONE: - hdr.dxfer_direction = SG_DXFER_NONE; - break; - default: - return -EINVAL; - } - - hdr.dxferp = cgc.buffer; - hdr.sbp = cgc.sense; - if (hdr.sbp) - hdr.mx_sb_len = sizeof(struct request_sense); - hdr.timeout = jiffies_to_msecs(cgc.timeout); - hdr.cmdp = ((struct cdrom_generic_command __user*) arg)->cmd; - hdr.cmd_len = sizeof(cgc.cmd); - - err = sg_io(q, bd_disk, &hdr, mode); - if (err == -EFAULT) - return -EFAULT; - - if (hdr.status) - return -EIO; - - cgc.stat = err; - cgc.buflen = hdr.resid; - if (scsi_put_cdrom_generic_arg(&cgc, arg)) - return -EFAULT; - - return err; -} - -int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mode, - unsigned int cmd, void __user *arg) -{ - int err; - - if (!q) - return -ENXIO; - - switch (cmd) { - /* - * new sgv3 interface - */ - case SG_GET_VERSION_NUM: - err = sg_get_version(arg); - break; - case SG_SET_TIMEOUT: - err = sg_set_timeout(q, arg); - break; - case SG_GET_TIMEOUT: - err = sg_get_timeout(q); - break; - case SG_GET_RESERVED_SIZE: - err = sg_get_reserved_size(q, arg); - break; - case SG_SET_RESERVED_SIZE: - err = sg_set_reserved_size(q, arg); - break; - case SG_EMULATED_HOST: - err = sg_emulated_host(q, arg); - break; - case SG_IO: { - struct sg_io_hdr hdr; - - err = get_sg_io_hdr(&hdr, arg); - if (err) - break; - err = sg_io(q, bd_disk, &hdr, mode); - if (err == -EFAULT) - break; - - if (put_sg_io_hdr(&hdr, arg)) - err = -EFAULT; - break; - } - case CDROM_SEND_PACKET: - err = scsi_cdrom_send_packet(q, bd_disk, mode, arg); - break; - - /* - * old junk scsi send command ioctl - */ - case SCSI_IOCTL_SEND_COMMAND: - printk(KERN_WARNING "program %s is using a deprecated SCSI ioctl, please convert it to SG_IO\n", current->comm); - err = -EINVAL; - if (!arg) - break; - - err = sg_scsi_ioctl(q, bd_disk, mode, arg); - break; - case CDROMCLOSETRAY: - err = blk_send_start_stop(q, bd_disk, 0x03); - break; - case CDROMEJECT: - err = blk_send_start_stop(q, bd_disk, 0x02); - break; - default: - err = -ENOTTY; - } - - return err; -} -EXPORT_SYMBOL(scsi_cmd_ioctl); diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c index 7739575b5229..2c4cdd0fc26e 100644 --- a/drivers/scsi/scsi_ioctl.c +++ b/drivers/scsi/scsi_ioctl.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -189,6 +190,706 @@ static int scsi_ioctl_get_pci(struct scsi_device *sdev, void __user *arg) ? -EFAULT: 0; } +static int sg_get_version(int __user *p) +{ + static const int sg_version_num = 30527; + return put_user(sg_version_num, p); +} + +static int sg_get_timeout(struct request_queue *q) +{ + return jiffies_to_clock_t(q->sg_timeout); +} + +static int sg_set_timeout(struct request_queue *q, int __user *p) +{ + int timeout, err = get_user(timeout, p); + + if (!err) + q->sg_timeout = clock_t_to_jiffies(timeout); + + return err; +} + +static int sg_get_reserved_size(struct request_queue *q, int __user *p) +{ + int val = min(q->sg_reserved_size, queue_max_bytes(q)); + + return put_user(val, p); +} + +static int sg_set_reserved_size(struct request_queue *q, int __user *p) +{ + int size, err = get_user(size, p); + + if (err) + return err; + + if (size < 0) + return -EINVAL; + + q->sg_reserved_size = min_t(unsigned int, size, queue_max_bytes(q)); + return 0; +} + +/* + * will always return that we are ATAPI even for a real SCSI drive, I'm not + * so sure this is worth doing anything about (why would you care??) + */ +static int sg_emulated_host(struct request_queue *q, int __user *p) +{ + return put_user(1, p); +} + +/* Send basic block requests */ +static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk, + int cmd, int data) +{ + struct request *rq; + int err; + + rq = blk_get_request(q, REQ_OP_DRV_OUT, 0); + if (IS_ERR(rq)) + return PTR_ERR(rq); + rq->timeout = BLK_DEFAULT_SG_TIMEOUT; + scsi_req(rq)->cmd[0] = cmd; + scsi_req(rq)->cmd[4] = data; + scsi_req(rq)->cmd_len = 6; + blk_execute_rq(bd_disk, rq, 0); + err = scsi_req(rq)->result ? -EIO : 0; + blk_put_request(rq); + + return err; +} + +static inline int blk_send_start_stop(struct request_queue *q, + struct gendisk *bd_disk, int data) +{ + return __blk_send_generic(q, bd_disk, GPCMD_START_STOP_UNIT, data); +} + +/* + * Check if the given command is allowed. + * + * Only a subset of commands are allowed for unprivileged users. Commands used + * to format the media, update the firmware, etc. are not permitted. + */ +bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode) +{ + /* root can do any command. */ + if (capable(CAP_SYS_RAWIO)) + return true; + + /* Anybody who can open the device can do a read-safe command */ + switch (cmd[0]) { + /* Basic read-only commands */ + case TEST_UNIT_READY: + case REQUEST_SENSE: + case READ_6: + case READ_10: + case READ_12: + case READ_16: + case READ_BUFFER: + case READ_DEFECT_DATA: + case READ_CAPACITY: /* also GPCMD_READ_CDVD_CAPACITY */ + case READ_LONG: + case INQUIRY: + case MODE_SENSE: + case MODE_SENSE_10: + case LOG_SENSE: + case START_STOP: + case GPCMD_VERIFY_10: + case VERIFY_16: + case REPORT_LUNS: + case SERVICE_ACTION_IN_16: + case RECEIVE_DIAGNOSTIC: + case MAINTENANCE_IN: /* also GPCMD_SEND_KEY, which is a write command */ + case GPCMD_READ_BUFFER_CAPACITY: + /* Audio CD commands */ + case GPCMD_PLAY_CD: + case GPCMD_PLAY_AUDIO_10: + case GPCMD_PLAY_AUDIO_MSF: + case GPCMD_PLAY_AUDIO_TI: + case GPCMD_PAUSE_RESUME: + /* CD/DVD data reading */ + case GPCMD_READ_CD: + case GPCMD_READ_CD_MSF: + case GPCMD_READ_DISC_INFO: + case GPCMD_READ_DVD_STRUCTURE: + case GPCMD_READ_HEADER: + case GPCMD_READ_TRACK_RZONE_INFO: + case GPCMD_READ_SUBCHANNEL: + case GPCMD_READ_TOC_PMA_ATIP: + case GPCMD_REPORT_KEY: + case GPCMD_SCAN: + case GPCMD_GET_CONFIGURATION: + case GPCMD_READ_FORMAT_CAPACITIES: + case GPCMD_GET_EVENT_STATUS_NOTIFICATION: + case GPCMD_GET_PERFORMANCE: + case GPCMD_SEEK: + case GPCMD_STOP_PLAY_SCAN: + /* ZBC */ + case ZBC_IN: + return true; + /* Basic writing commands */ + case WRITE_6: + case WRITE_10: + case WRITE_VERIFY: + case WRITE_12: + case WRITE_VERIFY_12: + case WRITE_16: + case WRITE_LONG: + case WRITE_LONG_2: + case WRITE_SAME: + case WRITE_SAME_16: + case WRITE_SAME_32: + case ERASE: + case GPCMD_MODE_SELECT_10: + case MODE_SELECT: + case LOG_SELECT: + case GPCMD_BLANK: + case GPCMD_CLOSE_TRACK: + case GPCMD_FLUSH_CACHE: + case GPCMD_FORMAT_UNIT: + case GPCMD_REPAIR_RZONE_TRACK: + case GPCMD_RESERVE_RZONE_TRACK: + case GPCMD_SEND_DVD_STRUCTURE: + case GPCMD_SEND_EVENT: + case GPCMD_SEND_OPC: + case GPCMD_SEND_CUE_SHEET: + case GPCMD_SET_SPEED: + case GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL: + case GPCMD_LOAD_UNLOAD: + case GPCMD_SET_STREAMING: + case GPCMD_SET_READ_AHEAD: + /* ZBC */ + case ZBC_OUT: + return (mode & FMODE_WRITE); + default: + return false; + } +} +EXPORT_SYMBOL(scsi_cmd_allowed); + +static int scsi_fill_sghdr_rq(struct request_queue *q, struct request *rq, + struct sg_io_hdr *hdr, fmode_t mode) +{ + struct scsi_request *req = scsi_req(rq); + + if (copy_from_user(req->cmd, hdr->cmdp, hdr->cmd_len)) + return -EFAULT; + if (!scsi_cmd_allowed(req->cmd, mode)) + return -EPERM; + + /* + * fill in request structure + */ + req->cmd_len = hdr->cmd_len; + + rq->timeout = msecs_to_jiffies(hdr->timeout); + if (!rq->timeout) + rq->timeout = q->sg_timeout; + if (!rq->timeout) + rq->timeout = BLK_DEFAULT_SG_TIMEOUT; + if (rq->timeout < BLK_MIN_SG_TIMEOUT) + rq->timeout = BLK_MIN_SG_TIMEOUT; + + return 0; +} + +static int scsi_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr, + struct bio *bio) +{ + struct scsi_request *req = scsi_req(rq); + int r, ret = 0; + + /* + * fill in all the output members + */ + hdr->status = req->result & 0xff; + hdr->masked_status = status_byte(req->result); + hdr->msg_status = COMMAND_COMPLETE; + hdr->host_status = host_byte(req->result); + hdr->driver_status = 0; + if (scsi_status_is_check_condition(hdr->status)) + hdr->driver_status = DRIVER_SENSE; + hdr->info = 0; + if (hdr->masked_status || hdr->host_status || hdr->driver_status) + hdr->info |= SG_INFO_CHECK; + hdr->resid = req->resid_len; + hdr->sb_len_wr = 0; + + if (req->sense_len && hdr->sbp) { + int len = min((unsigned int) hdr->mx_sb_len, req->sense_len); + + if (!copy_to_user(hdr->sbp, req->sense, len)) + hdr->sb_len_wr = len; + else + ret = -EFAULT; + } + + r = blk_rq_unmap_user(bio); + if (!ret) + ret = r; + + return ret; +} + +static int sg_io(struct request_queue *q, struct gendisk *bd_disk, + struct sg_io_hdr *hdr, fmode_t mode) +{ + unsigned long start_time; + ssize_t ret = 0; + int writing = 0; + int at_head = 0; + struct request *rq; + struct scsi_request *req; + struct bio *bio; + + if (hdr->interface_id != 'S') + return -EINVAL; + + if (hdr->dxfer_len > (queue_max_hw_sectors(q) << 9)) + return -EIO; + + if (hdr->dxfer_len) + switch (hdr->dxfer_direction) { + default: + return -EINVAL; + case SG_DXFER_TO_DEV: + writing = 1; + break; + case SG_DXFER_TO_FROM_DEV: + case SG_DXFER_FROM_DEV: + break; + } + if (hdr->flags & SG_FLAG_Q_AT_HEAD) + at_head = 1; + + ret = -ENOMEM; + rq = blk_get_request(q, writing ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); + if (IS_ERR(rq)) + return PTR_ERR(rq); + req = scsi_req(rq); + + if (hdr->cmd_len > BLK_MAX_CDB) { + req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL); + if (!req->cmd) + goto out_put_request; + } + + ret = scsi_fill_sghdr_rq(q, rq, hdr, mode); + if (ret < 0) + goto out_free_cdb; + + ret = 0; + if (hdr->iovec_count) { + struct iov_iter i; + struct iovec *iov = NULL; + + ret = import_iovec(rq_data_dir(rq), hdr->dxferp, + hdr->iovec_count, 0, &iov, &i); + if (ret < 0) + goto out_free_cdb; + + /* SG_IO howto says that the shorter of the two wins */ + iov_iter_truncate(&i, hdr->dxfer_len); + + ret = blk_rq_map_user_iov(q, rq, NULL, &i, GFP_KERNEL); + kfree(iov); + } else if (hdr->dxfer_len) + ret = blk_rq_map_user(q, rq, NULL, hdr->dxferp, hdr->dxfer_len, + GFP_KERNEL); + + if (ret) + goto out_free_cdb; + + bio = rq->bio; + req->retries = 0; + + start_time = jiffies; + + blk_execute_rq(bd_disk, rq, at_head); + + hdr->duration = jiffies_to_msecs(jiffies - start_time); + + ret = scsi_complete_sghdr_rq(rq, hdr, bio); + +out_free_cdb: + scsi_req_free_cmd(req); +out_put_request: + blk_put_request(rq); + return ret; +} + +/** + * sg_scsi_ioctl -- handle deprecated SCSI_IOCTL_SEND_COMMAND ioctl + * @q: request queue to send scsi commands down + * @disk: gendisk to operate on (option) + * @mode: mode used to open the file through which the ioctl has been + * submitted + * @sic: userspace structure describing the command to perform + * + * Send down the scsi command described by @sic to the device below + * the request queue @q. If @file is non-NULL it's used to perform + * fine-grained permission checks that allow users to send down + * non-destructive SCSI commands. If the caller has a struct gendisk + * available it should be passed in as @disk to allow the low level + * driver to use the information contained in it. A non-NULL @disk + * is only allowed if the caller knows that the low level driver doesn't + * need it (e.g. in the scsi subsystem). + * + * Notes: + * - This interface is deprecated - users should use the SG_IO + * interface instead, as this is a more flexible approach to + * performing SCSI commands on a device. + * - The SCSI command length is determined by examining the 1st byte + * of the given command. There is no way to override this. + * - Data transfers are limited to PAGE_SIZE + * - The length (x + y) must be at least OMAX_SB_LEN bytes long to + * accommodate the sense buffer when an error occurs. + * The sense buffer is truncated to OMAX_SB_LEN (16) bytes so that + * old code will not be surprised. + * - If a Unix error occurs (e.g. ENOMEM) then the user will receive + * a negative return and the Unix error code in 'errno'. + * If the SCSI command succeeds then 0 is returned. + * Positive numbers returned are the compacted SCSI error codes (4 + * bytes in one int) where the lowest byte is the SCSI status. + */ +int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, + struct scsi_ioctl_command __user *sic) +{ + enum { OMAX_SB_LEN = 16 }; /* For backward compatibility */ + struct request *rq; + struct scsi_request *req; + int err; + unsigned int in_len, out_len, bytes, opcode, cmdlen; + char *buffer = NULL; + + if (!sic) + return -EINVAL; + + /* + * get in an out lengths, verify they don't exceed a page worth of data + */ + if (get_user(in_len, &sic->inlen)) + return -EFAULT; + if (get_user(out_len, &sic->outlen)) + return -EFAULT; + if (in_len > PAGE_SIZE || out_len > PAGE_SIZE) + return -EINVAL; + if (get_user(opcode, sic->data)) + return -EFAULT; + + bytes = max(in_len, out_len); + if (bytes) { + buffer = kzalloc(bytes, GFP_NOIO | GFP_USER | __GFP_NOWARN); + if (!buffer) + return -ENOMEM; + + } + + rq = blk_get_request(q, in_len ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto error_free_buffer; + } + req = scsi_req(rq); + + cmdlen = COMMAND_SIZE(opcode); + + /* + * get command and data to send to device, if any + */ + err = -EFAULT; + req->cmd_len = cmdlen; + if (copy_from_user(req->cmd, sic->data, cmdlen)) + goto error; + + if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len)) + goto error; + + err = -EPERM; + if (!scsi_cmd_allowed(req->cmd, mode)) + goto error; + + /* default. possible overridden later */ + req->retries = 5; + + switch (opcode) { + case SEND_DIAGNOSTIC: + case FORMAT_UNIT: + rq->timeout = FORMAT_UNIT_TIMEOUT; + req->retries = 1; + break; + case START_STOP: + rq->timeout = START_STOP_TIMEOUT; + break; + case MOVE_MEDIUM: + rq->timeout = MOVE_MEDIUM_TIMEOUT; + break; + case READ_ELEMENT_STATUS: + rq->timeout = READ_ELEMENT_STATUS_TIMEOUT; + break; + case READ_DEFECT_DATA: + rq->timeout = READ_DEFECT_DATA_TIMEOUT; + req->retries = 1; + break; + default: + rq->timeout = BLK_DEFAULT_SG_TIMEOUT; + break; + } + + if (bytes) { + err = blk_rq_map_kern(q, rq, buffer, bytes, GFP_NOIO); + if (err) + goto error; + } + + blk_execute_rq(disk, rq, 0); + + err = req->result & 0xff; /* only 8 bit SCSI status */ + if (err) { + if (req->sense_len && req->sense) { + bytes = (OMAX_SB_LEN > req->sense_len) ? + req->sense_len : OMAX_SB_LEN; + if (copy_to_user(sic->data, req->sense, bytes)) + err = -EFAULT; + } + } else { + if (copy_to_user(sic->data, buffer, out_len)) + err = -EFAULT; + } + +error: + blk_put_request(rq); + +error_free_buffer: + kfree(buffer); + + return err; +} +EXPORT_SYMBOL_GPL(sg_scsi_ioctl); + +int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp) +{ +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) { + struct compat_sg_io_hdr hdr32 = { + .interface_id = hdr->interface_id, + .dxfer_direction = hdr->dxfer_direction, + .cmd_len = hdr->cmd_len, + .mx_sb_len = hdr->mx_sb_len, + .iovec_count = hdr->iovec_count, + .dxfer_len = hdr->dxfer_len, + .dxferp = (uintptr_t)hdr->dxferp, + .cmdp = (uintptr_t)hdr->cmdp, + .sbp = (uintptr_t)hdr->sbp, + .timeout = hdr->timeout, + .flags = hdr->flags, + .pack_id = hdr->pack_id, + .usr_ptr = (uintptr_t)hdr->usr_ptr, + .status = hdr->status, + .masked_status = hdr->masked_status, + .msg_status = hdr->msg_status, + .sb_len_wr = hdr->sb_len_wr, + .host_status = hdr->host_status, + .driver_status = hdr->driver_status, + .resid = hdr->resid, + .duration = hdr->duration, + .info = hdr->info, + }; + + if (copy_to_user(argp, &hdr32, sizeof(hdr32))) + return -EFAULT; + + return 0; + } +#endif + + if (copy_to_user(argp, hdr, sizeof(*hdr))) + return -EFAULT; + + return 0; +} +EXPORT_SYMBOL(put_sg_io_hdr); + +int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp) +{ +#ifdef CONFIG_COMPAT + struct compat_sg_io_hdr hdr32; + + if (in_compat_syscall()) { + if (copy_from_user(&hdr32, argp, sizeof(hdr32))) + return -EFAULT; + + *hdr = (struct sg_io_hdr) { + .interface_id = hdr32.interface_id, + .dxfer_direction = hdr32.dxfer_direction, + .cmd_len = hdr32.cmd_len, + .mx_sb_len = hdr32.mx_sb_len, + .iovec_count = hdr32.iovec_count, + .dxfer_len = hdr32.dxfer_len, + .dxferp = compat_ptr(hdr32.dxferp), + .cmdp = compat_ptr(hdr32.cmdp), + .sbp = compat_ptr(hdr32.sbp), + .timeout = hdr32.timeout, + .flags = hdr32.flags, + .pack_id = hdr32.pack_id, + .usr_ptr = compat_ptr(hdr32.usr_ptr), + .status = hdr32.status, + .masked_status = hdr32.masked_status, + .msg_status = hdr32.msg_status, + .sb_len_wr = hdr32.sb_len_wr, + .host_status = hdr32.host_status, + .driver_status = hdr32.driver_status, + .resid = hdr32.resid, + .duration = hdr32.duration, + .info = hdr32.info, + }; + + return 0; + } +#endif + + if (copy_from_user(hdr, argp, sizeof(*hdr))) + return -EFAULT; + + return 0; +} +EXPORT_SYMBOL(get_sg_io_hdr); + +#ifdef CONFIG_COMPAT +struct compat_cdrom_generic_command { + unsigned char cmd[CDROM_PACKET_SIZE]; + compat_caddr_t buffer; + compat_uint_t buflen; + compat_int_t stat; + compat_caddr_t sense; + unsigned char data_direction; + unsigned char pad[3]; + compat_int_t quiet; + compat_int_t timeout; + compat_caddr_t unused; +}; +#endif + +static int scsi_get_cdrom_generic_arg(struct cdrom_generic_command *cgc, + const void __user *arg) +{ +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) { + struct compat_cdrom_generic_command cgc32; + + if (copy_from_user(&cgc32, arg, sizeof(cgc32))) + return -EFAULT; + + *cgc = (struct cdrom_generic_command) { + .buffer = compat_ptr(cgc32.buffer), + .buflen = cgc32.buflen, + .stat = cgc32.stat, + .sense = compat_ptr(cgc32.sense), + .data_direction = cgc32.data_direction, + .quiet = cgc32.quiet, + .timeout = cgc32.timeout, + .unused = compat_ptr(cgc32.unused), + }; + memcpy(&cgc->cmd, &cgc32.cmd, CDROM_PACKET_SIZE); + return 0; + } +#endif + if (copy_from_user(cgc, arg, sizeof(*cgc))) + return -EFAULT; + + return 0; +} + +static int scsi_put_cdrom_generic_arg(const struct cdrom_generic_command *cgc, + void __user *arg) +{ +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) { + struct compat_cdrom_generic_command cgc32 = { + .buffer = (uintptr_t)(cgc->buffer), + .buflen = cgc->buflen, + .stat = cgc->stat, + .sense = (uintptr_t)(cgc->sense), + .data_direction = cgc->data_direction, + .quiet = cgc->quiet, + .timeout = cgc->timeout, + .unused = (uintptr_t)(cgc->unused), + }; + memcpy(&cgc32.cmd, &cgc->cmd, CDROM_PACKET_SIZE); + + if (copy_to_user(arg, &cgc32, sizeof(cgc32))) + return -EFAULT; + + return 0; + } +#endif + if (copy_to_user(arg, cgc, sizeof(*cgc))) + return -EFAULT; + + return 0; +} + +static int scsi_cdrom_send_packet(struct request_queue *q, + struct gendisk *bd_disk, + fmode_t mode, void __user *arg) +{ + struct cdrom_generic_command cgc; + struct sg_io_hdr hdr; + int err; + + err = scsi_get_cdrom_generic_arg(&cgc, arg); + if (err) + return err; + + cgc.timeout = clock_t_to_jiffies(cgc.timeout); + memset(&hdr, 0, sizeof(hdr)); + hdr.interface_id = 'S'; + hdr.cmd_len = sizeof(cgc.cmd); + hdr.dxfer_len = cgc.buflen; + switch (cgc.data_direction) { + case CGC_DATA_UNKNOWN: + hdr.dxfer_direction = SG_DXFER_UNKNOWN; + break; + case CGC_DATA_WRITE: + hdr.dxfer_direction = SG_DXFER_TO_DEV; + break; + case CGC_DATA_READ: + hdr.dxfer_direction = SG_DXFER_FROM_DEV; + break; + case CGC_DATA_NONE: + hdr.dxfer_direction = SG_DXFER_NONE; + break; + default: + return -EINVAL; + } + + hdr.dxferp = cgc.buffer; + hdr.sbp = cgc.sense; + if (hdr.sbp) + hdr.mx_sb_len = sizeof(struct request_sense); + hdr.timeout = jiffies_to_msecs(cgc.timeout); + hdr.cmdp = ((struct cdrom_generic_command __user *) arg)->cmd; + hdr.cmd_len = sizeof(cgc.cmd); + + err = sg_io(q, bd_disk, &hdr, mode); + if (err == -EFAULT) + return -EFAULT; + + if (hdr.status) + return -EIO; + + cgc.stat = err; + cgc.buflen = hdr.resid; + if (scsi_put_cdrom_generic_arg(&cgc, arg)) + return -EFAULT; + + return err; +} + /** * scsi_ioctl - Dispatch ioctl to scsi device * @sdev: scsi device receiving ioctl @@ -225,13 +926,42 @@ int scsi_ioctl(struct scsi_device *sdev, struct gendisk *disk, fmode_t mode, break; } - if (cmd != SCSI_IOCTL_GET_IDLUN && cmd != SCSI_IOCTL_GET_BUS_NUMBER) { - error = scsi_cmd_ioctl(q, disk, mode, cmd, arg); - if (error != -ENOTTY) + switch (cmd) { + case SG_GET_VERSION_NUM: + return sg_get_version(arg); + case SG_SET_TIMEOUT: + return sg_set_timeout(q, arg); + case SG_GET_TIMEOUT: + return sg_get_timeout(q); + case SG_GET_RESERVED_SIZE: + return sg_get_reserved_size(q, arg); + case SG_SET_RESERVED_SIZE: + return sg_set_reserved_size(q, arg); + case SG_EMULATED_HOST: + return sg_emulated_host(q, arg); + case SG_IO: { + struct sg_io_hdr hdr; + + error = get_sg_io_hdr(&hdr, arg); + if (error) return error; - } - switch (cmd) { + error = sg_io(q, disk, &hdr, mode); + if (error == -EFAULT) + return error; + + if (put_sg_io_hdr(&hdr, arg)) + return -EFAULT; + return 0; + } + case SCSI_IOCTL_SEND_COMMAND: + return sg_scsi_ioctl(q, disk, mode, arg); + case CDROM_SEND_PACKET: + return scsi_cdrom_send_packet(q, disk, mode, arg); + case CDROMCLOSETRAY: + return blk_send_start_stop(q, disk, 0x03); + case CDROMEJECT: + return blk_send_start_stop(q, disk, 0x02); case SCSI_IOCTL_GET_IDLUN: { struct scsi_idlun v = { .dev_id = (sdev->id & 0xff) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e28679e63373..8c617a5a5d61 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -28,8 +28,6 @@ #include struct module; -struct scsi_ioctl_command; - struct request_queue; struct elevator_queue; struct blk_trace; @@ -888,13 +886,6 @@ extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_queue_split(struct bio **); -extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, - unsigned int, void __user *); -extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, - struct scsi_ioctl_command __user *); -extern int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp); -extern int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp); - extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); @@ -1343,8 +1334,6 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, gfp_mask, 0); } -bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode); - static inline bool bdev_is_partition(struct block_device *bdev) { return bdev->bd_partno; diff --git a/include/scsi/scsi_ioctl.h b/include/scsi/scsi_ioctl.h index defbe8084eb8..b3918fded464 100644 --- a/include/scsi/scsi_ioctl.h +++ b/include/scsi/scsi_ioctl.h @@ -20,6 +20,7 @@ struct gendisk; struct scsi_device; +struct sg_io_hdr; /* * Structures used for scsi_ioctl et al. @@ -46,6 +47,11 @@ int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev, int cmd, bool ndelay); int scsi_ioctl(struct scsi_device *sdev, struct gendisk *disk, fmode_t mode, int cmd, void __user *arg); +int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, + struct scsi_ioctl_command __user *argp); +int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp); +int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp); +bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode); #endif /* __KERNEL__ */ #endif /* _SCSI_IOCTL_H */ -- cgit v1.2.3 From 38ef66b05cfa3560323344a0b3e09e583f1eb974 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 28 Jul 2021 21:37:28 -0700 Subject: fscrypt: document struct fscrypt_operations Document all fields of struct fscrypt_operations so that it's more clear what filesystems that use (or plan to use) fs/crypto/ need to implement. Link: https://lore.kernel.org/r/20210729043728.18480-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 109 ++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 105 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index b7bfd0cd4f3e..e912ed9141d9 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -47,27 +47,128 @@ struct fscrypt_name { #define FSCRYPT_SET_CONTEXT_MAX_SIZE 40 #ifdef CONFIG_FS_ENCRYPTION + /* - * fscrypt superblock flags + * If set, the fscrypt bounce page pool won't be allocated (unless another + * filesystem needs it). Set this if the filesystem always uses its own bounce + * pages for writes and therefore won't need the fscrypt bounce page pool. */ #define FS_CFLG_OWN_PAGES (1U << 1) -/* - * crypto operations for filesystems - */ +/* Crypto operations for filesystems */ struct fscrypt_operations { + + /* Set of optional flags; see above for allowed flags */ unsigned int flags; + + /* + * If set, this is a filesystem-specific key description prefix that + * will be accepted for "logon" keys for v1 fscrypt policies, in + * addition to the generic prefix "fscrypt:". This functionality is + * deprecated, so new filesystems shouldn't set this field. + */ const char *key_prefix; + + /* + * Get the fscrypt context of the given inode. + * + * @inode: the inode whose context to get + * @ctx: the buffer into which to get the context + * @len: length of the @ctx buffer in bytes + * + * Return: On success, returns the length of the context in bytes; this + * may be less than @len. On failure, returns -ENODATA if the + * inode doesn't have a context, -ERANGE if the context is + * longer than @len, or another -errno code. + */ int (*get_context)(struct inode *inode, void *ctx, size_t len); + + /* + * Set an fscrypt context on the given inode. + * + * @inode: the inode whose context to set. The inode won't already have + * an fscrypt context. + * @ctx: the context to set + * @len: length of @ctx in bytes (at most FSCRYPT_SET_CONTEXT_MAX_SIZE) + * @fs_data: If called from fscrypt_set_context(), this will be the + * value the filesystem passed to fscrypt_set_context(). + * Otherwise (i.e. when called from + * FS_IOC_SET_ENCRYPTION_POLICY) this will be NULL. + * + * i_rwsem will be held for write. + * + * Return: 0 on success, -errno on failure. + */ int (*set_context)(struct inode *inode, const void *ctx, size_t len, void *fs_data); + + /* + * Get the dummy fscrypt policy in use on the filesystem (if any). + * + * Filesystems only need to implement this function if they support the + * test_dummy_encryption mount option. + * + * Return: A pointer to the dummy fscrypt policy, if the filesystem is + * mounted with test_dummy_encryption; otherwise NULL. + */ const union fscrypt_policy *(*get_dummy_policy)(struct super_block *sb); + + /* + * Check whether a directory is empty. i_rwsem will be held for write. + */ bool (*empty_dir)(struct inode *inode); + + /* The filesystem's maximum ciphertext filename length, in bytes */ unsigned int max_namelen; + + /* + * Check whether the filesystem's inode numbers and UUID are stable, + * meaning that they will never be changed even by offline operations + * such as filesystem shrinking and therefore can be used in the + * encryption without the possibility of files becoming unreadable. + * + * Filesystems only need to implement this function if they want to + * support the FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{32,64} flags. These + * flags are designed to work around the limitations of UFS and eMMC + * inline crypto hardware, and they shouldn't be used in scenarios where + * such hardware isn't being used. + * + * Leaving this NULL is equivalent to always returning false. + */ bool (*has_stable_inodes)(struct super_block *sb); + + /* + * Get the number of bits that the filesystem uses to represent inode + * numbers and file logical block numbers. + * + * By default, both of these are assumed to be 64-bit. This function + * can be implemented to declare that either or both of these numbers is + * shorter, which may allow the use of the + * FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{32,64} flags and/or the use of + * inline crypto hardware whose maximum DUN length is less than 64 bits + * (e.g., eMMC v5.2 spec compliant hardware). This function only needs + * to be implemented if support for one of these features is needed. + */ void (*get_ino_and_lblk_bits)(struct super_block *sb, int *ino_bits_ret, int *lblk_bits_ret); + + /* + * Return the number of block devices to which the filesystem may write + * encrypted file contents. + * + * If the filesystem can use multiple block devices (other than block + * devices that aren't used for encrypted file contents, such as + * external journal devices), and wants to support inline encryption, + * then it must implement this function. Otherwise it's not needed. + */ int (*get_num_devices)(struct super_block *sb); + + /* + * If ->get_num_devices() returns a value greater than 1, then this + * function is called to get the array of request_queues that the + * filesystem is using -- one per block device. (There may be duplicate + * entries in this array, as block devices can share a request_queue.) + */ void (*get_devices)(struct super_block *sb, struct request_queue **devs); }; -- cgit v1.2.3 From 77ed5e9dec551765bde9f2e4b7ed9071ff03d61d Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 27 Jul 2021 13:10:34 +0300 Subject: memory: omap-gpmc: Drop custom PM calls with cpu_pm notifier We can now switch over to using cpu_pm instead of custom calls and make the context save and restore functions static. Let's also move the save and restore functions to avoid adding forward declarations for them. And get rid of the static data pointer while at it. Cc: Roger Quadros Signed-off-by: Tony Lindgren Link: https://lore.kernel.org/r/20210727101034.32148-2-tony@atomide.com Signed-off-by: Krzysztof Kozlowski --- arch/arm/mach-omap2/pm34xx.c | 5 -- drivers/memory/omap-gpmc.c | 193 ++++++++++++++++++++++++++----------------- include/linux/omap-gpmc.h | 3 - 3 files changed, 118 insertions(+), 83 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 71c1d18aafbc..d73c7b692116 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -26,7 +26,6 @@ #include #include #include -#include #include @@ -81,8 +80,6 @@ static void omap3_core_save_context(void) /* Save the Interrupt controller context */ omap_intc_save_context(); - /* Save the GPMC context */ - omap3_gpmc_save_context(); /* Save the system control module context, padconf already save above*/ omap3_control_save_context(); } @@ -91,8 +88,6 @@ static void omap3_core_restore_context(void) { /* Restore the control module context, padconf restored by h/w */ omap3_control_restore_context(); - /* Restore the GPMC context */ - omap3_gpmc_restore_context(); /* Restore the interrupt controller context */ omap_intc_restore_context(); } diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index 55752c858f3e..be0858bff4d3 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -9,6 +9,7 @@ * Copyright (C) 2009 Texas Instruments * Added OMAP4 support - Santosh Shilimkar */ +#include #include #include #include @@ -232,7 +233,10 @@ struct gpmc_device { int irq; struct irq_chip irq_chip; struct gpio_chip gpio_chip; + struct notifier_block nb; + struct omap3_gpmc_regs context; int nirqs; + unsigned int is_suspended:1; }; static struct irq_domain *gpmc_irq_domain; @@ -2384,6 +2388,106 @@ static int gpmc_gpio_init(struct gpmc_device *gpmc) return 0; } +static void omap3_gpmc_save_context(struct gpmc_device *gpmc) +{ + struct omap3_gpmc_regs *gpmc_context; + int i; + + if (!gpmc || !gpmc_base) + return; + + gpmc_context = &gpmc->context; + + gpmc_context->sysconfig = gpmc_read_reg(GPMC_SYSCONFIG); + gpmc_context->irqenable = gpmc_read_reg(GPMC_IRQENABLE); + gpmc_context->timeout_ctrl = gpmc_read_reg(GPMC_TIMEOUT_CONTROL); + gpmc_context->config = gpmc_read_reg(GPMC_CONFIG); + gpmc_context->prefetch_config1 = gpmc_read_reg(GPMC_PREFETCH_CONFIG1); + gpmc_context->prefetch_config2 = gpmc_read_reg(GPMC_PREFETCH_CONFIG2); + gpmc_context->prefetch_control = gpmc_read_reg(GPMC_PREFETCH_CONTROL); + for (i = 0; i < gpmc_cs_num; i++) { + gpmc_context->cs_context[i].is_valid = gpmc_cs_mem_enabled(i); + if (gpmc_context->cs_context[i].is_valid) { + gpmc_context->cs_context[i].config1 = + gpmc_cs_read_reg(i, GPMC_CS_CONFIG1); + gpmc_context->cs_context[i].config2 = + gpmc_cs_read_reg(i, GPMC_CS_CONFIG2); + gpmc_context->cs_context[i].config3 = + gpmc_cs_read_reg(i, GPMC_CS_CONFIG3); + gpmc_context->cs_context[i].config4 = + gpmc_cs_read_reg(i, GPMC_CS_CONFIG4); + gpmc_context->cs_context[i].config5 = + gpmc_cs_read_reg(i, GPMC_CS_CONFIG5); + gpmc_context->cs_context[i].config6 = + gpmc_cs_read_reg(i, GPMC_CS_CONFIG6); + gpmc_context->cs_context[i].config7 = + gpmc_cs_read_reg(i, GPMC_CS_CONFIG7); + } + } +} + +static void omap3_gpmc_restore_context(struct gpmc_device *gpmc) +{ + struct omap3_gpmc_regs *gpmc_context; + int i; + + if (!gpmc || !gpmc_base) + return; + + gpmc_context = &gpmc->context; + + gpmc_write_reg(GPMC_SYSCONFIG, gpmc_context->sysconfig); + gpmc_write_reg(GPMC_IRQENABLE, gpmc_context->irqenable); + gpmc_write_reg(GPMC_TIMEOUT_CONTROL, gpmc_context->timeout_ctrl); + gpmc_write_reg(GPMC_CONFIG, gpmc_context->config); + gpmc_write_reg(GPMC_PREFETCH_CONFIG1, gpmc_context->prefetch_config1); + gpmc_write_reg(GPMC_PREFETCH_CONFIG2, gpmc_context->prefetch_config2); + gpmc_write_reg(GPMC_PREFETCH_CONTROL, gpmc_context->prefetch_control); + for (i = 0; i < gpmc_cs_num; i++) { + if (gpmc_context->cs_context[i].is_valid) { + gpmc_cs_write_reg(i, GPMC_CS_CONFIG1, + gpmc_context->cs_context[i].config1); + gpmc_cs_write_reg(i, GPMC_CS_CONFIG2, + gpmc_context->cs_context[i].config2); + gpmc_cs_write_reg(i, GPMC_CS_CONFIG3, + gpmc_context->cs_context[i].config3); + gpmc_cs_write_reg(i, GPMC_CS_CONFIG4, + gpmc_context->cs_context[i].config4); + gpmc_cs_write_reg(i, GPMC_CS_CONFIG5, + gpmc_context->cs_context[i].config5); + gpmc_cs_write_reg(i, GPMC_CS_CONFIG6, + gpmc_context->cs_context[i].config6); + gpmc_cs_write_reg(i, GPMC_CS_CONFIG7, + gpmc_context->cs_context[i].config7); + } else { + gpmc_cs_write_reg(i, GPMC_CS_CONFIG7, 0); + } + } +} + +static int omap_gpmc_context_notifier(struct notifier_block *nb, + unsigned long cmd, void *v) +{ + struct gpmc_device *gpmc; + + gpmc = container_of(nb, struct gpmc_device, nb); + if (gpmc->is_suspended || pm_runtime_suspended(gpmc->dev)) + return NOTIFY_OK; + + switch (cmd) { + case CPU_CLUSTER_PM_ENTER: + omap3_gpmc_save_context(gpmc); + break; + case CPU_CLUSTER_PM_ENTER_FAILED: /* No need to restore context */ + break; + case CPU_CLUSTER_PM_EXIT: + omap3_gpmc_restore_context(gpmc); + break; + } + + return NOTIFY_OK; +} + static int gpmc_probe(struct platform_device *pdev) { int rc; @@ -2472,6 +2576,9 @@ static int gpmc_probe(struct platform_device *pdev) gpmc_probe_dt_children(pdev); + gpmc->nb.notifier_call = omap_gpmc_context_notifier; + cpu_pm_register_notifier(&gpmc->nb); + return 0; gpio_init_failed: @@ -2486,6 +2593,7 @@ static int gpmc_remove(struct platform_device *pdev) { struct gpmc_device *gpmc = platform_get_drvdata(pdev); + cpu_pm_unregister_notifier(&gpmc->nb); gpmc_free_irq(gpmc); gpmc_mem_exit(); pm_runtime_put_sync(&pdev->dev); @@ -2497,15 +2605,23 @@ static int gpmc_remove(struct platform_device *pdev) #ifdef CONFIG_PM_SLEEP static int gpmc_suspend(struct device *dev) { - omap3_gpmc_save_context(); + struct gpmc_device *gpmc = dev_get_drvdata(dev); + + omap3_gpmc_save_context(gpmc); pm_runtime_put_sync(dev); + gpmc->is_suspended = 1; + return 0; } static int gpmc_resume(struct device *dev) { + struct gpmc_device *gpmc = dev_get_drvdata(dev); + pm_runtime_get_sync(dev); - omap3_gpmc_restore_context(); + omap3_gpmc_restore_context(gpmc); + gpmc->is_suspended = 0; + return 0; } #endif @@ -2527,76 +2643,3 @@ static __init int gpmc_init(void) return platform_driver_register(&gpmc_driver); } postcore_initcall(gpmc_init); - -static struct omap3_gpmc_regs gpmc_context; - -void omap3_gpmc_save_context(void) -{ - int i; - - if (!gpmc_base) - return; - - gpmc_context.sysconfig = gpmc_read_reg(GPMC_SYSCONFIG); - gpmc_context.irqenable = gpmc_read_reg(GPMC_IRQENABLE); - gpmc_context.timeout_ctrl = gpmc_read_reg(GPMC_TIMEOUT_CONTROL); - gpmc_context.config = gpmc_read_reg(GPMC_CONFIG); - gpmc_context.prefetch_config1 = gpmc_read_reg(GPMC_PREFETCH_CONFIG1); - gpmc_context.prefetch_config2 = gpmc_read_reg(GPMC_PREFETCH_CONFIG2); - gpmc_context.prefetch_control = gpmc_read_reg(GPMC_PREFETCH_CONTROL); - for (i = 0; i < gpmc_cs_num; i++) { - gpmc_context.cs_context[i].is_valid = gpmc_cs_mem_enabled(i); - if (gpmc_context.cs_context[i].is_valid) { - gpmc_context.cs_context[i].config1 = - gpmc_cs_read_reg(i, GPMC_CS_CONFIG1); - gpmc_context.cs_context[i].config2 = - gpmc_cs_read_reg(i, GPMC_CS_CONFIG2); - gpmc_context.cs_context[i].config3 = - gpmc_cs_read_reg(i, GPMC_CS_CONFIG3); - gpmc_context.cs_context[i].config4 = - gpmc_cs_read_reg(i, GPMC_CS_CONFIG4); - gpmc_context.cs_context[i].config5 = - gpmc_cs_read_reg(i, GPMC_CS_CONFIG5); - gpmc_context.cs_context[i].config6 = - gpmc_cs_read_reg(i, GPMC_CS_CONFIG6); - gpmc_context.cs_context[i].config7 = - gpmc_cs_read_reg(i, GPMC_CS_CONFIG7); - } - } -} - -void omap3_gpmc_restore_context(void) -{ - int i; - - if (!gpmc_base) - return; - - gpmc_write_reg(GPMC_SYSCONFIG, gpmc_context.sysconfig); - gpmc_write_reg(GPMC_IRQENABLE, gpmc_context.irqenable); - gpmc_write_reg(GPMC_TIMEOUT_CONTROL, gpmc_context.timeout_ctrl); - gpmc_write_reg(GPMC_CONFIG, gpmc_context.config); - gpmc_write_reg(GPMC_PREFETCH_CONFIG1, gpmc_context.prefetch_config1); - gpmc_write_reg(GPMC_PREFETCH_CONFIG2, gpmc_context.prefetch_config2); - gpmc_write_reg(GPMC_PREFETCH_CONTROL, gpmc_context.prefetch_control); - for (i = 0; i < gpmc_cs_num; i++) { - if (gpmc_context.cs_context[i].is_valid) { - gpmc_cs_write_reg(i, GPMC_CS_CONFIG1, - gpmc_context.cs_context[i].config1); - gpmc_cs_write_reg(i, GPMC_CS_CONFIG2, - gpmc_context.cs_context[i].config2); - gpmc_cs_write_reg(i, GPMC_CS_CONFIG3, - gpmc_context.cs_context[i].config3); - gpmc_cs_write_reg(i, GPMC_CS_CONFIG4, - gpmc_context.cs_context[i].config4); - gpmc_cs_write_reg(i, GPMC_CS_CONFIG5, - gpmc_context.cs_context[i].config5); - gpmc_cs_write_reg(i, GPMC_CS_CONFIG6, - gpmc_context.cs_context[i].config6); - gpmc_cs_write_reg(i, GPMC_CS_CONFIG7, - gpmc_context.cs_context[i].config7); - } else { - gpmc_cs_write_reg(i, GPMC_CS_CONFIG7, 0); - } - } -} diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h index b7bf735960c2..082841908fe7 100644 --- a/include/linux/omap-gpmc.h +++ b/include/linux/omap-gpmc.h @@ -81,9 +81,6 @@ extern int gpmc_configure(int cmd, int wval); extern void gpmc_read_settings_dt(struct device_node *np, struct gpmc_settings *p); -extern void omap3_gpmc_save_context(void); -extern void omap3_gpmc_restore_context(void); - struct gpmc_timings; struct omap_nand_platform_data; struct omap_onenand_platform_data; -- cgit v1.2.3 From 5fc88f93edf2f797f1aa63334cc6c86f9c15d585 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 28 Jul 2021 18:23:59 +0200 Subject: sk_buff: introduce 'slow_gro' flags The new flag tracks if any state field is set, so that GRO requires 'unusual'/slow prepare steps. Set such flag when a ct entry is attached to the skb, and never clear it. The new bit uses an existing hole into the sk_buff struct RFC -> v1: - use a single state bit, never clear it - avoid moving the _nfct field Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f19190820e63..3ff18300d210 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -689,6 +689,7 @@ typedef unsigned char *sk_buff_data_t; * CHECKSUM_UNNECESSARY (max 3) * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB + * @slow_gro: state present at GRO time, slower prepare step required * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @secmark: security marking @@ -870,6 +871,7 @@ struct sk_buff { #ifdef CONFIG_TLS_DEVICE __u8 decrypted:1; #endif + __u8 slow_gro:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ @@ -4216,6 +4218,7 @@ static inline unsigned long skb_get_nfct(const struct sk_buff *skb) static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) + skb->slow_gro |= !!nfct; skb->_nfct = nfct; #endif } @@ -4375,6 +4378,7 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(dst)); #endif + dst->slow_gro = src->slow_gro; __nf_copy(dst, src, true); } -- cgit v1.2.3 From 8a886b142bd03d36612747e9aefdf0282c8b02dd Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 28 Jul 2021 18:24:00 +0200 Subject: sk_buff: track dst status in slow_gro Similar to the previous patch, but covering the dst field: the slow_gro flag is additionally set when a dst is attached to the skb RFC -> v1: - use the existing flag instead of adding a new one Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ include/net/dst.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3ff18300d210..b1e5bbfcc926 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -992,6 +992,7 @@ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { + skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } @@ -1008,6 +1009,7 @@ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + skb->slow_gro = !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } diff --git a/include/net/dst.h b/include/net/dst.h index 75b1e734e9c2..a057319aabef 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -277,6 +277,7 @@ static inline void skb_dst_drop(struct sk_buff *skb) static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst) { + nskb->slow_gro |= !!refdst; nskb->_skb_refdst = refdst; if (!(nskb->_skb_refdst & SKB_DST_NOREF)) dst_clone(skb_dst(nskb)); @@ -316,6 +317,7 @@ static inline bool skb_dst_force(struct sk_buff *skb) dst = NULL; skb->_skb_refdst = (unsigned long)dst; + skb->slow_gro |= !!dst; } return skb->_skb_refdst != 0UL; -- cgit v1.2.3 From bc49d8169aa72295104f1558830c568efb946315 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 29 Jul 2021 10:20:39 +0800 Subject: mctp: Add MCTP base Add basic Kconfig, an initial (empty) af_mctp source object, and {AF,PF}_MCTP definitions, and the required definitions for a new protocol type. Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- MAINTAINERS | 7 +++++++ include/linux/socket.h | 6 +++++- include/uapi/linux/mctp.h | 15 +++++++++++++++ net/Kconfig | 1 + net/Makefile | 1 + net/core/sock.c | 1 + net/mctp/Kconfig | 13 +++++++++++++ net/mctp/Makefile | 3 +++ net/mctp/af_mctp.c | 13 +++++++++++++ net/socket.c | 1 + security/selinux/hooks.c | 4 +++- security/selinux/include/classmap.h | 4 +++- 12 files changed, 66 insertions(+), 3 deletions(-) create mode 100644 include/uapi/linux/mctp.h create mode 100644 net/mctp/Kconfig create mode 100644 net/mctp/Makefile create mode 100644 net/mctp/af_mctp.c (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 4c32a9c532b7..22a1ff9afd9d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11032,6 +11032,13 @@ F: drivers/mailbox/arm_mhuv2.c F: include/linux/mailbox/arm_mhuv2_message.h F: Documentation/devicetree/bindings/mailbox/arm,mhuv2.yaml +MANAGEMENT COMPONENT TRANSPORT PROTOCOL (MCTP) +M: Jeremy Kerr +M: Matt Johnston +L: netdev@vger.kernel.org +S: Maintained +F: net/mctp/ + MAN-PAGES: MANUAL PAGES FOR LINUX -- Sections 2, 3, 4, 5, and 7 M: Michael Kerrisk L: linux-man@vger.kernel.org diff --git a/include/linux/socket.h b/include/linux/socket.h index 0d8e3dcb7f88..fd9ce51582d8 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -223,8 +223,11 @@ struct ucred { * reuses AF_INET address family */ #define AF_XDP 44 /* XDP sockets */ +#define AF_MCTP 45 /* Management component + * transport protocol + */ -#define AF_MAX 45 /* For now.. */ +#define AF_MAX 46 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -274,6 +277,7 @@ struct ucred { #define PF_QIPCRTR AF_QIPCRTR #define PF_SMC AF_SMC #define PF_XDP AF_XDP +#define PF_MCTP AF_MCTP #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h new file mode 100644 index 000000000000..2640a589c14c --- /dev/null +++ b/include/uapi/linux/mctp.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Management Component Transport Protocol (MCTP) + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#ifndef __UAPI_MCTP_H +#define __UAPI_MCTP_H + +struct sockaddr_mctp { +}; + +#endif /* __UAPI_MCTP_H */ diff --git a/net/Kconfig b/net/Kconfig index c7392c449b25..fb13460c6dab 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -363,6 +363,7 @@ source "net/bluetooth/Kconfig" source "net/rxrpc/Kconfig" source "net/kcm/Kconfig" source "net/strparser/Kconfig" +source "net/mctp/Kconfig" config FIB_RULES bool diff --git a/net/Makefile b/net/Makefile index 9ca9572188fe..fbfeb8a0bb37 100644 --- a/net/Makefile +++ b/net/Makefile @@ -78,3 +78,4 @@ obj-$(CONFIG_QRTR) += qrtr/ obj-$(CONFIG_NET_NCSI) += ncsi/ obj-$(CONFIG_XDP_SOCKETS) += xdp/ obj-$(CONFIG_MPTCP) += mptcp/ +obj-$(CONFIG_MCTP) += mctp/ diff --git a/net/core/sock.c b/net/core/sock.c index a3eea6e0b30a..9671c32e6ef5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -226,6 +226,7 @@ static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ + x "AF_MCTP" , \ x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { diff --git a/net/mctp/Kconfig b/net/mctp/Kconfig new file mode 100644 index 000000000000..2cdf3d0a28c9 --- /dev/null +++ b/net/mctp/Kconfig @@ -0,0 +1,13 @@ + +menuconfig MCTP + depends on NET + tristate "MCTP core protocol support" + help + Management Component Transport Protocol (MCTP) is an in-system + protocol for communicating between management controllers and + their managed devices (peripherals, host processors, etc.). The + protocol is defined by DMTF specification DSP0236. + + This option enables core MCTP support. For communicating with other + devices, you'll want to enable a driver for a specific hardware + channel. diff --git a/net/mctp/Makefile b/net/mctp/Makefile new file mode 100644 index 000000000000..7c056b1b7939 --- /dev/null +++ b/net/mctp/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_MCTP) += mctp.o +mctp-objs := af_mctp.o diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c new file mode 100644 index 000000000000..8f9c77e97357 --- /dev/null +++ b/net/mctp/af_mctp.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Management Component Transport Protocol (MCTP) + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#include + +MODULE_DESCRIPTION("MCTP core"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Jeremy Kerr "); diff --git a/net/socket.c b/net/socket.c index 42665bd99ea4..3c10504e46d9 100644 --- a/net/socket.c +++ b/net/socket.c @@ -212,6 +212,7 @@ static const char * const pf_family_names[] = { [PF_QIPCRTR] = "PF_QIPCRTR", [PF_SMC] = "PF_SMC", [PF_XDP] = "PF_XDP", + [PF_MCTP] = "PF_MCTP", }; /* diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index b0032c42333e..2143f590e3d6 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1330,7 +1330,9 @@ static inline u16 socket_type_to_security_class(int family, int type, int protoc return SECCLASS_SMC_SOCKET; case PF_XDP: return SECCLASS_XDP_SOCKET; -#if PF_MAX > 45 + case PF_MCTP: + return SECCLASS_MCTP_SOCKET; +#if PF_MAX > 46 #error New address family defined, please update this function. #endif } diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index 62d19bccf3de..084757ff4390 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -246,6 +246,8 @@ struct security_class_mapping secclass_map[] = { NULL } }, { "xdp_socket", { COMMON_SOCK_PERMS, NULL } }, + { "mctp_socket", + { COMMON_SOCK_PERMS, NULL } }, { "perf_event", { "open", "cpu", "kernel", "tracepoint", "read", "write", NULL } }, { "lockdown", @@ -255,6 +257,6 @@ struct security_class_mapping secclass_map[] = { { NULL } }; -#if PF_MAX > 45 +#if PF_MAX > 46 #error New address family defined, please update secclass_map. #endif -- cgit v1.2.3 From 583be982d93479ea3d85091b0fd0b01201ede87d Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 29 Jul 2021 10:20:44 +0800 Subject: mctp: Add device handling and netlink interface This change adds the infrastructure for managing MCTP netdevices; we add a pointer to the AF_MCTP-specific data to struct netdevice, and hook up the rtnetlink operations for adding and removing addresses. Includes changes from Matt Johnston . Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- MAINTAINERS | 1 + include/linux/netdevice.h | 4 + include/net/mctp.h | 14 ++ include/net/mctpdevice.h | 35 ++++ include/uapi/linux/if_ether.h | 3 + include/uapi/linux/if_link.h | 10 + include/uapi/linux/mctp.h | 1 + net/mctp/Makefile | 2 +- net/mctp/af_mctp.c | 8 + net/mctp/device.c | 414 ++++++++++++++++++++++++++++++++++++++++++ 10 files changed, 491 insertions(+), 1 deletion(-) create mode 100644 include/net/mctpdevice.h create mode 100644 net/mctp/device.c (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index e95eb3b00cd2..c2943c227ee6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11039,6 +11039,7 @@ L: netdev@vger.kernel.org S: Maintained F: drivers/net/mctp/ F: include/net/mctp.h +F: include/net/mctpdevice.h F: net/mctp/ MAN-PAGES: MANUAL PAGES FOR LINUX -- Sections 2, 3, 4, 5, and 7 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 226bbee06730..d63a94ecbf3b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1823,6 +1823,7 @@ enum netdev_ml_priv_type { * @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network * device struct * @mpls_ptr: mpls_dev struct pointer + * @mctp_ptr: MCTP specific data * * @dev_addr: Hw address (before bcast, * because most packets are unicast) @@ -2110,6 +2111,9 @@ struct net_device { #if IS_ENABLED(CONFIG_MPLS_ROUTING) struct mpls_dev __rcu *mpls_ptr; #endif +#if IS_ENABLED(CONFIG_MCTP) + struct mctp_dev __rcu *mctp_ptr; +#endif /* * Cache lines mostly used on receive path (including eth_type_trans()) diff --git a/include/net/mctp.h b/include/net/mctp.h index 4c01e083be45..61452e03aa85 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -10,6 +10,7 @@ #define __NET_MCTP_H #include +#include /* MCTP packet definitions */ struct mctp_hdr { @@ -32,4 +33,17 @@ struct mctp_hdr { #define MCTP_HDR_TAG_SHIFT 0 #define MCTP_HDR_TAG_MASK GENMASK(2, 0) +static inline bool mctp_address_ok(mctp_eid_t eid) +{ + return eid >= 8 && eid < 255; +} + +static inline struct mctp_hdr *mctp_hdr(struct sk_buff *skb) +{ + return (struct mctp_hdr *)skb_network_header(skb); +} + +void mctp_device_init(void); +void mctp_device_exit(void); + #endif /* __NET_MCTP_H */ diff --git a/include/net/mctpdevice.h b/include/net/mctpdevice.h new file mode 100644 index 000000000000..71a11012fac7 --- /dev/null +++ b/include/net/mctpdevice.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Management Component Transport Protocol (MCTP) - device + * definitions. + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#ifndef __NET_MCTPDEVICE_H +#define __NET_MCTPDEVICE_H + +#include +#include +#include + +struct mctp_dev { + struct net_device *dev; + + unsigned int net; + + /* Only modified under RTNL. Reads have addrs_lock held */ + u8 *addrs; + size_t num_addrs; + spinlock_t addrs_lock; + + struct rcu_head rcu; +}; + +#define MCTP_INITIAL_DEFAULT_NET 1 + +struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev); +struct mctp_dev *__mctp_dev_get(const struct net_device *dev); + +#endif /* __NET_MCTPDEVICE_H */ diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index a0b637911d3c..5f589c7a8382 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -151,6 +151,9 @@ #define ETH_P_MAP 0x00F9 /* Qualcomm multiplexing and * aggregation protocol */ +#define ETH_P_MCTP 0x00FA /* Management component transport + * protocol packets + */ /* * This is an Ethernet frame header. diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4882e81514b6..49b22afab78f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1260,4 +1260,14 @@ struct ifla_rmnet_flags { __u32 mask; }; +/* MCTP section */ + +enum { + IFLA_MCTP_UNSPEC, + IFLA_MCTP_NET, + __IFLA_MCTP_MAX, +}; + +#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 52b54d13f385..a9d8edb3402b 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -26,6 +26,7 @@ struct sockaddr_mctp { }; #define MCTP_NET_ANY 0x0 +#define MCTP_NET_DEFAULT 0x0 #define MCTP_ADDR_NULL 0x00 #define MCTP_ADDR_ANY 0xff diff --git a/net/mctp/Makefile b/net/mctp/Makefile index 7c056b1b7939..2ea98c27b262 100644 --- a/net/mctp/Makefile +++ b/net/mctp/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_MCTP) += mctp.o -mctp-objs := af_mctp.o +mctp-objs := af_mctp.o device.o diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index b3aeca6486e3..401b4fa141a5 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -6,13 +6,18 @@ * Copyright (c) 2021 Google */ +#include #include #include #include #include +#include +#include #include +/* socket implementation */ + struct mctp_sock { struct sock sk; }; @@ -152,6 +157,8 @@ static __init int mctp_init(void) if (rc) goto err_unreg_sock; + mctp_device_init(); + return 0; err_unreg_sock: @@ -162,6 +169,7 @@ err_unreg_sock: static __exit void mctp_exit(void) { + mctp_device_exit(); proto_unregister(&mctp_proto); sock_unregister(PF_MCTP); } diff --git a/net/mctp/device.c b/net/mctp/device.c new file mode 100644 index 000000000000..877abe5312cd --- /dev/null +++ b/net/mctp/device.c @@ -0,0 +1,414 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Management Component Transport Protocol (MCTP) - device implementation. + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +struct mctp_dump_cb { + int h; + int idx; + size_t a_idx; +}; + +/* unlocked: caller must hold rcu_read_lock */ +struct mctp_dev *__mctp_dev_get(const struct net_device *dev) +{ + return rcu_dereference(dev->mctp_ptr); +} + +struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev) +{ + return rtnl_dereference(dev->mctp_ptr); +} + +static void mctp_dev_destroy(struct mctp_dev *mdev) +{ + struct net_device *dev = mdev->dev; + + dev_put(dev); + kfree_rcu(mdev, rcu); +} + +static int mctp_fill_addrinfo(struct sk_buff *skb, struct netlink_callback *cb, + struct mctp_dev *mdev, mctp_eid_t eid) +{ + struct ifaddrmsg *hdr; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + RTM_NEWADDR, sizeof(*hdr), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + hdr = nlmsg_data(nlh); + hdr->ifa_family = AF_MCTP; + hdr->ifa_prefixlen = 0; + hdr->ifa_flags = 0; + hdr->ifa_scope = 0; + hdr->ifa_index = mdev->dev->ifindex; + + if (nla_put_u8(skb, IFA_LOCAL, eid)) + goto cancel; + + if (nla_put_u8(skb, IFA_ADDRESS, eid)) + goto cancel; + + nlmsg_end(skb, nlh); + + return 0; + +cancel: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int mctp_dump_dev_addrinfo(struct mctp_dev *mdev, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct mctp_dump_cb *mcb = (void *)cb->ctx; + int rc = 0; + + for (; mcb->a_idx < mdev->num_addrs; mcb->a_idx++) { + rc = mctp_fill_addrinfo(skb, cb, mdev, mdev->addrs[mcb->a_idx]); + if (rc < 0) + break; + } + + return rc; +} + +static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct mctp_dump_cb *mcb = (void *)cb->ctx; + struct net *net = sock_net(skb->sk); + struct hlist_head *head; + struct net_device *dev; + struct ifaddrmsg *hdr; + struct mctp_dev *mdev; + int ifindex; + int idx, rc; + + hdr = nlmsg_data(cb->nlh); + // filter by ifindex if requested + ifindex = hdr->ifa_index; + + rcu_read_lock(); + for (; mcb->h < NETDEV_HASHENTRIES; mcb->h++, mcb->idx = 0) { + idx = 0; + head = &net->dev_index_head[mcb->h]; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx >= mcb->idx && + (ifindex == 0 || ifindex == dev->ifindex)) { + mdev = __mctp_dev_get(dev); + if (mdev) { + rc = mctp_dump_dev_addrinfo(mdev, + skb, cb); + // Error indicates full buffer, this + // callback will get retried. + if (rc < 0) + goto out; + } + } + idx++; + // reset for next iteration + mcb->a_idx = 0; + } + } +out: + rcu_read_unlock(); + mcb->idx = idx; + + return skb->len; +} + +static const struct nla_policy ifa_mctp_policy[IFA_MAX + 1] = { + [IFA_ADDRESS] = { .type = NLA_U8 }, + [IFA_LOCAL] = { .type = NLA_U8 }, +}; + +static int mctp_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFA_MAX + 1]; + struct net_device *dev; + struct mctp_addr *addr; + struct mctp_dev *mdev; + struct ifaddrmsg *ifm; + unsigned long flags; + u8 *tmp_addrs; + int rc; + + rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy, + extack); + if (rc < 0) + return rc; + + ifm = nlmsg_data(nlh); + + if (tb[IFA_LOCAL]) + addr = nla_data(tb[IFA_LOCAL]); + else if (tb[IFA_ADDRESS]) + addr = nla_data(tb[IFA_ADDRESS]); + else + return -EINVAL; + + /* find device */ + dev = __dev_get_by_index(net, ifm->ifa_index); + if (!dev) + return -ENODEV; + + mdev = mctp_dev_get_rtnl(dev); + if (!mdev) + return -ENODEV; + + if (!mctp_address_ok(addr->s_addr)) + return -EINVAL; + + /* Prevent duplicates. Under RTNL so don't need to lock for reading */ + if (memchr(mdev->addrs, addr->s_addr, mdev->num_addrs)) + return -EEXIST; + + tmp_addrs = kmalloc(mdev->num_addrs + 1, GFP_KERNEL); + if (!tmp_addrs) + return -ENOMEM; + memcpy(tmp_addrs, mdev->addrs, mdev->num_addrs); + tmp_addrs[mdev->num_addrs] = addr->s_addr; + + /* Lock to write */ + spin_lock_irqsave(&mdev->addrs_lock, flags); + mdev->num_addrs++; + swap(mdev->addrs, tmp_addrs); + spin_unlock_irqrestore(&mdev->addrs_lock, flags); + + kfree(tmp_addrs); + + return 0; +} + +static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFA_MAX + 1]; + struct net_device *dev; + struct mctp_addr *addr; + struct mctp_dev *mdev; + struct ifaddrmsg *ifm; + unsigned long flags; + u8 *pos; + int rc; + + rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy, + extack); + if (rc < 0) + return rc; + + ifm = nlmsg_data(nlh); + + if (tb[IFA_LOCAL]) + addr = nla_data(tb[IFA_LOCAL]); + else if (tb[IFA_ADDRESS]) + addr = nla_data(tb[IFA_ADDRESS]); + else + return -EINVAL; + + /* find device */ + dev = __dev_get_by_index(net, ifm->ifa_index); + if (!dev) + return -ENODEV; + + mdev = mctp_dev_get_rtnl(dev); + if (!mdev) + return -ENODEV; + + pos = memchr(mdev->addrs, addr->s_addr, mdev->num_addrs); + if (!pos) + return -ENOENT; + + spin_lock_irqsave(&mdev->addrs_lock, flags); + memmove(pos, pos + 1, mdev->num_addrs - 1 - (pos - mdev->addrs)); + mdev->num_addrs--; + spin_unlock_irqrestore(&mdev->addrs_lock, flags); + + return 0; +} + +static struct mctp_dev *mctp_add_dev(struct net_device *dev) +{ + struct mctp_dev *mdev; + + ASSERT_RTNL(); + + mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); + if (!mdev) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&mdev->addrs_lock); + + mdev->net = MCTP_INITIAL_DEFAULT_NET; + + /* associate to net_device */ + rcu_assign_pointer(dev->mctp_ptr, mdev); + dev_hold(dev); + mdev->dev = dev; + + return mdev; +} + +static int mctp_fill_link_af(struct sk_buff *skb, + const struct net_device *dev, u32 ext_filter_mask) +{ + struct mctp_dev *mdev; + + mdev = mctp_dev_get_rtnl(dev); + if (!mdev) + return -ENODATA; + if (nla_put_u32(skb, IFLA_MCTP_NET, mdev->net)) + return -EMSGSIZE; + return 0; +} + +static size_t mctp_get_link_af_size(const struct net_device *dev, + u32 ext_filter_mask) +{ + struct mctp_dev *mdev; + unsigned int ret; + + /* caller holds RCU */ + mdev = __mctp_dev_get(dev); + if (!mdev) + return 0; + ret = nla_total_size(4); /* IFLA_MCTP_NET */ + return ret; +} + +static const struct nla_policy ifla_af_mctp_policy[IFLA_MCTP_MAX + 1] = { + [IFLA_MCTP_NET] = { .type = NLA_U32 }, +}; + +static int mctp_set_link_af(struct net_device *dev, const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_MCTP_MAX + 1]; + struct mctp_dev *mdev; + int rc; + + rc = nla_parse_nested(tb, IFLA_MCTP_MAX, attr, ifla_af_mctp_policy, + NULL); + if (rc) + return rc; + + mdev = mctp_dev_get_rtnl(dev); + if (!mdev) + return 0; + + if (tb[IFLA_MCTP_NET]) + WRITE_ONCE(mdev->net, nla_get_u32(tb[IFLA_MCTP_NET])); + + return 0; +} + +static void mctp_unregister(struct net_device *dev) +{ + struct mctp_dev *mdev; + + mdev = mctp_dev_get_rtnl(dev); + + if (!mdev) + return; + + RCU_INIT_POINTER(mdev->dev->mctp_ptr, NULL); + + kfree(mdev->addrs); + + mctp_dev_destroy(mdev); +} + +static int mctp_register(struct net_device *dev) +{ + struct mctp_dev *mdev; + + /* Already registered? */ + if (rtnl_dereference(dev->mctp_ptr)) + return 0; + + /* only register specific types; MCTP-specific and loopback for now */ + if (dev->type != ARPHRD_MCTP && dev->type != ARPHRD_LOOPBACK) + return 0; + + mdev = mctp_add_dev(dev); + if (IS_ERR(mdev)) + return PTR_ERR(mdev); + + return 0; +} + +static int mctp_dev_notify(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + int rc; + + switch (event) { + case NETDEV_REGISTER: + rc = mctp_register(dev); + if (rc) + return notifier_from_errno(rc); + break; + case NETDEV_UNREGISTER: + mctp_unregister(dev); + break; + } + + return NOTIFY_OK; +} + +static struct rtnl_af_ops mctp_af_ops = { + .family = AF_MCTP, + .fill_link_af = mctp_fill_link_af, + .get_link_af_size = mctp_get_link_af_size, + .set_link_af = mctp_set_link_af, +}; + +static struct notifier_block mctp_dev_nb = { + .notifier_call = mctp_dev_notify, + .priority = ADDRCONF_NOTIFY_PRIORITY, +}; + +void __init mctp_device_init(void) +{ + register_netdevice_notifier(&mctp_dev_nb); + + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_GETADDR, + NULL, mctp_dump_addrinfo, 0); + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_NEWADDR, + mctp_rtm_newaddr, NULL, 0); + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_DELADDR, + mctp_rtm_deladdr, NULL, 0); + rtnl_af_register(&mctp_af_ops); +} + +void __exit mctp_device_exit(void) +{ + rtnl_af_unregister(&mctp_af_ops); + rtnl_unregister(PF_MCTP, RTM_DELADDR); + rtnl_unregister(PF_MCTP, RTM_NEWADDR); + rtnl_unregister(PF_MCTP, RTM_GETADDR); + + unregister_netdevice_notifier(&mctp_dev_nb); +} -- cgit v1.2.3 From c9110dfcfccb3f31eda47a36ed0a022e390d1417 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 27 Jul 2021 14:06:34 +0100 Subject: printk: Remove console_silent() It' unused since removal of mn10300: commit 739d875dd698 ("mn10300: Remove the architecture") x86 stopped using it in v2.6.12 (see history git): commit 7574828b3dbb ("[PATCH] x86_64: add nmi button support") Let's clean it up from the header. Signed-off-by: Dmitry Safonov Reviewed-by: Petr Mladek Reviewed-by: Sergey Senozhatsky Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210727130635.675184-2-dima@arista.com --- include/linux/printk.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 1790a5521fd9..f3f1a1eb19bd 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -69,11 +69,6 @@ extern int console_printk[]; #define minimum_console_loglevel (console_printk[2]) #define default_console_loglevel (console_printk[3]) -static inline void console_silent(void) -{ - console_loglevel = CONSOLE_LOGLEVEL_SILENT; -} - static inline void console_verbose(void) { if (console_loglevel) -- cgit v1.2.3 From 10102a890b543a8a08457dc69fa55bc032403c7d Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 27 Jul 2021 14:06:35 +0100 Subject: printk: Add printk.console_no_auto_verbose boot parameter console_verbose() increases console loglevel to CONSOLE_LOGLEVEL_MOTORMOUTH, which provides more information to debug a panic/oops. Unfortunately, in Arista we maintain some DUTs (Device Under Test) that are configured to have 9600 baud rate. While verbose console messages have their value to post-analyze crashes, on such setup they: - may prevent panic/oops messages being printed - take too long to flush on console resulting in watchdog reboot In all our setups we use kdump which saves dmesg buffer after panic, so in reality those extra messages on console provide no additional value, but rather add risk of not getting to __crash_kexec(). Provide printk.console_no_auto_verbose boot parameter, which allows to switch off printk being verbose on oops/panic/lockdep. Cc: Andrew Morton Cc: John Ogness Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Steven Rostedt Signed-off-by: Dmitry Safonov Suggested-by: Petr Mladek Reviewed-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Tested-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210727130635.675184-3-dima@arista.com --- Documentation/admin-guide/kernel-parameters.txt | 9 +++++++++ include/linux/printk.h | 6 +----- kernel/printk/printk.c | 12 ++++++++++++ 3 files changed, 22 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 26453f250683..fdd80888217a 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4101,6 +4101,15 @@ Format: (1/Y/y=enable, 0/N/n=disable) default: disabled + printk.console_no_auto_verbose= + Disable console loglevel raise on oops, panic + or lockdep-detected issues (only if lock debug is on). + With an exception to setups with low baudrate on + serial console, keeping this 0 is a good choice + in order to provide more debug information. + Format: + default: 0 (auto_verbose is enabled) + printk.devkmsg={on,off,ratelimit} Control writing to /dev/kmsg. on - unlimited logging to /dev/kmsg from userspace diff --git a/include/linux/printk.h b/include/linux/printk.h index f3f1a1eb19bd..a5e1c5adfc3f 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -69,11 +69,7 @@ extern int console_printk[]; #define minimum_console_loglevel (console_printk[2]) #define default_console_loglevel (console_printk[3]) -static inline void console_verbose(void) -{ - if (console_loglevel) - console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; -} +extern void console_verbose(void); /* strlen("ratelimit") + 1 */ #define DEVKMSG_STR_MAX_SIZE 10 diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 142a58d124d9..a6b94c3c5ac5 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2404,6 +2404,18 @@ module_param_named(console_suspend, console_suspend_enabled, MODULE_PARM_DESC(console_suspend, "suspend console during suspend" " and hibernate operations"); +static bool printk_console_no_auto_verbose; + +void console_verbose(void) +{ + if (console_loglevel && !printk_console_no_auto_verbose) + console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; +} +EXPORT_SYMBOL_GPL(console_verbose); + +module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644); +MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc"); + /** * suspend_console - suspend the console subsystem * -- cgit v1.2.3 From 0912ef4855e8e463a8d724efd6bee08e9b5d3f1e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 29 Jul 2021 12:28:03 +0200 Subject: mei: constify passed buffers and structures Buffers and structures passed to MEI bus and client API can be made const for safer code and clear indication that it is not modified. Acked-by: Arnd Bergmann Acked-by: Tomas Winkler Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20210729102803.46289-1-krzysztof.kozlowski@canonical.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/bus.c | 18 +++++++++--------- drivers/misc/mei/client.h | 2 +- drivers/misc/mei/mei_dev.h | 2 +- include/linux/mei_cl_bus.h | 9 +++++---- 4 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 935acc6bbf3c..09188d9afc06 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -31,7 +31,7 @@ * * Return: written size bytes or < 0 on error */ -ssize_t __mei_cl_send(struct mei_cl *cl, u8 *buf, size_t length, u8 vtag, +ssize_t __mei_cl_send(struct mei_cl *cl, const u8 *buf, size_t length, u8 vtag, unsigned int mode) { struct mei_device *bus; @@ -232,8 +232,8 @@ out: * * < 0 on error */ -ssize_t mei_cldev_send_vtag(struct mei_cl_device *cldev, u8 *buf, size_t length, - u8 vtag) +ssize_t mei_cldev_send_vtag(struct mei_cl_device *cldev, const u8 *buf, + size_t length, u8 vtag) { struct mei_cl *cl = cldev->cl; @@ -296,7 +296,7 @@ EXPORT_SYMBOL_GPL(mei_cldev_recv_nonblock_vtag); * * written size in bytes * * < 0 on error */ -ssize_t mei_cldev_send(struct mei_cl_device *cldev, u8 *buf, size_t length) +ssize_t mei_cldev_send(struct mei_cl_device *cldev, const u8 *buf, size_t length) { return mei_cldev_send_vtag(cldev, buf, length, 0); } @@ -552,7 +552,7 @@ EXPORT_SYMBOL_GPL(mei_cldev_ver); * * Return: true if me client is initialized and connected */ -bool mei_cldev_enabled(struct mei_cl_device *cldev) +bool mei_cldev_enabled(const struct mei_cl_device *cldev) { return mei_cl_is_connected(cldev->cl); } @@ -771,8 +771,8 @@ EXPORT_SYMBOL_GPL(mei_cldev_disable); * Return: id on success; NULL if no id is matching */ static const -struct mei_cl_device_id *mei_cl_device_find(struct mei_cl_device *cldev, - struct mei_cl_driver *cldrv) +struct mei_cl_device_id *mei_cl_device_find(const struct mei_cl_device *cldev, + const struct mei_cl_driver *cldrv) { const struct mei_cl_device_id *id; const uuid_le *uuid; @@ -815,8 +815,8 @@ struct mei_cl_device_id *mei_cl_device_find(struct mei_cl_device *cldev, */ static int mei_cl_device_match(struct device *dev, struct device_driver *drv) { - struct mei_cl_device *cldev = to_mei_cl_device(dev); - struct mei_cl_driver *cldrv = to_mei_cl_driver(drv); + const struct mei_cl_device *cldev = to_mei_cl_device(dev); + const struct mei_cl_driver *cldrv = to_mei_cl_driver(drv); const struct mei_cl_device_id *found_id; if (!cldev) diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h index b12cdcde9436..418056fb1489 100644 --- a/drivers/misc/mei/client.h +++ b/drivers/misc/mei/client.h @@ -160,7 +160,7 @@ int mei_cl_vt_support_check(const struct mei_cl *cl); * * Return: true if the host client is connected */ -static inline bool mei_cl_is_connected(struct mei_cl *cl) +static inline bool mei_cl_is_connected(const struct mei_cl *cl) { return cl->state == MEI_FILE_CONNECTED; } diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h index b7b6ef344e80..694f866f87ef 100644 --- a/drivers/misc/mei/mei_dev.h +++ b/drivers/misc/mei/mei_dev.h @@ -356,7 +356,7 @@ struct mei_hw_ops { /* MEI bus API*/ void mei_cl_bus_rescan_work(struct work_struct *work); void mei_cl_bus_dev_fixup(struct mei_cl_device *dev); -ssize_t __mei_cl_send(struct mei_cl *cl, u8 *buf, size_t length, u8 vtag, +ssize_t __mei_cl_send(struct mei_cl *cl, const u8 *buf, size_t length, u8 vtag, unsigned int mode); ssize_t __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length, u8 *vtag, unsigned int mode, unsigned long timeout); diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 07f5ef8fc456..c6786c12b207 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -91,12 +91,13 @@ void mei_cldev_driver_unregister(struct mei_cl_driver *cldrv); mei_cldev_driver_register,\ mei_cldev_driver_unregister) -ssize_t mei_cldev_send(struct mei_cl_device *cldev, u8 *buf, size_t length); +ssize_t mei_cldev_send(struct mei_cl_device *cldev, const u8 *buf, + size_t length); ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length); ssize_t mei_cldev_recv_nonblock(struct mei_cl_device *cldev, u8 *buf, size_t length); -ssize_t mei_cldev_send_vtag(struct mei_cl_device *cldev, u8 *buf, size_t length, - u8 vtag); +ssize_t mei_cldev_send_vtag(struct mei_cl_device *cldev, const u8 *buf, + size_t length, u8 vtag); ssize_t mei_cldev_recv_vtag(struct mei_cl_device *cldev, u8 *buf, size_t length, u8 *vtag); ssize_t mei_cldev_recv_nonblock_vtag(struct mei_cl_device *cldev, u8 *buf, @@ -114,6 +115,6 @@ void mei_cldev_set_drvdata(struct mei_cl_device *cldev, void *data); int mei_cldev_enable(struct mei_cl_device *cldev); int mei_cldev_disable(struct mei_cl_device *cldev); -bool mei_cldev_enabled(struct mei_cl_device *cldev); +bool mei_cldev_enabled(const struct mei_cl_device *cldev); #endif /* _LINUX_MEI_CL_BUS_H */ -- cgit v1.2.3 From 4e804c39f1be4498d80f379e5b7bc6d4f80f813c Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Wed, 28 Jul 2021 06:12:51 +0200 Subject: gpiolib: convert 'devprop_gpiochip_set_names' to support multiple gpiochip banks per device The default gpiolib-of implementation does not work with the multiple gpiochip banks per device structure used for example by the gpio-mt7621 and gpio-brcmstb drivers. To fix these kind of situations driver code is forced to fill the names to avoid the gpiolib code to set names repeated along the banks. Instead of continue with that antipattern fix the gpiolib core function to get expected behaviour for every single situation adding a field 'offset' in the gpiochip structure. Doing in this way, we can assume this offset will be zero for normal driver code where only one gpiochip bank per device is used but can be set explicitly in those drivers that really need more than one gpiochip. Reviewed-by: Andy Shevchenko Reviewed-by: Gregory Fong Signed-off-by: Sergio Paracuellos Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib.c | 32 +++++++++++++++++++++++++++----- include/linux/gpio/driver.h | 4 ++++ 2 files changed, 31 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 27c07108496d..d1b9b721218f 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -382,10 +382,18 @@ static int devprop_gpiochip_set_names(struct gpio_chip *chip) if (count < 0) return 0; - if (count > gdev->ngpio) { - dev_warn(&gdev->dev, "gpio-line-names is length %d but should be at most length %d", - count, gdev->ngpio); - count = gdev->ngpio; + /* + * When offset is set in the driver side we assume the driver internally + * is using more than one gpiochip per the same device. We have to stop + * setting friendly names if the specified ones with 'gpio-line-names' + * are less than the offset in the device itself. This means all the + * lines are not present for every single pin within all the internal + * gpiochips. + */ + if (count <= chip->offset) { + dev_warn(&gdev->dev, "gpio-line-names too short (length %d), cannot map names for the gpiochip at offset %u\n", + count, chip->offset); + return 0; } names = kcalloc(count, sizeof(*names), GFP_KERNEL); @@ -400,8 +408,22 @@ static int devprop_gpiochip_set_names(struct gpio_chip *chip) return ret; } + /* + * When more that one gpiochip per device is used, 'count' can + * contain at most number gpiochips x chip->ngpio. We have to + * correctly distribute all defined lines taking into account + * chip->offset as starting point from where we will assign + * the names to pins from the 'names' array. Since property + * 'gpio-line-names' cannot contains gaps, we have to be sure + * we only assign those pins that really exists since chip->ngpio + * can be different of the chip->offset. + */ + count = (count > chip->offset) ? count - chip->offset : count; + if (count > chip->ngpio) + count = chip->ngpio; + for (i = 0; i < count; i++) - gdev->descs[i].name = names[i]; + gdev->descs[i].name = names[chip->offset + i]; kfree(names); diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 3a268781fcec..a0f9901dcae6 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -312,6 +312,9 @@ struct gpio_irq_chip { * get rid of the static GPIO number space in the long run. * @ngpio: the number of GPIOs handled by this controller; the last GPIO * handled is (base + ngpio - 1). + * @offset: when multiple gpio chips belong to the same device this + * can be used as offset within the device so friendly names can + * be properly assigned. * @names: if set, must be an array of strings to use as alternative * names for the GPIOs in this chip. Any entry in the array * may be NULL if there is no alias for the GPIO, however the @@ -398,6 +401,7 @@ struct gpio_chip { int base; u16 ngpio; + u16 offset; const char *const *names; bool can_sleep; -- cgit v1.2.3 From 1604986c3e6bd84f3f3fd709c1a619c6fc9d79a9 Mon Sep 17 00:00:00 2001 From: Martin Hundebøll Date: Fri, 16 Jul 2021 15:54:39 +0200 Subject: fpga: dfl: expose feature revision from struct dfl_device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DFL device drivers have a common need for checking feature revision information from the DFL header, as well as other common DFL information like the already exposed feature id and type. This patch exposes the feature revision information directly via the DFL device data structure. Since the DFL core code has already read the DFL header, this this patch saves additional mmio reads from DFL device drivers too. Acked-by: Wu Hao Acked-by: Matthew Gerlach Signed-off-by: Martin Hundebøll Signed-off-by: Moritz Fischer --- drivers/fpga/dfl.c | 27 +++++++++++++++++---------- drivers/fpga/dfl.h | 1 + include/linux/dfl.h | 1 + 3 files changed, 19 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index 511b20ff35a3..e73a70053906 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -381,6 +381,7 @@ dfl_dev_add(struct dfl_feature_platform_data *pdata, ddev->type = feature_dev_id_type(pdev); ddev->feature_id = feature->id; + ddev->revision = feature->revision; ddev->cdev = pdata->dfl_cdev; /* add mmio resource */ @@ -717,6 +718,7 @@ struct build_feature_devs_info { */ struct dfl_feature_info { u16 fid; + u8 revision; struct resource mmio_res; void __iomem *ioaddr; struct list_head node; @@ -796,6 +798,7 @@ static int build_info_commit_dev(struct build_feature_devs_info *binfo) /* save resource information for each feature */ feature->dev = fdev; feature->id = finfo->fid; + feature->revision = finfo->revision; /* * the FIU header feature has some fundamental functions (sriov @@ -910,19 +913,17 @@ static void build_info_free(struct build_feature_devs_info *binfo) devm_kfree(binfo->dev, binfo); } -static inline u32 feature_size(void __iomem *start) +static inline u32 feature_size(u64 value) { - u64 v = readq(start + DFH); - u32 ofst = FIELD_GET(DFH_NEXT_HDR_OFST, v); + u32 ofst = FIELD_GET(DFH_NEXT_HDR_OFST, value); /* workaround for private features with invalid size, use 4K instead */ return ofst ? ofst : 4096; } -static u16 feature_id(void __iomem *start) +static u16 feature_id(u64 value) { - u64 v = readq(start + DFH); - u16 id = FIELD_GET(DFH_ID, v); - u8 type = FIELD_GET(DFH_TYPE, v); + u16 id = FIELD_GET(DFH_ID, value); + u8 type = FIELD_GET(DFH_TYPE, value); if (type == DFH_TYPE_FIU) return FEATURE_ID_FIU_HEADER; @@ -1021,10 +1022,15 @@ create_feature_instance(struct build_feature_devs_info *binfo, unsigned int irq_base, nr_irqs; struct dfl_feature_info *finfo; int ret; + u8 revision; + u64 v; + + v = readq(binfo->ioaddr + ofst); + revision = FIELD_GET(DFH_REVISION, v); /* read feature size and id if inputs are invalid */ - size = size ? size : feature_size(binfo->ioaddr + ofst); - fid = fid ? fid : feature_id(binfo->ioaddr + ofst); + size = size ? size : feature_size(v); + fid = fid ? fid : feature_id(v); if (binfo->len - ofst < size) return -EINVAL; @@ -1038,6 +1044,7 @@ create_feature_instance(struct build_feature_devs_info *binfo, return -ENOMEM; finfo->fid = fid; + finfo->revision = revision; finfo->mmio_res.start = binfo->start + ofst; finfo->mmio_res.end = finfo->mmio_res.start + size - 1; finfo->mmio_res.flags = IORESOURCE_MEM; @@ -1166,7 +1173,7 @@ static int parse_feature_private(struct build_feature_devs_info *binfo, { if (!is_feature_dev_detected(binfo)) { dev_err(binfo->dev, "the private feature 0x%x does not belong to any AFU.\n", - feature_id(binfo->ioaddr + ofst)); + feature_id(readq(binfo->ioaddr + ofst))); return -EINVAL; } diff --git a/drivers/fpga/dfl.h b/drivers/fpga/dfl.h index dac9c3d45e6c..53572c7aced0 100644 --- a/drivers/fpga/dfl.h +++ b/drivers/fpga/dfl.h @@ -243,6 +243,7 @@ struct dfl_feature_irq_ctx { struct dfl_feature { struct platform_device *dev; u16 id; + u8 revision; int resource_index; void __iomem *ioaddr; struct dfl_feature_irq_ctx *irq_ctx; diff --git a/include/linux/dfl.h b/include/linux/dfl.h index 6cc10982351a..431636a0dc78 100644 --- a/include/linux/dfl.h +++ b/include/linux/dfl.h @@ -38,6 +38,7 @@ struct dfl_device { int id; u16 type; u16 feature_id; + u8 revision; struct resource mmio_res; int *irqs; unsigned int num_irqs; -- cgit v1.2.3 From d5ee8e750c9449e9849a09ce6fb6b8adeaa66adc Mon Sep 17 00:00:00 2001 From: Xiyu Yang Date: Tue, 20 Jul 2021 11:05:11 -0400 Subject: padata: Convert from atomic_t to refcount_t on parallel_data->refcnt refcount_t type and corresponding API can protect refcounters from accidental underflow and overflow and further use-after-free situations. Signed-off-by: Xiyu Yang Signed-off-by: Xin Tan Acked-by: Daniel Jordan Signed-off-by: Herbert Xu --- include/linux/padata.h | 3 ++- kernel/padata.c | 8 ++++---- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index a433f13fc4bf..495b16b6b4d7 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -12,6 +12,7 @@ #ifndef PADATA_H #define PADATA_H +#include #include #include #include @@ -96,7 +97,7 @@ struct parallel_data { struct padata_shell *ps; struct padata_list __percpu *reorder_list; struct padata_serial_queue __percpu *squeue; - atomic_t refcnt; + refcount_t refcnt; unsigned int seq_nr; unsigned int processed; int cpu; diff --git a/kernel/padata.c b/kernel/padata.c index d4d3ba6e1728..378c36080781 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -211,7 +211,7 @@ int padata_do_parallel(struct padata_shell *ps, if ((pinst->flags & PADATA_RESET)) goto out; - atomic_inc(&pd->refcnt); + refcount_inc(&pd->refcnt); padata->pd = pd; padata->cb_cpu = *cb_cpu; @@ -383,7 +383,7 @@ static void padata_serial_worker(struct work_struct *serial_work) } local_bh_enable(); - if (atomic_sub_and_test(cnt, &pd->refcnt)) + if (refcount_sub_and_test(cnt, &pd->refcnt)) padata_free_pd(pd); } @@ -593,7 +593,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps) padata_init_reorder_list(pd); padata_init_squeues(pd); pd->seq_nr = -1; - atomic_set(&pd->refcnt, 1); + refcount_set(&pd->refcnt, 1); spin_lock_init(&pd->lock); pd->cpu = cpumask_first(pd->cpumask.pcpu); INIT_WORK(&pd->reorder_work, invoke_padata_reorder); @@ -667,7 +667,7 @@ static int padata_replace(struct padata_instance *pinst) synchronize_rcu(); list_for_each_entry_continue_reverse(ps, &pinst->pslist, list) - if (atomic_dec_and_test(&ps->opd->refcnt)) + if (refcount_dec_and_test(&ps->opd->refcnt)) padata_free_pd(ps->opd); pinst->flags &= ~PADATA_RESET; -- cgit v1.2.3 From bc830525615df6b6b1793ac23750f32695903fd0 Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Thu, 29 Jul 2021 15:48:54 +0800 Subject: net: netlink: Remove unused function lockdep_genl_is_held() and its caller arm not used now, just remove them. Signed-off-by: Yajun Deng Link: https://lore.kernel.org/r/20210729074854.8968-1-yajun.deng@linux.dev Signed-off-by: Jakub Kicinski --- include/linux/genetlink.h | 23 ----------------------- net/netlink/genetlink.c | 8 -------- 2 files changed, 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index bc738504ab4a..c285968e437a 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -8,34 +8,11 @@ /* All generic netlink requests are serialized by a global lock. */ extern void genl_lock(void); extern void genl_unlock(void); -#ifdef CONFIG_LOCKDEP -extern bool lockdep_genl_is_held(void); -#endif /* for synchronisation between af_netlink and genetlink */ extern atomic_t genl_sk_destructing_cnt; extern wait_queue_head_t genl_sk_destructing_waitq; -/** - * rcu_dereference_genl - rcu_dereference with debug checking - * @p: The pointer to read, prior to dereferencing - * - * Do an rcu_dereference(p), but check caller either holds rcu_read_lock() - * or genl mutex. Note : Please prefer genl_dereference() or rcu_dereference() - */ -#define rcu_dereference_genl(p) \ - rcu_dereference_check(p, lockdep_genl_is_held()) - -/** - * genl_dereference - fetch RCU pointer when updates are prevented by genl mutex - * @p: The pointer to read, prior to dereferencing - * - * Return the value of the specified RCU-protected pointer, but omit - * the READ_ONCE(), because caller holds genl mutex. - */ -#define genl_dereference(p) \ - rcu_dereference_protected(p, lockdep_genl_is_held()) - #define MODULE_ALIAS_GENL_FAMILY(family)\ MODULE_ALIAS_NET_PF_PROTO_NAME(PF_NETLINK, NETLINK_GENERIC, "-family-" family) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index ae58da608a31..1afca2a6c2ac 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -40,14 +40,6 @@ void genl_unlock(void) } EXPORT_SYMBOL(genl_unlock); -#ifdef CONFIG_LOCKDEP -bool lockdep_genl_is_held(void) -{ - return lockdep_is_held(&genl_mutex); -} -EXPORT_SYMBOL(lockdep_genl_is_held); -#endif - static void genl_lock_all(void) { down_write(&cb_lock); -- cgit v1.2.3 From a432934a30679c0e3c47b87f13e4901bc1a3fc03 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 30 Jul 2021 18:30:53 +0200 Subject: sk_buff: avoid potentially clearing 'slow_gro' field If skb_dst_set_noref() is invoked with a NULL dst, the 'slow_gro' field is cleared, too. That could lead to wrong behavior if the skb later enters the GRO stage. Fix the potential issue replacing preserving a non-zero value of the 'slow_gro' field. Additionally, fix a comment typo. Reported-by: Sabrina Dubroca Reported-by: Jakub Kicinski Fixes: 8a886b142bd0 ("sk_buff: track dst status in slow_gro") Signed-off-by: Paolo Abeni Link: https://lore.kernel.org/r/aa42529252dc8bb02bd42e8629427040d1058537.1627662501.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 +- net/core/dev.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b1e5bbfcc926..2bcdc8cd38be 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1009,7 +1009,7 @@ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); - skb->slow_gro = !!dst; + skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } diff --git a/net/core/dev.c b/net/core/dev.c index b51e41d0a7fe..64e1a5f63f93 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6022,7 +6022,7 @@ static void gro_list_prepare(const struct list_head *head, skb_mac_header(skb), maclen); - /* in most common scenarions _state is 0 + /* in most common scenarions 'slow_gro' is 0 * otherwise we are already on some slower paths * either skip all the infrequent tests altogether or * avoid trying too hard to skip each of them individually -- cgit v1.2.3 From ba51bdafaafc065019c6f6a2cdae006d176cee48 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 5 Jul 2021 15:02:43 +0200 Subject: scsi: sr: cdrom: Move cdrom_read_cdda_bpc() into the sr driver cdrom_read_cdda_bpc() relies on sending SCSI command to the low level driver using a REQ_OP_SCSI_IN request. This isn't generic block layer functionality, so move the actual low-level code into the sr driver and call it through a new read_cdda_bpc method in the cdrom_device_ops structure. With this the CDROM code does not have to pull in scsi_normalize_sense() and depend on CONFIG_SCSI_COMMON. Link: https://lore.kernel.org/r/20210730072752.GB23847%40lst.de Tested-by: Anders Roxell Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/cdrom/cdrom.c | 71 ++++++--------------------------------------------- drivers/scsi/sr.c | 56 +++++++++++++++++++++++++++++++++++++++- include/linux/cdrom.h | 6 +++-- 3 files changed, 67 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 8882b311bafd..bd2e5b1560f5 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -629,7 +629,7 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) if (CDROM_CAN(CDC_MRW_W)) cdi->exit = cdrom_mrw_exit; - if (cdi->disk) + if (cdi->ops->read_cdda_bpc) cdi->cdda_method = CDDA_BPC_FULL; else cdi->cdda_method = CDDA_OLD; @@ -2159,81 +2159,26 @@ static int cdrom_read_cdda_old(struct cdrom_device_info *cdi, __u8 __user *ubuf, static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf, int lba, int nframes) { - struct request_queue *q = cdi->disk->queue; - struct request *rq; - struct scsi_request *req; - struct bio *bio; - unsigned int len; + int max_frames = (queue_max_sectors(cdi->disk->queue) << 9) / + CD_FRAMESIZE_RAW; int nr, ret = 0; - if (!q) - return -ENXIO; - - if (!blk_queue_scsi_passthrough(q)) { - WARN_ONCE(true, - "Attempt read CDDA info through a non-SCSI queue\n"); - return -EINVAL; - } - cdi->last_sense = 0; while (nframes) { - nr = nframes; if (cdi->cdda_method == CDDA_BPC_SINGLE) nr = 1; - if (nr * CD_FRAMESIZE_RAW > (queue_max_sectors(q) << 9)) - nr = (queue_max_sectors(q) << 9) / CD_FRAMESIZE_RAW; - - len = nr * CD_FRAMESIZE_RAW; - - rq = blk_get_request(q, REQ_OP_DRV_IN, 0); - if (IS_ERR(rq)) { - ret = PTR_ERR(rq); - break; - } - req = scsi_req(rq); - - ret = blk_rq_map_user(q, rq, NULL, ubuf, len, GFP_KERNEL); - if (ret) { - blk_put_request(rq); - break; - } - - req->cmd[0] = GPCMD_READ_CD; - req->cmd[1] = 1 << 2; - req->cmd[2] = (lba >> 24) & 0xff; - req->cmd[3] = (lba >> 16) & 0xff; - req->cmd[4] = (lba >> 8) & 0xff; - req->cmd[5] = lba & 0xff; - req->cmd[6] = (nr >> 16) & 0xff; - req->cmd[7] = (nr >> 8) & 0xff; - req->cmd[8] = nr & 0xff; - req->cmd[9] = 0xf8; - - req->cmd_len = 12; - rq->timeout = 60 * HZ; - bio = rq->bio; - - blk_execute_rq(cdi->disk, rq, 0); - if (scsi_req(rq)->result) { - struct scsi_sense_hdr sshdr; - - ret = -EIO; - scsi_normalize_sense(req->sense, req->sense_len, - &sshdr); - cdi->last_sense = sshdr.sense_key; - } - - if (blk_rq_unmap_user(bio)) - ret = -EFAULT; - blk_put_request(rq); + else + nr = min(nframes, max_frames); + ret = cdi->ops->read_cdda_bpc(cdi, ubuf, lba, nr, + &cdi->last_sense); if (ret) break; nframes -= nr; lba += nr; - ubuf += len; + ubuf += (nr * CD_FRAMESIZE_RAW); } return ret; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index b98e77fe700b..6203a8b58d40 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -120,6 +120,8 @@ static void get_capabilities(struct scsi_cd *); static unsigned int sr_check_events(struct cdrom_device_info *cdi, unsigned int clearing, int slot); static int sr_packet(struct cdrom_device_info *, struct packet_command *); +static int sr_read_cdda_bpc(struct cdrom_device_info *cdi, void __user *ubuf, + u32 lba, u32 nr, u8 *last_sense); static const struct cdrom_device_ops sr_dops = { .open = sr_open, @@ -133,8 +135,9 @@ static const struct cdrom_device_ops sr_dops = { .get_mcn = sr_get_mcn, .reset = sr_reset, .audio_ioctl = sr_audio_ioctl, - .capability = SR_CAPABILITIES, .generic_packet = sr_packet, + .read_cdda_bpc = sr_read_cdda_bpc, + .capability = SR_CAPABILITIES, }; static void sr_kref_release(struct kref *kref); @@ -951,6 +954,57 @@ static int sr_packet(struct cdrom_device_info *cdi, return cgc->stat; } +static int sr_read_cdda_bpc(struct cdrom_device_info *cdi, void __user *ubuf, + u32 lba, u32 nr, u8 *last_sense) +{ + struct gendisk *disk = cdi->disk; + u32 len = nr * CD_FRAMESIZE_RAW; + struct scsi_request *req; + struct request *rq; + struct bio *bio; + int ret; + + rq = blk_get_request(disk->queue, REQ_OP_DRV_IN, 0); + if (IS_ERR(rq)) + return PTR_ERR(rq); + req = scsi_req(rq); + + ret = blk_rq_map_user(disk->queue, rq, NULL, ubuf, len, GFP_KERNEL); + if (ret) + goto out_put_request; + + req->cmd[0] = GPCMD_READ_CD; + req->cmd[1] = 1 << 2; + req->cmd[2] = (lba >> 24) & 0xff; + req->cmd[3] = (lba >> 16) & 0xff; + req->cmd[4] = (lba >> 8) & 0xff; + req->cmd[5] = lba & 0xff; + req->cmd[6] = (nr >> 16) & 0xff; + req->cmd[7] = (nr >> 8) & 0xff; + req->cmd[8] = nr & 0xff; + req->cmd[9] = 0xf8; + req->cmd_len = 12; + rq->timeout = 60 * HZ; + bio = rq->bio; + + blk_execute_rq(disk, rq, 0); + if (scsi_req(rq)->result) { + struct scsi_sense_hdr sshdr; + + scsi_normalize_sense(req->sense, req->sense_len, + &sshdr); + *last_sense = sshdr.sense_key; + ret = -EIO; + } + + if (blk_rq_unmap_user(bio)) + ret = -EFAULT; +out_put_request: + blk_put_request(rq); + return ret; +} + + /** * sr_kref_release - Called to free the scsi_cd structure * @kref: pointer to embedded kref diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index f48d0a31deae..c4fef00abdf3 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -86,11 +86,13 @@ struct cdrom_device_ops { /* play stuff */ int (*audio_ioctl) (struct cdrom_device_info *,unsigned int, void *); -/* driver specifications */ - const int capability; /* capability flags */ /* handle uniform packets for scsi type devices (scsi,atapi) */ int (*generic_packet) (struct cdrom_device_info *, struct packet_command *); + int (*read_cdda_bpc)(struct cdrom_device_info *cdi, void __user *ubuf, + u32 lba, u32 nframes, u8 *last_sense); +/* driver specifications */ + const int capability; /* capability flags */ }; int cdrom_multisession(struct cdrom_device_info *cdi, -- cgit v1.2.3 From ead09dd3aed5cc6a6c6288a87a5bfa9bbc8d5ecf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Jul 2021 08:48:42 +0200 Subject: scsi: bsg: Simplify device registration Use the per-device cdev_device_interface to store the bsg data in the char device inode, and thus remove the need to embedd the bsg_class_device structure in the request_queue. Link: https://lore.kernel.org/r/20210729064845.1044147-2-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- block/bsg-lib.c | 11 +- block/bsg.c | 304 +++++++++++---------------------------------- drivers/scsi/scsi_bsg.c | 5 +- drivers/scsi/scsi_priv.h | 11 +- drivers/scsi/scsi_sysfs.c | 24 ++-- include/linux/blkdev.h | 6 - include/linux/bsg-lib.h | 1 + include/linux/bsg.h | 21 +--- include/scsi/scsi_device.h | 2 + 9 files changed, 108 insertions(+), 277 deletions(-) (limited to 'include/linux') diff --git a/block/bsg-lib.c b/block/bsg-lib.c index a89d80102304..fe43f5fda6e5 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -6,6 +6,7 @@ * Copyright (C) 2011 Red Hat, Inc. All rights reserved. * Copyright (C) 2011 Mike Christie */ +#include #include #include #include @@ -19,6 +20,7 @@ struct bsg_set { struct blk_mq_tag_set tag_set; + struct bsg_device *bd; bsg_job_fn *job_fn; bsg_timeout_fn *timeout_fn; }; @@ -327,7 +329,7 @@ void bsg_remove_queue(struct request_queue *q) struct bsg_set *bset = container_of(q->tag_set, struct bsg_set, tag_set); - bsg_unregister_queue(q); + bsg_unregister_queue(bset->bd); blk_cleanup_queue(q); blk_mq_free_tag_set(&bset->tag_set); kfree(bset); @@ -396,10 +398,9 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, q->queuedata = dev; blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); - ret = bsg_register_queue(q, dev, name, &bsg_transport_ops); - if (ret) { - printk(KERN_ERR "%s: bsg interface failed to " - "initialize - register queue\n", dev->kobj.name); + bset->bd = bsg_register_queue(q, dev, name, &bsg_transport_ops); + if (IS_ERR(bset->bd)) { + ret = PTR_ERR(bset->bd); goto out_cleanup_queue; } diff --git a/block/bsg.c b/block/bsg.c index 3dbfd2c6aef3..83a095185d33 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -20,38 +20,29 @@ #define BSG_DESCRIPTION "Block layer SCSI generic (bsg) driver" #define BSG_VERSION "0.4" -#define bsg_dbg(bd, fmt, ...) \ - pr_debug("%s: " fmt, (bd)->name, ##__VA_ARGS__) - struct bsg_device { struct request_queue *queue; - spinlock_t lock; - struct hlist_node dev_list; - refcount_t ref_count; - char name[20]; + const struct bsg_ops *ops; + struct device device; + struct cdev cdev; int max_queue; }; +static inline struct bsg_device *to_bsg_device(struct inode *inode) +{ + return container_of(inode->i_cdev, struct bsg_device, cdev); +} + #define BSG_DEFAULT_CMDS 64 #define BSG_MAX_DEVS 32768 -static DEFINE_MUTEX(bsg_mutex); -static DEFINE_IDR(bsg_minor_idr); - -#define BSG_LIST_ARRAY_SIZE 8 -static struct hlist_head bsg_device_list[BSG_LIST_ARRAY_SIZE]; - +static DEFINE_IDA(bsg_minor_ida); static struct class *bsg_class; static int bsg_major; -static inline struct hlist_head *bsg_dev_idx_hash(int index) -{ - return &bsg_device_list[index & (BSG_LIST_ARRAY_SIZE - 1)]; -} - #define uptr64(val) ((void __user *)(uintptr_t)(val)) -static int bsg_sg_io(struct request_queue *q, fmode_t mode, void __user *uarg) +static int bsg_sg_io(struct bsg_device *bd, fmode_t mode, void __user *uarg) { struct request *rq; struct bio *bio; @@ -61,21 +52,18 @@ static int bsg_sg_io(struct request_queue *q, fmode_t mode, void __user *uarg) if (copy_from_user(&hdr, uarg, sizeof(hdr))) return -EFAULT; - if (!q->bsg_dev.class_dev) - return -ENXIO; - if (hdr.guard != 'Q') return -EINVAL; - ret = q->bsg_dev.ops->check_proto(&hdr); + ret = bd->ops->check_proto(&hdr); if (ret) return ret; - rq = blk_get_request(q, hdr.dout_xfer_len ? + rq = blk_get_request(bd->queue, hdr.dout_xfer_len ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); if (IS_ERR(rq)) return PTR_ERR(rq); - ret = q->bsg_dev.ops->fill_hdr(rq, &hdr, mode); + ret = bd->ops->fill_hdr(rq, &hdr, mode); if (ret) { blk_put_request(rq); return ret; @@ -83,17 +71,17 @@ static int bsg_sg_io(struct request_queue *q, fmode_t mode, void __user *uarg) rq->timeout = msecs_to_jiffies(hdr.timeout); if (!rq->timeout) - rq->timeout = q->sg_timeout; + rq->timeout = rq->q->sg_timeout; if (!rq->timeout) rq->timeout = BLK_DEFAULT_SG_TIMEOUT; if (rq->timeout < BLK_MIN_SG_TIMEOUT) rq->timeout = BLK_MIN_SG_TIMEOUT; if (hdr.dout_xfer_len) { - ret = blk_rq_map_user(q, rq, NULL, uptr64(hdr.dout_xferp), + ret = blk_rq_map_user(rq->q, rq, NULL, uptr64(hdr.dout_xferp), hdr.dout_xfer_len, GFP_KERNEL); } else if (hdr.din_xfer_len) { - ret = blk_rq_map_user(q, rq, NULL, uptr64(hdr.din_xferp), + ret = blk_rq_map_user(rq->q, rq, NULL, uptr64(hdr.din_xferp), hdr.din_xfer_len, GFP_KERNEL); } @@ -103,171 +91,50 @@ static int bsg_sg_io(struct request_queue *q, fmode_t mode, void __user *uarg) bio = rq->bio; blk_execute_rq(NULL, rq, !(hdr.flags & BSG_FLAG_Q_AT_TAIL)); - ret = rq->q->bsg_dev.ops->complete_rq(rq, &hdr); + ret = bd->ops->complete_rq(rq, &hdr); blk_rq_unmap_user(bio); out_free_rq: - rq->q->bsg_dev.ops->free_rq(rq); + bd->ops->free_rq(rq); blk_put_request(rq); if (!ret && copy_to_user(uarg, &hdr, sizeof(hdr))) return -EFAULT; return ret; } -static struct bsg_device *bsg_alloc_device(void) -{ - struct bsg_device *bd; - - bd = kzalloc(sizeof(struct bsg_device), GFP_KERNEL); - if (unlikely(!bd)) - return NULL; - - spin_lock_init(&bd->lock); - bd->max_queue = BSG_DEFAULT_CMDS; - INIT_HLIST_NODE(&bd->dev_list); - return bd; -} - -static int bsg_put_device(struct bsg_device *bd) -{ - struct request_queue *q = bd->queue; - - mutex_lock(&bsg_mutex); - - if (!refcount_dec_and_test(&bd->ref_count)) { - mutex_unlock(&bsg_mutex); - return 0; - } - - hlist_del(&bd->dev_list); - mutex_unlock(&bsg_mutex); - - bsg_dbg(bd, "tearing down\n"); - - /* - * close can always block - */ - kfree(bd); - blk_put_queue(q); - return 0; -} - -static struct bsg_device *bsg_add_device(struct inode *inode, - struct request_queue *rq, - struct file *file) -{ - struct bsg_device *bd; - unsigned char buf[32]; - - lockdep_assert_held(&bsg_mutex); - - if (!blk_get_queue(rq)) - return ERR_PTR(-ENXIO); - - bd = bsg_alloc_device(); - if (!bd) { - blk_put_queue(rq); - return ERR_PTR(-ENOMEM); - } - - bd->queue = rq; - - refcount_set(&bd->ref_count, 1); - hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode))); - - strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1); - bsg_dbg(bd, "bound to <%s>, max queue %d\n", - format_dev_t(buf, inode->i_rdev), bd->max_queue); - - return bd; -} - -static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q) -{ - struct bsg_device *bd; - - lockdep_assert_held(&bsg_mutex); - - hlist_for_each_entry(bd, bsg_dev_idx_hash(minor), dev_list) { - if (bd->queue == q) { - refcount_inc(&bd->ref_count); - goto found; - } - } - bd = NULL; -found: - return bd; -} - -static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file) -{ - struct bsg_device *bd; - struct bsg_class_device *bcd; - - /* - * find the class device - */ - mutex_lock(&bsg_mutex); - bcd = idr_find(&bsg_minor_idr, iminor(inode)); - - if (!bcd) { - bd = ERR_PTR(-ENODEV); - goto out_unlock; - } - - bd = __bsg_get_device(iminor(inode), bcd->queue); - if (!bd) - bd = bsg_add_device(inode, bcd->queue, file); - -out_unlock: - mutex_unlock(&bsg_mutex); - return bd; -} - static int bsg_open(struct inode *inode, struct file *file) { - struct bsg_device *bd; - - bd = bsg_get_device(inode, file); - - if (IS_ERR(bd)) - return PTR_ERR(bd); - - file->private_data = bd; + if (!blk_get_queue(to_bsg_device(inode)->queue)) + return -ENXIO; return 0; } static int bsg_release(struct inode *inode, struct file *file) { - struct bsg_device *bd = file->private_data; - - file->private_data = NULL; - return bsg_put_device(bd); + blk_put_queue(to_bsg_device(inode)->queue); + return 0; } static int bsg_get_command_q(struct bsg_device *bd, int __user *uarg) { - return put_user(bd->max_queue, uarg); + return put_user(READ_ONCE(bd->max_queue), uarg); } static int bsg_set_command_q(struct bsg_device *bd, int __user *uarg) { - int queue; + int max_queue; - if (get_user(queue, uarg)) + if (get_user(max_queue, uarg)) return -EFAULT; - if (queue < 1) + if (max_queue < 1) return -EINVAL; - - spin_lock_irq(&bd->lock); - bd->max_queue = queue; - spin_unlock_irq(&bd->lock); + WRITE_ONCE(bd->max_queue, max_queue); return 0; } static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct bsg_device *bd = file->private_data; + struct bsg_device *bd = to_bsg_device(file_inode(file)); struct request_queue *q = bd->queue; void __user *uarg = (void __user *) arg; int __user *intp = uarg; @@ -312,7 +179,7 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case SG_EMULATED_HOST: return put_user(1, intp); case SG_IO: - return bsg_sg_io(q, file->f_mode, uarg); + return bsg_sg_io(bd, file->f_mode, uarg); case SCSI_IOCTL_SEND_COMMAND: pr_warn_ratelimited("%s: calling unsupported SCSI_IOCTL_SEND_COMMAND\n", current->comm); @@ -331,83 +198,66 @@ static const struct file_operations bsg_fops = { .llseek = default_llseek, }; -void bsg_unregister_queue(struct request_queue *q) +void bsg_unregister_queue(struct bsg_device *bd) { - struct bsg_class_device *bcd = &q->bsg_dev; - - if (!bcd->class_dev) - return; - - mutex_lock(&bsg_mutex); - idr_remove(&bsg_minor_idr, bcd->minor); - if (q->kobj.sd) - sysfs_remove_link(&q->kobj, "bsg"); - device_unregister(bcd->class_dev); - bcd->class_dev = NULL; - mutex_unlock(&bsg_mutex); + if (bd->queue->kobj.sd) + sysfs_remove_link(&bd->queue->kobj, "bsg"); + cdev_device_del(&bd->cdev, &bd->device); + ida_simple_remove(&bsg_minor_ida, MINOR(bd->device.devt)); + kfree(bd); } EXPORT_SYMBOL_GPL(bsg_unregister_queue); -int bsg_register_queue(struct request_queue *q, struct device *parent, - const char *name, const struct bsg_ops *ops) +struct bsg_device *bsg_register_queue(struct request_queue *q, + struct device *parent, const char *name, + const struct bsg_ops *ops) { - struct bsg_class_device *bcd; - dev_t dev; + struct bsg_device *bd; int ret; - struct device *class_dev = NULL; - - /* - * we need a proper transport to send commands, not a stacked device - */ - if (!queue_is_mq(q)) - return 0; - bcd = &q->bsg_dev; - memset(bcd, 0, sizeof(*bcd)); - - mutex_lock(&bsg_mutex); + bd = kzalloc(sizeof(*bd), GFP_KERNEL); + if (!bd) + return ERR_PTR(-ENOMEM); + bd->max_queue = BSG_DEFAULT_CMDS; + bd->queue = q; + bd->ops = ops; - ret = idr_alloc(&bsg_minor_idr, bcd, 0, BSG_MAX_DEVS, GFP_KERNEL); + ret = ida_simple_get(&bsg_minor_ida, 0, BSG_MAX_DEVS, GFP_KERNEL); if (ret < 0) { - if (ret == -ENOSPC) { - printk(KERN_ERR "bsg: too many bsg devices\n"); - ret = -EINVAL; - } - goto unlock; - } - - bcd->minor = ret; - bcd->queue = q; - bcd->ops = ops; - dev = MKDEV(bsg_major, bcd->minor); - class_dev = device_create(bsg_class, parent, dev, NULL, "%s", name); - if (IS_ERR(class_dev)) { - ret = PTR_ERR(class_dev); - goto idr_remove; + if (ret == -ENOSPC) + dev_err(parent, "bsg: too many bsg devices\n"); + goto out_kfree; } - bcd->class_dev = class_dev; + bd->device.devt = MKDEV(bsg_major, ret); + bd->device.class = bsg_class; + bd->device.parent = parent; + dev_set_name(&bd->device, "%s", name); + device_initialize(&bd->device); + + cdev_init(&bd->cdev, &bsg_fops); + bd->cdev.owner = THIS_MODULE; + ret = cdev_device_add(&bd->cdev, &bd->device); + if (ret) + goto out_ida_remove; if (q->kobj.sd) { - ret = sysfs_create_link(&q->kobj, &bcd->class_dev->kobj, "bsg"); + ret = sysfs_create_link(&q->kobj, &bd->device.kobj, "bsg"); if (ret) - goto unregister_class_dev; + goto out_device_del; } - mutex_unlock(&bsg_mutex); - return 0; + return bd; -unregister_class_dev: - device_unregister(class_dev); -idr_remove: - idr_remove(&bsg_minor_idr, bcd->minor); -unlock: - mutex_unlock(&bsg_mutex); - return ret; +out_device_del: + cdev_device_del(&bd->cdev, &bd->device); +out_ida_remove: + ida_simple_remove(&bsg_minor_ida, MINOR(bd->device.devt)); +out_kfree: + kfree(bd); + return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(bsg_register_queue); -static struct cdev bsg_cdev; - static char *bsg_devnode(struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "bsg/%s", dev_name(dev)); @@ -415,11 +265,8 @@ static char *bsg_devnode(struct device *dev, umode_t *mode) static int __init bsg_init(void) { - int ret, i; dev_t devid; - - for (i = 0; i < BSG_LIST_ARRAY_SIZE; i++) - INIT_HLIST_HEAD(&bsg_device_list[i]); + int ret; bsg_class = class_create(THIS_MODULE, "bsg"); if (IS_ERR(bsg_class)) @@ -429,19 +276,12 @@ static int __init bsg_init(void) ret = alloc_chrdev_region(&devid, 0, BSG_MAX_DEVS, "bsg"); if (ret) goto destroy_bsg_class; - bsg_major = MAJOR(devid); - cdev_init(&bsg_cdev, &bsg_fops); - ret = cdev_add(&bsg_cdev, MKDEV(bsg_major, 0), BSG_MAX_DEVS); - if (ret) - goto unregister_chrdev; - printk(KERN_INFO BSG_DESCRIPTION " version " BSG_VERSION " loaded (major %d)\n", bsg_major); return 0; -unregister_chrdev: - unregister_chrdev_region(MKDEV(bsg_major, 0), BSG_MAX_DEVS); + destroy_bsg_class: class_destroy(bsg_class); return ret; diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c index 68f60316adf1..c0d41c45c2be 100644 --- a/drivers/scsi/scsi_bsg.c +++ b/drivers/scsi/scsi_bsg.c @@ -89,7 +89,8 @@ static const struct bsg_ops scsi_bsg_ops = { .free_rq = scsi_bsg_free_rq, }; -int scsi_bsg_register_queue(struct request_queue *q, struct device *parent) +struct bsg_device *scsi_bsg_register_queue(struct scsi_device *sdev) { - return bsg_register_queue(q, parent, dev_name(parent), &scsi_bsg_ops); + return bsg_register_queue(sdev->request_queue, &sdev->sdev_gendev, + dev_name(&sdev->sdev_gendev), &scsi_bsg_ops); } diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index 0a0db35bab04..6d9152031a40 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -7,6 +7,7 @@ #include #include +struct bsg_device; struct request_queue; struct request; struct scsi_cmnd; @@ -180,15 +181,7 @@ static inline void scsi_dh_add_device(struct scsi_device *sdev) { } static inline void scsi_dh_release_device(struct scsi_device *sdev) { } #endif -#ifdef CONFIG_BLK_DEV_BSG -int scsi_bsg_register_queue(struct request_queue *q, struct device *parent); -#else -static inline int scsi_bsg_register_queue(struct request_queue *q, - struct device *parent) -{ - return 0; -} -#endif +struct bsg_device *scsi_bsg_register_queue(struct scsi_device *sdev); extern int scsi_device_max_queue_depth(struct scsi_device *sdev); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 4ff9ac3296d8..07cee8dc4100 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -1327,7 +1328,6 @@ static int scsi_target_add(struct scsi_target *starget) int scsi_sysfs_add_sdev(struct scsi_device *sdev) { int error, i; - struct request_queue *rq = sdev->request_queue; struct scsi_target *starget = sdev->sdev_target; error = scsi_target_add(starget); @@ -1366,12 +1366,19 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) transport_add_device(&sdev->sdev_gendev); sdev->is_visible = 1; - error = scsi_bsg_register_queue(rq, &sdev->sdev_gendev); - if (error) - /* we're treating error on bsg register as non-fatal, - * so pretend nothing went wrong */ - sdev_printk(KERN_INFO, sdev, - "Failed to register bsg queue, errno=%d\n", error); + if (IS_ENABLED(CONFIG_BLK_DEV_BSG)) { + sdev->bsg_dev = scsi_bsg_register_queue(sdev); + if (IS_ERR(sdev->bsg_dev)) { + /* + * We're treating error on bsg register as non-fatal, so + * pretend nothing went wrong. + */ + sdev_printk(KERN_INFO, sdev, + "Failed to register bsg queue, errno=%d\n", + error); + sdev->bsg_dev = NULL; + } + } /* add additional host specific attributes */ if (sdev->host->hostt->sdev_attrs) { @@ -1433,7 +1440,8 @@ void __scsi_remove_device(struct scsi_device *sdev) sysfs_remove_groups(&sdev->sdev_gendev.kobj, sdev->host->hostt->sdev_groups); - bsg_unregister_queue(sdev->request_queue); + if (IS_ENABLED(CONFIG_BLK_DEV_BSG) && sdev->bsg_dev) + bsg_unregister_queue(sdev->bsg_dev); device_unregister(&sdev->sdev_dev); transport_remove_device(dev); device_del(dev); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8c617a5a5d61..28957ccdd9c2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -33,7 +32,6 @@ struct elevator_queue; struct blk_trace; struct request; struct sg_io_hdr; -struct bsg_job; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; @@ -535,10 +533,6 @@ struct request_queue { int mq_freeze_depth; -#if IS_ENABLED(CONFIG_BLK_DEV_BSG_COMMON) - struct bsg_class_device bsg_dev; -#endif - #ifdef CONFIG_BLK_DEV_THROTTLING /* Throttle data */ struct throtl_data *td; diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 960988d42f77..6b211323a489 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -12,6 +12,7 @@ #include #include +struct bsg_job; struct request; struct device; struct scatterlist; diff --git a/include/linux/bsg.h b/include/linux/bsg.h index b887da20bd41..fa21f79beda2 100644 --- a/include/linux/bsg.h +++ b/include/linux/bsg.h @@ -4,10 +4,11 @@ #include +struct bsg_device; +struct device; struct request; struct request_queue; -#ifdef CONFIG_BLK_DEV_BSG_COMMON struct bsg_ops { int (*check_proto)(struct sg_io_v4 *hdr); int (*fill_hdr)(struct request *rq, struct sg_io_v4 *hdr, @@ -16,19 +17,9 @@ struct bsg_ops { void (*free_rq)(struct request *rq); }; -struct bsg_class_device { - struct device *class_dev; - int minor; - struct request_queue *queue; - const struct bsg_ops *ops; -}; +struct bsg_device *bsg_register_queue(struct request_queue *q, + struct device *parent, const char *name, + const struct bsg_ops *ops); +void bsg_unregister_queue(struct bsg_device *bcd); -int bsg_register_queue(struct request_queue *q, struct device *parent, - const char *name, const struct bsg_ops *ops); -void bsg_unregister_queue(struct request_queue *q); -#else -static inline void bsg_unregister_queue(struct request_queue *q) -{ -} -#endif /* CONFIG_BLK_DEV_BSG_COMMON */ #endif /* _LINUX_BSG_H */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index d1de21f799f4..99082da1b951 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -10,6 +10,7 @@ #include #include +struct bsg_device; struct device; struct request_queue; struct scsi_cmnd; @@ -235,6 +236,7 @@ struct scsi_device { size_t dma_drain_len; void *dma_drain_buf; + struct bsg_device *bsg_dev; unsigned char access_state; struct mutex state_mutex; enum scsi_device_state sdev_state; -- cgit v1.2.3 From cf93a27446fe1a6e0acb9bbedf5fce1e98e4fc5b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Jul 2021 08:48:43 +0200 Subject: scsi: block: Remove BLK_SCSI_MAX_CMDS This was used for the table based SCSI passthough permission checking that is gone now. Link: https://lore.kernel.org/r/20210729064845.1044147-3-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/linux/blkdev.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 28957ccdd9c2..e0bb14acb708 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -271,9 +271,6 @@ enum blk_queue_state { #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ #define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ -#define BLK_SCSI_MAX_CMDS (256) -#define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) - /* * Zoned block device models (zoned limit). * -- cgit v1.2.3 From 1e61c1a804d2a2a3c46add01cac3a6e9eca01080 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Jul 2021 08:48:44 +0200 Subject: scsi: block: Remove the remaining SG_IO-related fields from struct request_queue Move the sg_timeout and sg_reserved_size fields into the bsg_device and scsi_device structures as they have nothing to do with generic block I/O. Note that these values are now separate for bsg vs. SCSI device node access, but that just matches how /dev/sg vs the other nodes has always behaved. Link: https://lore.kernel.org/r/20210729064845.1044147-4-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- block/blk-mq.c | 2 -- block/bsg.c | 13 ++++++---- drivers/scsi/scsi_ioctl.c | 63 ++++++++++++++++++++++------------------------ drivers/scsi/scsi_scan.c | 2 ++ include/linux/blkdev.h | 5 ---- include/scsi/scsi_device.h | 3 +++ 6 files changed, 43 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 2c4ac51e54eb..495f508c6300 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3298,8 +3298,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, set->map[HCTX_TYPE_POLL].nr_queues) blk_queue_flag_set(QUEUE_FLAG_POLL, q); - q->sg_reserved_size = INT_MAX; - INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); INIT_LIST_HEAD(&q->requeue_list); spin_lock_init(&q->requeue_lock); diff --git a/block/bsg.c b/block/bsg.c index 83a095185d33..3ba74eec4ba2 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -26,6 +26,8 @@ struct bsg_device { struct device device; struct cdev cdev; int max_queue; + unsigned int timeout; + unsigned int reserved_size; }; static inline struct bsg_device *to_bsg_device(struct inode *inode) @@ -71,7 +73,7 @@ static int bsg_sg_io(struct bsg_device *bd, fmode_t mode, void __user *uarg) rq->timeout = msecs_to_jiffies(hdr.timeout); if (!rq->timeout) - rq->timeout = rq->q->sg_timeout; + rq->timeout = bd->timeout; if (!rq->timeout) rq->timeout = BLK_DEFAULT_SG_TIMEOUT; if (rq->timeout < BLK_MIN_SG_TIMEOUT) @@ -161,19 +163,19 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case SG_SET_TIMEOUT: if (get_user(val, intp)) return -EFAULT; - q->sg_timeout = clock_t_to_jiffies(val); + bd->timeout = clock_t_to_jiffies(val); return 0; case SG_GET_TIMEOUT: - return jiffies_to_clock_t(q->sg_timeout); + return jiffies_to_clock_t(bd->timeout); case SG_GET_RESERVED_SIZE: - return put_user(min(q->sg_reserved_size, queue_max_bytes(q)), + return put_user(min(bd->reserved_size, queue_max_bytes(q)), intp); case SG_SET_RESERVED_SIZE: if (get_user(val, intp)) return -EFAULT; if (val < 0) return -EINVAL; - q->sg_reserved_size = + bd->reserved_size = min_t(unsigned int, val, queue_max_bytes(q)); return 0; case SG_EMULATED_HOST: @@ -219,6 +221,7 @@ struct bsg_device *bsg_register_queue(struct request_queue *q, if (!bd) return ERR_PTR(-ENOMEM); bd->max_queue = BSG_DEFAULT_CMDS; + bd->reserved_size = INT_MAX; bd->queue = q; bd->ops = ops; diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c index 633f016c2bfe..7b2b0a1581f4 100644 --- a/drivers/scsi/scsi_ioctl.c +++ b/drivers/scsi/scsi_ioctl.c @@ -173,29 +173,25 @@ static int sg_get_version(int __user *p) return put_user(sg_version_num, p); } -static int sg_get_timeout(struct request_queue *q) -{ - return jiffies_to_clock_t(q->sg_timeout); -} - -static int sg_set_timeout(struct request_queue *q, int __user *p) +static int sg_set_timeout(struct scsi_device *sdev, int __user *p) { int timeout, err = get_user(timeout, p); if (!err) - q->sg_timeout = clock_t_to_jiffies(timeout); + sdev->sg_timeout = clock_t_to_jiffies(timeout); return err; } -static int sg_get_reserved_size(struct request_queue *q, int __user *p) +static int sg_get_reserved_size(struct scsi_device *sdev, int __user *p) { - int val = min(q->sg_reserved_size, queue_max_bytes(q)); + int val = min(sdev->sg_reserved_size, + queue_max_bytes(sdev->request_queue)); return put_user(val, p); } -static int sg_set_reserved_size(struct request_queue *q, int __user *p) +static int sg_set_reserved_size(struct scsi_device *sdev, int __user *p) { int size, err = get_user(size, p); @@ -205,7 +201,8 @@ static int sg_set_reserved_size(struct request_queue *q, int __user *p) if (size < 0) return -EINVAL; - q->sg_reserved_size = min_t(unsigned int, size, queue_max_bytes(q)); + sdev->sg_reserved_size = min_t(unsigned int, size, + queue_max_bytes(sdev->request_queue)); return 0; } @@ -345,7 +342,7 @@ bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode) } EXPORT_SYMBOL(scsi_cmd_allowed); -static int scsi_fill_sghdr_rq(struct request_queue *q, struct request *rq, +static int scsi_fill_sghdr_rq(struct scsi_device *sdev, struct request *rq, struct sg_io_hdr *hdr, fmode_t mode) { struct scsi_request *req = scsi_req(rq); @@ -362,7 +359,7 @@ static int scsi_fill_sghdr_rq(struct request_queue *q, struct request *rq, rq->timeout = msecs_to_jiffies(hdr->timeout); if (!rq->timeout) - rq->timeout = q->sg_timeout; + rq->timeout = sdev->sg_timeout; if (!rq->timeout) rq->timeout = BLK_DEFAULT_SG_TIMEOUT; if (rq->timeout < BLK_MIN_SG_TIMEOUT) @@ -409,7 +406,7 @@ static int scsi_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr, return ret; } -static int sg_io(struct request_queue *q, struct gendisk *bd_disk, +static int sg_io(struct scsi_device *sdev, struct gendisk *disk, struct sg_io_hdr *hdr, fmode_t mode) { unsigned long start_time; @@ -423,7 +420,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, if (hdr->interface_id != 'S') return -EINVAL; - if (hdr->dxfer_len > (queue_max_hw_sectors(q) << 9)) + if (hdr->dxfer_len > (queue_max_hw_sectors(sdev->request_queue) << 9)) return -EIO; if (hdr->dxfer_len) @@ -441,7 +438,8 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, at_head = 1; ret = -ENOMEM; - rq = blk_get_request(q, writing ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); + rq = blk_get_request(sdev->request_queue, writing ? + REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); if (IS_ERR(rq)) return PTR_ERR(rq); req = scsi_req(rq); @@ -452,7 +450,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, goto out_put_request; } - ret = scsi_fill_sghdr_rq(q, rq, hdr, mode); + ret = scsi_fill_sghdr_rq(sdev, rq, hdr, mode); if (ret < 0) goto out_free_cdb; @@ -469,11 +467,11 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, /* SG_IO howto says that the shorter of the two wins */ iov_iter_truncate(&i, hdr->dxfer_len); - ret = blk_rq_map_user_iov(q, rq, NULL, &i, GFP_KERNEL); + ret = blk_rq_map_user_iov(rq->q, rq, NULL, &i, GFP_KERNEL); kfree(iov); } else if (hdr->dxfer_len) - ret = blk_rq_map_user(q, rq, NULL, hdr->dxferp, hdr->dxfer_len, - GFP_KERNEL); + ret = blk_rq_map_user(rq->q, rq, NULL, hdr->dxferp, + hdr->dxfer_len, GFP_KERNEL); if (ret) goto out_free_cdb; @@ -483,7 +481,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, start_time = jiffies; - blk_execute_rq(bd_disk, rq, at_head); + blk_execute_rq(disk, rq, at_head); hdr->duration = jiffies_to_msecs(jiffies - start_time); @@ -806,9 +804,8 @@ static int scsi_put_cdrom_generic_arg(const struct cdrom_generic_command *cgc, return 0; } -static int scsi_cdrom_send_packet(struct request_queue *q, - struct gendisk *bd_disk, - fmode_t mode, void __user *arg) +static int scsi_cdrom_send_packet(struct scsi_device *sdev, struct gendisk *disk, + fmode_t mode, void __user *arg) { struct cdrom_generic_command cgc; struct sg_io_hdr hdr; @@ -848,7 +845,7 @@ static int scsi_cdrom_send_packet(struct request_queue *q, hdr.cmdp = ((struct cdrom_generic_command __user *) arg)->cmd; hdr.cmd_len = sizeof(cgc.cmd); - err = sg_io(q, bd_disk, &hdr, mode); + err = sg_io(sdev, disk, &hdr, mode); if (err == -EFAULT) return -EFAULT; @@ -863,7 +860,7 @@ static int scsi_cdrom_send_packet(struct request_queue *q, return err; } -static int scsi_ioctl_sg_io(struct request_queue *q, struct gendisk *disk, +static int scsi_ioctl_sg_io(struct scsi_device *sdev, struct gendisk *disk, fmode_t mode, void __user *argp) { struct sg_io_hdr hdr; @@ -872,7 +869,7 @@ static int scsi_ioctl_sg_io(struct request_queue *q, struct gendisk *disk, error = get_sg_io_hdr(&hdr, argp); if (error) return error; - error = sg_io(q, disk, &hdr, mode); + error = sg_io(sdev, disk, &hdr, mode); if (error == -EFAULT) return error; if (put_sg_io_hdr(&hdr, argp)) @@ -918,21 +915,21 @@ int scsi_ioctl(struct scsi_device *sdev, struct gendisk *disk, fmode_t mode, case SG_GET_VERSION_NUM: return sg_get_version(arg); case SG_SET_TIMEOUT: - return sg_set_timeout(q, arg); + return sg_set_timeout(sdev, arg); case SG_GET_TIMEOUT: - return sg_get_timeout(q); + return jiffies_to_clock_t(sdev->sg_timeout); case SG_GET_RESERVED_SIZE: - return sg_get_reserved_size(q, arg); + return sg_get_reserved_size(sdev, arg); case SG_SET_RESERVED_SIZE: - return sg_set_reserved_size(q, arg); + return sg_set_reserved_size(sdev, arg); case SG_EMULATED_HOST: return sg_emulated_host(q, arg); case SG_IO: - return scsi_ioctl_sg_io(q, disk, mode, arg); + return scsi_ioctl_sg_io(sdev, disk, mode, arg); case SCSI_IOCTL_SEND_COMMAND: return sg_scsi_ioctl(q, disk, mode, arg); case CDROM_SEND_PACKET: - return scsi_cdrom_send_packet(q, disk, mode, arg); + return scsi_cdrom_send_packet(sdev, disk, mode, arg); case CDROMCLOSETRAY: return scsi_send_start_stop(sdev, 3); case CDROMEJECT: diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 3faedf4970ec..e06a2602fca4 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -267,6 +267,8 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, */ sdev->borken = 1; + sdev->sg_reserved_size = INT_MAX; + q = blk_mq_init_queue(&sdev->host->tag_set); if (IS_ERR(q)) { /* release fn is set up in scsi_sysfs_device_initialise, so diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e0bb14acb708..987f15089eeb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -499,11 +499,6 @@ struct request_queue { unsigned int max_active_zones; #endif /* CONFIG_BLK_DEV_ZONED */ - /* - * sg stuff - */ - unsigned int sg_timeout; - unsigned int sg_reserved_size; int node; struct mutex debugfs_mutex; #ifdef CONFIG_BLK_DEV_IO_TRACE diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 99082da1b951..7137e7924913 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -236,6 +236,9 @@ struct scsi_device { size_t dma_drain_len; void *dma_drain_buf; + unsigned int sg_timeout; + unsigned int sg_reserved_size; + struct bsg_device *bsg_dev; unsigned char access_state; struct mutex state_mutex; -- cgit v1.2.3 From 75ca56409e5b35aa6ceef94462f39ef4f533fc41 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Jul 2021 08:48:45 +0200 Subject: scsi: bsg: Move the whole request execution into the SCSI/transport handlers Remove the amount of indirect calls by making the handler responsible for the entire execution of the request. Link: https://lore.kernel.org/r/20210729064845.1044147-5-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- block/bsg-lib.c | 80 ++++++++++++++++++++++++------------------------- block/bsg.c | 66 ++++++++++------------------------------ drivers/scsi/scsi_bsg.c | 69 +++++++++++++++++++++++------------------- include/linux/bsg.h | 12 ++------ 4 files changed, 96 insertions(+), 131 deletions(-) (limited to 'include/linux') diff --git a/block/bsg-lib.c b/block/bsg-lib.c index fe43f5fda6e5..239ebf747141 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -25,32 +25,39 @@ struct bsg_set { bsg_timeout_fn *timeout_fn; }; -static int bsg_transport_check_proto(struct sg_io_v4 *hdr) +static int bsg_transport_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, + fmode_t mode, unsigned int timeout) { + struct bsg_job *job; + struct request *rq; + struct bio *bio; + int ret; + if (hdr->protocol != BSG_PROTOCOL_SCSI || hdr->subprotocol != BSG_SUB_PROTOCOL_SCSI_TRANSPORT) return -EINVAL; if (!capable(CAP_SYS_RAWIO)) return -EPERM; - return 0; -} -static int bsg_transport_fill_hdr(struct request *rq, struct sg_io_v4 *hdr, - fmode_t mode) -{ - struct bsg_job *job = blk_mq_rq_to_pdu(rq); - int ret; + rq = blk_get_request(q, hdr->dout_xfer_len ? + REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); + if (IS_ERR(rq)) + return PTR_ERR(rq); + rq->timeout = timeout; + job = blk_mq_rq_to_pdu(rq); job->request_len = hdr->request_len; job->request = memdup_user(uptr64(hdr->request), hdr->request_len); - if (IS_ERR(job->request)) - return PTR_ERR(job->request); + if (IS_ERR(job->request)) { + ret = PTR_ERR(job->request); + goto out_put_request; + } if (hdr->dout_xfer_len && hdr->din_xfer_len) { job->bidi_rq = blk_get_request(rq->q, REQ_OP_DRV_IN, 0); if (IS_ERR(job->bidi_rq)) { ret = PTR_ERR(job->bidi_rq); - goto out; + goto out_free_job_request; } ret = blk_rq_map_user(rq->q, job->bidi_rq, NULL, @@ -65,20 +72,19 @@ static int bsg_transport_fill_hdr(struct request *rq, struct sg_io_v4 *hdr, job->bidi_bio = NULL; } - return 0; + if (hdr->dout_xfer_len) { + ret = blk_rq_map_user(rq->q, rq, NULL, uptr64(hdr->dout_xferp), + hdr->dout_xfer_len, GFP_KERNEL); + } else if (hdr->din_xfer_len) { + ret = blk_rq_map_user(rq->q, rq, NULL, uptr64(hdr->din_xferp), + hdr->din_xfer_len, GFP_KERNEL); + } -out_free_bidi_rq: - if (job->bidi_rq) - blk_put_request(job->bidi_rq); -out: - kfree(job->request); - return ret; -} + if (ret) + goto out_unmap_bidi_rq; -static int bsg_transport_complete_rq(struct request *rq, struct sg_io_v4 *hdr) -{ - struct bsg_job *job = blk_mq_rq_to_pdu(rq); - int ret = 0; + bio = rq->bio; + blk_execute_rq(NULL, rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL)); /* * The assignments below don't make much sense, but are kept for @@ -121,28 +127,20 @@ static int bsg_transport_complete_rq(struct request *rq, struct sg_io_v4 *hdr) hdr->din_resid = 0; } - return ret; -} - -static void bsg_transport_free_rq(struct request *rq) -{ - struct bsg_job *job = blk_mq_rq_to_pdu(rq); - - if (job->bidi_rq) { + blk_rq_unmap_user(bio); +out_unmap_bidi_rq: + if (job->bidi_rq) blk_rq_unmap_user(job->bidi_bio); +out_free_bidi_rq: + if (job->bidi_rq) blk_put_request(job->bidi_rq); - } - +out_free_job_request: kfree(job->request); +out_put_request: + blk_put_request(rq); + return ret; } -static const struct bsg_ops bsg_transport_ops = { - .check_proto = bsg_transport_check_proto, - .fill_hdr = bsg_transport_fill_hdr, - .complete_rq = bsg_transport_complete_rq, - .free_rq = bsg_transport_free_rq, -}; - /** * bsg_teardown_job - routine to teardown a bsg job * @kref: kref inside bsg_job that is to be torn down @@ -398,7 +396,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, q->queuedata = dev; blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); - bset->bd = bsg_register_queue(q, dev, name, &bsg_transport_ops); + bset->bd = bsg_register_queue(q, dev, name, bsg_transport_sg_io_fn); if (IS_ERR(bset->bd)) { ret = PTR_ERR(bset->bd); goto out_cleanup_queue; diff --git a/block/bsg.c b/block/bsg.c index 3ba74eec4ba2..351095193788 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -22,12 +22,12 @@ struct bsg_device { struct request_queue *queue; - const struct bsg_ops *ops; struct device device; struct cdev cdev; int max_queue; unsigned int timeout; unsigned int reserved_size; + bsg_sg_io_fn *sg_io_fn; }; static inline struct bsg_device *to_bsg_device(struct inode *inode) @@ -42,63 +42,28 @@ static DEFINE_IDA(bsg_minor_ida); static struct class *bsg_class; static int bsg_major; -#define uptr64(val) ((void __user *)(uintptr_t)(val)) +static unsigned int bsg_timeout(struct bsg_device *bd, struct sg_io_v4 *hdr) +{ + unsigned int timeout = BLK_DEFAULT_SG_TIMEOUT; + + if (hdr->timeout) + timeout = msecs_to_jiffies(hdr->timeout); + else if (bd->timeout) + timeout = bd->timeout; + + return max_t(unsigned int, timeout, BLK_MIN_SG_TIMEOUT); +} static int bsg_sg_io(struct bsg_device *bd, fmode_t mode, void __user *uarg) { - struct request *rq; - struct bio *bio; struct sg_io_v4 hdr; int ret; if (copy_from_user(&hdr, uarg, sizeof(hdr))) return -EFAULT; - if (hdr.guard != 'Q') return -EINVAL; - ret = bd->ops->check_proto(&hdr); - if (ret) - return ret; - - rq = blk_get_request(bd->queue, hdr.dout_xfer_len ? - REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); - if (IS_ERR(rq)) - return PTR_ERR(rq); - - ret = bd->ops->fill_hdr(rq, &hdr, mode); - if (ret) { - blk_put_request(rq); - return ret; - } - - rq->timeout = msecs_to_jiffies(hdr.timeout); - if (!rq->timeout) - rq->timeout = bd->timeout; - if (!rq->timeout) - rq->timeout = BLK_DEFAULT_SG_TIMEOUT; - if (rq->timeout < BLK_MIN_SG_TIMEOUT) - rq->timeout = BLK_MIN_SG_TIMEOUT; - - if (hdr.dout_xfer_len) { - ret = blk_rq_map_user(rq->q, rq, NULL, uptr64(hdr.dout_xferp), - hdr.dout_xfer_len, GFP_KERNEL); - } else if (hdr.din_xfer_len) { - ret = blk_rq_map_user(rq->q, rq, NULL, uptr64(hdr.din_xferp), - hdr.din_xfer_len, GFP_KERNEL); - } - - if (ret) - goto out_free_rq; - - bio = rq->bio; - - blk_execute_rq(NULL, rq, !(hdr.flags & BSG_FLAG_Q_AT_TAIL)); - ret = bd->ops->complete_rq(rq, &hdr); - blk_rq_unmap_user(bio); - -out_free_rq: - bd->ops->free_rq(rq); - blk_put_request(rq); + ret = bd->sg_io_fn(bd->queue, &hdr, mode, bsg_timeout(bd, &hdr)); if (!ret && copy_to_user(uarg, &hdr, sizeof(hdr))) return -EFAULT; return ret; @@ -211,8 +176,7 @@ void bsg_unregister_queue(struct bsg_device *bd) EXPORT_SYMBOL_GPL(bsg_unregister_queue); struct bsg_device *bsg_register_queue(struct request_queue *q, - struct device *parent, const char *name, - const struct bsg_ops *ops) + struct device *parent, const char *name, bsg_sg_io_fn *sg_io_fn) { struct bsg_device *bd; int ret; @@ -223,7 +187,7 @@ struct bsg_device *bsg_register_queue(struct request_queue *q, bd->max_queue = BSG_DEFAULT_CMDS; bd->reserved_size = INT_MAX; bd->queue = q; - bd->ops = ops; + bd->sg_io_fn = sg_io_fn; ret = ida_simple_get(&bsg_minor_ida, 0, BSG_MAX_DEVS, GFP_KERNEL); if (ret < 0) { diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c index c0d41c45c2be..d13a67b82429 100644 --- a/drivers/scsi/scsi_bsg.c +++ b/drivers/scsi/scsi_bsg.c @@ -9,42 +9,57 @@ #define uptr64(val) ((void __user *)(uintptr_t)(val)) -static int scsi_bsg_check_proto(struct sg_io_v4 *hdr) +static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, + fmode_t mode, unsigned int timeout) { + struct scsi_request *sreq; + struct request *rq; + struct bio *bio; + int ret; + if (hdr->protocol != BSG_PROTOCOL_SCSI || hdr->subprotocol != BSG_SUB_PROTOCOL_SCSI_CMD) return -EINVAL; - return 0; -} - -static int scsi_bsg_fill_hdr(struct request *rq, struct sg_io_v4 *hdr, - fmode_t mode) -{ - struct scsi_request *sreq = scsi_req(rq); - if (hdr->dout_xfer_len && hdr->din_xfer_len) { pr_warn_once("BIDI support in bsg has been removed.\n"); return -EOPNOTSUPP; } + rq = blk_get_request(q, hdr->dout_xfer_len ? + REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); + if (IS_ERR(rq)) + return PTR_ERR(rq); + rq->timeout = timeout; + + ret = -ENOMEM; + sreq = scsi_req(rq); sreq->cmd_len = hdr->request_len; if (sreq->cmd_len > BLK_MAX_CDB) { sreq->cmd = kzalloc(sreq->cmd_len, GFP_KERNEL); if (!sreq->cmd) - return -ENOMEM; + goto out_put_request; } + ret = -EFAULT; if (copy_from_user(sreq->cmd, uptr64(hdr->request), sreq->cmd_len)) - return -EFAULT; + goto out_free_cmd; + ret = -EPERM; if (!scsi_cmd_allowed(sreq->cmd, mode)) - return -EPERM; - return 0; -} + goto out_free_cmd; -static int scsi_bsg_complete_rq(struct request *rq, struct sg_io_v4 *hdr) -{ - struct scsi_request *sreq = scsi_req(rq); - int ret = 0; + if (hdr->dout_xfer_len) { + ret = blk_rq_map_user(rq->q, rq, NULL, uptr64(hdr->dout_xferp), + hdr->dout_xfer_len, GFP_KERNEL); + } else if (hdr->din_xfer_len) { + ret = blk_rq_map_user(rq->q, rq, NULL, uptr64(hdr->din_xferp), + hdr->din_xfer_len, GFP_KERNEL); + } + + if (ret) + goto out_free_cmd; + + bio = rq->bio; + blk_execute_rq(NULL, rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL)); /* * fill in all the output members @@ -74,23 +89,17 @@ static int scsi_bsg_complete_rq(struct request *rq, struct sg_io_v4 *hdr) else hdr->dout_resid = sreq->resid_len; - return ret; -} + blk_rq_unmap_user(bio); -static void scsi_bsg_free_rq(struct request *rq) -{ +out_free_cmd: scsi_req_free_cmd(scsi_req(rq)); +out_put_request: + blk_put_request(rq); + return ret; } -static const struct bsg_ops scsi_bsg_ops = { - .check_proto = scsi_bsg_check_proto, - .fill_hdr = scsi_bsg_fill_hdr, - .complete_rq = scsi_bsg_complete_rq, - .free_rq = scsi_bsg_free_rq, -}; - struct bsg_device *scsi_bsg_register_queue(struct scsi_device *sdev) { return bsg_register_queue(sdev->request_queue, &sdev->sdev_gendev, - dev_name(&sdev->sdev_gendev), &scsi_bsg_ops); + dev_name(&sdev->sdev_gendev), scsi_bsg_sg_io_fn); } diff --git a/include/linux/bsg.h b/include/linux/bsg.h index fa21f79beda2..1ac81c809da9 100644 --- a/include/linux/bsg.h +++ b/include/linux/bsg.h @@ -6,20 +6,14 @@ struct bsg_device; struct device; -struct request; struct request_queue; -struct bsg_ops { - int (*check_proto)(struct sg_io_v4 *hdr); - int (*fill_hdr)(struct request *rq, struct sg_io_v4 *hdr, - fmode_t mode); - int (*complete_rq)(struct request *rq, struct sg_io_v4 *hdr); - void (*free_rq)(struct request *rq); -}; +typedef int (bsg_sg_io_fn)(struct request_queue *, struct sg_io_v4 *hdr, + fmode_t mode, unsigned int timeout); struct bsg_device *bsg_register_queue(struct request_queue *q, struct device *parent, const char *name, - const struct bsg_ops *ops); + bsg_sg_io_fn *sg_io_fn); void bsg_unregister_queue(struct bsg_device *bcd); #endif /* _LINUX_BSG_H */ -- cgit v1.2.3 From 342f43af70dbc74f8629381998f92c060e1763a2 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Thu, 29 Jul 2021 15:52:50 +0200 Subject: iscsi_ibft: fix crash due to KASLR physical memory remapping Starting with commit a799c2bd29d1 ("x86/setup: Consolidate early memory reservations") memory reservations have been moved earlier during the boot process, before the execution of the Kernel Address Space Layout Randomization code. setup_arch() calls the iscsi_ibft's find_ibft_region() function to find and reserve the memory dedicated to the iBFT and this function also saves a virtual pointer to the iBFT table for later use. The problem is that if KALSR is active, the physical memory gets remapped somewhere else in the virtual address space and the pointer is no longer valid, this will cause a kernel panic when the iscsi driver tries to dereference it. iBFT detected. BUG: unable to handle page fault for address: ffff888000099fd8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI ..snip.. Call Trace: ? ibft_create_kobject+0x1d2/0x1d2 [iscsi_ibft] do_one_initcall+0x44/0x1d0 ? kmem_cache_alloc_trace+0x119/0x220 do_init_module+0x5c/0x270 __do_sys_init_module+0x12e/0x1b0 do_syscall_64+0x40/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Fix this bug by saving the address of the physical location of the ibft; later the driver will use isa_bus_to_virt() to get the correct virtual address. N.B. On each reboot KASLR randomizes the virtual addresses so assuming phys_to_virt before KASLR does its deed is incorrect. Simplify the code by renaming find_ibft_region() to reserve_ibft_region() and remove all the wrappers. Signed-off-by: Maurizio Lombardi Reviewed-by: Mike Rapoport Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/kernel/setup.c | 10 -------- drivers/firmware/iscsi_ibft.c | 10 +++++--- drivers/firmware/iscsi_ibft_find.c | 48 ++++++++++++++------------------------ include/linux/iscsi_ibft.h | 18 ++++++-------- 4 files changed, 32 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1e720626069a..b6a62af06a9f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -571,16 +571,6 @@ void __init reserve_standard_io_resources(void) } -static __init void reserve_ibft_region(void) -{ - unsigned long addr, size = 0; - - addr = find_ibft_region(&size); - - if (size) - memblock_reserve(addr, size); -} - static bool __init snb_gfx_workaround_needed(void) { #ifdef CONFIG_PCI diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c index 7127a04bca19..612a59e213df 100644 --- a/drivers/firmware/iscsi_ibft.c +++ b/drivers/firmware/iscsi_ibft.c @@ -84,8 +84,10 @@ MODULE_DESCRIPTION("sysfs interface to BIOS iBFT information"); MODULE_LICENSE("GPL"); MODULE_VERSION(IBFT_ISCSI_VERSION); +static struct acpi_table_ibft *ibft_addr; + #ifndef CONFIG_ISCSI_IBFT_FIND -struct acpi_table_ibft *ibft_addr; +phys_addr_t ibft_phys_addr; #endif struct ibft_hdr { @@ -858,11 +860,13 @@ static int __init ibft_init(void) int rc = 0; /* - As on UEFI systems the setup_arch()/find_ibft_region() + As on UEFI systems the setup_arch()/reserve_ibft_region() is called before ACPI tables are parsed and it only does legacy finding. */ - if (!ibft_addr) + if (ibft_phys_addr) + ibft_addr = isa_bus_to_virt(ibft_phys_addr); + else acpi_find_ibft_region(); if (ibft_addr) { diff --git a/drivers/firmware/iscsi_ibft_find.c b/drivers/firmware/iscsi_ibft_find.c index 64bb94523281..a0594590847d 100644 --- a/drivers/firmware/iscsi_ibft_find.c +++ b/drivers/firmware/iscsi_ibft_find.c @@ -31,8 +31,8 @@ /* * Physical location of iSCSI Boot Format Table. */ -struct acpi_table_ibft *ibft_addr; -EXPORT_SYMBOL_GPL(ibft_addr); +phys_addr_t ibft_phys_addr; +EXPORT_SYMBOL_GPL(ibft_phys_addr); static const struct { char *sign; @@ -47,13 +47,24 @@ static const struct { #define VGA_MEM 0xA0000 /* VGA buffer */ #define VGA_SIZE 0x20000 /* 128kB */ -static int __init find_ibft_in_mem(void) +/* + * Routine used to find and reserve the iSCSI Boot Format Table + */ +void __init reserve_ibft_region(void) { unsigned long pos; unsigned int len = 0; void *virt; int i; + ibft_phys_addr = 0; + + /* iBFT 1.03 section 1.4.3.1 mandates that UEFI machines will + * only use ACPI for this + */ + if (efi_enabled(EFI_BOOT)) + return; + for (pos = IBFT_START; pos < IBFT_END; pos += 16) { /* The table can't be inside the VGA BIOS reserved space, * so skip that area */ @@ -70,35 +81,12 @@ static int __init find_ibft_in_mem(void) /* if the length of the table extends past 1M, * the table cannot be valid. */ if (pos + len <= (IBFT_END-1)) { - ibft_addr = (struct acpi_table_ibft *)virt; - pr_info("iBFT found at 0x%lx.\n", pos); - goto done; + ibft_phys_addr = pos; + memblock_reserve(ibft_phys_addr, PAGE_ALIGN(len)); + pr_info("iBFT found at 0x%lx.\n", ibft_phys_addr); + return; } } } } -done: - return len; -} -/* - * Routine used to find the iSCSI Boot Format Table. The logical - * kernel address is set in the ibft_addr global variable. - */ -unsigned long __init find_ibft_region(unsigned long *sizep) -{ - ibft_addr = NULL; - - /* iBFT 1.03 section 1.4.3.1 mandates that UEFI machines will - * only use ACPI for this */ - - if (!efi_enabled(EFI_BOOT)) - find_ibft_in_mem(); - - if (ibft_addr) { - *sizep = PAGE_ALIGN(ibft_addr->header.length); - return (u64)virt_to_phys(ibft_addr); - } - - *sizep = 0; - return 0; } diff --git a/include/linux/iscsi_ibft.h b/include/linux/iscsi_ibft.h index b7b45ca82bea..790e7fcfc1a6 100644 --- a/include/linux/iscsi_ibft.h +++ b/include/linux/iscsi_ibft.h @@ -13,26 +13,22 @@ #ifndef ISCSI_IBFT_H #define ISCSI_IBFT_H -#include +#include /* - * Logical location of iSCSI Boot Format Table. - * If the value is NULL there is no iBFT on the machine. + * Physical location of iSCSI Boot Format Table. + * If the value is 0 there is no iBFT on the machine. */ -extern struct acpi_table_ibft *ibft_addr; +extern phys_addr_t ibft_phys_addr; /* * Routine used to find and reserve the iSCSI Boot Format Table. The - * mapped address is set in the ibft_addr variable. + * physical address is set in the ibft_phys_addr variable. */ #ifdef CONFIG_ISCSI_IBFT_FIND -unsigned long find_ibft_region(unsigned long *sizep); +void reserve_ibft_region(void); #else -static inline unsigned long find_ibft_region(unsigned long *sizep) -{ - *sizep = 0; - return 0; -} +static inline void reserve_ibft_region(void) {} #endif #endif /* ISCSI_IBFT_H */ -- cgit v1.2.3 From 4a7a603cad3f667fb02e194c0a3412d3a7292093 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 14 Jul 2021 11:22:05 +0800 Subject: soundwire: add flag to ignore all command/control for mockup devices SoundWire mockup devices don't take part in the command/control protocol, so all commands will complete with -ENODATA or Command_Ignored results. With a flag, we can suppress such errors in the bus management and make it appear as if all read/writes succeed. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20210714032209.11284-7-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 3 +++ sound/soc/codecs/sdw-mockup.c | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index a48ac3e77301..76ce3f3ac0f2 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -661,6 +661,8 @@ struct sdw_slave_ops { * initialized * @first_interrupt_done: status flag tracking if the interrupt handling * for a Slave happens for the first time after enumeration + * @is_mockup_device: status flag used to squelch errors in the command/control + * protocol for SoundWire mockup devices */ struct sdw_slave { struct sdw_slave_id id; @@ -683,6 +685,7 @@ struct sdw_slave { struct completion initialization_complete; u32 unattach_request; bool first_interrupt_done; + bool is_mockup_device; }; #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev) diff --git a/sound/soc/codecs/sdw-mockup.c b/sound/soc/codecs/sdw-mockup.c index a4f79eb2c69d..8ea13cfa9f8e 100644 --- a/sound/soc/codecs/sdw-mockup.c +++ b/sound/soc/codecs/sdw-mockup.c @@ -263,6 +263,8 @@ static int sdw_mockup_sdw_probe(struct sdw_slave *slave, dev_set_drvdata(dev, sdw_mockup); sdw_mockup->slave = slave; + slave->is_mockup_device = true; + ret = devm_snd_soc_register_component(dev, &snd_soc_sdw_mockup_component, sdw_mockup_dai, -- cgit v1.2.3 From 3136895cc5b665c1ab406d78f90c0700a3551e74 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 23 Jul 2021 02:32:05 -0700 Subject: iommu: Improve iommu_iotlb_gather helpers The Mediatek driver is not the only one which might want a basic address-based gathering behaviour, so although it's arguably simple enough to open-code, let's factor it out for the sake of cleanliness. Let's also take this opportunity to document the intent of these helpers for clarity. Cc: Joerg Roedel Cc: Will Deacon Cc: Jiajun Cao Cc: Robin Murphy Cc: Lu Baolu Cc: iommu@lists.linux-foundation.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Robin Murphy Signed-off-by: Nadav Amit Link: https://lore.kernel.org/r/20210723093209.714328-4-namit@vmware.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 6 +----- include/linux/iommu.h | 38 +++++++++++++++++++++++++++++++++----- 2 files changed, 34 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 6f7c69688ce2..d9939e4af35c 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -520,12 +520,8 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain, struct iommu_iotlb_gather *gather) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); - unsigned long end = iova + size - 1; - if (gather->start > iova) - gather->start = iova; - if (gather->end < end) - gather->end = end; + iommu_iotlb_gather_add_range(gather, iova, size); return dom->iop->unmap(dom->iop, iova, size, gather); } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 32d448050bf7..e554871db46f 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -497,6 +497,38 @@ static inline void iommu_iotlb_sync(struct iommu_domain *domain, iommu_iotlb_gather_init(iotlb_gather); } +/** + * iommu_iotlb_gather_add_range - Gather for address-based TLB invalidation + * @gather: TLB gather data + * @iova: start of page to invalidate + * @size: size of page to invalidate + * + * Helper for IOMMU drivers to build arbitrarily-sized invalidation commands + * where only the address range matters, and simply minimising intermediate + * syncs is preferred. + */ +static inline void iommu_iotlb_gather_add_range(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t size) +{ + unsigned long end = iova + size - 1; + + if (gather->start > iova) + gather->start = iova; + if (gather->end < end) + gather->end = end; +} + +/** + * iommu_iotlb_gather_add_page - Gather for page-based TLB invalidation + * @domain: IOMMU domain to be invalidated + * @gather: TLB gather data + * @iova: start of page to invalidate + * @size: size of page to invalidate + * + * Helper for IOMMU drivers to build invalidation commands based on individual + * pages, or with page size/table level hints which cannot be gathered if they + * differ. + */ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, struct iommu_iotlb_gather *gather, unsigned long iova, size_t size) @@ -515,11 +547,7 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, gather->pgsize = size; } - if (gather->end < end) - gather->end = end; - - if (gather->start > start) - gather->start = start; + iommu_iotlb_gather_add_range(gather, iova, size); } /* PCI device grouping function */ -- cgit v1.2.3 From febb82c208e481eee057c70fa3176bb48712a111 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Fri, 23 Jul 2021 02:32:06 -0700 Subject: iommu: Factor iommu_iotlb_gather_is_disjoint() out MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Refactor iommu_iotlb_gather_add_page() and factor out the logic that detects whether IOTLB gather range and a new range are disjoint. To be used by the next patch that implements different gathering logic for AMD. Note that updating gather->pgsize unconditionally does not affect correctness as the function had (and has) an invariant, in which gather->pgsize always represents the flushing granularity of its range. Arguably, “size" should never be zero, but lets assume for the matter of discussion that it might. If "size" equals to "gather->pgsize", then the assignment in question has no impact. Otherwise, if "size" is non-zero, then iommu_iotlb_sync() would initialize the size and range (see iommu_iotlb_gather_init()), and the invariant is kept. Otherwise, "size" is zero, and "gather" already holds a range, so gather->pgsize is non-zero and (gather->pgsize && gather->pgsize != size) is true. Therefore, again, iommu_iotlb_sync() would be called and initialize the size. Cc: Joerg Roedel Cc: Jiajun Cao Cc: Lu Baolu Cc: iommu@lists.linux-foundation.org Cc: linux-kernel@vger.kernel.org> Reviewed-by: Robin Murphy Acked-by: Will Deacon Signed-off-by: Nadav Amit Link: https://lore.kernel.org/r/20210723093209.714328-5-namit@vmware.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index e554871db46f..979a5ceeea55 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -497,6 +497,28 @@ static inline void iommu_iotlb_sync(struct iommu_domain *domain, iommu_iotlb_gather_init(iotlb_gather); } +/** + * iommu_iotlb_gather_is_disjoint - Checks whether a new range is disjoint + * + * @gather: TLB gather data + * @iova: start of page to invalidate + * @size: size of page to invalidate + * + * Helper for IOMMU drivers to check whether a new range and the gathered range + * are disjoint. For many IOMMUs, flushing the IOMMU in this case is better + * than merging the two, which might lead to unnecessary invalidations. + */ +static inline +bool iommu_iotlb_gather_is_disjoint(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t size) +{ + unsigned long start = iova, end = start + size - 1; + + return gather->end != 0 && + (end + 1 < gather->start || start > gather->end + 1); +} + + /** * iommu_iotlb_gather_add_range - Gather for address-based TLB invalidation * @gather: TLB gather data @@ -533,20 +555,16 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, struct iommu_iotlb_gather *gather, unsigned long iova, size_t size) { - unsigned long start = iova, end = start + size - 1; - /* * If the new page is disjoint from the current range or is mapped at * a different granularity, then sync the TLB so that the gather * structure can be rewritten. */ - if (gather->pgsize != size || - end + 1 < gather->start || start > gather->end + 1) { - if (gather->pgsize) - iommu_iotlb_sync(domain, gather); - gather->pgsize = size; - } + if ((gather->pgsize && gather->pgsize != size) || + iommu_iotlb_gather_is_disjoint(gather, iova, size)) + iommu_iotlb_sync(domain, gather); + gather->pgsize = size; iommu_iotlb_gather_add_range(gather, iova, size); } -- cgit v1.2.3 From 87663c39f898b18905499126548da61450628682 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 23 Jul 2021 15:18:01 +0200 Subject: netfilter: ebtables: do not hook tables by default If any of these modules is loaded, hooks get registered in all netns: Before: 'unshare -n nft list hooks' shows: family bridge hook prerouting { -2147483648 ebt_broute -0000000300 ebt_nat_hook } family bridge hook input { -0000000200 ebt_filter_hook } family bridge hook forward { -0000000200 ebt_filter_hook } family bridge hook output { +0000000100 ebt_nat_hook +0000000200 ebt_filter_hook } family bridge hook postrouting { +0000000300 ebt_nat_hook } This adds 'template 'tables' for ebtables. Each ebtable_foo registers the table as a template, with an init function that gets called once the first get/setsockopt call is made. ebtables core then searches the (per netns) list of tables. If no table is found, it searches the list of templates instead. If a template entry exists, the init function is called which will enable the table and register the hooks (so packets are diverted to the table). If no entry is found in the template list, request_module is called. After this, hook registration is delayed until the 'ebtables' (set/getsockopt) request is made for a given table and will only happen in the specific namespace. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge/ebtables.h | 2 + net/bridge/netfilter/ebtable_broute.c | 17 ++++- net/bridge/netfilter/ebtable_filter.c | 17 ++++- net/bridge/netfilter/ebtable_nat.c | 17 ++++- net/bridge/netfilter/ebtables.c | 109 ++++++++++++++++++++++++++---- 5 files changed, 139 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index a8178253ce53..10a01978bc0d 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -127,4 +127,6 @@ static inline bool ebt_invalid_target(int target) return (target < -NUM_STANDARD_TARGETS || target >= 0); } +int ebt_register_template(const struct ebt_table *t, int(*table_init)(struct net *net)); +void ebt_unregister_template(const struct ebt_table *t); #endif diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 020b1487ee0c..a7af4eaff17d 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -98,7 +98,7 @@ static const struct nf_hook_ops ebt_ops_broute = { .priority = NF_BR_PRI_FIRST, }; -static int __net_init broute_net_init(struct net *net) +static int broute_table_init(struct net *net) { return ebt_register_table(net, &broute_table, &ebt_ops_broute); } @@ -114,19 +114,30 @@ static void __net_exit broute_net_exit(struct net *net) } static struct pernet_operations broute_net_ops = { - .init = broute_net_init, .exit = broute_net_exit, .pre_exit = broute_net_pre_exit, }; static int __init ebtable_broute_init(void) { - return register_pernet_subsys(&broute_net_ops); + int ret = ebt_register_template(&broute_table, broute_table_init); + + if (ret) + return ret; + + ret = register_pernet_subsys(&broute_net_ops); + if (ret) { + ebt_unregister_template(&broute_table); + return ret; + } + + return 0; } static void __exit ebtable_broute_fini(void) { unregister_pernet_subsys(&broute_net_ops); + ebt_unregister_template(&broute_table); } module_init(ebtable_broute_init); diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 8ec0b3736803..c0b121df4a9a 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -86,7 +86,7 @@ static const struct nf_hook_ops ebt_ops_filter[] = { }, }; -static int __net_init frame_filter_net_init(struct net *net) +static int frame_filter_table_init(struct net *net) { return ebt_register_table(net, &frame_filter, ebt_ops_filter); } @@ -102,19 +102,30 @@ static void __net_exit frame_filter_net_exit(struct net *net) } static struct pernet_operations frame_filter_net_ops = { - .init = frame_filter_net_init, .exit = frame_filter_net_exit, .pre_exit = frame_filter_net_pre_exit, }; static int __init ebtable_filter_init(void) { - return register_pernet_subsys(&frame_filter_net_ops); + int ret = ebt_register_template(&frame_filter, frame_filter_table_init); + + if (ret) + return ret; + + ret = register_pernet_subsys(&frame_filter_net_ops); + if (ret) { + ebt_unregister_template(&frame_filter); + return ret; + } + + return 0; } static void __exit ebtable_filter_fini(void) { unregister_pernet_subsys(&frame_filter_net_ops); + ebt_unregister_template(&frame_filter); } module_init(ebtable_filter_init); diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 7c8a1064a531..4078151c224f 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -85,7 +85,7 @@ static const struct nf_hook_ops ebt_ops_nat[] = { }, }; -static int __net_init frame_nat_net_init(struct net *net) +static int frame_nat_table_init(struct net *net) { return ebt_register_table(net, &frame_nat, ebt_ops_nat); } @@ -101,19 +101,30 @@ static void __net_exit frame_nat_net_exit(struct net *net) } static struct pernet_operations frame_nat_net_ops = { - .init = frame_nat_net_init, .exit = frame_nat_net_exit, .pre_exit = frame_nat_net_pre_exit, }; static int __init ebtable_nat_init(void) { - return register_pernet_subsys(&frame_nat_net_ops); + int ret = ebt_register_template(&frame_nat, frame_nat_table_init); + + if (ret) + return ret; + + ret = register_pernet_subsys(&frame_nat_net_ops); + if (ret) { + ebt_unregister_template(&frame_nat); + return ret; + } + + return ret; } static void __exit ebtable_nat_fini(void) { unregister_pernet_subsys(&frame_nat_net_ops); + ebt_unregister_template(&frame_nat); } module_init(ebtable_nat_init); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index f022deb3721e..83d1798dfbb4 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -44,7 +44,16 @@ struct ebt_pernet { struct list_head tables; }; +struct ebt_template { + struct list_head list; + char name[EBT_TABLE_MAXNAMELEN]; + struct module *owner; + /* called when table is needed in the given netns */ + int (*table_init)(struct net *net); +}; + static unsigned int ebt_pernet_id __read_mostly; +static LIST_HEAD(template_tables); static DEFINE_MUTEX(ebt_mutex); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT @@ -309,30 +318,57 @@ letscontinue: /* If it succeeds, returns element and locks mutex */ static inline void * -find_inlist_lock_noload(struct list_head *head, const char *name, int *error, +find_inlist_lock_noload(struct net *net, const char *name, int *error, struct mutex *mutex) { - struct { - struct list_head list; - char name[EBT_FUNCTION_MAXNAMELEN]; - } *e; + struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); + struct ebt_template *tmpl; + struct ebt_table *table; mutex_lock(mutex); - list_for_each_entry(e, head, list) { - if (strcmp(e->name, name) == 0) - return e; + list_for_each_entry(table, &ebt_net->tables, list) { + if (strcmp(table->name, name) == 0) + return table; } + + list_for_each_entry(tmpl, &template_tables, list) { + if (strcmp(name, tmpl->name) == 0) { + struct module *owner = tmpl->owner; + + if (!try_module_get(owner)) + goto out; + + mutex_unlock(mutex); + + *error = tmpl->table_init(net); + if (*error) { + module_put(owner); + return NULL; + } + + mutex_lock(mutex); + module_put(owner); + break; + } + } + + list_for_each_entry(table, &ebt_net->tables, list) { + if (strcmp(table->name, name) == 0) + return table; + } + +out: *error = -ENOENT; mutex_unlock(mutex); return NULL; } static void * -find_inlist_lock(struct list_head *head, const char *name, const char *prefix, +find_inlist_lock(struct net *net, const char *name, const char *prefix, int *error, struct mutex *mutex) { return try_then_request_module( - find_inlist_lock_noload(head, name, error, mutex), + find_inlist_lock_noload(net, name, error, mutex), "%s%s", prefix, name); } @@ -340,10 +376,7 @@ static inline struct ebt_table * find_table_lock(struct net *net, const char *name, int *error, struct mutex *mutex) { - struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); - - return find_inlist_lock(&ebt_net->tables, name, - "ebtable_", error, mutex); + return find_inlist_lock(net, name, "ebtable_", error, mutex); } static inline void ebt_free_table_info(struct ebt_table_info *info) @@ -1258,6 +1291,54 @@ out: return ret; } +int ebt_register_template(const struct ebt_table *t, int (*table_init)(struct net *net)) +{ + struct ebt_template *tmpl; + + mutex_lock(&ebt_mutex); + list_for_each_entry(tmpl, &template_tables, list) { + if (WARN_ON_ONCE(strcmp(t->name, tmpl->name) == 0)) { + mutex_unlock(&ebt_mutex); + return -EEXIST; + } + } + + tmpl = kzalloc(sizeof(*tmpl), GFP_KERNEL); + if (!tmpl) { + mutex_unlock(&ebt_mutex); + return -ENOMEM; + } + + tmpl->table_init = table_init; + strscpy(tmpl->name, t->name, sizeof(tmpl->name)); + tmpl->owner = t->me; + list_add(&tmpl->list, &template_tables); + + mutex_unlock(&ebt_mutex); + return 0; +} +EXPORT_SYMBOL(ebt_register_template); + +void ebt_unregister_template(const struct ebt_table *t) +{ + struct ebt_template *tmpl; + + mutex_lock(&ebt_mutex); + list_for_each_entry(tmpl, &template_tables, list) { + if (strcmp(t->name, tmpl->name)) + continue; + + list_del(&tmpl->list); + mutex_unlock(&ebt_mutex); + kfree(tmpl); + return; + } + + mutex_unlock(&ebt_mutex); + WARN_ON_ONCE(1); +} +EXPORT_SYMBOL(ebt_unregister_template); + static struct ebt_table *__ebt_find_table(struct net *net, const char *name) { struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); -- cgit v1.2.3 From 40e159403896f7d55c98f858d0b20fee1d941fa4 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 2 Aug 2021 12:21:30 +0100 Subject: mhi: Fix networking tree build. Signed-off-by: David S. Miller --- include/linux/mhi.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 944aa3aa3035..5e08468854db 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -719,8 +719,13 @@ void mhi_device_put(struct mhi_device *mhi_dev); * host and device execution environments match and * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels + * @flags: MHI channel flags */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, + unsigned int flags); + +/* Automatically allocate and queue inbound buffers */ +#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0) /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. -- cgit v1.2.3 From 29c34975c9391d3ad1fd5dd3c92ba0d41afe9549 Mon Sep 17 00:00:00 2001 From: Icenowy Zheng Date: Mon, 2 Aug 2021 14:37:41 +0800 Subject: regmap: allow const array for {devm_,}regmap_field_bulk_alloc reg_fields The reg_fields array fed to {devm_}regmap_field_bulk_alloc is currently not const, which is not correct on semantics (the functions shouldn't change reg_field contents) and prevents pre-defined const reg_field array to be used. As the implementation of this function doesn't change the content of it, just add const to its prototype. Signed-off-by: Icenowy Zheng Link: https://lore.kernel.org/r/20210802063741.76301-1-icenowy@sipeed.com Signed-off-by: Mark Brown --- drivers/base/regmap/regmap.c | 4 ++-- include/linux/regmap.h | 5 +++-- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index dcfa99ea7f31..6ad41d0720ba 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1298,7 +1298,7 @@ EXPORT_SYMBOL_GPL(devm_regmap_field_alloc); */ int regmap_field_bulk_alloc(struct regmap *regmap, struct regmap_field **rm_field, - struct reg_field *reg_field, + const struct reg_field *reg_field, int num_fields) { struct regmap_field *rf; @@ -1334,7 +1334,7 @@ EXPORT_SYMBOL_GPL(regmap_field_bulk_alloc); int devm_regmap_field_bulk_alloc(struct device *dev, struct regmap *regmap, struct regmap_field **rm_field, - struct reg_field *reg_field, + const struct reg_field *reg_field, int num_fields) { struct regmap_field *rf; diff --git a/include/linux/regmap.h b/include/linux/regmap.h index f5f08dd0a116..77755196277c 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1269,12 +1269,13 @@ void devm_regmap_field_free(struct device *dev, struct regmap_field *field); int regmap_field_bulk_alloc(struct regmap *regmap, struct regmap_field **rm_field, - struct reg_field *reg_field, + const struct reg_field *reg_field, int num_fields); void regmap_field_bulk_free(struct regmap_field *field); int devm_regmap_field_bulk_alloc(struct device *dev, struct regmap *regmap, struct regmap_field **field, - struct reg_field *reg_field, int num_fields); + const struct reg_field *reg_field, + int num_fields); void devm_regmap_field_bulk_free(struct device *dev, struct regmap_field *field); -- cgit v1.2.3 From 205d76ff0684a0b4fe3ff3a283d143a47439d191 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 26 Jul 2021 16:35:50 +0100 Subject: KVM: Remove kvm_is_transparent_hugepage() and PageTransCompoundMap() Now that arm64 has stopped using kvm_is_transparent_hugepage(), we can remove it, as well as PageTransCompoundMap() which was only used by the former. Acked-by: Paolo Bonzini Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210726153552.1535838-5-maz@kernel.org --- include/linux/page-flags.h | 37 ------------------------------------- virt/kvm/kvm_main.c | 10 ---------- 2 files changed, 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5922031ffab6..1ace27c4a8e0 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -632,43 +632,6 @@ static inline int PageTransCompound(struct page *page) return PageCompound(page); } -/* - * PageTransCompoundMap is the same as PageTransCompound, but it also - * guarantees the primary MMU has the entire compound page mapped - * through pmd_trans_huge, which in turn guarantees the secondary MMUs - * can also map the entire compound page. This allows the secondary - * MMUs to call get_user_pages() only once for each compound page and - * to immediately map the entire compound page with a single secondary - * MMU fault. If there will be a pmd split later, the secondary MMUs - * will get an update through the MMU notifier invalidation through - * split_huge_pmd(). - * - * Unlike PageTransCompound, this is safe to be called only while - * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount check false - * positives. - * - * We have to treat page cache THP differently since every subpage of it - * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE - * mapped in the current process so comparing subpage's _mapcount to - * compound_mapcount to filter out PTE mapped case. - */ -static inline int PageTransCompoundMap(struct page *page) -{ - struct page *head; - - if (!PageTransCompound(page)) - return 0; - - if (PageAnon(page)) - return atomic_read(&page->_mapcount) < 0; - - head = compound_head(page); - /* File THP is PMD mapped and not PTE mapped */ - return atomic_read(&page->_mapcount) == - atomic_read(compound_mapcount_ptr(head)); -} - /* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d20fba0fc290..7b72a2b35a7e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -189,16 +189,6 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn) return true; } -bool kvm_is_transparent_hugepage(kvm_pfn_t pfn) -{ - struct page *page = pfn_to_page(pfn); - - if (!PageTransCompoundMap(page)) - return false; - - return is_transparent_hugepage(compound_head(page)); -} - /* * Switches to specified vcpu, until a matching vcpu_put() */ -- cgit v1.2.3 From 36c3ce6c0d03a6c9992c3359f879cdc70fde836a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 26 Jul 2021 16:35:52 +0100 Subject: KVM: Get rid of kvm_get_pfn() Nobody is using kvm_get_pfn() anymore. Get rid of it. Acked-by: Paolo Bonzini Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210726153552.1535838-7-maz@kernel.org --- include/linux/kvm_host.h | 1 - virt/kvm/kvm_main.c | 9 +-------- 2 files changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ae7735b490b4..9818d271c2a1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -824,7 +824,6 @@ void kvm_release_pfn_clean(kvm_pfn_t pfn); void kvm_release_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_accessed(kvm_pfn_t pfn); -void kvm_get_pfn(kvm_pfn_t pfn); void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7b72a2b35a7e..1d3a03c0fed3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2215,7 +2215,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, * Get a reference here because callers of *hva_to_pfn* and * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the * returned pfn. This is only needed if the VMA has VM_MIXEDMAP - * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will + * set, but the kvm_try_get_pfn/kvm_release_pfn_clean pair will * simply do nothing for reserved pfns. * * Whoever called remap_pfn_range is also going to call e.g. @@ -2612,13 +2612,6 @@ void kvm_set_pfn_accessed(kvm_pfn_t pfn) } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); -void kvm_get_pfn(kvm_pfn_t pfn) -{ - if (!kvm_is_reserved_pfn(pfn)) - get_page(pfn_to_page(pfn)); -} -EXPORT_SYMBOL_GPL(kvm_get_pfn); - static int next_segment(unsigned long len, int offset) { if (len > PAGE_SIZE - offset) -- cgit v1.2.3 From 0b8f11737cffc1a406d1134b58687abc29d76b52 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 2 Jul 2021 15:04:23 -0700 Subject: KVM: Add infrastructure and macro to mark VM as bugged Signed-off-by: Sean Christopherson Signed-off-by: Isaku Yamahata Reviewed-by: Paolo Bonzini Message-Id: <3a0998645c328bf0895f1290e61821b70f048549.1625186503.git.isaku.yamahata@intel.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 28 +++++++++++++++++++++++++++- virt/kvm/kvm_main.c | 10 +++++----- 2 files changed, 32 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ae7735b490b4..5342592841be 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -150,6 +150,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 +#define KVM_REQ_VM_BUGGED (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ @@ -596,6 +597,7 @@ struct kvm { pid_t userspace_pid; unsigned int max_halt_poll_ns; u32 dirty_ring_size; + bool vm_bugged; #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; @@ -629,6 +631,31 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); +static inline void kvm_vm_bugged(struct kvm *kvm) +{ + kvm->vm_bugged = true; + kvm_make_all_cpus_request(kvm, KVM_REQ_VM_BUGGED); +} + +#define KVM_BUG(cond, kvm, fmt...) \ +({ \ + int __ret = (cond); \ + \ + if (WARN_ONCE(__ret && !(kvm)->vm_bugged, fmt)) \ + kvm_vm_bugged(kvm); \ + unlikely(__ret); \ +}) + +#define KVM_BUG_ON(cond, kvm) \ +({ \ + int __ret = (cond); \ + \ + if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \ + kvm_vm_bugged(kvm); \ + unlikely(__ret); \ +}) + static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); @@ -946,7 +973,6 @@ void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, struct kvm_vcpu *except, unsigned long *vcpu_bitmap, cpumask_var_t tmp); -bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, struct kvm_vcpu *except); bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d20fba0fc290..965c51ab0fe3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3598,7 +3598,7 @@ static long kvm_vcpu_ioctl(struct file *filp, struct kvm_fpu *fpu = NULL; struct kvm_sregs *kvm_sregs = NULL; - if (vcpu->kvm->mm != current->mm) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged) return -EIO; if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) @@ -3808,7 +3808,7 @@ static long kvm_vcpu_compat_ioctl(struct file *filp, void __user *argp = compat_ptr(arg); int r; - if (vcpu->kvm->mm != current->mm) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged) return -EIO; switch (ioctl) { @@ -3874,7 +3874,7 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, { struct kvm_device *dev = filp->private_data; - if (dev->kvm->mm != current->mm) + if (dev->kvm->mm != current->mm || dev->kvm->vm_bugged) return -EIO; switch (ioctl) { @@ -4196,7 +4196,7 @@ static long kvm_vm_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; - if (kvm->mm != current->mm) + if (kvm->mm != current->mm || kvm->vm_bugged) return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: @@ -4407,7 +4407,7 @@ static long kvm_vm_compat_ioctl(struct file *filp, struct kvm *kvm = filp->private_data; int r; - if (kvm->mm != current->mm) + if (kvm->mm != current->mm || kvm->vm_bugged) return -EIO; switch (ioctl) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT -- cgit v1.2.3 From 7ee3e8c39d3aed6ff4cc618d86ba9128f0c80087 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 2 Jul 2021 15:04:24 -0700 Subject: KVM: Export kvm_make_all_cpus_request() for use in marking VMs as bugged Export kvm_make_all_cpus_request() and hoist the request helper declarations of request up to the KVM_REQ_* definitions in preparation for adding a "VM bugged" framework. The framework will add KVM_BUG() and KVM_BUG_ON() as alternatives to full BUG()/BUG_ON() for cases where KVM has definitely hit a bug (in itself or in silicon) and the VM is all but guaranteed to be hosed. Marking a VM bugged will trigger a request to all vCPUs to allow arch code to forcefully evict each vCPU from its run loop. Signed-off-by: Sean Christopherson Signed-off-by: Isaku Yamahata Message-Id: <1d8cbbc8065d831343e70b5dcaea92268145eef1.1625186503.git.isaku.yamahata@intel.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5342592841be..b7bf9d6a7780 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -159,6 +159,15 @@ static inline bool is_error_page(struct page *page) }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) +bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + struct kvm_vcpu *except, + unsigned long *vcpu_bitmap, cpumask_var_t tmp); +bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); +bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, + struct kvm_vcpu *except); +bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap); + #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -631,7 +640,6 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) -bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); static inline void kvm_vm_bugged(struct kvm *kvm) { kvm->vm_bugged = true; @@ -970,14 +978,6 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc); void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); #endif -bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except, - unsigned long *vcpu_bitmap, cpumask_var_t tmp); -bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except); -bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, - unsigned long *vcpu_bitmap); - long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vcpu_ioctl(struct file *filp, -- cgit v1.2.3 From 1c69d7cf4a8b6b6cfd920a1e809f1cd33ae4369c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Aug 2021 07:30:29 -0700 Subject: Revert "mhi: Fix networking tree build." This reverts commit 40e159403896f7d55c98f858d0b20fee1d941fa4. Looks like this commit breaks the build for me. Signed-off-by: Jakub Kicinski --- include/linux/mhi.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 5e08468854db..944aa3aa3035 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -719,13 +719,8 @@ void mhi_device_put(struct mhi_device *mhi_dev); * host and device execution environments match and * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels - * @flags: MHI channel flags */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, - unsigned int flags); - -/* Automatically allocate and queue inbound buffers */ -#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0) +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. -- cgit v1.2.3 From f01639589e252a6f72c04716e1b5f9bb10e2debc Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Fri, 23 Jul 2021 19:54:46 +0800 Subject: soundwire: move intel sdw register definitions to sdw_intel.h Those Intel sdw registers will be used by ASoC SOF drivers in the following commits. So move those definitions to sdw_intel.h and it can be visible to SOF drivers. Signed-off-by: Bard Liao Reviewed-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Acked-By: Vinod Koul Link: https://lore.kernel.org/r/20210723115451.7245-2-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- drivers/soundwire/intel.c | 74 ---------------------------------- drivers/soundwire/intel_init.c | 6 --- include/linux/soundwire/sdw_intel.h | 79 +++++++++++++++++++++++++++++++++++++ 3 files changed, 79 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index c11e3d8cd308..15668d6fecd6 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -40,80 +40,6 @@ static int md_flags; module_param_named(sdw_md_flags, md_flags, int, 0444); MODULE_PARM_DESC(sdw_md_flags, "SoundWire Intel Master device flags (0x0 all off)"); -/* Intel SHIM Registers Definition */ -#define SDW_SHIM_LCAP 0x0 -#define SDW_SHIM_LCTL 0x4 -#define SDW_SHIM_IPPTR 0x8 -#define SDW_SHIM_SYNC 0xC - -#define SDW_SHIM_CTLSCAP(x) (0x010 + 0x60 * (x)) -#define SDW_SHIM_CTLS0CM(x) (0x012 + 0x60 * (x)) -#define SDW_SHIM_CTLS1CM(x) (0x014 + 0x60 * (x)) -#define SDW_SHIM_CTLS2CM(x) (0x016 + 0x60 * (x)) -#define SDW_SHIM_CTLS3CM(x) (0x018 + 0x60 * (x)) -#define SDW_SHIM_PCMSCAP(x) (0x020 + 0x60 * (x)) - -#define SDW_SHIM_PCMSYCHM(x, y) (0x022 + (0x60 * (x)) + (0x2 * (y))) -#define SDW_SHIM_PCMSYCHC(x, y) (0x042 + (0x60 * (x)) + (0x2 * (y))) -#define SDW_SHIM_PDMSCAP(x) (0x062 + 0x60 * (x)) -#define SDW_SHIM_IOCTL(x) (0x06C + 0x60 * (x)) -#define SDW_SHIM_CTMCTL(x) (0x06E + 0x60 * (x)) - -#define SDW_SHIM_WAKEEN 0x190 -#define SDW_SHIM_WAKESTS 0x192 - -#define SDW_SHIM_LCTL_SPA BIT(0) -#define SDW_SHIM_LCTL_SPA_MASK GENMASK(3, 0) -#define SDW_SHIM_LCTL_CPA BIT(8) -#define SDW_SHIM_LCTL_CPA_MASK GENMASK(11, 8) - -#define SDW_SHIM_SYNC_SYNCPRD_VAL_24 (24000 / SDW_CADENCE_GSYNC_KHZ - 1) -#define SDW_SHIM_SYNC_SYNCPRD_VAL_38_4 (38400 / SDW_CADENCE_GSYNC_KHZ - 1) -#define SDW_SHIM_SYNC_SYNCPRD GENMASK(14, 0) -#define SDW_SHIM_SYNC_SYNCCPU BIT(15) -#define SDW_SHIM_SYNC_CMDSYNC_MASK GENMASK(19, 16) -#define SDW_SHIM_SYNC_CMDSYNC BIT(16) -#define SDW_SHIM_SYNC_SYNCGO BIT(24) - -#define SDW_SHIM_PCMSCAP_ISS GENMASK(3, 0) -#define SDW_SHIM_PCMSCAP_OSS GENMASK(7, 4) -#define SDW_SHIM_PCMSCAP_BSS GENMASK(12, 8) - -#define SDW_SHIM_PCMSYCM_LCHN GENMASK(3, 0) -#define SDW_SHIM_PCMSYCM_HCHN GENMASK(7, 4) -#define SDW_SHIM_PCMSYCM_STREAM GENMASK(13, 8) -#define SDW_SHIM_PCMSYCM_DIR BIT(15) - -#define SDW_SHIM_PDMSCAP_ISS GENMASK(3, 0) -#define SDW_SHIM_PDMSCAP_OSS GENMASK(7, 4) -#define SDW_SHIM_PDMSCAP_BSS GENMASK(12, 8) -#define SDW_SHIM_PDMSCAP_CPSS GENMASK(15, 13) - -#define SDW_SHIM_IOCTL_MIF BIT(0) -#define SDW_SHIM_IOCTL_CO BIT(1) -#define SDW_SHIM_IOCTL_COE BIT(2) -#define SDW_SHIM_IOCTL_DO BIT(3) -#define SDW_SHIM_IOCTL_DOE BIT(4) -#define SDW_SHIM_IOCTL_BKE BIT(5) -#define SDW_SHIM_IOCTL_WPDD BIT(6) -#define SDW_SHIM_IOCTL_CIBD BIT(8) -#define SDW_SHIM_IOCTL_DIBD BIT(9) - -#define SDW_SHIM_CTMCTL_DACTQE BIT(0) -#define SDW_SHIM_CTMCTL_DODS BIT(1) -#define SDW_SHIM_CTMCTL_DOAIS GENMASK(4, 3) - -#define SDW_SHIM_WAKEEN_ENABLE BIT(0) -#define SDW_SHIM_WAKESTS_STATUS BIT(0) - -/* Intel ALH Register definitions */ -#define SDW_ALH_STRMZCFG(x) (0x000 + (0x4 * (x))) -#define SDW_ALH_NUM_STREAMS 64 - -#define SDW_ALH_STRMZCFG_DMAT_VAL 0x3 -#define SDW_ALH_STRMZCFG_DMAT GENMASK(7, 0) -#define SDW_ALH_STRMZCFG_CHN GENMASK(19, 16) - enum intel_pdi_type { INTEL_PDI_IN = 0, INTEL_PDI_OUT = 1, diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c index 9e283bef53d2..03ff69ab1797 100644 --- a/drivers/soundwire/intel_init.c +++ b/drivers/soundwire/intel_init.c @@ -18,12 +18,6 @@ #include "cadence_master.h" #include "intel.h" -#define SDW_SHIM_LCAP 0x0 -#define SDW_SHIM_BASE 0x2C000 -#define SDW_ALH_BASE 0x2C800 -#define SDW_LINK_BASE 0x30000 -#define SDW_LINK_SIZE 0x10000 - static void intel_link_dev_release(struct device *dev) { struct auxiliary_device *auxdev = to_auxiliary_dev(dev); diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 1ebea7764011..7fce6aee0c36 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -7,6 +7,85 @@ #include #include +#define SDW_SHIM_BASE 0x2C000 +#define SDW_ALH_BASE 0x2C800 +#define SDW_LINK_BASE 0x30000 +#define SDW_LINK_SIZE 0x10000 + +/* Intel SHIM Registers Definition */ +#define SDW_SHIM_LCAP 0x0 +#define SDW_SHIM_LCTL 0x4 +#define SDW_SHIM_IPPTR 0x8 +#define SDW_SHIM_SYNC 0xC + +#define SDW_SHIM_CTLSCAP(x) (0x010 + 0x60 * (x)) +#define SDW_SHIM_CTLS0CM(x) (0x012 + 0x60 * (x)) +#define SDW_SHIM_CTLS1CM(x) (0x014 + 0x60 * (x)) +#define SDW_SHIM_CTLS2CM(x) (0x016 + 0x60 * (x)) +#define SDW_SHIM_CTLS3CM(x) (0x018 + 0x60 * (x)) +#define SDW_SHIM_PCMSCAP(x) (0x020 + 0x60 * (x)) + +#define SDW_SHIM_PCMSYCHM(x, y) (0x022 + (0x60 * (x)) + (0x2 * (y))) +#define SDW_SHIM_PCMSYCHC(x, y) (0x042 + (0x60 * (x)) + (0x2 * (y))) +#define SDW_SHIM_PDMSCAP(x) (0x062 + 0x60 * (x)) +#define SDW_SHIM_IOCTL(x) (0x06C + 0x60 * (x)) +#define SDW_SHIM_CTMCTL(x) (0x06E + 0x60 * (x)) + +#define SDW_SHIM_WAKEEN 0x190 +#define SDW_SHIM_WAKESTS 0x192 + +#define SDW_SHIM_LCTL_SPA BIT(0) +#define SDW_SHIM_LCTL_SPA_MASK GENMASK(3, 0) +#define SDW_SHIM_LCTL_CPA BIT(8) +#define SDW_SHIM_LCTL_CPA_MASK GENMASK(11, 8) + +#define SDW_SHIM_SYNC_SYNCPRD_VAL_24 (24000 / SDW_CADENCE_GSYNC_KHZ - 1) +#define SDW_SHIM_SYNC_SYNCPRD_VAL_38_4 (38400 / SDW_CADENCE_GSYNC_KHZ - 1) +#define SDW_SHIM_SYNC_SYNCPRD GENMASK(14, 0) +#define SDW_SHIM_SYNC_SYNCCPU BIT(15) +#define SDW_SHIM_SYNC_CMDSYNC_MASK GENMASK(19, 16) +#define SDW_SHIM_SYNC_CMDSYNC BIT(16) +#define SDW_SHIM_SYNC_SYNCGO BIT(24) + +#define SDW_SHIM_PCMSCAP_ISS GENMASK(3, 0) +#define SDW_SHIM_PCMSCAP_OSS GENMASK(7, 4) +#define SDW_SHIM_PCMSCAP_BSS GENMASK(12, 8) + +#define SDW_SHIM_PCMSYCM_LCHN GENMASK(3, 0) +#define SDW_SHIM_PCMSYCM_HCHN GENMASK(7, 4) +#define SDW_SHIM_PCMSYCM_STREAM GENMASK(13, 8) +#define SDW_SHIM_PCMSYCM_DIR BIT(15) + +#define SDW_SHIM_PDMSCAP_ISS GENMASK(3, 0) +#define SDW_SHIM_PDMSCAP_OSS GENMASK(7, 4) +#define SDW_SHIM_PDMSCAP_BSS GENMASK(12, 8) +#define SDW_SHIM_PDMSCAP_CPSS GENMASK(15, 13) + +#define SDW_SHIM_IOCTL_MIF BIT(0) +#define SDW_SHIM_IOCTL_CO BIT(1) +#define SDW_SHIM_IOCTL_COE BIT(2) +#define SDW_SHIM_IOCTL_DO BIT(3) +#define SDW_SHIM_IOCTL_DOE BIT(4) +#define SDW_SHIM_IOCTL_BKE BIT(5) +#define SDW_SHIM_IOCTL_WPDD BIT(6) +#define SDW_SHIM_IOCTL_CIBD BIT(8) +#define SDW_SHIM_IOCTL_DIBD BIT(9) + +#define SDW_SHIM_CTMCTL_DACTQE BIT(0) +#define SDW_SHIM_CTMCTL_DODS BIT(1) +#define SDW_SHIM_CTMCTL_DOAIS GENMASK(4, 3) + +#define SDW_SHIM_WAKEEN_ENABLE BIT(0) +#define SDW_SHIM_WAKESTS_STATUS BIT(0) + +/* Intel ALH Register definitions */ +#define SDW_ALH_STRMZCFG(x) (0x000 + (0x4 * (x))) +#define SDW_ALH_NUM_STREAMS 64 + +#define SDW_ALH_STRMZCFG_DMAT_VAL 0x3 +#define SDW_ALH_STRMZCFG_DMAT GENMASK(7, 0) +#define SDW_ALH_STRMZCFG_CHN GENMASK(19, 16) + /** * struct sdw_intel_stream_params_data: configuration passed during * the @params_stream callback, e.g. for interaction with DSP -- cgit v1.2.3 From 60e9feb781dfe84158b4ec7a4d61c5103e96e6f3 Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Fri, 23 Jul 2021 19:54:51 +0800 Subject: soundwire: intel: introduce shim and alh base shim base and alh base are platform-dependent. Adding these two parameters allows us to use different shim/alh base for each platform. Signed-off-by: Bard Liao Reviewed-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Acked-By: Vinod Koul Link: https://lore.kernel.org/r/20210723115451.7245-7-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- drivers/soundwire/intel_init.c | 8 +++++--- include/linux/soundwire/sdw_intel.h | 8 ++++++++ sound/soc/sof/intel/hda.c | 2 ++ 3 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c index 03ff69ab1797..e329022e1669 100644 --- a/drivers/soundwire/intel_init.c +++ b/drivers/soundwire/intel_init.c @@ -63,8 +63,8 @@ static struct sdw_intel_link_dev *intel_link_dev_register(struct sdw_intel_res * link->mmio_base = res->mmio_base; link->registers = res->mmio_base + SDW_LINK_BASE + (SDW_LINK_SIZE * link_id); - link->shim = res->mmio_base + SDW_SHIM_BASE; - link->alh = res->mmio_base + SDW_ALH_BASE; + link->shim = res->mmio_base + res->shim_base; + link->alh = res->mmio_base + res->alh_base; link->ops = res->ops; link->dev = res->dev; @@ -214,6 +214,8 @@ static struct sdw_intel_ctx } ctx->mmio_base = res->mmio_base; + ctx->shim_base = res->shim_base; + ctx->alh_base = res->alh_base; ctx->link_mask = res->link_mask; ctx->handle = res->handle; mutex_init(&ctx->shim_lock); @@ -302,7 +304,7 @@ sdw_intel_startup_controller(struct sdw_intel_ctx *ctx) return -EINVAL; /* Check SNDWLCAP.LCOUNT */ - caps = ioread32(ctx->mmio_base + SDW_SHIM_BASE + SDW_SHIM_LCAP); + caps = ioread32(ctx->mmio_base + ctx->shim_base + SDW_SHIM_LCAP); caps &= GENMASK(2, 0); /* Check HW supported vs property value */ diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 7fce6aee0c36..8a463b8fc12a 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -195,6 +195,8 @@ struct sdw_intel_slave_id { * @link_list: list to handle interrupts across all links * @shim_lock: mutex to handle concurrent rmw access to shared SHIM registers. * @shim_mask: flags to track initialization of SHIM shared registers + * @shim_base: sdw shim base. + * @alh_base: sdw alh base. */ struct sdw_intel_ctx { int count; @@ -207,6 +209,8 @@ struct sdw_intel_ctx { struct list_head link_list; struct mutex shim_lock; /* lock for access to shared SHIM registers */ u32 shim_mask; + u32 shim_base; + u32 alh_base; }; /** @@ -225,6 +229,8 @@ struct sdw_intel_ctx { * machine-specific quirks are handled in the DSP driver. * @clock_stop_quirks: mask array of possible behaviors requested by the * DSP driver. The quirks are common for all links for now. + * @shim_base: sdw shim base. + * @alh_base: sdw alh base. */ struct sdw_intel_res { int count; @@ -236,6 +242,8 @@ struct sdw_intel_res { struct device *dev; u32 link_mask; u32 clock_stop_quirks; + u32 shim_base; + u32 alh_base; }; /* diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index c979581c6812..b4e35fbbe693 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -166,6 +166,8 @@ static int hda_sdw_probe(struct snd_sof_dev *sdev) memset(&res, 0, sizeof(res)); res.mmio_base = sdev->bar[HDA_DSP_BAR]; + res.shim_base = hdev->desc->sdw_shim_base; + res.alh_base = hdev->desc->sdw_alh_base; res.irq = sdev->ipc_irq; res.handle = hdev->info.handle; res.parent = sdev->dev; -- cgit v1.2.3 From 605c713023e3925d0444f495a42c903cb6ce875f Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 25 Jun 2021 11:32:07 -0400 Subject: KVM: Introduce kvm_get_kvm_safe() Introduce this safe version of kvm_get_kvm() so that it can be called even during vm destruction. Use it in kvm_debugfs_open() and remove the verbose comment. Prepare to be used elsewhere. Signed-off-by: Peter Xu Message-Id: <20210625153214.43106-3-peterx@redhat.com> [Preserve the comment in kvm_debugfs_open. - Paolo] Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 20 +++++++++++++++----- 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b7bf9d6a7780..de58a0890b1a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -755,6 +755,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); +bool kvm_get_kvm_safe(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); bool file_is_kvm(struct file *file); void kvm_put_kvm_no_destroy(struct kvm *kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 965c51ab0fe3..5cc79373827f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1120,6 +1120,16 @@ void kvm_get_kvm(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_get_kvm); +/* + * Make sure the vm is not during destruction, which is a safe version of + * kvm_get_kvm(). Return true if kvm referenced successfully, false otherwise. + */ +bool kvm_get_kvm_safe(struct kvm *kvm) +{ + return refcount_inc_not_zero(&kvm->users_count); +} +EXPORT_SYMBOL_GPL(kvm_get_kvm_safe); + void kvm_put_kvm(struct kvm *kvm) { if (refcount_dec_and_test(&kvm->users_count)) @@ -4969,12 +4979,12 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file, struct kvm_stat_data *stat_data = (struct kvm_stat_data *) inode->i_private; - /* The debugfs files are a reference to the kvm struct which - * is still valid when kvm_destroy_vm is called. - * To avoid the race between open and the removal of the debugfs - * directory we test against the users count. + /* + * The debugfs files are a reference to the kvm struct which + * is still valid when kvm_destroy_vm is called. kvm_get_kvm_safe + * avoids the race between open and the removal of the debugfs directory. */ - if (!refcount_inc_not_zero(&stat_data->kvm->users_count)) + if (!kvm_get_kvm_safe(stat_data->kvm)) return -ENOENT; if (simple_attr_open(inode, file, get, -- cgit v1.2.3 From 82868247897bea2d69a83dca9a6a557e2c96dac4 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 14 Jul 2021 15:38:42 +0100 Subject: arm64: kasan: mte: use a constant kernel GCR_EL1 value When KASAN_HW_TAGS is selected, KASAN is enabled at boot time, and the hardware supports MTE, we'll initialize `kernel_gcr_excl` with a value dependent on KASAN_TAG_MAX. While the resulting value is a constant which depends on KASAN_TAG_MAX, we have to perform some runtime work to generate the value, and have to read the value from memory during the exception entry path. It would be better if we could generate this as a constant at compile-time, and use it as such directly. Early in boot within __cpu_setup(), we initialize GCR_EL1 to a safe value, and later override this with the value required by KASAN. If CONFIG_KASAN_HW_TAGS is not selected, or if KASAN is disabeld at boot time, the kernel will not use IRG instructions, and so the initial value of GCR_EL1 is does not matter to the kernel. Thus, we can instead have __cpu_setup() initialize GCR_EL1 to a value consistent with KASAN_TAG_MAX, and avoid the need to re-initialize it during hotplug and resume form suspend. This patch makes arem64 use a compile-time constant KERNEL_GCR_EL1 value, which is compatible with KASAN_HW_TAGS when this is selected. This removes the need to re-initialize GCR_EL1 dynamically, and acts as an optimization to the entry assembly, which no longer needs to load this value from memory. The redundant initialization hooks are removed. In order to do this, KASAN_TAG_MAX needs to be visible outside of the core KASAN code. To do this, I've moved the KASAN_TAG_* values into . There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Reviewed-by: Catalin Marinas Reviewed-by: Andrey Konovalov Tested-by: Andrey Konovalov Link: https://lore.kernel.org/r/20210714143843.56537-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/memory.h | 1 - arch/arm64/include/asm/mte-kasan.h | 5 ----- arch/arm64/include/asm/mte.h | 6 ------ arch/arm64/include/asm/sysreg.h | 16 ++++++++++++++++ arch/arm64/kernel/entry.S | 5 ++--- arch/arm64/kernel/mte.c | 31 ------------------------------- arch/arm64/kernel/suspend.c | 1 - arch/arm64/mm/proc.S | 3 +-- include/linux/kasan-tags.h | 15 +++++++++++++++ mm/kasan/hw_tags.c | 2 -- mm/kasan/kasan.h | 15 +-------------- 11 files changed, 35 insertions(+), 65 deletions(-) create mode 100644 include/linux/kasan-tags.h (limited to 'include/linux') diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 824a3655dd93..7f4e6a923aa6 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -245,7 +245,6 @@ static inline const void *__tag_set(const void *addr, u8 tag) #define arch_enable_tagging_async() mte_enable_kernel_async() #define arch_set_tagging_report_once(state) mte_set_report_once(state) #define arch_force_async_tag_fault() mte_check_tfsr_exit() -#define arch_init_tags(max_tag) mte_init_tags(max_tag) #define arch_get_random_tag() mte_get_random_tag() #define arch_get_mem_tag(addr) mte_get_mem_tag(addr) #define arch_set_mem_tag_range(addr, size, tag, init) \ diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h index d952352bd008..82fa4ac4ad4e 100644 --- a/arch/arm64/include/asm/mte-kasan.h +++ b/arch/arm64/include/asm/mte-kasan.h @@ -130,7 +130,6 @@ static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag, void mte_enable_kernel_sync(void); void mte_enable_kernel_async(void); -void mte_init_tags(u64 max_tag); void mte_set_report_once(bool state); bool mte_report_once(void); @@ -165,10 +164,6 @@ static inline void mte_enable_kernel_async(void) { } -static inline void mte_init_tags(u64 max_tag) -{ -} - static inline void mte_set_report_once(bool state) { } diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index 58c7f80f5596..3f93b9e0b339 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -16,8 +16,6 @@ #include -extern u64 gcr_kernel_excl; - void mte_clear_page_tags(void *addr); unsigned long mte_copy_tags_from_user(void *to, const void __user *from, unsigned long n); @@ -43,7 +41,6 @@ void mte_copy_page_tags(void *kto, const void *kfrom); void mte_thread_init_user(void); void mte_thread_switch(struct task_struct *next); void mte_suspend_enter(void); -void mte_suspend_exit(void); long set_mte_ctrl(struct task_struct *task, unsigned long arg); long get_mte_ctrl(struct task_struct *task); int mte_ptrace_copy_tags(struct task_struct *child, long request, @@ -72,9 +69,6 @@ static inline void mte_thread_switch(struct task_struct *next) static inline void mte_suspend_enter(void) { } -static inline void mte_suspend_exit(void) -{ -} static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg) { return 0; diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 7b9c3acba684..f6687f6f536b 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -11,6 +11,7 @@ #include #include +#include /* * ARMv8 ARM reserves the following encoding for system registers: @@ -1067,6 +1068,21 @@ #define SYS_GCR_EL1_RRND (BIT(16)) #define SYS_GCR_EL1_EXCL_MASK 0xffffUL +#ifdef CONFIG_KASAN_HW_TAGS +/* + * KASAN always uses a whole byte for its tags. With CONFIG_KASAN_HW_TAGS it + * only uses tags in the range 0xF0-0xFF, which we map to MTE tags 0x0-0xF. + */ +#define __MTE_TAG_MIN (KASAN_TAG_MIN & 0xf) +#define __MTE_TAG_MAX (KASAN_TAG_MAX & 0xf) +#define __MTE_TAG_INCL GENMASK(__MTE_TAG_MAX, __MTE_TAG_MIN) +#define KERNEL_GCR_EL1_EXCL (SYS_GCR_EL1_EXCL_MASK & ~__MTE_TAG_INCL) +#else +#define KERNEL_GCR_EL1_EXCL SYS_GCR_EL1_EXCL_MASK +#endif + +#define KERNEL_GCR_EL1 (SYS_GCR_EL1_RRND | KERNEL_GCR_EL1_EXCL) + /* RGSR_EL1 Definitions */ #define SYS_RGSR_EL1_TAG_MASK 0xfUL #define SYS_RGSR_EL1_SEED_SHIFT 8 diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 468fae024bec..923ee2ac85fd 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -181,9 +181,8 @@ alternative_else_nop_endif alternative_if_not ARM64_MTE b 1f alternative_else_nop_endif - ldr_l \tmp, gcr_kernel_excl - - mte_set_gcr \tmp, \tmp2 + mov \tmp, KERNEL_GCR_EL1 + msr_s SYS_GCR_EL1, \tmp 1: #endif .endm diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 20a40e5a14fa..b538ff27a912 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -23,8 +23,6 @@ #include #include -u64 gcr_kernel_excl __ro_after_init; - static bool report_fault_once = true; static DEFINE_PER_CPU_READ_MOSTLY(u64, mte_tcf_preferred); @@ -104,26 +102,6 @@ int memcmp_pages(struct page *page1, struct page *page2) return ret; } -void mte_init_tags(u64 max_tag) -{ - static bool gcr_kernel_excl_initialized; - - if (!gcr_kernel_excl_initialized) { - /* - * The format of the tags in KASAN is 0xFF and in MTE is 0xF. - * This conversion extracts an MTE tag from a KASAN tag. - */ - u64 incl = GENMASK(FIELD_GET(MTE_TAG_MASK >> MTE_TAG_SHIFT, - max_tag), 0); - - gcr_kernel_excl = ~incl & SYS_GCR_EL1_EXCL_MASK; - gcr_kernel_excl_initialized = true; - } - - /* Enable the kernel exclude mask for random tags generation. */ - write_sysreg_s(SYS_GCR_EL1_RRND | gcr_kernel_excl, SYS_GCR_EL1); -} - static inline void __mte_enable_kernel(const char *mode, unsigned long tcf) { /* Enable MTE Sync Mode for EL1. */ @@ -262,15 +240,6 @@ void mte_suspend_enter(void) mte_check_tfsr_el1(); } -void mte_suspend_exit(void) -{ - if (!system_supports_mte()) - return; - - sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, gcr_kernel_excl); - isb(); -} - long set_mte_ctrl(struct task_struct *task, unsigned long arg) { u64 mte_ctrl = (~((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT) & diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 938ce6fbee8a..19ee7c33769d 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -76,7 +76,6 @@ void notrace __cpu_suspend_exit(void) spectre_v4_enable_mitigation(NULL); /* Restore additional feature-specific configuration */ - mte_suspend_exit(); ptrauth_suspend_exit(); } diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 35936c5ae1ce..d35c90d2e47a 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -437,8 +437,7 @@ SYM_FUNC_START(__cpu_setup) mov x10, #MAIR_ATTR_NORMAL_TAGGED bfi mair, x10, #(8 * MT_NORMAL_TAGGED), #8 - /* initialize GCR_EL1: all non-zero tags excluded by default */ - mov x10, #(SYS_GCR_EL1_RRND | SYS_GCR_EL1_EXCL_MASK) + mov x10, #KERNEL_GCR_EL1 msr_s SYS_GCR_EL1, x10 /* diff --git a/include/linux/kasan-tags.h b/include/linux/kasan-tags.h new file mode 100644 index 000000000000..4f85f562512c --- /dev/null +++ b/include/linux/kasan-tags.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KASAN_TAGS_H +#define _LINUX_KASAN_TAGS_H + +#define KASAN_TAG_KERNEL 0xFF /* native kernel pointers tag */ +#define KASAN_TAG_INVALID 0xFE /* inaccessible memory tag */ +#define KASAN_TAG_MAX 0xFD /* maximum value for random tags */ + +#ifdef CONFIG_KASAN_HW_TAGS +#define KASAN_TAG_MIN 0xF0 /* minimum value for random tags */ +#else +#define KASAN_TAG_MIN 0x00 /* minimum value for random tags */ +#endif + +#endif /* LINUX_KASAN_TAGS_H */ diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 4ea8c368b5b8..2c6c6c6ddfa2 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -142,8 +142,6 @@ void kasan_init_hw_tags_cpu(void) if (kasan_arg == KASAN_ARG_OFF) return; - hw_init_tags(KASAN_TAG_MAX); - /* * Enable async mode only when explicitly requested through * the command line. diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index d739cdd1621a..28a16b80bbef 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -3,6 +3,7 @@ #define __MM_KASAN_KASAN_H #include +#include #include #include @@ -51,16 +52,6 @@ extern bool kasan_flag_async __ro_after_init; #define KASAN_MEMORY_PER_SHADOW_PAGE (KASAN_GRANULE_SIZE << PAGE_SHIFT) -#define KASAN_TAG_KERNEL 0xFF /* native kernel pointers tag */ -#define KASAN_TAG_INVALID 0xFE /* inaccessible memory tag */ -#define KASAN_TAG_MAX 0xFD /* maximum value for random tags */ - -#ifdef CONFIG_KASAN_HW_TAGS -#define KASAN_TAG_MIN 0xF0 /* minimum value for random tags */ -#else -#define KASAN_TAG_MIN 0x00 /* minimum value for random tags */ -#endif - #ifdef CONFIG_KASAN_GENERIC #define KASAN_FREE_PAGE 0xFF /* page was freed */ #define KASAN_PAGE_REDZONE 0xFE /* redzone for kmalloc_large allocations */ @@ -299,9 +290,6 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #ifndef arch_enable_tagging_async #define arch_enable_tagging_async() #endif -#ifndef arch_init_tags -#define arch_init_tags(max_tag) -#endif #ifndef arch_set_tagging_report_once #define arch_set_tagging_report_once(state) #endif @@ -320,7 +308,6 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #define hw_enable_tagging_sync() arch_enable_tagging_sync() #define hw_enable_tagging_async() arch_enable_tagging_async() -#define hw_init_tags(max_tag) arch_init_tags(max_tag) #define hw_set_tagging_report_once(state) arch_set_tagging_report_once(state) #define hw_force_async_tag_fault() arch_force_async_tag_fault() #define hw_get_random_tag() arch_get_random_tag() -- cgit v1.2.3 From 06447ae5e33bfbc5a777cc06d9854a31f3912833 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 14 Jul 2021 21:56:55 +0200 Subject: ioprio: move user space relevant ioprio bits to UAPI includes systemd added a modified copy of include/linux/ioprio.h into its code to get the relevant content definitions for the exposed ioprio_[get|set] system calls. Move the user space relevant ioprio bits to the UAPI includes to be able to use the ioprio_[get|set] syscalls as intended. Cc: Kay Sievers Cc: Greg Kroah-Hartman Cc: Jens Axboe Cc: linux-block@vger.kernel.org Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20210714195655.181943-1-socketcan@hartkopp.net Signed-off-by: Jens Axboe --- include/linux/ioprio.h | 41 +--------------------------------------- include/uapi/linux/ioprio.h | 46 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+), 40 deletions(-) create mode 100644 include/uapi/linux/ioprio.h (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index e9bfe6972aed..ef9ad4fb245f 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -6,46 +6,7 @@ #include #include -/* - * Gives us 8 prio classes with 13-bits of data for each class - */ -#define IOPRIO_CLASS_SHIFT (13) -#define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) - -#define IOPRIO_PRIO_CLASS(mask) ((mask) >> IOPRIO_CLASS_SHIFT) -#define IOPRIO_PRIO_DATA(mask) ((mask) & IOPRIO_PRIO_MASK) -#define IOPRIO_PRIO_VALUE(class, data) (((class) << IOPRIO_CLASS_SHIFT) | data) - -#define ioprio_valid(mask) (IOPRIO_PRIO_CLASS((mask)) != IOPRIO_CLASS_NONE) - -/* - * These are the io priority groups as implemented by CFQ. RT is the realtime - * class, it always gets premium service. BE is the best-effort scheduling - * class, the default for any process. IDLE is the idle scheduling class, it - * is only served when no one else is using the disk. - */ -enum { - IOPRIO_CLASS_NONE, - IOPRIO_CLASS_RT, - IOPRIO_CLASS_BE, - IOPRIO_CLASS_IDLE, -}; - -/* - * 8 best effort priority levels are supported - */ -#define IOPRIO_BE_NR (8) - -enum { - IOPRIO_WHO_PROCESS = 1, - IOPRIO_WHO_PGRP, - IOPRIO_WHO_USER, -}; - -/* - * Fallback BE priority - */ -#define IOPRIO_NORM (4) +#include /* * if process has set io priority explicitly, use that. if not, convert diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h new file mode 100644 index 000000000000..77b17e08b0da --- /dev/null +++ b/include/uapi/linux/ioprio.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_IOPRIO_H +#define _UAPI_LINUX_IOPRIO_H + +/* + * Gives us 8 prio classes with 13-bits of data for each class + */ +#define IOPRIO_CLASS_SHIFT (13) +#define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) + +#define IOPRIO_PRIO_CLASS(mask) ((mask) >> IOPRIO_CLASS_SHIFT) +#define IOPRIO_PRIO_DATA(mask) ((mask) & IOPRIO_PRIO_MASK) +#define IOPRIO_PRIO_VALUE(class, data) (((class) << IOPRIO_CLASS_SHIFT) | data) + +/* + * These are the io priority groups as implemented by CFQ. RT is the realtime + * class, it always gets premium service. BE is the best-effort scheduling + * class, the default for any process. IDLE is the idle scheduling class, it + * is only served when no one else is using the disk. + */ +enum { + IOPRIO_CLASS_NONE, + IOPRIO_CLASS_RT, + IOPRIO_CLASS_BE, + IOPRIO_CLASS_IDLE, +}; + +#define ioprio_valid(mask) (IOPRIO_PRIO_CLASS((mask)) != IOPRIO_CLASS_NONE) + +/* + * 8 best effort priority levels are supported + */ +#define IOPRIO_BE_NR (8) + +enum { + IOPRIO_WHO_PROCESS = 1, + IOPRIO_WHO_PGRP, + IOPRIO_WHO_USER, +}; + +/* + * Fallback BE priority + */ +#define IOPRIO_NORM (4) + +#endif /* _UAPI_LINUX_IOPRIO_H */ -- cgit v1.2.3 From e45cef51dba9765a6e1df1be724f3d26323512c8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 27 Jul 2021 07:56:33 +0200 Subject: bvec: fix the include guards for bvec.h Fix the include guards to match the file naming. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/20210727055646.118787-3-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bvec.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index ff832e698efb..883faf5f1523 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -4,8 +4,8 @@ * * Copyright (C) 2001 Ming Lei */ -#ifndef __LINUX_BVEC_ITER_H -#define __LINUX_BVEC_ITER_H +#ifndef __LINUX_BVEC_H +#define __LINUX_BVEC_H #include #include @@ -183,4 +183,4 @@ static inline void bvec_advance(const struct bio_vec *bvec, } } -#endif /* __LINUX_BVEC_ITER_H */ +#endif /* __LINUX_BVEC_H */ -- cgit v1.2.3 From e6e7471706dc42cbe0e01278540c0730138d43e5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 27 Jul 2021 07:56:34 +0200 Subject: bvec: add a bvec_kmap_local helper Add a helper to call kmap_local_page on a bvec. There is no need for an unmap helper given that kunmap_local accept any address in the mapped page. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/20210727055646.118787-4-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bvec.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 883faf5f1523..f8710af18eef 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -7,6 +7,7 @@ #ifndef __LINUX_BVEC_H #define __LINUX_BVEC_H +#include #include #include #include @@ -183,4 +184,16 @@ static inline void bvec_advance(const struct bio_vec *bvec, } } +/** + * bvec_kmap_local - map a bvec into the kernel virtual address space + * @bvec: bvec to map + * + * Must be called on single-page bvecs only. Call kunmap_local on the returned + * address to unmap. + */ +static inline void *bvec_kmap_local(struct bio_vec *bvec) +{ + return kmap_local_page(bvec->bv_page) + bvec->bv_offset; +} + #endif /* __LINUX_BVEC_H */ -- cgit v1.2.3 From f93a181af40b159aabea2ccf1a0496e9280be2d5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 27 Jul 2021 07:56:35 +0200 Subject: bvec: add memcpy_{from,to}_bvec and memzero_bvec helper Add helpers to perform common memory operation on a bvec. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/20210727055646.118787-5-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bvec.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index f8710af18eef..f9fa43b940ff 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -196,4 +196,37 @@ static inline void *bvec_kmap_local(struct bio_vec *bvec) return kmap_local_page(bvec->bv_page) + bvec->bv_offset; } +/** + * memcpy_from_bvec - copy data from a bvec + * @bvec: bvec to copy from + * + * Must be called on single-page bvecs only. + */ +static inline void memcpy_from_bvec(char *to, struct bio_vec *bvec) +{ + memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, bvec->bv_len); +} + +/** + * memcpy_to_bvec - copy data to a bvec + * @bvec: bvec to copy to + * + * Must be called on single-page bvecs only. + */ +static inline void memcpy_to_bvec(struct bio_vec *bvec, const char *from) +{ + memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, bvec->bv_len); +} + +/** + * memzero_bvec - zero all data in a bvec + * @bvec: bvec to zero + * + * Must be called on single-page bvecs only. + */ +static inline void memzero_bvec(struct bio_vec *bvec) +{ + memzero_page(bvec->bv_page, bvec->bv_offset, bvec->bv_len); +} + #endif /* __LINUX_BVEC_H */ -- cgit v1.2.3 From bda135d9c03fae64c910a8c8d751eccd8408f400 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 27 Jul 2021 07:56:40 +0200 Subject: block: remove bvec_kmap_irq and bvec_kunmap_irq These two helpers are entirely unused now. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20210727055646.118787-10-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 42 ------------------------------------------ 1 file changed, 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 2203b686e1f0..7b5f65a81f2b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -5,7 +5,6 @@ #ifndef __LINUX_BIO_H #define __LINUX_BIO_H -#include #include #include /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ @@ -519,47 +518,6 @@ static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ -#ifdef CONFIG_HIGHMEM -/* - * remember never ever reenable interrupts between a bvec_kmap_irq and - * bvec_kunmap_irq! - */ -static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) -{ - unsigned long addr; - - /* - * might not be a highmem page, but the preempt/irq count - * balancing is a lot nicer this way - */ - local_irq_save(*flags); - addr = (unsigned long) kmap_atomic(bvec->bv_page); - - BUG_ON(addr & ~PAGE_MASK); - - return (char *) addr + bvec->bv_offset; -} - -static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) -{ - unsigned long ptr = (unsigned long) buffer & PAGE_MASK; - - kunmap_atomic((void *) ptr); - local_irq_restore(*flags); -} - -#else -static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) -{ - return page_address(bvec->bv_page) + bvec->bv_offset; -} - -static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) -{ - *flags = 0; -} -#endif - /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * -- cgit v1.2.3 From 14cf1dbb55bb07427babee425fd2a8a9300737cc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 22 Jul 2021 09:54:01 +0200 Subject: block: remove bdgrab All callers are gone, and no one should grab a pure inode reference to a block device anymore. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Link: https://lore.kernel.org/r/20210722075402.983367-9-hch@lst.de Signed-off-by: Jens Axboe --- fs/block_dev.c | 15 --------------- include/linux/blkdev.h | 1 - 2 files changed, 16 deletions(-) (limited to 'include/linux') diff --git a/fs/block_dev.c b/fs/block_dev.c index 4a6c8c0a3bc9..4f2c4e9e84f5 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -921,21 +921,6 @@ void bdev_add(struct block_device *bdev, dev_t dev) insert_inode_hash(bdev->bd_inode); } -/** - * bdgrab -- Grab a reference to an already referenced block device - * @bdev: Block device to grab a reference to. - * - * Returns the block_device with an additional reference when successful, - * or NULL if the inode is already beeing freed. - */ -struct block_device *bdgrab(struct block_device *bdev) -{ - if (!igrab(bdev->bd_inode)) - return NULL; - return bdev; -} -EXPORT_SYMBOL(bdgrab); - long nr_blockdev_pages(void) { struct inode *inode; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d3afea47ade6..eb1289a58917 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1984,7 +1984,6 @@ void blkdev_put_no_open(struct block_device *bdev); struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); -struct block_device *bdgrab(struct block_device *bdev); void bdput(struct block_device *); int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, loff_t lend); -- cgit v1.2.3 From 2f4731dcd0bb73379fbb9e3eb07ae7324125caef Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 22 Jul 2021 09:54:02 +0200 Subject: block: remove bdput Now that we've stopped using inode references for anything meaninful in the block layer get rid of the helper to put it and just open code the call to iput on the block_device inode. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20210722075402.983367-10-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 4 ++-- block/partitions/core.c | 2 +- fs/block_dev.c | 6 ------ include/linux/blkdev.h | 1 - 4 files changed, 3 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index 716f5ca479ad..5dbb99b57b33 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1076,7 +1076,7 @@ static void disk_release(struct device *dev) xa_destroy(&disk->part_tbl); if (test_bit(GD_QUEUE_REF, &disk->state) && disk->queue) blk_put_queue(disk->queue); - bdput(disk->part0); /* frees the disk */ + iput(disk->part0->bd_inode); /* frees the disk */ } struct class block_class = { .name = "block", @@ -1261,7 +1261,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) out_destroy_part_tbl: xa_destroy(&disk->part_tbl); - bdput(disk->part0); + iput(disk->part0->bd_inode); out_free_disk: kfree(disk); return NULL; diff --git a/block/partitions/core.c b/block/partitions/core.c index 4f7a1a9cd544..2415bffc2771 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -262,7 +262,7 @@ static void part_release(struct device *dev) if (MAJOR(dev->devt) == BLOCK_EXT_MAJOR) blk_free_ext_minor(MINOR(dev->devt)); put_disk(dev_to_bdev(dev)->bd_disk); - bdput(dev_to_bdev(dev)); + iput(dev_to_bdev(dev)->bd_inode); } static int part_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/fs/block_dev.c b/fs/block_dev.c index 4f2c4e9e84f5..6658f40ae492 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -934,12 +934,6 @@ long nr_blockdev_pages(void) return ret; } -void bdput(struct block_device *bdev) -{ - iput(bdev->bd_inode); -} -EXPORT_SYMBOL(bdput); - /** * bd_may_claim - test whether a block device can be claimed * @bdev: block device of interest diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index eb1289a58917..b5c033cf5f26 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1984,7 +1984,6 @@ void blkdev_put_no_open(struct block_device *bdev); struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); -void bdput(struct block_device *); int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, loff_t lend); -- cgit v1.2.3 From 2164877c7f373e14e55fca20b7c4a9c436fe4462 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 28 Jul 2021 07:37:56 +0200 Subject: block: remove cmdline-parser.c cmdline-parser.c is only used by the cmdline faux partition format, so merge the code into that and avoid an indirect call. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210728053756.409654-1-hch@lst.de Signed-off-by: Jens Axboe --- arch/m68k/configs/stmark2_defconfig | 1 - block/Kconfig | 10 -- block/Makefile | 1 - block/cmdline-parser.c | 255 ---------------------------------- block/partitions/Kconfig | 1 - block/partitions/cmdline.c | 267 +++++++++++++++++++++++++++++++++++- include/linux/cmdline-parser.h | 46 ------- 7 files changed, 262 insertions(+), 319 deletions(-) delete mode 100644 block/cmdline-parser.c delete mode 100644 include/linux/cmdline-parser.h (limited to 'include/linux') diff --git a/arch/m68k/configs/stmark2_defconfig b/arch/m68k/configs/stmark2_defconfig index d92306472fce..8898ae321779 100644 --- a/arch/m68k/configs/stmark2_defconfig +++ b/arch/m68k/configs/stmark2_defconfig @@ -22,7 +22,6 @@ CONFIG_RAMSIZE=0x8000000 CONFIG_VECTORBASE=0x40000000 CONFIG_KERNELBASE=0x40001000 # CONFIG_BLK_DEV_BSG is not set -CONFIG_BLK_CMDLINE_PARSER=y CONFIG_BINFMT_FLAT=y CONFIG_BINFMT_ZFLAT=y CONFIG_BINFMT_MISC=y diff --git a/block/Kconfig b/block/Kconfig index fd732aede922..15dfb7660645 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -114,16 +114,6 @@ config BLK_DEV_THROTTLING_LOW Note, this is an experimental interface and could be changed someday. -config BLK_CMDLINE_PARSER - bool "Block device command line partition parser" - help - Enabling this option allows you to specify the partition layout from - the kernel boot args. This is typically of use for embedded devices - which don't otherwise have any standardized method for listing the - partitions on a block device. - - See Documentation/block/cmdline-partition.rst for more information. - config BLK_WBT bool "Enable support for block device writeback throttling" help diff --git a/block/Makefile b/block/Makefile index bfbe4e13ca1e..c72592b4cf31 100644 --- a/block/Makefile +++ b/block/Makefile @@ -28,7 +28,6 @@ obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o -obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o obj-$(CONFIG_BLK_DEV_INTEGRITY_T10) += t10-pi.o obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o diff --git a/block/cmdline-parser.c b/block/cmdline-parser.c deleted file mode 100644 index f2a14571882b..000000000000 --- a/block/cmdline-parser.c +++ /dev/null @@ -1,255 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Parse command line, get partition information - * - * Written by Cai Zhiyong - * - */ -#include -#include - -static int parse_subpart(struct cmdline_subpart **subpart, char *partdef) -{ - int ret = 0; - struct cmdline_subpart *new_subpart; - - *subpart = NULL; - - new_subpart = kzalloc(sizeof(struct cmdline_subpart), GFP_KERNEL); - if (!new_subpart) - return -ENOMEM; - - if (*partdef == '-') { - new_subpart->size = (sector_t)(~0ULL); - partdef++; - } else { - new_subpart->size = (sector_t)memparse(partdef, &partdef); - if (new_subpart->size < (sector_t)PAGE_SIZE) { - pr_warn("cmdline partition size is invalid."); - ret = -EINVAL; - goto fail; - } - } - - if (*partdef == '@') { - partdef++; - new_subpart->from = (sector_t)memparse(partdef, &partdef); - } else { - new_subpart->from = (sector_t)(~0ULL); - } - - if (*partdef == '(') { - int length; - char *next = strchr(++partdef, ')'); - - if (!next) { - pr_warn("cmdline partition format is invalid."); - ret = -EINVAL; - goto fail; - } - - length = min_t(int, next - partdef, - sizeof(new_subpart->name) - 1); - strncpy(new_subpart->name, partdef, length); - new_subpart->name[length] = '\0'; - - partdef = ++next; - } else - new_subpart->name[0] = '\0'; - - new_subpart->flags = 0; - - if (!strncmp(partdef, "ro", 2)) { - new_subpart->flags |= PF_RDONLY; - partdef += 2; - } - - if (!strncmp(partdef, "lk", 2)) { - new_subpart->flags |= PF_POWERUP_LOCK; - partdef += 2; - } - - *subpart = new_subpart; - return 0; -fail: - kfree(new_subpart); - return ret; -} - -static void free_subpart(struct cmdline_parts *parts) -{ - struct cmdline_subpart *subpart; - - while (parts->subpart) { - subpart = parts->subpart; - parts->subpart = subpart->next_subpart; - kfree(subpart); - } -} - -static int parse_parts(struct cmdline_parts **parts, const char *bdevdef) -{ - int ret = -EINVAL; - char *next; - int length; - struct cmdline_subpart **next_subpart; - struct cmdline_parts *newparts; - char buf[BDEVNAME_SIZE + 32 + 4]; - - *parts = NULL; - - newparts = kzalloc(sizeof(struct cmdline_parts), GFP_KERNEL); - if (!newparts) - return -ENOMEM; - - next = strchr(bdevdef, ':'); - if (!next) { - pr_warn("cmdline partition has no block device."); - goto fail; - } - - length = min_t(int, next - bdevdef, sizeof(newparts->name) - 1); - strncpy(newparts->name, bdevdef, length); - newparts->name[length] = '\0'; - newparts->nr_subparts = 0; - - next_subpart = &newparts->subpart; - - while (next && *(++next)) { - bdevdef = next; - next = strchr(bdevdef, ','); - - length = (!next) ? (sizeof(buf) - 1) : - min_t(int, next - bdevdef, sizeof(buf) - 1); - - strncpy(buf, bdevdef, length); - buf[length] = '\0'; - - ret = parse_subpart(next_subpart, buf); - if (ret) - goto fail; - - newparts->nr_subparts++; - next_subpart = &(*next_subpart)->next_subpart; - } - - if (!newparts->subpart) { - pr_warn("cmdline partition has no valid partition."); - ret = -EINVAL; - goto fail; - } - - *parts = newparts; - - return 0; -fail: - free_subpart(newparts); - kfree(newparts); - return ret; -} - -void cmdline_parts_free(struct cmdline_parts **parts) -{ - struct cmdline_parts *next_parts; - - while (*parts) { - next_parts = (*parts)->next_parts; - free_subpart(*parts); - kfree(*parts); - *parts = next_parts; - } -} -EXPORT_SYMBOL(cmdline_parts_free); - -int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline) -{ - int ret; - char *buf; - char *pbuf; - char *next; - struct cmdline_parts **next_parts; - - *parts = NULL; - - next = pbuf = buf = kstrdup(cmdline, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - next_parts = parts; - - while (next && *pbuf) { - next = strchr(pbuf, ';'); - if (next) - *next = '\0'; - - ret = parse_parts(next_parts, pbuf); - if (ret) - goto fail; - - if (next) - pbuf = ++next; - - next_parts = &(*next_parts)->next_parts; - } - - if (!*parts) { - pr_warn("cmdline partition has no valid partition."); - ret = -EINVAL; - goto fail; - } - - ret = 0; -done: - kfree(buf); - return ret; - -fail: - cmdline_parts_free(parts); - goto done; -} -EXPORT_SYMBOL(cmdline_parts_parse); - -struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts, - const char *bdev) -{ - while (parts && strncmp(bdev, parts->name, sizeof(parts->name))) - parts = parts->next_parts; - return parts; -} -EXPORT_SYMBOL(cmdline_parts_find); - -/* - * add_part() - * 0 success. - * 1 can not add so many partitions. - */ -int cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size, - int slot, - int (*add_part)(int, struct cmdline_subpart *, void *), - void *param) -{ - sector_t from = 0; - struct cmdline_subpart *subpart; - - for (subpart = parts->subpart; subpart; - subpart = subpart->next_subpart, slot++) { - if (subpart->from == (sector_t)(~0ULL)) - subpart->from = from; - else - from = subpart->from; - - if (from >= disk_size) - break; - - if (subpart->size > (disk_size - from)) - subpart->size = disk_size - from; - - from += subpart->size; - - if (add_part(slot, subpart, param)) - break; - } - - return slot; -} -EXPORT_SYMBOL(cmdline_parts_set); diff --git a/block/partitions/Kconfig b/block/partitions/Kconfig index 6e2a649669e5..278593b8e4e9 100644 --- a/block/partitions/Kconfig +++ b/block/partitions/Kconfig @@ -264,7 +264,6 @@ config SYSV68_PARTITION config CMDLINE_PARTITION bool "Command line partition support" if PARTITION_ADVANCED - select BLK_CMDLINE_PARSER help Say Y here if you want to read the partition table from bootargs. The format for the command line is just like mtdparts. diff --git a/block/partitions/cmdline.c b/block/partitions/cmdline.c index 8f545c36cde4..482a29e95dbd 100644 --- a/block/partitions/cmdline.c +++ b/block/partitions/cmdline.c @@ -14,20 +14,248 @@ * For further information, see "Documentation/block/cmdline-partition.rst" * */ +#include +#include +#include +#include "check.h" -#include -#include "check.h" +/* partition flags */ +#define PF_RDONLY 0x01 /* Device is read only */ +#define PF_POWERUP_LOCK 0x02 /* Always locked after reset */ + +struct cmdline_subpart { + char name[BDEVNAME_SIZE]; /* partition name, such as 'rootfs' */ + sector_t from; + sector_t size; + int flags; + struct cmdline_subpart *next_subpart; +}; + +struct cmdline_parts { + char name[BDEVNAME_SIZE]; /* block device, such as 'mmcblk0' */ + unsigned int nr_subparts; + struct cmdline_subpart *subpart; + struct cmdline_parts *next_parts; +}; + +static int parse_subpart(struct cmdline_subpart **subpart, char *partdef) +{ + int ret = 0; + struct cmdline_subpart *new_subpart; + + *subpart = NULL; + + new_subpart = kzalloc(sizeof(struct cmdline_subpart), GFP_KERNEL); + if (!new_subpart) + return -ENOMEM; + + if (*partdef == '-') { + new_subpart->size = (sector_t)(~0ULL); + partdef++; + } else { + new_subpart->size = (sector_t)memparse(partdef, &partdef); + if (new_subpart->size < (sector_t)PAGE_SIZE) { + pr_warn("cmdline partition size is invalid."); + ret = -EINVAL; + goto fail; + } + } + + if (*partdef == '@') { + partdef++; + new_subpart->from = (sector_t)memparse(partdef, &partdef); + } else { + new_subpart->from = (sector_t)(~0ULL); + } + + if (*partdef == '(') { + int length; + char *next = strchr(++partdef, ')'); + + if (!next) { + pr_warn("cmdline partition format is invalid."); + ret = -EINVAL; + goto fail; + } + + length = min_t(int, next - partdef, + sizeof(new_subpart->name) - 1); + strncpy(new_subpart->name, partdef, length); + new_subpart->name[length] = '\0'; + + partdef = ++next; + } else + new_subpart->name[0] = '\0'; + + new_subpart->flags = 0; + + if (!strncmp(partdef, "ro", 2)) { + new_subpart->flags |= PF_RDONLY; + partdef += 2; + } + + if (!strncmp(partdef, "lk", 2)) { + new_subpart->flags |= PF_POWERUP_LOCK; + partdef += 2; + } + + *subpart = new_subpart; + return 0; +fail: + kfree(new_subpart); + return ret; +} + +static void free_subpart(struct cmdline_parts *parts) +{ + struct cmdline_subpart *subpart; + + while (parts->subpart) { + subpart = parts->subpart; + parts->subpart = subpart->next_subpart; + kfree(subpart); + } +} + +static int parse_parts(struct cmdline_parts **parts, const char *bdevdef) +{ + int ret = -EINVAL; + char *next; + int length; + struct cmdline_subpart **next_subpart; + struct cmdline_parts *newparts; + char buf[BDEVNAME_SIZE + 32 + 4]; + + *parts = NULL; + + newparts = kzalloc(sizeof(struct cmdline_parts), GFP_KERNEL); + if (!newparts) + return -ENOMEM; + + next = strchr(bdevdef, ':'); + if (!next) { + pr_warn("cmdline partition has no block device."); + goto fail; + } + + length = min_t(int, next - bdevdef, sizeof(newparts->name) - 1); + strncpy(newparts->name, bdevdef, length); + newparts->name[length] = '\0'; + newparts->nr_subparts = 0; + + next_subpart = &newparts->subpart; + + while (next && *(++next)) { + bdevdef = next; + next = strchr(bdevdef, ','); + + length = (!next) ? (sizeof(buf) - 1) : + min_t(int, next - bdevdef, sizeof(buf) - 1); + + strncpy(buf, bdevdef, length); + buf[length] = '\0'; + + ret = parse_subpart(next_subpart, buf); + if (ret) + goto fail; + + newparts->nr_subparts++; + next_subpart = &(*next_subpart)->next_subpart; + } + + if (!newparts->subpart) { + pr_warn("cmdline partition has no valid partition."); + ret = -EINVAL; + goto fail; + } + + *parts = newparts; + + return 0; +fail: + free_subpart(newparts); + kfree(newparts); + return ret; +} + +static void cmdline_parts_free(struct cmdline_parts **parts) +{ + struct cmdline_parts *next_parts; + + while (*parts) { + next_parts = (*parts)->next_parts; + free_subpart(*parts); + kfree(*parts); + *parts = next_parts; + } +} + +static int cmdline_parts_parse(struct cmdline_parts **parts, + const char *cmdline) +{ + int ret; + char *buf; + char *pbuf; + char *next; + struct cmdline_parts **next_parts; + + *parts = NULL; + + next = pbuf = buf = kstrdup(cmdline, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + next_parts = parts; + + while (next && *pbuf) { + next = strchr(pbuf, ';'); + if (next) + *next = '\0'; + + ret = parse_parts(next_parts, pbuf); + if (ret) + goto fail; + + if (next) + pbuf = ++next; + + next_parts = &(*next_parts)->next_parts; + } + + if (!*parts) { + pr_warn("cmdline partition has no valid partition."); + ret = -EINVAL; + goto fail; + } + + ret = 0; +done: + kfree(buf); + return ret; + +fail: + cmdline_parts_free(parts); + goto done; +} + +static struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts, + const char *bdev) +{ + while (parts && strncmp(bdev, parts->name, sizeof(parts->name))) + parts = parts->next_parts; + return parts; +} static char *cmdline; static struct cmdline_parts *bdev_parts; -static int add_part(int slot, struct cmdline_subpart *subpart, void *param) +static int add_part(int slot, struct cmdline_subpart *subpart, + struct parsed_partitions *state) { int label_min; struct partition_meta_info *info; char tmp[sizeof(info->volname) + 4]; - struct parsed_partitions *state = (struct parsed_partitions *)param; if (slot >= state->limit) return 1; @@ -50,6 +278,35 @@ static int add_part(int slot, struct cmdline_subpart *subpart, void *param) return 0; } +static int cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size, + struct parsed_partitions *state) +{ + sector_t from = 0; + struct cmdline_subpart *subpart; + int slot = 1; + + for (subpart = parts->subpart; subpart; + subpart = subpart->next_subpart, slot++) { + if (subpart->from == (sector_t)(~0ULL)) + subpart->from = from; + else + from = subpart->from; + + if (from >= disk_size) + break; + + if (subpart->size > (disk_size - from)) + subpart->size = disk_size - from; + + from += subpart->size; + + if (add_part(slot, subpart, state)) + break; + } + + return slot; +} + static int __init cmdline_parts_setup(char *s) { cmdline = s; @@ -147,7 +404,7 @@ int cmdline_partition(struct parsed_partitions *state) disk_size = get_capacity(state->bdev->bd_disk) << 9; - cmdline_parts_set(parts, disk_size, 1, add_part, (void *)state); + cmdline_parts_set(parts, disk_size, state); cmdline_parts_verifier(1, state); strlcat(state->pp_buf, "\n", PAGE_SIZE); diff --git a/include/linux/cmdline-parser.h b/include/linux/cmdline-parser.h deleted file mode 100644 index 68a541807bdf..000000000000 --- a/include/linux/cmdline-parser.h +++ /dev/null @@ -1,46 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Parsing command line, get the partitions information. - * - * Written by Cai Zhiyong - * - */ -#ifndef CMDLINEPARSEH -#define CMDLINEPARSEH - -#include -#include -#include - -/* partition flags */ -#define PF_RDONLY 0x01 /* Device is read only */ -#define PF_POWERUP_LOCK 0x02 /* Always locked after reset */ - -struct cmdline_subpart { - char name[BDEVNAME_SIZE]; /* partition name, such as 'rootfs' */ - sector_t from; - sector_t size; - int flags; - struct cmdline_subpart *next_subpart; -}; - -struct cmdline_parts { - char name[BDEVNAME_SIZE]; /* block device, such as 'mmcblk0' */ - unsigned int nr_subparts; - struct cmdline_subpart *subpart; - struct cmdline_parts *next_parts; -}; - -void cmdline_parts_free(struct cmdline_parts **parts); - -int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline); - -struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts, - const char *bdev); - -int cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size, - int slot, - int (*add_part)(int, struct cmdline_subpart *, void *), - void *param); - -#endif /* CMDLINEPARSEH */ -- cgit v1.2.3 From cf179948554a2e0d2b622317bf6bf33138ac36e5 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Tue, 13 Jul 2021 01:05:25 +0200 Subject: block: add disk sequence number Associating uevents with block devices in userspace is difficult and racy: the uevent netlink socket is lossy, and on slow and overloaded systems has a very high latency. Block devices do not have exclusive owners in userspace, any process can set one up (e.g. loop devices). Moreover, device names can be reused (e.g. loop0 can be reused again and again). A userspace process setting up a block device and watching for its events cannot thus reliably tell whether an event relates to the device it just set up or another earlier instance with the same name. Being able to set a UUID on a loop device would solve the race conditions. But it does not allow to derive orderings from uevents: if you see a uevent with a UUID that does not match the device you are waiting for, you cannot tell whether it's because the right uevent has not arrived yet, or it was already sent and you missed it. So you cannot tell whether you should wait for it or not. Associating a unique, monotonically increasing sequential number to the lifetime of each block device, which can be retrieved with an ioctl immediately upon setting it up, allows to solve the race conditions with uevents, and also allows userspace processes to know whether they should wait for the uevent they need or if it was dropped and thus they should move on. Additionally, increment the disk sequence number when the media change, i.e. on DISK_EVENT_MEDIA_CHANGE event. Reviewed-by: Christoph Hellwig Signed-off-by: Matteo Croce Tested-by: Luca Boccassi Link: https://lore.kernel.org/r/20210712230530.29323-2-mcroce@linux.microsoft.com Signed-off-by: Jens Axboe --- block/disk-events.c | 3 +++ block/genhd.c | 24 ++++++++++++++++++++++++ include/linux/genhd.h | 2 ++ 3 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/block/disk-events.c b/block/disk-events.c index a75931ff5da4..04c52f3992ed 100644 --- a/block/disk-events.c +++ b/block/disk-events.c @@ -190,6 +190,9 @@ static void disk_check_events(struct disk_events *ev, spin_unlock_irq(&ev->lock); + if (events & DISK_EVENT_MEDIA_CHANGE) + inc_diskseq(disk); + /* * Tell userland about new events. Only the events listed in * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT diff --git a/block/genhd.c b/block/genhd.c index 38f053074159..ceb08af72c1a 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -29,6 +29,23 @@ static struct kobject *block_depr; +/* + * Unique, monotonically increasing sequential number associated with block + * devices instances (i.e. incremented each time a device is attached). + * Associating uevents with block devices in userspace is difficult and racy: + * the uevent netlink socket is lossy, and on slow and overloaded systems has + * a very high latency. + * Block devices do not have exclusive owners in userspace, any process can set + * one up (e.g. loop devices). Moreover, device names can be reused (e.g. loop0 + * can be reused again and again). + * A userspace process setting up a block device and watching for its events + * cannot thus reliably tell whether an event relates to the device it just set + * up or another earlier instance with the same name. + * This sequential number allows userspace processes to solve this problem, and + * uniquely associate an uevent to the lifetime to a device. + */ +static atomic64_t diskseq; + /* for extended dynamic devt allocation, currently only one major is used */ #define NR_EXT_DEVT (1 << MINORBITS) static DEFINE_IDA(ext_devt_ida); @@ -1252,6 +1269,8 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) disk_to_dev(disk)->class = &block_class; disk_to_dev(disk)->type = &disk_type; device_initialize(disk_to_dev(disk)); + inc_diskseq(disk); + return disk; out_destroy_part_tbl: @@ -1352,3 +1371,8 @@ int bdev_read_only(struct block_device *bdev) return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); } EXPORT_SYMBOL(bdev_read_only); + +void inc_diskseq(struct gendisk *disk) +{ + disk->diskseq = atomic64_inc_return(&diskseq); +} diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 13b34177cc85..140c028845af 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -172,6 +172,7 @@ struct gendisk { int node_id; struct badblocks *bb; struct lockdep_map lockdep_map; + u64 diskseq; }; /* @@ -332,6 +333,7 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, #endif /* CONFIG_SYSFS */ dev_t part_devt(struct gendisk *disk, u8 partno); +void inc_diskseq(struct gendisk *disk); dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); #ifdef CONFIG_BLOCK -- cgit v1.2.3 From e6138dc12de9df17cbda9c40314d69592855ac5e Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Tue, 13 Jul 2021 01:05:29 +0200 Subject: block: add a helper to raise a media changed event Refactor disk_check_events() and move some code into disk_event_uevent(). Then add disk_force_media_change(), a helper which will be used by devices to force issuing a DISK_EVENT_MEDIA_CHANGE event. Co-developed-by: Christoph Hellwig Signed-off-by: Christoph Hellwig Signed-off-by: Matteo Croce Tested-by: Luca Boccassi Link: https://lore.kernel.org/r/20210712230530.29323-6-mcroce@linux.microsoft.com Signed-off-by: Jens Axboe --- block/disk-events.c | 61 ++++++++++++++++++++++++++++++++++++++------------- include/linux/genhd.h | 1 + 2 files changed, 47 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/block/disk-events.c b/block/disk-events.c index 04c52f3992ed..7445b8ff2775 100644 --- a/block/disk-events.c +++ b/block/disk-events.c @@ -163,15 +163,31 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask) spin_unlock_irq(&ev->lock); } +/* + * Tell userland about new events. Only the events listed in @disk->events are + * reported, and only if DISK_EVENT_FLAG_UEVENT is set. Otherwise, events are + * processed internally but never get reported to userland. + */ +static void disk_event_uevent(struct gendisk *disk, unsigned int events) +{ + char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; + int nr_events = 0, i; + + for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) + if (events & disk->events & (1 << i)) + envp[nr_events++] = disk_uevents[i]; + + if (nr_events) + kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); +} + static void disk_check_events(struct disk_events *ev, unsigned int *clearing_ptr) { struct gendisk *disk = ev->disk; - char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; unsigned int clearing = *clearing_ptr; unsigned int events; unsigned long intv; - int nr_events = 0, i; /* check events */ events = disk->fops->check_events(disk, clearing); @@ -193,19 +209,8 @@ static void disk_check_events(struct disk_events *ev, if (events & DISK_EVENT_MEDIA_CHANGE) inc_diskseq(disk); - /* - * Tell userland about new events. Only the events listed in - * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT - * is set. Otherwise, events are processed internally but never - * get reported to userland. - */ - for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) - if ((events & disk->events & (1 << i)) && - (disk->event_flags & DISK_EVENT_FLAG_UEVENT)) - envp[nr_events++] = disk_uevents[i]; - - if (nr_events) - kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); + if (disk->event_flags & DISK_EVENT_FLAG_UEVENT) + disk_event_uevent(disk, events); } /** @@ -284,6 +289,32 @@ bool bdev_check_media_change(struct block_device *bdev) } EXPORT_SYMBOL(bdev_check_media_change); +/** + * disk_force_media_change - force a media change event + * @disk: the disk which will raise the event + * @events: the events to raise + * + * Generate uevents for the disk. If DISK_EVENT_MEDIA_CHANGE is present, + * attempt to free all dentries and inodes and invalidates all block + * device page cache entries in that case. + * + * Returns %true if DISK_EVENT_MEDIA_CHANGE was raised, or %false if not. + */ +bool disk_force_media_change(struct gendisk *disk, unsigned int events) +{ + disk_event_uevent(disk, events); + + if (!(events & DISK_EVENT_MEDIA_CHANGE)) + return false; + + if (__invalidate_device(disk->part0, true)) + pr_warn("VFS: busy inodes on changed media %s\n", + disk->disk_name); + set_bit(GD_NEED_PART_SCAN, &disk->state); + return true; +} +EXPORT_SYMBOL_GPL(disk_force_media_change); + /* * Separate this part out so that a different pointer for clearing_ptr can be * passed in for disk_clear_events. diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 140c028845af..849486de81c6 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -237,6 +237,7 @@ extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); bool set_capacity_and_notify(struct gendisk *disk, sector_t size); +bool disk_force_media_change(struct gendisk *disk, unsigned int events); /* drivers/char/random.c */ extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; -- cgit v1.2.3 From 371cf74e78f3468016e8c7a159fc288a71d4dc86 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Fri, 2 Jul 2021 10:38:32 +0300 Subject: net/mlx5: Move TTC logic to fs_ttc Now that TTC logic is not dependent on mlx5e structs, move it to lib/fs_ttc.c so it could be used other part of the mlx5 driver. Signed-off-by: Maor Gottlieb Reviewed-by: Tariq Toukan Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 - drivers/net/ethernet/mellanox/mlx5/core/en/fs.h | 78 +-- drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 558 -------------------- .../net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c | 584 +++++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h | 77 +++ include/linux/mlx5/fs.h | 2 + 7 files changed, 665 insertions(+), 638 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index e8522ccb3519..33e550d77fa6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -15,7 +15,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o port.o mr.o pd.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ - lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \ + lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \ fw_reset.o qos.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 594b7971caf9..4f6897c1ea8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -66,8 +66,6 @@ struct page_pool; #define MLX5E_METADATA_ETHER_TYPE (0x8CE4) #define MLX5E_METADATA_ETHER_LEN 8 -#define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) - #define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index c289f7004e10..8e7794c3d330 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -5,6 +5,7 @@ #define __MLX5E_FLOW_STEER_H__ #include "mod_hdr.h" +#include "lib/fs_ttc.h" enum { MLX5E_TC_FT_LEVEL = 0, @@ -67,21 +68,6 @@ struct mlx5e_l2_table { bool promisc_enabled; }; -enum mlx5_traffic_types { - MLX5_TT_IPV4_TCP, - MLX5_TT_IPV6_TCP, - MLX5_TT_IPV4_UDP, - MLX5_TT_IPV6_UDP, - MLX5_TT_IPV4_IPSEC_AH, - MLX5_TT_IPV6_IPSEC_AH, - MLX5_TT_IPV4_IPSEC_ESP, - MLX5_TT_IPV6_IPSEC_ESP, - MLX5_TT_IPV4, - MLX5_TT_IPV6, - MLX5_TT_ANY, - MLX5_NUM_TT, -}; - #define MLX5E_NUM_INDIR_TIRS (MLX5_NUM_TT - 1) #define MLX5_HASH_IP (MLX5_HASH_FIELD_SEL_SRC_IP |\ @@ -94,32 +80,6 @@ enum mlx5_traffic_types { MLX5_HASH_FIELD_SEL_DST_IP |\ MLX5_HASH_FIELD_SEL_IPSEC_SPI) -enum mlx5_tunnel_types { - MLX5_TT_IPV4_GRE, - MLX5_TT_IPV6_GRE, - MLX5_TT_IPV4_IPIP, - MLX5_TT_IPV6_IPIP, - MLX5_TT_IPV4_IPV6, - MLX5_TT_IPV6_IPV6, - MLX5_NUM_TUNNEL_TT, -}; - -bool mlx5_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev); - -struct mlx5_ttc_rule { - struct mlx5_flow_handle *rule; - struct mlx5_flow_destination default_dest; -}; - -/* L3/L4 traffic type classifier */ -struct mlx5_ttc_table { - int num_groups; - struct mlx5_flow_table *t; - struct mlx5_flow_group **g; - struct mlx5_ttc_rule rules[MLX5_NUM_TT]; - struct mlx5_flow_handle *tunnel_rules[MLX5_NUM_TUNNEL_TT]; -}; - /* NIC prio FTS */ enum { MLX5E_PROMISC_FT_LEVEL, @@ -141,22 +101,6 @@ enum { #endif }; -#define MLX5_TTC_NUM_GROUPS 3 -#define MLX5_TTC_GROUP1_SIZE (BIT(3) + MLX5_NUM_TUNNEL_TT) -#define MLX5_TTC_GROUP2_SIZE BIT(1) -#define MLX5_TTC_GROUP3_SIZE BIT(0) -#define MLX5_TTC_TABLE_SIZE (MLX5_TTC_GROUP1_SIZE +\ - MLX5_TTC_GROUP2_SIZE +\ - MLX5_TTC_GROUP3_SIZE) - -#define MLX5_INNER_TTC_NUM_GROUPS 3 -#define MLX5_INNER_TTC_GROUP1_SIZE BIT(3) -#define MLX5_INNER_TTC_GROUP2_SIZE BIT(1) -#define MLX5_INNER_TTC_GROUP3_SIZE BIT(0) -#define MLX5_INNER_TTC_TABLE_SIZE (MLX5_INNER_TTC_GROUP1_SIZE +\ - MLX5_INNER_TTC_GROUP2_SIZE +\ - MLX5_INNER_TTC_GROUP3_SIZE) - struct mlx5e_priv; #ifdef CONFIG_MLX5_EN_RXNFC @@ -238,29 +182,10 @@ struct mlx5e_flow_steering { struct mlx5e_ptp_fs *ptp_fs; }; -struct ttc_params { - struct mlx5_flow_namespace *ns; - struct mlx5_flow_table_attr ft_attr; - struct mlx5_flow_destination dests[MLX5_NUM_TT]; - bool inner_ttc; - struct mlx5_flow_destination tunnel_dests[MLX5_NUM_TUNNEL_TT]; -}; - void mlx5e_set_ttc_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params, bool tunnel); -int mlx5_create_ttc_table(struct mlx5_core_dev *dev, struct ttc_params *params, - struct mlx5_ttc_table *ttc); -void mlx5_destroy_ttc_table(struct mlx5_ttc_table *ttc); - void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft); -int mlx5_ttc_fwd_dest(struct mlx5_ttc_table *ttc, enum mlx5_traffic_types type, - struct mlx5_flow_destination *new_dest); -struct mlx5_flow_destination -mlx5_ttc_get_default_dest(struct mlx5_ttc_table *ttc, - enum mlx5_traffic_types type); -int mlx5_ttc_fwd_default_dest(struct mlx5_ttc_table *ttc, - enum mlx5_traffic_types type); void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); @@ -268,7 +193,6 @@ void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); int mlx5e_create_flow_steering(struct mlx5e_priv *priv); void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv); -u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt); int mlx5e_add_vlan_trap(struct mlx5e_priv *priv, int trap_id, int tir_num); void mlx5e_remove_vlan_trap(struct mlx5e_priv *priv); int mlx5e_add_mac_trap(struct mlx5e_priv *priv, int trap_id, int tir_num); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index a03842d132f6..cbad05760551 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -854,454 +854,6 @@ void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft) ft->t = NULL; } -static void mlx5_cleanup_ttc_rules(struct mlx5_ttc_table *ttc) -{ - int i; - - for (i = 0; i < MLX5_NUM_TT; i++) { - if (!IS_ERR_OR_NULL(ttc->rules[i].rule)) { - mlx5_del_flow_rules(ttc->rules[i].rule); - ttc->rules[i].rule = NULL; - } - } - - for (i = 0; i < MLX5_NUM_TUNNEL_TT; i++) { - if (!IS_ERR_OR_NULL(ttc->tunnel_rules[i])) { - mlx5_del_flow_rules(ttc->tunnel_rules[i]); - ttc->tunnel_rules[i] = NULL; - } - } -} - -struct mlx5_etype_proto { - u16 etype; - u8 proto; -}; - -static struct mlx5_etype_proto ttc_rules[] = { - [MLX5_TT_IPV4_TCP] = { - .etype = ETH_P_IP, - .proto = IPPROTO_TCP, - }, - [MLX5_TT_IPV6_TCP] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_TCP, - }, - [MLX5_TT_IPV4_UDP] = { - .etype = ETH_P_IP, - .proto = IPPROTO_UDP, - }, - [MLX5_TT_IPV6_UDP] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_UDP, - }, - [MLX5_TT_IPV4_IPSEC_AH] = { - .etype = ETH_P_IP, - .proto = IPPROTO_AH, - }, - [MLX5_TT_IPV6_IPSEC_AH] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_AH, - }, - [MLX5_TT_IPV4_IPSEC_ESP] = { - .etype = ETH_P_IP, - .proto = IPPROTO_ESP, - }, - [MLX5_TT_IPV6_IPSEC_ESP] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_ESP, - }, - [MLX5_TT_IPV4] = { - .etype = ETH_P_IP, - .proto = 0, - }, - [MLX5_TT_IPV6] = { - .etype = ETH_P_IPV6, - .proto = 0, - }, - [MLX5_TT_ANY] = { - .etype = 0, - .proto = 0, - }, -}; - -static struct mlx5_etype_proto ttc_tunnel_rules[] = { - [MLX5_TT_IPV4_GRE] = { - .etype = ETH_P_IP, - .proto = IPPROTO_GRE, - }, - [MLX5_TT_IPV6_GRE] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_GRE, - }, - [MLX5_TT_IPV4_IPIP] = { - .etype = ETH_P_IP, - .proto = IPPROTO_IPIP, - }, - [MLX5_TT_IPV6_IPIP] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_IPIP, - }, - [MLX5_TT_IPV4_IPV6] = { - .etype = ETH_P_IP, - .proto = IPPROTO_IPV6, - }, - [MLX5_TT_IPV6_IPV6] = { - .etype = ETH_P_IPV6, - .proto = IPPROTO_IPV6, - }, - -}; - -u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt) -{ - return ttc_tunnel_rules[tt].proto; -} - -static bool mlx5_tunnel_proto_supported_rx(struct mlx5_core_dev *mdev, - u8 proto_type) -{ - switch (proto_type) { - case IPPROTO_GRE: - return MLX5_CAP_ETH(mdev, tunnel_stateless_gre); - case IPPROTO_IPIP: - case IPPROTO_IPV6: - return (MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip) || - MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip_rx)); - default: - return false; - } -} - -static bool mlx5_tunnel_any_rx_proto_supported(struct mlx5_core_dev *mdev) -{ - int tt; - - for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) { - if (mlx5_tunnel_proto_supported_rx(mdev, - ttc_tunnel_rules[tt].proto)) - return true; - } - return false; -} - -bool mlx5_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) -{ - return (mlx5_tunnel_any_rx_proto_supported(mdev) && - MLX5_CAP_FLOWTABLE_NIC_RX(mdev, - ft_field_support.inner_ip_version)); -} - -static u8 mlx5_etype_to_ipv(u16 ethertype) -{ - if (ethertype == ETH_P_IP) - return 4; - - if (ethertype == ETH_P_IPV6) - return 6; - - return 0; -} - -static struct mlx5_flow_handle * -mlx5_generate_ttc_rule(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, - struct mlx5_flow_destination *dest, u16 etype, u8 proto) -{ - int match_ipv_outer = - MLX5_CAP_FLOWTABLE_NIC_RX(dev, - ft_field_support.outer_ip_version); - MLX5_DECLARE_FLOW_ACT(flow_act); - struct mlx5_flow_handle *rule; - struct mlx5_flow_spec *spec; - int err = 0; - u8 ipv; - - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) - return ERR_PTR(-ENOMEM); - - if (proto) { - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol); - MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, proto); - } - - ipv = mlx5_etype_to_ipv(etype); - if (match_ipv_outer && ipv) { - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version); - MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, ipv); - } else if (etype) { - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ethertype); - MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype); - } - - rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_err(dev, "%s: add rule failed\n", __func__); - } - - kvfree(spec); - return err ? ERR_PTR(err) : rule; -} - -static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev, - struct ttc_params *params, - struct mlx5_ttc_table *ttc) -{ - struct mlx5_flow_handle **trules; - struct mlx5_ttc_rule *rules; - struct mlx5_flow_table *ft; - int tt; - int err; - - ft = ttc->t; - rules = ttc->rules; - for (tt = 0; tt < MLX5_NUM_TT; tt++) { - struct mlx5_ttc_rule *rule = &rules[tt]; - - rule->rule = mlx5_generate_ttc_rule(dev, ft, ¶ms->dests[tt], - ttc_rules[tt].etype, - ttc_rules[tt].proto); - if (IS_ERR(rule->rule)) { - err = PTR_ERR(rule->rule); - rule->rule = NULL; - goto del_rules; - } - rule->default_dest = params->dests[tt]; - } - - if (!params->inner_ttc || !mlx5_tunnel_inner_ft_supported(dev)) - return 0; - - trules = ttc->tunnel_rules; - for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) { - if (!mlx5_tunnel_proto_supported_rx(dev, - ttc_tunnel_rules[tt].proto)) - continue; - trules[tt] = mlx5_generate_ttc_rule(dev, ft, - ¶ms->tunnel_dests[tt], - ttc_tunnel_rules[tt].etype, - ttc_tunnel_rules[tt].proto); - if (IS_ERR(trules[tt])) { - err = PTR_ERR(trules[tt]); - trules[tt] = NULL; - goto del_rules; - } - } - - return 0; - -del_rules: - mlx5_cleanup_ttc_rules(ttc); - return err; -} - -static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc, - bool use_ipv) -{ - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - int ix = 0; - u32 *in; - int err; - u8 *mc; - - ttc->g = kcalloc(MLX5_TTC_NUM_GROUPS, sizeof(*ttc->g), GFP_KERNEL); - if (!ttc->g) - return -ENOMEM; - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) { - kfree(ttc->g); - ttc->g = NULL; - return -ENOMEM; - } - - /* L4 Group */ - mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); - MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol); - if (use_ipv) - MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_version); - else - MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); - MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5_TTC_GROUP1_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); - if (IS_ERR(ttc->g[ttc->num_groups])) - goto err; - ttc->num_groups++; - - /* L3 Group */ - MLX5_SET(fte_match_param, mc, outer_headers.ip_protocol, 0); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5_TTC_GROUP2_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); - if (IS_ERR(ttc->g[ttc->num_groups])) - goto err; - ttc->num_groups++; - - /* Any Group */ - memset(in, 0, inlen); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5_TTC_GROUP3_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); - if (IS_ERR(ttc->g[ttc->num_groups])) - goto err; - ttc->num_groups++; - - kvfree(in); - return 0; - -err: - err = PTR_ERR(ttc->g[ttc->num_groups]); - ttc->g[ttc->num_groups] = NULL; - kvfree(in); - - return err; -} - -static struct mlx5_flow_handle * -mlx5_generate_inner_ttc_rule(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft, - struct mlx5_flow_destination *dest, - u16 etype, u8 proto) -{ - MLX5_DECLARE_FLOW_ACT(flow_act); - struct mlx5_flow_handle *rule; - struct mlx5_flow_spec *spec; - int err = 0; - u8 ipv; - - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) - return ERR_PTR(-ENOMEM); - - ipv = mlx5_etype_to_ipv(etype); - if (etype && ipv) { - spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_version); - MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_version, ipv); - } - - if (proto) { - spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_protocol); - MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_protocol, proto); - } - - rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_err(dev, "%s: add inner TTC rule failed\n", __func__); - } - - kvfree(spec); - return err ? ERR_PTR(err) : rule; -} - -static int mlx5_generate_inner_ttc_table_rules(struct mlx5_core_dev *dev, - struct ttc_params *params, - struct mlx5_ttc_table *ttc) -{ - struct mlx5_ttc_rule *rules; - struct mlx5_flow_table *ft; - int err; - int tt; - - ft = ttc->t; - rules = ttc->rules; - - for (tt = 0; tt < MLX5_NUM_TT; tt++) { - struct mlx5_ttc_rule *rule = &rules[tt]; - - rule->rule = mlx5_generate_inner_ttc_rule(dev, ft, - ¶ms->dests[tt], - ttc_rules[tt].etype, - ttc_rules[tt].proto); - if (IS_ERR(rule->rule)) { - err = PTR_ERR(rule->rule); - rule->rule = NULL; - goto del_rules; - } - rule->default_dest = params->dests[tt]; - } - - return 0; - -del_rules: - - mlx5_cleanup_ttc_rules(ttc); - return err; -} - -static int mlx5_create_inner_ttc_table_groups(struct mlx5_ttc_table *ttc) -{ - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - int ix = 0; - u32 *in; - int err; - u8 *mc; - - ttc->g = kcalloc(MLX5_INNER_TTC_NUM_GROUPS, sizeof(*ttc->g), - GFP_KERNEL); - if (!ttc->g) - return -ENOMEM; - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) { - kfree(ttc->g); - ttc->g = NULL; - return -ENOMEM; - } - - /* L4 Group */ - mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); - MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_protocol); - MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_version); - MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_INNER_HEADERS); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5_INNER_TTC_GROUP1_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); - if (IS_ERR(ttc->g[ttc->num_groups])) - goto err; - ttc->num_groups++; - - /* L3 Group */ - MLX5_SET(fte_match_param, mc, inner_headers.ip_protocol, 0); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5_INNER_TTC_GROUP2_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); - if (IS_ERR(ttc->g[ttc->num_groups])) - goto err; - ttc->num_groups++; - - /* Any Group */ - memset(in, 0, inlen); - MLX5_SET_CFG(in, start_flow_index, ix); - ix += MLX5_INNER_TTC_GROUP3_SIZE; - MLX5_SET_CFG(in, end_flow_index, ix - 1); - ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); - if (IS_ERR(ttc->g[ttc->num_groups])) - goto err; - ttc->num_groups++; - - kvfree(in); - return 0; - -err: - err = PTR_ERR(ttc->g[ttc->num_groups]); - ttc->g[ttc->num_groups] = NULL; - kvfree(in); - - return err; -} - static void mlx5e_set_inner_ttc_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params) { @@ -1356,116 +908,6 @@ void mlx5e_set_ttc_params(struct mlx5e_priv *priv, } } -static int mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev, - struct ttc_params *params, - struct mlx5_ttc_table *ttc) -{ - int err; - - WARN_ON_ONCE(params->ft_attr.max_fte); - params->ft_attr.max_fte = MLX5_INNER_TTC_TABLE_SIZE; - ttc->t = mlx5_create_flow_table(params->ns, ¶ms->ft_attr); - if (IS_ERR(ttc->t)) { - err = PTR_ERR(ttc->t); - ttc->t = NULL; - return err; - } - - err = mlx5_create_inner_ttc_table_groups(ttc); - if (err) - goto destroy_ttc; - - err = mlx5_generate_inner_ttc_table_rules(dev, params, ttc); - if (err) - goto destroy_ttc; - - return 0; - -destroy_ttc: - mlx5_destroy_ttc_table(ttc); - return err; -} - -void mlx5_destroy_ttc_table(struct mlx5_ttc_table *ttc) -{ - int i; - - mlx5_cleanup_ttc_rules(ttc); - for (i = ttc->num_groups - 1; i >= 0; i--) { - if (!IS_ERR_OR_NULL(ttc->g[i])) - mlx5_destroy_flow_group(ttc->g[i]); - ttc->g[i] = NULL; - } - - ttc->num_groups = 0; - kfree(ttc->g); - mlx5_destroy_flow_table(ttc->t); - ttc->t = NULL; -} - -static void mlx5_destroy_inner_ttc_table(struct mlx5_ttc_table *ttc) -{ - mlx5_destroy_ttc_table(ttc); -} - -int mlx5_create_ttc_table(struct mlx5_core_dev *dev, struct ttc_params *params, - struct mlx5_ttc_table *ttc) -{ - bool match_ipv_outer = - MLX5_CAP_FLOWTABLE_NIC_RX(dev, - ft_field_support.outer_ip_version); - int err; - - WARN_ON_ONCE(params->ft_attr.max_fte); - params->ft_attr.max_fte = MLX5_TTC_TABLE_SIZE; - ttc->t = mlx5_create_flow_table(params->ns, ¶ms->ft_attr); - if (IS_ERR(ttc->t)) { - err = PTR_ERR(ttc->t); - ttc->t = NULL; - return err; - } - - err = mlx5_create_ttc_table_groups(ttc, match_ipv_outer); - if (err) - goto destroy_ttc; - - err = mlx5_generate_ttc_table_rules(dev, params, ttc); - if (err) - goto destroy_ttc; - - return 0; -destroy_ttc: - mlx5_destroy_ttc_table(ttc); - return err; -} - -int mlx5_ttc_fwd_dest(struct mlx5_ttc_table *ttc, enum mlx5_traffic_types type, - struct mlx5_flow_destination *new_dest) -{ - return mlx5_modify_rule_destination(ttc->rules[type].rule, new_dest, - NULL); -} - -struct mlx5_flow_destination -mlx5_ttc_get_default_dest(struct mlx5_ttc_table *ttc, - enum mlx5_traffic_types type) -{ - struct mlx5_flow_destination *dest = &ttc->rules[type].default_dest; - - WARN_ONCE(dest->type != MLX5_FLOW_DESTINATION_TYPE_TIR, - "TTC[%d] default dest is not setup yet", type); - - return *dest; -} - -int mlx5_ttc_fwd_default_dest(struct mlx5_ttc_table *ttc, - enum mlx5_traffic_types type) -{ - struct mlx5_flow_destination dest = mlx5_ttc_get_default_dest(ttc, type); - - return mlx5_ttc_fwd_dest(ttc, type, &dest); -} - static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv, struct mlx5e_l2_rule *ai) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c new file mode 100644 index 000000000000..4b54b4127d33 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c @@ -0,0 +1,584 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021 NVIDIA CORPORATION & AFFILIATES. + +#include +#include +#include +#include +#include +#include "mlx5_core.h" +#include "lib/fs_ttc.h" + +#define MLX5_TTC_NUM_GROUPS 3 +#define MLX5_TTC_GROUP1_SIZE (BIT(3) + MLX5_NUM_TUNNEL_TT) +#define MLX5_TTC_GROUP2_SIZE BIT(1) +#define MLX5_TTC_GROUP3_SIZE BIT(0) +#define MLX5_TTC_TABLE_SIZE (MLX5_TTC_GROUP1_SIZE +\ + MLX5_TTC_GROUP2_SIZE +\ + MLX5_TTC_GROUP3_SIZE) + +#define MLX5_INNER_TTC_NUM_GROUPS 3 +#define MLX5_INNER_TTC_GROUP1_SIZE BIT(3) +#define MLX5_INNER_TTC_GROUP2_SIZE BIT(1) +#define MLX5_INNER_TTC_GROUP3_SIZE BIT(0) +#define MLX5_INNER_TTC_TABLE_SIZE (MLX5_INNER_TTC_GROUP1_SIZE +\ + MLX5_INNER_TTC_GROUP2_SIZE +\ + MLX5_INNER_TTC_GROUP3_SIZE) + +static void mlx5_cleanup_ttc_rules(struct mlx5_ttc_table *ttc) +{ + int i; + + for (i = 0; i < MLX5_NUM_TT; i++) { + if (!IS_ERR_OR_NULL(ttc->rules[i].rule)) { + mlx5_del_flow_rules(ttc->rules[i].rule); + ttc->rules[i].rule = NULL; + } + } + + for (i = 0; i < MLX5_NUM_TUNNEL_TT; i++) { + if (!IS_ERR_OR_NULL(ttc->tunnel_rules[i])) { + mlx5_del_flow_rules(ttc->tunnel_rules[i]); + ttc->tunnel_rules[i] = NULL; + } + } +} + +struct mlx5_etype_proto { + u16 etype; + u8 proto; +}; + +static struct mlx5_etype_proto ttc_rules[] = { + [MLX5_TT_IPV4_TCP] = { + .etype = ETH_P_IP, + .proto = IPPROTO_TCP, + }, + [MLX5_TT_IPV6_TCP] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_TCP, + }, + [MLX5_TT_IPV4_UDP] = { + .etype = ETH_P_IP, + .proto = IPPROTO_UDP, + }, + [MLX5_TT_IPV6_UDP] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_UDP, + }, + [MLX5_TT_IPV4_IPSEC_AH] = { + .etype = ETH_P_IP, + .proto = IPPROTO_AH, + }, + [MLX5_TT_IPV6_IPSEC_AH] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_AH, + }, + [MLX5_TT_IPV4_IPSEC_ESP] = { + .etype = ETH_P_IP, + .proto = IPPROTO_ESP, + }, + [MLX5_TT_IPV6_IPSEC_ESP] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_ESP, + }, + [MLX5_TT_IPV4] = { + .etype = ETH_P_IP, + .proto = 0, + }, + [MLX5_TT_IPV6] = { + .etype = ETH_P_IPV6, + .proto = 0, + }, + [MLX5_TT_ANY] = { + .etype = 0, + .proto = 0, + }, +}; + +static struct mlx5_etype_proto ttc_tunnel_rules[] = { + [MLX5_TT_IPV4_GRE] = { + .etype = ETH_P_IP, + .proto = IPPROTO_GRE, + }, + [MLX5_TT_IPV6_GRE] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_GRE, + }, + [MLX5_TT_IPV4_IPIP] = { + .etype = ETH_P_IP, + .proto = IPPROTO_IPIP, + }, + [MLX5_TT_IPV6_IPIP] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_IPIP, + }, + [MLX5_TT_IPV4_IPV6] = { + .etype = ETH_P_IP, + .proto = IPPROTO_IPV6, + }, + [MLX5_TT_IPV6_IPV6] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_IPV6, + }, + +}; + +u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt) +{ + return ttc_tunnel_rules[tt].proto; +} + +static bool mlx5_tunnel_proto_supported_rx(struct mlx5_core_dev *mdev, + u8 proto_type) +{ + switch (proto_type) { + case IPPROTO_GRE: + return MLX5_CAP_ETH(mdev, tunnel_stateless_gre); + case IPPROTO_IPIP: + case IPPROTO_IPV6: + return (MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip) || + MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip_rx)); + default: + return false; + } +} + +static bool mlx5_tunnel_any_rx_proto_supported(struct mlx5_core_dev *mdev) +{ + int tt; + + for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) { + if (mlx5_tunnel_proto_supported_rx(mdev, + ttc_tunnel_rules[tt].proto)) + return true; + } + return false; +} + +bool mlx5_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) +{ + return (mlx5_tunnel_any_rx_proto_supported(mdev) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, + ft_field_support.inner_ip_version)); +} + +static u8 mlx5_etype_to_ipv(u16 ethertype) +{ + if (ethertype == ETH_P_IP) + return 4; + + if (ethertype == ETH_P_IPV6) + return 6; + + return 0; +} + +static struct mlx5_flow_handle * +mlx5_generate_ttc_rule(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, + struct mlx5_flow_destination *dest, u16 etype, u8 proto) +{ + int match_ipv_outer = + MLX5_CAP_FLOWTABLE_NIC_RX(dev, + ft_field_support.outer_ip_version); + MLX5_DECLARE_FLOW_ACT(flow_act); + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + int err = 0; + u8 ipv; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return ERR_PTR(-ENOMEM); + + if (proto) { + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, proto); + } + + ipv = mlx5_etype_to_ipv(etype); + if (match_ipv_outer && ipv) { + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, ipv); + } else if (etype) { + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ethertype); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype); + } + + rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(dev, "%s: add rule failed\n", __func__); + } + + kvfree(spec); + return err ? ERR_PTR(err) : rule; +} + +static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev, + struct ttc_params *params, + struct mlx5_ttc_table *ttc) +{ + struct mlx5_flow_handle **trules; + struct mlx5_ttc_rule *rules; + struct mlx5_flow_table *ft; + int tt; + int err; + + ft = ttc->t; + rules = ttc->rules; + for (tt = 0; tt < MLX5_NUM_TT; tt++) { + struct mlx5_ttc_rule *rule = &rules[tt]; + + rule->rule = mlx5_generate_ttc_rule(dev, ft, ¶ms->dests[tt], + ttc_rules[tt].etype, + ttc_rules[tt].proto); + if (IS_ERR(rule->rule)) { + err = PTR_ERR(rule->rule); + rule->rule = NULL; + goto del_rules; + } + rule->default_dest = params->dests[tt]; + } + + if (!params->inner_ttc || !mlx5_tunnel_inner_ft_supported(dev)) + return 0; + + trules = ttc->tunnel_rules; + for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) { + if (!mlx5_tunnel_proto_supported_rx(dev, + ttc_tunnel_rules[tt].proto)) + continue; + trules[tt] = mlx5_generate_ttc_rule(dev, ft, + ¶ms->tunnel_dests[tt], + ttc_tunnel_rules[tt].etype, + ttc_tunnel_rules[tt].proto); + if (IS_ERR(trules[tt])) { + err = PTR_ERR(trules[tt]); + trules[tt] = NULL; + goto del_rules; + } + } + + return 0; + +del_rules: + mlx5_cleanup_ttc_rules(ttc); + return err; +} + +static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc, + bool use_ipv) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + int ix = 0; + u32 *in; + int err; + u8 *mc; + + ttc->g = kcalloc(MLX5_TTC_NUM_GROUPS, sizeof(*ttc->g), GFP_KERNEL); + if (!ttc->g) + return -ENOMEM; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + kfree(ttc->g); + ttc->g = NULL; + return -ENOMEM; + } + + /* L4 Group */ + mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol); + if (use_ipv) + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_version); + else + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_TTC_GROUP1_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + /* L3 Group */ + MLX5_SET(fte_match_param, mc, outer_headers.ip_protocol, 0); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_TTC_GROUP2_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + /* Any Group */ + memset(in, 0, inlen); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_TTC_GROUP3_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + kvfree(in); + return 0; + +err: + err = PTR_ERR(ttc->g[ttc->num_groups]); + ttc->g[ttc->num_groups] = NULL; + kvfree(in); + + return err; +} + +static struct mlx5_flow_handle * +mlx5_generate_inner_ttc_rule(struct mlx5_core_dev *dev, + struct mlx5_flow_table *ft, + struct mlx5_flow_destination *dest, + u16 etype, u8 proto) +{ + MLX5_DECLARE_FLOW_ACT(flow_act); + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + int err = 0; + u8 ipv; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return ERR_PTR(-ENOMEM); + + ipv = mlx5_etype_to_ipv(etype); + if (etype && ipv) { + spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_version); + MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_version, ipv); + } + + if (proto) { + spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_protocol); + MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_protocol, proto); + } + + rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(dev, "%s: add inner TTC rule failed\n", __func__); + } + + kvfree(spec); + return err ? ERR_PTR(err) : rule; +} + +static int mlx5_generate_inner_ttc_table_rules(struct mlx5_core_dev *dev, + struct ttc_params *params, + struct mlx5_ttc_table *ttc) +{ + struct mlx5_ttc_rule *rules; + struct mlx5_flow_table *ft; + int err; + int tt; + + ft = ttc->t; + rules = ttc->rules; + + for (tt = 0; tt < MLX5_NUM_TT; tt++) { + struct mlx5_ttc_rule *rule = &rules[tt]; + + rule->rule = mlx5_generate_inner_ttc_rule(dev, ft, + ¶ms->dests[tt], + ttc_rules[tt].etype, + ttc_rules[tt].proto); + if (IS_ERR(rule->rule)) { + err = PTR_ERR(rule->rule); + rule->rule = NULL; + goto del_rules; + } + rule->default_dest = params->dests[tt]; + } + + return 0; + +del_rules: + + mlx5_cleanup_ttc_rules(ttc); + return err; +} + +static int mlx5_create_inner_ttc_table_groups(struct mlx5_ttc_table *ttc) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + int ix = 0; + u32 *in; + int err; + u8 *mc; + + ttc->g = kcalloc(MLX5_INNER_TTC_NUM_GROUPS, sizeof(*ttc->g), + GFP_KERNEL); + if (!ttc->g) + return -ENOMEM; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + kfree(ttc->g); + ttc->g = NULL; + return -ENOMEM; + } + + /* L4 Group */ + mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_protocol); + MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_version); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_INNER_HEADERS); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_INNER_TTC_GROUP1_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + /* L3 Group */ + MLX5_SET(fte_match_param, mc, inner_headers.ip_protocol, 0); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_INNER_TTC_GROUP2_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + /* Any Group */ + memset(in, 0, inlen); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5_INNER_TTC_GROUP3_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in); + if (IS_ERR(ttc->g[ttc->num_groups])) + goto err; + ttc->num_groups++; + + kvfree(in); + return 0; + +err: + err = PTR_ERR(ttc->g[ttc->num_groups]); + ttc->g[ttc->num_groups] = NULL; + kvfree(in); + + return err; +} + +int mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev, + struct ttc_params *params, + struct mlx5_ttc_table *ttc) +{ + int err; + + WARN_ON_ONCE(params->ft_attr.max_fte); + params->ft_attr.max_fte = MLX5_INNER_TTC_TABLE_SIZE; + ttc->t = mlx5_create_flow_table(params->ns, ¶ms->ft_attr); + if (IS_ERR(ttc->t)) { + err = PTR_ERR(ttc->t); + ttc->t = NULL; + return err; + } + + err = mlx5_create_inner_ttc_table_groups(ttc); + if (err) + goto destroy_ft; + + err = mlx5_generate_inner_ttc_table_rules(dev, params, ttc); + if (err) + goto destroy_ft; + + return 0; + +destroy_ft: + mlx5_destroy_ttc_table(ttc); + return err; +} + +void mlx5_destroy_ttc_table(struct mlx5_ttc_table *ttc) +{ + int i; + + mlx5_cleanup_ttc_rules(ttc); + for (i = ttc->num_groups - 1; i >= 0; i--) { + if (!IS_ERR_OR_NULL(ttc->g[i])) + mlx5_destroy_flow_group(ttc->g[i]); + ttc->g[i] = NULL; + } + + ttc->num_groups = 0; + kfree(ttc->g); + mlx5_destroy_flow_table(ttc->t); + ttc->t = NULL; +} + +void mlx5_destroy_inner_ttc_table(struct mlx5_ttc_table *ttc) +{ + mlx5_destroy_ttc_table(ttc); +} + +int mlx5_create_ttc_table(struct mlx5_core_dev *dev, struct ttc_params *params, + struct mlx5_ttc_table *ttc) +{ + bool match_ipv_outer = + MLX5_CAP_FLOWTABLE_NIC_RX(dev, + ft_field_support.outer_ip_version); + int err; + + WARN_ON_ONCE(params->ft_attr.max_fte); + params->ft_attr.max_fte = MLX5_TTC_TABLE_SIZE; + ttc->t = mlx5_create_flow_table(params->ns, ¶ms->ft_attr); + if (IS_ERR(ttc->t)) { + err = PTR_ERR(ttc->t); + ttc->t = NULL; + return err; + } + + err = mlx5_create_ttc_table_groups(ttc, match_ipv_outer); + if (err) + goto destroy_ft; + + err = mlx5_generate_ttc_table_rules(dev, params, ttc); + if (err) + goto destroy_ft; + + return 0; +destroy_ft: + mlx5_destroy_ttc_table(ttc); + return err; +} + +int mlx5_ttc_fwd_dest(struct mlx5_ttc_table *ttc, enum mlx5_traffic_types type, + struct mlx5_flow_destination *new_dest) +{ + return mlx5_modify_rule_destination(ttc->rules[type].rule, new_dest, + NULL); +} + +struct mlx5_flow_destination +mlx5_ttc_get_default_dest(struct mlx5_ttc_table *ttc, + enum mlx5_traffic_types type) +{ + struct mlx5_flow_destination *dest = &ttc->rules[type].default_dest; + + WARN_ONCE(dest->type != MLX5_FLOW_DESTINATION_TYPE_TIR, + "TTC[%d] default dest is not setup yet", type); + + return *dest; +} + +int mlx5_ttc_fwd_default_dest(struct mlx5_ttc_table *ttc, + enum mlx5_traffic_types type) +{ + struct mlx5_flow_destination dest = mlx5_ttc_get_default_dest(ttc, type); + + return mlx5_ttc_fwd_dest(ttc, type, &dest); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h new file mode 100644 index 000000000000..1010e00c10bd --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies. */ + +#ifndef __ML5_FS_TTC_H__ +#define __ML5_FS_TTC_H__ + +#include + +enum mlx5_traffic_types { + MLX5_TT_IPV4_TCP, + MLX5_TT_IPV6_TCP, + MLX5_TT_IPV4_UDP, + MLX5_TT_IPV6_UDP, + MLX5_TT_IPV4_IPSEC_AH, + MLX5_TT_IPV6_IPSEC_AH, + MLX5_TT_IPV4_IPSEC_ESP, + MLX5_TT_IPV6_IPSEC_ESP, + MLX5_TT_IPV4, + MLX5_TT_IPV6, + MLX5_TT_ANY, + MLX5_NUM_TT, + MLX5_NUM_INDIR_TIRS = MLX5_TT_ANY, +}; + +enum mlx5_tunnel_types { + MLX5_TT_IPV4_GRE, + MLX5_TT_IPV6_GRE, + MLX5_TT_IPV4_IPIP, + MLX5_TT_IPV6_IPIP, + MLX5_TT_IPV4_IPV6, + MLX5_TT_IPV6_IPV6, + MLX5_NUM_TUNNEL_TT, +}; + +struct mlx5_ttc_rule { + struct mlx5_flow_handle *rule; + struct mlx5_flow_destination default_dest; +}; + +/* L3/L4 traffic type classifier */ +struct mlx5_ttc_table { + int num_groups; + struct mlx5_flow_table *t; + struct mlx5_flow_group **g; + struct mlx5_ttc_rule rules[MLX5_NUM_TT]; + struct mlx5_flow_handle *tunnel_rules[MLX5_NUM_TUNNEL_TT]; +}; + +struct ttc_params { + struct mlx5_flow_namespace *ns; + struct mlx5_flow_table_attr ft_attr; + struct mlx5_flow_destination dests[MLX5_NUM_TT]; + bool inner_ttc; + struct mlx5_flow_destination tunnel_dests[MLX5_NUM_TUNNEL_TT]; +}; + +int mlx5_create_ttc_table(struct mlx5_core_dev *dev, struct ttc_params *params, + struct mlx5_ttc_table *ttc); +void mlx5_destroy_ttc_table(struct mlx5_ttc_table *ttc); + +int mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev, + struct ttc_params *params, + struct mlx5_ttc_table *ttc); +void mlx5_destroy_inner_ttc_table(struct mlx5_ttc_table *ttc); + +int mlx5_ttc_fwd_dest(struct mlx5_ttc_table *ttc, enum mlx5_traffic_types type, + struct mlx5_flow_destination *new_dest); +struct mlx5_flow_destination +mlx5_ttc_get_default_dest(struct mlx5_ttc_table *ttc, + enum mlx5_traffic_types type); +int mlx5_ttc_fwd_default_dest(struct mlx5_ttc_table *ttc, + enum mlx5_traffic_types type); + +bool mlx5_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev); +u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt); + +#endif /* __MLX5_FS_TTC_H__ */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 77746f7e35b8..0106c67e8ccb 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -38,6 +38,8 @@ #define MLX5_FS_DEFAULT_FLOW_TAG 0x0 +#define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) + enum { MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16, MLX5_FLOW_CONTEXT_ACTION_ENCRYPT = 1 << 17, -- cgit v1.2.3 From 52ac8b358b0cb7e91c966225fca61be5d1c984bc Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 27 May 2021 08:09:15 -0400 Subject: KVM: Block memslot updates across range_start() and range_end() We would like to avoid taking mmu_lock for .invalidate_range_{start,end}() notifications that are unrelated to KVM. Because mmu_notifier_count must be modified while holding mmu_lock for write, and must always be paired across start->end to stay balanced, lock elision must happen in both or none. Therefore, in preparation for this change, this patch prevents memslot updates across range_start() and range_end(). Note, technically flag-only memslot updates could be allowed in parallel, but stalling a memslot update for a relatively short amount of time is not a scalability issue, and this is all more than complex enough. A long note on the locking: a previous version of the patch used an rwsem to block the memslot update while the MMU notifier run, but this resulted in the following deadlock involving the pseudo-lock tagged as "mmu_notifier_invalidate_range_start". ====================================================== WARNING: possible circular locking dependency detected 5.12.0-rc3+ #6 Tainted: G OE ------------------------------------------------------ qemu-system-x86/3069 is trying to acquire lock: ffffffff9c775ca0 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}, at: __mmu_notifier_invalidate_range_end+0x5/0x190 but task is already holding lock: ffffaff7410a9160 (&kvm->mmu_notifier_slots_lock){.+.+}-{3:3}, at: kvm_mmu_notifier_invalidate_range_start+0x36d/0x4f0 [kvm] which lock already depends on the new lock. This corresponds to the following MMU notifier logic: invalidate_range_start take pseudo lock down_read() (*) release pseudo lock invalidate_range_end take pseudo lock (**) up_read() release pseudo lock At point (*) we take the mmu_notifiers_slots_lock inside the pseudo lock; at point (**) we take the pseudo lock inside the mmu_notifiers_slots_lock. This could cause a deadlock (ignoring for a second that the pseudo lock is not a lock): - invalidate_range_start waits on down_read(), because the rwsem is held by install_new_memslots - install_new_memslots waits on down_write(), because the rwsem is held till (another) invalidate_range_end finishes - invalidate_range_end sits waits on the pseudo lock, held by invalidate_range_start. Removing the fairness of the rwsem breaks the cycle (in lockdep terms, it would change the *shared* rwsem readers into *shared recursive* readers), so open-code the wait using a readers count and a spinlock. This also allows handling blockable and non-blockable critical section in the same way. Losing the rwsem fairness does theoretically allow MMU notifiers to block install_new_memslots forever. Note that mm/mmu_notifier.c's own retry scheme in mmu_interval_read_begin also uses wait/wake_up and is likewise not fair. Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/locking.rst | 6 ++++ include/linux/kvm_host.h | 5 ++++ virt/kvm/kvm_main.c | 58 +++++++++++++++++++++++++++++++++++--- 3 files changed, 65 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 35eca377543d..8138201efb09 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -21,6 +21,12 @@ The acquisition orders for mutexes are as follows: can be taken inside a kvm->srcu read-side critical section, while kvm->slots_lock cannot. +- kvm->mn_active_invalidate_count ensures that pairs of + invalidate_range_start() and invalidate_range_end() callbacks + use the same memslots array. kvm->slots_lock and kvm->slots_arch_lock + are taken on the waiting side in install_new_memslots, so MMU notifiers + must not take either kvm->slots_lock or kvm->slots_arch_lock. + On x86: - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index de58a0890b1a..5b6a69caccb5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -548,6 +548,11 @@ struct kvm { struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + /* Used to wait for completion of MMU notifiers. */ + spinlock_t mn_invalidate_lock; + unsigned long mn_active_invalidate_count; + struct rcuwait mn_memslots_update_rcuwait; + /* * created_vcpus is protected by kvm->lock, and is incremented * at the beginning of KVM_CREATE_VCPU. online_vcpus is only diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5cc79373827f..8f9024d65866 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -604,11 +604,9 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, trace_kvm_set_spte_hva(address); /* - * .change_pte() must be surrounded by .invalidate_range_{start,end}(), - * and so always runs with an elevated notifier count. This obviates - * the need to bump the sequence count. + * .change_pte() must be surrounded by .invalidate_range_{start,end}(). */ - WARN_ON_ONCE(!kvm->mmu_notifier_count); + WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count)); kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn); } @@ -658,6 +656,18 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, trace_kvm_unmap_hva_range(range->start, range->end); + /* + * Prevent memslot modification between range_start() and range_end() + * so that conditionally locking provides the same result in both + * functions. Without that guarantee, the mmu_notifier_count + * adjustments will be imbalanced. + * + * Pairs with the decrement in range_end(). + */ + spin_lock(&kvm->mn_invalidate_lock); + kvm->mn_active_invalidate_count++; + spin_unlock(&kvm->mn_invalidate_lock); + __kvm_handle_hva_range(kvm, &hva_range); return 0; @@ -694,9 +704,22 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, .flush_on_ret = false, .may_block = mmu_notifier_range_blockable(range), }; + bool wake; __kvm_handle_hva_range(kvm, &hva_range); + /* Pairs with the increment in range_start(). */ + spin_lock(&kvm->mn_invalidate_lock); + wake = (--kvm->mn_active_invalidate_count == 0); + spin_unlock(&kvm->mn_invalidate_lock); + + /* + * There can only be one waiter, since the wait happens under + * slots_lock. + */ + if (wake) + rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait); + BUG_ON(kvm->mmu_notifier_count < 0); } @@ -977,6 +1000,9 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_init(&kvm->irq_lock); mutex_init(&kvm->slots_lock); mutex_init(&kvm->slots_arch_lock); + spin_lock_init(&kvm->mn_invalidate_lock); + rcuwait_init(&kvm->mn_memslots_update_rcuwait); + INIT_LIST_HEAD(&kvm->devices); BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); @@ -1099,6 +1125,16 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_coalesced_mmio_free(kvm); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); + /* + * At this point, pending calls to invalidate_range_start() + * have completed but no more MMU notifiers will run, so + * mn_active_invalidate_count may remain unbalanced. + * No threads can be waiting in install_new_memslots as the + * last reference on KVM has been dropped, but freeing + * memslots would deadlock without this manual intervention. + */ + WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); + kvm->mn_active_invalidate_count = 0; #else kvm_arch_flush_shadow_all(kvm); #endif @@ -1360,7 +1396,21 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; + /* + * Do not store the new memslots while there are invalidations in + * progress (preparatory change for the next commit). + */ + spin_lock(&kvm->mn_invalidate_lock); + prepare_to_rcuwait(&kvm->mn_memslots_update_rcuwait); + while (kvm->mn_active_invalidate_count) { + set_current_state(TASK_UNINTERRUPTIBLE); + spin_unlock(&kvm->mn_invalidate_lock); + schedule(); + spin_lock(&kvm->mn_invalidate_lock); + } + finish_rcuwait(&kvm->mn_memslots_update_rcuwait); rcu_assign_pointer(kvm->memslots[as_id], slots); + spin_unlock(&kvm->mn_invalidate_lock); /* * Acquired in kvm_set_memslot. Must be released before synchronize -- cgit v1.2.3 From ce78ffa3ef1681065ba451cfd545da6126f5ca88 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 3 Aug 2021 11:14:03 +0100 Subject: net: really fix the build... Signed-off-by: David S. Miller --- drivers/bus/mhi/core/internal.h | 2 +- drivers/bus/mhi/core/main.c | 9 ++++++--- drivers/net/mhi/net.c | 2 +- drivers/net/wwan/mhi_wwan_ctrl.c | 2 +- include/linux/mhi.h | 7 ++++++- net/qrtr/mhi.c | 16 +++++++++++++++- 6 files changed, 30 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h index 5b9ea66b92dc..bc239a11aa69 100644 --- a/drivers/bus/mhi/core/internal.h +++ b/drivers/bus/mhi/core/internal.h @@ -682,7 +682,7 @@ void mhi_rddm_prepare(struct mhi_controller *mhi_cntrl, struct image_info *img_info); void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl); int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan); + struct mhi_chan *mhi_chan, unsigned int flags); int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan); void mhi_deinit_chan_ctxt(struct mhi_controller *mhi_cntrl, diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index fc9196f11cb7..84448233f64c 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -1430,7 +1430,7 @@ exit_unprepare_channel: } int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan) + struct mhi_chan *mhi_chan, unsigned int flags) { int ret = 0; struct device *dev = &mhi_chan->mhi_dev->dev; @@ -1455,6 +1455,9 @@ int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, if (ret) goto error_pm_state; + if (mhi_chan->dir == DMA_FROM_DEVICE) + mhi_chan->pre_alloc = !!(flags & MHI_CH_INBOUND_ALLOC_BUFS); + /* Pre-allocate buffer for xfer ring */ if (mhi_chan->pre_alloc) { int nr_el = get_nr_avail_ring_elements(mhi_cntrl, @@ -1610,7 +1613,7 @@ void mhi_reset_chan(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan) } /* Move channel to start state */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags) { int ret, dir; struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl; @@ -1621,7 +1624,7 @@ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) if (!mhi_chan) continue; - ret = mhi_prepare_channel(mhi_cntrl, mhi_chan); + ret = mhi_prepare_channel(mhi_cntrl, mhi_chan, flags); if (ret) goto error_open_chan; } diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index e60e38c1f09d..11be6bcdd551 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -335,7 +335,7 @@ static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id, u64_stats_init(&mhi_netdev->stats.tx_syncp); /* Start MHI channels */ - err = mhi_prepare_for_transfer(mhi_dev); + err = mhi_prepare_for_transfer(mhi_dev, 0); if (err) goto out_err; diff --git a/drivers/net/wwan/mhi_wwan_ctrl.c b/drivers/net/wwan/mhi_wwan_ctrl.c index 1bc6b69aa530..1e18420ce404 100644 --- a/drivers/net/wwan/mhi_wwan_ctrl.c +++ b/drivers/net/wwan/mhi_wwan_ctrl.c @@ -110,7 +110,7 @@ static int mhi_wwan_ctrl_start(struct wwan_port *port) int ret; /* Start mhi device's channel(s) */ - ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev); + ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev, 0); if (ret) return ret; diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 944aa3aa3035..5e08468854db 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -719,8 +719,13 @@ void mhi_device_put(struct mhi_device *mhi_dev); * host and device execution environments match and * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels + * @flags: MHI channel flags */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, + unsigned int flags); + +/* Automatically allocate and queue inbound buffers */ +#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0) /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c index fa611678af05..1dc955ca57d3 100644 --- a/net/qrtr/mhi.c +++ b/net/qrtr/mhi.c @@ -15,6 +15,7 @@ struct qrtr_mhi_dev { struct qrtr_endpoint ep; struct mhi_device *mhi_dev; struct device *dev; + struct completion ready; }; /* From MHI to QRTR */ @@ -50,6 +51,10 @@ static int qcom_mhi_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb) struct qrtr_mhi_dev *qdev = container_of(ep, struct qrtr_mhi_dev, ep); int rc; + rc = wait_for_completion_interruptible(&qdev->ready); + if (rc) + goto free_skb; + if (skb->sk) sock_hold(skb->sk); @@ -79,7 +84,7 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, int rc; /* start channels */ - rc = mhi_prepare_for_transfer(mhi_dev); + rc = mhi_prepare_for_transfer(mhi_dev, 0); if (rc) return rc; @@ -96,6 +101,15 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, if (rc) return rc; + /* start channels */ + rc = mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS); + if (rc) { + qrtr_endpoint_unregister(&qdev->ep); + dev_set_drvdata(&mhi_dev->dev, NULL); + return rc; + } + + complete_all(&qdev->ready); dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n"); return 0; -- cgit v1.2.3 From f1260ff15a71b8fc122b2c9abd8a7abffb6e0168 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Mon, 2 Aug 2021 11:52:15 +0300 Subject: skbuff: introduce skb_expand_head() Like skb_realloc_headroom(), new helper increases headroom of specified skb. Unlike skb_realloc_headroom(), it does not allocate a new skb if possible; copies skb->sk on new skb when as needed and frees original skb in case of failures. This helps to simplify ip[6]_finish_output2() and a few other similar cases. Signed-off-by: Vasily Averin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + net/core/skbuff.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2bcdc8cd38be..783cc2368bb1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1183,6 +1183,7 @@ static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); +struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index fcbd977186b0..8bac7a1a81ba 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1789,6 +1789,48 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) } EXPORT_SYMBOL(skb_realloc_headroom); +/** + * skb_expand_head - reallocate header of &sk_buff + * @skb: buffer to reallocate + * @headroom: needed headroom + * + * Unlike skb_realloc_headroom, this one does not allocate a new skb + * if possible; copies skb->sk to new skb as needed + * and frees original skb in case of failures. + * + * It expect increased headroom and generates warning otherwise. + */ + +struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom) +{ + int delta = headroom - skb_headroom(skb); + + if (WARN_ONCE(delta <= 0, + "%s is expecting an increase in the headroom", __func__)) + return skb; + + /* pskb_expand_head() might crash, if skb is shared */ + if (skb_shared(skb)) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + if (likely(nskb)) { + if (skb->sk) + skb_set_owner_w(nskb, skb->sk); + consume_skb(skb); + } else { + kfree_skb(skb); + } + skb = nskb; + } + if (skb && + pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { + kfree_skb(skb); + skb = NULL; + } + return skb; +} +EXPORT_SYMBOL(skb_expand_head); + /** * skb_copy_expand - copy and expand sk_buff * @skb: buffer to copy -- cgit v1.2.3 From 5ea2f5ffde39251115ef9a566262fb9e52b91cb7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 3 Aug 2021 13:40:46 +0200 Subject: move netdev_boot_setup into Space.c This is now only used by a handful of old ISA drivers, and can be moved into the file they already all depend on. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/Space.c | 142 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/netdevice.h | 13 ----- net/core/dev.c | 125 ---------------------------------------- net/ethernet/eth.c | 2 - 4 files changed, 142 insertions(+), 140 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/Space.c b/drivers/net/Space.c index a03559f23295..f40f2e38682f 100644 --- a/drivers/net/Space.c +++ b/drivers/net/Space.c @@ -30,6 +30,148 @@ #include #include +/* + * This structure holds boot-time configured netdevice settings. They + * are then used in the device probing. + */ +struct netdev_boot_setup { + char name[IFNAMSIZ]; + struct ifmap map; +}; +#define NETDEV_BOOT_SETUP_MAX 8 + + +/****************************************************************************** + * + * Device Boot-time Settings Routines + * + ******************************************************************************/ + +/* Boot time configuration table */ +static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX]; + +/** + * netdev_boot_setup_add - add new setup entry + * @name: name of the device + * @map: configured settings for the device + * + * Adds new setup entry to the dev_boot_setup list. The function + * returns 0 on error and 1 on success. This is a generic routine to + * all netdevices. + */ +static int netdev_boot_setup_add(char *name, struct ifmap *map) +{ + struct netdev_boot_setup *s; + int i; + + s = dev_boot_setup; + for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { + if (s[i].name[0] == '\0' || s[i].name[0] == ' ') { + memset(s[i].name, 0, sizeof(s[i].name)); + strlcpy(s[i].name, name, IFNAMSIZ); + memcpy(&s[i].map, map, sizeof(s[i].map)); + break; + } + } + + return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1; +} + +/** + * netdev_boot_setup_check - check boot time settings + * @dev: the netdevice + * + * Check boot time settings for the device. + * The found settings are set for the device to be used + * later in the device probing. + * Returns 0 if no settings found, 1 if they are. + */ +int netdev_boot_setup_check(struct net_device *dev) +{ + struct netdev_boot_setup *s = dev_boot_setup; + int i; + + for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { + if (s[i].name[0] != '\0' && s[i].name[0] != ' ' && + !strcmp(dev->name, s[i].name)) { + dev->irq = s[i].map.irq; + dev->base_addr = s[i].map.base_addr; + dev->mem_start = s[i].map.mem_start; + dev->mem_end = s[i].map.mem_end; + return 1; + } + } + return 0; +} +EXPORT_SYMBOL(netdev_boot_setup_check); + +/** + * netdev_boot_base - get address from boot time settings + * @prefix: prefix for network device + * @unit: id for network device + * + * Check boot time settings for the base address of device. + * The found settings are set for the device to be used + * later in the device probing. + * Returns 0 if no settings found. + */ +static unsigned long netdev_boot_base(const char *prefix, int unit) +{ + const struct netdev_boot_setup *s = dev_boot_setup; + char name[IFNAMSIZ]; + int i; + + sprintf(name, "%s%d", prefix, unit); + + /* + * If device already registered then return base of 1 + * to indicate not to probe for this interface + */ + if (__dev_get_by_name(&init_net, name)) + return 1; + + for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) + if (!strcmp(name, s[i].name)) + return s[i].map.base_addr; + return 0; +} + +/* + * Saves at boot time configured settings for any netdevice. + */ +static int __init netdev_boot_setup(char *str) +{ + int ints[5]; + struct ifmap map; + + str = get_options(str, ARRAY_SIZE(ints), ints); + if (!str || !*str) + return 0; + + /* Save settings */ + memset(&map, 0, sizeof(map)); + if (ints[0] > 0) + map.irq = ints[1]; + if (ints[0] > 1) + map.base_addr = ints[2]; + if (ints[0] > 2) + map.mem_start = ints[3]; + if (ints[0] > 3) + map.mem_end = ints[4]; + + /* Add new entry to the list */ + return netdev_boot_setup_add(str, &map); +} + +__setup("netdev=", netdev_boot_setup); + +static int __init ether_boot_setup(char *str) +{ + return netdev_boot_setup(str); +} +__setup("ether=", ether_boot_setup); + + /* A unified ethernet device probe. This is the easiest way to have every * ethernet adaptor have the name "eth[0123...]". */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d63a94ecbf3b..cd136499ec59 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -295,18 +295,6 @@ enum netdev_state_t { }; -/* - * This structure holds boot-time configured netdevice settings. They - * are then used in the device probing. - */ -struct netdev_boot_setup { - char name[IFNAMSIZ]; - struct ifmap map; -}; -#define NETDEV_BOOT_SETUP_MAX 8 - -int __init netdev_boot_setup(char *str); - struct gro_list { struct list_head list; int count; @@ -2939,7 +2927,6 @@ static inline struct net_device *first_net_device_rcu(struct net *net) } int netdev_boot_setup_check(struct net_device *dev); -unsigned long netdev_boot_base(const char *prefix, int unit); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); diff --git a/net/core/dev.c b/net/core/dev.c index 64e1a5f63f93..4a1401008db9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -676,131 +676,6 @@ void dev_remove_offload(struct packet_offload *po) } EXPORT_SYMBOL(dev_remove_offload); -/****************************************************************************** - * - * Device Boot-time Settings Routines - * - ******************************************************************************/ - -/* Boot time configuration table */ -static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX]; - -/** - * netdev_boot_setup_add - add new setup entry - * @name: name of the device - * @map: configured settings for the device - * - * Adds new setup entry to the dev_boot_setup list. The function - * returns 0 on error and 1 on success. This is a generic routine to - * all netdevices. - */ -static int netdev_boot_setup_add(char *name, struct ifmap *map) -{ - struct netdev_boot_setup *s; - int i; - - s = dev_boot_setup; - for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { - if (s[i].name[0] == '\0' || s[i].name[0] == ' ') { - memset(s[i].name, 0, sizeof(s[i].name)); - strlcpy(s[i].name, name, IFNAMSIZ); - memcpy(&s[i].map, map, sizeof(s[i].map)); - break; - } - } - - return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1; -} - -/** - * netdev_boot_setup_check - check boot time settings - * @dev: the netdevice - * - * Check boot time settings for the device. - * The found settings are set for the device to be used - * later in the device probing. - * Returns 0 if no settings found, 1 if they are. - */ -int netdev_boot_setup_check(struct net_device *dev) -{ - struct netdev_boot_setup *s = dev_boot_setup; - int i; - - for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { - if (s[i].name[0] != '\0' && s[i].name[0] != ' ' && - !strcmp(dev->name, s[i].name)) { - dev->irq = s[i].map.irq; - dev->base_addr = s[i].map.base_addr; - dev->mem_start = s[i].map.mem_start; - dev->mem_end = s[i].map.mem_end; - return 1; - } - } - return 0; -} -EXPORT_SYMBOL(netdev_boot_setup_check); - - -/** - * netdev_boot_base - get address from boot time settings - * @prefix: prefix for network device - * @unit: id for network device - * - * Check boot time settings for the base address of device. - * The found settings are set for the device to be used - * later in the device probing. - * Returns 0 if no settings found. - */ -unsigned long netdev_boot_base(const char *prefix, int unit) -{ - const struct netdev_boot_setup *s = dev_boot_setup; - char name[IFNAMSIZ]; - int i; - - sprintf(name, "%s%d", prefix, unit); - - /* - * If device already registered then return base of 1 - * to indicate not to probe for this interface - */ - if (__dev_get_by_name(&init_net, name)) - return 1; - - for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) - if (!strcmp(name, s[i].name)) - return s[i].map.base_addr; - return 0; -} - -/* - * Saves at boot time configured settings for any netdevice. - */ -int __init netdev_boot_setup(char *str) -{ - int ints[5]; - struct ifmap map; - - str = get_options(str, ARRAY_SIZE(ints), ints); - if (!str || !*str) - return 0; - - /* Save settings */ - memset(&map, 0, sizeof(map)); - if (ints[0] > 0) - map.irq = ints[1]; - if (ints[0] > 1) - map.base_addr = ints[2]; - if (ints[0] > 2) - map.mem_start = ints[3]; - if (ints[0] > 3) - map.mem_end = ints[4]; - - /* Add new entry to the list */ - return netdev_boot_setup_add(str, &map); -} - -__setup("netdev=", netdev_boot_setup); - /******************************************************************************* * * Device Interface Subroutines diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 171ba75b74c9..73fce9467467 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -62,8 +62,6 @@ #include #include -__setup("ether=", netdev_boot_setup); - /** * eth_header - create the Ethernet header * @skb: buffer to alter -- cgit v1.2.3 From 67ccddf86621b18dbffe56f11a106774ee8f44bd Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Wed, 28 Jul 2021 23:25:45 +0200 Subject: ftrace: Introduce ftrace_need_init_nop() Implementing live patching on s390 requires each function's prologue to contain a very special kind of nop, which gcc and clang don't generate. However, the current code assumes that if CC_USING_NOP_MCOUNT is defined, then whatever the compiler generates is good enough. Move the CC_USING_NOP_MCOUNT check into the new ftrace_need_init_nop() macro, that the architectures can override. An alternative solution is to disable using -mnop-mcount in the Makefile, however, this makes the build logic (even) more complicated and forces the arch-specific code to deal with the useless __fentry__ symbol. Signed-off-by: Ilya Leoshkevich Reviewed-by: Steven Rostedt (VMware) Link: https://lore.kernel.org/r/20210728212546.128248-2-iii@linux.ibm.com Signed-off-by: Heiko Carstens --- include/linux/ftrace.h | 16 ++++++++++++++++ kernel/trace/ftrace.c | 4 ++-- 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a69f363b61bf..832e65f06754 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -643,6 +643,22 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; } extern int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr); +/** + * ftrace_need_init_nop - return whether nop call sites should be initialized + * + * Normally the compiler's -mnop-mcount generates suitable nops, so we don't + * need to call ftrace_init_nop() if the code is built with that flag. + * Architectures where this is not always the case may define their own + * condition. + * + * Return must be: + * 0 if ftrace_init_nop() should be called + * Nonzero if ftrace_init_nop() should not be called + */ + +#ifndef ftrace_need_init_nop +#define ftrace_need_init_nop() (!__is_defined(CC_USING_NOP_MCOUNT)) +#endif /** * ftrace_init_nop - initialize a nop call site diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 7b180f61e6d3..7efbc8aaf7f6 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3100,6 +3100,7 @@ ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec) static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) { + bool init_nop = ftrace_need_init_nop(); struct ftrace_page *pg; struct dyn_ftrace *p; u64 start, stop; @@ -3138,8 +3139,7 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) * Do the initial record conversion from mcount jump * to the NOP instructions. */ - if (!__is_defined(CC_USING_NOP_MCOUNT) && - !ftrace_nop_initialize(mod, p)) + if (init_nop && !ftrace_nop_initialize(mod, p)) break; update_cnt++; -- cgit v1.2.3 From 69f4a26c1e0c7c5e5e77c5bd7b271743c124c545 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Tue, 3 Aug 2021 09:38:22 -0700 Subject: iomap: support reading inline data from non-zero pos The existing inline data support only works for cases where the entire file is stored as inline data. For larger files, EROFS stores the initial blocks separately and the remainder of the file ("file tail") adjacent to the inode. Generalise inline data to allow reading the inline file tail. Tails may not cross a page boundary in memory. We currently have no filesystems that support tails and writing, so that case is currently disabled (see iomap_write_begin_inline). Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andreas Gruenbacher Signed-off-by: Gao Xiang Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 42 ++++++++++++++++++++++++++++++------------ fs/iomap/direct-io.c | 10 ++++++---- include/linux/iomap.h | 18 ++++++++++++++++++ 3 files changed, 54 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index a463b41c0a16..1d31ff6bfea0 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -205,25 +205,32 @@ struct iomap_readpage_ctx { struct readahead_control *rac; }; -static void -iomap_read_inline_data(struct inode *inode, struct page *page, +static int iomap_read_inline_data(struct inode *inode, struct page *page, struct iomap *iomap) { - size_t size = i_size_read(inode); + size_t size = i_size_read(inode) - iomap->offset; void *addr; if (PageUptodate(page)) - return; + return 0; - BUG_ON(page_has_private(page)); - BUG_ON(page->index); - BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data)); + /* inline data must start page aligned in the file */ + if (WARN_ON_ONCE(offset_in_page(iomap->offset))) + return -EIO; + if (WARN_ON_ONCE(size > PAGE_SIZE - + offset_in_page(iomap->inline_data))) + return -EIO; + if (WARN_ON_ONCE(size > iomap->length)) + return -EIO; + if (WARN_ON_ONCE(page_has_private(page))) + return -EIO; addr = kmap_atomic(page); memcpy(addr, iomap->inline_data, size); memset(addr + size, 0, PAGE_SIZE - size); kunmap_atomic(addr); SetPageUptodate(page); + return 0; } static inline bool iomap_block_needs_zeroing(struct inode *inode, @@ -246,8 +253,10 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, sector_t sector; if (iomap->type == IOMAP_INLINE) { - WARN_ON_ONCE(pos); - iomap_read_inline_data(inode, page, iomap); + int ret = iomap_read_inline_data(inode, page, iomap); + + if (ret) + return ret; return PAGE_SIZE; } @@ -581,6 +590,15 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, return 0; } +static int iomap_write_begin_inline(struct inode *inode, + struct page *page, struct iomap *srcmap) +{ + /* needs more work for the tailpacking case; disable for now */ + if (WARN_ON_ONCE(srcmap->offset != 0)) + return -EIO; + return iomap_read_inline_data(inode, page, srcmap); +} + static int iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, struct page **pagep, struct iomap *iomap, struct iomap *srcmap) @@ -610,7 +628,7 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, } if (srcmap->type == IOMAP_INLINE) - iomap_read_inline_data(inode, page, srcmap); + status = iomap_write_begin_inline(inode, page, srcmap); else if (iomap->flags & IOMAP_F_BUFFER_HEAD) status = __block_write_begin_int(page, pos, len, NULL, srcmap); else @@ -663,11 +681,11 @@ static size_t iomap_write_end_inline(struct inode *inode, struct page *page, void *addr; WARN_ON_ONCE(!PageUptodate(page)); - BUG_ON(pos + copied > PAGE_SIZE - offset_in_page(iomap->inline_data)); + BUG_ON(!iomap_inline_data_valid(iomap)); flush_dcache_page(page); addr = kmap_atomic(page); - memcpy(iomap->inline_data + pos, addr + pos, copied); + memcpy(iomap_inline_data(iomap, pos), addr + pos, copied); kunmap_atomic(addr); mark_inode_dirty(inode); diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 9398b8c31323..41ccbfc9dc82 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -378,23 +378,25 @@ iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length, struct iomap_dio *dio, struct iomap *iomap) { struct iov_iter *iter = dio->submit.iter; + void *inline_data = iomap_inline_data(iomap, pos); size_t copied; - BUG_ON(pos + length > PAGE_SIZE - offset_in_page(iomap->inline_data)); + if (WARN_ON_ONCE(!iomap_inline_data_valid(iomap))) + return -EIO; if (dio->flags & IOMAP_DIO_WRITE) { loff_t size = inode->i_size; if (pos > size) - memset(iomap->inline_data + size, 0, pos - size); - copied = copy_from_iter(iomap->inline_data + pos, length, iter); + memset(iomap_inline_data(iomap, size), 0, pos - size); + copied = copy_from_iter(inline_data, length, iter); if (copied) { if (pos + copied > size) i_size_write(inode, pos + copied); mark_inode_dirty(inode); } } else { - copied = copy_to_iter(iomap->inline_data + pos, length, iter); + copied = copy_to_iter(inline_data, length, iter); } dio->size += copied; return copied; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 479c1da3e221..b8ec145b2975 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -97,6 +97,24 @@ iomap_sector(struct iomap *iomap, loff_t pos) return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT; } +/* + * Returns the inline data pointer for logical offset @pos. + */ +static inline void *iomap_inline_data(struct iomap *iomap, loff_t pos) +{ + return iomap->inline_data + pos - iomap->offset; +} + +/* + * Check if the mapping's length is within the valid range for inline data. + * This is used to guard against accessing data beyond the page inline_data + * points at. + */ +static inline bool iomap_inline_data_valid(struct iomap *iomap) +{ + return iomap->length <= PAGE_SIZE - offset_in_page(iomap->inline_data); +} + /* * When a filesystem sets page_ops in an iomap mapping it returns, page_prepare * and page_done will be called for each page written to. This only applies to -- cgit v1.2.3 From d08c8b855140e9f5240b3ffd1b8b9d435675e281 Mon Sep 17 00:00:00 2001 From: Wasim Khan Date: Thu, 29 Jul 2021 14:17:47 +0200 Subject: PCI: Add ACS quirks for NXP LX2xx0 and LX2xx2 platforms Root Ports in NXP LX2xx0 and LX2xx2, where each Root Port is a Root Complex with unique segment numbers, do provide isolation features to disable peer transactions and validate bus numbers in requests, but do not provide an actual PCIe ACS capability. Add ACS quirks for NXP LX2xx0 A/C/E/N and LX2xx2 A/C/E/N platforms. LX2xx0A : without security features + CAN-FD LX2160A (0x8d81) - 16 cores LX2120A (0x8da1) - 12 cores LX2080A (0x8d83) - 8 cores LX2xx0C : security features + CAN-FD LX2160C (0x8d80) - 16 cores LX2120C (0x8da0) - 12 cores LX2080C (0x8d82) - 8 cores LX2xx0E : security features + CAN LX2160E (0x8d90) - 16 cores LX2120E (0x8db0) - 12 cores LX2080E (0x8d92) - 8 cores LX2xx0N : without security features + CAN LX2160N (0x8d91) - 16 cores LX2120N (0x8db1) - 12 cores LX2080N (0x8d93) - 8 cores LX2xx2A : without security features + CAN-FD LX2162A (0x8d89) - 16 cores LX2122A (0x8da9) - 12 cores LX2082A (0x8d8b) - 8 cores LX2xx2C : security features + CAN-FD LX2162C (0x8d88) - 16 cores LX2122C (0x8da8) - 12 cores LX2082C (0x8d8a) - 8 cores LX2xx2E : security features + CAN LX2162E (0x8d98) - 16 cores LX2122E (0x8db8) - 12 cores LX2082E (0x8d9a) - 8 cores LX2xx2N : without security features + CAN LX2162N (0x8d99) - 16 cores LX2122N (0x8db9) - 12 cores LX2082N (0x8d9b) - 8 cores [bhelgaas: put PCI_VENDOR_ID_NXP definition next to PCI_VENDOR_ID_FREESCALE as a clue that they share the same Device ID namespace] Link: https://lore.kernel.org/r/20210729121747.1823086-1-wasim.khan@oss.nxp.com Link: https://lore.kernel.org/r/20210803180021.3252886-1-wasim.khan@oss.nxp.com Signed-off-by: Wasim Khan Signed-off-by: Bjorn Helgaas --- drivers/pci/quirks.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci_ids.h | 3 ++- 2 files changed, 47 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 6d74386eadc2..207d089a8d37 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4614,6 +4614,18 @@ static int pci_quirk_qcom_rp_acs(struct pci_dev *dev, u16 acs_flags) PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); } +/* + * Each of these NXP Root Ports is in a Root Complex with a unique segment + * number and does provide isolation features to disable peer transactions + * and validate bus numbers in requests, but does not provide an ACS + * capability. + */ +static int pci_quirk_nxp_rp_acs(struct pci_dev *dev, u16 acs_flags) +{ + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); +} + static int pci_quirk_al_acs(struct pci_dev *dev, u16 acs_flags) { if (pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) @@ -4860,6 +4872,39 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_ZHAOXIN, 0x3038, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_ZHAOXIN, 0x3104, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_ZHAOXIN, 0x9083, pci_quirk_mf_endpoint_acs }, + /* NXP root ports, xx=16, 12, or 08 cores */ + /* LX2xx0A : without security features + CAN-FD */ + { PCI_VENDOR_ID_NXP, 0x8d81, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8da1, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8d83, pci_quirk_nxp_rp_acs }, + /* LX2xx0C : security features + CAN-FD */ + { PCI_VENDOR_ID_NXP, 0x8d80, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8da0, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8d82, pci_quirk_nxp_rp_acs }, + /* LX2xx0E : security features + CAN */ + { PCI_VENDOR_ID_NXP, 0x8d90, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8db0, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8d92, pci_quirk_nxp_rp_acs }, + /* LX2xx0N : without security features + CAN */ + { PCI_VENDOR_ID_NXP, 0x8d91, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8db1, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8d93, pci_quirk_nxp_rp_acs }, + /* LX2xx2A : without security features + CAN-FD */ + { PCI_VENDOR_ID_NXP, 0x8d89, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8da9, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8d8b, pci_quirk_nxp_rp_acs }, + /* LX2xx2C : security features + CAN-FD */ + { PCI_VENDOR_ID_NXP, 0x8d88, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8da8, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8d8a, pci_quirk_nxp_rp_acs }, + /* LX2xx2E : security features + CAN */ + { PCI_VENDOR_ID_NXP, 0x8d98, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8db8, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8d9a, pci_quirk_nxp_rp_acs }, + /* LX2xx2N : without security features + CAN */ + { PCI_VENDOR_ID_NXP, 0x8d99, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8db9, pci_quirk_nxp_rp_acs }, + { PCI_VENDOR_ID_NXP, 0x8d9b, pci_quirk_nxp_rp_acs }, /* Zhaoxin Root/Downstream Ports */ { PCI_VENDOR_ID_ZHAOXIN, PCI_ANY_ID, pci_quirk_zhaoxin_pcie_ports_acs }, { 0 } diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 4bac1831de80..1a9b8589391c 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2451,7 +2451,8 @@ #define PCI_VENDOR_ID_TDI 0x192E #define PCI_DEVICE_ID_TDI_EHCI 0x0101 -#define PCI_VENDOR_ID_FREESCALE 0x1957 +#define PCI_VENDOR_ID_FREESCALE 0x1957 /* duplicate: NXP */ +#define PCI_VENDOR_ID_NXP 0x1957 /* duplicate: FREESCALE */ #define PCI_DEVICE_ID_MPC8308 0xc006 #define PCI_DEVICE_ID_MPC8315E 0x00b4 #define PCI_DEVICE_ID_MPC8315 0x00b5 -- cgit v1.2.3 From 5f7b51bf09baca8e4f80cbe879536842bafb5f31 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Wed, 28 Jul 2021 17:01:15 +0200 Subject: netfilter: ipset: Limit the maximal range of consecutive elements to add/delete The range size of consecutive elements were not limited. Thus one could define a huge range which may result soft lockup errors due to the long execution time. Now the range size is limited to 2^20 entries. Reported-by: Brad Spengler Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 3 +++ net/netfilter/ipset/ip_set_hash_ip.c | 9 ++++++++- net/netfilter/ipset/ip_set_hash_ipmark.c | 10 +++++++++- net/netfilter/ipset/ip_set_hash_ipport.c | 3 +++ net/netfilter/ipset/ip_set_hash_ipportip.c | 3 +++ net/netfilter/ipset/ip_set_hash_ipportnet.c | 3 +++ net/netfilter/ipset/ip_set_hash_net.c | 11 ++++++++++- net/netfilter/ipset/ip_set_hash_netiface.c | 10 +++++++++- net/netfilter/ipset/ip_set_hash_netnet.c | 16 +++++++++++++++- net/netfilter/ipset/ip_set_hash_netport.c | 11 ++++++++++- net/netfilter/ipset/ip_set_hash_netportnet.c | 16 +++++++++++++++- 11 files changed, 88 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 10279c4830ac..ada1296c87d5 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -196,6 +196,9 @@ struct ip_set_region { u32 elements; /* Number of elements vs timeout */ }; +/* Max range where every element is added/deleted in one step */ +#define IPSET_MAX_RANGE (1<<20) + /* The max revision number supported by any set type + 1 */ #define IPSET_REVISION_MAX 9 diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index d1bef23fd4f5..dd30c03d5a23 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -132,8 +132,11 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -144,6 +147,10 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); + /* 64bit division is not allowed on 32bit */ + if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) { ip = ntohl(h->next.ip); e.ip = htonl(ip); diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index 18346d18aa16..153de3457423 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -121,6 +121,8 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK])); e.mark &= h->markmask; + if (e.mark == 0 && e.ip == 0) + return -IPSET_ERR_HASH_ELEM; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) { @@ -133,8 +135,11 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (e.mark == 0 && ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -143,6 +148,9 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ip_set_mask_from_to(ip, ip_to, cidr); } + if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index e1ca11196515..7303138e46be 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -173,6 +173,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index ab179e064597..334fb1ad0e86 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -180,6 +180,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 8f075b44cf64..7df94f437f60 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -253,6 +253,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c1a11f041ac6..1422739d9aa2 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -140,7 +140,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { .cidr = HOST_MASK }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -188,6 +188,15 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); do { diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index ddd51c2e1cb3..9810f5bf63f5 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -202,7 +202,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -256,6 +256,14 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; if (retried) ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 6532f0505e66..3d09eefe998a 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -168,7 +168,8 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0; - u32 ip2 = 0, ip2_from = 0, ip2_to = 0; + u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn; + u64 n = 0, m = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -244,6 +245,19 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index ec1564a1cb5a..09cf72eb37f8 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -158,7 +158,8 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 port, port_to, p = 0, ip = 0, ip_to = 0; + u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn; + u64 n = 0; bool with_ports = false; u8 cidr; int ret; @@ -235,6 +236,14 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr); + n++; + } while (ipn++ < ip_to); + + if (n*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 0e91d1e82f1c..19bcdb3141f6 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -182,7 +182,8 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to = 0, ip2; + u32 ip2_from = 0, ip2_to = 0, ip2, ipn; + u64 n = 0, m = 0; bool with_ports = false; int ret; @@ -284,6 +285,19 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); -- cgit v1.2.3 From 27cfdadd687deca58146b415f60b23d185cb3532 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Tue, 3 Aug 2021 19:57:42 +0300 Subject: bus: fsl-mc: extend fsl_mc_get_endpoint() to pass interface ID In case of a switch DPAA2 object, the interface ID is also needed when querying for the object endpoint. Extend fsl_mc_get_endpoint() so that users can also pass the interface ID that are interested in. Signed-off-by: Ioana Ciornei Signed-off-by: David S. Miller --- drivers/bus/fsl-mc/fsl-mc-bus.c | 4 +++- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 2 +- include/linux/fsl/mc.h | 3 ++- 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 09c8ab5e0959..b3691de8ac06 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -914,7 +914,8 @@ void fsl_mc_device_remove(struct fsl_mc_device *mc_dev) } EXPORT_SYMBOL_GPL(fsl_mc_device_remove); -struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev) +struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, + u16 if_id) { struct fsl_mc_device *mc_bus_dev, *endpoint; struct fsl_mc_obj_desc endpoint_desc = {{ 0 }}; @@ -925,6 +926,7 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev) mc_bus_dev = to_fsl_mc_device(mc_dev->dev.parent); strcpy(endpoint1.type, mc_dev->obj_desc.type); endpoint1.id = mc_dev->obj_desc.id; + endpoint1.if_id = if_id; err = dprc_get_connection(mc_bus_dev->mc_io, 0, mc_bus_dev->mc_handle, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index f664021c3ad1..7065c71ed7b8 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4138,7 +4138,7 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv) int err; dpni_dev = to_fsl_mc_device(priv->net_dev->dev.parent); - dpmac_dev = fsl_mc_get_endpoint(dpni_dev); + dpmac_dev = fsl_mc_get_endpoint(dpni_dev, 0); if (PTR_ERR(dpmac_dev) == -EPROBE_DEFER) return PTR_ERR(dpmac_dev); diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 63b56aba925a..30ece3ae6df7 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -423,7 +423,8 @@ int __must_check fsl_mc_allocate_irqs(struct fsl_mc_device *mc_dev); void fsl_mc_free_irqs(struct fsl_mc_device *mc_dev); -struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev); +struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, + u16 if_id); extern struct bus_type fsl_mc_bus_type; -- cgit v1.2.3 From 271e5b7d00aeff7c61fb6c5415d14dbedb783b68 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 3 Aug 2021 06:05:26 -0700 Subject: net: add netif_set_real_num_queues() for device reconfig netif_set_real_num_rx_queues() and netif_set_real_num_tx_queues() can fail which breaks drivers trying to implement reconfiguration in a way that can't leave the device half-broken. In other words those functions are incompatible with prepare/commit approach. Luckily setting real number of queues can fail only if the number is increased, meaning that if we order operations correctly we can guarantee ending up with either new config (success), or the old one (on error). Provide a helper implementing such logic so that drivers don't have to duplicate it. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ net/core/dev.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cd136499ec59..1b4d4509d04b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3916,6 +3916,8 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev, return 0; } #endif +int netif_set_real_num_queues(struct net_device *dev, + unsigned int txq, unsigned int rxq); static inline struct netdev_rx_queue * __netif_get_rx_queue(struct net_device *dev, unsigned int rxq) diff --git a/net/core/dev.c b/net/core/dev.c index 4a1401008db9..360cb2f1b1e9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2973,6 +2973,50 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) EXPORT_SYMBOL(netif_set_real_num_rx_queues); #endif +/** + * netif_set_real_num_queues - set actual number of RX and TX queues used + * @dev: Network device + * @txq: Actual number of TX queues + * @rxq: Actual number of RX queues + * + * Set the real number of both TX and RX queues. + * Does nothing if the number of queues is already correct. + */ +int netif_set_real_num_queues(struct net_device *dev, + unsigned int txq, unsigned int rxq) +{ + unsigned int old_rxq = dev->real_num_rx_queues; + int err; + + if (txq < 1 || txq > dev->num_tx_queues || + rxq < 1 || rxq > dev->num_rx_queues) + return -EINVAL; + + /* Start from increases, so the error path only does decreases - + * decreases can't fail. + */ + if (rxq > dev->real_num_rx_queues) { + err = netif_set_real_num_rx_queues(dev, rxq); + if (err) + return err; + } + if (txq > dev->real_num_tx_queues) { + err = netif_set_real_num_tx_queues(dev, txq); + if (err) + goto undo_rx; + } + if (rxq < dev->real_num_rx_queues) + WARN_ON(netif_set_real_num_rx_queues(dev, rxq)); + if (txq < dev->real_num_tx_queues) + WARN_ON(netif_set_real_num_tx_queues(dev, txq)); + + return 0; +undo_rx: + WARN_ON(netif_set_real_num_rx_queues(dev, old_rxq)); + return err; +} +EXPORT_SYMBOL(netif_set_real_num_queues); + /** * netif_get_num_default_rss_queues - default number of RSS queues * -- cgit v1.2.3 From 8e3d25a6231832a9525f0e0bb6fb4c13df347175 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 26 Jul 2021 10:37:55 +0200 Subject: pata: ixp4xx: Refer to cmd and ctl rather than csN The two "cs0" and "cs1" are "chip selects" but on some platforms such as GW2358 they are actually both in CS3 making this terminology very confusing. Call the addresses "cmd" and "ctl" after function instead. Signed-off-by: Linus Walleij --- drivers/ata/pata_ixp4xx_cf.c | 27 +++++++++++++-------------- include/linux/platform_data/pata_ixp4xx_cf.h | 4 ++-- 2 files changed, 15 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c index bc5029d6525d..72d6d6f2ef99 100644 --- a/drivers/ata/pata_ixp4xx_cf.c +++ b/drivers/ata/pata_ixp4xx_cf.c @@ -95,15 +95,14 @@ static struct ata_port_operations ixp4xx_port_ops = { static void ixp4xx_setup_port(struct ata_port *ap, struct ixp4xx_pata_data *data, - unsigned long raw_cs0, unsigned long raw_cs1) + unsigned long raw_cmd, unsigned long raw_ctl) { struct ata_ioports *ioaddr = &ap->ioaddr; - unsigned long raw_cmd = raw_cs0; - unsigned long raw_ctl = raw_cs1 + 0x06; - ioaddr->cmd_addr = data->cs0; - ioaddr->altstatus_addr = data->cs1 + 0x06; - ioaddr->ctl_addr = data->cs1 + 0x06; + raw_ctl += 0x06; + ioaddr->cmd_addr = data->cmd; + ioaddr->altstatus_addr = data->ctl + 0x06; + ioaddr->ctl_addr = data->ctl + 0x06; ata_sff_std_ports(ioaddr); @@ -135,7 +134,7 @@ static void ixp4xx_setup_port(struct ata_port *ap, static int ixp4xx_pata_probe(struct platform_device *pdev) { - struct resource *cs0, *cs1; + struct resource *cmd, *ctl; struct ata_host *host; struct ata_port *ap; struct device *dev = &pdev->dev; @@ -143,10 +142,10 @@ static int ixp4xx_pata_probe(struct platform_device *pdev) int ret; int irq; - cs0 = platform_get_resource(pdev, IORESOURCE_MEM, 0); - cs1 = platform_get_resource(pdev, IORESOURCE_MEM, 1); + cmd = platform_get_resource(pdev, IORESOURCE_MEM, 0); + ctl = platform_get_resource(pdev, IORESOURCE_MEM, 1); - if (!cs0 || !cs1) + if (!cmd || !ctl) return -EINVAL; /* allocate host */ @@ -159,10 +158,10 @@ static int ixp4xx_pata_probe(struct platform_device *pdev) if (ret) return ret; - data->cs0 = devm_ioremap(dev, cs0->start, 0x1000); - data->cs1 = devm_ioremap(dev, cs1->start, 0x1000); + data->cmd = devm_ioremap(dev, cmd->start, 0x1000); + data->ctl = devm_ioremap(dev, ctl->start, 0x1000); - if (!data->cs0 || !data->cs1) + if (!data->cmd || !data->ctl) return -ENOMEM; irq = platform_get_irq(pdev, 0); @@ -183,7 +182,7 @@ static int ixp4xx_pata_probe(struct platform_device *pdev) ap->pio_mask = ATA_PIO4; ap->flags |= ATA_FLAG_NO_ATAPI; - ixp4xx_setup_port(ap, data, cs0->start, cs1->start); + ixp4xx_setup_port(ap, data, cmd->start, ctl->start); ata_print_version_once(dev, DRV_VERSION); diff --git a/include/linux/platform_data/pata_ixp4xx_cf.h b/include/linux/platform_data/pata_ixp4xx_cf.h index 601ba97fef57..e60fa41da4a5 100644 --- a/include/linux/platform_data/pata_ixp4xx_cf.h +++ b/include/linux/platform_data/pata_ixp4xx_cf.h @@ -14,8 +14,8 @@ struct ixp4xx_pata_data { volatile u32 *cs1_cfg; unsigned long cs0_bits; unsigned long cs1_bits; - void __iomem *cs0; - void __iomem *cs1; + void __iomem *cmd; + void __iomem *ctl; }; #endif -- cgit v1.2.3 From 957e2235e5264c97cd6be8e2e17f2e11b41f2239 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 3 Aug 2021 23:34:08 +0300 Subject: net: make switchdev_bridge_port_{,unoffload} loosely coupled with the bridge With the introduction of explicit offloading API in switchdev in commit 2f5dc00f7a3e ("net: bridge: switchdev: let drivers inform which bridge ports are offloaded"), we started having Ethernet switch drivers calling directly into a function exported by net/bridge/br_switchdev.c, which is a function exported by the bridge driver. This means that drivers that did not have an explicit dependency on the bridge before, like cpsw and am65-cpsw, now do - otherwise it is not possible to call a symbol exported by a driver that can be built as module unless you are a module too. There was an attempt to solve the dependency issue in the form of commit b0e81817629a ("net: build all switchdev drivers as modules when the bridge is a module"). Grygorii Strashko, however, says about it: | In my opinion, the problem is a bit bigger here than just fixing the | build :( | | In case, of ^cpsw the switchdev mode is kinda optional and in many | cases (especially for testing purposes, NFS) the multi-mac mode is | still preferable mode. | | There were no such tight dependency between switchdev drivers and | bridge core before and switchdev serviced as independent, notification | based layer between them, so ^cpsw still can be "Y" and bridge can be | "M". Now for mostly every kernel build configuration the CONFIG_BRIDGE | will need to be set as "Y", or we will have to update drivers to | support build with BRIDGE=n and maintain separate builds for | networking vs non-networking testing. But is this enough? Wouldn't | it cause 'chain reaction' required to add more and more "Y" options | (like CONFIG_VLAN_8021Q)? | | PS. Just to be sure we on the same page - ARM builds will be forced | (with this patch) to have CONFIG_TI_CPSW_SWITCHDEV=m and so all our | automation testing will just fail with omap2plus_defconfig. In the light of this, it would be desirable for some configurations to avoid dependencies between switchdev drivers and the bridge, and have the switchdev mode as completely optional within the driver. Arnd Bergmann also tried to write a patch which better expressed the build time dependency for Ethernet switch drivers where the switchdev support is optional, like cpsw/am65-cpsw, and this made the drivers follow the bridge (compile as module if the bridge is a module) only if the optional switchdev support in the driver was enabled in the first place: https://patchwork.kernel.org/project/netdevbpf/patch/20210802144813.1152762-1-arnd@kernel.org/ but this still did not solve the fact that cpsw and am65-cpsw now must be built as modules when the bridge is a module - it just expressed correctly that optional dependency. But the new behavior is an apparent regression from Grygorii's perspective. So to support the use case where the Ethernet driver is built-in, NET_SWITCHDEV (a bool option) is enabled, and the bridge is a module, we need a framework that can handle the possible absence of the bridge from the running system, i.e. runtime bloatware as opposed to build-time bloatware. Luckily we already have this framework, since switchdev has been using it extensively. Events from the bridge side are transmitted to the driver side using notifier chains - this was originally done so that unrelated drivers could snoop for events emitted by the bridge towards ports that are implemented by other drivers (think of a switch driver with LAG offload that listens for switchdev events on a bonding/team interface that it offloads). There are also events which are transmitted from the driver side to the bridge side, which again are modeled using notifiers. SWITCHDEV_FDB_ADD_TO_BRIDGE is an example of this, and deals with notifying the bridge that a MAC address has been dynamically learned. So there is a precedent we can use for modeling the new framework. The difference compared to SWITCHDEV_FDB_ADD_TO_BRIDGE is that the work that the bridge needs to do when a port becomes offloaded is blocking in its nature: replay VLANs, MDBs etc. The calling context is indeed blocking (we are under rtnl_mutex), but the existing switchdev notification chain that the bridge is subscribed to is only the atomic one. So we need to subscribe the bridge to the blocking switchdev notification chain too. This patch: - keeps the driver-side perception of the switchdev_bridge_port_{,un}offload unchanged - moves the implementation of switchdev_bridge_port_{,un}offload from the bridge module into the switchdev module. - makes everybody that is subscribed to the switchdev blocking notifier chain "hear" offload & unoffload events - makes the bridge driver subscribe and handle those events - moves the bridge driver's handling of those events into 2 new functions called br_switchdev_port_{,un}offload. These functions contain in fact the core of the logic that was previously in switchdev_bridge_port_{,un}offload, just that now we go through an extra indirection layer to reach them. Unlike all the other switchdev notification structures, the structure used to carry the bridge port information, struct switchdev_notifier_brport_info, does not contain a "bool handled". This is because in the current usage pattern, we always know that a switchdev bridge port offloading event will be handled by the bridge, because the switchdev_bridge_port_offload() call was initiated by a NETDEV_CHANGEUPPER event in the first place, where info->upper_dev is a bridge. So if the bridge wasn't loaded, then the CHANGEUPPER event couldn't have happened. Signed-off-by: Vladimir Oltean Tested-by: Grygorii Strashko Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +- drivers/net/ethernet/ti/cpsw_new.c | 2 +- include/linux/if_bridge.h | 35 ---------------------- include/net/switchdev.h | 46 ++++++++++++++++++++++++++++ net/bridge/br.c | 51 +++++++++++++++++++++++++++++++- net/bridge/br_private.h | 29 ++++++++++++++++++ net/bridge/br_switchdev.c | 36 ++++++---------------- net/switchdev/switchdev.c | 48 ++++++++++++++++++++++++++++++ 8 files changed, 184 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 4f67d1a98c0d..fb5d2ac3f0d2 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -7,7 +7,6 @@ #include #include -#include #include #include #include @@ -28,6 +27,7 @@ #include #include #include +#include #include "cpsw_ale.h" #include "cpsw_sl.h" diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index b4f55ff4e84f..ae167223e87f 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -29,6 +28,7 @@ #include #include +#include #include #include #include diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 21daed10322e..509e18c7e740 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -190,39 +190,4 @@ static inline clock_t br_get_ageing_time(const struct net_device *br_dev) } #endif -#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_NET_SWITCHDEV) - -int switchdev_bridge_port_offload(struct net_device *brport_dev, - struct net_device *dev, const void *ctx, - struct notifier_block *atomic_nb, - struct notifier_block *blocking_nb, - bool tx_fwd_offload, - struct netlink_ext_ack *extack); -void switchdev_bridge_port_unoffload(struct net_device *brport_dev, - const void *ctx, - struct notifier_block *atomic_nb, - struct notifier_block *blocking_nb); - -#else - -static inline int -switchdev_bridge_port_offload(struct net_device *brport_dev, - struct net_device *dev, const void *ctx, - struct notifier_block *atomic_nb, - struct notifier_block *blocking_nb, - bool tx_fwd_offload, - struct netlink_ext_ack *extack) -{ - return -EINVAL; -} - -static inline void -switchdev_bridge_port_unoffload(struct net_device *brport_dev, - const void *ctx, - struct notifier_block *atomic_nb, - struct notifier_block *blocking_nb) -{ -} -#endif - #endif diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 66468ff8cc0a..60d806b6a5ae 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -180,6 +180,14 @@ struct switchdev_obj_in_state_mrp { typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); +struct switchdev_brport { + struct net_device *dev; + const void *ctx; + struct notifier_block *atomic_nb; + struct notifier_block *blocking_nb; + bool tx_fwd_offload; +}; + enum switchdev_notifier_type { SWITCHDEV_FDB_ADD_TO_BRIDGE = 1, SWITCHDEV_FDB_DEL_TO_BRIDGE, @@ -197,6 +205,9 @@ enum switchdev_notifier_type { SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE, SWITCHDEV_VXLAN_FDB_OFFLOADED, + + SWITCHDEV_BRPORT_OFFLOADED, + SWITCHDEV_BRPORT_UNOFFLOADED, }; struct switchdev_notifier_info { @@ -226,6 +237,11 @@ struct switchdev_notifier_port_attr_info { bool handled; }; +struct switchdev_notifier_brport_info { + struct switchdev_notifier_info info; /* must be first */ + const struct switchdev_brport brport; +}; + static inline struct net_device * switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) { @@ -246,6 +262,17 @@ switchdev_fdb_is_dynamically_learned(const struct switchdev_notifier_fdb_info *f #ifdef CONFIG_NET_SWITCHDEV +int switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack); +void switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb); + void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, @@ -316,6 +343,25 @@ int switchdev_handle_port_attr_set(struct net_device *dev, struct netlink_ext_ack *extack)); #else +static inline int +switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline void +switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) +{ +} + static inline void switchdev_deferred_process(void) { } diff --git a/net/bridge/br.c b/net/bridge/br.c index 8fb5dca5f8e0..d3a32c6813e0 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -201,6 +201,48 @@ static struct notifier_block br_switchdev_notifier = { .notifier_call = br_switchdev_event, }; +/* called under rtnl_mutex */ +static int br_switchdev_blocking_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + struct switchdev_notifier_brport_info *brport_info; + const struct switchdev_brport *b; + struct net_bridge_port *p; + int err = NOTIFY_DONE; + + p = br_port_get_rtnl(dev); + if (!p) + goto out; + + switch (event) { + case SWITCHDEV_BRPORT_OFFLOADED: + brport_info = ptr; + b = &brport_info->brport; + + err = br_switchdev_port_offload(p, b->dev, b->ctx, + b->atomic_nb, b->blocking_nb, + b->tx_fwd_offload, extack); + err = notifier_from_errno(err); + break; + case SWITCHDEV_BRPORT_UNOFFLOADED: + brport_info = ptr; + b = &brport_info->brport; + + br_switchdev_port_unoffload(p, b->ctx, b->atomic_nb, + b->blocking_nb); + break; + } + +out: + return err; +} + +static struct notifier_block br_switchdev_blocking_notifier = { + .notifier_call = br_switchdev_blocking_event, +}; + /* br_boolopt_toggle - change user-controlled boolean option * * @br: bridge device @@ -355,10 +397,14 @@ static int __init br_init(void) if (err) goto err_out4; - err = br_netlink_init(); + err = register_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); if (err) goto err_out5; + err = br_netlink_init(); + if (err) + goto err_out6; + brioctl_set(br_ioctl_stub); #if IS_ENABLED(CONFIG_ATM_LANE) @@ -373,6 +419,8 @@ static int __init br_init(void) return 0; +err_out6: + unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); err_out5: unregister_switchdev_notifier(&br_switchdev_notifier); err_out4: @@ -392,6 +440,7 @@ static void __exit br_deinit(void) { stp_proto_unregister(&br_stp_proto); br_netlink_fini(); + unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); unregister_switchdev_notifier(&br_switchdev_notifier); unregister_netdevice_notifier(&br_device_notifier); brioctl_set(NULL); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index c939631428b9..10d43bf4bb80 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1880,6 +1880,17 @@ static inline void br_sysfs_delbr(struct net_device *dev) { return; } /* br_switchdev.c */ #ifdef CONFIG_NET_SWITCHDEV +int br_switchdev_port_offload(struct net_bridge_port *p, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack); + +void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb); + bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb); void br_switchdev_frame_set_offload_fwd_mark(struct sk_buff *skb); @@ -1908,6 +1919,24 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb) skb->offload_fwd_mark = 0; } #else +static inline int +br_switchdev_port_offload(struct net_bridge_port *p, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline void +br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) +{ +} + static inline bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb) { return false; diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 36d75fd4a80c..6bf518d78f02 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -312,23 +312,16 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, /* Let the bridge know that this port is offloaded, so that it can assign a * switchdev hardware domain to it. */ -int switchdev_bridge_port_offload(struct net_device *brport_dev, - struct net_device *dev, const void *ctx, - struct notifier_block *atomic_nb, - struct notifier_block *blocking_nb, - bool tx_fwd_offload, - struct netlink_ext_ack *extack) +int br_switchdev_port_offload(struct net_bridge_port *p, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack) { struct netdev_phys_item_id ppid; - struct net_bridge_port *p; int err; - ASSERT_RTNL(); - - p = br_port_get_rtnl(brport_dev); - if (!p) - return -ENODEV; - err = dev_get_port_parent_id(dev, &ppid, false); if (err) return err; @@ -348,23 +341,12 @@ out_switchdev_del: return err; } -EXPORT_SYMBOL_GPL(switchdev_bridge_port_offload); -void switchdev_bridge_port_unoffload(struct net_device *brport_dev, - const void *ctx, - struct notifier_block *atomic_nb, - struct notifier_block *blocking_nb) +void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) { - struct net_bridge_port *p; - - ASSERT_RTNL(); - - p = br_port_get_rtnl(brport_dev); - if (!p) - return; - nbp_switchdev_unsync_objs(p, ctx, atomic_nb, blocking_nb); nbp_switchdev_del(p); } -EXPORT_SYMBOL_GPL(switchdev_bridge_port_unoffload); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 0ae3478561f4..0b2c18efc079 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -809,3 +809,51 @@ int switchdev_handle_port_attr_set(struct net_device *dev, return err; } EXPORT_SYMBOL_GPL(switchdev_handle_port_attr_set); + +int switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + struct switchdev_notifier_brport_info brport_info = { + .brport = { + .dev = dev, + .ctx = ctx, + .atomic_nb = atomic_nb, + .blocking_nb = blocking_nb, + .tx_fwd_offload = tx_fwd_offload, + }, + }; + int err; + + ASSERT_RTNL(); + + err = call_switchdev_blocking_notifiers(SWITCHDEV_BRPORT_OFFLOADED, + brport_dev, &brport_info.info, + extack); + return notifier_to_errno(err); +} +EXPORT_SYMBOL_GPL(switchdev_bridge_port_offload); + +void switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) +{ + struct switchdev_notifier_brport_info brport_info = { + .brport = { + .ctx = ctx, + .atomic_nb = atomic_nb, + .blocking_nb = blocking_nb, + }, + }; + + ASSERT_RTNL(); + + call_switchdev_blocking_notifiers(SWITCHDEV_BRPORT_UNOFFLOADED, + brport_dev, &brport_info.info, + NULL); +} +EXPORT_SYMBOL_GPL(switchdev_bridge_port_unoffload); -- cgit v1.2.3 From cb531cab62a19e97d8de0a2c9935daed93ec3736 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Fri, 25 Jun 2021 10:52:09 +0530 Subject: soc: qcom: geni: move GENI_IF_DISABLE_RO to common header GENI_IF_DISABLE_RO is used by geni spi driver as well to check the status if GENI, so move this to common header qcom-geni-se.h Reviewed-by: Bjorn Andersson Signed-off-by: Vinod Koul Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/20210625052213.32260-2-vkoul@kernel.org Signed-off-by: Bjorn Andersson --- drivers/soc/qcom/qcom-geni-se.c | 1 - include/linux/qcom-geni-se.h | 4 ++++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c index 5bdfb1565c14..fe666ea0c487 100644 --- a/drivers/soc/qcom/qcom-geni-se.c +++ b/drivers/soc/qcom/qcom-geni-se.c @@ -104,7 +104,6 @@ static const char * const icc_path_names[] = {"qup-core", "qup-config", #define GENI_OUTPUT_CTRL 0x24 #define GENI_CGC_CTRL 0x28 #define GENI_CLK_CTRL_RO 0x60 -#define GENI_IF_DISABLE_RO 0x64 #define GENI_FW_S_REVISION_RO 0x6c #define SE_GENI_BYTE_GRAN 0x254 #define SE_GENI_TX_PACKING_CFG0 0x260 diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 7c811eebcaab..5114e2144b17 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -63,6 +63,7 @@ struct geni_se { #define SE_GENI_STATUS 0x40 #define GENI_SER_M_CLK_CFG 0x48 #define GENI_SER_S_CLK_CFG 0x4c +#define GENI_IF_DISABLE_RO 0x64 #define GENI_FW_REVISION_RO 0x68 #define SE_GENI_CLK_SEL 0x7c #define SE_GENI_DMA_MODE_EN 0x258 @@ -105,6 +106,9 @@ struct geni_se { #define CLK_DIV_MSK GENMASK(15, 4) #define CLK_DIV_SHFT 4 +/* GENI_IF_DISABLE_RO fields */ +#define FIFO_IF_DISABLE (BIT(0)) + /* GENI_FW_REVISION_RO fields */ #define FW_REV_PROTOCOL_MSK GENMASK(15, 8) #define FW_REV_PROTOCOL_SHFT 8 -- cgit v1.2.3 From 0fa8266294754978da34d7ea785d621f51d939f2 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Fri, 25 Jun 2021 10:52:10 +0530 Subject: soc: qcom: geni: Add support for gpi dma GPI DMA is one of the DMA modes supported on geni, this adds support to enable that mode Also do better documentation of the enum geni_se_xfer_mode. Signed-off-by: Vinod Koul Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/20210625052213.32260-3-vkoul@kernel.org Signed-off-by: Bjorn Andersson --- drivers/soc/qcom/qcom-geni-se.c | 29 ++++++++++++++++++++++++++++- include/linux/qcom-geni-se.h | 15 ++++++++++++++- 2 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c index fe666ea0c487..7d649d2cf31e 100644 --- a/drivers/soc/qcom/qcom-geni-se.c +++ b/drivers/soc/qcom/qcom-geni-se.c @@ -321,6 +321,30 @@ static void geni_se_select_dma_mode(struct geni_se *se) writel_relaxed(val, se->base + SE_GENI_DMA_MODE_EN); } +static void geni_se_select_gpi_mode(struct geni_se *se) +{ + u32 val; + + geni_se_irq_clear(se); + + writel(0, se->base + SE_IRQ_EN); + + val = readl(se->base + SE_GENI_S_IRQ_EN); + val &= ~S_CMD_DONE_EN; + writel(val, se->base + SE_GENI_S_IRQ_EN); + + val = readl(se->base + SE_GENI_M_IRQ_EN); + val &= ~(M_CMD_DONE_EN | M_TX_FIFO_WATERMARK_EN | + M_RX_FIFO_WATERMARK_EN | M_RX_FIFO_LAST_EN); + writel(val, se->base + SE_GENI_M_IRQ_EN); + + writel(GENI_DMA_MODE_EN, se->base + SE_GENI_DMA_MODE_EN); + + val = readl(se->base + SE_GSI_EVENT_EN); + val |= (DMA_RX_EVENT_EN | DMA_TX_EVENT_EN | GENI_M_EVENT_EN | GENI_S_EVENT_EN); + writel(val, se->base + SE_GSI_EVENT_EN); +} + /** * geni_se_select_mode() - Select the serial engine transfer mode * @se: Pointer to the concerned serial engine. @@ -328,7 +352,7 @@ static void geni_se_select_dma_mode(struct geni_se *se) */ void geni_se_select_mode(struct geni_se *se, enum geni_se_xfer_mode mode) { - WARN_ON(mode != GENI_SE_FIFO && mode != GENI_SE_DMA); + WARN_ON(mode != GENI_SE_FIFO && mode != GENI_SE_DMA && mode != GENI_GPI_DMA); switch (mode) { case GENI_SE_FIFO: @@ -337,6 +361,9 @@ void geni_se_select_mode(struct geni_se *se, enum geni_se_xfer_mode mode) case GENI_SE_DMA: geni_se_select_dma_mode(se); break; + case GENI_GPI_DMA: + geni_se_select_gpi_mode(se); + break; case GENI_SE_INVALID: default: break; diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 5114e2144b17..f5672785c0c4 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -8,11 +8,24 @@ #include -/* Transfer mode supported by GENI Serial Engines */ +/** + * enum geni_se_xfer_mode: Transfer modes supported by Serial Engines + * + * @GENI_SE_INVALID: Invalid mode + * @GENI_SE_FIFO: FIFO mode. Data is transferred with SE FIFO + * by programmed IO method + * @GENI_SE_DMA: Serial Engine DMA mode. Data is transferred + * with SE by DMAengine internal to SE + * @GENI_GPI_DMA: GPI DMA mode. Data is transferred using a DMAengine + * configured by a firmware residing on a GSI engine. This DMA name is + * interchangeably used as GSI or GPI which seem to imply the same DMAengine + */ + enum geni_se_xfer_mode { GENI_SE_INVALID, GENI_SE_FIFO, GENI_SE_DMA, + GENI_GPI_DMA, }; /* Protocols supported by GENI Serial Engines */ -- cgit v1.2.3 From e6a1f7e0b0fe5997b896b793c70d12fc5ed06cdd Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 4 Aug 2021 16:18:50 -0500 Subject: net/ipv4/igmp: Use struct_size() helper Replace IP_SFLSIZE() with struct_size() helper in order to avoid any potential type mistakes or integer overflows that, in the worst scenario, could lead to heap overflows. Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- include/linux/igmp.h | 3 --- net/ipv4/igmp.c | 20 +++++++++++++------- 2 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 64ce8cd1cfaf..93c262ecbdc9 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -41,9 +41,6 @@ struct ip_sf_socklist { __be32 sl_addr[]; }; -#define IP_SFLSIZE(count) (sizeof(struct ip_sf_socklist) + \ - (count) * sizeof(__be32)) - #define IP_SFBLOCK 10 /* allocate this many at once */ /* ip_mc_socklist is real list now. Speed is not argument; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c2d477eb6825..7e5072722f05 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2233,7 +2233,7 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, iml->sfmode, psf->sl_count, psf->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ - atomic_sub(IP_SFLSIZE(psf->sl_max), &sk->sk_omem_alloc); + atomic_sub(struct_size(psf, sl_addr, psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); return err; } @@ -2382,7 +2382,8 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct if (psl) count += psl->sl_max; - newpsl = sock_kmalloc(sk, IP_SFLSIZE(count), GFP_KERNEL); + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), + GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; @@ -2393,7 +2394,8 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ - atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } rcu_assign_pointer(pmc->sflist, newpsl); @@ -2468,8 +2470,9 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) goto done; } if (msf->imsf_numsrc) { - newpsl = sock_kmalloc(sk, IP_SFLSIZE(msf->imsf_numsrc), - GFP_KERNEL); + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, + msf->imsf_numsrc), + GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; @@ -2480,7 +2483,9 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { - sock_kfree_s(sk, newpsl, IP_SFLSIZE(newpsl->sl_max)); + sock_kfree_s(sk, newpsl, + struct_size(newpsl, sl_addr, + newpsl->sl_max)); goto done; } } else { @@ -2493,7 +2498,8 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ - atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } else (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, -- cgit v1.2.3 From 0092a1e3f7636ff4e202a41b0320690699247e22 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Mon, 2 Aug 2021 10:42:46 +0530 Subject: bus: mhi: Add inbound buffers allocation flag Currently, the MHI controller driver defines which channels should have their inbound buffers allocated and queued. But ideally, this is something that should be decided by the MHI device driver instead, which actually deals with that buffers. Add a flag parameter to mhi_prepare_for_transfer allowing to specify if buffers have to be allocated and queued by the MHI stack. Keep auto_queue flag for now, but should be removed at some point. Link: https://lore.kernel.org/r/1624566520-20406-1-git-send-email-loic.poulain@linaro.org Tested-by: Bhaumik Bhatt Reviewed-by: Bhaumik Bhatt Reviewed-by: Hemant Kumar Reviewed-by: Manivannan Sadhasivam Acked-by: Jakub Kicinski Signed-off-by: Loic Poulain Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20210802051255.5771-2-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/bus/mhi/core/internal.h | 2 +- drivers/bus/mhi/core/main.c | 9 ++++++--- drivers/net/mhi/net.c | 2 +- drivers/net/wwan/mhi_wwan_ctrl.c | 2 +- include/linux/mhi.h | 7 ++++++- net/qrtr/mhi.c | 2 +- 6 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h index 5b9ea66b92dc..bc239a11aa69 100644 --- a/drivers/bus/mhi/core/internal.h +++ b/drivers/bus/mhi/core/internal.h @@ -682,7 +682,7 @@ void mhi_rddm_prepare(struct mhi_controller *mhi_cntrl, struct image_info *img_info); void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl); int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan); + struct mhi_chan *mhi_chan, unsigned int flags); int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan); void mhi_deinit_chan_ctxt(struct mhi_controller *mhi_cntrl, diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index fc9196f11cb7..26bbc812121d 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -1430,7 +1430,7 @@ exit_unprepare_channel: } int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan) + struct mhi_chan *mhi_chan, unsigned int flags) { int ret = 0; struct device *dev = &mhi_chan->mhi_dev->dev; @@ -1455,6 +1455,9 @@ int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, if (ret) goto error_pm_state; + if (mhi_chan->dir == DMA_FROM_DEVICE) + mhi_chan->pre_alloc = !!(flags & MHI_CH_INBOUND_ALLOC_BUFS); + /* Pre-allocate buffer for xfer ring */ if (mhi_chan->pre_alloc) { int nr_el = get_nr_avail_ring_elements(mhi_cntrl, @@ -1610,7 +1613,7 @@ void mhi_reset_chan(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan) } /* Move channel to start state */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags) { int ret, dir; struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl; @@ -1621,7 +1624,7 @@ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) if (!mhi_chan) continue; - ret = mhi_prepare_channel(mhi_cntrl, mhi_chan); + ret = mhi_prepare_channel(mhi_cntrl, mhi_chan, flags); if (ret) goto error_open_chan; } diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index e60e38c1f09d..11be6bcdd551 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -335,7 +335,7 @@ static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id, u64_stats_init(&mhi_netdev->stats.tx_syncp); /* Start MHI channels */ - err = mhi_prepare_for_transfer(mhi_dev); + err = mhi_prepare_for_transfer(mhi_dev, 0); if (err) goto out_err; diff --git a/drivers/net/wwan/mhi_wwan_ctrl.c b/drivers/net/wwan/mhi_wwan_ctrl.c index 1bc6b69aa530..1e18420ce404 100644 --- a/drivers/net/wwan/mhi_wwan_ctrl.c +++ b/drivers/net/wwan/mhi_wwan_ctrl.c @@ -110,7 +110,7 @@ static int mhi_wwan_ctrl_start(struct wwan_port *port) int ret; /* Start mhi device's channel(s) */ - ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev); + ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev, 0); if (ret) return ret; diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 944aa3aa3035..5e08468854db 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -719,8 +719,13 @@ void mhi_device_put(struct mhi_device *mhi_dev); * host and device execution environments match and * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels + * @flags: MHI channel flags */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, + unsigned int flags); + +/* Automatically allocate and queue inbound buffers */ +#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0) /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c index fa611678af05..29b4fa3b72ab 100644 --- a/net/qrtr/mhi.c +++ b/net/qrtr/mhi.c @@ -79,7 +79,7 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, int rc; /* start channels */ - rc = mhi_prepare_for_transfer(mhi_dev); + rc = mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS); if (rc) return rc; -- cgit v1.2.3 From baa7a08569358d9d16e71ce36f287c39a665d776 Mon Sep 17 00:00:00 2001 From: Bhaumik Bhatt Date: Mon, 2 Aug 2021 10:42:50 +0530 Subject: bus: mhi: Add MMIO region length to controller structure Make controller driver specify the MMIO register region length for range checking of BHI or BHIe space. This can help validate that offsets are in acceptable memory region or not and avoid any boot-up issues due to BHI or BHIe memory accesses. Link: https://lore.kernel.org/r/1620330705-40192-4-git-send-email-bbhatt@codeaurora.org Reviewed-by: Jeffrey Hugo Reviewed-by: Hemant Kumar Reviewed-by: Manivannan Sadhasivam Signed-off-by: Bhaumik Bhatt Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20210802051255.5771-6-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 5e08468854db..b8ca6943f0b7 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -303,6 +303,7 @@ struct mhi_controller_config { * @rddm_size: RAM dump size that host should allocate for debugging purpose * @sbl_size: SBL image size downloaded through BHIe (optional) * @seg_len: BHIe vector size (optional) + * @reg_len: Length of the MHI MMIO region (required) * @fbc_image: Points to firmware image buffer * @rddm_image: Points to RAM dump buffer * @mhi_chan: Points to the channel configuration table @@ -386,6 +387,7 @@ struct mhi_controller { size_t rddm_size; size_t sbl_size; size_t seg_len; + size_t reg_len; struct image_info *fbc_image; struct image_info *rddm_image; struct mhi_chan *mhi_chan; -- cgit v1.2.3 From b37a466837393af72fe8bcb8f1436410f3f173f3 Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Thu, 5 Aug 2021 19:54:34 +0800 Subject: netdevice: add the case if dev is NULL Add the case if dev is NULL in dev_{put, hold}, so the caller doesn't need to care whether dev is NULL or not. Signed-off-by: Yajun Deng Signed-off-by: David S. Miller --- include/linux/netdevice.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1b4d4509d04b..135c943699d0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4143,11 +4143,13 @@ void netdev_run_todo(void); */ static inline void dev_put(struct net_device *dev) { + if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT - this_cpu_dec(*dev->pcpu_refcnt); + this_cpu_dec(*dev->pcpu_refcnt); #else - refcount_dec(&dev->dev_refcnt); + refcount_dec(&dev->dev_refcnt); #endif + } } /** @@ -4158,11 +4160,13 @@ static inline void dev_put(struct net_device *dev) */ static inline void dev_hold(struct net_device *dev) { + if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT - this_cpu_inc(*dev->pcpu_refcnt); + this_cpu_inc(*dev->pcpu_refcnt); #else - refcount_inc(&dev->dev_refcnt); + refcount_inc(&dev->dev_refcnt); #endif + } } /* Carrier loss detection, dial on demand. The functions netif_carrier_on -- cgit v1.2.3 From fac58b4a5287c9d37c39d09d9bdc80846b744649 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Fri, 30 Jul 2021 21:10:35 +0200 Subject: zorro: Drop useless (and hardly used) .driver member in struct zorro_dev MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The only actual use is to check in zorro_device_probe() that the device isn't already bound. The driver core already ensures this however so the check can go away which allows to drop the then assigned-only member from struct zorro_dev. If the value was indeed needed somewhere it can always be calculated by to_zorro_driver(z->dev.driver) . Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210730191035.1455248-5-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/zorro/zorro-driver.c | 7 ++----- include/linux/zorro.h | 1 - 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/zorro/zorro-driver.c b/drivers/zorro/zorro-driver.c index ab06c9ce2c78..96f068830549 100644 --- a/drivers/zorro/zorro-driver.c +++ b/drivers/zorro/zorro-driver.c @@ -47,16 +47,14 @@ static int zorro_device_probe(struct device *dev) struct zorro_driver *drv = to_zorro_driver(dev->driver); struct zorro_dev *z = to_zorro_dev(dev); - if (!z->driver && drv->probe) { + if (drv->probe) { const struct zorro_device_id *id; id = zorro_match_device(drv->id_table, z); if (id) error = drv->probe(z, id); - if (error >= 0) { - z->driver = drv; + if (error >= 0) error = 0; - } } return error; } @@ -69,7 +67,6 @@ static void zorro_device_remove(struct device *dev) if (drv->remove) drv->remove(z); - z->driver = NULL; } diff --git a/include/linux/zorro.h b/include/linux/zorro.h index e2e4de188d84..db7416ed6057 100644 --- a/include/linux/zorro.h +++ b/include/linux/zorro.h @@ -29,7 +29,6 @@ struct zorro_dev { struct ExpansionRom rom; zorro_id id; - struct zorro_driver *driver; /* which driver has allocated this device */ struct device dev; /* Generic device interface */ u16 slotaddr; u16 slotsize; -- cgit v1.2.3 From 93bb8e352a9136a56dd26762bf54cf6554cfa96c Mon Sep 17 00:00:00 2001 From: Krzysztof Wilczyński Date: Thu, 29 Jul 2021 23:32:34 +0000 Subject: sysfs: Invoke iomem_get_mapping() from the sysfs open callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Defer invocation of the iomem_get_mapping() to the sysfs open callback so that it can be executed as needed when the binary sysfs object has been accessed. To do that, convert the "mapping" member of the struct bin_attribute from a pointer to the struct address_space into a function pointer with a signature that requires the same return type, and then updates the sysfs_kf_bin_open() to invoke provided function should the function pointer be valid. Also, convert every invocation of iomem_get_mapping() into a function pointer assignment, therefore allowing for the iomem_get_mapping() invocation to be deferred to when the sysfs open callback runs. Thus, this change removes the need for the fs_initcalls to complete before any other sub-system that uses the iomem_get_mapping() would be able to invoke it safely without leading to a failure and an Oops related to an invalid iomem_get_mapping() access. Suggested-by: Dan Williams Reviewed-by: Dan Williams Acked-by: Bjorn Helgaas Signed-off-by: Dan Williams Signed-off-by: Krzysztof Wilczyński Link: https://lore.kernel.org/r/20210729233235.1508920-2-kw@linux.com Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci-sysfs.c | 6 +++--- fs/sysfs/file.c | 2 +- include/linux/sysfs.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 5d63df7c1820..76e5545d0e73 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -965,7 +965,7 @@ void pci_create_legacy_files(struct pci_bus *b) b->legacy_io->read = pci_read_legacy_io; b->legacy_io->write = pci_write_legacy_io; b->legacy_io->mmap = pci_mmap_legacy_io; - b->legacy_io->mapping = iomem_get_mapping(); + b->legacy_io->mapping = iomem_get_mapping; pci_adjust_legacy_attr(b, pci_mmap_io); error = device_create_bin_file(&b->dev, b->legacy_io); if (error) @@ -978,7 +978,7 @@ void pci_create_legacy_files(struct pci_bus *b) b->legacy_mem->size = 1024*1024; b->legacy_mem->attr.mode = 0600; b->legacy_mem->mmap = pci_mmap_legacy_mem; - b->legacy_io->mapping = iomem_get_mapping(); + b->legacy_io->mapping = iomem_get_mapping; pci_adjust_legacy_attr(b, pci_mmap_mem); error = device_create_bin_file(&b->dev, b->legacy_mem); if (error) @@ -1195,7 +1195,7 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine) } } if (res_attr->mmap) - res_attr->mapping = iomem_get_mapping(); + res_attr->mapping = iomem_get_mapping; res_attr->attr.name = res_attr_name; res_attr->attr.mode = 0600; res_attr->size = pci_resource_len(pdev, num); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 9aefa7779b29..a3ee4c32a264 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -175,7 +175,7 @@ static int sysfs_kf_bin_open(struct kernfs_open_file *of) struct bin_attribute *battr = of->kn->priv; if (battr->mapping) - of->file->f_mapping = battr->mapping; + of->file->f_mapping = battr->mapping(); return 0; } diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index a12556a4b93a..d5bcc897583c 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -176,7 +176,7 @@ struct bin_attribute { struct attribute attr; size_t size; void *private; - struct address_space *mapping; + struct address_space *(*mapping)(void); ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *, -- cgit v1.2.3 From f06aff924f975881a6abf91d2af0078fc8cd37bf Mon Sep 17 00:00:00 2001 From: Krzysztof Wilczyński Date: Thu, 29 Jul 2021 23:32:35 +0000 Subject: sysfs: Rename struct bin_attribute member to f_mapping MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are two users of iomem_get_mapping(), the struct file and struct bin_attribute. The former has a member called "f_mapping" and the latter has a member called "mapping", and both are poniters to struct address_space. Rename struct bin_attribute member to "f_mapping" to keep both meaning and the usage consistent with other users of iomem_get_mapping(). Acked-by: Bjorn Helgaas Signed-off-by: Krzysztof Wilczyński Link: https://lore.kernel.org/r/20210729233235.1508920-3-kw@linux.com Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci-sysfs.c | 6 +++--- fs/sysfs/file.c | 4 ++-- include/linux/sysfs.h | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 76e5545d0e73..f65382915f01 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -965,7 +965,7 @@ void pci_create_legacy_files(struct pci_bus *b) b->legacy_io->read = pci_read_legacy_io; b->legacy_io->write = pci_write_legacy_io; b->legacy_io->mmap = pci_mmap_legacy_io; - b->legacy_io->mapping = iomem_get_mapping; + b->legacy_io->f_mapping = iomem_get_mapping; pci_adjust_legacy_attr(b, pci_mmap_io); error = device_create_bin_file(&b->dev, b->legacy_io); if (error) @@ -978,7 +978,7 @@ void pci_create_legacy_files(struct pci_bus *b) b->legacy_mem->size = 1024*1024; b->legacy_mem->attr.mode = 0600; b->legacy_mem->mmap = pci_mmap_legacy_mem; - b->legacy_io->mapping = iomem_get_mapping; + b->legacy_io->f_mapping = iomem_get_mapping; pci_adjust_legacy_attr(b, pci_mmap_mem); error = device_create_bin_file(&b->dev, b->legacy_mem); if (error) @@ -1195,7 +1195,7 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine) } } if (res_attr->mmap) - res_attr->mapping = iomem_get_mapping; + res_attr->f_mapping = iomem_get_mapping; res_attr->attr.name = res_attr_name; res_attr->attr.mode = 0600; res_attr->size = pci_resource_len(pdev, num); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index a3ee4c32a264..d019d6ac6ad0 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -174,8 +174,8 @@ static int sysfs_kf_bin_open(struct kernfs_open_file *of) { struct bin_attribute *battr = of->kn->priv; - if (battr->mapping) - of->file->f_mapping = battr->mapping(); + if (battr->f_mapping) + of->file->f_mapping = battr->f_mapping(); return 0; } diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index d5bcc897583c..e3f1e8ac1f85 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -176,7 +176,7 @@ struct bin_attribute { struct attribute attr; size_t size; void *private; - struct address_space *(*mapping)(void); + struct address_space *(*f_mapping)(void); ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *, -- cgit v1.2.3 From 8c33ebfeeb597ea953df93f84ea25482d29c664f Mon Sep 17 00:00:00 2001 From: Mason Zhang Date: Wed, 4 Aug 2021 21:37:17 +0800 Subject: spi: move cs spi_delay to spi_device As we know, spi core layer has removed spi_set_cs_timing() API. So this patch moved spi_delay for cs_timing from spi_controller to spi_device, because cs timing should be set by spi_device but not controller. Signed-off-by: Mason Zhang Link: https://lore.kernel.org/r/20210804133716.32040-1-Mason.Zhang@mediatek.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 6 +++--- include/linux/spi/spi.h | 20 +++++++++----------- 2 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index c99181165321..5d68e6cd2a18 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -842,9 +842,9 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force) if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio) || !spi->controller->set_cs_timing) { if (activate) - spi_delay_exec(&spi->controller->cs_setup, NULL); + spi_delay_exec(&spi->cs_setup, NULL); else - spi_delay_exec(&spi->controller->cs_hold, NULL); + spi_delay_exec(&spi->cs_hold, NULL); } if (spi->mode & SPI_CS_HIGH) @@ -887,7 +887,7 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force) if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio) || !spi->controller->set_cs_timing) { if (!activate) - spi_delay_exec(&spi->controller->cs_inactive, NULL); + spi_delay_exec(&spi->cs_inactive, NULL); } } diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 3a81b5d1c3cb..1efe2e08957e 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -147,7 +147,11 @@ extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); * not using a GPIO line) * @word_delay: delay to be inserted between consecutive * words of a transfer - * + * @cs_setup: delay to be introduced by the controller after CS is asserted + * @cs_hold: delay to be introduced by the controller before CS is deasserted + * @cs_inactive: delay to be introduced by the controller after CS is + * deasserted. If @cs_change_delay is used from @spi_transfer, then the + * two delays will be added up. * @statistics: statistics for the spi_device * * A @spi_device is used to interchange data between an SPI slave @@ -188,6 +192,10 @@ struct spi_device { int cs_gpio; /* LEGACY: chip select gpio */ struct gpio_desc *cs_gpiod; /* chip select gpio desc */ struct spi_delay word_delay; /* inter-word delay */ + /* CS delays */ + struct spi_delay cs_setup; + struct spi_delay cs_hold; + struct spi_delay cs_inactive; /* the statistics */ struct spi_statistics statistics; @@ -413,11 +421,6 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * controller has native support for memory like operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller - * @cs_setup: delay to be introduced by the controller after CS is asserted - * @cs_hold: delay to be introduced by the controller before CS is deasserted - * @cs_inactive: delay to be introduced by the controller after CS is - * deasserted. If @cs_change_delay is used from @spi_transfer, then the - * two delays will be added up. * @cs_gpios: LEGACY: array of GPIO descs to use as chip select lines; one per * CS number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). Use the cs_gpiods @@ -639,11 +642,6 @@ struct spi_controller { /* Optimized handlers for SPI memory-like operations. */ const struct spi_controller_mem_ops *mem_ops; - /* CS delays */ - struct spi_delay cs_setup; - struct spi_delay cs_hold; - struct spi_delay cs_inactive; - /* gpio chip select */ int *cs_gpios; struct gpio_desc **cs_gpiods; -- cgit v1.2.3 From 04e6bb0d6bb127bac929fb35edd2dd01613c9520 Mon Sep 17 00:00:00 2001 From: Mason Zhang Date: Wed, 4 Aug 2021 21:37:47 +0800 Subject: spi: modify set_cs_timing parameter This patch modified set_cs_timing parameter, no need pass in spi_delay to set_cs_timing callback. By the way, we modified the mediatek and tegra114 spi driver to fix build err. In mediatek spi driver, We have support set absolute time not clk_count, and call this function in prepare_message not user's API. Signed-off-by: Mason Zhang Link: https://lore.kernel.org/r/20210804133746.6742-1-Mason.Zhang@mediatek.com Signed-off-by: Mark Brown --- drivers/spi/spi-mt65xx.c | 107 ++++++++++++++++++++++++++------------------- drivers/spi/spi-tegra114.c | 8 ++-- include/linux/spi/spi.h | 3 +- 3 files changed, 66 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index b34fbc913fd6..20569c4c1fb6 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -208,6 +208,65 @@ static void mtk_spi_reset(struct mtk_spi *mdata) writel(reg_val, mdata->base + SPI_CMD_REG); } +static int mtk_spi_set_hw_cs_timing(struct spi_device *spi) +{ + struct mtk_spi *mdata = spi_master_get_devdata(spi->master); + struct spi_delay *cs_setup = &spi->cs_setup; + struct spi_delay *cs_hold = &spi->cs_hold; + struct spi_delay *cs_inactive = &spi->cs_inactive; + u16 setup, hold, inactive; + u32 reg_val; + int delay; + + delay = spi_delay_to_ns(cs_setup, NULL); + if (delay < 0) + return delay; + setup = (delay * DIV_ROUND_UP(mdata->spi_clk_hz, 1000000)) / 1000; + + delay = spi_delay_to_ns(cs_hold, NULL); + if (delay < 0) + return delay; + hold = (delay * DIV_ROUND_UP(mdata->spi_clk_hz, 1000000)) / 1000; + + delay = spi_delay_to_ns(cs_inactive, NULL); + if (delay < 0) + return delay; + inactive = (delay * DIV_ROUND_UP(mdata->spi_clk_hz, 1000000)) / 1000; + + setup = setup ? setup : 1; + hold = hold ? hold : 1; + inactive = inactive ? inactive : 1; + + reg_val = readl(mdata->base + SPI_CFG0_REG); + if (mdata->dev_comp->enhance_timing) { + hold = min(hold, 0xffff); + setup = min(setup, 0xffff); + reg_val &= ~(0xffff << SPI_ADJUST_CFG0_CS_HOLD_OFFSET); + reg_val |= (((hold - 1) & 0xffff) + << SPI_ADJUST_CFG0_CS_HOLD_OFFSET); + reg_val &= ~(0xffff << SPI_ADJUST_CFG0_CS_SETUP_OFFSET); + reg_val |= (((setup - 1) & 0xffff) + << SPI_ADJUST_CFG0_CS_SETUP_OFFSET); + } else { + hold = min(hold, 0xff); + setup = min(setup, 0xff); + reg_val &= ~(0xff << SPI_CFG0_CS_HOLD_OFFSET); + reg_val |= (((hold - 1) & 0xff) << SPI_CFG0_CS_HOLD_OFFSET); + reg_val &= ~(0xff << SPI_CFG0_CS_SETUP_OFFSET); + reg_val |= (((setup - 1) & 0xff) + << SPI_CFG0_CS_SETUP_OFFSET); + } + writel(reg_val, mdata->base + SPI_CFG0_REG); + + inactive = min(inactive, 0xff); + reg_val = readl(mdata->base + SPI_CFG1_REG); + reg_val &= ~SPI_CFG1_CS_IDLE_MASK; + reg_val |= (((inactive - 1) & 0xff) << SPI_CFG1_CS_IDLE_OFFSET); + writel(reg_val, mdata->base + SPI_CFG1_REG); + + return 0; +} + static int mtk_spi_prepare_message(struct spi_master *master, struct spi_message *msg) { @@ -284,6 +343,8 @@ static int mtk_spi_prepare_message(struct spi_master *master, << SPI_CFG1_GET_TICK_DLY_OFFSET); writel(reg_val, mdata->base + SPI_CFG1_REG); + /* set hw cs timing */ + mtk_spi_set_hw_cs_timing(spi); return 0; } @@ -528,52 +589,6 @@ static bool mtk_spi_can_dma(struct spi_master *master, (unsigned long)xfer->rx_buf % 4 == 0); } -static int mtk_spi_set_hw_cs_timing(struct spi_device *spi, - struct spi_delay *setup, - struct spi_delay *hold, - struct spi_delay *inactive) -{ - struct mtk_spi *mdata = spi_master_get_devdata(spi->master); - u16 setup_dly, hold_dly, inactive_dly; - u32 reg_val; - - if ((setup && setup->unit != SPI_DELAY_UNIT_SCK) || - (hold && hold->unit != SPI_DELAY_UNIT_SCK) || - (inactive && inactive->unit != SPI_DELAY_UNIT_SCK)) { - dev_err(&spi->dev, - "Invalid delay unit, should be SPI_DELAY_UNIT_SCK\n"); - return -EINVAL; - } - - setup_dly = setup ? setup->value : 1; - hold_dly = hold ? hold->value : 1; - inactive_dly = inactive ? inactive->value : 1; - - reg_val = readl(mdata->base + SPI_CFG0_REG); - if (mdata->dev_comp->enhance_timing) { - reg_val &= ~(0xffff << SPI_ADJUST_CFG0_CS_HOLD_OFFSET); - reg_val |= (((hold_dly - 1) & 0xffff) - << SPI_ADJUST_CFG0_CS_HOLD_OFFSET); - reg_val &= ~(0xffff << SPI_ADJUST_CFG0_CS_SETUP_OFFSET); - reg_val |= (((setup_dly - 1) & 0xffff) - << SPI_ADJUST_CFG0_CS_SETUP_OFFSET); - } else { - reg_val &= ~(0xff << SPI_CFG0_CS_HOLD_OFFSET); - reg_val |= (((hold_dly - 1) & 0xff) << SPI_CFG0_CS_HOLD_OFFSET); - reg_val &= ~(0xff << SPI_CFG0_CS_SETUP_OFFSET); - reg_val |= (((setup_dly - 1) & 0xff) - << SPI_CFG0_CS_SETUP_OFFSET); - } - writel(reg_val, mdata->base + SPI_CFG0_REG); - - reg_val = readl(mdata->base + SPI_CFG1_REG); - reg_val &= ~SPI_CFG1_CS_IDLE_MASK; - reg_val |= (((inactive_dly - 1) & 0xff) << SPI_CFG1_CS_IDLE_OFFSET); - writel(reg_val, mdata->base + SPI_CFG1_REG); - - return 0; -} - static int mtk_spi_setup(struct spi_device *spi) { struct mtk_spi *mdata = spi_master_get_devdata(spi->master); diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c index 5131141bbf0d..e9de1d958bbd 100644 --- a/drivers/spi/spi-tegra114.c +++ b/drivers/spi/spi-tegra114.c @@ -717,12 +717,12 @@ static void tegra_spi_deinit_dma_param(struct tegra_spi_data *tspi, dma_release_channel(dma_chan); } -static int tegra_spi_set_hw_cs_timing(struct spi_device *spi, - struct spi_delay *setup, - struct spi_delay *hold, - struct spi_delay *inactive) +static int tegra_spi_set_hw_cs_timing(struct spi_device *spi) { struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master); + struct spi_delay *setup = &spi->cs_setup; + struct spi_delay *hold = &spi->cs_hold; + struct spi_delay *inactive = &spi->cs_inactive; u8 setup_dly, hold_dly, inactive_dly; u32 setup_hold; u32 spi_cs_timing; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 1efe2e08957e..8371bca13729 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -554,8 +554,7 @@ struct spi_controller { * to configure specific CS timing through spi_set_cs_timing() after * spi_setup(). */ - int (*set_cs_timing)(struct spi_device *spi, struct spi_delay *setup, - struct spi_delay *hold, struct spi_delay *inactive); + int (*set_cs_timing)(struct spi_device *spi); /* bidirectional bulk transfers * -- cgit v1.2.3 From 90b7198001f23ea37d3b46dc631bdaa2357a20b1 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 5 Aug 2021 10:41:59 -0700 Subject: blk-mq: Introduce the BLK_MQ_F_NO_SCHED_BY_DEFAULT flag elevator_get_default() uses the following algorithm to select an I/O scheduler from inside add_disk(): - In case of a single hardware queue or if sharing hardware queues across multiple request queues (BLK_MQ_F_TAG_HCTX_SHARED), use mq-deadline. - Otherwise, use 'none'. This is a good choice for most but not for all block drivers. Make it possible to override the selection of mq-deadline with a new flag, namely BLK_MQ_F_NO_SCHED_BY_DEFAULT. Cc: Christoph Hellwig Cc: Ming Lei Cc: Tetsuo Handa Cc: Martijn Coenen Cc: Jaegeuk Kim Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20210805174200.3250718-2-bvanassche@acm.org Signed-off-by: Jens Axboe --- block/elevator.c | 3 +++ include/linux/blk-mq.h | 6 ++++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/block/elevator.c b/block/elevator.c index 52ada14cfe45..d0295e68f481 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -630,6 +630,9 @@ static inline bool elv_support_iosched(struct request_queue *q) */ static struct elevator_type *elevator_get_default(struct request_queue *q) { + if (q->tag_set && q->tag_set->flags & BLK_MQ_F_NO_SCHED_BY_DEFAULT) + return NULL; + if (q->nr_hw_queues != 1 && !blk_mq_is_sbitmap_shared(q->tag_set->flags)) return NULL; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 1d18447ebebc..22215db36122 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -404,7 +404,13 @@ enum { BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 5, + /* Do not allow an I/O scheduler to be configured. */ BLK_MQ_F_NO_SCHED = 1 << 6, + /* + * Select 'none' during queue registration in case of a single hwq + * or shared hwqs instead of 'mq-deadline'. + */ + BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 7, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, BLK_MQ_F_ALLOC_POLICY_BITS = 1, -- cgit v1.2.3 From a065d5615fc83908ef21ed8159ffb63d816ff5de Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 28 Jul 2021 16:42:27 +0200 Subject: of: unify of_count_phandle_with_args() arguments with !CONFIG_OF Unify the declaration of of_count_phandle_with_args() between enabled and disabled OF by making constifying pointed device_node. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Signed-off-by: Bartosz Golaszewski --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 9c2e71e202d1..dfeb065c3fad 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -896,7 +896,7 @@ static inline int of_parse_phandle_with_fixed_args(const struct device_node *np, return -ENOSYS; } -static inline int of_count_phandle_with_args(struct device_node *np, +static inline int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name) { -- cgit v1.2.3 From e6ae9a833ef4043b940954b8dcac31493706b9d6 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 28 Jul 2021 16:42:28 +0200 Subject: gpiolib: constify passed device_node pointer Several gpiolib functions receive pointer to struct device_node which is later passed to OF functions. These OF functions accept already pointer to const, so gpiolib can follow similar approach to indicate they are not modifying the struct device_node. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib-devres.c | 2 +- drivers/gpio/gpiolib-of.c | 8 ++++---- include/linux/gpio/consumer.h | 8 ++++---- include/linux/of_gpio.h | 15 ++++++++------- 4 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c index 4a517e5dedf0..79da85d17b71 100644 --- a/drivers/gpio/gpiolib-devres.c +++ b/drivers/gpio/gpiolib-devres.c @@ -145,7 +145,7 @@ EXPORT_SYMBOL_GPL(devm_gpiod_get_index); * In case of error an ERR_PTR() is returned. */ struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, - struct device_node *node, + const struct device_node *node, const char *propname, int index, enum gpiod_flags dflags, const char *label) diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index bbcc7c073f63..1e5a6f63b2fe 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -130,7 +130,7 @@ bool of_gpio_need_valid_mask(const struct gpio_chip *gc) return false; } -static void of_gpio_flags_quirks(struct device_node *np, +static void of_gpio_flags_quirks(const struct device_node *np, const char *propname, enum of_gpio_flags *flags, int index) @@ -236,7 +236,7 @@ static void of_gpio_flags_quirks(struct device_node *np, * value on the error condition. If @flags is not NULL the function also fills * in flags for the GPIO. */ -static struct gpio_desc *of_get_named_gpiod_flags(struct device_node *np, +static struct gpio_desc *of_get_named_gpiod_flags(const struct device_node *np, const char *propname, int index, enum of_gpio_flags *flags) { struct of_phandle_args gpiospec; @@ -275,7 +275,7 @@ out: return desc; } -int of_get_named_gpio_flags(struct device_node *np, const char *list_name, +int of_get_named_gpio_flags(const struct device_node *np, const char *list_name, int index, enum of_gpio_flags *flags) { struct gpio_desc *desc; @@ -303,7 +303,7 @@ EXPORT_SYMBOL_GPL(of_get_named_gpio_flags); * * In case of error an ERR_PTR() is returned. */ -struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, +struct gpio_desc *gpiod_get_from_of_node(const struct device_node *node, const char *propname, int index, enum gpiod_flags dflags, const char *label) diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 566feb56601f..bf945b776555 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -609,7 +609,7 @@ struct gpio_desc *devm_fwnode_get_gpiod_from_child(struct device *dev, #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_OF_GPIO) struct device_node; -struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, +struct gpio_desc *gpiod_get_from_of_node(const struct device_node *node, const char *propname, int index, enum gpiod_flags dflags, const char *label); @@ -619,7 +619,7 @@ struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, struct device_node; static inline -struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, +struct gpio_desc *gpiod_get_from_of_node(const struct device_node *node, const char *propname, int index, enum gpiod_flags dflags, const char *label) @@ -633,7 +633,7 @@ struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, struct device_node; struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, - struct device_node *node, + const struct device_node *node, const char *propname, int index, enum gpiod_flags dflags, const char *label); @@ -644,7 +644,7 @@ struct device_node; static inline struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, - struct device_node *node, + const struct device_node *node, const char *propname, int index, enum gpiod_flags dflags, const char *label) diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index f821095218b0..8bf2ea859653 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -49,7 +49,7 @@ static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc) return container_of(gc, struct of_mm_gpio_chip, gc); } -extern int of_get_named_gpio_flags(struct device_node *np, +extern int of_get_named_gpio_flags(const struct device_node *np, const char *list_name, int index, enum of_gpio_flags *flags); extern int of_mm_gpiochip_add_data(struct device_node *np, @@ -67,7 +67,7 @@ extern void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc); #include /* Drivers may not strictly depend on the GPIO support, so let them link. */ -static inline int of_get_named_gpio_flags(struct device_node *np, +static inline int of_get_named_gpio_flags(const struct device_node *np, const char *list_name, int index, enum of_gpio_flags *flags) { if (flags) @@ -98,7 +98,8 @@ static inline int of_get_named_gpio_flags(struct device_node *np, * The above example defines four GPIOs, two of which are not specified. * This function will return '4' */ -static inline int of_gpio_named_count(struct device_node *np, const char* propname) +static inline int of_gpio_named_count(const struct device_node *np, + const char *propname) { return of_count_phandle_with_args(np, propname, "#gpio-cells"); } @@ -109,12 +110,12 @@ static inline int of_gpio_named_count(struct device_node *np, const char* propna * * Same as of_gpio_named_count, but hard coded to use the 'gpios' property */ -static inline int of_gpio_count(struct device_node *np) +static inline int of_gpio_count(const struct device_node *np) { return of_gpio_named_count(np, "gpios"); } -static inline int of_get_gpio_flags(struct device_node *np, int index, +static inline int of_get_gpio_flags(const struct device_node *np, int index, enum of_gpio_flags *flags) { return of_get_named_gpio_flags(np, "gpios", index, flags); @@ -129,7 +130,7 @@ static inline int of_get_gpio_flags(struct device_node *np, int index, * Returns GPIO number to use with Linux generic GPIO API, or one of the errno * value on the error condition. */ -static inline int of_get_named_gpio(struct device_node *np, +static inline int of_get_named_gpio(const struct device_node *np, const char *propname, int index) { return of_get_named_gpio_flags(np, propname, index, NULL); @@ -143,7 +144,7 @@ static inline int of_get_named_gpio(struct device_node *np, * Returns GPIO number to use with Linux generic GPIO API, or one of the errno * value on the error condition. */ -static inline int of_get_gpio(struct device_node *np, int index) +static inline int of_get_gpio(const struct device_node *np, int index) { return of_get_gpio_flags(np, index, NULL); } -- cgit v1.2.3 From 97a8a8c1f985baf13a3d0d252b787850330d2ea7 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 3 Aug 2021 16:19:46 -0700 Subject: net/mlx5: Return mdev from eswitch Export a function so users can retrieve the mellanox device that manages the eswitch from the eswitch device. Signed-off-by: Mark Bloch Reviewed-by: Mark Zhang Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 12 ++++++++++++ include/linux/mlx5/eswitch.h | 6 ++++++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 97e6cb6f13c1..b65a472067d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2384,3 +2384,15 @@ u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev) return mlx5_esw_allowed(esw) ? esw->total_vports : 0; } EXPORT_SYMBOL_GPL(mlx5_eswitch_get_total_vports); + +/** + * mlx5_eswitch_get_core_dev - Get the mdev device + * @esw : eswitch device. + * + * Return the mellanox core device which manages the eswitch. + */ +struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw) +{ + return mlx5_esw_allowed(esw) ? esw->dev : NULL; +} +EXPORT_SYMBOL(mlx5_eswitch_get_core_dev); diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index bc7db2e059eb..c2a34ff85188 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -128,6 +128,7 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); +struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ @@ -171,6 +172,11 @@ static inline u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev) return 0; } +static inline struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw) +{ + return NULL; +} + #endif /* CONFIG_MLX5_ESWITCH */ static inline bool is_mdev_switchdev_mode(struct mlx5_core_dev *dev) -- cgit v1.2.3 From af8c0e25f249abf8829f0cfa074b08d7398e3e38 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 3 Aug 2021 16:19:47 -0700 Subject: net/mlx5: Lag, add initial logic for shared FDB As shared FDB requires changes in two subsystems first expose the needed core functions so the RDMA side can be changed. mlx5_lag_is_master(): return true if a given mlx5 device is the lag master. mlx5_lag_is_shared_fdb(): Returns true if the lag mode is shared FDB. mlx5_lag_get_peer_mdev(): Return the peer mdev in lag. The mentioned functions will be used by downstream patches in order to add support for shared FDB for the RDMA side. Signed-off-by: Mark Bloch Reviewed-by: Mark Zhang Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lag.c | 49 +++++++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/lag.h | 1 + include/linux/mlx5/driver.h | 3 ++ 3 files changed, 53 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 5c043c5cc403..3049de648256 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -746,6 +746,21 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_lag_is_active); +bool mlx5_lag_is_master(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev; + bool res; + + spin_lock(&lag_lock); + ldev = mlx5_lag_dev(dev); + res = ldev && __mlx5_lag_is_active(ldev) && + dev == ldev->pf[MLX5_LAG_P1].dev; + spin_unlock(&lag_lock); + + return res; +} +EXPORT_SYMBOL(mlx5_lag_is_master); + bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; @@ -760,6 +775,20 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_lag_is_sriov); +bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev; + bool res; + + spin_lock(&lag_lock); + ldev = mlx5_lag_dev(dev); + res = ldev && __mlx5_lag_is_sriov(ldev) && ldev->shared_fdb; + spin_unlock(&lag_lock); + + return res; +} +EXPORT_SYMBOL(mlx5_lag_is_shared_fdb); + void mlx5_lag_update(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; @@ -827,6 +856,26 @@ unlock: } EXPORT_SYMBOL(mlx5_lag_get_slave_port); +struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev) +{ + struct mlx5_core_dev *peer_dev = NULL; + struct mlx5_lag *ldev; + + spin_lock(&lag_lock); + ldev = mlx5_lag_dev(dev); + if (!ldev) + goto unlock; + + peer_dev = ldev->pf[MLX5_LAG_P1].dev == dev ? + ldev->pf[MLX5_LAG_P2].dev : + ldev->pf[MLX5_LAG_P1].dev; + +unlock: + spin_unlock(&lag_lock); + return peer_dev; +} +EXPORT_SYMBOL(mlx5_lag_get_peer_mdev); + int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h index 191392c37558..70b244b1a09e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h @@ -39,6 +39,7 @@ struct lag_tracker { */ struct mlx5_lag { u8 flags; + bool shared_fdb; u8 v2p_map[MLX5_MAX_PORTS]; struct kref ref; struct lag_func pf[MLX5_MAX_PORTS]; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1efe37466969..af4dd6e9f97f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1138,6 +1138,8 @@ bool mlx5_lag_is_roce(struct mlx5_core_dev *dev); bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev); bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); +bool mlx5_lag_is_master(struct mlx5_core_dev *dev); +bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev); struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, struct net_device *slave); @@ -1145,6 +1147,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, size_t *offsets); +struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev); struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, -- cgit v1.2.3 From 979bf468fc543444eb750c8f8817407f509bd504 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 3 Aug 2021 16:19:49 -0700 Subject: {net, RDMA}/mlx5: Extend send to vport rules In shared FDB there is only one eswitch which is active and it receives traffic from all representors and all vports in the HCA. While the Ethernet representor will always reside on its native PF the IB representor will not. Extend send to vport rule creation to support such flows. Need to account for source vport that sends the traffic (on which the representors resides) and the target eswitch the traffic which reach. Signed-off-by: Mark Bloch Reviewed-by: Mark Zhang Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/ib_rep.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 5 +++-- include/linux/mlx5/eswitch.h | 1 + 4 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c index b25e0b33a11a..bf5a6e4d1c03 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -123,7 +123,7 @@ struct mlx5_flow_handle *create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, rep = dev->port[port - 1].rep; - return mlx5_eswitch_add_send_to_vport_rule(esw, rep, sq->base.mqp.qpn); + return mlx5_eswitch_add_send_to_vport_rule(esw, esw, rep, sq->base.mqp.qpn); } static int mlx5r_rep_probe(struct auxiliary_device *adev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index bf94bcb6fa5d..1d016cc64015 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -337,7 +337,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, } /* Add re-inject rule to the PF/representor sqs */ - flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw, rep, + flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw, esw, rep, sqns_array[i]); if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 7579f3402776..12567002997f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -925,6 +925,7 @@ out: struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, + struct mlx5_eswitch *from_esw, struct mlx5_eswitch_rep *rep, u32 sqn) { @@ -943,10 +944,10 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn); /* source vport is the esw manager */ - MLX5_SET(fte_match_set_misc, misc, source_port, rep->esw->manager_vport); + MLX5_SET(fte_match_set_misc, misc, source_port, from_esw->manager_vport); if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch)) MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, - MLX5_CAP_GEN(rep->esw->dev, vhca_id)); + MLX5_CAP_GEN(from_esw->dev, vhca_id)); misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn); diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index c2a34ff85188..0bfcf7b8ecf9 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -63,6 +63,7 @@ struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw, void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type); struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, + struct mlx5_eswitch *from_esw, struct mlx5_eswitch_rep *rep, u32 sqn); #ifdef CONFIG_MLX5_ESWITCH -- cgit v1.2.3 From c8e6a9e6d6bb29db08e0b69ae97f1e46ccc5691c Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 3 Aug 2021 16:19:54 -0700 Subject: net/mlx5: E-Switch, Add event callback for representors This callback will allow to notify representors about relevant events when in OFFLOADS mode. In downstream patches, this will be used to notify about PAIR/UNPAIR devcom events. Signed-off-by: Mark Bloch Reviewed-by: Mark Zhang Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 50 ++++++++++++++++++++-- include/linux/mlx5/eswitch.h | 9 ++++ 2 files changed, 56 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index dd5eadd6047b..b57a5c188832 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2316,11 +2316,22 @@ void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num) #define ESW_OFFLOADS_DEVCOM_PAIR (0) #define ESW_OFFLOADS_DEVCOM_UNPAIR (1) -static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw, - struct mlx5_eswitch *peer_esw) +static void mlx5_esw_offloads_rep_event_unpair(struct mlx5_eswitch *esw) { + const struct mlx5_eswitch_rep_ops *ops; + struct mlx5_eswitch_rep *rep; + unsigned long i; + u8 rep_type; - return esw_add_fdb_peer_miss_rules(esw, peer_esw->dev); + mlx5_esw_for_each_rep(esw, i, rep) { + rep_type = NUM_REP_TYPES; + while (rep_type--) { + ops = esw->offloads.rep_ops[rep_type]; + if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED && + ops->event) + ops->event(esw, rep, MLX5_SWITCHDEV_EVENT_UNPAIR, NULL); + } + } } static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw) @@ -2328,9 +2339,42 @@ static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw) #if IS_ENABLED(CONFIG_MLX5_CLS_ACT) mlx5e_tc_clean_fdb_peer_flows(esw); #endif + mlx5_esw_offloads_rep_event_unpair(esw); esw_del_fdb_peer_miss_rules(esw); } +static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw, + struct mlx5_eswitch *peer_esw) +{ + const struct mlx5_eswitch_rep_ops *ops; + struct mlx5_eswitch_rep *rep; + unsigned long i; + u8 rep_type; + int err; + + err = esw_add_fdb_peer_miss_rules(esw, peer_esw->dev); + if (err) + return err; + + mlx5_esw_for_each_rep(esw, i, rep) { + for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) { + ops = esw->offloads.rep_ops[rep_type]; + if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED && + ops->event) { + err = ops->event(esw, rep, MLX5_SWITCHDEV_EVENT_PAIR, peer_esw); + if (err) + goto err_out; + } + } + } + + return 0; + +err_out: + mlx5_esw_offloads_unpair(esw); + return err; +} + static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw, struct mlx5_eswitch *peer_esw, bool pair) diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 0bfcf7b8ecf9..4ab5c1fc1270 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -29,11 +29,20 @@ enum { REP_LOADED, }; +enum mlx5_switchdev_event { + MLX5_SWITCHDEV_EVENT_PAIR, + MLX5_SWITCHDEV_EVENT_UNPAIR, +}; + struct mlx5_eswitch_rep; struct mlx5_eswitch_rep_ops { int (*load)(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep); void (*unload)(struct mlx5_eswitch_rep *rep); void *(*get_proto_dev)(struct mlx5_eswitch_rep *rep); + int (*event)(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, + enum mlx5_switchdev_event event, + void *data); }; struct mlx5_eswitch_rep_data { -- cgit v1.2.3 From edfa378448b566f705f5e81fd1565dc39ef6b716 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 14 Jul 2021 12:17:36 +0200 Subject: clk: Align provider-specific CLK_* bit definitions The definition of CLK_MULTIPLIER_ROUND_CLOSEST is not aligned to the two bit definitions next to it. A deeper inspection reveals that the alignment of CLK_MULTIPLIER_ROUND_CLOSEST does match the most common alignment. Align the bit definitions for the various provider types throughout the file at 40 columns, to increase uniformity. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/5468cd9e50cda8fc59cb6baab9413c6c0de1a974.1626257689.git.geert+renesas@glider.be Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index d83b829305c0..7be81d5fcf8c 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -342,7 +342,7 @@ struct clk_fixed_rate { unsigned long flags; }; -#define CLK_FIXED_RATE_PARENT_ACCURACY BIT(0) +#define CLK_FIXED_RATE_PARENT_ACCURACY BIT(0) extern const struct clk_ops clk_fixed_rate_ops; struct clk_hw *__clk_hw_register_fixed_rate(struct device *dev, @@ -1020,8 +1020,8 @@ struct clk_fractional_divider { #define to_clk_fd(_hw) container_of(_hw, struct clk_fractional_divider, hw) -#define CLK_FRAC_DIVIDER_ZERO_BASED BIT(0) -#define CLK_FRAC_DIVIDER_BIG_ENDIAN BIT(1) +#define CLK_FRAC_DIVIDER_ZERO_BASED BIT(0) +#define CLK_FRAC_DIVIDER_BIG_ENDIAN BIT(1) extern const struct clk_ops clk_fractional_divider_ops; struct clk *clk_register_fractional_divider(struct device *dev, @@ -1069,9 +1069,9 @@ struct clk_multiplier { #define to_clk_multiplier(_hw) container_of(_hw, struct clk_multiplier, hw) -#define CLK_MULTIPLIER_ZERO_BYPASS BIT(0) +#define CLK_MULTIPLIER_ZERO_BYPASS BIT(0) #define CLK_MULTIPLIER_ROUND_CLOSEST BIT(1) -#define CLK_MULTIPLIER_BIG_ENDIAN BIT(2) +#define CLK_MULTIPLIER_BIG_ENDIAN BIT(2) extern const struct clk_ops clk_multiplier_ops; -- cgit v1.2.3 From edeb2ca74716056b2be62925f21494d7af65150f Mon Sep 17 00:00:00 2001 From: Martin Botka Date: Fri, 30 Jul 2021 23:59:24 +0200 Subject: clk: qcom: smd: Add support for SM6125 rpm clocks Add rpm smd clocks, PMIC and bus clocks which are required on SM6125 for clients to vote on. Signed-off-by: Martin Botka Link: https://lore.kernel.org/r/20210730215924.733350-2-martin.botka@somainline.org Signed-off-by: Stephen Boyd --- drivers/clk/qcom/clk-smd-rpm.c | 56 ++++++++++++++++++++++++++++++++++++++++ include/linux/soc/qcom/smd-rpm.h | 1 + 2 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index 800b2fef1887..fa5215716465 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -913,6 +913,61 @@ static const struct rpm_smd_clk_desc rpm_clk_sdm660 = { .num_clks = ARRAY_SIZE(sdm660_clks), }; +/* SM6125 */ +DEFINE_CLK_SMD_RPM(sm6125, cnoc_clk, cnoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 1); +DEFINE_CLK_SMD_RPM(sm6125, snoc_clk, snoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 2); +DEFINE_CLK_SMD_RPM_BRANCH(sm6125, qdss_clk, qdss_a_clk, + QCOM_SMD_RPM_MISC_CLK, 1, 19200000); +DEFINE_CLK_SMD_RPM(sm6125, qup_clk, qup_a_clk, QCOM_SMD_RPM_QUP_CLK, 0); +DEFINE_CLK_SMD_RPM(sm6125, mmnrt_clk, mmnrt_a_clk, QCOM_SMD_RPM_MMAXI_CLK, 0); +DEFINE_CLK_SMD_RPM(sm6125, mmrt_clk, mmrt_a_clk, QCOM_SMD_RPM_MMAXI_CLK, 1); +DEFINE_CLK_SMD_RPM(sm6125, snoc_periph_clk, snoc_periph_a_clk, + QCOM_SMD_RPM_BUS_CLK, 0); +DEFINE_CLK_SMD_RPM(sm6125, snoc_lpass_clk, snoc_lpass_a_clk, + QCOM_SMD_RPM_BUS_CLK, 5); + +static struct clk_smd_rpm *sm6125_clks[] = { + [RPM_SMD_XO_CLK_SRC] = &sdm660_bi_tcxo, + [RPM_SMD_XO_A_CLK_SRC] = &sdm660_bi_tcxo_a, + [RPM_SMD_SNOC_CLK] = &sm6125_snoc_clk, + [RPM_SMD_SNOC_A_CLK] = &sm6125_snoc_a_clk, + [RPM_SMD_BIMC_CLK] = &msm8916_bimc_clk, + [RPM_SMD_BIMC_A_CLK] = &msm8916_bimc_a_clk, + [RPM_SMD_QDSS_CLK] = &sm6125_qdss_clk, + [RPM_SMD_QDSS_A_CLK] = &sm6125_qdss_a_clk, + [RPM_SMD_RF_CLK1] = &msm8916_rf_clk1, + [RPM_SMD_RF_CLK1_A] = &msm8916_rf_clk1_a, + [RPM_SMD_RF_CLK2] = &msm8916_rf_clk2, + [RPM_SMD_RF_CLK2_A] = &msm8916_rf_clk2_a, + [RPM_SMD_CNOC_CLK] = &sm6125_cnoc_clk, + [RPM_SMD_CNOC_A_CLK] = &sm6125_cnoc_a_clk, + [RPM_SMD_IPA_CLK] = &msm8976_ipa_clk, + [RPM_SMD_IPA_A_CLK] = &msm8976_ipa_a_clk, + [RPM_SMD_CE1_CLK] = &msm8992_ce1_clk, + [RPM_SMD_CE1_A_CLK] = &msm8992_ce1_a_clk, + [RPM_SMD_LN_BB_CLK1] = &msm8916_bb_clk1, + [RPM_SMD_LN_BB_CLK1_A] = &msm8916_bb_clk1_a, + [RPM_SMD_LN_BB_CLK2] = &msm8916_bb_clk2, + [RPM_SMD_LN_BB_CLK2_A] = &msm8916_bb_clk2_a, + [RPM_SMD_LN_BB_CLK3] = &sdm660_ln_bb_clk3, + [RPM_SMD_LN_BB_CLK3_A] = &sdm660_ln_bb_clk3_a, + [RPM_SMD_QUP_CLK] = &sm6125_qup_clk, + [RPM_SMD_QUP_A_CLK] = &sm6125_qup_a_clk, + [RPM_SMD_MMRT_CLK] = &sm6125_mmrt_clk, + [RPM_SMD_MMRT_A_CLK] = &sm6125_mmrt_a_clk, + [RPM_SMD_MMNRT_CLK] = &sm6125_mmnrt_clk, + [RPM_SMD_MMNRT_A_CLK] = &sm6125_mmnrt_a_clk, + [RPM_SMD_SNOC_PERIPH_CLK] = &sm6125_snoc_periph_clk, + [RPM_SMD_SNOC_PERIPH_A_CLK] = &sm6125_snoc_periph_a_clk, + [RPM_SMD_SNOC_LPASS_CLK] = &sm6125_snoc_lpass_clk, + [RPM_SMD_SNOC_LPASS_A_CLK] = &sm6125_snoc_lpass_a_clk, +}; + +static const struct rpm_smd_clk_desc rpm_clk_sm6125 = { + .clks = sm6125_clks, + .num_clks = ARRAY_SIZE(sm6125_clks), +}; + static const struct of_device_id rpm_smd_clk_match_table[] = { { .compatible = "qcom,rpmcc-msm8226", .data = &rpm_clk_msm8974 }, { .compatible = "qcom,rpmcc-msm8916", .data = &rpm_clk_msm8916 }, @@ -925,6 +980,7 @@ static const struct of_device_id rpm_smd_clk_match_table[] = { { .compatible = "qcom,rpmcc-msm8998", .data = &rpm_clk_msm8998 }, { .compatible = "qcom,rpmcc-qcs404", .data = &rpm_clk_qcs404 }, { .compatible = "qcom,rpmcc-sdm660", .data = &rpm_clk_sdm660 }, + { .compatible = "qcom,rpmcc-sm6125", .data = &rpm_clk_sm6125 }, { } }; MODULE_DEVICE_TABLE(of, rpm_smd_clk_match_table); diff --git a/include/linux/soc/qcom/smd-rpm.h b/include/linux/soc/qcom/smd-rpm.h index f2645ec52520..60e66fc9b6bf 100644 --- a/include/linux/soc/qcom/smd-rpm.h +++ b/include/linux/soc/qcom/smd-rpm.h @@ -29,6 +29,7 @@ struct qcom_smd_rpm; #define QCOM_SMD_RPM_NCPB 0x6270636E #define QCOM_SMD_RPM_OCMEM_PWR 0x706d636f #define QCOM_SMD_RPM_QPIC_CLK 0x63697071 +#define QCOM_SMD_RPM_QUP_CLK 0x707571 #define QCOM_SMD_RPM_SMPA 0x61706d73 #define QCOM_SMD_RPM_SMPB 0x62706d73 #define QCOM_SMD_RPM_SPDM 0x63707362 -- cgit v1.2.3 From 87689270b10fa9e6fac7242233b355cb6792b845 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Wed, 4 Aug 2021 22:28:38 +0000 Subject: KVM: Rename lru_slot to last_used_slot lru_slot is used to keep track of the index of the most-recently used memslot. The correct acronym would be "mru" but that is not a common acronym. So call it last_used_slot which is a bit more obvious. Suggested-by: Paolo Bonzini Signed-off-by: David Matlack Message-Id: <20210804222844.1419481-2-dmatlack@google.com> Signed-off-by: Paolo Bonzini --- arch/s390/kvm/kvm-s390.c | 4 ++-- include/linux/kvm_host.h | 6 +++--- virt/kvm/kvm_main.c | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 4527ac7b5961..02574d7b3612 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1953,7 +1953,7 @@ out: static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn) { int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->lru_slot); + int slot = atomic_read(&slots->last_used_slot); struct kvm_memory_slot *memslots = slots->memslots; if (gfn >= memslots[slot].base_gfn && @@ -1974,7 +1974,7 @@ static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn) if (gfn >= memslots[start].base_gfn && gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->lru_slot, start); + atomic_set(&slots->last_used_slot, start); } return start; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5b6a69caccb5..bdfd5ed539c9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -522,7 +522,7 @@ struct kvm_memslots { u64 generation; /* The mapping table from slot id to the index in memslots[]. */ short id_to_index[KVM_MEM_SLOTS_NUM]; - atomic_t lru_slot; + atomic_t last_used_slot; int used_slots; struct kvm_memory_slot memslots[]; }; @@ -1200,7 +1200,7 @@ static inline struct kvm_memory_slot * search_memslots(struct kvm_memslots *slots, gfn_t gfn) { int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->lru_slot); + int slot = atomic_read(&slots->last_used_slot); struct kvm_memory_slot *memslots = slots->memslots; if (unlikely(!slots->used_slots)) @@ -1221,7 +1221,7 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn) if (start < slots->used_slots && gfn >= memslots[start].base_gfn && gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->lru_slot, start); + atomic_set(&slots->last_used_slot, start); return &memslots[start]; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 930aeb8d3c3e..1984c7389787 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1224,8 +1224,8 @@ static inline void kvm_memslot_delete(struct kvm_memslots *slots, slots->used_slots--; - if (atomic_read(&slots->lru_slot) >= slots->used_slots) - atomic_set(&slots->lru_slot, 0); + if (atomic_read(&slots->last_used_slot) >= slots->used_slots) + atomic_set(&slots->last_used_slot, 0); for (i = slots->id_to_index[memslot->id]; i < slots->used_slots; i++) { mslots[i] = mslots[i + 1]; -- cgit v1.2.3 From 0f22af940dc8ec4f437189096a5f8677995323b0 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Wed, 4 Aug 2021 22:28:39 +0000 Subject: KVM: Move last_used_slot logic out of search_memslots Make search_memslots unconditionally search all memslots and move the last_used_slot logic up one level to __gfn_to_memslot. This is in preparation for introducing a per-vCPU last_used_slot. As part of this change convert existing callers of search_memslots to __gfn_to_memslot to avoid making any functional changes. Signed-off-by: David Matlack Message-Id: <20210804222844.1419481-3-dmatlack@google.com> Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/book3s_64_vio.c | 2 +- arch/powerpc/kvm/book3s_64_vio_hv.c | 2 +- include/linux/kvm_host.h | 64 +++++++++++++++++++++++++++---------- 3 files changed, 50 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 8da93fdfa59e..6365087f3160 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -346,7 +346,7 @@ static long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce, unsigned long gfn = tce >> PAGE_SHIFT; struct kvm_memory_slot *memslot; - memslot = search_memslots(kvm_memslots(kvm), gfn); + memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn); if (!memslot) return -EINVAL; diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index dc6591548f0c..f38dfe195ef2 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -80,7 +80,7 @@ static long kvmppc_rm_tce_to_ua(struct kvm *kvm, unsigned long gfn = tce >> PAGE_SHIFT; struct kvm_memory_slot *memslot; - memslot = search_memslots(kvm_memslots_raw(kvm), gfn); + memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn); if (!memslot) return -EINVAL; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bdfd5ed539c9..f30b53a07917 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1189,29 +1189,43 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* - * search_memslots() and __gfn_to_memslot() are here because they are - * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c. - * gfn_to_memslot() itself isn't here as an inline because that would - * bloat other code too much. + * Returns a pointer to the memslot at slot_index if it contains gfn. + * Otherwise returns NULL. + */ +static inline struct kvm_memory_slot * +try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) +{ + struct kvm_memory_slot *slot; + + if (slot_index < 0 || slot_index >= slots->used_slots) + return NULL; + + slot = &slots->memslots[slot_index]; + + if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) + return slot; + else + return NULL; +} + +/* + * Returns a pointer to the memslot that contains gfn and records the index of + * the slot in index. Otherwise returns NULL. * * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! */ static inline struct kvm_memory_slot * -search_memslots(struct kvm_memslots *slots, gfn_t gfn) +search_memslots(struct kvm_memslots *slots, gfn_t gfn, int *index) { int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->last_used_slot); struct kvm_memory_slot *memslots = slots->memslots; + struct kvm_memory_slot *slot; if (unlikely(!slots->used_slots)) return NULL; - if (gfn >= memslots[slot].base_gfn && - gfn < memslots[slot].base_gfn + memslots[slot].npages) - return &memslots[slot]; - while (start < end) { - slot = start + (end - start) / 2; + int slot = start + (end - start) / 2; if (gfn >= memslots[slot].base_gfn) end = slot; @@ -1219,19 +1233,37 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn) start = slot + 1; } - if (start < slots->used_slots && gfn >= memslots[start].base_gfn && - gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->last_used_slot, start); - return &memslots[start]; + slot = try_get_memslot(slots, start, gfn); + if (slot) { + *index = start; + return slot; } return NULL; } +/* + * __gfn_to_memslot() and its descendants are here because it is called from + * non-modular code in arch/powerpc/kvm/book3s_64_vio{,_hv}.c. gfn_to_memslot() + * itself isn't here as an inline because that would bloat other code too much. + */ static inline struct kvm_memory_slot * __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) { - return search_memslots(slots, gfn); + struct kvm_memory_slot *slot; + int slot_index = atomic_read(&slots->last_used_slot); + + slot = try_get_memslot(slots, slot_index, gfn); + if (slot) + return slot; + + slot = search_memslots(slots, gfn, &slot_index); + if (slot) { + atomic_set(&slots->last_used_slot, slot_index); + return slot; + } + + return NULL; } static inline unsigned long -- cgit v1.2.3 From fe22ed827c5b60b895b15c5c3f04e04ac606be38 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Wed, 4 Aug 2021 22:28:40 +0000 Subject: KVM: Cache the last used slot index per vCPU The memslot for a given gfn is looked up multiple times during page fault handling. Avoid binary searching for it multiple times by caching the most recently used slot. There is an existing VM-wide last_used_slot but that does not work well for cases where vCPUs are accessing memory in different slots (see performance data below). Another benefit of caching the most recently use slot (versus looking up the slot once and passing around a pointer) is speeding up memslot lookups *across* faults and during spte prefetching. To measure the performance of this change I ran dirty_log_perf_test with 64 vCPUs and 64 memslots and measured "Populate memory time" and "Iteration 2 dirty memory time". Tests were ran with eptad=N to force dirty logging to use fast_page_fault so its performance could be measured. Config | Metric | Before | After ---------- | ----------------------------- | ------ | ------ tdp_mmu=Y | Populate memory time | 6.76s | 5.47s tdp_mmu=Y | Iteration 2 dirty memory time | 2.83s | 0.31s tdp_mmu=N | Populate memory time | 20.4s | 18.7s tdp_mmu=N | Iteration 2 dirty memory time | 2.65s | 0.30s The "Iteration 2 dirty memory time" results are especially compelling because they are equivalent to running the same test with a single memslot. In other words, fast_page_fault performance no longer scales with the number of memslots. Signed-off-by: David Matlack Message-Id: <20210804222844.1419481-4-dmatlack@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 13 +++++++++++++ virt/kvm/kvm_main.c | 22 +++++++++++++++++++++- 2 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f30b53a07917..492d183dd7d0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -354,6 +354,13 @@ struct kvm_vcpu { struct kvm_vcpu_stat stat; char stats_id[KVM_STATS_NAME_SIZE]; struct kvm_dirty_ring dirty_ring; + + /* + * The index of the most recently used memslot by this vCPU. It's ok + * if this becomes stale due to memslot changes since we always check + * it is a valid slot. + */ + int last_used_slot; }; /* must be called with irqs disabled */ @@ -1200,6 +1207,12 @@ try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) if (slot_index < 0 || slot_index >= slots->used_slots) return NULL; + /* + * slot_index can come from vcpu->last_used_slot which is not kept + * in sync with userspace-controllable memslot deletion. So use nospec + * to prevent the CPU from speculating past the end of memslots[]. + */ + slot_index = array_index_nospec(slot_index, slots->used_slots); slot = &slots->memslots[slot_index]; if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1984c7389787..30d322519253 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -415,6 +415,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->preempted = false; vcpu->ready = false; preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); + vcpu->last_used_slot = 0; } void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) @@ -2025,7 +2026,26 @@ EXPORT_SYMBOL_GPL(gfn_to_memslot); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn) { - return __gfn_to_memslot(kvm_vcpu_memslots(vcpu), gfn); + struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu); + struct kvm_memory_slot *slot; + int slot_index; + + slot = try_get_memslot(slots, vcpu->last_used_slot, gfn); + if (slot) + return slot; + + /* + * Fall back to searching all memslots. We purposely use + * search_memslots() instead of __gfn_to_memslot() to avoid + * thrashing the VM-wide last_used_index in kvm_memslots. + */ + slot = search_memslots(slots, gfn, &slot_index); + if (slot) { + vcpu->last_used_slot = slot_index; + return slot; + } + + return NULL; } EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_memslot); -- cgit v1.2.3 From 7fcc17d0cb12938d2b3507973a6f93fc9ed2c7a1 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Tue, 3 Aug 2021 11:27:43 +0100 Subject: PM: EM: Increase energy calculation precision The Energy Model (EM) provides useful information about device power in each performance state to other subsystems like: Energy Aware Scheduler (EAS). The energy calculation in EAS does arithmetic operation based on the EM em_cpu_energy(). Current implementation of that function uses em_perf_state::cost as a pre-computed cost coefficient equal to: cost = power * max_frequency / frequency. The 'power' is expressed in milli-Watts (or in abstract scale). There are corner cases when the EAS energy calculation for two Performance Domains (PDs) return the same value. The EAS compares these values to choose smaller one. It might happen that this values are equal due to rounding error. In such scenario, we need better resolution, e.g. 1000 times better. To provide this possibility increase the resolution in the em_perf_state::cost for 64-bit architectures. The cost of increasing resolution on 32-bit is pretty high (64-bit division) and is not justified since there are no new 32bit big.LITTLE EAS systems expected which would benefit from this higher resolution. This patch allows to avoid the rounding to milli-Watt errors, which might occur in EAS energy estimation for each PD. The rounding error is common for small tasks which have small utilization value. There are two places in the code where it makes a difference: 1. In the find_energy_efficient_cpu() where we are searching for best_delta. We might suffer there when two PDs return the same result, like in the example below. Scenario: Low utilized system e.g. ~200 sum_util for PD0 and ~220 for PD1. There are quite a few small tasks ~10-15 util. These tasks would suffer for the rounding error. These utilization values are typical when running games on Android. One of our partners has reported 5..10mA less battery drain when running with increased resolution. Some details: We have two PDs: PD0 (big) and PD1 (little) Let's compare w/o patch set ('old') and w/ patch set ('new') We are comparing energy w/ task and w/o task placed in the PDs a) 'old' w/o patch set, PD0 task_util = 13 cost = 480 sum_util_w/o_task = 215 sum_util_w_task = 228 scale_cpu = 1024 energy_w/o_task = 480 * 215 / 1024 = 100.78 => 100 energy_w_task = 480 * 228 / 1024 = 106.87 => 106 energy_diff = 106 - 100 = 6 (this is equal to 'old' PD1's energy_diff in 'c)') b) 'new' w/ patch set, PD0 task_util = 13 cost = 480 * 1000 = 480000 sum_util_w/o_task = 215 sum_util_w_task = 228 energy_w/o_task = 480000 * 215 / 1024 = 100781 energy_w_task = 480000 * 228 / 1024 = 106875 energy_diff = 106875 - 100781 = 6094 (this is not equal to 'new' PD1's energy_diff in 'd)') c) 'old' w/o patch set, PD1 task_util = 13 cost = 160 sum_util_w/o_task = 283 sum_util_w_task = 293 scale_cpu = 355 energy_w/o_task = 160 * 283 / 355 = 127.55 => 127 energy_w_task = 160 * 296 / 355 = 133.41 => 133 energy_diff = 133 - 127 = 6 (this is equal to 'old' PD0's energy_diff in 'a)') d) 'new' w/ patch set, PD1 task_util = 13 cost = 160 * 1000 = 160000 sum_util_w/o_task = 283 sum_util_w_task = 293 scale_cpu = 355 energy_w/o_task = 160000 * 283 / 355 = 127549 energy_w_task = 160000 * 296 / 355 = 133408 energy_diff = 133408 - 127549 = 5859 (this is not equal to 'new' PD0's energy_diff in 'b)') 2. Difference in the 6% energy margin filter at the end of find_energy_efficient_cpu(). With this patch the margin comparison also has better resolution, so it's possible to have better task placement thanks to that. Fixes: 27871f7a8a341ef ("PM: Introduce an Energy Model management framework") Reported-by: CCJ Yeh Reviewed-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 16 ++++++++++++++++ kernel/power/energy_model.c | 4 +++- 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 3f221dbf5f95..1834752c5617 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -53,6 +53,22 @@ struct em_perf_domain { #ifdef CONFIG_ENERGY_MODEL #define EM_MAX_POWER 0xFFFF +/* + * Increase resolution of energy estimation calculations for 64-bit + * architectures. The extra resolution improves decision made by EAS for the + * task placement when two Performance Domains might provide similar energy + * estimation values (w/o better resolution the values could be equal). + * + * We increase resolution only if we have enough bits to allow this increased + * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit + * are pretty high and the returns do not justify the increased costs. + */ +#ifdef CONFIG_64BIT +#define em_scale_power(p) ((p) * 1000) +#else +#define em_scale_power(p) (p) +#endif + struct em_data_callback { /** * active_power() - Provide power at the next performance state of diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 0f4530b3a8cd..a332ccd829e2 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -170,7 +170,9 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, /* Compute the cost of each performance state. */ fmax = (u64) table[nr_states - 1].frequency; for (i = 0; i < nr_states; i++) { - table[i].cost = div64_u64(fmax * table[i].power, + unsigned long power_res = em_scale_power(table[i].power); + + table[i].cost = div64_u64(fmax * power_res, table[i].frequency); } -- cgit v1.2.3 From 08bf54fcf5ca87328541e035090c6a85c8e064f4 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 2 Aug 2021 21:43:54 +0300 Subject: dmaengine: dw: Convert members to u32 in platform data u32 is a type that is used for properties retrieval from DT. With the type change it allows to clean up properties reading routine. While at it, order the fields in way how they are parsed. Signed-off-by: Andy Shevchenko Reviewed-by: Serge Semin Tested-by: Serge Semin Link: https://lore.kernel.org/r/20210802184355.49879-2-andriy.shevchenko@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-dw.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index b11b0c8bc5da..860ba4bc5ead 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -41,11 +41,11 @@ struct dw_dma_slave { /** * struct dw_dma_platform_data - Controller configuration parameters + * @nr_masters: Number of AHB masters supported by the controller * @nr_channels: Number of channels supported by hardware (max 8) * @chan_allocation_order: Allocate channels starting from 0 or 7 * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0. * @block_size: Maximum block size supported by the controller - * @nr_masters: Number of AHB masters supported by the controller * @data_width: Maximum data width supported by hardware per AHB master * (in bytes, power of 2) * @multi_block: Multi block transfers supported by hardware per channel. @@ -55,25 +55,25 @@ struct dw_dma_slave { * @quirks: Optional platform quirks. */ struct dw_dma_platform_data { - unsigned int nr_channels; + u32 nr_masters; + u32 nr_channels; #define CHAN_ALLOCATION_ASCENDING 0 /* zero to seven */ #define CHAN_ALLOCATION_DESCENDING 1 /* seven to zero */ - unsigned char chan_allocation_order; + u32 chan_allocation_order; #define CHAN_PRIORITY_ASCENDING 0 /* chan0 highest */ #define CHAN_PRIORITY_DESCENDING 1 /* chan7 highest */ - unsigned char chan_priority; - unsigned int block_size; - unsigned char nr_masters; - unsigned char data_width[DW_DMA_MAX_NR_MASTERS]; - unsigned char multi_block[DW_DMA_MAX_NR_CHANNELS]; + u32 chan_priority; + u32 block_size; + u32 data_width[DW_DMA_MAX_NR_MASTERS]; + u32 multi_block[DW_DMA_MAX_NR_CHANNELS]; u32 max_burst[DW_DMA_MAX_NR_CHANNELS]; #define CHAN_PROTCTL_PRIVILEGED BIT(0) #define CHAN_PROTCTL_BUFFERABLE BIT(1) #define CHAN_PROTCTL_CACHEABLE BIT(2) #define CHAN_PROTCTL_MASK GENMASK(2, 0) - unsigned char protctl; + u32 protctl; #define DW_DMA_QUIRK_XBAR_PRESENT BIT(0) - unsigned int quirks; + u32 quirks; }; #endif /* _PLATFORM_DATA_DMA_DW_H */ -- cgit v1.2.3 From f1653c2e2831e9db6cd68473bbec581782df03a5 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 6 Aug 2021 11:05:37 -0700 Subject: xfs: introduce CPU hotplug infrastructure We need to move to per-cpu state for both deferred inode inactivation and CIL tracking, but to do that we need to handle CPUs being removed from the system by the hot-plug code. Introduce generic XFS infrastructure to handle CPU hotplug events that is set up at module init time and torn down at module exit time. Initially, we only need CPU dead notifications, so we only set up a callback for these notifications. The infrastructure can be updated in future for other CPU hotplug state machine notifications easily if ever needed. Signed-off-by: Dave Chinner [djwong: rearrange some macros, fix function prototypes] Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_super.c | 42 +++++++++++++++++++++++++++++++++++++++++- include/linux/cpuhotplug.h | 1 + 2 files changed, 42 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 36fc81e52dc2..d47fac7c8afd 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -2111,6 +2111,39 @@ xfs_destroy_workqueues(void) destroy_workqueue(xfs_alloc_wq); } +#ifdef CONFIG_HOTPLUG_CPU +static int +xfs_cpu_dead( + unsigned int cpu) +{ + return 0; +} + +static int __init +xfs_cpu_hotplug_init(void) +{ + int error; + + error = cpuhp_setup_state_nocalls(CPUHP_XFS_DEAD, "xfs:dead", NULL, + xfs_cpu_dead); + if (error < 0) + xfs_alert(NULL, +"Failed to initialise CPU hotplug, error %d. XFS is non-functional.", + error); + return error; +} + +static void +xfs_cpu_hotplug_destroy(void) +{ + cpuhp_remove_state_nocalls(CPUHP_XFS_DEAD); +} + +#else /* !CONFIG_HOTPLUG_CPU */ +static inline int xfs_cpu_hotplug_init(void) { return 0; } +static inline void xfs_cpu_hotplug_destroy(void) {} +#endif + STATIC int __init init_xfs_fs(void) { @@ -2123,10 +2156,14 @@ init_xfs_fs(void) xfs_dir_startup(); - error = xfs_init_zones(); + error = xfs_cpu_hotplug_init(); if (error) goto out; + error = xfs_init_zones(); + if (error) + goto out_destroy_hp; + error = xfs_init_workqueues(); if (error) goto out_destroy_zones; @@ -2206,6 +2243,8 @@ init_xfs_fs(void) xfs_destroy_workqueues(); out_destroy_zones: xfs_destroy_zones(); + out_destroy_hp: + xfs_cpu_hotplug_destroy(); out: return error; } @@ -2228,6 +2267,7 @@ exit_xfs_fs(void) xfs_destroy_workqueues(); xfs_destroy_zones(); xfs_uuid_table_free(); + xfs_cpu_hotplug_destroy(); } module_init(init_xfs_fs); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f39b34b13871..439adc05be4e 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -52,6 +52,7 @@ enum cpuhp_state { CPUHP_FS_BUFF_DEAD, CPUHP_PRINTK_DEAD, CPUHP_MM_MEMCQ_DEAD, + CPUHP_XFS_DEAD, CPUHP_PERCPU_CNT_DEAD, CPUHP_RADIX_DEAD, CPUHP_PAGE_ALLOC, -- cgit v1.2.3 From a86baa69c2b7b85bab41692fa3ec188a5aae1d27 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Tue, 18 May 2021 19:17:16 -0700 Subject: rcu: Remove special bit at the bottom of the ->dynticks counter Commit b8c17e6664c4 ("rcu: Maintain special bits at bottom of ->dynticks counter") reserved a bit at the bottom of the ->dynticks counter to defer flushing of TLBs, but this facility never has been used. This commit therefore removes this capability along with the rcu_eqs_special_set() function used to trigger it. Link: https://lore.kernel.org/linux-doc/CALCETrWNPOOdTrFabTDd=H7+wc6xJ9rJceg6OL1S0rTV5pfSsA@mail.gmail.com/ Suggested-by: Andy Lutomirski Signed-off-by: "Joel Fernandes (Google)" [ paulmck: Forward-port to v5.13-rc1. ] Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 3 -- kernel/rcu/tree.c | 77 +++++++++---------------------------------------- 2 files changed, 14 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 953e70fafe38..9be015305f9f 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -14,9 +14,6 @@ #include /* for HZ */ -/* Never flag non-existent other CPUs! */ -static inline bool rcu_eqs_special_set(int cpu) { return false; } - unsigned long get_state_synchronize_rcu(void); unsigned long start_poll_synchronize_rcu(void); bool poll_state_synchronize_rcu(unsigned long oldstate); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 51f24ecd94b2..42a0032dd99f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -74,17 +74,10 @@ /* Data structures. */ -/* - * Steal a bit from the bottom of ->dynticks for idle entry/exit - * control. Initially this is for TLB flushing. - */ -#define RCU_DYNTICK_CTRL_MASK 0x1 -#define RCU_DYNTICK_CTRL_CTR (RCU_DYNTICK_CTRL_MASK + 1) - static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { .dynticks_nesting = 1, .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, - .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), + .dynticks = ATOMIC_INIT(1), #ifdef CONFIG_RCU_NOCB_CPU .cblist.flags = SEGCBLIST_SOFTIRQ_ONLY, #endif @@ -266,7 +259,6 @@ void rcu_softirq_qs(void) */ static noinstr void rcu_dynticks_eqs_enter(void) { - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); int seq; /* @@ -275,13 +267,9 @@ static noinstr void rcu_dynticks_eqs_enter(void) * next idle sojourn. */ rcu_dynticks_task_trace_enter(); // Before ->dynticks update! - seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); + seq = arch_atomic_inc_return(&this_cpu_ptr(&rcu_data)->dynticks); // RCU is no longer watching. Better be in extended quiescent state! - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - (seq & RCU_DYNTICK_CTRL_CTR)); - /* Better not have special action (TLB flush) pending! */ - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - (seq & RCU_DYNTICK_CTRL_MASK)); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & 0x1)); } /* @@ -291,7 +279,6 @@ static noinstr void rcu_dynticks_eqs_enter(void) */ static noinstr void rcu_dynticks_eqs_exit(void) { - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); int seq; /* @@ -299,15 +286,10 @@ static noinstr void rcu_dynticks_eqs_exit(void) * and we also must force ordering with the next RCU read-side * critical section. */ - seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); + seq = arch_atomic_inc_return(&this_cpu_ptr(&rcu_data)->dynticks); // RCU is now watching. Better not be in an extended quiescent state! rcu_dynticks_task_trace_exit(); // After ->dynticks update! - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - !(seq & RCU_DYNTICK_CTRL_CTR)); - if (seq & RCU_DYNTICK_CTRL_MASK) { - arch_atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks); - smp_mb__after_atomic(); /* _exit after clearing mask. */ - } + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & 0x1)); } /* @@ -324,9 +306,9 @@ static void rcu_dynticks_eqs_online(void) { struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - if (atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR) + if (atomic_read(&rdp->dynticks) & 0x1) return; - atomic_add(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); + atomic_inc(&rdp->dynticks); } /* @@ -336,9 +318,7 @@ static void rcu_dynticks_eqs_online(void) */ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void) { - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - - return !(arch_atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR); + return !(arch_atomic_read(&this_cpu_ptr(&rcu_data)->dynticks) & 0x1); } /* @@ -347,9 +327,7 @@ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void) */ static int rcu_dynticks_snap(struct rcu_data *rdp) { - int snap = atomic_add_return(0, &rdp->dynticks); - - return snap & ~RCU_DYNTICK_CTRL_MASK; + return atomic_add_return(0, &rdp->dynticks); } /* @@ -358,7 +336,7 @@ static int rcu_dynticks_snap(struct rcu_data *rdp) */ static bool rcu_dynticks_in_eqs(int snap) { - return !(snap & RCU_DYNTICK_CTRL_CTR); + return !(snap & 0x1); } /* Return true if the specified CPU is currently idle from an RCU viewpoint. */ @@ -389,8 +367,7 @@ bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) int snap; // If not quiescent, force back to earlier extended quiescent state. - snap = atomic_read(&rdp->dynticks) & ~(RCU_DYNTICK_CTRL_MASK | - RCU_DYNTICK_CTRL_CTR); + snap = atomic_read(&rdp->dynticks) & ~0x1; smp_rmb(); // Order ->dynticks and *vp reads. if (READ_ONCE(*vp)) @@ -398,32 +375,7 @@ bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) smp_rmb(); // Order *vp read and ->dynticks re-read. // If still in the same extended quiescent state, we are good! - return snap == (atomic_read(&rdp->dynticks) & ~RCU_DYNTICK_CTRL_MASK); -} - -/* - * Set the special (bottom) bit of the specified CPU so that it - * will take special action (such as flushing its TLB) on the - * next exit from an extended quiescent state. Returns true if - * the bit was successfully set, or false if the CPU was not in - * an extended quiescent state. - */ -bool rcu_eqs_special_set(int cpu) -{ - int old; - int new; - int new_old; - struct rcu_data *rdp = &per_cpu(rcu_data, cpu); - - new_old = atomic_read(&rdp->dynticks); - do { - old = new_old; - if (old & RCU_DYNTICK_CTRL_CTR) - return false; - new = old | RCU_DYNTICK_CTRL_MASK; - new_old = atomic_cmpxchg(&rdp->dynticks, old, new); - } while (new_old != old); - return true; + return snap == atomic_read(&rdp->dynticks); } /* @@ -442,10 +394,9 @@ notrace void rcu_momentary_dyntick_idle(void) int special; raw_cpu_write(rcu_data.rcu_need_heavy_qs, false); - special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, - &this_cpu_ptr(&rcu_data)->dynticks); + special = atomic_add_return(2, &this_cpu_ptr(&rcu_data)->dynticks); /* It is illegal to call this from idle state. */ - WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); + WARN_ON_ONCE(!(special & 0x1)); rcu_preempt_deferred_qs(current); } EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle); -- cgit v1.2.3 From 5fcb3a5f04ee6422714adb02f5364042228bfc2e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 20 May 2021 13:35:50 -0700 Subject: rcu: Mark accesses to ->rcu_read_lock_nesting KCSAN flags accesses to ->rcu_read_lock_nesting as data races, but in the past, the overhead of marked accesses was excessive. However, that was long ago, and much has changed since then, both in terms of hardware and of compilers. Here is data taken on an eight-core laptop using Intel(R) Core(TM) i9-10885H CPU @ 2.40GHz with a kernel built using gcc version 9.3.0, with all data in nanoseconds. Unmarked accesses (status quo), measured by three refscale runs: Minimum reader duration: 3.286 2.851 3.395 Median reader duration: 3.698 3.531 3.4695 Maximum reader duration: 4.481 5.215 5.157 Marked accesses, also measured by three refscale runs: Minimum reader duration: 3.501 3.677 3.580 Median reader duration: 4.053 3.723 3.895 Maximum reader duration: 7.307 4.999 5.511 This focused microbenhmark shows only sub-nanosecond differences which are unlikely to be visible at the system level. This commit therefore marks data-racing accesses to ->rcu_read_lock_nesting. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 +- kernel/rcu/tree_plugin.h | 9 ++++++--- 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index d9680b798b21..cfeb43bfc719 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -53,7 +53,7 @@ void __rcu_read_unlock(void); * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ -#define rcu_preempt_depth() (current->rcu_read_lock_nesting) +#define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index de1dc3bb7f70..83a702a4e296 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -405,17 +405,20 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) static void rcu_preempt_read_enter(void) { - current->rcu_read_lock_nesting++; + WRITE_ONCE(current->rcu_read_lock_nesting, READ_ONCE(current->rcu_read_lock_nesting) + 1); } static int rcu_preempt_read_exit(void) { - return --current->rcu_read_lock_nesting; + int ret = READ_ONCE(current->rcu_read_lock_nesting) - 1; + + WRITE_ONCE(current->rcu_read_lock_nesting, ret); + return ret; } static void rcu_preempt_depth_set(int val) { - current->rcu_read_lock_nesting = val; + WRITE_ONCE(current->rcu_read_lock_nesting, val); } /* -- cgit v1.2.3 From 751b1710eb09b0ba21718add68cd340707ca2446 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 21 May 2021 12:08:29 +0200 Subject: rculist: Unify documentation about missing list_empty_rcu() We have two separate sections that talk about why list_empty_rcu() is not needed, so this commit consolidates them. Signed-off-by: Julian Wiedmann [ paulmck: The usual wordsmithing. ] Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 35 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index f8633d37e358..d29740be4833 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -10,15 +10,6 @@ #include #include -/* - * Why is there no list_empty_rcu()? Because list_empty() serves this - * purpose. The list_empty() function fetches the RCU-protected pointer - * and compares it to the address of the list head, but neither dereferences - * this pointer itself nor provides this pointer to the caller. Therefore, - * it is not necessary to use rcu_dereference(), so that list_empty() can - * be used anywhere you would want to use a list_empty_rcu(). - */ - /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized @@ -318,21 +309,29 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, /* * Where are list_empty_rcu() and list_first_entry_rcu()? * - * Implementing those functions following their counterparts list_empty() and - * list_first_entry() is not advisable because they lead to subtle race - * conditions as the following snippet shows: + * They do not exist because they would lead to subtle race conditions: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * - * The list may not be empty when list_empty_rcu checks it, but it may be when - * list_first_entry_rcu rereads the ->next pointer. - * - * Rereading the ->next pointer is not a problem for list_empty() and - * list_first_entry() because they would be protected by a lock that blocks - * writers. + * The list might be non-empty when list_empty_rcu() checks it, but it + * might have become empty by the time that list_first_entry_rcu() rereads + * the ->next pointer, which would result in a SEGV. + * + * When not using RCU, it is OK for list_first_entry() to re-read that + * pointer because both functions should be protected by some lock that + * blocks writers. + * + * When using RCU, list_empty() uses READ_ONCE() to fetch the + * RCU-protected ->next pointer and then compares it to the address of the + * list head. However, it neither dereferences this pointer nor provides + * this pointer to its caller. Thus, READ_ONCE() suffices (that is, + * rcu_dereference() is not needed), which means that list_empty() can be + * used anywhere you would want to use list_empty_rcu(). Just don't + * expect anything useful to happen if you do a subsequent lockless + * call to list_first_entry_rcu()!!! * * See list_first_or_null_rcu for an alternative. */ -- cgit v1.2.3 From 65bfdd36c113f5d579a382d8f2847210ea4cdca6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 2 Jun 2021 16:31:38 -0700 Subject: srcutiny: Mark read-side data races This commit marks some interrupt-induced read-side data races in __srcu_read_lock(), __srcu_read_unlock(), and srcu_torture_stats_print(). Signed-off-by: Paul E. McKenney --- include/linux/srcutiny.h | 8 ++++---- kernel/rcu/srcutiny.c | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 0e0cf4d6a72a..6cfaa0a9a9b9 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -61,7 +61,7 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp) int idx; idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; - WRITE_ONCE(ssp->srcu_lock_nesting[idx], ssp->srcu_lock_nesting[idx] + 1); + WRITE_ONCE(ssp->srcu_lock_nesting[idx], READ_ONCE(ssp->srcu_lock_nesting[idx]) + 1); return idx; } @@ -81,11 +81,11 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp, { int idx; - idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; + idx = ((data_race(READ_ONCE(ssp->srcu_idx)) + 1) & 0x2) >> 1; pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n", tt, tf, idx, - READ_ONCE(ssp->srcu_lock_nesting[!idx]), - READ_ONCE(ssp->srcu_lock_nesting[idx])); + data_race(READ_ONCE(ssp->srcu_lock_nesting[!idx])), + data_race(READ_ONCE(ssp->srcu_lock_nesting[idx]))); } #endif diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 26344dc6483b..a0ba2ed49bc6 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -96,7 +96,7 @@ EXPORT_SYMBOL_GPL(cleanup_srcu_struct); */ void __srcu_read_unlock(struct srcu_struct *ssp, int idx) { - int newval = ssp->srcu_lock_nesting[idx] - 1; + int newval = READ_ONCE(ssp->srcu_lock_nesting[idx]) - 1; WRITE_ONCE(ssp->srcu_lock_nesting[idx], newval); if (!newval && READ_ONCE(ssp->srcu_gp_waiting)) -- cgit v1.2.3 From 1027b96ec9d34f9abab69bc1a4dc5b1ad8ab1349 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 6 Aug 2021 16:21:24 +0800 Subject: once: Fix panic when module unload DO_ONCE DEFINE_STATIC_KEY_TRUE(___once_key); __do_once_done once_disable_jump(once_key); INIT_WORK(&w->work, once_deferred); struct once_work *w; w->key = key; schedule_work(&w->work); module unload //*the key is destroy* process_one_work once_deferred BUG_ON(!static_key_enabled(work->key)); static_key_count((struct static_key *)x) //*access key, crash* When module uses DO_ONCE mechanism, it could crash due to the above concurrency problem, we could reproduce it with link[1]. Fix it by add/put module refcount in the once work process. [1] https://lore.kernel.org/netdev/eaa6c371-465e-57eb-6be9-f4b16b9d7cbf@huawei.com/ Cc: Hannes Frederic Sowa Cc: Daniel Borkmann Cc: David S. Miller Cc: Eric Dumazet Reported-by: Minmin chen Signed-off-by: Kefeng Wang Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/once.h | 4 ++-- lib/once.c | 11 ++++++++--- 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/once.h b/include/linux/once.h index 9225ee6d96c7..ae6f4eb41cbe 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -7,7 +7,7 @@ bool __do_once_start(bool *done, unsigned long *flags); void __do_once_done(bool *done, struct static_key_true *once_key, - unsigned long *flags); + unsigned long *flags, struct module *mod); /* Call a function exactly once. The idea of DO_ONCE() is to perform * a function call such as initialization of random seeds, etc, only @@ -46,7 +46,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key, if (unlikely(___ret)) { \ func(__VA_ARGS__); \ __do_once_done(&___done, &___once_key, \ - &___flags); \ + &___flags, THIS_MODULE); \ } \ } \ ___ret; \ diff --git a/lib/once.c b/lib/once.c index 8b7d6235217e..59149bf3bfb4 100644 --- a/lib/once.c +++ b/lib/once.c @@ -3,10 +3,12 @@ #include #include #include +#include struct once_work { struct work_struct work; struct static_key_true *key; + struct module *module; }; static void once_deferred(struct work_struct *w) @@ -16,10 +18,11 @@ static void once_deferred(struct work_struct *w) work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); static_branch_disable(work->key); + module_put(work->module); kfree(work); } -static void once_disable_jump(struct static_key_true *key) +static void once_disable_jump(struct static_key_true *key, struct module *mod) { struct once_work *w; @@ -29,6 +32,8 @@ static void once_disable_jump(struct static_key_true *key) INIT_WORK(&w->work, once_deferred); w->key = key; + w->module = mod; + __module_get(mod); schedule_work(&w->work); } @@ -53,11 +58,11 @@ bool __do_once_start(bool *done, unsigned long *flags) EXPORT_SYMBOL(__do_once_start); void __do_once_done(bool *done, struct static_key_true *once_key, - unsigned long *flags) + unsigned long *flags, struct module *mod) __releases(once_lock) { *done = true; spin_unlock_irqrestore(&once_lock, *flags); - once_disable_jump(once_key); + once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_done); -- cgit v1.2.3 From fdacd57c79b79a03c7ca88f706ad9fb7b46831c1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 3 Aug 2021 16:47:19 +0200 Subject: netfilter: x_tables: never register tables by default For historical reasons x_tables still register tables by default in the initial namespace. Only newly created net namespaces add the hook on demand. This means that the init_net always pays hook cost, even if no filtering rules are added (e.g. only used inside a single netns). Note that the hooks are added even when 'iptables -L' is called. This is because there is no way to tell 'iptables -A' and 'iptables -L' apart at kernel level. The only solution would be to register the table, but delay hook registration until the first rule gets added (or policy gets changed). That however means that counters are not hooked either, so 'iptables -L' would always show 0-counters even when traffic is flowing which might be unexpected. This keeps table and hook registration consistent with what is already done in non-init netns: first iptables(-save) invocation registers both table and hooks. This applies the same solution adopted for ebtables. All tables register a template that contains the l3 family, the name and a constructor function that is called when the initial table has to be added. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 6 +-- net/ipv4/netfilter/arptable_filter.c | 23 ++++---- net/ipv4/netfilter/iptable_filter.c | 24 ++++++--- net/ipv4/netfilter/iptable_mangle.c | 17 +++--- net/ipv4/netfilter/iptable_nat.c | 20 +++---- net/ipv4/netfilter/iptable_raw.c | 21 ++++---- net/ipv4/netfilter/iptable_security.c | 23 ++++---- net/ipv6/netfilter/ip6table_filter.c | 23 +++++--- net/ipv6/netfilter/ip6table_mangle.c | 22 ++++---- net/ipv6/netfilter/ip6table_nat.c | 16 +++--- net/ipv6/netfilter/ip6table_raw.c | 24 ++++----- net/ipv6/netfilter/ip6table_security.c | 22 ++++---- net/netfilter/x_tables.c | 98 +++++++++++++++++++++++++++------- 13 files changed, 204 insertions(+), 135 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 28d7027cd460..5897f3dbaf7c 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -238,9 +238,6 @@ struct xt_table { u_int8_t af; /* address/protocol family */ int priority; /* hook order */ - /* called when table is needed in the given netns */ - int (*table_init)(struct net *net); - /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; }; @@ -452,6 +449,9 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); +int xt_register_template(const struct xt_table *t, int(*table_init)(struct net *net)); +void xt_unregister_template(const struct xt_table *t); + #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 6922612df456..3de78416ec76 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -18,15 +18,12 @@ MODULE_DESCRIPTION("arptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | \ (1 << NF_ARP_FORWARD)) -static int __net_init arptable_filter_table_init(struct net *net); - static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_ARP, .priority = NF_IP_PRI_FILTER, - .table_init = arptable_filter_table_init, }; /* The work comes in here from netfilter.c */ @@ -39,7 +36,7 @@ arptable_filter_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *arpfilter_ops __read_mostly; -static int __net_init arptable_filter_table_init(struct net *net) +static int arptable_filter_table_init(struct net *net) { struct arpt_replace *repl; int err; @@ -69,30 +66,32 @@ static struct pernet_operations arptable_filter_net_ops = { static int __init arptable_filter_init(void) { - int ret; + int ret = xt_register_template(&packet_filter, + arptable_filter_table_init); + + if (ret < 0) + return ret; arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arptable_filter_hook); - if (IS_ERR(arpfilter_ops)) + if (IS_ERR(arpfilter_ops)) { + xt_unregister_template(&packet_filter); return PTR_ERR(arpfilter_ops); + } ret = register_pernet_subsys(&arptable_filter_net_ops); if (ret < 0) { + xt_unregister_template(&packet_filter); kfree(arpfilter_ops); return ret; } - ret = arptable_filter_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&arptable_filter_net_ops); - kfree(arpfilter_ops); - } - return ret; } static void __exit arptable_filter_fini(void) { unregister_pernet_subsys(&arptable_filter_net_ops); + xt_unregister_template(&packet_filter); kfree(arpfilter_ops); } diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 8272df7c6ad5..0eb0e2ab9bfc 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -19,7 +19,6 @@ MODULE_DESCRIPTION("iptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) -static int __net_init iptable_filter_table_init(struct net *net); static const struct xt_table packet_filter = { .name = "filter", @@ -27,7 +26,6 @@ static const struct xt_table packet_filter = { .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_FILTER, - .table_init = iptable_filter_table_init, }; static unsigned int @@ -43,7 +41,7 @@ static struct nf_hook_ops *filter_ops __read_mostly; static bool forward __read_mostly = true; module_param(forward, bool, 0000); -static int __net_init iptable_filter_table_init(struct net *net) +static int iptable_filter_table_init(struct net *net) { struct ipt_replace *repl; int err; @@ -62,7 +60,7 @@ static int __net_init iptable_filter_table_init(struct net *net) static int __net_init iptable_filter_net_init(struct net *net) { - if (net == &init_net || !forward) + if (!forward) return iptable_filter_table_init(net); return 0; @@ -86,22 +84,32 @@ static struct pernet_operations iptable_filter_net_ops = { static int __init iptable_filter_init(void) { - int ret; + int ret = xt_register_template(&packet_filter, + iptable_filter_table_init); + + if (ret < 0) + return ret; filter_ops = xt_hook_ops_alloc(&packet_filter, iptable_filter_hook); - if (IS_ERR(filter_ops)) + if (IS_ERR(filter_ops)) { + xt_unregister_template(&packet_filter); return PTR_ERR(filter_ops); + } ret = register_pernet_subsys(&iptable_filter_net_ops); - if (ret < 0) + if (ret < 0) { + xt_unregister_template(&packet_filter); kfree(filter_ops); + return ret; + } - return ret; + return 0; } static void __exit iptable_filter_fini(void) { unregister_pernet_subsys(&iptable_filter_net_ops); + xt_unregister_template(&packet_filter); kfree(filter_ops); } diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 2abc3836f391..b52a4c8a14fc 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -25,15 +25,12 @@ MODULE_DESCRIPTION("iptables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) -static int __net_init iptable_mangle_table_init(struct net *net); - static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_MANGLE, - .table_init = iptable_mangle_table_init, }; static unsigned int @@ -83,7 +80,7 @@ iptable_mangle_hook(void *priv, } static struct nf_hook_ops *mangle_ops __read_mostly; -static int __net_init iptable_mangle_table_init(struct net *net) +static int iptable_mangle_table_init(struct net *net) { struct ipt_replace *repl; int ret; @@ -113,32 +110,30 @@ static struct pernet_operations iptable_mangle_net_ops = { static int __init iptable_mangle_init(void) { - int ret; + int ret = xt_register_template(&packet_mangler, + iptable_mangle_table_init); mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook); if (IS_ERR(mangle_ops)) { + xt_unregister_template(&packet_mangler); ret = PTR_ERR(mangle_ops); return ret; } ret = register_pernet_subsys(&iptable_mangle_net_ops); if (ret < 0) { + xt_unregister_template(&packet_mangler); kfree(mangle_ops); return ret; } - ret = iptable_mangle_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&iptable_mangle_net_ops); - kfree(mangle_ops); - } - return ret; } static void __exit iptable_mangle_fini(void) { unregister_pernet_subsys(&iptable_mangle_net_ops); + xt_unregister_template(&packet_mangler); kfree(mangle_ops); } diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index a9913842ef18..45d7e072e6a5 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -17,8 +17,6 @@ struct iptable_nat_pernet { struct nf_hook_ops *nf_nat_ops; }; -static int __net_init iptable_nat_table_init(struct net *net); - static unsigned int iptable_nat_net_id __read_mostly; static const struct xt_table nf_nat_ipv4_table = { @@ -29,7 +27,6 @@ static const struct xt_table nf_nat_ipv4_table = { (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV4, - .table_init = iptable_nat_table_init, }; static unsigned int iptable_nat_do_chain(void *priv, @@ -113,7 +110,7 @@ static void ipt_nat_unregister_lookups(struct net *net) kfree(ops); } -static int __net_init iptable_nat_table_init(struct net *net) +static int iptable_nat_table_init(struct net *net) { struct ipt_replace *repl; int ret; @@ -155,20 +152,25 @@ static struct pernet_operations iptable_nat_net_ops = { static int __init iptable_nat_init(void) { - int ret = register_pernet_subsys(&iptable_nat_net_ops); + int ret = xt_register_template(&nf_nat_ipv4_table, + iptable_nat_table_init); + + if (ret < 0) + return ret; - if (ret) + ret = register_pernet_subsys(&iptable_nat_net_ops); + if (ret < 0) { + xt_unregister_template(&nf_nat_ipv4_table); return ret; + } - ret = iptable_nat_table_init(&init_net); - if (ret) - unregister_pernet_subsys(&iptable_nat_net_ops); return ret; } static void __exit iptable_nat_exit(void) { unregister_pernet_subsys(&iptable_nat_net_ops); + xt_unregister_template(&nf_nat_ipv4_table); } module_init(iptable_nat_init); diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index ceef397c1f5f..b88e0f36cd05 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -12,8 +12,6 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -static int __net_init iptable_raw_table_init(struct net *net); - static bool raw_before_defrag __read_mostly; MODULE_PARM_DESC(raw_before_defrag, "Enable raw table before defrag"); module_param(raw_before_defrag, bool, 0000); @@ -24,7 +22,6 @@ static const struct xt_table packet_raw = { .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_RAW, - .table_init = iptable_raw_table_init, }; static const struct xt_table packet_raw_before_defrag = { @@ -33,7 +30,6 @@ static const struct xt_table packet_raw_before_defrag = { .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_RAW_BEFORE_DEFRAG, - .table_init = iptable_raw_table_init, }; /* The work comes in here from netfilter.c. */ @@ -89,22 +85,24 @@ static int __init iptable_raw_init(void) pr_info("Enabling raw table before defrag\n"); } + ret = xt_register_template(table, + iptable_raw_table_init); + if (ret < 0) + return ret; + rawtable_ops = xt_hook_ops_alloc(table, iptable_raw_hook); - if (IS_ERR(rawtable_ops)) + if (IS_ERR(rawtable_ops)) { + xt_unregister_template(table); return PTR_ERR(rawtable_ops); + } ret = register_pernet_subsys(&iptable_raw_net_ops); if (ret < 0) { + xt_unregister_template(table); kfree(rawtable_ops); return ret; } - ret = iptable_raw_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&iptable_raw_net_ops); - kfree(rawtable_ops); - } - return ret; } @@ -112,6 +110,7 @@ static void __exit iptable_raw_fini(void) { unregister_pernet_subsys(&iptable_raw_net_ops); kfree(rawtable_ops); + xt_unregister_template(&packet_raw); } module_init(iptable_raw_init); diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 77973f5fd8f6..f519162a2fa5 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -25,15 +25,12 @@ MODULE_DESCRIPTION("iptables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) -static int __net_init iptable_security_table_init(struct net *net); - static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_SECURITY, - .table_init = iptable_security_table_init, }; static unsigned int @@ -45,7 +42,7 @@ iptable_security_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *sectbl_ops __read_mostly; -static int __net_init iptable_security_table_init(struct net *net) +static int iptable_security_table_init(struct net *net) { struct ipt_replace *repl; int ret; @@ -75,24 +72,25 @@ static struct pernet_operations iptable_security_net_ops = { static int __init iptable_security_init(void) { - int ret; + int ret = xt_register_template(&security_table, + iptable_security_table_init); + + if (ret < 0) + return ret; sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook); - if (IS_ERR(sectbl_ops)) + if (IS_ERR(sectbl_ops)) { + xt_unregister_template(&security_table); return PTR_ERR(sectbl_ops); + } ret = register_pernet_subsys(&iptable_security_net_ops); if (ret < 0) { + xt_unregister_template(&security_table); kfree(sectbl_ops); return ret; } - ret = iptable_security_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&iptable_security_net_ops); - kfree(sectbl_ops); - } - return ret; } @@ -100,6 +98,7 @@ static void __exit iptable_security_fini(void) { unregister_pernet_subsys(&iptable_security_net_ops); kfree(sectbl_ops); + xt_unregister_template(&security_table); } module_init(iptable_security_init); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index bb784ea7bbd3..727ee8097012 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -19,15 +19,12 @@ MODULE_DESCRIPTION("ip6tables filter table"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) -static int __net_init ip6table_filter_table_init(struct net *net); - static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_FILTER, - .table_init = ip6table_filter_table_init, }; /* The work comes in here from netfilter.c. */ @@ -44,7 +41,7 @@ static struct nf_hook_ops *filter_ops __read_mostly; static bool forward = true; module_param(forward, bool, 0000); -static int __net_init ip6table_filter_table_init(struct net *net) +static int ip6table_filter_table_init(struct net *net) { struct ip6t_replace *repl; int err; @@ -63,7 +60,7 @@ static int __net_init ip6table_filter_table_init(struct net *net) static int __net_init ip6table_filter_net_init(struct net *net) { - if (net == &init_net || !forward) + if (!forward) return ip6table_filter_table_init(net); return 0; @@ -87,15 +84,24 @@ static struct pernet_operations ip6table_filter_net_ops = { static int __init ip6table_filter_init(void) { - int ret; + int ret = xt_register_template(&packet_filter, + ip6table_filter_table_init); + + if (ret < 0) + return ret; filter_ops = xt_hook_ops_alloc(&packet_filter, ip6table_filter_hook); - if (IS_ERR(filter_ops)) + if (IS_ERR(filter_ops)) { + xt_unregister_template(&packet_filter); return PTR_ERR(filter_ops); + } ret = register_pernet_subsys(&ip6table_filter_net_ops); - if (ret < 0) + if (ret < 0) { + xt_unregister_template(&packet_filter); kfree(filter_ops); + return ret; + } return ret; } @@ -103,6 +109,7 @@ static int __init ip6table_filter_init(void) static void __exit ip6table_filter_fini(void) { unregister_pernet_subsys(&ip6table_filter_net_ops); + xt_unregister_template(&packet_filter); kfree(filter_ops); } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index c76cffd63041..9b518ce37d6a 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -20,15 +20,12 @@ MODULE_DESCRIPTION("ip6tables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) -static int __net_init ip6table_mangle_table_init(struct net *net); - static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_MANGLE, - .table_init = ip6table_mangle_table_init, }; static unsigned int @@ -76,7 +73,7 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb, } static struct nf_hook_ops *mangle_ops __read_mostly; -static int __net_init ip6table_mangle_table_init(struct net *net) +static int ip6table_mangle_table_init(struct net *net) { struct ip6t_replace *repl; int ret; @@ -106,29 +103,32 @@ static struct pernet_operations ip6table_mangle_net_ops = { static int __init ip6table_mangle_init(void) { - int ret; + int ret = xt_register_template(&packet_mangler, + ip6table_mangle_table_init); + + if (ret < 0) + return ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook); - if (IS_ERR(mangle_ops)) + if (IS_ERR(mangle_ops)) { + xt_unregister_template(&packet_mangler); return PTR_ERR(mangle_ops); + } ret = register_pernet_subsys(&ip6table_mangle_net_ops); if (ret < 0) { + xt_unregister_template(&packet_mangler); kfree(mangle_ops); return ret; } - ret = ip6table_mangle_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&ip6table_mangle_net_ops); - kfree(mangle_ops); - } return ret; } static void __exit ip6table_mangle_fini(void) { unregister_pernet_subsys(&ip6table_mangle_net_ops); + xt_unregister_template(&packet_mangler); kfree(mangle_ops); } diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index b0292251e655..921c1723a01e 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -19,8 +19,6 @@ struct ip6table_nat_pernet { struct nf_hook_ops *nf_nat_ops; }; -static int __net_init ip6table_nat_table_init(struct net *net); - static unsigned int ip6table_nat_net_id __read_mostly; static const struct xt_table nf_nat_ipv6_table = { @@ -31,7 +29,6 @@ static const struct xt_table nf_nat_ipv6_table = { (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV6, - .table_init = ip6table_nat_table_init, }; static unsigned int ip6table_nat_do_chain(void *priv, @@ -115,7 +112,7 @@ static void ip6t_nat_unregister_lookups(struct net *net) kfree(ops); } -static int __net_init ip6table_nat_table_init(struct net *net) +static int ip6table_nat_table_init(struct net *net) { struct ip6t_replace *repl; int ret; @@ -157,20 +154,23 @@ static struct pernet_operations ip6table_nat_net_ops = { static int __init ip6table_nat_init(void) { - int ret = register_pernet_subsys(&ip6table_nat_net_ops); + int ret = xt_register_template(&nf_nat_ipv6_table, + ip6table_nat_table_init); - if (ret) + if (ret < 0) return ret; - ret = ip6table_nat_table_init(&init_net); + ret = register_pernet_subsys(&ip6table_nat_net_ops); if (ret) - unregister_pernet_subsys(&ip6table_nat_net_ops); + xt_unregister_template(&nf_nat_ipv6_table); + return ret; } static void __exit ip6table_nat_exit(void) { unregister_pernet_subsys(&ip6table_nat_net_ops); + xt_unregister_template(&nf_nat_ipv6_table); } module_init(ip6table_nat_init); diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index f63c106c521e..4f2a04af71d3 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -11,8 +11,6 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -static int __net_init ip6table_raw_table_init(struct net *net); - static bool raw_before_defrag __read_mostly; MODULE_PARM_DESC(raw_before_defrag, "Enable raw table before defrag"); module_param(raw_before_defrag, bool, 0000); @@ -23,7 +21,6 @@ static const struct xt_table packet_raw = { .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_RAW, - .table_init = ip6table_raw_table_init, }; static const struct xt_table packet_raw_before_defrag = { @@ -32,7 +29,6 @@ static const struct xt_table packet_raw_before_defrag = { .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_RAW_BEFORE_DEFRAG, - .table_init = ip6table_raw_table_init, }; /* The work comes in here from netfilter.c. */ @@ -45,7 +41,7 @@ ip6table_raw_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *rawtable_ops __read_mostly; -static int __net_init ip6table_raw_table_init(struct net *net) +static int ip6table_raw_table_init(struct net *net) { struct ip6t_replace *repl; const struct xt_table *table = &packet_raw; @@ -79,37 +75,39 @@ static struct pernet_operations ip6table_raw_net_ops = { static int __init ip6table_raw_init(void) { - int ret; const struct xt_table *table = &packet_raw; + int ret; if (raw_before_defrag) { table = &packet_raw_before_defrag; - pr_info("Enabling raw table before defrag\n"); } + ret = xt_register_template(table, ip6table_raw_table_init); + if (ret < 0) + return ret; + /* Register hooks */ rawtable_ops = xt_hook_ops_alloc(table, ip6table_raw_hook); - if (IS_ERR(rawtable_ops)) + if (IS_ERR(rawtable_ops)) { + xt_unregister_template(table); return PTR_ERR(rawtable_ops); + } ret = register_pernet_subsys(&ip6table_raw_net_ops); if (ret < 0) { kfree(rawtable_ops); + xt_unregister_template(table); return ret; } - ret = ip6table_raw_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&ip6table_raw_net_ops); - kfree(rawtable_ops); - } return ret; } static void __exit ip6table_raw_fini(void) { unregister_pernet_subsys(&ip6table_raw_net_ops); + xt_unregister_template(&packet_raw); kfree(rawtable_ops); } diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 8dc335cf450b..931674034d8b 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -24,15 +24,12 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) -static int __net_init ip6table_security_table_init(struct net *net); - static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_SECURITY, - .table_init = ip6table_security_table_init, }; static unsigned int @@ -44,7 +41,7 @@ ip6table_security_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *sectbl_ops __read_mostly; -static int __net_init ip6table_security_table_init(struct net *net) +static int ip6table_security_table_init(struct net *net) { struct ip6t_replace *repl; int ret; @@ -74,29 +71,32 @@ static struct pernet_operations ip6table_security_net_ops = { static int __init ip6table_security_init(void) { - int ret; + int ret = xt_register_template(&security_table, + ip6table_security_table_init); + + if (ret < 0) + return ret; sectbl_ops = xt_hook_ops_alloc(&security_table, ip6table_security_hook); - if (IS_ERR(sectbl_ops)) + if (IS_ERR(sectbl_ops)) { + xt_unregister_template(&security_table); return PTR_ERR(sectbl_ops); + } ret = register_pernet_subsys(&ip6table_security_net_ops); if (ret < 0) { kfree(sectbl_ops); + xt_unregister_template(&security_table); return ret; } - ret = ip6table_security_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&ip6table_security_net_ops); - kfree(sectbl_ops); - } return ret; } static void __exit ip6table_security_fini(void) { unregister_pernet_subsys(&ip6table_security_net_ops); + xt_unregister_template(&security_table); kfree(sectbl_ops); } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 84e58ee501a4..25524e393349 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -39,6 +39,20 @@ MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); #define XT_PCPU_BLOCK_SIZE 4096 #define XT_MAX_TABLE_SIZE (512 * 1024 * 1024) +struct xt_template { + struct list_head list; + + /* called when table is needed in the given netns */ + int (*table_init)(struct net *net); + + struct module *me; + + /* A unique name... */ + char name[XT_TABLE_MAXNAMELEN]; +}; + +static struct list_head xt_templates[NFPROTO_NUMPROTO]; + struct xt_pernet { struct list_head tables[NFPROTO_NUMPROTO]; }; @@ -1221,48 +1235,43 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); - struct xt_table *t, *found = NULL; + struct module *owner = NULL; + struct xt_template *tmpl; + struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0 && try_module_get(t->me)) return t; - if (net == &init_net) - goto out; - - /* Table doesn't exist in this netns, re-try init */ - xt_net = net_generic(&init_net, xt_pernet_id); - list_for_each_entry(t, &xt_net->tables[af], list) { + /* Table doesn't exist in this netns, check larval list */ + list_for_each_entry(tmpl, &xt_templates[af], list) { int err; - if (strcmp(t->name, name)) + if (strcmp(tmpl->name, name)) continue; - if (!try_module_get(t->me)) + if (!try_module_get(tmpl->me)) goto out; + + owner = tmpl->me; + mutex_unlock(&xt[af].mutex); - err = t->table_init(net); + err = tmpl->table_init(net); if (err < 0) { - module_put(t->me); + module_put(owner); return ERR_PTR(err); } - found = t; - mutex_lock(&xt[af].mutex); break; } - if (!found) - goto out; - - xt_net = net_generic(net, xt_pernet_id); /* and once again: */ list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0) return t; - module_put(found->me); + module_put(owner); out: mutex_unlock(&xt[af].mutex); return ERR_PTR(-ENOENT); @@ -1749,6 +1758,58 @@ xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn) } EXPORT_SYMBOL_GPL(xt_hook_ops_alloc); +int xt_register_template(const struct xt_table *table, + int (*table_init)(struct net *net)) +{ + int ret = -EEXIST, af = table->af; + struct xt_template *t; + + mutex_lock(&xt[af].mutex); + + list_for_each_entry(t, &xt_templates[af], list) { + if (WARN_ON_ONCE(strcmp(table->name, t->name) == 0)) + goto out_unlock; + } + + ret = -ENOMEM; + t = kzalloc(sizeof(*t), GFP_KERNEL); + if (!t) + goto out_unlock; + + BUILD_BUG_ON(sizeof(t->name) != sizeof(table->name)); + + strscpy(t->name, table->name, sizeof(t->name)); + t->table_init = table_init; + t->me = table->me; + list_add(&t->list, &xt_templates[af]); + ret = 0; +out_unlock: + mutex_unlock(&xt[af].mutex); + return ret; +} +EXPORT_SYMBOL_GPL(xt_register_template); + +void xt_unregister_template(const struct xt_table *table) +{ + struct xt_template *t; + int af = table->af; + + mutex_lock(&xt[af].mutex); + list_for_each_entry(t, &xt_templates[af], list) { + if (strcmp(table->name, t->name)) + continue; + + list_del(&t->list); + mutex_unlock(&xt[af].mutex); + kfree(t); + return; + } + + mutex_unlock(&xt[af].mutex); + WARN_ON_ONCE(1); +} +EXPORT_SYMBOL_GPL(xt_unregister_template); + int xt_proto_init(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS @@ -1937,6 +1998,7 @@ static int __init xt_init(void) #endif INIT_LIST_HEAD(&xt[i].target); INIT_LIST_HEAD(&xt[i].match); + INIT_LIST_HEAD(&xt_templates[i]); } rv = register_pernet_subsys(&xt_net_ops); if (rv < 0) -- cgit v1.2.3 From 9050ad816f5205c0d069e3e492eb849265ae5167 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 2 Aug 2021 01:33:14 +0200 Subject: mfd: db8500-prcmu: Handle missing FW variant There was an "unknown" firmware variant turning up in the wild causing problems in the clock driver. Add this missing variant and clarify that varian 11 and 15 are Samsung variants, as this is now very well known from released products. Signed-off-by: Linus Walleij Acked-by: Stephen Boyd Signed-off-by: Lee Jones --- drivers/clk/ux500/u8500_of_clk.c | 3 ++- drivers/mfd/db8500-prcmu.c | 6 ++++-- include/linux/mfd/dbx500-prcmu.h | 3 ++- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/clk/ux500/u8500_of_clk.c b/drivers/clk/ux500/u8500_of_clk.c index 0aedd42fad52..528c5bb397cc 100644 --- a/drivers/clk/ux500/u8500_of_clk.c +++ b/drivers/clk/ux500/u8500_of_clk.c @@ -99,10 +99,11 @@ static void u8500_clk_init(struct device_node *np) if (fw_version != NULL) { switch (fw_version->project) { case PRCMU_FW_PROJECT_U8500_C2: - case PRCMU_FW_PROJECT_U8500_MBL: + case PRCMU_FW_PROJECT_U8500_SSG1: case PRCMU_FW_PROJECT_U8520: case PRCMU_FW_PROJECT_U8420: case PRCMU_FW_PROJECT_U8420_SYSCLK: + case PRCMU_FW_PROJECT_U8500_SSG2: sgaclk_parent = "soc0_pll"; break; default: diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c index 82058d11099f..75049cf38832 100644 --- a/drivers/mfd/db8500-prcmu.c +++ b/drivers/mfd/db8500-prcmu.c @@ -2565,14 +2565,16 @@ static char *fw_project_name(u32 project) return "U8500 C4"; case PRCMU_FW_PROJECT_U9500_MBL: return "U9500 MBL"; - case PRCMU_FW_PROJECT_U8500_MBL: - return "U8500 MBL"; + case PRCMU_FW_PROJECT_U8500_SSG1: + return "U8500 Samsung 1"; case PRCMU_FW_PROJECT_U8500_MBL2: return "U8500 MBL2"; case PRCMU_FW_PROJECT_U8520: return "U8520 MBL"; case PRCMU_FW_PROJECT_U8420: return "U8420"; + case PRCMU_FW_PROJECT_U8500_SSG2: + return "U8500 Samsung 2"; case PRCMU_FW_PROJECT_U8420_SYSCLK: return "U8420-sysclk"; case PRCMU_FW_PROJECT_U9540: diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index e6ee2ec35de9..cbf9d7619493 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -186,10 +186,11 @@ enum ddr_pwrst { #define PRCMU_FW_PROJECT_U8500_C3 8 #define PRCMU_FW_PROJECT_U8500_C4 9 #define PRCMU_FW_PROJECT_U9500_MBL 10 -#define PRCMU_FW_PROJECT_U8500_MBL 11 /* Customer specific */ +#define PRCMU_FW_PROJECT_U8500_SSG1 11 /* Samsung specific */ #define PRCMU_FW_PROJECT_U8500_MBL2 12 /* Customer specific */ #define PRCMU_FW_PROJECT_U8520 13 #define PRCMU_FW_PROJECT_U8420 14 +#define PRCMU_FW_PROJECT_U8500_SSG2 15 /* Samsung specific */ #define PRCMU_FW_PROJECT_U8420_SYSCLK 17 #define PRCMU_FW_PROJECT_A9420 20 /* [32..63] 9540 and derivatives */ -- cgit v1.2.3 From e390909ac763589558ffb91856f121820f933e4b Mon Sep 17 00:00:00 2001 From: Sanjay R Mehta Date: Fri, 6 Aug 2021 11:59:05 -0500 Subject: thunderbolt: Add vendor specific NHI quirk for auto-clearing interrupt status Introduce nhi_check_quirks() routine to handle any vendor specific quirks to manage a hardware specific implementation. On Intel hardware the USB4 controller supports clearing the interrupt status register automatically right after it is being issued. For this reason add a new quirk that does that on all Intel hardware. Signed-off-by: Basavaraj Natikar Signed-off-by: Sanjay R Mehta Signed-off-by: Mika Westerberg --- drivers/thunderbolt/nhi.c | 33 +++++++++++++++++++++++++-------- include/linux/thunderbolt.h | 2 ++ 2 files changed, 27 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index fa44332845a1..c7a2841ed3b7 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -35,6 +35,8 @@ #define NHI_MAILBOX_TIMEOUT 500 /* ms */ +#define QUIRK_AUTO_CLEAR_INT BIT(0) + static int ring_interrupt_index(struct tb_ring *ring) { int bit = ring->hop; @@ -66,14 +68,17 @@ static void ring_interrupt_active(struct tb_ring *ring, bool active) else index = ring->hop + ring->nhi->hop_count; - /* - * Ask the hardware to clear interrupt status bits automatically - * since we already know which interrupt was triggered. - */ - misc = ioread32(ring->nhi->iobase + REG_DMA_MISC); - if (!(misc & REG_DMA_MISC_INT_AUTO_CLEAR)) { - misc |= REG_DMA_MISC_INT_AUTO_CLEAR; - iowrite32(misc, ring->nhi->iobase + REG_DMA_MISC); + if (ring->nhi->quirks & QUIRK_AUTO_CLEAR_INT) { + /* + * Ask the hardware to clear interrupt status + * bits automatically since we already know + * which interrupt was triggered. + */ + misc = ioread32(ring->nhi->iobase + REG_DMA_MISC); + if (!(misc & REG_DMA_MISC_INT_AUTO_CLEAR)) { + misc |= REG_DMA_MISC_INT_AUTO_CLEAR; + iowrite32(misc, ring->nhi->iobase + REG_DMA_MISC); + } } ivr_base = ring->nhi->iobase + REG_INT_VEC_ALLOC_BASE; @@ -1074,6 +1079,16 @@ static void nhi_shutdown(struct tb_nhi *nhi) nhi->ops->shutdown(nhi); } +static void nhi_check_quirks(struct tb_nhi *nhi) +{ + /* + * Intel hardware supports auto clear of the interrupt status + * reqister right after interrupt is being issued. + */ + if (nhi->pdev->vendor == PCI_VENDOR_ID_INTEL) + nhi->quirks |= QUIRK_AUTO_CLEAR_INT; +} + static int nhi_init_msi(struct tb_nhi *nhi) { struct pci_dev *pdev = nhi->pdev; @@ -1190,6 +1205,8 @@ static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!nhi->tx_rings || !nhi->rx_rings) return -ENOMEM; + nhi_check_quirks(nhi); + res = nhi_init_msi(nhi); if (res) { dev_err(&pdev->dev, "cannot enable MSI, aborting\n"); diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index e7c96c37174f..124e13cb1469 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -468,6 +468,7 @@ static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc) * @interrupt_work: Work scheduled to handle ring interrupt when no * MSI-X is used. * @hop_count: Number of rings (end point hops) supported by NHI. + * @quirks: NHI specific quirks if any */ struct tb_nhi { spinlock_t lock; @@ -480,6 +481,7 @@ struct tb_nhi { bool going_away; struct work_struct interrupt_work; u32 hop_count; + unsigned long quirks; }; /** -- cgit v1.2.3 From fffe3cc8c2194f60c4af4fac7f27d25e8828f001 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 29 Jul 2021 14:15:19 -0600 Subject: dma-mapping: allow map_sg() ops to return negative error codes Allow dma_map_sgtable() to pass errors from the map_sg() ops. This will be required for returning appropriate error codes when mapping P2PDMA memory. Introduce __dma_map_sg_attrs() which will return the raw error code from the map_sg operation (whether it be negative or zero). Then add a dma_map_sg_attrs() wrapper to convert any negative errors to zero to satisfy the existing calling convention. dma_map_sgtable() defines three error codes that .map_sg implementations are allowed to return: -EINVAL, -ENOMEM and -EIO. The latter of which is a generic return for cases that are passing DMA_MAPPING_ERROR through. dma_map_sgtable() will convert a zero error return for old map_sg() ops into a -EIO return and return any negative errors as reported. This allows map_sg implementations to start returning multiple negative error codes. Legacy map_sg implementations can continue to return zero until they are all converted. Signed-off-by: Logan Gunthorpe Signed-off-by: Christoph Hellwig --- include/linux/dma-map-ops.h | 5 +-- include/linux/dma-mapping.h | 35 ++++--------------- kernel/dma/mapping.c | 82 ++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 84 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 0d53a96a3d64..2f842498c448 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -41,8 +41,9 @@ struct dma_map_ops { size_t size, enum dma_data_direction dir, unsigned long attrs); /* - * map_sg returns 0 on error and a value > 0 on success. - * It should never return a value < 0. + * map_sg should return a negative error code on error. See + * dma_map_sgtable() for a list of appropriate error codes + * and their meanings. */ int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 183e7103a66d..daa1e360f0ee 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -110,6 +110,8 @@ int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs); +int dma_map_sgtable(struct device *dev, struct sg_table *sgt, + enum dma_data_direction dir, unsigned long attrs); dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs); void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, @@ -174,6 +176,11 @@ static inline void dma_unmap_sg_attrs(struct device *dev, unsigned long attrs) { } +static inline int dma_map_sgtable(struct device *dev, struct sg_table *sgt, + enum dma_data_direction dir, unsigned long attrs) +{ + return -EOPNOTSUPP; +} static inline dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -343,34 +350,6 @@ static inline void dma_sync_single_range_for_device(struct device *dev, return dma_sync_single_for_device(dev, addr + offset, size, dir); } -/** - * dma_map_sgtable - Map the given buffer for DMA - * @dev: The device for which to perform the DMA operation - * @sgt: The sg_table object describing the buffer - * @dir: DMA direction - * @attrs: Optional DMA attributes for the map operation - * - * Maps a buffer described by a scatterlist stored in the given sg_table - * object for the @dir DMA operation by the @dev device. After success the - * ownership for the buffer is transferred to the DMA domain. One has to - * call dma_sync_sgtable_for_cpu() or dma_unmap_sgtable() to move the - * ownership of the buffer back to the CPU domain before touching the - * buffer by the CPU. - * - * Returns 0 on success or -EINVAL on error during mapping the buffer. - */ -static inline int dma_map_sgtable(struct device *dev, struct sg_table *sgt, - enum dma_data_direction dir, unsigned long attrs) -{ - int nents; - - nents = dma_map_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs); - if (nents <= 0) - return -EINVAL; - sgt->nents = nents; - return 0; -} - /** * dma_unmap_sgtable - Unmap the given buffer for DMA * @dev: The device for which to perform the DMA operation diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 2b06a809d0b9..21e550076be5 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -177,12 +177,8 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, } EXPORT_SYMBOL(dma_unmap_page_attrs); -/* - * dma_maps_sg_attrs returns 0 on error and > 0 on success. - * It should never return a value < 0. - */ -int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs) +static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); int ents; @@ -197,13 +193,83 @@ int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, ents = dma_direct_map_sg(dev, sg, nents, dir, attrs); else ents = ops->map_sg(dev, sg, nents, dir, attrs); - BUG_ON(ents < 0); - debug_dma_map_sg(dev, sg, nents, ents, dir); + + if (ents > 0) + debug_dma_map_sg(dev, sg, nents, ents, dir); + else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM && + ents != -EIO && ents != 0)) + return -EIO; return ents; } + +/** + * dma_map_sg_attrs - Map the given buffer for DMA + * @dev: The device for which to perform the DMA operation + * @sg: The sg_table object describing the buffer + * @dir: DMA direction + * @attrs: Optional DMA attributes for the map operation + * + * Maps a buffer described by a scatterlist passed in the sg argument with + * nents segments for the @dir DMA operation by the @dev device. + * + * Returns the number of mapped entries (which can be less than nents) + * on success. Zero is returned for any error. + * + * dma_unmap_sg_attrs() should be used to unmap the buffer with the + * original sg and original nents (not the value returned by this funciton). + */ +int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + int ret; + + ret = __dma_map_sg_attrs(dev, sg, nents, dir, attrs); + if (ret < 0) + return 0; + return ret; +} EXPORT_SYMBOL(dma_map_sg_attrs); +/** + * dma_map_sgtable - Map the given buffer for DMA + * @dev: The device for which to perform the DMA operation + * @sgt: The sg_table object describing the buffer + * @dir: DMA direction + * @attrs: Optional DMA attributes for the map operation + * + * Maps a buffer described by a scatterlist stored in the given sg_table + * object for the @dir DMA operation by the @dev device. After success, the + * ownership for the buffer is transferred to the DMA domain. One has to + * call dma_sync_sgtable_for_cpu() or dma_unmap_sgtable() to move the + * ownership of the buffer back to the CPU domain before touching the + * buffer by the CPU. + * + * Returns 0 on success or a negative error code on error. The following + * error codes are supported with the given meaning: + * + * -EINVAL - An invalid argument, unaligned access or other error + * in usage. Will not succeed if retried. + * -ENOMEM - Insufficient resources (like memory or IOVA space) to + * complete the mapping. Should succeed if retried later. + * -EIO - Legacy error code with an unknown meaning. eg. this is + * returned if a lower level call returned DMA_MAPPING_ERROR. + */ +int dma_map_sgtable(struct device *dev, struct sg_table *sgt, + enum dma_data_direction dir, unsigned long attrs) +{ + int nents; + + nents = __dma_map_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs); + if (nents == 0) + return -EIO; + if (nents < 0) + return nents; + sgt->nents = nents; + return 0; +} +EXPORT_SYMBOL_GPL(dma_map_sgtable); + void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs) -- cgit v1.2.3 From ad8f36e4b6b1c826a0daa5fda2c5839205b5aa8b Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 29 Jul 2021 14:15:21 -0600 Subject: iommu: return full error code from iommu_map_sg[_atomic]() Convert to ssize_t return code so the return code from __iommu_map() can be returned all the way down through dma_iommu_map_sg(). Signed-off-by: Logan Gunthorpe Cc: Joerg Roedel Cc: Will Deacon Signed-off-by: Christoph Hellwig --- drivers/iommu/iommu.c | 15 +++++++-------- include/linux/iommu.h | 22 +++++++++++----------- 2 files changed, 18 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 5419c4b9f27a..bf971b4e34aa 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2567,9 +2567,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_unmap_fast); -static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot, - gfp_t gfp) +static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot, + gfp_t gfp) { const struct iommu_ops *ops = domain->ops; size_t len = 0, mapped = 0; @@ -2610,19 +2610,18 @@ out_err: /* undo mappings already done */ iommu_unmap(domain, iova, mapped); - return 0; - + return ret; } -size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) +ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot) { might_sleep(); return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL); } EXPORT_SYMBOL_GPL(iommu_map_sg); -size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova, +ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) { return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 32d448050bf7..9369458ba1bd 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -414,11 +414,11 @@ extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, extern size_t iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); -extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg,unsigned int nents, int prot); -extern size_t iommu_map_sg_atomic(struct iommu_domain *domain, - unsigned long iova, struct scatterlist *sg, - unsigned int nents, int prot); +extern ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot); +extern ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, + unsigned long iova, struct scatterlist *sg, + unsigned int nents, int prot); extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); @@ -679,18 +679,18 @@ static inline size_t iommu_unmap_fast(struct iommu_domain *domain, return 0; } -static inline size_t iommu_map_sg(struct iommu_domain *domain, - unsigned long iova, struct scatterlist *sg, - unsigned int nents, int prot) +static inline ssize_t iommu_map_sg(struct iommu_domain *domain, + unsigned long iova, struct scatterlist *sg, + unsigned int nents, int prot) { - return 0; + return -ENODEV; } -static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain, +static inline ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) { - return 0; + return -ENODEV; } static inline void iommu_flush_iotlb_all(struct iommu_domain *domain) -- cgit v1.2.3 From c66fd019713e9cf7d6f1243c378cd177d01fe18a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 4 Aug 2021 11:41:40 +0200 Subject: block: make the block holder code optional Move the block holder code into a separate file as it is not in any way related to the other block_dev.c code, and add a new selectable config option for it so that we don't have to build it without any remapped drivers selected. The Kconfig symbol contains a _DEPRECATED suffix to match the comments added in commit 49731baa41df ("block: restore multiple bd_link_disk_holder() support"). Signed-off-by: Christoph Hellwig Reviewed-by: Mike Snitzer Link: https://lore.kernel.org/r/20210804094147.459763-2-hch@lst.de Signed-off-by: Jens Axboe --- block/Kconfig | 4 ++ block/Makefile | 1 + block/holder.c | 139 ++++++++++++++++++++++++++++++++++++++++++++ drivers/md/Kconfig | 2 + drivers/md/bcache/Kconfig | 1 + fs/block_dev.c | 144 +--------------------------------------------- include/linux/blk_types.h | 2 +- include/linux/genhd.h | 4 +- 8 files changed, 151 insertions(+), 146 deletions(-) create mode 100644 block/holder.c (limited to 'include/linux') diff --git a/block/Kconfig b/block/Kconfig index 15dfb7660645..bac87d773c54 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -241,4 +241,8 @@ config BLK_MQ_RDMA config BLK_PM def_bool BLOCK && PM +# do not use in new code +config BLOCK_HOLDER_DEPRECATED + bool + source "block/Kconfig.iosched" diff --git a/block/Makefile b/block/Makefile index c72592b4cf31..0d951adce796 100644 --- a/block/Makefile +++ b/block/Makefile @@ -41,3 +41,4 @@ obj-$(CONFIG_BLK_SED_OPAL) += sed-opal.o obj-$(CONFIG_BLK_PM) += blk-pm.o obj-$(CONFIG_BLK_INLINE_ENCRYPTION) += keyslot-manager.o blk-crypto.o obj-$(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) += blk-crypto-fallback.o +obj-$(CONFIG_BLOCK_HOLDER_DEPRECATED) += holder.o diff --git a/block/holder.c b/block/holder.c new file mode 100644 index 000000000000..904a1dcd5c12 --- /dev/null +++ b/block/holder.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include + +struct bd_holder_disk { + struct list_head list; + struct gendisk *disk; + int refcnt; +}; + +static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev, + struct gendisk *disk) +{ + struct bd_holder_disk *holder; + + list_for_each_entry(holder, &bdev->bd_holder_disks, list) + if (holder->disk == disk) + return holder; + return NULL; +} + +static int add_symlink(struct kobject *from, struct kobject *to) +{ + return sysfs_create_link(from, to, kobject_name(to)); +} + +static void del_symlink(struct kobject *from, struct kobject *to) +{ + sysfs_remove_link(from, kobject_name(to)); +} + +/** + * bd_link_disk_holder - create symlinks between holding disk and slave bdev + * @bdev: the claimed slave bdev + * @disk: the holding disk + * + * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. + * + * This functions creates the following sysfs symlinks. + * + * - from "slaves" directory of the holder @disk to the claimed @bdev + * - from "holders" directory of the @bdev to the holder @disk + * + * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is + * passed to bd_link_disk_holder(), then: + * + * /sys/block/dm-0/slaves/sda --> /sys/block/sda + * /sys/block/sda/holders/dm-0 --> /sys/block/dm-0 + * + * The caller must have claimed @bdev before calling this function and + * ensure that both @bdev and @disk are valid during the creation and + * lifetime of these symlinks. + * + * CONTEXT: + * Might sleep. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) +{ + struct bd_holder_disk *holder; + int ret = 0; + + mutex_lock(&bdev->bd_disk->open_mutex); + + WARN_ON_ONCE(!bdev->bd_holder); + + /* FIXME: remove the following once add_disk() handles errors */ + if (WARN_ON(!disk->slave_dir || !bdev->bd_holder_dir)) + goto out_unlock; + + holder = bd_find_holder_disk(bdev, disk); + if (holder) { + holder->refcnt++; + goto out_unlock; + } + + holder = kzalloc(sizeof(*holder), GFP_KERNEL); + if (!holder) { + ret = -ENOMEM; + goto out_unlock; + } + + INIT_LIST_HEAD(&holder->list); + holder->disk = disk; + holder->refcnt = 1; + + ret = add_symlink(disk->slave_dir, bdev_kobj(bdev)); + if (ret) + goto out_free; + + ret = add_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); + if (ret) + goto out_del; + /* + * bdev could be deleted beneath us which would implicitly destroy + * the holder directory. Hold on to it. + */ + kobject_get(bdev->bd_holder_dir); + + list_add(&holder->list, &bdev->bd_holder_disks); + goto out_unlock; + +out_del: + del_symlink(disk->slave_dir, bdev_kobj(bdev)); +out_free: + kfree(holder); +out_unlock: + mutex_unlock(&bdev->bd_disk->open_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(bd_link_disk_holder); + +/** + * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder() + * @bdev: the calimed slave bdev + * @disk: the holding disk + * + * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. + * + * CONTEXT: + * Might sleep. + */ +void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) +{ + struct bd_holder_disk *holder; + + mutex_lock(&bdev->bd_disk->open_mutex); + holder = bd_find_holder_disk(bdev, disk); + if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { + del_symlink(disk->slave_dir, bdev_kobj(bdev)); + del_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); + kobject_put(bdev->bd_holder_dir); + list_del_init(&holder->list); + kfree(holder); + } + mutex_unlock(&bdev->bd_disk->open_mutex); +} +EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 0602e82a9516..f821dae101a9 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -15,6 +15,7 @@ if MD config BLK_DEV_MD tristate "RAID support" + select BLOCK_HOLDER_DEPRECATED if SYSFS help This driver lets you combine several hard disk partitions into one logical block device. This can be used to simply append one @@ -201,6 +202,7 @@ config BLK_DEV_DM_BUILTIN config BLK_DEV_DM tristate "Device mapper support" + select BLOCK_HOLDER_DEPRECATED if SYSFS select BLK_DEV_DM_BUILTIN depends on DAX || DAX=n help diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig index d1ca4d059c20..cf3e8096942a 100644 --- a/drivers/md/bcache/Kconfig +++ b/drivers/md/bcache/Kconfig @@ -2,6 +2,7 @@ config BCACHE tristate "Block device as cache" + select BLOCK_HOLDER_DEPRECATED if SYSFS select CRC64 help Allows a block device to be used as cache for other devices; uses diff --git a/fs/block_dev.c b/fs/block_dev.c index 6658f40ae492..ae9651cad923 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -902,7 +902,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) bdev->bd_disk = disk; bdev->bd_partno = partno; bdev->bd_inode = inode; -#ifdef CONFIG_SYSFS +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED INIT_LIST_HEAD(&bdev->bd_holder_disks); #endif bdev->bd_stats = alloc_percpu(struct disk_stats); @@ -1063,148 +1063,6 @@ void bd_abort_claiming(struct block_device *bdev, void *holder) } EXPORT_SYMBOL(bd_abort_claiming); -#ifdef CONFIG_SYSFS -struct bd_holder_disk { - struct list_head list; - struct gendisk *disk; - int refcnt; -}; - -static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev, - struct gendisk *disk) -{ - struct bd_holder_disk *holder; - - list_for_each_entry(holder, &bdev->bd_holder_disks, list) - if (holder->disk == disk) - return holder; - return NULL; -} - -static int add_symlink(struct kobject *from, struct kobject *to) -{ - return sysfs_create_link(from, to, kobject_name(to)); -} - -static void del_symlink(struct kobject *from, struct kobject *to) -{ - sysfs_remove_link(from, kobject_name(to)); -} - -/** - * bd_link_disk_holder - create symlinks between holding disk and slave bdev - * @bdev: the claimed slave bdev - * @disk: the holding disk - * - * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. - * - * This functions creates the following sysfs symlinks. - * - * - from "slaves" directory of the holder @disk to the claimed @bdev - * - from "holders" directory of the @bdev to the holder @disk - * - * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is - * passed to bd_link_disk_holder(), then: - * - * /sys/block/dm-0/slaves/sda --> /sys/block/sda - * /sys/block/sda/holders/dm-0 --> /sys/block/dm-0 - * - * The caller must have claimed @bdev before calling this function and - * ensure that both @bdev and @disk are valid during the creation and - * lifetime of these symlinks. - * - * CONTEXT: - * Might sleep. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) -{ - struct bd_holder_disk *holder; - int ret = 0; - - mutex_lock(&bdev->bd_disk->open_mutex); - - WARN_ON_ONCE(!bdev->bd_holder); - - /* FIXME: remove the following once add_disk() handles errors */ - if (WARN_ON(!disk->slave_dir || !bdev->bd_holder_dir)) - goto out_unlock; - - holder = bd_find_holder_disk(bdev, disk); - if (holder) { - holder->refcnt++; - goto out_unlock; - } - - holder = kzalloc(sizeof(*holder), GFP_KERNEL); - if (!holder) { - ret = -ENOMEM; - goto out_unlock; - } - - INIT_LIST_HEAD(&holder->list); - holder->disk = disk; - holder->refcnt = 1; - - ret = add_symlink(disk->slave_dir, bdev_kobj(bdev)); - if (ret) - goto out_free; - - ret = add_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); - if (ret) - goto out_del; - /* - * bdev could be deleted beneath us which would implicitly destroy - * the holder directory. Hold on to it. - */ - kobject_get(bdev->bd_holder_dir); - - list_add(&holder->list, &bdev->bd_holder_disks); - goto out_unlock; - -out_del: - del_symlink(disk->slave_dir, bdev_kobj(bdev)); -out_free: - kfree(holder); -out_unlock: - mutex_unlock(&bdev->bd_disk->open_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(bd_link_disk_holder); - -/** - * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder() - * @bdev: the calimed slave bdev - * @disk: the holding disk - * - * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. - * - * CONTEXT: - * Might sleep. - */ -void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) -{ - struct bd_holder_disk *holder; - - mutex_lock(&bdev->bd_disk->open_mutex); - - holder = bd_find_holder_disk(bdev, disk); - - if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { - del_symlink(disk->slave_dir, bdev_kobj(bdev)); - del_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); - kobject_put(bdev->bd_holder_dir); - list_del_init(&holder->list); - kfree(holder); - } - - mutex_unlock(&bdev->bd_disk->open_mutex); -} -EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); -#endif - static void blkdev_flush_mapping(struct block_device *bdev) { WARN_ON_ONCE(bdev->bd_holders); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 290f9061b29a..7a4e139d24ef 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -34,7 +34,7 @@ struct block_device { void * bd_holder; int bd_holders; bool bd_write_holder; -#ifdef CONFIG_SYSFS +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED struct list_head bd_holder_disks; #endif struct kobject *bd_holder_dir; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 849486de81c6..e21a91c16a79 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -318,7 +318,7 @@ void set_capacity(struct gendisk *disk, sector_t size); int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); -#ifdef CONFIG_SYSFS +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); #else @@ -331,7 +331,7 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { } -#endif /* CONFIG_SYSFS */ +#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ dev_t part_devt(struct gendisk *disk, u8 partno); void inc_diskseq(struct gendisk *disk); -- cgit v1.2.3 From 0dbcfe247f22a6d73302dfa691c48b3c14d31c4c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 4 Aug 2021 11:41:42 +0200 Subject: block: look up holders by bdev Invert they way the holder relations are tracked. This very slightly reduces the memory overhead for partitioned devices. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210804094147.459763-4-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 4 +++- block/holder.c | 18 +++++++++--------- fs/block_dev.c | 3 --- include/linux/blk_types.h | 3 --- include/linux/genhd.h | 4 +++- 5 files changed, 15 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index a4817e42f3a3..cd4eab744667 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1289,7 +1289,9 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) disk_to_dev(disk)->type = &disk_type; device_initialize(disk_to_dev(disk)); inc_diskseq(disk); - +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED + INIT_LIST_HEAD(&disk->slave_bdevs); +#endif return disk; out_destroy_part_tbl: diff --git a/block/holder.c b/block/holder.c index 960654a71342..11e65d99a9fb 100644 --- a/block/holder.c +++ b/block/holder.c @@ -3,7 +3,7 @@ struct bd_holder_disk { struct list_head list; - struct gendisk *disk; + struct block_device *bdev; int refcnt; }; @@ -12,8 +12,8 @@ static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev, { struct bd_holder_disk *holder; - list_for_each_entry(holder, &bdev->bd_holder_disks, list) - if (holder->disk == disk) + list_for_each_entry(holder, &disk->slave_bdevs, list) + if (holder->bdev == bdev) return holder; return NULL; } @@ -61,7 +61,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) struct bd_holder_disk *holder; int ret = 0; - mutex_lock(&bdev->bd_disk->open_mutex); + mutex_lock(&disk->open_mutex); WARN_ON_ONCE(!bdev->bd_holder); @@ -82,7 +82,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) } INIT_LIST_HEAD(&holder->list); - holder->disk = disk; + holder->bdev = bdev; holder->refcnt = 1; ret = add_symlink(disk->slave_dir, bdev_kobj(bdev)); @@ -93,7 +93,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) if (ret) goto out_del; - list_add(&holder->list, &bdev->bd_holder_disks); + list_add(&holder->list, &disk->slave_bdevs); goto out_unlock; out_del: @@ -101,7 +101,7 @@ out_del: out_free: kfree(holder); out_unlock: - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); return ret; } EXPORT_SYMBOL_GPL(bd_link_disk_holder); @@ -120,7 +120,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { struct bd_holder_disk *holder; - mutex_lock(&bdev->bd_disk->open_mutex); + mutex_lock(&disk->open_mutex); holder = bd_find_holder_disk(bdev, disk); if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { del_symlink(disk->slave_dir, bdev_kobj(bdev)); @@ -128,6 +128,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) list_del_init(&holder->list); kfree(holder); } - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); } EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); diff --git a/fs/block_dev.c b/fs/block_dev.c index ae9651cad923..cc801767a377 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -902,9 +902,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) bdev->bd_disk = disk; bdev->bd_partno = partno; bdev->bd_inode = inode; -#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED - INIT_LIST_HEAD(&bdev->bd_holder_disks); -#endif bdev->bd_stats = alloc_percpu(struct disk_stats); if (!bdev->bd_stats) { iput(inode); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 7a4e139d24ef..e92735655684 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -34,9 +34,6 @@ struct block_device { void * bd_holder; int bd_holders; bool bd_write_holder; -#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED - struct list_head bd_holder_disks; -#endif struct kobject *bd_holder_dir; u8 bd_partno; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index e21a91c16a79..0721807d76ee 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -159,7 +159,9 @@ struct gendisk { unsigned open_partitions; /* number of open partitions */ struct kobject *slave_dir; - +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED + struct list_head slave_bdevs; +#endif struct timer_rand_state *random; atomic_t sync_io; /* RAID */ struct disk_events *ev; -- cgit v1.2.3 From d626338735909bc2b2e7cafc332f44ed41cfdeee Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 4 Aug 2021 11:41:43 +0200 Subject: block: support delayed holder registration device mapper needs to register holders before it is ready to do I/O. Currently it does so by registering the disk early, which can leave the disk and queue in a weird half state where the queue is registered with the disk, except for sysfs and the elevator. And this state has been a bit promlematic before, and will get more so when sorting out the responsibilities between the queue and the disk. Support registering holders on an initialized but not registered disk instead by delaying the sysfs registration until the disk is registered. Signed-off-by: Christoph Hellwig Reviewed-by: Mike Snitzer Link: https://lore.kernel.org/r/20210804094147.459763-5-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 10 ++++++++ block/holder.c | 68 ++++++++++++++++++++++++++++++++++++++------------- include/linux/genhd.h | 5 ++++ 3 files changed, 66 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index cd4eab744667..db916f779077 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -447,6 +447,16 @@ static void register_disk(struct device *parent, struct gendisk *disk, kobject_create_and_add("holders", &ddev->kobj); disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); + /* + * XXX: this is a mess, can't wait for real error handling in add_disk. + * Make sure ->slave_dir is NULL if we failed some of the registration + * so that the cleanup in bd_unlink_disk_holder works properly. + */ + if (bd_register_pending_holders(disk) < 0) { + kobject_put(disk->slave_dir); + disk->slave_dir = NULL; + } + if (disk->flags & GENHD_FL_HIDDEN) return; diff --git a/block/holder.c b/block/holder.c index 11e65d99a9fb..4568cc4f6827 100644 --- a/block/holder.c +++ b/block/holder.c @@ -28,6 +28,19 @@ static void del_symlink(struct kobject *from, struct kobject *to) sysfs_remove_link(from, kobject_name(to)); } +static int __link_disk_holder(struct block_device *bdev, struct gendisk *disk) +{ + int ret; + + ret = add_symlink(disk->slave_dir, bdev_kobj(bdev)); + if (ret) + return ret; + ret = add_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); + if (ret) + del_symlink(disk->slave_dir, bdev_kobj(bdev)); + return ret; +} + /** * bd_link_disk_holder - create symlinks between holding disk and slave bdev * @bdev: the claimed slave bdev @@ -66,7 +79,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) WARN_ON_ONCE(!bdev->bd_holder); /* FIXME: remove the following once add_disk() handles errors */ - if (WARN_ON(!disk->slave_dir || !bdev->bd_holder_dir)) + if (WARN_ON(!bdev->bd_holder_dir)) goto out_unlock; holder = bd_find_holder_disk(bdev, disk); @@ -84,28 +97,28 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) INIT_LIST_HEAD(&holder->list); holder->bdev = bdev; holder->refcnt = 1; - - ret = add_symlink(disk->slave_dir, bdev_kobj(bdev)); - if (ret) - goto out_free; - - ret = add_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); - if (ret) - goto out_del; + if (disk->slave_dir) { + ret = __link_disk_holder(bdev, disk); + if (ret) { + kfree(holder); + goto out_unlock; + } + } list_add(&holder->list, &disk->slave_bdevs); - goto out_unlock; - -out_del: - del_symlink(disk->slave_dir, bdev_kobj(bdev)); -out_free: - kfree(holder); out_unlock: mutex_unlock(&disk->open_mutex); return ret; } EXPORT_SYMBOL_GPL(bd_link_disk_holder); +static void __unlink_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ + del_symlink(disk->slave_dir, bdev_kobj(bdev)); + del_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); +} + /** * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder() * @bdev: the calimed slave bdev @@ -123,11 +136,32 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) mutex_lock(&disk->open_mutex); holder = bd_find_holder_disk(bdev, disk); if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { - del_symlink(disk->slave_dir, bdev_kobj(bdev)); - del_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj); + if (disk->slave_dir) + __unlink_disk_holder(bdev, disk); list_del_init(&holder->list); kfree(holder); } mutex_unlock(&disk->open_mutex); } EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); + +int bd_register_pending_holders(struct gendisk *disk) +{ + struct bd_holder_disk *holder; + int ret; + + mutex_lock(&disk->open_mutex); + list_for_each_entry(holder, &disk->slave_bdevs, list) { + ret = __link_disk_holder(holder->bdev, disk); + if (ret) + goto out_undo; + } + mutex_unlock(&disk->open_mutex); + return 0; + +out_undo: + list_for_each_entry_continue_reverse(holder, &disk->slave_bdevs, list) + __unlink_disk_holder(holder->bdev, disk); + mutex_unlock(&disk->open_mutex); + return ret; +} diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 0721807d76ee..80952f038d79 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -323,6 +323,7 @@ long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); +int bd_register_pending_holders(struct gendisk *disk); #else static inline int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) @@ -333,6 +334,10 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { } +static inline int bd_register_pending_holders(struct gendisk *disk) +{ + return 0; +} #endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ dev_t part_devt(struct gendisk *disk, u8 partno); -- cgit v1.2.3 From d1254a8749711e0d7441036a74ce592341f89697 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 4 Aug 2021 11:41:47 +0200 Subject: block: remove support for delayed queue registrations Now that device mapper has been changed to register the disk once it is fully ready all this code is unused. Signed-off-by: Christoph Hellwig Reviewed-by: Mike Snitzer Link: https://lore.kernel.org/r/20210804094147.459763-9-hch@lst.de Signed-off-by: Jens Axboe --- block/elevator.c | 1 - block/genhd.c | 29 +++++++---------------------- include/linux/genhd.h | 6 ------ 3 files changed, 7 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/block/elevator.c b/block/elevator.c index d0295e68f481..9beaafd238e0 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -705,7 +705,6 @@ void elevator_init_mq(struct request_queue *q) elevator_put(e); } } -EXPORT_SYMBOL_GPL(elevator_init_mq); /* only for dm-rq */ /* * switch to new_e io scheduler. be careful not to introduce deadlocks - diff --git a/block/genhd.c b/block/genhd.c index db916f779077..b0b6e0caa389 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -475,20 +475,20 @@ static void register_disk(struct device *parent, struct gendisk *disk, } /** - * __device_add_disk - add disk information to kernel list + * device_add_disk - add disk information to kernel list * @parent: parent device for the disk * @disk: per-device partitioning information * @groups: Additional per-device sysfs groups - * @register_queue: register the queue if set to true * * This function registers the partitioning information in @disk * with the kernel. * * FIXME: error handling */ -static void __device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups, - bool register_queue) + +void device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups) + { int ret; @@ -498,8 +498,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, * elevator if one is needed, that is, for devices requesting queue * registration. */ - if (register_queue) - elevator_init_mq(disk->queue); + elevator_init_mq(disk->queue); /* * If the driver provides an explicit major number it also must provide @@ -553,8 +552,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, bdev_add(disk->part0, dev->devt); } register_disk(parent, disk, groups); - if (register_queue) - blk_register_queue(disk); + blk_register_queue(disk); /* * Take an extra ref on queue which will be put on disk_release() @@ -568,21 +566,8 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, disk_add_events(disk); blk_integrity_add(disk); } - -void device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups) - -{ - __device_add_disk(parent, disk, groups, true); -} EXPORT_SYMBOL(device_add_disk); -void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk) -{ - __device_add_disk(parent, disk, NULL, false); -} -EXPORT_SYMBOL(device_add_disk_no_queue_reg); - /** * del_gendisk - remove the gendisk * @disk: the struct gendisk to remove diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 80952f038d79..473d93c6ebda 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -219,12 +219,6 @@ static inline void add_disk(struct gendisk *disk) { device_add_disk(NULL, disk, NULL); } -extern void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk); -static inline void add_disk_no_queue_reg(struct gendisk *disk) -{ - device_add_disk_no_queue_reg(NULL, disk); -} - extern void del_gendisk(struct gendisk *gp); void set_disk_ro(struct gendisk *disk, bool read_only); -- cgit v1.2.3 From 471aa704db4904f7af5a50019ca3b5b018c0cf62 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 9 Aug 2021 16:17:41 +0200 Subject: block: pass a gendisk to blk_queue_update_readahead .. and rename the function to disk_update_readahead. This is in preparation for moving the BDI from the request_queue to the gendisk. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210809141744.1203023-3-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-settings.c | 8 +++++--- block/blk-sysfs.c | 2 +- drivers/block/drbd/drbd_nl.c | 2 +- drivers/md/dm-table.c | 2 +- drivers/nvme/host/core.c | 2 +- include/linux/blkdev.h | 2 +- 6 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/block/blk-settings.c b/block/blk-settings.c index 109012719aa0..44aaef9bf736 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -380,8 +380,10 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset) } EXPORT_SYMBOL(blk_queue_alignment_offset); -void blk_queue_update_readahead(struct request_queue *q) +void disk_update_readahead(struct gendisk *disk) { + struct request_queue *q = disk->queue; + /* * For read-ahead of large files to be effective, we need to read ahead * at least twice the optimal I/O size. @@ -391,7 +393,7 @@ void blk_queue_update_readahead(struct request_queue *q) q->backing_dev_info->io_pages = queue_max_sectors(q) >> (PAGE_SHIFT - 9); } -EXPORT_SYMBOL_GPL(blk_queue_update_readahead); +EXPORT_SYMBOL_GPL(disk_update_readahead); /** * blk_limits_io_min - set minimum request size for a device @@ -665,7 +667,7 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, pr_notice("%s: Warning: Device %pg is misaligned\n", disk->disk_name, bdev); - blk_queue_update_readahead(disk->queue); + disk_update_readahead(disk); } EXPORT_SYMBOL(disk_stack_limits); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 370d83c18057..3af2ab7d5086 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -866,7 +866,7 @@ int blk_register_queue(struct gendisk *disk) "%s is registering an already registered queue\n", kobject_name(&dev->kobj)); - blk_queue_update_readahead(q); + disk_update_readahead(disk); ret = blk_trace_init_sysfs(dev); if (ret) diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index e7d0e637e632..44ccf8b4f4b2 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1364,7 +1364,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi if (b) { blk_stack_limits(&q->limits, &b->limits, 0); - blk_queue_update_readahead(q); + disk_update_readahead(device->vdisk); } fixup_discard_if_not_supported(q); fixup_write_zeroes(device, q); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 0543cdf89e92..b03eabc1ed7c 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -2076,7 +2076,7 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, } dm_update_keyslot_manager(q, t); - blk_queue_update_readahead(q); + disk_update_readahead(t->md->disk); return 0; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index dfd9dec0c1f6..f6c0a59c4b53 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1890,7 +1890,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) nvme_update_disk_info(ns->head->disk, ns, id); blk_stack_limits(&ns->head->disk->queue->limits, &ns->queue->limits, 0); - blk_queue_update_readahead(ns->head->disk->queue); + disk_update_readahead(ns->head->disk); blk_mq_unfreeze_queue(ns->head->disk->queue); } return 0; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b5c033cf5f26..ac3642c88a4d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1139,7 +1139,7 @@ void blk_queue_zone_write_granularity(struct request_queue *q, unsigned int size); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); -void blk_queue_update_readahead(struct request_queue *q); +void disk_update_readahead(struct gendisk *disk); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); -- cgit v1.2.3 From 1008162b2782a3624d12b0aee8da58bc75d12e19 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 9 Aug 2021 16:17:42 +0200 Subject: block: add a queue_has_disk helper Add a helper to check if a gendisk is associated with a request_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210809141744.1203023-4-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ac3642c88a4d..96f3d9617cd8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -664,6 +664,7 @@ extern void blk_clear_pm_only(struct request_queue *q); dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ (dir), (attrs)) +#define queue_has_disk(q) ((q)->kobj.parent != NULL) #define queue_to_disk(q) (dev_to_disk(kobj_to_dev((q)->kobj.parent))) static inline bool queue_is_mq(struct request_queue *q) -- cgit v1.2.3 From edb0872f44ec9976ea6d052cb4b93cd2d23ac2ba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 9 Aug 2021 16:17:43 +0200 Subject: block: move the bdi from the request_queue to the gendisk The backing device information only makes sense for file system I/O, and thus belongs into the gendisk and not the lower level request_queue structure. Move it there. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210809141744.1203023-5-hch@lst.de Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 4 ++-- block/blk-cgroup.c | 7 +++---- block/blk-core.c | 13 +++---------- block/blk-mq.c | 2 +- block/blk-settings.c | 14 +++++++++----- block/blk-sysfs.c | 26 ++++++++++++-------------- block/blk-wbt.c | 10 +++++----- block/genhd.c | 23 ++++++++++++++--------- drivers/block/drbd/drbd_req.c | 5 ++--- drivers/block/pktcdvd.c | 8 +++----- fs/block_dev.c | 4 ++-- fs/fat/fatent.c | 1 + include/linux/blkdev.h | 3 --- include/linux/genhd.h | 1 + 14 files changed, 58 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 727955918563..1576e858d3a5 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5266,8 +5266,8 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) switch (ioprio_class) { default: pr_err("bdi %s: bfq: bad prio class %d\n", - bdi_dev_name(bfqq->bfqd->queue->backing_dev_info), - ioprio_class); + bdi_dev_name(queue_to_disk(bfqq->bfqd->queue)->bdi), + ioprio_class); fallthrough; case IOPRIO_CLASS_NONE: /* diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 575d7a2e7203..db034e35ae20 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -489,10 +489,9 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, const char *blkg_dev_name(struct blkcg_gq *blkg) { - /* some drivers (floppy) instantiate a queue w/o disk registered */ - if (blkg->q->backing_dev_info->dev) - return bdi_dev_name(blkg->q->backing_dev_info); - return NULL; + if (!queue_has_disk(blkg->q) || !queue_to_disk(blkg->q)->bdi->dev) + return NULL; + return bdi_dev_name(queue_to_disk(blkg->q)->bdi); } /** diff --git a/block/blk-core.c b/block/blk-core.c index 5897bc37467d..0874bc2fcdb4 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -14,7 +14,6 @@ */ #include #include -#include #include #include #include @@ -531,13 +530,9 @@ struct request_queue *blk_alloc_queue(int node_id) if (ret) goto fail_id; - q->backing_dev_info = bdi_alloc(node_id); - if (!q->backing_dev_info) - goto fail_split; - q->stats = blk_alloc_queue_stats(); if (!q->stats) - goto fail_stats; + goto fail_split; q->node = node_id; @@ -567,7 +562,7 @@ struct request_queue *blk_alloc_queue(int node_id) if (percpu_ref_init(&q->q_usage_counter, blk_queue_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) - goto fail_bdi; + goto fail_stats; if (blkcg_init_queue(q)) goto fail_ref; @@ -580,10 +575,8 @@ struct request_queue *blk_alloc_queue(int node_id) fail_ref: percpu_ref_exit(&q->q_usage_counter); -fail_bdi: - blk_free_queue_stats(q->stats); fail_stats: - bdi_put(q->backing_dev_info); + blk_free_queue_stats(q->stats); fail_split: bioset_exit(&q->bio_split); fail_id: diff --git a/block/blk-mq.c b/block/blk-mq.c index 2c4ac51e54eb..d2725f94491d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -525,7 +525,7 @@ void blk_mq_free_request(struct request *rq) __blk_mq_dec_active_requests(hctx); if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) - laptop_io_completion(q->backing_dev_info); + laptop_io_completion(queue_to_disk(q)->bdi); rq_qos_done(q, rq); diff --git a/block/blk-settings.c b/block/blk-settings.c index 44aaef9bf736..3613d2cc0688 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -140,7 +141,9 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto limits->logical_block_size >> SECTOR_SHIFT); limits->max_sectors = max_sectors; - q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9); + if (!queue_has_disk(q)) + return; + queue_to_disk(q)->bdi->io_pages = max_sectors >> (PAGE_SHIFT - 9); } EXPORT_SYMBOL(blk_queue_max_hw_sectors); @@ -388,10 +391,9 @@ void disk_update_readahead(struct gendisk *disk) * For read-ahead of large files to be effective, we need to read ahead * at least twice the optimal I/O size. */ - q->backing_dev_info->ra_pages = + disk->bdi->ra_pages = max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES); - q->backing_dev_info->io_pages = - queue_max_sectors(q) >> (PAGE_SHIFT - 9); + disk->bdi->io_pages = queue_max_sectors(q) >> (PAGE_SHIFT - 9); } EXPORT_SYMBOL_GPL(disk_update_readahead); @@ -473,7 +475,9 @@ EXPORT_SYMBOL(blk_limits_io_opt); void blk_queue_io_opt(struct request_queue *q, unsigned int opt) { blk_limits_io_opt(&q->limits, opt); - q->backing_dev_info->ra_pages = + if (!queue_has_disk(q)) + return; + queue_to_disk(q)->bdi->ra_pages = max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES); } EXPORT_SYMBOL(blk_queue_io_opt); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 3af2ab7d5086..1832587dce3a 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -88,9 +88,11 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count) static ssize_t queue_ra_show(struct request_queue *q, char *page) { - unsigned long ra_kb = q->backing_dev_info->ra_pages << - (PAGE_SHIFT - 10); + unsigned long ra_kb; + if (!queue_has_disk(q)) + return -EINVAL; + ra_kb = queue_to_disk(q)->bdi->ra_pages << (PAGE_SHIFT - 10); return queue_var_show(ra_kb, page); } @@ -98,13 +100,14 @@ static ssize_t queue_ra_store(struct request_queue *q, const char *page, size_t count) { unsigned long ra_kb; - ssize_t ret = queue_var_store(&ra_kb, page, count); + ssize_t ret; + if (!queue_has_disk(q)) + return -EINVAL; + ret = queue_var_store(&ra_kb, page, count); if (ret < 0) return ret; - - q->backing_dev_info->ra_pages = ra_kb >> (PAGE_SHIFT - 10); - + queue_to_disk(q)->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); return ret; } @@ -251,7 +254,9 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) spin_lock_irq(&q->queue_lock); q->limits.max_sectors = max_sectors_kb << 1; - q->backing_dev_info->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10); + if (queue_has_disk(q)) + queue_to_disk(q)->bdi->io_pages = + max_sectors_kb >> (PAGE_SHIFT - 10); spin_unlock_irq(&q->queue_lock); return ret; @@ -766,13 +771,6 @@ static void blk_exit_queue(struct request_queue *q) * e.g. blkcg_print_blkgs() to crash. */ blkcg_exit_queue(q); - - /* - * Since the cgroup code may dereference the @q->backing_dev_info - * pointer, only decrease its reference count after having removed the - * association with the block cgroup controller. - */ - bdi_put(q->backing_dev_info); } /** diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 3ed71b8da887..31086afaad9c 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -97,7 +97,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) */ static bool wb_recent_wait(struct rq_wb *rwb) { - struct bdi_writeback *wb = &rwb->rqos.q->backing_dev_info->wb; + struct bdi_writeback *wb = &queue_to_disk(rwb->rqos.q)->bdi->wb; return time_before(jiffies, wb->dirty_sleep + HZ); } @@ -234,7 +234,7 @@ enum { static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) { - struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info; + struct backing_dev_info *bdi = queue_to_disk(rwb->rqos.q)->bdi; struct rq_depth *rqd = &rwb->rq_depth; u64 thislat; @@ -287,7 +287,7 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) static void rwb_trace_step(struct rq_wb *rwb, const char *msg) { - struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info; + struct backing_dev_info *bdi = queue_to_disk(rwb->rqos.q)->bdi; struct rq_depth *rqd = &rwb->rq_depth; trace_wbt_step(bdi, msg, rqd->scale_step, rwb->cur_win_nsec, @@ -359,8 +359,8 @@ static void wb_timer_fn(struct blk_stat_callback *cb) status = latency_exceeded(rwb, cb->stat); - trace_wbt_timer(rwb->rqos.q->backing_dev_info, status, rqd->scale_step, - inflight); + trace_wbt_timer(queue_to_disk(rwb->rqos.q)->bdi, status, + rqd->scale_step, inflight); /* * If we exceeded the latency target, step down. If we did not, diff --git a/block/genhd.c b/block/genhd.c index b0b6e0caa389..f8def1129501 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -466,10 +466,9 @@ static void register_disk(struct device *parent, struct gendisk *disk, dev_set_uevent_suppress(ddev, 0); disk_uevent(disk, KOBJ_ADD); - if (disk->queue->backing_dev_info->dev) { - err = sysfs_create_link(&ddev->kobj, - &disk->queue->backing_dev_info->dev->kobj, - "bdi"); + if (disk->bdi->dev) { + err = sysfs_create_link(&ddev->kobj, &disk->bdi->dev->kobj, + "bdi"); WARN_ON(err); } } @@ -540,15 +539,14 @@ void device_add_disk(struct device *parent, struct gendisk *disk, disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO; disk->flags |= GENHD_FL_NO_PART_SCAN; } else { - struct backing_dev_info *bdi = disk->queue->backing_dev_info; struct device *dev = disk_to_dev(disk); /* Register BDI before referencing it from bdev */ dev->devt = MKDEV(disk->major, disk->first_minor); - ret = bdi_register(bdi, "%u:%u", + ret = bdi_register(disk->bdi, "%u:%u", disk->major, disk->first_minor); WARN_ON(ret); - bdi_set_owner(bdi, dev); + bdi_set_owner(disk->bdi, dev); bdev_add(disk->part0, dev->devt); } register_disk(parent, disk, groups); @@ -615,7 +613,7 @@ void del_gendisk(struct gendisk *disk) * Unregister bdi before releasing device numbers (as they can * get reused and we'd get clashes in sysfs). */ - bdi_unregister(disk->queue->backing_dev_info); + bdi_unregister(disk->bdi); } blk_unregister_queue(disk); @@ -1088,6 +1086,7 @@ static void disk_release(struct device *dev) might_sleep(); + bdi_put(disk->bdi); if (MAJOR(dev->devt) == BLOCK_EXT_MAJOR) blk_free_ext_minor(MINOR(dev->devt)); disk_release_events(disk); @@ -1268,9 +1267,13 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) if (!disk) return NULL; + disk->bdi = bdi_alloc(node_id); + if (!disk->bdi) + goto out_free_disk; + disk->part0 = bdev_alloc(disk, 0); if (!disk->part0) - goto out_free_disk; + goto out_free_bdi; disk->node_id = node_id; mutex_init(&disk->open_mutex); @@ -1292,6 +1295,8 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) out_destroy_part_tbl: xa_destroy(&disk->part_tbl); iput(disk->part0->bd_inode); +out_free_bdi: + bdi_put(disk->bdi); out_free_disk: kfree(disk); return NULL; diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 13beb98a7c5a..5ca233644d70 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -905,13 +905,12 @@ static bool drbd_may_do_local_read(struct drbd_device *device, sector_t sector, static bool remote_due_to_read_balancing(struct drbd_device *device, sector_t sector, enum drbd_read_balancing rbm) { - struct backing_dev_info *bdi; int stripe_shift; switch (rbm) { case RB_CONGESTED_REMOTE: - bdi = device->ldev->backing_bdev->bd_disk->queue->backing_dev_info; - return bdi_read_congested(bdi); + return bdi_read_congested( + device->ldev->backing_bdev->bd_disk->bdi); case RB_LEAST_PENDING: return atomic_read(&device->local_cnt) > atomic_read(&device->ap_pending_cnt) + atomic_read(&device->rs_pending_cnt); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 538446b652de..0f26b2510a75 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1183,10 +1183,8 @@ try_next_bio: wakeup = (pd->write_congestion_on > 0 && pd->bio_queue_size <= pd->write_congestion_off); spin_unlock(&pd->lock); - if (wakeup) { - clear_bdi_congested(pd->disk->queue->backing_dev_info, - BLK_RW_ASYNC); - } + if (wakeup) + clear_bdi_congested(pd->disk->bdi, BLK_RW_ASYNC); pkt->sleep_time = max(PACKET_WAIT_TIME, 1); pkt_set_state(pkt, PACKET_WAITING_STATE); @@ -2366,7 +2364,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) spin_lock(&pd->lock); if (pd->write_congestion_on > 0 && pd->bio_queue_size >= pd->write_congestion_on) { - set_bdi_congested(q->backing_dev_info, BLK_RW_ASYNC); + set_bdi_congested(bio->bi_bdev->bd_disk->bdi, BLK_RW_ASYNC); do { spin_unlock(&pd->lock); congestion_wait(BLK_RW_ASYNC, HZ); diff --git a/fs/block_dev.c b/fs/block_dev.c index cc801767a377..43be5463a4c4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1087,7 +1087,7 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) if (!bdev->bd_openers) { set_init_blocksize(bdev); if (bdev->bd_bdi == &noop_backing_dev_info) - bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); + bdev->bd_bdi = bdi_get(disk->bdi); } if (test_bit(GD_NEED_PART_SCAN, &disk->state)) bdev_disk_changed(disk, false); @@ -1122,7 +1122,7 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode) disk->open_partitions++; set_init_blocksize(part); if (part->bd_bdi == &noop_backing_dev_info) - part->bd_bdi = bdi_get(disk->queue->backing_dev_info); + part->bd_bdi = bdi_get(disk->bdi); done: part->bd_openers++; return 0; diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 860e884e56e8..978ac6751aeb 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -5,6 +5,7 @@ #include #include +#include #include "fat.h" struct fatent_operations { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 96f3d9617cd8..23e1253a8d88 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -398,8 +397,6 @@ struct request_queue { struct blk_mq_hw_ctx **queue_hw_ctx; unsigned int nr_hw_queues; - struct backing_dev_info *backing_dev_info; - /* * The queue owner gets to use this for whatever they like. * ll_rw_blk doesn't touch it. diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 473d93c6ebda..b3bab578f03a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -158,6 +158,7 @@ struct gendisk { struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ + struct backing_dev_info *bdi; struct kobject *slave_dir; #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED struct list_head slave_bdevs; -- cgit v1.2.3 From a11d7fc2d05fb509cd9e33d4093507d6eda3ad53 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 9 Aug 2021 16:17:44 +0200 Subject: block: remove the bd_bdi in struct block_device Just retrieve the bdi from the disk. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210809141744.1203023-6-hch@lst.de Signed-off-by: Jens Axboe --- block/ioctl.c | 7 ++++--- fs/block_dev.c | 13 +------------ fs/nilfs2/super.c | 2 +- fs/super.c | 2 +- fs/xfs/xfs_buf.c | 2 +- include/linux/backing-dev.h | 2 +- include/linux/blk_types.h | 1 - 7 files changed, 9 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/block/ioctl.c b/block/ioctl.c index 0c3a4a53fa11..fff161eaab42 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -506,7 +506,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, case BLKFRASET: if(!capable(CAP_SYS_ADMIN)) return -EACCES; - bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE; + bdev->bd_disk->bdi->ra_pages = (arg * 512) / PAGE_SIZE; return 0; case BLKRRPART: return blkdev_reread_part(bdev, mode); @@ -556,7 +556,8 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKFRAGET: if (!argp) return -EINVAL; - return put_long(argp, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512); + return put_long(argp, + (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: size = i_size_read(bdev->bd_inode); if ((size >> 9) > ~0UL) @@ -628,7 +629,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (!argp) return -EINVAL; return compat_put_long(argp, - (bdev->bd_bdi->ra_pages * PAGE_SIZE) / 512); + (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: size = i_size_read(bdev->bd_inode); if ((size >> 9) > ~0UL) diff --git a/fs/block_dev.c b/fs/block_dev.c index 43be5463a4c4..e1c14c2e0504 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -801,7 +801,6 @@ static struct inode *bdev_alloc_inode(struct super_block *sb) if (!ei) return NULL; memset(&ei->bdev, 0, sizeof(ei->bdev)); - ei->bdev.bd_bdi = &noop_backing_dev_info; return &ei->vfs_inode; } @@ -826,16 +825,11 @@ static void init_once(void *data) static void bdev_evict_inode(struct inode *inode) { - struct block_device *bdev = &BDEV_I(inode)->bdev; truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); /* is it needed here? */ clear_inode(inode); /* Detach inode from wb early as bdi_put() may free bdi->wb */ inode_detach_wb(inode); - if (bdev->bd_bdi != &noop_backing_dev_info) { - bdi_put(bdev->bd_bdi); - bdev->bd_bdi = &noop_backing_dev_info; - } } static const struct super_operations bdev_sops = { @@ -1084,11 +1078,8 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) } } - if (!bdev->bd_openers) { + if (!bdev->bd_openers) set_init_blocksize(bdev); - if (bdev->bd_bdi == &noop_backing_dev_info) - bdev->bd_bdi = bdi_get(disk->bdi); - } if (test_bit(GD_NEED_PART_SCAN, &disk->state)) bdev_disk_changed(disk, false); bdev->bd_openers++; @@ -1121,8 +1112,6 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode) disk->open_partitions++; set_init_blocksize(part); - if (part->bd_bdi == &noop_backing_dev_info) - part->bd_bdi = bdi_get(disk->bdi); done: part->bd_openers++; return 0; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 4abd928b0bc8..f6b2d280aab5 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1053,7 +1053,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_time_gran = 1; sb->s_max_links = NILFS_LINK_MAX; - sb->s_bdi = bdi_get(sb->s_bdev->bd_bdi); + sb->s_bdi = bdi_get(sb->s_bdev->bd_disk->bdi); err = load_nilfs(nilfs, sb); if (err) diff --git a/fs/super.c b/fs/super.c index 91b7f156735b..bcef3a6f4c4b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1203,7 +1203,7 @@ static int set_bdev_super(struct super_block *s, void *data) { s->s_bdev = data; s->s_dev = s->s_bdev->bd_dev; - s->s_bdi = bdi_get(s->s_bdev->bd_bdi); + s->s_bdi = bdi_get(s->s_bdev->bd_disk->bdi); if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue)) s->s_iflags |= SB_I_STABLE_WRITES; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 8ff42b3585e0..3ab73567a0f5 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -844,7 +844,7 @@ xfs_buf_readahead_map( { struct xfs_buf *bp; - if (bdi_read_congested(target->bt_bdev->bd_bdi)) + if (bdi_read_congested(target->bt_bdev->bd_disk->bdi)) return; xfs_buf_read_map(target, map, nmaps, diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 44df4fcef65c..29530859d9ff 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -143,7 +143,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) - return I_BDEV(inode)->bd_bdi; + return I_BDEV(inode)->bd_disk->bdi; #endif return sb->s_bdi; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index e92735655684..1335efa8a1db 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -38,7 +38,6 @@ struct block_device { u8 bd_partno; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; - struct backing_dev_info *bd_bdi; /* The counter of freeze processes */ int bd_fsfreeze_count; -- cgit v1.2.3 From 493b938a14ed78d7e44c33d1c1e349656a16c360 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Tue, 3 Aug 2021 21:06:14 +0900 Subject: counter: Rename counter_signal_value to counter_signal_level Signal values will always be levels so let's be explicit it about it to make the intent of the code clear. Cc: Oleksij Rempel Cc: Kamel Bouhara Acked-by: Syed Nayyar Waris Reviewed-by: David Lechner Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/3f17010abe2415859cea9a5fddabd3c97f635ff5.1627990337.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- drivers/counter/104-quad-8.c | 5 +++-- drivers/counter/counter.c | 12 ++++++------ drivers/counter/interrupt-cnt.c | 4 ++-- drivers/counter/microchip-tcb-capture.c | 4 ++-- include/linux/counter.h | 12 ++++++------ 5 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index d54efdb8d393..b4dd07cf51eb 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -97,7 +97,8 @@ struct quad8 { #define QUAD8_CMR_QUADRATURE_X4 0x18 static int quad8_signal_read(struct counter_device *counter, - struct counter_signal *signal, enum counter_signal_value *val) + struct counter_signal *signal, + enum counter_signal_level *level) { const struct quad8 *const priv = counter->priv; unsigned int state; @@ -109,7 +110,7 @@ static int quad8_signal_read(struct counter_device *counter, state = inb(priv->base + QUAD8_REG_INDEX_INPUT_LEVELS) & BIT(signal->id - 16); - *val = (state) ? COUNTER_SIGNAL_HIGH : COUNTER_SIGNAL_LOW; + *level = (state) ? COUNTER_SIGNAL_LEVEL_HIGH : COUNTER_SIGNAL_LEVEL_LOW; return 0; } diff --git a/drivers/counter/counter.c b/drivers/counter/counter.c index 6a683d086008..cb92673552b5 100644 --- a/drivers/counter/counter.c +++ b/drivers/counter/counter.c @@ -289,9 +289,9 @@ struct counter_signal_unit { struct counter_signal *signal; }; -static const char *const counter_signal_value_str[] = { - [COUNTER_SIGNAL_LOW] = "low", - [COUNTER_SIGNAL_HIGH] = "high" +static const char *const counter_signal_level_str[] = { + [COUNTER_SIGNAL_LEVEL_LOW] = "low", + [COUNTER_SIGNAL_LEVEL_HIGH] = "high" }; static ssize_t counter_signal_show(struct device *dev, @@ -302,13 +302,13 @@ static ssize_t counter_signal_show(struct device *dev, const struct counter_signal_unit *const component = devattr->component; struct counter_signal *const signal = component->signal; int err; - enum counter_signal_value val; + enum counter_signal_level level; - err = counter->ops->signal_read(counter, signal, &val); + err = counter->ops->signal_read(counter, signal, &level); if (err) return err; - return sprintf(buf, "%s\n", counter_signal_value_str[val]); + return sprintf(buf, "%s\n", counter_signal_level_str[level]); } struct counter_name_unit { diff --git a/drivers/counter/interrupt-cnt.c b/drivers/counter/interrupt-cnt.c index 66cac4900327..d06367bef8f0 100644 --- a/drivers/counter/interrupt-cnt.c +++ b/drivers/counter/interrupt-cnt.c @@ -130,7 +130,7 @@ static int interrupt_cnt_function_get(struct counter_device *counter, static int interrupt_cnt_signal_read(struct counter_device *counter, struct counter_signal *signal, - enum counter_signal_value *val) + enum counter_signal_level *level) { struct interrupt_cnt_priv *priv = counter->priv; int ret; @@ -142,7 +142,7 @@ static int interrupt_cnt_signal_read(struct counter_device *counter, if (ret < 0) return ret; - *val = ret ? COUNTER_SIGNAL_HIGH : COUNTER_SIGNAL_LOW; + *level = ret ? COUNTER_SIGNAL_LEVEL_HIGH : COUNTER_SIGNAL_LEVEL_LOW; return 0; } diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c index 0c9a61962911..6be3adf74114 100644 --- a/drivers/counter/microchip-tcb-capture.c +++ b/drivers/counter/microchip-tcb-capture.c @@ -158,7 +158,7 @@ static int mchp_tc_count_function_set(struct counter_device *counter, static int mchp_tc_count_signal_read(struct counter_device *counter, struct counter_signal *signal, - enum counter_signal_value *val) + enum counter_signal_level *lvl) { struct mchp_tc_data *const priv = counter->priv; bool sigstatus; @@ -171,7 +171,7 @@ static int mchp_tc_count_signal_read(struct counter_device *counter, else sigstatus = (sr & ATMEL_TC_MTIOA); - *val = sigstatus ? COUNTER_SIGNAL_HIGH : COUNTER_SIGNAL_LOW; + *lvl = sigstatus ? COUNTER_SIGNAL_LEVEL_HIGH : COUNTER_SIGNAL_LEVEL_LOW; return 0; } diff --git a/include/linux/counter.h b/include/linux/counter.h index 9dbd5df4cd34..79f5dcaf6ba0 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -290,16 +290,16 @@ struct counter_device_state { const struct attribute_group **groups; }; -enum counter_signal_value { - COUNTER_SIGNAL_LOW = 0, - COUNTER_SIGNAL_HIGH +enum counter_signal_level { + COUNTER_SIGNAL_LEVEL_LOW, + COUNTER_SIGNAL_LEVEL_HIGH, }; /** * struct counter_ops - Callbacks from driver * @signal_read: optional read callback for Signal attribute. The read - * value of the respective Signal should be passed back via - * the val parameter. + * level of the respective Signal should be passed back via + * the level parameter. * @count_read: optional read callback for Count attribute. The read * value of the respective Count should be passed back via * the val parameter. @@ -324,7 +324,7 @@ enum counter_signal_value { struct counter_ops { int (*signal_read)(struct counter_device *counter, struct counter_signal *signal, - enum counter_signal_value *val); + enum counter_signal_level *level); int (*count_read)(struct counter_device *counter, struct counter_count *count, unsigned long *val); int (*count_write)(struct counter_device *counter, -- cgit v1.2.3 From 394a0150a0644389ce4d587f5c67393308eec28c Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Tue, 3 Aug 2021 21:06:15 +0900 Subject: counter: Rename counter_count_function to counter_function The phrase "Counter Count function" is verbose and unintentionally implies that function is a Count extension. This patch adjusts the Counter subsystem code to use the more direct "Counter function" phrase to make the intent of this code clearer. Cc: Jarkko Nikula Cc: Patrick Havelange Cc: Oleksij Rempel Cc: Kamel Bouhara Cc: Maxime Coquelin Cc: Alexandre Torgue Cc: David Lechner Acked-by: Syed Nayyar Waris Reviewed-by: Fabrice Gasnier Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/8268c54d6f42075a19bb08151a37831e22652499.1627990337.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- drivers/counter/104-quad-8.c | 10 ++++----- drivers/counter/counter.c | 38 ++++++++++++++++----------------- drivers/counter/ftm-quaddec.c | 5 ++--- drivers/counter/intel-qep.c | 4 ++-- drivers/counter/interrupt-cnt.c | 4 ++-- drivers/counter/microchip-tcb-capture.c | 6 +++--- drivers/counter/stm32-lptimer-cnt.c | 6 +++--- drivers/counter/stm32-timer-cnt.c | 10 ++++----- drivers/counter/ti-eqep.c | 10 ++++----- include/linux/counter.h | 20 ++++++++--------- 10 files changed, 56 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index b4dd07cf51eb..5283ff128c17 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -194,11 +194,11 @@ enum quad8_count_function { QUAD8_COUNT_FUNCTION_QUADRATURE_X4 }; -static const enum counter_count_function quad8_count_functions_list[] = { - [QUAD8_COUNT_FUNCTION_PULSE_DIRECTION] = COUNTER_COUNT_FUNCTION_PULSE_DIRECTION, - [QUAD8_COUNT_FUNCTION_QUADRATURE_X1] = COUNTER_COUNT_FUNCTION_QUADRATURE_X1_A, - [QUAD8_COUNT_FUNCTION_QUADRATURE_X2] = COUNTER_COUNT_FUNCTION_QUADRATURE_X2_A, - [QUAD8_COUNT_FUNCTION_QUADRATURE_X4] = COUNTER_COUNT_FUNCTION_QUADRATURE_X4 +static const enum counter_function quad8_count_functions_list[] = { + [QUAD8_COUNT_FUNCTION_PULSE_DIRECTION] = COUNTER_FUNCTION_PULSE_DIRECTION, + [QUAD8_COUNT_FUNCTION_QUADRATURE_X1] = COUNTER_FUNCTION_QUADRATURE_X1_A, + [QUAD8_COUNT_FUNCTION_QUADRATURE_X2] = COUNTER_FUNCTION_QUADRATURE_X2_A, + [QUAD8_COUNT_FUNCTION_QUADRATURE_X4] = COUNTER_FUNCTION_QUADRATURE_X4 }; static int quad8_function_get(struct counter_device *counter, diff --git a/drivers/counter/counter.c b/drivers/counter/counter.c index cb92673552b5..de921e8a3f72 100644 --- a/drivers/counter/counter.c +++ b/drivers/counter/counter.c @@ -744,15 +744,15 @@ static ssize_t counter_count_store(struct device *dev, return len; } -static const char *const counter_count_function_str[] = { - [COUNTER_COUNT_FUNCTION_INCREASE] = "increase", - [COUNTER_COUNT_FUNCTION_DECREASE] = "decrease", - [COUNTER_COUNT_FUNCTION_PULSE_DIRECTION] = "pulse-direction", - [COUNTER_COUNT_FUNCTION_QUADRATURE_X1_A] = "quadrature x1 a", - [COUNTER_COUNT_FUNCTION_QUADRATURE_X1_B] = "quadrature x1 b", - [COUNTER_COUNT_FUNCTION_QUADRATURE_X2_A] = "quadrature x2 a", - [COUNTER_COUNT_FUNCTION_QUADRATURE_X2_B] = "quadrature x2 b", - [COUNTER_COUNT_FUNCTION_QUADRATURE_X4] = "quadrature x4" +static const char *const counter_function_str[] = { + [COUNTER_FUNCTION_INCREASE] = "increase", + [COUNTER_FUNCTION_DECREASE] = "decrease", + [COUNTER_FUNCTION_PULSE_DIRECTION] = "pulse-direction", + [COUNTER_FUNCTION_QUADRATURE_X1_A] = "quadrature x1 a", + [COUNTER_FUNCTION_QUADRATURE_X1_B] = "quadrature x1 b", + [COUNTER_FUNCTION_QUADRATURE_X2_A] = "quadrature x2 a", + [COUNTER_FUNCTION_QUADRATURE_X2_B] = "quadrature x2 b", + [COUNTER_FUNCTION_QUADRATURE_X4] = "quadrature x4" }; static ssize_t counter_function_show(struct device *dev, @@ -764,7 +764,7 @@ static ssize_t counter_function_show(struct device *dev, const struct counter_count_unit *const component = devattr->component; struct counter_count *const count = component->count; size_t func_index; - enum counter_count_function function; + enum counter_function function; err = counter->ops->function_get(counter, count, &func_index); if (err) @@ -773,7 +773,7 @@ static ssize_t counter_function_show(struct device *dev, count->function = func_index; function = count->functions_list[func_index]; - return sprintf(buf, "%s\n", counter_count_function_str[function]); + return sprintf(buf, "%s\n", counter_function_str[function]); } static ssize_t counter_function_store(struct device *dev, @@ -785,14 +785,14 @@ static ssize_t counter_function_store(struct device *dev, struct counter_count *const count = component->count; const size_t num_functions = count->num_functions; size_t func_index; - enum counter_count_function function; + enum counter_function function; int err; struct counter_device *const counter = dev_get_drvdata(dev); /* Find requested Count function mode */ for (func_index = 0; func_index < num_functions; func_index++) { function = count->functions_list[func_index]; - if (sysfs_streq(buf, counter_count_function_str[function])) + if (sysfs_streq(buf, counter_function_str[function])) break; } /* Return error if requested Count function mode not found */ @@ -880,25 +880,25 @@ err_free_attr_list: } struct counter_func_avail_unit { - const enum counter_count_function *functions_list; + const enum counter_function *functions_list; size_t num_functions; }; -static ssize_t counter_count_function_available_show(struct device *dev, +static ssize_t counter_function_available_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct counter_device_attr *const devattr = to_counter_attr(attr); const struct counter_func_avail_unit *const component = devattr->component; - const enum counter_count_function *const func_list = component->functions_list; + const enum counter_function *const func_list = component->functions_list; const size_t num_functions = component->num_functions; size_t i; - enum counter_count_function function; + enum counter_function function; ssize_t len = 0; for (i = 0; i < num_functions; i++) { function = func_list[i]; len += sprintf(buf + len, "%s\n", - counter_count_function_str[function]); + counter_function_str[function]); } return len; @@ -968,7 +968,7 @@ static int counter_count_attributes_create( parm.group = group; parm.prefix = ""; parm.name = "function_available"; - parm.show = counter_count_function_available_show; + parm.show = counter_function_available_show; parm.store = NULL; parm.component = avail_comp; err = counter_attribute_create(&parm); diff --git a/drivers/counter/ftm-quaddec.c b/drivers/counter/ftm-quaddec.c index 9371532406ca..53c15f84909b 100644 --- a/drivers/counter/ftm-quaddec.c +++ b/drivers/counter/ftm-quaddec.c @@ -171,9 +171,8 @@ enum ftm_quaddec_count_function { FTM_QUADDEC_COUNT_ENCODER_MODE_1, }; -static const enum counter_count_function ftm_quaddec_count_functions[] = { - [FTM_QUADDEC_COUNT_ENCODER_MODE_1] = - COUNTER_COUNT_FUNCTION_QUADRATURE_X4 +static const enum counter_function ftm_quaddec_count_functions[] = { + [FTM_QUADDEC_COUNT_ENCODER_MODE_1] = COUNTER_FUNCTION_QUADRATURE_X4 }; static int ftm_quaddec_count_read(struct counter_device *counter, diff --git a/drivers/counter/intel-qep.c b/drivers/counter/intel-qep.c index 204f94577666..8a6847d5fb2b 100644 --- a/drivers/counter/intel-qep.c +++ b/drivers/counter/intel-qep.c @@ -126,8 +126,8 @@ static int intel_qep_count_read(struct counter_device *counter, return 0; } -static const enum counter_count_function intel_qep_count_functions[] = { - COUNTER_COUNT_FUNCTION_QUADRATURE_X4, +static const enum counter_function intel_qep_count_functions[] = { + COUNTER_FUNCTION_QUADRATURE_X4, }; static int intel_qep_function_get(struct counter_device *counter, diff --git a/drivers/counter/interrupt-cnt.c b/drivers/counter/interrupt-cnt.c index d06367bef8f0..1de4243db488 100644 --- a/drivers/counter/interrupt-cnt.c +++ b/drivers/counter/interrupt-cnt.c @@ -115,8 +115,8 @@ static int interrupt_cnt_write(struct counter_device *counter, return 0; } -static const enum counter_count_function interrupt_cnt_functions[] = { - COUNTER_COUNT_FUNCTION_INCREASE, +static const enum counter_function interrupt_cnt_functions[] = { + COUNTER_FUNCTION_INCREASE, }; static int interrupt_cnt_function_get(struct counter_device *counter, diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c index 6be3adf74114..1aa70b9c4833 100644 --- a/drivers/counter/microchip-tcb-capture.c +++ b/drivers/counter/microchip-tcb-capture.c @@ -37,9 +37,9 @@ enum mchp_tc_count_function { MCHP_TC_FUNCTION_QUADRATURE, }; -static const enum counter_count_function mchp_tc_count_functions[] = { - [MCHP_TC_FUNCTION_INCREASE] = COUNTER_COUNT_FUNCTION_INCREASE, - [MCHP_TC_FUNCTION_QUADRATURE] = COUNTER_COUNT_FUNCTION_QUADRATURE_X4, +static const enum counter_function mchp_tc_count_functions[] = { + [MCHP_TC_FUNCTION_INCREASE] = COUNTER_FUNCTION_INCREASE, + [MCHP_TC_FUNCTION_QUADRATURE] = COUNTER_FUNCTION_QUADRATURE_X4, }; enum mchp_tc_synapse_action { diff --git a/drivers/counter/stm32-lptimer-cnt.c b/drivers/counter/stm32-lptimer-cnt.c index 49aeb9e393f3..13656957c45f 100644 --- a/drivers/counter/stm32-lptimer-cnt.c +++ b/drivers/counter/stm32-lptimer-cnt.c @@ -134,9 +134,9 @@ enum stm32_lptim_cnt_function { STM32_LPTIM_ENCODER_BOTH_EDGE, }; -static const enum counter_count_function stm32_lptim_cnt_functions[] = { - [STM32_LPTIM_COUNTER_INCREASE] = COUNTER_COUNT_FUNCTION_INCREASE, - [STM32_LPTIM_ENCODER_BOTH_EDGE] = COUNTER_COUNT_FUNCTION_QUADRATURE_X4, +static const enum counter_function stm32_lptim_cnt_functions[] = { + [STM32_LPTIM_COUNTER_INCREASE] = COUNTER_FUNCTION_INCREASE, + [STM32_LPTIM_ENCODER_BOTH_EDGE] = COUNTER_FUNCTION_QUADRATURE_X4, }; enum stm32_lptim_synapse_action { diff --git a/drivers/counter/stm32-timer-cnt.c b/drivers/counter/stm32-timer-cnt.c index 603b30ada839..3fb0debd7425 100644 --- a/drivers/counter/stm32-timer-cnt.c +++ b/drivers/counter/stm32-timer-cnt.c @@ -50,11 +50,11 @@ enum stm32_count_function { STM32_COUNT_ENCODER_MODE_3, }; -static const enum counter_count_function stm32_count_functions[] = { - [STM32_COUNT_SLAVE_MODE_DISABLED] = COUNTER_COUNT_FUNCTION_INCREASE, - [STM32_COUNT_ENCODER_MODE_1] = COUNTER_COUNT_FUNCTION_QUADRATURE_X2_A, - [STM32_COUNT_ENCODER_MODE_2] = COUNTER_COUNT_FUNCTION_QUADRATURE_X2_B, - [STM32_COUNT_ENCODER_MODE_3] = COUNTER_COUNT_FUNCTION_QUADRATURE_X4, +static const enum counter_function stm32_count_functions[] = { + [STM32_COUNT_SLAVE_MODE_DISABLED] = COUNTER_FUNCTION_INCREASE, + [STM32_COUNT_ENCODER_MODE_1] = COUNTER_FUNCTION_QUADRATURE_X2_A, + [STM32_COUNT_ENCODER_MODE_2] = COUNTER_FUNCTION_QUADRATURE_X2_B, + [STM32_COUNT_ENCODER_MODE_3] = COUNTER_FUNCTION_QUADRATURE_X4, }; static int stm32_count_read(struct counter_device *counter, diff --git a/drivers/counter/ti-eqep.c b/drivers/counter/ti-eqep.c index c303eb17c111..94fe58bb3eab 100644 --- a/drivers/counter/ti-eqep.c +++ b/drivers/counter/ti-eqep.c @@ -294,11 +294,11 @@ static struct counter_signal ti_eqep_signals[] = { }, }; -static const enum counter_count_function ti_eqep_position_functions[] = { - [TI_EQEP_COUNT_FUNC_QUAD_COUNT] = COUNTER_COUNT_FUNCTION_QUADRATURE_X4, - [TI_EQEP_COUNT_FUNC_DIR_COUNT] = COUNTER_COUNT_FUNCTION_PULSE_DIRECTION, - [TI_EQEP_COUNT_FUNC_UP_COUNT] = COUNTER_COUNT_FUNCTION_INCREASE, - [TI_EQEP_COUNT_FUNC_DOWN_COUNT] = COUNTER_COUNT_FUNCTION_DECREASE, +static const enum counter_function ti_eqep_position_functions[] = { + [TI_EQEP_COUNT_FUNC_QUAD_COUNT] = COUNTER_FUNCTION_QUADRATURE_X4, + [TI_EQEP_COUNT_FUNC_DIR_COUNT] = COUNTER_FUNCTION_PULSE_DIRECTION, + [TI_EQEP_COUNT_FUNC_UP_COUNT] = COUNTER_FUNCTION_INCREASE, + [TI_EQEP_COUNT_FUNC_DOWN_COUNT] = COUNTER_FUNCTION_DECREASE, }; static const enum counter_synapse_action ti_eqep_position_synapse_actions[] = { diff --git a/include/linux/counter.h b/include/linux/counter.h index 79f5dcaf6ba0..d16ce2819b48 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -162,15 +162,15 @@ struct counter_count_ext { void *priv; }; -enum counter_count_function { - COUNTER_COUNT_FUNCTION_INCREASE = 0, - COUNTER_COUNT_FUNCTION_DECREASE, - COUNTER_COUNT_FUNCTION_PULSE_DIRECTION, - COUNTER_COUNT_FUNCTION_QUADRATURE_X1_A, - COUNTER_COUNT_FUNCTION_QUADRATURE_X1_B, - COUNTER_COUNT_FUNCTION_QUADRATURE_X2_A, - COUNTER_COUNT_FUNCTION_QUADRATURE_X2_B, - COUNTER_COUNT_FUNCTION_QUADRATURE_X4 +enum counter_function { + COUNTER_FUNCTION_INCREASE = 0, + COUNTER_FUNCTION_DECREASE, + COUNTER_FUNCTION_PULSE_DIRECTION, + COUNTER_FUNCTION_QUADRATURE_X1_A, + COUNTER_FUNCTION_QUADRATURE_X1_B, + COUNTER_FUNCTION_QUADRATURE_X2_A, + COUNTER_FUNCTION_QUADRATURE_X2_B, + COUNTER_FUNCTION_QUADRATURE_X4 }; /** @@ -192,7 +192,7 @@ struct counter_count { const char *name; size_t function; - const enum counter_count_function *functions_list; + const enum counter_function *functions_list; size_t num_functions; struct counter_synapse *synapses; -- cgit v1.2.3 From 71330842ff93ae67a066c1fa68d75672527312fa Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 9 Aug 2021 21:45:32 +0200 Subject: bpf: Add _kernel suffix to internal lockdown_bpf_read Rename LOCKDOWN_BPF_READ into LOCKDOWN_BPF_READ_KERNEL so we have naming more consistent with a LOCKDOWN_BPF_WRITE_USER option that we are adding. Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko --- include/linux/security.h | 2 +- kernel/bpf/helpers.c | 4 ++-- kernel/trace/bpf_trace.c | 8 ++++---- security/security.c | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 24eda04221e9..724d7a4a0c91 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -123,7 +123,7 @@ enum lockdown_reason { LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, - LOCKDOWN_BPF_READ, + LOCKDOWN_BPF_READ_KERNEL, LOCKDOWN_PERF, LOCKDOWN_TRACEFS, LOCKDOWN_XMON_RW, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 62cf00383910..0b04553e8c44 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1070,12 +1070,12 @@ bpf_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index b4916ef388ad..1836591197a5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -999,19 +999,19 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE case BPF_FUNC_probe_read: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_str_proto; #endif #ifdef CONFIG_CGROUPS diff --git a/security/security.c b/security/security.c index 09533cbb7221..6b83ab4e9d66 100644 --- a/security/security.c +++ b/security/security.c @@ -61,7 +61,7 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", - [LOCKDOWN_BPF_READ] = "use of bpf to read kernel RAM", + [LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", -- cgit v1.2.3 From 866663b7b52d2da267b28e12eed89ee781b8fed1 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 29 Jul 2021 11:42:26 +0800 Subject: block: return ELEVATOR_DISCARD_MERGE if possible When merging one bio to request, if they are discard IO and the queue supports multi-range discard, we need to return ELEVATOR_DISCARD_MERGE because both block core and related drivers(nvme, virtio-blk) doesn't handle mixed discard io merge(traditional IO merge together with discard merge) well. Fix the issue by returning ELEVATOR_DISCARD_MERGE in this situation, so both blk-mq and drivers just need to handle multi-range discard. Reported-by: Oleksandr Natalenko Signed-off-by: Ming Lei Tested-by: Oleksandr Natalenko Fixes: 2705dfb20947 ("block: fix discard request merge") Link: https://lore.kernel.org/r/20210729034226.1591070-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 3 +++ block/blk-merge.c | 16 ---------------- block/elevator.c | 3 +++ block/mq-deadline-main.c | 2 ++ include/linux/blkdev.h | 16 ++++++++++++++++ 5 files changed, 24 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 1576e858d3a5..e4a61eda2d0f 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2361,6 +2361,9 @@ static int bfq_request_merge(struct request_queue *q, struct request **req, __rq = bfq_find_rq_fmerge(bfqd, bio, q); if (__rq && elv_bio_merge_ok(__rq, bio)) { *req = __rq; + + if (blk_discard_mergable(__rq)) + return ELEVATOR_DISCARD_MERGE; return ELEVATOR_FRONT_MERGE; } diff --git a/block/blk-merge.c b/block/blk-merge.c index a11b3b53717e..f8707ff7e2fc 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -705,22 +705,6 @@ static void blk_account_io_merge_request(struct request *req) } } -/* - * Two cases of handling DISCARD merge: - * If max_discard_segments > 1, the driver takes every bio - * as a range and send them to controller together. The ranges - * needn't to be contiguous. - * Otherwise, the bios/requests will be handled as same as - * others which should be contiguous. - */ -static inline bool blk_discard_mergable(struct request *req) -{ - if (req_op(req) == REQ_OP_DISCARD && - queue_max_discard_segments(req->q) > 1) - return true; - return false; -} - static enum elv_merge blk_try_req_merge(struct request *req, struct request *next) { diff --git a/block/elevator.c b/block/elevator.c index 9beaafd238e0..ff45d8388f48 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -336,6 +336,9 @@ enum elv_merge elv_merge(struct request_queue *q, struct request **req, __rq = elv_rqhash_find(q, bio->bi_iter.bi_sector); if (__rq && elv_bio_merge_ok(__rq, bio)) { *req = __rq; + + if (blk_discard_mergable(__rq)) + return ELEVATOR_DISCARD_MERGE; return ELEVATOR_BACK_MERGE; } diff --git a/block/mq-deadline-main.c b/block/mq-deadline-main.c index 6f612e6dc82b..294be0c0db65 100644 --- a/block/mq-deadline-main.c +++ b/block/mq-deadline-main.c @@ -677,6 +677,8 @@ static int dd_request_merge(struct request_queue *q, struct request **rq, if (elv_bio_merge_ok(__rq, bio)) { *rq = __rq; + if (blk_discard_mergable(__rq)) + return ELEVATOR_DISCARD_MERGE; return ELEVATOR_FRONT_MERGE; } } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 23e1253a8d88..07eef02325b4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1519,6 +1519,22 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector return offset << SECTOR_SHIFT; } +/* + * Two cases of handling DISCARD merge: + * If max_discard_segments > 1, the driver takes every bio + * as a range and send them to controller together. The ranges + * needn't to be contiguous. + * Otherwise, the bios/requests will be handled as same as + * others which should be contiguous. + */ +static inline bool blk_discard_mergable(struct request *req) +{ + if (req_op(req) == REQ_OP_DISCARD && + queue_max_discard_segments(req->q) > 1) + return true; + return false; +} + static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 71d3d0ebc894294ef9454e45a3ac2e9ba60b3351 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 26 Jul 2021 08:01:27 -0400 Subject: SUNRPC: Convert rpc_client refcount to use refcount_t There are now tools in the refcount library that allow us to convert the client shutdown code. Reported-by: Xiyu Yang Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/sunrpc/clnt.h | 3 ++- net/sunrpc/auth_gss/gss_rpc_upcall.c | 2 +- net/sunrpc/clnt.c | 22 ++++++++++------------ net/sunrpc/debugfs.c | 2 +- net/sunrpc/rpc_pipe.c | 2 +- 5 files changed, 15 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 8b5d5c97553e..b2edd5fc2f0c 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -35,7 +36,7 @@ struct rpc_sysfs_client; * The high-level client handle */ struct rpc_clnt { - atomic_t cl_count; /* Number of references */ + refcount_t cl_count; /* Number of references */ unsigned int cl_clid; /* client id */ struct list_head cl_clients; /* Global list of clients */ struct list_head cl_tasks; /* List of tasks */ diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index d1c003a25b0f..61c276bddaf2 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -160,7 +160,7 @@ static struct rpc_clnt *get_gssp_clnt(struct sunrpc_net *sn) mutex_lock(&sn->gssp_lock); clnt = sn->gssp_clnt; if (clnt) - atomic_inc(&clnt->cl_count); + refcount_inc(&clnt->cl_count); mutex_unlock(&sn->gssp_lock); return clnt; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d34737a8a68a..a5b7f6e34d15 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -167,7 +167,7 @@ static int rpc_clnt_skip_event(struct rpc_clnt *clnt, unsigned long event) case RPC_PIPEFS_MOUNT: if (clnt->cl_pipedir_objects.pdh_dentry != NULL) return 1; - if (atomic_read(&clnt->cl_count) == 0) + if (refcount_read(&clnt->cl_count) == 0) return 1; break; case RPC_PIPEFS_UMOUNT: @@ -419,7 +419,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, clnt->cl_rtt = &clnt->cl_rtt_default; rpc_init_rtt(&clnt->cl_rtt_default, clnt->cl_timeout->to_initval); - atomic_set(&clnt->cl_count, 1); + refcount_set(&clnt->cl_count, 1); if (nodename == NULL) nodename = utsname()->nodename; @@ -431,7 +431,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, if (err) goto out_no_path; if (parent) - atomic_inc(&parent->cl_count); + refcount_inc(&parent->cl_count); trace_rpc_clnt_new(clnt, xprt, program->name, args->servername); return clnt; @@ -918,18 +918,16 @@ rpc_free_client(struct rpc_clnt *clnt) static struct rpc_clnt * rpc_free_auth(struct rpc_clnt *clnt) { - if (clnt->cl_auth == NULL) - return rpc_free_client(clnt); - /* * Note: RPCSEC_GSS may need to send NULL RPC calls in order to * release remaining GSS contexts. This mechanism ensures * that it can do so safely. */ - atomic_inc(&clnt->cl_count); - rpcauth_release(clnt->cl_auth); - clnt->cl_auth = NULL; - if (atomic_dec_and_test(&clnt->cl_count)) + if (clnt->cl_auth != NULL) { + rpcauth_release(clnt->cl_auth); + clnt->cl_auth = NULL; + } + if (refcount_dec_and_test(&clnt->cl_count)) return rpc_free_client(clnt); return NULL; } @@ -943,7 +941,7 @@ rpc_release_client(struct rpc_clnt *clnt) do { if (list_empty(&clnt->cl_tasks)) wake_up(&destroy_wait); - if (!atomic_dec_and_test(&clnt->cl_count)) + if (refcount_dec_not_one(&clnt->cl_count)) break; clnt = rpc_free_auth(clnt); } while (clnt != NULL); @@ -1082,7 +1080,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) if (clnt != NULL) { rpc_task_set_transport(task, clnt); task->tk_client = clnt; - atomic_inc(&clnt->cl_count); + refcount_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; if (clnt->cl_softerr) diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c index 56029e3af6ff..79995eb95927 100644 --- a/net/sunrpc/debugfs.c +++ b/net/sunrpc/debugfs.c @@ -90,7 +90,7 @@ static int tasks_open(struct inode *inode, struct file *filp) struct seq_file *seq = filp->private_data; struct rpc_clnt *clnt = seq->private = inode->i_private; - if (!atomic_inc_not_zero(&clnt->cl_count)) { + if (!refcount_inc_not_zero(&clnt->cl_count)) { seq_release(inode, filp); ret = -EINVAL; } diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 09c000d490a1..ee5336d73fdd 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -423,7 +423,7 @@ rpc_info_open(struct inode *inode, struct file *file) spin_lock(&file->f_path.dentry->d_lock); if (!d_unhashed(file->f_path.dentry)) clnt = RPC_I(inode)->private; - if (clnt != NULL && atomic_inc_not_zero(&clnt->cl_count)) { + if (clnt != NULL && refcount_inc_not_zero(&clnt->cl_count)) { spin_unlock(&file->f_path.dentry->d_lock); m->private = clnt; } else { -- cgit v1.2.3 From c2dc3e5fad13aca5d7bdf4bcb52b1a1d707c8555 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 26 Jul 2021 07:59:23 -0400 Subject: SUNRPC: Fix potential memory corruption We really should not call rpc_wake_up_queued_task_set_status() with xprt->snd_task as an argument unless we are certain that is actually an rpc_task. Fixes: 0445f92c5d53 ("SUNRPC: Fix disconnection races") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xprt.h | 1 + net/sunrpc/xprt.c | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index c8c39f22d3b1..59cd97da895b 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -432,6 +432,7 @@ void xprt_release_write(struct rpc_xprt *, struct rpc_task *); #define XPRT_CONGESTED (9) #define XPRT_CWND_WAIT (10) #define XPRT_WRITE_SPACE (11) +#define XPRT_SND_IS_COOKIE (12) static inline void xprt_set_connected(struct rpc_xprt *xprt) { diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index fb6db09725c7..bddd354a0076 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -775,9 +775,9 @@ void xprt_force_disconnect(struct rpc_xprt *xprt) /* Try to schedule an autoclose RPC call */ if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) queue_work(xprtiod_workqueue, &xprt->task_cleanup); - else if (xprt->snd_task) + else if (xprt->snd_task && !test_bit(XPRT_SND_IS_COOKIE, &xprt->state)) rpc_wake_up_queued_task_set_status(&xprt->pending, - xprt->snd_task, -ENOTCONN); + xprt->snd_task, -ENOTCONN); spin_unlock(&xprt->transport_lock); } EXPORT_SYMBOL_GPL(xprt_force_disconnect); @@ -866,6 +866,7 @@ bool xprt_lock_connect(struct rpc_xprt *xprt, goto out; if (xprt->snd_task != task) goto out; + set_bit(XPRT_SND_IS_COOKIE, &xprt->state); xprt->snd_task = cookie; ret = true; out: @@ -881,6 +882,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) if (!test_bit(XPRT_LOCKED, &xprt->state)) goto out; xprt->snd_task =NULL; + clear_bit(XPRT_SND_IS_COOKIE, &xprt->state); xprt->ops->release_xprt(xprt, NULL); xprt_schedule_autodisconnect(xprt); out: -- cgit v1.2.3 From 879af96ffd72706c6e3278ea6b45b0b0e37ec5d7 Mon Sep 17 00:00:00 2001 From: Jussi Maki Date: Sat, 31 Jul 2021 05:57:33 +0000 Subject: net, core: Add support for XDP redirection to slave device This adds the ndo_xdp_get_xmit_slave hook for transforming XDP_TX into XDP_REDIRECT after BPF program run when the ingress device is a bond slave. The dev_xdp_prog_count is exposed so that slave devices can be checked for loaded XDP programs in order to avoid the situation where both bond master and slave have programs loaded according to xdp_state. Signed-off-by: Jussi Maki Signed-off-by: Daniel Borkmann Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Link: https://lore.kernel.org/bpf/20210731055738.16820-3-joamaki@gmail.com --- include/linux/filter.h | 13 ++++++++++++- include/linux/netdevice.h | 6 ++++++ net/core/dev.c | 13 ++++++++++++- net/core/filter.c | 25 +++++++++++++++++++++++++ 4 files changed, 55 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index ff698c9d1c94..1797e8506929 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -776,6 +776,10 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, DECLARE_BPF_DISPATCHER(xdp) +DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); + +u32 xdp_master_redirect(struct xdp_buff *xdp); + static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { @@ -783,7 +787,14 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, * under local_bh_disable(), which provides the needed RCU protection * for accessing map entries. */ - return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); + u32 act = __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); + + if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) { + if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev)) + act = xdp_master_redirect(xdp); + } + + return act; } void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d63a94ecbf3b..02c6e8e10c86 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1330,6 +1330,9 @@ struct netdev_net_notifier { * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. + * struct net_device *(*ndo_xdp_get_xmit_slave)(struct net_device *dev, + * struct xdp_buff *xdp); + * Get the xmit slave of master device based on the xdp_buff. * int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); * This function is used to wake up the softirq, ksoftirqd or kthread * responsible for sending and/or receiving packets on a specific @@ -1557,6 +1560,8 @@ struct net_device_ops { int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, u32 flags); + struct net_device * (*ndo_xdp_get_xmit_slave)(struct net_device *dev, + struct xdp_buff *xdp); int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); @@ -4087,6 +4092,7 @@ typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags); int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +u8 dev_xdp_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index 64e1a5f63f93..9eb6dc9e02b3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9380,7 +9380,7 @@ static struct bpf_prog *dev_xdp_prog(struct net_device *dev, return dev->xdp_state[mode].prog; } -static u8 dev_xdp_prog_count(struct net_device *dev) +u8 dev_xdp_prog_count(struct net_device *dev) { u8 count = 0; int i; @@ -9390,6 +9390,7 @@ static u8 dev_xdp_prog_count(struct net_device *dev) count++; return count; } +EXPORT_SYMBOL_GPL(dev_xdp_prog_count); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { @@ -9483,6 +9484,8 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack { unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; + struct net_device *upper; + struct list_head *iter; enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err; @@ -9521,6 +9524,14 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack return -EBUSY; } + /* don't allow if an upper device already has a program */ + netdev_for_each_upper_dev_rcu(dev, upper, iter) { + if (dev_xdp_prog_count(upper) > 0) { + NL_SET_ERR_MSG(extack, "Cannot attach when an upper device already has a program"); + return -EEXIST; + } + } + cur_prog = dev_xdp_prog(dev, mode); /* can't replace attached prog with link */ if (link && cur_prog) { diff --git a/net/core/filter.c b/net/core/filter.c index faf29fd82276..ff62cd39046d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3950,6 +3950,31 @@ void bpf_clear_redirect_map(struct bpf_map *map) } } +DEFINE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); +EXPORT_SYMBOL_GPL(bpf_master_redirect_enabled_key); + +u32 xdp_master_redirect(struct xdp_buff *xdp) +{ + struct net_device *master, *slave; + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev); + slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp); + if (slave && slave != xdp->rxq->dev) { + /* The target device is different from the receiving device, so + * redirect it to the new device. + * Using XDP_REDIRECT gets the correct behaviour from XDP enabled + * drivers to unmap the packet from their rx ring. + */ + ri->tgt_index = slave->ifindex; + ri->map_id = INT_MAX; + ri->map_type = BPF_MAP_TYPE_UNSPEC; + return XDP_REDIRECT; + } + return XDP_TX; +} +EXPORT_SYMBOL_GPL(xdp_master_redirect); + int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { -- cgit v1.2.3 From 67dc8325370844ffce92aa59abe8b453aa6aa83c Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Sat, 31 Jul 2021 08:01:29 +0800 Subject: workqueue: Fix typo in comments Fix typo: *assing ==> assign *alloced ==> allocated *Retun ==> Return *excute ==> execute v1->v2: *reverse 'iff' *update changelog Signed-off-by: Cai Huoqing Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- kernel/workqueue.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index d15a7730ee18..5fcf3d048a5a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -324,7 +324,7 @@ enum { * to execute and tries to keep idle cores idle to conserve power; * however, for example, a per-cpu work item scheduled from an * interrupt handler on an idle CPU will force the scheduler to - * excute the work item on that CPU breaking the idleness, which in + * execute the work item on that CPU breaking the idleness, which in * turn may lead to more scheduling choices which are sub-optimal * in terms of power consumption. * diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 542c2d03dab6..d3c35e47aa90 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -524,7 +524,7 @@ static inline void debug_work_deactivate(struct work_struct *work) { } #endif /** - * worker_pool_assign_id - allocate ID and assing it to @pool + * worker_pool_assign_id - allocate ID and assign it to @pool * @pool: the pool pointer of interest * * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned @@ -3763,7 +3763,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq) raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); } -/* initialize newly alloced @pwq which is associated with @wq and @pool */ +/* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { @@ -5331,7 +5331,7 @@ static int workqueue_apply_unbound_cpumask(void) * the affinity of all unbound workqueues. This function check the @cpumask * and apply it to all unbound workqueues and updates all pwqs of them. * - * Retun: 0 - Success + * Return: 0 - Success * -EINVAL - Invalid @cpumask * -ENOMEM - Failed to allocate memory for attrs or pwqs. */ -- cgit v1.2.3 From 57f05bc2ab2443b89c2e2562c05053bcc7d30e8b Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Fri, 6 Aug 2021 10:46:19 +0800 Subject: page_pool: keep pp info as long as page pool owns the page Currently, page->pp is cleared and set everytime the page is recycled, which is unnecessary. So only set the page->pp when the page is added to the page pool and only clear it when the page is released from the page pool. This is also a preparation to support allocating frag page in page pool. Reviewed-by: Ilias Apalodimas Signed-off-by: Yunsheng Lin Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/mvneta.c | 6 +----- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +- drivers/net/ethernet/ti/cpsw.c | 2 +- drivers/net/ethernet/ti/cpsw_new.c | 2 +- include/linux/skbuff.h | 4 +--- include/net/page_pool.h | 7 ------- net/core/page_pool.c | 21 +++++++++++++++++---- 7 files changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index ff8db311963c..5d1007e1b5c9 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2327,7 +2327,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool, if (!skb) return ERR_PTR(-ENOMEM); - skb_mark_for_recycle(skb, virt_to_page(xdp->data), pool); + skb_mark_for_recycle(skb); skb_reserve(skb, xdp->data - xdp->data_hard_start); skb_put(skb, xdp->data_end - xdp->data); @@ -2339,10 +2339,6 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool, skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, skb_frag_page(frag), skb_frag_off(frag), skb_frag_size(frag), PAGE_SIZE); - /* We don't need to reset pp_recycle here. It's already set, so - * just mark fragments for recycling. - */ - page_pool_store_mem_info(skb_frag_page(frag), pool); } return skb; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 99bd8b8aa0e2..744f58f41ecc 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3995,7 +3995,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, } if (pp) - skb_mark_for_recycle(skb, page, pp); + skb_mark_for_recycle(skb); else dma_unmap_single_attrs(dev->dev.parent, dma_addr, bm_pool->buf_size, DMA_FROM_DEVICE, diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 8e1e582a10c8..9f70e40779f6 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -431,7 +431,7 @@ static void cpsw_rx_handler(void *token, int len, int status) skb->protocol = eth_type_trans(skb, ndev); /* mark skb for recycling */ - skb_mark_for_recycle(skb, page, pool); + skb_mark_for_recycle(skb); netif_receive_skb(skb); ndev->stats.rx_bytes += len; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 192394fe4c1c..ff3a96b084ee 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -375,7 +375,7 @@ static void cpsw_rx_handler(void *token, int len, int status) skb->protocol = eth_type_trans(skb, ndev); /* mark skb for recycling */ - skb_mark_for_recycle(skb, page, pool); + skb_mark_for_recycle(skb); netif_receive_skb(skb); ndev->stats.rx_bytes += len; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 783cc2368bb1..6bdb0db3e825 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4712,11 +4712,9 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) } #ifdef CONFIG_PAGE_POOL -static inline void skb_mark_for_recycle(struct sk_buff *skb, struct page *page, - struct page_pool *pp) +static inline void skb_mark_for_recycle(struct sk_buff *skb) { skb->pp_recycle = 1; - page_pool_store_mem_info(page, pp); } #endif diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 3dd62dd73027..8d7744d1c7c1 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -253,11 +253,4 @@ static inline void page_pool_ring_unlock(struct page_pool *pool) spin_unlock_bh(&pool->ring.producer_lock); } -/* Store mem_info on struct page and use it while recycling skb frags */ -static inline -void page_pool_store_mem_info(struct page *page, struct page_pool *pp) -{ - page->pp = pp; -} - #endif /* _NET_PAGE_POOL_H */ diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 5e4eb45b139c..78838c6fe007 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -206,6 +206,19 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) return true; } +static void page_pool_set_pp_info(struct page_pool *pool, + struct page *page) +{ + page->pp = pool; + page->pp_magic |= PP_SIGNATURE; +} + +static void page_pool_clear_pp_info(struct page *page) +{ + page->pp_magic = 0; + page->pp = NULL; +} + static struct page *__page_pool_alloc_page_order(struct page_pool *pool, gfp_t gfp) { @@ -222,7 +235,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool, return NULL; } - page->pp_magic |= PP_SIGNATURE; + page_pool_set_pp_info(pool, page); /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; @@ -266,7 +279,8 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, put_page(page); continue; } - page->pp_magic |= PP_SIGNATURE; + + page_pool_set_pp_info(pool, page); pool->alloc.cache[pool->alloc.count++] = page; /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; @@ -345,7 +359,7 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) DMA_ATTR_SKIP_CPU_SYNC); page_pool_set_dma_addr(page, 0); skip_dma_unmap: - page->pp_magic = 0; + page_pool_clear_pp_info(page); /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. @@ -644,7 +658,6 @@ bool page_pool_return_skb_page(struct page *page) * The page will be returned to the pool here regardless of the * 'flipped' fragment being in use or not. */ - page->pp = NULL; page_pool_put_full_page(pp, page, false); return true; -- cgit v1.2.3 From 0e9d2a0a3a836c37528899010e73b5be8111753e Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Fri, 6 Aug 2021 10:46:20 +0800 Subject: page_pool: add interface to manipulate frag count in page pool For 32 bit systems with 64 bit dma, dma_addr[1] is used to store the upper 32 bit dma addr, those system should be rare those days. For normal system, the dma_addr[1] in 'struct page' is not used, so we can reuse dma_addr[1] for storing frag count, which means how many frags this page might be splited to. In order to simplify the page frag support in the page pool, the PAGE_POOL_DMA_USE_PP_FRAG_COUNT macro is added to indicate the 32 bit systems with 64 bit dma, and the page frag support in page pool is disabled for such system. The newly added page_pool_set_frag_count() is called to reserve the maximum frag count before any page frag is passed to the user. The page_pool_atomic_sub_frag_count_return() is called when user is done with the page frag. Signed-off-by: Yunsheng Lin Signed-off-by: Jakub Kicinski --- include/linux/mm_types.h | 18 +++++++++++++----- include/net/page_pool.h | 46 +++++++++++++++++++++++++++++++++++++++------- net/core/page_pool.c | 4 ++++ 3 files changed, 56 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 52bbd2b7cb46..7f8ee09c711f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -103,11 +103,19 @@ struct page { unsigned long pp_magic; struct page_pool *pp; unsigned long _pp_mapping_pad; - /** - * @dma_addr: might require a 64-bit value on - * 32-bit architectures. - */ - unsigned long dma_addr[2]; + unsigned long dma_addr; + union { + /** + * dma_addr_upper: might require a 64-bit + * value on 32-bit architectures. + */ + unsigned long dma_addr_upper; + /** + * For frag page support, not supported in + * 32-bit architectures with 64-bit DMA. + */ + atomic_long_t pp_frag_count; + }; }; struct { /* slab, slob and slub */ union { diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 8d7744d1c7c1..42e6997e637d 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -45,7 +45,10 @@ * Please note DMA-sync-for-CPU is still * device driver responsibility */ -#define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV) +#define PP_FLAG_PAGE_FRAG BIT(2) /* for page frag feature */ +#define PP_FLAG_ALL (PP_FLAG_DMA_MAP |\ + PP_FLAG_DMA_SYNC_DEV |\ + PP_FLAG_PAGE_FRAG) /* * Fast allocation side cache array/stack @@ -198,19 +201,48 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ + (sizeof(dma_addr_t) > sizeof(unsigned long)) + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - dma_addr_t ret = page->dma_addr[0]; - if (sizeof(dma_addr_t) > sizeof(unsigned long)) - ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16; + dma_addr_t ret = page->dma_addr; + + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; + return ret; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { - page->dma_addr[0] = addr; - if (sizeof(dma_addr_t) > sizeof(unsigned long)) - page->dma_addr[1] = upper_32_bits(addr); + page->dma_addr = addr; + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + page->dma_addr_upper = upper_32_bits(addr); +} + +static inline void page_pool_set_frag_count(struct page *page, long nr) +{ + atomic_long_set(&page->pp_frag_count, nr); +} + +static inline long page_pool_atomic_sub_frag_count_return(struct page *page, + long nr) +{ + long ret; + + /* As suggested by Alexander, atomic_long_read() may cover up the + * reference count errors, so avoid calling atomic_long_read() in + * the cases of freeing or draining the page_frags, where we would + * not expect it to match or that are slowpath anyway. + */ + if (__builtin_constant_p(nr) && + atomic_long_read(&page->pp_frag_count) == nr) + return 0; + + ret = atomic_long_sub_return(nr, &page->pp_frag_count); + WARN_ON(ret < 0); + return ret; } static inline bool is_page_pool_compiled_in(void) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 78838c6fe007..68fab94ac422 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -67,6 +67,10 @@ static int page_pool_init(struct page_pool *pool, */ } + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && + pool->p.flags & PP_FLAG_PAGE_FRAG) + return -EINVAL; + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; -- cgit v1.2.3 From de2860f4636256836450c6543be744a50118fc66 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 9 Aug 2021 10:10:00 -0700 Subject: mm: Add kvrealloc() During log recovery of an XFS filesystem with 64kB directory buffers, rebuilding a buffer split across two log records results in a memory allocation warning from krealloc like this: xfs filesystem being mounted at /mnt/scratch supports timestamps until 2038 (0x7fffffff) XFS (dm-0): Unmounting Filesystem XFS (dm-0): Mounting V5 Filesystem XFS (dm-0): Starting recovery (logdev: internal) ------------[ cut here ]------------ WARNING: CPU: 5 PID: 3435170 at mm/page_alloc.c:3539 get_page_from_freelist+0xdee/0xe40 ..... RIP: 0010:get_page_from_freelist+0xdee/0xe40 Call Trace: ? complete+0x3f/0x50 __alloc_pages+0x16f/0x300 alloc_pages+0x87/0x110 kmalloc_order+0x2c/0x90 kmalloc_order_trace+0x1d/0x90 __kmalloc_track_caller+0x215/0x270 ? xlog_recover_add_to_cont_trans+0x63/0x1f0 krealloc+0x54/0xb0 xlog_recover_add_to_cont_trans+0x63/0x1f0 xlog_recovery_process_trans+0xc1/0xd0 xlog_recover_process_ophdr+0x86/0x130 xlog_recover_process_data+0x9f/0x160 xlog_recover_process+0xa2/0x120 xlog_do_recovery_pass+0x40b/0x7d0 ? __irq_work_queue_local+0x4f/0x60 ? irq_work_queue+0x3a/0x50 xlog_do_log_recovery+0x70/0x150 xlog_do_recover+0x38/0x1d0 xlog_recover+0xd8/0x170 xfs_log_mount+0x181/0x300 xfs_mountfs+0x4a1/0x9b0 xfs_fs_fill_super+0x3c0/0x7b0 get_tree_bdev+0x171/0x270 ? suffix_kstrtoint.constprop.0+0xf0/0xf0 xfs_fs_get_tree+0x15/0x20 vfs_get_tree+0x24/0xc0 path_mount+0x2f5/0xaf0 __x64_sys_mount+0x108/0x140 do_syscall_64+0x3a/0x70 entry_SYSCALL_64_after_hwframe+0x44/0xae Essentially, we are taking a multi-order allocation from kmem_alloc() (which has an open coded no fail, no warn loop) and then reallocating it out to 64kB using krealloc(__GFP_NOFAIL) and that is then triggering the above warning. This is a regression caused by converting this code from an open coded no fail/no warn reallocation loop to using __GFP_NOFAIL. What we actually need here is kvrealloc(), so that if contiguous page allocation fails we fall back to vmalloc() and we don't get nasty warnings happening in XFS. Fixes: 771915c4f688 ("xfs: remove kmem_realloc()") Signed-off-by: Dave Chinner Acked-by: Mel Gorman Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log_recover.c | 4 +++- include/linux/mm.h | 2 ++ mm/util.c | 15 +++++++++++++++ 3 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index a98d2429d795..cc3c2329c4e5 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2062,7 +2062,9 @@ xlog_recover_add_to_cont_trans( old_ptr = item->ri_buf[item->ri_cnt-1].i_addr; old_len = item->ri_buf[item->ri_cnt-1].i_len; - ptr = krealloc(old_ptr, len + old_len, GFP_KERNEL | __GFP_NOFAIL); + ptr = kvrealloc(old_ptr, old_len, len + old_len, GFP_KERNEL); + if (!ptr) + return -ENOMEM; memcpy(&ptr[old_len], dp, len); item->ri_buf[item->ri_cnt-1].i_len += len; item->ri_buf[item->ri_cnt-1].i_addr = ptr; diff --git a/include/linux/mm.h b/include/linux/mm.h index 7ca22e6e694a..e59646a5d44d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -829,6 +829,8 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) return kvmalloc_array(n, size, flags | __GFP_ZERO); } +extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, + gfp_t flags); extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); diff --git a/mm/util.c b/mm/util.c index 9043d03750a7..db3091116b7c 100644 --- a/mm/util.c +++ b/mm/util.c @@ -635,6 +635,21 @@ void kvfree_sensitive(const void *addr, size_t len) } EXPORT_SYMBOL(kvfree_sensitive); +void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) +{ + void *newp; + + if (oldsize >= newsize) + return (void *)p; + newp = kvmalloc(newsize, flags); + if (!newp) + return NULL; + memcpy(newp, p, oldsize); + kvfree(p); + return newp; +} +EXPORT_SYMBOL(kvrealloc); + static inline void *__page_rmapping(struct page *page) { unsigned long mapping; -- cgit v1.2.3 From 563476ae0c5e48a028cbfa38fa9d2fc0418eb88f Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Sun, 11 Apr 2021 15:32:55 +0300 Subject: net/mlx5: Synchronize correct IRQ when destroying CQ The CQ destroy is performed based on the IRQ number that is stored in cq->irqn. That number wasn't set explicitly during CQ creation and as expected some of the API users of mlx5_core_create_cq() forgot to update it. This caused to wrong synchronization call of the wrong IRQ with a number 0 instead of the real one. As a fix, set the IRQ number directly in the mlx5_core_create_cq() and update all users accordingly. Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices") Fixes: ef1659ade359 ("IB/mlx5: Add DEVX support for CQ events") Signed-off-by: Shay Drory Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/cq.c | 4 +--- drivers/infiniband/hw/mlx5/devx.c | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/cq.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 13 ++----------- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 20 ++++++++++++++++---- drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c | 4 +--- drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h | 2 ++ .../ethernet/mellanox/mlx5/core/steering/dr_send.c | 4 +--- drivers/vdpa/mlx5/net/mlx5_vnet.c | 3 +-- include/linux/mlx5/driver.h | 3 +-- 10 files changed, 27 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 7abeb576b3c5..b8e5e371bb19 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -945,7 +945,6 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, u32 *cqb = NULL; void *cqc; int cqe_size; - unsigned int irqn; int eqn; int err; @@ -984,7 +983,7 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, INIT_WORK(&cq->notify_work, notify_soft_wc_handler); } - err = mlx5_vector2eqn(dev->mdev, vector, &eqn, &irqn); + err = mlx5_vector2eqn(dev->mdev, vector, &eqn); if (err) goto err_cqb; @@ -1007,7 +1006,6 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, goto err_cqb; mlx5_ib_dbg(dev, "cqn 0x%x\n", cq->mcq.cqn); - cq->mcq.irqn = irqn; if (udata) cq->mcq.tasklet_ctx.comp = mlx5_ib_cq_comp; else diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index eb9b0a2707f8..c869b2a91a28 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -975,7 +975,6 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_QUERY_EQN)( struct mlx5_ib_dev *dev; int user_vector; int dev_eqn; - unsigned int irqn; int err; if (uverbs_copy_from(&user_vector, attrs, @@ -987,7 +986,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_QUERY_EQN)( return PTR_ERR(c); dev = to_mdev(c->ibucontext.device); - err = mlx5_vector2eqn(dev->mdev, user_vector, &dev_eqn, &irqn); + err = mlx5_vector2eqn(dev->mdev, user_vector, &dev_eqn); if (err < 0) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index df3e4938ecdd..360e093874d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -134,6 +134,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, cq->cqn); cq->uar = dev->priv.uar; + cq->irqn = eq->core.irqn; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index fd250f7bcd88..24f919ef9b8e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1535,15 +1535,9 @@ static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_core_cq *mcq = &cq->mcq; - int eqn_not_used; - unsigned int irqn; int err; u32 i; - err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn); - if (err) - return err; - err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq, &cq->wq_ctrl); if (err) @@ -1557,7 +1551,6 @@ static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, mcq->vector = param->eq_ix; mcq->comp = mlx5e_completion_event; mcq->event = mlx5e_cq_error_event; - mcq->irqn = irqn; for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) { struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, i); @@ -1605,11 +1598,10 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) void *in; void *cqc; int inlen; - unsigned int irqn_not_used; int eqn; int err; - err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used); + err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn); if (err) return err; @@ -1983,9 +1975,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct mlx5e_channel *c; unsigned int irq; int err; - int eqn; - err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq); + err = mlx5_vector2irqn(priv->mdev, ix, &irq); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 6e074cc457de..605c8ecc3610 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -855,8 +855,8 @@ clean: return err; } -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, - unsigned int *irqn) +static int vector2eqnirqn(struct mlx5_core_dev *dev, int vector, int *eqn, + unsigned int *irqn) { struct mlx5_eq_table *table = dev->priv.eq_table; struct mlx5_eq_comp *eq, *n; @@ -865,8 +865,10 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) { if (i++ == vector) { - *eqn = eq->core.eqn; - *irqn = eq->core.irqn; + if (irqn) + *irqn = eq->core.irqn; + if (eqn) + *eqn = eq->core.eqn; err = 0; break; } @@ -874,8 +876,18 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, return err; } + +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn) +{ + return vector2eqnirqn(dev, vector, eqn, NULL); +} EXPORT_SYMBOL(mlx5_vector2eqn); +int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn) +{ + return vector2eqnirqn(dev, vector, NULL, irqn); +} + unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev) { return dev->priv.eq_table->num_comp_eqs; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index bd66ab2af5b5..d5da4ab65766 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -417,7 +417,6 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) struct mlx5_wq_param wqp; struct mlx5_cqe64 *cqe; int inlen, err, eqn; - unsigned int irqn; void *cqc, *in; __be64 *pas; u32 i; @@ -446,7 +445,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) goto err_cqwq; } - err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn); + err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn); if (err) { kvfree(in); goto err_cqwq; @@ -476,7 +475,6 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) *conn->cq.mcq.arm_db = 0; conn->cq.mcq.vector = 0; conn->cq.mcq.comp = mlx5_fpga_conn_cq_complete; - conn->cq.mcq.irqn = irqn; conn->cq.mcq.uar = fdev->conn_res.uar; tasklet_setup(&conn->cq.tasklet, mlx5_fpga_conn_cq_tasklet); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 624cedebb510..d3d628b862f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -104,4 +104,6 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev); struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev); #endif +int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn); + #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 12cf323a5943..9df0e73d1c35 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -749,7 +749,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, struct mlx5_cqe64 *cqe; struct mlx5dr_cq *cq; int inlen, err, eqn; - unsigned int irqn; void *cqc, *in; __be64 *pas; int vector; @@ -782,7 +781,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, goto err_cqwq; vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev); - err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn); + err = mlx5_vector2eqn(mdev, vector, &eqn); if (err) { kvfree(in); goto err_cqwq; @@ -818,7 +817,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, *cq->mcq.arm_db = cpu_to_be32(2 << 28); cq->mcq.vector = 0; - cq->mcq.irqn = irqn; cq->mcq.uar = uar; return cq; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 2a31467f7ac5..379a19144a25 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -526,7 +526,6 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) void __iomem *uar_page = ndev->mvdev.res.uar->map; u32 out[MLX5_ST_SZ_DW(create_cq_out)]; struct mlx5_vdpa_cq *vcq = &mvq->cq; - unsigned int irqn; __be64 *pas; int inlen; void *cqc; @@ -566,7 +565,7 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) /* Use vector 0 by default. Consider adding code to choose least used * vector. */ - err = mlx5_vector2eqn(mdev, 0, &eqn, &irqn); + err = mlx5_vector2eqn(mdev, 0, &eqn); if (err) goto err_vec; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1efe37466969..25a8be58d289 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1044,8 +1044,7 @@ void mlx5_unregister_debugfs(void); void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas); void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, - unsigned int *irqn); +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); -- cgit v1.2.3 From 51e1bb9eeaf7868db56e58f47848e364ab4c4129 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 9 Aug 2021 12:43:17 +0200 Subject: bpf: Add lockdown check for probe_write_user helper Back then, commit 96ae52279594 ("bpf: Add bpf_probe_write_user BPF helper to be called in tracers") added the bpf_probe_write_user() helper in order to allow to override user space memory. Its original goal was to have a facility to "debug, divert, and manipulate execution of semi-cooperative processes" under CAP_SYS_ADMIN. Write to kernel was explicitly disallowed since it would otherwise tamper with its integrity. One use case was shown in cf9b1199de27 ("samples/bpf: Add test/example of using bpf_probe_write_user bpf helper") where the program DNATs traffic at the time of connect(2) syscall, meaning, it rewrites the arguments to a syscall while they're still in userspace, and before the syscall has a chance to copy the argument into kernel space. These days we have better mechanisms in BPF for achieving the same (e.g. for load-balancers), but without having to write to userspace memory. Of course the bpf_probe_write_user() helper can also be used to abuse many other things for both good or bad purpose. Outside of BPF, there is a similar mechanism for ptrace(2) such as PTRACE_PEEK{TEXT,DATA} and PTRACE_POKE{TEXT,DATA}, but would likely require some more effort. Commit 96ae52279594 explicitly dedicated the helper for experimentation purpose only. Thus, move the helper's availability behind a newly added LOCKDOWN_BPF_WRITE_USER lockdown knob so that the helper is disabled under the "integrity" mode. More fine-grained control can be implemented also from LSM side with this change. Fixes: 96ae52279594 ("bpf: Add bpf_probe_write_user BPF helper to be called in tracers") Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko --- include/linux/security.h | 1 + kernel/trace/bpf_trace.c | 5 +++-- security/security.c | 1 + 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 724d7a4a0c91..5b7288521300 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -120,6 +120,7 @@ enum lockdown_reason { LOCKDOWN_MMIOTRACE, LOCKDOWN_DEBUGFS, LOCKDOWN_XMON_WR, + LOCKDOWN_BPF_WRITE_USER, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1836591197a5..fdd14072fc3b 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -990,12 +990,13 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_numa_node_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; - case BPF_FUNC_probe_write_user: - return bpf_get_probe_write_proto(); case BPF_FUNC_current_task_under_cgroup: return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; + case BPF_FUNC_probe_write_user: + return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ? + NULL : bpf_get_probe_write_proto(); case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: diff --git a/security/security.c b/security/security.c index 6b83ab4e9d66..9ffa9e9c5c55 100644 --- a/security/security.c +++ b/security/security.c @@ -58,6 +58,7 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", + [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", -- cgit v1.2.3 From a2baf4e8bb0f306fbed7b5e6197c02896a638ab5 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 9 Aug 2021 18:04:13 -0700 Subject: bpf: Fix potentially incorrect results with bpf_get_local_storage() Commit b910eaaaa4b8 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper") fixed a bug for bpf_get_local_storage() helper so different tasks won't mess up with each other's percpu local storage. The percpu data contains 8 slots so it can hold up to 8 contexts (same or different tasks), for 8 different program runs, at the same time. This in general is sufficient. But our internal testing showed the following warning multiple times: [...] warning: WARNING: CPU: 13 PID: 41661 at include/linux/bpf-cgroup.h:193 __cgroup_bpf_run_filter_sock_ops+0x13e/0x180 RIP: 0010:__cgroup_bpf_run_filter_sock_ops+0x13e/0x180 tcp_call_bpf.constprop.99+0x93/0xc0 tcp_conn_request+0x41e/0xa50 ? tcp_rcv_state_process+0x203/0xe00 tcp_rcv_state_process+0x203/0xe00 ? sk_filter_trim_cap+0xbc/0x210 ? tcp_v6_inbound_md5_hash.constprop.41+0x44/0x160 tcp_v6_do_rcv+0x181/0x3e0 tcp_v6_rcv+0xc65/0xcb0 ip6_protocol_deliver_rcu+0xbd/0x450 ip6_input_finish+0x11/0x20 ip6_input+0xb5/0xc0 ip6_sublist_rcv_finish+0x37/0x50 ip6_sublist_rcv+0x1dc/0x270 ipv6_list_rcv+0x113/0x140 __netif_receive_skb_list_core+0x1a0/0x210 netif_receive_skb_list_internal+0x186/0x2a0 gro_normal_list.part.170+0x19/0x40 napi_complete_done+0x65/0x150 mlx5e_napi_poll+0x1ae/0x680 __napi_poll+0x25/0x120 net_rx_action+0x11e/0x280 __do_softirq+0xbb/0x271 irq_exit_rcu+0x97/0xa0 common_interrupt+0x7f/0xa0 asm_common_interrupt+0x1e/0x40 RIP: 0010:bpf_prog_1835a9241238291a_tw_egress+0x5/0xbac ? __cgroup_bpf_run_filter_skb+0x378/0x4e0 ? do_softirq+0x34/0x70 ? ip6_finish_output2+0x266/0x590 ? ip6_finish_output+0x66/0xa0 ? ip6_output+0x6c/0x130 ? ip6_xmit+0x279/0x550 ? ip6_dst_check+0x61/0xd0 [...] Using drgn [0] to dump the percpu buffer contents showed that on this CPU slot 0 is still available, but slots 1-7 are occupied and those tasks in slots 1-7 mostly don't exist any more. So we might have issues in bpf_cgroup_storage_unset(). Further debugging confirmed that there is a bug in bpf_cgroup_storage_unset(). Currently, it tries to unset "current" slot with searching from the start. So the following sequence is possible: 1. A task is running and claims slot 0 2. Running BPF program is done, and it checked slot 0 has the "task" and ready to reset it to NULL (not yet). 3. An interrupt happens, another BPF program runs and it claims slot 1 with the *same* task. 4. The unset() in interrupt context releases slot 0 since it matches "task". 5. Interrupt is done, the task in process context reset slot 0. At the end, slot 1 is not reset and the same process can continue to occupy slots 2-7 and finally, when the above step 1-5 is repeated again, step 3 BPF program won't be able to claim an empty slot and a warning will be issued. To fix the issue, for unset() function, we should traverse from the last slot to the first. This way, the above issue can be avoided. The same reverse traversal should also be done in bpf_get_local_storage() helper itself. Otherwise, incorrect local storage may be returned to BPF program. [0] https://github.com/osandov/drgn Fixes: b910eaaaa4b8 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper") Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210810010413.1976277-1-yhs@fb.com --- include/linux/bpf-cgroup.h | 4 ++-- kernel/bpf/helpers.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8b77d08d4b47..6c9b10d82c80 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -201,8 +201,8 @@ static inline void bpf_cgroup_storage_unset(void) { int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { + if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) continue; this_cpu_write(bpf_cgroup_storage_info[i].task, NULL); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 0b04553e8c44..7a97b2f4747d 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -397,8 +397,8 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) void *ptr; int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { + if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) continue; storage = this_cpu_read(bpf_cgroup_storage_info[i].storage[stype]); -- cgit v1.2.3 From 77e89afc25f30abd56e76a809ee2884d7c1b63ce Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:47 +0200 Subject: PCI/MSI: Protect msi_desc::masked for multi-MSI Multi-MSI uses a single MSI descriptor and there is a single mask register when the device supports per vector masking. To avoid reading back the mask register the value is cached in the MSI descriptor and updates are done by clearing and setting bits in the cache and writing it to the device. But nothing protects msi_desc::masked and the mask register from being modified concurrently on two different CPUs for two different Linux interrupts which belong to the same multi-MSI descriptor. Add a lock to struct device and protect any operation on the mask and the mask register with it. This makes the update of msi_desc::masked unconditional, but there is no place which requires a modification of the hardware register without updating the masked cache. msi_mask_irq() is now an empty wrapper which will be cleaned up in follow up changes. The problem goes way back to the initial support of multi-MSI, but picking the commit which introduced the mask cache is a valid cut off point (2.6.30). Fixes: f2440d9acbe8 ("PCI MSI: Refactor interrupt masking code") Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.726833414@linutronix.de --- drivers/base/core.c | 1 + drivers/pci/msi.c | 19 ++++++++++--------- include/linux/device.h | 1 + include/linux/msi.h | 2 +- 4 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index f6360490a4a3..6c0ef9d55a34 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2837,6 +2837,7 @@ void device_initialize(struct device *dev) device_pm_init(dev); set_dev_node(dev, -1); #ifdef CONFIG_GENERIC_MSI_IRQ + raw_spin_lock_init(&dev->msi_lock); INIT_LIST_HEAD(&dev->msi_list); #endif INIT_LIST_HEAD(&dev->links.consumers); diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index f0f7026b7ac0..e5e75331b415 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -143,24 +143,25 @@ static inline __attribute_const__ u32 msi_mask(unsigned x) * reliably as devices without an INTx disable bit will then generate a * level IRQ which will never be cleared. */ -u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { - u32 mask_bits = desc->masked; + raw_spinlock_t *lock = &desc->dev->msi_lock; + unsigned long flags; if (pci_msi_ignore_mask || !desc->msi_attrib.maskbit) - return 0; + return; - mask_bits &= ~mask; - mask_bits |= flag; + raw_spin_lock_irqsave(lock, flags); + desc->masked &= ~mask; + desc->masked |= flag; pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->mask_pos, - mask_bits); - - return mask_bits; + desc->masked); + raw_spin_unlock_irqrestore(lock, flags); } static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { - desc->masked = __pci_msi_desc_mask_irq(desc, mask, flag); + __pci_msi_desc_mask_irq(desc, mask, flag); } static void __iomem *pci_msix_desc_addr(struct msi_desc *desc) diff --git a/include/linux/device.h b/include/linux/device.h index 59940f1744c1..e53aa5065f58 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -506,6 +506,7 @@ struct device { struct dev_pin_info *pins; #endif #ifdef CONFIG_GENERIC_MSI_IRQ + raw_spinlock_t msi_lock; struct list_head msi_list; #endif #ifdef CONFIG_DMA_OPS diff --git a/include/linux/msi.h b/include/linux/msi.h index 6aff469e511d..e8bdcb83172b 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -233,7 +233,7 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag); -u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); +void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); -- cgit v1.2.3 From 826da771291fc25a428e871f9e7fb465e390f852 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:48 +0200 Subject: genirq: Provide IRQCHIP_AFFINITY_PRE_STARTUP X86 IO/APIC and MSI interrupts (when used without interrupts remapping) require that the affinity setup on startup is done before the interrupt is enabled for the first time as the non-remapped operation mode cannot safely migrate enabled interrupts from arbitrary contexts. Provide a new irq chip flag which allows affected hardware to request this. This has to be opt-in because there have been reports in the past that some interrupt chips cannot handle affinity setting before startup. Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)") Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.779791738@linutronix.de --- include/linux/irq.h | 2 ++ kernel/irq/chip.c | 5 ++++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 8e9a9ae471a6..c8293c817646 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state + * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -581,6 +582,7 @@ enum { IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7), IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), + IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), }; #include diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 7f04c7d8296e..a98bcfc4be7b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -265,8 +265,11 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) } else { switch (__irq_startup_managed(desc, aff, force)) { case IRQ_STARTUP_NORMAL: + if (d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP) + irq_setup_affinity(desc); ret = __irq_startup(desc); - irq_setup_affinity(desc); + if (!(d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP)) + irq_setup_affinity(desc); break; case IRQ_STARTUP_MANAGED: irq_do_set_affinity(d, aff, false); -- cgit v1.2.3 From 3998527d2e3ee2bfdf710a45b7b90968ff87babc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:51 +0200 Subject: s390/pci: Do not mask MSI[-X] entries on teardown The PCI core already ensures that the MSI[-X] state is correct when MSI[-X] is disabled. For MSI the reset state is all entries unmasked and for MSI-X all vectors are masked. S390 masks all MSI entries and masks the already masked MSI-X entries again. Remove it and let the device in the correct state. Signed-off-by: Thomas Gleixner Tested-by: Niklas Schnelle Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Acked-by: Niklas Schnelle Link: https://lore.kernel.org/r/20210729222542.939798136@linutronix.de --- arch/s390/pci/pci_irq.c | 4 ---- drivers/pci/msi.c | 4 ++-- include/linux/msi.h | 2 -- 3 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 9c7de9089939..3823e159bf74 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -365,10 +365,6 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) for_each_pci_msi_entry(msi, pdev) { if (!msi->irq) continue; - if (msi->msi_attrib.is_msix) - __pci_msix_desc_mask_irq(msi, 1); - else - __pci_msi_desc_mask_irq(msi, 1, 1); irq_set_msi_desc(msi->irq, NULL); irq_free_desc(msi->irq); msi->msg.address_lo = 0; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index e5e75331b415..95e6ce478c04 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -143,7 +143,7 @@ static inline __attribute_const__ u32 msi_mask(unsigned x) * reliably as devices without an INTx disable bit will then generate a * level IRQ which will never be cleared. */ -void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +static void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { raw_spinlock_t *lock = &desc->dev->msi_lock; unsigned long flags; @@ -180,7 +180,7 @@ static void __iomem *pci_msix_desc_addr(struct msi_desc *desc) * file. This saves a few milliseconds when initialising devices with lots * of MSI-X interrupts. */ -u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag) +static u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag) { u32 mask_bits = desc->masked; void __iomem *desc_addr; diff --git a/include/linux/msi.h b/include/linux/msi.h index e8bdcb83172b..3d0e747a3a95 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -232,8 +232,6 @@ void free_msi_entry(struct msi_desc *entry); void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); -u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag); -void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); -- cgit v1.2.3 From 67961e77a39b8e975dd1906179b9224f29150357 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:53 +0200 Subject: PCI/MSI: Rename msi_desc::masked msi_desc::masked is a misnomer. For MSI it's used to cache the MSI mask bits when the device supports per vector masking. For MSI-X it's used to cache the content of the vector control word which contains the mask bit for the vector. Replace it with a union of msi_mask and msix_ctrl to make the purpose clear and fix up the usage sites. No functional change Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20210729222543.045993608@linutronix.de --- drivers/pci/msi.c | 30 +++++++++++++++--------------- include/linux/msi.h | 8 ++++++-- 2 files changed, 21 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index b59957c021a8..175f4d6b8e56 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -152,10 +152,10 @@ static void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) return; raw_spin_lock_irqsave(lock, flags); - desc->masked &= ~mask; - desc->masked |= flag; + desc->msi_mask &= ~mask; + desc->msi_mask |= flag; pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->mask_pos, - desc->masked); + desc->msi_mask); raw_spin_unlock_irqrestore(lock, flags); } @@ -182,7 +182,7 @@ static void __iomem *pci_msix_desc_addr(struct msi_desc *desc) */ static u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag) { - u32 mask_bits = desc->masked; + u32 ctrl = desc->msix_ctrl; void __iomem *desc_addr; if (pci_msi_ignore_mask) @@ -192,18 +192,18 @@ static u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag) if (!desc_addr) return 0; - mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; - if (flag & PCI_MSIX_ENTRY_CTRL_MASKBIT) - mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT; + ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; + if (ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT) + ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT; - writel(mask_bits, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); + writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); - return mask_bits; + return ctrl; } static void msix_mask_irq(struct msi_desc *desc, u32 flag) { - desc->masked = __pci_msix_desc_mask_irq(desc, flag); + desc->msix_ctrl = __pci_msix_desc_mask_irq(desc, flag); } static void msi_set_mask_bit(struct irq_data *data, u32 flag) @@ -290,7 +290,7 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) /* Don't touch the hardware now */ } else if (entry->msi_attrib.is_msix) { void __iomem *base = pci_msix_desc_addr(entry); - bool unmasked = !(entry->masked & PCI_MSIX_ENTRY_CTRL_MASKBIT); + bool unmasked = !(entry->msix_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT); if (!base) goto skip; @@ -430,7 +430,7 @@ static void __pci_restore_msi_state(struct pci_dev *dev) pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control); msi_mask_irq(entry, msi_mask(entry->msi_attrib.multi_cap), - entry->masked); + entry->msi_mask); control &= ~PCI_MSI_FLAGS_QSIZE; control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE; pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control); @@ -461,7 +461,7 @@ static void __pci_restore_msix_state(struct pci_dev *dev) arch_restore_msi_irqs(dev); for_each_pci_msi_entry(entry, dev) - msix_mask_irq(entry, entry->masked); + msix_mask_irq(entry, entry->msix_ctrl); pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); } @@ -602,7 +602,7 @@ msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd) /* Save the initial mask status */ if (entry->msi_attrib.maskbit) - pci_read_config_dword(dev, entry->mask_pos, &entry->masked); + pci_read_config_dword(dev, entry->mask_pos, &entry->msi_mask); out: kfree(masks); @@ -750,7 +750,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, addr = pci_msix_desc_addr(entry); if (addr) - entry->masked = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); + entry->msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); list_add_tail(&entry->list, dev_to_msi_list(&dev->dev)); if (masks) diff --git a/include/linux/msi.h b/include/linux/msi.h index 3d0e747a3a95..a20dc66b9946 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -107,7 +107,8 @@ struct ti_sci_inta_msi_desc { * address or data changes * @write_msi_msg_data: Data parameter for the callback. * - * @masked: [PCI MSI/X] Mask bits + * @msi_mask: [PCI MSI] MSI cached mask bits + * @msix_ctrl: [PCI MSI-X] MSI-X cached per vector control bits * @is_msix: [PCI MSI/X] True if MSI-X * @multiple: [PCI MSI/X] log2 num of messages allocated * @multi_cap: [PCI MSI/X] log2 num of messages supported @@ -139,7 +140,10 @@ struct msi_desc { union { /* PCI MSI/X specific data */ struct { - u32 masked; + union { + u32 msi_mask; + u32 msix_ctrl; + }; struct { u8 is_msix : 1; u8 multiple : 3; -- cgit v1.2.3 From c576e0fcd6188d0edb50b0fb83f853433ef4819b Mon Sep 17 00:00:00 2001 From: Matthew Bobrowski Date: Sun, 8 Aug 2021 15:24:33 +1000 Subject: kernel/pid.c: remove static qualifier from pidfd_create() With the idea of returning pidfds from the fanotify API, we need to expose a mechanism for creating pidfds. We drop the static qualifier from pidfd_create() and add its declaration to linux/pid.h so that the pidfd_create() helper can be called from other kernel subsystems i.e. fanotify. Link: https://lore.kernel.org/r/0c68653ec32f1b7143301f0231f7ed14062fd82b.1628398044.git.repnop@google.com Signed-off-by: Matthew Bobrowski Acked-by: Christian Brauner Signed-off-by: Jan Kara --- include/linux/pid.h | 1 + kernel/pid.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index fa10acb8d6a4..af308e15f174 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -78,6 +78,7 @@ struct file; extern struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); +int pidfd_create(struct pid *pid, unsigned int flags); static inline struct pid *get_pid(struct pid *pid) { diff --git a/kernel/pid.c b/kernel/pid.c index ebdf9c60cd0b..d3cd95b8b080 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -550,10 +550,12 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) * Note, that this function can only be called after the fd table has * been unshared to avoid leaking the pidfd to the new process. * + * This symbol should not be explicitly exported to loadable modules. + * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ -static int pidfd_create(struct pid *pid, unsigned int flags) +int pidfd_create(struct pid *pid, unsigned int flags) { int fd; -- cgit v1.2.3 From 0aca67bb7f0d8c997dfef8ff0bfeb0afb361f0e6 Mon Sep 17 00:00:00 2001 From: Matthew Bobrowski Date: Sun, 8 Aug 2021 15:25:58 +1000 Subject: fanotify: introduce a generic info record copying helper The copy_info_records_to_user() helper allows for the separation of info record copying routines/conditionals from copy_event_to_user(), which reduces the overall clutter within this function. This becomes especially true as we start introducing additional info records in the future i.e. struct fanotify_event_info_pidfd. On success, this helper returns the total amount of bytes that have been copied into the user supplied buffer and on error, a negative value is returned to the caller. The newly defined macro FANOTIFY_INFO_MODES can be used to obtain info record types that have been enabled for a specific notification group. This macro becomes useful in the subsequent patch when the FAN_REPORT_PIDFD initialization flag is introduced. Link: https://lore.kernel.org/r/8872947dfe12ce8ae6e9a7f2d49ea29bc8006af0.1628398044.git.repnop@google.com Signed-off-by: Matthew Bobrowski Reviewed-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 155 +++++++++++++++++++++---------------- include/linux/fanotify.h | 2 + 2 files changed, 90 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 182fea255376..99d145eaab49 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -173,7 +173,7 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group, size_t event_size = FAN_EVENT_METADATA_LEN; struct fanotify_event *event = NULL; struct fsnotify_event *fsn_event; - unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); + unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES); pr_debug("%s: group=%p count=%zd\n", __func__, group, count); @@ -183,8 +183,8 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group, goto out; event = FANOTIFY_E(fsn_event); - if (fid_mode) - event_size += fanotify_event_info_len(fid_mode, event); + if (info_mode) + event_size += fanotify_event_info_len(info_mode, event); if (event_size > count) { event = ERR_PTR(-EINVAL); @@ -401,6 +401,86 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, return info_len; } +static int copy_info_records_to_user(struct fanotify_event *event, + struct fanotify_info *info, + unsigned int info_mode, + char __user *buf, size_t count) +{ + int ret, total_bytes = 0, info_type = 0; + unsigned int fid_mode = info_mode & FANOTIFY_FID_BITS; + + /* + * Event info records order is as follows: dir fid + name, child fid. + */ + if (fanotify_event_dir_fh_len(event)) { + info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME : + FAN_EVENT_INFO_TYPE_DFID; + ret = copy_fid_info_to_user(fanotify_event_fsid(event), + fanotify_info_dir_fh(info), + info_type, + fanotify_info_name(info), + info->name_len, buf, count); + if (ret < 0) + return ret; + + buf += ret; + count -= ret; + total_bytes += ret; + } + + if (fanotify_event_object_fh_len(event)) { + const char *dot = NULL; + int dot_len = 0; + + if (fid_mode == FAN_REPORT_FID || info_type) { + /* + * With only group flag FAN_REPORT_FID only type FID is + * reported. Second info record type is always FID. + */ + info_type = FAN_EVENT_INFO_TYPE_FID; + } else if ((fid_mode & FAN_REPORT_NAME) && + (event->mask & FAN_ONDIR)) { + /* + * With group flag FAN_REPORT_NAME, if name was not + * recorded in an event on a directory, report the name + * "." with info type DFID_NAME. + */ + info_type = FAN_EVENT_INFO_TYPE_DFID_NAME; + dot = "."; + dot_len = 1; + } else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) || + (event->mask & FAN_ONDIR)) { + /* + * With group flag FAN_REPORT_DIR_FID, a single info + * record has type DFID for directory entry modification + * event and for event on a directory. + */ + info_type = FAN_EVENT_INFO_TYPE_DFID; + } else { + /* + * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID, + * a single info record has type FID for event on a + * non-directory, when there is no directory to report. + * For example, on FAN_DELETE_SELF event. + */ + info_type = FAN_EVENT_INFO_TYPE_FID; + } + + ret = copy_fid_info_to_user(fanotify_event_fsid(event), + fanotify_event_object_fh(event), + info_type, dot, dot_len, + buf, count); + if (ret < 0) + return ret; + + buf += ret; + count -= ret; + total_bytes += ret; + } + + return total_bytes; +} + static ssize_t copy_event_to_user(struct fsnotify_group *group, struct fanotify_event *event, char __user *buf, size_t count) @@ -408,15 +488,14 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, struct fanotify_event_metadata metadata; struct path *path = fanotify_event_path(event); struct fanotify_info *info = fanotify_event_info(event); - unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); + unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES); struct file *f = NULL; int ret, fd = FAN_NOFD; - int info_type = 0; pr_debug("%s: group=%p event=%p\n", __func__, group, event); metadata.event_len = FAN_EVENT_METADATA_LEN + - fanotify_event_info_len(fid_mode, event); + fanotify_event_info_len(info_mode, event); metadata.metadata_len = FAN_EVENT_METADATA_LEN; metadata.vers = FANOTIFY_METADATA_VERSION; metadata.reserved = 0; @@ -465,69 +544,11 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, if (f) fd_install(fd, f); - /* Event info records order is: dir fid + name, child fid */ - if (fanotify_event_dir_fh_len(event)) { - info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME : - FAN_EVENT_INFO_TYPE_DFID; - ret = copy_fid_info_to_user(fanotify_event_fsid(event), - fanotify_info_dir_fh(info), - info_type, - fanotify_info_name(info), - info->name_len, buf, count); - if (ret < 0) - goto out_close_fd; - - buf += ret; - count -= ret; - } - - if (fanotify_event_object_fh_len(event)) { - const char *dot = NULL; - int dot_len = 0; - - if (fid_mode == FAN_REPORT_FID || info_type) { - /* - * With only group flag FAN_REPORT_FID only type FID is - * reported. Second info record type is always FID. - */ - info_type = FAN_EVENT_INFO_TYPE_FID; - } else if ((fid_mode & FAN_REPORT_NAME) && - (event->mask & FAN_ONDIR)) { - /* - * With group flag FAN_REPORT_NAME, if name was not - * recorded in an event on a directory, report the - * name "." with info type DFID_NAME. - */ - info_type = FAN_EVENT_INFO_TYPE_DFID_NAME; - dot = "."; - dot_len = 1; - } else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) || - (event->mask & FAN_ONDIR)) { - /* - * With group flag FAN_REPORT_DIR_FID, a single info - * record has type DFID for directory entry modification - * event and for event on a directory. - */ - info_type = FAN_EVENT_INFO_TYPE_DFID; - } else { - /* - * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID, - * a single info record has type FID for event on a - * non-directory, when there is no directory to report. - * For example, on FAN_DELETE_SELF event. - */ - info_type = FAN_EVENT_INFO_TYPE_FID; - } - - ret = copy_fid_info_to_user(fanotify_event_fsid(event), - fanotify_event_object_fh(event), - info_type, dot, dot_len, - buf, count); + if (info_mode) { + ret = copy_info_records_to_user(event, info, info_mode, + buf, count); if (ret < 0) goto out_close_fd; - - buf += ret; - count -= ret; } return metadata.event_len; diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index a16dbeced152..10a7e26ddba6 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -27,6 +27,8 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DFID_NAME) +#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS) + /* * fanotify_init() flags that require CAP_SYS_ADMIN. * We do not allow unprivileged groups to request permission events. -- cgit v1.2.3 From af579beb666aefb17e9a335c12c788c92932baf1 Mon Sep 17 00:00:00 2001 From: Matthew Bobrowski Date: Sun, 8 Aug 2021 15:26:25 +1000 Subject: fanotify: add pidfd support to the fanotify API Introduce a new flag FAN_REPORT_PIDFD for fanotify_init(2) which allows userspace applications to control whether a pidfd information record containing a pidfd is to be returned alongside the generic event metadata for each event. If FAN_REPORT_PIDFD is enabled for a notification group, an additional struct fanotify_event_info_pidfd object type will be supplied alongside the generic struct fanotify_event_metadata for a single event. This functionality is analogous to that of FAN_REPORT_FID in terms of how the event structure is supplied to a userspace application. Usage of FAN_REPORT_PIDFD with FAN_REPORT_FID/FAN_REPORT_DFID_NAME is permitted, and in this case a struct fanotify_event_info_pidfd object will likely follow any struct fanotify_event_info_fid object. Currently, the usage of the FAN_REPORT_TID flag is not permitted along with FAN_REPORT_PIDFD as the pidfd API currently only supports the creation of pidfds for thread-group leaders. Additionally, usage of the FAN_REPORT_PIDFD flag is limited to privileged processes only i.e. event listeners that are running with the CAP_SYS_ADMIN capability. Attempting to supply the FAN_REPORT_TID initialization flags with FAN_REPORT_PIDFD or creating a notification group without CAP_SYS_ADMIN will result with -EINVAL being returned to the caller. In the event of a pidfd creation error, there are two types of error values that can be reported back to the listener. There is FAN_NOPIDFD, which will be reported in cases where the process responsible for generating the event has terminated prior to the event listener being able to read the event. Then there is FAN_EPIDFD, which will be reported when a more generic pidfd creation error has occurred when fanotify calls pidfd_create(). Link: https://lore.kernel.org/r/5f9e09cff7ed62bfaa51c1369e0f7ea5f16a91aa.1628398044.git.repnop@google.com Signed-off-by: Matthew Bobrowski Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 85 ++++++++++++++++++++++++++++++++++++-- include/linux/fanotify.h | 3 +- include/uapi/linux/fanotify.h | 13 ++++++ 3 files changed, 96 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 99d145eaab49..084a83b1214d 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include @@ -106,6 +107,8 @@ struct kmem_cache *fanotify_perm_event_cachep __read_mostly; #define FANOTIFY_EVENT_ALIGN 4 #define FANOTIFY_FID_INFO_HDR_LEN \ (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle)) +#define FANOTIFY_PIDFD_INFO_HDR_LEN \ + sizeof(struct fanotify_event_info_pidfd) static int fanotify_fid_info_len(int fh_len, int name_len) { @@ -138,6 +141,9 @@ static int fanotify_event_info_len(unsigned int info_mode, dot_len = 1; } + if (info_mode & FAN_REPORT_PIDFD) + info_len += FANOTIFY_PIDFD_INFO_HDR_LEN; + if (fh_len) info_len += fanotify_fid_info_len(fh_len, dot_len); @@ -401,13 +407,34 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, return info_len; } +static int copy_pidfd_info_to_user(int pidfd, + char __user *buf, + size_t count) +{ + struct fanotify_event_info_pidfd info = { }; + size_t info_len = FANOTIFY_PIDFD_INFO_HDR_LEN; + + if (WARN_ON_ONCE(info_len > count)) + return -EFAULT; + + info.hdr.info_type = FAN_EVENT_INFO_TYPE_PIDFD; + info.hdr.len = info_len; + info.pidfd = pidfd; + + if (copy_to_user(buf, &info, info_len)) + return -EFAULT; + + return info_len; +} + static int copy_info_records_to_user(struct fanotify_event *event, struct fanotify_info *info, - unsigned int info_mode, + unsigned int info_mode, int pidfd, char __user *buf, size_t count) { int ret, total_bytes = 0, info_type = 0; unsigned int fid_mode = info_mode & FANOTIFY_FID_BITS; + unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD; /* * Event info records order is as follows: dir fid + name, child fid. @@ -478,6 +505,16 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } + if (pidfd_mode) { + ret = copy_pidfd_info_to_user(pidfd, buf, count); + if (ret < 0) + return ret; + + buf += ret; + count -= ret; + total_bytes += ret; + } + return total_bytes; } @@ -489,8 +526,9 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, struct path *path = fanotify_event_path(event); struct fanotify_info *info = fanotify_event_info(event); unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES); + unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD; struct file *f = NULL; - int ret, fd = FAN_NOFD; + int ret, pidfd = FAN_NOPIDFD, fd = FAN_NOFD; pr_debug("%s: group=%p event=%p\n", __func__, group, event); @@ -524,6 +562,33 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, } metadata.fd = fd; + if (pidfd_mode) { + /* + * Complain if the FAN_REPORT_PIDFD and FAN_REPORT_TID mutual + * exclusion is ever lifted. At the time of incoporating pidfd + * support within fanotify, the pidfd API only supported the + * creation of pidfds for thread-group leaders. + */ + WARN_ON_ONCE(FAN_GROUP_FLAG(group, FAN_REPORT_TID)); + + /* + * The PIDTYPE_TGID check for an event->pid is performed + * preemptively in an attempt to catch out cases where the event + * listener reads events after the event generating process has + * already terminated. Report FAN_NOPIDFD to the event listener + * in those cases, with all other pidfd creation errors being + * reported as FAN_EPIDFD. + */ + if (metadata.pid == 0 || + !pid_has_task(event->pid, PIDTYPE_TGID)) { + pidfd = FAN_NOPIDFD; + } else { + pidfd = pidfd_create(event->pid, 0); + if (pidfd < 0) + pidfd = FAN_EPIDFD; + } + } + ret = -EFAULT; /* * Sanity check copy size in case get_one_event() and @@ -545,7 +610,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, fd_install(fd, f); if (info_mode) { - ret = copy_info_records_to_user(event, info, info_mode, + ret = copy_info_records_to_user(event, info, info_mode, pidfd, buf, count); if (ret < 0) goto out_close_fd; @@ -558,6 +623,10 @@ out_close_fd: put_unused_fd(fd); fput(f); } + + if (pidfd >= 0) + close_fd(pidfd); + return ret; } @@ -1103,6 +1172,14 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) #endif return -EINVAL; + /* + * A pidfd can only be returned for a thread-group leader; thus + * FAN_REPORT_PIDFD and FAN_REPORT_TID need to remain mutually + * exclusive. + */ + if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID)) + return -EINVAL; + if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS) return -EINVAL; @@ -1504,7 +1581,7 @@ static int __init fanotify_user_setup(void) FANOTIFY_DEFAULT_MAX_USER_MARKS); BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS); - BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10); + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 11); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9); fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 10a7e26ddba6..eec3b7c40811 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -27,7 +27,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DFID_NAME) -#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS) +#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) /* * fanotify_init() flags that require CAP_SYS_ADMIN. @@ -37,6 +37,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ */ #define FANOTIFY_ADMIN_INIT_FLAGS (FANOTIFY_PERM_CLASSES | \ FAN_REPORT_TID | \ + FAN_REPORT_PIDFD | \ FAN_UNLIMITED_QUEUE | \ FAN_UNLIMITED_MARKS) diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index fbf9c5c7dd59..64553df9d735 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -51,6 +51,7 @@ #define FAN_ENABLE_AUDIT 0x00000040 /* Flags to determine fanotify event format */ +#define FAN_REPORT_PIDFD 0x00000080 /* Report pidfd for event->pid */ #define FAN_REPORT_TID 0x00000100 /* event->pid is thread id */ #define FAN_REPORT_FID 0x00000200 /* Report unique file id */ #define FAN_REPORT_DIR_FID 0x00000400 /* Report unique directory id */ @@ -123,6 +124,7 @@ struct fanotify_event_metadata { #define FAN_EVENT_INFO_TYPE_FID 1 #define FAN_EVENT_INFO_TYPE_DFID_NAME 2 #define FAN_EVENT_INFO_TYPE_DFID 3 +#define FAN_EVENT_INFO_TYPE_PIDFD 4 /* Variable length info record following event metadata */ struct fanotify_event_info_header { @@ -148,6 +150,15 @@ struct fanotify_event_info_fid { unsigned char handle[0]; }; +/* + * This structure is used for info records of type FAN_EVENT_INFO_TYPE_PIDFD. + * It holds a pidfd for the pid that was responsible for generating an event. + */ +struct fanotify_event_info_pidfd { + struct fanotify_event_info_header hdr; + __s32 pidfd; +}; + struct fanotify_response { __s32 fd; __u32 response; @@ -160,6 +171,8 @@ struct fanotify_response { /* No fd set in event */ #define FAN_NOFD -1 +#define FAN_NOPIDFD FAN_NOFD +#define FAN_EPIDFD -2 /* Helper functions to deal with fanotify_event_metadata buffers */ #define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata)) -- cgit v1.2.3 From 687db2207b1bc94ca34743871167923a6de78d85 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 10 Jun 2021 14:04:42 +0300 Subject: gpu: host1x: Add DMA fence implementation Add an implementation of dma_fences based on syncpoints. Syncpoint interrupts are used to signal fences. Additionally, after software signaling has been enabled, a 30 second timeout is started. If the syncpoint threshold is not reached within this period, the fence is signalled with an -ETIMEDOUT error code. This is to allow fences that would never reach their syncpoint threshold to be cleaned up. The timeout can potentially be removed in the future after job tracking code has been refactored. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/host1x/Makefile | 1 + drivers/gpu/host1x/fence.c | 168 ++++++++++++++++++++++++++++++++++++++++++++ drivers/gpu/host1x/fence.h | 13 ++++ drivers/gpu/host1x/intr.c | 9 +++ drivers/gpu/host1x/intr.h | 2 + include/linux/host1x.h | 2 + 6 files changed, 195 insertions(+) create mode 100644 drivers/gpu/host1x/fence.c create mode 100644 drivers/gpu/host1x/fence.h (limited to 'include/linux') diff --git a/drivers/gpu/host1x/Makefile b/drivers/gpu/host1x/Makefile index 096017b8789d..d2b6f7de0498 100644 --- a/drivers/gpu/host1x/Makefile +++ b/drivers/gpu/host1x/Makefile @@ -9,6 +9,7 @@ host1x-y = \ job.o \ debug.o \ mipi.o \ + fence.o \ hw/host1x01.o \ hw/host1x02.o \ hw/host1x04.o \ diff --git a/drivers/gpu/host1x/fence.c b/drivers/gpu/host1x/fence.c new file mode 100644 index 000000000000..6941add95d0f --- /dev/null +++ b/drivers/gpu/host1x/fence.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Syncpoint dma_fence implementation + * + * Copyright (c) 2020, NVIDIA Corporation. + */ + +#include +#include +#include +#include +#include + +#include "fence.h" +#include "intr.h" +#include "syncpt.h" + +DEFINE_SPINLOCK(lock); + +struct host1x_syncpt_fence { + struct dma_fence base; + + atomic_t signaling; + + struct host1x_syncpt *sp; + u32 threshold; + + struct host1x_waitlist *waiter; + void *waiter_ref; + + struct delayed_work timeout_work; +}; + +static const char *host1x_syncpt_fence_get_driver_name(struct dma_fence *f) +{ + return "host1x"; +} + +static const char *host1x_syncpt_fence_get_timeline_name(struct dma_fence *f) +{ + return "syncpoint"; +} + +static struct host1x_syncpt_fence *to_host1x_fence(struct dma_fence *f) +{ + return container_of(f, struct host1x_syncpt_fence, base); +} + +static bool host1x_syncpt_fence_enable_signaling(struct dma_fence *f) +{ + struct host1x_syncpt_fence *sf = to_host1x_fence(f); + int err; + + if (host1x_syncpt_is_expired(sf->sp, sf->threshold)) + return false; + + dma_fence_get(f); + + /* + * The dma_fence framework requires the fence driver to keep a + * reference to any fences for which 'enable_signaling' has been + * called (and that have not been signalled). + * + * We provide a userspace API to create arbitrary syncpoint fences, + * so we cannot normally guarantee that all fences get signalled. + * As such, setup a timeout, so that long-lasting fences will get + * reaped eventually. + */ + schedule_delayed_work(&sf->timeout_work, msecs_to_jiffies(30000)); + + err = host1x_intr_add_action(sf->sp->host, sf->sp, sf->threshold, + HOST1X_INTR_ACTION_SIGNAL_FENCE, f, + sf->waiter, &sf->waiter_ref); + if (err) { + cancel_delayed_work_sync(&sf->timeout_work); + dma_fence_put(f); + return false; + } + + /* intr framework takes ownership of waiter */ + sf->waiter = NULL; + + /* + * The fence may get signalled at any time after the above call, + * so we need to initialize all state used by signalling + * before it. + */ + + return true; +} + +static void host1x_syncpt_fence_release(struct dma_fence *f) +{ + struct host1x_syncpt_fence *sf = to_host1x_fence(f); + + if (sf->waiter) + kfree(sf->waiter); + + dma_fence_free(f); +} + +const struct dma_fence_ops host1x_syncpt_fence_ops = { + .get_driver_name = host1x_syncpt_fence_get_driver_name, + .get_timeline_name = host1x_syncpt_fence_get_timeline_name, + .enable_signaling = host1x_syncpt_fence_enable_signaling, + .release = host1x_syncpt_fence_release, +}; + +void host1x_fence_signal(struct host1x_syncpt_fence *f) +{ + if (atomic_xchg(&f->signaling, 1)) + return; + + /* + * Cancel pending timeout work - if it races, it will + * not get 'f->signaling' and return. + */ + cancel_delayed_work_sync(&f->timeout_work); + + host1x_intr_put_ref(f->sp->host, f->sp->id, f->waiter_ref, false); + + dma_fence_signal(&f->base); + dma_fence_put(&f->base); +} + +static void do_fence_timeout(struct work_struct *work) +{ + struct delayed_work *dwork = (struct delayed_work *)work; + struct host1x_syncpt_fence *f = + container_of(dwork, struct host1x_syncpt_fence, timeout_work); + + if (atomic_xchg(&f->signaling, 1)) + return; + + /* + * Cancel pending timeout work - if it races, it will + * not get 'f->signaling' and return. + */ + host1x_intr_put_ref(f->sp->host, f->sp->id, f->waiter_ref, true); + + dma_fence_set_error(&f->base, -ETIMEDOUT); + dma_fence_signal(&f->base); + dma_fence_put(&f->base); +} + +struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold) +{ + struct host1x_syncpt_fence *fence; + + fence = kzalloc(sizeof(*fence), GFP_KERNEL); + if (!fence) + return ERR_PTR(-ENOMEM); + + fence->waiter = kzalloc(sizeof(*fence->waiter), GFP_KERNEL); + if (!fence->waiter) + return ERR_PTR(-ENOMEM); + + fence->sp = sp; + fence->threshold = threshold; + + dma_fence_init(&fence->base, &host1x_syncpt_fence_ops, &lock, + dma_fence_context_alloc(1), 0); + + INIT_DELAYED_WORK(&fence->timeout_work, do_fence_timeout); + + return &fence->base; +} +EXPORT_SYMBOL(host1x_fence_create); diff --git a/drivers/gpu/host1x/fence.h b/drivers/gpu/host1x/fence.h new file mode 100644 index 000000000000..70c91de82f14 --- /dev/null +++ b/drivers/gpu/host1x/fence.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2020, NVIDIA Corporation. + */ + +#ifndef HOST1X_FENCE_H +#define HOST1X_FENCE_H + +struct host1x_syncpt_fence; + +void host1x_fence_signal(struct host1x_syncpt_fence *fence); + +#endif diff --git a/drivers/gpu/host1x/intr.c b/drivers/gpu/host1x/intr.c index 6d1f3c0fdbe7..45b6be927ec4 100644 --- a/drivers/gpu/host1x/intr.c +++ b/drivers/gpu/host1x/intr.c @@ -13,6 +13,7 @@ #include #include "channel.h" #include "dev.h" +#include "fence.h" #include "intr.h" /* Wait list management */ @@ -121,12 +122,20 @@ static void action_wakeup_interruptible(struct host1x_waitlist *waiter) wake_up_interruptible(wq); } +static void action_signal_fence(struct host1x_waitlist *waiter) +{ + struct host1x_syncpt_fence *f = waiter->data; + + host1x_fence_signal(f); +} + typedef void (*action_handler)(struct host1x_waitlist *waiter); static const action_handler action_handlers[HOST1X_INTR_ACTION_COUNT] = { action_submit_complete, action_wakeup, action_wakeup_interruptible, + action_signal_fence, }; static void run_handlers(struct list_head completed[HOST1X_INTR_ACTION_COUNT]) diff --git a/drivers/gpu/host1x/intr.h b/drivers/gpu/host1x/intr.h index 6ea55e615e3a..e4c346099273 100644 --- a/drivers/gpu/host1x/intr.h +++ b/drivers/gpu/host1x/intr.h @@ -33,6 +33,8 @@ enum host1x_intr_action { */ HOST1X_INTR_ACTION_WAKEUP_INTERRUPTIBLE, + HOST1X_INTR_ACTION_SIGNAL_FENCE, + HOST1X_INTR_ACTION_COUNT }; diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 9b0487c88571..eb4cc8c964a4 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -170,6 +170,8 @@ u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base); void host1x_syncpt_release_vblank_reservation(struct host1x_client *client, u32 syncpt_id); +struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold); + /* * host1x channel */ -- cgit v1.2.3 From c78f837ae3d1e532ff4eb90155b42d7a2e892a3f Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 10 Jun 2021 14:04:43 +0300 Subject: gpu: host1x: Add no-recovery mode Add a new property for jobs to enable or disable recovery i.e. CPU increments of syncpoints to max value on job timeout. This allows for a more solid model for hanged jobs, where userspace doesn't need to guess if a syncpoint increment happened because the job completed, or because job timeout was triggered. On job timeout, we stop the channel, NOP all future jobs on the channel using the same syncpoint, mark the syncpoint as locked and resume the channel from the next job, if any. The future jobs are NOPed, since because we don't do the CPU increments, the value of the syncpoint is no longer synchronized, and any waiters would become confused if a future job incremented the syncpoint. The syncpoint is marked locked to ensure that any future jobs cannot increment the syncpoint either, until the application has recognized the situation and reallocated the syncpoint. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/drm.c | 1 + drivers/gpu/host1x/cdma.c | 58 ++++++++++++++++++++++++++++++++++---- drivers/gpu/host1x/hw/channel_hw.c | 2 +- drivers/gpu/host1x/job.c | 4 +++ drivers/gpu/host1x/syncpt.c | 2 ++ drivers/gpu/host1x/syncpt.h | 12 ++++++++ include/linux/host1x.h | 9 ++++++ 7 files changed, 81 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index f96c237b2242..739250acd498 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -201,6 +201,7 @@ int tegra_drm_submit(struct tegra_drm_context *context, job->client = client; job->class = client->class; job->serialize = true; + job->syncpt_recovery = true; /* * Track referenced BOs so that they can be unreferenced after the diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c index 6e6ca774f68d..765e5aa64eb6 100644 --- a/drivers/gpu/host1x/cdma.c +++ b/drivers/gpu/host1x/cdma.c @@ -312,10 +312,6 @@ static void update_cdma_locked(struct host1x_cdma *cdma) bool signal = false; struct host1x_job *job, *n; - /* If CDMA is stopped, queue is cleared and we can return */ - if (!cdma->running) - return; - /* * Walk the sync queue, reading the sync point registers as necessary, * to consume as many sync queue entries as possible without blocking @@ -324,7 +320,8 @@ static void update_cdma_locked(struct host1x_cdma *cdma) struct host1x_syncpt *sp = job->syncpt; /* Check whether this syncpt has completed, and bail if not */ - if (!host1x_syncpt_is_expired(sp, job->syncpt_end)) { + if (!host1x_syncpt_is_expired(sp, job->syncpt_end) && + !job->cancelled) { /* Start timer on next pending syncpt */ if (job->timeout) cdma_start_timer_locked(cdma, job); @@ -413,8 +410,11 @@ syncpt_incr: else restart_addr = cdma->last_pos; + if (!job) + goto resume; + /* do CPU increments for the remaining syncpts */ - if (job) { + if (job->syncpt_recovery) { dev_dbg(dev, "%s: perform CPU incr on pending buffers\n", __func__); @@ -433,8 +433,44 @@ syncpt_incr: dev_dbg(dev, "%s: finished sync_queue modification\n", __func__); + } else { + struct host1x_job *failed_job = job; + + host1x_job_dump(dev, job); + + host1x_syncpt_set_locked(job->syncpt); + failed_job->cancelled = true; + + list_for_each_entry_continue(job, &cdma->sync_queue, list) { + unsigned int i; + + if (job->syncpt != failed_job->syncpt) + continue; + + for (i = 0; i < job->num_slots; i++) { + unsigned int slot = (job->first_get/8 + i) % + HOST1X_PUSHBUFFER_SLOTS; + u32 *mapped = cdma->push_buffer.mapped; + + /* + * Overwrite opcodes with 0 word writes + * to offset 0xbad. This does nothing but + * has a easily detected signature in debug + * traces. + */ + mapped[2*slot+0] = 0x1bad0000; + mapped[2*slot+1] = 0x1bad0000; + } + + job->cancelled = true; + } + + wmb(); + + update_cdma_locked(cdma); } +resume: /* roll back DMAGET and start up channel again */ host1x_hw_cdma_resume(host1x, cdma, restart_addr); } @@ -490,6 +526,16 @@ int host1x_cdma_begin(struct host1x_cdma *cdma, struct host1x_job *job) mutex_lock(&cdma->lock); + /* + * Check if syncpoint was locked due to previous job timeout. + * This needs to be done within the cdma lock to avoid a race + * with the timeout handler. + */ + if (job->syncpt->locked) { + mutex_unlock(&cdma->lock); + return -EPERM; + } + if (job->timeout) { /* init state on first submit with timeout value */ if (!cdma->timeout.initialized) { diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c index d4c28faf27d1..bf21512e5078 100644 --- a/drivers/gpu/host1x/hw/channel_hw.c +++ b/drivers/gpu/host1x/hw/channel_hw.c @@ -191,7 +191,7 @@ static int channel_submit(struct host1x_job *job) /* schedule a submit complete interrupt */ err = host1x_intr_add_action(host, sp, syncval, HOST1X_INTR_ACTION_SUBMIT_COMPLETE, ch, - completed_waiter, NULL); + completed_waiter, &job->waiter); completed_waiter = NULL; WARN(err, "Failed to set submit complete interrupt"); diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index adbdc225de8d..8f59b34672c2 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -79,6 +79,10 @@ static void job_free(struct kref *ref) { struct host1x_job *job = container_of(ref, struct host1x_job, ref); + if (job->waiter) + host1x_intr_put_ref(job->syncpt->host, job->syncpt->id, + job->waiter, false); + if (job->syncpt) host1x_syncpt_put(job->syncpt); diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c index e648ebbb2027..d198a10848c6 100644 --- a/drivers/gpu/host1x/syncpt.c +++ b/drivers/gpu/host1x/syncpt.c @@ -407,6 +407,8 @@ static void syncpt_release(struct kref *ref) atomic_set(&sp->max_val, host1x_syncpt_read(sp)); + sp->locked = false; + mutex_lock(&sp->host->syncpt_mutex); host1x_syncpt_base_free(sp->base); diff --git a/drivers/gpu/host1x/syncpt.h b/drivers/gpu/host1x/syncpt.h index a6766f8d55ee..95cd29b79d6d 100644 --- a/drivers/gpu/host1x/syncpt.h +++ b/drivers/gpu/host1x/syncpt.h @@ -40,6 +40,13 @@ struct host1x_syncpt { /* interrupt data */ struct host1x_syncpt_intr intr; + + /* + * If a submission incrementing this syncpoint fails, lock it so that + * further submission cannot be made until application has handled the + * failure. + */ + bool locked; }; /* Initialize sync point array */ @@ -115,4 +122,9 @@ static inline int host1x_syncpt_is_valid(struct host1x_syncpt *sp) return sp->id < host1x_syncpt_nb_pts(sp->host); } +static inline void host1x_syncpt_set_locked(struct host1x_syncpt *sp) +{ + sp->locked = true; +} + #endif diff --git a/include/linux/host1x.h b/include/linux/host1x.h index eb4cc8c964a4..8da088ad0b5e 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -236,9 +236,15 @@ struct host1x_job { u32 syncpt_incrs; u32 syncpt_end; + /* Completion waiter ref */ + void *waiter; + /* Maximum time to wait for this job */ unsigned int timeout; + /* Job has timed out and should be released */ + bool cancelled; + /* Index and number of slots used in the push buffer */ unsigned int first_get; unsigned int num_slots; @@ -259,6 +265,9 @@ struct host1x_job { /* Add a channel wait for previous ops to complete */ bool serialize; + + /* Fast-forward syncpoint increments on job timeout */ + bool syncpt_recovery; }; struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, -- cgit v1.2.3 From 17a298e9ac7c011e64a9c0b6f807b43f9af22eac Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 10 Jun 2021 14:04:44 +0300 Subject: gpu: host1x: Add job release callback Add a callback field to the job structure, to be called just before the job is to be freed. This allows the job's submitter to clean up any of its own state, like decrement runtime PM refcounts. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/host1x/job.c | 3 +++ include/linux/host1x.h | 4 ++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index 8f59b34672c2..09097e19c0d0 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -79,6 +79,9 @@ static void job_free(struct kref *ref) { struct host1x_job *job = container_of(ref, struct host1x_job, ref); + if (job->release) + job->release(job); + if (job->waiter) host1x_intr_put_ref(job->syncpt->host, job->syncpt->id, job->waiter, false); diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 8da088ad0b5e..57271ab1fee8 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -268,6 +268,10 @@ struct host1x_job { /* Fast-forward syncpoint increments on job timeout */ bool syncpt_recovery; + + /* Callback called when job is freed */ + void (*release)(struct host1x_job *job); + void *user_data; }; struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, -- cgit v1.2.3 From e902585fc8b639f1a1258eaa6265e98994e34ef8 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 10 Jun 2021 14:04:45 +0300 Subject: gpu: host1x: Add support for syncpoint waits in CDMA pushbuffer Add support for inserting syncpoint waits in the CDMA pushbuffer. These waits need to be done in HOST1X class, while gather submitted by the application execute in engine class. Support is added by converting the gather list of job into a command list that can include both gathers and waits. When the job is submitted, these commands are pushed as the appropriate opcodes on the CDMA pushbuffer. Also supported are waits relative to the start of the job, which are useful for jobs doing multiple things with an engine that doesn't natively support pipelining. While at it, use 32-bit waits on chips that support them. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/host1x/hw/channel_hw.c | 85 +++++++++++++++++++++++------- drivers/gpu/host1x/hw/debug_hw.c | 9 +++- drivers/gpu/host1x/hw/hw_host1x02_uclass.h | 12 +++++ drivers/gpu/host1x/hw/hw_host1x04_uclass.h | 12 +++++ drivers/gpu/host1x/hw/hw_host1x05_uclass.h | 12 +++++ drivers/gpu/host1x/hw/hw_host1x06_uclass.h | 12 +++++ drivers/gpu/host1x/hw/hw_host1x07_uclass.h | 12 +++++ drivers/gpu/host1x/job.c | 70 +++++++++++++++++------- drivers/gpu/host1x/job.h | 16 ++++++ include/linux/host1x.h | 6 ++- 10 files changed, 203 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c index bf21512e5078..1999780a7203 100644 --- a/drivers/gpu/host1x/hw/channel_hw.c +++ b/drivers/gpu/host1x/hw/channel_hw.c @@ -47,39 +47,84 @@ static void trace_write_gather(struct host1x_cdma *cdma, struct host1x_bo *bo, } } -static void submit_gathers(struct host1x_job *job) +static void submit_wait(struct host1x_cdma *cdma, u32 id, u32 threshold, + u32 next_class) +{ +#if HOST1X_HW >= 2 + host1x_cdma_push_wide(cdma, + host1x_opcode_setclass( + HOST1X_CLASS_HOST1X, + HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32, + /* WAIT_SYNCPT_32 is at SYNCPT_PAYLOAD_32+2 */ + BIT(0) | BIT(2) + ), + threshold, + id, + host1x_opcode_setclass(next_class, 0, 0) + ); +#else + /* TODO add waitchk or use waitbases or other mitigation */ + host1x_cdma_push(cdma, + host1x_opcode_setclass( + HOST1X_CLASS_HOST1X, + host1x_uclass_wait_syncpt_r(), + BIT(0) + ), + host1x_class_host_wait_syncpt(id, threshold) + ); + host1x_cdma_push(cdma, + host1x_opcode_setclass(next_class, 0, 0), + HOST1X_OPCODE_NOP + ); +#endif +} + +static void submit_gathers(struct host1x_job *job, u32 job_syncpt_base) { struct host1x_cdma *cdma = &job->channel->cdma; #if HOST1X_HW < 6 struct device *dev = job->channel->dev; #endif unsigned int i; + u32 threshold; - for (i = 0; i < job->num_gathers; i++) { - struct host1x_job_gather *g = &job->gathers[i]; - dma_addr_t addr = g->base + g->offset; - u32 op2, op3; + for (i = 0; i < job->num_cmds; i++) { + struct host1x_job_cmd *cmd = &job->cmds[i]; - op2 = lower_32_bits(addr); - op3 = upper_32_bits(addr); + if (cmd->is_wait) { + if (cmd->wait.relative) + threshold = job_syncpt_base + cmd->wait.threshold; + else + threshold = cmd->wait.threshold; - trace_write_gather(cdma, g->bo, g->offset, g->words); + submit_wait(cdma, cmd->wait.id, threshold, cmd->wait.next_class); + } else { + struct host1x_job_gather *g = &cmd->gather; + + dma_addr_t addr = g->base + g->offset; + u32 op2, op3; + + op2 = lower_32_bits(addr); + op3 = upper_32_bits(addr); - if (op3 != 0) { + trace_write_gather(cdma, g->bo, g->offset, g->words); + + if (op3 != 0) { #if HOST1X_HW >= 6 - u32 op1 = host1x_opcode_gather_wide(g->words); - u32 op4 = HOST1X_OPCODE_NOP; + u32 op1 = host1x_opcode_gather_wide(g->words); + u32 op4 = HOST1X_OPCODE_NOP; - host1x_cdma_push_wide(cdma, op1, op2, op3, op4); + host1x_cdma_push_wide(cdma, op1, op2, op3, op4); #else - dev_err(dev, "invalid gather for push buffer %pad\n", - &addr); - continue; + dev_err(dev, "invalid gather for push buffer %pad\n", + &addr); + continue; #endif - } else { - u32 op1 = host1x_opcode_gather(g->words); + } else { + u32 op1 = host1x_opcode_gather(g->words); - host1x_cdma_push(cdma, op1, op2); + host1x_cdma_push(cdma, op1, op2); + } } } } @@ -126,7 +171,7 @@ static int channel_submit(struct host1x_job *job) struct host1x *host = dev_get_drvdata(ch->dev->parent); trace_host1x_channel_submit(dev_name(ch->dev), - job->num_gathers, job->num_relocs, + job->num_cmds, job->num_relocs, job->syncpt->id, job->syncpt_incrs); /* before error checks, return current max */ @@ -181,7 +226,7 @@ static int channel_submit(struct host1x_job *job) host1x_opcode_setclass(job->class, 0, 0), HOST1X_OPCODE_NOP); - submit_gathers(job); + submit_gathers(job, syncval - user_syncpt_incrs); /* end CDMA submit & stash pinned hMems into sync queue */ host1x_cdma_end(&ch->cdma, job); diff --git a/drivers/gpu/host1x/hw/debug_hw.c b/drivers/gpu/host1x/hw/debug_hw.c index ceb48229d14b..35952fd5597e 100644 --- a/drivers/gpu/host1x/hw/debug_hw.c +++ b/drivers/gpu/host1x/hw/debug_hw.c @@ -208,10 +208,15 @@ static void show_channel_gathers(struct output *o, struct host1x_cdma *cdma) job->first_get, job->timeout, job->num_slots, job->num_unpins); - for (i = 0; i < job->num_gathers; i++) { - struct host1x_job_gather *g = &job->gathers[i]; + for (i = 0; i < job->num_cmds; i++) { + struct host1x_job_gather *g; u32 *mapped; + if (job->cmds[i].is_wait) + continue; + + g = &job->cmds[i].gather; + if (job->gather_copy_mapped) mapped = (u32 *)job->gather_copy_mapped; else diff --git a/drivers/gpu/host1x/hw/hw_host1x02_uclass.h b/drivers/gpu/host1x/hw/hw_host1x02_uclass.h index 4fc51f70496b..0a2ab8f1da6f 100644 --- a/drivers/gpu/host1x/hw/hw_host1x02_uclass.h +++ b/drivers/gpu/host1x/hw/hw_host1x02_uclass.h @@ -165,5 +165,17 @@ static inline u32 host1x_uclass_indoff_rwn_read_v(void) } #define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \ host1x_uclass_indoff_indroffset_f(v) +static inline u32 host1x_uclass_load_syncpt_payload_32_r(void) +{ + return 0x4e; +} +#define HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32 \ + host1x_uclass_load_syncpt_payload_32_r() +static inline u32 host1x_uclass_wait_syncpt_32_r(void) +{ + return 0x50; +} +#define HOST1X_UCLASS_WAIT_SYNCPT_32 \ + host1x_uclass_wait_syncpt_32_r() #endif diff --git a/drivers/gpu/host1x/hw/hw_host1x04_uclass.h b/drivers/gpu/host1x/hw/hw_host1x04_uclass.h index 9e84a4adca9f..60c692b92955 100644 --- a/drivers/gpu/host1x/hw/hw_host1x04_uclass.h +++ b/drivers/gpu/host1x/hw/hw_host1x04_uclass.h @@ -165,5 +165,17 @@ static inline u32 host1x_uclass_indoff_rwn_read_v(void) } #define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \ host1x_uclass_indoff_indroffset_f(v) +static inline u32 host1x_uclass_load_syncpt_payload_32_r(void) +{ + return 0x4e; +} +#define HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32 \ + host1x_uclass_load_syncpt_payload_32_r() +static inline u32 host1x_uclass_wait_syncpt_32_r(void) +{ + return 0x50; +} +#define HOST1X_UCLASS_WAIT_SYNCPT_32 \ + host1x_uclass_wait_syncpt_32_r() #endif diff --git a/drivers/gpu/host1x/hw/hw_host1x05_uclass.h b/drivers/gpu/host1x/hw/hw_host1x05_uclass.h index aee5a4e32877..2fcc9a2ad3ef 100644 --- a/drivers/gpu/host1x/hw/hw_host1x05_uclass.h +++ b/drivers/gpu/host1x/hw/hw_host1x05_uclass.h @@ -165,5 +165,17 @@ static inline u32 host1x_uclass_indoff_rwn_read_v(void) } #define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \ host1x_uclass_indoff_indroffset_f(v) +static inline u32 host1x_uclass_load_syncpt_payload_32_r(void) +{ + return 0x4e; +} +#define HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32 \ + host1x_uclass_load_syncpt_payload_32_r() +static inline u32 host1x_uclass_wait_syncpt_32_r(void) +{ + return 0x50; +} +#define HOST1X_UCLASS_WAIT_SYNCPT_32 \ + host1x_uclass_wait_syncpt_32_r() #endif diff --git a/drivers/gpu/host1x/hw/hw_host1x06_uclass.h b/drivers/gpu/host1x/hw/hw_host1x06_uclass.h index c4bacdb7155f..5f831438d19b 100644 --- a/drivers/gpu/host1x/hw/hw_host1x06_uclass.h +++ b/drivers/gpu/host1x/hw/hw_host1x06_uclass.h @@ -165,5 +165,17 @@ static inline u32 host1x_uclass_indoff_rwn_read_v(void) } #define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \ host1x_uclass_indoff_indroffset_f(v) +static inline u32 host1x_uclass_load_syncpt_payload_32_r(void) +{ + return 0x4e; +} +#define HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32 \ + host1x_uclass_load_syncpt_payload_32_r() +static inline u32 host1x_uclass_wait_syncpt_32_r(void) +{ + return 0x50; +} +#define HOST1X_UCLASS_WAIT_SYNCPT_32 \ + host1x_uclass_wait_syncpt_32_r() #endif diff --git a/drivers/gpu/host1x/hw/hw_host1x07_uclass.h b/drivers/gpu/host1x/hw/hw_host1x07_uclass.h index c74070f3f203..8cd2ef087d5d 100644 --- a/drivers/gpu/host1x/hw/hw_host1x07_uclass.h +++ b/drivers/gpu/host1x/hw/hw_host1x07_uclass.h @@ -165,5 +165,17 @@ static inline u32 host1x_uclass_indoff_rwn_read_v(void) } #define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \ host1x_uclass_indoff_indroffset_f(v) +static inline u32 host1x_uclass_load_syncpt_payload_32_r(void) +{ + return 0x4e; +} +#define HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32 \ + host1x_uclass_load_syncpt_payload_32_r() +static inline u32 host1x_uclass_wait_syncpt_32_r(void) +{ + return 0x50; +} +#define HOST1X_UCLASS_WAIT_SYNCPT_32 \ + host1x_uclass_wait_syncpt_32_r() #endif diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index 09097e19c0d0..32619b73a2fc 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -38,7 +38,7 @@ struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, total = sizeof(struct host1x_job) + (u64)num_relocs * sizeof(struct host1x_reloc) + (u64)num_unpins * sizeof(struct host1x_job_unpin_data) + - (u64)num_cmdbufs * sizeof(struct host1x_job_gather) + + (u64)num_cmdbufs * sizeof(struct host1x_job_cmd) + (u64)num_unpins * sizeof(dma_addr_t) + (u64)num_unpins * sizeof(u32 *); if (total > ULONG_MAX) @@ -57,8 +57,8 @@ struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, mem += num_relocs * sizeof(struct host1x_reloc); job->unpins = num_unpins ? mem : NULL; mem += num_unpins * sizeof(struct host1x_job_unpin_data); - job->gathers = num_cmdbufs ? mem : NULL; - mem += num_cmdbufs * sizeof(struct host1x_job_gather); + job->cmds = num_cmdbufs ? mem : NULL; + mem += num_cmdbufs * sizeof(struct host1x_job_cmd); job->addr_phys = num_unpins ? mem : NULL; job->reloc_addr_phys = job->addr_phys; @@ -101,22 +101,38 @@ EXPORT_SYMBOL(host1x_job_put); void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *bo, unsigned int words, unsigned int offset) { - struct host1x_job_gather *gather = &job->gathers[job->num_gathers]; + struct host1x_job_gather *gather = &job->cmds[job->num_cmds].gather; gather->words = words; gather->bo = bo; gather->offset = offset; - job->num_gathers++; + job->num_cmds++; } EXPORT_SYMBOL(host1x_job_add_gather); +void host1x_job_add_wait(struct host1x_job *job, u32 id, u32 thresh, + bool relative, u32 next_class) +{ + struct host1x_job_cmd *cmd = &job->cmds[job->num_cmds]; + + cmd->is_wait = true; + cmd->wait.id = id; + cmd->wait.threshold = thresh; + cmd->wait.next_class = next_class; + cmd->wait.relative = relative; + + job->num_cmds++; +} +EXPORT_SYMBOL(host1x_job_add_wait); + static unsigned int pin_job(struct host1x *host, struct host1x_job *job) { struct host1x_client *client = job->client; struct device *dev = client->dev; struct host1x_job_gather *g; struct iommu_domain *domain; + struct sg_table *sgt; unsigned int i; int err; @@ -126,7 +142,6 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) for (i = 0; i < job->num_relocs; i++) { struct host1x_reloc *reloc = &job->relocs[i]; dma_addr_t phys_addr, *phys; - struct sg_table *sgt; reloc->target.bo = host1x_bo_get(reloc->target.bo); if (!reloc->target.bo) { @@ -202,17 +217,20 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) return 0; - for (i = 0; i < job->num_gathers; i++) { + for (i = 0; i < job->num_cmds; i++) { size_t gather_size = 0; struct scatterlist *sg; - struct sg_table *sgt; dma_addr_t phys_addr; unsigned long shift; struct iova *alloc; dma_addr_t *phys; unsigned int j; - g = &job->gathers[i]; + if (job->cmds[i].is_wait) + continue; + + g = &job->cmds[i].gather; + g->bo = host1x_bo_get(g->bo); if (!g->bo) { err = -EINVAL; @@ -545,8 +563,13 @@ static inline int copy_gathers(struct device *host, struct host1x_job *job, fw.num_relocs = job->num_relocs; fw.class = job->class; - for (i = 0; i < job->num_gathers; i++) { - struct host1x_job_gather *g = &job->gathers[i]; + for (i = 0; i < job->num_cmds; i++) { + struct host1x_job_gather *g; + + if (job->cmds[i].is_wait) + continue; + + g = &job->cmds[i].gather; size += g->words * sizeof(u32); } @@ -568,10 +591,14 @@ static inline int copy_gathers(struct device *host, struct host1x_job *job, job->gather_copy_size = size; - for (i = 0; i < job->num_gathers; i++) { - struct host1x_job_gather *g = &job->gathers[i]; + for (i = 0; i < job->num_cmds; i++) { + struct host1x_job_gather *g; void *gather; + if (job->cmds[i].is_wait) + continue; + g = &job->cmds[i].gather; + /* Copy the gather */ gather = host1x_bo_mmap(g->bo); memcpy(job->gather_copy_mapped + offset, gather + g->offset, @@ -614,8 +641,12 @@ int host1x_job_pin(struct host1x_job *job, struct device *dev) } /* patch gathers */ - for (i = 0; i < job->num_gathers; i++) { - struct host1x_job_gather *g = &job->gathers[i]; + for (i = 0; i < job->num_cmds; i++) { + struct host1x_job_gather *g; + + if (job->cmds[i].is_wait) + continue; + g = &job->cmds[i].gather; /* process each gather mem only once */ if (g->handled) @@ -625,10 +656,11 @@ int host1x_job_pin(struct host1x_job *job, struct device *dev) if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) g->base = job->gather_addr_phys[i]; - for (j = i + 1; j < job->num_gathers; j++) { - if (job->gathers[j].bo == g->bo) { - job->gathers[j].handled = true; - job->gathers[j].base = g->base; + for (j = i + 1; j < job->num_cmds; j++) { + if (!job->cmds[j].is_wait && + job->cmds[j].gather.bo == g->bo) { + job->cmds[j].gather.handled = true; + job->cmds[j].gather.base = g->base; } } diff --git a/drivers/gpu/host1x/job.h b/drivers/gpu/host1x/job.h index 94bc2e4ae241..b4428c5495c9 100644 --- a/drivers/gpu/host1x/job.h +++ b/drivers/gpu/host1x/job.h @@ -18,6 +18,22 @@ struct host1x_job_gather { bool handled; }; +struct host1x_job_wait { + u32 id; + u32 threshold; + u32 next_class; + bool relative; +}; + +struct host1x_job_cmd { + bool is_wait; + + union { + struct host1x_job_gather gather; + struct host1x_job_wait wait; + }; +}; + struct host1x_job_unpin_data { struct host1x_bo *bo; struct sg_table *sgt; diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 57271ab1fee8..2127762fc63d 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -218,8 +218,8 @@ struct host1x_job { struct host1x_client *client; /* Gathers and their memory */ - struct host1x_job_gather *gathers; - unsigned int num_gathers; + struct host1x_job_cmd *cmds; + unsigned int num_cmds; /* Array of handles to be pinned & unpinned */ struct host1x_reloc *relocs; @@ -278,6 +278,8 @@ struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, u32 num_cmdbufs, u32 num_relocs); void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *bo, unsigned int words, unsigned int offset); +void host1x_job_add_wait(struct host1x_job *job, u32 id, u32 thresh, + bool relative, u32 next_class); struct host1x_job *host1x_job_get(struct host1x_job *job); void host1x_job_put(struct host1x_job *job); int host1x_job_pin(struct host1x_job *job, struct device *dev); -- cgit v1.2.3 From 0fddaa85d66140466df8e848afcda452b7d7b416 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 10 Jun 2021 14:04:46 +0300 Subject: gpu: host1x: Add option to skip firewall for a job The new UAPI will have its own firewall, and we don't want to run the firewall in the Host1x driver for those jobs. As such, add a parameter to host1x_job_alloc to specify if we want to skip the firewall in the Host1x driver. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/drm.c | 2 +- drivers/gpu/host1x/job.c | 21 +++++++++++++-------- include/linux/host1x.h | 6 +++++- 3 files changed, 19 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 739250acd498..0e2a6f24c4f6 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -193,7 +193,7 @@ int tegra_drm_submit(struct tegra_drm_context *context, return -EINVAL; job = host1x_job_alloc(context->channel, args->num_cmdbufs, - args->num_relocs); + args->num_relocs, false); if (!job) return -ENOMEM; diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index 32619b73a2fc..0eef6df7c89e 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -24,14 +24,18 @@ #define HOST1X_WAIT_SYNCPT_OFFSET 0x8 struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, - u32 num_cmdbufs, u32 num_relocs) + u32 num_cmdbufs, u32 num_relocs, + bool skip_firewall) { struct host1x_job *job = NULL; unsigned int num_unpins = num_relocs; + bool enable_firewall; u64 total; void *mem; - if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) + enable_firewall = IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && !skip_firewall; + + if (!enable_firewall) num_unpins += num_cmdbufs; /* Check that we're not going to overflow */ @@ -48,6 +52,8 @@ struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, if (!job) return NULL; + job->enable_firewall = enable_firewall; + kref_init(&job->ref); job->channel = ch; @@ -214,7 +220,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) * We will copy gathers BO content later, so there is no need to * hold and pin them. */ - if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) + if (job->enable_firewall) return 0; for (i = 0; i < job->num_cmds; i++) { @@ -321,7 +327,7 @@ static int do_relocs(struct host1x_job *job, struct host1x_job_gather *g) if (cmdbuf != reloc->cmdbuf.bo) continue; - if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) { + if (job->enable_firewall) { target = (u32 *)job->gather_copy_mapped + reloc->cmdbuf.offset / sizeof(u32) + g->offset / sizeof(u32); @@ -634,7 +640,7 @@ int host1x_job_pin(struct host1x_job *job, struct device *dev) if (err) goto out; - if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) { + if (job->enable_firewall) { err = copy_gathers(host->dev, job, dev); if (err) goto out; @@ -653,7 +659,7 @@ int host1x_job_pin(struct host1x_job *job, struct device *dev) continue; /* copy_gathers() sets gathers base if firewall is enabled */ - if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) + if (!job->enable_firewall) g->base = job->gather_addr_phys[i]; for (j = i + 1; j < job->num_cmds; j++) { @@ -688,8 +694,7 @@ void host1x_job_unpin(struct host1x_job *job) struct device *dev = unpin->dev ?: host->dev; struct sg_table *sgt = unpin->sgt; - if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && - unpin->size && host->domain) { + if (!job->enable_firewall && unpin->size && host->domain) { iommu_unmap(host->domain, job->addr_phys[i], unpin->size); free_iova(&host->iova, diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 2127762fc63d..7bccf589aba7 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -272,10 +272,14 @@ struct host1x_job { /* Callback called when job is freed */ void (*release)(struct host1x_job *job); void *user_data; + + /* Whether host1x-side firewall should be ran for this job or not */ + bool enable_firewall; }; struct host1x_job *host1x_job_alloc(struct host1x_channel *ch, - u32 num_cmdbufs, u32 num_relocs); + u32 num_cmdbufs, u32 num_relocs, + bool skip_firewall); void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *bo, unsigned int words, unsigned int offset); void host1x_job_add_wait(struct host1x_job *job, u32 id, u32 thresh, -- cgit v1.2.3 From 99d26de2f6d79badc80f55b54bd90d4cb9d1ad90 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 14:39:24 +0200 Subject: writeback: make the laptop_mode prototypes available unconditionally Fix the !CONFIG_BLOCK build after the recent cleanup. Fixes: 5ed964f8e54e ("mm: hide laptop_mode_wb_timer entirely behind the BDI API") Reported-by: Stephen Rothwell Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/writeback.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 667e86cfbdcf..270677dc4f36 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -336,14 +336,9 @@ static inline void cgroup_writeback_umount(void) /* * mm/page-writeback.c */ -#ifdef CONFIG_BLOCK void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); -void laptop_mode_sync(struct work_struct *work); void laptop_mode_timer_fn(struct timer_list *t); -#else -static inline void laptop_sync_completion(void) { } -#endif bool node_dirty_ok(struct pglist_data *pgdat); int wb_domain_init(struct wb_domain *dom, gfp_t gfp); #ifdef CONFIG_CGROUP_WRITEBACK -- cgit v1.2.3 From a5dec9f82ab2ae486119f0b0820ea16db3e522c3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 26 Jul 2021 14:55:08 +0200 Subject: posix-cpu-timers: Assert task sighand is locked while starting cputime counter Starting the process wide cputime counter needs to be done in the same sighand locking sequence than actually arming the related timer otherwise this races against concurrent timers setting/expiring in the same threadgroup. Detecting that the cputime counter is started without holding the sighand lock is a first step toward debugging such situations. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210726125513.271824-2-frederic@kernel.org --- include/linux/sched/signal.h | 6 ++++++ kernel/signal.c | 15 +++++++++++++++ kernel/time/posix-cpu-timers.c | 2 ++ 3 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index b9126fe06c3f..0310a5add9ab 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -714,6 +714,12 @@ static inline void unlock_task_sighand(struct task_struct *task, spin_unlock_irqrestore(&task->sighand->siglock, *flags); } +#ifdef CONFIG_LOCKDEP +extern void lockdep_assert_task_sighand_held(struct task_struct *task); +#else +static inline void lockdep_assert_task_sighand_held(struct task_struct *task) { } +#endif + static inline unsigned long task_rlimit(const struct task_struct *task, unsigned int limit) { diff --git a/kernel/signal.c b/kernel/signal.c index a3229add4455..52b6abec0ff8 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1413,6 +1413,21 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, return sighand; } +#ifdef CONFIG_LOCKDEP +void lockdep_assert_task_sighand_held(struct task_struct *task) +{ + struct sighand_struct *sighand; + + rcu_read_lock(); + sighand = rcu_dereference(task->sighand); + if (sighand) + lockdep_assert_held(&sighand->siglock); + else + WARN_ON_ONCE(1); + rcu_read_unlock(); +} +#endif + /* * send signal info to all the members of a group */ diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 517be7fd175e..4693d3c71e7e 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -291,6 +291,8 @@ static void thread_group_start_cputime(struct task_struct *tsk, u64 *samples) struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; struct posix_cputimers *pct = &tsk->signal->posix_cputimers; + lockdep_assert_task_sighand_held(tsk); + /* Check if cputimer isn't running. This is accessed without locking. */ if (!READ_ONCE(pct->timers_active)) { struct task_cputime sum; -- cgit v1.2.3 From 175cc3ab28e3509ddee8de4f164b563d99daa570 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 26 Jul 2021 14:55:09 +0200 Subject: posix-cpu-timers: Force next_expiration recalc after timer deletion A timer deletion only dequeues the timer but it doesn't shutdown the related costly process wide cputimer counter and the tick dependency. The following code snippet keeps this overhead around for one week after the timer deletion: void trigger_process_counter(void) { timer_t id; struct itimerspec val = { }; val.it_value.tv_sec = 604800; timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id); timer_settime(id, 0, &val, NULL); timer_delete(id); } Make sure the next target's tick recalculates the nearest expiration and clears the process wide counter and tick dependency if necessary. Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210726125513.271824-3-frederic@kernel.org --- include/linux/posix-timers.h | 4 +++- kernel/time/posix-cpu-timers.c | 33 ++++++++++++++++++++++++++++++++- 2 files changed, 35 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 896c16d2c5fb..4cf1fbe8d1bc 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -82,12 +82,14 @@ static inline bool cpu_timer_enqueue(struct timerqueue_head *head, return timerqueue_add(head, &ctmr->node); } -static inline void cpu_timer_dequeue(struct cpu_timer *ctmr) +static inline bool cpu_timer_dequeue(struct cpu_timer *ctmr) { if (ctmr->head) { timerqueue_del(ctmr->head, &ctmr->node); ctmr->head = NULL; + return true; } + return false; } static inline u64 cpu_timer_getexpires(struct cpu_timer *ctmr) diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 4693d3c71e7e..61c78b62fe6a 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -407,6 +407,37 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer) return 0; } +/* + * Dequeue the timer and reset the base if it was its earliest expiration. + * It makes sure the next tick recalculates the base next expiration so we + * don't keep the costly process wide cputime counter around for a random + * amount of time, along with the tick dependency. + * + * If another timer gets queued between this and the next tick, its + * expiration will update the base next event if necessary on the next + * tick. + */ +static void disarm_timer(struct k_itimer *timer, struct task_struct *p) +{ + struct cpu_timer *ctmr = &timer->it.cpu; + struct posix_cputimer_base *base; + int clkidx; + + if (!cpu_timer_dequeue(ctmr)) + return; + + clkidx = CPUCLOCK_WHICH(timer->it_clock); + + if (CPUCLOCK_PERTHREAD(timer->it_clock)) + base = p->posix_cputimers.bases + clkidx; + else + base = p->signal->posix_cputimers.bases + clkidx; + + if (cpu_timer_getexpires(ctmr) == base->nextevt) + base->nextevt = 0; +} + + /* * Clean up a CPU-clock timer that is about to be destroyed. * This is called from timer deletion with the timer already locked. @@ -441,7 +472,7 @@ static int posix_cpu_timer_del(struct k_itimer *timer) if (timer->it.cpu.firing) ret = TIMER_RETRY; else - cpu_timer_dequeue(ctmr); + disarm_timer(timer, p); unlock_task_sighand(p, &flags); } -- cgit v1.2.3 From ee375328f579f94251eb66d5dc91aba056019a31 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 26 Jul 2021 14:55:13 +0200 Subject: posix-cpu-timers: Recalc next expiration when timer_settime() ends up not queueing There are several scenarios that can result in posix_cpu_timer_set() not queueing the timer but still leaving the threadgroup cputime counter running or keeping the tick dependency around for a random amount of time. 1) If timer_settime() is called with a 0 expiration on a timer that is already disabled, the process wide cputime counter will be started and won't ever get a chance to be stopped by stop_process_timer() since no timer is actually armed to be processed. The following snippet is enough to trigger the issue. void trigger_process_counter(void) { timer_t id; struct itimerspec val = { }; timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id); timer_settime(id, TIMER_ABSTIME, &val, NULL); timer_delete(id); } 2) If timer_settime() is called with a 0 expiration on a timer that is already armed, the timer is dequeued but not really disarmed. So the process wide cputime counter and the tick dependency may still remain a while around. The following code snippet keeps this overhead around for one week after the timer deletion: void trigger_process_counter(void) { timer_t id; struct itimerspec val = { }; val.it_value.tv_sec = 604800; timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id); timer_settime(id, 0, &val, NULL); timer_delete(id); } 3) If the timer was initially deactivated, this call to timer_settime() with an early expiration may have started the process wide cputime counter even though the timer hasn't been queued and armed because it has fired early and inline within posix_cpu_timer_set() itself. As a result the process wide cputime counter may never stop until a new timer is ever armed in the future. The following code snippet can reproduce this: void trigger_process_counter(void) { timer_t id; struct itimerspec val = { }; signal(SIGALRM, SIG_IGN); timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id); val.it_value.tv_nsec = 1; timer_settime(id, TIMER_ABSTIME, &val, NULL); } 4) If the timer was initially armed with a former expiration value before this call to timer_settime() and the current call sets an early deadline that has already expired, the timer fires inline within posix_cpu_timer_set(). In this case it must have been dequeued before firing inline with its new expiration value, yet it hasn't been disarmed in this case. So the process wide cputime counter and the tick dependency may still be around for a while even after the timer fired. The following code snippet can reproduce this: void trigger_process_counter(void) { timer_t id; struct itimerspec val = { }; signal(SIGALRM, SIG_IGN); timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id); val.it_value.tv_sec = 100; timer_settime(id, TIMER_ABSTIME, &val, NULL); val.it_value.tv_sec = 0; val.it_value.tv_nsec = 1; timer_settime(id, TIMER_ABSTIME, &val, NULL); } Fix all these issues with triggering the related base next expiration recalculation on the next tick. This also implies to re-evaluate the need to keep around the process wide cputime counter and the tick dependency, in a similar fashion to disarm_timer(). Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210726125513.271824-7-frederic@kernel.org --- include/linux/posix-timers.h | 7 ++++++- kernel/time/posix-cpu-timers.c | 41 +++++++++++++++++++++++++++++++++++------ 2 files changed, 41 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 4cf1fbe8d1bc..00fef0064355 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -82,9 +82,14 @@ static inline bool cpu_timer_enqueue(struct timerqueue_head *head, return timerqueue_add(head, &ctmr->node); } +static inline bool cpu_timer_queued(struct cpu_timer *ctmr) +{ + return !!ctmr->head; +} + static inline bool cpu_timer_dequeue(struct cpu_timer *ctmr) { - if (ctmr->head) { + if (cpu_timer_queued(ctmr)) { timerqueue_del(ctmr->head, &ctmr->node); ctmr->head = NULL; return true; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 0d918117a3e0..ee736861b18f 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -418,6 +418,20 @@ static struct posix_cputimer_base *timer_base(struct k_itimer *timer, return tsk->signal->posix_cputimers.bases + clkidx; } +/* + * Force recalculating the base earliest expiration on the next tick. + * This will also re-evaluate the need to keep around the process wide + * cputime counter and tick dependency and eventually shut these down + * if necessary. + */ +static void trigger_base_recalc_expires(struct k_itimer *timer, + struct task_struct *tsk) +{ + struct posix_cputimer_base *base = timer_base(timer, tsk); + + base->nextevt = 0; +} + /* * Dequeue the timer and reset the base if it was its earliest expiration. * It makes sure the next tick recalculates the base next expiration so we @@ -438,7 +452,7 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) base = timer_base(timer, p); if (cpu_timer_getexpires(ctmr) == base->nextevt) - base->nextevt = 0; + trigger_base_recalc_expires(timer, p); } @@ -734,13 +748,28 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, timer->it_overrun_last = 0; timer->it_overrun = -1; - if (new_expires != 0 && !(val < new_expires)) { + if (val >= new_expires) { + if (new_expires != 0) { + /* + * The designated time already passed, so we notify + * immediately, even if the thread never runs to + * accumulate more time on this clock. + */ + cpu_timer_fire(timer); + } + /* - * The designated time already passed, so we notify - * immediately, even if the thread never runs to - * accumulate more time on this clock. + * Make sure we don't keep around the process wide cputime + * counter or the tick dependency if they are not necessary. */ - cpu_timer_fire(timer); + sighand = lock_task_sighand(p, &flags); + if (!sighand) + goto out; + + if (!cpu_timer_queued(ctmr)) + trigger_base_recalc_expires(timer, p); + + unlock_task_sighand(p, &flags); } out: rcu_read_unlock(); -- cgit v1.2.3 From 0e566c8f0f2e8325e35f6f97e13cde5356b41814 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 21 Jul 2021 17:26:47 +0300 Subject: virtio: Protect vqs list access VQs may be accessed to mark the device broken while they are created/destroyed. Hence protect the access to the vqs list. Fixes: e2dcdfe95c0b ("virtio: virtio_break_device() to mark all virtqueues broken.") Signed-off-by: Parav Pandit Link: https://lore.kernel.org/r/20210721142648.1525924-4-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio.c | 1 + drivers/virtio/virtio_ring.c | 8 ++++++++ include/linux/virtio.h | 1 + 3 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 4b15c00c0a0a..49984d2cba24 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -355,6 +355,7 @@ int register_virtio_device(struct virtio_device *dev) virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); INIT_LIST_HEAD(&dev->vqs); + spin_lock_init(&dev->vqs_list_lock); /* * device_add() causes the bus infrastructure to look for a matching diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index d5934c2e5a89..c2aaa0eff6df 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1755,7 +1755,9 @@ static struct virtqueue *vring_create_virtqueue_packed( cpu_to_le16(vq->packed.event_flags_shadow); } + spin_lock(&vdev->vqs_list_lock); list_add_tail(&vq->vq.list, &vdev->vqs); + spin_unlock(&vdev->vqs_list_lock); return &vq->vq; err_desc_extra: @@ -2229,7 +2231,9 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, memset(vq->split.desc_state, 0, vring.num * sizeof(struct vring_desc_state_split)); + spin_lock(&vdev->vqs_list_lock); list_add_tail(&vq->vq.list, &vdev->vqs); + spin_unlock(&vdev->vqs_list_lock); return &vq->vq; err_extra: @@ -2291,7 +2295,9 @@ void vring_del_virtqueue(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); + spin_lock(&vq->vq.vdev->vqs_list_lock); list_del(&_vq->list); + spin_unlock(&vq->vq.vdev->vqs_list_lock); if (vq->we_own_ring) { if (vq->packed_ring) { @@ -2386,12 +2392,14 @@ void virtio_break_device(struct virtio_device *dev) { struct virtqueue *_vq; + spin_lock(&dev->vqs_list_lock); list_for_each_entry(_vq, &dev->vqs, list) { struct vring_virtqueue *vq = to_vvq(_vq); /* Pairs with READ_ONCE() in virtqueue_is_broken(). */ WRITE_ONCE(vq->broken, true); } + spin_unlock(&dev->vqs_list_lock); } EXPORT_SYMBOL_GPL(virtio_break_device); diff --git a/include/linux/virtio.h b/include/linux/virtio.h index b1894e0323fa..41edbc01ffa4 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -110,6 +110,7 @@ struct virtio_device { bool config_enabled; bool config_change_pending; spinlock_t config_lock; + spinlock_t vqs_list_lock; /* Protects VQs list access */ struct device dev; struct virtio_device_id id; const struct virtio_config_ops *config; -- cgit v1.2.3 From 8c3b5e6ec0fee18bc2ce38d1dfe913413205f908 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 13 Jul 2021 15:39:48 +0200 Subject: hrtimer: Ensure timerfd notification for HIGHRES=n If high resolution timers are disabled the timerfd notification about a clock was set event is not happening for all cases which use clock_was_set_delayed() because that's a NOP for HIGHRES=n, which is wrong. Make clock_was_set_delayed() unconditially available to fix that. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210713135158.196661266@linutronix.de --- include/linux/hrtimer.h | 5 ----- kernel/time/hrtimer.c | 32 ++++++++++++++++---------------- kernel/time/tick-internal.h | 3 +++ 3 files changed, 19 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index bb5e7b0a4274..77295af72426 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -318,16 +318,12 @@ struct clock_event_device; extern void hrtimer_interrupt(struct clock_event_device *dev); -extern void clock_was_set_delayed(void); - extern unsigned int hrtimer_resolution; #else #define hrtimer_resolution (unsigned int)LOW_RES_NSEC -static inline void clock_was_set_delayed(void) { } - #endif static inline ktime_t @@ -351,7 +347,6 @@ hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) timer->base->get_time()); } -extern void clock_was_set(void); #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); #else diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 5f7c46598d9f..7ebf642b53f9 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -777,22 +777,6 @@ static void hrtimer_switch_to_hres(void) retrigger_next_event(NULL); } -static void clock_was_set_work(struct work_struct *work) -{ - clock_was_set(); -} - -static DECLARE_WORK(hrtimer_work, clock_was_set_work); - -/* - * Called from timekeeping and resume code to reprogram the hrtimer - * interrupt device on all cpus. - */ -void clock_was_set_delayed(void) -{ - schedule_work(&hrtimer_work); -} - #else static inline int hrtimer_is_hres_enabled(void) { return 0; } @@ -877,6 +861,22 @@ void clock_was_set(void) timerfd_clock_was_set(); } +static void clock_was_set_work(struct work_struct *work) +{ + clock_was_set(); +} + +static DECLARE_WORK(hrtimer_work, clock_was_set_work); + +/* + * Called from timekeeping and resume code to reprogram the hrtimer + * interrupt device on all cpus and to notify timerfd. + */ +void clock_was_set_delayed(void) +{ + schedule_work(&hrtimer_work); +} + /* * During resume we might have to reprogram the high resolution timer * interrupt on all online CPUs. However, all other CPUs will be diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 6a742a29e545..cd610faa2523 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -165,3 +165,6 @@ DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem); void timer_clear_idle(void); + +void clock_was_set(void); +void clock_was_set_delayed(void); -- cgit v1.2.3 From 66f7b0c8aadd2785fc29f2c71477ebc16f4e38cc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 13 Jul 2021 15:39:50 +0200 Subject: timerfd: Provide timerfd_resume() Resuming timekeeping is a clock-was-set event and uses the clock-was-set notification mechanism. This is in the way of making the clock-was-set update for hrtimers selective so unnecessary IPIs are avoided when a CPU base does not have timers queued which are affected by the clock setting. Provide a seperate timerfd_resume() interface so the resume logic and the clock-was-set mechanism can be distangled in the core code. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210713135158.395287410@linutronix.de --- fs/timerfd.c | 16 ++++++++++++++++ include/linux/hrtimer.h | 2 ++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/fs/timerfd.c b/fs/timerfd.c index c5509d2448e3..e9c96a0c79f1 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -115,6 +115,22 @@ void timerfd_clock_was_set(void) rcu_read_unlock(); } +static void timerfd_resume_work(struct work_struct *work) +{ + timerfd_clock_was_set(); +} + +static DECLARE_WORK(timerfd_work, timerfd_resume_work); + +/* + * Invoked from timekeeping_resume(). Defer the actual update to work so + * timerfd_clock_was_set() runs in task context. + */ +void timerfd_resume(void) +{ + schedule_work(&timerfd_work); +} + static void __timerfd_remove_cancel(struct timerfd_ctx *ctx) { if (ctx->might_cancel) { diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 77295af72426..253c6e25f331 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -349,8 +349,10 @@ hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); +extern void timerfd_resume(void); #else static inline void timerfd_clock_was_set(void) { } +static inline void timerfd_resume(void) { } #endif extern void hrtimers_resume(void); -- cgit v1.2.3 From a761a67f591a8c7476c30bb20ed0f09fdfb1a704 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 13 Jul 2021 15:39:51 +0200 Subject: timekeeping: Distangle resume and clock-was-set events Resuming timekeeping is a clock-was-set event and uses the clock-was-set notification mechanism. This is in the way of making the clock-was-set update for hrtimers selective so unnecessary IPIs are avoided when a CPU base does not have timers queued which are affected by the clock setting. Distangle it by invoking hrtimer_resume() on each unfreezing CPU and invoke the new timerfd_resume() function from timekeeping_resume() which is the only place where this is needed. Rename hrtimer_resume() to hrtimer_resume_local() to reflect the change. With this the clock_was_set*() functions are not longer required to IPI all CPUs unconditionally and can get some smarts to avoid them. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210713135158.488853478@linutronix.de --- include/linux/hrtimer.h | 1 - kernel/time/hrtimer.c | 15 ++++++--------- kernel/time/tick-common.c | 7 +++++++ kernel/time/tick-internal.h | 2 ++ kernel/time/timekeeping.c | 4 +++- 5 files changed, 18 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 253c6e25f331..0ee140176f10 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -354,7 +354,6 @@ extern void timerfd_resume(void); static inline void timerfd_clock_was_set(void) { } static inline void timerfd_resume(void) { } #endif -extern void hrtimers_resume(void); DECLARE_PER_CPU(struct tick_device, tick_cpu_device); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 214fd65a9597..68e56f0ecb09 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -900,8 +900,8 @@ static void clock_was_set_work(struct work_struct *work) static DECLARE_WORK(hrtimer_work, clock_was_set_work); /* - * Called from timekeeping and resume code to reprogram the hrtimer - * interrupt device on all cpus and to notify timerfd. + * Called from timekeeping code to reprogram the hrtimer interrupt device + * on all cpus and to notify timerfd. */ void clock_was_set_delayed(void) { @@ -909,18 +909,15 @@ void clock_was_set_delayed(void) } /* - * During resume we might have to reprogram the high resolution timer - * interrupt on all online CPUs. However, all other CPUs will be - * stopped with IRQs interrupts disabled so the clock_was_set() call - * must be deferred. + * Called during resume either directly from via timekeeping_resume() + * or in the case of s2idle from tick_unfreeze() to ensure that the + * hrtimers are up to date. */ -void hrtimers_resume(void) +void hrtimers_resume_local(void) { lockdep_assert_irqs_disabled(); /* Retrigger on the local CPU */ retrigger_next_event(NULL); - /* And schedule a retrigger for all others */ - clock_was_set_delayed(); } /* diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index d663249652ef..46789356f856 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -470,6 +470,13 @@ void tick_resume_local(void) else tick_resume_oneshot(); } + + /* + * Ensure that hrtimers are up to date and the clockevents device + * is reprogrammed correctly when high resolution timers are + * enabled. + */ + hrtimers_resume_local(); } /** diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index cd610faa2523..22de98cc6dd8 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -168,3 +168,5 @@ void timer_clear_idle(void); void clock_was_set(void); void clock_was_set_delayed(void); + +void hrtimers_resume_local(void); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 8a364aa9881a..c8a9b9e54c9d 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1810,8 +1810,10 @@ void timekeeping_resume(void) touch_softlockup_watchdog(); + /* Resume the clockevent device(s) and hrtimers */ tick_resume(); - hrtimers_resume(); + /* Notify timerfd as resume is equivalent to clock_was_set() */ + timerfd_resume(); } int timekeeping_suspend(void) -- cgit v1.2.3 From c91eb2837310a4e8490fb712598aa7d7148e6d7f Mon Sep 17 00:00:00 2001 From: John Garry Date: Fri, 21 May 2021 16:28:09 +0800 Subject: cpu/hotplug: Fix comment typo /s/reatdown/teardown/ Signed-off-by: John Garry Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/1621585689-177398-1-git-send-email-john.garry@huawei.com --- include/linux/cpuhotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f39b34b13871..6ac543d33b66 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -399,7 +399,7 @@ static inline int cpuhp_state_remove_instance(enum cpuhp_state state, /** * cpuhp_state_remove_instance_nocalls - Remove hotplug instance from state - * without invoking the reatdown callback + * without invoking the teardown callback * @state: The state from which the instance is removed * @node: The node for this individual state. * -- cgit v1.2.3 From 91ccbbac1747eea155632a1c6bb100052309b215 Mon Sep 17 00:00:00 2001 From: Tushar Sugandhi Date: Mon, 12 Jul 2021 17:48:58 -0700 Subject: dm ima: measure data on table load MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DM configures a block device with various target specific attributes passed to it as a table. DM loads the table, and calls each target’s respective constructors with the attributes as input parameters. Some of these attributes are critical to ensure the device meets certain security bar. Thus, IMA should measure these attributes, to ensure they are not tampered with, during the lifetime of the device. So that the external services can have high confidence in the configuration of the block-devices on a given system. Some devices may have large tables. And a given device may change its state (table-load, suspend, resume, rename, remove, table-clear etc.) many times. Measuring these attributes each time when the device changes its state will significantly increase the size of the IMA logs. Further, once configured, these attributes are not expected to change unless a new table is loaded, or a device is removed and recreated. Therefore the clear-text of the attributes should only be measured during table load, and the hash of the active/inactive table should be measured for the remaining device state changes. Export IMA function ima_measure_critical_data() to allow measurement of DM device parameters, as well as target specific attributes, during table load. Compute the hash of the inactive table and store it for measurements during future state change. If a load is called multiple times, update the inactive table hash with the hash of the latest populated table. So that the correct inactive table hash is measured when the device transitions to different states like resume, remove, rename, etc. Signed-off-by: Tushar Sugandhi Signed-off-by: Colin Ian King # leak fix Signed-off-by: Mike Snitzer --- drivers/md/Makefile | 4 + drivers/md/dm-core.h | 5 + drivers/md/dm-ima.c | 330 ++++++++++++++++++++++++++++++++++++++ drivers/md/dm-ima.h | 59 +++++++ drivers/md/dm-ioctl.c | 7 +- drivers/md/dm.c | 3 + include/linux/device-mapper.h | 2 +- include/uapi/linux/dm-ioctl.h | 6 + security/integrity/ima/ima_main.c | 1 + 9 files changed, 415 insertions(+), 2 deletions(-) create mode 100644 drivers/md/dm-ima.c create mode 100644 drivers/md/dm-ima.h (limited to 'include/linux') diff --git a/drivers/md/Makefile b/drivers/md/Makefile index a74aaf8b1445..816945eeed7f 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -96,6 +96,10 @@ ifeq ($(CONFIG_BLK_DEV_ZONED),y) dm-mod-objs += dm-zone.o endif +ifeq ($(CONFIG_IMA),y) +dm-mod-objs += dm-ima.o +endif + ifeq ($(CONFIG_DM_VERITY_FEC),y) dm-verity-objs += dm-verity-fec.o endif diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index edc1553c4eea..55dccdfbcb22 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -18,6 +18,7 @@ #include #include "dm.h" +#include "dm-ima.h" #define DM_RESERVED_MAX_IOS 1024 @@ -119,6 +120,10 @@ struct mapped_device { unsigned int nr_zones; unsigned int *zwp_offset; #endif + +#ifdef CONFIG_IMA + struct dm_ima_measurements ima; +#endif }; /* diff --git a/drivers/md/dm-ima.c b/drivers/md/dm-ima.c new file mode 100644 index 000000000000..c8f54d9f6c8d --- /dev/null +++ b/drivers/md/dm-ima.c @@ -0,0 +1,330 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Microsoft Corporation + * + * Author: Tushar Sugandhi + * + * File: dm-ima.c + * Enables IMA measurements for DM targets + */ + +#include "dm-core.h" +#include "dm-ima.h" + +#include +#include +#include +#include + +#define DM_MSG_PREFIX "ima" + +/* + * Internal function to prefix separator characters in input buffer with escape + * character, so that they don't interfere with the construction of key-value pairs, + * and clients can split the key1=val1,key2=val2,key3=val3; pairs properly. + */ +static void fix_separator_chars(char **buf) +{ + int l = strlen(*buf); + int i, j, sp = 0; + + for (i = 0; i < l; i++) + if ((*buf)[i] == '\\' || (*buf)[i] == ';' || (*buf)[i] == '=' || (*buf)[i] == ',') + sp++; + + if (!sp) + return; + + for (i = l-1, j = i+sp; i >= 0; i--) { + (*buf)[j--] = (*buf)[i]; + if ((*buf)[i] == '\\' || (*buf)[i] == ';' || (*buf)[i] == '=' || (*buf)[i] == ',') + (*buf)[j--] = '\\'; + } +} + +/* + * Internal function to allocate memory for IMA measurements. + */ +static void *dm_ima_alloc(size_t len, gfp_t flags, bool noio) +{ + unsigned int noio_flag; + void *ptr; + + if (noio) + noio_flag = memalloc_noio_save(); + + ptr = kzalloc(len, flags); + + if (noio) + memalloc_noio_restore(noio_flag); + + return ptr; +} + +/* + * Internal function to allocate and copy name and uuid for IMA measurements. + */ +static int dm_ima_alloc_and_copy_name_uuid(struct mapped_device *md, char **dev_name, + char **dev_uuid, bool noio) +{ + int r; + *dev_name = dm_ima_alloc(DM_NAME_LEN*2, GFP_KERNEL, noio); + if (!(*dev_name)) { + r = -ENOMEM; + goto error; + } + + *dev_uuid = dm_ima_alloc(DM_UUID_LEN*2, GFP_KERNEL, noio); + if (!(*dev_uuid)) { + r = -ENOMEM; + goto error; + } + + r = dm_copy_name_and_uuid(md, *dev_name, *dev_uuid); + if (r) + goto error; + + fix_separator_chars(dev_name); + fix_separator_chars(dev_uuid); + + return 0; +error: + kfree(*dev_name); + kfree(*dev_uuid); + *dev_name = NULL; + *dev_uuid = NULL; + return r; +} + +/* + * Internal function to allocate and copy device data for IMA measurements. + */ +static int dm_ima_alloc_and_copy_device_data(struct mapped_device *md, char **device_data, + unsigned int num_targets, bool noio) +{ + char *dev_name = NULL, *dev_uuid = NULL; + int r; + + r = dm_ima_alloc_and_copy_name_uuid(md, &dev_name, &dev_uuid, noio); + if (r) + return r; + + *device_data = dm_ima_alloc(DM_IMA_DEVICE_BUF_LEN, GFP_KERNEL, noio); + if (!(*device_data)) { + r = -ENOMEM; + goto error; + } + + scnprintf(*device_data, DM_IMA_DEVICE_BUF_LEN, + "name=%s,uuid=%s,major=%d,minor=%d,minor_count=%d,num_targets=%u;", + dev_name, dev_uuid, md->disk->major, md->disk->first_minor, + md->disk->minors, num_targets); +error: + kfree(dev_name); + kfree(dev_uuid); + return r; +} + +/* + * Internal wrapper function to call IMA to measure DM data. + */ +static void dm_ima_measure_data(const char *event_name, const void *buf, size_t buf_len, + bool noio) +{ + unsigned int noio_flag; + + if (noio) + noio_flag = memalloc_noio_save(); + + ima_measure_critical_data(DM_NAME, event_name, buf, buf_len, false); + + if (noio) + memalloc_noio_restore(noio_flag); +} + +/* + * Initialize/reset the dm ima related data structure variables. + */ +void dm_ima_reset_data(struct mapped_device *md) +{ + memset(&(md->ima), 0, sizeof(md->ima)); +} + +/* + * Build up the IMA data for each target, and finally measure. + */ +void dm_ima_measure_on_table_load(struct dm_table *table, unsigned int status_flags) +{ + size_t device_data_buf_len, target_metadata_buf_len, target_data_buf_len, l = 0; + char *target_metadata_buf = NULL, *target_data_buf = NULL, *digest_buf = NULL; + char *ima_buf = NULL, *device_data_buf = NULL; + int digest_size, last_target_measured = -1, r; + status_type_t type = STATUSTYPE_IMA; + size_t cur_total_buf_len = 0; + unsigned int num_targets, i; + SHASH_DESC_ON_STACK(shash, NULL); + struct crypto_shash *tfm = NULL; + u8 *digest = NULL; + bool noio = false; + + ima_buf = dm_ima_alloc(DM_IMA_MEASUREMENT_BUF_LEN, GFP_KERNEL, noio); + if (!ima_buf) + return; + + target_metadata_buf = dm_ima_alloc(DM_IMA_TARGET_METADATA_BUF_LEN, GFP_KERNEL, noio); + if (!target_metadata_buf) + goto error; + + target_data_buf = dm_ima_alloc(DM_IMA_TARGET_DATA_BUF_LEN, GFP_KERNEL, noio); + if (!target_data_buf) + goto error; + + num_targets = dm_table_get_num_targets(table); + + if (dm_ima_alloc_and_copy_device_data(table->md, &device_data_buf, num_targets, noio)) + goto error; + + tfm = crypto_alloc_shash("sha256", 0, 0); + if (IS_ERR(tfm)) + goto error; + + shash->tfm = tfm; + digest_size = crypto_shash_digestsize(tfm); + digest = dm_ima_alloc(digest_size, GFP_KERNEL, noio); + if (!digest) + goto error; + + r = crypto_shash_init(shash); + if (r) + goto error; + + device_data_buf_len = strlen(device_data_buf); + memcpy(ima_buf + l, device_data_buf, device_data_buf_len); + l += device_data_buf_len; + + for (i = 0; i < num_targets; i++) { + struct dm_target *ti = dm_table_get_target(table, i); + + if (!ti) + goto error; + + last_target_measured = 0; + + /* + * First retrieve the target metadata. + */ + scnprintf(target_metadata_buf, DM_IMA_TARGET_METADATA_BUF_LEN, + "target_index=%d,target_begin=%llu,target_len=%llu,", + i, ti->begin, ti->len); + target_metadata_buf_len = strlen(target_metadata_buf); + + /* + * Then retrieve the actual target data. + */ + if (ti->type->status) + ti->type->status(ti, type, status_flags, target_data_buf, + DM_IMA_TARGET_DATA_BUF_LEN); + else + target_data_buf[0] = '\0'; + + target_data_buf_len = strlen(target_data_buf); + + /* + * Check if the total data can fit into the IMA buffer. + */ + cur_total_buf_len = l + target_metadata_buf_len + target_data_buf_len; + + /* + * IMA measurements for DM targets are best-effort. + * If the total data buffered so far, including the current target, + * is too large to fit into DM_IMA_MEASUREMENT_BUF_LEN, measure what + * we have in the current buffer, and continue measuring the remaining + * targets by prefixing the device metadata again. + */ + if (unlikely(cur_total_buf_len >= DM_IMA_MEASUREMENT_BUF_LEN)) { + dm_ima_measure_data("table_load", ima_buf, l, noio); + r = crypto_shash_update(shash, (const u8 *)ima_buf, l); + if (r < 0) + goto error; + + memset(ima_buf, 0, DM_IMA_MEASUREMENT_BUF_LEN); + l = 0; + + /* + * Each new "table_load" entry in IMA log should have device data + * prefix, so that multiple records from the same table_load for + * a given device can be linked together. + */ + memcpy(ima_buf + l, device_data_buf, device_data_buf_len); + l += device_data_buf_len; + + /* + * If this iteration of the for loop turns out to be the last target + * in the table, dm_ima_measure_data("table_load", ...) doesn't need + * to be called again, just the hash needs to be finalized. + * "last_target_measured" tracks this state. + */ + last_target_measured = 1; + } + + /* + * Fill-in all the target metadata, so that multiple targets for the same + * device can be linked together. + */ + memcpy(ima_buf + l, target_metadata_buf, target_metadata_buf_len); + l += target_metadata_buf_len; + + memcpy(ima_buf + l, target_data_buf, target_data_buf_len); + l += target_data_buf_len; + } + + if (!last_target_measured) { + dm_ima_measure_data("table_load", ima_buf, l, noio); + + r = crypto_shash_update(shash, (const u8 *)ima_buf, l); + if (r < 0) + goto error; + } + + /* + * Finalize the table hash, and store it in table->md->ima.inactive_table.hash, + * so that the table data can be verified against the future device state change + * events, e.g. resume, rename, remove, table-clear etc. + */ + r = crypto_shash_final(shash, digest); + if (r < 0) + goto error; + + digest_buf = dm_ima_alloc((digest_size*2)+1, GFP_KERNEL, noio); + if (!digest_buf) + goto error; + + for (i = 0; i < digest_size; i++) + snprintf((digest_buf+(i*2)), 3, "%02x", digest[i]); + + if (table->md->ima.active_table.hash != table->md->ima.inactive_table.hash) + kfree(table->md->ima.inactive_table.hash); + + table->md->ima.inactive_table.hash = digest_buf; + table->md->ima.inactive_table.hash_len = strlen(digest_buf); + table->md->ima.inactive_table.num_targets = num_targets; + + if (table->md->ima.active_table.device_metadata != + table->md->ima.inactive_table.device_metadata) + kfree(table->md->ima.inactive_table.device_metadata); + + table->md->ima.inactive_table.device_metadata = device_data_buf; + table->md->ima.inactive_table.device_metadata_len = device_data_buf_len; + + goto exit; +error: + kfree(digest_buf); + kfree(device_data_buf); +exit: + kfree(digest); + if (tfm) + crypto_free_shash(tfm); + kfree(ima_buf); + kfree(target_metadata_buf); + kfree(target_data_buf); +} diff --git a/drivers/md/dm-ima.h b/drivers/md/dm-ima.h new file mode 100644 index 000000000000..16afd9a8c0b2 --- /dev/null +++ b/drivers/md/dm-ima.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (C) 2021 Microsoft Corporation + * + * Author: Tushar Sugandhi + * + * File: dm-ima.h + * Header file for device mapper IMA measurements. + */ + +#ifndef DM_IMA_H +#define DM_IMA_H + +#define DM_IMA_MEASUREMENT_BUF_LEN 4096 +#define DM_IMA_DEVICE_BUF_LEN 1024 +#define DM_IMA_TARGET_METADATA_BUF_LEN 128 +#define DM_IMA_TARGET_DATA_BUF_LEN 2048 + +#ifdef CONFIG_IMA + +struct dm_ima_device_table_metadata { + /* + * Contains data specific to the device which is common across + * all the targets in the table (e.g. name, uuid, major, minor, etc). + * The values are stored in comma separated list of key1=val1,key2=val2; + * pairs delimited by a semicolon at the end of the list. + */ + char *device_metadata; + unsigned int device_metadata_len; + unsigned int num_targets; + + /* + * Contains the sha256 hashes of the IMA measurements of the target + * attributes' key-value pairs from the active/inactive tables. + */ + char *hash; + unsigned int hash_len; +}; + +/* + * This structure contains device metadata, and table hash for + * active and inactive tables for ima measurements. + */ +struct dm_ima_measurements { + struct dm_ima_device_table_metadata active_table; + struct dm_ima_device_table_metadata inactive_table; +}; + +void dm_ima_reset_data(struct mapped_device *md); +void dm_ima_measure_on_table_load(struct dm_table *table, unsigned int status_flags); + +#else + +static inline void dm_ima_reset_data(struct mapped_device *md) {} +static inline void dm_ima_measure_on_table_load(struct dm_table *table, unsigned int status_flags) {} + +#endif /* CONFIG_IMA */ + +#endif /* DM_IMA_H */ diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 2575074a2204..d7c3456bf858 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -6,7 +6,7 @@ */ #include "dm-core.h" - +#include "dm-ima.h" #include #include #include @@ -20,6 +20,7 @@ #include #include +#include #define DM_MSG_PREFIX "ioctl" #define DM_DRIVER_EMAIL "dm-devel@redhat.com" @@ -1224,6 +1225,8 @@ static void retrieve_status(struct dm_table *table, if (param->flags & DM_STATUS_TABLE_FLAG) type = STATUSTYPE_TABLE; + else if (param->flags & DM_IMA_MEASUREMENT_FLAG) + type = STATUSTYPE_IMA; else type = STATUSTYPE_INFO; @@ -1425,6 +1428,8 @@ static int table_load(struct file *filp, struct dm_ioctl *param, size_t param_si if (r) goto err_unlock_md_type; + dm_ima_measure_on_table_load(t, STATUSTYPE_IMA); + immutable_target_type = dm_get_immutable_target_type(md); if (immutable_target_type && (immutable_target_type != dm_table_get_immutable_target_type(t)) && diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7981b7287628..33e55ac9ec65 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -8,6 +8,7 @@ #include "dm-core.h" #include "dm-rq.h" #include "dm-uevent.h" +#include "dm-ima.h" #include #include @@ -1997,6 +1998,8 @@ int dm_create(int minor, struct mapped_device **result) if (!md) return -ENXIO; + dm_ima_reset_data(md); + *result = md; return 0; } diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 7457d49acf9a..74486c332946 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -31,7 +31,7 @@ enum dm_queue_mode { DM_TYPE_DAX_BIO_BASED = 3, }; -typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t; +typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE, STATUSTYPE_IMA } status_type_t; union map_info { void *ptr; diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index e5c6e458bdf7..c12ce30b52df 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -376,4 +376,10 @@ enum { */ #define DM_INTERNAL_SUSPEND_FLAG (1 << 18) /* Out */ +/* + * If set, returns in the in buffer passed by UM, the raw table information + * that would be measured by IMA subsystem on device state change. + */ +#define DM_IMA_MEASUREMENT_FLAG (1 << 19) /* In */ + #endif /* _LINUX_DM_IOCTL_H */ diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 287b90509006..673833f94069 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -985,6 +985,7 @@ void ima_measure_critical_data(const char *event_label, CRITICAL_DATA, 0, event_label, hash); } +EXPORT_SYMBOL_GPL(ima_measure_critical_data); static int __init init_ima(void) { -- cgit v1.2.3 From 8ec456629d0bf051e41ef2c87a60755f941dd11c Mon Sep 17 00:00:00 2001 From: Tushar Sugandhi Date: Mon, 12 Jul 2021 17:49:03 -0700 Subject: dm: update target status functions to support IMA measurement For device mapper targets to take advantage of IMA's measurement capabilities, the status functions for the individual targets need to be updated to handle the status_type_t case for value STATUSTYPE_IMA. Update status functions for the following target types, to log their respective attributes to be measured using IMA. 01. cache 02. crypt 03. integrity 04. linear 05. mirror 06. multipath 07. raid 08. snapshot 09. striped 10. verity For rest of the targets, handle the STATUSTYPE_IMA case by setting the measurement buffer to NULL. For IMA to measure the data on a given system, the IMA policy on the system needs to be updated to have the following line, and the system needs to be restarted for the measurements to take effect. /etc/ima/ima-policy measure func=CRITICAL_DATA label=device-mapper template=ima-buf The measurements will be reflected in the IMA logs, which are located at: /sys/kernel/security/integrity/ima/ascii_runtime_measurements /sys/kernel/security/integrity/ima/binary_runtime_measurements These IMA logs can later be consumed by various attestation clients running on the system, and send them to external services for attesting the system. The DM target data measured by IMA subsystem can alternatively be queried from userspace by setting DM_IMA_MEASUREMENT_FLAG with DM_TABLE_STATUS_CMD. Signed-off-by: Tushar Sugandhi Signed-off-by: Mike Snitzer --- drivers/md/dm-cache-target.c | 24 +++++++++++++++++ drivers/md/dm-clone-target.c | 5 ++++ drivers/md/dm-crypt.c | 27 ++++++++++++++++++++ drivers/md/dm-delay.c | 4 +++ drivers/md/dm-dust.c | 4 +++ drivers/md/dm-ebs-target.c | 3 +++ drivers/md/dm-era-target.c | 4 +++ drivers/md/dm-flakey.c | 4 +++ drivers/md/dm-integrity.c | 25 ++++++++++++++++++ drivers/md/dm-linear.c | 10 ++++++-- drivers/md/dm-log-userspace-base.c | 3 +++ drivers/md/dm-log-writes.c | 4 +++ drivers/md/dm-log.c | 10 ++++++++ drivers/md/dm-mpath.c | 28 ++++++++++++++++++++ drivers/md/dm-ps-historical-service-time.c | 3 +++ drivers/md/dm-ps-io-affinity.c | 3 +++ drivers/md/dm-ps-queue-length.c | 3 +++ drivers/md/dm-ps-round-robin.c | 4 +++ drivers/md/dm-ps-service-time.c | 3 +++ drivers/md/dm-raid.c | 39 ++++++++++++++++++++++++++++ drivers/md/dm-raid1.c | 17 +++++++++++++ drivers/md/dm-snap-persistent.c | 4 +++ drivers/md/dm-snap-transient.c | 4 +++ drivers/md/dm-snap.c | 13 ++++++++++ drivers/md/dm-stripe.c | 15 +++++++++++ drivers/md/dm-switch.c | 4 +++ drivers/md/dm-thin.c | 8 ++++++ drivers/md/dm-unstripe.c | 4 +++ drivers/md/dm-verity-target.c | 41 ++++++++++++++++++++++++++++++ drivers/md/dm-writecache.c | 3 +++ drivers/md/dm-zoned-target.c | 3 +++ include/linux/device-mapper.h | 4 +++ 32 files changed, 328 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 8e4ced5a2516..bdd500447dea 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3122,6 +3122,30 @@ static void cache_status(struct dm_target *ti, status_type_t type, DMEMIT(" %s", cache->ctr_args[i]); if (cache->nr_ctr_args) DMEMIT(" %s", cache->ctr_args[cache->nr_ctr_args - 1]); + break; + + case STATUSTYPE_IMA: + DMEMIT_TARGET_NAME_VERSION(ti->type); + if (get_cache_mode(cache) == CM_FAIL) + DMEMIT(",metadata_mode=fail"); + else if (get_cache_mode(cache) == CM_READ_ONLY) + DMEMIT(",metadata_mode=ro"); + else + DMEMIT(",metadata_mode=rw"); + + format_dev_t(buf, cache->metadata_dev->bdev->bd_dev); + DMEMIT(",cache_metadata_device=%s", buf); + format_dev_t(buf, cache->cache_dev->bdev->bd_dev); + DMEMIT(",cache_device=%s", buf); + format_dev_t(buf, cache->origin_dev->bdev->bd_dev); + DMEMIT(",cache_origin_device=%s", buf); + DMEMIT(",writethrough=%c", writethrough_mode(cache) ? 'y' : 'n'); + DMEMIT(",writeback=%c", writeback_mode(cache) ? 'y' : 'n'); + DMEMIT(",passthrough=%c", passthrough_mode(cache) ? 'y' : 'n'); + DMEMIT(",metadata2=%c", cache->features.metadata_version == 2 ? 'y' : 'n'); + DMEMIT(",no_discard_passdown=%c", cache->features.discard_passdown ? 'n' : 'y'); + DMEMIT(";"); + break; } return; diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index a90bdf9b2ca6..84dbe08ad205 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -1499,6 +1499,11 @@ static void clone_status(struct dm_target *ti, status_type_t type, for (i = 0; i < clone->nr_ctr_args; i++) DMEMIT(" %s", clone->ctr_args[i]); + break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } return; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 50f4cbd600d5..80fdc42ce3c8 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -3485,7 +3485,34 @@ static void crypt_status(struct dm_target *ti, status_type_t type, if (test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags)) DMEMIT(" iv_large_sectors"); } + break; + + case STATUSTYPE_IMA: + DMEMIT_TARGET_NAME_VERSION(ti->type); + DMEMIT(",allow_discards=%c", ti->num_discard_bios ? 'y' : 'n'); + DMEMIT(",same_cpu_crypt=%c", test_bit(DM_CRYPT_SAME_CPU, &cc->flags) ? 'y' : 'n'); + DMEMIT(",submit_from_crypt_cpus=%c", test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags) ? + 'y' : 'n'); + DMEMIT(",no_read_workqueue=%c", test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags) ? + 'y' : 'n'); + DMEMIT(",no_write_workqueue=%c", test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags) ? + 'y' : 'n'); + DMEMIT(",iv_large_sectors=%c", test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags) ? + 'y' : 'n'); + if (cc->on_disk_tag_size) + DMEMIT(",integrity_tag_size=%u,cipher_auth=%s", + cc->on_disk_tag_size, cc->cipher_auth); + if (cc->sector_size != (1 << SECTOR_SHIFT)) + DMEMIT(",sector_size=%d", cc->sector_size); + if (cc->cipher_string) + DMEMIT(",cipher_string=%s", cc->cipher_string); + + DMEMIT(",key_size=%u", cc->key_size); + DMEMIT(",key_parts=%u", cc->key_parts); + DMEMIT(",key_extra_size=%u", cc->key_extra_size); + DMEMIT(",key_mac_size=%u", cc->key_mac_size); + DMEMIT(";"); break; } } diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 2628a832787b..59e51d285b0e 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -326,6 +326,10 @@ static void delay_status(struct dm_target *ti, status_type_t type, DMEMIT_DELAY_CLASS(&dc->flush); } break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } } diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c index cbe1058ee589..3163e2b1418e 100644 --- a/drivers/md/dm-dust.c +++ b/drivers/md/dm-dust.c @@ -527,6 +527,10 @@ static void dust_status(struct dm_target *ti, status_type_t type, DMEMIT("%s %llu %u", dd->dev->name, (unsigned long long)dd->start, dd->blksz); break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } } diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 71475a2410be..ec8426611cc6 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -401,6 +401,9 @@ static void ebs_status(struct dm_target *ti, status_type_t type, snprintf(result, maxlen, ec->u_bs_set ? "%s %llu %u %u" : "%s %llu %u", ec->dev->name, (unsigned long long) ec->start, ec->e_bs, ec->u_bs); break; + case STATUSTYPE_IMA: + *result = '\0'; + break; } } diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 3b748393fca5..2a78f6874143 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -1644,6 +1644,10 @@ static void era_status(struct dm_target *ti, status_type_t type, format_dev_t(buf, era->origin_dev->bdev->bd_dev); DMEMIT("%s %u", buf, era->sectors_per_block); break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } return; diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 5877220c01ed..4b94ffe6f2d4 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -440,6 +440,10 @@ static void flakey_status(struct dm_target *ti, status_type_t type, fc->corrupt_bio_value, fc->corrupt_bio_flags); break; + + case STATUSTYPE_IMA: + result[0] = '\0'; + break; } } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 20f2510db1f6..40f8116c8e44 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -3306,6 +3306,31 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, EMIT_ALG(journal_mac_alg, "journal_mac"); break; } + case STATUSTYPE_IMA: + DMEMIT_TARGET_NAME_VERSION(ti->type); + DMEMIT(",dev_name=%s,start=%llu,tag_size=%u,mode=%c", + ic->dev->name, ic->start, ic->tag_size, ic->mode); + + if (ic->meta_dev) + DMEMIT(",meta_device=%s", ic->meta_dev->name); + if (ic->sectors_per_block != 1) + DMEMIT(",block_size=%u", ic->sectors_per_block << SECTOR_SHIFT); + + DMEMIT(",recalculate=%c", (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) ? + 'y' : 'n'); + DMEMIT(",allow_discards=%c", ic->discard ? 'y' : 'n'); + DMEMIT(",fix_padding=%c", + ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0) ? 'y' : 'n'); + DMEMIT(",fix_hmac=%c", + ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) != 0) ? 'y' : 'n'); + DMEMIT(",legacy_recalculate=%c", ic->legacy_recalculate ? 'y' : 'n'); + + DMEMIT(",journal_sectors=%u", ic->initial_sectors - SB_SECTORS); + DMEMIT(",interleave_sectors=%u", 1U << ic->sb->log2_interleave_sectors); + DMEMIT(",buffer_sectors=%u", 1U << ic->log2_buffer_sectors); + DMEMIT(",mode=%c", ic->mode); + DMEMIT(";"); + break; } } diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index c91f1e2e2f65..679b4c0a2eea 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -106,6 +106,7 @@ static void linear_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { struct linear_c *lc = (struct linear_c *) ti->private; + size_t sz = 0; switch (type) { case STATUSTYPE_INFO: @@ -113,8 +114,13 @@ static void linear_status(struct dm_target *ti, status_type_t type, break; case STATUSTYPE_TABLE: - snprintf(result, maxlen, "%s %llu", lc->dev->name, - (unsigned long long)lc->start); + DMEMIT("%s %llu", lc->dev->name, (unsigned long long)lc->start); + break; + + case STATUSTYPE_IMA: + DMEMIT_TARGET_NAME_VERSION(ti->type); + DMEMIT(",device_name=%s,start=%llu;", lc->dev->name, + (unsigned long long)lc->start); break; } } diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 52090bee17c2..9ab93ebea889 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -820,6 +820,9 @@ static int userspace_status(struct dm_dirty_log *log, status_type_t status_type, DMEMIT("integrated_flush "); DMEMIT("%s ", table_args); break; + case STATUSTYPE_IMA: + *result = '\0'; + break; } return (r) ? 0 : (int)sz; } diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 57882654ffee..d93a4db23512 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -834,6 +834,10 @@ static void log_writes_status(struct dm_target *ti, status_type_t type, case STATUSTYPE_TABLE: DMEMIT("%s %s", lc->dev->name, lc->logdev->name); break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } } diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index 33e71ea6cc14..1ecf75ef276a 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -793,6 +793,11 @@ static int core_status(struct dm_dirty_log *log, status_type_t status, DMEMIT("%s %u %u ", log->type->name, lc->sync == DEFAULTSYNC ? 1 : 2, lc->region_size); DMEMIT_SYNC; + break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } return sz; @@ -817,6 +822,11 @@ static int disk_status(struct dm_dirty_log *log, status_type_t status, lc->sync == DEFAULTSYNC ? 2 : 3, lc->log_dev->name, lc->region_size); DMEMIT_SYNC; + break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } return sz; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index bced42f082b0..c3c514a9edbb 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1904,6 +1904,34 @@ static void multipath_status(struct dm_target *ti, status_type_t type, } } break; + + case STATUSTYPE_IMA: + DMEMIT_TARGET_NAME_VERSION(ti->type); + list_for_each_entry(pg, &m->priority_groups, list) { + if (pg->bypassed) + state = 'D'; /* Disabled */ + else if (pg == m->current_pg) + state = 'A'; /* Currently Active */ + else + state = 'E'; /* Enabled */ + DMEMIT(",pg_state=%c", state); + DMEMIT(",nr_pgpaths=%u", pg->nr_pgpaths); + DMEMIT(",path_selector_name=%s", pg->ps.type->name); + + list_for_each_entry(p, &pg->pgpaths, list) { + DMEMIT(",path_name=%s,is_active=%c,fail_count=%u", + p->path.dev->name, p->is_active ? 'A' : 'F', + p->fail_count); + if (pg->ps.type->status) { + DMEMIT(",path_selector_status="); + sz += pg->ps.type->status(&pg->ps, &p->path, + type, result + sz, + maxlen - sz); + } + } + } + DMEMIT(";"); + break; } spin_unlock_irqrestore(&m->lock, flags); diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c index 186f91e2752c..1856a1b125cc 100644 --- a/drivers/md/dm-ps-historical-service-time.c +++ b/drivers/md/dm-ps-historical-service-time.c @@ -255,6 +255,9 @@ static int hst_status(struct path_selector *ps, struct dm_path *path, case STATUSTYPE_TABLE: DMEMIT("0 "); break; + case STATUSTYPE_IMA: + *result = '\0'; + break; } } diff --git a/drivers/md/dm-ps-io-affinity.c b/drivers/md/dm-ps-io-affinity.c index cb8e83bfb1a7..f74501e65a8e 100644 --- a/drivers/md/dm-ps-io-affinity.c +++ b/drivers/md/dm-ps-io-affinity.c @@ -170,6 +170,9 @@ static int ioa_status(struct path_selector *ps, struct dm_path *path, pi = path->pscontext; DMEMIT("%*pb ", cpumask_pr_args(pi->cpumask)); break; + case STATUSTYPE_IMA: + *result = '\0'; + break; } return sz; diff --git a/drivers/md/dm-ps-queue-length.c b/drivers/md/dm-ps-queue-length.c index 5fd018d18418..cef70657bbbc 100644 --- a/drivers/md/dm-ps-queue-length.c +++ b/drivers/md/dm-ps-queue-length.c @@ -102,6 +102,9 @@ static int ql_status(struct path_selector *ps, struct dm_path *path, case STATUSTYPE_TABLE: DMEMIT("%u ", pi->repeat_count); break; + case STATUSTYPE_IMA: + *result = '\0'; + break; } } diff --git a/drivers/md/dm-ps-round-robin.c b/drivers/md/dm-ps-round-robin.c index bdbb7e6e8212..27f44c5fa04e 100644 --- a/drivers/md/dm-ps-round-robin.c +++ b/drivers/md/dm-ps-round-robin.c @@ -100,6 +100,10 @@ static int rr_status(struct path_selector *ps, struct dm_path *path, pi = path->pscontext; DMEMIT("%u ", pi->repeat_count); break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } } diff --git a/drivers/md/dm-ps-service-time.c b/drivers/md/dm-ps-service-time.c index 9cfda665e9eb..3ec9c33265c5 100644 --- a/drivers/md/dm-ps-service-time.c +++ b/drivers/md/dm-ps-service-time.c @@ -99,6 +99,9 @@ static int st_status(struct path_selector *ps, struct dm_path *path, DMEMIT("%u %u ", pi->repeat_count, pi->relative_throughput); break; + case STATUSTYPE_IMA: + result[0] = '\0'; + break; } } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index bf4a467fc73a..d9ef52159a22 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3671,6 +3671,45 @@ static void raid_status(struct dm_target *ti, status_type_t type, for (i = 0; i < rs->raid_disks; i++) DMEMIT(" %s %s", __get_dev_name(rs->dev[i].meta_dev), __get_dev_name(rs->dev[i].data_dev)); + break; + + case STATUSTYPE_IMA: + rt = get_raid_type_by_ll(mddev->new_level, mddev->new_layout); + if (!rt) + return; + + DMEMIT_TARGET_NAME_VERSION(ti->type); + DMEMIT(",raid_type=%s,raid_disks=%d", rt->name, mddev->raid_disks); + + /* Access most recent mddev properties for status output */ + smp_rmb(); + recovery = rs->md.recovery; + state = decipher_sync_action(mddev, recovery); + DMEMIT(",raid_state=%s", sync_str(state)); + + for (i = 0; i < rs->raid_disks; i++) { + DMEMIT(",raid_device_%d_status=", i); + DMEMIT(__raid_dev_status(rs, &rs->dev[i].rdev)); + } + + if (rt_is_raid456(rt)) { + DMEMIT(",journal_dev_mode="); + switch (rs->journal_dev.mode) { + case R5C_JOURNAL_MODE_WRITE_THROUGH: + DMEMIT("%s", + _raid456_journal_mode[R5C_JOURNAL_MODE_WRITE_THROUGH].param); + break; + case R5C_JOURNAL_MODE_WRITE_BACK: + DMEMIT("%s", + _raid456_journal_mode[R5C_JOURNAL_MODE_WRITE_BACK].param); + break; + default: + DMEMIT("invalid"); + break; + } + } + DMEMIT(";"); + break; } } diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index ebb4810cc3b4..8811d484fdd1 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1435,6 +1435,23 @@ static void mirror_status(struct dm_target *ti, status_type_t type, } break; + + case STATUSTYPE_IMA: + DMEMIT_TARGET_NAME_VERSION(ti->type); + DMEMIT(",nr_mirrors=%d", ms->nr_mirrors); + for (m = 0; m < ms->nr_mirrors; m++) { + DMEMIT(",mirror_device_%d=%s", m, ms->mirror[m].dev->name); + DMEMIT(",mirror_device_%d_status=%c", + m, device_status_char(&(ms->mirror[m]))); + } + + DMEMIT(",handle_errors=%c", errors_handled(ms) ? 'y' : 'n'); + DMEMIT(",keep_log=%c", keep_log(ms) ? 'y' : 'n'); + + DMEMIT(",log_type_status="); + sz += log->type->status(log, type, result+sz, maxlen-sz); + DMEMIT(";"); + break; } } diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 9ab4bf651ca9..3bb5cff5d6fc 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -908,6 +908,10 @@ static unsigned persistent_status(struct dm_exception_store *store, case STATUSTYPE_TABLE: DMEMIT(" %s %llu", store->userspace_supports_overflow ? "PO" : "P", (unsigned long long)store->chunk_size); + break; + case STATUSTYPE_IMA: + *result = '\0'; + break; } return sz; diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c index 4d50a12cf00c..0e0ae4c36b37 100644 --- a/drivers/md/dm-snap-transient.c +++ b/drivers/md/dm-snap-transient.c @@ -95,6 +95,10 @@ static unsigned transient_status(struct dm_exception_store *store, break; case STATUSTYPE_TABLE: DMEMIT(" N %llu", (unsigned long long)store->chunk_size); + break; + case STATUSTYPE_IMA: + *result = '\0'; + break; } return sz; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 751ec5ea1dbb..dcf34c6b05ad 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -2390,6 +2390,16 @@ static void snapshot_status(struct dm_target *ti, status_type_t type, DMEMIT(" discard_passdown_origin"); } break; + + case STATUSTYPE_IMA: + DMEMIT_TARGET_NAME_VERSION(ti->type); + DMEMIT(",snap_origin_name=%s", snap->origin->name); + DMEMIT(",snap_cow_name=%s", snap->cow->name); + DMEMIT(",snap_valid=%c", snap->valid ? 'y' : 'n'); + DMEMIT(",snap_merge_failed=%c", snap->merge_failed ? 'y' : 'n'); + DMEMIT(",snapshot_overflowed=%c", snap->snapshot_overflowed ? 'y' : 'n'); + DMEMIT(";"); + break; } } @@ -2734,6 +2744,9 @@ static void origin_status(struct dm_target *ti, status_type_t type, case STATUSTYPE_TABLE: snprintf(result, maxlen, "%s", o->dev->name); break; + case STATUSTYPE_IMA: + result[0] = '\0'; + break; } } diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index df359d33cda8..6660b6b53d5b 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -428,6 +428,21 @@ static void stripe_status(struct dm_target *ti, status_type_t type, DMEMIT(" %s %llu", sc->stripe[i].dev->name, (unsigned long long)sc->stripe[i].physical_start); break; + + case STATUSTYPE_IMA: + DMEMIT_TARGET_NAME_VERSION(ti->type); + DMEMIT(",stripes=%d,chunk_size=%llu", sc->stripes, + (unsigned long long)sc->chunk_size); + + for (i = 0; i < sc->stripes; i++) { + DMEMIT(",stripe_%d_device_name=%s", i, sc->stripe[i].dev->name); + DMEMIT(",stripe_%d_physical_start=%llu", i, + (unsigned long long)sc->stripe[i].physical_start); + DMEMIT(",stripe_%d_status=%c", i, + atomic_read(&(sc->stripe[i].error_count)) ? 'D' : 'A'); + } + DMEMIT(";"); + break; } } diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c index 262e2b0fd975..028a92ff6d57 100644 --- a/drivers/md/dm-switch.c +++ b/drivers/md/dm-switch.c @@ -504,6 +504,10 @@ static void switch_status(struct dm_target *ti, status_type_t type, DMEMIT(" %s %llu", sctx->path_list[path_nr].dmdev->name, (unsigned long long)sctx->path_list[path_nr].start); break; + + case STATUSTYPE_IMA: + result[0] = '\0'; + break; } } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 985baee3a678..4c67b77c23c1 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -4012,6 +4012,10 @@ static void pool_status(struct dm_target *ti, status_type_t type, (unsigned long long)pt->low_water_blocks); emit_flags(&pt->requested_pf, result, sz, maxlen); break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } return; @@ -4423,6 +4427,10 @@ static void thin_status(struct dm_target *ti, status_type_t type, if (tc->origin_dev) DMEMIT(" %s", format_dev_t(buf, tc->origin_dev->bdev->bd_dev)); break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } } diff --git a/drivers/md/dm-unstripe.c b/drivers/md/dm-unstripe.c index 7357c1bd5863..fdc8921e5c19 100644 --- a/drivers/md/dm-unstripe.c +++ b/drivers/md/dm-unstripe.c @@ -156,6 +156,10 @@ static void unstripe_status(struct dm_target *ti, status_type_t type, uc->stripes, (unsigned long long)uc->chunk_size, uc->unstripe, uc->dev->name, (unsigned long long)uc->physical_start); break; + + case STATUSTYPE_IMA: + *result = '\0'; + break; } } diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index d3e76aefc1a6..bfefa100c265 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -772,6 +772,47 @@ static void verity_status(struct dm_target *ti, status_type_t type, DMEMIT(" " DM_VERITY_ROOT_HASH_VERIFICATION_OPT_SIG_KEY " %s", v->signature_key_desc); break; + + case STATUSTYPE_IMA: + DMEMIT_TARGET_NAME_VERSION(ti->type); + DMEMIT(",hash_failed=%c", v->hash_failed ? 'C' : 'V'); + DMEMIT(",verity_version=%u", v->version); + DMEMIT(",data_device_name=%s", v->data_dev->name); + DMEMIT(",hash_device_name=%s", v->hash_dev->name); + DMEMIT(",verity_algorithm=%s", v->alg_name); + + DMEMIT(",root_digest="); + for (x = 0; x < v->digest_size; x++) + DMEMIT("%02x", v->root_digest[x]); + + DMEMIT(",salt="); + if (!v->salt_size) + DMEMIT("-"); + else + for (x = 0; x < v->salt_size; x++) + DMEMIT("%02x", v->salt[x]); + + DMEMIT(",ignore_zero_blocks=%c", v->zero_digest ? 'y' : 'n'); + DMEMIT(",check_at_most_once=%c", v->validated_blocks ? 'y' : 'n'); + + if (v->mode != DM_VERITY_MODE_EIO) { + DMEMIT(",verity_mode="); + switch (v->mode) { + case DM_VERITY_MODE_LOGGING: + DMEMIT(DM_VERITY_OPT_LOGGING); + break; + case DM_VERITY_MODE_RESTART: + DMEMIT(DM_VERITY_OPT_RESTART); + break; + case DM_VERITY_MODE_PANIC: + DMEMIT(DM_VERITY_OPT_PANIC); + break; + default: + DMEMIT("invalid"); + } + } + DMEMIT(";"); + break; } } diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index e1d7234eec3f..18320444fb0a 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -2723,6 +2723,9 @@ static void writecache_status(struct dm_target *ti, status_type_t type, if (wc->pause_set) DMEMIT(" pause_writeback %u", wc->pause_value); break; + case STATUSTYPE_IMA: + *result = '\0'; + break; } } diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 7e88df64d197..ae1bc48c0043 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -1119,6 +1119,9 @@ static void dmz_status(struct dm_target *ti, status_type_t type, DMEMIT(" %s", buf); } break; + case STATUSTYPE_IMA: + *result = '\0'; + break; } return; } diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 74486c332946..a92260273eb2 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -603,6 +603,10 @@ void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm); #define DMEMIT(x...) sz += ((sz >= maxlen) ? \ 0 : scnprintf(result + sz, maxlen - sz, x)) +#define DMEMIT_TARGET_NAME_VERSION(y) \ + DMEMIT("target_name=%s,target_version=%u.%u.%u", \ + (y)->name, (y)->version[0], (y)->version[1], (y)->version[2]) + /* * Definitions of return values from target end_io function. */ -- cgit v1.2.3 From 438623a06bacd69c40c4af633bb09a3bbb9dfc78 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 15 Jul 2021 15:52:06 -0400 Subject: SUNRPC: Add svc_rqst::rq_auth_stat I'd like to take commit 4532608d71c8 ("SUNRPC: Clean up generic dispatcher code") even further by using only private local SVC dispatchers for all kernel RPC services. This change would enable the removal of the logic that switches between svc_generic_dispatch() and a service's private dispatcher, and simplify the invocation of the service's pc_release method so that humans can visually verify that it is always invoked properly. All that will come later. First, let's provide a better way to return authentication errors from SVC dispatcher functions. Instead of overloading the dispatch method's *statp argument, add a field to struct svc_rqst that can hold an error value. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/svc.h | 1 + include/linux/sunrpc/svcauth.h | 4 ++-- include/trace/events/sunrpc.h | 6 +++--- net/sunrpc/auth_gss/svcauth_gss.c | 43 +++++++++++++++++++-------------------- net/sunrpc/svc.c | 17 ++++++++-------- net/sunrpc/svcauth.c | 8 ++++---- net/sunrpc/svcauth_unix.c | 12 +++++------ 7 files changed, 46 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index e91d51ea028b..35f12963e1ff 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -282,6 +282,7 @@ struct svc_rqst { void * rq_argp; /* decoded arguments */ void * rq_resp; /* xdr'd results */ void * rq_auth_data; /* flavor-specific data */ + __be32 rq_auth_stat; /* authentication status */ int rq_auth_slack; /* extra space xdr code * should leave in head * for krb5i, krb5p. diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index b0003866a249..6d9cc9080aca 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -127,7 +127,7 @@ struct auth_ops { char * name; struct module *owner; int flavour; - int (*accept)(struct svc_rqst *rq, __be32 *authp); + int (*accept)(struct svc_rqst *rq); int (*release)(struct svc_rqst *rq); void (*domain_release)(struct auth_domain *); int (*set_client)(struct svc_rqst *rq); @@ -149,7 +149,7 @@ struct auth_ops { struct svc_xprt; -extern int svc_authenticate(struct svc_rqst *rqstp, __be32 *authp); +extern int svc_authenticate(struct svc_rqst *rqstp); extern int svc_authorise(struct svc_rqst *rqstp); extern int svc_set_client(struct svc_rqst *rqstp); extern int svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops); diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 18d552a17c19..c7d9e6c7a979 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1582,9 +1582,9 @@ TRACE_DEFINE_ENUM(SVC_COMPLETE); { SVC_COMPLETE, "SVC_COMPLETE" }) TRACE_EVENT(svc_authenticate, - TP_PROTO(const struct svc_rqst *rqst, int auth_res, __be32 auth_stat), + TP_PROTO(const struct svc_rqst *rqst, int auth_res), - TP_ARGS(rqst, auth_res, auth_stat), + TP_ARGS(rqst, auth_res), TP_STRUCT__entry( __field(u32, xid) @@ -1595,7 +1595,7 @@ TRACE_EVENT(svc_authenticate, TP_fast_assign( __entry->xid = be32_to_cpu(rqst->rq_xid); __entry->svc_status = auth_res; - __entry->auth_stat = be32_to_cpu(auth_stat); + __entry->auth_stat = be32_to_cpu(rqst->rq_auth_stat); ), TP_printk("xid=0x%08x auth_res=%s auth_stat=%s", diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index a81be45f40d9..635449ed7af6 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -707,11 +707,11 @@ svc_safe_putnetobj(struct kvec *resv, struct xdr_netobj *o) /* * Verify the checksum on the header and return SVC_OK on success. * Otherwise, return SVC_DROP (in the case of a bad sequence number) - * or return SVC_DENIED and indicate error in authp. + * or return SVC_DENIED and indicate error in rqstp->rq_auth_stat. */ static int gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, - __be32 *rpcstart, struct rpc_gss_wire_cred *gc, __be32 *authp) + __be32 *rpcstart, struct rpc_gss_wire_cred *gc) { struct gss_ctx *ctx_id = rsci->mechctx; struct xdr_buf rpchdr; @@ -725,7 +725,7 @@ gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, iov.iov_len = (u8 *)argv->iov_base - (u8 *)rpcstart; xdr_buf_from_iov(&iov, &rpchdr); - *authp = rpc_autherr_badverf; + rqstp->rq_auth_stat = rpc_autherr_badverf; if (argv->iov_len < 4) return SVC_DENIED; flavor = svc_getnl(argv); @@ -737,13 +737,13 @@ gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, if (rqstp->rq_deferred) /* skip verification of revisited request */ return SVC_OK; if (gss_verify_mic(ctx_id, &rpchdr, &checksum) != GSS_S_COMPLETE) { - *authp = rpcsec_gsserr_credproblem; + rqstp->rq_auth_stat = rpcsec_gsserr_credproblem; return SVC_DENIED; } if (gc->gc_seq > MAXSEQ) { trace_rpcgss_svc_seqno_large(rqstp, gc->gc_seq); - *authp = rpcsec_gsserr_ctxproblem; + rqstp->rq_auth_stat = rpcsec_gsserr_ctxproblem; return SVC_DENIED; } if (!gss_check_seq_num(rqstp, rsci, gc->gc_seq)) @@ -1142,7 +1142,7 @@ static void gss_free_in_token_pages(struct gssp_in_token *in_token) } static int gss_read_proxy_verf(struct svc_rqst *rqstp, - struct rpc_gss_wire_cred *gc, __be32 *authp, + struct rpc_gss_wire_cred *gc, struct xdr_netobj *in_handle, struct gssp_in_token *in_token) { @@ -1151,7 +1151,7 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, int pages, i, res, pgto, pgfrom; size_t inlen, to_offs, from_offs; - res = gss_read_common_verf(gc, argv, authp, in_handle); + res = gss_read_common_verf(gc, argv, &rqstp->rq_auth_stat, in_handle); if (res) return res; @@ -1227,7 +1227,7 @@ gss_write_resv(struct kvec *resv, size_t size_limit, * Otherwise, drop the request pending an answer to the upcall. */ static int svcauth_gss_legacy_init(struct svc_rqst *rqstp, - struct rpc_gss_wire_cred *gc, __be32 *authp) + struct rpc_gss_wire_cred *gc) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -1236,7 +1236,7 @@ static int svcauth_gss_legacy_init(struct svc_rqst *rqstp, struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); memset(&rsikey, 0, sizeof(rsikey)); - ret = gss_read_verf(gc, argv, authp, + ret = gss_read_verf(gc, argv, &rqstp->rq_auth_stat, &rsikey.in_handle, &rsikey.in_token); if (ret) return ret; @@ -1339,7 +1339,7 @@ out: } static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, - struct rpc_gss_wire_cred *gc, __be32 *authp) + struct rpc_gss_wire_cred *gc) { struct kvec *resv = &rqstp->rq_res.head[0]; struct xdr_netobj cli_handle; @@ -1351,8 +1351,7 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); memset(&ud, 0, sizeof(ud)); - ret = gss_read_proxy_verf(rqstp, gc, authp, - &ud.in_handle, &ud.in_token); + ret = gss_read_proxy_verf(rqstp, gc, &ud.in_handle, &ud.in_token); if (ret) return ret; @@ -1525,7 +1524,7 @@ static void destroy_use_gss_proxy_proc_entry(struct net *net) {} * response here and return SVC_COMPLETE. */ static int -svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) +svcauth_gss_accept(struct svc_rqst *rqstp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -1538,7 +1537,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) int ret; struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); - *authp = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; if (!svcdata) svcdata = kmalloc(sizeof(*svcdata), GFP_KERNEL); if (!svcdata) @@ -1575,22 +1574,22 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) if ((gc->gc_proc != RPC_GSS_PROC_DATA) && (rqstp->rq_proc != 0)) goto auth_err; - *authp = rpc_autherr_badverf; + rqstp->rq_auth_stat = rpc_autherr_badverf; switch (gc->gc_proc) { case RPC_GSS_PROC_INIT: case RPC_GSS_PROC_CONTINUE_INIT: if (use_gss_proxy(SVC_NET(rqstp))) - return svcauth_gss_proxy_init(rqstp, gc, authp); + return svcauth_gss_proxy_init(rqstp, gc); else - return svcauth_gss_legacy_init(rqstp, gc, authp); + return svcauth_gss_legacy_init(rqstp, gc); case RPC_GSS_PROC_DATA: case RPC_GSS_PROC_DESTROY: /* Look up the context, and check the verifier: */ - *authp = rpcsec_gsserr_credproblem; + rqstp->rq_auth_stat = rpcsec_gsserr_credproblem; rsci = gss_svc_searchbyctx(sn->rsc_cache, &gc->gc_ctx); if (!rsci) goto auth_err; - switch (gss_verify_header(rqstp, rsci, rpcstart, gc, authp)) { + switch (gss_verify_header(rqstp, rsci, rpcstart, gc)) { case SVC_OK: break; case SVC_DENIED: @@ -1600,7 +1599,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) } break; default: - *authp = rpc_autherr_rejectedcred; + rqstp->rq_auth_stat = rpc_autherr_rejectedcred; goto auth_err; } @@ -1616,13 +1615,13 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) svc_putnl(resv, RPC_SUCCESS); goto complete; case RPC_GSS_PROC_DATA: - *authp = rpcsec_gsserr_ctxproblem; + rqstp->rq_auth_stat = rpcsec_gsserr_ctxproblem; svcdata->verf_start = resv->iov_base + resv->iov_len; if (gss_write_verf(rqstp, rsci->mechctx, gc->gc_seq)) goto auth_err; rqstp->rq_cred = rsci->cred; get_group_info(rsci->cred.cr_group_info); - *authp = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; switch (gc->gc_svc) { case RPC_GSS_SVC_NONE: break; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 0de918cb3d90..360dab62b6b4 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1283,7 +1283,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) struct svc_process_info process; __be32 *statp; u32 prog, vers; - __be32 auth_stat, rpc_stat; + __be32 rpc_stat; int auth_res; __be32 *reply_statp; @@ -1326,14 +1326,14 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) * We do this before anything else in order to get a decent * auth verifier. */ - auth_res = svc_authenticate(rqstp, &auth_stat); + auth_res = svc_authenticate(rqstp); /* Also give the program a chance to reject this call: */ if (auth_res == SVC_OK && progp) { - auth_stat = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; auth_res = progp->pg_authenticate(rqstp); } if (auth_res != SVC_OK) - trace_svc_authenticate(rqstp, auth_res, auth_stat); + trace_svc_authenticate(rqstp, auth_res); switch (auth_res) { case SVC_OK: break; @@ -1392,8 +1392,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) goto release_dropit; if (*statp == rpc_garbage_args) goto err_garbage; - auth_stat = svc_get_autherr(rqstp, statp); - if (auth_stat != rpc_auth_ok) + rqstp->rq_auth_stat = svc_get_autherr(rqstp, statp); + if (rqstp->rq_auth_stat != rpc_auth_ok) goto err_release_bad_auth; } else { dprintk("svc: calling dispatcher\n"); @@ -1450,13 +1450,14 @@ err_release_bad_auth: if (procp->pc_release) procp->pc_release(rqstp); err_bad_auth: - dprintk("svc: authentication failed (%d)\n", ntohl(auth_stat)); + dprintk("svc: authentication failed (%d)\n", + be32_to_cpu(rqstp->rq_auth_stat)); serv->sv_stats->rpcbadauth++; /* Restore write pointer to location of accept status: */ xdr_ressize_check(rqstp, reply_statp); svc_putnl(resv, 1); /* REJECT */ svc_putnl(resv, 1); /* AUTH_ERROR */ - svc_putnl(resv, ntohl(auth_stat)); /* status */ + svc_putu32(resv, rqstp->rq_auth_stat); /* status */ goto sendit; err_bad_prog: diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 998b196b6176..5a8b8e03fdd4 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -59,12 +59,12 @@ svc_put_auth_ops(struct auth_ops *aops) } int -svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) +svc_authenticate(struct svc_rqst *rqstp) { rpc_authflavor_t flavor; struct auth_ops *aops; - *authp = rpc_auth_ok; + rqstp->rq_auth_stat = rpc_auth_ok; flavor = svc_getnl(&rqstp->rq_arg.head[0]); @@ -72,7 +72,7 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) aops = svc_get_auth_ops(flavor); if (aops == NULL) { - *authp = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } @@ -80,7 +80,7 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) init_svc_cred(&rqstp->rq_cred); rqstp->rq_authop = aops; - return aops->accept(rqstp, authp); + return aops->accept(rqstp); } EXPORT_SYMBOL_GPL(svc_authenticate); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 35b7966ac3b3..eacfebf326dd 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -725,7 +725,7 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) EXPORT_SYMBOL_GPL(svcauth_unix_set_client); static int -svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp) +svcauth_null_accept(struct svc_rqst *rqstp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -736,12 +736,12 @@ svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp) if (svc_getu32(argv) != 0) { dprintk("svc: bad null cred\n"); - *authp = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { dprintk("svc: bad null verf\n"); - *authp = rpc_autherr_badverf; + rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } @@ -785,7 +785,7 @@ struct auth_ops svcauth_null = { static int -svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) +svcauth_unix_accept(struct svc_rqst *rqstp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -827,7 +827,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) } groups_sort(cred->cr_group_info); if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { - *authp = rpc_autherr_badverf; + rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } @@ -839,7 +839,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) return SVC_OK; badcred: - *authp = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } -- cgit v1.2.3 From 9082e1d914f8b27114352b1940bbcc7522f682e7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 15 Jul 2021 15:52:19 -0400 Subject: SUNRPC: Eliminate the RQ_AUTHERR flag Now that there is an alternate method for returning an auth_stat value, replace the RQ_AUTHERR flag with use of that new method. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- fs/nfs/callback_xdr.c | 3 ++- include/linux/sunrpc/svc.h | 2 -- include/trace/events/sunrpc.h | 3 +-- net/sunrpc/svc.c | 24 ++++-------------------- 4 files changed, 7 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index c5348ba81129..7ff99155b023 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -988,7 +988,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp) out_invalidcred: pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n"); - return svc_return_autherr(rqstp, rpc_autherr_badcred); + rqstp->rq_auth_stat = rpc_autherr_badcred; + return rpc_success; } /* diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 35f12963e1ff..63c9210cae06 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -275,7 +275,6 @@ struct svc_rqst { #define RQ_VICTIM (5) /* about to be shut down */ #define RQ_BUSY (6) /* request is busy */ #define RQ_DATA (7) /* request has data */ -#define RQ_AUTHERR (8) /* Request status is auth error */ unsigned long rq_flags; /* flags field */ ktime_t rq_qtime; /* enqueue time */ @@ -533,7 +532,6 @@ unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, struct kvec *first, void *p, size_t total); -__be32 svc_return_autherr(struct svc_rqst *rqstp, __be32 auth_err); __be32 svc_generic_init_request(struct svc_rqst *rqstp, const struct svc_program *progp, struct svc_process_info *procinfo); diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index c7d9e6c7a979..169b93e4dbc1 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1539,8 +1539,7 @@ DEFINE_SVCXDRBUF_EVENT(sendto); svc_rqst_flag(SPLICE_OK) \ svc_rqst_flag(VICTIM) \ svc_rqst_flag(BUSY) \ - svc_rqst_flag(DATA) \ - svc_rqst_flag_end(AUTHERR) + svc_rqst_flag_end(DATA) #undef svc_rqst_flag #undef svc_rqst_flag_end diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 2019d1203641..95836bf514b5 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1163,22 +1163,6 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} #endif -__be32 -svc_return_autherr(struct svc_rqst *rqstp, __be32 auth_err) -{ - set_bit(RQ_AUTHERR, &rqstp->rq_flags); - return auth_err; -} -EXPORT_SYMBOL_GPL(svc_return_autherr); - -static __be32 -svc_get_autherr(struct svc_rqst *rqstp, __be32 *statp) -{ - if (test_and_clear_bit(RQ_AUTHERR, &rqstp->rq_flags)) - return *statp; - return rpc_auth_ok; -} - static int svc_generic_dispatch(struct svc_rqst *rqstp, __be32 *statp) { @@ -1202,7 +1186,7 @@ svc_generic_dispatch(struct svc_rqst *rqstp, __be32 *statp) test_bit(RQ_DROPME, &rqstp->rq_flags)) return 0; - if (test_bit(RQ_AUTHERR, &rqstp->rq_flags)) + if (rqstp->rq_auth_stat != rpc_auth_ok) return 1; if (*statp != rpc_success) @@ -1390,15 +1374,15 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) goto release_dropit; if (*statp == rpc_garbage_args) goto err_garbage; - rqstp->rq_auth_stat = svc_get_autherr(rqstp, statp); - if (rqstp->rq_auth_stat != rpc_auth_ok) - goto err_release_bad_auth; } else { dprintk("svc: calling dispatcher\n"); if (!process.dispatch(rqstp, statp)) goto release_dropit; /* Release reply info */ } + if (rqstp->rq_auth_stat != rpc_auth_ok) + goto err_release_bad_auth; + /* Check RPC status result */ if (*statp != rpc_success) resv->iov_len = ((void*)statp) - resv->iov_base + 4; -- cgit v1.2.3 From 91cc470e797828d779cd4c1efbe8519bcb358bae Mon Sep 17 00:00:00 2001 From: Tanner Love Date: Wed, 2 Jun 2021 14:03:38 -0400 Subject: genirq: Change force_irqthreads to a static key With CONFIG_IRQ_FORCED_THREADING=y, testing the boolean force_irqthreads could incur a cache line miss in invoke_softirq() and other places. Replace the test with a static key to avoid the potential cache miss. [ tglx: Dropped the IDE part, removed the export and updated blk-mq ] Suggested-by: Eric Dumazet Signed-off-by: Tanner Love Signed-off-by: Thomas Gleixner Reviewed-by: Eric Dumazet Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20210602180338.3324213-1-tannerlove.kernel@gmail.com --- block/blk-mq.c | 2 +- include/linux/interrupt.h | 8 +++++--- kernel/irq/manage.c | 11 +++++------ kernel/softirq.c | 2 +- 4 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 2c4ac51e54eb..572d8ab34014 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -606,7 +606,7 @@ static inline bool blk_mq_complete_need_ipi(struct request *rq) * This is probably worse than completing the request on a different * cache domain. */ - if (force_irqthreads) + if (force_irqthreads()) return false; /* same CPU or cache domain? Complete locally */ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 2ed65b01c961..1f22a30c0963 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -474,12 +475,13 @@ extern int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, #ifdef CONFIG_IRQ_FORCED_THREADING # ifdef CONFIG_PREEMPT_RT -# define force_irqthreads (true) +# define force_irqthreads() (true) # else -extern bool force_irqthreads; +DECLARE_STATIC_KEY_FALSE(force_irqthreads_key); +# define force_irqthreads() (static_branch_unlikely(&force_irqthreads_key)) # endif #else -#define force_irqthreads (0) +#define force_irqthreads() (false) #endif #ifndef local_softirq_pending diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 766468a2fc5a..34a66c4543a2 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -25,12 +25,11 @@ #include "internals.h" #if defined(CONFIG_IRQ_FORCED_THREADING) && !defined(CONFIG_PREEMPT_RT) -__read_mostly bool force_irqthreads; -EXPORT_SYMBOL_GPL(force_irqthreads); +DEFINE_STATIC_KEY_FALSE(force_irqthreads_key); static int __init setup_forced_irqthreads(char *arg) { - force_irqthreads = true; + static_branch_enable(&force_irqthreads_key); return 0; } early_param("threadirqs", setup_forced_irqthreads); @@ -1260,8 +1259,8 @@ static int irq_thread(void *data) irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); - if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD, - &action->thread_flags)) + if (force_irqthreads() && test_bit(IRQTF_FORCED_THREAD, + &action->thread_flags)) handler_fn = irq_forced_thread_fn; else handler_fn = irq_thread_fn; @@ -1322,7 +1321,7 @@ EXPORT_SYMBOL_GPL(irq_wake_thread); static int irq_setup_forced_threading(struct irqaction *new) { - if (!force_irqthreads) + if (!force_irqthreads()) return 0; if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) return 0; diff --git a/kernel/softirq.c b/kernel/softirq.c index f3a012179f47..322b65d45676 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -422,7 +422,7 @@ static inline void invoke_softirq(void) if (ksoftirqd_running(local_softirq_pending())) return; - if (!force_irqthreads || !__this_cpu_read(ksoftirqd)) { + if (!force_irqthreads() || !__this_cpu_read(ksoftirqd)) { #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK /* * We can safely execute softirq on the current stack if -- cgit v1.2.3 From 1ce849c755342b236fc6236dfe39dbbf536b64b6 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 20 Jul 2021 05:27:54 +0200 Subject: x86/PCI: Add support for the ALi M1487 (IBC) PIRQ router The ALi M1487 ISA Bus Controller (IBC), a part of the ALi FinALi 486 chipset, implements PCI interrupt steering with a PIRQ router[1] in the form of four 4-bit mappings, spread across two PCI INTx Routing Table Mapping Registers, available in the port I/O space accessible indirectly via the index/data register pair at 0x22/0x23, located at indices 0x42 and 0x43 for the INT1/INT2 and INT3/INT4 lines respectively. Additionally there is a separate PCI INTx Sensitivity Register at index 0x44 in the same port I/O space, whose bits 3:0 select the trigger mode for INT[4:1] lines respectively[2]. Manufacturer's documentation says that this register has to be set consistently with the relevant ELCR register[3]. Add a router-specific hook then and use it to handle this register. Accesses to the port I/O space concerned here need to be unlocked by writing the value of 0xc5 to the Lock Register at index 0x03 beforehand[4]. Do so then and then lock access after use for safety. The IBC is implemented as a peer bridge on the host bus rather than a southbridge on PCI and therefore it does not itself appear in the PCI configuration space. It is complemented by the M1489 Cache-Memory PCI Controller (CMP) host-to-PCI bridge, so use that device's identification for determining the presence of the IBC. References: [1] "M1489/M1487: 486 PCI Chip Set", Version 1.2, Acer Laboratories Inc., July 1997, Section 4: "Configuration Registers", pp. 76-77 [2] same, p. 77 [3] same, Section 5: "M1489/M1487 Software Programming Guide", pp. 99-100 [4] same, Section 4: "Configuration Registers", p. 37 Signed-off-by: Maciej W. Rozycki Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/alpine.DEB.2.21.2107191702020.9461@angie.orcam.me.uk --- arch/x86/pci/irq.c | 154 +++++++++++++++++++++++++++++++++++++++++++++++- include/linux/pci_ids.h | 1 + 2 files changed, 153 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index d3a73f9335e1..1bccbc419630 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -13,9 +13,12 @@ #include #include #include +#include #include #include #include + +#include #include #define PIRQ_SIGNATURE (('$' << 0) + ('P' << 8) + ('I' << 16) + ('R' << 24)) @@ -47,6 +50,8 @@ struct irq_router { int (*get)(struct pci_dev *router, struct pci_dev *dev, int pirq); int (*set)(struct pci_dev *router, struct pci_dev *dev, int pirq, int new); + int (*lvl)(struct pci_dev *router, struct pci_dev *dev, int pirq, + int irq); }; struct irq_router_handler { @@ -169,6 +174,139 @@ void elcr_set_level_irq(unsigned int irq) } } +/* + * PIRQ routing for the M1487 ISA Bus Controller (IBC) ASIC used + * with the ALi FinALi 486 chipset. The IBC is not decoded in the + * PCI configuration space, so we identify it by the accompanying + * M1489 Cache-Memory PCI Controller (CMP) ASIC. + * + * There are four 4-bit mappings provided, spread across two PCI + * INTx Routing Table Mapping Registers, available in the port I/O + * space accessible indirectly via the index/data register pair at + * 0x22/0x23, located at indices 0x42 and 0x43 for the INT1/INT2 + * and INT3/INT4 lines respectively. The INT1/INT3 and INT2/INT4 + * lines are mapped in the low and the high 4-bit nibble of the + * corresponding register as follows: + * + * 0000 : Disabled + * 0001 : IRQ9 + * 0010 : IRQ3 + * 0011 : IRQ10 + * 0100 : IRQ4 + * 0101 : IRQ5 + * 0110 : IRQ7 + * 0111 : IRQ6 + * 1000 : Reserved + * 1001 : IRQ11 + * 1010 : Reserved + * 1011 : IRQ12 + * 1100 : Reserved + * 1101 : IRQ14 + * 1110 : Reserved + * 1111 : IRQ15 + * + * In addition to the usual ELCR register pair there is a separate + * PCI INTx Sensitivity Register at index 0x44 in the same port I/O + * space, whose bits 3:0 select the trigger mode for INT[4:1] lines + * respectively. Any bit set to 1 causes interrupts coming on the + * corresponding line to be passed to ISA as edge-triggered and + * otherwise they are passed as level-triggered. Manufacturer's + * documentation says this register has to be set consistently with + * the relevant ELCR register. + * + * Accesses to the port I/O space concerned here need to be unlocked + * by writing the value of 0xc5 to the Lock Register at index 0x03 + * beforehand. Any other value written to said register prevents + * further accesses from reaching the register file, except for the + * Lock Register being written with 0xc5 again. + * + * References: + * + * "M1489/M1487: 486 PCI Chip Set", Version 1.2, Acer Laboratories + * Inc., July 1997 + */ + +#define PC_CONF_FINALI_LOCK 0x03u +#define PC_CONF_FINALI_PCI_INTX_RT1 0x42u +#define PC_CONF_FINALI_PCI_INTX_RT2 0x43u +#define PC_CONF_FINALI_PCI_INTX_SENS 0x44u + +#define PC_CONF_FINALI_LOCK_KEY 0xc5u + +static u8 read_pc_conf_nybble(u8 base, u8 index) +{ + u8 reg = base + (index >> 1); + u8 x; + + x = pc_conf_get(reg); + return index & 1 ? x >> 4 : x & 0xf; +} + +static void write_pc_conf_nybble(u8 base, u8 index, u8 val) +{ + u8 reg = base + (index >> 1); + u8 x; + + x = pc_conf_get(reg); + x = index & 1 ? (x & 0x0f) | (val << 4) : (x & 0xf0) | val; + pc_conf_set(reg, x); +} + +static int pirq_finali_get(struct pci_dev *router, struct pci_dev *dev, + int pirq) +{ + static const u8 irqmap[16] = { + 0, 9, 3, 10, 4, 5, 7, 6, 0, 11, 0, 12, 0, 14, 0, 15 + }; + unsigned long flags; + u8 x; + + raw_spin_lock_irqsave(&pc_conf_lock, flags); + pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); + x = irqmap[read_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, pirq - 1)]; + pc_conf_set(PC_CONF_FINALI_LOCK, 0); + raw_spin_unlock_irqrestore(&pc_conf_lock, flags); + return x; +} + +static int pirq_finali_set(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) +{ + static const u8 irqmap[16] = { + 0, 0, 0, 2, 4, 5, 7, 6, 0, 1, 3, 9, 11, 0, 13, 15 + }; + u8 val = irqmap[irq]; + unsigned long flags; + + if (!val) + return 0; + + raw_spin_lock_irqsave(&pc_conf_lock, flags); + pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); + write_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, pirq - 1, val); + pc_conf_set(PC_CONF_FINALI_LOCK, 0); + raw_spin_unlock_irqrestore(&pc_conf_lock, flags); + return 1; +} + +static int pirq_finali_lvl(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) +{ + u8 mask = ~(1u << (pirq - 1)); + unsigned long flags; + u8 trig; + + elcr_set_level_irq(irq); + raw_spin_lock_irqsave(&pc_conf_lock, flags); + pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); + trig = pc_conf_get(PC_CONF_FINALI_PCI_INTX_SENS); + trig &= mask; + pc_conf_set(PC_CONF_FINALI_PCI_INTX_SENS, trig); + pc_conf_set(PC_CONF_FINALI_LOCK, 0); + raw_spin_unlock_irqrestore(&pc_conf_lock, flags); + return 1; +} + /* * Common IRQ routing practice: nibbles in config space, * offset by some magic constant. @@ -745,6 +883,12 @@ static __init int ite_router_probe(struct irq_router *r, struct pci_dev *router, static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { switch (device) { + case PCI_DEVICE_ID_AL_M1489: + r->name = "FinALi"; + r->get = pirq_finali_get; + r->set = pirq_finali_set; + r->lvl = pirq_finali_lvl; + return 1; case PCI_DEVICE_ID_AL_M1533: case PCI_DEVICE_ID_AL_M1563: r->name = "ALI"; @@ -968,11 +1112,17 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) } else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) { msg = "found"; - elcr_set_level_irq(irq); + if (r->lvl) + r->lvl(pirq_router_dev, dev, pirq, irq); + else + elcr_set_level_irq(irq); } else if (newirq && r->set && (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { if (r->set(pirq_router_dev, dev, pirq, newirq)) { - elcr_set_level_irq(newirq); + if (r->lvl) + r->lvl(pirq_router_dev, dev, pirq, newirq); + else + elcr_set_level_irq(newirq); msg = "assigned"; irq = newirq; } diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 4bac1831de80..256fa4d7e86c 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1121,6 +1121,7 @@ #define PCI_DEVICE_ID_3COM_3CR990SVR 0x990a #define PCI_VENDOR_ID_AL 0x10b9 +#define PCI_DEVICE_ID_AL_M1489 0x1489 #define PCI_DEVICE_ID_AL_M1533 0x1533 #define PCI_DEVICE_ID_AL_M1535 0x1535 #define PCI_DEVICE_ID_AL_M1541 0x1541 -- cgit v1.2.3 From 0e8c6f56fab3af3ef9f78f486e198792d3af0fa1 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 20 Jul 2021 05:28:04 +0200 Subject: x86/PCI: Add support for the Intel 82426EX PIRQ router The Intel 82426EX ISA Bridge (IB), a part of the Intel 82420EX PCIset, implements PCI interrupt steering with a PIRQ router in the form of two PIRQ Route Control registers, available in the PCI configuration space at locations 0x66 and 0x67 for the PIRQ0# and PIRQ1# lines respectively. The semantics is the same as with the PIIX router, however it is not clear if BIOSes use register indices or line numbers as the cookie to identify PCI interrupts in their routing tables and therefore support either scheme. The IB is directly attached to the Intel 82425EX PCI System Controller (PSC) component of the chipset via a dedicated PSC/IB Link interface rather than the host bus or PCI. Therefore it does not itself appear in the PCI configuration space even though it responds to configuration cycles addressing registers it implements. Use 82425EX's identification then for determining the presence of the IB. References: [1] "82420EX PCIset Data Sheet, 82425EX PCI System Controller (PSC) and 82426EX ISA Bridge (IB)", Intel Corporation, Order Number: 290488-004, December 1995, Section 3.3.18 "PIRQ1RC/PIRQ0RC--PIRQ Route Control Registers", p. 61 Signed-off-by: Maciej W. Rozycki Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/alpine.DEB.2.21.2107200213490.9461@angie.orcam.me.uk --- arch/x86/pci/irq.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci_ids.h | 1 + 2 files changed, 50 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 187e284f2021..b937c96f9f85 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -443,6 +443,50 @@ static int pirq_piix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, return 1; } +/* + * PIRQ routing for the 82426EX ISA Bridge (IB) ASIC used with the + * Intel 82420EX PCIset. + * + * There are only two PIRQ Route Control registers, available in the + * combined 82425EX/82426EX PCI configuration space, at 0x66 and 0x67 + * for the PIRQ0# and PIRQ1# lines respectively. The semantics is + * the same as with the PIIX router. + * + * References: + * + * "82420EX PCIset Data Sheet, 82425EX PCI System Controller (PSC) + * and 82426EX ISA Bridge (IB)", Intel Corporation, Order Number: + * 290488-004, December 1995 + */ + +#define PCI_I82426EX_PIRQ_ROUTE_CONTROL 0x66u + +static int pirq_ib_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + int reg; + u8 x; + + reg = pirq; + if (reg >= 1 && reg <= 2) + reg += PCI_I82426EX_PIRQ_ROUTE_CONTROL - 1; + + pci_read_config_byte(router, reg, &x); + return (x < 16) ? x : 0; +} + +static int pirq_ib_set(struct pci_dev *router, struct pci_dev *dev, int pirq, + int irq) +{ + int reg; + + reg = pirq; + if (reg >= 1 && reg <= 2) + reg += PCI_I82426EX_PIRQ_ROUTE_CONTROL - 1; + + pci_write_config_byte(router, reg, irq); + return 1; +} + /* * The VIA pirq rules are nibble-based, like ALI, * but without the ugly irq number munging. @@ -805,6 +849,11 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route r->get = pirq_piix_get; r->set = pirq_piix_set; return 1; + case PCI_DEVICE_ID_INTEL_82425: + r->name = "PSC/IB"; + r->get = pirq_ib_get; + r->set = pirq_ib_set; + return 1; } if ((device >= PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MIN && diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 256fa4d7e86c..60e2101a009d 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2644,6 +2644,7 @@ #define PCI_DEVICE_ID_INTEL_82375 0x0482 #define PCI_DEVICE_ID_INTEL_82424 0x0483 #define PCI_DEVICE_ID_INTEL_82378 0x0484 +#define PCI_DEVICE_ID_INTEL_82425 0x0486 #define PCI_DEVICE_ID_INTEL_MRST_SD0 0x0807 #define PCI_DEVICE_ID_INTEL_MRST_SD1 0x0808 #define PCI_DEVICE_ID_INTEL_MFD_SD 0x0820 -- cgit v1.2.3 From ed4520d6a10bbc1d6fdebf325f0395995ce634cf Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 9 Aug 2021 11:27:47 -0500 Subject: soc: ti: Remove pm_runtime_irq_safe() usage for smartreflex For the smartreflex device, we need to disable smartreflex on SoC idle, and have been using pm_runtime_irq_safe() to do that. But we want to remove the irq_safe usage as PM runtime takes a permanent usage count on the parent device with it. In order to remove the need for pm_runtime_irq_safe(), let's gate the clock directly in the driver. This removes the need to call PM runtime during idle, and allows us to switch to using CPU_PM in the following patch. Note that the smartreflex interconnect target module is configured for smart idle, but the clock does not have autoidle capability, and needs to be gated manually. If the clock supported autoidle, we would not need to even gate the clock. With this change, we can now remove the related quirk flags for ti-sysc also. Signed-off-by: Tony Lindgren Signed-off-by: Santosh Shilimkar --- drivers/bus/ti-sysc.c | 6 ++--- drivers/soc/ti/smartreflex.c | 52 +++++++++++++++++---------------------- include/linux/power/smartreflex.h | 2 ++ 3 files changed, 26 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 38cb116ed433..f87783a5489a 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1444,10 +1444,6 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK_LEGACY_IDLE | SYSC_QUIRK_OPT_CLKS_IN_RESET), SYSC_QUIRK("sham", 0, 0x100, 0x110, 0x114, 0x40000c03, 0xffffffff, SYSC_QUIRK_LEGACY_IDLE), - SYSC_QUIRK("smartreflex", 0, -ENODEV, 0x24, -ENODEV, 0x00000000, 0xffffffff, - SYSC_QUIRK_LEGACY_IDLE), - SYSC_QUIRK("smartreflex", 0, -ENODEV, 0x38, -ENODEV, 0x00000000, 0xffffffff, - SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x00000046, 0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x00000052, 0xffffffff, @@ -1583,6 +1579,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("sdma", 0, 0, 0x2c, 0x28, 0x00010900, 0xffffffff, 0), SYSC_QUIRK("slimbus", 0, 0, 0x10, -ENODEV, 0x40000902, 0xffffffff, 0), SYSC_QUIRK("slimbus", 0, 0, 0x10, -ENODEV, 0x40002903, 0xffffffff, 0), + SYSC_QUIRK("smartreflex", 0, -ENODEV, 0x24, -ENODEV, 0x00000000, 0xffffffff, 0), + SYSC_QUIRK("smartreflex", 0, -ENODEV, 0x38, -ENODEV, 0x00000000, 0xffffffff, 0), SYSC_QUIRK("spinlock", 0, 0, 0x10, -ENODEV, 0x50020000, 0xffffffff, 0), SYSC_QUIRK("rng", 0, 0x1fe0, 0x1fe4, -ENODEV, 0x00000020, 0xffffffff, 0), SYSC_QUIRK("timer", 0, 0, 0x10, 0x14, 0x00000013, 0xffffffff, 0), diff --git a/drivers/soc/ti/smartreflex.c b/drivers/soc/ti/smartreflex.c index 06cbee5fd254..b5b2fa538d5c 100644 --- a/drivers/soc/ti/smartreflex.c +++ b/drivers/soc/ti/smartreflex.c @@ -126,23 +126,13 @@ static irqreturn_t sr_interrupt(int irq, void *data) static void sr_set_clk_length(struct omap_sr *sr) { - struct clk *fck; u32 fclk_speed; /* Try interconnect target module fck first if it already exists */ - fck = clk_get(sr->pdev->dev.parent, "fck"); - if (IS_ERR(fck)) { - fck = clk_get(&sr->pdev->dev, "fck"); - if (IS_ERR(fck)) { - dev_err(&sr->pdev->dev, - "%s: unable to get fck for device %s\n", - __func__, dev_name(&sr->pdev->dev)); - return; - } - } + if (IS_ERR(sr->fck)) + return; - fclk_speed = clk_get_rate(fck); - clk_put(fck); + fclk_speed = clk_get_rate(sr->fck); switch (fclk_speed) { case 12000000: @@ -587,21 +577,25 @@ int sr_enable(struct omap_sr *sr, unsigned long volt) /* errminlimit is opp dependent and hence linked to voltage */ sr->err_minlimit = nvalue_row->errminlimit; - pm_runtime_get_sync(&sr->pdev->dev); + clk_enable(sr->fck); /* Check if SR is already enabled. If yes do nothing */ if (sr_read_reg(sr, SRCONFIG) & SRCONFIG_SRENABLE) - return 0; + goto out_enabled; /* Configure SR */ ret = sr_class->configure(sr); if (ret) - return ret; + goto out_enabled; sr_write_reg(sr, NVALUERECIPROCAL, nvalue_row->nvalue); /* SRCONFIG - enable SR */ sr_modify_reg(sr, SRCONFIG, SRCONFIG_SRENABLE, SRCONFIG_SRENABLE); + +out_enabled: + sr->enabled = 1; + return 0; } @@ -621,7 +615,7 @@ void sr_disable(struct omap_sr *sr) } /* Check if SR clocks are already disabled. If yes do nothing */ - if (pm_runtime_suspended(&sr->pdev->dev)) + if (!sr->enabled) return; /* @@ -642,7 +636,8 @@ void sr_disable(struct omap_sr *sr) } } - pm_runtime_put_sync_suspend(&sr->pdev->dev); + clk_disable(sr->fck); + sr->enabled = 0; } /** @@ -851,8 +846,12 @@ static int omap_sr_probe(struct platform_device *pdev) irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + sr_info->fck = devm_clk_get(pdev->dev.parent, "fck"); + if (IS_ERR(sr_info->fck)) + return PTR_ERR(sr_info->fck); + clk_prepare(sr_info->fck); + pm_runtime_enable(&pdev->dev); - pm_runtime_irq_safe(&pdev->dev); snprintf(sr_info->name, SMARTREFLEX_NAME_LEN, "%s", pdata->name); @@ -878,12 +877,6 @@ static int omap_sr_probe(struct platform_device *pdev) list_add(&sr_info->node, &sr_list); - ret = pm_runtime_get_sync(&pdev->dev); - if (ret < 0) { - pm_runtime_put_noidle(&pdev->dev); - goto err_list_del; - } - /* * Call into late init to do initializations that require * both sr driver and sr class driver to be initiallized. @@ -933,16 +926,13 @@ static int omap_sr_probe(struct platform_device *pdev) } - pm_runtime_put_sync(&pdev->dev); - return ret; err_debugfs: debugfs_remove_recursive(sr_info->dbg_dir); err_list_del: list_del(&sr_info->node); - - pm_runtime_put_sync(&pdev->dev); + clk_unprepare(sr_info->fck); return ret; } @@ -950,6 +940,7 @@ err_list_del: static int omap_sr_remove(struct platform_device *pdev) { struct omap_sr_data *pdata = pdev->dev.platform_data; + struct device *dev = &pdev->dev; struct omap_sr *sr_info; if (!pdata) { @@ -968,7 +959,8 @@ static int omap_sr_remove(struct platform_device *pdev) sr_stop_vddautocomp(sr_info); debugfs_remove_recursive(sr_info->dbg_dir); - pm_runtime_disable(&pdev->dev); + pm_runtime_disable(dev); + clk_unprepare(sr_info->fck); list_del(&sr_info->node); return 0; } diff --git a/include/linux/power/smartreflex.h b/include/linux/power/smartreflex.h index 971c9264179e..167b9b040091 100644 --- a/include/linux/power/smartreflex.h +++ b/include/linux/power/smartreflex.h @@ -155,6 +155,7 @@ struct omap_sr { struct voltagedomain *voltdm; struct dentry *dbg_dir; unsigned int irq; + struct clk *fck; int srid; int ip_type; int nvalue_count; @@ -169,6 +170,7 @@ struct omap_sr { u32 senp_mod; u32 senn_mod; void __iomem *base; + unsigned long enabled:1; }; /** -- cgit v1.2.3 From 63c8b1231929b8aa80abc753c1c91b6b49e2c0b0 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:14 +0000 Subject: x86/resctrl: Split struct rdt_resource resctrl is the defacto Linux ABI for SoC resource partitioning features. To support it on another architecture, it needs to be abstracted from the features provided by Intel RDT and AMD PQoS, and moved to /fs/. struct rdt_resource contains a mix of architecture private details and properties of the filesystem interface user-space uses. Start by splitting struct rdt_resource, into an architecture private 'hw' struct, which contains the common resctrl structure that would be used by any architecture. The foreach helpers are most commonly used by the filesystem code, and should return the common resctrl structure. for_each_rdt_resource() is changed to walk the common structure in its parent arch private structure. Move as much of the structure as possible into the common structure in the core code's header file. The x86 hardware accessors remain part of the architecture private code, as do num_closid, mon_scale and mbm_width. mon_scale and mbm_width are used to detect overflow of the hardware counters, and convert them from their native size to bytes. Any cross-architecture abstraction should be in terms of bytes, making these properties private. The hardware's num_closid is kept in the private structure to force the filesystem code to use a helper to access it. MPAM would return a single value for the system, regardless of the resource. Using the helper prevents this field from being confused with the version of num_closid that is being exposed to user-space (added in a later patch). After this split, filesystem code touching a 'hw' struct indicates where an abstraction is needed. Splitting this structure only moves types around, and should not lead to any change in behaviour. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-2-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/core.c | 257 +++++++++++++++++------------- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 14 +- arch/x86/kernel/cpu/resctrl/internal.h | 149 +++++------------ arch/x86/kernel/cpu/resctrl/monitor.c | 32 ++-- arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 4 +- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 68 ++++---- include/linux/resctrl.h | 110 +++++++++++++ 7 files changed, 362 insertions(+), 272 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 23001ae03e82..942d070aa92c 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -57,120 +57,134 @@ static void mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); -#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains) +#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains) -struct rdt_resource rdt_resources_all[] = { +struct rdt_hw_resource rdt_resources_all[] = { [RDT_RESOURCE_L3] = { - .rid = RDT_RESOURCE_L3, - .name = "L3", - .domains = domain_init(RDT_RESOURCE_L3), + .r_resctrl = { + .rid = RDT_RESOURCE_L3, + .name = "L3", + .cache_level = 3, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 1, + .cbm_idx_offset = 0, + }, + .domains = domain_init(RDT_RESOURCE_L3), + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, .msr_base = MSR_IA32_L3_CBM_BASE, .msr_update = cat_wrmsr, - .cache_level = 3, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 1, - .cbm_idx_offset = 0, - }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, }, [RDT_RESOURCE_L3DATA] = { - .rid = RDT_RESOURCE_L3DATA, - .name = "L3DATA", - .domains = domain_init(RDT_RESOURCE_L3DATA), + .r_resctrl = { + .rid = RDT_RESOURCE_L3DATA, + .name = "L3DATA", + .cache_level = 3, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 0, + }, + .domains = domain_init(RDT_RESOURCE_L3DATA), + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, .msr_base = MSR_IA32_L3_CBM_BASE, .msr_update = cat_wrmsr, - .cache_level = 3, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 0, - }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, }, [RDT_RESOURCE_L3CODE] = { - .rid = RDT_RESOURCE_L3CODE, - .name = "L3CODE", - .domains = domain_init(RDT_RESOURCE_L3CODE), + .r_resctrl = { + .rid = RDT_RESOURCE_L3CODE, + .name = "L3CODE", + .cache_level = 3, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 1, + }, + .domains = domain_init(RDT_RESOURCE_L3CODE), + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, .msr_base = MSR_IA32_L3_CBM_BASE, .msr_update = cat_wrmsr, - .cache_level = 3, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 1, - }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, }, [RDT_RESOURCE_L2] = { - .rid = RDT_RESOURCE_L2, - .name = "L2", - .domains = domain_init(RDT_RESOURCE_L2), + .r_resctrl = { + .rid = RDT_RESOURCE_L2, + .name = "L2", + .cache_level = 2, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 1, + .cbm_idx_offset = 0, + }, + .domains = domain_init(RDT_RESOURCE_L2), + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, .msr_base = MSR_IA32_L2_CBM_BASE, .msr_update = cat_wrmsr, - .cache_level = 2, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 1, - .cbm_idx_offset = 0, - }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, }, [RDT_RESOURCE_L2DATA] = { - .rid = RDT_RESOURCE_L2DATA, - .name = "L2DATA", - .domains = domain_init(RDT_RESOURCE_L2DATA), + .r_resctrl = { + .rid = RDT_RESOURCE_L2DATA, + .name = "L2DATA", + .cache_level = 2, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 0, + }, + .domains = domain_init(RDT_RESOURCE_L2DATA), + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, .msr_base = MSR_IA32_L2_CBM_BASE, .msr_update = cat_wrmsr, - .cache_level = 2, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 0, - }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, }, [RDT_RESOURCE_L2CODE] = { - .rid = RDT_RESOURCE_L2CODE, - .name = "L2CODE", - .domains = domain_init(RDT_RESOURCE_L2CODE), + .r_resctrl = { + .rid = RDT_RESOURCE_L2CODE, + .name = "L2CODE", + .cache_level = 2, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 1, + }, + .domains = domain_init(RDT_RESOURCE_L2CODE), + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, .msr_base = MSR_IA32_L2_CBM_BASE, .msr_update = cat_wrmsr, - .cache_level = 2, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 1, - }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, }, [RDT_RESOURCE_MBA] = { - .rid = RDT_RESOURCE_MBA, - .name = "MB", - .domains = domain_init(RDT_RESOURCE_MBA), - .cache_level = 3, - .parse_ctrlval = parse_bw, - .format_str = "%d=%*u", - .fflags = RFTYPE_RES_MB, + .r_resctrl = { + .rid = RDT_RESOURCE_MBA, + .name = "MB", + .cache_level = 3, + .domains = domain_init(RDT_RESOURCE_MBA), + .parse_ctrlval = parse_bw, + .format_str = "%d=%*u", + .fflags = RFTYPE_RES_MB, + }, }, }; @@ -199,7 +213,8 @@ static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid) */ static inline void cache_alloc_hsw_probe(void) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_L3]; + struct rdt_resource *r = &hw_res->r_resctrl; u32 l, h, max_cbm = BIT_MASK(20) - 1; if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0)) @@ -211,7 +226,7 @@ static inline void cache_alloc_hsw_probe(void) if (l != max_cbm) return; - r->num_closid = 4; + hw_res->num_closid = 4; r->default_ctrl = max_cbm; r->cache.cbm_len = 20; r->cache.shareable_bits = 0xc0000; @@ -225,7 +240,7 @@ static inline void cache_alloc_hsw_probe(void) bool is_mba_sc(struct rdt_resource *r) { if (!r) - return rdt_resources_all[RDT_RESOURCE_MBA].membw.mba_sc; + return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc; return r->membw.mba_sc; } @@ -253,12 +268,13 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r) static bool __get_mem_config_intel(struct rdt_resource *r) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_3_eax eax; union cpuid_0x10_x_edx edx; u32 ebx, ecx, max_delay; cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full); - r->num_closid = edx.split.cos_max + 1; + hw_res->num_closid = edx.split.cos_max + 1; max_delay = eax.split.max_delay + 1; r->default_ctrl = MAX_MBA_BW; r->membw.arch_needs_linear = true; @@ -287,12 +303,13 @@ static bool __get_mem_config_intel(struct rdt_resource *r) static bool __rdt_get_mem_config_amd(struct rdt_resource *r) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_3_eax eax; union cpuid_0x10_x_edx edx; u32 ebx, ecx; cpuid_count(0x80000020, 1, &eax.full, &ebx, &ecx, &edx.full); - r->num_closid = edx.split.cos_max + 1; + hw_res->num_closid = edx.split.cos_max + 1; r->default_ctrl = MAX_MBA_BW_AMD; /* AMD does not use delay */ @@ -317,12 +334,13 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r) static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_1_eax eax; union cpuid_0x10_x_edx edx; u32 ebx, ecx; cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full); - r->num_closid = edx.split.cos_max + 1; + hw_res->num_closid = edx.split.cos_max + 1; r->cache.cbm_len = eax.split.cbm_len + 1; r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; r->cache.shareable_bits = ebx & r->default_ctrl; @@ -333,10 +351,12 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) static void rdt_get_cdp_config(int level, int type) { - struct rdt_resource *r_l = &rdt_resources_all[level]; - struct rdt_resource *r = &rdt_resources_all[type]; + struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl; + struct rdt_hw_resource *hw_res_l = resctrl_to_arch_res(r_l); + struct rdt_resource *r = &rdt_resources_all[type].r_resctrl; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - r->num_closid = r_l->num_closid / 2; + hw_res->num_closid = hw_res_l->num_closid / 2; r->cache.cbm_len = r_l->cache.cbm_len; r->default_ctrl = r_l->default_ctrl; r->cache.shareable_bits = r_l->cache.shareable_bits; @@ -365,9 +385,10 @@ static void mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) { unsigned int i; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); for (i = m->low; i < m->high; i++) - wrmsrl(r->msr_base + i, d->ctrl_val[i]); + wrmsrl(hw_res->msr_base + i, d->ctrl_val[i]); } /* @@ -389,19 +410,21 @@ mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) { unsigned int i; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); /* Write the delay values for mba. */ for (i = m->low; i < m->high; i++) - wrmsrl(r->msr_base + i, delay_bw_map(d->ctrl_val[i], r)); + wrmsrl(hw_res->msr_base + i, delay_bw_map(d->ctrl_val[i], r)); } static void cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) { unsigned int i; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); for (i = m->low; i < m->high; i++) - wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]); + wrmsrl(hw_res->msr_base + cbm_idx(r, i), d->ctrl_val[i]); } struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) @@ -420,13 +443,14 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) void rdt_ctrl_update(void *arg) { struct msr_param *m = arg; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res); struct rdt_resource *r = m->res; int cpu = smp_processor_id(); struct rdt_domain *d; d = get_domain_from_cpu(cpu, r); if (d) { - r->msr_update(d, m, r); + hw_res->msr_update(d, m, r); return; } pr_warn_once("cpu %d not found in any domain for resource %s\n", @@ -468,6 +492,7 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); int i; /* @@ -476,7 +501,7 @@ void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) * For Memory Allocation: Set b/w requested to 100% * and the bandwidth in MBps to U32_MAX */ - for (i = 0; i < r->num_closid; i++, dc++, dm++) { + for (i = 0; i < hw_res->num_closid; i++, dc++, dm++) { *dc = r->default_ctrl; *dm = MBA_MAX_MBPS; } @@ -484,14 +509,15 @@ void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); struct msr_param m; u32 *dc, *dm; - dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL); + dc = kmalloc_array(hw_res->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL); if (!dc) return -ENOMEM; - dm = kmalloc_array(r->num_closid, sizeof(*d->mbps_val), GFP_KERNEL); + dm = kmalloc_array(hw_res->num_closid, sizeof(*d->mbps_val), GFP_KERNEL); if (!dm) { kfree(dc); return -ENOMEM; @@ -502,8 +528,8 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) setup_default_ctrlval(r, dc, dm); m.low = 0; - m.high = r->num_closid; - r->msr_update(d, &m, r); + m.high = hw_res->num_closid; + hw_res->msr_update(d, &m, r); return 0; } @@ -655,7 +681,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) return; } - if (r == &rdt_resources_all[RDT_RESOURCE_L3]) { + if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) { if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { cancel_delayed_work(&d->mbm_over); mbm_setup_overflow_handler(d, 0); @@ -827,19 +853,22 @@ static bool __init rdt_cpu_has(int flag) static __init bool get_mem_config(void) { + struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_MBA]; + if (!rdt_cpu_has(X86_FEATURE_MBA)) return false; if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - return __get_mem_config_intel(&rdt_resources_all[RDT_RESOURCE_MBA]); + return __get_mem_config_intel(&hw_res->r_resctrl); else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) - return __rdt_get_mem_config_amd(&rdt_resources_all[RDT_RESOURCE_MBA]); + return __rdt_get_mem_config_amd(&hw_res->r_resctrl); return false; } static __init bool get_rdt_alloc_resources(void) { + struct rdt_resource *r; bool ret = false; if (rdt_alloc_capable) @@ -849,14 +878,16 @@ static __init bool get_rdt_alloc_resources(void) return false; if (rdt_cpu_has(X86_FEATURE_CAT_L3)) { - rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]); + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + rdt_get_cache_alloc_cfg(1, r); if (rdt_cpu_has(X86_FEATURE_CDP_L3)) rdt_get_cdp_l3_config(); ret = true; } if (rdt_cpu_has(X86_FEATURE_CAT_L2)) { /* CPUID 0x10.2 fields are same format at 0x10.1 */ - rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]); + r = &rdt_resources_all[RDT_RESOURCE_L2].r_resctrl; + rdt_get_cache_alloc_cfg(2, r); if (rdt_cpu_has(X86_FEATURE_CDP_L2)) rdt_get_cdp_l2_config(); ret = true; @@ -870,6 +901,8 @@ static __init bool get_rdt_alloc_resources(void) static __init bool get_rdt_mon_resources(void) { + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID); if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) @@ -880,7 +913,7 @@ static __init bool get_rdt_mon_resources(void) if (!rdt_mon_features) return false; - return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]); + return !rdt_get_mon_l3_config(r); } static __init void __check_quirks_intel(void) @@ -918,9 +951,12 @@ static __init bool get_rdt_resources(void) static __init void rdt_init_res_defs_intel(void) { + struct rdt_hw_resource *hw_res; struct rdt_resource *r; for_each_rdt_resource(r) { + hw_res = resctrl_to_arch_res(r); + if (r->rid == RDT_RESOURCE_L3 || r->rid == RDT_RESOURCE_L3DATA || r->rid == RDT_RESOURCE_L3CODE || @@ -931,17 +967,20 @@ static __init void rdt_init_res_defs_intel(void) r->cache.arch_has_empty_bitmaps = false; r->cache.arch_has_per_cpu_cfg = false; } else if (r->rid == RDT_RESOURCE_MBA) { - r->msr_base = MSR_IA32_MBA_THRTL_BASE; - r->msr_update = mba_wrmsr_intel; + hw_res->msr_base = MSR_IA32_MBA_THRTL_BASE; + hw_res->msr_update = mba_wrmsr_intel; } } } static __init void rdt_init_res_defs_amd(void) { + struct rdt_hw_resource *hw_res; struct rdt_resource *r; for_each_rdt_resource(r) { + hw_res = resctrl_to_arch_res(r); + if (r->rid == RDT_RESOURCE_L3 || r->rid == RDT_RESOURCE_L3DATA || r->rid == RDT_RESOURCE_L3CODE || @@ -952,8 +991,8 @@ static __init void rdt_init_res_defs_amd(void) r->cache.arch_has_empty_bitmaps = true; r->cache.arch_has_per_cpu_cfg = true; } else if (r->rid == RDT_RESOURCE_MBA) { - r->msr_base = MSR_IA32_MBA_BW_BASE; - r->msr_update = mba_wrmsr_amd; + hw_res->msr_base = MSR_IA32_MBA_BW_BASE; + hw_res->msr_update = mba_wrmsr_amd; } } } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index c877642e8a14..3f0c33d5b658 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -284,10 +284,12 @@ done: static int rdtgroup_parse_resource(char *resname, char *tok, struct rdtgroup *rdtgrp) { + struct rdt_hw_resource *hw_res; struct rdt_resource *r; for_each_alloc_enabled_rdt_resource(r) { - if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid) + hw_res = resctrl_to_arch_res(r); + if (!strcmp(resname, r->name) && rdtgrp->closid < hw_res->num_closid) return parse_line(tok, r, rdtgrp); } rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname); @@ -394,6 +396,7 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { + struct rdt_hw_resource *hw_res; struct rdtgroup *rdtgrp; struct rdt_resource *r; int ret = 0; @@ -418,7 +421,8 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, } else { closid = rdtgrp->closid; for_each_alloc_enabled_rdt_resource(r) { - if (closid < r->num_closid) + hw_res = resctrl_to_arch_res(r); + if (closid < hw_res->num_closid) show_doms(s, r, closid); } } @@ -449,6 +453,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, int rdtgroup_mondata_show(struct seq_file *m, void *arg) { struct kernfs_open_file *of = m->private; + struct rdt_hw_resource *hw_res; u32 resid, evtid, domid; struct rdtgroup *rdtgrp; struct rdt_resource *r; @@ -468,7 +473,8 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) domid = md.u.domid; evtid = md.u.evtid; - r = &rdt_resources_all[resid]; + hw_res = &rdt_resources_all[resid]; + r = &hw_res->r_resctrl; d = rdt_find_domain(r, domid, NULL); if (IS_ERR_OR_NULL(d)) { ret = -ENOENT; @@ -482,7 +488,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) else if (rr.val & RMID_VAL_UNAVAIL) seq_puts(m, "Unavailable\n"); else - seq_printf(m, "%llu\n", rr.val * r->mon_scale); + seq_printf(m, "%llu\n", rr.val * hw_res->mon_scale); out: rdtgroup_kn_unlock(of->kn); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 6a5f60a37219..caf9248339d5 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_RESCTRL_INTERNAL_H #define _ASM_X86_RESCTRL_INTERNAL_H +#include #include #include #include @@ -353,67 +354,6 @@ struct msr_param { int high; }; -/** - * struct rdt_cache - Cache allocation related data - * @cbm_len: Length of the cache bit mask - * @min_cbm_bits: Minimum number of consecutive bits to be set - * @cbm_idx_mult: Multiplier of CBM index - * @cbm_idx_offset: Offset of CBM index. CBM index is computed by: - * closid * cbm_idx_multi + cbm_idx_offset - * in a cache bit mask - * @shareable_bits: Bitmask of shareable resource with other - * executing entities - * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. - * @arch_has_empty_bitmaps: True if the '0' bitmap is valid. - * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache - * level has CPU scope. - */ -struct rdt_cache { - unsigned int cbm_len; - unsigned int min_cbm_bits; - unsigned int cbm_idx_mult; - unsigned int cbm_idx_offset; - unsigned int shareable_bits; - bool arch_has_sparse_bitmaps; - bool arch_has_empty_bitmaps; - bool arch_has_per_cpu_cfg; -}; - -/** - * enum membw_throttle_mode - System's memory bandwidth throttling mode - * @THREAD_THROTTLE_UNDEFINED: Not relevant to the system - * @THREAD_THROTTLE_MAX: Memory bandwidth is throttled at the core - * always using smallest bandwidth percentage - * assigned to threads, aka "max throttling" - * @THREAD_THROTTLE_PER_THREAD: Memory bandwidth is throttled at the thread - */ -enum membw_throttle_mode { - THREAD_THROTTLE_UNDEFINED = 0, - THREAD_THROTTLE_MAX, - THREAD_THROTTLE_PER_THREAD, -}; - -/** - * struct rdt_membw - Memory bandwidth allocation related data - * @min_bw: Minimum memory bandwidth percentage user can request - * @bw_gran: Granularity at which the memory bandwidth is allocated - * @delay_linear: True if memory B/W delay is in linear scale - * @arch_needs_linear: True if we can't configure non-linear resources - * @throttle_mode: Bandwidth throttling mode when threads request - * different memory bandwidths - * @mba_sc: True if MBA software controller(mba_sc) is enabled - * @mb_map: Mapping of memory B/W percentage to memory B/W delay - */ -struct rdt_membw { - u32 min_bw; - u32 bw_gran; - u32 delay_linear; - bool arch_needs_linear; - enum membw_throttle_mode throttle_mode; - bool mba_sc; - u32 *mb_map; -}; - static inline bool is_llc_occupancy_enabled(void) { return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID)); @@ -446,58 +386,33 @@ struct rdt_parse_data { }; /** - * struct rdt_resource - attributes of an RDT resource - * @rid: The index of the resource - * @alloc_enabled: Is allocation enabled on this machine - * @mon_enabled: Is monitoring enabled for this feature - * @alloc_capable: Is allocation available on this machine - * @mon_capable: Is monitor feature available on this machine - * @name: Name to use in "schemata" file - * @num_closid: Number of CLOSIDs available - * @cache_level: Which cache level defines scope of this resource - * @default_ctrl: Specifies default cache cbm or memory B/W percent. + * struct rdt_hw_resource - arch private attributes of a resctrl resource + * @r_resctrl: Attributes of the resource used directly by resctrl. + * @num_closid: Maximum number of closid this hardware can support. * @msr_base: Base MSR address for CBMs * @msr_update: Function pointer to update QOS MSRs - * @data_width: Character width of data when displaying - * @domains: All domains for this resource - * @cache: Cache allocation related data - * @membw: If the component has bandwidth controls, their properties. - * @format_str: Per resource format string to show domain value - * @parse_ctrlval: Per resource function pointer to parse control values - * @evt_list: List of monitoring events - * @num_rmid: Number of RMIDs available * @mon_scale: cqm counter * mon_scale = occupancy in bytes * @mbm_width: Monitor width, to detect and correct for overflow. - * @fflags: flags to choose base and info files + * + * Members of this structure are either private to the architecture + * e.g. mbm_width, or accessed via helpers that provide abstraction. e.g. + * msr_update and msr_base. */ -struct rdt_resource { - int rid; - bool alloc_enabled; - bool mon_enabled; - bool alloc_capable; - bool mon_capable; - char *name; +struct rdt_hw_resource { + struct rdt_resource r_resctrl; int num_closid; - int cache_level; - u32 default_ctrl; unsigned int msr_base; void (*msr_update) (struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); - int data_width; - struct list_head domains; - struct rdt_cache cache; - struct rdt_membw membw; - const char *format_str; - int (*parse_ctrlval)(struct rdt_parse_data *data, - struct rdt_resource *r, - struct rdt_domain *d); - struct list_head evt_list; - int num_rmid; unsigned int mon_scale; unsigned int mbm_width; - unsigned long fflags; }; +static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r) +{ + return container_of(r, struct rdt_hw_resource, r_resctrl); +} + int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, struct rdt_domain *d); int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, @@ -505,7 +420,7 @@ int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, extern struct mutex rdtgroup_mutex; -extern struct rdt_resource rdt_resources_all[]; +extern struct rdt_hw_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); @@ -524,33 +439,41 @@ enum { RDT_NUM_RESOURCES, }; +static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res) +{ + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res); + + hw_res++; + return &hw_res->r_resctrl; +} + +/* + * To return the common struct rdt_resource, which is contained in struct + * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource. + */ #define for_each_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) + for (r = &rdt_resources_all[0].r_resctrl; \ + r <= &rdt_resources_all[RDT_NUM_RESOURCES - 1].r_resctrl; \ + r = resctrl_inc(r)) #define for_each_capable_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + for_each_rdt_resource(r) \ if (r->alloc_capable || r->mon_capable) #define for_each_alloc_capable_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + for_each_rdt_resource(r) \ if (r->alloc_capable) #define for_each_mon_capable_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + for_each_rdt_resource(r) \ if (r->mon_capable) #define for_each_alloc_enabled_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + for_each_rdt_resource(r) \ if (r->alloc_enabled) #define for_each_mon_enabled_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + for_each_rdt_resource(r) \ if (r->mon_enabled) /* CPUID.(EAX=10H, ECX=ResID=1).EAX */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f07c10b87a87..5daf5847ff4c 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -174,7 +174,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free) struct rdt_resource *r; u32 crmid = 1, nrmid; - r = &rdt_resources_all[RDT_RESOURCE_L3]; + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; /* * Skip RMID 0 and start from RMID 1 and check all the RMIDs that @@ -232,7 +232,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) int cpu; u64 val; - r = &rdt_resources_all[RDT_RESOURCE_L3]; + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; entry->busy = 0; cpu = get_cpu(); @@ -287,6 +287,7 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) static int __mon_event_count(u32 rmid, struct rmid_read *rr) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r); struct mbm_state *m; u64 chunks, tval; @@ -319,7 +320,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) return 0; } - chunks = mbm_overflow_count(m->prev_msr, tval, rr->r->mbm_width); + chunks = mbm_overflow_count(m->prev_msr, tval, hw_res->mbm_width); m->chunks += chunks; m->prev_msr = tval; @@ -334,7 +335,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) */ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r); struct mbm_state *m = &rr->d->mbm_local[rmid]; u64 tval, cur_bw, chunks; @@ -342,8 +343,8 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) return; - chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width); - cur_bw = (get_corrected_mbm_count(rmid, chunks) * r->mon_scale) >> 20; + chunks = mbm_overflow_count(m->prev_bw_msr, tval, hw_res->mbm_width); + cur_bw = (get_corrected_mbm_count(rmid, chunks) * hw_res->mon_scale) >> 20; if (m->delta_comp) m->delta_bw = abs(cur_bw - m->prev_bw); @@ -416,6 +417,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) { u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; + struct rdt_hw_resource *hw_r_mba; u32 cur_bw, delta_bw, user_bw; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; @@ -425,7 +427,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) if (!is_mbm_local_enabled()) return; - r_mba = &rdt_resources_all[RDT_RESOURCE_MBA]; + hw_r_mba = &rdt_resources_all[RDT_RESOURCE_MBA]; + r_mba = &hw_r_mba->r_resctrl; closid = rgrp->closid; rmid = rgrp->mon.rmid; pmbm_data = &dom_mbm->mbm_local[rmid]; @@ -474,7 +477,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) return; } - cur_msr = r_mba->msr_base + closid; + cur_msr = hw_r_mba->msr_base + closid; wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba)); dom_mba->ctrl_val[closid] = new_msr_val; @@ -538,7 +541,7 @@ void cqm_handle_limbo(struct work_struct *work) mutex_lock(&rdtgroup_mutex); - r = &rdt_resources_all[RDT_RESOURCE_L3]; + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; d = container_of(work, struct rdt_domain, cqm_limbo.work); __check_limbo(d, false); @@ -574,7 +577,7 @@ void mbm_handle_overflow(struct work_struct *work) if (!static_branch_likely(&rdt_mon_enable_key)) goto out_unlock; - r = &rdt_resources_all[RDT_RESOURCE_L3]; + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; d = container_of(work, struct rdt_domain, mbm_over.work); list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { @@ -671,15 +674,16 @@ static void l3_mon_evt_init(struct rdt_resource *r) int rdt_get_mon_l3_config(struct rdt_resource *r) { unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); unsigned int cl_size = boot_cpu_data.x86_cache_size; int ret; - r->mon_scale = boot_cpu_data.x86_cache_occ_scale; + hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale; r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1; - r->mbm_width = MBM_CNTR_WIDTH_BASE; + hw_res->mbm_width = MBM_CNTR_WIDTH_BASE; if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX) - r->mbm_width += mbm_offset; + hw_res->mbm_width += mbm_offset; else if (mbm_offset > MBM_CNTR_WIDTH_OFFSET_MAX) pr_warn("Ignoring impossible MBM counter offset\n"); @@ -693,7 +697,7 @@ int rdt_get_mon_l3_config(struct rdt_resource *r) resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid; /* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */ - resctrl_cqm_threshold /= r->mon_scale; + resctrl_cqm_threshold /= hw_res->mon_scale; ret = dom_data_init(r); if (ret) diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 2207916cae65..17868acd9b9c 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -688,8 +688,8 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) * resource, the portion of cache used by it should be made * unavailable to all future allocations from both resources. */ - if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled || - rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) { + if (rdt_resources_all[RDT_RESOURCE_L3DATA].r_resctrl.alloc_enabled || + rdt_resources_all[RDT_RESOURCE_L2DATA].r_resctrl.alloc_enabled) { rdt_last_cmd_puts("CDP enabled\n"); return -EINVAL; } diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 01fd30e7829d..d49a00754d98 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -100,12 +100,15 @@ int closids_supported(void) static void closid_init(void) { + struct rdt_hw_resource *hw_res; struct rdt_resource *r; int rdt_min_closid = 32; /* Compute rdt_min_closid across all resources */ - for_each_alloc_enabled_rdt_resource(r) - rdt_min_closid = min(rdt_min_closid, r->num_closid); + for_each_alloc_enabled_rdt_resource(r) { + hw_res = resctrl_to_arch_res(r); + rdt_min_closid = min(rdt_min_closid, hw_res->num_closid); + } closid_free_map = BIT_MASK(rdt_min_closid) - 1; @@ -843,8 +846,10 @@ static int rdt_num_closids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { struct rdt_resource *r = of->kn->parent->priv; + struct rdt_hw_resource *hw_res; - seq_printf(seq, "%d\n", r->num_closid); + hw_res = resctrl_to_arch_res(r); + seq_printf(seq, "%d\n", hw_res->num_closid); return 0; } @@ -1020,8 +1025,9 @@ static int max_threshold_occ_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { struct rdt_resource *r = of->kn->parent->priv; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - seq_printf(seq, "%u\n", resctrl_cqm_threshold * r->mon_scale); + seq_printf(seq, "%u\n", resctrl_cqm_threshold * hw_res->mon_scale); return 0; } @@ -1042,7 +1048,7 @@ static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_hw_resource *hw_res; unsigned int bytes; int ret; @@ -1053,7 +1059,8 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, if (bytes > (boot_cpu_data.x86_cache_size * 1024)) return -EINVAL; - resctrl_cqm_threshold = bytes / r->mon_scale; + hw_res = resctrl_to_arch_res(of->kn->parent->priv); + resctrl_cqm_threshold = bytes / hw_res->mon_scale; return nbytes; } @@ -1111,16 +1118,16 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, switch (r->rid) { case RDT_RESOURCE_L3DATA: - _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE]; + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE].r_resctrl; break; case RDT_RESOURCE_L3CODE: - _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3DATA]; + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3DATA].r_resctrl; break; case RDT_RESOURCE_L2DATA: - _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2CODE]; + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2CODE].r_resctrl; break; case RDT_RESOURCE_L2CODE: - _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2DATA]; + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2DATA].r_resctrl; break; default: ret = -ENOENT; @@ -1867,7 +1874,7 @@ static void l2_qos_cfg_update(void *arg) static inline bool is_mba_linear(void) { - return rdt_resources_all[RDT_RESOURCE_MBA].membw.delay_linear; + return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.delay_linear; } static int set_cache_qos_cfg(int level, bool enable) @@ -1888,7 +1895,7 @@ static int set_cache_qos_cfg(int level, bool enable) if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; - r_l = &rdt_resources_all[level]; + r_l = &rdt_resources_all[level].r_resctrl; list_for_each_entry(d, &r_l->domains, list) { if (r_l->cache.arch_has_per_cpu_cfg) /* Pick all the CPUs in the domain instance */ @@ -1917,10 +1924,10 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r) if (!r->alloc_capable) return; - if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA]) + if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA].r_resctrl) l2_qos_cfg_update(&r->alloc_enabled); - if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA]) + if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA].r_resctrl) l3_qos_cfg_update(&r->alloc_enabled); } @@ -1932,7 +1939,7 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r) */ static int set_mba_sc(bool mba_sc) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA]; + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; struct rdt_domain *d; if (!is_mbm_enabled() || !is_mba_linear() || @@ -1948,9 +1955,9 @@ static int set_mba_sc(bool mba_sc) static int cdp_enable(int level, int data_type, int code_type) { - struct rdt_resource *r_ldata = &rdt_resources_all[data_type]; - struct rdt_resource *r_lcode = &rdt_resources_all[code_type]; - struct rdt_resource *r_l = &rdt_resources_all[level]; + struct rdt_resource *r_ldata = &rdt_resources_all[data_type].r_resctrl; + struct rdt_resource *r_lcode = &rdt_resources_all[code_type].r_resctrl; + struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl; int ret; if (!r_l->alloc_capable || !r_ldata->alloc_capable || @@ -1980,13 +1987,13 @@ static int cdpl2_enable(void) static void cdp_disable(int level, int data_type, int code_type) { - struct rdt_resource *r = &rdt_resources_all[level]; + struct rdt_resource *r = &rdt_resources_all[level].r_resctrl; r->alloc_enabled = r->alloc_capable; - if (rdt_resources_all[data_type].alloc_enabled) { - rdt_resources_all[data_type].alloc_enabled = false; - rdt_resources_all[code_type].alloc_enabled = false; + if (rdt_resources_all[data_type].r_resctrl.alloc_enabled) { + rdt_resources_all[data_type].r_resctrl.alloc_enabled = false; + rdt_resources_all[code_type].r_resctrl.alloc_enabled = false; set_cache_qos_cfg(level, false); } } @@ -2003,9 +2010,9 @@ static void cdpl2_disable(void) static void cdp_disable_all(void) { - if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) + if (rdt_resources_all[RDT_RESOURCE_L3DATA].r_resctrl.alloc_enabled) cdpl3_disable(); - if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) + if (rdt_resources_all[RDT_RESOURCE_L2DATA].r_resctrl.alloc_enabled) cdpl2_disable(); } @@ -2153,7 +2160,7 @@ static int rdt_get_tree(struct fs_context *fc) static_branch_enable_cpuslocked(&rdt_enable_key); if (is_mbm_enabled()) { - r = &rdt_resources_all[RDT_RESOURCE_L3]; + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; list_for_each_entry(dom, &r->domains, list) mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL); } @@ -2257,6 +2264,7 @@ static int rdt_init_fs_context(struct fs_context *fc) static int reset_all_ctrls(struct rdt_resource *r) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); struct msr_param msr_param; cpumask_var_t cpu_mask; struct rdt_domain *d; @@ -2267,7 +2275,7 @@ static int reset_all_ctrls(struct rdt_resource *r) msr_param.res = r; msr_param.low = 0; - msr_param.high = r->num_closid; + msr_param.high = hw_res->num_closid; /* * Disable resource control for this resource by setting all @@ -2277,7 +2285,7 @@ static int reset_all_ctrls(struct rdt_resource *r) list_for_each_entry(d, &r->domains, list) { cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); - for (i = 0; i < r->num_closid; i++) + for (i = 0; i < hw_res->num_closid; i++) d->ctrl_val[i] = r->default_ctrl; } cpu = get_cpu(); @@ -3124,13 +3132,13 @@ out: static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { - if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) + if (rdt_resources_all[RDT_RESOURCE_L3DATA].r_resctrl.alloc_enabled) seq_puts(seq, ",cdp"); - if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) + if (rdt_resources_all[RDT_RESOURCE_L2DATA].r_resctrl.alloc_enabled) seq_puts(seq, ",cdpl2"); - if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA])) + if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl)) seq_puts(seq, ",mba_MBps"); return 0; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 9b05af9b3e28..5ccf36b7dbbf 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -2,6 +2,8 @@ #ifndef _RESCTRL_H #define _RESCTRL_H +#include +#include #include #ifdef CONFIG_PROC_CPU_RESCTRL @@ -13,4 +15,112 @@ int proc_resctrl_show(struct seq_file *m, #endif +struct rdt_domain; + +/** + * struct resctrl_cache - Cache allocation related data + * @cbm_len: Length of the cache bit mask + * @min_cbm_bits: Minimum number of consecutive bits to be set + * @cbm_idx_mult: Multiplier of CBM index + * @cbm_idx_offset: Offset of CBM index. CBM index is computed by: + * closid * cbm_idx_multi + cbm_idx_offset + * in a cache bit mask + * @shareable_bits: Bitmask of shareable resource with other + * executing entities + * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. + * @arch_has_empty_bitmaps: True if the '0' bitmap is valid. + * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache + * level has CPU scope. + */ +struct resctrl_cache { + unsigned int cbm_len; + unsigned int min_cbm_bits; + unsigned int cbm_idx_mult; // TODO remove this + unsigned int cbm_idx_offset; // TODO remove this + unsigned int shareable_bits; + bool arch_has_sparse_bitmaps; + bool arch_has_empty_bitmaps; + bool arch_has_per_cpu_cfg; +}; + +/** + * enum membw_throttle_mode - System's memory bandwidth throttling mode + * @THREAD_THROTTLE_UNDEFINED: Not relevant to the system + * @THREAD_THROTTLE_MAX: Memory bandwidth is throttled at the core + * always using smallest bandwidth percentage + * assigned to threads, aka "max throttling" + * @THREAD_THROTTLE_PER_THREAD: Memory bandwidth is throttled at the thread + */ +enum membw_throttle_mode { + THREAD_THROTTLE_UNDEFINED = 0, + THREAD_THROTTLE_MAX, + THREAD_THROTTLE_PER_THREAD, +}; + +/** + * struct resctrl_membw - Memory bandwidth allocation related data + * @min_bw: Minimum memory bandwidth percentage user can request + * @bw_gran: Granularity at which the memory bandwidth is allocated + * @delay_linear: True if memory B/W delay is in linear scale + * @arch_needs_linear: True if we can't configure non-linear resources + * @throttle_mode: Bandwidth throttling mode when threads request + * different memory bandwidths + * @mba_sc: True if MBA software controller(mba_sc) is enabled + * @mb_map: Mapping of memory B/W percentage to memory B/W delay + */ +struct resctrl_membw { + u32 min_bw; + u32 bw_gran; + u32 delay_linear; + bool arch_needs_linear; + enum membw_throttle_mode throttle_mode; + bool mba_sc; + u32 *mb_map; +}; + +struct rdt_parse_data; + +/** + * struct rdt_resource - attributes of a resctrl resource + * @rid: The index of the resource + * @alloc_enabled: Is allocation enabled on this machine + * @mon_enabled: Is monitoring enabled for this feature + * @alloc_capable: Is allocation available on this machine + * @mon_capable: Is monitor feature available on this machine + * @num_rmid: Number of RMIDs available + * @cache_level: Which cache level defines scope of this resource + * @cache: Cache allocation related data + * @membw: If the component has bandwidth controls, their properties. + * @domains: All domains for this resource + * @name: Name to use in "schemata" file. + * @data_width: Character width of data when displaying + * @default_ctrl: Specifies default cache cbm or memory B/W percent. + * @format_str: Per resource format string to show domain value + * @parse_ctrlval: Per resource function pointer to parse control values + * @evt_list: List of monitoring events + * @fflags: flags to choose base and info files + */ +struct rdt_resource { + int rid; + bool alloc_enabled; + bool mon_enabled; + bool alloc_capable; + bool mon_capable; + int num_rmid; + int cache_level; + struct resctrl_cache cache; + struct resctrl_membw membw; + struct list_head domains; + char *name; + int data_width; + u32 default_ctrl; + const char *format_str; + int (*parse_ctrlval)(struct rdt_parse_data *data, + struct rdt_resource *r, + struct rdt_domain *d); + struct list_head evt_list; + unsigned long fflags; + +}; + #endif /* _RESCTRL_H */ -- cgit v1.2.3 From 792e0f6f789bda5e31b1dbcfcc84068da36a79b1 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:15 +0000 Subject: x86/resctrl: Split struct rdt_domain resctrl is the defacto Linux ABI for SoC resource partitioning features. To support it on another architecture, it needs to be abstracted from the features provided by Intel RDT and AMD PQoS, and moved to /fs/. struct rdt_domain contains a mix of architecture private details and properties of the filesystem interface user-space uses. Continue by splitting struct rdt_domain, into an architecture private 'hw' struct, which contains the common resctrl structure that would be used by any architecture. The hardware values in ctrl_val and mbps_val need to be accessed via helpers to allow another architecture to convert these into a different format if necessary. After this split, filesystem code paths touching a 'hw' struct indicates where an abstraction is needed. Splitting this structure only moves types around, and should not lead to any change in behaviour. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-3-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/core.c | 32 ++++++++++++++--------- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 10 ++++--- arch/x86/kernel/cpu/resctrl/internal.h | 43 +++++++++---------------------- arch/x86/kernel/cpu/resctrl/monitor.c | 8 +++--- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 29 ++++++++++++++------- include/linux/resctrl.h | 32 ++++++++++++++++++++++- 6 files changed, 94 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 942d070aa92c..10fbbc3cf40a 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -385,10 +385,11 @@ static void mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) { unsigned int i; + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); for (i = m->low; i < m->high; i++) - wrmsrl(hw_res->msr_base + i, d->ctrl_val[i]); + wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]); } /* @@ -410,21 +411,23 @@ mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) { unsigned int i; + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); /* Write the delay values for mba. */ for (i = m->low; i < m->high; i++) - wrmsrl(hw_res->msr_base + i, delay_bw_map(d->ctrl_val[i], r)); + wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], r)); } static void cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) { unsigned int i; + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); for (i = m->low; i < m->high; i++) - wrmsrl(hw_res->msr_base + cbm_idx(r, i), d->ctrl_val[i]); + wrmsrl(hw_res->msr_base + cbm_idx(r, i), hw_dom->ctrl_val[i]); } struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) @@ -510,21 +513,22 @@ void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct msr_param m; u32 *dc, *dm; - dc = kmalloc_array(hw_res->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL); + dc = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->ctrl_val), GFP_KERNEL); if (!dc) return -ENOMEM; - dm = kmalloc_array(hw_res->num_closid, sizeof(*d->mbps_val), GFP_KERNEL); + dm = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->mbps_val), GFP_KERNEL); if (!dm) { kfree(dc); return -ENOMEM; } - d->ctrl_val = dc; - d->mbps_val = dm; + hw_dom->ctrl_val = dc; + hw_dom->mbps_val = dm; setup_default_ctrlval(r, dc, dm); m.low = 0; @@ -586,6 +590,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) { int id = get_cpu_cacheinfo_id(cpu, r->cache_level); struct list_head *add_pos = NULL; + struct rdt_hw_domain *hw_dom; struct rdt_domain *d; d = rdt_find_domain(r, id, &add_pos); @@ -601,10 +606,11 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) return; } - d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu)); - if (!d) + hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu)); + if (!hw_dom) return; + d = &hw_dom->d_resctrl; d->id = id; cpumask_set_cpu(cpu, &d->cpu_mask); @@ -633,6 +639,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) static void domain_remove_cpu(int cpu, struct rdt_resource *r) { int id = get_cpu_cacheinfo_id(cpu, r->cache_level); + struct rdt_hw_domain *hw_dom; struct rdt_domain *d; d = rdt_find_domain(r, id, NULL); @@ -640,6 +647,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) pr_warn("Couldn't find cache id for CPU %d\n", cpu); return; } + hw_dom = resctrl_to_arch_dom(d); cpumask_clear_cpu(cpu, &d->cpu_mask); if (cpumask_empty(&d->cpu_mask)) { @@ -672,12 +680,12 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) if (d->plr) d->plr->d = NULL; - kfree(d->ctrl_val); - kfree(d->mbps_val); + kfree(hw_dom->ctrl_val); + kfree(hw_dom->mbps_val); bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); kfree(d->mbm_local); - kfree(d); + kfree(hw_dom); return; } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 3f0c33d5b658..08eef539cb6c 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -238,6 +238,7 @@ next: int update_domains(struct rdt_resource *r, int closid) { + struct rdt_hw_domain *hw_dom; struct msr_param msr_param; cpumask_var_t cpu_mask; struct rdt_domain *d; @@ -254,7 +255,8 @@ int update_domains(struct rdt_resource *r, int closid) mba_sc = is_mba_sc(r); list_for_each_entry(d, &r->domains, list) { - dc = !mba_sc ? d->ctrl_val : d->mbps_val; + hw_dom = resctrl_to_arch_dom(d); + dc = !mba_sc ? hw_dom->ctrl_val : hw_dom->mbps_val; if (d->have_new_ctrl && d->new_ctrl != dc[closid]) { cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); dc[closid] = d->new_ctrl; @@ -375,17 +377,19 @@ out: static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) { + struct rdt_hw_domain *hw_dom; struct rdt_domain *dom; bool sep = false; u32 ctrl_val; seq_printf(s, "%*s:", max_name_width, r->name); list_for_each_entry(dom, &r->domains, list) { + hw_dom = resctrl_to_arch_dom(dom); if (sep) seq_puts(s, ";"); - ctrl_val = (!is_mba_sc(r) ? dom->ctrl_val[closid] : - dom->mbps_val[closid]); + ctrl_val = (!is_mba_sc(r) ? hw_dom->ctrl_val[closid] : + hw_dom->mbps_val[closid]); seq_printf(s, r->format_str, dom->id, max_data_width, ctrl_val); sep = true; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index caf9248339d5..02c85c795113 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -304,44 +304,25 @@ struct mbm_state { }; /** - * struct rdt_domain - group of cpus sharing an RDT resource - * @list: all instances of this resource - * @id: unique id for this instance - * @cpu_mask: which cpus share this resource - * @rmid_busy_llc: - * bitmap of which limbo RMIDs are above threshold - * @mbm_total: saved state for MBM total bandwidth - * @mbm_local: saved state for MBM local bandwidth - * @mbm_over: worker to periodically read MBM h/w counters - * @cqm_limbo: worker to periodically read CQM h/w counters - * @mbm_work_cpu: - * worker cpu for MBM h/w counters - * @cqm_work_cpu: - * worker cpu for CQM h/w counters + * struct rdt_hw_domain - Arch private attributes of a set of CPUs that share + * a resource + * @d_resctrl: Properties exposed to the resctrl file system * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps - * @new_ctrl: new ctrl value to be loaded - * @have_new_ctrl: did user provide new_ctrl for this domain - * @plr: pseudo-locked region (if any) associated with domain + * + * Members of this structure are accessed via helpers that provide abstraction. */ -struct rdt_domain { - struct list_head list; - int id; - struct cpumask cpu_mask; - unsigned long *rmid_busy_llc; - struct mbm_state *mbm_total; - struct mbm_state *mbm_local; - struct delayed_work mbm_over; - struct delayed_work cqm_limbo; - int mbm_work_cpu; - int cqm_work_cpu; +struct rdt_hw_domain { + struct rdt_domain d_resctrl; u32 *ctrl_val; u32 *mbps_val; - u32 new_ctrl; - bool have_new_ctrl; - struct pseudo_lock_region *plr; }; +static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r) +{ + return container_of(r, struct rdt_hw_domain, d_resctrl); +} + /** * struct msr_param - set a range of MSRs from a domain * @res: The resource to use diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 5daf5847ff4c..26a094870c16 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -418,6 +418,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; struct rdt_hw_resource *hw_r_mba; + struct rdt_hw_domain *hw_dom_mba; u32 cur_bw, delta_bw, user_bw; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; @@ -438,11 +439,12 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) pr_warn_once("Failure to get domain for MBA update\n"); return; } + hw_dom_mba = resctrl_to_arch_dom(dom_mba); cur_bw = pmbm_data->prev_bw; - user_bw = dom_mba->mbps_val[closid]; + user_bw = hw_dom_mba->mbps_val[closid]; delta_bw = pmbm_data->delta_bw; - cur_msr_val = dom_mba->ctrl_val[closid]; + cur_msr_val = hw_dom_mba->ctrl_val[closid]; /* * For Ctrl groups read data from child monitor groups. @@ -479,7 +481,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) cur_msr = hw_r_mba->msr_base + closid; wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba)); - dom_mba->ctrl_val[closid] = new_msr_val; + hw_dom_mba->ctrl_val[closid] = new_msr_val; /* * Delta values are updated dynamically package wise for each diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index d49a00754d98..d190a21845ce 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -915,7 +915,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, list_for_each_entry(dom, &r->domains, list) { if (sep) seq_putc(seq, ';'); - ctrl = dom->ctrl_val; + ctrl = resctrl_to_arch_dom(dom)->ctrl_val; sw_shareable = 0; exclusive = 0; seq_printf(seq, "%d=", dom->id); @@ -1193,7 +1193,7 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d } /* Check for overlap with other resource groups */ - ctrl = d->ctrl_val; + ctrl = resctrl_to_arch_dom(d)->ctrl_val; for (i = 0; i < closids_supported(); i++, ctrl++) { ctrl_b = *ctrl; mode = rdtgroup_mode_by_closid(i); @@ -1262,6 +1262,7 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, */ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) { + struct rdt_hw_domain *hw_dom; int closid = rdtgrp->closid; struct rdt_resource *r; bool has_cache = false; @@ -1272,7 +1273,8 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) continue; has_cache = true; list_for_each_entry(d, &r->domains, list) { - if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], + hw_dom = resctrl_to_arch_dom(d); + if (rdtgroup_cbm_overlaps(r, d, hw_dom->ctrl_val[closid], rdtgrp->closid, false)) { rdt_last_cmd_puts("Schemata overlaps\n"); return false; @@ -1404,6 +1406,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, static int rdtgroup_size_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { + struct rdt_hw_domain *hw_dom; struct rdtgroup *rdtgrp; struct rdt_resource *r; struct rdt_domain *d; @@ -1438,14 +1441,15 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, sep = false; seq_printf(s, "%*s:", max_name_width, r->name); list_for_each_entry(d, &r->domains, list) { + hw_dom = resctrl_to_arch_dom(d); if (sep) seq_putc(s, ';'); if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { size = 0; } else { ctrl = (!is_mba_sc(r) ? - d->ctrl_val[rdtgrp->closid] : - d->mbps_val[rdtgrp->closid]); + hw_dom->ctrl_val[rdtgrp->closid] : + hw_dom->mbps_val[rdtgrp->closid]); if (r->rid == RDT_RESOURCE_MBA) size = ctrl; else @@ -1940,6 +1944,7 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r) static int set_mba_sc(bool mba_sc) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; + struct rdt_hw_domain *hw_dom; struct rdt_domain *d; if (!is_mbm_enabled() || !is_mba_linear() || @@ -1947,8 +1952,10 @@ static int set_mba_sc(bool mba_sc) return -EINVAL; r->membw.mba_sc = mba_sc; - list_for_each_entry(d, &r->domains, list) - setup_default_ctrlval(r, d->ctrl_val, d->mbps_val); + list_for_each_entry(d, &r->domains, list) { + hw_dom = resctrl_to_arch_dom(d); + setup_default_ctrlval(r, hw_dom->ctrl_val, hw_dom->mbps_val); + } return 0; } @@ -2265,6 +2272,7 @@ static int rdt_init_fs_context(struct fs_context *fc) static int reset_all_ctrls(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + struct rdt_hw_domain *hw_dom; struct msr_param msr_param; cpumask_var_t cpu_mask; struct rdt_domain *d; @@ -2283,10 +2291,11 @@ static int reset_all_ctrls(struct rdt_resource *r) * from each domain to update the MSRs below. */ list_for_each_entry(d, &r->domains, list) { + hw_dom = resctrl_to_arch_dom(d); cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); for (i = 0; i < hw_res->num_closid; i++) - d->ctrl_val[i] = r->default_ctrl; + hw_dom->ctrl_val[i] = r->default_ctrl; } cpu = get_cpu(); /* Update CBM on this cpu if it's in cpu_mask. */ @@ -2665,7 +2674,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r, d->have_new_ctrl = false; d->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; - ctrl = d->ctrl_val; + ctrl = resctrl_to_arch_dom(d)->ctrl_val; for (i = 0; i < closids_supported(); i++, ctrl++) { if (closid_allocated(i) && i != closid) { mode = rdtgroup_mode_by_closid(i); @@ -2682,7 +2691,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r, * with an exclusive group. */ if (d_cdp) - peer_ctl = d_cdp->ctrl_val[i]; + peer_ctl = resctrl_to_arch_dom(d_cdp)->ctrl_val[i]; else peer_ctl = 0; used_b |= *ctrl | peer_ctl; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 5ccf36b7dbbf..a4c89dafd7fa 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -15,7 +15,37 @@ int proc_resctrl_show(struct seq_file *m, #endif -struct rdt_domain; +/** + * struct rdt_domain - group of CPUs sharing a resctrl resource + * @list: all instances of this resource + * @id: unique id for this instance + * @cpu_mask: which CPUs share this resource + * @new_ctrl: new ctrl value to be loaded + * @have_new_ctrl: did user provide new_ctrl for this domain + * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold + * @mbm_total: saved state for MBM total bandwidth + * @mbm_local: saved state for MBM local bandwidth + * @mbm_over: worker to periodically read MBM h/w counters + * @cqm_limbo: worker to periodically read CQM h/w counters + * @mbm_work_cpu: worker CPU for MBM h/w counters + * @cqm_work_cpu: worker CPU for CQM h/w counters + * @plr: pseudo-locked region (if any) associated with domain + */ +struct rdt_domain { + struct list_head list; + int id; + struct cpumask cpu_mask; + u32 new_ctrl; + bool have_new_ctrl; + unsigned long *rmid_busy_llc; + struct mbm_state *mbm_total; + struct mbm_state *mbm_local; + struct delayed_work mbm_over; + struct delayed_work cqm_limbo; + int mbm_work_cpu; + int cqm_work_cpu; + struct pseudo_lock_region *plr; +}; /** * struct resctrl_cache - Cache allocation related data -- cgit v1.2.3 From cdb9ebc9178461c27d618bb1238e851da17271de Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:16 +0000 Subject: x86/resctrl: Add a separate schema list for resctrl Resctrl exposes schemata to user-space, which allow the control values to be specified for a group of tasks. User-visible properties of the interface, (such as the schemata names and how the values are parsed) are rooted in a struct provided by the architecture code. (struct rdt_hw_resource). Once a second architecture uses resctrl, this would allow user-visible properties to diverge between architectures. These properties should come from the resctrl code that will be common to all architectures. Resctrl has no per-schema structure, only struct rdt_{hw_,}resource. Create a struct resctrl_schema to hold the rdt_resource. Before a second architecture can be supported, this structure will also need to hold the schema name visible to user-space and the type of configuration values for resctrl. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-4-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/internal.h | 1 + arch/x86/kernel/cpu/resctrl/rdtgroup.c | 43 +++++++++++++++++++++++++++++++++- include/linux/resctrl.h | 11 +++++++++ 3 files changed, 54 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 02c85c795113..2cc4b37bc128 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -110,6 +110,7 @@ extern unsigned int resctrl_cqm_threshold; extern bool rdt_alloc_capable; extern bool rdt_mon_capable; extern unsigned int rdt_mon_features; +extern struct list_head resctrl_schema_all; enum rdt_group_type { RDTCTRL_GROUP = 0, diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index d190a21845ce..3e0b6aa94571 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -39,6 +39,9 @@ static struct kernfs_root *rdt_root; struct rdtgroup rdtgroup_default; LIST_HEAD(rdt_all_groups); +/* list of entries for the schemata file */ +LIST_HEAD(resctrl_schema_all); + /* Kernel fs node for "info" directory under root */ static struct kernfs_node *kn_info; @@ -2109,6 +2112,35 @@ static int rdt_enable_ctx(struct rdt_fs_context *ctx) return ret; } +static int schemata_list_create(void) +{ + struct resctrl_schema *s; + struct rdt_resource *r; + + for_each_alloc_enabled_rdt_resource(r) { + s = kzalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + s->res = r; + + INIT_LIST_HEAD(&s->list); + list_add(&s->list, &resctrl_schema_all); + } + + return 0; +} + +static void schemata_list_destroy(void) +{ + struct resctrl_schema *s, *tmp; + + list_for_each_entry_safe(s, tmp, &resctrl_schema_all, list) { + list_del(&s->list); + kfree(s); + } +} + static int rdt_get_tree(struct fs_context *fc) { struct rdt_fs_context *ctx = rdt_fc2context(fc); @@ -2130,11 +2162,17 @@ static int rdt_get_tree(struct fs_context *fc) if (ret < 0) goto out_cdp; + ret = schemata_list_create(); + if (ret) { + schemata_list_destroy(); + goto out_mba; + } + closid_init(); ret = rdtgroup_create_info_dir(rdtgroup_default.kn); if (ret < 0) - goto out_mba; + goto out_schemata_free; if (rdt_mon_capable) { ret = mongroup_create_dir(rdtgroup_default.kn, @@ -2184,6 +2222,8 @@ out_mongrp: kernfs_remove(kn_mongrp); out_info: kernfs_remove(kn_info); +out_schemata_free: + schemata_list_destroy(); out_mba: if (ctx->enable_mba_mbps) set_mba_sc(false); @@ -2425,6 +2465,7 @@ static void rdt_kill_sb(struct super_block *sb) rmdir_all_sub(); rdt_pseudo_lock_release(); rdtgroup_default.mode = RDT_MODE_SHAREABLE; + schemata_list_destroy(); static_branch_disable_cpuslocked(&rdt_alloc_enable_key); static_branch_disable_cpuslocked(&rdt_mon_enable_key); static_branch_disable_cpuslocked(&rdt_enable_key); diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index a4c89dafd7fa..5a21d483da6a 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -153,4 +153,15 @@ struct rdt_resource { }; +/** + * struct resctrl_schema - configuration abilities of a resource presented to + * user-space + * @list: Member of resctrl_schema_all. + * @res: The resource structure exported by the architecture to describe + * the hardware that is configured by this schema. + */ +struct resctrl_schema { + struct list_head list; + struct rdt_resource *res; +}; #endif /* _RESCTRL_H */ -- cgit v1.2.3 From c8d182bd387a09a8b95303c8086238e8bf61fcfc Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 15 Jul 2021 16:00:26 +0800 Subject: vdpa: Add documentation for vdpa_alloc_device() macro The return value of vdpa_alloc_device() macro is not very clear, so that most of callers did the wrong check. Let's add some comments to better document it. Signed-off-by: Xie Yongji Link: https://lore.kernel.org/r/20210715080026.242-4-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Reviewed-by: Stefano Garzarella --- include/linux/vdpa.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 3357ac98878d..8cfe49d201dd 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -277,6 +277,17 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, size_t size, const char *name); +/** + * vdpa_alloc_device - allocate and initilaize a vDPA device + * + * @dev_struct: the type of the parent structure + * @member: the name of struct vdpa_device within the @dev_struct + * @parent: the parent device + * @config: the bus operations that is supported by this device + * @name: name of the vdpa device + * + * Return allocated data structure or ERR_PTR upon error + */ #define vdpa_alloc_device(dev_struct, member, parent, config, name) \ container_of(__vdpa_alloc_device( \ parent, config, \ -- cgit v1.2.3 From ea2f6af16532511eb1cd8eb62845c37861f24ce8 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 10 Aug 2021 12:25:05 -0400 Subject: vringh: pull in spinlock header we use a spinlock now pull in the correct header to make vring.h self sufficient. Signed-off-by: Michael S. Tsirkin --- include/linux/vringh.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 84db7b8f912f..212892cf9822 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -14,6 +14,7 @@ #include #include #include +#include #if IS_REACHABLE(CONFIG_VHOST_IOTLB) #include #include -- cgit v1.2.3 From 879753c816dbbdb2a9a395aa4448d29feee92d1a Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 11 Aug 2021 08:37:59 +0300 Subject: vdpa/mlx5: Fix queue type selection logic get_queue_type() comments that splict virtqueue is preferred, however, the actual logic preferred packed virtqueues. Since firmware has not supported packed virtqueues we ended up using split virtqueues as was desired. Since we do not advertise support for packed virtqueues, we add a check to verify split virtqueues are indeed supported. Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices") Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20210811053759.66752-1-elic@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/mlx5/net/mlx5_vnet.c | 14 ++++++++++---- include/linux/mlx5/mlx5_ifc_vdpa.h | 10 ++++++---- 2 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 2a31467f7ac5..b1230fa2f5d1 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -753,12 +753,12 @@ static int get_queue_type(struct mlx5_vdpa_net *ndev) type_mask = MLX5_CAP_DEV_VDPA_EMULATION(ndev->mvdev.mdev, virtio_queue_type); /* prefer split queue */ - if (type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED) - return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED; + if (type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT) + return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT; - WARN_ON(!(type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT)); + WARN_ON(!(type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED)); - return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT; + return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED; } static bool vq_is_tx(u16 idx) @@ -2030,6 +2030,12 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) return -ENOSPC; mdev = mgtdev->madev->mdev; + if (!(MLX5_CAP_DEV_VDPA_EMULATION(mdev, virtio_queue_type) & + MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT)) { + dev_warn(mdev->device, "missing support for split virtqueues\n"); + return -EOPNOTSUPP; + } + /* we save one virtqueue for control virtqueue should we require it */ max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues); max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS); diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h index 98b56b75c625..1a9c9d94cb59 100644 --- a/include/linux/mlx5/mlx5_ifc_vdpa.h +++ b/include/linux/mlx5/mlx5_ifc_vdpa.h @@ -11,13 +11,15 @@ enum { }; enum { - MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT = 0x1, // do I check this caps? - MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED = 0x2, + MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT = 0, + MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED = 1, }; enum { - MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT = 0, - MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED = 1, + MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT = + BIT(MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT), + MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED = + BIT(MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED), }; struct mlx5_ifc_virtio_q_bits { -- cgit v1.2.3 From 208ab16847c562c0d53a0266b6628ef6cb5ab5c2 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:18 +0000 Subject: x86/resctrl: Label the resources with their configuration type The names of resources are used for the schema name presented to user-space. The name used is rooted in a structure provided by the architecture code because the names are different when CDP is enabled. x86 implements this by swapping between two sets of resource structures based on their alloc_enabled flag. The type of configuration in-use is encoded in the name (and cbm_idx_offset). Once the CDP behaviour is moved into the parts of resctrl that will move to /fs/, there will be two struct resctrl_schema for one struct rdt_resource. The schema describes the type of configuration being applied to the resource. The name of the schema should be generated by resctrl, base on the type of configuration. To do this struct resctrl_schema needs to store the type of configuration in use for a schema. Create an enum resctrl_conf_type describing the options, and add it to struct resctrl_schema. The underlying resources are still separate, as cbm_idx_offset is still in use. Temporarily label all the entries in rdt_resources_all[] and copy that value to struct resctrl_schema. Copying the value ensures there is no mismatch while the filesystem parts of resctrl are modified to use the schema. Once the resources are merged, the filesystem code can assign this value based on the schema being created. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-6-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/core.c | 7 +++++++ arch/x86/kernel/cpu/resctrl/internal.h | 2 ++ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 1 + include/linux/resctrl.h | 14 ++++++++++++++ 4 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 10fbbc3cf40a..c5b5c7227837 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -62,6 +62,7 @@ mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_hw_resource rdt_resources_all[] = { [RDT_RESOURCE_L3] = { + .conf_type = CDP_NONE, .r_resctrl = { .rid = RDT_RESOURCE_L3, .name = "L3", @@ -81,6 +82,7 @@ struct rdt_hw_resource rdt_resources_all[] = { }, [RDT_RESOURCE_L3DATA] = { + .conf_type = CDP_DATA, .r_resctrl = { .rid = RDT_RESOURCE_L3DATA, .name = "L3DATA", @@ -100,6 +102,7 @@ struct rdt_hw_resource rdt_resources_all[] = { }, [RDT_RESOURCE_L3CODE] = { + .conf_type = CDP_CODE, .r_resctrl = { .rid = RDT_RESOURCE_L3CODE, .name = "L3CODE", @@ -119,6 +122,7 @@ struct rdt_hw_resource rdt_resources_all[] = { }, [RDT_RESOURCE_L2] = { + .conf_type = CDP_NONE, .r_resctrl = { .rid = RDT_RESOURCE_L2, .name = "L2", @@ -138,6 +142,7 @@ struct rdt_hw_resource rdt_resources_all[] = { }, [RDT_RESOURCE_L2DATA] = { + .conf_type = CDP_DATA, .r_resctrl = { .rid = RDT_RESOURCE_L2DATA, .name = "L2DATA", @@ -157,6 +162,7 @@ struct rdt_hw_resource rdt_resources_all[] = { }, [RDT_RESOURCE_L2CODE] = { + .conf_type = CDP_CODE, .r_resctrl = { .rid = RDT_RESOURCE_L2CODE, .name = "L2CODE", @@ -176,6 +182,7 @@ struct rdt_hw_resource rdt_resources_all[] = { }, [RDT_RESOURCE_MBA] = { + .conf_type = CDP_NONE, .r_resctrl = { .rid = RDT_RESOURCE_MBA, .name = "MB", diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 2cc4b37bc128..5e4a0a8d743c 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -369,6 +369,7 @@ struct rdt_parse_data { /** * struct rdt_hw_resource - arch private attributes of a resctrl resource + * @conf_type: The type that should be used when configuring. temporary * @r_resctrl: Attributes of the resource used directly by resctrl. * @num_closid: Maximum number of closid this hardware can support. * @msr_base: Base MSR address for CBMs @@ -381,6 +382,7 @@ struct rdt_parse_data { * msr_update and msr_base. */ struct rdt_hw_resource { + enum resctrl_conf_type conf_type; struct rdt_resource r_resctrl; int num_closid; unsigned int msr_base; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 1fc40dbce85d..d7fd0712e76c 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2135,6 +2135,7 @@ static int schemata_list_create(void) return -ENOMEM; s->res = r; + s->conf_type = resctrl_to_arch_res(r)->conf_type; INIT_LIST_HEAD(&s->list); list_add(&s->list, &resctrl_schema_all); diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 5a21d483da6a..095ed48168d7 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -15,6 +15,18 @@ int proc_resctrl_show(struct seq_file *m, #endif +/** + * enum resctrl_conf_type - The type of configuration. + * @CDP_NONE: No prioritisation, both code and data are controlled or monitored. + * @CDP_CODE: Configuration applies to instruction fetches. + * @CDP_DATA: Configuration applies to reads and writes. + */ +enum resctrl_conf_type { + CDP_NONE, + CDP_CODE, + CDP_DATA, +}; + /** * struct rdt_domain - group of CPUs sharing a resctrl resource * @list: all instances of this resource @@ -157,11 +169,13 @@ struct rdt_resource { * struct resctrl_schema - configuration abilities of a resource presented to * user-space * @list: Member of resctrl_schema_all. + * @conf_type: Whether this schema is specific to code/data. * @res: The resource structure exported by the architecture to describe * the hardware that is configured by this schema. */ struct resctrl_schema { struct list_head list; + enum resctrl_conf_type conf_type; struct rdt_resource *res; }; #endif /* _RESCTRL_H */ -- cgit v1.2.3 From ec44610fe2b86daef70f3f53f47d2a2542d7094f Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Tue, 10 Aug 2021 18:12:19 +0300 Subject: fsnotify: count all objects with attached connectors Rename s_fsnotify_inode_refs to s_fsnotify_connectors and count all objects with attached connectors, not only inodes with attached connectors. This will be used to optimize fsnotify() calls on sb without any type of marks. Link: https://lore.kernel.org/r/20210810151220.285179-4-amir73il@gmail.com Signed-off-by: Amir Goldstein Reviewed-by: Matthew Bobrowski Signed-off-by: Jan Kara --- fs/notify/fsnotify.c | 6 +++--- fs/notify/fsnotify.h | 15 +++++++++++++++ fs/notify/mark.c | 24 +++++++++++++++++++++--- include/linux/fs.h | 7 +++++-- 4 files changed, 44 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 30d422b8c0fc..963e6ce75b96 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -87,15 +87,15 @@ static void fsnotify_unmount_inodes(struct super_block *sb) if (iput_inode) iput(iput_inode); - /* Wait for outstanding inode references from connectors */ - wait_var_event(&sb->s_fsnotify_inode_refs, - !atomic_long_read(&sb->s_fsnotify_inode_refs)); } void fsnotify_sb_delete(struct super_block *sb) { fsnotify_unmount_inodes(sb); fsnotify_clear_marks_by_sb(sb); + /* Wait for outstanding object references from connectors */ + wait_var_event(&sb->s_fsnotify_connectors, + !atomic_long_read(&sb->s_fsnotify_connectors)); } /* diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h index ff2063ec6b0f..87d8a50ee803 100644 --- a/fs/notify/fsnotify.h +++ b/fs/notify/fsnotify.h @@ -27,6 +27,21 @@ static inline struct super_block *fsnotify_conn_sb( return container_of(conn->obj, struct super_block, s_fsnotify_marks); } +static inline struct super_block *fsnotify_connector_sb( + struct fsnotify_mark_connector *conn) +{ + switch (conn->type) { + case FSNOTIFY_OBJ_TYPE_INODE: + return fsnotify_conn_inode(conn)->i_sb; + case FSNOTIFY_OBJ_TYPE_VFSMOUNT: + return fsnotify_conn_mount(conn)->mnt.mnt_sb; + case FSNOTIFY_OBJ_TYPE_SB: + return fsnotify_conn_sb(conn); + default: + return NULL; + } +} + /* destroy all events sitting in this groups notification queue */ extern void fsnotify_flush_notify(struct fsnotify_group *group); diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 2d8c46e1167d..95006d1d29ab 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -172,7 +172,7 @@ static void fsnotify_connector_destroy_workfn(struct work_struct *work) static void fsnotify_get_inode_ref(struct inode *inode) { ihold(inode); - atomic_long_inc(&inode->i_sb->s_fsnotify_inode_refs); + atomic_long_inc(&inode->i_sb->s_fsnotify_connectors); } static void fsnotify_put_inode_ref(struct inode *inode) @@ -180,8 +180,24 @@ static void fsnotify_put_inode_ref(struct inode *inode) struct super_block *sb = inode->i_sb; iput(inode); - if (atomic_long_dec_and_test(&sb->s_fsnotify_inode_refs)) - wake_up_var(&sb->s_fsnotify_inode_refs); + if (atomic_long_dec_and_test(&sb->s_fsnotify_connectors)) + wake_up_var(&sb->s_fsnotify_connectors); +} + +static void fsnotify_get_sb_connectors(struct fsnotify_mark_connector *conn) +{ + struct super_block *sb = fsnotify_connector_sb(conn); + + if (sb) + atomic_long_inc(&sb->s_fsnotify_connectors); +} + +static void fsnotify_put_sb_connectors(struct fsnotify_mark_connector *conn) +{ + struct super_block *sb = fsnotify_connector_sb(conn); + + if (sb && atomic_long_dec_and_test(&sb->s_fsnotify_connectors)) + wake_up_var(&sb->s_fsnotify_connectors); } static void *fsnotify_detach_connector_from_object( @@ -203,6 +219,7 @@ static void *fsnotify_detach_connector_from_object( fsnotify_conn_sb(conn)->s_fsnotify_mask = 0; } + fsnotify_put_sb_connectors(conn); rcu_assign_pointer(*(conn->obj), NULL); conn->obj = NULL; conn->type = FSNOTIFY_OBJ_TYPE_DETACHED; @@ -504,6 +521,7 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, inode = fsnotify_conn_inode(conn); fsnotify_get_inode_ref(inode); } + fsnotify_get_sb_connectors(conn); /* * cmpxchg() provides the barrier so that readers of *connp can see diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..bea8ec5c726c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1507,8 +1507,11 @@ struct super_block { /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; - /* Pending fsnotify inode refs */ - atomic_long_t s_fsnotify_inode_refs; + /* + * Number of inode/mount/sb objects that are being watched, note that + * inodes objects are currently double-accounted. + */ + atomic_long_t s_fsnotify_connectors; /* Being remounted read-only */ int s_readonly_remount; -- cgit v1.2.3 From e43de7f0862b8598cd1ef440e3b4701cd107ea40 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Tue, 10 Aug 2021 18:12:20 +0300 Subject: fsnotify: optimize the case of no marks of any type Add a simple check in the inline helpers to avoid calling fsnotify() and __fsnotify_parent() in case there are no marks of any type (inode/sb/mount) for an inode's sb, so there can be no objects of any type interested in the event. Link: https://lore.kernel.org/r/20210810151220.285179-5-amir73il@gmail.com Reviewed-by: Matthew Bobrowski Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index f8acddcf54fb..12d3a7d308ab 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -30,6 +30,9 @@ static inline void fsnotify_name(struct inode *dir, __u32 mask, struct inode *child, const struct qstr *name, u32 cookie) { + if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0) + return; + fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie); } @@ -41,6 +44,9 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, static inline void fsnotify_inode(struct inode *inode, __u32 mask) { + if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0) + return; + if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; @@ -53,6 +59,9 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, { struct inode *inode = d_inode(dentry); + if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0) + return 0; + if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; -- cgit v1.2.3 From b390752191a6e09e8fb89625e227db0d5cc0ca33 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 3 Aug 2021 20:39:25 +0300 Subject: gpiolib: Deduplicate forward declaration in the consumer.h header struct acpi_device is repeated in two branches of ifdeffery. Move it out and hence deduplicate. Signed-off-by: Andy Shevchenko Reviewed-by: Linus Walleij --- include/linux/gpio/consumer.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 566feb56601f..414b8f98d70f 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -680,10 +680,10 @@ struct acpi_gpio_mapping { unsigned int quirks; }; -#if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_ACPI) - struct acpi_device; +#if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_ACPI) + int acpi_dev_add_driver_gpios(struct acpi_device *adev, const struct acpi_gpio_mapping *gpios); void acpi_dev_remove_driver_gpios(struct acpi_device *adev); @@ -696,8 +696,6 @@ struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ -struct acpi_device; - static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, const struct acpi_gpio_mapping *gpios) { -- cgit v1.2.3 From c1b291e96a6d27ac83938596829086945ff8a36e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 4 Aug 2021 19:00:16 +0300 Subject: gpio: dwapb: Unify ACPI enumeration checks in get_irq() and configure_irqs() Shared IRQ is only enabled for ACPI enumeration, there is no need to have a special flag for that, since we simple can test if device has been enumerated by ACPI. This unifies the checks in dwapb_get_irq() and dwapb_configure_irqs(). Signed-off-by: Andy Shevchenko Acked-by: Lee Jones Acked-by: Serge Semin Tested-by: Serge Semin --- drivers/gpio/gpio-dwapb.c | 24 ++++++++++++------------ drivers/mfd/intel_quark_i2c_gpio.c | 1 - include/linux/platform_data/gpio-dwapb.h | 1 - 3 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 3eb13d6d31ef..4c7153cb646c 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -436,21 +436,17 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, pirq->irqchip.irq_set_wake = dwapb_irq_set_wake; #endif - if (!pp->irq_shared) { - girq->num_parents = pirq->nr_irqs; - girq->parents = pirq->irq; - girq->parent_handler_data = gpio; - girq->parent_handler = dwapb_irq_handler; - } else { - /* This will let us handle the parent IRQ in the driver */ + /* + * Intel ACPI-based platforms mostly have the DesignWare APB GPIO + * IRQ lane shared between several devices. In that case the parental + * IRQ has to be handled in the shared way so to be properly delivered + * to all the connected devices. + */ + if (has_acpi_companion(gpio->dev)) { girq->num_parents = 0; girq->parents = NULL; girq->parent_handler = NULL; - /* - * Request a shared IRQ since where MFD would have devices - * using the same irq pin - */ err = devm_request_irq(gpio->dev, pp->irq[0], dwapb_irq_handler_mfd, IRQF_SHARED, DWAPB_DRIVER_NAME, gpio); @@ -458,6 +454,11 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, dev_err(gpio->dev, "error requesting IRQ\n"); goto err_kfree_pirq; } + } else { + girq->num_parents = pirq->nr_irqs; + girq->parents = pirq->irq; + girq->parent_handler_data = gpio; + girq->parent_handler = dwapb_irq_handler; } girq->chip = &pirq->irqchip; @@ -581,7 +582,6 @@ static struct dwapb_platform_data *dwapb_gpio_get_pdata(struct device *dev) pp->ngpio = DWAPB_MAX_GPIOS; } - pp->irq_shared = false; pp->gpio_base = -1; /* diff --git a/drivers/mfd/intel_quark_i2c_gpio.c b/drivers/mfd/intel_quark_i2c_gpio.c index 01935ae4e9e1..a43993e38b6e 100644 --- a/drivers/mfd/intel_quark_i2c_gpio.c +++ b/drivers/mfd/intel_quark_i2c_gpio.c @@ -227,7 +227,6 @@ static int intel_quark_gpio_setup(struct pci_dev *pdev) pdata->properties->ngpio = INTEL_QUARK_MFD_NGPIO; pdata->properties->gpio_base = INTEL_QUARK_MFD_GPIO_BASE; pdata->properties->irq[0] = pci_irq_vector(pdev, 0); - pdata->properties->irq_shared = true; cell->platform_data = pdata; cell->pdata_size = sizeof(*pdata); diff --git a/include/linux/platform_data/gpio-dwapb.h b/include/linux/platform_data/gpio-dwapb.h index 0aa5c6720259..535e5ed549d9 100644 --- a/include/linux/platform_data/gpio-dwapb.h +++ b/include/linux/platform_data/gpio-dwapb.h @@ -14,7 +14,6 @@ struct dwapb_port_property { unsigned int ngpio; unsigned int gpio_base; int irq[DWAPB_MAX_GPIOS]; - bool irq_shared; }; struct dwapb_platform_data { -- cgit v1.2.3 From 5111c2b6b0194b509f47e6338c4deeeb4497bda8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 4 Aug 2021 19:00:19 +0300 Subject: gpio: dwapb: Get rid of legacy platform data Platform data is a legacy interface to supply device properties to the driver. In this case we don't have anymore in-kernel users for it. Just remove it for good. Signed-off-by: Andy Shevchenko Acked-by: Serge Semin Tested-by: Serge Semin --- drivers/gpio/gpio-dwapb.c | 28 ++++++++++++++++++---------- include/linux/platform_data/gpio-dwapb.h | 24 ------------------------ 2 files changed, 18 insertions(+), 34 deletions(-) delete mode 100644 include/linux/platform_data/gpio-dwapb.h (limited to 'include/linux') diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 674e91e69cc5..f98fa33e1679 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -48,6 +47,7 @@ #define DWAPB_DRIVER_NAME "gpio-dwapb" #define DWAPB_MAX_PORTS 4 +#define DWAPB_MAX_GPIOS 32 #define GPIO_EXT_PORT_STRIDE 0x04 /* register stride 32 bits */ #define GPIO_SWPORT_DR_STRIDE 0x0c /* register stride 3*32 bits */ @@ -65,6 +65,19 @@ struct dwapb_gpio; +struct dwapb_port_property { + struct fwnode_handle *fwnode; + unsigned int idx; + unsigned int ngpio; + unsigned int gpio_base; + int irq[DWAPB_MAX_GPIOS]; +}; + +struct dwapb_platform_data { + struct dwapb_port_property *properties; + unsigned int nports; +}; + #ifdef CONFIG_PM_SLEEP /* Store GPIO context across system-wide suspend/resume transitions */ struct dwapb_context { @@ -674,17 +687,12 @@ static int dwapb_gpio_probe(struct platform_device *pdev) unsigned int i; struct dwapb_gpio *gpio; int err; + struct dwapb_platform_data *pdata; struct device *dev = &pdev->dev; - struct dwapb_platform_data *pdata = dev_get_platdata(dev); - - if (!pdata) { - pdata = dwapb_gpio_get_pdata(dev); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - } - if (!pdata->nports) - return -ENODEV; + pdata = dwapb_gpio_get_pdata(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL); if (!gpio) diff --git a/include/linux/platform_data/gpio-dwapb.h b/include/linux/platform_data/gpio-dwapb.h deleted file mode 100644 index 535e5ed549d9..000000000000 --- a/include/linux/platform_data/gpio-dwapb.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright(c) 2014 Intel Corporation. - */ - -#ifndef GPIO_DW_APB_H -#define GPIO_DW_APB_H - -#define DWAPB_MAX_GPIOS 32 - -struct dwapb_port_property { - struct fwnode_handle *fwnode; - unsigned int idx; - unsigned int ngpio; - unsigned int gpio_base; - int irq[DWAPB_MAX_GPIOS]; -}; - -struct dwapb_platform_data { - struct dwapb_port_property *properties; - unsigned int nports; -}; - -#endif -- cgit v1.2.3 From 3183e87c1b797caaeb208b01c99bea8140273a16 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:20 +0000 Subject: x86/resctrl: Store the effective num_closid in the schema Struct resctrl_schema holds properties that vary with the style of configuration that resctrl applies to a resource. There are already two values for the hardware's num_closid, depending on whether the architecture presents the L3 or L3CODE/L3DATA resources. As the way CDP changes the number of control groups that resctrl can create is part of the user-space interface, it should be managed by the filesystem parts of resctrl. This allows the architecture code to only describe the value the hardware supports. Add num_closid to resctrl_schema. This is the value seen by the filesystem, which may be different to the maximum value described by the arch code when CDP is enabled. These functions operate on the num_closid value that is exposed to user-space: * rdtgroup_parse_resource() * rdtgroup_schemata_show() * rdt_num_closids_show() * closid_init() Change them to use the schema value instead. schemata_list_create() sets this value, and reaches into the architecture-specific structure to get the value. This will eventually be replaced with a helper. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-8-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 9 +++------ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 13 ++++--------- include/linux/resctrl.h | 4 ++++ 3 files changed, 11 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 405b99d31ef9..d10fddaef5f4 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -286,14 +286,12 @@ done: static int rdtgroup_parse_resource(char *resname, char *tok, struct rdtgroup *rdtgrp) { - struct rdt_hw_resource *hw_res; struct resctrl_schema *s; struct rdt_resource *r; list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; - hw_res = resctrl_to_arch_res(s->res); - if (!strcmp(resname, r->name) && rdtgrp->closid < hw_res->num_closid) + if (!strcmp(resname, r->name) && rdtgrp->closid < s->num_closid) return parse_line(tok, r, rdtgrp); } rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname); @@ -404,7 +402,6 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { - struct rdt_hw_resource *hw_res; struct resctrl_schema *schema; struct rdtgroup *rdtgrp; struct rdt_resource *r; @@ -432,8 +429,8 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, } else { closid = rdtgrp->closid; list_for_each_entry(schema, &resctrl_schema_all, list) { - hw_res = resctrl_to_arch_res(schema->res); - if (closid < hw_res->num_closid) + r = schema->res; + if (closid < schema->num_closid) show_doms(s, r, closid); } } diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 7502b7de3916..2f29b7d7d602 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -103,15 +103,12 @@ int closids_supported(void) static void closid_init(void) { - struct rdt_hw_resource *hw_res; struct resctrl_schema *s; int rdt_min_closid = 32; /* Compute rdt_min_closid across all resources */ - list_for_each_entry(s, &resctrl_schema_all, list) { - hw_res = resctrl_to_arch_res(s->res); - rdt_min_closid = min(rdt_min_closid, hw_res->num_closid); - } + list_for_each_entry(s, &resctrl_schema_all, list) + rdt_min_closid = min(rdt_min_closid, s->num_closid); closid_free_map = BIT_MASK(rdt_min_closid) - 1; @@ -849,11 +846,8 @@ static int rdt_num_closids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { struct resctrl_schema *s = of->kn->parent->priv; - struct rdt_resource *r = s->res; - struct rdt_hw_resource *hw_res; - hw_res = resctrl_to_arch_res(r); - seq_printf(seq, "%d\n", hw_res->num_closid); + seq_printf(seq, "%u\n", s->num_closid); return 0; } @@ -2140,6 +2134,7 @@ static int schemata_list_create(void) s->res = r; s->conf_type = resctrl_to_arch_res(r)->conf_type; + s->num_closid = resctrl_to_arch_res(r)->num_closid; INIT_LIST_HEAD(&s->list); list_add(&s->list, &resctrl_schema_all); diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 095ed48168d7..59d0fa78bb69 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -172,10 +172,14 @@ struct rdt_resource { * @conf_type: Whether this schema is specific to code/data. * @res: The resource structure exported by the architecture to describe * the hardware that is configured by this schema. + * @num_closid: The number of closid that can be used with this schema. When + * features like CDP are enabled, this will be lower than the + * hardware supports for the resource. */ struct resctrl_schema { struct list_head list; enum resctrl_conf_type conf_type; struct rdt_resource *res; + int num_closid; }; #endif /* _RESCTRL_H */ -- cgit v1.2.3 From eb6f3187694158ca36e50083e861531488d5c1b1 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:21 +0000 Subject: x86/resctrl: Add resctrl_arch_get_num_closid() To initialise struct resctrl_schema's num_closid, schemata_list_create() reaches into the architectures private structure to retrieve num_closid from the struct rdt_hw_resource. The 'half the closids' behaviour should be part of the filesystem parts of resctrl that are the same on any architecture. struct resctrl_schema's num_closid should include any correction for CDP. Having two properties called num_closid is likely to be confusing when they have different values. Add a helper to read the resource's num_closid from the arch code. This should return the number of closid that the resource supports, regardless of whether CDP is in use. Once the CDP resources are merged, schemata_list_create() can apply the correction itself. Using a type with an obvious size for the arch helper means changing the type of num_closid to u32, which matches the type already used by struct rdtgroup. reset_all_ctrls() does not use resctrl_arch_get_num_closid(), even though it sets up a structure for modifying the hardware. This function will be part of the architecture code, the maximum closid should be the maximum value the hardware has, regardless of the way resctrl is using it. All the uses of num_closid in core.c are naturally part of the architecture specific code. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-9-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/core.c | 5 +++++ arch/x86/kernel/cpu/resctrl/internal.h | 8 ++++++-- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 4 ++-- include/linux/resctrl.h | 6 +++++- 4 files changed, 18 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index c5b5c7227837..26e8d20cd072 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -450,6 +450,11 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) return NULL; } +u32 resctrl_arch_get_num_closid(struct rdt_resource *r) +{ + return resctrl_to_arch_res(r)->num_closid; +} + void rdt_ctrl_update(void *arg) { struct msr_param *m = arg; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 5e4a0a8d743c..c4bc5fae5a29 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -371,7 +371,11 @@ struct rdt_parse_data { * struct rdt_hw_resource - arch private attributes of a resctrl resource * @conf_type: The type that should be used when configuring. temporary * @r_resctrl: Attributes of the resource used directly by resctrl. - * @num_closid: Maximum number of closid this hardware can support. + * @num_closid: Maximum number of closid this hardware can support, + * regardless of CDP. This is exposed via + * resctrl_arch_get_num_closid() to avoid confusion + * with struct resctrl_schema's property of the same name, + * which has been corrected for features like CDP. * @msr_base: Base MSR address for CBMs * @msr_update: Function pointer to update QOS MSRs * @mon_scale: cqm counter * mon_scale = occupancy in bytes @@ -384,7 +388,7 @@ struct rdt_parse_data { struct rdt_hw_resource { enum resctrl_conf_type conf_type; struct rdt_resource r_resctrl; - int num_closid; + u32 num_closid; unsigned int msr_base; void (*msr_update) (struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 2f29b7d7d602..09ffe9a4a32b 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -104,7 +104,7 @@ int closids_supported(void) static void closid_init(void) { struct resctrl_schema *s; - int rdt_min_closid = 32; + u32 rdt_min_closid = 32; /* Compute rdt_min_closid across all resources */ list_for_each_entry(s, &resctrl_schema_all, list) @@ -2134,7 +2134,7 @@ static int schemata_list_create(void) s->res = r; s->conf_type = resctrl_to_arch_res(r)->conf_type; - s->num_closid = resctrl_to_arch_res(r)->num_closid; + s->num_closid = resctrl_arch_get_num_closid(r); INIT_LIST_HEAD(&s->list); list_add(&s->list, &resctrl_schema_all); diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 59d0fa78bb69..b9d200592e54 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -180,6 +180,10 @@ struct resctrl_schema { struct list_head list; enum resctrl_conf_type conf_type; struct rdt_resource *res; - int num_closid; + u32 num_closid; }; + +/* The number of closid supported by this resource regardless of CDP */ +u32 resctrl_arch_get_num_closid(struct rdt_resource *r); + #endif /* _RESCTRL_H */ -- cgit v1.2.3 From 1c290682c0c9c47aa7594ffc83b9cedd20c1ec87 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:22 +0000 Subject: x86/resctrl: Pass the schema to resctrl filesystem functions Once the CDP resources are merged, there will be two struct resctrl_schema for one struct rdt_resource. CDP becomes a type of configuration that belongs to the schema. Helpers like rdtgroup_cbm_overlaps() need access to the schema to query the configuration (or configurations) based on schema properties. Change these functions to take a struct schema instead of the struct rdt_resource. All the modified functions are part of the filesystem code that will move to /fs/resctrl once it is possible to support a second architecture. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-10-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 23 +++++++++++++---------- arch/x86/kernel/cpu/resctrl/internal.h | 6 +++--- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 19 +++++++++++-------- include/linux/resctrl.h | 3 ++- 4 files changed, 29 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index d10fddaef5f4..219b057e65b0 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -57,9 +57,10 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, +int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d) { + struct rdt_resource *r = s->res; unsigned long bw_val; if (d->have_new_ctrl) { @@ -125,10 +126,11 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, +int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d) { struct rdtgroup *rdtgrp = data->rdtgrp; + struct rdt_resource *r = s->res; u32 cbm_val; if (d->have_new_ctrl) { @@ -160,12 +162,12 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, * The CBM may not overlap with the CBM of another closid if * either is exclusive. */ - if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) { + if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, true)) { rdt_last_cmd_puts("Overlaps with exclusive group\n"); return -EINVAL; } - if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) { + if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, false)) { if (rdtgrp->mode == RDT_MODE_EXCLUSIVE || rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { rdt_last_cmd_puts("Overlaps with other group\n"); @@ -185,9 +187,10 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, * separated by ";". The "id" is in decimal, and must match one of * the "id"s for this resource. */ -static int parse_line(char *line, struct rdt_resource *r, +static int parse_line(char *line, struct resctrl_schema *s, struct rdtgroup *rdtgrp) { + struct rdt_resource *r = s->res; struct rdt_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; @@ -213,7 +216,7 @@ next: if (d->id == dom_id) { data.buf = dom; data.rdtgrp = rdtgrp; - if (r->parse_ctrlval(&data, r, d)) + if (r->parse_ctrlval(&data, s, d)) return -EINVAL; if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { /* @@ -292,7 +295,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok, list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; if (!strcmp(resname, r->name) && rdtgrp->closid < s->num_closid) - return parse_line(tok, r, rdtgrp); + return parse_line(tok, s, rdtgrp); } rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname); return -EINVAL; @@ -377,8 +380,9 @@ out: return ret ?: nbytes; } -static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) +static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid) { + struct rdt_resource *r = schema->res; struct rdt_hw_domain *hw_dom; struct rdt_domain *dom; bool sep = false; @@ -429,9 +433,8 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, } else { closid = rdtgrp->closid; list_for_each_entry(schema, &resctrl_schema_all, list) { - r = schema->res; if (closid < schema->num_closid) - show_doms(s, r, closid); + show_doms(s, schema, closid); } } } else { diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index c4bc5fae5a29..5d5debe6e8d2 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -401,9 +401,9 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r return container_of(r, struct rdt_hw_resource, r_resctrl); } -int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, +int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d); -int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, +int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -505,7 +505,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); -bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, +bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, unsigned long cbm, int closid, bool exclusive); unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, unsigned long cbm); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 09ffe9a4a32b..53d281a9f54f 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1221,7 +1221,7 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d /** * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware - * @r: Resource to which domain instance @d belongs. + * @s: Schema for the resource to which domain instance @d belongs. * @d: The domain instance for which @closid is being tested. * @cbm: Capacity bitmask being tested. * @closid: Intended closid for @cbm. @@ -1239,9 +1239,10 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d * * Return: true if CBM overlap detected, false if there is no overlap */ -bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, +bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, unsigned long cbm, int closid, bool exclusive) { + struct rdt_resource *r = s->res; struct rdt_resource *r_cdp; struct rdt_domain *d_cdp; @@ -1282,7 +1283,8 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) has_cache = true; list_for_each_entry(d, &r->domains, list) { hw_dom = resctrl_to_arch_dom(d); - if (rdtgroup_cbm_overlaps(r, d, hw_dom->ctrl_val[closid], + if (rdtgroup_cbm_overlaps(s, d, + hw_dom->ctrl_val[closid], rdtgrp->closid, false)) { rdt_last_cmd_puts("Schemata overlaps\n"); return false; @@ -2712,11 +2714,12 @@ static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r) * Set the RDT domain up to start off with all usable allocations. That is, * all shareable and unused bits. All-zero CBM is invalid. */ -static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r, +static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, u32 closid) { struct rdt_resource *r_cdp = NULL; struct rdt_domain *d_cdp = NULL; + struct rdt_resource *r = s->res; u32 used_b = 0, unused_b = 0; unsigned long tmp_cbm; enum rdtgrp_mode mode; @@ -2786,13 +2789,13 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r, * If there are no more shareable bits available on any domain then * the entire allocation will fail. */ -static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid) +static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid) { struct rdt_domain *d; int ret; - list_for_each_entry(d, &r->domains, list) { - ret = __init_one_rdt_domain(d, r, closid); + list_for_each_entry(d, &s->res->domains, list) { + ret = __init_one_rdt_domain(d, s, closid); if (ret < 0) return ret; } @@ -2823,7 +2826,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) if (r->rid == RDT_RESOURCE_MBA) { rdtgroup_init_mba(r); } else { - ret = rdtgroup_init_cat(r, rdtgrp->closid); + ret = rdtgroup_init_cat(s, rdtgrp->closid); if (ret < 0) return ret; } diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index b9d200592e54..979592c869e6 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -121,6 +121,7 @@ struct resctrl_membw { }; struct rdt_parse_data; +struct resctrl_schema; /** * struct rdt_resource - attributes of a resctrl resource @@ -158,7 +159,7 @@ struct rdt_resource { u32 default_ctrl; const char *format_str; int (*parse_ctrlval)(struct rdt_parse_data *data, - struct rdt_resource *r, + struct resctrl_schema *s, struct rdt_domain *d); struct list_head evt_list; unsigned long fflags; -- cgit v1.2.3 From c091e90721b836c2367fa3017636d92427f3f8f7 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:24 +0000 Subject: x86/resctrl: Add a helper to read/set the CDP configuration Whether CDP is enabled for a hardware resource like the L3 cache can be found by inspecting the alloc_enabled flags of the L3CODE/L3DATA struct rdt_hw_resources, even if they aren't in use. Once these resources are merged, the flags can't be compared. Whether CDP is enabled needs tracking explicitly. If another architecture is emulating CDP the behaviour may not be per-resource. 'cdp_capable' needs to be visible to resctrl, even if its not in use, as this affects the padding of the schemata table visible to user-space. Add cdp_enabled to struct rdt_hw_resource and cdp_capable to struct rdt_resource. Add resctrl_arch_set_cdp_enabled() to let resctrl enable or disable CDP on a resource. resctrl_arch_get_cdp_enabled() lets it read the current state. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-12-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/core.c | 4 ++ arch/x86/kernel/cpu/resctrl/internal.h | 11 ++++- arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 4 +- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 75 ++++++++++++++++++------------- include/linux/resctrl.h | 3 +- 5 files changed, 62 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 26e8d20cd072..87b5aa7683ee 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -374,6 +374,10 @@ static void rdt_get_cdp_config(int level, int type) * "cdp" during resctrl file system mount time. */ r->alloc_enabled = false; + rdt_resources_all[level].cdp_enabled = false; + rdt_resources_all[type].cdp_enabled = false; + r_l->cdp_capable = true; + r->cdp_capable = true; } static void rdt_get_cdp_l3_config(void) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index c8521efe90e7..4e15667b88a8 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -380,6 +380,7 @@ struct rdt_parse_data { * @msr_update: Function pointer to update QOS MSRs * @mon_scale: cqm counter * mon_scale = occupancy in bytes * @mbm_width: Monitor width, to detect and correct for overflow. + * @cdp_enabled: CDP state of this resource * * Members of this structure are either private to the architecture * e.g. mbm_width, or accessed via helpers that provide abstraction. e.g. @@ -394,6 +395,7 @@ struct rdt_hw_resource { struct rdt_resource *r); unsigned int mon_scale; unsigned int mbm_width; + bool cdp_enabled; }; static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r) @@ -414,7 +416,7 @@ DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); extern struct dentry *debugfs_resctrl; -enum { +enum resctrl_res_level { RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE, @@ -435,6 +437,13 @@ static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res) return &hw_res->r_resctrl; } +static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l) +{ + return rdt_resources_all[l].cdp_enabled; +} + +int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable); + /* * To return the common struct rdt_resource, which is contained in struct * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource. diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 3c035a7fa61d..db813f819ad6 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -688,8 +688,8 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) * resource, the portion of cache used by it should be made * unavailable to all future allocations from both resources. */ - if (rdt_resources_all[RDT_RESOURCE_L3DATA].r_resctrl.alloc_enabled || - rdt_resources_all[RDT_RESOURCE_L2DATA].r_resctrl.alloc_enabled) { + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3) || + resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) { rdt_last_cmd_puts("CDP enabled\n"); return -EINVAL; } diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 305dcf8850a0..cc9dacd73438 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1940,14 +1940,16 @@ static int set_cache_qos_cfg(int level, bool enable) /* Restore the qos cfg state when a domain comes online */ void rdt_domain_reconfigure_cdp(struct rdt_resource *r) { - if (!r->alloc_capable) + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + + if (!r->cdp_capable) return; if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA].r_resctrl) - l2_qos_cfg_update(&r->alloc_enabled); + l2_qos_cfg_update(&hw_res->cdp_enabled); if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA].r_resctrl) - l3_qos_cfg_update(&r->alloc_enabled); + l3_qos_cfg_update(&hw_res->cdp_enabled); } /* @@ -1991,51 +1993,62 @@ static int cdp_enable(int level, int data_type, int code_type) r_l->alloc_enabled = false; r_ldata->alloc_enabled = true; r_lcode->alloc_enabled = true; + rdt_resources_all[level].cdp_enabled = true; + rdt_resources_all[data_type].cdp_enabled = true; + rdt_resources_all[code_type].cdp_enabled = true; } return ret; } -static int cdpl3_enable(void) -{ - return cdp_enable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, - RDT_RESOURCE_L3CODE); -} - -static int cdpl2_enable(void) -{ - return cdp_enable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, - RDT_RESOURCE_L2CODE); -} - static void cdp_disable(int level, int data_type, int code_type) { - struct rdt_resource *r = &rdt_resources_all[level].r_resctrl; + struct rdt_hw_resource *r_hw = &rdt_resources_all[level]; + struct rdt_resource *r = &r_hw->r_resctrl; r->alloc_enabled = r->alloc_capable; - if (rdt_resources_all[data_type].r_resctrl.alloc_enabled) { + if (r_hw->cdp_enabled) { rdt_resources_all[data_type].r_resctrl.alloc_enabled = false; rdt_resources_all[code_type].r_resctrl.alloc_enabled = false; set_cache_qos_cfg(level, false); + r_hw->cdp_enabled = false; + rdt_resources_all[data_type].cdp_enabled = false; + rdt_resources_all[code_type].cdp_enabled = false; } } -static void cdpl3_disable(void) +int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable) { - cdp_disable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE); -} + struct rdt_hw_resource *hw_res = &rdt_resources_all[l]; + enum resctrl_res_level code_type, data_type; -static void cdpl2_disable(void) -{ - cdp_disable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, RDT_RESOURCE_L2CODE); + if (!hw_res->r_resctrl.cdp_capable) + return -EINVAL; + + if (l == RDT_RESOURCE_L3) { + code_type = RDT_RESOURCE_L3CODE; + data_type = RDT_RESOURCE_L3DATA; + } else if (l == RDT_RESOURCE_L2) { + code_type = RDT_RESOURCE_L2CODE; + data_type = RDT_RESOURCE_L2DATA; + } else { + return -EINVAL; + } + + if (enable) + return cdp_enable(l, data_type, code_type); + + cdp_disable(l, data_type, code_type); + + return 0; } static void cdp_disable_all(void) { - if (rdt_resources_all[RDT_RESOURCE_L3DATA].r_resctrl.alloc_enabled) - cdpl3_disable(); - if (rdt_resources_all[RDT_RESOURCE_L2DATA].r_resctrl.alloc_enabled) - cdpl2_disable(); + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3)) + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); } /* @@ -2113,10 +2126,10 @@ static int rdt_enable_ctx(struct rdt_fs_context *ctx) int ret = 0; if (ctx->enable_cdpl2) - ret = cdpl2_enable(); + ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true); if (!ret && ctx->enable_cdpl3) - ret = cdpl3_enable(); + ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true); if (!ret && ctx->enable_mba_mbps) ret = set_mba_sc(true); @@ -3199,10 +3212,10 @@ out: static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { - if (rdt_resources_all[RDT_RESOURCE_L3DATA].r_resctrl.alloc_enabled) + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3)) seq_puts(seq, ",cdp"); - if (rdt_resources_all[RDT_RESOURCE_L2DATA].r_resctrl.alloc_enabled) + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) seq_puts(seq, ",cdpl2"); if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl)) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 979592c869e6..4b30571fbc8e 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -142,6 +142,7 @@ struct resctrl_schema; * @parse_ctrlval: Per resource function pointer to parse control values * @evt_list: List of monitoring events * @fflags: flags to choose base and info files + * @cdp_capable: Is the CDP feature available on this resource */ struct rdt_resource { int rid; @@ -163,7 +164,7 @@ struct rdt_resource { struct rdt_domain *d); struct list_head evt_list; unsigned long fflags; - + bool cdp_capable; }; /** -- cgit v1.2.3 From e198fde3fe0892a5d1e28c0e29f1eebfb6f8c1cd Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:25 +0000 Subject: x86/resctrl: Move the schemata names into struct resctrl_schema resctrl 'info' directories and schema parsing use the schema name. This lives in the struct rdt_resource, and is specified by the architecture code. Once the CDP resources are merged, there will only be one resource (and one name) in use by two schemata. To allow the CDP CODE/DATA property to be the type of configuration the schema uses, the name should also be per-schema. Add a name field to struct resctrl_schema, and use this wherever the schema name is exposed (or read from) user-space. Calculating max_name_width for padding the schemata file also moves as this is visible to user-space. As the names in struct rdt_resource already include the CDP information, schemata_list_create() copies them. schemata_list_create() includes the length of the CDP suffix when calculating max_name_width in preparation for CDP resources being merged. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-13-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/core.c | 5 ----- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 10 +++------- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 29 +++++++++++++++++++++++++---- include/linux/resctrl.h | 2 ++ 4 files changed, 30 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 87b5aa7683ee..755118a9ef38 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -782,13 +782,8 @@ static int resctrl_offline_cpu(unsigned int cpu) static __init void rdt_init_padding(void) { struct rdt_resource *r; - int cl; for_each_alloc_capable_rdt_resource(r) { - cl = strlen(r->name); - if (cl > max_name_width) - max_name_width = cl; - if (r->data_width > max_data_width) max_data_width = r->data_width; } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 0ee1ded5b8ff..104b285f8a60 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -290,11 +290,9 @@ static int rdtgroup_parse_resource(char *resname, char *tok, struct rdtgroup *rdtgrp) { struct resctrl_schema *s; - struct rdt_resource *r; list_for_each_entry(s, &resctrl_schema_all, list) { - r = s->res; - if (!strcmp(resname, r->name) && rdtgrp->closid < s->num_closid) + if (!strcmp(resname, s->name) && rdtgrp->closid < s->num_closid) return parse_line(tok, s, rdtgrp); } rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname); @@ -388,7 +386,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo bool sep = false; u32 ctrl_val; - seq_printf(s, "%*s:", max_name_width, r->name); + seq_printf(s, "%*s:", max_name_width, schema->name); list_for_each_entry(dom, &r->domains, list) { hw_dom = resctrl_to_arch_dom(dom); if (sep) @@ -408,7 +406,6 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, { struct resctrl_schema *schema; struct rdtgroup *rdtgrp; - struct rdt_resource *r; int ret = 0; u32 closid; @@ -416,8 +413,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, if (rdtgrp) { if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { list_for_each_entry(schema, &resctrl_schema_all, list) { - r = schema->res; - seq_printf(s, "%s:uninitialized\n", r->name); + seq_printf(s, "%s:uninitialized\n", schema->name); } } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { if (!rdtgrp->plr->d) { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index cc9dacd73438..1f8c8d79d00b 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1439,7 +1439,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, ret = -ENODEV; } else { seq_printf(s, "%*s:", max_name_width, - rdtgrp->plr->s->res->name); + rdtgrp->plr->s->name); size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res, rdtgrp->plr->d, rdtgrp->plr->cbm); @@ -1451,7 +1451,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, list_for_each_entry(schema, &resctrl_schema_all, list) { r = schema->res; sep = false; - seq_printf(s, "%*s:", max_name_width, r->name); + seq_printf(s, "%*s:", max_name_width, schema->name); list_for_each_entry(d, &r->domains, list) { hw_dom = resctrl_to_arch_dom(d); if (sep) @@ -1823,7 +1823,7 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; fflags = r->fflags | RF_CTRL_INFO; - ret = rdtgroup_mkdir_info_resdir(s, r->name, fflags); + ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags); if (ret) goto out_destroy; } @@ -2141,6 +2141,7 @@ static int schemata_list_create(void) { struct resctrl_schema *s; struct rdt_resource *r; + int ret, cl; for_each_alloc_enabled_rdt_resource(r) { s = kzalloc(sizeof(*s), GFP_KERNEL); @@ -2151,6 +2152,26 @@ static int schemata_list_create(void) s->conf_type = resctrl_to_arch_res(r)->conf_type; s->num_closid = resctrl_arch_get_num_closid(r); + ret = snprintf(s->name, sizeof(s->name), r->name); + if (ret >= sizeof(s->name)) { + kfree(s); + return -EINVAL; + } + + cl = strlen(s->name); + + /* + * If CDP is supported by this resource, but not enabled, + * include the suffix. This ensures the tabular format of the + * schemata file does not change between mounts of the + * filesystem. + */ + if (r->cdp_capable && !resctrl_arch_get_cdp_enabled(r->rid)) + cl += 4; + + if (cl > max_name_width) + max_name_width = cl; + INIT_LIST_HEAD(&s->list); list_add(&s->list, &resctrl_schema_all); } @@ -2784,7 +2805,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, */ tmp_cbm = d->new_ctrl; if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) { - rdt_last_cmd_printf("No space on %s:%d\n", r->name, d->id); + rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->id); return -ENOSPC; } d->have_new_ctrl = true; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 4b30571fbc8e..e482ce790ce2 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -171,6 +171,7 @@ struct rdt_resource { * struct resctrl_schema - configuration abilities of a resource presented to * user-space * @list: Member of resctrl_schema_all. + * @name: The name to use in the "schemata" file. * @conf_type: Whether this schema is specific to code/data. * @res: The resource structure exported by the architecture to describe * the hardware that is configured by this schema. @@ -180,6 +181,7 @@ struct rdt_resource { */ struct resctrl_schema { struct list_head list; + char name[8]; enum resctrl_conf_type conf_type; struct rdt_resource *res; u32 num_closid; -- cgit v1.2.3 From e8f7282552b902af3bd1f07a87d657b7f5f12ab8 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:26 +0000 Subject: x86/resctrl: Group staged configuration into a separate struct When configuration changes are made, the new value is written to struct rdt_domain's new_ctrl field and the have_new_ctrl flag is set. Later new_ctrl is copied to hardware by a call to update_domains(). Once the CDP resources are merged, there will be one new_ctrl field in use by two struct resctrl_schema requiring a per-schema IPI to copy the value to hardware. Move new_ctrl and have_new_ctrl into a new struct resctrl_staged_config. Before the CDP resources can be merged, struct rdt_domain will need an array of these, one per type of configuration. Using the type as an index to the array will ensure that a schema configuration string can't specify the same domain twice. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-14-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 43 +++++++++++++++++++++---------- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 22 +++++++++------- include/linux/resctrl.h | 16 +++++++++--- 3 files changed, 54 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 104b285f8a60..9ddfa7607234 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -62,16 +62,17 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, { struct rdt_resource *r = s->res; unsigned long bw_val; + struct resctrl_staged_config *cfg = &d->staged_config; - if (d->have_new_ctrl) { + if (cfg->have_new_ctrl) { rdt_last_cmd_printf("Duplicate domain %d\n", d->id); return -EINVAL; } if (!bw_validate(data->buf, &bw_val, r)) return -EINVAL; - d->new_ctrl = bw_val; - d->have_new_ctrl = true; + cfg->new_ctrl = bw_val; + cfg->have_new_ctrl = true; return 0; } @@ -129,11 +130,12 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d) { + struct resctrl_staged_config *cfg = &d->staged_config; struct rdtgroup *rdtgrp = data->rdtgrp; struct rdt_resource *r = s->res; u32 cbm_val; - if (d->have_new_ctrl) { + if (cfg->have_new_ctrl) { rdt_last_cmd_printf("Duplicate domain %d\n", d->id); return -EINVAL; } @@ -175,8 +177,8 @@ int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, } } - d->new_ctrl = cbm_val; - d->have_new_ctrl = true; + cfg->new_ctrl = cbm_val; + cfg->have_new_ctrl = true; return 0; } @@ -190,6 +192,7 @@ int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, static int parse_line(char *line, struct resctrl_schema *s, struct rdtgroup *rdtgrp) { + struct resctrl_staged_config *cfg; struct rdt_resource *r = s->res; struct rdt_parse_data data; char *dom = NULL, *id; @@ -219,6 +222,7 @@ next: if (r->parse_ctrlval(&data, s, d)) return -EINVAL; if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + cfg = &d->staged_config; /* * In pseudo-locking setup mode and just * parsed a valid CBM that should be @@ -229,7 +233,7 @@ next: */ rdtgrp->plr->s = s; rdtgrp->plr->d = d; - rdtgrp->plr->cbm = d->new_ctrl; + rdtgrp->plr->cbm = cfg->new_ctrl; d->plr = rdtgrp->plr; return 0; } @@ -239,14 +243,27 @@ next: return -EINVAL; } +static void apply_config(struct rdt_hw_domain *hw_dom, + struct resctrl_staged_config *cfg, int closid, + cpumask_var_t cpu_mask, bool mba_sc) +{ + struct rdt_domain *dom = &hw_dom->d_resctrl; + u32 *dc = !mba_sc ? hw_dom->ctrl_val : hw_dom->mbps_val; + + if (cfg->new_ctrl != dc[closid]) { + cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask); + dc[closid] = cfg->new_ctrl; + } +} + int update_domains(struct rdt_resource *r, int closid) { + struct resctrl_staged_config *cfg; struct rdt_hw_domain *hw_dom; struct msr_param msr_param; cpumask_var_t cpu_mask; struct rdt_domain *d; bool mba_sc; - u32 *dc; int cpu; if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) @@ -259,11 +276,9 @@ int update_domains(struct rdt_resource *r, int closid) mba_sc = is_mba_sc(r); list_for_each_entry(d, &r->domains, list) { hw_dom = resctrl_to_arch_dom(d); - dc = !mba_sc ? hw_dom->ctrl_val : hw_dom->mbps_val; - if (d->have_new_ctrl && d->new_ctrl != dc[closid]) { - cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); - dc[closid] = d->new_ctrl; - } + cfg = &hw_dom->d_resctrl.staged_config; + if (cfg->have_new_ctrl) + apply_config(hw_dom, cfg, closid, cpu_mask, mba_sc); } /* @@ -335,7 +350,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, list_for_each_entry(s, &resctrl_schema_all, list) { list_for_each_entry(dom, &s->res->domains, list) - dom->have_new_ctrl = false; + memset(&dom->staged_config, 0, sizeof(dom->staged_config)); } while ((tok = strsep(&buf, "\n")) != NULL) { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 1f8c8d79d00b..62cc82d7b06e 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2752,6 +2752,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, u32 closid) { struct rdt_resource *r_cdp = NULL; + struct resctrl_staged_config *cfg; struct rdt_domain *d_cdp = NULL; struct rdt_resource *r = s->res; u32 used_b = 0, unused_b = 0; @@ -2761,8 +2762,9 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, int i; rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp); - d->have_new_ctrl = false; - d->new_ctrl = r->cache.shareable_bits; + cfg = &d->staged_config; + cfg->have_new_ctrl = false; + cfg->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; ctrl = resctrl_to_arch_dom(d)->ctrl_val; for (i = 0; i < closids_supported(); i++, ctrl++) { @@ -2786,29 +2788,29 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, peer_ctl = 0; used_b |= *ctrl | peer_ctl; if (mode == RDT_MODE_SHAREABLE) - d->new_ctrl |= *ctrl | peer_ctl; + cfg->new_ctrl |= *ctrl | peer_ctl; } } if (d->plr && d->plr->cbm > 0) used_b |= d->plr->cbm; unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1); unused_b &= BIT_MASK(r->cache.cbm_len) - 1; - d->new_ctrl |= unused_b; + cfg->new_ctrl |= unused_b; /* * Force the initial CBM to be valid, user can * modify the CBM based on system availability. */ - d->new_ctrl = cbm_ensure_valid(d->new_ctrl, r); + cfg->new_ctrl = cbm_ensure_valid(cfg->new_ctrl, r); /* * Assign the u32 CBM to an unsigned long to ensure that * bitmap_weight() does not access out-of-bound memory. */ - tmp_cbm = d->new_ctrl; + tmp_cbm = cfg->new_ctrl; if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) { rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->id); return -ENOSPC; } - d->have_new_ctrl = true; + cfg->have_new_ctrl = true; return 0; } @@ -2840,11 +2842,13 @@ static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid) /* Initialize MBA resource with default values. */ static void rdtgroup_init_mba(struct rdt_resource *r) { + struct resctrl_staged_config *cfg; struct rdt_domain *d; list_for_each_entry(d, &r->domains, list) { - d->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl; - d->have_new_ctrl = true; + cfg = &d->staged_config; + cfg->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl; + cfg->have_new_ctrl = true; } } diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index e482ce790ce2..ff7f7d7e1348 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -27,13 +27,21 @@ enum resctrl_conf_type { CDP_DATA, }; +/** + * struct resctrl_staged_config - parsed configuration to be applied + * @new_ctrl: new ctrl value to be loaded + * @have_new_ctrl: whether the user provided new_ctrl is valid + */ +struct resctrl_staged_config { + u32 new_ctrl; + bool have_new_ctrl; +}; + /** * struct rdt_domain - group of CPUs sharing a resctrl resource * @list: all instances of this resource * @id: unique id for this instance * @cpu_mask: which CPUs share this resource - * @new_ctrl: new ctrl value to be loaded - * @have_new_ctrl: did user provide new_ctrl for this domain * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold * @mbm_total: saved state for MBM total bandwidth * @mbm_local: saved state for MBM local bandwidth @@ -42,13 +50,12 @@ enum resctrl_conf_type { * @mbm_work_cpu: worker CPU for MBM h/w counters * @cqm_work_cpu: worker CPU for CQM h/w counters * @plr: pseudo-locked region (if any) associated with domain + * @staged_config: parsed configuration to be applied */ struct rdt_domain { struct list_head list; int id; struct cpumask cpu_mask; - u32 new_ctrl; - bool have_new_ctrl; unsigned long *rmid_busy_llc; struct mbm_state *mbm_total; struct mbm_state *mbm_local; @@ -57,6 +64,7 @@ struct rdt_domain { int mbm_work_cpu; int cqm_work_cpu; struct pseudo_lock_region *plr; + struct resctrl_staged_config staged_config; }; /** -- cgit v1.2.3 From 75408e43509ed6207870c0e7e28656acbbc1f7fd Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:27 +0000 Subject: x86/resctrl: Allow different CODE/DATA configurations to be staged Before the CDP resources can be merged, struct rdt_domain will need an array of struct resctrl_staged_config, one per type of configuration. Use the type as an index to the array to ensure that a schema configuration string can't specify the same domain twice. This will allow two schemata to apply configuration changes to one resource. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-15-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 20 ++++++++++++++------ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 5 +++-- include/linux/resctrl.h | 4 +++- 3 files changed, 20 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 9ddfa7607234..f29848f98846 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -60,10 +60,11 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d) { + struct resctrl_staged_config *cfg; struct rdt_resource *r = s->res; unsigned long bw_val; - struct resctrl_staged_config *cfg = &d->staged_config; + cfg = &d->staged_config[s->conf_type]; if (cfg->have_new_ctrl) { rdt_last_cmd_printf("Duplicate domain %d\n", d->id); return -EINVAL; @@ -130,11 +131,12 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d) { - struct resctrl_staged_config *cfg = &d->staged_config; struct rdtgroup *rdtgrp = data->rdtgrp; + struct resctrl_staged_config *cfg; struct rdt_resource *r = s->res; u32 cbm_val; + cfg = &d->staged_config[s->conf_type]; if (cfg->have_new_ctrl) { rdt_last_cmd_printf("Duplicate domain %d\n", d->id); return -EINVAL; @@ -192,6 +194,7 @@ int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, static int parse_line(char *line, struct resctrl_schema *s, struct rdtgroup *rdtgrp) { + enum resctrl_conf_type t = s->conf_type; struct resctrl_staged_config *cfg; struct rdt_resource *r = s->res; struct rdt_parse_data data; @@ -222,7 +225,7 @@ next: if (r->parse_ctrlval(&data, s, d)) return -EINVAL; if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { - cfg = &d->staged_config; + cfg = &d->staged_config[t]; /* * In pseudo-locking setup mode and just * parsed a valid CBM that should be @@ -261,6 +264,7 @@ int update_domains(struct rdt_resource *r, int closid) struct resctrl_staged_config *cfg; struct rdt_hw_domain *hw_dom; struct msr_param msr_param; + enum resctrl_conf_type t; cpumask_var_t cpu_mask; struct rdt_domain *d; bool mba_sc; @@ -276,9 +280,13 @@ int update_domains(struct rdt_resource *r, int closid) mba_sc = is_mba_sc(r); list_for_each_entry(d, &r->domains, list) { hw_dom = resctrl_to_arch_dom(d); - cfg = &hw_dom->d_resctrl.staged_config; - if (cfg->have_new_ctrl) + for (t = 0; t < CDP_NUM_TYPES; t++) { + cfg = &hw_dom->d_resctrl.staged_config[t]; + if (!cfg->have_new_ctrl) + continue; + apply_config(hw_dom, cfg, closid, cpu_mask, mba_sc); + } } /* @@ -350,7 +358,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, list_for_each_entry(s, &resctrl_schema_all, list) { list_for_each_entry(dom, &s->res->domains, list) - memset(&dom->staged_config, 0, sizeof(dom->staged_config)); + memset(dom->staged_config, 0, sizeof(dom->staged_config)); } while ((tok = strsep(&buf, "\n")) != NULL) { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 62cc82d7b06e..9f1354cb94e9 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2751,6 +2751,7 @@ static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r) static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, u32 closid) { + enum resctrl_conf_type t = s->conf_type; struct rdt_resource *r_cdp = NULL; struct resctrl_staged_config *cfg; struct rdt_domain *d_cdp = NULL; @@ -2762,7 +2763,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, int i; rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp); - cfg = &d->staged_config; + cfg = &d->staged_config[t]; cfg->have_new_ctrl = false; cfg->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; @@ -2846,7 +2847,7 @@ static void rdtgroup_init_mba(struct rdt_resource *r) struct rdt_domain *d; list_for_each_entry(d, &r->domains, list) { - cfg = &d->staged_config; + cfg = &d->staged_config[CDP_NONE]; cfg->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl; cfg->have_new_ctrl = true; } diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index ff7f7d7e1348..51ba372f96cd 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -27,6 +27,8 @@ enum resctrl_conf_type { CDP_DATA, }; +#define CDP_NUM_TYPES (CDP_DATA + 1) + /** * struct resctrl_staged_config - parsed configuration to be applied * @new_ctrl: new ctrl value to be loaded @@ -64,7 +66,7 @@ struct rdt_domain { int mbm_work_cpu; int cqm_work_cpu; struct pseudo_lock_region *plr; - struct resctrl_staged_config staged_config; + struct resctrl_staged_config staged_config[CDP_NUM_TYPES]; }; /** -- cgit v1.2.3 From 2e6678195d59c51b6ca234169ad3de01134d3dec Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:28 +0000 Subject: x86/resctrl: Rename update_domains() to resctrl_arch_update_domains() update_domains() merges the staged configuration changes into the arch codes configuration array. Rename to make it clear it is part of the arch code interface to resctrl. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-16-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 4 ++-- arch/x86/kernel/cpu/resctrl/internal.h | 1 - arch/x86/kernel/cpu/resctrl/rdtgroup.c | 2 +- include/linux/resctrl.h | 1 + 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index f29848f98846..8cde76df888a 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -259,7 +259,7 @@ static void apply_config(struct rdt_hw_domain *hw_dom, } } -int update_domains(struct rdt_resource *r, int closid) +int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) { struct resctrl_staged_config *cfg; struct rdt_hw_domain *hw_dom; @@ -380,7 +380,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; - ret = update_domains(r, rdtgrp->closid); + ret = resctrl_arch_update_domains(r, rdtgrp->closid); if (ret) goto out; } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 4e15667b88a8..a95893ed3795 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -529,7 +529,6 @@ void rdt_pseudo_lock_release(void); int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); -int update_domains(struct rdt_resource *r, int closid); int closids_supported(void); void closid_free(int closid); int alloc_rmid(void); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 9f1354cb94e9..4b6de76493d6 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2870,7 +2870,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) return ret; } - ret = update_domains(r, rdtgrp->closid); + ret = resctrl_arch_update_domains(r, rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("Failed to initialize allocations\n"); return ret; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 51ba372f96cd..be5881171576 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -199,5 +199,6 @@ struct resctrl_schema { /* The number of closid supported by this resource regardless of CDP */ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); +int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); #endif /* _RESCTRL_H */ -- cgit v1.2.3 From 26471d4a6cf8d5d0bd0fb55c7169de7d67cc703a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 12 Jul 2021 17:20:25 +0300 Subject: units: Add SI metric prefix definitions Sometimes it's useful to have well-defined SI metric prefix to be used to self-describe the formulas or equations. List most popular ones in the units.h. Signed-off-by: Andy Shevchenko Signed-off-by: Wolfram Sang --- include/linux/units.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/units.h b/include/linux/units.h index dcc30a53fa93..4a25e0cc8fb3 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -4,6 +4,22 @@ #include +/* Metric prefixes in accordance with Système international (d'unités) */ +#define PETA 1000000000000000ULL +#define TERA 1000000000000ULL +#define GIGA 1000000000UL +#define MEGA 1000000UL +#define KILO 1000UL +#define HECTO 100UL +#define DECA 10UL +#define DECI 10UL +#define CENTI 100UL +#define MILLI 1000UL +#define MICRO 1000000UL +#define NANO 1000000000UL +#define PICO 1000000000000ULL +#define FEMTO 1000000000000000ULL + #define MILLIWATT_PER_WATT 1000L #define MICROWATT_PER_MILLIWATT 1000L #define MICROWATT_PER_WATT 1000000L -- cgit v1.2.3 From f07e9d0250577a23eb06d4334798291616c01f2d Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:29 +0000 Subject: x86/resctrl: Add a helper to read a closid's configuration Functions like show_doms() reach into the architecture's private structure to retrieve the configuration from the struct rdt_hw_resource. The hardware configuration may look completely different to the values resctrl gets from user-space. The staged configuration and resctrl_arch_update_domains() allow the architecture to convert or translate these values. Resctrl shouldn't read or write the ctrl_val[] values directly. Add a helper to read the current configuration. This will allow another architecture to scale the bitmaps if necessary, and possibly use controls that don't take the user-space control format at all. Of the remaining functions that access ctrl_val[] directly, apply_config() is part of the architecture-specific code, and is called via resctrl_arch_update_domains(). reset_all_ctrls() will be an architecture specific helper. update_mba_bw() manipulates both ctrl_val[], mbps_val[] and the hardware. The mbps_val[] that matches the mba_sc state of the resource is changed, but the other is left unchanged. Abstracting this is the subject of later patches that affect set_mba_sc() too. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-17-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 16 +++++++++--- arch/x86/kernel/cpu/resctrl/monitor.c | 6 ++++- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 43 +++++++++++++------------------ include/linux/resctrl.h | 2 ++ 4 files changed, 37 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 8cde76df888a..4da08ba0deda 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -401,22 +401,30 @@ out: return ret ?: nbytes; } +void resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, + u32 closid, u32 *value) +{ + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + + if (!is_mba_sc(r)) + *value = hw_dom->ctrl_val[closid]; + else + *value = hw_dom->mbps_val[closid]; +} + static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid) { struct rdt_resource *r = schema->res; - struct rdt_hw_domain *hw_dom; struct rdt_domain *dom; bool sep = false; u32 ctrl_val; seq_printf(s, "%*s:", max_name_width, schema->name); list_for_each_entry(dom, &r->domains, list) { - hw_dom = resctrl_to_arch_dom(dom); if (sep) seq_puts(s, ";"); - ctrl_val = (!is_mba_sc(r) ? hw_dom->ctrl_val[closid] : - hw_dom->mbps_val[closid]); + resctrl_arch_get_config(r, dom, closid, &ctrl_val); seq_printf(s, r->format_str, dom->id, max_data_width, ctrl_val); sep = true; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 26a094870c16..e45e7150eb81 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -442,8 +442,12 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) hw_dom_mba = resctrl_to_arch_dom(dom_mba); cur_bw = pmbm_data->prev_bw; - user_bw = hw_dom_mba->mbps_val[closid]; + resctrl_arch_get_config(r_mba, dom_mba, closid, &user_bw); delta_bw = pmbm_data->delta_bw; + /* + * resctrl_arch_get_config() chooses the mbps/ctrl value to return + * based on is_mba_sc(). For now, reach into the hw_dom. + */ cur_msr_val = hw_dom_mba->ctrl_val[closid]; /* diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 4b6de76493d6..6b2be5633536 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -910,27 +910,27 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, int i, hwb, swb, excl, psl; enum rdtgrp_mode mode; bool sep = false; - u32 *ctrl; + u32 ctrl_val; mutex_lock(&rdtgroup_mutex); hw_shareable = r->cache.shareable_bits; list_for_each_entry(dom, &r->domains, list) { if (sep) seq_putc(seq, ';'); - ctrl = resctrl_to_arch_dom(dom)->ctrl_val; sw_shareable = 0; exclusive = 0; seq_printf(seq, "%d=", dom->id); - for (i = 0; i < closids_supported(); i++, ctrl++) { + for (i = 0; i < closids_supported(); i++) { if (!closid_allocated(i)) continue; + resctrl_arch_get_config(r, dom, i, &ctrl_val); mode = rdtgroup_mode_by_closid(i); switch (mode) { case RDT_MODE_SHAREABLE: - sw_shareable |= *ctrl; + sw_shareable |= ctrl_val; break; case RDT_MODE_EXCLUSIVE: - exclusive |= *ctrl; + exclusive |= ctrl_val; break; case RDT_MODE_PSEUDO_LOCKSETUP: /* @@ -1188,7 +1188,6 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d { enum rdtgrp_mode mode; unsigned long ctrl_b; - u32 *ctrl; int i; /* Check for any overlap with regions used by hardware directly */ @@ -1199,9 +1198,8 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d } /* Check for overlap with other resource groups */ - ctrl = resctrl_to_arch_dom(d)->ctrl_val; - for (i = 0; i < closids_supported(); i++, ctrl++) { - ctrl_b = *ctrl; + for (i = 0; i < closids_supported(); i++) { + resctrl_arch_get_config(r, d, i, (u32 *)&ctrl_b); mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && mode != RDT_MODE_PSEUDO_LOCKSETUP) { @@ -1269,12 +1267,12 @@ bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, */ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) { - struct rdt_hw_domain *hw_dom; int closid = rdtgrp->closid; struct resctrl_schema *s; struct rdt_resource *r; bool has_cache = false; struct rdt_domain *d; + u32 ctrl; list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; @@ -1282,10 +1280,8 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) continue; has_cache = true; list_for_each_entry(d, &r->domains, list) { - hw_dom = resctrl_to_arch_dom(d); - if (rdtgroup_cbm_overlaps(s, d, - hw_dom->ctrl_val[closid], - rdtgrp->closid, false)) { + resctrl_arch_get_config(r, d, closid, &ctrl); + if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) { rdt_last_cmd_puts("Schemata overlaps\n"); return false; } @@ -1417,7 +1413,6 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { struct resctrl_schema *schema; - struct rdt_hw_domain *hw_dom; struct rdtgroup *rdtgrp; struct rdt_resource *r; struct rdt_domain *d; @@ -1453,15 +1448,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, sep = false; seq_printf(s, "%*s:", max_name_width, schema->name); list_for_each_entry(d, &r->domains, list) { - hw_dom = resctrl_to_arch_dom(d); if (sep) seq_putc(s, ';'); if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { size = 0; } else { - ctrl = (!is_mba_sc(r) ? - hw_dom->ctrl_val[rdtgrp->closid] : - hw_dom->mbps_val[rdtgrp->closid]); + resctrl_arch_get_config(r, d, rdtgrp->closid, + &ctrl); if (r->rid == RDT_RESOURCE_MBA) size = ctrl; else @@ -2759,7 +2752,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, u32 used_b = 0, unused_b = 0; unsigned long tmp_cbm; enum rdtgrp_mode mode; - u32 peer_ctl, *ctrl; + u32 peer_ctl, ctrl_val; int i; rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp); @@ -2767,8 +2760,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, cfg->have_new_ctrl = false; cfg->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; - ctrl = resctrl_to_arch_dom(d)->ctrl_val; - for (i = 0; i < closids_supported(); i++, ctrl++) { + for (i = 0; i < closids_supported(); i++) { if (closid_allocated(i) && i != closid) { mode = rdtgroup_mode_by_closid(i); if (mode == RDT_MODE_PSEUDO_LOCKSETUP) @@ -2784,12 +2776,13 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, * with an exclusive group. */ if (d_cdp) - peer_ctl = resctrl_to_arch_dom(d_cdp)->ctrl_val[i]; + resctrl_arch_get_config(r_cdp, d_cdp, i, &peer_ctl); else peer_ctl = 0; - used_b |= *ctrl | peer_ctl; + resctrl_arch_get_config(r, d, i, &ctrl_val); + used_b |= ctrl_val | peer_ctl; if (mode == RDT_MODE_SHAREABLE) - cfg->new_ctrl |= *ctrl | peer_ctl; + cfg->new_ctrl |= ctrl_val | peer_ctl; } } if (d->plr && d->plr->cbm > 0) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index be5881171576..3a2309403094 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -200,5 +200,7 @@ struct resctrl_schema { /* The number of closid supported by this resource regardless of CDP */ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); +void resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, + u32 closid, u32 *value); #endif /* _RESCTRL_H */ -- cgit v1.2.3 From ae03c3771b8cbbed3802ad1153d896c32015c520 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 5 Aug 2021 22:18:59 -0300 Subject: vfio: Introduce a vfio_uninit_group_dev() API call This pairs with vfio_init_group_dev() and allows undoing any state that is stored in the vfio_device unrelated to registration. Add appropriately placed calls to all the drivers. The following patch will use this to add pre-registration state for the device set. Signed-off-by: Max Gurtovoy Reviewed-by: Cornelia Huck Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/3-v4-9ea22c5e6afb+1adf-vfio_reflck_jgg@nvidia.com Signed-off-by: Alex Williamson --- Documentation/driver-api/vfio.rst | 4 +++- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 7 ++++--- drivers/vfio/mdev/vfio_mdev.c | 13 +++++++++---- drivers/vfio/pci/vfio_pci.c | 6 ++++-- drivers/vfio/platform/vfio_platform_common.c | 7 +++++-- drivers/vfio/vfio.c | 5 +++++ include/linux/vfio.h | 1 + samples/vfio-mdev/mbochs.c | 2 ++ samples/vfio-mdev/mdpy.c | 25 +++++++++++++++---------- samples/vfio-mdev/mtty.c | 27 ++++++++++++++++----------- 10 files changed, 64 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/vfio.rst b/Documentation/driver-api/vfio.rst index 606eed8823ce..c663b6f97825 100644 --- a/Documentation/driver-api/vfio.rst +++ b/Documentation/driver-api/vfio.rst @@ -255,11 +255,13 @@ vfio_unregister_group_dev() respectively:: void vfio_init_group_dev(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops); + void vfio_uninit_group_dev(struct vfio_device *device); int vfio_register_group_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); The driver should embed the vfio_device in its own structure and call -vfio_init_group_dev() to pre-configure it before going to registration. +vfio_init_group_dev() to pre-configure it before going to registration +and call vfio_uninit_group_dev() after completing the un-registration. vfio_register_group_dev() indicates to the core to begin tracking the iommu_group of the specified dev and register the dev as owned by a VFIO bus driver. Once vfio_register_group_dev() returns it is possible for userspace to diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index 90cad109583b..122997c61ba4 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -627,7 +627,7 @@ static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev) ret = vfio_fsl_mc_reflck_attach(vdev); if (ret) - goto out_kfree; + goto out_uninit; ret = vfio_fsl_mc_init_device(vdev); if (ret) @@ -657,7 +657,8 @@ out_device: vfio_fsl_uninit_device(vdev); out_reflck: vfio_fsl_mc_reflck_put(vdev->reflck); -out_kfree: +out_uninit: + vfio_uninit_group_dev(&vdev->vdev); kfree(vdev); out_group_put: vfio_iommu_group_put(group, dev); @@ -675,7 +676,7 @@ static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev) dprc_remove_devices(mc_dev, NULL, 0); vfio_fsl_uninit_device(vdev); vfio_fsl_mc_reflck_put(vdev->reflck); - + vfio_uninit_group_dev(&vdev->vdev); kfree(vdev); vfio_iommu_group_put(mc_dev->dev.iommu_group, dev); diff --git a/drivers/vfio/mdev/vfio_mdev.c b/drivers/vfio/mdev/vfio_mdev.c index 39ef7489fe47..a5c77ccb24f7 100644 --- a/drivers/vfio/mdev/vfio_mdev.c +++ b/drivers/vfio/mdev/vfio_mdev.c @@ -120,12 +120,16 @@ static int vfio_mdev_probe(struct mdev_device *mdev) vfio_init_group_dev(vdev, &mdev->dev, &vfio_mdev_dev_ops); ret = vfio_register_group_dev(vdev); - if (ret) { - kfree(vdev); - return ret; - } + if (ret) + goto out_uninit; + dev_set_drvdata(&mdev->dev, vdev); return 0; + +out_uninit: + vfio_uninit_group_dev(vdev); + kfree(vdev); + return ret; } static void vfio_mdev_remove(struct mdev_device *mdev) @@ -133,6 +137,7 @@ static void vfio_mdev_remove(struct mdev_device *mdev) struct vfio_device *vdev = dev_get_drvdata(&mdev->dev); vfio_unregister_group_dev(vdev); + vfio_uninit_group_dev(vdev); kfree(vdev); } diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 318864d52837..fab3715d60d4 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -2022,7 +2022,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = vfio_pci_reflck_attach(vdev); if (ret) - goto out_free; + goto out_uninit; ret = vfio_pci_vf_init(vdev); if (ret) goto out_reflck; @@ -2059,7 +2059,8 @@ out_vf: vfio_pci_vf_uninit(vdev); out_reflck: vfio_pci_reflck_put(vdev->reflck); -out_free: +out_uninit: + vfio_uninit_group_dev(&vdev->vdev); kfree(vdev->pm_save); kfree(vdev); out_group_put: @@ -2077,6 +2078,7 @@ static void vfio_pci_remove(struct pci_dev *pdev) vfio_pci_vf_uninit(vdev); vfio_pci_reflck_put(vdev->reflck); + vfio_uninit_group_dev(&vdev->vdev); vfio_pci_vga_uninit(vdev); vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev); diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index 703164df7637..bdde8605178c 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -667,7 +667,7 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev, ret = vfio_platform_of_probe(vdev, dev); if (ret) - return ret; + goto out_uninit; vdev->device = dev; @@ -675,7 +675,7 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev, if (ret && vdev->reset_required) { dev_err(dev, "No reset function found for device %s\n", vdev->name); - return ret; + goto out_uninit; } group = vfio_iommu_group_get(dev); @@ -698,6 +698,8 @@ put_iommu: vfio_iommu_group_put(group, dev); put_reset: vfio_platform_put_reset(vdev); +out_uninit: + vfio_uninit_group_dev(&vdev->vdev); return ret; } EXPORT_SYMBOL_GPL(vfio_platform_probe_common); @@ -708,6 +710,7 @@ void vfio_platform_remove_common(struct vfio_platform_device *vdev) pm_runtime_disable(vdev->device); vfio_platform_put_reset(vdev); + vfio_uninit_group_dev(&vdev->vdev); vfio_iommu_group_put(vdev->vdev.dev->iommu_group, vdev->vdev.dev); } EXPORT_SYMBOL_GPL(vfio_platform_remove_common); diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 02cc51ce6891..cc375df0fd5d 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -749,6 +749,11 @@ void vfio_init_group_dev(struct vfio_device *device, struct device *dev, } EXPORT_SYMBOL_GPL(vfio_init_group_dev); +void vfio_uninit_group_dev(struct vfio_device *device) +{ +} +EXPORT_SYMBOL_GPL(vfio_uninit_group_dev); + int vfio_register_group_dev(struct vfio_device *device) { struct vfio_device *existing_device; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index a2c5b30e1763..b0875cf8e496 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -61,6 +61,7 @@ extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev); void vfio_init_group_dev(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops); +void vfio_uninit_group_dev(struct vfio_device *device); int vfio_register_group_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); extern struct vfio_device *vfio_device_get_from_dev(struct device *dev); diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c index 3e885be7d076..0f1511849b7c 100644 --- a/samples/vfio-mdev/mbochs.c +++ b/samples/vfio-mdev/mbochs.c @@ -559,6 +559,7 @@ static int mbochs_probe(struct mdev_device *mdev) dev_set_drvdata(&mdev->dev, mdev_state); return 0; err_mem: + vfio_uninit_group_dev(&mdev_state->vdev); kfree(mdev_state->pages); kfree(mdev_state->vconfig); kfree(mdev_state); @@ -572,6 +573,7 @@ static void mbochs_remove(struct mdev_device *mdev) struct mdev_state *mdev_state = dev_get_drvdata(&mdev->dev); vfio_unregister_group_dev(&mdev_state->vdev); + vfio_uninit_group_dev(&mdev_state->vdev); atomic_add(mdev_state->type->mbytes, &mbochs_avail_mbytes); kfree(mdev_state->pages); kfree(mdev_state->vconfig); diff --git a/samples/vfio-mdev/mdpy.c b/samples/vfio-mdev/mdpy.c index a7d4ed28d664..57334034cde6 100644 --- a/samples/vfio-mdev/mdpy.c +++ b/samples/vfio-mdev/mdpy.c @@ -235,17 +235,16 @@ static int mdpy_probe(struct mdev_device *mdev) mdev_state->vconfig = kzalloc(MDPY_CONFIG_SPACE_SIZE, GFP_KERNEL); if (mdev_state->vconfig == NULL) { - kfree(mdev_state); - return -ENOMEM; + ret = -ENOMEM; + goto err_state; } fbsize = roundup_pow_of_two(type->width * type->height * type->bytepp); mdev_state->memblk = vmalloc_user(fbsize); if (!mdev_state->memblk) { - kfree(mdev_state->vconfig); - kfree(mdev_state); - return -ENOMEM; + ret = -ENOMEM; + goto err_vconfig; } dev_info(dev, "%s: %s (%dx%d)\n", __func__, type->name, type->width, type->height); @@ -260,13 +259,18 @@ static int mdpy_probe(struct mdev_device *mdev) mdpy_count++; ret = vfio_register_group_dev(&mdev_state->vdev); - if (ret) { - kfree(mdev_state->vconfig); - kfree(mdev_state); - return ret; - } + if (ret) + goto err_mem; dev_set_drvdata(&mdev->dev, mdev_state); return 0; +err_mem: + vfree(mdev_state->memblk); +err_vconfig: + kfree(mdev_state->vconfig); +err_state: + vfio_uninit_group_dev(&mdev_state->vdev); + kfree(mdev_state); + return ret; } static void mdpy_remove(struct mdev_device *mdev) @@ -278,6 +282,7 @@ static void mdpy_remove(struct mdev_device *mdev) vfio_unregister_group_dev(&mdev_state->vdev); vfree(mdev_state->memblk); kfree(mdev_state->vconfig); + vfio_uninit_group_dev(&mdev_state->vdev); kfree(mdev_state); mdpy_count--; diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c index 8b26fecc4afe..37cc9067e160 100644 --- a/samples/vfio-mdev/mtty.c +++ b/samples/vfio-mdev/mtty.c @@ -718,8 +718,8 @@ static int mtty_probe(struct mdev_device *mdev) mdev_state = kzalloc(sizeof(struct mdev_state), GFP_KERNEL); if (mdev_state == NULL) { - atomic_add(nr_ports, &mdev_avail_ports); - return -ENOMEM; + ret = -ENOMEM; + goto err_nr_ports; } vfio_init_group_dev(&mdev_state->vdev, &mdev->dev, &mtty_dev_ops); @@ -732,9 +732,8 @@ static int mtty_probe(struct mdev_device *mdev) mdev_state->vconfig = kzalloc(MTTY_CONFIG_SPACE_SIZE, GFP_KERNEL); if (mdev_state->vconfig == NULL) { - kfree(mdev_state); - atomic_add(nr_ports, &mdev_avail_ports); - return -ENOMEM; + ret = -ENOMEM; + goto err_state; } mutex_init(&mdev_state->ops_lock); @@ -743,14 +742,19 @@ static int mtty_probe(struct mdev_device *mdev) mtty_create_config_space(mdev_state); ret = vfio_register_group_dev(&mdev_state->vdev); - if (ret) { - kfree(mdev_state); - atomic_add(nr_ports, &mdev_avail_ports); - return ret; - } - + if (ret) + goto err_vconfig; dev_set_drvdata(&mdev->dev, mdev_state); return 0; + +err_vconfig: + kfree(mdev_state->vconfig); +err_state: + vfio_uninit_group_dev(&mdev_state->vdev); + kfree(mdev_state); +err_nr_ports: + atomic_add(nr_ports, &mdev_avail_ports); + return ret; } static void mtty_remove(struct mdev_device *mdev) @@ -761,6 +765,7 @@ static void mtty_remove(struct mdev_device *mdev) vfio_unregister_group_dev(&mdev_state->vdev); kfree(mdev_state->vconfig); + vfio_uninit_group_dev(&mdev_state->vdev); kfree(mdev_state); atomic_add(nr_ports, &mdev_avail_ports); } -- cgit v1.2.3 From 2fd585f4ed9de9b9259e95affdd7d8cde06b48c3 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 5 Aug 2021 22:19:00 -0300 Subject: vfio: Provide better generic support for open/release vfio_device_ops Currently the driver ops have an open/release pair that is called once each time a device FD is opened or closed. Add an additional set of open/close_device() ops which are called when the device FD is opened for the first time and closed for the last time. An analysis shows that all of the drivers require this semantic. Some are open coding it as part of their reflck implementation, and some are just buggy and miss it completely. To retain the current semantics PCI and FSL depend on, introduce the idea of a "device set" which is a grouping of vfio_device's that share the same lock around opening. The device set is established by providing a 'set_id' pointer. All vfio_device's that provide the same pointer will be joined to the same singleton memory and lock across the whole set. This effectively replaces the oddly named reflck. After conversion the set_id will be sourced from: - A struct device from a fsl_mc_device (fsl) - A struct pci_slot (pci) - A struct pci_bus (pci) - The struct vfio_device (everything) The design ensures that the above pointers are live as long as the vfio_device is registered, so they form reliable unique keys to group vfio_devices into sets. This implementation uses xarray instead of searching through the driver core structures, which simplifies the somewhat tricky locking in this area. Following patches convert all the drivers. Signed-off-by: Yishai Hadas Reviewed-by: Cornelia Huck Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/4-v4-9ea22c5e6afb+1adf-vfio_reflck_jgg@nvidia.com Signed-off-by: Alex Williamson --- drivers/vfio/mdev/vfio_mdev.c | 26 +++++++- drivers/vfio/vfio.c | 149 +++++++++++++++++++++++++++++++++++------- include/linux/mdev.h | 2 + include/linux/vfio.h | 21 ++++++ 4 files changed, 174 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/mdev/vfio_mdev.c b/drivers/vfio/mdev/vfio_mdev.c index a5c77ccb24f7..e12196ffd487 100644 --- a/drivers/vfio/mdev/vfio_mdev.c +++ b/drivers/vfio/mdev/vfio_mdev.c @@ -17,13 +17,33 @@ #include "mdev_private.h" +static int vfio_mdev_open_device(struct vfio_device *core_vdev) +{ + struct mdev_device *mdev = to_mdev_device(core_vdev->dev); + struct mdev_parent *parent = mdev->type->parent; + + if (unlikely(!parent->ops->open_device)) + return 0; + + return parent->ops->open_device(mdev); +} + +static void vfio_mdev_close_device(struct vfio_device *core_vdev) +{ + struct mdev_device *mdev = to_mdev_device(core_vdev->dev); + struct mdev_parent *parent = mdev->type->parent; + + if (likely(parent->ops->close_device)) + parent->ops->close_device(mdev); +} + static int vfio_mdev_open(struct vfio_device *core_vdev) { struct mdev_device *mdev = to_mdev_device(core_vdev->dev); struct mdev_parent *parent = mdev->type->parent; if (unlikely(!parent->ops->open)) - return -EINVAL; + return 0; return parent->ops->open(mdev); } @@ -44,7 +64,7 @@ static long vfio_mdev_unlocked_ioctl(struct vfio_device *core_vdev, struct mdev_parent *parent = mdev->type->parent; if (unlikely(!parent->ops->ioctl)) - return -EINVAL; + return 0; return parent->ops->ioctl(mdev, cmd, arg); } @@ -100,6 +120,8 @@ static void vfio_mdev_request(struct vfio_device *core_vdev, unsigned int count) static const struct vfio_device_ops vfio_mdev_dev_ops = { .name = "vfio-mdev", + .open_device = vfio_mdev_open_device, + .close_device = vfio_mdev_close_device, .open = vfio_mdev_open, .release = vfio_mdev_release, .ioctl = vfio_mdev_unlocked_ioctl, diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index cc375df0fd5d..9cc17768c425 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -96,6 +96,79 @@ module_param_named(enable_unsafe_noiommu_mode, MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)"); #endif +static DEFINE_XARRAY(vfio_device_set_xa); + +int vfio_assign_device_set(struct vfio_device *device, void *set_id) +{ + unsigned long idx = (unsigned long)set_id; + struct vfio_device_set *new_dev_set; + struct vfio_device_set *dev_set; + + if (WARN_ON(!set_id)) + return -EINVAL; + + /* + * Atomically acquire a singleton object in the xarray for this set_id + */ + xa_lock(&vfio_device_set_xa); + dev_set = xa_load(&vfio_device_set_xa, idx); + if (dev_set) + goto found_get_ref; + xa_unlock(&vfio_device_set_xa); + + new_dev_set = kzalloc(sizeof(*new_dev_set), GFP_KERNEL); + if (!new_dev_set) + return -ENOMEM; + mutex_init(&new_dev_set->lock); + INIT_LIST_HEAD(&new_dev_set->device_list); + new_dev_set->set_id = set_id; + + xa_lock(&vfio_device_set_xa); + dev_set = __xa_cmpxchg(&vfio_device_set_xa, idx, NULL, new_dev_set, + GFP_KERNEL); + if (!dev_set) { + dev_set = new_dev_set; + goto found_get_ref; + } + + kfree(new_dev_set); + if (xa_is_err(dev_set)) { + xa_unlock(&vfio_device_set_xa); + return xa_err(dev_set); + } + +found_get_ref: + dev_set->device_count++; + xa_unlock(&vfio_device_set_xa); + mutex_lock(&dev_set->lock); + device->dev_set = dev_set; + list_add_tail(&device->dev_set_list, &dev_set->device_list); + mutex_unlock(&dev_set->lock); + return 0; +} +EXPORT_SYMBOL_GPL(vfio_assign_device_set); + +static void vfio_release_device_set(struct vfio_device *device) +{ + struct vfio_device_set *dev_set = device->dev_set; + + if (!dev_set) + return; + + mutex_lock(&dev_set->lock); + list_del(&device->dev_set_list); + mutex_unlock(&dev_set->lock); + + xa_lock(&vfio_device_set_xa); + if (!--dev_set->device_count) { + __xa_erase(&vfio_device_set_xa, + (unsigned long)dev_set->set_id); + mutex_destroy(&dev_set->lock); + kfree(dev_set); + } + xa_unlock(&vfio_device_set_xa); +} + /* * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe * and remove functions, any use cases other than acquiring the first @@ -751,6 +824,7 @@ EXPORT_SYMBOL_GPL(vfio_init_group_dev); void vfio_uninit_group_dev(struct vfio_device *device) { + vfio_release_device_set(device); } EXPORT_SYMBOL_GPL(vfio_uninit_group_dev); @@ -760,6 +834,13 @@ int vfio_register_group_dev(struct vfio_device *device) struct iommu_group *iommu_group; struct vfio_group *group; + /* + * If the driver doesn't specify a set then the device is added to a + * singleton set just for itself. + */ + if (!device->dev_set) + vfio_assign_device_set(device, device); + iommu_group = iommu_group_get(device->dev); if (!iommu_group) return -EINVAL; @@ -1361,7 +1442,8 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) { struct vfio_device *device; struct file *filep; - int ret; + int fdno; + int ret = 0; if (0 == atomic_read(&group->container_users) || !group->container->iommu_driver || !vfio_group_viable(group)) @@ -1375,38 +1457,38 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) return PTR_ERR(device); if (!try_module_get(device->dev->driver->owner)) { - vfio_device_put(device); - return -ENODEV; + ret = -ENODEV; + goto err_device_put; } - ret = device->ops->open(device); - if (ret) { - module_put(device->dev->driver->owner); - vfio_device_put(device); - return ret; + mutex_lock(&device->dev_set->lock); + device->open_count++; + if (device->open_count == 1 && device->ops->open_device) { + ret = device->ops->open_device(device); + if (ret) + goto err_undo_count; + } + mutex_unlock(&device->dev_set->lock); + + if (device->ops->open) { + ret = device->ops->open(device); + if (ret) + goto err_close_device; } /* * We can't use anon_inode_getfd() because we need to modify * the f_mode flags directly to allow more than just ioctls */ - ret = get_unused_fd_flags(O_CLOEXEC); - if (ret < 0) { - device->ops->release(device); - module_put(device->dev->driver->owner); - vfio_device_put(device); - return ret; - } + fdno = ret = get_unused_fd_flags(O_CLOEXEC); + if (ret < 0) + goto err_release; filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops, device, O_RDWR); if (IS_ERR(filep)) { - put_unused_fd(ret); ret = PTR_ERR(filep); - device->ops->release(device); - module_put(device->dev->driver->owner); - vfio_device_put(device); - return ret; + goto err_fd; } /* @@ -1418,12 +1500,28 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) atomic_inc(&group->container_users); - fd_install(ret, filep); + fd_install(fdno, filep); if (group->noiommu) dev_warn(device->dev, "vfio-noiommu device opened by user " "(%s:%d)\n", current->comm, task_pid_nr(current)); + return fdno; +err_fd: + put_unused_fd(fdno); +err_release: + if (device->ops->release) + device->ops->release(device); +err_close_device: + mutex_lock(&device->dev_set->lock); + if (device->open_count == 1 && device->ops->close_device) + device->ops->close_device(device); +err_undo_count: + device->open_count--; + mutex_unlock(&device->dev_set->lock); + module_put(device->dev->driver->owner); +err_device_put: + vfio_device_put(device); return ret; } @@ -1561,7 +1659,13 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep) { struct vfio_device *device = filep->private_data; - device->ops->release(device); + if (device->ops->release) + device->ops->release(device); + + mutex_lock(&device->dev_set->lock); + if (!--device->open_count && device->ops->close_device) + device->ops->close_device(device); + mutex_unlock(&device->dev_set->lock); module_put(device->dev->driver->owner); @@ -2364,6 +2468,7 @@ static void __exit vfio_cleanup(void) class_destroy(vfio.class); vfio.class = NULL; misc_deregister(&vfio_dev); + xa_destroy(&vfio_device_set_xa); } module_init(vfio_init); diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 3a38598c2605..cb5b7ed1d7c3 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -111,6 +111,8 @@ struct mdev_parent_ops { int (*create)(struct mdev_device *mdev); int (*remove)(struct mdev_device *mdev); + int (*open_device)(struct mdev_device *mdev); + void (*close_device)(struct mdev_device *mdev); int (*open)(struct mdev_device *mdev); void (*release)(struct mdev_device *mdev); ssize_t (*read)(struct mdev_device *mdev, char __user *buf, diff --git a/include/linux/vfio.h b/include/linux/vfio.h index b0875cf8e496..f0e6a72875e4 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -15,13 +15,28 @@ #include #include +/* + * VFIO devices can be placed in a set, this allows all devices to share this + * structure and the VFIO core will provide a lock that is held around + * open_device()/close_device() for all devices in the set. + */ +struct vfio_device_set { + void *set_id; + struct mutex lock; + struct list_head device_list; + unsigned int device_count; +}; + struct vfio_device { struct device *dev; const struct vfio_device_ops *ops; struct vfio_group *group; + struct vfio_device_set *dev_set; + struct list_head dev_set_list; /* Members below here are private, not for driver use */ refcount_t refcount; + unsigned int open_count; struct completion comp; struct list_head group_next; }; @@ -29,6 +44,8 @@ struct vfio_device { /** * struct vfio_device_ops - VFIO bus driver device callbacks * + * @open_device: Called when the first file descriptor is opened for this device + * @close_device: Opposite of open_device * @open: Called when userspace creates new file descriptor for device * @release: Called when userspace releases file descriptor for device * @read: Perform read(2) on device file descriptor @@ -43,6 +60,8 @@ struct vfio_device { */ struct vfio_device_ops { char *name; + int (*open_device)(struct vfio_device *vdev); + void (*close_device)(struct vfio_device *vdev); int (*open)(struct vfio_device *vdev); void (*release)(struct vfio_device *vdev); ssize_t (*read)(struct vfio_device *vdev, char __user *buf, @@ -67,6 +86,8 @@ void vfio_unregister_group_dev(struct vfio_device *device); extern struct vfio_device *vfio_device_get_from_dev(struct device *dev); extern void vfio_device_put(struct vfio_device *device); +int vfio_assign_device_set(struct vfio_device *device, void *set_id); + /* events for the backend driver notify callback */ enum vfio_iommu_notify_type { VFIO_IOMMU_CONTAINER_CLOSE = 0, -- cgit v1.2.3 From eb24c1007e6852e024dc33b0dd9617b8500a1291 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 5 Aug 2021 22:19:10 -0300 Subject: vfio: Remove struct vfio_device_ops open/release Nothing uses this anymore, delete it. Signed-off-by: Yishai Hadas Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Reviewed-by: Cornelia Huck Link: https://lore.kernel.org/r/14-v4-9ea22c5e6afb+1adf-vfio_reflck_jgg@nvidia.com Signed-off-by: Alex Williamson --- drivers/vfio/mdev/vfio_mdev.c | 22 ---------------------- drivers/vfio/vfio.c | 14 +------------- include/linux/mdev.h | 7 ------- include/linux/vfio.h | 4 ---- 4 files changed, 1 insertion(+), 46 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/mdev/vfio_mdev.c b/drivers/vfio/mdev/vfio_mdev.c index e12196ffd487..7a9883048216 100644 --- a/drivers/vfio/mdev/vfio_mdev.c +++ b/drivers/vfio/mdev/vfio_mdev.c @@ -37,26 +37,6 @@ static void vfio_mdev_close_device(struct vfio_device *core_vdev) parent->ops->close_device(mdev); } -static int vfio_mdev_open(struct vfio_device *core_vdev) -{ - struct mdev_device *mdev = to_mdev_device(core_vdev->dev); - struct mdev_parent *parent = mdev->type->parent; - - if (unlikely(!parent->ops->open)) - return 0; - - return parent->ops->open(mdev); -} - -static void vfio_mdev_release(struct vfio_device *core_vdev) -{ - struct mdev_device *mdev = to_mdev_device(core_vdev->dev); - struct mdev_parent *parent = mdev->type->parent; - - if (likely(parent->ops->release)) - parent->ops->release(mdev); -} - static long vfio_mdev_unlocked_ioctl(struct vfio_device *core_vdev, unsigned int cmd, unsigned long arg) { @@ -122,8 +102,6 @@ static const struct vfio_device_ops vfio_mdev_dev_ops = { .name = "vfio-mdev", .open_device = vfio_mdev_open_device, .close_device = vfio_mdev_close_device, - .open = vfio_mdev_open, - .release = vfio_mdev_release, .ioctl = vfio_mdev_unlocked_ioctl, .read = vfio_mdev_read, .write = vfio_mdev_write, diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 9cc17768c425..3c034fe14ccb 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1470,19 +1470,13 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) } mutex_unlock(&device->dev_set->lock); - if (device->ops->open) { - ret = device->ops->open(device); - if (ret) - goto err_close_device; - } - /* * We can't use anon_inode_getfd() because we need to modify * the f_mode flags directly to allow more than just ioctls */ fdno = ret = get_unused_fd_flags(O_CLOEXEC); if (ret < 0) - goto err_release; + goto err_close_device; filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops, device, O_RDWR); @@ -1509,9 +1503,6 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) err_fd: put_unused_fd(fdno); -err_release: - if (device->ops->release) - device->ops->release(device); err_close_device: mutex_lock(&device->dev_set->lock); if (device->open_count == 1 && device->ops->close_device) @@ -1659,9 +1650,6 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep) { struct vfio_device *device = filep->private_data; - if (device->ops->release) - device->ops->release(device); - mutex_lock(&device->dev_set->lock); if (!--device->open_count && device->ops->close_device) device->ops->close_device(device); diff --git a/include/linux/mdev.h b/include/linux/mdev.h index cb5b7ed1d7c3..68427e8fadeb 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -72,11 +72,6 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype); * @mdev: mdev_device device structure which is being * destroyed * Returns integer: success (0) or error (< 0) - * @open: Open mediated device. - * @mdev: mediated device. - * Returns integer: success (0) or error (< 0) - * @release: release mediated device - * @mdev: mediated device. * @read: Read emulation callback * @mdev: mediated device structure * @buf: read buffer @@ -113,8 +108,6 @@ struct mdev_parent_ops { int (*remove)(struct mdev_device *mdev); int (*open_device)(struct mdev_device *mdev); void (*close_device)(struct mdev_device *mdev); - int (*open)(struct mdev_device *mdev); - void (*release)(struct mdev_device *mdev); ssize_t (*read)(struct mdev_device *mdev, char __user *buf, size_t count, loff_t *ppos); ssize_t (*write)(struct mdev_device *mdev, const char __user *buf, diff --git a/include/linux/vfio.h b/include/linux/vfio.h index f0e6a72875e4..b53a9557884a 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -46,8 +46,6 @@ struct vfio_device { * * @open_device: Called when the first file descriptor is opened for this device * @close_device: Opposite of open_device - * @open: Called when userspace creates new file descriptor for device - * @release: Called when userspace releases file descriptor for device * @read: Perform read(2) on device file descriptor * @write: Perform write(2) on device file descriptor * @ioctl: Perform ioctl(2) on device file descriptor, supporting VFIO_DEVICE_* @@ -62,8 +60,6 @@ struct vfio_device_ops { char *name; int (*open_device)(struct vfio_device *vdev); void (*close_device)(struct vfio_device *vdev); - int (*open)(struct vfio_device *vdev); - void (*release)(struct vfio_device *vdev); ssize_t (*read)(struct vfio_device *vdev, char __user *buf, size_t count, loff_t *ppos); ssize_t (*write)(struct vfio_device *vdev, const char __user *buf, -- cgit v1.2.3 From fa8f711d2f14381d1a47420b6da94b62e6484c56 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:30 +0000 Subject: x86/resctrl: Pass configuration type to resctrl_arch_get_config() The ctrl_val[] array for a struct rdt_hw_resource only holds configurations of one type. The type is implicit. Once the CDP resources are merged, the ctrl_val[] array will hold all the configurations for the hardware resource. When a particular type of configuration is needed, it must be specified explicitly. Pass the expected type from the schema into resctrl_arch_get_config(). Nothing uses this yet, but once a single ctrl_val[] array is used for the three struct rdt_hw_resources that share hardware, the type will be used to return the correct configuration value from the shared array. Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-18-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 5 +++-- arch/x86/kernel/cpu/resctrl/monitor.c | 2 +- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 35 ++++++++++++++++++++----------- include/linux/resctrl.h | 3 ++- 4 files changed, 29 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 4da08ba0deda..9ead0c0bf6ee 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -402,7 +402,7 @@ out: } void resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, - u32 closid, u32 *value) + u32 closid, enum resctrl_conf_type type, u32 *value) { struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); @@ -424,7 +424,8 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo if (sep) seq_puts(s, ";"); - resctrl_arch_get_config(r, dom, closid, &ctrl_val); + resctrl_arch_get_config(r, dom, closid, schema->conf_type, + &ctrl_val); seq_printf(s, r->format_str, dom->id, max_data_width, ctrl_val); sep = true; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index e45e7150eb81..eb227298487f 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -442,7 +442,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) hw_dom_mba = resctrl_to_arch_dom(dom_mba); cur_bw = pmbm_data->prev_bw; - resctrl_arch_get_config(r_mba, dom_mba, closid, &user_bw); + resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE, &user_bw); delta_bw = pmbm_data->delta_bw; /* * resctrl_arch_get_config() chooses the mbps/ctrl value to return diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 6b2be5633536..61037b239327 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -923,7 +923,8 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, for (i = 0; i < closids_supported(); i++) { if (!closid_allocated(i)) continue; - resctrl_arch_get_config(r, dom, i, &ctrl_val); + resctrl_arch_get_config(r, dom, i, s->conf_type, + &ctrl_val); mode = rdtgroup_mode_by_closid(i); switch (mode) { case RDT_MODE_SHAREABLE: @@ -1099,6 +1100,7 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, * Used to return the result. * @d_cdp: RDT domain that shares hardware with @d (RDT domain peer) * Used to return the result. + * @peer_type: The CDP configuration type of the peer resource. * * RDT resources are managed independently and by extension the RDT domains * (RDT resource instances) are managed independently also. The Code and @@ -1116,7 +1118,8 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, */ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, struct rdt_resource **r_cdp, - struct rdt_domain **d_cdp) + struct rdt_domain **d_cdp, + enum resctrl_conf_type *peer_type) { struct rdt_resource *_r_cdp = NULL; struct rdt_domain *_d_cdp = NULL; @@ -1125,15 +1128,19 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, switch (r->rid) { case RDT_RESOURCE_L3DATA: _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE].r_resctrl; + *peer_type = CDP_CODE; break; case RDT_RESOURCE_L3CODE: _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3DATA].r_resctrl; + *peer_type = CDP_DATA; break; case RDT_RESOURCE_L2DATA: _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2CODE].r_resctrl; + *peer_type = CDP_CODE; break; case RDT_RESOURCE_L2CODE: _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2DATA].r_resctrl; + *peer_type = CDP_DATA; break; default: ret = -ENOENT; @@ -1184,7 +1191,8 @@ out: * Return: false if CBM does not overlap, true if it does. */ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - unsigned long cbm, int closid, bool exclusive) + unsigned long cbm, int closid, + enum resctrl_conf_type type, bool exclusive) { enum rdtgrp_mode mode; unsigned long ctrl_b; @@ -1199,7 +1207,7 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d /* Check for overlap with other resource groups */ for (i = 0; i < closids_supported(); i++) { - resctrl_arch_get_config(r, d, i, (u32 *)&ctrl_b); + resctrl_arch_get_config(r, d, i, type, (u32 *)&ctrl_b); mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && mode != RDT_MODE_PSEUDO_LOCKSETUP) { @@ -1240,17 +1248,19 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, unsigned long cbm, int closid, bool exclusive) { + enum resctrl_conf_type peer_type; struct rdt_resource *r = s->res; struct rdt_resource *r_cdp; struct rdt_domain *d_cdp; - if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, exclusive)) + if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, s->conf_type, + exclusive)) return true; - if (rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp) < 0) + if (rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp, &peer_type) < 0) return false; - return __rdtgroup_cbm_overlaps(r_cdp, d_cdp, cbm, closid, exclusive); + return __rdtgroup_cbm_overlaps(r_cdp, d_cdp, cbm, closid, peer_type, exclusive); } /** @@ -1280,7 +1290,7 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) continue; has_cache = true; list_for_each_entry(d, &r->domains, list) { - resctrl_arch_get_config(r, d, closid, &ctrl); + resctrl_arch_get_config(r, d, closid, s->conf_type, &ctrl); if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) { rdt_last_cmd_puts("Schemata overlaps\n"); return false; @@ -1454,7 +1464,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, size = 0; } else { resctrl_arch_get_config(r, d, rdtgrp->closid, - &ctrl); + schema->conf_type, &ctrl); if (r->rid == RDT_RESOURCE_MBA) size = ctrl; else @@ -2747,6 +2757,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, enum resctrl_conf_type t = s->conf_type; struct rdt_resource *r_cdp = NULL; struct resctrl_staged_config *cfg; + enum resctrl_conf_type peer_type; struct rdt_domain *d_cdp = NULL; struct rdt_resource *r = s->res; u32 used_b = 0, unused_b = 0; @@ -2755,7 +2766,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, u32 peer_ctl, ctrl_val; int i; - rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp); + rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp, &peer_type); cfg = &d->staged_config[t]; cfg->have_new_ctrl = false; cfg->new_ctrl = r->cache.shareable_bits; @@ -2776,10 +2787,10 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, * with an exclusive group. */ if (d_cdp) - resctrl_arch_get_config(r_cdp, d_cdp, i, &peer_ctl); + resctrl_arch_get_config(r_cdp, d_cdp, i, peer_type, &peer_ctl); else peer_ctl = 0; - resctrl_arch_get_config(r, d, i, &ctrl_val); + resctrl_arch_get_config(r, d, i, s->conf_type, &ctrl_val); used_b |= ctrl_val | peer_ctl; if (mode == RDT_MODE_SHAREABLE) cfg->new_ctrl |= ctrl_val | peer_ctl; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 3a2309403094..69d7387b7f22 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -201,6 +201,7 @@ struct resctrl_schema { u32 resctrl_arch_get_num_closid(struct rdt_resource *r); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); void resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, - u32 closid, u32 *value); + u32 closid, enum resctrl_conf_type type, + u32 *value); #endif /* _RESCTRL_H */ -- cgit v1.2.3 From 2b8dd4ab65dad1251822fbf74fb0d5623e4eaee0 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 28 Jul 2021 17:06:33 +0000 Subject: x86/resctrl: Calculate the index from the configuration type resctrl uses cbm_idx() to map a closid to an index in the configuration array. This is based on a multiplier and offset that are held in the resource. To merge the resources, the resctrl arch code needs to calculate the index from something else, as there will only be one resource. Decide based on the staged configuration type. This makes the static mult and offset parameters redundant. [ bp: Remove superfluous brackets in get_config_index() ] Signed-off-by: James Morse Signed-off-by: Borislav Petkov Reviewed-by: Jamie Iles Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lkml.kernel.org/r/20210728170637.25610-21-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/core.c | 12 ------------ arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 25 +++++++++++++++---------- include/linux/resctrl.h | 6 ------ 3 files changed, 15 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 990e41661b4a..c6b953fe7fdf 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -69,8 +69,6 @@ struct rdt_hw_resource rdt_resources_all[] = { .cache_level = 3, .cache = { .min_cbm_bits = 1, - .cbm_idx_mult = 1, - .cbm_idx_offset = 0, }, .domains = domain_init(RDT_RESOURCE_L3), .parse_ctrlval = parse_cbm, @@ -89,8 +87,6 @@ struct rdt_hw_resource rdt_resources_all[] = { .cache_level = 3, .cache = { .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 0, }, .domains = domain_init(RDT_RESOURCE_L3DATA), .parse_ctrlval = parse_cbm, @@ -109,8 +105,6 @@ struct rdt_hw_resource rdt_resources_all[] = { .cache_level = 3, .cache = { .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 1, }, .domains = domain_init(RDT_RESOURCE_L3CODE), .parse_ctrlval = parse_cbm, @@ -129,8 +123,6 @@ struct rdt_hw_resource rdt_resources_all[] = { .cache_level = 2, .cache = { .min_cbm_bits = 1, - .cbm_idx_mult = 1, - .cbm_idx_offset = 0, }, .domains = domain_init(RDT_RESOURCE_L2), .parse_ctrlval = parse_cbm, @@ -149,8 +141,6 @@ struct rdt_hw_resource rdt_resources_all[] = { .cache_level = 2, .cache = { .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 0, }, .domains = domain_init(RDT_RESOURCE_L2DATA), .parse_ctrlval = parse_cbm, @@ -169,8 +159,6 @@ struct rdt_hw_resource rdt_resources_all[] = { .cache_level = 2, .cache = { .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 1, }, .domains = domain_init(RDT_RESOURCE_L2CODE), .parse_ctrlval = parse_cbm, diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index fdb0e11a78dc..92d79c88b965 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -246,12 +246,17 @@ next: return -EINVAL; } -static u32 cbm_idx(struct rdt_resource *r, unsigned int closid) +static u32 get_config_index(u32 closid, enum resctrl_conf_type type) { - if (r->rid == RDT_RESOURCE_MBA) + switch (type) { + default: + case CDP_NONE: return closid; - - return closid * r->cache.cbm_idx_mult + r->cache.cbm_idx_offset; + case CDP_CODE: + return closid * 2 + 1; + case CDP_DATA: + return closid * 2; + } } static bool apply_config(struct rdt_hw_domain *hw_dom, @@ -286,10 +291,6 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; - msr_param.low = cbm_idx(r, closid); - msr_param.high = msr_param.low + 1; - msr_param.res = r; - mba_sc = is_mba_sc(r); list_for_each_entry(d, &r->domains, list) { hw_dom = resctrl_to_arch_dom(d); @@ -298,9 +299,13 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) if (!cfg->have_new_ctrl) continue; - idx = cbm_idx(r, closid); + idx = get_config_index(closid, t); if (!apply_config(hw_dom, cfg, idx, cpu_mask, mba_sc)) continue; + + msr_param.low = idx; + msr_param.high = msr_param.low + 1; + msr_param.res = r; } } @@ -420,7 +425,7 @@ void resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, u32 closid, enum resctrl_conf_type type, u32 *value) { struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); - u32 idx = cbm_idx(r, closid); + u32 idx = get_config_index(closid, type); if (!is_mba_sc(r)) *value = hw_dom->ctrl_val[idx]; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 69d7387b7f22..18dd764af0dd 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -73,10 +73,6 @@ struct rdt_domain { * struct resctrl_cache - Cache allocation related data * @cbm_len: Length of the cache bit mask * @min_cbm_bits: Minimum number of consecutive bits to be set - * @cbm_idx_mult: Multiplier of CBM index - * @cbm_idx_offset: Offset of CBM index. CBM index is computed by: - * closid * cbm_idx_multi + cbm_idx_offset - * in a cache bit mask * @shareable_bits: Bitmask of shareable resource with other * executing entities * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. @@ -87,8 +83,6 @@ struct rdt_domain { struct resctrl_cache { unsigned int cbm_len; unsigned int min_cbm_bits; - unsigned int cbm_idx_mult; // TODO remove this - unsigned int cbm_idx_offset; // TODO remove this unsigned int shareable_bits; bool arch_has_sparse_bitmaps; bool arch_has_empty_bitmaps; -- cgit v1.2.3 From 111136e69c9df50c3ca7d4e3977344b8a2d0d947 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 11 Aug 2021 16:38:31 +0000 Subject: x86/resctrl: Make resctrl_arch_get_config() return its value resctrl_arch_get_config() has no return, but does pass a single value back via one of its arguments. Return the value instead. Suggested-by: Borislav Petkov Signed-off-by: James Morse Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210811163831.14917-1-james.morse@arm.com --- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 13 ++++++------- arch/x86/kernel/cpu/resctrl/monitor.c | 2 +- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 20 ++++++++++++-------- include/linux/resctrl.h | 5 ++--- 4 files changed, 21 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index a487cf7ff04e..87666275eed9 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -427,16 +427,15 @@ out: return ret ?: nbytes; } -void resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, - u32 closid, enum resctrl_conf_type type, u32 *value) +u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, + u32 closid, enum resctrl_conf_type type) { struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); u32 idx = get_config_index(closid, type); if (!is_mba_sc(r)) - *value = hw_dom->ctrl_val[idx]; - else - *value = hw_dom->mbps_val[idx]; + return hw_dom->ctrl_val[idx]; + return hw_dom->mbps_val[idx]; } static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid) @@ -451,8 +450,8 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo if (sep) seq_puts(s, ";"); - resctrl_arch_get_config(r, dom, closid, schema->conf_type, - &ctrl_val); + ctrl_val = resctrl_arch_get_config(r, dom, closid, + schema->conf_type); seq_printf(s, r->format_str, dom->id, max_data_width, ctrl_val); sep = true; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index eb227298487f..b0741bee79fc 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -442,7 +442,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) hw_dom_mba = resctrl_to_arch_dom(dom_mba); cur_bw = pmbm_data->prev_bw; - resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE, &user_bw); + user_bw = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); delta_bw = pmbm_data->delta_bw; /* * resctrl_arch_get_config() chooses the mbps/ctrl value to return diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 89123a4977cf..b57b3db9a6a7 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -923,8 +923,8 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, for (i = 0; i < closids_supported(); i++) { if (!closid_allocated(i)) continue; - resctrl_arch_get_config(r, dom, i, s->conf_type, - &ctrl_val); + ctrl_val = resctrl_arch_get_config(r, dom, i, + s->conf_type); mode = rdtgroup_mode_by_closid(i); switch (mode) { case RDT_MODE_SHAREABLE: @@ -1142,7 +1142,7 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d /* Check for overlap with other resource groups */ for (i = 0; i < closids_supported(); i++) { - resctrl_arch_get_config(r, d, i, type, (u32 *)&ctrl_b); + ctrl_b = resctrl_arch_get_config(r, d, i, type); mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && mode != RDT_MODE_PSEUDO_LOCKSETUP) { @@ -1222,7 +1222,8 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) continue; has_cache = true; list_for_each_entry(d, &r->domains, list) { - resctrl_arch_get_config(r, d, closid, s->conf_type, &ctrl); + ctrl = resctrl_arch_get_config(r, d, closid, + s->conf_type); if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) { rdt_last_cmd_puts("Schemata overlaps\n"); return false; @@ -1395,8 +1396,9 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { size = 0; } else { - resctrl_arch_get_config(r, d, rdtgrp->closid, - schema->conf_type, &ctrl); + ctrl = resctrl_arch_get_config(r, d, + rdtgrp->closid, + schema->conf_type); if (r->rid == RDT_RESOURCE_MBA) size = ctrl; else @@ -2724,10 +2726,12 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, * with an exclusive group. */ if (resctrl_arch_get_cdp_enabled(r->rid)) - resctrl_arch_get_config(r, d, i, peer_type, &peer_ctl); + peer_ctl = resctrl_arch_get_config(r, d, i, + peer_type); else peer_ctl = 0; - resctrl_arch_get_config(r, d, i, s->conf_type, &ctrl_val); + ctrl_val = resctrl_arch_get_config(r, d, i, + s->conf_type); used_b |= ctrl_val | peer_ctl; if (mode == RDT_MODE_SHAREABLE) cfg->new_ctrl |= ctrl_val | peer_ctl; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 18dd764af0dd..21deb5212bbd 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -194,8 +194,7 @@ struct resctrl_schema { /* The number of closid supported by this resource regardless of CDP */ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); -void resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, - u32 closid, enum resctrl_conf_type type, - u32 *value); +u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, + u32 closid, enum resctrl_conf_type type); #endif /* _RESCTRL_H */ -- cgit v1.2.3 From 39c538d64479c949aaeca4fe73d2226f715adfb7 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Fri, 30 Jul 2021 11:03:00 +0800 Subject: net/mlx5: Fix typo in comments Fix typo: *vectores ==> vectors *realeased ==> released *erros ==> errors *namepsace ==> namespace *trafic ==> traffic *proccessed ==> processed *retore ==> restore *Currenlty ==> Currently *crated ==> created *chane ==> change *cannnot ==> cannot *usuallly ==> usually *failes ==> fails *importent ==> important *reenabled ==> re-enabled *alocation ==> allocation *recived ==> received *tanslation ==> translation Signed-off-by: Cai Huoqing Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_rep.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/events.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/health.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c | 2 +- include/linux/mlx5/device.h | 2 +- include/linux/mlx5/driver.h | 4 ++-- 16 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 8f79f04eccd6..a61731cb6045 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -520,7 +520,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->out_dev = attr.out_dev; e->route_dev_ifindex = attr.route_dev->ifindex; - /* It's importent to add the neigh to the hash table before checking + /* It's important to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the * neigh changes it's validity state, we would find the relevant neigh * in the hash. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index c06267477b27..538bc2419bd8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -126,7 +126,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, /* Create a separate SQ, so that when the buff pool is disabled, we could * close this SQ safely and stop receiving CQEs. In other case, e.g., if * the XDPSQ was used instead, we might run into trouble when the buff pool - * is disabled and then reenabled, but the SQ continues receiving CQEs + * is disabled and then re-enabled, but the SQ continues receiving CQEs * from the old buff pool. */ err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, pool, &c->xsksq, true); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index c4db367d4baf..84eb7201c142 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -33,7 +33,7 @@ #include "en.h" /* mlx5e global resources should be placed in this file. - * Global resources are common to all the netdevices crated on the same nic. + * Global resources are common to all the netdevices created on the same nic. */ void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 8f0c82448eec..756f806401d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -146,7 +146,7 @@ struct mlx5e_neigh_hash_entry { */ refcount_t refcnt; - /* Save the last reported time offloaded trafic pass over one of the + /* Save the last reported time offloaded traffic pass over one of the * neigh hash entry flows. Use it to periodically update the neigh * 'used' value and avoid neigh deleting by the kernel. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e5c4344a114e..d6ad7328f298 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -97,7 +97,7 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { [MARK_TO_REG] = mark_to_reg_ct, [LABELS_TO_REG] = labels_to_reg_ct, [FTEID_TO_REG] = fteid_to_reg_ct, - /* For NIC rules we store the retore metadata directly + /* For NIC rules we store the restore metadata directly * into reg_b that is passed to SW since we don't * jump between steering domains. */ @@ -2448,7 +2448,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3; } } - /* Currenlty supported only for MPLS over UDP */ + /* Currently supported only for MPLS over UDP */ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS) && !netif_is_bareudp(filter_dev)) { NL_SET_ERR_MSG_MOD(extack, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 7ffea2350f44..2fde9f59e8b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1492,7 +1492,7 @@ abort: /** * mlx5_eswitch_enable - Enable eswitch * @esw: Pointer to eswitch - * @num_vfs: Enable eswitch swich for given number of VFs. + * @num_vfs: Enable eswitch switch for given number of VFs. * Caller must pass num_vfs > 0 when enabling eswitch for * vf vports. * mlx5_eswitch_enable() returns 0 on success or error code on failure. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index d713ae24d6b6..a1ac3a654962 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -27,7 +27,7 @@ static int pcie_core(struct notifier_block *, unsigned long, void *); static int forward_event(struct notifier_block *, unsigned long, void *); static struct mlx5_nb events_nbs_ref[] = { - /* Events to be proccessed by mlx5_core */ + /* Events to be processed by mlx5_core */ {.nb.notifier_call = any_notifier, .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY }, {.nb.notifier_call = temp_warn, .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT }, {.nb.notifier_call = port_module, .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c index 0bba92cf5dc0..8ec148010d62 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -1516,7 +1516,7 @@ static int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, mutex_lock(&fpga_xfrm->lock); if (!fpga_xfrm->sa_ctx) - /* Unbounded xfrm, chane only sw attrs */ + /* Unbounded xfrm, change only sw attrs */ goto change_sw_xfrm_attrs; /* copy original hw sa */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 8481027e493c..fee51050ed64 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2493,7 +2493,7 @@ static void set_prio_attrs_in_prio(struct fs_prio *prio, int acc_level) acc_level_ns = set_prio_attrs_in_ns(ns, acc_level); /* If this a prio with chains, and we can jump from one chain - * (namepsace) to another, so we accumulate the levels + * (namespace) to another, so we accumulate the levels */ if (prio->node.type == FS_TYPE_PRIO_CHAINS) acc_level = acc_level_ns; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 9abeb80ffa31..4a7de1259004 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -170,7 +170,7 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev) /* The reset only needs to be issued by one PF. The health buffer is * shared between all functions, and will be cleared during a reset. - * Check again to avoid a redundant 2nd reset. If the fatal erros was + * Check again to avoid a redundant 2nd reset. If the fatal errors was * PCI related a reset won't help. */ fatal_error = mlx5_health_check_fatal_sensors(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index ce696d523493..ffac8a0e7a23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -749,7 +749,7 @@ static int mlx5_pps_event(struct notifier_block *nb, } else { ptp_event.type = PTP_CLOCK_EXTTS; } - /* TODOL clock->ptp can be NULL if ptp_clock_register failes */ + /* TODOL clock->ptp can be NULL if ptp_clock_register fails */ ptp_clock_event(clock->ptp, &ptp_event); break; case PTP_PF_PEROUT: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c index 38084400ee8f..e3b0a131c3e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -40,7 +40,7 @@ struct mlx5_vxlan { struct mlx5_core_dev *mdev; - /* max_num_ports is usuallly 4, 16 buckets is more than enough */ + /* max_num_ports is usually 4, 16 buckets is more than enough */ DECLARE_HASHTABLE(htable, 4); struct mutex sync_lock; /* sync add/del port HW operations */ }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index b25f764daa08..9fb75d79bf08 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -18,7 +18,7 @@ #define MLX5_SFS_PER_CTRL_IRQ 64 #define MLX5_IRQ_CTRL_SF_MAX 8 -/* min num of vectores for SFs to be enabled */ +/* min num of vectors for SFs to be enabled */ #define MLX5_IRQ_VEC_COMP_BASE_SF 2 #define MLX5_EQ_SHARE_IRQ_MAX_COMP (8) @@ -597,7 +597,7 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) return; /* There are cases where IRQs still will be in used when we reaching - * to here. Hence, making sure all the irqs are realeased. + * to here. Hence, making sure all the irqs are released. */ irq_pools_destroy(table); pci_free_irq_vectors(dev->pdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index 720195c4be7c..13891fdc607e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -476,7 +476,7 @@ static void mlx5_sf_table_disable(struct mlx5_sf_table *table) return; /* Balances with refcount_set; drop the reference so that new user cmd cannot start - * and new vhca event handler cannnot run. + * and new vhca event handler cannot run. */ mlx5_sf_table_put(table); wait_for_completion(&table->disable_complete); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0025913505ab..1e9d55dc1a9c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1038,7 +1038,7 @@ enum { struct mlx5_mkey_seg { /* This is a two bit field occupying bits 31-30. * bit 31 is always 0, - * bit 30 is zero for regular MRs and 1 (e.g free) for UMRs that do not have tanslation + * bit 30 is zero for regular MRs and 1 (e.g free) for UMRs that do not have translation */ u8 status; u8 pcie_control; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index af4dd6e9f97f..524051d1b2e3 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -581,7 +581,7 @@ struct mlx5_priv { /* end: qp staff */ /* start: alloc staff */ - /* protect buffer alocation according to numa node */ + /* protect buffer allocation according to numa node */ struct mutex alloc_mutex; int numa_node; @@ -1111,7 +1111,7 @@ static inline u8 mlx5_mkey_variant(u32 mkey) } /* Async-atomic event notifier used by mlx5 core to forward FW - * evetns recived from event queue to mlx5 consumers. + * evetns received from event queue to mlx5 consumers. * Optimise event queue dipatching. */ int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); -- cgit v1.2.3 From 8e792700b994a4b79abe1303eb379bbd1f4212be Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 1 Aug 2021 11:37:57 +0300 Subject: net/mlx5: Delete impossible dev->state checks New mlx5_core device structure is allocated through devlink_alloc with\ kzalloc and that ensures that all fields are equal to zero and it includes ->state too. That means that checks of that field in the mlx5_init_one() is completely redundant, because that function is called only once in the begging of mlx5_core_dev lifetime. PCI: .probe() -> probe_one() -> mlx5_init_one() The recovery flow can't run at that time or before it, because relevant work initialized later in mlx5_init_once(). Such initialization flow ensures that dev->state can't be MLX5_DEVICE_STATE_UNINITIALIZED at all, so remove such impossible checks. Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 4 ---- drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ------ include/linux/mlx5/driver.h | 3 +-- 3 files changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 4a7de1259004..037e18dd4be0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -213,10 +213,6 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) mutex_lock(&dev->intf_state_mutex); if (!err_detected && dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) goto unlock;/* a previous error is still being handled */ - if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) { - dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; - goto unlock; - } enter_error_state(dev, force); unlock: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 6fe560307c05..1a65e744d2e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1249,11 +1249,6 @@ int mlx5_init_one(struct mlx5_core_dev *dev) int err = 0; mutex_lock(&dev->intf_state_mutex); - if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { - mlx5_core_warn(dev, "interface is up, NOP\n"); - goto out; - } - /* remove any previous indication of internal error */ dev->state = MLX5_DEVICE_STATE_UP; err = mlx5_function_setup(dev, true); @@ -1294,7 +1289,6 @@ function_teardown: mlx5_function_teardown(dev, true); err_function: dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; -out: mutex_unlock(&dev->intf_state_mutex); return err; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 524051d1b2e3..2b5c5604b091 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -623,8 +623,7 @@ struct mlx5_priv { }; enum mlx5_device_state { - MLX5_DEVICE_STATE_UNINITIALIZED, - MLX5_DEVICE_STATE_UP, + MLX5_DEVICE_STATE_UP = 1, MLX5_DEVICE_STATE_INTERNAL_ERROR, }; -- cgit v1.2.3 From 5958a6fad623ad3b67a9e4d8dbd5f1874cc7039e Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 13 Jul 2021 12:36:05 +0300 Subject: net/mlx5: Reorganize current and maximal capabilities to be per-type In the current code, the current and maximal capabilities are maintained in separate arrays which are both per type. In order to allow the creation of such a basic structure as a dynamically allocated array, we move curr and max fields to a unified structure so that specific capabilities can be allocated as one unit. Signed-off-by: Parav Pandit Reviewed-by: Leon Romanovsky Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/main.c | 10 ++-- include/linux/mlx5/device.h | 66 +++++++++++------------ include/linux/mlx5/driver.h | 8 ++- 4 files changed, 45 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index fee51050ed64..813ff8186829 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2343,7 +2343,7 @@ static int create_leaf_prios(struct mlx5_flow_namespace *ns, int prio, #define FLOW_TABLE_BIT_SZ 1 #define GET_FLOW_TABLE_CAP(dev, offset) \ - ((be32_to_cpu(*((__be32 *)(dev->caps.hca_cur[MLX5_CAP_FLOW_TABLE]) + \ + ((be32_to_cpu(*((__be32 *)(dev->caps.hca[MLX5_CAP_FLOW_TABLE].cur) + \ offset / 32)) >> \ (32 - FLOW_TABLE_BIT_SZ - (offset & 0x1f))) & FLOW_TABLE_BIT_SZ) static bool has_required_caps(struct mlx5_core_dev *dev, struct node_caps *caps) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 1a65e744d2e2..6cefe2a981c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -389,11 +389,11 @@ static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, switch (cap_mode) { case HCA_CAP_OPMOD_GET_MAX: - memcpy(dev->caps.hca_max[cap_type], hca_caps, + memcpy(dev->caps.hca[cap_type].max, hca_caps, MLX5_UN_SZ_BYTES(hca_cap_union)); break; case HCA_CAP_OPMOD_GET_CUR: - memcpy(dev->caps.hca_cur[cap_type], hca_caps, + memcpy(dev->caps.hca[cap_type].cur, hca_caps, MLX5_UN_SZ_BYTES(hca_cap_union)); break; default: @@ -469,7 +469,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) return err; set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); - memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP], + memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ODP].cur, MLX5_ST_SZ_BYTES(odp_cap)); #define ODP_CAP_SET_MAX(dev, field) \ @@ -514,7 +514,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); - memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_GENERAL], + memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_GENERAL].cur, MLX5_ST_SZ_BYTES(cmd_hca_cap)); mlx5_core_dbg(dev, "Current Pkey table size %d Setting new size %d\n", @@ -596,7 +596,7 @@ static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx) return 0; set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); - memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ROCE], + memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ROCE].cur, MLX5_ST_SZ_BYTES(roce_cap)); MLX5_SET(roce_cap, set_hca_cap, sw_r_roce_src_udp_port, 1); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 1e9d55dc1a9c..2736f12bb57c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1213,55 +1213,55 @@ enum mlx5_qcam_feature_groups { /* GET Dev Caps macros */ #define MLX5_CAP_GEN(mdev, cap) \ - MLX5_GET(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap) + MLX5_GET(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL].cur, cap) #define MLX5_CAP_GEN_64(mdev, cap) \ - MLX5_GET64(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap) + MLX5_GET64(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL].cur, cap) #define MLX5_CAP_GEN_MAX(mdev, cap) \ - MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap) + MLX5_GET(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL].max, cap) #define MLX5_CAP_GEN_2(mdev, cap) \ - MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2].cur, cap) #define MLX5_CAP_GEN_2_64(mdev, cap) \ - MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2].cur, cap) #define MLX5_CAP_GEN_2_MAX(mdev, cap) \ - MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_max[MLX5_CAP_GENERAL_2], cap) + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2].max, cap) #define MLX5_CAP_ETH(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) + mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS].cur, cap) #define MLX5_CAP_ETH_MAX(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca_max[MLX5_CAP_ETHERNET_OFFLOADS], cap) + mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS].max, cap) #define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca_cur[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS], cap) + mdev->caps.hca[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS].cur, cap) #define MLX5_CAP_ROCE(mdev, cap) \ - MLX5_GET(roce_cap, mdev->caps.hca_cur[MLX5_CAP_ROCE], cap) + MLX5_GET(roce_cap, mdev->caps.hca[MLX5_CAP_ROCE].cur, cap) #define MLX5_CAP_ROCE_MAX(mdev, cap) \ - MLX5_GET(roce_cap, mdev->caps.hca_max[MLX5_CAP_ROCE], cap) + MLX5_GET(roce_cap, mdev->caps.hca[MLX5_CAP_ROCE].max, cap) #define MLX5_CAP_ATOMIC(mdev, cap) \ - MLX5_GET(atomic_caps, mdev->caps.hca_cur[MLX5_CAP_ATOMIC], cap) + MLX5_GET(atomic_caps, mdev->caps.hca[MLX5_CAP_ATOMIC].cur, cap) #define MLX5_CAP_ATOMIC_MAX(mdev, cap) \ - MLX5_GET(atomic_caps, mdev->caps.hca_max[MLX5_CAP_ATOMIC], cap) + MLX5_GET(atomic_caps, mdev->caps.hca[MLX5_CAP_ATOMIC].max, cap) #define MLX5_CAP_FLOWTABLE(mdev, cap) \ - MLX5_GET(flow_table_nic_cap, mdev->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap) + MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE].cur, cap) #define MLX5_CAP64_FLOWTABLE(mdev, cap) \ - MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap) + MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca[MLX5_CAP_FLOW_TABLE].cur, cap) #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ - MLX5_GET(flow_table_nic_cap, mdev->caps.hca_max[MLX5_CAP_FLOW_TABLE], cap) + MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE].max, cap) #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap) @@ -1301,11 +1301,11 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ - mdev->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE].cur, cap) #define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ - mdev->caps.hca_max[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE].max, cap) #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap) @@ -1327,31 +1327,31 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ - mdev->caps.hca_cur[MLX5_CAP_ESWITCH], cap) + mdev->caps.hca[MLX5_CAP_ESWITCH].cur, cap) #define MLX5_CAP64_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET64(flow_table_eswitch_cap, \ - (mdev)->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + (mdev)->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE].cur, cap) #define MLX5_CAP_ESW_MAX(mdev, cap) \ MLX5_GET(e_switch_cap, \ - mdev->caps.hca_max[MLX5_CAP_ESWITCH], cap) + mdev->caps.hca[MLX5_CAP_ESWITCH].max, cap) #define MLX5_CAP_ODP(mdev, cap)\ - MLX5_GET(odp_cap, mdev->caps.hca_cur[MLX5_CAP_ODP], cap) + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP].cur, cap) #define MLX5_CAP_ODP_MAX(mdev, cap)\ - MLX5_GET(odp_cap, mdev->caps.hca_max[MLX5_CAP_ODP], cap) + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP].max, cap) #define MLX5_CAP_VECTOR_CALC(mdev, cap) \ MLX5_GET(vector_calc_cap, \ - mdev->caps.hca_cur[MLX5_CAP_VECTOR_CALC], cap) + mdev->caps.hca[MLX5_CAP_VECTOR_CALC].cur, cap) #define MLX5_CAP_QOS(mdev, cap)\ - MLX5_GET(qos_cap, mdev->caps.hca_cur[MLX5_CAP_QOS], cap) + MLX5_GET(qos_cap, mdev->caps.hca[MLX5_CAP_QOS].cur, cap) #define MLX5_CAP_DEBUG(mdev, cap)\ - MLX5_GET(debug_cap, mdev->caps.hca_cur[MLX5_CAP_DEBUG], cap) + MLX5_GET(debug_cap, mdev->caps.hca[MLX5_CAP_DEBUG].cur, cap) #define MLX5_CAP_PCAM_FEATURE(mdev, fld) \ MLX5_GET(pcam_reg, (mdev)->caps.pcam, feature_cap_mask.enhanced_features.fld) @@ -1387,27 +1387,27 @@ enum mlx5_qcam_feature_groups { MLX5_GET64(fpga_cap, (mdev)->caps.fpga, cap) #define MLX5_CAP_DEV_MEM(mdev, cap)\ - MLX5_GET(device_mem_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_MEM], cap) + MLX5_GET(device_mem_cap, mdev->caps.hca[MLX5_CAP_DEV_MEM].cur, cap) #define MLX5_CAP64_DEV_MEM(mdev, cap)\ - MLX5_GET64(device_mem_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_MEM], cap) + MLX5_GET64(device_mem_cap, mdev->caps.hca[MLX5_CAP_DEV_MEM].cur, cap) #define MLX5_CAP_TLS(mdev, cap) \ - MLX5_GET(tls_cap, (mdev)->caps.hca_cur[MLX5_CAP_TLS], cap) + MLX5_GET(tls_cap, (mdev)->caps.hca[MLX5_CAP_TLS].cur, cap) #define MLX5_CAP_DEV_EVENT(mdev, cap)\ - MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap) + MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca[MLX5_CAP_DEV_EVENT].cur, cap) #define MLX5_CAP_DEV_VDPA_EMULATION(mdev, cap)\ MLX5_GET(virtio_emulation_cap, \ - (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap) + (mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION].cur, cap) #define MLX5_CAP64_DEV_VDPA_EMULATION(mdev, cap)\ MLX5_GET64(virtio_emulation_cap, \ - (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap) + (mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION].cur, cap) #define MLX5_CAP_IPSEC(mdev, cap)\ - MLX5_GET(ipsec_cap, (mdev)->caps.hca_cur[MLX5_CAP_IPSEC], cap) + MLX5_GET(ipsec_cap, (mdev)->caps.hca[MLX5_CAP_IPSEC].cur, cap) enum { MLX5_CMD_STAT_OK = 0x0, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2b5c5604b091..854443ea812c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -729,6 +729,11 @@ struct mlx5_profile { } mr_cache[MAX_MR_CACHE_ENTRIES]; }; +struct mlx5_hca_cap { + u32 cur[MLX5_UN_SZ_DW(hca_cap_union)]; + u32 max[MLX5_UN_SZ_DW(hca_cap_union)]; +}; + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -740,8 +745,7 @@ struct mlx5_core_dev { char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; struct { - u32 hca_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; - u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; + struct mlx5_hca_cap hca[MLX5_CAP_NUM]; u32 pcam[MLX5_ST_SZ_DW(pcam_reg)]; u32 mcam[MLX5_MCAM_REGS_NUM][MLX5_ST_SZ_DW(mcam_reg)]; u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; -- cgit v1.2.3 From 48f02eef7f764f33e520ed8009d293396ca690cd Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 13 Jul 2021 14:17:03 +0300 Subject: net/mlx5: Allocate individual capability Currently mlx5_core_dev contains array of capabilities. It contains 19 valid capabilities of the device, 2 reserved entries and 12 holes. Due to this for 14 unused entries, mlx5_core_dev allocates 14 * 8K = 112K bytes of memory which is never used. Due to this mlx5_core_dev structure size is 270Kbytes odd. This allocation further aligns to next power of 2 to 512Kbytes. By skipping non-existent entries, (a) 112Kbyte is saved, (b) mlx5_core_dev reduces to 8KB with alignment (c) 350KB saved in alignment In future individual capability allocation can be used to skip its allocation when such capability is disabled at the device level. This patch prepares mlx5_core_dev to hold capability using a pointer instead of inline array. Signed-off-by: Parav Pandit Reviewed-by: Leon Romanovsky Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/main.c | 71 +++++++++++++++++++++-- include/linux/mlx5/device.h | 69 +++++++++++----------- include/linux/mlx5/driver.h | 2 +- 4 files changed, 104 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 813ff8186829..9fe8e3c204d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2343,7 +2343,7 @@ static int create_leaf_prios(struct mlx5_flow_namespace *ns, int prio, #define FLOW_TABLE_BIT_SZ 1 #define GET_FLOW_TABLE_CAP(dev, offset) \ - ((be32_to_cpu(*((__be32 *)(dev->caps.hca[MLX5_CAP_FLOW_TABLE].cur) + \ + ((be32_to_cpu(*((__be32 *)(dev->caps.hca[MLX5_CAP_FLOW_TABLE]->cur) + \ offset / 32)) >> \ (32 - FLOW_TABLE_BIT_SZ - (offset & 0x1f))) & FLOW_TABLE_BIT_SZ) static bool has_required_caps(struct mlx5_core_dev *dev, struct node_caps *caps) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 6cefe2a981c7..20f693cf58cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -389,11 +389,11 @@ static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, switch (cap_mode) { case HCA_CAP_OPMOD_GET_MAX: - memcpy(dev->caps.hca[cap_type].max, hca_caps, + memcpy(dev->caps.hca[cap_type]->max, hca_caps, MLX5_UN_SZ_BYTES(hca_cap_union)); break; case HCA_CAP_OPMOD_GET_CUR: - memcpy(dev->caps.hca[cap_type].cur, hca_caps, + memcpy(dev->caps.hca[cap_type]->cur, hca_caps, MLX5_UN_SZ_BYTES(hca_cap_union)); break; default: @@ -469,7 +469,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) return err; set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); - memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ODP].cur, + memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ODP]->cur, MLX5_ST_SZ_BYTES(odp_cap)); #define ODP_CAP_SET_MAX(dev, field) \ @@ -514,7 +514,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); - memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_GENERAL].cur, + memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_GENERAL]->cur, MLX5_ST_SZ_BYTES(cmd_hca_cap)); mlx5_core_dbg(dev, "Current Pkey table size %d Setting new size %d\n", @@ -596,7 +596,7 @@ static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx) return 0; set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); - memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ROCE].cur, + memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ROCE]->cur, MLX5_ST_SZ_BYTES(roce_cap)); MLX5_SET(roce_cap, set_hca_cap, sw_r_roce_src_udp_port, 1); @@ -1375,6 +1375,60 @@ out: mutex_unlock(&dev->intf_state_mutex); } +static const int types[] = { + MLX5_CAP_GENERAL, + MLX5_CAP_GENERAL_2, + MLX5_CAP_ETHERNET_OFFLOADS, + MLX5_CAP_IPOIB_ENHANCED_OFFLOADS, + MLX5_CAP_ODP, + MLX5_CAP_ATOMIC, + MLX5_CAP_ROCE, + MLX5_CAP_IPOIB_OFFLOADS, + MLX5_CAP_FLOW_TABLE, + MLX5_CAP_ESWITCH_FLOW_TABLE, + MLX5_CAP_ESWITCH, + MLX5_CAP_VECTOR_CALC, + MLX5_CAP_QOS, + MLX5_CAP_DEBUG, + MLX5_CAP_DEV_MEM, + MLX5_CAP_DEV_EVENT, + MLX5_CAP_TLS, + MLX5_CAP_VDPA_EMULATION, + MLX5_CAP_IPSEC, +}; + +static void mlx5_hca_caps_free(struct mlx5_core_dev *dev) +{ + int type; + int i; + + for (i = 0; i < ARRAY_SIZE(types); i++) { + type = types[i]; + kfree(dev->caps.hca[type]); + } +} + +static int mlx5_hca_caps_alloc(struct mlx5_core_dev *dev) +{ + struct mlx5_hca_cap *cap; + int type; + int i; + + for (i = 0; i < ARRAY_SIZE(types); i++) { + cap = kzalloc(sizeof(*cap), GFP_KERNEL); + if (!cap) + goto err; + type = types[i]; + dev->caps.hca[type] = cap; + } + + return 0; + +err: + mlx5_hca_caps_free(dev); + return -ENOMEM; +} + int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) { struct mlx5_priv *priv = &dev->priv; @@ -1410,8 +1464,14 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) if (err) goto err_adev_init; + err = mlx5_hca_caps_alloc(dev); + if (err) + goto err_hca_caps; + return 0; +err_hca_caps: + mlx5_adev_cleanup(dev); err_adev_init: mlx5_pagealloc_cleanup(dev); err_pagealloc_init: @@ -1430,6 +1490,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; + mlx5_hca_caps_free(dev); mlx5_adev_cleanup(dev); mlx5_pagealloc_cleanup(dev); mlx5_health_cleanup(dev); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 2736f12bb57c..66eaf0aa7f69 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1157,6 +1157,9 @@ enum mlx5_cap_mode { HCA_CAP_OPMOD_GET_CUR = 1, }; +/* Any new cap addition must update mlx5_hca_caps_alloc() to allocate + * capability memory. + */ enum mlx5_cap_type { MLX5_CAP_GENERAL = 0, MLX5_CAP_ETHERNET_OFFLOADS, @@ -1213,55 +1216,55 @@ enum mlx5_qcam_feature_groups { /* GET Dev Caps macros */ #define MLX5_CAP_GEN(mdev, cap) \ - MLX5_GET(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL].cur, cap) + MLX5_GET(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL]->cur, cap) #define MLX5_CAP_GEN_64(mdev, cap) \ - MLX5_GET64(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL].cur, cap) + MLX5_GET64(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL]->cur, cap) #define MLX5_CAP_GEN_MAX(mdev, cap) \ - MLX5_GET(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL].max, cap) + MLX5_GET(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL]->max, cap) #define MLX5_CAP_GEN_2(mdev, cap) \ - MLX5_GET(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2].cur, cap) + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2]->cur, cap) #define MLX5_CAP_GEN_2_64(mdev, cap) \ - MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2].cur, cap) + MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2]->cur, cap) #define MLX5_CAP_GEN_2_MAX(mdev, cap) \ - MLX5_GET(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2].max, cap) + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2]->max, cap) #define MLX5_CAP_ETH(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS].cur, cap) + mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->cur, cap) #define MLX5_CAP_ETH_MAX(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS].max, cap) + mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->max, cap) #define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS].cur, cap) + mdev->caps.hca[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS]->cur, cap) #define MLX5_CAP_ROCE(mdev, cap) \ - MLX5_GET(roce_cap, mdev->caps.hca[MLX5_CAP_ROCE].cur, cap) + MLX5_GET(roce_cap, mdev->caps.hca[MLX5_CAP_ROCE]->cur, cap) #define MLX5_CAP_ROCE_MAX(mdev, cap) \ - MLX5_GET(roce_cap, mdev->caps.hca[MLX5_CAP_ROCE].max, cap) + MLX5_GET(roce_cap, mdev->caps.hca[MLX5_CAP_ROCE]->max, cap) #define MLX5_CAP_ATOMIC(mdev, cap) \ - MLX5_GET(atomic_caps, mdev->caps.hca[MLX5_CAP_ATOMIC].cur, cap) + MLX5_GET(atomic_caps, mdev->caps.hca[MLX5_CAP_ATOMIC]->cur, cap) #define MLX5_CAP_ATOMIC_MAX(mdev, cap) \ - MLX5_GET(atomic_caps, mdev->caps.hca[MLX5_CAP_ATOMIC].max, cap) + MLX5_GET(atomic_caps, mdev->caps.hca[MLX5_CAP_ATOMIC]->max, cap) #define MLX5_CAP_FLOWTABLE(mdev, cap) \ - MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE].cur, cap) + MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE]->cur, cap) #define MLX5_CAP64_FLOWTABLE(mdev, cap) \ - MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca[MLX5_CAP_FLOW_TABLE].cur, cap) + MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca[MLX5_CAP_FLOW_TABLE]->cur, cap) #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ - MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE].max, cap) + MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE]->max, cap) #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap) @@ -1301,11 +1304,11 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ - mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE].cur, cap) + mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap) #define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ - mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE].max, cap) + mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->max, cap) #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap) @@ -1327,31 +1330,31 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ - mdev->caps.hca[MLX5_CAP_ESWITCH].cur, cap) + mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) #define MLX5_CAP64_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET64(flow_table_eswitch_cap, \ - (mdev)->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE].cur, cap) + (mdev)->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap) #define MLX5_CAP_ESW_MAX(mdev, cap) \ MLX5_GET(e_switch_cap, \ - mdev->caps.hca[MLX5_CAP_ESWITCH].max, cap) + mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap) #define MLX5_CAP_ODP(mdev, cap)\ - MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP].cur, cap) + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) #define MLX5_CAP_ODP_MAX(mdev, cap)\ - MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP].max, cap) + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap) #define MLX5_CAP_VECTOR_CALC(mdev, cap) \ MLX5_GET(vector_calc_cap, \ - mdev->caps.hca[MLX5_CAP_VECTOR_CALC].cur, cap) + mdev->caps.hca[MLX5_CAP_VECTOR_CALC]->cur, cap) #define MLX5_CAP_QOS(mdev, cap)\ - MLX5_GET(qos_cap, mdev->caps.hca[MLX5_CAP_QOS].cur, cap) + MLX5_GET(qos_cap, mdev->caps.hca[MLX5_CAP_QOS]->cur, cap) #define MLX5_CAP_DEBUG(mdev, cap)\ - MLX5_GET(debug_cap, mdev->caps.hca[MLX5_CAP_DEBUG].cur, cap) + MLX5_GET(debug_cap, mdev->caps.hca[MLX5_CAP_DEBUG]->cur, cap) #define MLX5_CAP_PCAM_FEATURE(mdev, fld) \ MLX5_GET(pcam_reg, (mdev)->caps.pcam, feature_cap_mask.enhanced_features.fld) @@ -1387,27 +1390,27 @@ enum mlx5_qcam_feature_groups { MLX5_GET64(fpga_cap, (mdev)->caps.fpga, cap) #define MLX5_CAP_DEV_MEM(mdev, cap)\ - MLX5_GET(device_mem_cap, mdev->caps.hca[MLX5_CAP_DEV_MEM].cur, cap) + MLX5_GET(device_mem_cap, mdev->caps.hca[MLX5_CAP_DEV_MEM]->cur, cap) #define MLX5_CAP64_DEV_MEM(mdev, cap)\ - MLX5_GET64(device_mem_cap, mdev->caps.hca[MLX5_CAP_DEV_MEM].cur, cap) + MLX5_GET64(device_mem_cap, mdev->caps.hca[MLX5_CAP_DEV_MEM]->cur, cap) #define MLX5_CAP_TLS(mdev, cap) \ - MLX5_GET(tls_cap, (mdev)->caps.hca[MLX5_CAP_TLS].cur, cap) + MLX5_GET(tls_cap, (mdev)->caps.hca[MLX5_CAP_TLS]->cur, cap) #define MLX5_CAP_DEV_EVENT(mdev, cap)\ - MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca[MLX5_CAP_DEV_EVENT].cur, cap) + MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca[MLX5_CAP_DEV_EVENT]->cur, cap) #define MLX5_CAP_DEV_VDPA_EMULATION(mdev, cap)\ MLX5_GET(virtio_emulation_cap, \ - (mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION].cur, cap) + (mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION]->cur, cap) #define MLX5_CAP64_DEV_VDPA_EMULATION(mdev, cap)\ MLX5_GET64(virtio_emulation_cap, \ - (mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION].cur, cap) + (mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION]->cur, cap) #define MLX5_CAP_IPSEC(mdev, cap)\ - MLX5_GET(ipsec_cap, (mdev)->caps.hca[MLX5_CAP_IPSEC].cur, cap) + MLX5_GET(ipsec_cap, (mdev)->caps.hca[MLX5_CAP_IPSEC]->cur, cap) enum { MLX5_CMD_STAT_OK = 0x0, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 854443ea812c..90e5f42baa50 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -745,7 +745,7 @@ struct mlx5_core_dev { char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; struct { - struct mlx5_hca_cap hca[MLX5_CAP_NUM]; + struct mlx5_hca_cap *hca[MLX5_CAP_NUM]; u32 pcam[MLX5_ST_SZ_DW(pcam_reg)]; u32 mcam[MLX5_MCAM_REGS_NUM][MLX5_ST_SZ_DW(mcam_reg)]; u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; -- cgit v1.2.3 From b69dd5b3780a7298bd893816a09da751bc0636f7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Aug 2021 12:57:15 -0700 Subject: net: igmp: increase size of mr_ifc_count Some arches support cmpxchg() on 4-byte and 8-byte only. Increase mr_ifc_count width to 32bit to fix this problem. Fixes: 4a2b285e7e10 ("net: igmp: fix data-race in igmp_ifc_timer_expire()") Signed-off-by: Eric Dumazet Reported-by: Guenter Roeck Link: https://lore.kernel.org/r/20210811195715.3684218-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/inetdevice.h | 2 +- net/ipv4/igmp.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 53aa0343bf69..aaf4f1b4c277 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -41,7 +41,7 @@ struct in_device { unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; - unsigned char mr_ifc_count; + u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a51360087b19..00576bae183d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -803,7 +803,7 @@ static void igmp_gq_timer_expire(struct timer_list *t) static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); - u8 mr_ifc_count; + u32 mr_ifc_count; igmpv3_send_cr(in_dev); restart: -- cgit v1.2.3 From 018eca456c4b4dca56aaf1ec27f309c74d0fe246 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Wed, 21 Jul 2021 10:53:15 +0800 Subject: block: move some macros to blkdev.h Move them (PAGE_SECTORS_SHIFT, PAGE_SECTORS and SECTOR_MASK) to the generic header file to remove redundancy. Signed-off-by: Guoqing Jiang Link: https://lore.kernel.org/r/20210721025315.1729118-1-guoqing.jiang@linux.dev Signed-off-by: Jens Axboe --- drivers/block/brd.c | 3 --- drivers/block/null_blk/main.c | 4 ---- drivers/md/bcache/util.h | 2 -- include/linux/blkdev.h | 4 ++++ include/linux/device-mapper.h | 1 - 5 files changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 95694113e38e..58ec167aa018 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -27,9 +27,6 @@ #include -#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) -#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) - /* * Each block ramdisk device has a radix_tree brd_pages of pages that stores * the pages containing the block device's contents. A brd page's ->index is diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index d734e9ee1546..f128242d1170 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -11,10 +11,6 @@ #include #include "null_blk.h" -#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) -#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) -#define SECTOR_MASK (PAGE_SECTORS - 1) - #define FREE_BATCH 16 #define TICKS_PER_SEC 50ULL diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index bca4a7c97da7..b64460a76267 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -15,8 +15,6 @@ #include "closure.h" -#define PAGE_SECTORS (PAGE_SIZE / 512) - struct closure; #ifdef CONFIG_BCACHE_DEBUG diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 07eef02325b4..df404c1fb087 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -939,6 +939,10 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) #define SECTOR_SIZE (1 << SECTOR_SHIFT) #endif +#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) +#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) +#define SECTOR_MASK (PAGE_SECTORS - 1) + /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 7457d49acf9a..94f2cd6a8e83 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -151,7 +151,6 @@ typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); -#define PAGE_SECTORS (PAGE_SIZE / 512) void dm_error(const char *message); -- cgit v1.2.3 From c17495b01b72b53bd290f442d39b060e015c7aea Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 10 Aug 2021 12:04:33 +0530 Subject: cpufreq: Add callback to register with energy model Many cpufreq drivers register with the energy model for each policy and do exactly the same thing. Follow the footsteps of thermal-cooling, to get it done from the cpufreq core itself. Provide a new callback, which will be called, if present, by the cpufreq core at the right moment (more on that in the code's comment). Also provide a generic implementation that uses dev_pm_opp_of_register_em(). This also allows us to register with the EM at a later point of time, compared to ->init(), from where the EM core can access cpufreq policy directly using cpufreq_cpu_get() type of helpers and perform other work, like marking few frequencies inefficient, this will be done separately. Reviewed-by: Quentin Perret Reviewed-by: Lukasz Luba Signed-off-by: Viresh Kumar --- drivers/cpufreq/cpufreq.c | 13 +++++++++++++ include/linux/cpufreq.h | 14 ++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 45f3416988f1..d301f39248a0 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1491,6 +1491,19 @@ static int cpufreq_online(unsigned int cpu) write_lock_irqsave(&cpufreq_driver_lock, flags); list_add(&policy->policy_list, &cpufreq_policy_list); write_unlock_irqrestore(&cpufreq_driver_lock, flags); + + /* + * Register with the energy model before + * sched_cpufreq_governor_change() is called, which will result + * in rebuilding of the sched domains, which should only be done + * once the energy model is properly initialized for the policy + * first. + * + * Also, this should be called before the policy is registered + * with cooling framework. + */ + if (cpufreq_driver->register_em) + cpufreq_driver->register_em(policy); } ret = cpufreq_init_policy(policy); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9fd719475fcd..c65a1d7385f8 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -9,10 +9,12 @@ #define _LINUX_CPUFREQ_H #include +#include #include #include #include #include +#include #include #include #include @@ -373,6 +375,12 @@ struct cpufreq_driver { /* platform specific boost support code */ bool boost_enabled; int (*set_boost)(struct cpufreq_policy *policy, int state); + + /* + * Set by drivers that want to register with the energy model after the + * policy is properly initialized, but before the governor is started. + */ + void (*register_em)(struct cpufreq_policy *policy); }; /* flags */ @@ -1046,4 +1054,10 @@ unsigned int cpufreq_generic_get(unsigned int cpu); void cpufreq_generic_init(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table, unsigned int transition_latency); + +static inline void cpufreq_register_em_with_opp(struct cpufreq_policy *policy) +{ + dev_pm_opp_of_register_em(get_cpu_device(policy->cpu), + policy->related_cpus); +} #endif /* _LINUX_CPUFREQ_H */ -- cgit v1.2.3 From 892384cd998a17960dff6ebefc27375f63364111 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Tue, 3 Aug 2021 14:16:49 +0200 Subject: iommu/io-pgtable: Add DART pagetable format Apple's DART iommu uses a pagetable format that shares some similarities with the ones already implemented by io-pgtable.c. Add a new format variant to support the required differences so that we don't have to duplicate the pagetable handling code. Reviewed-by: Alexander Graf Reviewed-by: Alyssa Rosenzweig Reviewed-by: Robin Murphy Signed-off-by: Sven Peter Link: https://lore.kernel.org/r/20210803121651.61594-2-sven@svenpeter.dev Signed-off-by: Joerg Roedel --- drivers/iommu/io-pgtable-arm.c | 63 ++++++++++++++++++++++++++++++++++++++++++ drivers/iommu/io-pgtable.c | 1 + include/linux/io-pgtable.h | 7 +++++ 3 files changed, 71 insertions(+) (limited to 'include/linux') diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 053df4048a29..0779eb96bd29 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -130,6 +130,9 @@ #define ARM_MALI_LPAE_MEMATTR_IMP_DEF 0x88ULL #define ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC 0x8DULL +#define APPLE_DART_PTE_PROT_NO_WRITE (1<<7) +#define APPLE_DART_PTE_PROT_NO_READ (1<<8) + /* IOPTE accessors */ #define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d)) @@ -402,6 +405,15 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, { arm_lpae_iopte pte; + if (data->iop.fmt == APPLE_DART) { + pte = 0; + if (!(prot & IOMMU_WRITE)) + pte |= APPLE_DART_PTE_PROT_NO_WRITE; + if (!(prot & IOMMU_READ)) + pte |= APPLE_DART_PTE_PROT_NO_READ; + return pte; + } + if (data->iop.fmt == ARM_64_LPAE_S1 || data->iop.fmt == ARM_32_LPAE_S1) { pte = ARM_LPAE_PTE_nG; @@ -1102,6 +1114,52 @@ out_free_data: return NULL; } +static struct io_pgtable * +apple_dart_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie) +{ + struct arm_lpae_io_pgtable *data; + int i; + + if (cfg->oas > 36) + return NULL; + + data = arm_lpae_alloc_pgtable(cfg); + if (!data) + return NULL; + + /* + * The table format itself always uses two levels, but the total VA + * space is mapped by four separate tables, making the MMIO registers + * an effective "level 1". For simplicity, though, we treat this + * equivalently to LPAE stage 2 concatenation at level 2, with the + * additional TTBRs each just pointing at consecutive pages. + */ + if (data->start_level < 1) + goto out_free_data; + if (data->start_level == 1 && data->pgd_bits > 2) + goto out_free_data; + if (data->start_level > 1) + data->pgd_bits = 0; + data->start_level = 2; + cfg->apple_dart_cfg.n_ttbrs = 1 << data->pgd_bits; + data->pgd_bits += data->bits_per_level; + + data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), GFP_KERNEL, + cfg); + if (!data->pgd) + goto out_free_data; + + for (i = 0; i < cfg->apple_dart_cfg.n_ttbrs; ++i) + cfg->apple_dart_cfg.ttbr[i] = + virt_to_phys(data->pgd + i * ARM_LPAE_GRANULE(data)); + + return &data->iop; + +out_free_data: + kfree(data); + return NULL; +} + struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = { .alloc = arm_64_lpae_alloc_pgtable_s1, .free = arm_lpae_free_pgtable, @@ -1127,6 +1185,11 @@ struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = { .free = arm_lpae_free_pgtable, }; +struct io_pgtable_init_fns io_pgtable_apple_dart_init_fns = { + .alloc = apple_dart_alloc_pgtable, + .free = arm_lpae_free_pgtable, +}; + #ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST static struct io_pgtable_cfg *cfg_cookie __initdata; diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c index 6e9917ce980f..f4bfcef98297 100644 --- a/drivers/iommu/io-pgtable.c +++ b/drivers/iommu/io-pgtable.c @@ -20,6 +20,7 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = { [ARM_64_LPAE_S1] = &io_pgtable_arm_64_lpae_s1_init_fns, [ARM_64_LPAE_S2] = &io_pgtable_arm_64_lpae_s2_init_fns, [ARM_MALI_LPAE] = &io_pgtable_arm_mali_lpae_init_fns, + [APPLE_DART] = &io_pgtable_apple_dart_init_fns, #endif #ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S [ARM_V7S] = &io_pgtable_arm_v7s_init_fns, diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index c43f3b899d2a..a738483fb4da 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -16,6 +16,7 @@ enum io_pgtable_fmt { ARM_V7S, ARM_MALI_LPAE, AMD_IOMMU_V1, + APPLE_DART, IO_PGTABLE_NUM_FMTS, }; @@ -136,6 +137,11 @@ struct io_pgtable_cfg { u64 transtab; u64 memattr; } arm_mali_lpae_cfg; + + struct { + u64 ttbr[4]; + u32 n_ttbrs; + } apple_dart_cfg; }; }; @@ -254,5 +260,6 @@ extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns; extern struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns; +extern struct io_pgtable_init_fns io_pgtable_apple_dart_init_fns; #endif /* __IO_PGTABLE_H */ -- cgit v1.2.3 From ca91ea34778f9b2a44a391b10164bcd73b4b0f25 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Sat, 7 Aug 2021 14:36:54 +1200 Subject: asus-wmi: Add panel overdrive functionality Some ASUS ROG laptops have the ability to drive the display panel a higher rate to eliminate or reduce ghosting. Signed-off-by: Luke D. Jones Link: https://lore.kernel.org/r/20210807023656.25020-2-luke@ljones.dev Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/asus-wmi.c | 92 ++++++++++++++++++++++++++++++ include/linux/platform_data/x86/asus-wmi.h | 1 + 2 files changed, 93 insertions(+) (limited to 'include/linux') diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index ebaeb7bb80f5..cbf91a9134fd 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -216,6 +216,9 @@ struct asus_wmi { // The RSOC controls the maximum charging percentage. bool battery_rsoc_available; + bool panel_overdrive_available; + bool panel_overdrive; + struct hotplug_slot hotplug_slot; struct mutex hotplug_lock; struct mutex wmi_lock; @@ -1221,6 +1224,87 @@ exit: return result; } +/* Panel Overdrive ************************************************************/ +static int panel_od_check_present(struct asus_wmi *asus) +{ + u32 result; + int err; + + asus->panel_overdrive_available = false; + + err = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_PANEL_OD, &result); + if (err) { + if (err == -ENODEV) + return 0; + return err; + } + + if (result & ASUS_WMI_DSTS_PRESENCE_BIT) { + asus->panel_overdrive_available = true; + asus->panel_overdrive = result & ASUS_WMI_DSTS_STATUS_BIT; + } + + return 0; +} + +static int panel_od_write(struct asus_wmi *asus) +{ + u32 retval; + u8 value; + int err; + + /* Don't rely on type conversion */ + value = asus->panel_overdrive ? 1 : 0; + + err = asus_wmi_set_devstate(ASUS_WMI_DEVID_PANEL_OD, value, &retval); + + if (err) { + pr_warn("Failed to set panel overdrive: %d\n", err); + return err; + } + + if (retval > 1 || retval < 0) { + pr_warn("Failed to set panel overdrive (retval): 0x%x\n", retval); + return -EIO; + } + + sysfs_notify(&asus->platform_device->dev.kobj, NULL, "panel_od"); + + return 0; +} + +static ssize_t panel_od_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct asus_wmi *asus = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%d\n", asus->panel_overdrive); +} + +static ssize_t panel_od_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + bool overdrive; + int result; + + struct asus_wmi *asus = dev_get_drvdata(dev); + + result = kstrtobool(buf, &overdrive); + if (result) + return result; + + asus->panel_overdrive = overdrive; + result = panel_od_write(asus); + + if (result) + return result; + + return count; +} + +static DEVICE_ATTR_RW(panel_od); + /* Quirks *********************************************************************/ static void asus_wmi_set_xusb2pr(struct asus_wmi *asus) @@ -2332,6 +2416,7 @@ static struct attribute *platform_attributes[] = { &dev_attr_als_enable.attr, &dev_attr_fan_boost_mode.attr, &dev_attr_throttle_thermal_policy.attr, + &dev_attr_panel_od.attr, NULL }; @@ -2357,6 +2442,8 @@ static umode_t asus_sysfs_is_visible(struct kobject *kobj, ok = asus->fan_boost_mode_available; else if (attr == &dev_attr_throttle_thermal_policy.attr) ok = asus->throttle_thermal_policy_available; + else if (attr == &dev_attr_panel_od.attr) + ok = asus->panel_overdrive_available; if (devid != -1) ok = !(asus_wmi_get_devstate_simple(asus, devid) < 0); @@ -2622,6 +2709,10 @@ static int asus_wmi_add(struct platform_device *pdev) else throttle_thermal_policy_set_default(asus); + err = panel_od_check_present(asus); + if (err) + goto fail_panel_od; + err = asus_wmi_sysfs_init(asus->platform_device); if (err) goto fail_sysfs; @@ -2709,6 +2800,7 @@ fail_sysfs: fail_throttle_thermal_policy: fail_fan_boost_mode: fail_platform: +fail_panel_od: kfree(asus); return err; } diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 2f274cf52805..428aea701c7b 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -61,6 +61,7 @@ #define ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY 0x00120075 /* Misc */ +#define ASUS_WMI_DEVID_PANEL_OD 0x00050019 #define ASUS_WMI_DEVID_CAMERA 0x00060013 #define ASUS_WMI_DEVID_LID_FLIP 0x00060062 -- cgit v1.2.3 From 98829e84dc67630efb7de675f0a70066620468a3 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Sat, 7 Aug 2021 14:36:55 +1200 Subject: asus-wmi: Add dgpu disable method In Windows the ASUS Armory Crate program can enable or disable the dGPU via a WMI call. This functions much the same as various Linux methods in software where the dGPU is removed from the device tree. However the WMI call saves the state of dGPU (enabled or not) and this then changes the dGPU visibility in Linux with no way for Linux users to re-enable it. We expose the WMI method so users can see and change the dGPU ACPI state. Signed-off-by: Luke D. Jones Link: https://lore.kernel.org/r/20210807023656.25020-3-luke@ljones.dev Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/asus-wmi.c | 98 ++++++++++++++++++++++++++++++ include/linux/platform_data/x86/asus-wmi.h | 3 + 2 files changed, 101 insertions(+) (limited to 'include/linux') diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index cbf91a9134fd..bee22a12bf3d 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -210,6 +210,9 @@ struct asus_wmi { u8 fan_boost_mode_mask; u8 fan_boost_mode; + bool dgpu_disable_available; + bool dgpu_disable; + bool throttle_thermal_policy_available; u8 throttle_thermal_policy_mode; @@ -427,6 +430,93 @@ static void lid_flip_tablet_mode_get_state(struct asus_wmi *asus) } } +/* dGPU ********************************************************************/ +static int dgpu_disable_check_present(struct asus_wmi *asus) +{ + u32 result; + int err; + + asus->dgpu_disable_available = false; + + err = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_DGPU, &result); + if (err) { + if (err == -ENODEV) + return 0; + return err; + } + + if (result & ASUS_WMI_DSTS_PRESENCE_BIT) { + asus->dgpu_disable_available = true; + asus->dgpu_disable = result & ASUS_WMI_DSTS_STATUS_BIT; + } + + return 0; +} + +static int dgpu_disable_write(struct asus_wmi *asus) +{ + u32 retval; + u8 value; + int err; + + /* Don't rely on type conversion */ + value = asus->dgpu_disable ? 1 : 0; + + err = asus_wmi_set_devstate(ASUS_WMI_DEVID_DGPU, value, &retval); + if (err) { + pr_warn("Failed to set dgpu disable: %d\n", err); + return err; + } + + if (retval > 1 || retval < 0) { + pr_warn("Failed to set dgpu disable (retval): 0x%x\n", retval); + return -EIO; + } + + sysfs_notify(&asus->platform_device->dev.kobj, NULL, "dgpu_disable"); + + return 0; +} + +static ssize_t dgpu_disable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct asus_wmi *asus = dev_get_drvdata(dev); + u8 mode = asus->dgpu_disable; + + return sysfs_emit(buf, "%d\n", mode); +} + +/* + * A user may be required to store the value twice, typcial store first, then + * rescan PCI bus to activate power, then store a second time to save correctly. + * The reason for this is that an extra code path in the ACPI is enabled when + * the device and bus are powered. + */ +static ssize_t dgpu_disable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + bool disable; + int result; + + struct asus_wmi *asus = dev_get_drvdata(dev); + + result = kstrtobool(buf, &disable); + if (result) + return result; + + asus->dgpu_disable = disable; + + result = dgpu_disable_write(asus); + if (result) + return result; + + return count; +} + +static DEVICE_ATTR_RW(dgpu_disable); + /* Battery ********************************************************************/ /* The battery maximum charging percentage */ @@ -2412,6 +2502,7 @@ static struct attribute *platform_attributes[] = { &dev_attr_camera.attr, &dev_attr_cardr.attr, &dev_attr_touchpad.attr, + &dev_attr_dgpu_disable.attr, &dev_attr_lid_resume.attr, &dev_attr_als_enable.attr, &dev_attr_fan_boost_mode.attr, @@ -2438,6 +2529,8 @@ static umode_t asus_sysfs_is_visible(struct kobject *kobj, devid = ASUS_WMI_DEVID_LID_RESUME; else if (attr == &dev_attr_als_enable.attr) devid = ASUS_WMI_DEVID_ALS_ENABLE; + else if (attr == &dev_attr_dgpu_disable.attr) + ok = asus->dgpu_disable_available; else if (attr == &dev_attr_fan_boost_mode.attr) ok = asus->fan_boost_mode_available; else if (attr == &dev_attr_throttle_thermal_policy.attr) @@ -2699,6 +2792,10 @@ static int asus_wmi_add(struct platform_device *pdev) if (err) goto fail_platform; + err = dgpu_disable_check_present(asus); + if (err) + goto fail_dgpu_disable; + err = fan_boost_mode_check_present(asus); if (err) goto fail_fan_boost_mode; @@ -2799,6 +2896,7 @@ fail_input: fail_sysfs: fail_throttle_thermal_policy: fail_fan_boost_mode: +fail_dgpu_disable: fail_platform: fail_panel_od: kfree(asus); diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 428aea701c7b..a528f9d0e4b7 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -90,6 +90,9 @@ /* Keyboard dock */ #define ASUS_WMI_DEVID_KBD_DOCK 0x00120063 +/* dgpu on/off */ +#define ASUS_WMI_DEVID_DGPU 0x00090020 + /* DSTS masks */ #define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 #define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 -- cgit v1.2.3 From 382b91db8044669d254006df799df9d85d4ad891 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Sat, 7 Aug 2021 14:36:56 +1200 Subject: asus-wmi: Add egpu enable method The X13 Flow laptops can utilise an external GPU. This requires toggling an ACPI method which will first disable the internal dGPU, and then enable the eGPU. Signed-off-by: Luke D. Jones Link: https://lore.kernel.org/r/20210807023656.25020-4-luke@ljones.dev Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/asus-wmi.c | 99 ++++++++++++++++++++++++++++++ include/linux/platform_data/x86/asus-wmi.h | 3 + 2 files changed, 102 insertions(+) (limited to 'include/linux') diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index bee22a12bf3d..90a6a0d00deb 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -210,6 +210,9 @@ struct asus_wmi { u8 fan_boost_mode_mask; u8 fan_boost_mode; + bool egpu_enable_available; // 0 = enable + bool egpu_enable; + bool dgpu_disable_available; bool dgpu_disable; @@ -517,6 +520,94 @@ static ssize_t dgpu_disable_store(struct device *dev, static DEVICE_ATTR_RW(dgpu_disable); +/* eGPU ********************************************************************/ +static int egpu_enable_check_present(struct asus_wmi *asus) +{ + u32 result; + int err; + + asus->egpu_enable_available = false; + + err = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_EGPU, &result); + if (err) { + if (err == -ENODEV) + return 0; + return err; + } + + if (result & ASUS_WMI_DSTS_PRESENCE_BIT) { + asus->egpu_enable_available = true; + asus->egpu_enable = result & ASUS_WMI_DSTS_STATUS_BIT; + } + + return 0; +} + +static int egpu_enable_write(struct asus_wmi *asus) +{ + u32 retval; + u8 value; + int err; + + /* Don't rely on type conversion */ + value = asus->egpu_enable ? 1 : 0; + + err = asus_wmi_set_devstate(ASUS_WMI_DEVID_EGPU, value, &retval); + + if (err) { + pr_warn("Failed to set egpu disable: %d\n", err); + return err; + } + + if (retval > 1 || retval < 0) { + pr_warn("Failed to set egpu disable (retval): 0x%x\n", retval); + return -EIO; + } + + sysfs_notify(&asus->platform_device->dev.kobj, NULL, "egpu_enable"); + + return 0; +} + +static ssize_t egpu_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct asus_wmi *asus = dev_get_drvdata(dev); + bool mode = asus->egpu_enable; + + return sysfs_emit(buf, "%d\n", mode); +} + +/* The ACPI call to enable the eGPU also disables the internal dGPU */ +static ssize_t egpu_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + bool enable; + int result; + + struct asus_wmi *asus = dev_get_drvdata(dev); + + result = kstrtobool(buf, &enable); + if (result) + return result; + + asus->egpu_enable = enable; + + result = egpu_enable_write(asus); + if (result) + return result; + + /* Ensure that the kernel status of dgpu is updated */ + result = dgpu_disable_check_present(asus); + if (result) + return result; + + return count; +} + +static DEVICE_ATTR_RW(egpu_enable); + /* Battery ********************************************************************/ /* The battery maximum charging percentage */ @@ -2502,6 +2593,7 @@ static struct attribute *platform_attributes[] = { &dev_attr_camera.attr, &dev_attr_cardr.attr, &dev_attr_touchpad.attr, + &dev_attr_egpu_enable.attr, &dev_attr_dgpu_disable.attr, &dev_attr_lid_resume.attr, &dev_attr_als_enable.attr, @@ -2529,6 +2621,8 @@ static umode_t asus_sysfs_is_visible(struct kobject *kobj, devid = ASUS_WMI_DEVID_LID_RESUME; else if (attr == &dev_attr_als_enable.attr) devid = ASUS_WMI_DEVID_ALS_ENABLE; + else if (attr == &dev_attr_egpu_enable.attr) + ok = asus->egpu_enable_available; else if (attr == &dev_attr_dgpu_disable.attr) ok = asus->dgpu_disable_available; else if (attr == &dev_attr_fan_boost_mode.attr) @@ -2792,6 +2886,10 @@ static int asus_wmi_add(struct platform_device *pdev) if (err) goto fail_platform; + err = egpu_enable_check_present(asus); + if (err) + goto fail_egpu_enable; + err = dgpu_disable_check_present(asus); if (err) goto fail_dgpu_disable; @@ -2896,6 +2994,7 @@ fail_input: fail_sysfs: fail_throttle_thermal_policy: fail_fan_boost_mode: +fail_egpu_enable: fail_dgpu_disable: fail_platform: fail_panel_od: diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index a528f9d0e4b7..17dc5cb6f3f2 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -90,6 +90,9 @@ /* Keyboard dock */ #define ASUS_WMI_DEVID_KBD_DOCK 0x00120063 +/* dgpu on/off */ +#define ASUS_WMI_DEVID_EGPU 0x00090019 + /* dgpu on/off */ #define ASUS_WMI_DEVID_DGPU 0x00090020 -- cgit v1.2.3 From 20a1b3acfc802ad7b6b327f2bdc0570711538561 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 3 Aug 2021 18:00:41 +0200 Subject: i2c: acpi: Add an i2c_acpi_client_count() helper function We have 3 files now which have the need to count the number of I2cSerialBus resources in an ACPI-device's resource-list. Currently all implement their own helper function for this, add a generic helper function to replace the 3 implementations. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20210803160044.158802-2-hdegoede@redhat.com Acked-by: Mika Westerberg Acked-by: Wolfram Sang --- drivers/i2c/i2c-core-acpi.c | 32 ++++++++++++++++++++++++++++++++ include/linux/i2c.h | 5 +++++ 2 files changed, 37 insertions(+) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 6f0aa0ed3241..aaeeacc12121 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -69,6 +69,38 @@ bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, } EXPORT_SYMBOL_GPL(i2c_acpi_get_i2c_resource); +static int i2c_acpi_resource_count(struct acpi_resource *ares, void *data) +{ + struct acpi_resource_i2c_serialbus *sb; + int *count = data; + + if (i2c_acpi_get_i2c_resource(ares, &sb)) + *count = *count + 1; + + return 1; +} + +/** + * i2c_acpi_client_count - Count the number of I2cSerialBus resources + * @adev: ACPI device + * + * Returns the number of I2cSerialBus resources in the ACPI-device's + * resource-list; or a negative error code. + */ +int i2c_acpi_client_count(struct acpi_device *adev) +{ + int ret, count = 0; + LIST_HEAD(r); + + ret = acpi_dev_get_resources(adev, &r, i2c_acpi_resource_count, &count); + if (ret < 0) + return ret; + + acpi_dev_free_resource_list(&r); + return count; +} +EXPORT_SYMBOL_GPL(i2c_acpi_client_count); + static int i2c_acpi_fill_info(struct acpi_resource *ares, void *data) { struct i2c_acpi_lookup *lookup = data; diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 3eb60a2e9e61..2ce3efbe9198 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1010,6 +1010,7 @@ struct acpi_resource_i2c_serialbus; #if IS_ENABLED(CONFIG_ACPI) bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); +int i2c_acpi_client_count(struct acpi_device *adev); u32 i2c_acpi_find_bus_speed(struct device *dev); struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info); @@ -1020,6 +1021,10 @@ static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, { return false; } +static inline int i2c_acpi_client_count(struct acpi_device *adev) +{ + return 0; +} static inline u32 i2c_acpi_find_bus_speed(struct device *dev) { return 0; -- cgit v1.2.3 From 50b4aecfbbb09869db967e4a26212a47e10c0088 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 9 Aug 2021 08:40:28 +0200 Subject: block: remove GENHD_FL_UP Just check inode_unhashed on the whole device bdev inode instead, and provide a helper to check for that information. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210809064028.1198327-9-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 6 ++---- block/partitions/core.c | 4 ++-- drivers/md/md.h | 4 +--- drivers/nvme/host/core.c | 2 +- fs/block_dev.c | 2 +- include/linux/genhd.h | 9 +++++---- 6 files changed, 12 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index f8def1129501..9d6b3aeea288 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -77,7 +77,8 @@ bool set_capacity_and_notify(struct gendisk *disk, sector_t size) * initial capacity during probing. */ if (size == capacity || - (disk->flags & (GENHD_FL_UP | GENHD_FL_HIDDEN)) != GENHD_FL_UP) + !disk_live(disk) || + (disk->flags & GENHD_FL_HIDDEN)) return false; pr_info("%s: detected capacity change from %lld to %lld\n", @@ -527,8 +528,6 @@ void device_add_disk(struct device *parent, struct gendisk *disk, disk->flags |= GENHD_FL_EXT_DEVT; } - disk->flags |= GENHD_FL_UP; - disk_alloc_events(disk); if (disk->flags & GENHD_FL_HIDDEN) { @@ -597,7 +596,6 @@ void del_gendisk(struct gendisk *disk) mutex_lock(&disk->open_mutex); remove_inode_hash(disk->part0->bd_inode); - disk->flags &= ~GENHD_FL_UP; blk_drop_partitions(disk); mutex_unlock(&disk->open_mutex); diff --git a/block/partitions/core.c b/block/partitions/core.c index fb3a556cacce..c6738ccbcee5 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -459,7 +459,7 @@ int bdev_add_partition(struct block_device *bdev, int partno, int ret; mutex_lock(&disk->open_mutex); - if (!(disk->flags & GENHD_FL_UP)) { + if (!disk_live(disk)) { ret = -ENXIO; goto out; } @@ -669,7 +669,7 @@ int bdev_disk_changed(struct gendisk *disk, bool invalidate) lockdep_assert_held(&disk->open_mutex); - if (!(disk->flags & GENHD_FL_UP)) + if (!disk_live(disk)) return -ENXIO; rescan: diff --git a/drivers/md/md.h b/drivers/md/md.h index 832547cf038f..4c96c36bd01a 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -764,9 +764,7 @@ struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev); static inline bool is_mddev_broken(struct md_rdev *rdev, const char *md_type) { - int flags = rdev->bdev->bd_disk->flags; - - if (!(flags & GENHD_FL_UP)) { + if (!disk_live(rdev->bdev->bd_disk)) { if (!test_and_set_bit(MD_BROKEN, &rdev->mddev->flags)) pr_warn("md: %s: %s array has a missing/failed member\n", mdname(rdev->mddev), md_type); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index dbe7144f0026..1478d825011d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1822,7 +1822,7 @@ static void nvme_update_disk_info(struct gendisk *disk, static inline bool nvme_first_scan(struct gendisk *disk) { /* nvme_alloc_ns() scans the disk prior to adding it */ - return !(disk->flags & GENHD_FL_UP); + return !disk_live(disk); } static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id) diff --git a/fs/block_dev.c b/fs/block_dev.c index e1c14c2e0504..38a8b0e04a0c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1218,7 +1218,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) mutex_lock(&disk->open_mutex); ret = -ENXIO; - if (!(disk->flags & GENHD_FL_UP)) + if (!disk_live(disk)) goto abort_claiming; if (bdev_is_partition(bdev)) ret = blkdev_get_part(bdev, mode); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index b3bab578f03a..b47e297cd551 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -60,9 +60,6 @@ struct partition_meta_info { * device. * Affects responses to the ``CDROM_GET_CAPABILITY`` ioctl. * - * ``GENHD_FL_UP`` (0x0010): indicates that the block device is "up", - * with a similar meaning to network interfaces. - * * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include * partition information in ``/proc/partitions`` or in the output of * printk_all_partitions(). @@ -97,7 +94,6 @@ struct partition_meta_info { /* 2 is unused (used to be GENHD_FL_DRIVERFS) */ /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ #define GENHD_FL_CD 0x0008 -#define GENHD_FL_UP 0x0010 #define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 #define GENHD_FL_EXT_DEVT 0x0040 #define GENHD_FL_NATIVE_CAPACITY 0x0080 @@ -178,6 +174,11 @@ struct gendisk { u64 diskseq; }; +static inline bool disk_live(struct gendisk *disk) +{ + return !inode_unhashed(disk->part0->bd_inode); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. -- cgit v1.2.3 From fd00faa375fbb9d46ae0730d0faf4a3006301005 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 8 Aug 2021 19:21:56 +0200 Subject: PCI/VPD: Embed struct pci_vpd in struct pci_dev Now that struct pci_vpd is really small, simplify the code by embedding struct pci_vpd directly in struct pci_dev instead of dynamically allocating it. Link: https://lore.kernel.org/r/d898489e-22ba-71f1-2f31-f1a78dc15849@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- drivers/pci/probe.c | 1 - drivers/pci/vpd.c | 63 ++++++++++++----------------------------------------- include/linux/pci.h | 9 ++++++-- 3 files changed, 21 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 79177ac37880..0ec5c792c27d 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2225,7 +2225,6 @@ static void pci_release_capabilities(struct pci_dev *dev) { pci_aer_exit(dev); pci_rcec_exit(dev); - pci_vpd_release(dev); pci_iov_release(dev); pci_free_cap_save_buffers(dev); } diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 9d9cff5f89e2..ee48e167145f 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -13,12 +13,6 @@ /* VPD access through PCI 2.2+ VPD capability */ -struct pci_vpd { - struct mutex lock; - unsigned int len; - u8 cap; -}; - static struct pci_dev *pci_get_func0_dev(struct pci_dev *dev) { return pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0)); @@ -37,7 +31,7 @@ static size_t pci_vpd_size(struct pci_dev *dev) unsigned char tag, header[1+2]; /* 1 byte tag, 2 bytes length */ /* Otherwise the following reads would fail. */ - dev->vpd->len = PCI_VPD_MAX_SIZE; + dev->vpd.len = PCI_VPD_MAX_SIZE; while (pci_read_vpd(dev, off, 1, header) == 1) { size = 0; @@ -89,7 +83,7 @@ error: */ static int pci_vpd_wait(struct pci_dev *dev, bool set) { - struct pci_vpd *vpd = dev->vpd; + struct pci_vpd *vpd = &dev->vpd; unsigned long timeout = jiffies + msecs_to_jiffies(125); unsigned long max_sleep = 16; u16 status; @@ -119,12 +113,12 @@ static int pci_vpd_wait(struct pci_dev *dev, bool set) static ssize_t pci_vpd_read(struct pci_dev *dev, loff_t pos, size_t count, void *arg) { - struct pci_vpd *vpd = dev->vpd; + struct pci_vpd *vpd = &dev->vpd; int ret = 0; loff_t end = pos + count; u8 *buf = arg; - if (!vpd) + if (!vpd->cap) return -ENODEV; if (pos < 0) @@ -186,12 +180,12 @@ static ssize_t pci_vpd_read(struct pci_dev *dev, loff_t pos, size_t count, static ssize_t pci_vpd_write(struct pci_dev *dev, loff_t pos, size_t count, const void *arg) { - struct pci_vpd *vpd = dev->vpd; + struct pci_vpd *vpd = &dev->vpd; const u8 *buf = arg; loff_t end = pos + count; int ret = 0; - if (!vpd) + if (!vpd->cap) return -ENODEV; if (pos < 0 || (pos & 3) || (count & 3)) @@ -238,25 +232,8 @@ static ssize_t pci_vpd_write(struct pci_dev *dev, loff_t pos, size_t count, void pci_vpd_init(struct pci_dev *dev) { - struct pci_vpd *vpd; - u8 cap; - - cap = pci_find_capability(dev, PCI_CAP_ID_VPD); - if (!cap) - return; - - vpd = kzalloc(sizeof(*vpd), GFP_ATOMIC); - if (!vpd) - return; - - mutex_init(&vpd->lock); - vpd->cap = cap; - dev->vpd = vpd; -} - -void pci_vpd_release(struct pci_dev *dev) -{ - kfree(dev->vpd); + dev->vpd.cap = pci_find_capability(dev, PCI_CAP_ID_VPD); + mutex_init(&dev->vpd.lock); } static ssize_t vpd_read(struct file *filp, struct kobject *kobj, @@ -288,7 +265,7 @@ static umode_t vpd_attr_is_visible(struct kobject *kobj, { struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj)); - if (!pdev->vpd) + if (!pdev->vpd.cap) return 0; return a->attr.mode; @@ -400,7 +377,7 @@ static void quirk_f0_vpd_link(struct pci_dev *dev) if (!f0) return; - if (f0->vpd && dev->class == f0->class && + if (f0->vpd.cap && dev->class == f0->class && dev->vendor == f0->vendor && dev->device == f0->device) dev->dev_flags |= PCI_DEV_FLAGS_VPD_REF_F0; @@ -418,10 +395,8 @@ DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, */ static void quirk_blacklist_vpd(struct pci_dev *dev) { - if (dev->vpd) { - dev->vpd->len = PCI_VPD_SZ_INVALID; - pci_warn(dev, FW_BUG "disabling VPD access (can't determine size of non-standard VPD format)\n"); - } + dev->vpd.len = PCI_VPD_SZ_INVALID; + pci_warn(dev, FW_BUG "disabling VPD access (can't determine size of non-standard VPD format)\n"); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x0060, quirk_blacklist_vpd); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x007c, quirk_blacklist_vpd); @@ -443,16 +418,6 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, PCI_ANY_ID, DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, PCI_CLASS_BRIDGE_PCI, 8, quirk_blacklist_vpd); -static void pci_vpd_set_size(struct pci_dev *dev, size_t len) -{ - struct pci_vpd *vpd = dev->vpd; - - if (!vpd || len == 0 || len > PCI_VPD_MAX_SIZE) - return; - - vpd->len = len; -} - static void quirk_chelsio_extend_vpd(struct pci_dev *dev) { int chip = (dev->device & 0xf000) >> 12; @@ -471,9 +436,9 @@ static void quirk_chelsio_extend_vpd(struct pci_dev *dev) * limits. */ if (chip == 0x0 && prod >= 0x20) - pci_vpd_set_size(dev, 8192); + dev->vpd.len = 8192; else if (chip >= 0x4 && func < 0x8) - pci_vpd_set_size(dev, 2048); + dev->vpd.len = 2048; } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID, diff --git a/include/linux/pci.h b/include/linux/pci.h index 540b377ca8f6..e752cc39a1fe 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -300,9 +300,14 @@ struct pci_cap_saved_state { struct pci_cap_saved_data cap; }; +struct pci_vpd { + struct mutex lock; + unsigned int len; + u8 cap; +}; + struct irq_affinity; struct pcie_link_state; -struct pci_vpd; struct pci_sriov; struct pci_p2pdma; struct rcec_ea; @@ -473,7 +478,7 @@ struct pci_dev { #ifdef CONFIG_PCI_MSI const struct attribute_group **msi_irq_groups; #endif - struct pci_vpd *vpd; + struct pci_vpd vpd; #ifdef CONFIG_PCIE_DPC u16 dpc_cap; unsigned int dpc_rp_extensions:1; -- cgit v1.2.3 From 928f9e2686110825262685b7aedc7b21b805fecd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 12 Aug 2021 20:00:23 +0300 Subject: clk: fractional-divider: Hide clk_fractional_divider_ops from wide audience The providers are all located in drivers/clk/ and hence no need to export the clock operations to wider audience. Hide them by moving to drivers/clk/clk-fractional-divider.h. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210812170025.67074-2-andriy.shevchenko@linux.intel.com Signed-off-by: Stephen Boyd --- drivers/clk/clk-fractional-divider.h | 2 ++ drivers/clk/imx/clk-composite-7ulp.c | 1 + include/linux/clk-provider.h | 1 - 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/clk/clk-fractional-divider.h b/drivers/clk/clk-fractional-divider.h index a05649eceb17..f0f71d23797b 100644 --- a/drivers/clk/clk-fractional-divider.h +++ b/drivers/clk/clk-fractional-divider.h @@ -4,6 +4,8 @@ struct clk_hw; +extern const struct clk_ops clk_fractional_divider_ops; + void clk_fractional_divider_general_approximation(struct clk_hw *hw, unsigned long rate, unsigned long *parent_rate, diff --git a/drivers/clk/imx/clk-composite-7ulp.c b/drivers/clk/imx/clk-composite-7ulp.c index 7c4f31b31eb0..d85ba78abbb1 100644 --- a/drivers/clk/imx/clk-composite-7ulp.c +++ b/drivers/clk/imx/clk-composite-7ulp.c @@ -10,6 +10,7 @@ #include #include +#include "../clk-fractional-divider.h" #include "clk.h" #define PCG_PCS_SHIFT 24 diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index d83b829305c0..acb8e10d2898 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1023,7 +1023,6 @@ struct clk_fractional_divider { #define CLK_FRAC_DIVIDER_ZERO_BASED BIT(0) #define CLK_FRAC_DIVIDER_BIG_ENDIAN BIT(1) -extern const struct clk_ops clk_fractional_divider_ops; struct clk *clk_register_fractional_divider(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 mshift, u8 mwidth, u8 nshift, u8 nwidth, -- cgit v1.2.3 From 82f53f9ee5770177eb102446cc3513bf07e2668a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 12 Aug 2021 20:00:24 +0300 Subject: clk: fractional-divider: Introduce POWER_OF_TWO_PS flag The newly introduced POWER_OF_TWO_PS flag, when set, makes the flow to skip the assumption that the caller will use an additional 2^scale prescaler to get the desired clock rate. Reported-by: Liu Ying Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210812170025.67074-3-andriy.shevchenko@linux.intel.com Signed-off-by: Stephen Boyd --- drivers/acpi/acpi_lpss.c | 4 ++-- drivers/clk/clk-fractional-divider.c | 10 ++++++---- drivers/mfd/intel-lpss.c | 3 ++- include/linux/clk-provider.h | 7 +++++++ 4 files changed, 17 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 894b7e6ae144..55c5e89d6a7b 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -434,8 +434,8 @@ static int register_device_clock(struct acpi_device *adev, if (!clk_name) return -ENOMEM; clk = clk_register_fractional_divider(NULL, clk_name, parent, - 0, prv_base, - 1, 15, 16, 15, 0, NULL); + CLK_FRAC_DIVIDER_POWER_OF_TWO_PS, + prv_base, 1, 15, 16, 15, 0, NULL); parent = clk_name; clk_name = kasprintf(GFP_KERNEL, "%s-update", devname); diff --git a/drivers/clk/clk-fractional-divider.c b/drivers/clk/clk-fractional-divider.c index 535d299af646..6a3ed82fdae9 100644 --- a/drivers/clk/clk-fractional-divider.c +++ b/drivers/clk/clk-fractional-divider.c @@ -76,16 +76,18 @@ void clk_fractional_divider_general_approximation(struct clk_hw *hw, unsigned long *m, unsigned long *n) { struct clk_fractional_divider *fd = to_clk_fd(hw); - unsigned long scale; /* * Get rate closer to *parent_rate to guarantee there is no overflow * for m and n. In the result it will be the nearest rate left shifted * by (scale - fd->nwidth) bits. */ - scale = fls_long(*parent_rate / rate - 1); - if (scale > fd->nwidth) - rate <<= scale - fd->nwidth; + if (fd->flags & CLK_FRAC_DIVIDER_POWER_OF_TWO_PS) { + unsigned long scale = fls_long(*parent_rate / rate - 1); + + if (scale > fd->nwidth) + rate <<= scale - fd->nwidth; + } rational_best_approximation(rate, *parent_rate, GENMASK(fd->mwidth - 1, 0), GENMASK(fd->nwidth - 1, 0), diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c index a9bf10bee796..0e15afc39f54 100644 --- a/drivers/mfd/intel-lpss.c +++ b/drivers/mfd/intel-lpss.c @@ -301,7 +301,8 @@ static int intel_lpss_register_clock_divider(struct intel_lpss *lpss, snprintf(name, sizeof(name), "%s-div", devname); tmp = clk_register_fractional_divider(NULL, name, __clk_get_name(tmp), - 0, lpss->priv, 1, 15, 16, 15, 0, + CLK_FRAC_DIVIDER_POWER_OF_TWO_PS, + lpss->priv, 1, 15, 16, 15, 0, NULL); if (IS_ERR(tmp)) return PTR_ERR(tmp); diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index acb8e10d2898..d63d07fd251b 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1001,6 +1001,12 @@ struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev, * CLK_FRAC_DIVIDER_BIG_ENDIAN - By default little endian register accesses are * used for the divider register. Setting this flag makes the register * accesses big endian. + * CLK_FRAC_DIVIDER_POWER_OF_TWO_PS - By default the resulting fraction might + * be saturated and the caller will get quite far from the good enough + * approximation. Instead the caller may require, by setting this flag, + * to shift left by a few bits in case, when the asked one is quite small + * to satisfy the desired range of denominator. It assumes that on the + * caller's side the power-of-two capable prescaler exists. */ struct clk_fractional_divider { struct clk_hw hw; @@ -1022,6 +1028,7 @@ struct clk_fractional_divider { #define CLK_FRAC_DIVIDER_ZERO_BASED BIT(0) #define CLK_FRAC_DIVIDER_BIG_ENDIAN BIT(1) +#define CLK_FRAC_DIVIDER_POWER_OF_TWO_PS BIT(2) struct clk *clk_register_fractional_divider(struct device *dev, const char *name, const char *parent_name, unsigned long flags, -- cgit v1.2.3 From 7bb698f09bdd01fbb6d48c14bb1dde556dc1af00 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 28 Jul 2021 07:47:33 -0500 Subject: fs: Move notify_change permission checks into may_setattr Move the permission checks in notify_change into a separate function to make them available to filesystems. When notify_change is called, the vfs performs those checks before calling into iop->setattr. However, a filesystem like gfs2 can only lock and revalidate the inode inside ->setattr, and it must then repeat those checks to err on the safe side. It would be nice to get rid of the double checking, but moving the permission check into iop->setattr altogether isn't really an option. Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson Signed-off-by: Al Viro --- fs/attr.c | 50 +++++++++++++++++++++++++++++++------------------- include/linux/fs.h | 2 ++ 2 files changed, 33 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/fs/attr.c b/fs/attr.c index 87ef39db1c34..473d21b3a86d 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -249,6 +249,34 @@ void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode, } EXPORT_SYMBOL(setattr_copy); +int may_setattr(struct user_namespace *mnt_userns, struct inode *inode, + unsigned int ia_valid) +{ + int error; + + if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { + if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) + return -EPERM; + } + + /* + * If utimes(2) and friends are called with times == NULL (or both + * times are UTIME_NOW), then we need to check for write permission + */ + if (ia_valid & ATTR_TOUCH) { + if (IS_IMMUTABLE(inode)) + return -EPERM; + + if (!inode_owner_or_capable(mnt_userns, inode)) { + error = inode_permission(mnt_userns, inode, MAY_WRITE); + if (error) + return error; + } + } + return 0; +} +EXPORT_SYMBOL(may_setattr); + /** * notify_change - modify attributes of a filesytem object * @mnt_userns: user namespace of the mount the inode was found from @@ -290,25 +318,9 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, WARN_ON_ONCE(!inode_is_locked(inode)); - if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { - if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) - return -EPERM; - } - - /* - * If utimes(2) and friends are called with times == NULL (or both - * times are UTIME_NOW), then we need to check for write permission - */ - if (ia_valid & ATTR_TOUCH) { - if (IS_IMMUTABLE(inode)) - return -EPERM; - - if (!inode_owner_or_capable(mnt_userns, inode)) { - error = inode_permission(mnt_userns, inode, MAY_WRITE); - if (error) - return error; - } - } + error = may_setattr(mnt_userns, inode, ia_valid); + if (error) + return error; if ((ia_valid & ATTR_MODE)) { umode_t amode = attr->ia_mode; diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..50192964bf6b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3469,6 +3469,8 @@ extern int buffer_migrate_page_norefs(struct address_space *, #define buffer_migrate_page_norefs NULL #endif +int may_setattr(struct user_namespace *mnt_userns, struct inode *inode, + unsigned int ia_valid); int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); void setattr_copy(struct user_namespace *, struct inode *inode, -- cgit v1.2.3 From 0a732d7dfb44da367405b23a54b305d0979e02c1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 6 Aug 2021 14:17:35 +0300 Subject: serdev: Split and export serdev_acpi_get_uart_resource() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The same as for I²C Serial Bus resource split and export serdev_acpi_get_uart_resource(). We have already a few users one of which is converted here. Rationale of this is to consolidate parsing UART Serial Bus resource in one place as it's done, e.g., for I²C Serial Bus. Reviewed-by: Hans de Goede Acked-by: Hans de Goede Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210806111736.66591-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serdev/core.c | 36 +++++++++++++++++++++++++++++------- include/linux/serdev.h | 14 ++++++++++++++ 2 files changed, 43 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c index 9cdfcfe07e87..6b997aa25f74 100644 --- a/drivers/tty/serdev/core.c +++ b/drivers/tty/serdev/core.c @@ -564,23 +564,45 @@ struct acpi_serdev_lookup { int index; }; +/** + * serdev_acpi_get_uart_resource - Gets UARTSerialBus resource if type matches + * @ares: ACPI resource + * @uart: Pointer to UARTSerialBus resource will be returned here + * + * Checks if the given ACPI resource is of type UARTSerialBus. + * In this case, returns a pointer to it to the caller. + * + * Return: True if resource type is of UARTSerialBus, otherwise false. + */ +bool serdev_acpi_get_uart_resource(struct acpi_resource *ares, + struct acpi_resource_uart_serialbus **uart) +{ + struct acpi_resource_uart_serialbus *sb; + + if (ares->type != ACPI_RESOURCE_TYPE_SERIAL_BUS) + return false; + + sb = &ares->data.uart_serial_bus; + if (sb->type != ACPI_RESOURCE_SERIAL_TYPE_UART) + return false; + + *uart = sb; + return true; +} +EXPORT_SYMBOL_GPL(serdev_acpi_get_uart_resource); + static int acpi_serdev_parse_resource(struct acpi_resource *ares, void *data) { struct acpi_serdev_lookup *lookup = data; struct acpi_resource_uart_serialbus *sb; acpi_status status; - if (ares->type != ACPI_RESOURCE_TYPE_SERIAL_BUS) - return 1; - - if (ares->data.common_serial_bus.type != ACPI_RESOURCE_SERIAL_TYPE_UART) + if (!serdev_acpi_get_uart_resource(ares, &sb)) return 1; if (lookup->index != -1 && lookup->n++ != lookup->index) return 1; - sb = &ares->data.uart_serial_bus; - status = acpi_get_handle(lookup->device_handle, sb->resource_source.string_ptr, &lookup->controller_handle); @@ -588,7 +610,7 @@ static int acpi_serdev_parse_resource(struct acpi_resource *ares, void *data) return 1; /* - * NOTE: Ideally, we would also want to retreive other properties here, + * NOTE: Ideally, we would also want to retrieve other properties here, * once setting them before opening the device is supported by serdev. */ diff --git a/include/linux/serdev.h b/include/linux/serdev.h index 9f14f9c12ec4..3368c261ab62 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -327,4 +327,18 @@ static inline int serdev_tty_port_unregister(struct tty_port *port) } #endif /* CONFIG_SERIAL_DEV_CTRL_TTYPORT */ +struct acpi_resource; +struct acpi_resource_uart_serialbus; + +#ifdef CONFIG_ACPI +bool serdev_acpi_get_uart_resource(struct acpi_resource *ares, + struct acpi_resource_uart_serialbus **uart); +#else +static inline bool serdev_acpi_get_uart_resource(struct acpi_resource *ares, + struct acpi_resource_uart_serialbus **uart) +{ + return false; +} +#endif /* CONFIG_ACPI */ + #endif /*_LINUX_SERDEV_H */ -- cgit v1.2.3 From 920792aa44ffb255c66d5295d71cc747d038cc98 Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Wed, 11 Aug 2021 14:48:24 +0300 Subject: tty: serial: samsung: Init USI to keep clocks running UART block is a part of USI (Universal Serial Interface) IP-core in Samsung SoCs since Exynos9810 (e.g. in Exynos850). USI allows one to enable one of three types of serial interface: UART, SPI or I2C. That's possible because USI shares almost all internal circuits within each protocol. USI also provides some additional registers so it's possible to configure it. One USI register called USI_OPTION has reset value of 0x0. Because of this the clock gating behavior is controlled by hardware (HWACG = Hardware Auto Clock Gating), which simply means the serial won't work after reset as is. In order to make it work, USI_OPTION[2:1] bits must be set to 0b01, so that HWACG is controlled manually (by software). Bits meaning: - CLKREQ_ON = 1: clock is continuously provided to IP - CLKSTOP_ON = 0: drive IP_CLKREQ to High (needs to be set along with CLKREQ_ON = 1) USI is not present on older chips, like s3c2410, s3c2412, s3c2440, s3c6400, s5pv210, exynos5433, exynos4210. So the new boolean field '.has_usi' was added to struct s3c24xx_uart_info. USI registers will be only actually accessed when '.has_usi' field is set to "1". This feature is needed for further serial enablement on Exynos850, but some other new Exynos chips (like Exynos9810) may benefit from this feature as well. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Sam Protsenko Link: https://lore.kernel.org/r/20210811114827.27322-5-semen.protsenko@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/samsung_tty.c | 32 +++++++++++++++++++++++++++++++- include/linux/serial_s3c.h | 9 +++++++++ 2 files changed, 40 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index 0cf4dfe77c32..857afcd5fe2d 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -65,6 +65,7 @@ enum s3c24xx_port_type { struct s3c24xx_uart_info { char *name; enum s3c24xx_port_type type; + unsigned int has_usi; unsigned int port_type; unsigned int fifosize; unsigned long rx_fifomask; @@ -1356,6 +1357,28 @@ static int apple_s5l_serial_startup(struct uart_port *port) return ret; } +static void exynos_usi_init(struct uart_port *port) +{ + struct s3c24xx_uart_port *ourport = to_ourport(port); + struct s3c24xx_uart_info *info = ourport->info; + unsigned int val; + + if (!info->has_usi) + return; + + /* Clear the software reset of USI block (it's set at startup) */ + val = rd_regl(port, USI_CON); + val &= ~USI_CON_RESET_MASK; + wr_regl(port, USI_CON, val); + udelay(1); + + /* Continuously provide the clock to USI IP w/o gating (for Rx mode) */ + val = rd_regl(port, USI_OPTION); + val &= ~USI_OPTION_HWACG_MASK; + val |= USI_OPTION_HWACG_CLKREQ_ON; + wr_regl(port, USI_OPTION, val); +} + /* power power management control */ static void s3c24xx_serial_pm(struct uart_port *port, unsigned int level, @@ -1383,6 +1406,7 @@ static void s3c24xx_serial_pm(struct uart_port *port, unsigned int level, if (!IS_ERR(ourport->baudclk)) clk_prepare_enable(ourport->baudclk); + exynos_usi_init(port); break; default: dev_err(port->dev, "s3c24xx_serial: unknown pm %d\n", level); @@ -2106,6 +2130,8 @@ static int s3c24xx_serial_init_port(struct s3c24xx_uart_port *ourport, if (ret) pr_warn("uart: failed to enable baudclk\n"); + exynos_usi_init(port); + /* Keep all interrupts masked and cleared */ switch (ourport->info->type) { case TYPE_S3C6400: @@ -2754,10 +2780,11 @@ static struct s3c24xx_serial_drv_data s5pv210_serial_drv_data = { #endif #if defined(CONFIG_ARCH_EXYNOS) -#define EXYNOS_COMMON_SERIAL_DRV_DATA \ +#define EXYNOS_COMMON_SERIAL_DRV_DATA_USI(_has_usi) \ .info = &(struct s3c24xx_uart_info) { \ .name = "Samsung Exynos UART", \ .type = TYPE_S3C6400, \ + .has_usi = _has_usi, \ .port_type = PORT_S3C6400, \ .has_divslot = 1, \ .rx_fifomask = S5PV210_UFSTAT_RXMASK, \ @@ -2777,6 +2804,9 @@ static struct s3c24xx_serial_drv_data s5pv210_serial_drv_data = { .has_fracval = 1, \ } \ +#define EXYNOS_COMMON_SERIAL_DRV_DATA \ + EXYNOS_COMMON_SERIAL_DRV_DATA_USI(0) + static struct s3c24xx_serial_drv_data exynos4210_serial_drv_data = { EXYNOS_COMMON_SERIAL_DRV_DATA, .fifosize = { 256, 64, 16, 16 }, diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h index f6c3323fc4c5..cf0de4a86640 100644 --- a/include/linux/serial_s3c.h +++ b/include/linux/serial_s3c.h @@ -27,6 +27,15 @@ #define S3C2410_UERSTAT (0x14) #define S3C2410_UFSTAT (0x18) #define S3C2410_UMSTAT (0x1C) +#define USI_CON (0xC4) +#define USI_OPTION (0xC8) + +#define USI_CON_RESET (1<<0) +#define USI_CON_RESET_MASK (1<<0) + +#define USI_OPTION_HWACG_CLKREQ_ON (1<<1) +#define USI_OPTION_HWACG_CLKSTOP_ON (1<<2) +#define USI_OPTION_HWACG_MASK (3<<1) #define S3C2410_LCON_CFGMASK ((0xF<<3)|(0x3)) -- cgit v1.2.3 From 3165af738ed3224a84ead7d97c6909de2e453b4c Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 30 Jul 2021 18:04:49 -0400 Subject: KVM: Allow to have arch-specific per-vm debugfs files Allow archs to create arch-specific nodes under kvm->debugfs_dentry directory besides the stats fields. The new interface kvm_arch_create_vm_debugfs() is defined but not yet used. It's called after kvm->debugfs_dentry is created, so it can be referenced directly in kvm_arch_create_vm_debugfs(). Arch should define their own versions when they want to create extra debugfs nodes. Signed-off-by: Peter Xu Message-Id: <20210730220455.26054-2-peterx@redhat.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 20 +++++++++++++++++++- 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 492d183dd7d0..f50bfcf225f0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1073,6 +1073,7 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_post_init_vm(struct kvm *kvm); void kvm_arch_pre_destroy_vm(struct kvm *kvm); +int kvm_arch_create_vm_debugfs(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c115e2648d9d..3e81b5d8b709 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -919,7 +919,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) char dir_name[ITOA_MAX_LEN * 2]; struct kvm_stat_data *stat_data; const struct _kvm_stats_desc *pdesc; - int i; + int i, ret; int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; @@ -976,6 +976,13 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); } + + ret = kvm_arch_create_vm_debugfs(kvm); + if (ret) { + kvm_destroy_vm_debugfs(kvm); + return i; + } + return 0; } @@ -996,6 +1003,17 @@ void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm) { } +/* + * Called after per-vm debugfs created. When called kvm->debugfs_dentry should + * be setup already, so we can create arch-specific debugfs entries under it. + * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so + * a per-arch destroy interface is not needed. + */ +int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) +{ + return 0; +} + static struct kvm *kvm_create_vm(unsigned long type) { struct kvm *kvm = kvm_arch_alloc_vm(); -- cgit v1.2.3 From 1fae562983ca5c7eb36d4974be5e235374661806 Mon Sep 17 00:00:00 2001 From: Tian Tao Date: Fri, 6 Aug 2021 23:02:47 +1200 Subject: cpumask: introduce cpumap_print_list/bitmask_to_buf to support large bitmask and list The existing cpumap_print_to_pagebuf() is used by cpu topology and other drivers to export hexadecimal bitmask and decimal list to userspace by sysfs ABI. Right now, those drivers are using a normal attribute for this kind of ABIs. A normal attribute typically has show entry as below: static ssize_t example_dev_show(struct device *dev, struct device_attribute *attr, char *buf) { ... return cpumap_print_to_pagebuf(true, buf, &pmu_mmdc->cpu); } show entry of attribute has no offset and count parameters and this means the file is limited to one page only. cpumap_print_to_pagebuf() API works terribly well for this kind of normal attribute with buf parameter and without offset, count: static inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } The problem is once we have many cpus, we have a chance to make bitmask or list more than one page. Especially for list, it could be as complex as 0,3,5,7,9,...... We have no simple way to know it exact size. It turns out bin_attribute is a way to break this limit. bin_attribute has show entry as below: static ssize_t example_bin_attribute_show(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t count) { ... } With the new offset and count parameters, this makes sysfs ABI be able to support file size more than one page. For example, offset could be >= 4096. This patch introduces cpumap_print_bitmask/list_to_buf() and their bitmap infrastructure bitmap_print_bitmask/list_to_buf() so that those drivers can move to bin_attribute to support large bitmask and list. At the same time, we have to pass those corresponding parameters such as offset, count from bin_attribute to this new API. Cc: Andrew Morton Cc: Andy Shevchenko Cc: Randy Dunlap Cc: Stefano Brivio Cc: Alexander Gordeev Cc: "Ma, Jianpeng" Cc: Yury Norov Cc: Valentin Schneider Cc: Peter Zijlstra Cc: Daniel Bristot de Oliveira Reviewed-by: Jonathan Cameron Signed-off-by: Tian Tao Signed-off-by: Barry Song Link: https://lore.kernel.org/r/20210806110251.560-2-song.bao.hua@hisilicon.com Signed-off-by: Greg Kroah-Hartman --- include/linux/bitmap.h | 6 +++ include/linux/cpumask.h | 38 ++++++++++++++++++ lib/bitmap.c | 103 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 147 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index a36cfcec4e77..37f36dad18bd 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -227,6 +227,12 @@ unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, un int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); +extern int bitmap_print_bitmask_to_buf(char *buf, const unsigned long *maskp, + int nmaskbits, loff_t off, size_t count); + +extern int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp, + int nmaskbits, loff_t off, size_t count); + #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index f3689a52bfd0..5d4d07a9e1ed 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -983,6 +983,44 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) nr_cpu_ids); } +/** + * cpumap_print_bitmask_to_buf - copies the cpumask into the buffer as + * hex values of cpumask + * + * @buf: the buffer to copy into + * @mask: the cpumask to copy + * @off: in the string from which we are copying, we copy to @buf + * @count: the maximum number of bytes to print + * + * The function prints the cpumask into the buffer as hex values of + * cpumask; Typically used by bin_attribute to export cpumask bitmask + * ABI. + * + * Returns the length of how many bytes have been copied. + */ +static inline ssize_t +cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) +{ + return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), + nr_cpu_ids, off, count); +} + +/** + * cpumap_print_list_to_buf - copies the cpumask into the buffer as + * comma-separated list of cpus + * + * Everything is same with the above cpumap_print_bitmask_to_buf() + * except the print format. + */ +static inline ssize_t +cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) +{ + return bitmap_print_list_to_buf(buf, cpumask_bits(mask), + nr_cpu_ids, off, count); +} + #if NR_CPUS <= BITS_PER_LONG #define CPU_MASK_ALL \ (cpumask_t) { { \ diff --git a/lib/bitmap.c b/lib/bitmap.c index 9401d39e4722..73746d96af81 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -487,6 +487,109 @@ int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, } EXPORT_SYMBOL(bitmap_print_to_pagebuf); +/** + * bitmap_print_to_buf - convert bitmap to list or hex format ASCII string + * @list: indicates whether the bitmap must be list + * true: print in decimal list format + * false: print in hexadecimal bitmask format + */ +static int bitmap_print_to_buf(bool list, char *buf, const unsigned long *maskp, + int nmaskbits, loff_t off, size_t count) +{ + const char *fmt = list ? "%*pbl\n" : "%*pb\n"; + ssize_t size; + void *data; + + data = kasprintf(GFP_KERNEL, fmt, nmaskbits, maskp); + if (!data) + return -ENOMEM; + + size = memory_read_from_buffer(buf, count, &off, data, strlen(data) + 1); + kfree(data); + + return size; +} + +/** + * bitmap_print_bitmask_to_buf - convert bitmap to hex bitmask format ASCII string + * + * The bitmap_print_to_pagebuf() is used indirectly via its cpumap wrapper + * cpumap_print_to_pagebuf() or directly by drivers to export hexadecimal + * bitmask and decimal list to userspace by sysfs ABI. + * Drivers might be using a normal attribute for this kind of ABIs. A + * normal attribute typically has show entry as below: + * static ssize_t example_attribute_show(struct device *dev, + * struct device_attribute *attr, char *buf) + * { + * ... + * return bitmap_print_to_pagebuf(true, buf, &mask, nr_trig_max); + * } + * show entry of attribute has no offset and count parameters and this + * means the file is limited to one page only. + * bitmap_print_to_pagebuf() API works terribly well for this kind of + * normal attribute with buf parameter and without offset, count: + * bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, + * int nmaskbits) + * { + * } + * The problem is once we have a large bitmap, we have a chance to get a + * bitmask or list more than one page. Especially for list, it could be + * as complex as 0,3,5,7,9,... We have no simple way to know it exact size. + * It turns out bin_attribute is a way to break this limit. bin_attribute + * has show entry as below: + * static ssize_t + * example_bin_attribute_show(struct file *filp, struct kobject *kobj, + * struct bin_attribute *attr, char *buf, + * loff_t offset, size_t count) + * { + * ... + * } + * With the new offset and count parameters, this makes sysfs ABI be able + * to support file size more than one page. For example, offset could be + * >= 4096. + * bitmap_print_bitmask_to_buf(), bitmap_print_list_to_buf() wit their + * cpumap wrapper cpumap_print_bitmask_to_buf(), cpumap_print_list_to_buf() + * make those drivers be able to support large bitmask and list after they + * move to use bin_attribute. In result, we have to pass the corresponding + * parameters such as off, count from bin_attribute show entry to this API. + * + * @buf: buffer into which string is placed + * @maskp: pointer to bitmap to convert + * @nmaskbits: size of bitmap, in bits + * @off: in the string from which we are copying, We copy to @buf + * @count: the maximum number of bytes to print + * + * The role of cpumap_print_bitmask_to_buf() and cpumap_print_list_to_buf() + * is similar with cpumap_print_to_pagebuf(), the difference is that + * bitmap_print_to_pagebuf() mainly serves sysfs attribute with the assumption + * the destination buffer is exactly one page and won't be more than one page. + * cpumap_print_bitmask_to_buf() and cpumap_print_list_to_buf(), on the other + * hand, mainly serves bin_attribute which doesn't work with exact one page, + * and it can break the size limit of converted decimal list and hexadecimal + * bitmask. + * + * Returns the number of characters actually printed to @buf + */ +int bitmap_print_bitmask_to_buf(char *buf, const unsigned long *maskp, + int nmaskbits, loff_t off, size_t count) +{ + return bitmap_print_to_buf(false, buf, maskp, nmaskbits, off, count); +} +EXPORT_SYMBOL(bitmap_print_bitmask_to_buf); + +/** + * bitmap_print_list_to_buf - convert bitmap to decimal list format ASCII string + * + * Everything is same with the above bitmap_print_bitmask_to_buf() except + * the print format. + */ +int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp, + int nmaskbits, loff_t off, size_t count) +{ + return bitmap_print_to_buf(true, buf, maskp, nmaskbits, off, count); +} +EXPORT_SYMBOL(bitmap_print_list_to_buf); + /* * Region 9-38:4/10 describes the following bitmap structure: * 0 9 12 18 38 N -- cgit v1.2.3 From 7a3dc4f35bf8e1a07e5c3f8ecc8ac923f48493fe Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 13 Aug 2021 12:36:14 +0200 Subject: driver core: Add missing kernel doc for device::msi_lock Fixes: 77e89afc25f3 ("PCI/MSI: Protect msi_desc::masked for multi-MSI") Reported-by: Stephen Rothwell Signed-off-by: Thomas Gleixner --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index e53aa5065f58..65d84b67b024 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -407,6 +407,7 @@ struct dev_links_info { * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. + * @msi_lock: Lock to protect MSI mask cache and mask register * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. -- cgit v1.2.3 From 97d99f7e8f1ccaa18d6447f4a3b0b48ed64aa214 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Fri, 13 Aug 2021 14:30:53 +0800 Subject: usb: gadget: remove unnecessary AND operation when get ep maxp usb_endpoint_maxp() already returns actual max packet size, no need to AND 0x7ff. Acked-by: Felipe Balbi Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/1628836253-7432-7-git-send-email-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 776851e57741..10fe57cf40be 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -492,7 +492,7 @@ extern char *usb_get_gadget_udc_name(void); */ static inline size_t usb_ep_align(struct usb_ep *ep, size_t len) { - int max_packet_size = (size_t)usb_endpoint_maxp(ep->desc) & 0x7ff; + int max_packet_size = (size_t)usb_endpoint_maxp(ep->desc); return round_up(len, max_packet_size); } -- cgit v1.2.3 From e12ef7bf34113f55c9bf444a680a15b6daf76f26 Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Mon, 19 Jul 2021 11:39:12 +0800 Subject: lib: add linear range get selector within Add linear range get selector within for choose closest selector between minimum and maximum selector. Signed-off-by: Gene Chen Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- include/linux/linear_range.h | 2 ++ lib/linear_ranges.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/linear_range.h b/include/linux/linear_range.h index 17b5943727d5..fd3d0b358f22 100644 --- a/include/linux/linear_range.h +++ b/include/linux/linear_range.h @@ -41,6 +41,8 @@ int linear_range_get_selector_low(const struct linear_range *r, int linear_range_get_selector_high(const struct linear_range *r, unsigned int val, unsigned int *selector, bool *found); +void linear_range_get_selector_within(const struct linear_range *r, + unsigned int val, unsigned int *selector); int linear_range_get_selector_low_array(const struct linear_range *r, int ranges, unsigned int val, unsigned int *selector, bool *found); diff --git a/lib/linear_ranges.c b/lib/linear_ranges.c index ced5c15d3f04..a1a7dfa881de 100644 --- a/lib/linear_ranges.c +++ b/lib/linear_ranges.c @@ -241,5 +241,36 @@ int linear_range_get_selector_high(const struct linear_range *r, } EXPORT_SYMBOL_GPL(linear_range_get_selector_high); +/** + * linear_range_get_selector_within - return linear range selector for value + * @r: pointer to linear range where selector is looked from + * @val: value for which the selector is searched + * @selector: address where found selector value is updated + * + * Return selector for which range value is closest match for given + * input value. Value is matching if it is equal or lower than given + * value. But return maximum selector if given value is higher than + * maximum value. + */ +void linear_range_get_selector_within(const struct linear_range *r, + unsigned int val, unsigned int *selector) +{ + if (r->min > val) { + *selector = r->min_sel; + return; + } + + if (linear_range_get_max_value(r) < val) { + *selector = r->max_sel; + return; + } + + if (r->step == 0) + *selector = r->min_sel; + else + *selector = (val - r->min) / r->step + r->min_sel; +} +EXPORT_SYMBOL_GPL(linear_range_get_selector_within); + MODULE_DESCRIPTION("linear-ranges helper"); MODULE_LICENSE("GPL"); -- cgit v1.2.3 From afa79d08c6c8e1901cb1547591e3ccd3ec6965d9 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 13 Aug 2021 22:57:49 +0800 Subject: net: in_irq() cleanup Replace the obsolete and ambiguos macro in_irq() with new macro in_hardirq(). Signed-off-by: Changbin Du Link: https://lore.kernel.org/r/20210813145749.86512-1-changbin.du@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 +- net/core/bpf_sk_storage.c | 4 ++-- net/core/dev.c | 2 +- net/core/skbuff.c | 6 +++--- net/nfc/rawsock.c | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bd8d5b8e2de3..2f03cd9e371a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3956,7 +3956,7 @@ void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); /* * It is not allowed to call kfree_skb() or consume_skb() from hardware * interrupt context or with hardware interrupts being disabled. - * (in_irq() || irqs_disabled()) + * (in_hardirq() || irqs_disabled()) * * We provide four helpers that can be used in following contexts : * diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index f564f82e91d9..68d2cbf8331a 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -416,7 +416,7 @@ static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { - if (in_irq() || in_nmi()) + if (in_hardirq() || in_nmi()) return (unsigned long)NULL; return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags); @@ -425,7 +425,7 @@ BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map, struct sock *, sk) { - if (in_irq() || in_nmi()) + if (in_hardirq() || in_nmi()) return -EPERM; return ____bpf_sk_storage_delete(map, sk); diff --git a/net/core/dev.c b/net/core/dev.c index 88650791c360..74fd402d26dd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3107,7 +3107,7 @@ EXPORT_SYMBOL(__dev_kfree_skb_irq); void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { - if (in_irq() || irqs_disabled()) + if (in_hardirq() || irqs_disabled()) __dev_kfree_skb_irq(skb, reason); else dev_kfree_skb(skb); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9240af2ea8c9..f9311762cc47 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -156,7 +156,7 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) void *data; fragsz = SKB_DATA_ALIGN(fragsz); - if (in_irq() || irqs_disabled()) { + if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); } else { @@ -502,7 +502,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; - if (in_irq() || irqs_disabled()) { + if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; @@ -724,7 +724,7 @@ void skb_release_head_state(struct sk_buff *skb) { skb_dst_drop(skb); if (skb->destructor) { - WARN_ON(in_irq()); + WARN_ON(in_hardirq()); skb->destructor(skb); } #if IS_ENABLED(CONFIG_NF_CONNTRACK) diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 5e39640becdb..0ca214ab5aef 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -140,7 +140,7 @@ static void rawsock_data_exchange_complete(void *context, struct sk_buff *skb, { struct sock *sk = (struct sock *) context; - BUG_ON(in_irq()); + BUG_ON(in_hardirq()); pr_debug("sk=%p err=%d\n", sk, err); -- cgit v1.2.3 From e5f31552674e88bff3a4e3ca3e5357668b5f2973 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 12 Aug 2021 20:33:58 +0200 Subject: ethernet: fix PTP_1588_CLOCK dependencies The 'imply' keyword does not do what most people think it does, it only politely asks Kconfig to turn on another symbol, but does not prevent it from being disabled manually or built as a loadable module when the user is built-in. In the ICE driver, the latter now causes a link failure: aarch64-linux-ld: drivers/net/ethernet/intel/ice/ice_main.o: in function `ice_eth_ioctl': ice_main.c:(.text+0x13b0): undefined reference to `ice_ptp_get_ts_config' ice_main.c:(.text+0x13b0): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `ice_ptp_get_ts_config' aarch64-linux-ld: ice_main.c:(.text+0x13bc): undefined reference to `ice_ptp_set_ts_config' ice_main.c:(.text+0x13bc): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `ice_ptp_set_ts_config' aarch64-linux-ld: drivers/net/ethernet/intel/ice/ice_main.o: in function `ice_prepare_for_reset': ice_main.c:(.text+0x31fc): undefined reference to `ice_ptp_release' ice_main.c:(.text+0x31fc): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `ice_ptp_release' aarch64-linux-ld: drivers/net/ethernet/intel/ice/ice_main.o: in function `ice_rebuild': This is a recurring problem in many drivers, and we have discussed it several times befores, without reaching a consensus. I'm providing a link to the previous email thread for reference, which discusses some related problems. To solve the dependency issue better than the 'imply' keyword, introduce a separate Kconfig symbol "CONFIG_PTP_1588_CLOCK_OPTIONAL" that any driver can depend on if it is able to use PTP support when available, but works fine without it. Whenever CONFIG_PTP_1588_CLOCK=m, those drivers are then prevented from being built-in, the same way as with a 'depends on PTP_1588_CLOCK || !PTP_1588_CLOCK' dependency that does the same trick, but that can be rather confusing when you first see it. Since this should cover the dependencies correctly, the IS_REACHABLE() hack in the header is no longer needed now, and can be turned back into a normal IS_ENABLED() check. Any driver that gets the dependency wrong will now cause a link time failure rather than being unable to use PTP support when that is in a loadable module. However, the two recently added ptp_get_vclocks_index() and ptp_convert_timestamp() interfaces are only called from builtin code with ethtool and socket timestamps, so keep the current behavior by stubbing those out completely when PTP is in a loadable module. This should be addressed properly in a follow-up. As Richard suggested, we may want to actually turn PTP support into a 'bool' option later on, preventing it from being a loadable module altogether, which would be one way to solve the problem with the ethtool interface. Fixes: 06c16d89d2cb ("ice: register 1588 PTP clock device object for E810 devices") Link: https://lore.kernel.org/netdev/20210804121318.337276-1-arnd@kernel.org/ Link: https://lore.kernel.org/netdev/CAK8P3a06enZOf=XyZ+zcAwBczv41UuCTz+=0FMf2gBz1_cOnZQ@mail.gmail.com/ Link: https://lore.kernel.org/netdev/CAK8P3a3=eOxE-K25754+fB_-i_0BZzf9a9RfPTX3ppSwu9WZXw@mail.gmail.com/ Link: https://lore.kernel.org/netdev/20210726084540.3282344-1-arnd@kernel.org/ Acked-by: Shannon Nelson Acked-by: Jacob Keller Acked-by: Richard Cochran Reviewed-by: Vladimir Oltean Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210812183509.1362782-1-arnd@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mv88e6xxx/Kconfig | 1 + drivers/net/dsa/ocelot/Kconfig | 2 ++ drivers/net/dsa/sja1105/Kconfig | 1 + drivers/net/ethernet/amd/Kconfig | 2 +- drivers/net/ethernet/broadcom/Kconfig | 6 ++-- drivers/net/ethernet/cadence/Kconfig | 1 + drivers/net/ethernet/cavium/Kconfig | 4 +-- drivers/net/ethernet/chelsio/Kconfig | 1 + drivers/net/ethernet/freescale/Kconfig | 2 +- drivers/net/ethernet/hisilicon/Kconfig | 2 +- drivers/net/ethernet/intel/Kconfig | 12 +++---- drivers/net/ethernet/marvell/octeontx2/Kconfig | 2 ++ drivers/net/ethernet/mellanox/mlx4/Kconfig | 2 +- drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 2 +- drivers/net/ethernet/mellanox/mlxsw/Kconfig | 2 +- drivers/net/ethernet/microchip/Kconfig | 1 + drivers/net/ethernet/mscc/Kconfig | 1 + drivers/net/ethernet/oki-semi/pch_gbe/Kconfig | 1 + drivers/net/ethernet/pensando/Kconfig | 2 +- drivers/net/ethernet/qlogic/Kconfig | 2 +- drivers/net/ethernet/renesas/Kconfig | 2 +- drivers/net/ethernet/samsung/Kconfig | 2 +- drivers/net/ethernet/sfc/Kconfig | 2 +- drivers/net/ethernet/stmicro/stmmac/Kconfig | 2 +- drivers/net/phy/Kconfig | 2 ++ drivers/ptp/Kconfig | 15 +++++++- drivers/ptp/ptp_vclock.c | 2 ++ drivers/scsi/cxgbi/cxgb4i/Kconfig | 1 + include/linux/ptp_clock_kernel.h | 48 ++++++++++++++----------- 29 files changed, 81 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig index 634a48e6616b..7a2445a34eb7 100644 --- a/drivers/net/dsa/mv88e6xxx/Kconfig +++ b/drivers/net/dsa/mv88e6xxx/Kconfig @@ -2,6 +2,7 @@ config NET_DSA_MV88E6XXX tristate "Marvell 88E6xxx Ethernet switch fabric support" depends on NET_DSA + depends on PTP_1588_CLOCK_OPTIONAL select IRQ_DOMAIN select NET_DSA_TAG_EDSA select NET_DSA_TAG_DSA diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index 932b6b6fe817..9948544ba1c4 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -5,6 +5,7 @@ config NET_DSA_MSCC_FELIX depends on NET_VENDOR_MICROSEMI depends on NET_VENDOR_FREESCALE depends on HAS_IOMEM + depends on PTP_1588_CLOCK_OPTIONAL select MSCC_OCELOT_SWITCH_LIB select NET_DSA_TAG_OCELOT_8021Q select NET_DSA_TAG_OCELOT @@ -19,6 +20,7 @@ config NET_DSA_MSCC_SEVILLE depends on NET_DSA depends on NET_VENDOR_MICROSEMI depends on HAS_IOMEM + depends on PTP_1588_CLOCK_OPTIONAL select MSCC_OCELOT_SWITCH_LIB select NET_DSA_TAG_OCELOT_8021Q select NET_DSA_TAG_OCELOT diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig index b29d41e5e1e7..1291bba3f3b6 100644 --- a/drivers/net/dsa/sja1105/Kconfig +++ b/drivers/net/dsa/sja1105/Kconfig @@ -2,6 +2,7 @@ config NET_DSA_SJA1105 tristate "NXP SJA1105 Ethernet switch family support" depends on NET_DSA && SPI + depends on PTP_1588_CLOCK_OPTIONAL select NET_DSA_TAG_SJA1105 select PCS_XPCS select PACKING diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index c6a3abec86f5..4786f0504691 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -170,11 +170,11 @@ config AMD_XGBE tristate "AMD 10GbE Ethernet driver" depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM depends on X86 || ARM64 || COMPILE_TEST + depends on PTP_1588_CLOCK_OPTIONAL select BITREVERSE select CRC32 select PHYLIB select AMD_XGBE_HAVE_ECC if X86 - imply PTP_1588_CLOCK help This driver supports the AMD 10GbE Ethernet device found on an AMD SoC. diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 1a02ca600b71..56e0fb07aec7 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -122,8 +122,8 @@ config SB1250_MAC config TIGON3 tristate "Broadcom Tigon3 support" depends on PCI + depends on PTP_1588_CLOCK_OPTIONAL select PHYLIB - imply PTP_1588_CLOCK help This driver supports Broadcom Tigon3 based gigabit Ethernet cards. @@ -140,7 +140,7 @@ config TIGON3_HWMON config BNX2X tristate "Broadcom NetXtremeII 10Gb support" depends on PCI - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL select FW_LOADER select ZLIB_INFLATE select LIBCRC32C @@ -206,7 +206,7 @@ config SYSTEMPORT config BNXT tristate "Broadcom NetXtreme-C/E support" depends on PCI - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL select FW_LOADER select LIBCRC32C select NET_DEVLINK diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig index e432a68ac520..5b2a461dfd28 100644 --- a/drivers/net/ethernet/cadence/Kconfig +++ b/drivers/net/ethernet/cadence/Kconfig @@ -22,6 +22,7 @@ if NET_VENDOR_CADENCE config MACB tristate "Cadence MACB/GEM support" depends on HAS_DMA && COMMON_CLK + depends on PTP_1588_CLOCK_OPTIONAL select PHYLINK select CRC32 help diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 4875cdae622e..1c76c95b0b27 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -66,7 +66,7 @@ config LIQUIDIO tristate "Cavium LiquidIO support" depends on 64BIT && PCI depends on PCI - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL select FW_LOADER select LIBCRC32C select NET_DEVLINK @@ -91,7 +91,7 @@ config OCTEON_MGMT_ETHERNET config LIQUIDIO_VF tristate "Cavium LiquidIO VF support" depends on 64BIT && PCI_MSI - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL help This driver supports Cavium LiquidIO Intelligent Server Adapter based on CN23XX chips. diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig index 8ba0e08e5e64..c931ec8cac40 100644 --- a/drivers/net/ethernet/chelsio/Kconfig +++ b/drivers/net/ethernet/chelsio/Kconfig @@ -69,6 +69,7 @@ config CHELSIO_T3 config CHELSIO_T4 tristate "Chelsio Communications T4/T5/T6 Ethernet support" depends on PCI && (IPV6 || IPV6=n) && (TLS || TLS=n) + depends on PTP_1588_CLOCK_OPTIONAL select FW_LOADER select MDIO select ZLIB_DEFLATE diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index 2d1abdd58fab..e04e1c5cb013 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -25,10 +25,10 @@ config FEC depends on (M523x || M527x || M5272 || M528x || M520x || M532x || \ ARCH_MXC || SOC_IMX28 || COMPILE_TEST) default ARCH_MXC || SOC_IMX28 if ARM + depends on PTP_1588_CLOCK_OPTIONAL select CRC32 select PHYLIB imply NET_SELFTESTS - imply PTP_1588_CLOCK help Say Y here if you want to use the built-in 10/100 Fast ethernet controller on some Motorola ColdFire and Freescale i.MX processors. diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 2ba0e7bd3466..3312e1d93c3b 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -104,7 +104,7 @@ config HNS3_HCLGE tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support" default m depends on PCI_MSI - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL help This selects the HNS3_HCLGE network acceleration engine & its hardware compatibility layer. The engine would be used in Hisilicon hip08 family of diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 82744a7501c7..b0b6f90deb7d 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -58,8 +58,8 @@ config E1000 config E1000E tristate "Intel(R) PRO/1000 PCI-Express Gigabit Ethernet support" depends on PCI && (!SPARC32 || BROKEN) + depends on PTP_1588_CLOCK_OPTIONAL select CRC32 - imply PTP_1588_CLOCK help This driver supports the PCI-Express Intel(R) PRO/1000 gigabit ethernet family of adapters. For PCI or PCI-X e1000 adapters, @@ -87,7 +87,7 @@ config E1000E_HWTS config IGB tristate "Intel(R) 82575/82576 PCI-Express Gigabit Ethernet support" depends on PCI - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL select I2C select I2C_ALGOBIT help @@ -159,9 +159,9 @@ config IXGB config IXGBE tristate "Intel(R) 10GbE PCI Express adapters support" depends on PCI + depends on PTP_1588_CLOCK_OPTIONAL select MDIO select PHYLIB - imply PTP_1588_CLOCK help This driver supports Intel(R) 10GbE PCI Express family of adapters. For more information on how to identify your adapter, go @@ -239,7 +239,7 @@ config IXGBEVF_IPSEC config I40E tristate "Intel(R) Ethernet Controller XL710 Family support" - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL depends on PCI select AUXILIARY_BUS help @@ -295,11 +295,11 @@ config ICE tristate "Intel(R) Ethernet Connection E800 Series Support" default n depends on PCI_MSI + depends on PTP_1588_CLOCK_OPTIONAL select AUXILIARY_BUS select DIMLIB select NET_DEVLINK select PLDMFW - imply PTP_1588_CLOCK help This driver supports Intel(R) Ethernet Connection E800 Series of devices. For more information on how to identify your adapter, go @@ -317,7 +317,7 @@ config FM10K tristate "Intel(R) FM10000 Ethernet Switch Host Interface Support" default n depends on PCI_MSI - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL help This driver supports Intel(R) FM10000 Ethernet Switch Host Interface. For more information on how to identify your adapter, diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig index 16caa02095fe..2aa0ae8abfbb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/Kconfig +++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig @@ -12,6 +12,7 @@ config OCTEONTX2_AF select NET_DEVLINK depends on (64BIT && COMPILE_TEST) || ARM64 depends on PCI + depends on PTP_1588_CLOCK_OPTIONAL help This driver supports Marvell's OcteonTX2 Resource Virtualization Unit's admin function manager which manages all RVU HW resources @@ -32,6 +33,7 @@ config OCTEONTX2_PF select OCTEONTX2_MBOX depends on (64BIT && COMPILE_TEST) || ARM64 depends on PCI + depends on PTP_1588_CLOCK_OPTIONAL help This driver supports Marvell's OcteonTX2 NIC physical function. diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig index 400e611ba041..1b4b1f642317 100644 --- a/drivers/net/ethernet/mellanox/mlx4/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig @@ -6,8 +6,8 @@ config MLX4_EN tristate "Mellanox Technologies 1/10/40Gbit Ethernet support" depends on PCI && NETDEVICES && ETHERNET && INET + depends on PTP_1588_CLOCK_OPTIONAL select MLX4_CORE - imply PTP_1588_CLOCK help This driver supports Mellanox Technologies ConnectX Ethernet devices. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index e1a5a79e27c7..92056452a9e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -10,7 +10,7 @@ config MLX5_CORE select NET_DEVLINK depends on VXLAN || !VXLAN depends on MLXFW || !MLXFW - depends on PTP_1588_CLOCK || !PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE help Core driver for low level functionality of the ConnectX-4 and diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 12871c8dc7c1..d1ae248e125c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -58,10 +58,10 @@ config MLXSW_SPECTRUM depends on NET_IPGRE || NET_IPGRE=n depends on IPV6_GRE || IPV6_GRE=n depends on VXLAN || VXLAN=n + depends on PTP_1588_CLOCK_OPTIONAL select GENERIC_ALLOCATOR select PARMAN select OBJAGG - imply PTP_1588_CLOCK select NET_PTP_CLASSIFY if PTP_1588_CLOCK default m help diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig index d54aa164c4e9..735eea1dacf1 100644 --- a/drivers/net/ethernet/microchip/Kconfig +++ b/drivers/net/ethernet/microchip/Kconfig @@ -45,6 +45,7 @@ config ENCX24J600 config LAN743X tristate "LAN743x support" depends on PCI + depends on PTP_1588_CLOCK_OPTIONAL select PHYLIB select CRC16 select CRC32 diff --git a/drivers/net/ethernet/mscc/Kconfig b/drivers/net/ethernet/mscc/Kconfig index 2d3157e4d081..b1d68e197258 100644 --- a/drivers/net/ethernet/mscc/Kconfig +++ b/drivers/net/ethernet/mscc/Kconfig @@ -24,6 +24,7 @@ config MSCC_OCELOT_SWITCH_LIB config MSCC_OCELOT_SWITCH tristate "Ocelot switch driver" + depends on PTP_1588_CLOCK_OPTIONAL depends on BRIDGE || BRIDGE=n depends on NET_SWITCHDEV depends on HAS_IOMEM diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig index af84f72bf08e..4e18b64dceb9 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig +++ b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig @@ -6,6 +6,7 @@ config PCH_GBE tristate "OKI SEMICONDUCTOR IOH(ML7223/ML7831) GbE" depends on PCI && (X86_32 || COMPILE_TEST) + depends on PTP_1588_CLOCK select MII select PTP_1588_CLOCK_PCH select NET_PTP_CLASSIFY diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig index 202973a82712..3f7519e435b8 100644 --- a/drivers/net/ethernet/pensando/Kconfig +++ b/drivers/net/ethernet/pensando/Kconfig @@ -20,7 +20,7 @@ if NET_VENDOR_PENSANDO config IONIC tristate "Pensando Ethernet IONIC Support" depends on 64BIT && PCI - depends on PTP_1588_CLOCK || !PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL select NET_DEVLINK select DIMLIB help diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig index 98f430905ffa..1203353238e5 100644 --- a/drivers/net/ethernet/qlogic/Kconfig +++ b/drivers/net/ethernet/qlogic/Kconfig @@ -99,7 +99,7 @@ config QED_SRIOV config QEDE tristate "QLogic QED 25/40/100Gb Ethernet NIC" depends on QED - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL help This enables the support for Marvell FastLinQ adapters family, ethernet driver. diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index 5a2a4af31812..8008b2f45934 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -32,11 +32,11 @@ config SH_ETH config RAVB tristate "Renesas Ethernet AVB support" depends on ARCH_RENESAS || COMPILE_TEST + depends on PTP_1588_CLOCK_OPTIONAL select CRC32 select MII select MDIO_BITBANG select PHYLIB - imply PTP_1588_CLOCK help Renesas Ethernet AVB device driver. This driver supports the following SoCs: diff --git a/drivers/net/ethernet/samsung/Kconfig b/drivers/net/ethernet/samsung/Kconfig index 0582e110b1c0..2a6c2658d284 100644 --- a/drivers/net/ethernet/samsung/Kconfig +++ b/drivers/net/ethernet/samsung/Kconfig @@ -20,9 +20,9 @@ if NET_VENDOR_SAMSUNG config SXGBE_ETH tristate "Samsung 10G/2.5G/1G SXGBE Ethernet driver" depends on HAS_IOMEM && HAS_DMA + depends on PTP_1588_CLOCK_OPTIONAL select PHYLIB select CRC32 - imply PTP_1588_CLOCK help This is the driver for the SXGBE 10G Ethernet IP block found on Samsung platforms. diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig index 5e37c8313725..97ce64079855 100644 --- a/drivers/net/ethernet/sfc/Kconfig +++ b/drivers/net/ethernet/sfc/Kconfig @@ -19,9 +19,9 @@ if NET_VENDOR_SOLARFLARE config SFC tristate "Solarflare SFC9000/SFC9100/EF100-family support" depends on PCI + depends on PTP_1588_CLOCK_OPTIONAL select MDIO select CRC32 - imply PTP_1588_CLOCK help This driver supports 10/40-gigabit Ethernet cards based on the Solarflare SFC9000-family and SFC9100-family controllers. diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index ac3c248d4f9b..929cfc22cd0c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -2,12 +2,12 @@ config STMMAC_ETH tristate "STMicroelectronics Multi-Gigabit Ethernet driver" depends on HAS_IOMEM && HAS_DMA + depends on PTP_1588_CLOCK_OPTIONAL select MII select PCS_XPCS select PAGE_POOL select PHYLINK select CRC32 - imply PTP_1588_CLOCK select RESET_CONTROLLER help This is the driver for the Ethernet IPs built around a diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 7564ae0c1997..902495afcb38 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -236,6 +236,7 @@ config MICROCHIP_T1_PHY config MICROSEMI_PHY tristate "Microsemi PHYs" depends on MACSEC || MACSEC=n + depends on PTP_1588_CLOCK_OPTIONAL || !NETWORK_PHY_TIMESTAMPING select CRYPTO_LIB_AES if MACSEC help Currently supports VSC8514, VSC8530, VSC8531, VSC8540 and VSC8541 PHYs @@ -253,6 +254,7 @@ config NATIONAL_PHY config NXP_C45_TJA11XX_PHY tristate "NXP C45 TJA11XX PHYs" + depends on PTP_1588_CLOCK_OPTIONAL help Enable support for NXP C45 TJA11XX PHYs. Currently supports only the TJA1103 PHY. diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index 8b08745e1ca1..e82b4a678acb 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -8,6 +8,7 @@ menu "PTP clock support" config PTP_1588_CLOCK tristate "PTP clock support" depends on NET && POSIX_TIMERS + default ETHERNET select PPS select NET_PTP_CLASSIFY help @@ -26,6 +27,18 @@ config PTP_1588_CLOCK To compile this driver as a module, choose M here: the module will be called ptp. +config PTP_1588_CLOCK_OPTIONAL + tristate + default y if PTP_1588_CLOCK=n + default PTP_1588_CLOCK + help + Drivers that can optionally use the PTP_1588_CLOCK framework + should depend on this symbol to prevent them from being built + into vmlinux while the PTP support itself is in a loadable + module. + If PTP support is disabled, this dependency will still be + met, and drivers refer to dummy helpers. + config PTP_1588_CLOCK_DTE tristate "Broadcom DTE as PTP clock" depends on PTP_1588_CLOCK @@ -91,7 +104,7 @@ config PTP_1588_CLOCK_PCH tristate "Intel PCH EG20T as PTP clock" depends on X86_32 || COMPILE_TEST depends on HAS_IOMEM && NET - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK help This driver adds support for using the PCH EG20T as a PTP clock. The hardware supports time stamping of PTP packets diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index e0f87c57749a..baee0379482b 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -149,6 +149,7 @@ void ptp_vclock_unregister(struct ptp_vclock *vclock) kfree(vclock); } +#if IS_BUILTIN(CONFIG_PTP_1588_CLOCK) int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { char name[PTP_CLOCK_NAME_LEN] = ""; @@ -217,3 +218,4 @@ void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, hwtstamps->hwtstamp = ns_to_ktime(ns); } EXPORT_SYMBOL(ptp_convert_timestamp); +#endif diff --git a/drivers/scsi/cxgbi/cxgb4i/Kconfig b/drivers/scsi/cxgbi/cxgb4i/Kconfig index 8b0deece9758..63c8a0f3cd0c 100644 --- a/drivers/scsi/cxgbi/cxgb4i/Kconfig +++ b/drivers/scsi/cxgbi/cxgb4i/Kconfig @@ -2,6 +2,7 @@ config SCSI_CXGB4_ISCSI tristate "Chelsio T4 iSCSI support" depends on PCI && INET && (IPV6 || IPV6=n) + depends on PTP_1588_CLOCK_OPTIONAL depends on THERMAL || !THERMAL depends on ETHERNET depends on TLS || TLS=n diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 71fac9237725..2e5565067355 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -215,7 +215,7 @@ static inline long scaled_ppm_to_ppb(long ppm) return (long)ppb; } -#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) /** * ptp_clock_register() - register a PTP hardware clock driver @@ -307,6 +307,33 @@ int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay); */ void ptp_cancel_worker_sync(struct ptp_clock *ptp); +#else +static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, + struct device *parent) +{ return NULL; } +static inline int ptp_clock_unregister(struct ptp_clock *ptp) +{ return 0; } +static inline void ptp_clock_event(struct ptp_clock *ptp, + struct ptp_clock_event *event) +{ } +static inline int ptp_clock_index(struct ptp_clock *ptp) +{ return -1; } +static inline int ptp_find_pin(struct ptp_clock *ptp, + enum ptp_pin_function func, unsigned int chan) +{ return -1; } +static inline int ptp_schedule_worker(struct ptp_clock *ptp, + unsigned long delay) +{ return -EOPNOTSUPP; } +static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) +{ } +#endif + +#if IS_BUILTIN(CONFIG_PTP_1588_CLOCK) +/* + * These are called by the network core, and don't work if PTP is in + * a loadable module. + */ + /** * ptp_get_vclocks_index() - get all vclocks index on pclock, and * caller is responsible to free memory @@ -327,26 +354,7 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); */ void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, int vclock_index); - #else -static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, - struct device *parent) -{ return NULL; } -static inline int ptp_clock_unregister(struct ptp_clock *ptp) -{ return 0; } -static inline void ptp_clock_event(struct ptp_clock *ptp, - struct ptp_clock_event *event) -{ } -static inline int ptp_clock_index(struct ptp_clock *ptp) -{ return -1; } -static inline int ptp_find_pin(struct ptp_clock *ptp, - enum ptp_pin_function func, unsigned int chan) -{ return -1; } -static inline int ptp_schedule_worker(struct ptp_clock *ptp, - unsigned long delay) -{ return -EOPNOTSUPP; } -static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) -{ } static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } static inline void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, -- cgit v1.2.3 From 2a047e0662aee1bd773e0415accd785ad26a9398 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 9 Aug 2021 17:19:36 +0200 Subject: dma-mapping: return an unsigned int from dma_map_sg{,_attrs} These can only return 0 for failure or the number of entries, so turn the return value into an unsigned int. Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe --- include/linux/dma-mapping.h | 9 +++++---- kernel/dma/mapping.c | 2 +- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index daa1e360f0ee..dca2b1355bb1 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -105,8 +105,8 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, unsigned long attrs); void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs); -int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs); +unsigned int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, unsigned long attrs); void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs); @@ -166,8 +166,9 @@ static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { } -static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, unsigned long attrs) +static inline unsigned int dma_map_sg_attrs(struct device *dev, + struct scatterlist *sg, int nents, enum dma_data_direction dir, + unsigned long attrs) { return 0; } diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 967b62692102..7ee5284bff58 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -219,7 +219,7 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, * dma_unmap_sg_attrs() should be used to unmap the buffer with the * original sg and original nents (not the value returned by this funciton). */ -int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, +unsigned int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs) { int ret; -- cgit v1.2.3 From 4eef766b7d4d88f0b984781bc1bcb574a6eafdc7 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 5 Aug 2021 10:58:28 +0200 Subject: power: supply: core: Parse battery chemistry/technology This extends the struct power_supply_battery_info with a "technology" field makes the core DT parser optionally obtain this from the device tree. Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel --- drivers/power/supply/power_supply_core.c | 20 ++++++++++++++++++++ include/linux/power_supply.h | 1 + 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index d99e2f11c183..dd62c871b2b5 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -571,6 +571,7 @@ int power_supply_get_battery_info(struct power_supply *psy, int err, len, index; const __be32 *list; + info->technology = POWER_SUPPLY_TECHNOLOGY_UNKNOWN; info->energy_full_design_uwh = -EINVAL; info->charge_full_design_uah = -EINVAL; info->voltage_min_design_uv = -EINVAL; @@ -618,6 +619,25 @@ int power_supply_get_battery_info(struct power_supply *psy, * Documentation/power/power_supply_class.rst. */ + err = of_property_read_string(battery_np, "device-chemistry", &value); + if (!err) { + if (!strcmp("nickel-cadmium", value)) + info->technology = POWER_SUPPLY_TECHNOLOGY_NiCd; + else if (!strcmp("nickel-metal-hydride", value)) + info->technology = POWER_SUPPLY_TECHNOLOGY_NiMH; + else if (!strcmp("lithium-ion", value)) + /* Imprecise lithium-ion type */ + info->technology = POWER_SUPPLY_TECHNOLOGY_LION; + else if (!strcmp("lithium-ion-polymer", value)) + info->technology = POWER_SUPPLY_TECHNOLOGY_LIPO; + else if (!strcmp("lithium-ion-iron-phosphate", value)) + info->technology = POWER_SUPPLY_TECHNOLOGY_LiFe; + else if (!strcmp("lithium-ion-manganese-oxide", value)) + info->technology = POWER_SUPPLY_TECHNOLOGY_LiMn; + else + dev_warn(&psy->dev, "%s unknown battery type\n", value); + } + of_property_read_u32(battery_np, "energy-full-design-microwatt-hours", &info->energy_full_design_uwh); of_property_read_u32(battery_np, "charge-full-design-microamp-hours", diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index be203985ecdd..9ca1f120a211 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -352,6 +352,7 @@ struct power_supply_resistance_temp_table { */ struct power_supply_battery_info { + unsigned int technology; /* from the enum above */ int energy_full_design_uwh; /* microWatt-hours */ int charge_full_design_uah; /* microAmp-hours */ int voltage_min_design_uv; /* microVolts */ -- cgit v1.2.3 From fb83610762dd5927212aa62a468dd3b756b57a88 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 22 Jul 2021 11:06:44 +0200 Subject: thermal/core: Fix thermal_cooling_device_register() prototype There are two pairs of declarations for thermal_cooling_device_register() and thermal_of_cooling_device_register(), and only one set was changed in a recent patch, so the other one now causes a compile-time warning: drivers/net/wireless/mediatek/mt76/mt7915/init.c: In function 'mt7915_thermal_init': drivers/net/wireless/mediatek/mt76/mt7915/init.c:134:48: error: passing argument 1 of 'thermal_cooling_device_register' discards 'const' qualifier from pointer target type [-Werror=discarded-qualifiers] 134 | cdev = thermal_cooling_device_register(wiphy_name(wiphy), phy, | ^~~~~~~~~~~~~~~~~ In file included from drivers/net/wireless/mediatek/mt76/mt7915/init.c:7: include/linux/thermal.h:407:39: note: expected 'char *' but argument is of type 'const char *' 407 | thermal_cooling_device_register(char *type, void *devdata, | ~~~~~~^~~~ Change the dummy helper functions to have the same arguments as the normal version. Fixes: f991de53a8ab ("thermal: make device_register's type argument const") Signed-off-by: Arnd Bergmann Reviewed-by: Jean-Francois Dagenais Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20210722090717.1116748-1-arnd@kernel.org --- include/linux/thermal.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index d296f3b88fb9..8050d929a5b4 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -404,12 +404,13 @@ static inline void thermal_zone_device_unregister( struct thermal_zone_device *tz) { } static inline struct thermal_cooling_device * -thermal_cooling_device_register(char *type, void *devdata, +thermal_cooling_device_register(const char *type, void *devdata, const struct thermal_cooling_device_ops *ops) { return ERR_PTR(-ENODEV); } static inline struct thermal_cooling_device * thermal_of_cooling_device_register(struct device_node *np, - char *type, void *devdata, const struct thermal_cooling_device_ops *ops) + const char *type, void *devdata, + const struct thermal_cooling_device_ops *ops) { return ERR_PTR(-ENODEV); } static inline struct thermal_cooling_device * devm_thermal_of_cooling_device_register(struct device *dev, -- cgit v1.2.3 From 454f2ed4b34f9ef5726d080b1eb5dc47a7f36d6f Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 14 Jul 2021 13:27:01 +0200 Subject: thermal: Spelling s/scallbacks/callbacks/ Fix a misspelling of the word "callbacks". Signed-off-by: Geert Uytterhoeven Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/ae38372996a23bb67769e2d62ca170ae9457c4df.1626261946.git.geert+renesas@glider.be --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 8050d929a5b4..c314893970b3 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -285,7 +285,7 @@ struct thermal_zone_params { }; /** - * struct thermal_zone_of_device_ops - scallbacks for handling DT based zones + * struct thermal_zone_of_device_ops - callbacks for handling DT based zones * * Mandatory: * @get_temp: a pointer to a function that reads the sensor temperature. -- cgit v1.2.3 From 9ea9b9c48387edc101d56349492ad9c0492ff78d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 12 Aug 2021 15:23:08 +0200 Subject: remove the lightnvm subsystem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Lightnvm supports the OCSSD 1.x and 2.0 specs which were early attempts to produce Open Channel SSDs and never made it into the NVMe spec proper. They have since been superceeded by NVMe enhancements such as ZNS support. Remove the support per the deprecation schedule. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210812132308.38486-1-hch@lst.de Reviewed-by: Matias Bjørling Reviewed-by: Javier González Signed-off-by: Jens Axboe --- Documentation/driver-api/index.rst | 1 - Documentation/driver-api/lightnvm-pblk.rst | 21 - Documentation/userspace-api/ioctl/ioctl-number.rst | 1 - MAINTAINERS | 9 - drivers/Kconfig | 2 - drivers/Makefile | 1 - drivers/lightnvm/Kconfig | 44 - drivers/lightnvm/Makefile | 11 - drivers/lightnvm/core.c | 1440 ------------- drivers/lightnvm/pblk-cache.c | 137 -- drivers/lightnvm/pblk-core.c | 2151 -------------------- drivers/lightnvm/pblk-gc.c | 726 ------- drivers/lightnvm/pblk-init.c | 1324 ------------ drivers/lightnvm/pblk-map.c | 210 -- drivers/lightnvm/pblk-rb.c | 858 -------- drivers/lightnvm/pblk-read.c | 474 ----- drivers/lightnvm/pblk-recovery.c | 874 -------- drivers/lightnvm/pblk-rl.c | 254 --- drivers/lightnvm/pblk-sysfs.c | 728 ------- drivers/lightnvm/pblk-trace.h | 145 -- drivers/lightnvm/pblk-write.c | 665 ------ drivers/lightnvm/pblk.h | 1358 ------------ drivers/nvme/host/Makefile | 1 - drivers/nvme/host/core.c | 13 - drivers/nvme/host/ioctl.c | 4 +- drivers/nvme/host/lightnvm.c | 1274 ------------ drivers/nvme/host/nvme.h | 26 - drivers/nvme/host/pci.c | 6 - include/linux/lightnvm.h | 697 ------- include/uapi/linux/lightnvm.h | 224 -- 30 files changed, 1 insertion(+), 13678 deletions(-) delete mode 100644 Documentation/driver-api/lightnvm-pblk.rst delete mode 100644 drivers/lightnvm/Kconfig delete mode 100644 drivers/lightnvm/Makefile delete mode 100644 drivers/lightnvm/core.c delete mode 100644 drivers/lightnvm/pblk-cache.c delete mode 100644 drivers/lightnvm/pblk-core.c delete mode 100644 drivers/lightnvm/pblk-gc.c delete mode 100644 drivers/lightnvm/pblk-init.c delete mode 100644 drivers/lightnvm/pblk-map.c delete mode 100644 drivers/lightnvm/pblk-rb.c delete mode 100644 drivers/lightnvm/pblk-read.c delete mode 100644 drivers/lightnvm/pblk-recovery.c delete mode 100644 drivers/lightnvm/pblk-rl.c delete mode 100644 drivers/lightnvm/pblk-sysfs.c delete mode 100644 drivers/lightnvm/pblk-trace.h delete mode 100644 drivers/lightnvm/pblk-write.c delete mode 100644 drivers/lightnvm/pblk.h delete mode 100644 drivers/nvme/host/lightnvm.c delete mode 100644 include/linux/lightnvm.h delete mode 100644 include/uapi/linux/lightnvm.h (limited to 'include/linux') diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index f5a3207aa7fa..c57c609ad2eb 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -85,7 +85,6 @@ available subsections can be seen below. io-mapping io_ordering generic-counter - lightnvm-pblk memory-devices/index men-chameleon-bus ntb diff --git a/Documentation/driver-api/lightnvm-pblk.rst b/Documentation/driver-api/lightnvm-pblk.rst deleted file mode 100644 index 1040ed1cec81..000000000000 --- a/Documentation/driver-api/lightnvm-pblk.rst +++ /dev/null @@ -1,21 +0,0 @@ -pblk: Physical Block Device Target -================================== - -pblk implements a fully associative, host-based FTL that exposes a traditional -block I/O interface. Its primary responsibilities are: - - - Map logical addresses onto physical addresses (4KB granularity) in a - logical-to-physical (L2P) table. - - Maintain the integrity and consistency of the L2P table as well as its - recovery from normal tear down and power outage. - - Deal with controller- and media-specific constrains. - - Handle I/O errors. - - Implement garbage collection. - - Maintain consistency across the I/O stack during synchronization points. - -For more information please refer to: - - http://lightnvm.io - -which maintains updated FAQs, manual pages, technical documentation, tools, -contacts, etc. diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 1409e40e6345..b7070d76f076 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -160,7 +160,6 @@ Code Seq# Include File Comments 'K' all linux/kd.h 'L' 00-1F linux/loop.h conflict! 'L' 10-1F drivers/scsi/mpt3sas/mpt3sas_ctl.h conflict! -'L' 20-2F linux/lightnvm.h 'L' E0-FF linux/ppdd.h encrypted disk device driver 'M' all linux/soundcard.h conflict! diff --git a/MAINTAINERS b/MAINTAINERS index c9467d2839f5..ec3f59a16c9a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10609,15 +10609,6 @@ F: LICENSES/ F: scripts/spdxcheck-test.sh F: scripts/spdxcheck.py -LIGHTNVM PLATFORM SUPPORT -M: Matias Bjorling -L: linux-block@vger.kernel.org -S: Maintained -W: http://github/OpenChannelSSD -F: drivers/lightnvm/ -F: include/linux/lightnvm.h -F: include/uapi/linux/lightnvm.h - LINEAR RANGES HELPERS M: Mark Brown R: Matti Vaittinen diff --git a/drivers/Kconfig b/drivers/Kconfig index 8bad63417a50..30d2db37cc87 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -51,8 +51,6 @@ source "drivers/net/Kconfig" source "drivers/isdn/Kconfig" -source "drivers/lightnvm/Kconfig" - # input before char - char/joystick depends on it. As does USB. source "drivers/input/Kconfig" diff --git a/drivers/Makefile b/drivers/Makefile index 27c018bdf4de..be5d40ae1488 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -70,7 +70,6 @@ obj-$(CONFIG_FB_I810) += video/fbdev/i810/ obj-$(CONFIG_FB_INTEL) += video/fbdev/intelfb/ obj-$(CONFIG_PARPORT) += parport/ -obj-$(CONFIG_NVM) += lightnvm/ obj-y += base/ block/ misc/ mfd/ nfc/ obj-$(CONFIG_LIBNVDIMM) += nvdimm/ obj-$(CONFIG_DAX) += dax/ diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig deleted file mode 100644 index 04caa0f2d445..000000000000 --- a/drivers/lightnvm/Kconfig +++ /dev/null @@ -1,44 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# Open-Channel SSD NVM configuration -# - -menuconfig NVM - bool "Open-Channel SSD target support (DEPRECATED)" - depends on BLOCK - help - Say Y here to get to enable Open-channel SSDs. - - Open-Channel SSDs implement a set of extension to SSDs, that - exposes direct access to the underlying non-volatile memory. - - If you say N, all options in this submenu will be skipped and disabled - only do this if you know what you are doing. - - This code is deprecated and will be removed in Linux 5.15. - -if NVM - -config NVM_PBLK - tristate "Physical Block Device Open-Channel SSD target" - select CRC32 - help - Allows an open-channel SSD to be exposed as a block device to the - host. The target assumes the device exposes raw flash and must be - explicitly managed by the host. - - Please note the disk format is considered EXPERIMENTAL for now. - -if NVM_PBLK - -config NVM_PBLK_DEBUG - bool "PBlk Debug Support" - default n - help - Enables debug support for pblk. This includes extra checks, more - vocal error messages, and extra tracking fields in the pblk sysfs - entries. - -endif # NVM_PBLK_DEBUG - -endif # NVM diff --git a/drivers/lightnvm/Makefile b/drivers/lightnvm/Makefile deleted file mode 100644 index 97d9d7c71550..000000000000 --- a/drivers/lightnvm/Makefile +++ /dev/null @@ -1,11 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for Open-Channel SSDs. -# - -obj-$(CONFIG_NVM) := core.o -obj-$(CONFIG_NVM_PBLK) += pblk.o -pblk-y := pblk-init.o pblk-core.o pblk-rb.o \ - pblk-write.o pblk-cache.o pblk-read.o \ - pblk-gc.o pblk-recovery.o pblk-map.o \ - pblk-rl.o pblk-sysfs.o diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c deleted file mode 100644 index cf8a75494833..000000000000 --- a/drivers/lightnvm/core.c +++ /dev/null @@ -1,1440 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2015 IT University of Copenhagen. All rights reserved. - * Initial release: Matias Bjorling - */ - -#define pr_fmt(fmt) "nvm: " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static LIST_HEAD(nvm_tgt_types); -static DECLARE_RWSEM(nvm_tgtt_lock); -static LIST_HEAD(nvm_devices); -static DECLARE_RWSEM(nvm_lock); - -/* Map between virtual and physical channel and lun */ -struct nvm_ch_map { - int ch_off; - int num_lun; - int *lun_offs; -}; - -struct nvm_dev_map { - struct nvm_ch_map *chnls; - int num_ch; -}; - -static void nvm_free(struct kref *ref); - -static struct nvm_target *nvm_find_target(struct nvm_dev *dev, const char *name) -{ - struct nvm_target *tgt; - - list_for_each_entry(tgt, &dev->targets, list) - if (!strcmp(name, tgt->disk->disk_name)) - return tgt; - - return NULL; -} - -static bool nvm_target_exists(const char *name) -{ - struct nvm_dev *dev; - struct nvm_target *tgt; - bool ret = false; - - down_write(&nvm_lock); - list_for_each_entry(dev, &nvm_devices, devices) { - mutex_lock(&dev->mlock); - list_for_each_entry(tgt, &dev->targets, list) { - if (!strcmp(name, tgt->disk->disk_name)) { - ret = true; - mutex_unlock(&dev->mlock); - goto out; - } - } - mutex_unlock(&dev->mlock); - } - -out: - up_write(&nvm_lock); - return ret; -} - -static int nvm_reserve_luns(struct nvm_dev *dev, int lun_begin, int lun_end) -{ - int i; - - for (i = lun_begin; i <= lun_end; i++) { - if (test_and_set_bit(i, dev->lun_map)) { - pr_err("lun %d already allocated\n", i); - goto err; - } - } - - return 0; -err: - while (--i >= lun_begin) - clear_bit(i, dev->lun_map); - - return -EBUSY; -} - -static void nvm_release_luns_err(struct nvm_dev *dev, int lun_begin, - int lun_end) -{ - int i; - - for (i = lun_begin; i <= lun_end; i++) - WARN_ON(!test_and_clear_bit(i, dev->lun_map)); -} - -static void nvm_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev, int clear) -{ - struct nvm_dev *dev = tgt_dev->parent; - struct nvm_dev_map *dev_map = tgt_dev->map; - int i, j; - - for (i = 0; i < dev_map->num_ch; i++) { - struct nvm_ch_map *ch_map = &dev_map->chnls[i]; - int *lun_offs = ch_map->lun_offs; - int ch = i + ch_map->ch_off; - - if (clear) { - for (j = 0; j < ch_map->num_lun; j++) { - int lun = j + lun_offs[j]; - int lunid = (ch * dev->geo.num_lun) + lun; - - WARN_ON(!test_and_clear_bit(lunid, - dev->lun_map)); - } - } - - kfree(ch_map->lun_offs); - } - - kfree(dev_map->chnls); - kfree(dev_map); - - kfree(tgt_dev->luns); - kfree(tgt_dev); -} - -static struct nvm_tgt_dev *nvm_create_tgt_dev(struct nvm_dev *dev, - u16 lun_begin, u16 lun_end, - u16 op) -{ - struct nvm_tgt_dev *tgt_dev = NULL; - struct nvm_dev_map *dev_rmap = dev->rmap; - struct nvm_dev_map *dev_map; - struct ppa_addr *luns; - int num_lun = lun_end - lun_begin + 1; - int luns_left = num_lun; - int num_ch = num_lun / dev->geo.num_lun; - int num_ch_mod = num_lun % dev->geo.num_lun; - int bch = lun_begin / dev->geo.num_lun; - int blun = lun_begin % dev->geo.num_lun; - int lunid = 0; - int lun_balanced = 1; - int sec_per_lun, prev_num_lun; - int i, j; - - num_ch = (num_ch_mod == 0) ? num_ch : num_ch + 1; - - dev_map = kmalloc(sizeof(struct nvm_dev_map), GFP_KERNEL); - if (!dev_map) - goto err_dev; - - dev_map->chnls = kcalloc(num_ch, sizeof(struct nvm_ch_map), GFP_KERNEL); - if (!dev_map->chnls) - goto err_chnls; - - luns = kcalloc(num_lun, sizeof(struct ppa_addr), GFP_KERNEL); - if (!luns) - goto err_luns; - - prev_num_lun = (luns_left > dev->geo.num_lun) ? - dev->geo.num_lun : luns_left; - for (i = 0; i < num_ch; i++) { - struct nvm_ch_map *ch_rmap = &dev_rmap->chnls[i + bch]; - int *lun_roffs = ch_rmap->lun_offs; - struct nvm_ch_map *ch_map = &dev_map->chnls[i]; - int *lun_offs; - int luns_in_chnl = (luns_left > dev->geo.num_lun) ? - dev->geo.num_lun : luns_left; - - if (lun_balanced && prev_num_lun != luns_in_chnl) - lun_balanced = 0; - - ch_map->ch_off = ch_rmap->ch_off = bch; - ch_map->num_lun = luns_in_chnl; - - lun_offs = kcalloc(luns_in_chnl, sizeof(int), GFP_KERNEL); - if (!lun_offs) - goto err_ch; - - for (j = 0; j < luns_in_chnl; j++) { - luns[lunid].ppa = 0; - luns[lunid].a.ch = i; - luns[lunid++].a.lun = j; - - lun_offs[j] = blun; - lun_roffs[j + blun] = blun; - } - - ch_map->lun_offs = lun_offs; - - /* when starting a new channel, lun offset is reset */ - blun = 0; - luns_left -= luns_in_chnl; - } - - dev_map->num_ch = num_ch; - - tgt_dev = kmalloc(sizeof(struct nvm_tgt_dev), GFP_KERNEL); - if (!tgt_dev) - goto err_ch; - - /* Inherit device geometry from parent */ - memcpy(&tgt_dev->geo, &dev->geo, sizeof(struct nvm_geo)); - - /* Target device only owns a portion of the physical device */ - tgt_dev->geo.num_ch = num_ch; - tgt_dev->geo.num_lun = (lun_balanced) ? prev_num_lun : -1; - tgt_dev->geo.all_luns = num_lun; - tgt_dev->geo.all_chunks = num_lun * dev->geo.num_chk; - - tgt_dev->geo.op = op; - - sec_per_lun = dev->geo.clba * dev->geo.num_chk; - tgt_dev->geo.total_secs = num_lun * sec_per_lun; - - tgt_dev->q = dev->q; - tgt_dev->map = dev_map; - tgt_dev->luns = luns; - tgt_dev->parent = dev; - - return tgt_dev; -err_ch: - while (--i >= 0) - kfree(dev_map->chnls[i].lun_offs); - kfree(luns); -err_luns: - kfree(dev_map->chnls); -err_chnls: - kfree(dev_map); -err_dev: - return tgt_dev; -} - -static struct nvm_tgt_type *__nvm_find_target_type(const char *name) -{ - struct nvm_tgt_type *tt; - - list_for_each_entry(tt, &nvm_tgt_types, list) - if (!strcmp(name, tt->name)) - return tt; - - return NULL; -} - -static struct nvm_tgt_type *nvm_find_target_type(const char *name) -{ - struct nvm_tgt_type *tt; - - down_write(&nvm_tgtt_lock); - tt = __nvm_find_target_type(name); - up_write(&nvm_tgtt_lock); - - return tt; -} - -static int nvm_config_check_luns(struct nvm_geo *geo, int lun_begin, - int lun_end) -{ - if (lun_begin > lun_end || lun_end >= geo->all_luns) { - pr_err("lun out of bound (%u:%u > %u)\n", - lun_begin, lun_end, geo->all_luns - 1); - return -EINVAL; - } - - return 0; -} - -static int __nvm_config_simple(struct nvm_dev *dev, - struct nvm_ioctl_create_simple *s) -{ - struct nvm_geo *geo = &dev->geo; - - if (s->lun_begin == -1 && s->lun_end == -1) { - s->lun_begin = 0; - s->lun_end = geo->all_luns - 1; - } - - return nvm_config_check_luns(geo, s->lun_begin, s->lun_end); -} - -static int __nvm_config_extended(struct nvm_dev *dev, - struct nvm_ioctl_create_extended *e) -{ - if (e->lun_begin == 0xFFFF && e->lun_end == 0xFFFF) { - e->lun_begin = 0; - e->lun_end = dev->geo.all_luns - 1; - } - - /* op not set falls into target's default */ - if (e->op == 0xFFFF) { - e->op = NVM_TARGET_DEFAULT_OP; - } else if (e->op < NVM_TARGET_MIN_OP || e->op > NVM_TARGET_MAX_OP) { - pr_err("invalid over provisioning value\n"); - return -EINVAL; - } - - return nvm_config_check_luns(&dev->geo, e->lun_begin, e->lun_end); -} - -static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) -{ - struct nvm_ioctl_create_extended e; - struct gendisk *tdisk; - struct nvm_tgt_type *tt; - struct nvm_target *t; - struct nvm_tgt_dev *tgt_dev; - void *targetdata; - unsigned int mdts; - int ret; - - switch (create->conf.type) { - case NVM_CONFIG_TYPE_SIMPLE: - ret = __nvm_config_simple(dev, &create->conf.s); - if (ret) - return ret; - - e.lun_begin = create->conf.s.lun_begin; - e.lun_end = create->conf.s.lun_end; - e.op = NVM_TARGET_DEFAULT_OP; - break; - case NVM_CONFIG_TYPE_EXTENDED: - ret = __nvm_config_extended(dev, &create->conf.e); - if (ret) - return ret; - - e = create->conf.e; - break; - default: - pr_err("config type not valid\n"); - return -EINVAL; - } - - tt = nvm_find_target_type(create->tgttype); - if (!tt) { - pr_err("target type %s not found\n", create->tgttype); - return -EINVAL; - } - - if ((tt->flags & NVM_TGT_F_HOST_L2P) != (dev->geo.dom & NVM_RSP_L2P)) { - pr_err("device is incompatible with target L2P type.\n"); - return -EINVAL; - } - - if (nvm_target_exists(create->tgtname)) { - pr_err("target name already exists (%s)\n", - create->tgtname); - return -EINVAL; - } - - ret = nvm_reserve_luns(dev, e.lun_begin, e.lun_end); - if (ret) - return ret; - - t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL); - if (!t) { - ret = -ENOMEM; - goto err_reserve; - } - - tgt_dev = nvm_create_tgt_dev(dev, e.lun_begin, e.lun_end, e.op); - if (!tgt_dev) { - pr_err("could not create target device\n"); - ret = -ENOMEM; - goto err_t; - } - - tdisk = blk_alloc_disk(dev->q->node); - if (!tdisk) { - ret = -ENOMEM; - goto err_dev; - } - - strlcpy(tdisk->disk_name, create->tgtname, sizeof(tdisk->disk_name)); - tdisk->major = 0; - tdisk->first_minor = 0; - tdisk->fops = tt->bops; - - targetdata = tt->init(tgt_dev, tdisk, create->flags); - if (IS_ERR(targetdata)) { - ret = PTR_ERR(targetdata); - goto err_init; - } - - tdisk->private_data = targetdata; - tdisk->queue->queuedata = targetdata; - - mdts = (dev->geo.csecs >> 9) * NVM_MAX_VLBA; - if (dev->geo.mdts) { - mdts = min_t(u32, dev->geo.mdts, - (dev->geo.csecs >> 9) * NVM_MAX_VLBA); - } - blk_queue_max_hw_sectors(tdisk->queue, mdts); - - set_capacity(tdisk, tt->capacity(targetdata)); - add_disk(tdisk); - - if (tt->sysfs_init && tt->sysfs_init(tdisk)) { - ret = -ENOMEM; - goto err_sysfs; - } - - t->type = tt; - t->disk = tdisk; - t->dev = tgt_dev; - - mutex_lock(&dev->mlock); - list_add_tail(&t->list, &dev->targets); - mutex_unlock(&dev->mlock); - - __module_get(tt->owner); - - return 0; -err_sysfs: - if (tt->exit) - tt->exit(targetdata, true); -err_init: - blk_cleanup_disk(tdisk); -err_dev: - nvm_remove_tgt_dev(tgt_dev, 0); -err_t: - kfree(t); -err_reserve: - nvm_release_luns_err(dev, e.lun_begin, e.lun_end); - return ret; -} - -static void __nvm_remove_target(struct nvm_target *t, bool graceful) -{ - struct nvm_tgt_type *tt = t->type; - struct gendisk *tdisk = t->disk; - - del_gendisk(tdisk); - - if (tt->sysfs_exit) - tt->sysfs_exit(tdisk); - - if (tt->exit) - tt->exit(tdisk->private_data, graceful); - - nvm_remove_tgt_dev(t->dev, 1); - blk_cleanup_disk(tdisk); - module_put(t->type->owner); - - list_del(&t->list); - kfree(t); -} - -/** - * nvm_remove_tgt - Removes a target from the media manager - * @remove: ioctl structure with target name to remove. - * - * Returns: - * 0: on success - * 1: on not found - * <0: on error - */ -static int nvm_remove_tgt(struct nvm_ioctl_remove *remove) -{ - struct nvm_target *t = NULL; - struct nvm_dev *dev; - - down_read(&nvm_lock); - list_for_each_entry(dev, &nvm_devices, devices) { - mutex_lock(&dev->mlock); - t = nvm_find_target(dev, remove->tgtname); - if (t) { - mutex_unlock(&dev->mlock); - break; - } - mutex_unlock(&dev->mlock); - } - up_read(&nvm_lock); - - if (!t) { - pr_err("failed to remove target %s\n", - remove->tgtname); - return 1; - } - - __nvm_remove_target(t, true); - kref_put(&dev->ref, nvm_free); - - return 0; -} - -static int nvm_register_map(struct nvm_dev *dev) -{ - struct nvm_dev_map *rmap; - int i, j; - - rmap = kmalloc(sizeof(struct nvm_dev_map), GFP_KERNEL); - if (!rmap) - goto err_rmap; - - rmap->chnls = kcalloc(dev->geo.num_ch, sizeof(struct nvm_ch_map), - GFP_KERNEL); - if (!rmap->chnls) - goto err_chnls; - - for (i = 0; i < dev->geo.num_ch; i++) { - struct nvm_ch_map *ch_rmap; - int *lun_roffs; - int luns_in_chnl = dev->geo.num_lun; - - ch_rmap = &rmap->chnls[i]; - - ch_rmap->ch_off = -1; - ch_rmap->num_lun = luns_in_chnl; - - lun_roffs = kcalloc(luns_in_chnl, sizeof(int), GFP_KERNEL); - if (!lun_roffs) - goto err_ch; - - for (j = 0; j < luns_in_chnl; j++) - lun_roffs[j] = -1; - - ch_rmap->lun_offs = lun_roffs; - } - - dev->rmap = rmap; - - return 0; -err_ch: - while (--i >= 0) - kfree(rmap->chnls[i].lun_offs); -err_chnls: - kfree(rmap); -err_rmap: - return -ENOMEM; -} - -static void nvm_unregister_map(struct nvm_dev *dev) -{ - struct nvm_dev_map *rmap = dev->rmap; - int i; - - for (i = 0; i < dev->geo.num_ch; i++) - kfree(rmap->chnls[i].lun_offs); - - kfree(rmap->chnls); - kfree(rmap); -} - -static void nvm_map_to_dev(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p) -{ - struct nvm_dev_map *dev_map = tgt_dev->map; - struct nvm_ch_map *ch_map = &dev_map->chnls[p->a.ch]; - int lun_off = ch_map->lun_offs[p->a.lun]; - - p->a.ch += ch_map->ch_off; - p->a.lun += lun_off; -} - -static void nvm_map_to_tgt(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p) -{ - struct nvm_dev *dev = tgt_dev->parent; - struct nvm_dev_map *dev_rmap = dev->rmap; - struct nvm_ch_map *ch_rmap = &dev_rmap->chnls[p->a.ch]; - int lun_roff = ch_rmap->lun_offs[p->a.lun]; - - p->a.ch -= ch_rmap->ch_off; - p->a.lun -= lun_roff; -} - -static void nvm_ppa_tgt_to_dev(struct nvm_tgt_dev *tgt_dev, - struct ppa_addr *ppa_list, int nr_ppas) -{ - int i; - - for (i = 0; i < nr_ppas; i++) { - nvm_map_to_dev(tgt_dev, &ppa_list[i]); - ppa_list[i] = generic_to_dev_addr(tgt_dev->parent, ppa_list[i]); - } -} - -static void nvm_ppa_dev_to_tgt(struct nvm_tgt_dev *tgt_dev, - struct ppa_addr *ppa_list, int nr_ppas) -{ - int i; - - for (i = 0; i < nr_ppas; i++) { - ppa_list[i] = dev_to_generic_addr(tgt_dev->parent, ppa_list[i]); - nvm_map_to_tgt(tgt_dev, &ppa_list[i]); - } -} - -static void nvm_rq_tgt_to_dev(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd) -{ - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - - nvm_ppa_tgt_to_dev(tgt_dev, ppa_list, rqd->nr_ppas); -} - -static void nvm_rq_dev_to_tgt(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd) -{ - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - - nvm_ppa_dev_to_tgt(tgt_dev, ppa_list, rqd->nr_ppas); -} - -int nvm_register_tgt_type(struct nvm_tgt_type *tt) -{ - int ret = 0; - - down_write(&nvm_tgtt_lock); - if (__nvm_find_target_type(tt->name)) - ret = -EEXIST; - else - list_add(&tt->list, &nvm_tgt_types); - up_write(&nvm_tgtt_lock); - - return ret; -} -EXPORT_SYMBOL(nvm_register_tgt_type); - -void nvm_unregister_tgt_type(struct nvm_tgt_type *tt) -{ - if (!tt) - return; - - down_write(&nvm_tgtt_lock); - list_del(&tt->list); - up_write(&nvm_tgtt_lock); -} -EXPORT_SYMBOL(nvm_unregister_tgt_type); - -void *nvm_dev_dma_alloc(struct nvm_dev *dev, gfp_t mem_flags, - dma_addr_t *dma_handler) -{ - return dev->ops->dev_dma_alloc(dev, dev->dma_pool, mem_flags, - dma_handler); -} -EXPORT_SYMBOL(nvm_dev_dma_alloc); - -void nvm_dev_dma_free(struct nvm_dev *dev, void *addr, dma_addr_t dma_handler) -{ - dev->ops->dev_dma_free(dev->dma_pool, addr, dma_handler); -} -EXPORT_SYMBOL(nvm_dev_dma_free); - -static struct nvm_dev *nvm_find_nvm_dev(const char *name) -{ - struct nvm_dev *dev; - - list_for_each_entry(dev, &nvm_devices, devices) - if (!strcmp(name, dev->name)) - return dev; - - return NULL; -} - -static int nvm_set_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd, - const struct ppa_addr *ppas, int nr_ppas) -{ - struct nvm_dev *dev = tgt_dev->parent; - struct nvm_geo *geo = &tgt_dev->geo; - int i, plane_cnt, pl_idx; - struct ppa_addr ppa; - - if (geo->pln_mode == NVM_PLANE_SINGLE && nr_ppas == 1) { - rqd->nr_ppas = nr_ppas; - rqd->ppa_addr = ppas[0]; - - return 0; - } - - rqd->nr_ppas = nr_ppas; - rqd->ppa_list = nvm_dev_dma_alloc(dev, GFP_KERNEL, &rqd->dma_ppa_list); - if (!rqd->ppa_list) { - pr_err("failed to allocate dma memory\n"); - return -ENOMEM; - } - - plane_cnt = geo->pln_mode; - rqd->nr_ppas *= plane_cnt; - - for (i = 0; i < nr_ppas; i++) { - for (pl_idx = 0; pl_idx < plane_cnt; pl_idx++) { - ppa = ppas[i]; - ppa.g.pl = pl_idx; - rqd->ppa_list[(pl_idx * nr_ppas) + i] = ppa; - } - } - - return 0; -} - -static void nvm_free_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, - struct nvm_rq *rqd) -{ - if (!rqd->ppa_list) - return; - - nvm_dev_dma_free(tgt_dev->parent, rqd->ppa_list, rqd->dma_ppa_list); -} - -static int nvm_set_flags(struct nvm_geo *geo, struct nvm_rq *rqd) -{ - int flags = 0; - - if (geo->version == NVM_OCSSD_SPEC_20) - return 0; - - if (rqd->is_seq) - flags |= geo->pln_mode >> 1; - - if (rqd->opcode == NVM_OP_PREAD) - flags |= (NVM_IO_SCRAMBLE_ENABLE | NVM_IO_SUSPEND); - else if (rqd->opcode == NVM_OP_PWRITE) - flags |= NVM_IO_SCRAMBLE_ENABLE; - - return flags; -} - -int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd, void *buf) -{ - struct nvm_dev *dev = tgt_dev->parent; - int ret; - - if (!dev->ops->submit_io) - return -ENODEV; - - nvm_rq_tgt_to_dev(tgt_dev, rqd); - - rqd->dev = tgt_dev; - rqd->flags = nvm_set_flags(&tgt_dev->geo, rqd); - - /* In case of error, fail with right address format */ - ret = dev->ops->submit_io(dev, rqd, buf); - if (ret) - nvm_rq_dev_to_tgt(tgt_dev, rqd); - return ret; -} -EXPORT_SYMBOL(nvm_submit_io); - -static void nvm_sync_end_io(struct nvm_rq *rqd) -{ - struct completion *waiting = rqd->private; - - complete(waiting); -} - -static int nvm_submit_io_wait(struct nvm_dev *dev, struct nvm_rq *rqd, - void *buf) -{ - DECLARE_COMPLETION_ONSTACK(wait); - int ret = 0; - - rqd->end_io = nvm_sync_end_io; - rqd->private = &wait; - - ret = dev->ops->submit_io(dev, rqd, buf); - if (ret) - return ret; - - wait_for_completion_io(&wait); - - return 0; -} - -int nvm_submit_io_sync(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd, - void *buf) -{ - struct nvm_dev *dev = tgt_dev->parent; - int ret; - - if (!dev->ops->submit_io) - return -ENODEV; - - nvm_rq_tgt_to_dev(tgt_dev, rqd); - - rqd->dev = tgt_dev; - rqd->flags = nvm_set_flags(&tgt_dev->geo, rqd); - - ret = nvm_submit_io_wait(dev, rqd, buf); - - return ret; -} -EXPORT_SYMBOL(nvm_submit_io_sync); - -void nvm_end_io(struct nvm_rq *rqd) -{ - struct nvm_tgt_dev *tgt_dev = rqd->dev; - - /* Convert address space */ - if (tgt_dev) - nvm_rq_dev_to_tgt(tgt_dev, rqd); - - if (rqd->end_io) - rqd->end_io(rqd); -} -EXPORT_SYMBOL(nvm_end_io); - -static int nvm_submit_io_sync_raw(struct nvm_dev *dev, struct nvm_rq *rqd) -{ - if (!dev->ops->submit_io) - return -ENODEV; - - rqd->dev = NULL; - rqd->flags = nvm_set_flags(&dev->geo, rqd); - - return nvm_submit_io_wait(dev, rqd, NULL); -} - -static int nvm_bb_chunk_sense(struct nvm_dev *dev, struct ppa_addr ppa) -{ - struct nvm_rq rqd = { NULL }; - struct bio bio; - struct bio_vec bio_vec; - struct page *page; - int ret; - - page = alloc_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - bio_init(&bio, &bio_vec, 1); - bio_add_page(&bio, page, PAGE_SIZE, 0); - bio_set_op_attrs(&bio, REQ_OP_READ, 0); - - rqd.bio = &bio; - rqd.opcode = NVM_OP_PREAD; - rqd.is_seq = 1; - rqd.nr_ppas = 1; - rqd.ppa_addr = generic_to_dev_addr(dev, ppa); - - ret = nvm_submit_io_sync_raw(dev, &rqd); - __free_page(page); - if (ret) - return ret; - - return rqd.error; -} - -/* - * Scans a 1.2 chunk first and last page to determine if its state. - * If the chunk is found to be open, also scan it to update the write - * pointer. - */ -static int nvm_bb_chunk_scan(struct nvm_dev *dev, struct ppa_addr ppa, - struct nvm_chk_meta *meta) -{ - struct nvm_geo *geo = &dev->geo; - int ret, pg, pl; - - /* sense first page */ - ret = nvm_bb_chunk_sense(dev, ppa); - if (ret < 0) /* io error */ - return ret; - else if (ret == 0) /* valid data */ - meta->state = NVM_CHK_ST_OPEN; - else if (ret > 0) { - /* - * If empty page, the chunk is free, else it is an - * actual io error. In that case, mark it offline. - */ - switch (ret) { - case NVM_RSP_ERR_EMPTYPAGE: - meta->state = NVM_CHK_ST_FREE; - return 0; - case NVM_RSP_ERR_FAILCRC: - case NVM_RSP_ERR_FAILECC: - case NVM_RSP_WARN_HIGHECC: - meta->state = NVM_CHK_ST_OPEN; - goto scan; - default: - return -ret; /* other io error */ - } - } - - /* sense last page */ - ppa.g.pg = geo->num_pg - 1; - ppa.g.pl = geo->num_pln - 1; - - ret = nvm_bb_chunk_sense(dev, ppa); - if (ret < 0) /* io error */ - return ret; - else if (ret == 0) { /* Chunk fully written */ - meta->state = NVM_CHK_ST_CLOSED; - meta->wp = geo->clba; - return 0; - } else if (ret > 0) { - switch (ret) { - case NVM_RSP_ERR_EMPTYPAGE: - case NVM_RSP_ERR_FAILCRC: - case NVM_RSP_ERR_FAILECC: - case NVM_RSP_WARN_HIGHECC: - meta->state = NVM_CHK_ST_OPEN; - break; - default: - return -ret; /* other io error */ - } - } - -scan: - /* - * chunk is open, we scan sequentially to update the write pointer. - * We make the assumption that targets write data across all planes - * before moving to the next page. - */ - for (pg = 0; pg < geo->num_pg; pg++) { - for (pl = 0; pl < geo->num_pln; pl++) { - ppa.g.pg = pg; - ppa.g.pl = pl; - - ret = nvm_bb_chunk_sense(dev, ppa); - if (ret < 0) /* io error */ - return ret; - else if (ret == 0) { - meta->wp += geo->ws_min; - } else if (ret > 0) { - switch (ret) { - case NVM_RSP_ERR_EMPTYPAGE: - return 0; - case NVM_RSP_ERR_FAILCRC: - case NVM_RSP_ERR_FAILECC: - case NVM_RSP_WARN_HIGHECC: - meta->wp += geo->ws_min; - break; - default: - return -ret; /* other io error */ - } - } - } - } - - return 0; -} - -/* - * folds a bad block list from its plane representation to its - * chunk representation. - * - * If any of the planes status are bad or grown bad, the chunk is marked - * offline. If not bad, the first plane state acts as the chunk state. - */ -static int nvm_bb_to_chunk(struct nvm_dev *dev, struct ppa_addr ppa, - u8 *blks, int nr_blks, struct nvm_chk_meta *meta) -{ - struct nvm_geo *geo = &dev->geo; - int ret, blk, pl, offset, blktype; - - for (blk = 0; blk < geo->num_chk; blk++) { - offset = blk * geo->pln_mode; - blktype = blks[offset]; - - for (pl = 0; pl < geo->pln_mode; pl++) { - if (blks[offset + pl] & - (NVM_BLK_T_BAD|NVM_BLK_T_GRWN_BAD)) { - blktype = blks[offset + pl]; - break; - } - } - - ppa.g.blk = blk; - - meta->wp = 0; - meta->type = NVM_CHK_TP_W_SEQ; - meta->wi = 0; - meta->slba = generic_to_dev_addr(dev, ppa).ppa; - meta->cnlb = dev->geo.clba; - - if (blktype == NVM_BLK_T_FREE) { - ret = nvm_bb_chunk_scan(dev, ppa, meta); - if (ret) - return ret; - } else { - meta->state = NVM_CHK_ST_OFFLINE; - } - - meta++; - } - - return 0; -} - -static int nvm_get_bb_meta(struct nvm_dev *dev, sector_t slba, - int nchks, struct nvm_chk_meta *meta) -{ - struct nvm_geo *geo = &dev->geo; - struct ppa_addr ppa; - u8 *blks; - int ch, lun, nr_blks; - int ret = 0; - - ppa.ppa = slba; - ppa = dev_to_generic_addr(dev, ppa); - - if (ppa.g.blk != 0) - return -EINVAL; - - if ((nchks % geo->num_chk) != 0) - return -EINVAL; - - nr_blks = geo->num_chk * geo->pln_mode; - - blks = kmalloc(nr_blks, GFP_KERNEL); - if (!blks) - return -ENOMEM; - - for (ch = ppa.g.ch; ch < geo->num_ch; ch++) { - for (lun = ppa.g.lun; lun < geo->num_lun; lun++) { - struct ppa_addr ppa_gen, ppa_dev; - - if (!nchks) - goto done; - - ppa_gen.ppa = 0; - ppa_gen.g.ch = ch; - ppa_gen.g.lun = lun; - ppa_dev = generic_to_dev_addr(dev, ppa_gen); - - ret = dev->ops->get_bb_tbl(dev, ppa_dev, blks); - if (ret) - goto done; - - ret = nvm_bb_to_chunk(dev, ppa_gen, blks, nr_blks, - meta); - if (ret) - goto done; - - meta += geo->num_chk; - nchks -= geo->num_chk; - } - } -done: - kfree(blks); - return ret; -} - -int nvm_get_chunk_meta(struct nvm_tgt_dev *tgt_dev, struct ppa_addr ppa, - int nchks, struct nvm_chk_meta *meta) -{ - struct nvm_dev *dev = tgt_dev->parent; - - nvm_ppa_tgt_to_dev(tgt_dev, &ppa, 1); - - if (dev->geo.version == NVM_OCSSD_SPEC_12) - return nvm_get_bb_meta(dev, (sector_t)ppa.ppa, nchks, meta); - - return dev->ops->get_chk_meta(dev, (sector_t)ppa.ppa, nchks, meta); -} -EXPORT_SYMBOL_GPL(nvm_get_chunk_meta); - -int nvm_set_chunk_meta(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas, - int nr_ppas, int type) -{ - struct nvm_dev *dev = tgt_dev->parent; - struct nvm_rq rqd; - int ret; - - if (dev->geo.version == NVM_OCSSD_SPEC_20) - return 0; - - if (nr_ppas > NVM_MAX_VLBA) { - pr_err("unable to update all blocks atomically\n"); - return -EINVAL; - } - - memset(&rqd, 0, sizeof(struct nvm_rq)); - - nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas); - nvm_rq_tgt_to_dev(tgt_dev, &rqd); - - ret = dev->ops->set_bb_tbl(dev, &rqd.ppa_addr, rqd.nr_ppas, type); - nvm_free_rqd_ppalist(tgt_dev, &rqd); - if (ret) - return -EINVAL; - - return 0; -} -EXPORT_SYMBOL_GPL(nvm_set_chunk_meta); - -static int nvm_core_init(struct nvm_dev *dev) -{ - struct nvm_geo *geo = &dev->geo; - int ret; - - dev->lun_map = kcalloc(BITS_TO_LONGS(geo->all_luns), - sizeof(unsigned long), GFP_KERNEL); - if (!dev->lun_map) - return -ENOMEM; - - INIT_LIST_HEAD(&dev->area_list); - INIT_LIST_HEAD(&dev->targets); - mutex_init(&dev->mlock); - spin_lock_init(&dev->lock); - - ret = nvm_register_map(dev); - if (ret) - goto err_fmtype; - - return 0; -err_fmtype: - kfree(dev->lun_map); - return ret; -} - -static void nvm_free(struct kref *ref) -{ - struct nvm_dev *dev = container_of(ref, struct nvm_dev, ref); - - if (dev->dma_pool) - dev->ops->destroy_dma_pool(dev->dma_pool); - - if (dev->rmap) - nvm_unregister_map(dev); - - kfree(dev->lun_map); - kfree(dev); -} - -static int nvm_init(struct nvm_dev *dev) -{ - struct nvm_geo *geo = &dev->geo; - int ret = -EINVAL; - - if (dev->ops->identity(dev)) { - pr_err("device could not be identified\n"); - goto err; - } - - pr_debug("ver:%u.%u nvm_vendor:%x\n", geo->major_ver_id, - geo->minor_ver_id, geo->vmnt); - - ret = nvm_core_init(dev); - if (ret) { - pr_err("could not initialize core structures.\n"); - goto err; - } - - pr_info("registered %s [%u/%u/%u/%u/%u]\n", - dev->name, dev->geo.ws_min, dev->geo.ws_opt, - dev->geo.num_chk, dev->geo.all_luns, - dev->geo.num_ch); - return 0; -err: - pr_err("failed to initialize nvm\n"); - return ret; -} - -struct nvm_dev *nvm_alloc_dev(int node) -{ - struct nvm_dev *dev; - - dev = kzalloc_node(sizeof(struct nvm_dev), GFP_KERNEL, node); - if (dev) - kref_init(&dev->ref); - - return dev; -} -EXPORT_SYMBOL(nvm_alloc_dev); - -int nvm_register(struct nvm_dev *dev) -{ - int ret, exp_pool_size; - - pr_warn_once("lightnvm support is deprecated and will be removed in Linux 5.15.\n"); - - if (!dev->q || !dev->ops) { - kref_put(&dev->ref, nvm_free); - return -EINVAL; - } - - ret = nvm_init(dev); - if (ret) { - kref_put(&dev->ref, nvm_free); - return ret; - } - - exp_pool_size = max_t(int, PAGE_SIZE, - (NVM_MAX_VLBA * (sizeof(u64) + dev->geo.sos))); - exp_pool_size = round_up(exp_pool_size, PAGE_SIZE); - - dev->dma_pool = dev->ops->create_dma_pool(dev, "ppalist", - exp_pool_size); - if (!dev->dma_pool) { - pr_err("could not create dma pool\n"); - kref_put(&dev->ref, nvm_free); - return -ENOMEM; - } - - /* register device with a supported media manager */ - down_write(&nvm_lock); - list_add(&dev->devices, &nvm_devices); - up_write(&nvm_lock); - - return 0; -} -EXPORT_SYMBOL(nvm_register); - -void nvm_unregister(struct nvm_dev *dev) -{ - struct nvm_target *t, *tmp; - - mutex_lock(&dev->mlock); - list_for_each_entry_safe(t, tmp, &dev->targets, list) { - if (t->dev->parent != dev) - continue; - __nvm_remove_target(t, false); - kref_put(&dev->ref, nvm_free); - } - mutex_unlock(&dev->mlock); - - down_write(&nvm_lock); - list_del(&dev->devices); - up_write(&nvm_lock); - - kref_put(&dev->ref, nvm_free); -} -EXPORT_SYMBOL(nvm_unregister); - -static int __nvm_configure_create(struct nvm_ioctl_create *create) -{ - struct nvm_dev *dev; - int ret; - - down_write(&nvm_lock); - dev = nvm_find_nvm_dev(create->dev); - up_write(&nvm_lock); - - if (!dev) { - pr_err("device not found\n"); - return -EINVAL; - } - - kref_get(&dev->ref); - ret = nvm_create_tgt(dev, create); - if (ret) - kref_put(&dev->ref, nvm_free); - - return ret; -} - -static long nvm_ioctl_info(struct file *file, void __user *arg) -{ - struct nvm_ioctl_info *info; - struct nvm_tgt_type *tt; - int tgt_iter = 0; - - info = memdup_user(arg, sizeof(struct nvm_ioctl_info)); - if (IS_ERR(info)) - return PTR_ERR(info); - - info->version[0] = NVM_VERSION_MAJOR; - info->version[1] = NVM_VERSION_MINOR; - info->version[2] = NVM_VERSION_PATCH; - - down_write(&nvm_tgtt_lock); - list_for_each_entry(tt, &nvm_tgt_types, list) { - struct nvm_ioctl_info_tgt *tgt = &info->tgts[tgt_iter]; - - tgt->version[0] = tt->version[0]; - tgt->version[1] = tt->version[1]; - tgt->version[2] = tt->version[2]; - strncpy(tgt->tgtname, tt->name, NVM_TTYPE_NAME_MAX); - - tgt_iter++; - } - - info->tgtsize = tgt_iter; - up_write(&nvm_tgtt_lock); - - if (copy_to_user(arg, info, sizeof(struct nvm_ioctl_info))) { - kfree(info); - return -EFAULT; - } - - kfree(info); - return 0; -} - -static long nvm_ioctl_get_devices(struct file *file, void __user *arg) -{ - struct nvm_ioctl_get_devices *devices; - struct nvm_dev *dev; - int i = 0; - - devices = kzalloc(sizeof(struct nvm_ioctl_get_devices), GFP_KERNEL); - if (!devices) - return -ENOMEM; - - down_write(&nvm_lock); - list_for_each_entry(dev, &nvm_devices, devices) { - struct nvm_ioctl_device_info *info = &devices->info[i]; - - strlcpy(info->devname, dev->name, sizeof(info->devname)); - - /* kept for compatibility */ - info->bmversion[0] = 1; - info->bmversion[1] = 0; - info->bmversion[2] = 0; - strlcpy(info->bmname, "gennvm", sizeof(info->bmname)); - i++; - - if (i >= ARRAY_SIZE(devices->info)) { - pr_err("max %zd devices can be reported.\n", - ARRAY_SIZE(devices->info)); - break; - } - } - up_write(&nvm_lock); - - devices->nr_devices = i; - - if (copy_to_user(arg, devices, - sizeof(struct nvm_ioctl_get_devices))) { - kfree(devices); - return -EFAULT; - } - - kfree(devices); - return 0; -} - -static long nvm_ioctl_dev_create(struct file *file, void __user *arg) -{ - struct nvm_ioctl_create create; - - if (copy_from_user(&create, arg, sizeof(struct nvm_ioctl_create))) - return -EFAULT; - - if (create.conf.type == NVM_CONFIG_TYPE_EXTENDED && - create.conf.e.rsv != 0) { - pr_err("reserved config field in use\n"); - return -EINVAL; - } - - create.dev[DISK_NAME_LEN - 1] = '\0'; - create.tgttype[NVM_TTYPE_NAME_MAX - 1] = '\0'; - create.tgtname[DISK_NAME_LEN - 1] = '\0'; - - if (create.flags != 0) { - __u32 flags = create.flags; - - /* Check for valid flags */ - if (flags & NVM_TARGET_FACTORY) - flags &= ~NVM_TARGET_FACTORY; - - if (flags) { - pr_err("flag not supported\n"); - return -EINVAL; - } - } - - return __nvm_configure_create(&create); -} - -static long nvm_ioctl_dev_remove(struct file *file, void __user *arg) -{ - struct nvm_ioctl_remove remove; - - if (copy_from_user(&remove, arg, sizeof(struct nvm_ioctl_remove))) - return -EFAULT; - - remove.tgtname[DISK_NAME_LEN - 1] = '\0'; - - if (remove.flags != 0) { - pr_err("no flags supported\n"); - return -EINVAL; - } - - return nvm_remove_tgt(&remove); -} - -/* kept for compatibility reasons */ -static long nvm_ioctl_dev_init(struct file *file, void __user *arg) -{ - struct nvm_ioctl_dev_init init; - - if (copy_from_user(&init, arg, sizeof(struct nvm_ioctl_dev_init))) - return -EFAULT; - - if (init.flags != 0) { - pr_err("no flags supported\n"); - return -EINVAL; - } - - return 0; -} - -/* Kept for compatibility reasons */ -static long nvm_ioctl_dev_factory(struct file *file, void __user *arg) -{ - struct nvm_ioctl_dev_factory fact; - - if (copy_from_user(&fact, arg, sizeof(struct nvm_ioctl_dev_factory))) - return -EFAULT; - - fact.dev[DISK_NAME_LEN - 1] = '\0'; - - if (fact.flags & ~(NVM_FACTORY_NR_BITS - 1)) - return -EINVAL; - - return 0; -} - -static long nvm_ctl_ioctl(struct file *file, uint cmd, unsigned long arg) -{ - void __user *argp = (void __user *)arg; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - switch (cmd) { - case NVM_INFO: - return nvm_ioctl_info(file, argp); - case NVM_GET_DEVICES: - return nvm_ioctl_get_devices(file, argp); - case NVM_DEV_CREATE: - return nvm_ioctl_dev_create(file, argp); - case NVM_DEV_REMOVE: - return nvm_ioctl_dev_remove(file, argp); - case NVM_DEV_INIT: - return nvm_ioctl_dev_init(file, argp); - case NVM_DEV_FACTORY: - return nvm_ioctl_dev_factory(file, argp); - } - return 0; -} - -static const struct file_operations _ctl_fops = { - .open = nonseekable_open, - .unlocked_ioctl = nvm_ctl_ioctl, - .owner = THIS_MODULE, - .llseek = noop_llseek, -}; - -static struct miscdevice _nvm_misc = { - .minor = MISC_DYNAMIC_MINOR, - .name = "lightnvm", - .nodename = "lightnvm/control", - .fops = &_ctl_fops, -}; -builtin_misc_device(_nvm_misc); diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c deleted file mode 100644 index f185f1a00008..000000000000 --- a/drivers/lightnvm/pblk-cache.c +++ /dev/null @@ -1,137 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2016 CNEX Labs - * Initial release: Javier Gonzalez - * Matias Bjorling - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * pblk-cache.c - pblk's write cache - */ - -#include "pblk.h" - -void pblk_write_to_cache(struct pblk *pblk, struct bio *bio, - unsigned long flags) -{ - struct pblk_w_ctx w_ctx; - sector_t lba = pblk_get_lba(bio); - unsigned long start_time; - unsigned int bpos, pos; - int nr_entries = pblk_get_secs(bio); - int i, ret; - - start_time = bio_start_io_acct(bio); - - /* Update the write buffer head (mem) with the entries that we can - * write. The write in itself cannot fail, so there is no need to - * rollback from here on. - */ -retry: - ret = pblk_rb_may_write_user(&pblk->rwb, bio, nr_entries, &bpos); - switch (ret) { - case NVM_IO_REQUEUE: - io_schedule(); - goto retry; - case NVM_IO_ERR: - pblk_pipeline_stop(pblk); - bio_io_error(bio); - goto out; - } - - pblk_ppa_set_empty(&w_ctx.ppa); - w_ctx.flags = flags; - if (bio->bi_opf & REQ_PREFLUSH) { - w_ctx.flags |= PBLK_FLUSH_ENTRY; - pblk_write_kick(pblk); - } - - if (unlikely(!bio_has_data(bio))) - goto out; - - for (i = 0; i < nr_entries; i++) { - void *data = bio_data(bio); - - w_ctx.lba = lba + i; - - pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + i); - pblk_rb_write_entry_user(&pblk->rwb, data, w_ctx, pos); - - bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE); - } - - atomic64_add(nr_entries, &pblk->user_wa); - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_add(nr_entries, &pblk->inflight_writes); - atomic_long_add(nr_entries, &pblk->req_writes); -#endif - - pblk_rl_inserted(&pblk->rl, nr_entries); - -out: - bio_end_io_acct(bio, start_time); - pblk_write_should_kick(pblk); - - if (ret == NVM_IO_DONE) - bio_endio(bio); -} - -/* - * On GC the incoming lbas are not necessarily sequential. Also, some of the - * lbas might not be valid entries, which are marked as empty by the GC thread - */ -int pblk_write_gc_to_cache(struct pblk *pblk, struct pblk_gc_rq *gc_rq) -{ - struct pblk_w_ctx w_ctx; - unsigned int bpos, pos; - void *data = gc_rq->data; - int i, valid_entries; - - /* Update the write buffer head (mem) with the entries that we can - * write. The write in itself cannot fail, so there is no need to - * rollback from here on. - */ -retry: - if (!pblk_rb_may_write_gc(&pblk->rwb, gc_rq->secs_to_gc, &bpos)) { - io_schedule(); - goto retry; - } - - w_ctx.flags = PBLK_IOTYPE_GC; - pblk_ppa_set_empty(&w_ctx.ppa); - - for (i = 0, valid_entries = 0; i < gc_rq->nr_secs; i++) { - if (gc_rq->lba_list[i] == ADDR_EMPTY) - continue; - - w_ctx.lba = gc_rq->lba_list[i]; - - pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + valid_entries); - pblk_rb_write_entry_gc(&pblk->rwb, data, w_ctx, gc_rq->line, - gc_rq->paddr_list[i], pos); - - data += PBLK_EXPOSED_PAGE_SIZE; - valid_entries++; - } - - WARN_ONCE(gc_rq->secs_to_gc != valid_entries, - "pblk: inconsistent GC write\n"); - - atomic64_add(valid_entries, &pblk->gc_wa); - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_add(valid_entries, &pblk->inflight_writes); - atomic_long_add(valid_entries, &pblk->recov_gc_writes); -#endif - - pblk_write_should_kick(pblk); - return NVM_IO_OK; -} diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c deleted file mode 100644 index 33d39d3dd343..000000000000 --- a/drivers/lightnvm/pblk-core.c +++ /dev/null @@ -1,2151 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2016 CNEX Labs - * Initial release: Javier Gonzalez - * Matias Bjorling - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * pblk-core.c - pblk's core functionality - * - */ - -#define CREATE_TRACE_POINTS - -#include "pblk.h" -#include "pblk-trace.h" - -static void pblk_line_mark_bb(struct work_struct *work) -{ - struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws, - ws); - struct pblk *pblk = line_ws->pblk; - struct nvm_tgt_dev *dev = pblk->dev; - struct ppa_addr *ppa = line_ws->priv; - int ret; - - ret = nvm_set_chunk_meta(dev, ppa, 1, NVM_BLK_T_GRWN_BAD); - if (ret) { - struct pblk_line *line; - int pos; - - line = pblk_ppa_to_line(pblk, *ppa); - pos = pblk_ppa_to_pos(&dev->geo, *ppa); - - pblk_err(pblk, "failed to mark bb, line:%d, pos:%d\n", - line->id, pos); - } - - kfree(ppa); - mempool_free(line_ws, &pblk->gen_ws_pool); -} - -static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line, - struct ppa_addr ppa_addr) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct ppa_addr *ppa; - int pos = pblk_ppa_to_pos(geo, ppa_addr); - - pblk_debug(pblk, "erase failed: line:%d, pos:%d\n", line->id, pos); - atomic_long_inc(&pblk->erase_failed); - - atomic_dec(&line->blk_in_line); - if (test_and_set_bit(pos, line->blk_bitmap)) - pblk_err(pblk, "attempted to erase bb: line:%d, pos:%d\n", - line->id, pos); - - /* Not necessary to mark bad blocks on 2.0 spec. */ - if (geo->version == NVM_OCSSD_SPEC_20) - return; - - ppa = kmalloc(sizeof(struct ppa_addr), GFP_ATOMIC); - if (!ppa) - return; - - *ppa = ppa_addr; - pblk_gen_run_ws(pblk, NULL, ppa, pblk_line_mark_bb, - GFP_ATOMIC, pblk->bb_wq); -} - -static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct nvm_chk_meta *chunk; - struct pblk_line *line; - int pos; - - line = pblk_ppa_to_line(pblk, rqd->ppa_addr); - pos = pblk_ppa_to_pos(geo, rqd->ppa_addr); - chunk = &line->chks[pos]; - - atomic_dec(&line->left_seblks); - - if (rqd->error) { - trace_pblk_chunk_reset(pblk_disk_name(pblk), - &rqd->ppa_addr, PBLK_CHUNK_RESET_FAILED); - - chunk->state = NVM_CHK_ST_OFFLINE; - pblk_mark_bb(pblk, line, rqd->ppa_addr); - } else { - trace_pblk_chunk_reset(pblk_disk_name(pblk), - &rqd->ppa_addr, PBLK_CHUNK_RESET_DONE); - - chunk->state = NVM_CHK_ST_FREE; - } - - trace_pblk_chunk_state(pblk_disk_name(pblk), &rqd->ppa_addr, - chunk->state); - - atomic_dec(&pblk->inflight_io); -} - -/* Erase completion assumes that only one block is erased at the time */ -static void pblk_end_io_erase(struct nvm_rq *rqd) -{ - struct pblk *pblk = rqd->private; - - __pblk_end_io_erase(pblk, rqd); - mempool_free(rqd, &pblk->e_rq_pool); -} - -/* - * Get information for all chunks from the device. - * - * The caller is responsible for freeing (vmalloc) the returned structure - */ -struct nvm_chk_meta *pblk_get_chunk_meta(struct pblk *pblk) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct nvm_chk_meta *meta; - struct ppa_addr ppa; - unsigned long len; - int ret; - - ppa.ppa = 0; - - len = geo->all_chunks * sizeof(*meta); - meta = vzalloc(len); - if (!meta) - return ERR_PTR(-ENOMEM); - - ret = nvm_get_chunk_meta(dev, ppa, geo->all_chunks, meta); - if (ret) { - vfree(meta); - return ERR_PTR(-EIO); - } - - return meta; -} - -struct nvm_chk_meta *pblk_chunk_get_off(struct pblk *pblk, - struct nvm_chk_meta *meta, - struct ppa_addr ppa) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - int ch_off = ppa.m.grp * geo->num_chk * geo->num_lun; - int lun_off = ppa.m.pu * geo->num_chk; - int chk_off = ppa.m.chk; - - return meta + ch_off + lun_off + chk_off; -} - -void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line, - u64 paddr) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct list_head *move_list = NULL; - - /* Lines being reclaimed (GC'ed) cannot be invalidated. Before the L2P - * table is modified with reclaimed sectors, a check is done to endure - * that newer updates are not overwritten. - */ - spin_lock(&line->lock); - WARN_ON(line->state == PBLK_LINESTATE_FREE); - - if (test_and_set_bit(paddr, line->invalid_bitmap)) { - WARN_ONCE(1, "pblk: double invalidate\n"); - spin_unlock(&line->lock); - return; - } - le32_add_cpu(line->vsc, -1); - - if (line->state == PBLK_LINESTATE_CLOSED) - move_list = pblk_line_gc_list(pblk, line); - spin_unlock(&line->lock); - - if (move_list) { - spin_lock(&l_mg->gc_lock); - spin_lock(&line->lock); - /* Prevent moving a line that has just been chosen for GC */ - if (line->state == PBLK_LINESTATE_GC) { - spin_unlock(&line->lock); - spin_unlock(&l_mg->gc_lock); - return; - } - spin_unlock(&line->lock); - - list_move_tail(&line->list, move_list); - spin_unlock(&l_mg->gc_lock); - } -} - -void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa) -{ - struct pblk_line *line; - u64 paddr; - -#ifdef CONFIG_NVM_PBLK_DEBUG - /* Callers must ensure that the ppa points to a device address */ - BUG_ON(pblk_addr_in_cache(ppa)); - BUG_ON(pblk_ppa_empty(ppa)); -#endif - - line = pblk_ppa_to_line(pblk, ppa); - paddr = pblk_dev_ppa_to_line_addr(pblk, ppa); - - __pblk_map_invalidate(pblk, line, paddr); -} - -static void pblk_invalidate_range(struct pblk *pblk, sector_t slba, - unsigned int nr_secs) -{ - sector_t lba; - - spin_lock(&pblk->trans_lock); - for (lba = slba; lba < slba + nr_secs; lba++) { - struct ppa_addr ppa; - - ppa = pblk_trans_map_get(pblk, lba); - - if (!pblk_addr_in_cache(ppa) && !pblk_ppa_empty(ppa)) - pblk_map_invalidate(pblk, ppa); - - pblk_ppa_set_empty(&ppa); - pblk_trans_map_set(pblk, lba, ppa); - } - spin_unlock(&pblk->trans_lock); -} - -int pblk_alloc_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd) -{ - struct nvm_tgt_dev *dev = pblk->dev; - - rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, - &rqd->dma_meta_list); - if (!rqd->meta_list) - return -ENOMEM; - - if (rqd->nr_ppas == 1) - return 0; - - rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size(pblk); - rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size(pblk); - - return 0; -} - -void pblk_free_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd) -{ - struct nvm_tgt_dev *dev = pblk->dev; - - if (rqd->meta_list) - nvm_dev_dma_free(dev->parent, rqd->meta_list, - rqd->dma_meta_list); -} - -/* Caller must guarantee that the request is a valid type */ -struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type) -{ - mempool_t *pool; - struct nvm_rq *rqd; - int rq_size; - - switch (type) { - case PBLK_WRITE: - case PBLK_WRITE_INT: - pool = &pblk->w_rq_pool; - rq_size = pblk_w_rq_size; - break; - case PBLK_READ: - pool = &pblk->r_rq_pool; - rq_size = pblk_g_rq_size; - break; - default: - pool = &pblk->e_rq_pool; - rq_size = pblk_g_rq_size; - } - - rqd = mempool_alloc(pool, GFP_KERNEL); - memset(rqd, 0, rq_size); - - return rqd; -} - -/* Typically used on completion path. Cannot guarantee request consistency */ -void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type) -{ - mempool_t *pool; - - switch (type) { - case PBLK_WRITE: - kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap); - fallthrough; - case PBLK_WRITE_INT: - pool = &pblk->w_rq_pool; - break; - case PBLK_READ: - pool = &pblk->r_rq_pool; - break; - case PBLK_ERASE: - pool = &pblk->e_rq_pool; - break; - default: - pblk_err(pblk, "trying to free unknown rqd type\n"); - return; - } - - pblk_free_rqd_meta(pblk, rqd); - mempool_free(rqd, pool); -} - -void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off, - int nr_pages) -{ - struct bio_vec *bv; - struct page *page; - int i, e, nbv = 0; - - for (i = 0; i < bio->bi_vcnt; i++) { - bv = &bio->bi_io_vec[i]; - page = bv->bv_page; - for (e = 0; e < bv->bv_len; e += PBLK_EXPOSED_PAGE_SIZE, nbv++) - if (nbv >= off) - mempool_free(page++, &pblk->page_bio_pool); - } -} - -int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags, - int nr_pages) -{ - struct request_queue *q = pblk->dev->q; - struct page *page; - int i, ret; - - for (i = 0; i < nr_pages; i++) { - page = mempool_alloc(&pblk->page_bio_pool, flags); - - ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0); - if (ret != PBLK_EXPOSED_PAGE_SIZE) { - pblk_err(pblk, "could not add page to bio\n"); - mempool_free(page, &pblk->page_bio_pool); - goto err; - } - } - - return 0; -err: - pblk_bio_free_pages(pblk, bio, (bio->bi_vcnt - i), i); - return -1; -} - -void pblk_write_kick(struct pblk *pblk) -{ - wake_up_process(pblk->writer_ts); - mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(1000)); -} - -void pblk_write_timer_fn(struct timer_list *t) -{ - struct pblk *pblk = from_timer(pblk, t, wtimer); - - /* kick the write thread every tick to flush outstanding data */ - pblk_write_kick(pblk); -} - -void pblk_write_should_kick(struct pblk *pblk) -{ - unsigned int secs_avail = pblk_rb_read_count(&pblk->rwb); - - if (secs_avail >= pblk->min_write_pgs_data) - pblk_write_kick(pblk); -} - -static void pblk_wait_for_meta(struct pblk *pblk) -{ - do { - if (!atomic_read(&pblk->inflight_io)) - break; - - schedule(); - } while (1); -} - -static void pblk_flush_writer(struct pblk *pblk) -{ - pblk_rb_flush(&pblk->rwb); - do { - if (!pblk_rb_sync_count(&pblk->rwb)) - break; - - pblk_write_kick(pblk); - schedule(); - } while (1); -} - -struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct list_head *move_list = NULL; - int packed_meta = (le32_to_cpu(*line->vsc) / pblk->min_write_pgs_data) - * (pblk->min_write_pgs - pblk->min_write_pgs_data); - int vsc = le32_to_cpu(*line->vsc) + packed_meta; - - lockdep_assert_held(&line->lock); - - if (line->w_err_gc->has_write_err) { - if (line->gc_group != PBLK_LINEGC_WERR) { - line->gc_group = PBLK_LINEGC_WERR; - move_list = &l_mg->gc_werr_list; - pblk_rl_werr_line_in(&pblk->rl); - } - } else if (!vsc) { - if (line->gc_group != PBLK_LINEGC_FULL) { - line->gc_group = PBLK_LINEGC_FULL; - move_list = &l_mg->gc_full_list; - } - } else if (vsc < lm->high_thrs) { - if (line->gc_group != PBLK_LINEGC_HIGH) { - line->gc_group = PBLK_LINEGC_HIGH; - move_list = &l_mg->gc_high_list; - } - } else if (vsc < lm->mid_thrs) { - if (line->gc_group != PBLK_LINEGC_MID) { - line->gc_group = PBLK_LINEGC_MID; - move_list = &l_mg->gc_mid_list; - } - } else if (vsc < line->sec_in_line) { - if (line->gc_group != PBLK_LINEGC_LOW) { - line->gc_group = PBLK_LINEGC_LOW; - move_list = &l_mg->gc_low_list; - } - } else if (vsc == line->sec_in_line) { - if (line->gc_group != PBLK_LINEGC_EMPTY) { - line->gc_group = PBLK_LINEGC_EMPTY; - move_list = &l_mg->gc_empty_list; - } - } else { - line->state = PBLK_LINESTATE_CORRUPT; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - - line->gc_group = PBLK_LINEGC_NONE; - move_list = &l_mg->corrupt_list; - pblk_err(pblk, "corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n", - line->id, vsc, - line->sec_in_line, - lm->high_thrs, lm->mid_thrs); - } - - return move_list; -} - -void pblk_discard(struct pblk *pblk, struct bio *bio) -{ - sector_t slba = pblk_get_lba(bio); - sector_t nr_secs = pblk_get_secs(bio); - - pblk_invalidate_range(pblk, slba, nr_secs); -} - -void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd) -{ - atomic_long_inc(&pblk->write_failed); -#ifdef CONFIG_NVM_PBLK_DEBUG - pblk_print_failed_rqd(pblk, rqd, rqd->error); -#endif -} - -void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd) -{ - /* Empty page read is not necessarily an error (e.g., L2P recovery) */ - if (rqd->error == NVM_RSP_ERR_EMPTYPAGE) { - atomic_long_inc(&pblk->read_empty); - return; - } - - switch (rqd->error) { - case NVM_RSP_WARN_HIGHECC: - atomic_long_inc(&pblk->read_high_ecc); - break; - case NVM_RSP_ERR_FAILECC: - case NVM_RSP_ERR_FAILCRC: - atomic_long_inc(&pblk->read_failed); - break; - default: - pblk_err(pblk, "unknown read error:%d\n", rqd->error); - } -#ifdef CONFIG_NVM_PBLK_DEBUG - pblk_print_failed_rqd(pblk, rqd, rqd->error); -#endif -} - -void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write) -{ - pblk->sec_per_write = sec_per_write; -} - -int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd, void *buf) -{ - struct nvm_tgt_dev *dev = pblk->dev; - - atomic_inc(&pblk->inflight_io); - -#ifdef CONFIG_NVM_PBLK_DEBUG - if (pblk_check_io(pblk, rqd)) - return NVM_IO_ERR; -#endif - - return nvm_submit_io(dev, rqd, buf); -} - -void pblk_check_chunk_state_update(struct pblk *pblk, struct nvm_rq *rqd) -{ - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - - int i; - - for (i = 0; i < rqd->nr_ppas; i++) { - struct ppa_addr *ppa = &ppa_list[i]; - struct nvm_chk_meta *chunk = pblk_dev_ppa_to_chunk(pblk, *ppa); - u64 caddr = pblk_dev_ppa_to_chunk_addr(pblk, *ppa); - - if (caddr == 0) - trace_pblk_chunk_state(pblk_disk_name(pblk), - ppa, NVM_CHK_ST_OPEN); - else if (caddr == (chunk->cnlb - 1)) - trace_pblk_chunk_state(pblk_disk_name(pblk), - ppa, NVM_CHK_ST_CLOSED); - } -} - -int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd, void *buf) -{ - struct nvm_tgt_dev *dev = pblk->dev; - int ret; - - atomic_inc(&pblk->inflight_io); - -#ifdef CONFIG_NVM_PBLK_DEBUG - if (pblk_check_io(pblk, rqd)) - return NVM_IO_ERR; -#endif - - ret = nvm_submit_io_sync(dev, rqd, buf); - - if (trace_pblk_chunk_state_enabled() && !ret && - rqd->opcode == NVM_OP_PWRITE) - pblk_check_chunk_state_update(pblk, rqd); - - return ret; -} - -static int pblk_submit_io_sync_sem(struct pblk *pblk, struct nvm_rq *rqd, - void *buf) -{ - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - int ret; - - pblk_down_chunk(pblk, ppa_list[0]); - ret = pblk_submit_io_sync(pblk, rqd, buf); - pblk_up_chunk(pblk, ppa_list[0]); - - return ret; -} - -int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail, - unsigned long secs_to_flush, bool skip_meta) -{ - int max = pblk->sec_per_write; - int min = pblk->min_write_pgs; - int secs_to_sync = 0; - - if (skip_meta && pblk->min_write_pgs_data != pblk->min_write_pgs) - min = max = pblk->min_write_pgs_data; - - if (secs_avail >= max) - secs_to_sync = max; - else if (secs_avail >= min) - secs_to_sync = min * (secs_avail / min); - else if (secs_to_flush) - secs_to_sync = min; - - return secs_to_sync; -} - -void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs) -{ - u64 addr; - int i; - - spin_lock(&line->lock); - addr = find_next_zero_bit(line->map_bitmap, - pblk->lm.sec_per_line, line->cur_sec); - line->cur_sec = addr - nr_secs; - - for (i = 0; i < nr_secs; i++, line->cur_sec--) - WARN_ON(!test_and_clear_bit(line->cur_sec, line->map_bitmap)); - spin_unlock(&line->lock); -} - -u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs) -{ - u64 addr; - int i; - - lockdep_assert_held(&line->lock); - - /* logic error: ppa out-of-bounds. Prevent generating bad address */ - if (line->cur_sec + nr_secs > pblk->lm.sec_per_line) { - WARN(1, "pblk: page allocation out of bounds\n"); - nr_secs = pblk->lm.sec_per_line - line->cur_sec; - } - - line->cur_sec = addr = find_next_zero_bit(line->map_bitmap, - pblk->lm.sec_per_line, line->cur_sec); - for (i = 0; i < nr_secs; i++, line->cur_sec++) - WARN_ON(test_and_set_bit(line->cur_sec, line->map_bitmap)); - - return addr; -} - -u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs) -{ - u64 addr; - - /* Lock needed in case a write fails and a recovery needs to remap - * failed write buffer entries - */ - spin_lock(&line->lock); - addr = __pblk_alloc_page(pblk, line, nr_secs); - line->left_msecs -= nr_secs; - WARN(line->left_msecs < 0, "pblk: page allocation out of bounds\n"); - spin_unlock(&line->lock); - - return addr; -} - -u64 pblk_lookup_page(struct pblk *pblk, struct pblk_line *line) -{ - u64 paddr; - - spin_lock(&line->lock); - paddr = find_next_zero_bit(line->map_bitmap, - pblk->lm.sec_per_line, line->cur_sec); - spin_unlock(&line->lock); - - return paddr; -} - -u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - int bit; - - /* This usually only happens on bad lines */ - bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line); - if (bit >= lm->blk_per_line) - return -1; - - return bit * geo->ws_opt; -} - -int pblk_line_smeta_read(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct ppa_addr *ppa_list; - struct nvm_rq rqd; - u64 paddr = pblk_line_smeta_start(pblk, line); - int i, ret; - - memset(&rqd, 0, sizeof(struct nvm_rq)); - - ret = pblk_alloc_rqd_meta(pblk, &rqd); - if (ret) - return ret; - - rqd.opcode = NVM_OP_PREAD; - rqd.nr_ppas = lm->smeta_sec; - rqd.is_seq = 1; - ppa_list = nvm_rq_to_ppa_list(&rqd); - - for (i = 0; i < lm->smeta_sec; i++, paddr++) - ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id); - - ret = pblk_submit_io_sync(pblk, &rqd, line->smeta); - if (ret) { - pblk_err(pblk, "smeta I/O submission failed: %d\n", ret); - goto clear_rqd; - } - - atomic_dec(&pblk->inflight_io); - - if (rqd.error && rqd.error != NVM_RSP_WARN_HIGHECC) { - pblk_log_read_err(pblk, &rqd); - ret = -EIO; - } - -clear_rqd: - pblk_free_rqd_meta(pblk, &rqd); - return ret; -} - -static int pblk_line_smeta_write(struct pblk *pblk, struct pblk_line *line, - u64 paddr) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct ppa_addr *ppa_list; - struct nvm_rq rqd; - __le64 *lba_list = emeta_to_lbas(pblk, line->emeta->buf); - __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); - int i, ret; - - memset(&rqd, 0, sizeof(struct nvm_rq)); - - ret = pblk_alloc_rqd_meta(pblk, &rqd); - if (ret) - return ret; - - rqd.opcode = NVM_OP_PWRITE; - rqd.nr_ppas = lm->smeta_sec; - rqd.is_seq = 1; - ppa_list = nvm_rq_to_ppa_list(&rqd); - - for (i = 0; i < lm->smeta_sec; i++, paddr++) { - struct pblk_sec_meta *meta = pblk_get_meta(pblk, - rqd.meta_list, i); - - ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id); - meta->lba = lba_list[paddr] = addr_empty; - } - - ret = pblk_submit_io_sync_sem(pblk, &rqd, line->smeta); - if (ret) { - pblk_err(pblk, "smeta I/O submission failed: %d\n", ret); - goto clear_rqd; - } - - atomic_dec(&pblk->inflight_io); - - if (rqd.error) { - pblk_log_write_err(pblk, &rqd); - ret = -EIO; - } - -clear_rqd: - pblk_free_rqd_meta(pblk, &rqd); - return ret; -} - -int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line, - void *emeta_buf) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - void *ppa_list_buf, *meta_list; - struct ppa_addr *ppa_list; - struct nvm_rq rqd; - u64 paddr = line->emeta_ssec; - dma_addr_t dma_ppa_list, dma_meta_list; - int min = pblk->min_write_pgs; - int left_ppas = lm->emeta_sec[0]; - int line_id = line->id; - int rq_ppas, rq_len; - int i, j; - int ret; - - meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, - &dma_meta_list); - if (!meta_list) - return -ENOMEM; - - ppa_list_buf = meta_list + pblk_dma_meta_size(pblk); - dma_ppa_list = dma_meta_list + pblk_dma_meta_size(pblk); - -next_rq: - memset(&rqd, 0, sizeof(struct nvm_rq)); - - rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false); - rq_len = rq_ppas * geo->csecs; - - rqd.meta_list = meta_list; - rqd.ppa_list = ppa_list_buf; - rqd.dma_meta_list = dma_meta_list; - rqd.dma_ppa_list = dma_ppa_list; - rqd.opcode = NVM_OP_PREAD; - rqd.nr_ppas = rq_ppas; - ppa_list = nvm_rq_to_ppa_list(&rqd); - - for (i = 0; i < rqd.nr_ppas; ) { - struct ppa_addr ppa = addr_to_gen_ppa(pblk, paddr, line_id); - int pos = pblk_ppa_to_pos(geo, ppa); - - if (pblk_io_aligned(pblk, rq_ppas)) - rqd.is_seq = 1; - - while (test_bit(pos, line->blk_bitmap)) { - paddr += min; - if (pblk_boundary_paddr_checks(pblk, paddr)) { - ret = -EINTR; - goto free_rqd_dma; - } - - ppa = addr_to_gen_ppa(pblk, paddr, line_id); - pos = pblk_ppa_to_pos(geo, ppa); - } - - if (pblk_boundary_paddr_checks(pblk, paddr + min)) { - ret = -EINTR; - goto free_rqd_dma; - } - - for (j = 0; j < min; j++, i++, paddr++) - ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line_id); - } - - ret = pblk_submit_io_sync(pblk, &rqd, emeta_buf); - if (ret) { - pblk_err(pblk, "emeta I/O submission failed: %d\n", ret); - goto free_rqd_dma; - } - - atomic_dec(&pblk->inflight_io); - - if (rqd.error && rqd.error != NVM_RSP_WARN_HIGHECC) { - pblk_log_read_err(pblk, &rqd); - ret = -EIO; - goto free_rqd_dma; - } - - emeta_buf += rq_len; - left_ppas -= rq_ppas; - if (left_ppas) - goto next_rq; - -free_rqd_dma: - nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list); - return ret; -} - -static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd, - struct ppa_addr ppa) -{ - rqd->opcode = NVM_OP_ERASE; - rqd->ppa_addr = ppa; - rqd->nr_ppas = 1; - rqd->is_seq = 1; - rqd->bio = NULL; -} - -static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa) -{ - struct nvm_rq rqd = {NULL}; - int ret; - - trace_pblk_chunk_reset(pblk_disk_name(pblk), &ppa, - PBLK_CHUNK_RESET_START); - - pblk_setup_e_rq(pblk, &rqd, ppa); - - /* The write thread schedules erases so that it minimizes disturbances - * with writes. Thus, there is no need to take the LUN semaphore. - */ - ret = pblk_submit_io_sync(pblk, &rqd, NULL); - rqd.private = pblk; - __pblk_end_io_erase(pblk, &rqd); - - return ret; -} - -int pblk_line_erase(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct ppa_addr ppa; - int ret, bit = -1; - - /* Erase only good blocks, one at a time */ - do { - spin_lock(&line->lock); - bit = find_next_zero_bit(line->erase_bitmap, lm->blk_per_line, - bit + 1); - if (bit >= lm->blk_per_line) { - spin_unlock(&line->lock); - break; - } - - ppa = pblk->luns[bit].bppa; /* set ch and lun */ - ppa.a.blk = line->id; - - atomic_dec(&line->left_eblks); - WARN_ON(test_and_set_bit(bit, line->erase_bitmap)); - spin_unlock(&line->lock); - - ret = pblk_blk_erase_sync(pblk, ppa); - if (ret) { - pblk_err(pblk, "failed to erase line %d\n", line->id); - return ret; - } - } while (1); - - return 0; -} - -static void pblk_line_setup_metadata(struct pblk_line *line, - struct pblk_line_mgmt *l_mg, - struct pblk_line_meta *lm) -{ - int meta_line; - - lockdep_assert_held(&l_mg->free_lock); - -retry_meta: - meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES); - if (meta_line == PBLK_DATA_LINES) { - spin_unlock(&l_mg->free_lock); - io_schedule(); - spin_lock(&l_mg->free_lock); - goto retry_meta; - } - - set_bit(meta_line, &l_mg->meta_bitmap); - line->meta_line = meta_line; - - line->smeta = l_mg->sline_meta[meta_line]; - line->emeta = l_mg->eline_meta[meta_line]; - - memset(line->smeta, 0, lm->smeta_len); - memset(line->emeta->buf, 0, lm->emeta_len[0]); - - line->emeta->mem = 0; - atomic_set(&line->emeta->sync, 0); -} - -/* For now lines are always assumed full lines. Thus, smeta former and current - * lun bitmaps are omitted. - */ -static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line, - struct pblk_line *cur) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_emeta *emeta = line->emeta; - struct line_emeta *emeta_buf = emeta->buf; - struct line_smeta *smeta_buf = (struct line_smeta *)line->smeta; - int nr_blk_line; - - /* After erasing the line, new bad blocks might appear and we risk - * having an invalid line - */ - nr_blk_line = lm->blk_per_line - - bitmap_weight(line->blk_bitmap, lm->blk_per_line); - if (nr_blk_line < lm->min_blk_line) { - spin_lock(&l_mg->free_lock); - spin_lock(&line->lock); - line->state = PBLK_LINESTATE_BAD; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - spin_unlock(&line->lock); - - list_add_tail(&line->list, &l_mg->bad_list); - spin_unlock(&l_mg->free_lock); - - pblk_debug(pblk, "line %d is bad\n", line->id); - - return 0; - } - - /* Run-time metadata */ - line->lun_bitmap = ((void *)(smeta_buf)) + sizeof(struct line_smeta); - - /* Mark LUNs allocated in this line (all for now) */ - bitmap_set(line->lun_bitmap, 0, lm->lun_bitmap_len); - - smeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC); - export_guid(smeta_buf->header.uuid, &pblk->instance_uuid); - smeta_buf->header.id = cpu_to_le32(line->id); - smeta_buf->header.type = cpu_to_le16(line->type); - smeta_buf->header.version_major = SMETA_VERSION_MAJOR; - smeta_buf->header.version_minor = SMETA_VERSION_MINOR; - - /* Start metadata */ - smeta_buf->seq_nr = cpu_to_le64(line->seq_nr); - smeta_buf->window_wr_lun = cpu_to_le32(geo->all_luns); - - /* Fill metadata among lines */ - if (cur) { - memcpy(line->lun_bitmap, cur->lun_bitmap, lm->lun_bitmap_len); - smeta_buf->prev_id = cpu_to_le32(cur->id); - cur->emeta->buf->next_id = cpu_to_le32(line->id); - } else { - smeta_buf->prev_id = cpu_to_le32(PBLK_LINE_EMPTY); - } - - /* All smeta must be set at this point */ - smeta_buf->header.crc = cpu_to_le32( - pblk_calc_meta_header_crc(pblk, &smeta_buf->header)); - smeta_buf->crc = cpu_to_le32(pblk_calc_smeta_crc(pblk, smeta_buf)); - - /* End metadata */ - memcpy(&emeta_buf->header, &smeta_buf->header, - sizeof(struct line_header)); - - emeta_buf->header.version_major = EMETA_VERSION_MAJOR; - emeta_buf->header.version_minor = EMETA_VERSION_MINOR; - emeta_buf->header.crc = cpu_to_le32( - pblk_calc_meta_header_crc(pblk, &emeta_buf->header)); - - emeta_buf->seq_nr = cpu_to_le64(line->seq_nr); - emeta_buf->nr_lbas = cpu_to_le64(line->sec_in_line); - emeta_buf->nr_valid_lbas = cpu_to_le64(0); - emeta_buf->next_id = cpu_to_le32(PBLK_LINE_EMPTY); - emeta_buf->crc = cpu_to_le32(0); - emeta_buf->prev_id = smeta_buf->prev_id; - - return 1; -} - -static int pblk_line_alloc_bitmaps(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - - line->map_bitmap = mempool_alloc(l_mg->bitmap_pool, GFP_KERNEL); - if (!line->map_bitmap) - return -ENOMEM; - - memset(line->map_bitmap, 0, lm->sec_bitmap_len); - - /* will be initialized using bb info from map_bitmap */ - line->invalid_bitmap = mempool_alloc(l_mg->bitmap_pool, GFP_KERNEL); - if (!line->invalid_bitmap) { - mempool_free(line->map_bitmap, l_mg->bitmap_pool); - line->map_bitmap = NULL; - return -ENOMEM; - } - - return 0; -} - -/* For now lines are always assumed full lines. Thus, smeta former and current - * lun bitmaps are omitted. - */ -static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line, - int init) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - u64 off; - int bit = -1; - int emeta_secs; - - line->sec_in_line = lm->sec_per_line; - - /* Capture bad block information on line mapping bitmaps */ - while ((bit = find_next_bit(line->blk_bitmap, lm->blk_per_line, - bit + 1)) < lm->blk_per_line) { - off = bit * geo->ws_opt; - bitmap_shift_left(l_mg->bb_aux, l_mg->bb_template, off, - lm->sec_per_line); - bitmap_or(line->map_bitmap, line->map_bitmap, l_mg->bb_aux, - lm->sec_per_line); - line->sec_in_line -= geo->clba; - } - - /* Mark smeta metadata sectors as bad sectors */ - bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line); - off = bit * geo->ws_opt; - bitmap_set(line->map_bitmap, off, lm->smeta_sec); - line->sec_in_line -= lm->smeta_sec; - line->cur_sec = off + lm->smeta_sec; - - if (init && pblk_line_smeta_write(pblk, line, off)) { - pblk_debug(pblk, "line smeta I/O failed. Retry\n"); - return 0; - } - - bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line); - - /* Mark emeta metadata sectors as bad sectors. We need to consider bad - * blocks to make sure that there are enough sectors to store emeta - */ - emeta_secs = lm->emeta_sec[0]; - off = lm->sec_per_line; - while (emeta_secs) { - off -= geo->ws_opt; - if (!test_bit(off, line->invalid_bitmap)) { - bitmap_set(line->invalid_bitmap, off, geo->ws_opt); - emeta_secs -= geo->ws_opt; - } - } - - line->emeta_ssec = off; - line->sec_in_line -= lm->emeta_sec[0]; - line->nr_valid_lbas = 0; - line->left_msecs = line->sec_in_line; - *line->vsc = cpu_to_le32(line->sec_in_line); - - if (lm->sec_per_line - line->sec_in_line != - bitmap_weight(line->invalid_bitmap, lm->sec_per_line)) { - spin_lock(&line->lock); - line->state = PBLK_LINESTATE_BAD; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - spin_unlock(&line->lock); - - list_add_tail(&line->list, &l_mg->bad_list); - pblk_err(pblk, "unexpected line %d is bad\n", line->id); - - return 0; - } - - return 1; -} - -static int pblk_prepare_new_line(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - int blk_to_erase = atomic_read(&line->blk_in_line); - int i; - - for (i = 0; i < lm->blk_per_line; i++) { - struct pblk_lun *rlun = &pblk->luns[i]; - int pos = pblk_ppa_to_pos(geo, rlun->bppa); - int state = line->chks[pos].state; - - /* Free chunks should not be erased */ - if (state & NVM_CHK_ST_FREE) { - set_bit(pblk_ppa_to_pos(geo, rlun->bppa), - line->erase_bitmap); - blk_to_erase--; - } - } - - return blk_to_erase; -} - -static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - int blk_in_line = atomic_read(&line->blk_in_line); - int blk_to_erase; - - /* Bad blocks do not need to be erased */ - bitmap_copy(line->erase_bitmap, line->blk_bitmap, lm->blk_per_line); - - spin_lock(&line->lock); - - /* If we have not written to this line, we need to mark up free chunks - * as already erased - */ - if (line->state == PBLK_LINESTATE_NEW) { - blk_to_erase = pblk_prepare_new_line(pblk, line); - line->state = PBLK_LINESTATE_FREE; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - } else { - blk_to_erase = blk_in_line; - } - - if (blk_in_line < lm->min_blk_line) { - spin_unlock(&line->lock); - return -EAGAIN; - } - - if (line->state != PBLK_LINESTATE_FREE) { - WARN(1, "pblk: corrupted line %d, state %d\n", - line->id, line->state); - spin_unlock(&line->lock); - return -EINTR; - } - - line->state = PBLK_LINESTATE_OPEN; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - - atomic_set(&line->left_eblks, blk_to_erase); - atomic_set(&line->left_seblks, blk_to_erase); - - line->meta_distance = lm->meta_distance; - spin_unlock(&line->lock); - - kref_init(&line->ref); - atomic_set(&line->sec_to_update, 0); - - return 0; -} - -/* Line allocations in the recovery path are always single threaded */ -int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - int ret; - - spin_lock(&l_mg->free_lock); - l_mg->data_line = line; - list_del(&line->list); - - ret = pblk_line_prepare(pblk, line); - if (ret) { - list_add(&line->list, &l_mg->free_list); - spin_unlock(&l_mg->free_lock); - return ret; - } - spin_unlock(&l_mg->free_lock); - - ret = pblk_line_alloc_bitmaps(pblk, line); - if (ret) - goto fail; - - if (!pblk_line_init_bb(pblk, line, 0)) { - ret = -EINTR; - goto fail; - } - - pblk_rl_free_lines_dec(&pblk->rl, line, true); - return 0; - -fail: - spin_lock(&l_mg->free_lock); - list_add(&line->list, &l_mg->free_list); - spin_unlock(&l_mg->free_lock); - - return ret; -} - -void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - - mempool_free(line->map_bitmap, l_mg->bitmap_pool); - line->map_bitmap = NULL; - line->smeta = NULL; - line->emeta = NULL; -} - -static void pblk_line_reinit(struct pblk_line *line) -{ - *line->vsc = cpu_to_le32(EMPTY_ENTRY); - - line->map_bitmap = NULL; - line->invalid_bitmap = NULL; - line->smeta = NULL; - line->emeta = NULL; -} - -void pblk_line_free(struct pblk_line *line) -{ - struct pblk *pblk = line->pblk; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - - mempool_free(line->map_bitmap, l_mg->bitmap_pool); - mempool_free(line->invalid_bitmap, l_mg->bitmap_pool); - - pblk_line_reinit(line); -} - -struct pblk_line *pblk_line_get(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line *line; - int ret, bit; - - lockdep_assert_held(&l_mg->free_lock); - -retry: - if (list_empty(&l_mg->free_list)) { - pblk_err(pblk, "no free lines\n"); - return NULL; - } - - line = list_first_entry(&l_mg->free_list, struct pblk_line, list); - list_del(&line->list); - l_mg->nr_free_lines--; - - bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line); - if (unlikely(bit >= lm->blk_per_line)) { - spin_lock(&line->lock); - line->state = PBLK_LINESTATE_BAD; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - spin_unlock(&line->lock); - - list_add_tail(&line->list, &l_mg->bad_list); - - pblk_debug(pblk, "line %d is bad\n", line->id); - goto retry; - } - - ret = pblk_line_prepare(pblk, line); - if (ret) { - switch (ret) { - case -EAGAIN: - list_add(&line->list, &l_mg->bad_list); - goto retry; - case -EINTR: - list_add(&line->list, &l_mg->corrupt_list); - goto retry; - default: - pblk_err(pblk, "failed to prepare line %d\n", line->id); - list_add(&line->list, &l_mg->free_list); - l_mg->nr_free_lines++; - return NULL; - } - } - - return line; -} - -static struct pblk_line *pblk_line_retry(struct pblk *pblk, - struct pblk_line *line) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line *retry_line; - -retry: - spin_lock(&l_mg->free_lock); - retry_line = pblk_line_get(pblk); - if (!retry_line) { - l_mg->data_line = NULL; - spin_unlock(&l_mg->free_lock); - return NULL; - } - - retry_line->map_bitmap = line->map_bitmap; - retry_line->invalid_bitmap = line->invalid_bitmap; - retry_line->smeta = line->smeta; - retry_line->emeta = line->emeta; - retry_line->meta_line = line->meta_line; - - pblk_line_reinit(line); - - l_mg->data_line = retry_line; - spin_unlock(&l_mg->free_lock); - - pblk_rl_free_lines_dec(&pblk->rl, line, false); - - if (pblk_line_erase(pblk, retry_line)) - goto retry; - - return retry_line; -} - -static void pblk_set_space_limit(struct pblk *pblk) -{ - struct pblk_rl *rl = &pblk->rl; - - atomic_set(&rl->rb_space, 0); -} - -struct pblk_line *pblk_line_get_first_data(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line *line; - - spin_lock(&l_mg->free_lock); - line = pblk_line_get(pblk); - if (!line) { - spin_unlock(&l_mg->free_lock); - return NULL; - } - - line->seq_nr = l_mg->d_seq_nr++; - line->type = PBLK_LINETYPE_DATA; - l_mg->data_line = line; - - pblk_line_setup_metadata(line, l_mg, &pblk->lm); - - /* Allocate next line for preparation */ - l_mg->data_next = pblk_line_get(pblk); - if (!l_mg->data_next) { - /* If we cannot get a new line, we need to stop the pipeline. - * Only allow as many writes in as we can store safely and then - * fail gracefully - */ - pblk_set_space_limit(pblk); - - l_mg->data_next = NULL; - } else { - l_mg->data_next->seq_nr = l_mg->d_seq_nr++; - l_mg->data_next->type = PBLK_LINETYPE_DATA; - } - spin_unlock(&l_mg->free_lock); - - if (pblk_line_alloc_bitmaps(pblk, line)) - return NULL; - - if (pblk_line_erase(pblk, line)) { - line = pblk_line_retry(pblk, line); - if (!line) - return NULL; - } - -retry_setup: - if (!pblk_line_init_metadata(pblk, line, NULL)) { - line = pblk_line_retry(pblk, line); - if (!line) - return NULL; - - goto retry_setup; - } - - if (!pblk_line_init_bb(pblk, line, 1)) { - line = pblk_line_retry(pblk, line); - if (!line) - return NULL; - - goto retry_setup; - } - - pblk_rl_free_lines_dec(&pblk->rl, line, true); - - return line; -} - -void pblk_ppa_to_line_put(struct pblk *pblk, struct ppa_addr ppa) -{ - struct pblk_line *line; - - line = pblk_ppa_to_line(pblk, ppa); - kref_put(&line->ref, pblk_line_put_wq); -} - -void pblk_rq_to_line_put(struct pblk *pblk, struct nvm_rq *rqd) -{ - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - int i; - - for (i = 0; i < rqd->nr_ppas; i++) - pblk_ppa_to_line_put(pblk, ppa_list[i]); -} - -static void pblk_stop_writes(struct pblk *pblk, struct pblk_line *line) -{ - lockdep_assert_held(&pblk->l_mg.free_lock); - - pblk_set_space_limit(pblk); - pblk->state = PBLK_STATE_STOPPING; - trace_pblk_state(pblk_disk_name(pblk), pblk->state); -} - -static void pblk_line_close_meta_sync(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line *line, *tline; - LIST_HEAD(list); - - spin_lock(&l_mg->close_lock); - if (list_empty(&l_mg->emeta_list)) { - spin_unlock(&l_mg->close_lock); - return; - } - - list_cut_position(&list, &l_mg->emeta_list, l_mg->emeta_list.prev); - spin_unlock(&l_mg->close_lock); - - list_for_each_entry_safe(line, tline, &list, list) { - struct pblk_emeta *emeta = line->emeta; - - while (emeta->mem < lm->emeta_len[0]) { - int ret; - - ret = pblk_submit_meta_io(pblk, line); - if (ret) { - pblk_err(pblk, "sync meta line %d failed (%d)\n", - line->id, ret); - return; - } - } - } - - pblk_wait_for_meta(pblk); - flush_workqueue(pblk->close_wq); -} - -void __pblk_pipeline_flush(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - int ret; - - spin_lock(&l_mg->free_lock); - if (pblk->state == PBLK_STATE_RECOVERING || - pblk->state == PBLK_STATE_STOPPED) { - spin_unlock(&l_mg->free_lock); - return; - } - pblk->state = PBLK_STATE_RECOVERING; - trace_pblk_state(pblk_disk_name(pblk), pblk->state); - spin_unlock(&l_mg->free_lock); - - pblk_flush_writer(pblk); - pblk_wait_for_meta(pblk); - - ret = pblk_recov_pad(pblk); - if (ret) { - pblk_err(pblk, "could not close data on teardown(%d)\n", ret); - return; - } - - flush_workqueue(pblk->bb_wq); - pblk_line_close_meta_sync(pblk); -} - -void __pblk_pipeline_stop(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - - spin_lock(&l_mg->free_lock); - pblk->state = PBLK_STATE_STOPPED; - trace_pblk_state(pblk_disk_name(pblk), pblk->state); - l_mg->data_line = NULL; - l_mg->data_next = NULL; - spin_unlock(&l_mg->free_lock); -} - -void pblk_pipeline_stop(struct pblk *pblk) -{ - __pblk_pipeline_flush(pblk); - __pblk_pipeline_stop(pblk); -} - -struct pblk_line *pblk_line_replace_data(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line *cur, *new = NULL; - unsigned int left_seblks; - - new = l_mg->data_next; - if (!new) - goto out; - - spin_lock(&l_mg->free_lock); - cur = l_mg->data_line; - l_mg->data_line = new; - - pblk_line_setup_metadata(new, l_mg, &pblk->lm); - spin_unlock(&l_mg->free_lock); - -retry_erase: - left_seblks = atomic_read(&new->left_seblks); - if (left_seblks) { - /* If line is not fully erased, erase it */ - if (atomic_read(&new->left_eblks)) { - if (pblk_line_erase(pblk, new)) - goto out; - } else { - io_schedule(); - } - goto retry_erase; - } - - if (pblk_line_alloc_bitmaps(pblk, new)) - return NULL; - -retry_setup: - if (!pblk_line_init_metadata(pblk, new, cur)) { - new = pblk_line_retry(pblk, new); - if (!new) - goto out; - - goto retry_setup; - } - - if (!pblk_line_init_bb(pblk, new, 1)) { - new = pblk_line_retry(pblk, new); - if (!new) - goto out; - - goto retry_setup; - } - - pblk_rl_free_lines_dec(&pblk->rl, new, true); - - /* Allocate next line for preparation */ - spin_lock(&l_mg->free_lock); - l_mg->data_next = pblk_line_get(pblk); - if (!l_mg->data_next) { - /* If we cannot get a new line, we need to stop the pipeline. - * Only allow as many writes in as we can store safely and then - * fail gracefully - */ - pblk_stop_writes(pblk, new); - l_mg->data_next = NULL; - } else { - l_mg->data_next->seq_nr = l_mg->d_seq_nr++; - l_mg->data_next->type = PBLK_LINETYPE_DATA; - } - spin_unlock(&l_mg->free_lock); - -out: - return new; -} - -static void __pblk_line_put(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_gc *gc = &pblk->gc; - - spin_lock(&line->lock); - WARN_ON(line->state != PBLK_LINESTATE_GC); - if (line->w_err_gc->has_gc_err) { - spin_unlock(&line->lock); - pblk_err(pblk, "line %d had errors during GC\n", line->id); - pblk_put_line_back(pblk, line); - line->w_err_gc->has_gc_err = 0; - return; - } - - line->state = PBLK_LINESTATE_FREE; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - line->gc_group = PBLK_LINEGC_NONE; - pblk_line_free(line); - - if (line->w_err_gc->has_write_err) { - pblk_rl_werr_line_out(&pblk->rl); - line->w_err_gc->has_write_err = 0; - } - - spin_unlock(&line->lock); - atomic_dec(&gc->pipeline_gc); - - spin_lock(&l_mg->free_lock); - list_add_tail(&line->list, &l_mg->free_list); - l_mg->nr_free_lines++; - spin_unlock(&l_mg->free_lock); - - pblk_rl_free_lines_inc(&pblk->rl, line); -} - -static void pblk_line_put_ws(struct work_struct *work) -{ - struct pblk_line_ws *line_put_ws = container_of(work, - struct pblk_line_ws, ws); - struct pblk *pblk = line_put_ws->pblk; - struct pblk_line *line = line_put_ws->line; - - __pblk_line_put(pblk, line); - mempool_free(line_put_ws, &pblk->gen_ws_pool); -} - -void pblk_line_put(struct kref *ref) -{ - struct pblk_line *line = container_of(ref, struct pblk_line, ref); - struct pblk *pblk = line->pblk; - - __pblk_line_put(pblk, line); -} - -void pblk_line_put_wq(struct kref *ref) -{ - struct pblk_line *line = container_of(ref, struct pblk_line, ref); - struct pblk *pblk = line->pblk; - struct pblk_line_ws *line_put_ws; - - line_put_ws = mempool_alloc(&pblk->gen_ws_pool, GFP_ATOMIC); - if (!line_put_ws) - return; - - line_put_ws->pblk = pblk; - line_put_ws->line = line; - line_put_ws->priv = NULL; - - INIT_WORK(&line_put_ws->ws, pblk_line_put_ws); - queue_work(pblk->r_end_wq, &line_put_ws->ws); -} - -int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa) -{ - struct nvm_rq *rqd; - int err; - - rqd = pblk_alloc_rqd(pblk, PBLK_ERASE); - - pblk_setup_e_rq(pblk, rqd, ppa); - - rqd->end_io = pblk_end_io_erase; - rqd->private = pblk; - - trace_pblk_chunk_reset(pblk_disk_name(pblk), - &ppa, PBLK_CHUNK_RESET_START); - - /* The write thread schedules erases so that it minimizes disturbances - * with writes. Thus, there is no need to take the LUN semaphore. - */ - err = pblk_submit_io(pblk, rqd, NULL); - if (err) { - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - - pblk_err(pblk, "could not async erase line:%d,blk:%d\n", - pblk_ppa_to_line_id(ppa), - pblk_ppa_to_pos(geo, ppa)); - } - - return err; -} - -struct pblk_line *pblk_line_get_data(struct pblk *pblk) -{ - return pblk->l_mg.data_line; -} - -/* For now, always erase next line */ -struct pblk_line *pblk_line_get_erase(struct pblk *pblk) -{ - return pblk->l_mg.data_next; -} - -int pblk_line_is_full(struct pblk_line *line) -{ - return (line->left_msecs == 0); -} - -static void pblk_line_should_sync_meta(struct pblk *pblk) -{ - if (pblk_rl_is_limit(&pblk->rl)) - pblk_line_close_meta_sync(pblk); -} - -void pblk_line_close(struct pblk *pblk, struct pblk_line *line) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct list_head *move_list; - int i; - -#ifdef CONFIG_NVM_PBLK_DEBUG - WARN(!bitmap_full(line->map_bitmap, lm->sec_per_line), - "pblk: corrupt closed line %d\n", line->id); -#endif - - spin_lock(&l_mg->free_lock); - WARN_ON(!test_and_clear_bit(line->meta_line, &l_mg->meta_bitmap)); - spin_unlock(&l_mg->free_lock); - - spin_lock(&l_mg->gc_lock); - spin_lock(&line->lock); - WARN_ON(line->state != PBLK_LINESTATE_OPEN); - line->state = PBLK_LINESTATE_CLOSED; - move_list = pblk_line_gc_list(pblk, line); - list_add_tail(&line->list, move_list); - - mempool_free(line->map_bitmap, l_mg->bitmap_pool); - line->map_bitmap = NULL; - line->smeta = NULL; - line->emeta = NULL; - - for (i = 0; i < lm->blk_per_line; i++) { - struct pblk_lun *rlun = &pblk->luns[i]; - int pos = pblk_ppa_to_pos(geo, rlun->bppa); - int state = line->chks[pos].state; - - if (!(state & NVM_CHK_ST_OFFLINE)) - state = NVM_CHK_ST_CLOSED; - } - - spin_unlock(&line->lock); - spin_unlock(&l_mg->gc_lock); - - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); -} - -void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_emeta *emeta = line->emeta; - struct line_emeta *emeta_buf = emeta->buf; - struct wa_counters *wa = emeta_to_wa(lm, emeta_buf); - - /* No need for exact vsc value; avoid a big line lock and take aprox. */ - memcpy(emeta_to_vsc(pblk, emeta_buf), l_mg->vsc_list, lm->vsc_list_len); - memcpy(emeta_to_bb(emeta_buf), line->blk_bitmap, lm->blk_bitmap_len); - - wa->user = cpu_to_le64(atomic64_read(&pblk->user_wa)); - wa->pad = cpu_to_le64(atomic64_read(&pblk->pad_wa)); - wa->gc = cpu_to_le64(atomic64_read(&pblk->gc_wa)); - - if (le32_to_cpu(emeta_buf->header.identifier) != PBLK_MAGIC) { - emeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC); - export_guid(emeta_buf->header.uuid, &pblk->instance_uuid); - emeta_buf->header.id = cpu_to_le32(line->id); - emeta_buf->header.type = cpu_to_le16(line->type); - emeta_buf->header.version_major = EMETA_VERSION_MAJOR; - emeta_buf->header.version_minor = EMETA_VERSION_MINOR; - emeta_buf->header.crc = cpu_to_le32( - pblk_calc_meta_header_crc(pblk, &emeta_buf->header)); - } - - emeta_buf->nr_valid_lbas = cpu_to_le64(line->nr_valid_lbas); - emeta_buf->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, emeta_buf)); - - spin_lock(&l_mg->close_lock); - spin_lock(&line->lock); - - /* Update the in-memory start address for emeta, in case it has - * shifted due to write errors - */ - if (line->emeta_ssec != line->cur_sec) - line->emeta_ssec = line->cur_sec; - - list_add_tail(&line->list, &l_mg->emeta_list); - spin_unlock(&line->lock); - spin_unlock(&l_mg->close_lock); - - pblk_line_should_sync_meta(pblk); -} - -static void pblk_save_lba_list(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - unsigned int lba_list_size = lm->emeta_len[2]; - struct pblk_w_err_gc *w_err_gc = line->w_err_gc; - struct pblk_emeta *emeta = line->emeta; - - w_err_gc->lba_list = kvmalloc(lba_list_size, GFP_KERNEL); - memcpy(w_err_gc->lba_list, emeta_to_lbas(pblk, emeta->buf), - lba_list_size); -} - -void pblk_line_close_ws(struct work_struct *work) -{ - struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws, - ws); - struct pblk *pblk = line_ws->pblk; - struct pblk_line *line = line_ws->line; - struct pblk_w_err_gc *w_err_gc = line->w_err_gc; - - /* Write errors makes the emeta start address stored in smeta invalid, - * so keep a copy of the lba list until we've gc'd the line - */ - if (w_err_gc->has_write_err) - pblk_save_lba_list(pblk, line); - - pblk_line_close(pblk, line); - mempool_free(line_ws, &pblk->gen_ws_pool); -} - -void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv, - void (*work)(struct work_struct *), gfp_t gfp_mask, - struct workqueue_struct *wq) -{ - struct pblk_line_ws *line_ws; - - line_ws = mempool_alloc(&pblk->gen_ws_pool, gfp_mask); - if (!line_ws) { - pblk_err(pblk, "pblk: could not allocate memory\n"); - return; - } - - line_ws->pblk = pblk; - line_ws->line = line; - line_ws->priv = priv; - - INIT_WORK(&line_ws->ws, work); - queue_work(wq, &line_ws->ws); -} - -static void __pblk_down_chunk(struct pblk *pblk, int pos) -{ - struct pblk_lun *rlun = &pblk->luns[pos]; - int ret; - - /* - * Only send one inflight I/O per LUN. Since we map at a page - * granurality, all ppas in the I/O will map to the same LUN - */ - - ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(30000)); - if (ret == -ETIME || ret == -EINTR) - pblk_err(pblk, "taking lun semaphore timed out: err %d\n", - -ret); -} - -void pblk_down_chunk(struct pblk *pblk, struct ppa_addr ppa) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - int pos = pblk_ppa_to_pos(geo, ppa); - - __pblk_down_chunk(pblk, pos); -} - -void pblk_down_rq(struct pblk *pblk, struct ppa_addr ppa, - unsigned long *lun_bitmap) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - int pos = pblk_ppa_to_pos(geo, ppa); - - /* If the LUN has been locked for this same request, do no attempt to - * lock it again - */ - if (test_and_set_bit(pos, lun_bitmap)) - return; - - __pblk_down_chunk(pblk, pos); -} - -void pblk_up_chunk(struct pblk *pblk, struct ppa_addr ppa) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_lun *rlun; - int pos = pblk_ppa_to_pos(geo, ppa); - - rlun = &pblk->luns[pos]; - up(&rlun->wr_sem); -} - -void pblk_up_rq(struct pblk *pblk, unsigned long *lun_bitmap) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_lun *rlun; - int num_lun = geo->all_luns; - int bit = -1; - - while ((bit = find_next_bit(lun_bitmap, num_lun, bit + 1)) < num_lun) { - rlun = &pblk->luns[bit]; - up(&rlun->wr_sem); - } -} - -void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa) -{ - struct ppa_addr ppa_l2p; - - /* logic error: lba out-of-bounds. Ignore update */ - if (!(lba < pblk->capacity)) { - WARN(1, "pblk: corrupted L2P map request\n"); - return; - } - - spin_lock(&pblk->trans_lock); - ppa_l2p = pblk_trans_map_get(pblk, lba); - - if (!pblk_addr_in_cache(ppa_l2p) && !pblk_ppa_empty(ppa_l2p)) - pblk_map_invalidate(pblk, ppa_l2p); - - pblk_trans_map_set(pblk, lba, ppa); - spin_unlock(&pblk->trans_lock); -} - -void pblk_update_map_cache(struct pblk *pblk, sector_t lba, struct ppa_addr ppa) -{ - -#ifdef CONFIG_NVM_PBLK_DEBUG - /* Callers must ensure that the ppa points to a cache address */ - BUG_ON(!pblk_addr_in_cache(ppa)); - BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa))); -#endif - - pblk_update_map(pblk, lba, ppa); -} - -int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa_new, - struct pblk_line *gc_line, u64 paddr_gc) -{ - struct ppa_addr ppa_l2p, ppa_gc; - int ret = 1; - -#ifdef CONFIG_NVM_PBLK_DEBUG - /* Callers must ensure that the ppa points to a cache address */ - BUG_ON(!pblk_addr_in_cache(ppa_new)); - BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa_new))); -#endif - - /* logic error: lba out-of-bounds. Ignore update */ - if (!(lba < pblk->capacity)) { - WARN(1, "pblk: corrupted L2P map request\n"); - return 0; - } - - spin_lock(&pblk->trans_lock); - ppa_l2p = pblk_trans_map_get(pblk, lba); - ppa_gc = addr_to_gen_ppa(pblk, paddr_gc, gc_line->id); - - if (!pblk_ppa_comp(ppa_l2p, ppa_gc)) { - spin_lock(&gc_line->lock); - WARN(!test_bit(paddr_gc, gc_line->invalid_bitmap), - "pblk: corrupted GC update"); - spin_unlock(&gc_line->lock); - - ret = 0; - goto out; - } - - pblk_trans_map_set(pblk, lba, ppa_new); -out: - spin_unlock(&pblk->trans_lock); - return ret; -} - -void pblk_update_map_dev(struct pblk *pblk, sector_t lba, - struct ppa_addr ppa_mapped, struct ppa_addr ppa_cache) -{ - struct ppa_addr ppa_l2p; - -#ifdef CONFIG_NVM_PBLK_DEBUG - /* Callers must ensure that the ppa points to a device address */ - BUG_ON(pblk_addr_in_cache(ppa_mapped)); -#endif - /* Invalidate and discard padded entries */ - if (lba == ADDR_EMPTY) { - atomic64_inc(&pblk->pad_wa); -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_inc(&pblk->padded_wb); -#endif - if (!pblk_ppa_empty(ppa_mapped)) - pblk_map_invalidate(pblk, ppa_mapped); - return; - } - - /* logic error: lba out-of-bounds. Ignore update */ - if (!(lba < pblk->capacity)) { - WARN(1, "pblk: corrupted L2P map request\n"); - return; - } - - spin_lock(&pblk->trans_lock); - ppa_l2p = pblk_trans_map_get(pblk, lba); - - /* Do not update L2P if the cacheline has been updated. In this case, - * the mapped ppa must be invalidated - */ - if (!pblk_ppa_comp(ppa_l2p, ppa_cache)) { - if (!pblk_ppa_empty(ppa_mapped)) - pblk_map_invalidate(pblk, ppa_mapped); - goto out; - } - -#ifdef CONFIG_NVM_PBLK_DEBUG - WARN_ON(!pblk_addr_in_cache(ppa_l2p) && !pblk_ppa_empty(ppa_l2p)); -#endif - - pblk_trans_map_set(pblk, lba, ppa_mapped); -out: - spin_unlock(&pblk->trans_lock); -} - -int pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas, - sector_t blba, int nr_secs, bool *from_cache) -{ - int i; - - spin_lock(&pblk->trans_lock); - for (i = 0; i < nr_secs; i++) { - struct ppa_addr ppa; - - ppa = ppas[i] = pblk_trans_map_get(pblk, blba + i); - - /* If the L2P entry maps to a line, the reference is valid */ - if (!pblk_ppa_empty(ppa) && !pblk_addr_in_cache(ppa)) { - struct pblk_line *line = pblk_ppa_to_line(pblk, ppa); - - if (i > 0 && *from_cache) - break; - *from_cache = false; - - kref_get(&line->ref); - } else { - if (i > 0 && !*from_cache) - break; - *from_cache = true; - } - } - spin_unlock(&pblk->trans_lock); - return i; -} - -void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas, - u64 *lba_list, int nr_secs) -{ - u64 lba; - int i; - - spin_lock(&pblk->trans_lock); - for (i = 0; i < nr_secs; i++) { - lba = lba_list[i]; - if (lba != ADDR_EMPTY) { - /* logic error: lba out-of-bounds. Ignore update */ - if (!(lba < pblk->capacity)) { - WARN(1, "pblk: corrupted L2P map request\n"); - continue; - } - ppas[i] = pblk_trans_map_get(pblk, lba); - } - } - spin_unlock(&pblk->trans_lock); -} - -void *pblk_get_meta_for_writes(struct pblk *pblk, struct nvm_rq *rqd) -{ - void *buffer; - - if (pblk_is_oob_meta_supported(pblk)) { - /* Just use OOB metadata buffer as always */ - buffer = rqd->meta_list; - } else { - /* We need to reuse last page of request (packed metadata) - * in similar way as traditional oob metadata - */ - buffer = page_to_virt( - rqd->bio->bi_io_vec[rqd->bio->bi_vcnt - 1].bv_page); - } - - return buffer; -} - -void pblk_get_packed_meta(struct pblk *pblk, struct nvm_rq *rqd) -{ - void *meta_list = rqd->meta_list; - void *page; - int i = 0; - - if (pblk_is_oob_meta_supported(pblk)) - return; - - page = page_to_virt(rqd->bio->bi_io_vec[rqd->bio->bi_vcnt - 1].bv_page); - /* We need to fill oob meta buffer with data from packed metadata */ - for (; i < rqd->nr_ppas; i++) - memcpy(pblk_get_meta(pblk, meta_list, i), - page + (i * sizeof(struct pblk_sec_meta)), - sizeof(struct pblk_sec_meta)); -} diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c deleted file mode 100644 index b31658be35a7..000000000000 --- a/drivers/lightnvm/pblk-gc.c +++ /dev/null @@ -1,726 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2016 CNEX Labs - * Initial release: Javier Gonzalez - * Matias Bjorling - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * pblk-gc.c - pblk's garbage collector - */ - -#include "pblk.h" -#include "pblk-trace.h" -#include - - -static void pblk_gc_free_gc_rq(struct pblk_gc_rq *gc_rq) -{ - vfree(gc_rq->data); - kfree(gc_rq); -} - -static int pblk_gc_write(struct pblk *pblk) -{ - struct pblk_gc *gc = &pblk->gc; - struct pblk_gc_rq *gc_rq, *tgc_rq; - LIST_HEAD(w_list); - - spin_lock(&gc->w_lock); - if (list_empty(&gc->w_list)) { - spin_unlock(&gc->w_lock); - return 1; - } - - list_cut_position(&w_list, &gc->w_list, gc->w_list.prev); - gc->w_entries = 0; - spin_unlock(&gc->w_lock); - - list_for_each_entry_safe(gc_rq, tgc_rq, &w_list, list) { - pblk_write_gc_to_cache(pblk, gc_rq); - list_del(&gc_rq->list); - kref_put(&gc_rq->line->ref, pblk_line_put); - pblk_gc_free_gc_rq(gc_rq); - } - - return 0; -} - -static void pblk_gc_writer_kick(struct pblk_gc *gc) -{ - wake_up_process(gc->gc_writer_ts); -} - -void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct list_head *move_list; - - spin_lock(&l_mg->gc_lock); - spin_lock(&line->lock); - WARN_ON(line->state != PBLK_LINESTATE_GC); - line->state = PBLK_LINESTATE_CLOSED; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - - /* We need to reset gc_group in order to ensure that - * pblk_line_gc_list will return proper move_list - * since right now current line is not on any of the - * gc lists. - */ - line->gc_group = PBLK_LINEGC_NONE; - move_list = pblk_line_gc_list(pblk, line); - spin_unlock(&line->lock); - list_add_tail(&line->list, move_list); - spin_unlock(&l_mg->gc_lock); -} - -static void pblk_gc_line_ws(struct work_struct *work) -{ - struct pblk_line_ws *gc_rq_ws = container_of(work, - struct pblk_line_ws, ws); - struct pblk *pblk = gc_rq_ws->pblk; - struct pblk_gc *gc = &pblk->gc; - struct pblk_line *line = gc_rq_ws->line; - struct pblk_gc_rq *gc_rq = gc_rq_ws->priv; - int ret; - - up(&gc->gc_sem); - - /* Read from GC victim block */ - ret = pblk_submit_read_gc(pblk, gc_rq); - if (ret) { - line->w_err_gc->has_gc_err = 1; - goto out; - } - - if (!gc_rq->secs_to_gc) - goto out; - -retry: - spin_lock(&gc->w_lock); - if (gc->w_entries >= PBLK_GC_RQ_QD) { - spin_unlock(&gc->w_lock); - pblk_gc_writer_kick(&pblk->gc); - usleep_range(128, 256); - goto retry; - } - gc->w_entries++; - list_add_tail(&gc_rq->list, &gc->w_list); - spin_unlock(&gc->w_lock); - - pblk_gc_writer_kick(&pblk->gc); - - kfree(gc_rq_ws); - return; - -out: - pblk_gc_free_gc_rq(gc_rq); - kref_put(&line->ref, pblk_line_put); - kfree(gc_rq_ws); -} - -static __le64 *get_lba_list_from_emeta(struct pblk *pblk, - struct pblk_line *line) -{ - struct line_emeta *emeta_buf; - struct pblk_line_meta *lm = &pblk->lm; - unsigned int lba_list_size = lm->emeta_len[2]; - __le64 *lba_list; - int ret; - - emeta_buf = kvmalloc(lm->emeta_len[0], GFP_KERNEL); - if (!emeta_buf) - return NULL; - - ret = pblk_line_emeta_read(pblk, line, emeta_buf); - if (ret) { - pblk_err(pblk, "line %d read emeta failed (%d)\n", - line->id, ret); - kvfree(emeta_buf); - return NULL; - } - - /* If this read fails, it means that emeta is corrupted. - * For now, leave the line untouched. - * TODO: Implement a recovery routine that scans and moves - * all sectors on the line. - */ - - ret = pblk_recov_check_emeta(pblk, emeta_buf); - if (ret) { - pblk_err(pblk, "inconsistent emeta (line %d)\n", - line->id); - kvfree(emeta_buf); - return NULL; - } - - lba_list = kvmalloc(lba_list_size, GFP_KERNEL); - - if (lba_list) - memcpy(lba_list, emeta_to_lbas(pblk, emeta_buf), lba_list_size); - - kvfree(emeta_buf); - - return lba_list; -} - -static void pblk_gc_line_prepare_ws(struct work_struct *work) -{ - struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws, - ws); - struct pblk *pblk = line_ws->pblk; - struct pblk_line *line = line_ws->line; - struct pblk_line_meta *lm = &pblk->lm; - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_gc *gc = &pblk->gc; - struct pblk_line_ws *gc_rq_ws; - struct pblk_gc_rq *gc_rq; - __le64 *lba_list; - unsigned long *invalid_bitmap; - int sec_left, nr_secs, bit; - - invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_KERNEL); - if (!invalid_bitmap) - goto fail_free_ws; - - if (line->w_err_gc->has_write_err) { - lba_list = line->w_err_gc->lba_list; - line->w_err_gc->lba_list = NULL; - } else { - lba_list = get_lba_list_from_emeta(pblk, line); - if (!lba_list) { - pblk_err(pblk, "could not interpret emeta (line %d)\n", - line->id); - goto fail_free_invalid_bitmap; - } - } - - spin_lock(&line->lock); - bitmap_copy(invalid_bitmap, line->invalid_bitmap, lm->sec_per_line); - sec_left = pblk_line_vsc(line); - spin_unlock(&line->lock); - - if (sec_left < 0) { - pblk_err(pblk, "corrupted GC line (%d)\n", line->id); - goto fail_free_lba_list; - } - - bit = -1; -next_rq: - gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL); - if (!gc_rq) - goto fail_free_lba_list; - - nr_secs = 0; - do { - bit = find_next_zero_bit(invalid_bitmap, lm->sec_per_line, - bit + 1); - if (bit > line->emeta_ssec) - break; - - gc_rq->paddr_list[nr_secs] = bit; - gc_rq->lba_list[nr_secs++] = le64_to_cpu(lba_list[bit]); - } while (nr_secs < pblk->max_write_pgs); - - if (unlikely(!nr_secs)) { - kfree(gc_rq); - goto out; - } - - gc_rq->nr_secs = nr_secs; - gc_rq->line = line; - - gc_rq->data = vmalloc(array_size(gc_rq->nr_secs, geo->csecs)); - if (!gc_rq->data) - goto fail_free_gc_rq; - - gc_rq_ws = kmalloc(sizeof(struct pblk_line_ws), GFP_KERNEL); - if (!gc_rq_ws) - goto fail_free_gc_data; - - gc_rq_ws->pblk = pblk; - gc_rq_ws->line = line; - gc_rq_ws->priv = gc_rq; - - /* The write GC path can be much slower than the read GC one due to - * the budget imposed by the rate-limiter. Balance in case that we get - * back pressure from the write GC path. - */ - while (down_timeout(&gc->gc_sem, msecs_to_jiffies(30000))) - io_schedule(); - - kref_get(&line->ref); - - INIT_WORK(&gc_rq_ws->ws, pblk_gc_line_ws); - queue_work(gc->gc_line_reader_wq, &gc_rq_ws->ws); - - sec_left -= nr_secs; - if (sec_left > 0) - goto next_rq; - -out: - kvfree(lba_list); - kfree(line_ws); - kfree(invalid_bitmap); - - kref_put(&line->ref, pblk_line_put); - atomic_dec(&gc->read_inflight_gc); - - return; - -fail_free_gc_data: - vfree(gc_rq->data); -fail_free_gc_rq: - kfree(gc_rq); -fail_free_lba_list: - kvfree(lba_list); -fail_free_invalid_bitmap: - kfree(invalid_bitmap); -fail_free_ws: - kfree(line_ws); - - /* Line goes back to closed state, so we cannot release additional - * reference for line, since we do that only when we want to do - * gc to free line state transition. - */ - pblk_put_line_back(pblk, line); - atomic_dec(&gc->read_inflight_gc); - - pblk_err(pblk, "failed to GC line %d\n", line->id); -} - -static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_gc *gc = &pblk->gc; - struct pblk_line_ws *line_ws; - - pblk_debug(pblk, "line '%d' being reclaimed for GC\n", line->id); - - line_ws = kmalloc(sizeof(struct pblk_line_ws), GFP_KERNEL); - if (!line_ws) - return -ENOMEM; - - line_ws->pblk = pblk; - line_ws->line = line; - - atomic_inc(&gc->pipeline_gc); - INIT_WORK(&line_ws->ws, pblk_gc_line_prepare_ws); - queue_work(gc->gc_reader_wq, &line_ws->ws); - - return 0; -} - -static void pblk_gc_reader_kick(struct pblk_gc *gc) -{ - wake_up_process(gc->gc_reader_ts); -} - -static void pblk_gc_kick(struct pblk *pblk) -{ - struct pblk_gc *gc = &pblk->gc; - - pblk_gc_writer_kick(gc); - pblk_gc_reader_kick(gc); - - /* If we're shutting down GC, let's not start it up again */ - if (gc->gc_enabled) { - wake_up_process(gc->gc_ts); - mod_timer(&gc->gc_timer, - jiffies + msecs_to_jiffies(GC_TIME_MSECS)); - } -} - -static int pblk_gc_read(struct pblk *pblk) -{ - struct pblk_gc *gc = &pblk->gc; - struct pblk_line *line; - - spin_lock(&gc->r_lock); - if (list_empty(&gc->r_list)) { - spin_unlock(&gc->r_lock); - return 1; - } - - line = list_first_entry(&gc->r_list, struct pblk_line, list); - list_del(&line->list); - spin_unlock(&gc->r_lock); - - pblk_gc_kick(pblk); - - if (pblk_gc_line(pblk, line)) { - pblk_err(pblk, "failed to GC line %d\n", line->id); - /* rollback */ - spin_lock(&gc->r_lock); - list_add_tail(&line->list, &gc->r_list); - spin_unlock(&gc->r_lock); - } - - return 0; -} - -static struct pblk_line *pblk_gc_get_victim_line(struct pblk *pblk, - struct list_head *group_list) -{ - struct pblk_line *line, *victim; - unsigned int line_vsc = ~0x0L, victim_vsc = ~0x0L; - - victim = list_first_entry(group_list, struct pblk_line, list); - - list_for_each_entry(line, group_list, list) { - if (!atomic_read(&line->sec_to_update)) - line_vsc = le32_to_cpu(*line->vsc); - if (line_vsc < victim_vsc) { - victim = line; - victim_vsc = le32_to_cpu(*victim->vsc); - } - } - - if (victim_vsc == ~0x0) - return NULL; - - return victim; -} - -static bool pblk_gc_should_run(struct pblk_gc *gc, struct pblk_rl *rl) -{ - unsigned int nr_blocks_free, nr_blocks_need; - unsigned int werr_lines = atomic_read(&rl->werr_lines); - - nr_blocks_need = pblk_rl_high_thrs(rl); - nr_blocks_free = pblk_rl_nr_free_blks(rl); - - /* This is not critical, no need to take lock here */ - return ((werr_lines > 0) || - ((gc->gc_active) && (nr_blocks_need > nr_blocks_free))); -} - -void pblk_gc_free_full_lines(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_gc *gc = &pblk->gc; - struct pblk_line *line; - - do { - spin_lock(&l_mg->gc_lock); - if (list_empty(&l_mg->gc_full_list)) { - spin_unlock(&l_mg->gc_lock); - return; - } - - line = list_first_entry(&l_mg->gc_full_list, - struct pblk_line, list); - - spin_lock(&line->lock); - WARN_ON(line->state != PBLK_LINESTATE_CLOSED); - line->state = PBLK_LINESTATE_GC; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - spin_unlock(&line->lock); - - list_del(&line->list); - spin_unlock(&l_mg->gc_lock); - - atomic_inc(&gc->pipeline_gc); - kref_put(&line->ref, pblk_line_put); - } while (1); -} - -/* - * Lines with no valid sectors will be returned to the free list immediately. If - * GC is activated - either because the free block count is under the determined - * threshold, or because it is being forced from user space - only lines with a - * high count of invalid sectors will be recycled. - */ -static void pblk_gc_run(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_gc *gc = &pblk->gc; - struct pblk_line *line; - struct list_head *group_list; - bool run_gc; - int read_inflight_gc, gc_group = 0, prev_group = 0; - - pblk_gc_free_full_lines(pblk); - - run_gc = pblk_gc_should_run(&pblk->gc, &pblk->rl); - if (!run_gc || (atomic_read(&gc->read_inflight_gc) >= PBLK_GC_L_QD)) - return; - -next_gc_group: - group_list = l_mg->gc_lists[gc_group++]; - - do { - spin_lock(&l_mg->gc_lock); - - line = pblk_gc_get_victim_line(pblk, group_list); - if (!line) { - spin_unlock(&l_mg->gc_lock); - break; - } - - spin_lock(&line->lock); - WARN_ON(line->state != PBLK_LINESTATE_CLOSED); - line->state = PBLK_LINESTATE_GC; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - spin_unlock(&line->lock); - - list_del(&line->list); - spin_unlock(&l_mg->gc_lock); - - spin_lock(&gc->r_lock); - list_add_tail(&line->list, &gc->r_list); - spin_unlock(&gc->r_lock); - - read_inflight_gc = atomic_inc_return(&gc->read_inflight_gc); - pblk_gc_reader_kick(gc); - - prev_group = 1; - - /* No need to queue up more GC lines than we can handle */ - run_gc = pblk_gc_should_run(&pblk->gc, &pblk->rl); - if (!run_gc || read_inflight_gc >= PBLK_GC_L_QD) - break; - } while (1); - - if (!prev_group && pblk->rl.rb_state > gc_group && - gc_group < PBLK_GC_NR_LISTS) - goto next_gc_group; -} - -static void pblk_gc_timer(struct timer_list *t) -{ - struct pblk *pblk = from_timer(pblk, t, gc.gc_timer); - - pblk_gc_kick(pblk); -} - -static int pblk_gc_ts(void *data) -{ - struct pblk *pblk = data; - - while (!kthread_should_stop()) { - pblk_gc_run(pblk); - set_current_state(TASK_INTERRUPTIBLE); - io_schedule(); - } - - return 0; -} - -static int pblk_gc_writer_ts(void *data) -{ - struct pblk *pblk = data; - - while (!kthread_should_stop()) { - if (!pblk_gc_write(pblk)) - continue; - set_current_state(TASK_INTERRUPTIBLE); - io_schedule(); - } - - return 0; -} - -static int pblk_gc_reader_ts(void *data) -{ - struct pblk *pblk = data; - struct pblk_gc *gc = &pblk->gc; - - while (!kthread_should_stop()) { - if (!pblk_gc_read(pblk)) - continue; - set_current_state(TASK_INTERRUPTIBLE); - io_schedule(); - } - -#ifdef CONFIG_NVM_PBLK_DEBUG - pblk_info(pblk, "flushing gc pipeline, %d lines left\n", - atomic_read(&gc->pipeline_gc)); -#endif - - do { - if (!atomic_read(&gc->pipeline_gc)) - break; - - schedule(); - } while (1); - - return 0; -} - -static void pblk_gc_start(struct pblk *pblk) -{ - pblk->gc.gc_active = 1; - pblk_debug(pblk, "gc start\n"); -} - -void pblk_gc_should_start(struct pblk *pblk) -{ - struct pblk_gc *gc = &pblk->gc; - - if (gc->gc_enabled && !gc->gc_active) { - pblk_gc_start(pblk); - pblk_gc_kick(pblk); - } -} - -void pblk_gc_should_stop(struct pblk *pblk) -{ - struct pblk_gc *gc = &pblk->gc; - - if (gc->gc_active && !gc->gc_forced) - gc->gc_active = 0; -} - -void pblk_gc_should_kick(struct pblk *pblk) -{ - pblk_rl_update_rates(&pblk->rl); -} - -void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled, - int *gc_active) -{ - struct pblk_gc *gc = &pblk->gc; - - spin_lock(&gc->lock); - *gc_enabled = gc->gc_enabled; - *gc_active = gc->gc_active; - spin_unlock(&gc->lock); -} - -int pblk_gc_sysfs_force(struct pblk *pblk, int force) -{ - struct pblk_gc *gc = &pblk->gc; - - if (force < 0 || force > 1) - return -EINVAL; - - spin_lock(&gc->lock); - gc->gc_forced = force; - - if (force) - gc->gc_enabled = 1; - else - gc->gc_enabled = 0; - spin_unlock(&gc->lock); - - pblk_gc_should_start(pblk); - - return 0; -} - -int pblk_gc_init(struct pblk *pblk) -{ - struct pblk_gc *gc = &pblk->gc; - int ret; - - gc->gc_ts = kthread_create(pblk_gc_ts, pblk, "pblk-gc-ts"); - if (IS_ERR(gc->gc_ts)) { - pblk_err(pblk, "could not allocate GC main kthread\n"); - return PTR_ERR(gc->gc_ts); - } - - gc->gc_writer_ts = kthread_create(pblk_gc_writer_ts, pblk, - "pblk-gc-writer-ts"); - if (IS_ERR(gc->gc_writer_ts)) { - pblk_err(pblk, "could not allocate GC writer kthread\n"); - ret = PTR_ERR(gc->gc_writer_ts); - goto fail_free_main_kthread; - } - - gc->gc_reader_ts = kthread_create(pblk_gc_reader_ts, pblk, - "pblk-gc-reader-ts"); - if (IS_ERR(gc->gc_reader_ts)) { - pblk_err(pblk, "could not allocate GC reader kthread\n"); - ret = PTR_ERR(gc->gc_reader_ts); - goto fail_free_writer_kthread; - } - - timer_setup(&gc->gc_timer, pblk_gc_timer, 0); - mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS)); - - gc->gc_active = 0; - gc->gc_forced = 0; - gc->gc_enabled = 1; - gc->w_entries = 0; - atomic_set(&gc->read_inflight_gc, 0); - atomic_set(&gc->pipeline_gc, 0); - - /* Workqueue that reads valid sectors from a line and submit them to the - * GC writer to be recycled. - */ - gc->gc_line_reader_wq = alloc_workqueue("pblk-gc-line-reader-wq", - WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_GC_MAX_READERS); - if (!gc->gc_line_reader_wq) { - pblk_err(pblk, "could not allocate GC line reader workqueue\n"); - ret = -ENOMEM; - goto fail_free_reader_kthread; - } - - /* Workqueue that prepare lines for GC */ - gc->gc_reader_wq = alloc_workqueue("pblk-gc-line_wq", - WQ_MEM_RECLAIM | WQ_UNBOUND, 1); - if (!gc->gc_reader_wq) { - pblk_err(pblk, "could not allocate GC reader workqueue\n"); - ret = -ENOMEM; - goto fail_free_reader_line_wq; - } - - spin_lock_init(&gc->lock); - spin_lock_init(&gc->w_lock); - spin_lock_init(&gc->r_lock); - - sema_init(&gc->gc_sem, PBLK_GC_RQ_QD); - - INIT_LIST_HEAD(&gc->w_list); - INIT_LIST_HEAD(&gc->r_list); - - return 0; - -fail_free_reader_line_wq: - destroy_workqueue(gc->gc_line_reader_wq); -fail_free_reader_kthread: - kthread_stop(gc->gc_reader_ts); -fail_free_writer_kthread: - kthread_stop(gc->gc_writer_ts); -fail_free_main_kthread: - kthread_stop(gc->gc_ts); - - return ret; -} - -void pblk_gc_exit(struct pblk *pblk, bool graceful) -{ - struct pblk_gc *gc = &pblk->gc; - - gc->gc_enabled = 0; - del_timer_sync(&gc->gc_timer); - gc->gc_active = 0; - - if (gc->gc_ts) - kthread_stop(gc->gc_ts); - - if (gc->gc_reader_ts) - kthread_stop(gc->gc_reader_ts); - - if (graceful) { - flush_workqueue(gc->gc_reader_wq); - flush_workqueue(gc->gc_line_reader_wq); - } - - destroy_workqueue(gc->gc_reader_wq); - destroy_workqueue(gc->gc_line_reader_wq); - - if (gc->gc_writer_ts) - kthread_stop(gc->gc_writer_ts); -} diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c deleted file mode 100644 index 5924f09c217b..000000000000 --- a/drivers/lightnvm/pblk-init.c +++ /dev/null @@ -1,1324 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2015 IT University of Copenhagen (rrpc.c) - * Copyright (C) 2016 CNEX Labs - * Initial release: Javier Gonzalez - * Matias Bjorling - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * Implementation of a physical block-device target for Open-channel SSDs. - * - * pblk-init.c - pblk's initialization. - */ - -#include "pblk.h" -#include "pblk-trace.h" - -static unsigned int write_buffer_size; - -module_param(write_buffer_size, uint, 0644); -MODULE_PARM_DESC(write_buffer_size, "number of entries in a write buffer"); - -struct pblk_global_caches { - struct kmem_cache *ws; - struct kmem_cache *rec; - struct kmem_cache *g_rq; - struct kmem_cache *w_rq; - - struct kref kref; - - struct mutex mutex; /* Ensures consistency between - * caches and kref - */ -}; - -static struct pblk_global_caches pblk_caches = { - .mutex = __MUTEX_INITIALIZER(pblk_caches.mutex), - .kref = KREF_INIT(0), -}; - -struct bio_set pblk_bio_set; - -static blk_qc_t pblk_submit_bio(struct bio *bio) -{ - struct pblk *pblk = bio->bi_bdev->bd_disk->queue->queuedata; - - if (bio_op(bio) == REQ_OP_DISCARD) { - pblk_discard(pblk, bio); - if (!(bio->bi_opf & REQ_PREFLUSH)) { - bio_endio(bio); - return BLK_QC_T_NONE; - } - } - - /* Read requests must be <= 256kb due to NVMe's 64 bit completion bitmap - * constraint. Writes can be of arbitrary size. - */ - if (bio_data_dir(bio) == READ) { - blk_queue_split(&bio); - pblk_submit_read(pblk, bio); - } else { - /* Prevent deadlock in the case of a modest LUN configuration - * and large user I/Os. Unless stalled, the rate limiter - * leaves at least 256KB available for user I/O. - */ - if (pblk_get_secs(bio) > pblk_rl_max_io(&pblk->rl)) - blk_queue_split(&bio); - - pblk_write_to_cache(pblk, bio, PBLK_IOTYPE_USER); - } - - return BLK_QC_T_NONE; -} - -static const struct block_device_operations pblk_bops = { - .owner = THIS_MODULE, - .submit_bio = pblk_submit_bio, -}; - - -static size_t pblk_trans_map_size(struct pblk *pblk) -{ - int entry_size = 8; - - if (pblk->addrf_len < 32) - entry_size = 4; - - return entry_size * pblk->capacity; -} - -#ifdef CONFIG_NVM_PBLK_DEBUG -static u32 pblk_l2p_crc(struct pblk *pblk) -{ - size_t map_size; - u32 crc = ~(u32)0; - - map_size = pblk_trans_map_size(pblk); - crc = crc32_le(crc, pblk->trans_map, map_size); - return crc; -} -#endif - -static void pblk_l2p_free(struct pblk *pblk) -{ - vfree(pblk->trans_map); -} - -static int pblk_l2p_recover(struct pblk *pblk, bool factory_init) -{ - struct pblk_line *line = NULL; - - if (factory_init) { - guid_gen(&pblk->instance_uuid); - } else { - line = pblk_recov_l2p(pblk); - if (IS_ERR(line)) { - pblk_err(pblk, "could not recover l2p table\n"); - return -EFAULT; - } - } - -#ifdef CONFIG_NVM_PBLK_DEBUG - pblk_info(pblk, "init: L2P CRC: %x\n", pblk_l2p_crc(pblk)); -#endif - - /* Free full lines directly as GC has not been started yet */ - pblk_gc_free_full_lines(pblk); - - if (!line) { - /* Configure next line for user data */ - line = pblk_line_get_first_data(pblk); - if (!line) - return -EFAULT; - } - - return 0; -} - -static int pblk_l2p_init(struct pblk *pblk, bool factory_init) -{ - sector_t i; - struct ppa_addr ppa; - size_t map_size; - int ret = 0; - - map_size = pblk_trans_map_size(pblk); - pblk->trans_map = __vmalloc(map_size, GFP_KERNEL | __GFP_NOWARN | - __GFP_RETRY_MAYFAIL | __GFP_HIGHMEM); - if (!pblk->trans_map) { - pblk_err(pblk, "failed to allocate L2P (need %zu of memory)\n", - map_size); - return -ENOMEM; - } - - pblk_ppa_set_empty(&ppa); - - for (i = 0; i < pblk->capacity; i++) - pblk_trans_map_set(pblk, i, ppa); - - ret = pblk_l2p_recover(pblk, factory_init); - if (ret) - vfree(pblk->trans_map); - - return ret; -} - -static void pblk_rwb_free(struct pblk *pblk) -{ - if (pblk_rb_tear_down_check(&pblk->rwb)) - pblk_err(pblk, "write buffer error on tear down\n"); - - pblk_rb_free(&pblk->rwb); -} - -static int pblk_rwb_init(struct pblk *pblk) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - unsigned long buffer_size; - int pgs_in_buffer, threshold; - - threshold = geo->mw_cunits * geo->all_luns; - pgs_in_buffer = (max(geo->mw_cunits, geo->ws_opt) + geo->ws_opt) - * geo->all_luns; - - if (write_buffer_size && (write_buffer_size > pgs_in_buffer)) - buffer_size = write_buffer_size; - else - buffer_size = pgs_in_buffer; - - return pblk_rb_init(&pblk->rwb, buffer_size, threshold, geo->csecs); -} - -static int pblk_set_addrf_12(struct pblk *pblk, struct nvm_geo *geo, - struct nvm_addrf_12 *dst) -{ - struct nvm_addrf_12 *src = (struct nvm_addrf_12 *)&geo->addrf; - int power_len; - - /* Re-calculate channel and lun format to adapt to configuration */ - power_len = get_count_order(geo->num_ch); - if (1 << power_len != geo->num_ch) { - pblk_err(pblk, "supports only power-of-two channel config.\n"); - return -EINVAL; - } - dst->ch_len = power_len; - - power_len = get_count_order(geo->num_lun); - if (1 << power_len != geo->num_lun) { - pblk_err(pblk, "supports only power-of-two LUN config.\n"); - return -EINVAL; - } - dst->lun_len = power_len; - - dst->blk_len = src->blk_len; - dst->pg_len = src->pg_len; - dst->pln_len = src->pln_len; - dst->sec_len = src->sec_len; - - dst->sec_offset = 0; - dst->pln_offset = dst->sec_len; - dst->ch_offset = dst->pln_offset + dst->pln_len; - dst->lun_offset = dst->ch_offset + dst->ch_len; - dst->pg_offset = dst->lun_offset + dst->lun_len; - dst->blk_offset = dst->pg_offset + dst->pg_len; - - dst->sec_mask = ((1ULL << dst->sec_len) - 1) << dst->sec_offset; - dst->pln_mask = ((1ULL << dst->pln_len) - 1) << dst->pln_offset; - dst->ch_mask = ((1ULL << dst->ch_len) - 1) << dst->ch_offset; - dst->lun_mask = ((1ULL << dst->lun_len) - 1) << dst->lun_offset; - dst->pg_mask = ((1ULL << dst->pg_len) - 1) << dst->pg_offset; - dst->blk_mask = ((1ULL << dst->blk_len) - 1) << dst->blk_offset; - - return dst->blk_offset + src->blk_len; -} - -static int pblk_set_addrf_20(struct nvm_geo *geo, struct nvm_addrf *adst, - struct pblk_addrf *udst) -{ - struct nvm_addrf *src = &geo->addrf; - - adst->ch_len = get_count_order(geo->num_ch); - adst->lun_len = get_count_order(geo->num_lun); - adst->chk_len = src->chk_len; - adst->sec_len = src->sec_len; - - adst->sec_offset = 0; - adst->ch_offset = adst->sec_len; - adst->lun_offset = adst->ch_offset + adst->ch_len; - adst->chk_offset = adst->lun_offset + adst->lun_len; - - adst->sec_mask = ((1ULL << adst->sec_len) - 1) << adst->sec_offset; - adst->chk_mask = ((1ULL << adst->chk_len) - 1) << adst->chk_offset; - adst->lun_mask = ((1ULL << adst->lun_len) - 1) << adst->lun_offset; - adst->ch_mask = ((1ULL << adst->ch_len) - 1) << adst->ch_offset; - - udst->sec_stripe = geo->ws_opt; - udst->ch_stripe = geo->num_ch; - udst->lun_stripe = geo->num_lun; - - udst->sec_lun_stripe = udst->sec_stripe * udst->ch_stripe; - udst->sec_ws_stripe = udst->sec_lun_stripe * udst->lun_stripe; - - return adst->chk_offset + adst->chk_len; -} - -static int pblk_set_addrf(struct pblk *pblk) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - int mod; - - switch (geo->version) { - case NVM_OCSSD_SPEC_12: - div_u64_rem(geo->clba, pblk->min_write_pgs, &mod); - if (mod) { - pblk_err(pblk, "bad configuration of sectors/pages\n"); - return -EINVAL; - } - - pblk->addrf_len = pblk_set_addrf_12(pblk, geo, - (void *)&pblk->addrf); - break; - case NVM_OCSSD_SPEC_20: - pblk->addrf_len = pblk_set_addrf_20(geo, (void *)&pblk->addrf, - &pblk->uaddrf); - break; - default: - pblk_err(pblk, "OCSSD revision not supported (%d)\n", - geo->version); - return -EINVAL; - } - - return 0; -} - -static int pblk_create_global_caches(void) -{ - - pblk_caches.ws = kmem_cache_create("pblk_blk_ws", - sizeof(struct pblk_line_ws), 0, 0, NULL); - if (!pblk_caches.ws) - return -ENOMEM; - - pblk_caches.rec = kmem_cache_create("pblk_rec", - sizeof(struct pblk_rec_ctx), 0, 0, NULL); - if (!pblk_caches.rec) - goto fail_destroy_ws; - - pblk_caches.g_rq = kmem_cache_create("pblk_g_rq", pblk_g_rq_size, - 0, 0, NULL); - if (!pblk_caches.g_rq) - goto fail_destroy_rec; - - pblk_caches.w_rq = kmem_cache_create("pblk_w_rq", pblk_w_rq_size, - 0, 0, NULL); - if (!pblk_caches.w_rq) - goto fail_destroy_g_rq; - - return 0; - -fail_destroy_g_rq: - kmem_cache_destroy(pblk_caches.g_rq); -fail_destroy_rec: - kmem_cache_destroy(pblk_caches.rec); -fail_destroy_ws: - kmem_cache_destroy(pblk_caches.ws); - - return -ENOMEM; -} - -static int pblk_get_global_caches(void) -{ - int ret = 0; - - mutex_lock(&pblk_caches.mutex); - - if (kref_get_unless_zero(&pblk_caches.kref)) - goto out; - - ret = pblk_create_global_caches(); - if (!ret) - kref_init(&pblk_caches.kref); - -out: - mutex_unlock(&pblk_caches.mutex); - return ret; -} - -static void pblk_destroy_global_caches(struct kref *ref) -{ - struct pblk_global_caches *c; - - c = container_of(ref, struct pblk_global_caches, kref); - - kmem_cache_destroy(c->ws); - kmem_cache_destroy(c->rec); - kmem_cache_destroy(c->g_rq); - kmem_cache_destroy(c->w_rq); -} - -static void pblk_put_global_caches(void) -{ - mutex_lock(&pblk_caches.mutex); - kref_put(&pblk_caches.kref, pblk_destroy_global_caches); - mutex_unlock(&pblk_caches.mutex); -} - -static int pblk_core_init(struct pblk *pblk) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - int ret, max_write_ppas; - - atomic64_set(&pblk->user_wa, 0); - atomic64_set(&pblk->pad_wa, 0); - atomic64_set(&pblk->gc_wa, 0); - pblk->user_rst_wa = 0; - pblk->pad_rst_wa = 0; - pblk->gc_rst_wa = 0; - - atomic64_set(&pblk->nr_flush, 0); - pblk->nr_flush_rst = 0; - - pblk->min_write_pgs = geo->ws_opt; - pblk->min_write_pgs_data = pblk->min_write_pgs; - max_write_ppas = pblk->min_write_pgs * geo->all_luns; - pblk->max_write_pgs = min_t(int, max_write_ppas, NVM_MAX_VLBA); - pblk->max_write_pgs = min_t(int, pblk->max_write_pgs, - queue_max_hw_sectors(dev->q) / (geo->csecs >> SECTOR_SHIFT)); - pblk_set_sec_per_write(pblk, pblk->min_write_pgs); - - pblk->oob_meta_size = geo->sos; - if (!pblk_is_oob_meta_supported(pblk)) { - /* For drives which does not have OOB metadata feature - * in order to support recovery feature we need to use - * so called packed metadata. Packed metada will store - * the same information as OOB metadata (l2p table mapping, - * but in the form of the single page at the end of - * every write request. - */ - if (pblk->min_write_pgs - * sizeof(struct pblk_sec_meta) > PAGE_SIZE) { - /* We want to keep all the packed metadata on single - * page per write requests. So we need to ensure that - * it will fit. - * - * This is more like sanity check, since there is - * no device with such a big minimal write size - * (above 1 metabytes). - */ - pblk_err(pblk, "Not supported min write size\n"); - return -EINVAL; - } - /* For packed meta approach we do some simplification. - * On read path we always issue requests which size - * equal to max_write_pgs, with all pages filled with - * user payload except of last one page which will be - * filled with packed metadata. - */ - pblk->max_write_pgs = pblk->min_write_pgs; - pblk->min_write_pgs_data = pblk->min_write_pgs - 1; - } - - pblk->pad_dist = kcalloc(pblk->min_write_pgs - 1, sizeof(atomic64_t), - GFP_KERNEL); - if (!pblk->pad_dist) - return -ENOMEM; - - if (pblk_get_global_caches()) - goto fail_free_pad_dist; - - /* Internal bios can be at most the sectors signaled by the device. */ - ret = mempool_init_page_pool(&pblk->page_bio_pool, NVM_MAX_VLBA, 0); - if (ret) - goto free_global_caches; - - ret = mempool_init_slab_pool(&pblk->gen_ws_pool, PBLK_GEN_WS_POOL_SIZE, - pblk_caches.ws); - if (ret) - goto free_page_bio_pool; - - ret = mempool_init_slab_pool(&pblk->rec_pool, geo->all_luns, - pblk_caches.rec); - if (ret) - goto free_gen_ws_pool; - - ret = mempool_init_slab_pool(&pblk->r_rq_pool, geo->all_luns, - pblk_caches.g_rq); - if (ret) - goto free_rec_pool; - - ret = mempool_init_slab_pool(&pblk->e_rq_pool, geo->all_luns, - pblk_caches.g_rq); - if (ret) - goto free_r_rq_pool; - - ret = mempool_init_slab_pool(&pblk->w_rq_pool, geo->all_luns, - pblk_caches.w_rq); - if (ret) - goto free_e_rq_pool; - - pblk->close_wq = alloc_workqueue("pblk-close-wq", - WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_NR_CLOSE_JOBS); - if (!pblk->close_wq) - goto free_w_rq_pool; - - pblk->bb_wq = alloc_workqueue("pblk-bb-wq", - WQ_MEM_RECLAIM | WQ_UNBOUND, 0); - if (!pblk->bb_wq) - goto free_close_wq; - - pblk->r_end_wq = alloc_workqueue("pblk-read-end-wq", - WQ_MEM_RECLAIM | WQ_UNBOUND, 0); - if (!pblk->r_end_wq) - goto free_bb_wq; - - if (pblk_set_addrf(pblk)) - goto free_r_end_wq; - - INIT_LIST_HEAD(&pblk->compl_list); - INIT_LIST_HEAD(&pblk->resubmit_list); - - return 0; - -free_r_end_wq: - destroy_workqueue(pblk->r_end_wq); -free_bb_wq: - destroy_workqueue(pblk->bb_wq); -free_close_wq: - destroy_workqueue(pblk->close_wq); -free_w_rq_pool: - mempool_exit(&pblk->w_rq_pool); -free_e_rq_pool: - mempool_exit(&pblk->e_rq_pool); -free_r_rq_pool: - mempool_exit(&pblk->r_rq_pool); -free_rec_pool: - mempool_exit(&pblk->rec_pool); -free_gen_ws_pool: - mempool_exit(&pblk->gen_ws_pool); -free_page_bio_pool: - mempool_exit(&pblk->page_bio_pool); -free_global_caches: - pblk_put_global_caches(); -fail_free_pad_dist: - kfree(pblk->pad_dist); - return -ENOMEM; -} - -static void pblk_core_free(struct pblk *pblk) -{ - if (pblk->close_wq) - destroy_workqueue(pblk->close_wq); - - if (pblk->r_end_wq) - destroy_workqueue(pblk->r_end_wq); - - if (pblk->bb_wq) - destroy_workqueue(pblk->bb_wq); - - mempool_exit(&pblk->page_bio_pool); - mempool_exit(&pblk->gen_ws_pool); - mempool_exit(&pblk->rec_pool); - mempool_exit(&pblk->r_rq_pool); - mempool_exit(&pblk->e_rq_pool); - mempool_exit(&pblk->w_rq_pool); - - pblk_put_global_caches(); - kfree(pblk->pad_dist); -} - -static void pblk_line_mg_free(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - int i; - - kfree(l_mg->bb_template); - kfree(l_mg->bb_aux); - kfree(l_mg->vsc_list); - - for (i = 0; i < PBLK_DATA_LINES; i++) { - kfree(l_mg->sline_meta[i]); - kvfree(l_mg->eline_meta[i]->buf); - kfree(l_mg->eline_meta[i]); - } - - mempool_destroy(l_mg->bitmap_pool); - kmem_cache_destroy(l_mg->bitmap_cache); -} - -static void pblk_line_meta_free(struct pblk_line_mgmt *l_mg, - struct pblk_line *line) -{ - struct pblk_w_err_gc *w_err_gc = line->w_err_gc; - - kfree(line->blk_bitmap); - kfree(line->erase_bitmap); - kfree(line->chks); - - kvfree(w_err_gc->lba_list); - kfree(w_err_gc); -} - -static void pblk_lines_free(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line *line; - int i; - - for (i = 0; i < l_mg->nr_lines; i++) { - line = &pblk->lines[i]; - - pblk_line_free(line); - pblk_line_meta_free(l_mg, line); - } - - pblk_line_mg_free(pblk); - - kfree(pblk->luns); - kfree(pblk->lines); -} - -static int pblk_luns_init(struct pblk *pblk) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_lun *rlun; - int i; - - /* TODO: Implement unbalanced LUN support */ - if (geo->num_lun < 0) { - pblk_err(pblk, "unbalanced LUN config.\n"); - return -EINVAL; - } - - pblk->luns = kcalloc(geo->all_luns, sizeof(struct pblk_lun), - GFP_KERNEL); - if (!pblk->luns) - return -ENOMEM; - - for (i = 0; i < geo->all_luns; i++) { - /* Stripe across channels */ - int ch = i % geo->num_ch; - int lun_raw = i / geo->num_ch; - int lunid = lun_raw + ch * geo->num_lun; - - rlun = &pblk->luns[i]; - rlun->bppa = dev->luns[lunid]; - - sema_init(&rlun->wr_sem, 1); - } - - return 0; -} - -/* See comment over struct line_emeta definition */ -static unsigned int calc_emeta_len(struct pblk *pblk) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - - /* Round to sector size so that lba_list starts on its own sector */ - lm->emeta_sec[1] = DIV_ROUND_UP( - sizeof(struct line_emeta) + lm->blk_bitmap_len + - sizeof(struct wa_counters), geo->csecs); - lm->emeta_len[1] = lm->emeta_sec[1] * geo->csecs; - - /* Round to sector size so that vsc_list starts on its own sector */ - lm->dsec_per_line = lm->sec_per_line - lm->emeta_sec[0]; - lm->emeta_sec[2] = DIV_ROUND_UP(lm->dsec_per_line * sizeof(u64), - geo->csecs); - lm->emeta_len[2] = lm->emeta_sec[2] * geo->csecs; - - lm->emeta_sec[3] = DIV_ROUND_UP(l_mg->nr_lines * sizeof(u32), - geo->csecs); - lm->emeta_len[3] = lm->emeta_sec[3] * geo->csecs; - - lm->vsc_list_len = l_mg->nr_lines * sizeof(u32); - - return (lm->emeta_len[1] + lm->emeta_len[2] + lm->emeta_len[3]); -} - -static int pblk_set_provision(struct pblk *pblk, int nr_free_chks) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line_meta *lm = &pblk->lm; - struct nvm_geo *geo = &dev->geo; - sector_t provisioned; - int sec_meta, blk_meta, clba; - int minimum; - - if (geo->op == NVM_TARGET_DEFAULT_OP) - pblk->op = PBLK_DEFAULT_OP; - else - pblk->op = geo->op; - - minimum = pblk_get_min_chks(pblk); - provisioned = nr_free_chks; - provisioned *= (100 - pblk->op); - sector_div(provisioned, 100); - - if ((nr_free_chks - provisioned) < minimum) { - if (geo->op != NVM_TARGET_DEFAULT_OP) { - pblk_err(pblk, "OP too small to create a sane instance\n"); - return -EINTR; - } - - /* If the user did not specify an OP value, and PBLK_DEFAULT_OP - * is not enough, calculate and set sane value - */ - - provisioned = nr_free_chks - minimum; - pblk->op = (100 * minimum) / nr_free_chks; - pblk_info(pblk, "Default OP insufficient, adjusting OP to %d\n", - pblk->op); - } - - pblk->op_blks = nr_free_chks - provisioned; - - /* Internally pblk manages all free blocks, but all calculations based - * on user capacity consider only provisioned blocks - */ - pblk->rl.total_blocks = nr_free_chks; - - /* Consider sectors used for metadata */ - sec_meta = (lm->smeta_sec + lm->emeta_sec[0]) * l_mg->nr_free_lines; - blk_meta = DIV_ROUND_UP(sec_meta, geo->clba); - - clba = (geo->clba / pblk->min_write_pgs) * pblk->min_write_pgs_data; - pblk->capacity = (provisioned - blk_meta) * clba; - - atomic_set(&pblk->rl.free_blocks, nr_free_chks); - atomic_set(&pblk->rl.free_user_blocks, nr_free_chks); - - return 0; -} - -static int pblk_setup_line_meta_chk(struct pblk *pblk, struct pblk_line *line, - struct nvm_chk_meta *meta) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - int i, nr_bad_chks = 0; - - for (i = 0; i < lm->blk_per_line; i++) { - struct pblk_lun *rlun = &pblk->luns[i]; - struct nvm_chk_meta *chunk; - struct nvm_chk_meta *chunk_meta; - struct ppa_addr ppa; - int pos; - - ppa = rlun->bppa; - pos = pblk_ppa_to_pos(geo, ppa); - chunk = &line->chks[pos]; - - ppa.m.chk = line->id; - chunk_meta = pblk_chunk_get_off(pblk, meta, ppa); - - chunk->state = chunk_meta->state; - chunk->type = chunk_meta->type; - chunk->wi = chunk_meta->wi; - chunk->slba = chunk_meta->slba; - chunk->cnlb = chunk_meta->cnlb; - chunk->wp = chunk_meta->wp; - - trace_pblk_chunk_state(pblk_disk_name(pblk), &ppa, - chunk->state); - - if (chunk->type & NVM_CHK_TP_SZ_SPEC) { - WARN_ONCE(1, "pblk: custom-sized chunks unsupported\n"); - continue; - } - - if (!(chunk->state & NVM_CHK_ST_OFFLINE)) - continue; - - set_bit(pos, line->blk_bitmap); - nr_bad_chks++; - } - - return nr_bad_chks; -} - -static long pblk_setup_line_meta(struct pblk *pblk, struct pblk_line *line, - void *chunk_meta, int line_id) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line_meta *lm = &pblk->lm; - long nr_bad_chks, chk_in_line; - - line->pblk = pblk; - line->id = line_id; - line->type = PBLK_LINETYPE_FREE; - line->state = PBLK_LINESTATE_NEW; - line->gc_group = PBLK_LINEGC_NONE; - line->vsc = &l_mg->vsc_list[line_id]; - spin_lock_init(&line->lock); - - nr_bad_chks = pblk_setup_line_meta_chk(pblk, line, chunk_meta); - - chk_in_line = lm->blk_per_line - nr_bad_chks; - if (nr_bad_chks < 0 || nr_bad_chks > lm->blk_per_line || - chk_in_line < lm->min_blk_line) { - line->state = PBLK_LINESTATE_BAD; - list_add_tail(&line->list, &l_mg->bad_list); - return 0; - } - - atomic_set(&line->blk_in_line, chk_in_line); - list_add_tail(&line->list, &l_mg->free_list); - l_mg->nr_free_lines++; - - return chk_in_line; -} - -static int pblk_alloc_line_meta(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - - line->blk_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL); - if (!line->blk_bitmap) - return -ENOMEM; - - line->erase_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL); - if (!line->erase_bitmap) - goto free_blk_bitmap; - - - line->chks = kmalloc_array(lm->blk_per_line, - sizeof(struct nvm_chk_meta), GFP_KERNEL); - if (!line->chks) - goto free_erase_bitmap; - - line->w_err_gc = kzalloc(sizeof(struct pblk_w_err_gc), GFP_KERNEL); - if (!line->w_err_gc) - goto free_chks; - - return 0; - -free_chks: - kfree(line->chks); -free_erase_bitmap: - kfree(line->erase_bitmap); -free_blk_bitmap: - kfree(line->blk_bitmap); - return -ENOMEM; -} - -static int pblk_line_mg_init(struct pblk *pblk) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line_meta *lm = &pblk->lm; - int i, bb_distance; - - l_mg->nr_lines = geo->num_chk; - l_mg->log_line = l_mg->data_line = NULL; - l_mg->l_seq_nr = l_mg->d_seq_nr = 0; - l_mg->nr_free_lines = 0; - bitmap_zero(&l_mg->meta_bitmap, PBLK_DATA_LINES); - - INIT_LIST_HEAD(&l_mg->free_list); - INIT_LIST_HEAD(&l_mg->corrupt_list); - INIT_LIST_HEAD(&l_mg->bad_list); - INIT_LIST_HEAD(&l_mg->gc_full_list); - INIT_LIST_HEAD(&l_mg->gc_high_list); - INIT_LIST_HEAD(&l_mg->gc_mid_list); - INIT_LIST_HEAD(&l_mg->gc_low_list); - INIT_LIST_HEAD(&l_mg->gc_empty_list); - INIT_LIST_HEAD(&l_mg->gc_werr_list); - - INIT_LIST_HEAD(&l_mg->emeta_list); - - l_mg->gc_lists[0] = &l_mg->gc_werr_list; - l_mg->gc_lists[1] = &l_mg->gc_high_list; - l_mg->gc_lists[2] = &l_mg->gc_mid_list; - l_mg->gc_lists[3] = &l_mg->gc_low_list; - - spin_lock_init(&l_mg->free_lock); - spin_lock_init(&l_mg->close_lock); - spin_lock_init(&l_mg->gc_lock); - - l_mg->vsc_list = kcalloc(l_mg->nr_lines, sizeof(__le32), GFP_KERNEL); - if (!l_mg->vsc_list) - goto fail; - - l_mg->bb_template = kzalloc(lm->sec_bitmap_len, GFP_KERNEL); - if (!l_mg->bb_template) - goto fail_free_vsc_list; - - l_mg->bb_aux = kzalloc(lm->sec_bitmap_len, GFP_KERNEL); - if (!l_mg->bb_aux) - goto fail_free_bb_template; - - /* smeta is always small enough to fit on a kmalloc memory allocation, - * emeta depends on the number of LUNs allocated to the pblk instance - */ - for (i = 0; i < PBLK_DATA_LINES; i++) { - l_mg->sline_meta[i] = kmalloc(lm->smeta_len, GFP_KERNEL); - if (!l_mg->sline_meta[i]) - goto fail_free_smeta; - } - - l_mg->bitmap_cache = kmem_cache_create("pblk_lm_bitmap", - lm->sec_bitmap_len, 0, 0, NULL); - if (!l_mg->bitmap_cache) - goto fail_free_smeta; - - /* the bitmap pool is used for both valid and map bitmaps */ - l_mg->bitmap_pool = mempool_create_slab_pool(PBLK_DATA_LINES * 2, - l_mg->bitmap_cache); - if (!l_mg->bitmap_pool) - goto fail_destroy_bitmap_cache; - - /* emeta allocates three different buffers for managing metadata with - * in-memory and in-media layouts - */ - for (i = 0; i < PBLK_DATA_LINES; i++) { - struct pblk_emeta *emeta; - - emeta = kmalloc(sizeof(struct pblk_emeta), GFP_KERNEL); - if (!emeta) - goto fail_free_emeta; - - emeta->buf = kvmalloc(lm->emeta_len[0], GFP_KERNEL); - if (!emeta->buf) { - kfree(emeta); - goto fail_free_emeta; - } - - emeta->nr_entries = lm->emeta_sec[0]; - l_mg->eline_meta[i] = emeta; - } - - for (i = 0; i < l_mg->nr_lines; i++) - l_mg->vsc_list[i] = cpu_to_le32(EMPTY_ENTRY); - - bb_distance = (geo->all_luns) * geo->ws_opt; - for (i = 0; i < lm->sec_per_line; i += bb_distance) - bitmap_set(l_mg->bb_template, i, geo->ws_opt); - - return 0; - -fail_free_emeta: - while (--i >= 0) { - kvfree(l_mg->eline_meta[i]->buf); - kfree(l_mg->eline_meta[i]); - } - - mempool_destroy(l_mg->bitmap_pool); -fail_destroy_bitmap_cache: - kmem_cache_destroy(l_mg->bitmap_cache); -fail_free_smeta: - for (i = 0; i < PBLK_DATA_LINES; i++) - kfree(l_mg->sline_meta[i]); - kfree(l_mg->bb_aux); -fail_free_bb_template: - kfree(l_mg->bb_template); -fail_free_vsc_list: - kfree(l_mg->vsc_list); -fail: - return -ENOMEM; -} - -static int pblk_line_meta_init(struct pblk *pblk) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - unsigned int smeta_len, emeta_len; - int i; - - lm->sec_per_line = geo->clba * geo->all_luns; - lm->blk_per_line = geo->all_luns; - lm->blk_bitmap_len = BITS_TO_LONGS(geo->all_luns) * sizeof(long); - lm->sec_bitmap_len = BITS_TO_LONGS(lm->sec_per_line) * sizeof(long); - lm->lun_bitmap_len = BITS_TO_LONGS(geo->all_luns) * sizeof(long); - lm->mid_thrs = lm->sec_per_line / 2; - lm->high_thrs = lm->sec_per_line / 4; - lm->meta_distance = (geo->all_luns / 2) * pblk->min_write_pgs; - - /* Calculate necessary pages for smeta. See comment over struct - * line_smeta definition - */ - i = 1; -add_smeta_page: - lm->smeta_sec = i * geo->ws_opt; - lm->smeta_len = lm->smeta_sec * geo->csecs; - - smeta_len = sizeof(struct line_smeta) + lm->lun_bitmap_len; - if (smeta_len > lm->smeta_len) { - i++; - goto add_smeta_page; - } - - /* Calculate necessary pages for emeta. See comment over struct - * line_emeta definition - */ - i = 1; -add_emeta_page: - lm->emeta_sec[0] = i * geo->ws_opt; - lm->emeta_len[0] = lm->emeta_sec[0] * geo->csecs; - - emeta_len = calc_emeta_len(pblk); - if (emeta_len > lm->emeta_len[0]) { - i++; - goto add_emeta_page; - } - - lm->emeta_bb = geo->all_luns > i ? geo->all_luns - i : 0; - - lm->min_blk_line = 1; - if (geo->all_luns > 1) - lm->min_blk_line += DIV_ROUND_UP(lm->smeta_sec + - lm->emeta_sec[0], geo->clba); - - if (lm->min_blk_line > lm->blk_per_line) { - pblk_err(pblk, "config. not supported. Min. LUN in line:%d\n", - lm->blk_per_line); - return -EINVAL; - } - - return 0; -} - -static int pblk_lines_init(struct pblk *pblk) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line *line; - void *chunk_meta; - int nr_free_chks = 0; - int i, ret; - - ret = pblk_line_meta_init(pblk); - if (ret) - return ret; - - ret = pblk_line_mg_init(pblk); - if (ret) - return ret; - - ret = pblk_luns_init(pblk); - if (ret) - goto fail_free_meta; - - chunk_meta = pblk_get_chunk_meta(pblk); - if (IS_ERR(chunk_meta)) { - ret = PTR_ERR(chunk_meta); - goto fail_free_luns; - } - - pblk->lines = kcalloc(l_mg->nr_lines, sizeof(struct pblk_line), - GFP_KERNEL); - if (!pblk->lines) { - ret = -ENOMEM; - goto fail_free_chunk_meta; - } - - for (i = 0; i < l_mg->nr_lines; i++) { - line = &pblk->lines[i]; - - ret = pblk_alloc_line_meta(pblk, line); - if (ret) - goto fail_free_lines; - - nr_free_chks += pblk_setup_line_meta(pblk, line, chunk_meta, i); - - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - } - - if (!nr_free_chks) { - pblk_err(pblk, "too many bad blocks prevent for sane instance\n"); - ret = -EINTR; - goto fail_free_lines; - } - - ret = pblk_set_provision(pblk, nr_free_chks); - if (ret) - goto fail_free_lines; - - vfree(chunk_meta); - return 0; - -fail_free_lines: - while (--i >= 0) - pblk_line_meta_free(l_mg, &pblk->lines[i]); - kfree(pblk->lines); -fail_free_chunk_meta: - vfree(chunk_meta); -fail_free_luns: - kfree(pblk->luns); -fail_free_meta: - pblk_line_mg_free(pblk); - - return ret; -} - -static int pblk_writer_init(struct pblk *pblk) -{ - pblk->writer_ts = kthread_create(pblk_write_ts, pblk, "pblk-writer-t"); - if (IS_ERR(pblk->writer_ts)) { - int err = PTR_ERR(pblk->writer_ts); - - if (err != -EINTR) - pblk_err(pblk, "could not allocate writer kthread (%d)\n", - err); - return err; - } - - timer_setup(&pblk->wtimer, pblk_write_timer_fn, 0); - mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(100)); - - return 0; -} - -static void pblk_writer_stop(struct pblk *pblk) -{ - /* The pipeline must be stopped and the write buffer emptied before the - * write thread is stopped - */ - WARN(pblk_rb_read_count(&pblk->rwb), - "Stopping not fully persisted write buffer\n"); - - WARN(pblk_rb_sync_count(&pblk->rwb), - "Stopping not fully synced write buffer\n"); - - del_timer_sync(&pblk->wtimer); - if (pblk->writer_ts) - kthread_stop(pblk->writer_ts); -} - -static void pblk_free(struct pblk *pblk) -{ - pblk_lines_free(pblk); - pblk_l2p_free(pblk); - pblk_rwb_free(pblk); - pblk_core_free(pblk); - - kfree(pblk); -} - -static void pblk_tear_down(struct pblk *pblk, bool graceful) -{ - if (graceful) - __pblk_pipeline_flush(pblk); - __pblk_pipeline_stop(pblk); - pblk_writer_stop(pblk); - pblk_rb_sync_l2p(&pblk->rwb); - pblk_rl_free(&pblk->rl); - - pblk_debug(pblk, "consistent tear down (graceful:%d)\n", graceful); -} - -static void pblk_exit(void *private, bool graceful) -{ - struct pblk *pblk = private; - - pblk_gc_exit(pblk, graceful); - pblk_tear_down(pblk, graceful); - -#ifdef CONFIG_NVM_PBLK_DEBUG - pblk_info(pblk, "exit: L2P CRC: %x\n", pblk_l2p_crc(pblk)); -#endif - - pblk_free(pblk); -} - -static sector_t pblk_capacity(void *private) -{ - struct pblk *pblk = private; - - return pblk->capacity * NR_PHY_IN_LOG; -} - -static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk, - int flags) -{ - struct nvm_geo *geo = &dev->geo; - struct request_queue *bqueue = dev->q; - struct request_queue *tqueue = tdisk->queue; - struct pblk *pblk; - int ret; - - pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL); - if (!pblk) - return ERR_PTR(-ENOMEM); - - pblk->dev = dev; - pblk->disk = tdisk; - pblk->state = PBLK_STATE_RUNNING; - trace_pblk_state(pblk_disk_name(pblk), pblk->state); - pblk->gc.gc_enabled = 0; - - if (!(geo->version == NVM_OCSSD_SPEC_12 || - geo->version == NVM_OCSSD_SPEC_20)) { - pblk_err(pblk, "OCSSD version not supported (%u)\n", - geo->version); - kfree(pblk); - return ERR_PTR(-EINVAL); - } - - if (geo->ext) { - pblk_err(pblk, "extended metadata not supported\n"); - kfree(pblk); - return ERR_PTR(-EINVAL); - } - - spin_lock_init(&pblk->resubmit_lock); - spin_lock_init(&pblk->trans_lock); - spin_lock_init(&pblk->lock); - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_set(&pblk->inflight_writes, 0); - atomic_long_set(&pblk->padded_writes, 0); - atomic_long_set(&pblk->padded_wb, 0); - atomic_long_set(&pblk->req_writes, 0); - atomic_long_set(&pblk->sub_writes, 0); - atomic_long_set(&pblk->sync_writes, 0); - atomic_long_set(&pblk->inflight_reads, 0); - atomic_long_set(&pblk->cache_reads, 0); - atomic_long_set(&pblk->sync_reads, 0); - atomic_long_set(&pblk->recov_writes, 0); - atomic_long_set(&pblk->recov_writes, 0); - atomic_long_set(&pblk->recov_gc_writes, 0); - atomic_long_set(&pblk->recov_gc_reads, 0); -#endif - - atomic_long_set(&pblk->read_failed, 0); - atomic_long_set(&pblk->read_empty, 0); - atomic_long_set(&pblk->read_high_ecc, 0); - atomic_long_set(&pblk->read_failed_gc, 0); - atomic_long_set(&pblk->write_failed, 0); - atomic_long_set(&pblk->erase_failed, 0); - - ret = pblk_core_init(pblk); - if (ret) { - pblk_err(pblk, "could not initialize core\n"); - goto fail; - } - - ret = pblk_lines_init(pblk); - if (ret) { - pblk_err(pblk, "could not initialize lines\n"); - goto fail_free_core; - } - - ret = pblk_rwb_init(pblk); - if (ret) { - pblk_err(pblk, "could not initialize write buffer\n"); - goto fail_free_lines; - } - - ret = pblk_l2p_init(pblk, flags & NVM_TARGET_FACTORY); - if (ret) { - pblk_err(pblk, "could not initialize maps\n"); - goto fail_free_rwb; - } - - ret = pblk_writer_init(pblk); - if (ret) { - if (ret != -EINTR) - pblk_err(pblk, "could not initialize write thread\n"); - goto fail_free_l2p; - } - - ret = pblk_gc_init(pblk); - if (ret) { - pblk_err(pblk, "could not initialize gc\n"); - goto fail_stop_writer; - } - - /* inherit the size from the underlying device */ - blk_queue_logical_block_size(tqueue, queue_physical_block_size(bqueue)); - blk_queue_max_hw_sectors(tqueue, queue_max_hw_sectors(bqueue)); - - blk_queue_write_cache(tqueue, true, false); - - tqueue->limits.discard_granularity = geo->clba * geo->csecs; - tqueue->limits.discard_alignment = 0; - blk_queue_max_discard_sectors(tqueue, UINT_MAX >> 9); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, tqueue); - - pblk_info(pblk, "luns:%u, lines:%d, secs:%llu, buf entries:%u\n", - geo->all_luns, pblk->l_mg.nr_lines, - (unsigned long long)pblk->capacity, - pblk->rwb.nr_entries); - - wake_up_process(pblk->writer_ts); - - /* Check if we need to start GC */ - pblk_gc_should_kick(pblk); - - return pblk; - -fail_stop_writer: - pblk_writer_stop(pblk); -fail_free_l2p: - pblk_l2p_free(pblk); -fail_free_rwb: - pblk_rwb_free(pblk); -fail_free_lines: - pblk_lines_free(pblk); -fail_free_core: - pblk_core_free(pblk); -fail: - kfree(pblk); - return ERR_PTR(ret); -} - -/* physical block device target */ -static struct nvm_tgt_type tt_pblk = { - .name = "pblk", - .version = {1, 0, 0}, - - .bops = &pblk_bops, - .capacity = pblk_capacity, - - .init = pblk_init, - .exit = pblk_exit, - - .sysfs_init = pblk_sysfs_init, - .sysfs_exit = pblk_sysfs_exit, - .owner = THIS_MODULE, -}; - -static int __init pblk_module_init(void) -{ - int ret; - - ret = bioset_init(&pblk_bio_set, BIO_POOL_SIZE, 0, 0); - if (ret) - return ret; - ret = nvm_register_tgt_type(&tt_pblk); - if (ret) - bioset_exit(&pblk_bio_set); - return ret; -} - -static void pblk_module_exit(void) -{ - bioset_exit(&pblk_bio_set); - nvm_unregister_tgt_type(&tt_pblk); -} - -module_init(pblk_module_init); -module_exit(pblk_module_exit); -MODULE_AUTHOR("Javier Gonzalez "); -MODULE_AUTHOR("Matias Bjorling "); -MODULE_LICENSE("GPL v2"); -MODULE_DESCRIPTION("Physical Block-Device for Open-Channel SSDs"); diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c deleted file mode 100644 index 5408e32b2f13..000000000000 --- a/drivers/lightnvm/pblk-map.c +++ /dev/null @@ -1,210 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2016 CNEX Labs - * Initial release: Javier Gonzalez - * Matias Bjorling - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * pblk-map.c - pblk's lba-ppa mapping strategy - * - */ - -#include "pblk.h" - -static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry, - struct ppa_addr *ppa_list, - unsigned long *lun_bitmap, - void *meta_list, - unsigned int valid_secs) -{ - struct pblk_line *line = pblk_line_get_data(pblk); - struct pblk_emeta *emeta; - struct pblk_w_ctx *w_ctx; - __le64 *lba_list; - u64 paddr; - int nr_secs = pblk->min_write_pgs; - int i; - - if (!line) - return -ENOSPC; - - if (pblk_line_is_full(line)) { - struct pblk_line *prev_line = line; - - /* If we cannot allocate a new line, make sure to store metadata - * on current line and then fail - */ - line = pblk_line_replace_data(pblk); - pblk_line_close_meta(pblk, prev_line); - - if (!line) { - pblk_pipeline_stop(pblk); - return -ENOSPC; - } - - } - - emeta = line->emeta; - lba_list = emeta_to_lbas(pblk, emeta->buf); - - paddr = pblk_alloc_page(pblk, line, nr_secs); - - for (i = 0; i < nr_secs; i++, paddr++) { - struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i); - __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); - - /* ppa to be sent to the device */ - ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id); - - /* Write context for target bio completion on write buffer. Note - * that the write buffer is protected by the sync backpointer, - * and a single writer thread have access to each specific entry - * at a time. Thus, it is safe to modify the context for the - * entry we are setting up for submission without taking any - * lock or memory barrier. - */ - if (i < valid_secs) { - kref_get(&line->ref); - atomic_inc(&line->sec_to_update); - w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i); - w_ctx->ppa = ppa_list[i]; - meta->lba = cpu_to_le64(w_ctx->lba); - lba_list[paddr] = cpu_to_le64(w_ctx->lba); - if (lba_list[paddr] != addr_empty) - line->nr_valid_lbas++; - else - atomic64_inc(&pblk->pad_wa); - } else { - lba_list[paddr] = addr_empty; - meta->lba = addr_empty; - __pblk_map_invalidate(pblk, line, paddr); - } - } - - pblk_down_rq(pblk, ppa_list[0], lun_bitmap); - return 0; -} - -int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry, - unsigned long *lun_bitmap, unsigned int valid_secs, - unsigned int off) -{ - void *meta_list = pblk_get_meta_for_writes(pblk, rqd); - void *meta_buffer; - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - unsigned int map_secs; - int min = pblk->min_write_pgs; - int i; - int ret; - - for (i = off; i < rqd->nr_ppas; i += min) { - map_secs = (i + min > valid_secs) ? (valid_secs % min) : min; - meta_buffer = pblk_get_meta(pblk, meta_list, i); - - ret = pblk_map_page_data(pblk, sentry + i, &ppa_list[i], - lun_bitmap, meta_buffer, map_secs); - if (ret) - return ret; - } - - return 0; -} - -/* only if erase_ppa is set, acquire erase semaphore */ -int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd, - unsigned int sentry, unsigned long *lun_bitmap, - unsigned int valid_secs, struct ppa_addr *erase_ppa) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - void *meta_list = pblk_get_meta_for_writes(pblk, rqd); - void *meta_buffer; - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - struct pblk_line *e_line, *d_line; - unsigned int map_secs; - int min = pblk->min_write_pgs; - int i, erase_lun; - int ret; - - - for (i = 0; i < rqd->nr_ppas; i += min) { - map_secs = (i + min > valid_secs) ? (valid_secs % min) : min; - meta_buffer = pblk_get_meta(pblk, meta_list, i); - - ret = pblk_map_page_data(pblk, sentry + i, &ppa_list[i], - lun_bitmap, meta_buffer, map_secs); - if (ret) - return ret; - - erase_lun = pblk_ppa_to_pos(geo, ppa_list[i]); - - /* line can change after page map. We might also be writing the - * last line. - */ - e_line = pblk_line_get_erase(pblk); - if (!e_line) - return pblk_map_rq(pblk, rqd, sentry, lun_bitmap, - valid_secs, i + min); - - spin_lock(&e_line->lock); - if (!test_bit(erase_lun, e_line->erase_bitmap)) { - set_bit(erase_lun, e_line->erase_bitmap); - atomic_dec(&e_line->left_eblks); - - *erase_ppa = ppa_list[i]; - erase_ppa->a.blk = e_line->id; - erase_ppa->a.reserved = 0; - - spin_unlock(&e_line->lock); - - /* Avoid evaluating e_line->left_eblks */ - return pblk_map_rq(pblk, rqd, sentry, lun_bitmap, - valid_secs, i + min); - } - spin_unlock(&e_line->lock); - } - - d_line = pblk_line_get_data(pblk); - - /* line can change after page map. We might also be writing the - * last line. - */ - e_line = pblk_line_get_erase(pblk); - if (!e_line) - return -ENOSPC; - - /* Erase blocks that are bad in this line but might not be in next */ - if (unlikely(pblk_ppa_empty(*erase_ppa)) && - bitmap_weight(d_line->blk_bitmap, lm->blk_per_line)) { - int bit = -1; - -retry: - bit = find_next_bit(d_line->blk_bitmap, - lm->blk_per_line, bit + 1); - if (bit >= lm->blk_per_line) - return 0; - - spin_lock(&e_line->lock); - if (test_bit(bit, e_line->erase_bitmap)) { - spin_unlock(&e_line->lock); - goto retry; - } - spin_unlock(&e_line->lock); - - set_bit(bit, e_line->erase_bitmap); - atomic_dec(&e_line->left_eblks); - *erase_ppa = pblk->luns[bit].bppa; /* set ch and lun */ - erase_ppa->a.blk = e_line->id; - } - - return 0; -} diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c deleted file mode 100644 index 5abb1705b039..000000000000 --- a/drivers/lightnvm/pblk-rb.c +++ /dev/null @@ -1,858 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2016 CNEX Labs - * Initial release: Javier Gonzalez - * - * Based upon the circular ringbuffer. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * pblk-rb.c - pblk's write buffer - */ - -#include - -#include "pblk.h" - -static DECLARE_RWSEM(pblk_rb_lock); - -static void pblk_rb_data_free(struct pblk_rb *rb) -{ - struct pblk_rb_pages *p, *t; - - down_write(&pblk_rb_lock); - list_for_each_entry_safe(p, t, &rb->pages, list) { - free_pages((unsigned long)page_address(p->pages), p->order); - list_del(&p->list); - kfree(p); - } - up_write(&pblk_rb_lock); -} - -void pblk_rb_free(struct pblk_rb *rb) -{ - pblk_rb_data_free(rb); - vfree(rb->entries); -} - -/* - * pblk_rb_calculate_size -- calculate the size of the write buffer - */ -static unsigned int pblk_rb_calculate_size(unsigned int nr_entries, - unsigned int threshold) -{ - unsigned int thr_sz = 1 << (get_count_order(threshold + NVM_MAX_VLBA)); - unsigned int max_sz = max(thr_sz, nr_entries); - unsigned int max_io; - - /* Alloc a write buffer that can (i) fit at least two split bios - * (considering max I/O size NVM_MAX_VLBA, and (ii) guarantee that the - * threshold will be respected - */ - max_io = (1 << max((int)(get_count_order(max_sz)), - (int)(get_count_order(NVM_MAX_VLBA << 1)))); - if ((threshold + NVM_MAX_VLBA) >= max_io) - max_io <<= 1; - - return max_io; -} - -/* - * Initialize ring buffer. The data and metadata buffers must be previously - * allocated and their size must be a power of two - * (Documentation/core-api/circular-buffers.rst) - */ -int pblk_rb_init(struct pblk_rb *rb, unsigned int size, unsigned int threshold, - unsigned int seg_size) -{ - struct pblk *pblk = container_of(rb, struct pblk, rwb); - struct pblk_rb_entry *entries; - unsigned int init_entry = 0; - unsigned int max_order = MAX_ORDER - 1; - unsigned int power_size, power_seg_sz; - unsigned int alloc_order, order, iter; - unsigned int nr_entries; - - nr_entries = pblk_rb_calculate_size(size, threshold); - entries = vzalloc(array_size(nr_entries, sizeof(struct pblk_rb_entry))); - if (!entries) - return -ENOMEM; - - power_size = get_count_order(nr_entries); - power_seg_sz = get_count_order(seg_size); - - down_write(&pblk_rb_lock); - rb->entries = entries; - rb->seg_size = (1 << power_seg_sz); - rb->nr_entries = (1 << power_size); - rb->mem = rb->subm = rb->sync = rb->l2p_update = 0; - rb->back_thres = threshold; - rb->flush_point = EMPTY_ENTRY; - - spin_lock_init(&rb->w_lock); - spin_lock_init(&rb->s_lock); - - INIT_LIST_HEAD(&rb->pages); - - alloc_order = power_size; - if (alloc_order >= max_order) { - order = max_order; - iter = (1 << (alloc_order - max_order)); - } else { - order = alloc_order; - iter = 1; - } - - do { - struct pblk_rb_entry *entry; - struct pblk_rb_pages *page_set; - void *kaddr; - unsigned long set_size; - int i; - - page_set = kmalloc(sizeof(struct pblk_rb_pages), GFP_KERNEL); - if (!page_set) { - up_write(&pblk_rb_lock); - vfree(entries); - return -ENOMEM; - } - - page_set->order = order; - page_set->pages = alloc_pages(GFP_KERNEL, order); - if (!page_set->pages) { - kfree(page_set); - pblk_rb_data_free(rb); - up_write(&pblk_rb_lock); - vfree(entries); - return -ENOMEM; - } - kaddr = page_address(page_set->pages); - - entry = &rb->entries[init_entry]; - entry->data = kaddr; - entry->cacheline = pblk_cacheline_to_addr(init_entry++); - entry->w_ctx.flags = PBLK_WRITABLE_ENTRY; - - set_size = (1 << order); - for (i = 1; i < set_size; i++) { - entry = &rb->entries[init_entry]; - entry->cacheline = pblk_cacheline_to_addr(init_entry++); - entry->data = kaddr + (i * rb->seg_size); - entry->w_ctx.flags = PBLK_WRITABLE_ENTRY; - bio_list_init(&entry->w_ctx.bios); - } - - list_add_tail(&page_set->list, &rb->pages); - iter--; - } while (iter > 0); - up_write(&pblk_rb_lock); - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_set(&rb->inflight_flush_point, 0); -#endif - - /* - * Initialize rate-limiter, which controls access to the write buffer - * by user and GC I/O - */ - pblk_rl_init(&pblk->rl, rb->nr_entries, threshold); - - return 0; -} - -static void clean_wctx(struct pblk_w_ctx *w_ctx) -{ - int flags; - - flags = READ_ONCE(w_ctx->flags); - WARN_ONCE(!(flags & PBLK_SUBMITTED_ENTRY), - "pblk: overwriting unsubmitted data\n"); - - /* Release flags on context. Protect from writes and reads */ - smp_store_release(&w_ctx->flags, PBLK_WRITABLE_ENTRY); - pblk_ppa_set_empty(&w_ctx->ppa); - w_ctx->lba = ADDR_EMPTY; -} - -#define pblk_rb_ring_count(head, tail, size) CIRC_CNT(head, tail, size) -#define pblk_rb_ring_space(rb, head, tail, size) \ - (CIRC_SPACE(head, tail, size)) - -/* - * Buffer space is calculated with respect to the back pointer signaling - * synchronized entries to the media. - */ -static unsigned int pblk_rb_space(struct pblk_rb *rb) -{ - unsigned int mem = READ_ONCE(rb->mem); - unsigned int sync = READ_ONCE(rb->sync); - - return pblk_rb_ring_space(rb, mem, sync, rb->nr_entries); -} - -unsigned int pblk_rb_ptr_wrap(struct pblk_rb *rb, unsigned int p, - unsigned int nr_entries) -{ - return (p + nr_entries) & (rb->nr_entries - 1); -} - -/* - * Buffer count is calculated with respect to the submission entry signaling the - * entries that are available to send to the media - */ -unsigned int pblk_rb_read_count(struct pblk_rb *rb) -{ - unsigned int mem = READ_ONCE(rb->mem); - unsigned int subm = READ_ONCE(rb->subm); - - return pblk_rb_ring_count(mem, subm, rb->nr_entries); -} - -unsigned int pblk_rb_sync_count(struct pblk_rb *rb) -{ - unsigned int mem = READ_ONCE(rb->mem); - unsigned int sync = READ_ONCE(rb->sync); - - return pblk_rb_ring_count(mem, sync, rb->nr_entries); -} - -unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int nr_entries) -{ - unsigned int subm; - - subm = READ_ONCE(rb->subm); - /* Commit read means updating submission pointer */ - smp_store_release(&rb->subm, pblk_rb_ptr_wrap(rb, subm, nr_entries)); - - return subm; -} - -static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int to_update) -{ - struct pblk *pblk = container_of(rb, struct pblk, rwb); - struct pblk_line *line; - struct pblk_rb_entry *entry; - struct pblk_w_ctx *w_ctx; - unsigned int user_io = 0, gc_io = 0; - unsigned int i; - int flags; - - for (i = 0; i < to_update; i++) { - entry = &rb->entries[rb->l2p_update]; - w_ctx = &entry->w_ctx; - - flags = READ_ONCE(entry->w_ctx.flags); - if (flags & PBLK_IOTYPE_USER) - user_io++; - else if (flags & PBLK_IOTYPE_GC) - gc_io++; - else - WARN(1, "pblk: unknown IO type\n"); - - pblk_update_map_dev(pblk, w_ctx->lba, w_ctx->ppa, - entry->cacheline); - - line = pblk_ppa_to_line(pblk, w_ctx->ppa); - atomic_dec(&line->sec_to_update); - kref_put(&line->ref, pblk_line_put); - clean_wctx(w_ctx); - rb->l2p_update = pblk_rb_ptr_wrap(rb, rb->l2p_update, 1); - } - - pblk_rl_out(&pblk->rl, user_io, gc_io); - - return 0; -} - -/* - * When we move the l2p_update pointer, we update the l2p table - lookups will - * point to the physical address instead of to the cacheline in the write buffer - * from this moment on. - */ -static int pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int nr_entries, - unsigned int mem, unsigned int sync) -{ - unsigned int space, count; - int ret = 0; - - lockdep_assert_held(&rb->w_lock); - - /* Update l2p only as buffer entries are being overwritten */ - space = pblk_rb_ring_space(rb, mem, rb->l2p_update, rb->nr_entries); - if (space > nr_entries) - goto out; - - count = nr_entries - space; - /* l2p_update used exclusively under rb->w_lock */ - ret = __pblk_rb_update_l2p(rb, count); - -out: - return ret; -} - -/* - * Update the l2p entry for all sectors stored on the write buffer. This means - * that all future lookups to the l2p table will point to a device address, not - * to the cacheline in the write buffer. - */ -void pblk_rb_sync_l2p(struct pblk_rb *rb) -{ - unsigned int sync; - unsigned int to_update; - - spin_lock(&rb->w_lock); - - /* Protect from reads and writes */ - sync = smp_load_acquire(&rb->sync); - - to_update = pblk_rb_ring_count(sync, rb->l2p_update, rb->nr_entries); - __pblk_rb_update_l2p(rb, to_update); - - spin_unlock(&rb->w_lock); -} - -/* - * Write @nr_entries to ring buffer from @data buffer if there is enough space. - * Typically, 4KB data chunks coming from a bio will be copied to the ring - * buffer, thus the write will fail if not all incoming data can be copied. - * - */ -static void __pblk_rb_write_entry(struct pblk_rb *rb, void *data, - struct pblk_w_ctx w_ctx, - struct pblk_rb_entry *entry) -{ - memcpy(entry->data, data, rb->seg_size); - - entry->w_ctx.lba = w_ctx.lba; - entry->w_ctx.ppa = w_ctx.ppa; -} - -void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data, - struct pblk_w_ctx w_ctx, unsigned int ring_pos) -{ - struct pblk *pblk = container_of(rb, struct pblk, rwb); - struct pblk_rb_entry *entry; - int flags; - - entry = &rb->entries[ring_pos]; - flags = READ_ONCE(entry->w_ctx.flags); -#ifdef CONFIG_NVM_PBLK_DEBUG - /* Caller must guarantee that the entry is free */ - BUG_ON(!(flags & PBLK_WRITABLE_ENTRY)); -#endif - - __pblk_rb_write_entry(rb, data, w_ctx, entry); - - pblk_update_map_cache(pblk, w_ctx.lba, entry->cacheline); - flags = w_ctx.flags | PBLK_WRITTEN_DATA; - - /* Release flags on write context. Protect from writes */ - smp_store_release(&entry->w_ctx.flags, flags); -} - -void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data, - struct pblk_w_ctx w_ctx, struct pblk_line *line, - u64 paddr, unsigned int ring_pos) -{ - struct pblk *pblk = container_of(rb, struct pblk, rwb); - struct pblk_rb_entry *entry; - int flags; - - entry = &rb->entries[ring_pos]; - flags = READ_ONCE(entry->w_ctx.flags); -#ifdef CONFIG_NVM_PBLK_DEBUG - /* Caller must guarantee that the entry is free */ - BUG_ON(!(flags & PBLK_WRITABLE_ENTRY)); -#endif - - __pblk_rb_write_entry(rb, data, w_ctx, entry); - - if (!pblk_update_map_gc(pblk, w_ctx.lba, entry->cacheline, line, paddr)) - entry->w_ctx.lba = ADDR_EMPTY; - - flags = w_ctx.flags | PBLK_WRITTEN_DATA; - - /* Release flags on write context. Protect from writes */ - smp_store_release(&entry->w_ctx.flags, flags); -} - -static int pblk_rb_flush_point_set(struct pblk_rb *rb, struct bio *bio, - unsigned int pos) -{ - struct pblk_rb_entry *entry; - unsigned int sync, flush_point; - - pblk_rb_sync_init(rb, NULL); - sync = READ_ONCE(rb->sync); - - if (pos == sync) { - pblk_rb_sync_end(rb, NULL); - return 0; - } - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_inc(&rb->inflight_flush_point); -#endif - - flush_point = (pos == 0) ? (rb->nr_entries - 1) : (pos - 1); - entry = &rb->entries[flush_point]; - - /* Protect flush points */ - smp_store_release(&rb->flush_point, flush_point); - - if (bio) - bio_list_add(&entry->w_ctx.bios, bio); - - pblk_rb_sync_end(rb, NULL); - - return bio ? 1 : 0; -} - -static int __pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries, - unsigned int *pos) -{ - unsigned int mem; - unsigned int sync; - unsigned int threshold; - - sync = READ_ONCE(rb->sync); - mem = READ_ONCE(rb->mem); - - threshold = nr_entries + rb->back_thres; - - if (pblk_rb_ring_space(rb, mem, sync, rb->nr_entries) < threshold) - return 0; - - if (pblk_rb_update_l2p(rb, nr_entries, mem, sync)) - return 0; - - *pos = mem; - - return 1; -} - -static int pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries, - unsigned int *pos) -{ - if (!__pblk_rb_may_write(rb, nr_entries, pos)) - return 0; - - /* Protect from read count */ - smp_store_release(&rb->mem, pblk_rb_ptr_wrap(rb, *pos, nr_entries)); - return 1; -} - -void pblk_rb_flush(struct pblk_rb *rb) -{ - struct pblk *pblk = container_of(rb, struct pblk, rwb); - unsigned int mem = READ_ONCE(rb->mem); - - if (pblk_rb_flush_point_set(rb, NULL, mem)) - return; - - pblk_write_kick(pblk); -} - -static int pblk_rb_may_write_flush(struct pblk_rb *rb, unsigned int nr_entries, - unsigned int *pos, struct bio *bio, - int *io_ret) -{ - unsigned int mem; - - if (!__pblk_rb_may_write(rb, nr_entries, pos)) - return 0; - - mem = pblk_rb_ptr_wrap(rb, *pos, nr_entries); - *io_ret = NVM_IO_DONE; - - if (bio->bi_opf & REQ_PREFLUSH) { - struct pblk *pblk = container_of(rb, struct pblk, rwb); - - atomic64_inc(&pblk->nr_flush); - if (pblk_rb_flush_point_set(&pblk->rwb, bio, mem)) - *io_ret = NVM_IO_OK; - } - - /* Protect from read count */ - smp_store_release(&rb->mem, mem); - - return 1; -} - -/* - * Atomically check that (i) there is space on the write buffer for the - * incoming I/O, and (ii) the current I/O type has enough budget in the write - * buffer (rate-limiter). - */ -int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio, - unsigned int nr_entries, unsigned int *pos) -{ - struct pblk *pblk = container_of(rb, struct pblk, rwb); - int io_ret; - - spin_lock(&rb->w_lock); - io_ret = pblk_rl_user_may_insert(&pblk->rl, nr_entries); - if (io_ret) { - spin_unlock(&rb->w_lock); - return io_ret; - } - - if (!pblk_rb_may_write_flush(rb, nr_entries, pos, bio, &io_ret)) { - spin_unlock(&rb->w_lock); - return NVM_IO_REQUEUE; - } - - pblk_rl_user_in(&pblk->rl, nr_entries); - spin_unlock(&rb->w_lock); - - return io_ret; -} - -/* - * Look at pblk_rb_may_write_user comment - */ -int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries, - unsigned int *pos) -{ - struct pblk *pblk = container_of(rb, struct pblk, rwb); - - spin_lock(&rb->w_lock); - if (!pblk_rl_gc_may_insert(&pblk->rl, nr_entries)) { - spin_unlock(&rb->w_lock); - return 0; - } - - if (!pblk_rb_may_write(rb, nr_entries, pos)) { - spin_unlock(&rb->w_lock); - return 0; - } - - pblk_rl_gc_in(&pblk->rl, nr_entries); - spin_unlock(&rb->w_lock); - - return 1; -} - -/* - * Read available entries on rb and add them to the given bio. To avoid a memory - * copy, a page reference to the write buffer is used to be added to the bio. - * - * This function is used by the write thread to form the write bio that will - * persist data on the write buffer to the media. - */ -unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd, - unsigned int pos, unsigned int nr_entries, - unsigned int count) -{ - struct pblk *pblk = container_of(rb, struct pblk, rwb); - struct request_queue *q = pblk->dev->q; - struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd); - struct bio *bio = rqd->bio; - struct pblk_rb_entry *entry; - struct page *page; - unsigned int pad = 0, to_read = nr_entries; - unsigned int i; - int flags; - - if (count < nr_entries) { - pad = nr_entries - count; - to_read = count; - } - - /* Add space for packed metadata if in use*/ - pad += (pblk->min_write_pgs - pblk->min_write_pgs_data); - - c_ctx->sentry = pos; - c_ctx->nr_valid = to_read; - c_ctx->nr_padded = pad; - - for (i = 0; i < to_read; i++) { - entry = &rb->entries[pos]; - - /* A write has been allowed into the buffer, but data is still - * being copied to it. It is ok to busy wait. - */ -try: - flags = READ_ONCE(entry->w_ctx.flags); - if (!(flags & PBLK_WRITTEN_DATA)) { - io_schedule(); - goto try; - } - - page = virt_to_page(entry->data); - if (!page) { - pblk_err(pblk, "could not allocate write bio page\n"); - flags &= ~PBLK_WRITTEN_DATA; - flags |= PBLK_SUBMITTED_ENTRY; - /* Release flags on context. Protect from writes */ - smp_store_release(&entry->w_ctx.flags, flags); - return NVM_IO_ERR; - } - - if (bio_add_pc_page(q, bio, page, rb->seg_size, 0) != - rb->seg_size) { - pblk_err(pblk, "could not add page to write bio\n"); - flags &= ~PBLK_WRITTEN_DATA; - flags |= PBLK_SUBMITTED_ENTRY; - /* Release flags on context. Protect from writes */ - smp_store_release(&entry->w_ctx.flags, flags); - return NVM_IO_ERR; - } - - flags &= ~PBLK_WRITTEN_DATA; - flags |= PBLK_SUBMITTED_ENTRY; - - /* Release flags on context. Protect from writes */ - smp_store_release(&entry->w_ctx.flags, flags); - - pos = pblk_rb_ptr_wrap(rb, pos, 1); - } - - if (pad) { - if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, pad)) { - pblk_err(pblk, "could not pad page in write bio\n"); - return NVM_IO_ERR; - } - - if (pad < pblk->min_write_pgs) - atomic64_inc(&pblk->pad_dist[pad - 1]); - else - pblk_warn(pblk, "padding more than min. sectors\n"); - - atomic64_add(pad, &pblk->pad_wa); - } - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_add(pad, &pblk->padded_writes); -#endif - - return NVM_IO_OK; -} - -/* - * Copy to bio only if the lba matches the one on the given cache entry. - * Otherwise, it means that the entry has been overwritten, and the bio should - * be directed to disk. - */ -int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba, - struct ppa_addr ppa) -{ - struct pblk *pblk = container_of(rb, struct pblk, rwb); - struct pblk_rb_entry *entry; - struct pblk_w_ctx *w_ctx; - struct ppa_addr l2p_ppa; - u64 pos = pblk_addr_to_cacheline(ppa); - void *data; - int flags; - int ret = 1; - - -#ifdef CONFIG_NVM_PBLK_DEBUG - /* Caller must ensure that the access will not cause an overflow */ - BUG_ON(pos >= rb->nr_entries); -#endif - entry = &rb->entries[pos]; - w_ctx = &entry->w_ctx; - flags = READ_ONCE(w_ctx->flags); - - spin_lock(&rb->w_lock); - spin_lock(&pblk->trans_lock); - l2p_ppa = pblk_trans_map_get(pblk, lba); - spin_unlock(&pblk->trans_lock); - - /* Check if the entry has been overwritten or is scheduled to be */ - if (!pblk_ppa_comp(l2p_ppa, ppa) || w_ctx->lba != lba || - flags & PBLK_WRITABLE_ENTRY) { - ret = 0; - goto out; - } - data = bio_data(bio); - memcpy(data, entry->data, rb->seg_size); - -out: - spin_unlock(&rb->w_lock); - return ret; -} - -struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos) -{ - unsigned int entry = pblk_rb_ptr_wrap(rb, pos, 0); - - return &rb->entries[entry].w_ctx; -} - -unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags) - __acquires(&rb->s_lock) -{ - if (flags) - spin_lock_irqsave(&rb->s_lock, *flags); - else - spin_lock_irq(&rb->s_lock); - - return rb->sync; -} - -void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags) - __releases(&rb->s_lock) -{ - lockdep_assert_held(&rb->s_lock); - - if (flags) - spin_unlock_irqrestore(&rb->s_lock, *flags); - else - spin_unlock_irq(&rb->s_lock); -} - -unsigned int pblk_rb_sync_advance(struct pblk_rb *rb, unsigned int nr_entries) -{ - unsigned int sync, flush_point; - lockdep_assert_held(&rb->s_lock); - - sync = READ_ONCE(rb->sync); - flush_point = READ_ONCE(rb->flush_point); - - if (flush_point != EMPTY_ENTRY) { - unsigned int secs_to_flush; - - secs_to_flush = pblk_rb_ring_count(flush_point, sync, - rb->nr_entries); - if (secs_to_flush < nr_entries) { - /* Protect flush points */ - smp_store_release(&rb->flush_point, EMPTY_ENTRY); - } - } - - sync = pblk_rb_ptr_wrap(rb, sync, nr_entries); - - /* Protect from counts */ - smp_store_release(&rb->sync, sync); - - return sync; -} - -/* Calculate how many sectors to submit up to the current flush point. */ -unsigned int pblk_rb_flush_point_count(struct pblk_rb *rb) -{ - unsigned int subm, sync, flush_point; - unsigned int submitted, to_flush; - - /* Protect flush points */ - flush_point = smp_load_acquire(&rb->flush_point); - if (flush_point == EMPTY_ENTRY) - return 0; - - /* Protect syncs */ - sync = smp_load_acquire(&rb->sync); - - subm = READ_ONCE(rb->subm); - submitted = pblk_rb_ring_count(subm, sync, rb->nr_entries); - - /* The sync point itself counts as a sector to sync */ - to_flush = pblk_rb_ring_count(flush_point, sync, rb->nr_entries) + 1; - - return (submitted < to_flush) ? (to_flush - submitted) : 0; -} - -int pblk_rb_tear_down_check(struct pblk_rb *rb) -{ - struct pblk_rb_entry *entry; - int i; - int ret = 0; - - spin_lock(&rb->w_lock); - spin_lock_irq(&rb->s_lock); - - if ((rb->mem == rb->subm) && (rb->subm == rb->sync) && - (rb->sync == rb->l2p_update) && - (rb->flush_point == EMPTY_ENTRY)) { - goto out; - } - - if (!rb->entries) { - ret = 1; - goto out; - } - - for (i = 0; i < rb->nr_entries; i++) { - entry = &rb->entries[i]; - - if (!entry->data) { - ret = 1; - goto out; - } - } - -out: - spin_unlock_irq(&rb->s_lock); - spin_unlock(&rb->w_lock); - - return ret; -} - -unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos) -{ - return (pos & (rb->nr_entries - 1)); -} - -int pblk_rb_pos_oob(struct pblk_rb *rb, u64 pos) -{ - return (pos >= rb->nr_entries); -} - -ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf) -{ - struct pblk *pblk = container_of(rb, struct pblk, rwb); - struct pblk_c_ctx *c; - ssize_t offset; - int queued_entries = 0; - - spin_lock_irq(&rb->s_lock); - list_for_each_entry(c, &pblk->compl_list, list) - queued_entries++; - spin_unlock_irq(&rb->s_lock); - - if (rb->flush_point != EMPTY_ENTRY) - offset = scnprintf(buf, PAGE_SIZE, - "%u\t%u\t%u\t%u\t%u\t%u\t%u - %u/%u/%u - %d\n", - rb->nr_entries, - rb->mem, - rb->subm, - rb->sync, - rb->l2p_update, -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_read(&rb->inflight_flush_point), -#else - 0, -#endif - rb->flush_point, - pblk_rb_read_count(rb), - pblk_rb_space(rb), - pblk_rb_flush_point_count(rb), - queued_entries); - else - offset = scnprintf(buf, PAGE_SIZE, - "%u\t%u\t%u\t%u\t%u\t%u\tNULL - %u/%u/%u - %d\n", - rb->nr_entries, - rb->mem, - rb->subm, - rb->sync, - rb->l2p_update, -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_read(&rb->inflight_flush_point), -#else - 0, -#endif - pblk_rb_read_count(rb), - pblk_rb_space(rb), - pblk_rb_flush_point_count(rb), - queued_entries); - - return offset; -} diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c deleted file mode 100644 index c28537a489bc..000000000000 --- a/drivers/lightnvm/pblk-read.c +++ /dev/null @@ -1,474 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2016 CNEX Labs - * Initial release: Javier Gonzalez - * Matias Bjorling - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * pblk-read.c - pblk's read path - */ - -#include "pblk.h" - -/* - * There is no guarantee that the value read from cache has not been updated and - * resides at another location in the cache. We guarantee though that if the - * value is read from the cache, it belongs to the mapped lba. In order to - * guarantee and order between writes and reads are ordered, a flush must be - * issued. - */ -static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio, - sector_t lba, struct ppa_addr ppa) -{ -#ifdef CONFIG_NVM_PBLK_DEBUG - /* Callers must ensure that the ppa points to a cache address */ - BUG_ON(pblk_ppa_empty(ppa)); - BUG_ON(!pblk_addr_in_cache(ppa)); -#endif - - return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba, ppa); -} - -static int pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd, - struct bio *bio, sector_t blba, - bool *from_cache) -{ - void *meta_list = rqd->meta_list; - int nr_secs, i; - -retry: - nr_secs = pblk_lookup_l2p_seq(pblk, rqd->ppa_list, blba, rqd->nr_ppas, - from_cache); - - if (!*from_cache) - goto end; - - for (i = 0; i < nr_secs; i++) { - struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i); - sector_t lba = blba + i; - - if (pblk_ppa_empty(rqd->ppa_list[i])) { - __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); - - meta->lba = addr_empty; - } else if (pblk_addr_in_cache(rqd->ppa_list[i])) { - /* - * Try to read from write buffer. The address is later - * checked on the write buffer to prevent retrieving - * overwritten data. - */ - if (!pblk_read_from_cache(pblk, bio, lba, - rqd->ppa_list[i])) { - if (i == 0) { - /* - * We didn't call with bio_advance() - * yet, so we can just retry. - */ - goto retry; - } else { - /* - * We already call bio_advance() - * so we cannot retry and we need - * to quit that function in order - * to allow caller to handle the bio - * splitting in the current sector - * position. - */ - nr_secs = i; - goto end; - } - } - meta->lba = cpu_to_le64(lba); -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_inc(&pblk->cache_reads); -#endif - } - bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE); - } - -end: - if (pblk_io_aligned(pblk, nr_secs)) - rqd->is_seq = 1; - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_add(nr_secs, &pblk->inflight_reads); -#endif - - return nr_secs; -} - - -static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd, - sector_t blba) -{ - void *meta_list = rqd->meta_list; - int nr_lbas = rqd->nr_ppas; - int i; - - if (!pblk_is_oob_meta_supported(pblk)) - return; - - for (i = 0; i < nr_lbas; i++) { - struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i); - u64 lba = le64_to_cpu(meta->lba); - - if (lba == ADDR_EMPTY) - continue; - - if (lba != blba + i) { -#ifdef CONFIG_NVM_PBLK_DEBUG - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - - print_ppa(pblk, &ppa_list[i], "seq", i); -#endif - pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n", - lba, (u64)blba + i); - WARN_ON(1); - } - } -} - -/* - * There can be holes in the lba list. - */ -static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd, - u64 *lba_list, int nr_lbas) -{ - void *meta_lba_list = rqd->meta_list; - int i, j; - - if (!pblk_is_oob_meta_supported(pblk)) - return; - - for (i = 0, j = 0; i < nr_lbas; i++) { - struct pblk_sec_meta *meta = pblk_get_meta(pblk, - meta_lba_list, j); - u64 lba = lba_list[i]; - u64 meta_lba; - - if (lba == ADDR_EMPTY) - continue; - - meta_lba = le64_to_cpu(meta->lba); - - if (lba != meta_lba) { -#ifdef CONFIG_NVM_PBLK_DEBUG - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - - print_ppa(pblk, &ppa_list[j], "rnd", j); -#endif - pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n", - meta_lba, lba); - WARN_ON(1); - } - - j++; - } - - WARN_ONCE(j != rqd->nr_ppas, "pblk: corrupted random request\n"); -} - -static void pblk_end_user_read(struct bio *bio, int error) -{ - if (error && error != NVM_RSP_WARN_HIGHECC) - bio_io_error(bio); - else - bio_endio(bio); -} - -static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd, - bool put_line) -{ - struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd); - struct bio *int_bio = rqd->bio; - unsigned long start_time = r_ctx->start_time; - - bio_end_io_acct(int_bio, start_time); - - if (rqd->error) - pblk_log_read_err(pblk, rqd); - - pblk_read_check_seq(pblk, rqd, r_ctx->lba); - bio_put(int_bio); - - if (put_line) - pblk_rq_to_line_put(pblk, rqd); - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_add(rqd->nr_ppas, &pblk->sync_reads); - atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads); -#endif - - pblk_free_rqd(pblk, rqd, PBLK_READ); - atomic_dec(&pblk->inflight_io); -} - -static void pblk_end_io_read(struct nvm_rq *rqd) -{ - struct pblk *pblk = rqd->private; - struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd); - struct bio *bio = (struct bio *)r_ctx->private; - - pblk_end_user_read(bio, rqd->error); - __pblk_end_io_read(pblk, rqd, true); -} - -static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio, - sector_t lba, bool *from_cache) -{ - struct pblk_sec_meta *meta = pblk_get_meta(pblk, rqd->meta_list, 0); - struct ppa_addr ppa; - - pblk_lookup_l2p_seq(pblk, &ppa, lba, 1, from_cache); - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_inc(&pblk->inflight_reads); -#endif - -retry: - if (pblk_ppa_empty(ppa)) { - __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); - - meta->lba = addr_empty; - return; - } - - /* Try to read from write buffer. The address is later checked on the - * write buffer to prevent retrieving overwritten data. - */ - if (pblk_addr_in_cache(ppa)) { - if (!pblk_read_from_cache(pblk, bio, lba, ppa)) { - pblk_lookup_l2p_seq(pblk, &ppa, lba, 1, from_cache); - goto retry; - } - - meta->lba = cpu_to_le64(lba); - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_inc(&pblk->cache_reads); -#endif - } else { - rqd->ppa_addr = ppa; - } -} - -void pblk_submit_read(struct pblk *pblk, struct bio *bio) -{ - sector_t blba = pblk_get_lba(bio); - unsigned int nr_secs = pblk_get_secs(bio); - bool from_cache; - struct pblk_g_ctx *r_ctx; - struct nvm_rq *rqd; - struct bio *int_bio, *split_bio; - unsigned long start_time; - - start_time = bio_start_io_acct(bio); - - rqd = pblk_alloc_rqd(pblk, PBLK_READ); - - rqd->opcode = NVM_OP_PREAD; - rqd->nr_ppas = nr_secs; - rqd->private = pblk; - rqd->end_io = pblk_end_io_read; - - r_ctx = nvm_rq_to_pdu(rqd); - r_ctx->start_time = start_time; - r_ctx->lba = blba; - - if (pblk_alloc_rqd_meta(pblk, rqd)) { - bio_io_error(bio); - pblk_free_rqd(pblk, rqd, PBLK_READ); - return; - } - - /* Clone read bio to deal internally with: - * -read errors when reading from drive - * -bio_advance() calls during cache reads - */ - int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set); - - if (nr_secs > 1) - nr_secs = pblk_read_ppalist_rq(pblk, rqd, int_bio, blba, - &from_cache); - else - pblk_read_rq(pblk, rqd, int_bio, blba, &from_cache); - -split_retry: - r_ctx->private = bio; /* original bio */ - rqd->bio = int_bio; /* internal bio */ - - if (from_cache && nr_secs == rqd->nr_ppas) { - /* All data was read from cache, we can complete the IO. */ - pblk_end_user_read(bio, 0); - atomic_inc(&pblk->inflight_io); - __pblk_end_io_read(pblk, rqd, false); - } else if (nr_secs != rqd->nr_ppas) { - /* The read bio request could be partially filled by the write - * buffer, but there are some holes that need to be read from - * the drive. In order to handle this, we will use block layer - * mechanism to split this request in to smaller ones and make - * a chain of it. - */ - split_bio = bio_split(bio, nr_secs * NR_PHY_IN_LOG, GFP_KERNEL, - &pblk_bio_set); - bio_chain(split_bio, bio); - submit_bio_noacct(bio); - - /* New bio contains first N sectors of the previous one, so - * we can continue to use existing rqd, but we need to shrink - * the number of PPAs in it. New bio is also guaranteed that - * it contains only either data from cache or from drive, newer - * mix of them. - */ - bio = split_bio; - rqd->nr_ppas = nr_secs; - if (rqd->nr_ppas == 1) - rqd->ppa_addr = rqd->ppa_list[0]; - - /* Recreate int_bio - existing might have some needed internal - * fields modified already. - */ - bio_put(int_bio); - int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set); - goto split_retry; - } else if (pblk_submit_io(pblk, rqd, NULL)) { - /* Submitting IO to drive failed, let's report an error */ - rqd->error = -ENODEV; - pblk_end_io_read(rqd); - } -} - -static int read_ppalist_rq_gc(struct pblk *pblk, struct nvm_rq *rqd, - struct pblk_line *line, u64 *lba_list, - u64 *paddr_list_gc, unsigned int nr_secs) -{ - struct ppa_addr ppa_list_l2p[NVM_MAX_VLBA]; - struct ppa_addr ppa_gc; - int valid_secs = 0; - int i; - - pblk_lookup_l2p_rand(pblk, ppa_list_l2p, lba_list, nr_secs); - - for (i = 0; i < nr_secs; i++) { - if (lba_list[i] == ADDR_EMPTY) - continue; - - ppa_gc = addr_to_gen_ppa(pblk, paddr_list_gc[i], line->id); - if (!pblk_ppa_comp(ppa_list_l2p[i], ppa_gc)) { - paddr_list_gc[i] = lba_list[i] = ADDR_EMPTY; - continue; - } - - rqd->ppa_list[valid_secs++] = ppa_list_l2p[i]; - } - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_add(valid_secs, &pblk->inflight_reads); -#endif - - return valid_secs; -} - -static int read_rq_gc(struct pblk *pblk, struct nvm_rq *rqd, - struct pblk_line *line, sector_t lba, - u64 paddr_gc) -{ - struct ppa_addr ppa_l2p, ppa_gc; - int valid_secs = 0; - - if (lba == ADDR_EMPTY) - goto out; - - /* logic error: lba out-of-bounds */ - if (lba >= pblk->capacity) { - WARN(1, "pblk: read lba out of bounds\n"); - goto out; - } - - spin_lock(&pblk->trans_lock); - ppa_l2p = pblk_trans_map_get(pblk, lba); - spin_unlock(&pblk->trans_lock); - - ppa_gc = addr_to_gen_ppa(pblk, paddr_gc, line->id); - if (!pblk_ppa_comp(ppa_l2p, ppa_gc)) - goto out; - - rqd->ppa_addr = ppa_l2p; - valid_secs = 1; - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_inc(&pblk->inflight_reads); -#endif - -out: - return valid_secs; -} - -int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq) -{ - struct nvm_rq rqd; - int ret = NVM_IO_OK; - - memset(&rqd, 0, sizeof(struct nvm_rq)); - - ret = pblk_alloc_rqd_meta(pblk, &rqd); - if (ret) - return ret; - - if (gc_rq->nr_secs > 1) { - gc_rq->secs_to_gc = read_ppalist_rq_gc(pblk, &rqd, gc_rq->line, - gc_rq->lba_list, - gc_rq->paddr_list, - gc_rq->nr_secs); - if (gc_rq->secs_to_gc == 1) - rqd.ppa_addr = rqd.ppa_list[0]; - } else { - gc_rq->secs_to_gc = read_rq_gc(pblk, &rqd, gc_rq->line, - gc_rq->lba_list[0], - gc_rq->paddr_list[0]); - } - - if (!(gc_rq->secs_to_gc)) - goto out; - - rqd.opcode = NVM_OP_PREAD; - rqd.nr_ppas = gc_rq->secs_to_gc; - - if (pblk_submit_io_sync(pblk, &rqd, gc_rq->data)) { - ret = -EIO; - goto err_free_dma; - } - - pblk_read_check_rand(pblk, &rqd, gc_rq->lba_list, gc_rq->nr_secs); - - atomic_dec(&pblk->inflight_io); - - if (rqd.error) { - atomic_long_inc(&pblk->read_failed_gc); -#ifdef CONFIG_NVM_PBLK_DEBUG - pblk_print_failed_rqd(pblk, &rqd, rqd.error); -#endif - } - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_add(gc_rq->secs_to_gc, &pblk->sync_reads); - atomic_long_add(gc_rq->secs_to_gc, &pblk->recov_gc_reads); - atomic_long_sub(gc_rq->secs_to_gc, &pblk->inflight_reads); -#endif - -out: - pblk_free_rqd_meta(pblk, &rqd); - return ret; - -err_free_dma: - pblk_free_rqd_meta(pblk, &rqd); - return ret; -} diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c deleted file mode 100644 index 0e6f0c76e930..000000000000 --- a/drivers/lightnvm/pblk-recovery.c +++ /dev/null @@ -1,874 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2016 CNEX Labs - * Initial: Javier Gonzalez - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * pblk-recovery.c - pblk's recovery path - * - * The L2P recovery path is single threaded as the L2P table is updated in order - * following the line sequence ID. - */ - -#include "pblk.h" -#include "pblk-trace.h" - -int pblk_recov_check_emeta(struct pblk *pblk, struct line_emeta *emeta_buf) -{ - u32 crc; - - crc = pblk_calc_emeta_crc(pblk, emeta_buf); - if (le32_to_cpu(emeta_buf->crc) != crc) - return 1; - - if (le32_to_cpu(emeta_buf->header.identifier) != PBLK_MAGIC) - return 1; - - return 0; -} - -static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_emeta *emeta = line->emeta; - struct line_emeta *emeta_buf = emeta->buf; - __le64 *lba_list; - u64 data_start, data_end; - u64 nr_valid_lbas, nr_lbas = 0; - u64 i; - - lba_list = emeta_to_lbas(pblk, emeta_buf); - if (!lba_list) - return 1; - - data_start = pblk_line_smeta_start(pblk, line) + lm->smeta_sec; - data_end = line->emeta_ssec; - nr_valid_lbas = le64_to_cpu(emeta_buf->nr_valid_lbas); - - for (i = data_start; i < data_end; i++) { - struct ppa_addr ppa; - int pos; - - ppa = addr_to_gen_ppa(pblk, i, line->id); - pos = pblk_ppa_to_pos(geo, ppa); - - /* Do not update bad blocks */ - if (test_bit(pos, line->blk_bitmap)) - continue; - - if (le64_to_cpu(lba_list[i]) == ADDR_EMPTY) { - spin_lock(&line->lock); - if (test_and_set_bit(i, line->invalid_bitmap)) - WARN_ONCE(1, "pblk: rec. double invalidate:\n"); - else - le32_add_cpu(line->vsc, -1); - spin_unlock(&line->lock); - - continue; - } - - pblk_update_map(pblk, le64_to_cpu(lba_list[i]), ppa); - nr_lbas++; - } - - if (nr_valid_lbas != nr_lbas) - pblk_err(pblk, "line %d - inconsistent lba list(%llu/%llu)\n", - line->id, nr_valid_lbas, nr_lbas); - - line->left_msecs = 0; - - return 0; -} - -static void pblk_update_line_wp(struct pblk *pblk, struct pblk_line *line, - u64 written_secs) -{ - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - int i; - - for (i = 0; i < written_secs; i += pblk->min_write_pgs) - __pblk_alloc_page(pblk, line, pblk->min_write_pgs); - - spin_lock(&l_mg->free_lock); - if (written_secs > line->left_msecs) { - /* - * We have all data sectors written - * and some emeta sectors written too. - */ - line->left_msecs = 0; - } else { - /* We have only some data sectors written. */ - line->left_msecs -= written_secs; - } - spin_unlock(&l_mg->free_lock); -} - -static u64 pblk_sec_in_open_line(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - int nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line); - u64 written_secs = 0; - int valid_chunks = 0; - int i; - - for (i = 0; i < lm->blk_per_line; i++) { - struct nvm_chk_meta *chunk = &line->chks[i]; - - if (chunk->state & NVM_CHK_ST_OFFLINE) - continue; - - written_secs += chunk->wp; - valid_chunks++; - } - - if (lm->blk_per_line - nr_bb != valid_chunks) - pblk_err(pblk, "recovery line %d is bad\n", line->id); - - pblk_update_line_wp(pblk, line, written_secs - lm->smeta_sec); - - return written_secs; -} - -struct pblk_recov_alloc { - struct ppa_addr *ppa_list; - void *meta_list; - struct nvm_rq *rqd; - void *data; - dma_addr_t dma_ppa_list; - dma_addr_t dma_meta_list; -}; - -static void pblk_recov_complete(struct kref *ref) -{ - struct pblk_pad_rq *pad_rq = container_of(ref, struct pblk_pad_rq, ref); - - complete(&pad_rq->wait); -} - -static void pblk_end_io_recov(struct nvm_rq *rqd) -{ - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - struct pblk_pad_rq *pad_rq = rqd->private; - struct pblk *pblk = pad_rq->pblk; - - pblk_up_chunk(pblk, ppa_list[0]); - - pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT); - - atomic_dec(&pblk->inflight_io); - kref_put(&pad_rq->ref, pblk_recov_complete); -} - -/* pad line using line bitmap. */ -static int pblk_recov_pad_line(struct pblk *pblk, struct pblk_line *line, - int left_ppas) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - void *meta_list; - struct pblk_pad_rq *pad_rq; - struct nvm_rq *rqd; - struct ppa_addr *ppa_list; - void *data; - __le64 *lba_list = emeta_to_lbas(pblk, line->emeta->buf); - u64 w_ptr = line->cur_sec; - int left_line_ppas, rq_ppas; - int i, j; - int ret = 0; - - spin_lock(&line->lock); - left_line_ppas = line->left_msecs; - spin_unlock(&line->lock); - - pad_rq = kmalloc(sizeof(struct pblk_pad_rq), GFP_KERNEL); - if (!pad_rq) - return -ENOMEM; - - data = vzalloc(array_size(pblk->max_write_pgs, geo->csecs)); - if (!data) { - ret = -ENOMEM; - goto free_rq; - } - - pad_rq->pblk = pblk; - init_completion(&pad_rq->wait); - kref_init(&pad_rq->ref); - -next_pad_rq: - rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false); - if (rq_ppas < pblk->min_write_pgs) { - pblk_err(pblk, "corrupted pad line %d\n", line->id); - goto fail_complete; - } - - rqd = pblk_alloc_rqd(pblk, PBLK_WRITE_INT); - - ret = pblk_alloc_rqd_meta(pblk, rqd); - if (ret) { - pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT); - goto fail_complete; - } - - rqd->bio = NULL; - rqd->opcode = NVM_OP_PWRITE; - rqd->is_seq = 1; - rqd->nr_ppas = rq_ppas; - rqd->end_io = pblk_end_io_recov; - rqd->private = pad_rq; - - ppa_list = nvm_rq_to_ppa_list(rqd); - meta_list = rqd->meta_list; - - for (i = 0; i < rqd->nr_ppas; ) { - struct ppa_addr ppa; - int pos; - - w_ptr = pblk_alloc_page(pblk, line, pblk->min_write_pgs); - ppa = addr_to_gen_ppa(pblk, w_ptr, line->id); - pos = pblk_ppa_to_pos(geo, ppa); - - while (test_bit(pos, line->blk_bitmap)) { - w_ptr += pblk->min_write_pgs; - ppa = addr_to_gen_ppa(pblk, w_ptr, line->id); - pos = pblk_ppa_to_pos(geo, ppa); - } - - for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++) { - struct ppa_addr dev_ppa; - struct pblk_sec_meta *meta; - __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); - - dev_ppa = addr_to_gen_ppa(pblk, w_ptr, line->id); - - pblk_map_invalidate(pblk, dev_ppa); - lba_list[w_ptr] = addr_empty; - meta = pblk_get_meta(pblk, meta_list, i); - meta->lba = addr_empty; - ppa_list[i] = dev_ppa; - } - } - - kref_get(&pad_rq->ref); - pblk_down_chunk(pblk, ppa_list[0]); - - ret = pblk_submit_io(pblk, rqd, data); - if (ret) { - pblk_err(pblk, "I/O submission failed: %d\n", ret); - pblk_up_chunk(pblk, ppa_list[0]); - kref_put(&pad_rq->ref, pblk_recov_complete); - pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT); - goto fail_complete; - } - - left_line_ppas -= rq_ppas; - left_ppas -= rq_ppas; - if (left_ppas && left_line_ppas) - goto next_pad_rq; - -fail_complete: - kref_put(&pad_rq->ref, pblk_recov_complete); - wait_for_completion(&pad_rq->wait); - - if (!pblk_line_is_full(line)) - pblk_err(pblk, "corrupted padded line: %d\n", line->id); - - vfree(data); -free_rq: - kfree(pad_rq); - return ret; -} - -static int pblk_pad_distance(struct pblk *pblk, struct pblk_line *line) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - int distance = geo->mw_cunits * geo->all_luns * geo->ws_opt; - - return (distance > line->left_msecs) ? line->left_msecs : distance; -} - -/* Return a chunk belonging to a line by stripe(write order) index */ -static struct nvm_chk_meta *pblk_get_stripe_chunk(struct pblk *pblk, - struct pblk_line *line, - int index) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_lun *rlun; - struct ppa_addr ppa; - int pos; - - rlun = &pblk->luns[index]; - ppa = rlun->bppa; - pos = pblk_ppa_to_pos(geo, ppa); - - return &line->chks[pos]; -} - -static int pblk_line_wps_are_unbalanced(struct pblk *pblk, - struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - int blk_in_line = lm->blk_per_line; - struct nvm_chk_meta *chunk; - u64 max_wp, min_wp; - int i; - - i = find_first_zero_bit(line->blk_bitmap, blk_in_line); - - /* If there is one or zero good chunks in the line, - * the write pointers can't be unbalanced. - */ - if (i >= (blk_in_line - 1)) - return 0; - - chunk = pblk_get_stripe_chunk(pblk, line, i); - max_wp = chunk->wp; - if (max_wp > pblk->max_write_pgs) - min_wp = max_wp - pblk->max_write_pgs; - else - min_wp = 0; - - i = find_next_zero_bit(line->blk_bitmap, blk_in_line, i + 1); - while (i < blk_in_line) { - chunk = pblk_get_stripe_chunk(pblk, line, i); - if (chunk->wp > max_wp || chunk->wp < min_wp) - return 1; - - i = find_next_zero_bit(line->blk_bitmap, blk_in_line, i + 1); - } - - return 0; -} - -static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line, - struct pblk_recov_alloc p) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct pblk_line_meta *lm = &pblk->lm; - struct nvm_geo *geo = &dev->geo; - struct ppa_addr *ppa_list; - void *meta_list; - struct nvm_rq *rqd; - void *data; - dma_addr_t dma_ppa_list, dma_meta_list; - __le64 *lba_list; - u64 paddr = pblk_line_smeta_start(pblk, line) + lm->smeta_sec; - bool padded = false; - int rq_ppas; - int i, j; - int ret; - u64 left_ppas = pblk_sec_in_open_line(pblk, line) - lm->smeta_sec; - - if (pblk_line_wps_are_unbalanced(pblk, line)) - pblk_warn(pblk, "recovering unbalanced line (%d)\n", line->id); - - ppa_list = p.ppa_list; - meta_list = p.meta_list; - rqd = p.rqd; - data = p.data; - dma_ppa_list = p.dma_ppa_list; - dma_meta_list = p.dma_meta_list; - - lba_list = emeta_to_lbas(pblk, line->emeta->buf); - -next_rq: - memset(rqd, 0, pblk_g_rq_size); - - rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false); - if (!rq_ppas) - rq_ppas = pblk->min_write_pgs; - -retry_rq: - rqd->bio = NULL; - rqd->opcode = NVM_OP_PREAD; - rqd->meta_list = meta_list; - rqd->nr_ppas = rq_ppas; - rqd->ppa_list = ppa_list; - rqd->dma_ppa_list = dma_ppa_list; - rqd->dma_meta_list = dma_meta_list; - ppa_list = nvm_rq_to_ppa_list(rqd); - - if (pblk_io_aligned(pblk, rq_ppas)) - rqd->is_seq = 1; - - for (i = 0; i < rqd->nr_ppas; ) { - struct ppa_addr ppa; - int pos; - - ppa = addr_to_gen_ppa(pblk, paddr, line->id); - pos = pblk_ppa_to_pos(geo, ppa); - - while (test_bit(pos, line->blk_bitmap)) { - paddr += pblk->min_write_pgs; - ppa = addr_to_gen_ppa(pblk, paddr, line->id); - pos = pblk_ppa_to_pos(geo, ppa); - } - - for (j = 0; j < pblk->min_write_pgs; j++, i++) - ppa_list[i] = - addr_to_gen_ppa(pblk, paddr + j, line->id); - } - - ret = pblk_submit_io_sync(pblk, rqd, data); - if (ret) { - pblk_err(pblk, "I/O submission failed: %d\n", ret); - return ret; - } - - atomic_dec(&pblk->inflight_io); - - /* If a read fails, do a best effort by padding the line and retrying */ - if (rqd->error && rqd->error != NVM_RSP_WARN_HIGHECC) { - int pad_distance, ret; - - if (padded) { - pblk_log_read_err(pblk, rqd); - return -EINTR; - } - - pad_distance = pblk_pad_distance(pblk, line); - ret = pblk_recov_pad_line(pblk, line, pad_distance); - if (ret) { - return ret; - } - - padded = true; - goto retry_rq; - } - - pblk_get_packed_meta(pblk, rqd); - - for (i = 0; i < rqd->nr_ppas; i++) { - struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i); - u64 lba = le64_to_cpu(meta->lba); - - lba_list[paddr++] = cpu_to_le64(lba); - - if (lba == ADDR_EMPTY || lba >= pblk->capacity) - continue; - - line->nr_valid_lbas++; - pblk_update_map(pblk, lba, ppa_list[i]); - } - - left_ppas -= rq_ppas; - if (left_ppas > 0) - goto next_rq; - -#ifdef CONFIG_NVM_PBLK_DEBUG - WARN_ON(padded && !pblk_line_is_full(line)); -#endif - - return 0; -} - -/* Scan line for lbas on out of bound area */ -static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct nvm_rq *rqd; - struct ppa_addr *ppa_list; - void *meta_list; - struct pblk_recov_alloc p; - void *data; - dma_addr_t dma_ppa_list, dma_meta_list; - int ret = 0; - - meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list); - if (!meta_list) - return -ENOMEM; - - ppa_list = (void *)(meta_list) + pblk_dma_meta_size(pblk); - dma_ppa_list = dma_meta_list + pblk_dma_meta_size(pblk); - - data = kcalloc(pblk->max_write_pgs, geo->csecs, GFP_KERNEL); - if (!data) { - ret = -ENOMEM; - goto free_meta_list; - } - - rqd = mempool_alloc(&pblk->r_rq_pool, GFP_KERNEL); - memset(rqd, 0, pblk_g_rq_size); - - p.ppa_list = ppa_list; - p.meta_list = meta_list; - p.rqd = rqd; - p.data = data; - p.dma_ppa_list = dma_ppa_list; - p.dma_meta_list = dma_meta_list; - - ret = pblk_recov_scan_oob(pblk, line, p); - if (ret) { - pblk_err(pblk, "could not recover L2P form OOB\n"); - goto out; - } - - if (pblk_line_is_full(line)) - pblk_line_recov_close(pblk, line); - -out: - mempool_free(rqd, &pblk->r_rq_pool); - kfree(data); -free_meta_list: - nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list); - - return ret; -} - -/* Insert lines ordered by sequence number (seq_num) on list */ -static void pblk_recov_line_add_ordered(struct list_head *head, - struct pblk_line *line) -{ - struct pblk_line *t = NULL; - - list_for_each_entry(t, head, list) - if (t->seq_nr > line->seq_nr) - break; - - __list_add(&line->list, t->list.prev, &t->list); -} - -static u64 pblk_line_emeta_start(struct pblk *pblk, struct pblk_line *line) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - unsigned int emeta_secs; - u64 emeta_start; - struct ppa_addr ppa; - int pos; - - emeta_secs = lm->emeta_sec[0]; - emeta_start = lm->sec_per_line; - - while (emeta_secs) { - emeta_start--; - ppa = addr_to_gen_ppa(pblk, emeta_start, line->id); - pos = pblk_ppa_to_pos(geo, ppa); - if (!test_bit(pos, line->blk_bitmap)) - emeta_secs--; - } - - return emeta_start; -} - -static int pblk_recov_check_line_version(struct pblk *pblk, - struct line_emeta *emeta) -{ - struct line_header *header = &emeta->header; - - if (header->version_major != EMETA_VERSION_MAJOR) { - pblk_err(pblk, "line major version mismatch: %d, expected: %d\n", - header->version_major, EMETA_VERSION_MAJOR); - return 1; - } - -#ifdef CONFIG_NVM_PBLK_DEBUG - if (header->version_minor > EMETA_VERSION_MINOR) - pblk_info(pblk, "newer line minor version found: %d\n", - header->version_minor); -#endif - - return 0; -} - -static void pblk_recov_wa_counters(struct pblk *pblk, - struct line_emeta *emeta) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct line_header *header = &emeta->header; - struct wa_counters *wa = emeta_to_wa(lm, emeta); - - /* WA counters were introduced in emeta version 0.2 */ - if (header->version_major > 0 || header->version_minor >= 2) { - u64 user = le64_to_cpu(wa->user); - u64 pad = le64_to_cpu(wa->pad); - u64 gc = le64_to_cpu(wa->gc); - - atomic64_set(&pblk->user_wa, user); - atomic64_set(&pblk->pad_wa, pad); - atomic64_set(&pblk->gc_wa, gc); - - pblk->user_rst_wa = user; - pblk->pad_rst_wa = pad; - pblk->gc_rst_wa = gc; - } -} - -static int pblk_line_was_written(struct pblk_line *line, - struct pblk *pblk) -{ - - struct pblk_line_meta *lm = &pblk->lm; - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct nvm_chk_meta *chunk; - struct ppa_addr bppa; - int smeta_blk; - - if (line->state == PBLK_LINESTATE_BAD) - return 0; - - smeta_blk = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line); - if (smeta_blk >= lm->blk_per_line) - return 0; - - bppa = pblk->luns[smeta_blk].bppa; - chunk = &line->chks[pblk_ppa_to_pos(geo, bppa)]; - - if (chunk->state & NVM_CHK_ST_CLOSED || - (chunk->state & NVM_CHK_ST_OPEN - && chunk->wp >= lm->smeta_sec)) - return 1; - - return 0; -} - -static bool pblk_line_is_open(struct pblk *pblk, struct pblk_line *line) -{ - struct pblk_line_meta *lm = &pblk->lm; - int i; - - for (i = 0; i < lm->blk_per_line; i++) - if (line->chks[i].state & NVM_CHK_ST_OPEN) - return true; - - return false; -} - -struct pblk_line *pblk_recov_l2p(struct pblk *pblk) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line *line, *tline, *data_line = NULL; - struct pblk_smeta *smeta; - struct pblk_emeta *emeta; - struct line_smeta *smeta_buf; - int found_lines = 0, recovered_lines = 0, open_lines = 0; - int is_next = 0; - int meta_line; - int i, valid_uuid = 0; - LIST_HEAD(recov_list); - - /* TODO: Implement FTL snapshot */ - - /* Scan recovery - takes place when FTL snapshot fails */ - spin_lock(&l_mg->free_lock); - meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES); - set_bit(meta_line, &l_mg->meta_bitmap); - smeta = l_mg->sline_meta[meta_line]; - emeta = l_mg->eline_meta[meta_line]; - smeta_buf = (struct line_smeta *)smeta; - spin_unlock(&l_mg->free_lock); - - /* Order data lines using their sequence number */ - for (i = 0; i < l_mg->nr_lines; i++) { - u32 crc; - - line = &pblk->lines[i]; - - memset(smeta, 0, lm->smeta_len); - line->smeta = smeta; - line->lun_bitmap = ((void *)(smeta_buf)) + - sizeof(struct line_smeta); - - if (!pblk_line_was_written(line, pblk)) - continue; - - /* Lines that cannot be read are assumed as not written here */ - if (pblk_line_smeta_read(pblk, line)) - continue; - - crc = pblk_calc_smeta_crc(pblk, smeta_buf); - if (le32_to_cpu(smeta_buf->crc) != crc) - continue; - - if (le32_to_cpu(smeta_buf->header.identifier) != PBLK_MAGIC) - continue; - - if (smeta_buf->header.version_major != SMETA_VERSION_MAJOR) { - pblk_err(pblk, "found incompatible line version %u\n", - smeta_buf->header.version_major); - return ERR_PTR(-EINVAL); - } - - /* The first valid instance uuid is used for initialization */ - if (!valid_uuid) { - import_guid(&pblk->instance_uuid, smeta_buf->header.uuid); - valid_uuid = 1; - } - - if (!guid_equal(&pblk->instance_uuid, - (guid_t *)&smeta_buf->header.uuid)) { - pblk_debug(pblk, "ignore line %u due to uuid mismatch\n", - i); - continue; - } - - /* Update line metadata */ - spin_lock(&line->lock); - line->id = le32_to_cpu(smeta_buf->header.id); - line->type = le16_to_cpu(smeta_buf->header.type); - line->seq_nr = le64_to_cpu(smeta_buf->seq_nr); - spin_unlock(&line->lock); - - /* Update general metadata */ - spin_lock(&l_mg->free_lock); - if (line->seq_nr >= l_mg->d_seq_nr) - l_mg->d_seq_nr = line->seq_nr + 1; - l_mg->nr_free_lines--; - spin_unlock(&l_mg->free_lock); - - if (pblk_line_recov_alloc(pblk, line)) - goto out; - - pblk_recov_line_add_ordered(&recov_list, line); - found_lines++; - pblk_debug(pblk, "recovering data line %d, seq:%llu\n", - line->id, smeta_buf->seq_nr); - } - - if (!found_lines) { - guid_gen(&pblk->instance_uuid); - - spin_lock(&l_mg->free_lock); - WARN_ON_ONCE(!test_and_clear_bit(meta_line, - &l_mg->meta_bitmap)); - spin_unlock(&l_mg->free_lock); - - goto out; - } - - /* Verify closed blocks and recover this portion of L2P table*/ - list_for_each_entry_safe(line, tline, &recov_list, list) { - recovered_lines++; - - line->emeta_ssec = pblk_line_emeta_start(pblk, line); - line->emeta = emeta; - memset(line->emeta->buf, 0, lm->emeta_len[0]); - - if (pblk_line_is_open(pblk, line)) { - pblk_recov_l2p_from_oob(pblk, line); - goto next; - } - - if (pblk_line_emeta_read(pblk, line, line->emeta->buf)) { - pblk_recov_l2p_from_oob(pblk, line); - goto next; - } - - if (pblk_recov_check_emeta(pblk, line->emeta->buf)) { - pblk_recov_l2p_from_oob(pblk, line); - goto next; - } - - if (pblk_recov_check_line_version(pblk, line->emeta->buf)) - return ERR_PTR(-EINVAL); - - pblk_recov_wa_counters(pblk, line->emeta->buf); - - if (pblk_recov_l2p_from_emeta(pblk, line)) - pblk_recov_l2p_from_oob(pblk, line); - -next: - if (pblk_line_is_full(line)) { - struct list_head *move_list; - - spin_lock(&line->lock); - line->state = PBLK_LINESTATE_CLOSED; - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - move_list = pblk_line_gc_list(pblk, line); - spin_unlock(&line->lock); - - spin_lock(&l_mg->gc_lock); - list_move_tail(&line->list, move_list); - spin_unlock(&l_mg->gc_lock); - - mempool_free(line->map_bitmap, l_mg->bitmap_pool); - line->map_bitmap = NULL; - line->smeta = NULL; - line->emeta = NULL; - } else { - spin_lock(&line->lock); - line->state = PBLK_LINESTATE_OPEN; - spin_unlock(&line->lock); - - line->emeta->mem = 0; - atomic_set(&line->emeta->sync, 0); - - trace_pblk_line_state(pblk_disk_name(pblk), line->id, - line->state); - - data_line = line; - line->meta_line = meta_line; - - open_lines++; - } - } - - if (!open_lines) { - spin_lock(&l_mg->free_lock); - WARN_ON_ONCE(!test_and_clear_bit(meta_line, - &l_mg->meta_bitmap)); - spin_unlock(&l_mg->free_lock); - } else { - spin_lock(&l_mg->free_lock); - l_mg->data_line = data_line; - /* Allocate next line for preparation */ - l_mg->data_next = pblk_line_get(pblk); - if (l_mg->data_next) { - l_mg->data_next->seq_nr = l_mg->d_seq_nr++; - l_mg->data_next->type = PBLK_LINETYPE_DATA; - is_next = 1; - } - spin_unlock(&l_mg->free_lock); - } - - if (is_next) - pblk_line_erase(pblk, l_mg->data_next); - -out: - if (found_lines != recovered_lines) - pblk_err(pblk, "failed to recover all found lines %d/%d\n", - found_lines, recovered_lines); - - return data_line; -} - -/* - * Pad current line - */ -int pblk_recov_pad(struct pblk *pblk) -{ - struct pblk_line *line; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - int left_msecs; - int ret = 0; - - spin_lock(&l_mg->free_lock); - line = l_mg->data_line; - left_msecs = line->left_msecs; - spin_unlock(&l_mg->free_lock); - - ret = pblk_recov_pad_line(pblk, line, left_msecs); - if (ret) { - pblk_err(pblk, "tear down padding failed (%d)\n", ret); - return ret; - } - - pblk_line_close_meta(pblk, line); - return ret; -} diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c deleted file mode 100644 index a5f8bc2defbc..000000000000 --- a/drivers/lightnvm/pblk-rl.c +++ /dev/null @@ -1,254 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2016 CNEX Labs - * Initial release: Javier Gonzalez - * Matias Bjorling - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * pblk-rl.c - pblk's rate limiter for user I/O - * - */ - -#include "pblk.h" - -static void pblk_rl_kick_u_timer(struct pblk_rl *rl) -{ - mod_timer(&rl->u_timer, jiffies + msecs_to_jiffies(5000)); -} - -int pblk_rl_is_limit(struct pblk_rl *rl) -{ - int rb_space; - - rb_space = atomic_read(&rl->rb_space); - - return (rb_space == 0); -} - -int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries) -{ - int rb_user_cnt = atomic_read(&rl->rb_user_cnt); - int rb_space = atomic_read(&rl->rb_space); - - if (unlikely(rb_space >= 0) && (rb_space - nr_entries < 0)) - return NVM_IO_ERR; - - if (rb_user_cnt >= rl->rb_user_max) - return NVM_IO_REQUEUE; - - return NVM_IO_OK; -} - -void pblk_rl_inserted(struct pblk_rl *rl, int nr_entries) -{ - int rb_space = atomic_read(&rl->rb_space); - - if (unlikely(rb_space >= 0)) - atomic_sub(nr_entries, &rl->rb_space); -} - -int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries) -{ - int rb_gc_cnt = atomic_read(&rl->rb_gc_cnt); - int rb_user_active; - - /* If there is no user I/O let GC take over space on the write buffer */ - rb_user_active = READ_ONCE(rl->rb_user_active); - return (!(rb_gc_cnt >= rl->rb_gc_max && rb_user_active)); -} - -void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries) -{ - atomic_add(nr_entries, &rl->rb_user_cnt); - - /* Release user I/O state. Protect from GC */ - smp_store_release(&rl->rb_user_active, 1); - pblk_rl_kick_u_timer(rl); -} - -void pblk_rl_werr_line_in(struct pblk_rl *rl) -{ - atomic_inc(&rl->werr_lines); -} - -void pblk_rl_werr_line_out(struct pblk_rl *rl) -{ - atomic_dec(&rl->werr_lines); -} - -void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries) -{ - atomic_add(nr_entries, &rl->rb_gc_cnt); -} - -void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc) -{ - atomic_sub(nr_user, &rl->rb_user_cnt); - atomic_sub(nr_gc, &rl->rb_gc_cnt); -} - -unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl) -{ - return atomic_read(&rl->free_blocks); -} - -unsigned long pblk_rl_nr_user_free_blks(struct pblk_rl *rl) -{ - return atomic_read(&rl->free_user_blocks); -} - -static void __pblk_rl_update_rates(struct pblk_rl *rl, - unsigned long free_blocks) -{ - struct pblk *pblk = container_of(rl, struct pblk, rl); - int max = rl->rb_budget; - int werr_gc_needed = atomic_read(&rl->werr_lines); - - if (free_blocks >= rl->high) { - if (werr_gc_needed) { - /* Allocate a small budget for recovering - * lines with write errors - */ - rl->rb_gc_max = 1 << rl->rb_windows_pw; - rl->rb_user_max = max - rl->rb_gc_max; - rl->rb_state = PBLK_RL_WERR; - } else { - rl->rb_user_max = max; - rl->rb_gc_max = 0; - rl->rb_state = PBLK_RL_OFF; - } - } else if (free_blocks < rl->high) { - int shift = rl->high_pw - rl->rb_windows_pw; - int user_windows = free_blocks >> shift; - int user_max = user_windows << ilog2(NVM_MAX_VLBA); - - rl->rb_user_max = user_max; - rl->rb_gc_max = max - user_max; - - if (free_blocks <= rl->rsv_blocks) { - rl->rb_user_max = 0; - rl->rb_gc_max = max; - } - - /* In the worst case, we will need to GC lines in the low list - * (high valid sector count). If there are lines to GC on high - * or mid lists, these will be prioritized - */ - rl->rb_state = PBLK_RL_LOW; - } - - if (rl->rb_state != PBLK_RL_OFF) - pblk_gc_should_start(pblk); - else - pblk_gc_should_stop(pblk); -} - -void pblk_rl_update_rates(struct pblk_rl *rl) -{ - __pblk_rl_update_rates(rl, pblk_rl_nr_user_free_blks(rl)); -} - -void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line) -{ - int blk_in_line = atomic_read(&line->blk_in_line); - int free_blocks; - - atomic_add(blk_in_line, &rl->free_blocks); - free_blocks = atomic_add_return(blk_in_line, &rl->free_user_blocks); - - __pblk_rl_update_rates(rl, free_blocks); -} - -void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line, - bool used) -{ - int blk_in_line = atomic_read(&line->blk_in_line); - int free_blocks; - - atomic_sub(blk_in_line, &rl->free_blocks); - - if (used) - free_blocks = atomic_sub_return(blk_in_line, - &rl->free_user_blocks); - else - free_blocks = atomic_read(&rl->free_user_blocks); - - __pblk_rl_update_rates(rl, free_blocks); -} - -int pblk_rl_high_thrs(struct pblk_rl *rl) -{ - return rl->high; -} - -int pblk_rl_max_io(struct pblk_rl *rl) -{ - return rl->rb_max_io; -} - -static void pblk_rl_u_timer(struct timer_list *t) -{ - struct pblk_rl *rl = from_timer(rl, t, u_timer); - - /* Release user I/O state. Protect from GC */ - smp_store_release(&rl->rb_user_active, 0); -} - -void pblk_rl_free(struct pblk_rl *rl) -{ - del_timer(&rl->u_timer); -} - -void pblk_rl_init(struct pblk_rl *rl, int budget, int threshold) -{ - struct pblk *pblk = container_of(rl, struct pblk, rl); - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line_meta *lm = &pblk->lm; - int sec_meta, blk_meta; - unsigned int rb_windows; - - /* Consider sectors used for metadata */ - sec_meta = (lm->smeta_sec + lm->emeta_sec[0]) * l_mg->nr_free_lines; - blk_meta = DIV_ROUND_UP(sec_meta, geo->clba); - - rl->high = pblk->op_blks - blk_meta - lm->blk_per_line; - rl->high_pw = get_count_order(rl->high); - - rl->rsv_blocks = pblk_get_min_chks(pblk); - - /* This will always be a power-of-2 */ - rb_windows = budget / NVM_MAX_VLBA; - rl->rb_windows_pw = get_count_order(rb_windows); - - /* To start with, all buffer is available to user I/O writers */ - rl->rb_budget = budget; - rl->rb_user_max = budget; - rl->rb_gc_max = 0; - rl->rb_state = PBLK_RL_HIGH; - - /* Maximize I/O size and ansure that back threshold is respected */ - if (threshold) - rl->rb_max_io = budget - pblk->min_write_pgs_data - threshold; - else - rl->rb_max_io = budget - pblk->min_write_pgs_data - 1; - - atomic_set(&rl->rb_user_cnt, 0); - atomic_set(&rl->rb_gc_cnt, 0); - atomic_set(&rl->rb_space, -1); - atomic_set(&rl->werr_lines, 0); - - timer_setup(&rl->u_timer, pblk_rl_u_timer, 0); - - rl->rb_user_active = 0; - rl->rb_gc_active = 0; -} diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c deleted file mode 100644 index 6387302b03f2..000000000000 --- a/drivers/lightnvm/pblk-sysfs.c +++ /dev/null @@ -1,728 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2016 CNEX Labs - * Initial release: Javier Gonzalez - * Matias Bjorling - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * Implementation of a physical block-device target for Open-channel SSDs. - * - * pblk-sysfs.c - pblk's sysfs - * - */ - -#include "pblk.h" - -static ssize_t pblk_sysfs_luns_show(struct pblk *pblk, char *page) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_lun *rlun; - ssize_t sz = 0; - int i; - - for (i = 0; i < geo->all_luns; i++) { - int active = 1; - - rlun = &pblk->luns[i]; - if (!down_trylock(&rlun->wr_sem)) { - active = 0; - up(&rlun->wr_sem); - } - sz += scnprintf(page + sz, PAGE_SIZE - sz, - "pblk: pos:%d, ch:%d, lun:%d - %d\n", - i, - rlun->bppa.a.ch, - rlun->bppa.a.lun, - active); - } - - return sz; -} - -static ssize_t pblk_sysfs_rate_limiter(struct pblk *pblk, char *page) -{ - int free_blocks, free_user_blocks, total_blocks; - int rb_user_max, rb_user_cnt; - int rb_gc_max, rb_gc_cnt, rb_budget, rb_state; - - free_blocks = pblk_rl_nr_free_blks(&pblk->rl); - free_user_blocks = pblk_rl_nr_user_free_blks(&pblk->rl); - rb_user_max = pblk->rl.rb_user_max; - rb_user_cnt = atomic_read(&pblk->rl.rb_user_cnt); - rb_gc_max = pblk->rl.rb_gc_max; - rb_gc_cnt = atomic_read(&pblk->rl.rb_gc_cnt); - rb_budget = pblk->rl.rb_budget; - rb_state = pblk->rl.rb_state; - - total_blocks = pblk->rl.total_blocks; - - return snprintf(page, PAGE_SIZE, - "u:%u/%u,gc:%u/%u(%u)(stop:<%u,full:>%u,free:%d/%d/%d)-%d\n", - rb_user_cnt, - rb_user_max, - rb_gc_cnt, - rb_gc_max, - rb_state, - rb_budget, - pblk->rl.high, - free_blocks, - free_user_blocks, - total_blocks, - READ_ONCE(pblk->rl.rb_user_active)); -} - -static ssize_t pblk_sysfs_gc_state_show(struct pblk *pblk, char *page) -{ - int gc_enabled, gc_active; - - pblk_gc_sysfs_state_show(pblk, &gc_enabled, &gc_active); - return snprintf(page, PAGE_SIZE, "gc_enabled=%d, gc_active=%d\n", - gc_enabled, gc_active); -} - -static ssize_t pblk_sysfs_stats(struct pblk *pblk, char *page) -{ - ssize_t sz; - - sz = snprintf(page, PAGE_SIZE, - "read_failed=%lu, read_high_ecc=%lu, read_empty=%lu, read_failed_gc=%lu, write_failed=%lu, erase_failed=%lu\n", - atomic_long_read(&pblk->read_failed), - atomic_long_read(&pblk->read_high_ecc), - atomic_long_read(&pblk->read_empty), - atomic_long_read(&pblk->read_failed_gc), - atomic_long_read(&pblk->write_failed), - atomic_long_read(&pblk->erase_failed)); - - return sz; -} - -static ssize_t pblk_sysfs_write_buffer(struct pblk *pblk, char *page) -{ - return pblk_rb_sysfs(&pblk->rwb, page); -} - -static ssize_t pblk_sysfs_ppaf(struct pblk *pblk, char *page) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - ssize_t sz = 0; - - if (geo->version == NVM_OCSSD_SPEC_12) { - struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&pblk->addrf; - struct nvm_addrf_12 *gppaf = (struct nvm_addrf_12 *)&geo->addrf; - - sz = scnprintf(page, PAGE_SIZE, - "g:(b:%d)blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n", - pblk->addrf_len, - ppaf->blk_offset, ppaf->blk_len, - ppaf->pg_offset, ppaf->pg_len, - ppaf->lun_offset, ppaf->lun_len, - ppaf->ch_offset, ppaf->ch_len, - ppaf->pln_offset, ppaf->pln_len, - ppaf->sec_offset, ppaf->sec_len); - - sz += scnprintf(page + sz, PAGE_SIZE - sz, - "d:blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n", - gppaf->blk_offset, gppaf->blk_len, - gppaf->pg_offset, gppaf->pg_len, - gppaf->lun_offset, gppaf->lun_len, - gppaf->ch_offset, gppaf->ch_len, - gppaf->pln_offset, gppaf->pln_len, - gppaf->sec_offset, gppaf->sec_len); - } else { - struct nvm_addrf *ppaf = &pblk->addrf; - struct nvm_addrf *gppaf = &geo->addrf; - - sz = scnprintf(page, PAGE_SIZE, - "pblk:(s:%d)ch:%d/%d,lun:%d/%d,chk:%d/%d/sec:%d/%d\n", - pblk->addrf_len, - ppaf->ch_offset, ppaf->ch_len, - ppaf->lun_offset, ppaf->lun_len, - ppaf->chk_offset, ppaf->chk_len, - ppaf->sec_offset, ppaf->sec_len); - - sz += scnprintf(page + sz, PAGE_SIZE - sz, - "device:ch:%d/%d,lun:%d/%d,chk:%d/%d,sec:%d/%d\n", - gppaf->ch_offset, gppaf->ch_len, - gppaf->lun_offset, gppaf->lun_len, - gppaf->chk_offset, gppaf->chk_len, - gppaf->sec_offset, gppaf->sec_len); - } - - return sz; -} - -static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line *line; - ssize_t sz = 0; - int nr_free_lines; - int cur_data, cur_log; - int free_line_cnt = 0, closed_line_cnt = 0, emeta_line_cnt = 0; - int d_line_cnt = 0, l_line_cnt = 0; - int gc_full = 0, gc_high = 0, gc_mid = 0, gc_low = 0, gc_empty = 0; - int gc_werr = 0; - - int bad = 0, cor = 0; - int msecs = 0, cur_sec = 0, vsc = 0, sec_in_line = 0; - int map_weight = 0, meta_weight = 0; - - spin_lock(&l_mg->free_lock); - cur_data = (l_mg->data_line) ? l_mg->data_line->id : -1; - cur_log = (l_mg->log_line) ? l_mg->log_line->id : -1; - nr_free_lines = l_mg->nr_free_lines; - - list_for_each_entry(line, &l_mg->free_list, list) - free_line_cnt++; - spin_unlock(&l_mg->free_lock); - - spin_lock(&l_mg->close_lock); - list_for_each_entry(line, &l_mg->emeta_list, list) - emeta_line_cnt++; - spin_unlock(&l_mg->close_lock); - - spin_lock(&l_mg->gc_lock); - list_for_each_entry(line, &l_mg->gc_full_list, list) { - if (line->type == PBLK_LINETYPE_DATA) - d_line_cnt++; - else if (line->type == PBLK_LINETYPE_LOG) - l_line_cnt++; - closed_line_cnt++; - gc_full++; - } - - list_for_each_entry(line, &l_mg->gc_high_list, list) { - if (line->type == PBLK_LINETYPE_DATA) - d_line_cnt++; - else if (line->type == PBLK_LINETYPE_LOG) - l_line_cnt++; - closed_line_cnt++; - gc_high++; - } - - list_for_each_entry(line, &l_mg->gc_mid_list, list) { - if (line->type == PBLK_LINETYPE_DATA) - d_line_cnt++; - else if (line->type == PBLK_LINETYPE_LOG) - l_line_cnt++; - closed_line_cnt++; - gc_mid++; - } - - list_for_each_entry(line, &l_mg->gc_low_list, list) { - if (line->type == PBLK_LINETYPE_DATA) - d_line_cnt++; - else if (line->type == PBLK_LINETYPE_LOG) - l_line_cnt++; - closed_line_cnt++; - gc_low++; - } - - list_for_each_entry(line, &l_mg->gc_empty_list, list) { - if (line->type == PBLK_LINETYPE_DATA) - d_line_cnt++; - else if (line->type == PBLK_LINETYPE_LOG) - l_line_cnt++; - closed_line_cnt++; - gc_empty++; - } - - list_for_each_entry(line, &l_mg->gc_werr_list, list) { - if (line->type == PBLK_LINETYPE_DATA) - d_line_cnt++; - else if (line->type == PBLK_LINETYPE_LOG) - l_line_cnt++; - closed_line_cnt++; - gc_werr++; - } - - list_for_each_entry(line, &l_mg->bad_list, list) - bad++; - list_for_each_entry(line, &l_mg->corrupt_list, list) - cor++; - spin_unlock(&l_mg->gc_lock); - - spin_lock(&l_mg->free_lock); - if (l_mg->data_line) { - cur_sec = l_mg->data_line->cur_sec; - msecs = l_mg->data_line->left_msecs; - vsc = le32_to_cpu(*l_mg->data_line->vsc); - sec_in_line = l_mg->data_line->sec_in_line; - meta_weight = bitmap_weight(&l_mg->meta_bitmap, - PBLK_DATA_LINES); - - spin_lock(&l_mg->data_line->lock); - if (l_mg->data_line->map_bitmap) - map_weight = bitmap_weight(l_mg->data_line->map_bitmap, - lm->sec_per_line); - else - map_weight = 0; - spin_unlock(&l_mg->data_line->lock); - } - spin_unlock(&l_mg->free_lock); - - if (nr_free_lines != free_line_cnt) - pblk_err(pblk, "corrupted free line list:%d/%d\n", - nr_free_lines, free_line_cnt); - - sz = scnprintf(page, PAGE_SIZE - sz, - "line: nluns:%d, nblks:%d, nsecs:%d\n", - geo->all_luns, lm->blk_per_line, lm->sec_per_line); - - sz += scnprintf(page + sz, PAGE_SIZE - sz, - "lines:d:%d,l:%d-f:%d,m:%d/%d,c:%d,b:%d,co:%d(d:%d,l:%d)t:%d\n", - cur_data, cur_log, - nr_free_lines, - emeta_line_cnt, meta_weight, - closed_line_cnt, - bad, cor, - d_line_cnt, l_line_cnt, - l_mg->nr_lines); - - sz += scnprintf(page + sz, PAGE_SIZE - sz, - "GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, werr: %d, queue:%d\n", - gc_full, gc_high, gc_mid, gc_low, gc_empty, gc_werr, - atomic_read(&pblk->gc.read_inflight_gc)); - - sz += scnprintf(page + sz, PAGE_SIZE - sz, - "data (%d) cur:%d, left:%d, vsc:%d, s:%d, map:%d/%d (%d)\n", - cur_data, cur_sec, msecs, vsc, sec_in_line, - map_weight, lm->sec_per_line, - atomic_read(&pblk->inflight_io)); - - return sz; -} - -static ssize_t pblk_sysfs_lines_info(struct pblk *pblk, char *page) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; - ssize_t sz = 0; - - sz = scnprintf(page, PAGE_SIZE - sz, - "smeta - len:%d, secs:%d\n", - lm->smeta_len, lm->smeta_sec); - sz += scnprintf(page + sz, PAGE_SIZE - sz, - "emeta - len:%d, sec:%d, bb_start:%d\n", - lm->emeta_len[0], lm->emeta_sec[0], - lm->emeta_bb); - sz += scnprintf(page + sz, PAGE_SIZE - sz, - "bitmap lengths: sec:%d, blk:%d, lun:%d\n", - lm->sec_bitmap_len, - lm->blk_bitmap_len, - lm->lun_bitmap_len); - sz += scnprintf(page + sz, PAGE_SIZE - sz, - "blk_line:%d, sec_line:%d, sec_blk:%d\n", - lm->blk_per_line, - lm->sec_per_line, - geo->clba); - - return sz; -} - -static ssize_t pblk_sysfs_get_sec_per_write(struct pblk *pblk, char *page) -{ - return snprintf(page, PAGE_SIZE, "%d\n", pblk->sec_per_write); -} - -static ssize_t pblk_get_write_amp(u64 user, u64 gc, u64 pad, - char *page) -{ - int sz; - - sz = scnprintf(page, PAGE_SIZE, - "user:%lld gc:%lld pad:%lld WA:", - user, gc, pad); - - if (!user) { - sz += scnprintf(page + sz, PAGE_SIZE - sz, "NaN\n"); - } else { - u64 wa_int; - u32 wa_frac; - - wa_int = (user + gc + pad) * 100000; - wa_int = div64_u64(wa_int, user); - wa_int = div_u64_rem(wa_int, 100000, &wa_frac); - - sz += scnprintf(page + sz, PAGE_SIZE - sz, "%llu.%05u\n", - wa_int, wa_frac); - } - - return sz; -} - -static ssize_t pblk_sysfs_get_write_amp_mileage(struct pblk *pblk, char *page) -{ - return pblk_get_write_amp(atomic64_read(&pblk->user_wa), - atomic64_read(&pblk->gc_wa), atomic64_read(&pblk->pad_wa), - page); -} - -static ssize_t pblk_sysfs_get_write_amp_trip(struct pblk *pblk, char *page) -{ - return pblk_get_write_amp( - atomic64_read(&pblk->user_wa) - pblk->user_rst_wa, - atomic64_read(&pblk->gc_wa) - pblk->gc_rst_wa, - atomic64_read(&pblk->pad_wa) - pblk->pad_rst_wa, page); -} - -static long long bucket_percentage(unsigned long long bucket, - unsigned long long total) -{ - int p = bucket * 100; - - p = div_u64(p, total); - - return p; -} - -static ssize_t pblk_sysfs_get_padding_dist(struct pblk *pblk, char *page) -{ - int sz = 0; - unsigned long long total; - unsigned long long total_buckets = 0; - int buckets = pblk->min_write_pgs - 1; - int i; - - total = atomic64_read(&pblk->nr_flush) - pblk->nr_flush_rst; - if (!total) { - for (i = 0; i < (buckets + 1); i++) - sz += scnprintf(page + sz, PAGE_SIZE - sz, - "%d:0 ", i); - sz += scnprintf(page + sz, PAGE_SIZE - sz, "\n"); - - return sz; - } - - for (i = 0; i < buckets; i++) - total_buckets += atomic64_read(&pblk->pad_dist[i]); - - sz += scnprintf(page + sz, PAGE_SIZE - sz, "0:%lld%% ", - bucket_percentage(total - total_buckets, total)); - - for (i = 0; i < buckets; i++) { - unsigned long long p; - - p = bucket_percentage(atomic64_read(&pblk->pad_dist[i]), - total); - sz += scnprintf(page + sz, PAGE_SIZE - sz, "%d:%lld%% ", - i + 1, p); - } - sz += scnprintf(page + sz, PAGE_SIZE - sz, "\n"); - - return sz; -} - -#ifdef CONFIG_NVM_PBLK_DEBUG -static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page) -{ - return snprintf(page, PAGE_SIZE, - "%lu\t%lu\t%ld\t%llu\t%ld\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\n", - atomic_long_read(&pblk->inflight_writes), - atomic_long_read(&pblk->inflight_reads), - atomic_long_read(&pblk->req_writes), - (u64)atomic64_read(&pblk->nr_flush), - atomic_long_read(&pblk->padded_writes), - atomic_long_read(&pblk->padded_wb), - atomic_long_read(&pblk->sub_writes), - atomic_long_read(&pblk->sync_writes), - atomic_long_read(&pblk->recov_writes), - atomic_long_read(&pblk->recov_gc_writes), - atomic_long_read(&pblk->recov_gc_reads), - atomic_long_read(&pblk->cache_reads), - atomic_long_read(&pblk->sync_reads)); -} -#endif - -static ssize_t pblk_sysfs_gc_force(struct pblk *pblk, const char *page, - size_t len) -{ - size_t c_len; - int force; - - c_len = strcspn(page, "\n"); - if (c_len >= len) - return -EINVAL; - - if (kstrtouint(page, 0, &force)) - return -EINVAL; - - pblk_gc_sysfs_force(pblk, force); - - return len; -} - -static ssize_t pblk_sysfs_set_sec_per_write(struct pblk *pblk, - const char *page, size_t len) -{ - size_t c_len; - int sec_per_write; - - c_len = strcspn(page, "\n"); - if (c_len >= len) - return -EINVAL; - - if (kstrtouint(page, 0, &sec_per_write)) - return -EINVAL; - - if (!pblk_is_oob_meta_supported(pblk)) { - /* For packed metadata case it is - * not allowed to change sec_per_write. - */ - return -EINVAL; - } - - if (sec_per_write < pblk->min_write_pgs - || sec_per_write > pblk->max_write_pgs - || sec_per_write % pblk->min_write_pgs != 0) - return -EINVAL; - - pblk_set_sec_per_write(pblk, sec_per_write); - - return len; -} - -static ssize_t pblk_sysfs_set_write_amp_trip(struct pblk *pblk, - const char *page, size_t len) -{ - size_t c_len; - int reset_value; - - c_len = strcspn(page, "\n"); - if (c_len >= len) - return -EINVAL; - - if (kstrtouint(page, 0, &reset_value)) - return -EINVAL; - - if (reset_value != 0) - return -EINVAL; - - pblk->user_rst_wa = atomic64_read(&pblk->user_wa); - pblk->pad_rst_wa = atomic64_read(&pblk->pad_wa); - pblk->gc_rst_wa = atomic64_read(&pblk->gc_wa); - - return len; -} - - -static ssize_t pblk_sysfs_set_padding_dist(struct pblk *pblk, - const char *page, size_t len) -{ - size_t c_len; - int reset_value; - int buckets = pblk->min_write_pgs - 1; - int i; - - c_len = strcspn(page, "\n"); - if (c_len >= len) - return -EINVAL; - - if (kstrtouint(page, 0, &reset_value)) - return -EINVAL; - - if (reset_value != 0) - return -EINVAL; - - for (i = 0; i < buckets; i++) - atomic64_set(&pblk->pad_dist[i], 0); - - pblk->nr_flush_rst = atomic64_read(&pblk->nr_flush); - - return len; -} - -static struct attribute sys_write_luns = { - .name = "write_luns", - .mode = 0444, -}; - -static struct attribute sys_rate_limiter_attr = { - .name = "rate_limiter", - .mode = 0444, -}; - -static struct attribute sys_gc_state = { - .name = "gc_state", - .mode = 0444, -}; - -static struct attribute sys_errors_attr = { - .name = "errors", - .mode = 0444, -}; - -static struct attribute sys_rb_attr = { - .name = "write_buffer", - .mode = 0444, -}; - -static struct attribute sys_stats_ppaf_attr = { - .name = "ppa_format", - .mode = 0444, -}; - -static struct attribute sys_lines_attr = { - .name = "lines", - .mode = 0444, -}; - -static struct attribute sys_lines_info_attr = { - .name = "lines_info", - .mode = 0444, -}; - -static struct attribute sys_gc_force = { - .name = "gc_force", - .mode = 0200, -}; - -static struct attribute sys_max_sec_per_write = { - .name = "max_sec_per_write", - .mode = 0644, -}; - -static struct attribute sys_write_amp_mileage = { - .name = "write_amp_mileage", - .mode = 0444, -}; - -static struct attribute sys_write_amp_trip = { - .name = "write_amp_trip", - .mode = 0644, -}; - -static struct attribute sys_padding_dist = { - .name = "padding_dist", - .mode = 0644, -}; - -#ifdef CONFIG_NVM_PBLK_DEBUG -static struct attribute sys_stats_debug_attr = { - .name = "stats", - .mode = 0444, -}; -#endif - -static struct attribute *pblk_attrs[] = { - &sys_write_luns, - &sys_rate_limiter_attr, - &sys_errors_attr, - &sys_gc_state, - &sys_gc_force, - &sys_max_sec_per_write, - &sys_rb_attr, - &sys_stats_ppaf_attr, - &sys_lines_attr, - &sys_lines_info_attr, - &sys_write_amp_mileage, - &sys_write_amp_trip, - &sys_padding_dist, -#ifdef CONFIG_NVM_PBLK_DEBUG - &sys_stats_debug_attr, -#endif - NULL, -}; - -static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr, - char *buf) -{ - struct pblk *pblk = container_of(kobj, struct pblk, kobj); - - if (strcmp(attr->name, "rate_limiter") == 0) - return pblk_sysfs_rate_limiter(pblk, buf); - else if (strcmp(attr->name, "write_luns") == 0) - return pblk_sysfs_luns_show(pblk, buf); - else if (strcmp(attr->name, "gc_state") == 0) - return pblk_sysfs_gc_state_show(pblk, buf); - else if (strcmp(attr->name, "errors") == 0) - return pblk_sysfs_stats(pblk, buf); - else if (strcmp(attr->name, "write_buffer") == 0) - return pblk_sysfs_write_buffer(pblk, buf); - else if (strcmp(attr->name, "ppa_format") == 0) - return pblk_sysfs_ppaf(pblk, buf); - else if (strcmp(attr->name, "lines") == 0) - return pblk_sysfs_lines(pblk, buf); - else if (strcmp(attr->name, "lines_info") == 0) - return pblk_sysfs_lines_info(pblk, buf); - else if (strcmp(attr->name, "max_sec_per_write") == 0) - return pblk_sysfs_get_sec_per_write(pblk, buf); - else if (strcmp(attr->name, "write_amp_mileage") == 0) - return pblk_sysfs_get_write_amp_mileage(pblk, buf); - else if (strcmp(attr->name, "write_amp_trip") == 0) - return pblk_sysfs_get_write_amp_trip(pblk, buf); - else if (strcmp(attr->name, "padding_dist") == 0) - return pblk_sysfs_get_padding_dist(pblk, buf); -#ifdef CONFIG_NVM_PBLK_DEBUG - else if (strcmp(attr->name, "stats") == 0) - return pblk_sysfs_stats_debug(pblk, buf); -#endif - return 0; -} - -static ssize_t pblk_sysfs_store(struct kobject *kobj, struct attribute *attr, - const char *buf, size_t len) -{ - struct pblk *pblk = container_of(kobj, struct pblk, kobj); - - if (strcmp(attr->name, "gc_force") == 0) - return pblk_sysfs_gc_force(pblk, buf, len); - else if (strcmp(attr->name, "max_sec_per_write") == 0) - return pblk_sysfs_set_sec_per_write(pblk, buf, len); - else if (strcmp(attr->name, "write_amp_trip") == 0) - return pblk_sysfs_set_write_amp_trip(pblk, buf, len); - else if (strcmp(attr->name, "padding_dist") == 0) - return pblk_sysfs_set_padding_dist(pblk, buf, len); - return 0; -} - -static const struct sysfs_ops pblk_sysfs_ops = { - .show = pblk_sysfs_show, - .store = pblk_sysfs_store, -}; - -static struct kobj_type pblk_ktype = { - .sysfs_ops = &pblk_sysfs_ops, - .default_attrs = pblk_attrs, -}; - -int pblk_sysfs_init(struct gendisk *tdisk) -{ - struct pblk *pblk = tdisk->private_data; - struct device *parent_dev = disk_to_dev(pblk->disk); - int ret; - - ret = kobject_init_and_add(&pblk->kobj, &pblk_ktype, - kobject_get(&parent_dev->kobj), - "%s", "pblk"); - if (ret) { - pblk_err(pblk, "could not register\n"); - return ret; - } - - kobject_uevent(&pblk->kobj, KOBJ_ADD); - return 0; -} - -void pblk_sysfs_exit(struct gendisk *tdisk) -{ - struct pblk *pblk = tdisk->private_data; - - kobject_uevent(&pblk->kobj, KOBJ_REMOVE); - kobject_del(&pblk->kobj); - kobject_put(&pblk->kobj); -} diff --git a/drivers/lightnvm/pblk-trace.h b/drivers/lightnvm/pblk-trace.h deleted file mode 100644 index 47b67c6bff7a..000000000000 --- a/drivers/lightnvm/pblk-trace.h +++ /dev/null @@ -1,145 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM pblk - -#if !defined(_TRACE_PBLK_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_PBLK_H - -#include - -struct ppa_addr; - -#define show_chunk_flags(state) __print_flags(state, "", \ - { NVM_CHK_ST_FREE, "FREE", }, \ - { NVM_CHK_ST_CLOSED, "CLOSED", }, \ - { NVM_CHK_ST_OPEN, "OPEN", }, \ - { NVM_CHK_ST_OFFLINE, "OFFLINE", }) - -#define show_line_state(state) __print_symbolic(state, \ - { PBLK_LINESTATE_NEW, "NEW", }, \ - { PBLK_LINESTATE_FREE, "FREE", }, \ - { PBLK_LINESTATE_OPEN, "OPEN", }, \ - { PBLK_LINESTATE_CLOSED, "CLOSED", }, \ - { PBLK_LINESTATE_GC, "GC", }, \ - { PBLK_LINESTATE_BAD, "BAD", }, \ - { PBLK_LINESTATE_CORRUPT, "CORRUPT" }) - - -#define show_pblk_state(state) __print_symbolic(state, \ - { PBLK_STATE_RUNNING, "RUNNING", }, \ - { PBLK_STATE_STOPPING, "STOPPING", }, \ - { PBLK_STATE_RECOVERING, "RECOVERING", }, \ - { PBLK_STATE_STOPPED, "STOPPED" }) - -#define show_chunk_erase_state(state) __print_symbolic(state, \ - { PBLK_CHUNK_RESET_START, "START", }, \ - { PBLK_CHUNK_RESET_DONE, "OK", }, \ - { PBLK_CHUNK_RESET_FAILED, "FAILED" }) - - -TRACE_EVENT(pblk_chunk_reset, - - TP_PROTO(const char *name, struct ppa_addr *ppa, int state), - - TP_ARGS(name, ppa, state), - - TP_STRUCT__entry( - __string(name, name) - __field(u64, ppa) - __field(int, state) - ), - - TP_fast_assign( - __assign_str(name, name); - __entry->ppa = ppa->ppa; - __entry->state = state; - ), - - TP_printk("dev=%s grp=%llu pu=%llu chk=%llu state=%s", __get_str(name), - (u64)(((struct ppa_addr *)(&__entry->ppa))->m.grp), - (u64)(((struct ppa_addr *)(&__entry->ppa))->m.pu), - (u64)(((struct ppa_addr *)(&__entry->ppa))->m.chk), - show_chunk_erase_state((int)__entry->state)) - -); - -TRACE_EVENT(pblk_chunk_state, - - TP_PROTO(const char *name, struct ppa_addr *ppa, int state), - - TP_ARGS(name, ppa, state), - - TP_STRUCT__entry( - __string(name, name) - __field(u64, ppa) - __field(int, state) - ), - - TP_fast_assign( - __assign_str(name, name); - __entry->ppa = ppa->ppa; - __entry->state = state; - ), - - TP_printk("dev=%s grp=%llu pu=%llu chk=%llu state=%s", __get_str(name), - (u64)(((struct ppa_addr *)(&__entry->ppa))->m.grp), - (u64)(((struct ppa_addr *)(&__entry->ppa))->m.pu), - (u64)(((struct ppa_addr *)(&__entry->ppa))->m.chk), - show_chunk_flags((int)__entry->state)) - -); - -TRACE_EVENT(pblk_line_state, - - TP_PROTO(const char *name, int line, int state), - - TP_ARGS(name, line, state), - - TP_STRUCT__entry( - __string(name, name) - __field(int, line) - __field(int, state) - ), - - TP_fast_assign( - __assign_str(name, name); - __entry->line = line; - __entry->state = state; - ), - - TP_printk("dev=%s line=%d state=%s", __get_str(name), - (int)__entry->line, - show_line_state((int)__entry->state)) - -); - -TRACE_EVENT(pblk_state, - - TP_PROTO(const char *name, int state), - - TP_ARGS(name, state), - - TP_STRUCT__entry( - __string(name, name) - __field(int, state) - ), - - TP_fast_assign( - __assign_str(name, name); - __entry->state = state; - ), - - TP_printk("dev=%s state=%s", __get_str(name), - show_pblk_state((int)__entry->state)) - -); - -#endif /* !defined(_TRACE_PBLK_H) || defined(TRACE_HEADER_MULTI_READ) */ - -/* This part must be outside protection */ - -#undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH ../../drivers/lightnvm -#undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_FILE pblk-trace -#include diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c deleted file mode 100644 index b9a2aeba95ab..000000000000 --- a/drivers/lightnvm/pblk-write.c +++ /dev/null @@ -1,665 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2016 CNEX Labs - * Initial release: Javier Gonzalez - * Matias Bjorling - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * pblk-write.c - pblk's write path from write buffer to media - */ - -#include "pblk.h" -#include "pblk-trace.h" - -static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd, - struct pblk_c_ctx *c_ctx) -{ - struct bio *original_bio; - struct pblk_rb *rwb = &pblk->rwb; - unsigned long ret; - int i; - - for (i = 0; i < c_ctx->nr_valid; i++) { - struct pblk_w_ctx *w_ctx; - int pos = c_ctx->sentry + i; - int flags; - - w_ctx = pblk_rb_w_ctx(rwb, pos); - flags = READ_ONCE(w_ctx->flags); - - if (flags & PBLK_FLUSH_ENTRY) { - flags &= ~PBLK_FLUSH_ENTRY; - /* Release flags on context. Protect from writes */ - smp_store_release(&w_ctx->flags, flags); - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_dec(&rwb->inflight_flush_point); -#endif - } - - while ((original_bio = bio_list_pop(&w_ctx->bios))) - bio_endio(original_bio); - } - - if (c_ctx->nr_padded) - pblk_bio_free_pages(pblk, rqd->bio, c_ctx->nr_valid, - c_ctx->nr_padded); - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_add(rqd->nr_ppas, &pblk->sync_writes); -#endif - - ret = pblk_rb_sync_advance(&pblk->rwb, c_ctx->nr_valid); - - bio_put(rqd->bio); - pblk_free_rqd(pblk, rqd, PBLK_WRITE); - - return ret; -} - -static unsigned long pblk_end_queued_w_bio(struct pblk *pblk, - struct nvm_rq *rqd, - struct pblk_c_ctx *c_ctx) -{ - list_del(&c_ctx->list); - return pblk_end_w_bio(pblk, rqd, c_ctx); -} - -static void pblk_complete_write(struct pblk *pblk, struct nvm_rq *rqd, - struct pblk_c_ctx *c_ctx) -{ - struct pblk_c_ctx *c, *r; - unsigned long flags; - unsigned long pos; - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_sub(c_ctx->nr_valid, &pblk->inflight_writes); -#endif - pblk_up_rq(pblk, c_ctx->lun_bitmap); - - pos = pblk_rb_sync_init(&pblk->rwb, &flags); - if (pos == c_ctx->sentry) { - pos = pblk_end_w_bio(pblk, rqd, c_ctx); - -retry: - list_for_each_entry_safe(c, r, &pblk->compl_list, list) { - rqd = nvm_rq_from_c_ctx(c); - if (c->sentry == pos) { - pos = pblk_end_queued_w_bio(pblk, rqd, c); - goto retry; - } - } - } else { - WARN_ON(nvm_rq_from_c_ctx(c_ctx) != rqd); - list_add_tail(&c_ctx->list, &pblk->compl_list); - } - pblk_rb_sync_end(&pblk->rwb, &flags); -} - -/* Map remaining sectors in chunk, starting from ppa */ -static void pblk_map_remaining(struct pblk *pblk, struct ppa_addr *ppa, - int rqd_ppas) -{ - struct pblk_line *line; - struct ppa_addr map_ppa = *ppa; - __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); - __le64 *lba_list; - u64 paddr; - int done = 0; - int n = 0; - - line = pblk_ppa_to_line(pblk, *ppa); - lba_list = emeta_to_lbas(pblk, line->emeta->buf); - - spin_lock(&line->lock); - - while (!done) { - paddr = pblk_dev_ppa_to_line_addr(pblk, map_ppa); - - if (!test_and_set_bit(paddr, line->map_bitmap)) - line->left_msecs--; - - if (n < rqd_ppas && lba_list[paddr] != addr_empty) - line->nr_valid_lbas--; - - lba_list[paddr] = addr_empty; - - if (!test_and_set_bit(paddr, line->invalid_bitmap)) - le32_add_cpu(line->vsc, -1); - - done = nvm_next_ppa_in_chk(pblk->dev, &map_ppa); - - n++; - } - - line->w_err_gc->has_write_err = 1; - spin_unlock(&line->lock); -} - -static void pblk_prepare_resubmit(struct pblk *pblk, unsigned int sentry, - unsigned int nr_entries) -{ - struct pblk_rb *rb = &pblk->rwb; - struct pblk_rb_entry *entry; - struct pblk_line *line; - struct pblk_w_ctx *w_ctx; - struct ppa_addr ppa_l2p; - int flags; - unsigned int i; - - spin_lock(&pblk->trans_lock); - for (i = 0; i < nr_entries; i++) { - entry = &rb->entries[pblk_rb_ptr_wrap(rb, sentry, i)]; - w_ctx = &entry->w_ctx; - - /* Check if the lba has been overwritten */ - if (w_ctx->lba != ADDR_EMPTY) { - ppa_l2p = pblk_trans_map_get(pblk, w_ctx->lba); - if (!pblk_ppa_comp(ppa_l2p, entry->cacheline)) - w_ctx->lba = ADDR_EMPTY; - } - - /* Mark up the entry as submittable again */ - flags = READ_ONCE(w_ctx->flags); - flags |= PBLK_WRITTEN_DATA; - /* Release flags on write context. Protect from writes */ - smp_store_release(&w_ctx->flags, flags); - - /* Decrease the reference count to the line as we will - * re-map these entries - */ - line = pblk_ppa_to_line(pblk, w_ctx->ppa); - atomic_dec(&line->sec_to_update); - kref_put(&line->ref, pblk_line_put); - } - spin_unlock(&pblk->trans_lock); -} - -static void pblk_queue_resubmit(struct pblk *pblk, struct pblk_c_ctx *c_ctx) -{ - struct pblk_c_ctx *r_ctx; - - r_ctx = kzalloc(sizeof(struct pblk_c_ctx), GFP_KERNEL); - if (!r_ctx) - return; - - r_ctx->lun_bitmap = NULL; - r_ctx->sentry = c_ctx->sentry; - r_ctx->nr_valid = c_ctx->nr_valid; - r_ctx->nr_padded = c_ctx->nr_padded; - - spin_lock(&pblk->resubmit_lock); - list_add_tail(&r_ctx->list, &pblk->resubmit_list); - spin_unlock(&pblk->resubmit_lock); - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_add(c_ctx->nr_valid, &pblk->recov_writes); -#endif -} - -static void pblk_submit_rec(struct work_struct *work) -{ - struct pblk_rec_ctx *recovery = - container_of(work, struct pblk_rec_ctx, ws_rec); - struct pblk *pblk = recovery->pblk; - struct nvm_rq *rqd = recovery->rqd; - struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd); - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - - pblk_log_write_err(pblk, rqd); - - pblk_map_remaining(pblk, ppa_list, rqd->nr_ppas); - pblk_queue_resubmit(pblk, c_ctx); - - pblk_up_rq(pblk, c_ctx->lun_bitmap); - if (c_ctx->nr_padded) - pblk_bio_free_pages(pblk, rqd->bio, c_ctx->nr_valid, - c_ctx->nr_padded); - bio_put(rqd->bio); - pblk_free_rqd(pblk, rqd, PBLK_WRITE); - mempool_free(recovery, &pblk->rec_pool); - - atomic_dec(&pblk->inflight_io); - pblk_write_kick(pblk); -} - - -static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd) -{ - struct pblk_rec_ctx *recovery; - - recovery = mempool_alloc(&pblk->rec_pool, GFP_ATOMIC); - if (!recovery) { - pblk_err(pblk, "could not allocate recovery work\n"); - return; - } - - recovery->pblk = pblk; - recovery->rqd = rqd; - - INIT_WORK(&recovery->ws_rec, pblk_submit_rec); - queue_work(pblk->close_wq, &recovery->ws_rec); -} - -static void pblk_end_io_write(struct nvm_rq *rqd) -{ - struct pblk *pblk = rqd->private; - struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd); - - if (rqd->error) { - pblk_end_w_fail(pblk, rqd); - return; - } else { - if (trace_pblk_chunk_state_enabled()) - pblk_check_chunk_state_update(pblk, rqd); -#ifdef CONFIG_NVM_PBLK_DEBUG - WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n"); -#endif - } - - pblk_complete_write(pblk, rqd, c_ctx); - atomic_dec(&pblk->inflight_io); -} - -static void pblk_end_io_write_meta(struct nvm_rq *rqd) -{ - struct pblk *pblk = rqd->private; - struct pblk_g_ctx *m_ctx = nvm_rq_to_pdu(rqd); - struct pblk_line *line = m_ctx->private; - struct pblk_emeta *emeta = line->emeta; - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - int sync; - - pblk_up_chunk(pblk, ppa_list[0]); - - if (rqd->error) { - pblk_log_write_err(pblk, rqd); - pblk_err(pblk, "metadata I/O failed. Line %d\n", line->id); - line->w_err_gc->has_write_err = 1; - } else { - if (trace_pblk_chunk_state_enabled()) - pblk_check_chunk_state_update(pblk, rqd); - } - - sync = atomic_add_return(rqd->nr_ppas, &emeta->sync); - if (sync == emeta->nr_entries) - pblk_gen_run_ws(pblk, line, NULL, pblk_line_close_ws, - GFP_ATOMIC, pblk->close_wq); - - pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT); - - atomic_dec(&pblk->inflight_io); -} - -static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd, - unsigned int nr_secs, nvm_end_io_fn(*end_io)) -{ - /* Setup write request */ - rqd->opcode = NVM_OP_PWRITE; - rqd->nr_ppas = nr_secs; - rqd->is_seq = 1; - rqd->private = pblk; - rqd->end_io = end_io; - - return pblk_alloc_rqd_meta(pblk, rqd); -} - -static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd, - struct ppa_addr *erase_ppa) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line *e_line = pblk_line_get_erase(pblk); - struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd); - unsigned int valid = c_ctx->nr_valid; - unsigned int padded = c_ctx->nr_padded; - unsigned int nr_secs = valid + padded; - unsigned long *lun_bitmap; - int ret; - - lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL); - if (!lun_bitmap) - return -ENOMEM; - c_ctx->lun_bitmap = lun_bitmap; - - ret = pblk_alloc_w_rq(pblk, rqd, nr_secs, pblk_end_io_write); - if (ret) { - kfree(lun_bitmap); - return ret; - } - - if (likely(!e_line || !atomic_read(&e_line->left_eblks))) - ret = pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, - valid, 0); - else - ret = pblk_map_erase_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, - valid, erase_ppa); - - return ret; -} - -static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail, - unsigned int secs_to_flush) -{ - int secs_to_sync; - - secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush, true); - -#ifdef CONFIG_NVM_PBLK_DEBUG - if ((!secs_to_sync && secs_to_flush) - || (secs_to_sync < 0) - || (secs_to_sync > secs_avail && !secs_to_flush)) { - pblk_err(pblk, "bad sector calculation (a:%d,s:%d,f:%d)\n", - secs_avail, secs_to_sync, secs_to_flush); - } -#endif - - return secs_to_sync; -} - -int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_emeta *emeta = meta_line->emeta; - struct ppa_addr *ppa_list; - struct pblk_g_ctx *m_ctx; - struct nvm_rq *rqd; - void *data; - u64 paddr; - int rq_ppas = pblk->min_write_pgs; - int id = meta_line->id; - int rq_len; - int i, j; - int ret; - - rqd = pblk_alloc_rqd(pblk, PBLK_WRITE_INT); - - m_ctx = nvm_rq_to_pdu(rqd); - m_ctx->private = meta_line; - - rq_len = rq_ppas * geo->csecs; - data = ((void *)emeta->buf) + emeta->mem; - - ret = pblk_alloc_w_rq(pblk, rqd, rq_ppas, pblk_end_io_write_meta); - if (ret) - goto fail_free_rqd; - - ppa_list = nvm_rq_to_ppa_list(rqd); - for (i = 0; i < rqd->nr_ppas; ) { - spin_lock(&meta_line->lock); - paddr = __pblk_alloc_page(pblk, meta_line, rq_ppas); - spin_unlock(&meta_line->lock); - for (j = 0; j < rq_ppas; j++, i++, paddr++) - ppa_list[i] = addr_to_gen_ppa(pblk, paddr, id); - } - - spin_lock(&l_mg->close_lock); - emeta->mem += rq_len; - if (emeta->mem >= lm->emeta_len[0]) - list_del(&meta_line->list); - spin_unlock(&l_mg->close_lock); - - pblk_down_chunk(pblk, ppa_list[0]); - - ret = pblk_submit_io(pblk, rqd, data); - if (ret) { - pblk_err(pblk, "emeta I/O submission failed: %d\n", ret); - goto fail_rollback; - } - - return NVM_IO_OK; - -fail_rollback: - pblk_up_chunk(pblk, ppa_list[0]); - spin_lock(&l_mg->close_lock); - pblk_dealloc_page(pblk, meta_line, rq_ppas); - list_add(&meta_line->list, &meta_line->list); - spin_unlock(&l_mg->close_lock); -fail_free_rqd: - pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT); - return ret; -} - -static inline bool pblk_valid_meta_ppa(struct pblk *pblk, - struct pblk_line *meta_line, - struct nvm_rq *data_rqd) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_c_ctx *data_c_ctx = nvm_rq_to_pdu(data_rqd); - struct pblk_line *data_line = pblk_line_get_data(pblk); - struct ppa_addr ppa, ppa_opt; - u64 paddr; - int pos_opt; - - /* Schedule a metadata I/O that is half the distance from the data I/O - * with regards to the number of LUNs forming the pblk instance. This - * balances LUN conflicts across every I/O. - * - * When the LUN configuration changes (e.g., due to GC), this distance - * can align, which would result on metadata and data I/Os colliding. In - * this case, modify the distance to not be optimal, but move the - * optimal in the right direction. - */ - paddr = pblk_lookup_page(pblk, meta_line); - ppa = addr_to_gen_ppa(pblk, paddr, 0); - ppa_opt = addr_to_gen_ppa(pblk, paddr + data_line->meta_distance, 0); - pos_opt = pblk_ppa_to_pos(geo, ppa_opt); - - if (test_bit(pos_opt, data_c_ctx->lun_bitmap) || - test_bit(pos_opt, data_line->blk_bitmap)) - return true; - - if (unlikely(pblk_ppa_comp(ppa_opt, ppa))) - data_line->meta_distance--; - - return false; -} - -static struct pblk_line *pblk_should_submit_meta_io(struct pblk *pblk, - struct nvm_rq *data_rqd) -{ - struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line *meta_line; - - spin_lock(&l_mg->close_lock); - if (list_empty(&l_mg->emeta_list)) { - spin_unlock(&l_mg->close_lock); - return NULL; - } - meta_line = list_first_entry(&l_mg->emeta_list, struct pblk_line, list); - if (meta_line->emeta->mem >= lm->emeta_len[0]) { - spin_unlock(&l_mg->close_lock); - return NULL; - } - spin_unlock(&l_mg->close_lock); - - if (!pblk_valid_meta_ppa(pblk, meta_line, data_rqd)) - return NULL; - - return meta_line; -} - -static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd) -{ - struct ppa_addr erase_ppa; - struct pblk_line *meta_line; - int err; - - pblk_ppa_set_empty(&erase_ppa); - - /* Assign lbas to ppas and populate request structure */ - err = pblk_setup_w_rq(pblk, rqd, &erase_ppa); - if (err) { - pblk_err(pblk, "could not setup write request: %d\n", err); - return NVM_IO_ERR; - } - - meta_line = pblk_should_submit_meta_io(pblk, rqd); - - /* Submit data write for current data line */ - err = pblk_submit_io(pblk, rqd, NULL); - if (err) { - pblk_err(pblk, "data I/O submission failed: %d\n", err); - return NVM_IO_ERR; - } - - if (!pblk_ppa_empty(erase_ppa)) { - /* Submit erase for next data line */ - if (pblk_blk_erase_async(pblk, erase_ppa)) { - struct pblk_line *e_line = pblk_line_get_erase(pblk); - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - int bit; - - atomic_inc(&e_line->left_eblks); - bit = pblk_ppa_to_pos(geo, erase_ppa); - WARN_ON(!test_and_clear_bit(bit, e_line->erase_bitmap)); - } - } - - if (meta_line) { - /* Submit metadata write for previous data line */ - err = pblk_submit_meta_io(pblk, meta_line); - if (err) { - pblk_err(pblk, "metadata I/O submission failed: %d", - err); - return NVM_IO_ERR; - } - } - - return NVM_IO_OK; -} - -static void pblk_free_write_rqd(struct pblk *pblk, struct nvm_rq *rqd) -{ - struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd); - struct bio *bio = rqd->bio; - - if (c_ctx->nr_padded) - pblk_bio_free_pages(pblk, bio, c_ctx->nr_valid, - c_ctx->nr_padded); -} - -static int pblk_submit_write(struct pblk *pblk, int *secs_left) -{ - struct bio *bio; - struct nvm_rq *rqd; - unsigned int secs_avail, secs_to_sync, secs_to_com; - unsigned int secs_to_flush, packed_meta_pgs; - unsigned long pos; - unsigned int resubmit; - - *secs_left = 0; - - spin_lock(&pblk->resubmit_lock); - resubmit = !list_empty(&pblk->resubmit_list); - spin_unlock(&pblk->resubmit_lock); - - /* Resubmit failed writes first */ - if (resubmit) { - struct pblk_c_ctx *r_ctx; - - spin_lock(&pblk->resubmit_lock); - r_ctx = list_first_entry(&pblk->resubmit_list, - struct pblk_c_ctx, list); - list_del(&r_ctx->list); - spin_unlock(&pblk->resubmit_lock); - - secs_avail = r_ctx->nr_valid; - pos = r_ctx->sentry; - - pblk_prepare_resubmit(pblk, pos, secs_avail); - secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail, - secs_avail); - - kfree(r_ctx); - } else { - /* If there are no sectors in the cache, - * flushes (bios without data) will be cleared on - * the cache threads - */ - secs_avail = pblk_rb_read_count(&pblk->rwb); - if (!secs_avail) - return 0; - - secs_to_flush = pblk_rb_flush_point_count(&pblk->rwb); - if (!secs_to_flush && secs_avail < pblk->min_write_pgs_data) - return 0; - - secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail, - secs_to_flush); - if (secs_to_sync > pblk->max_write_pgs) { - pblk_err(pblk, "bad buffer sync calculation\n"); - return 0; - } - - secs_to_com = (secs_to_sync > secs_avail) ? - secs_avail : secs_to_sync; - pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com); - } - - packed_meta_pgs = (pblk->min_write_pgs - pblk->min_write_pgs_data); - bio = bio_alloc(GFP_KERNEL, secs_to_sync + packed_meta_pgs); - - bio->bi_iter.bi_sector = 0; /* internal bio */ - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - - rqd = pblk_alloc_rqd(pblk, PBLK_WRITE); - rqd->bio = bio; - - if (pblk_rb_read_to_bio(&pblk->rwb, rqd, pos, secs_to_sync, - secs_avail)) { - pblk_err(pblk, "corrupted write bio\n"); - goto fail_put_bio; - } - - if (pblk_submit_io_set(pblk, rqd)) - goto fail_free_bio; - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_long_add(secs_to_sync, &pblk->sub_writes); -#endif - - *secs_left = 1; - return 0; - -fail_free_bio: - pblk_free_write_rqd(pblk, rqd); -fail_put_bio: - bio_put(bio); - pblk_free_rqd(pblk, rqd, PBLK_WRITE); - - return -EINTR; -} - -int pblk_write_ts(void *data) -{ - struct pblk *pblk = data; - int secs_left; - int write_failure = 0; - - while (!kthread_should_stop()) { - if (!write_failure) { - write_failure = pblk_submit_write(pblk, &secs_left); - - if (secs_left) - continue; - } - set_current_state(TASK_INTERRUPTIBLE); - io_schedule(); - } - - return 0; -} diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h deleted file mode 100644 index 86ffa875bfe1..000000000000 --- a/drivers/lightnvm/pblk.h +++ /dev/null @@ -1,1358 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2015 IT University of Copenhagen (rrpc.h) - * Copyright (C) 2016 CNEX Labs - * Initial release: Matias Bjorling - * Write buffering: Javier Gonzalez - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * Implementation of a Physical Block-device target for Open-channel SSDs. - * - */ - -#ifndef PBLK_H_ -#define PBLK_H_ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -/* Run only GC if less than 1/X blocks are free */ -#define GC_LIMIT_INVERSE 5 -#define GC_TIME_MSECS 1000 - -#define PBLK_SECTOR (512) -#define PBLK_EXPOSED_PAGE_SIZE (4096) - -#define PBLK_NR_CLOSE_JOBS (4) - -#define PBLK_CACHE_NAME_LEN (DISK_NAME_LEN + 16) - -/* Max 512 LUNs per device */ -#define PBLK_MAX_LUNS_BITMAP (4) - -#define NR_PHY_IN_LOG (PBLK_EXPOSED_PAGE_SIZE / PBLK_SECTOR) - -/* Static pool sizes */ -#define PBLK_GEN_WS_POOL_SIZE (2) - -#define PBLK_DEFAULT_OP (11) - -enum { - PBLK_READ = READ, - PBLK_WRITE = WRITE,/* Write from write buffer */ - PBLK_WRITE_INT, /* Internal write - no write buffer */ - PBLK_READ_RECOV, /* Recovery read - errors allowed */ - PBLK_ERASE, -}; - -enum { - /* IO Types */ - PBLK_IOTYPE_USER = 1 << 0, - PBLK_IOTYPE_GC = 1 << 1, - - /* Write buffer flags */ - PBLK_FLUSH_ENTRY = 1 << 2, - PBLK_WRITTEN_DATA = 1 << 3, - PBLK_SUBMITTED_ENTRY = 1 << 4, - PBLK_WRITABLE_ENTRY = 1 << 5, -}; - -enum { - PBLK_BLK_ST_OPEN = 0x1, - PBLK_BLK_ST_CLOSED = 0x2, -}; - -enum { - PBLK_CHUNK_RESET_START, - PBLK_CHUNK_RESET_DONE, - PBLK_CHUNK_RESET_FAILED, -}; - -struct pblk_sec_meta { - u64 reserved; - __le64 lba; -}; - -/* The number of GC lists and the rate-limiter states go together. This way the - * rate-limiter can dictate how much GC is needed based on resource utilization. - */ -#define PBLK_GC_NR_LISTS 4 - -enum { - PBLK_RL_OFF = 0, - PBLK_RL_WERR = 1, - PBLK_RL_HIGH = 2, - PBLK_RL_MID = 3, - PBLK_RL_LOW = 4 -}; - -#define pblk_dma_ppa_size (sizeof(u64) * NVM_MAX_VLBA) - -/* write buffer completion context */ -struct pblk_c_ctx { - struct list_head list; /* Head for out-of-order completion */ - - unsigned long *lun_bitmap; /* Luns used on current request */ - unsigned int sentry; - unsigned int nr_valid; - unsigned int nr_padded; -}; - -/* read context */ -struct pblk_g_ctx { - void *private; - unsigned long start_time; - u64 lba; -}; - -/* Pad context */ -struct pblk_pad_rq { - struct pblk *pblk; - struct completion wait; - struct kref ref; -}; - -/* Recovery context */ -struct pblk_rec_ctx { - struct pblk *pblk; - struct nvm_rq *rqd; - struct work_struct ws_rec; -}; - -/* Write context */ -struct pblk_w_ctx { - struct bio_list bios; /* Original bios - used for completion - * in REQ_FUA, REQ_FLUSH case - */ - u64 lba; /* Logic addr. associated with entry */ - struct ppa_addr ppa; /* Physic addr. associated with entry */ - int flags; /* Write context flags */ -}; - -struct pblk_rb_entry { - struct ppa_addr cacheline; /* Cacheline for this entry */ - void *data; /* Pointer to data on this entry */ - struct pblk_w_ctx w_ctx; /* Context for this entry */ - struct list_head index; /* List head to enable indexes */ -}; - -#define EMPTY_ENTRY (~0U) - -struct pblk_rb_pages { - struct page *pages; - int order; - struct list_head list; -}; - -struct pblk_rb { - struct pblk_rb_entry *entries; /* Ring buffer entries */ - unsigned int mem; /* Write offset - points to next - * writable entry in memory - */ - unsigned int subm; /* Read offset - points to last entry - * that has been submitted to the media - * to be persisted - */ - unsigned int sync; /* Synced - backpointer that signals - * the last submitted entry that has - * been successfully persisted to media - */ - unsigned int flush_point; /* Sync point - last entry that must be - * flushed to the media. Used with - * REQ_FLUSH and REQ_FUA - */ - unsigned int l2p_update; /* l2p update point - next entry for - * which l2p mapping will be updated to - * contain a device ppa address (instead - * of a cacheline - */ - unsigned int nr_entries; /* Number of entries in write buffer - - * must be a power of two - */ - unsigned int seg_size; /* Size of the data segments being - * stored on each entry. Typically this - * will be 4KB - */ - - unsigned int back_thres; /* Threshold that shall be maintained by - * the backpointer in order to respect - * geo->mw_cunits on a per chunk basis - */ - - struct list_head pages; /* List of data pages */ - - spinlock_t w_lock; /* Write lock */ - spinlock_t s_lock; /* Sync lock */ - -#ifdef CONFIG_NVM_PBLK_DEBUG - atomic_t inflight_flush_point; /* Not served REQ_FLUSH | REQ_FUA */ -#endif -}; - -#define PBLK_RECOVERY_SECTORS 16 - -struct pblk_lun { - struct ppa_addr bppa; - struct semaphore wr_sem; -}; - -struct pblk_gc_rq { - struct pblk_line *line; - void *data; - u64 paddr_list[NVM_MAX_VLBA]; - u64 lba_list[NVM_MAX_VLBA]; - int nr_secs; - int secs_to_gc; - struct list_head list; -}; - -struct pblk_gc { - /* These states are not protected by a lock since (i) they are in the - * fast path, and (ii) they are not critical. - */ - int gc_active; - int gc_enabled; - int gc_forced; - - struct task_struct *gc_ts; - struct task_struct *gc_writer_ts; - struct task_struct *gc_reader_ts; - - struct workqueue_struct *gc_line_reader_wq; - struct workqueue_struct *gc_reader_wq; - - struct timer_list gc_timer; - - struct semaphore gc_sem; - atomic_t read_inflight_gc; /* Number of lines with inflight GC reads */ - atomic_t pipeline_gc; /* Number of lines in the GC pipeline - - * started reads to finished writes - */ - int w_entries; - - struct list_head w_list; - struct list_head r_list; - - spinlock_t lock; - spinlock_t w_lock; - spinlock_t r_lock; -}; - -struct pblk_rl { - unsigned int high; /* Upper threshold for rate limiter (free run - - * user I/O rate limiter - */ - unsigned int high_pw; /* High rounded up as a power of 2 */ - -#define PBLK_USER_HIGH_THRS 8 /* Begin write limit at 12% available blks */ -#define PBLK_USER_LOW_THRS 10 /* Aggressive GC at 10% available blocks */ - - int rb_windows_pw; /* Number of rate windows in the write buffer - * given as a power-of-2. This guarantees that - * when user I/O is being rate limited, there - * will be reserved enough space for the GC to - * place its payload. A window is of - * pblk->max_write_pgs size, which in NVMe is - * 64, i.e., 256kb. - */ - int rb_budget; /* Total number of entries available for I/O */ - int rb_user_max; /* Max buffer entries available for user I/O */ - int rb_gc_max; /* Max buffer entries available for GC I/O */ - int rb_gc_rsv; /* Reserved buffer entries for GC I/O */ - int rb_state; /* Rate-limiter current state */ - int rb_max_io; /* Maximum size for an I/O giving the config */ - - atomic_t rb_user_cnt; /* User I/O buffer counter */ - atomic_t rb_gc_cnt; /* GC I/O buffer counter */ - atomic_t rb_space; /* Space limit in case of reaching capacity */ - - int rsv_blocks; /* Reserved blocks for GC */ - - int rb_user_active; - int rb_gc_active; - - atomic_t werr_lines; /* Number of write error lines that needs gc */ - - struct timer_list u_timer; - - unsigned long total_blocks; - - atomic_t free_blocks; /* Total number of free blocks (+ OP) */ - atomic_t free_user_blocks; /* Number of user free blocks (no OP) */ -}; - -#define PBLK_LINE_EMPTY (~0U) - -enum { - /* Line Types */ - PBLK_LINETYPE_FREE = 0, - PBLK_LINETYPE_LOG = 1, - PBLK_LINETYPE_DATA = 2, - - /* Line state */ - PBLK_LINESTATE_NEW = 9, - PBLK_LINESTATE_FREE = 10, - PBLK_LINESTATE_OPEN = 11, - PBLK_LINESTATE_CLOSED = 12, - PBLK_LINESTATE_GC = 13, - PBLK_LINESTATE_BAD = 14, - PBLK_LINESTATE_CORRUPT = 15, - - /* GC group */ - PBLK_LINEGC_NONE = 20, - PBLK_LINEGC_EMPTY = 21, - PBLK_LINEGC_LOW = 22, - PBLK_LINEGC_MID = 23, - PBLK_LINEGC_HIGH = 24, - PBLK_LINEGC_FULL = 25, - PBLK_LINEGC_WERR = 26 -}; - -#define PBLK_MAGIC 0x70626c6b /*pblk*/ - -/* emeta/smeta persistent storage format versions: - * Changes in major version requires offline migration. - * Changes in minor version are handled automatically during - * recovery. - */ - -#define SMETA_VERSION_MAJOR (0) -#define SMETA_VERSION_MINOR (1) - -#define EMETA_VERSION_MAJOR (0) -#define EMETA_VERSION_MINOR (2) - -struct line_header { - __le32 crc; - __le32 identifier; /* pblk identifier */ - __u8 uuid[16]; /* instance uuid */ - __le16 type; /* line type */ - __u8 version_major; /* version major */ - __u8 version_minor; /* version minor */ - __le32 id; /* line id for current line */ -}; - -struct line_smeta { - struct line_header header; - - __le32 crc; /* Full structure including struct crc */ - /* Previous line metadata */ - __le32 prev_id; /* Line id for previous line */ - - /* Current line metadata */ - __le64 seq_nr; /* Sequence number for current line */ - - /* Active writers */ - __le32 window_wr_lun; /* Number of parallel LUNs to write */ - - __le32 rsvd[2]; - - __le64 lun_bitmap[]; -}; - - -/* - * Metadata layout in media: - * First sector: - * 1. struct line_emeta - * 2. bad block bitmap (u64 * window_wr_lun) - * 3. write amplification counters - * Mid sectors (start at lbas_sector): - * 3. nr_lbas (u64) forming lba list - * Last sectors (start at vsc_sector): - * 4. u32 valid sector count (vsc) for all lines (~0U: free line) - */ -struct line_emeta { - struct line_header header; - - __le32 crc; /* Full structure including struct crc */ - - /* Previous line metadata */ - __le32 prev_id; /* Line id for prev line */ - - /* Current line metadata */ - __le64 seq_nr; /* Sequence number for current line */ - - /* Active writers */ - __le32 window_wr_lun; /* Number of parallel LUNs to write */ - - /* Bookkeeping for recovery */ - __le32 next_id; /* Line id for next line */ - __le64 nr_lbas; /* Number of lbas mapped in line */ - __le64 nr_valid_lbas; /* Number of valid lbas mapped in line */ - __le64 bb_bitmap[]; /* Updated bad block bitmap for line */ -}; - - -/* Write amplification counters stored on media */ -struct wa_counters { - __le64 user; /* Number of user written sectors */ - __le64 gc; /* Number of sectors written by GC*/ - __le64 pad; /* Number of padded sectors */ -}; - -struct pblk_emeta { - struct line_emeta *buf; /* emeta buffer in media format */ - int mem; /* Write offset - points to next - * writable entry in memory - */ - atomic_t sync; /* Synced - backpointer that signals the - * last entry that has been successfully - * persisted to media - */ - unsigned int nr_entries; /* Number of emeta entries */ -}; - -struct pblk_smeta { - struct line_smeta *buf; /* smeta buffer in persistent format */ -}; - -struct pblk_w_err_gc { - int has_write_err; - int has_gc_err; - __le64 *lba_list; -}; - -struct pblk_line { - struct pblk *pblk; - unsigned int id; /* Line number corresponds to the - * block line - */ - unsigned int seq_nr; /* Unique line sequence number */ - - int state; /* PBLK_LINESTATE_X */ - int type; /* PBLK_LINETYPE_X */ - int gc_group; /* PBLK_LINEGC_X */ - struct list_head list; /* Free, GC lists */ - - unsigned long *lun_bitmap; /* Bitmap for LUNs mapped in line */ - - struct nvm_chk_meta *chks; /* Chunks forming line */ - - struct pblk_smeta *smeta; /* Start metadata */ - struct pblk_emeta *emeta; /* End medatada */ - - int meta_line; /* Metadata line id */ - int meta_distance; /* Distance between data and metadata */ - - u64 emeta_ssec; /* Sector where emeta starts */ - - unsigned int sec_in_line; /* Number of usable secs in line */ - - atomic_t blk_in_line; /* Number of good blocks in line */ - unsigned long *blk_bitmap; /* Bitmap for valid/invalid blocks */ - unsigned long *erase_bitmap; /* Bitmap for erased blocks */ - - unsigned long *map_bitmap; /* Bitmap for mapped sectors in line */ - unsigned long *invalid_bitmap; /* Bitmap for invalid sectors in line */ - - atomic_t left_eblks; /* Blocks left for erasing */ - atomic_t left_seblks; /* Blocks left for sync erasing */ - - int left_msecs; /* Sectors left for mapping */ - unsigned int cur_sec; /* Sector map pointer */ - unsigned int nr_valid_lbas; /* Number of valid lbas in line */ - - __le32 *vsc; /* Valid sector count in line */ - - struct kref ref; /* Write buffer L2P references */ - atomic_t sec_to_update; /* Outstanding L2P updates to ppa */ - - struct pblk_w_err_gc *w_err_gc; /* Write error gc recovery metadata */ - - spinlock_t lock; /* Necessary for invalid_bitmap only */ -}; - -#define PBLK_DATA_LINES 4 - -enum { - PBLK_EMETA_TYPE_HEADER = 1, /* struct line_emeta first sector */ - PBLK_EMETA_TYPE_LLBA = 2, /* lba list - type: __le64 */ - PBLK_EMETA_TYPE_VSC = 3, /* vsc list - type: __le32 */ -}; - -struct pblk_line_mgmt { - int nr_lines; /* Total number of full lines */ - int nr_free_lines; /* Number of full lines in free list */ - - /* Free lists - use free_lock */ - struct list_head free_list; /* Full lines ready to use */ - struct list_head corrupt_list; /* Full lines corrupted */ - struct list_head bad_list; /* Full lines bad */ - - /* GC lists - use gc_lock */ - struct list_head *gc_lists[PBLK_GC_NR_LISTS]; - struct list_head gc_high_list; /* Full lines ready to GC, high isc */ - struct list_head gc_mid_list; /* Full lines ready to GC, mid isc */ - struct list_head gc_low_list; /* Full lines ready to GC, low isc */ - - struct list_head gc_werr_list; /* Write err recovery list */ - - struct list_head gc_full_list; /* Full lines ready to GC, no valid */ - struct list_head gc_empty_list; /* Full lines close, all valid */ - - struct pblk_line *log_line; /* Current FTL log line */ - struct pblk_line *data_line; /* Current data line */ - struct pblk_line *log_next; /* Next FTL log line */ - struct pblk_line *data_next; /* Next data line */ - - struct list_head emeta_list; /* Lines queued to schedule emeta */ - - __le32 *vsc_list; /* Valid sector counts for all lines */ - - /* Pre-allocated metadata for data lines */ - struct pblk_smeta *sline_meta[PBLK_DATA_LINES]; - struct pblk_emeta *eline_meta[PBLK_DATA_LINES]; - unsigned long meta_bitmap; - - /* Cache and mempool for map/invalid bitmaps */ - struct kmem_cache *bitmap_cache; - mempool_t *bitmap_pool; - - /* Helpers for fast bitmap calculations */ - unsigned long *bb_template; - unsigned long *bb_aux; - - unsigned long d_seq_nr; /* Data line unique sequence number */ - unsigned long l_seq_nr; /* Log line unique sequence number */ - - spinlock_t free_lock; - spinlock_t close_lock; - spinlock_t gc_lock; -}; - -struct pblk_line_meta { - unsigned int smeta_len; /* Total length for smeta */ - unsigned int smeta_sec; /* Sectors needed for smeta */ - - unsigned int emeta_len[4]; /* Lengths for emeta: - * [0]: Total - * [1]: struct line_emeta + - * bb_bitmap + struct wa_counters - * [2]: L2P portion - * [3]: vsc - */ - unsigned int emeta_sec[4]; /* Sectors needed for emeta. Same layout - * as emeta_len - */ - - unsigned int emeta_bb; /* Boundary for bb that affects emeta */ - - unsigned int vsc_list_len; /* Length for vsc list */ - unsigned int sec_bitmap_len; /* Length for sector bitmap in line */ - unsigned int blk_bitmap_len; /* Length for block bitmap in line */ - unsigned int lun_bitmap_len; /* Length for lun bitmap in line */ - - unsigned int blk_per_line; /* Number of blocks in a full line */ - unsigned int sec_per_line; /* Number of sectors in a line */ - unsigned int dsec_per_line; /* Number of data sectors in a line */ - unsigned int min_blk_line; /* Min. number of good blocks in line */ - - unsigned int mid_thrs; /* Threshold for GC mid list */ - unsigned int high_thrs; /* Threshold for GC high list */ - - unsigned int meta_distance; /* Distance between data and metadata */ -}; - -enum { - PBLK_STATE_RUNNING = 0, - PBLK_STATE_STOPPING = 1, - PBLK_STATE_RECOVERING = 2, - PBLK_STATE_STOPPED = 3, -}; - -/* Internal format to support not power-of-2 device formats */ -struct pblk_addrf { - /* gen to dev */ - int sec_stripe; - int ch_stripe; - int lun_stripe; - - /* dev to gen */ - int sec_lun_stripe; - int sec_ws_stripe; -}; - -struct pblk { - struct nvm_tgt_dev *dev; - struct gendisk *disk; - - struct kobject kobj; - - struct pblk_lun *luns; - - struct pblk_line *lines; /* Line array */ - struct pblk_line_mgmt l_mg; /* Line management */ - struct pblk_line_meta lm; /* Line metadata */ - - struct nvm_addrf addrf; /* Aligned address format */ - struct pblk_addrf uaddrf; /* Unaligned address format */ - int addrf_len; - - struct pblk_rb rwb; - - int state; /* pblk line state */ - - int min_write_pgs; /* Minimum amount of pages required by controller */ - int min_write_pgs_data; /* Minimum amount of payload pages */ - int max_write_pgs; /* Maximum amount of pages supported by controller */ - int oob_meta_size; /* Size of OOB sector metadata */ - - sector_t capacity; /* Device capacity when bad blocks are subtracted */ - - int op; /* Percentage of device used for over-provisioning */ - int op_blks; /* Number of blocks used for over-provisioning */ - - /* pblk provisioning values. Used by rate limiter */ - struct pblk_rl rl; - - int sec_per_write; - - guid_t instance_uuid; - - /* Persistent write amplification counters, 4kb sector I/Os */ - atomic64_t user_wa; /* Sectors written by user */ - atomic64_t gc_wa; /* Sectors written by GC */ - atomic64_t pad_wa; /* Padded sectors written */ - - /* Reset values for delta write amplification measurements */ - u64 user_rst_wa; - u64 gc_rst_wa; - u64 pad_rst_wa; - - /* Counters used for calculating padding distribution */ - atomic64_t *pad_dist; /* Padding distribution buckets */ - u64 nr_flush_rst; /* Flushes reset value for pad dist.*/ - atomic64_t nr_flush; /* Number of flush/fua I/O */ - -#ifdef CONFIG_NVM_PBLK_DEBUG - /* Non-persistent debug counters, 4kb sector I/Os */ - atomic_long_t inflight_writes; /* Inflight writes (user and gc) */ - atomic_long_t padded_writes; /* Sectors padded due to flush/fua */ - atomic_long_t padded_wb; /* Sectors padded in write buffer */ - atomic_long_t req_writes; /* Sectors stored on write buffer */ - atomic_long_t sub_writes; /* Sectors submitted from buffer */ - atomic_long_t sync_writes; /* Sectors synced to media */ - atomic_long_t inflight_reads; /* Inflight sector read requests */ - atomic_long_t cache_reads; /* Read requests that hit the cache */ - atomic_long_t sync_reads; /* Completed sector read requests */ - atomic_long_t recov_writes; /* Sectors submitted from recovery */ - atomic_long_t recov_gc_writes; /* Sectors submitted from write GC */ - atomic_long_t recov_gc_reads; /* Sectors submitted from read GC */ -#endif - - spinlock_t lock; - - atomic_long_t read_failed; - atomic_long_t read_empty; - atomic_long_t read_high_ecc; - atomic_long_t read_failed_gc; - atomic_long_t write_failed; - atomic_long_t erase_failed; - - atomic_t inflight_io; /* General inflight I/O counter */ - - struct task_struct *writer_ts; - - /* Simple translation map of logical addresses to physical addresses. - * The logical addresses is known by the host system, while the physical - * addresses are used when writing to the disk block device. - */ - unsigned char *trans_map; - spinlock_t trans_lock; - - struct list_head compl_list; - - spinlock_t resubmit_lock; /* Resubmit list lock */ - struct list_head resubmit_list; /* Resubmit list for failed writes*/ - - mempool_t page_bio_pool; - mempool_t gen_ws_pool; - mempool_t rec_pool; - mempool_t r_rq_pool; - mempool_t w_rq_pool; - mempool_t e_rq_pool; - - struct workqueue_struct *close_wq; - struct workqueue_struct *bb_wq; - struct workqueue_struct *r_end_wq; - - struct timer_list wtimer; - - struct pblk_gc gc; -}; - -struct pblk_line_ws { - struct pblk *pblk; - struct pblk_line *line; - void *priv; - struct work_struct ws; -}; - -#define pblk_g_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_g_ctx)) -#define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx)) - -#define pblk_err(pblk, fmt, ...) \ - pr_err("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__) -#define pblk_info(pblk, fmt, ...) \ - pr_info("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__) -#define pblk_warn(pblk, fmt, ...) \ - pr_warn("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__) -#define pblk_debug(pblk, fmt, ...) \ - pr_debug("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__) - -/* - * pblk ring buffer operations - */ -int pblk_rb_init(struct pblk_rb *rb, unsigned int size, unsigned int threshold, - unsigned int seg_sz); -int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio, - unsigned int nr_entries, unsigned int *pos); -int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries, - unsigned int *pos); -void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data, - struct pblk_w_ctx w_ctx, unsigned int pos); -void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data, - struct pblk_w_ctx w_ctx, struct pblk_line *line, - u64 paddr, unsigned int pos); -struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos); -void pblk_rb_flush(struct pblk_rb *rb); - -void pblk_rb_sync_l2p(struct pblk_rb *rb); -unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd, - unsigned int pos, unsigned int nr_entries, - unsigned int count); -int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba, - struct ppa_addr ppa); -unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries); - -unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags); -unsigned int pblk_rb_sync_advance(struct pblk_rb *rb, unsigned int nr_entries); -unsigned int pblk_rb_ptr_wrap(struct pblk_rb *rb, unsigned int p, - unsigned int nr_entries); -void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags); -unsigned int pblk_rb_flush_point_count(struct pblk_rb *rb); - -unsigned int pblk_rb_read_count(struct pblk_rb *rb); -unsigned int pblk_rb_sync_count(struct pblk_rb *rb); -unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos); - -int pblk_rb_tear_down_check(struct pblk_rb *rb); -int pblk_rb_pos_oob(struct pblk_rb *rb, u64 pos); -void pblk_rb_free(struct pblk_rb *rb); -ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf); - -/* - * pblk core - */ -struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type); -void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type); -int pblk_alloc_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd); -void pblk_free_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd); -void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write); -int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd, - struct pblk_c_ctx *c_ctx); -void pblk_discard(struct pblk *pblk, struct bio *bio); -struct nvm_chk_meta *pblk_get_chunk_meta(struct pblk *pblk); -struct nvm_chk_meta *pblk_chunk_get_off(struct pblk *pblk, - struct nvm_chk_meta *lp, - struct ppa_addr ppa); -void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd); -void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd); -int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd, void *buf); -int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd, void *buf); -int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line); -void pblk_check_chunk_state_update(struct pblk *pblk, struct nvm_rq *rqd); -struct pblk_line *pblk_line_get(struct pblk *pblk); -struct pblk_line *pblk_line_get_first_data(struct pblk *pblk); -struct pblk_line *pblk_line_replace_data(struct pblk *pblk); -void pblk_ppa_to_line_put(struct pblk *pblk, struct ppa_addr ppa); -void pblk_rq_to_line_put(struct pblk *pblk, struct nvm_rq *rqd); -int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line); -void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line); -struct pblk_line *pblk_line_get_data(struct pblk *pblk); -struct pblk_line *pblk_line_get_erase(struct pblk *pblk); -int pblk_line_erase(struct pblk *pblk, struct pblk_line *line); -int pblk_line_is_full(struct pblk_line *line); -void pblk_line_free(struct pblk_line *line); -void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line); -void pblk_line_close(struct pblk *pblk, struct pblk_line *line); -void pblk_line_close_ws(struct work_struct *work); -void pblk_pipeline_stop(struct pblk *pblk); -void __pblk_pipeline_stop(struct pblk *pblk); -void __pblk_pipeline_flush(struct pblk *pblk); -void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv, - void (*work)(struct work_struct *), gfp_t gfp_mask, - struct workqueue_struct *wq); -u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line); -int pblk_line_smeta_read(struct pblk *pblk, struct pblk_line *line); -int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line, - void *emeta_buf); -int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr erase_ppa); -void pblk_line_put(struct kref *ref); -void pblk_line_put_wq(struct kref *ref); -struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line); -u64 pblk_lookup_page(struct pblk *pblk, struct pblk_line *line); -void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs); -u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs); -u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs); -int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail, - unsigned long secs_to_flush, bool skip_meta); -void pblk_down_rq(struct pblk *pblk, struct ppa_addr ppa, - unsigned long *lun_bitmap); -void pblk_down_chunk(struct pblk *pblk, struct ppa_addr ppa); -void pblk_up_chunk(struct pblk *pblk, struct ppa_addr ppa); -void pblk_up_rq(struct pblk *pblk, unsigned long *lun_bitmap); -int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags, - int nr_pages); -void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off, - int nr_pages); -void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa); -void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line, - u64 paddr); -void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa); -void pblk_update_map_cache(struct pblk *pblk, sector_t lba, - struct ppa_addr ppa); -void pblk_update_map_dev(struct pblk *pblk, sector_t lba, - struct ppa_addr ppa, struct ppa_addr entry_line); -int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa, - struct pblk_line *gc_line, u64 paddr); -void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas, - u64 *lba_list, int nr_secs); -int pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas, - sector_t blba, int nr_secs, bool *from_cache); -void *pblk_get_meta_for_writes(struct pblk *pblk, struct nvm_rq *rqd); -void pblk_get_packed_meta(struct pblk *pblk, struct nvm_rq *rqd); - -/* - * pblk user I/O write path - */ -void pblk_write_to_cache(struct pblk *pblk, struct bio *bio, - unsigned long flags); -int pblk_write_gc_to_cache(struct pblk *pblk, struct pblk_gc_rq *gc_rq); - -/* - * pblk map - */ -int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd, - unsigned int sentry, unsigned long *lun_bitmap, - unsigned int valid_secs, struct ppa_addr *erase_ppa); -int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry, - unsigned long *lun_bitmap, unsigned int valid_secs, - unsigned int off); - -/* - * pblk write thread - */ -int pblk_write_ts(void *data); -void pblk_write_timer_fn(struct timer_list *t); -void pblk_write_should_kick(struct pblk *pblk); -void pblk_write_kick(struct pblk *pblk); - -/* - * pblk read path - */ -extern struct bio_set pblk_bio_set; -void pblk_submit_read(struct pblk *pblk, struct bio *bio); -int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq); -/* - * pblk recovery - */ -struct pblk_line *pblk_recov_l2p(struct pblk *pblk); -int pblk_recov_pad(struct pblk *pblk); -int pblk_recov_check_emeta(struct pblk *pblk, struct line_emeta *emeta); - -/* - * pblk gc - */ -#define PBLK_GC_MAX_READERS 8 /* Max number of outstanding GC reader jobs */ -#define PBLK_GC_RQ_QD 128 /* Queue depth for inflight GC requests */ -#define PBLK_GC_L_QD 4 /* Queue depth for inflight GC lines */ - -int pblk_gc_init(struct pblk *pblk); -void pblk_gc_exit(struct pblk *pblk, bool graceful); -void pblk_gc_should_start(struct pblk *pblk); -void pblk_gc_should_stop(struct pblk *pblk); -void pblk_gc_should_kick(struct pblk *pblk); -void pblk_gc_free_full_lines(struct pblk *pblk); -void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled, - int *gc_active); -int pblk_gc_sysfs_force(struct pblk *pblk, int force); -void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line); - -/* - * pblk rate limiter - */ -void pblk_rl_init(struct pblk_rl *rl, int budget, int threshold); -void pblk_rl_free(struct pblk_rl *rl); -void pblk_rl_update_rates(struct pblk_rl *rl); -int pblk_rl_high_thrs(struct pblk_rl *rl); -unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl); -unsigned long pblk_rl_nr_user_free_blks(struct pblk_rl *rl); -int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries); -void pblk_rl_inserted(struct pblk_rl *rl, int nr_entries); -void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries); -int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries); -void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries); -void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc); -int pblk_rl_max_io(struct pblk_rl *rl); -void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line); -void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line, - bool used); -int pblk_rl_is_limit(struct pblk_rl *rl); - -void pblk_rl_werr_line_in(struct pblk_rl *rl); -void pblk_rl_werr_line_out(struct pblk_rl *rl); - -/* - * pblk sysfs - */ -int pblk_sysfs_init(struct gendisk *tdisk); -void pblk_sysfs_exit(struct gendisk *tdisk); - -static inline struct nvm_rq *nvm_rq_from_c_ctx(void *c_ctx) -{ - return c_ctx - sizeof(struct nvm_rq); -} - -static inline void *emeta_to_bb(struct line_emeta *emeta) -{ - return emeta->bb_bitmap; -} - -static inline void *emeta_to_wa(struct pblk_line_meta *lm, - struct line_emeta *emeta) -{ - return emeta->bb_bitmap + lm->blk_bitmap_len; -} - -static inline void *emeta_to_lbas(struct pblk *pblk, struct line_emeta *emeta) -{ - return ((void *)emeta + pblk->lm.emeta_len[1]); -} - -static inline void *emeta_to_vsc(struct pblk *pblk, struct line_emeta *emeta) -{ - return (emeta_to_lbas(pblk, emeta) + pblk->lm.emeta_len[2]); -} - -static inline int pblk_line_vsc(struct pblk_line *line) -{ - return le32_to_cpu(*line->vsc); -} - -static inline int pblk_ppa_to_line_id(struct ppa_addr p) -{ - return p.a.blk; -} - -static inline struct pblk_line *pblk_ppa_to_line(struct pblk *pblk, - struct ppa_addr p) -{ - return &pblk->lines[pblk_ppa_to_line_id(p)]; -} - -static inline int pblk_ppa_to_pos(struct nvm_geo *geo, struct ppa_addr p) -{ - return p.a.lun * geo->num_ch + p.a.ch; -} - -static inline struct ppa_addr addr_to_gen_ppa(struct pblk *pblk, u64 paddr, - u64 line_id) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct ppa_addr ppa; - - if (geo->version == NVM_OCSSD_SPEC_12) { - struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&pblk->addrf; - - ppa.ppa = 0; - ppa.g.blk = line_id; - ppa.g.pg = (paddr & ppaf->pg_mask) >> ppaf->pg_offset; - ppa.g.lun = (paddr & ppaf->lun_mask) >> ppaf->lun_offset; - ppa.g.ch = (paddr & ppaf->ch_mask) >> ppaf->ch_offset; - ppa.g.pl = (paddr & ppaf->pln_mask) >> ppaf->pln_offset; - ppa.g.sec = (paddr & ppaf->sec_mask) >> ppaf->sec_offset; - } else { - struct pblk_addrf *uaddrf = &pblk->uaddrf; - int secs, chnls, luns; - - ppa.ppa = 0; - - ppa.m.chk = line_id; - - paddr = div_u64_rem(paddr, uaddrf->sec_stripe, &secs); - ppa.m.sec = secs; - - paddr = div_u64_rem(paddr, uaddrf->ch_stripe, &chnls); - ppa.m.grp = chnls; - - paddr = div_u64_rem(paddr, uaddrf->lun_stripe, &luns); - ppa.m.pu = luns; - - ppa.m.sec += uaddrf->sec_stripe * paddr; - } - - return ppa; -} - -static inline struct nvm_chk_meta *pblk_dev_ppa_to_chunk(struct pblk *pblk, - struct ppa_addr p) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - struct pblk_line *line = pblk_ppa_to_line(pblk, p); - int pos = pblk_ppa_to_pos(geo, p); - - return &line->chks[pos]; -} - -static inline u64 pblk_dev_ppa_to_chunk_addr(struct pblk *pblk, - struct ppa_addr p) -{ - struct nvm_tgt_dev *dev = pblk->dev; - - return dev_to_chunk_addr(dev->parent, &pblk->addrf, p); -} - -static inline u64 pblk_dev_ppa_to_line_addr(struct pblk *pblk, - struct ppa_addr p) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - u64 paddr; - - if (geo->version == NVM_OCSSD_SPEC_12) { - struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&pblk->addrf; - - paddr = (u64)p.g.ch << ppaf->ch_offset; - paddr |= (u64)p.g.lun << ppaf->lun_offset; - paddr |= (u64)p.g.pg << ppaf->pg_offset; - paddr |= (u64)p.g.pl << ppaf->pln_offset; - paddr |= (u64)p.g.sec << ppaf->sec_offset; - } else { - struct pblk_addrf *uaddrf = &pblk->uaddrf; - u64 secs = p.m.sec; - int sec_stripe; - - paddr = (u64)p.m.grp * uaddrf->sec_stripe; - paddr += (u64)p.m.pu * uaddrf->sec_lun_stripe; - - secs = div_u64_rem(secs, uaddrf->sec_stripe, &sec_stripe); - paddr += secs * uaddrf->sec_ws_stripe; - paddr += sec_stripe; - } - - return paddr; -} - -static inline struct ppa_addr pblk_ppa32_to_ppa64(struct pblk *pblk, u32 ppa32) -{ - struct nvm_tgt_dev *dev = pblk->dev; - - return nvm_ppa32_to_ppa64(dev->parent, &pblk->addrf, ppa32); -} - -static inline u32 pblk_ppa64_to_ppa32(struct pblk *pblk, struct ppa_addr ppa64) -{ - struct nvm_tgt_dev *dev = pblk->dev; - - return nvm_ppa64_to_ppa32(dev->parent, &pblk->addrf, ppa64); -} - -static inline struct ppa_addr pblk_trans_map_get(struct pblk *pblk, - sector_t lba) -{ - struct ppa_addr ppa; - - if (pblk->addrf_len < 32) { - u32 *map = (u32 *)pblk->trans_map; - - ppa = pblk_ppa32_to_ppa64(pblk, map[lba]); - } else { - struct ppa_addr *map = (struct ppa_addr *)pblk->trans_map; - - ppa = map[lba]; - } - - return ppa; -} - -static inline void pblk_trans_map_set(struct pblk *pblk, sector_t lba, - struct ppa_addr ppa) -{ - if (pblk->addrf_len < 32) { - u32 *map = (u32 *)pblk->trans_map; - - map[lba] = pblk_ppa64_to_ppa32(pblk, ppa); - } else { - u64 *map = (u64 *)pblk->trans_map; - - map[lba] = ppa.ppa; - } -} - -static inline int pblk_ppa_empty(struct ppa_addr ppa_addr) -{ - return (ppa_addr.ppa == ADDR_EMPTY); -} - -static inline void pblk_ppa_set_empty(struct ppa_addr *ppa_addr) -{ - ppa_addr->ppa = ADDR_EMPTY; -} - -static inline bool pblk_ppa_comp(struct ppa_addr lppa, struct ppa_addr rppa) -{ - return (lppa.ppa == rppa.ppa); -} - -static inline int pblk_addr_in_cache(struct ppa_addr ppa) -{ - return (ppa.ppa != ADDR_EMPTY && ppa.c.is_cached); -} - -static inline int pblk_addr_to_cacheline(struct ppa_addr ppa) -{ - return ppa.c.line; -} - -static inline struct ppa_addr pblk_cacheline_to_addr(int addr) -{ - struct ppa_addr p; - - p.c.line = addr; - p.c.is_cached = 1; - - return p; -} - -static inline u32 pblk_calc_meta_header_crc(struct pblk *pblk, - struct line_header *header) -{ - u32 crc = ~(u32)0; - - crc = crc32_le(crc, (unsigned char *)header + sizeof(crc), - sizeof(struct line_header) - sizeof(crc)); - - return crc; -} - -static inline u32 pblk_calc_smeta_crc(struct pblk *pblk, - struct line_smeta *smeta) -{ - struct pblk_line_meta *lm = &pblk->lm; - u32 crc = ~(u32)0; - - crc = crc32_le(crc, (unsigned char *)smeta + - sizeof(struct line_header) + sizeof(crc), - lm->smeta_len - - sizeof(struct line_header) - sizeof(crc)); - - return crc; -} - -static inline u32 pblk_calc_emeta_crc(struct pblk *pblk, - struct line_emeta *emeta) -{ - struct pblk_line_meta *lm = &pblk->lm; - u32 crc = ~(u32)0; - - crc = crc32_le(crc, (unsigned char *)emeta + - sizeof(struct line_header) + sizeof(crc), - lm->emeta_len[0] - - sizeof(struct line_header) - sizeof(crc)); - - return crc; -} - -static inline int pblk_io_aligned(struct pblk *pblk, int nr_secs) -{ - return !(nr_secs % pblk->min_write_pgs); -} - -#ifdef CONFIG_NVM_PBLK_DEBUG -static inline void print_ppa(struct pblk *pblk, struct ppa_addr *p, - char *msg, int error) -{ - struct nvm_geo *geo = &pblk->dev->geo; - - if (p->c.is_cached) { - pblk_err(pblk, "ppa: (%s: %x) cache line: %llu\n", - msg, error, (u64)p->c.line); - } else if (geo->version == NVM_OCSSD_SPEC_12) { - pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n", - msg, error, - p->g.ch, p->g.lun, p->g.blk, - p->g.pg, p->g.pl, p->g.sec); - } else { - pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n", - msg, error, - p->m.grp, p->m.pu, p->m.chk, p->m.sec); - } -} - -static inline void pblk_print_failed_rqd(struct pblk *pblk, struct nvm_rq *rqd, - int error) -{ - int bit = -1; - - if (rqd->nr_ppas == 1) { - print_ppa(pblk, &rqd->ppa_addr, "rqd", error); - return; - } - - while ((bit = find_next_bit((void *)&rqd->ppa_status, rqd->nr_ppas, - bit + 1)) < rqd->nr_ppas) { - print_ppa(pblk, &rqd->ppa_list[bit], "rqd", error); - } - - pblk_err(pblk, "error:%d, ppa_status:%llx\n", error, rqd->ppa_status); -} - -static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev, - struct ppa_addr *ppas, int nr_ppas) -{ - struct nvm_geo *geo = &tgt_dev->geo; - struct ppa_addr *ppa; - int i; - - for (i = 0; i < nr_ppas; i++) { - ppa = &ppas[i]; - - if (geo->version == NVM_OCSSD_SPEC_12) { - if (!ppa->c.is_cached && - ppa->g.ch < geo->num_ch && - ppa->g.lun < geo->num_lun && - ppa->g.pl < geo->num_pln && - ppa->g.blk < geo->num_chk && - ppa->g.pg < geo->num_pg && - ppa->g.sec < geo->ws_min) - continue; - } else { - if (!ppa->c.is_cached && - ppa->m.grp < geo->num_ch && - ppa->m.pu < geo->num_lun && - ppa->m.chk < geo->num_chk && - ppa->m.sec < geo->clba) - continue; - } - - print_ppa(tgt_dev->q->queuedata, ppa, "boundary", i); - - return 1; - } - return 0; -} - -static inline int pblk_check_io(struct pblk *pblk, struct nvm_rq *rqd) -{ - struct nvm_tgt_dev *dev = pblk->dev; - struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd); - - if (pblk_boundary_ppa_checks(dev, ppa_list, rqd->nr_ppas)) { - WARN_ON(1); - return -EINVAL; - } - - if (rqd->opcode == NVM_OP_PWRITE) { - struct pblk_line *line; - int i; - - for (i = 0; i < rqd->nr_ppas; i++) { - line = pblk_ppa_to_line(pblk, ppa_list[i]); - - spin_lock(&line->lock); - if (line->state != PBLK_LINESTATE_OPEN) { - pblk_err(pblk, "bad ppa: line:%d,state:%d\n", - line->id, line->state); - WARN_ON(1); - spin_unlock(&line->lock); - return -EINVAL; - } - spin_unlock(&line->lock); - } - } - - return 0; -} -#endif - -static inline int pblk_boundary_paddr_checks(struct pblk *pblk, u64 paddr) -{ - struct pblk_line_meta *lm = &pblk->lm; - - if (paddr > lm->sec_per_line) - return 1; - - return 0; -} - -static inline unsigned int pblk_get_bi_idx(struct bio *bio) -{ - return bio->bi_iter.bi_idx; -} - -static inline sector_t pblk_get_lba(struct bio *bio) -{ - return bio->bi_iter.bi_sector / NR_PHY_IN_LOG; -} - -static inline unsigned int pblk_get_secs(struct bio *bio) -{ - return bio->bi_iter.bi_size / PBLK_EXPOSED_PAGE_SIZE; -} - -static inline char *pblk_disk_name(struct pblk *pblk) -{ - struct gendisk *disk = pblk->disk; - - return disk->disk_name; -} - -static inline unsigned int pblk_get_min_chks(struct pblk *pblk) -{ - struct pblk_line_meta *lm = &pblk->lm; - /* In a worst-case scenario every line will have OP invalid sectors. - * We will then need a minimum of 1/OP lines to free up a single line - */ - - return DIV_ROUND_UP(100, pblk->op) * lm->blk_per_line; -} - -static inline struct pblk_sec_meta *pblk_get_meta(struct pblk *pblk, - void *meta, int index) -{ - return meta + - max_t(int, sizeof(struct pblk_sec_meta), pblk->oob_meta_size) - * index; -} - -static inline int pblk_dma_meta_size(struct pblk *pblk) -{ - return max_t(int, sizeof(struct pblk_sec_meta), pblk->oob_meta_size) - * NVM_MAX_VLBA; -} - -static inline int pblk_is_oob_meta_supported(struct pblk *pblk) -{ - return pblk->oob_meta_size >= sizeof(struct pblk_sec_meta); -} -#endif /* PBLK_H_ */ diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile index cbc509784b2e..dfaacd472e5d 100644 --- a/drivers/nvme/host/Makefile +++ b/drivers/nvme/host/Makefile @@ -12,7 +12,6 @@ obj-$(CONFIG_NVME_TCP) += nvme-tcp.o nvme-core-y := core.o ioctl.o nvme-core-$(CONFIG_TRACING) += trace.o nvme-core-$(CONFIG_NVME_MULTIPATH) += multipath.o -nvme-core-$(CONFIG_NVM) += lightnvm.o nvme-core-$(CONFIG_BLK_DEV_ZONED) += zns.o nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS) += fault_inject.o nvme-core-$(CONFIG_NVME_HWMON) += hwmon.o diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index dfd9dec0c1f6..ce33014e3eb0 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -587,9 +587,6 @@ static void nvme_free_ns(struct kref *kref) { struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref); - if (ns->ndev) - nvme_nvm_unregister(ns); - put_disk(ns->disk); nvme_put_ns_head(ns->head); nvme_put_ctrl(ns->ctrl); @@ -3218,9 +3215,6 @@ static const struct attribute_group nvme_ns_id_attr_group = { const struct attribute_group *nvme_ns_id_attr_groups[] = { &nvme_ns_id_attr_group, -#ifdef CONFIG_NVM - &nvme_nvm_attr_group, -#endif NULL, }; @@ -3767,13 +3761,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, if (nvme_update_ns_info(ns, id)) goto out_put_disk; - if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) { - if (nvme_nvm_register(ns, disk->disk_name, node)) { - dev_warn(ctrl->device, "LightNVM init failure\n"); - goto out_put_disk; - } - } - down_write(&ctrl->namespaces_rwsem); list_add_tail(&ns->list, &ctrl->namespaces); up_write(&ctrl->namespaces_rwsem); diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 305ddd415e45..22314962842d 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -342,9 +342,7 @@ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd, case NVME_IOCTL_IO64_CMD: return nvme_user_cmd64(ns->ctrl, ns, argp); default: - if (!ns->ndev) - return -ENOTTY; - return nvme_nvm_ioctl(ns, cmd, argp); + return -ENOTTY; } } diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c deleted file mode 100644 index e9d9ad47f70f..000000000000 --- a/drivers/nvme/host/lightnvm.c +++ /dev/null @@ -1,1274 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * nvme-lightnvm.c - LightNVM NVMe device - * - * Copyright (C) 2014-2015 IT University of Copenhagen - * Initial release: Matias Bjorling - */ - -#include "nvme.h" - -#include -#include -#include -#include -#include -#include - -enum nvme_nvm_admin_opcode { - nvme_nvm_admin_identity = 0xe2, - nvme_nvm_admin_get_bb_tbl = 0xf2, - nvme_nvm_admin_set_bb_tbl = 0xf1, -}; - -enum nvme_nvm_log_page { - NVME_NVM_LOG_REPORT_CHUNK = 0xca, -}; - -struct nvme_nvm_ph_rw { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2; - __le64 metadata; - __le64 prp1; - __le64 prp2; - __le64 spba; - __le16 length; - __le16 control; - __le32 dsmgmt; - __le64 resv; -}; - -struct nvme_nvm_erase_blk { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd[2]; - __le64 prp1; - __le64 prp2; - __le64 spba; - __le16 length; - __le16 control; - __le32 dsmgmt; - __le64 resv; -}; - -struct nvme_nvm_identity { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd[2]; - __le64 prp1; - __le64 prp2; - __u32 rsvd11[6]; -}; - -struct nvme_nvm_getbbtbl { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd[2]; - __le64 prp1; - __le64 prp2; - __le64 spba; - __u32 rsvd4[4]; -}; - -struct nvme_nvm_setbbtbl { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __le64 rsvd[2]; - __le64 prp1; - __le64 prp2; - __le64 spba; - __le16 nlb; - __u8 value; - __u8 rsvd3; - __u32 rsvd4[3]; -}; - -struct nvme_nvm_command { - union { - struct nvme_common_command common; - struct nvme_nvm_ph_rw ph_rw; - struct nvme_nvm_erase_blk erase; - struct nvme_nvm_identity identity; - struct nvme_nvm_getbbtbl get_bb; - struct nvme_nvm_setbbtbl set_bb; - }; -}; - -struct nvme_nvm_id12_grp { - __u8 mtype; - __u8 fmtype; - __le16 res16; - __u8 num_ch; - __u8 num_lun; - __u8 num_pln; - __u8 rsvd1; - __le16 num_chk; - __le16 num_pg; - __le16 fpg_sz; - __le16 csecs; - __le16 sos; - __le16 rsvd2; - __le32 trdt; - __le32 trdm; - __le32 tprt; - __le32 tprm; - __le32 tbet; - __le32 tbem; - __le32 mpos; - __le32 mccap; - __le16 cpar; - __u8 reserved[906]; -} __packed; - -struct nvme_nvm_id12_addrf { - __u8 ch_offset; - __u8 ch_len; - __u8 lun_offset; - __u8 lun_len; - __u8 pln_offset; - __u8 pln_len; - __u8 blk_offset; - __u8 blk_len; - __u8 pg_offset; - __u8 pg_len; - __u8 sec_offset; - __u8 sec_len; - __u8 res[4]; -} __packed; - -struct nvme_nvm_id12 { - __u8 ver_id; - __u8 vmnt; - __u8 cgrps; - __u8 res; - __le32 cap; - __le32 dom; - struct nvme_nvm_id12_addrf ppaf; - __u8 resv[228]; - struct nvme_nvm_id12_grp grp; - __u8 resv2[2880]; -} __packed; - -struct nvme_nvm_bb_tbl { - __u8 tblid[4]; - __le16 verid; - __le16 revid; - __le32 rvsd1; - __le32 tblks; - __le32 tfact; - __le32 tgrown; - __le32 tdresv; - __le32 thresv; - __le32 rsvd2[8]; - __u8 blk[]; -}; - -struct nvme_nvm_id20_addrf { - __u8 grp_len; - __u8 pu_len; - __u8 chk_len; - __u8 lba_len; - __u8 resv[4]; -}; - -struct nvme_nvm_id20 { - __u8 mjr; - __u8 mnr; - __u8 resv[6]; - - struct nvme_nvm_id20_addrf lbaf; - - __le32 mccap; - __u8 resv2[12]; - - __u8 wit; - __u8 resv3[31]; - - /* Geometry */ - __le16 num_grp; - __le16 num_pu; - __le32 num_chk; - __le32 clba; - __u8 resv4[52]; - - /* Write data requirements */ - __le32 ws_min; - __le32 ws_opt; - __le32 mw_cunits; - __le32 maxoc; - __le32 maxocpu; - __u8 resv5[44]; - - /* Performance related metrics */ - __le32 trdt; - __le32 trdm; - __le32 twrt; - __le32 twrm; - __le32 tcrst; - __le32 tcrsm; - __u8 resv6[40]; - - /* Reserved area */ - __u8 resv7[2816]; - - /* Vendor specific */ - __u8 vs[1024]; -}; - -struct nvme_nvm_chk_meta { - __u8 state; - __u8 type; - __u8 wi; - __u8 rsvd[5]; - __le64 slba; - __le64 cnlb; - __le64 wp; -}; - -/* - * Check we didn't inadvertently grow the command struct - */ -static inline void _nvme_nvm_check_size(void) -{ - BUILD_BUG_ON(sizeof(struct nvme_nvm_identity) != 64); - BUILD_BUG_ON(sizeof(struct nvme_nvm_ph_rw) != 64); - BUILD_BUG_ON(sizeof(struct nvme_nvm_erase_blk) != 64); - BUILD_BUG_ON(sizeof(struct nvme_nvm_getbbtbl) != 64); - BUILD_BUG_ON(sizeof(struct nvme_nvm_setbbtbl) != 64); - BUILD_BUG_ON(sizeof(struct nvme_nvm_id12_grp) != 960); - BUILD_BUG_ON(sizeof(struct nvme_nvm_id12_addrf) != 16); - BUILD_BUG_ON(sizeof(struct nvme_nvm_id12) != NVME_IDENTIFY_DATA_SIZE); - BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 64); - BUILD_BUG_ON(sizeof(struct nvme_nvm_id20_addrf) != 8); - BUILD_BUG_ON(sizeof(struct nvme_nvm_id20) != NVME_IDENTIFY_DATA_SIZE); - BUILD_BUG_ON(sizeof(struct nvme_nvm_chk_meta) != 32); - BUILD_BUG_ON(sizeof(struct nvme_nvm_chk_meta) != - sizeof(struct nvm_chk_meta)); -} - -static void nvme_nvm_set_addr_12(struct nvm_addrf_12 *dst, - struct nvme_nvm_id12_addrf *src) -{ - dst->ch_len = src->ch_len; - dst->lun_len = src->lun_len; - dst->blk_len = src->blk_len; - dst->pg_len = src->pg_len; - dst->pln_len = src->pln_len; - dst->sec_len = src->sec_len; - - dst->ch_offset = src->ch_offset; - dst->lun_offset = src->lun_offset; - dst->blk_offset = src->blk_offset; - dst->pg_offset = src->pg_offset; - dst->pln_offset = src->pln_offset; - dst->sec_offset = src->sec_offset; - - dst->ch_mask = ((1ULL << dst->ch_len) - 1) << dst->ch_offset; - dst->lun_mask = ((1ULL << dst->lun_len) - 1) << dst->lun_offset; - dst->blk_mask = ((1ULL << dst->blk_len) - 1) << dst->blk_offset; - dst->pg_mask = ((1ULL << dst->pg_len) - 1) << dst->pg_offset; - dst->pln_mask = ((1ULL << dst->pln_len) - 1) << dst->pln_offset; - dst->sec_mask = ((1ULL << dst->sec_len) - 1) << dst->sec_offset; -} - -static int nvme_nvm_setup_12(struct nvme_nvm_id12 *id, - struct nvm_geo *geo) -{ - struct nvme_nvm_id12_grp *src; - int sec_per_pg, sec_per_pl, pg_per_blk; - - if (id->cgrps != 1) - return -EINVAL; - - src = &id->grp; - - if (src->mtype != 0) { - pr_err("nvm: memory type not supported\n"); - return -EINVAL; - } - - /* 1.2 spec. only reports a single version id - unfold */ - geo->major_ver_id = id->ver_id; - geo->minor_ver_id = 2; - - /* Set compacted version for upper layers */ - geo->version = NVM_OCSSD_SPEC_12; - - geo->num_ch = src->num_ch; - geo->num_lun = src->num_lun; - geo->all_luns = geo->num_ch * geo->num_lun; - - geo->num_chk = le16_to_cpu(src->num_chk); - - geo->csecs = le16_to_cpu(src->csecs); - geo->sos = le16_to_cpu(src->sos); - - pg_per_blk = le16_to_cpu(src->num_pg); - sec_per_pg = le16_to_cpu(src->fpg_sz) / geo->csecs; - sec_per_pl = sec_per_pg * src->num_pln; - geo->clba = sec_per_pl * pg_per_blk; - - geo->all_chunks = geo->all_luns * geo->num_chk; - geo->total_secs = geo->clba * geo->all_chunks; - - geo->ws_min = sec_per_pg; - geo->ws_opt = sec_per_pg; - geo->mw_cunits = geo->ws_opt << 3; /* default to MLC safe values */ - - /* Do not impose values for maximum number of open blocks as it is - * unspecified in 1.2. Users of 1.2 must be aware of this and eventually - * specify these values through a quirk if restrictions apply. - */ - geo->maxoc = geo->all_luns * geo->num_chk; - geo->maxocpu = geo->num_chk; - - geo->mccap = le32_to_cpu(src->mccap); - - geo->trdt = le32_to_cpu(src->trdt); - geo->trdm = le32_to_cpu(src->trdm); - geo->tprt = le32_to_cpu(src->tprt); - geo->tprm = le32_to_cpu(src->tprm); - geo->tbet = le32_to_cpu(src->tbet); - geo->tbem = le32_to_cpu(src->tbem); - - /* 1.2 compatibility */ - geo->vmnt = id->vmnt; - geo->cap = le32_to_cpu(id->cap); - geo->dom = le32_to_cpu(id->dom); - - geo->mtype = src->mtype; - geo->fmtype = src->fmtype; - - geo->cpar = le16_to_cpu(src->cpar); - geo->mpos = le32_to_cpu(src->mpos); - - geo->pln_mode = NVM_PLANE_SINGLE; - - if (geo->mpos & 0x020202) { - geo->pln_mode = NVM_PLANE_DOUBLE; - geo->ws_opt <<= 1; - } else if (geo->mpos & 0x040404) { - geo->pln_mode = NVM_PLANE_QUAD; - geo->ws_opt <<= 2; - } - - geo->num_pln = src->num_pln; - geo->num_pg = le16_to_cpu(src->num_pg); - geo->fpg_sz = le16_to_cpu(src->fpg_sz); - - nvme_nvm_set_addr_12((struct nvm_addrf_12 *)&geo->addrf, &id->ppaf); - - return 0; -} - -static void nvme_nvm_set_addr_20(struct nvm_addrf *dst, - struct nvme_nvm_id20_addrf *src) -{ - dst->ch_len = src->grp_len; - dst->lun_len = src->pu_len; - dst->chk_len = src->chk_len; - dst->sec_len = src->lba_len; - - dst->sec_offset = 0; - dst->chk_offset = dst->sec_len; - dst->lun_offset = dst->chk_offset + dst->chk_len; - dst->ch_offset = dst->lun_offset + dst->lun_len; - - dst->ch_mask = ((1ULL << dst->ch_len) - 1) << dst->ch_offset; - dst->lun_mask = ((1ULL << dst->lun_len) - 1) << dst->lun_offset; - dst->chk_mask = ((1ULL << dst->chk_len) - 1) << dst->chk_offset; - dst->sec_mask = ((1ULL << dst->sec_len) - 1) << dst->sec_offset; -} - -static int nvme_nvm_setup_20(struct nvme_nvm_id20 *id, - struct nvm_geo *geo) -{ - geo->major_ver_id = id->mjr; - geo->minor_ver_id = id->mnr; - - /* Set compacted version for upper layers */ - geo->version = NVM_OCSSD_SPEC_20; - - geo->num_ch = le16_to_cpu(id->num_grp); - geo->num_lun = le16_to_cpu(id->num_pu); - geo->all_luns = geo->num_ch * geo->num_lun; - - geo->num_chk = le32_to_cpu(id->num_chk); - geo->clba = le32_to_cpu(id->clba); - - geo->all_chunks = geo->all_luns * geo->num_chk; - geo->total_secs = geo->clba * geo->all_chunks; - - geo->ws_min = le32_to_cpu(id->ws_min); - geo->ws_opt = le32_to_cpu(id->ws_opt); - geo->mw_cunits = le32_to_cpu(id->mw_cunits); - geo->maxoc = le32_to_cpu(id->maxoc); - geo->maxocpu = le32_to_cpu(id->maxocpu); - - geo->trdt = le32_to_cpu(id->trdt); - geo->trdm = le32_to_cpu(id->trdm); - geo->tprt = le32_to_cpu(id->twrt); - geo->tprm = le32_to_cpu(id->twrm); - geo->tbet = le32_to_cpu(id->tcrst); - geo->tbem = le32_to_cpu(id->tcrsm); - - nvme_nvm_set_addr_20(&geo->addrf, &id->lbaf); - - return 0; -} - -static int nvme_nvm_identity(struct nvm_dev *nvmdev) -{ - struct nvme_ns *ns = nvmdev->q->queuedata; - struct nvme_nvm_id12 *id; - struct nvme_nvm_command c = {}; - int ret; - - c.identity.opcode = nvme_nvm_admin_identity; - c.identity.nsid = cpu_to_le32(ns->head->ns_id); - - id = kmalloc(sizeof(struct nvme_nvm_id12), GFP_KERNEL); - if (!id) - return -ENOMEM; - - ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, (struct nvme_command *)&c, - id, sizeof(struct nvme_nvm_id12)); - if (ret) { - ret = -EIO; - goto out; - } - - /* - * The 1.2 and 2.0 specifications share the first byte in their geometry - * command to make it possible to know what version a device implements. - */ - switch (id->ver_id) { - case 1: - ret = nvme_nvm_setup_12(id, &nvmdev->geo); - break; - case 2: - ret = nvme_nvm_setup_20((struct nvme_nvm_id20 *)id, - &nvmdev->geo); - break; - default: - dev_err(ns->ctrl->device, "OCSSD revision not supported (%d)\n", - id->ver_id); - ret = -EINVAL; - } - -out: - kfree(id); - return ret; -} - -static int nvme_nvm_get_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr ppa, - u8 *blks) -{ - struct request_queue *q = nvmdev->q; - struct nvm_geo *geo = &nvmdev->geo; - struct nvme_ns *ns = q->queuedata; - struct nvme_ctrl *ctrl = ns->ctrl; - struct nvme_nvm_command c = {}; - struct nvme_nvm_bb_tbl *bb_tbl; - int nr_blks = geo->num_chk * geo->num_pln; - int tblsz = sizeof(struct nvme_nvm_bb_tbl) + nr_blks; - int ret = 0; - - c.get_bb.opcode = nvme_nvm_admin_get_bb_tbl; - c.get_bb.nsid = cpu_to_le32(ns->head->ns_id); - c.get_bb.spba = cpu_to_le64(ppa.ppa); - - bb_tbl = kzalloc(tblsz, GFP_KERNEL); - if (!bb_tbl) - return -ENOMEM; - - ret = nvme_submit_sync_cmd(ctrl->admin_q, (struct nvme_command *)&c, - bb_tbl, tblsz); - if (ret) { - dev_err(ctrl->device, "get bad block table failed (%d)\n", ret); - ret = -EIO; - goto out; - } - - if (bb_tbl->tblid[0] != 'B' || bb_tbl->tblid[1] != 'B' || - bb_tbl->tblid[2] != 'L' || bb_tbl->tblid[3] != 'T') { - dev_err(ctrl->device, "bbt format mismatch\n"); - ret = -EINVAL; - goto out; - } - - if (le16_to_cpu(bb_tbl->verid) != 1) { - ret = -EINVAL; - dev_err(ctrl->device, "bbt version not supported\n"); - goto out; - } - - if (le32_to_cpu(bb_tbl->tblks) != nr_blks) { - ret = -EINVAL; - dev_err(ctrl->device, - "bbt unsuspected blocks returned (%u!=%u)", - le32_to_cpu(bb_tbl->tblks), nr_blks); - goto out; - } - - memcpy(blks, bb_tbl->blk, geo->num_chk * geo->num_pln); -out: - kfree(bb_tbl); - return ret; -} - -static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr *ppas, - int nr_ppas, int type) -{ - struct nvme_ns *ns = nvmdev->q->queuedata; - struct nvme_nvm_command c = {}; - int ret = 0; - - c.set_bb.opcode = nvme_nvm_admin_set_bb_tbl; - c.set_bb.nsid = cpu_to_le32(ns->head->ns_id); - c.set_bb.spba = cpu_to_le64(ppas->ppa); - c.set_bb.nlb = cpu_to_le16(nr_ppas - 1); - c.set_bb.value = type; - - ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, (struct nvme_command *)&c, - NULL, 0); - if (ret) - dev_err(ns->ctrl->device, "set bad block table failed (%d)\n", - ret); - return ret; -} - -/* - * Expect the lba in device format - */ -static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev, - sector_t slba, int nchks, - struct nvm_chk_meta *meta) -{ - struct nvm_geo *geo = &ndev->geo; - struct nvme_ns *ns = ndev->q->queuedata; - struct nvme_ctrl *ctrl = ns->ctrl; - struct nvme_nvm_chk_meta *dev_meta, *dev_meta_off; - struct ppa_addr ppa; - size_t left = nchks * sizeof(struct nvme_nvm_chk_meta); - size_t log_pos, offset, len; - int i, max_len; - int ret = 0; - - /* - * limit requests to maximum 256K to avoid issuing arbitrary large - * requests when the device does not specific a maximum transfer size. - */ - max_len = min_t(unsigned int, ctrl->max_hw_sectors << 9, 256 * 1024); - - dev_meta = kmalloc(max_len, GFP_KERNEL); - if (!dev_meta) - return -ENOMEM; - - /* Normalize lba address space to obtain log offset */ - ppa.ppa = slba; - ppa = dev_to_generic_addr(ndev, ppa); - - log_pos = ppa.m.chk; - log_pos += ppa.m.pu * geo->num_chk; - log_pos += ppa.m.grp * geo->num_lun * geo->num_chk; - - offset = log_pos * sizeof(struct nvme_nvm_chk_meta); - - while (left) { - len = min_t(unsigned int, left, max_len); - - memset(dev_meta, 0, max_len); - dev_meta_off = dev_meta; - - ret = nvme_get_log(ctrl, ns->head->ns_id, - NVME_NVM_LOG_REPORT_CHUNK, 0, NVME_CSI_NVM, - dev_meta, len, offset); - if (ret) { - dev_err(ctrl->device, "Get REPORT CHUNK log error\n"); - break; - } - - for (i = 0; i < len; i += sizeof(struct nvme_nvm_chk_meta)) { - meta->state = dev_meta_off->state; - meta->type = dev_meta_off->type; - meta->wi = dev_meta_off->wi; - meta->slba = le64_to_cpu(dev_meta_off->slba); - meta->cnlb = le64_to_cpu(dev_meta_off->cnlb); - meta->wp = le64_to_cpu(dev_meta_off->wp); - - meta++; - dev_meta_off++; - } - - offset += len; - left -= len; - } - - kfree(dev_meta); - - return ret; -} - -static inline void nvme_nvm_rqtocmd(struct nvm_rq *rqd, struct nvme_ns *ns, - struct nvme_nvm_command *c) -{ - c->ph_rw.opcode = rqd->opcode; - c->ph_rw.nsid = cpu_to_le32(ns->head->ns_id); - c->ph_rw.spba = cpu_to_le64(rqd->ppa_addr.ppa); - c->ph_rw.metadata = cpu_to_le64(rqd->dma_meta_list); - c->ph_rw.control = cpu_to_le16(rqd->flags); - c->ph_rw.length = cpu_to_le16(rqd->nr_ppas - 1); -} - -static void nvme_nvm_end_io(struct request *rq, blk_status_t status) -{ - struct nvm_rq *rqd = rq->end_io_data; - - rqd->ppa_status = le64_to_cpu(nvme_req(rq)->result.u64); - rqd->error = nvme_req(rq)->status; - nvm_end_io(rqd); - - kfree(nvme_req(rq)->cmd); - blk_mq_free_request(rq); -} - -static struct request *nvme_nvm_alloc_request(struct request_queue *q, - struct nvm_rq *rqd, - struct nvme_nvm_command *cmd) -{ - struct nvme_ns *ns = q->queuedata; - struct request *rq; - - nvme_nvm_rqtocmd(rqd, ns, cmd); - - rq = nvme_alloc_request(q, (struct nvme_command *)cmd, 0); - if (IS_ERR(rq)) - return rq; - - rq->cmd_flags &= ~REQ_FAILFAST_DRIVER; - - if (rqd->bio) - blk_rq_append_bio(rq, rqd->bio); - else - rq->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); - - return rq; -} - -static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd, - void *buf) -{ - struct nvm_geo *geo = &dev->geo; - struct request_queue *q = dev->q; - struct nvme_nvm_command *cmd; - struct request *rq; - int ret; - - cmd = kzalloc(sizeof(struct nvme_nvm_command), GFP_KERNEL); - if (!cmd) - return -ENOMEM; - - rq = nvme_nvm_alloc_request(q, rqd, cmd); - if (IS_ERR(rq)) { - ret = PTR_ERR(rq); - goto err_free_cmd; - } - - if (buf) { - ret = blk_rq_map_kern(q, rq, buf, geo->csecs * rqd->nr_ppas, - GFP_KERNEL); - if (ret) - goto err_free_cmd; - } - - rq->end_io_data = rqd; - - blk_execute_rq_nowait(NULL, rq, 0, nvme_nvm_end_io); - - return 0; - -err_free_cmd: - kfree(cmd); - return ret; -} - -static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name, - int size) -{ - struct nvme_ns *ns = nvmdev->q->queuedata; - - return dma_pool_create(name, ns->ctrl->dev, size, PAGE_SIZE, 0); -} - -static void nvme_nvm_destroy_dma_pool(void *pool) -{ - struct dma_pool *dma_pool = pool; - - dma_pool_destroy(dma_pool); -} - -static void *nvme_nvm_dev_dma_alloc(struct nvm_dev *dev, void *pool, - gfp_t mem_flags, dma_addr_t *dma_handler) -{ - return dma_pool_alloc(pool, mem_flags, dma_handler); -} - -static void nvme_nvm_dev_dma_free(void *pool, void *addr, - dma_addr_t dma_handler) -{ - dma_pool_free(pool, addr, dma_handler); -} - -static struct nvm_dev_ops nvme_nvm_dev_ops = { - .identity = nvme_nvm_identity, - - .get_bb_tbl = nvme_nvm_get_bb_tbl, - .set_bb_tbl = nvme_nvm_set_bb_tbl, - - .get_chk_meta = nvme_nvm_get_chk_meta, - - .submit_io = nvme_nvm_submit_io, - - .create_dma_pool = nvme_nvm_create_dma_pool, - .destroy_dma_pool = nvme_nvm_destroy_dma_pool, - .dev_dma_alloc = nvme_nvm_dev_dma_alloc, - .dev_dma_free = nvme_nvm_dev_dma_free, -}; - -static int nvme_nvm_submit_user_cmd(struct request_queue *q, - struct nvme_ns *ns, - struct nvme_nvm_command *vcmd, - void __user *ubuf, unsigned int bufflen, - void __user *meta_buf, unsigned int meta_len, - void __user *ppa_buf, unsigned int ppa_len, - u32 *result, u64 *status, unsigned int timeout) -{ - bool write = nvme_is_write((struct nvme_command *)vcmd); - struct nvm_dev *dev = ns->ndev; - struct request *rq; - struct bio *bio = NULL; - __le64 *ppa_list = NULL; - dma_addr_t ppa_dma; - __le64 *metadata = NULL; - dma_addr_t metadata_dma; - DECLARE_COMPLETION_ONSTACK(wait); - int ret = 0; - - rq = nvme_alloc_request(q, (struct nvme_command *)vcmd, 0); - if (IS_ERR(rq)) { - ret = -ENOMEM; - goto err_cmd; - } - - if (timeout) - rq->timeout = timeout; - - if (ppa_buf && ppa_len) { - ppa_list = dma_pool_alloc(dev->dma_pool, GFP_KERNEL, &ppa_dma); - if (!ppa_list) { - ret = -ENOMEM; - goto err_rq; - } - if (copy_from_user(ppa_list, (void __user *)ppa_buf, - sizeof(u64) * (ppa_len + 1))) { - ret = -EFAULT; - goto err_ppa; - } - vcmd->ph_rw.spba = cpu_to_le64(ppa_dma); - } else { - vcmd->ph_rw.spba = cpu_to_le64((uintptr_t)ppa_buf); - } - - if (ubuf && bufflen) { - ret = blk_rq_map_user(q, rq, NULL, ubuf, bufflen, GFP_KERNEL); - if (ret) - goto err_ppa; - bio = rq->bio; - - if (meta_buf && meta_len) { - metadata = dma_pool_alloc(dev->dma_pool, GFP_KERNEL, - &metadata_dma); - if (!metadata) { - ret = -ENOMEM; - goto err_map; - } - - if (write) { - if (copy_from_user(metadata, - (void __user *)meta_buf, - meta_len)) { - ret = -EFAULT; - goto err_meta; - } - } - vcmd->ph_rw.metadata = cpu_to_le64(metadata_dma); - } - - bio_set_dev(bio, ns->disk->part0); - } - - blk_execute_rq(NULL, rq, 0); - - if (nvme_req(rq)->flags & NVME_REQ_CANCELLED) - ret = -EINTR; - else if (nvme_req(rq)->status & 0x7ff) - ret = -EIO; - if (result) - *result = nvme_req(rq)->status & 0x7ff; - if (status) - *status = le64_to_cpu(nvme_req(rq)->result.u64); - - if (metadata && !ret && !write) { - if (copy_to_user(meta_buf, (void *)metadata, meta_len)) - ret = -EFAULT; - } -err_meta: - if (meta_buf && meta_len) - dma_pool_free(dev->dma_pool, metadata, metadata_dma); -err_map: - if (bio) - blk_rq_unmap_user(bio); -err_ppa: - if (ppa_buf && ppa_len) - dma_pool_free(dev->dma_pool, ppa_list, ppa_dma); -err_rq: - blk_mq_free_request(rq); -err_cmd: - return ret; -} - -static int nvme_nvm_submit_vio(struct nvme_ns *ns, - struct nvm_user_vio __user *uvio) -{ - struct nvm_user_vio vio; - struct nvme_nvm_command c; - unsigned int length; - int ret; - - if (copy_from_user(&vio, uvio, sizeof(vio))) - return -EFAULT; - if (vio.flags) - return -EINVAL; - - memset(&c, 0, sizeof(c)); - c.ph_rw.opcode = vio.opcode; - c.ph_rw.nsid = cpu_to_le32(ns->head->ns_id); - c.ph_rw.control = cpu_to_le16(vio.control); - c.ph_rw.length = cpu_to_le16(vio.nppas); - - length = (vio.nppas + 1) << ns->lba_shift; - - ret = nvme_nvm_submit_user_cmd(ns->queue, ns, &c, - (void __user *)(uintptr_t)vio.addr, length, - (void __user *)(uintptr_t)vio.metadata, - vio.metadata_len, - (void __user *)(uintptr_t)vio.ppa_list, vio.nppas, - &vio.result, &vio.status, 0); - - if (ret && copy_to_user(uvio, &vio, sizeof(vio))) - return -EFAULT; - - return ret; -} - -static int nvme_nvm_user_vcmd(struct nvme_ns *ns, int admin, - struct nvm_passthru_vio __user *uvcmd) -{ - struct nvm_passthru_vio vcmd; - struct nvme_nvm_command c; - struct request_queue *q; - unsigned int timeout = 0; - int ret; - - if (copy_from_user(&vcmd, uvcmd, sizeof(vcmd))) - return -EFAULT; - if ((vcmd.opcode != 0xF2) && (!capable(CAP_SYS_ADMIN))) - return -EACCES; - if (vcmd.flags) - return -EINVAL; - - memset(&c, 0, sizeof(c)); - c.common.opcode = vcmd.opcode; - c.common.nsid = cpu_to_le32(ns->head->ns_id); - c.common.cdw2[0] = cpu_to_le32(vcmd.cdw2); - c.common.cdw2[1] = cpu_to_le32(vcmd.cdw3); - /* cdw11-12 */ - c.ph_rw.length = cpu_to_le16(vcmd.nppas); - c.ph_rw.control = cpu_to_le16(vcmd.control); - c.common.cdw13 = cpu_to_le32(vcmd.cdw13); - c.common.cdw14 = cpu_to_le32(vcmd.cdw14); - c.common.cdw15 = cpu_to_le32(vcmd.cdw15); - - if (vcmd.timeout_ms) - timeout = msecs_to_jiffies(vcmd.timeout_ms); - - q = admin ? ns->ctrl->admin_q : ns->queue; - - ret = nvme_nvm_submit_user_cmd(q, ns, - (struct nvme_nvm_command *)&c, - (void __user *)(uintptr_t)vcmd.addr, vcmd.data_len, - (void __user *)(uintptr_t)vcmd.metadata, - vcmd.metadata_len, - (void __user *)(uintptr_t)vcmd.ppa_list, vcmd.nppas, - &vcmd.result, &vcmd.status, timeout); - - if (ret && copy_to_user(uvcmd, &vcmd, sizeof(vcmd))) - return -EFAULT; - - return ret; -} - -int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *argp) -{ - switch (cmd) { - case NVME_NVM_IOCTL_ADMIN_VIO: - return nvme_nvm_user_vcmd(ns, 1, argp); - case NVME_NVM_IOCTL_IO_VIO: - return nvme_nvm_user_vcmd(ns, 0, argp); - case NVME_NVM_IOCTL_SUBMIT_VIO: - return nvme_nvm_submit_vio(ns, argp); - default: - return -ENOTTY; - } -} - -int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node) -{ - struct request_queue *q = ns->queue; - struct nvm_dev *dev; - struct nvm_geo *geo; - - _nvme_nvm_check_size(); - - dev = nvm_alloc_dev(node); - if (!dev) - return -ENOMEM; - - /* Note that csecs and sos will be overridden if it is a 1.2 drive. */ - geo = &dev->geo; - geo->csecs = 1 << ns->lba_shift; - geo->sos = ns->ms; - if (ns->features & NVME_NS_EXT_LBAS) - geo->ext = true; - else - geo->ext = false; - geo->mdts = ns->ctrl->max_hw_sectors; - - dev->q = q; - memcpy(dev->name, disk_name, DISK_NAME_LEN); - dev->ops = &nvme_nvm_dev_ops; - dev->private_data = ns; - ns->ndev = dev; - - return nvm_register(dev); -} - -void nvme_nvm_unregister(struct nvme_ns *ns) -{ - nvm_unregister(ns->ndev); -} - -static ssize_t nvm_dev_attr_show(struct device *dev, - struct device_attribute *dattr, char *page) -{ - struct nvme_ns *ns = nvme_get_ns_from_dev(dev); - struct nvm_dev *ndev = ns->ndev; - struct nvm_geo *geo = &ndev->geo; - struct attribute *attr; - - if (!ndev) - return 0; - - attr = &dattr->attr; - - if (strcmp(attr->name, "version") == 0) { - if (geo->major_ver_id == 1) - return scnprintf(page, PAGE_SIZE, "%u\n", - geo->major_ver_id); - else - return scnprintf(page, PAGE_SIZE, "%u.%u\n", - geo->major_ver_id, - geo->minor_ver_id); - } else if (strcmp(attr->name, "capabilities") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->cap); - } else if (strcmp(attr->name, "read_typ") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->trdt); - } else if (strcmp(attr->name, "read_max") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->trdm); - } else { - return scnprintf(page, - PAGE_SIZE, - "Unhandled attr(%s) in `%s`\n", - attr->name, __func__); - } -} - -static ssize_t nvm_dev_attr_show_ppaf(struct nvm_addrf_12 *ppaf, char *page) -{ - return scnprintf(page, PAGE_SIZE, - "0x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x\n", - ppaf->ch_offset, ppaf->ch_len, - ppaf->lun_offset, ppaf->lun_len, - ppaf->pln_offset, ppaf->pln_len, - ppaf->blk_offset, ppaf->blk_len, - ppaf->pg_offset, ppaf->pg_len, - ppaf->sec_offset, ppaf->sec_len); -} - -static ssize_t nvm_dev_attr_show_12(struct device *dev, - struct device_attribute *dattr, char *page) -{ - struct nvme_ns *ns = nvme_get_ns_from_dev(dev); - struct nvm_dev *ndev = ns->ndev; - struct nvm_geo *geo = &ndev->geo; - struct attribute *attr; - - if (!ndev) - return 0; - - attr = &dattr->attr; - - if (strcmp(attr->name, "vendor_opcode") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->vmnt); - } else if (strcmp(attr->name, "device_mode") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->dom); - /* kept for compatibility */ - } else if (strcmp(attr->name, "media_manager") == 0) { - return scnprintf(page, PAGE_SIZE, "%s\n", "gennvm"); - } else if (strcmp(attr->name, "ppa_format") == 0) { - return nvm_dev_attr_show_ppaf((void *)&geo->addrf, page); - } else if (strcmp(attr->name, "media_type") == 0) { /* u8 */ - return scnprintf(page, PAGE_SIZE, "%u\n", geo->mtype); - } else if (strcmp(attr->name, "flash_media_type") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->fmtype); - } else if (strcmp(attr->name, "num_channels") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_ch); - } else if (strcmp(attr->name, "num_luns") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_lun); - } else if (strcmp(attr->name, "num_planes") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_pln); - } else if (strcmp(attr->name, "num_blocks") == 0) { /* u16 */ - return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_chk); - } else if (strcmp(attr->name, "num_pages") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_pg); - } else if (strcmp(attr->name, "page_size") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->fpg_sz); - } else if (strcmp(attr->name, "hw_sector_size") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->csecs); - } else if (strcmp(attr->name, "oob_sector_size") == 0) {/* u32 */ - return scnprintf(page, PAGE_SIZE, "%u\n", geo->sos); - } else if (strcmp(attr->name, "prog_typ") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->tprt); - } else if (strcmp(attr->name, "prog_max") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->tprm); - } else if (strcmp(attr->name, "erase_typ") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->tbet); - } else if (strcmp(attr->name, "erase_max") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->tbem); - } else if (strcmp(attr->name, "multiplane_modes") == 0) { - return scnprintf(page, PAGE_SIZE, "0x%08x\n", geo->mpos); - } else if (strcmp(attr->name, "media_capabilities") == 0) { - return scnprintf(page, PAGE_SIZE, "0x%08x\n", geo->mccap); - } else if (strcmp(attr->name, "max_phys_secs") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", NVM_MAX_VLBA); - } else { - return scnprintf(page, PAGE_SIZE, - "Unhandled attr(%s) in `%s`\n", - attr->name, __func__); - } -} - -static ssize_t nvm_dev_attr_show_20(struct device *dev, - struct device_attribute *dattr, char *page) -{ - struct nvme_ns *ns = nvme_get_ns_from_dev(dev); - struct nvm_dev *ndev = ns->ndev; - struct nvm_geo *geo = &ndev->geo; - struct attribute *attr; - - if (!ndev) - return 0; - - attr = &dattr->attr; - - if (strcmp(attr->name, "groups") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_ch); - } else if (strcmp(attr->name, "punits") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_lun); - } else if (strcmp(attr->name, "chunks") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->num_chk); - } else if (strcmp(attr->name, "clba") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->clba); - } else if (strcmp(attr->name, "ws_min") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->ws_min); - } else if (strcmp(attr->name, "ws_opt") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->ws_opt); - } else if (strcmp(attr->name, "maxoc") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->maxoc); - } else if (strcmp(attr->name, "maxocpu") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->maxocpu); - } else if (strcmp(attr->name, "mw_cunits") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->mw_cunits); - } else if (strcmp(attr->name, "write_typ") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->tprt); - } else if (strcmp(attr->name, "write_max") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->tprm); - } else if (strcmp(attr->name, "reset_typ") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->tbet); - } else if (strcmp(attr->name, "reset_max") == 0) { - return scnprintf(page, PAGE_SIZE, "%u\n", geo->tbem); - } else { - return scnprintf(page, PAGE_SIZE, - "Unhandled attr(%s) in `%s`\n", - attr->name, __func__); - } -} - -#define NVM_DEV_ATTR_RO(_name) \ - DEVICE_ATTR(_name, S_IRUGO, nvm_dev_attr_show, NULL) -#define NVM_DEV_ATTR_12_RO(_name) \ - DEVICE_ATTR(_name, S_IRUGO, nvm_dev_attr_show_12, NULL) -#define NVM_DEV_ATTR_20_RO(_name) \ - DEVICE_ATTR(_name, S_IRUGO, nvm_dev_attr_show_20, NULL) - -/* general attributes */ -static NVM_DEV_ATTR_RO(version); -static NVM_DEV_ATTR_RO(capabilities); - -static NVM_DEV_ATTR_RO(read_typ); -static NVM_DEV_ATTR_RO(read_max); - -/* 1.2 values */ -static NVM_DEV_ATTR_12_RO(vendor_opcode); -static NVM_DEV_ATTR_12_RO(device_mode); -static NVM_DEV_ATTR_12_RO(ppa_format); -static NVM_DEV_ATTR_12_RO(media_manager); -static NVM_DEV_ATTR_12_RO(media_type); -static NVM_DEV_ATTR_12_RO(flash_media_type); -static NVM_DEV_ATTR_12_RO(num_channels); -static NVM_DEV_ATTR_12_RO(num_luns); -static NVM_DEV_ATTR_12_RO(num_planes); -static NVM_DEV_ATTR_12_RO(num_blocks); -static NVM_DEV_ATTR_12_RO(num_pages); -static NVM_DEV_ATTR_12_RO(page_size); -static NVM_DEV_ATTR_12_RO(hw_sector_size); -static NVM_DEV_ATTR_12_RO(oob_sector_size); -static NVM_DEV_ATTR_12_RO(prog_typ); -static NVM_DEV_ATTR_12_RO(prog_max); -static NVM_DEV_ATTR_12_RO(erase_typ); -static NVM_DEV_ATTR_12_RO(erase_max); -static NVM_DEV_ATTR_12_RO(multiplane_modes); -static NVM_DEV_ATTR_12_RO(media_capabilities); -static NVM_DEV_ATTR_12_RO(max_phys_secs); - -/* 2.0 values */ -static NVM_DEV_ATTR_20_RO(groups); -static NVM_DEV_ATTR_20_RO(punits); -static NVM_DEV_ATTR_20_RO(chunks); -static NVM_DEV_ATTR_20_RO(clba); -static NVM_DEV_ATTR_20_RO(ws_min); -static NVM_DEV_ATTR_20_RO(ws_opt); -static NVM_DEV_ATTR_20_RO(maxoc); -static NVM_DEV_ATTR_20_RO(maxocpu); -static NVM_DEV_ATTR_20_RO(mw_cunits); -static NVM_DEV_ATTR_20_RO(write_typ); -static NVM_DEV_ATTR_20_RO(write_max); -static NVM_DEV_ATTR_20_RO(reset_typ); -static NVM_DEV_ATTR_20_RO(reset_max); - -static struct attribute *nvm_dev_attrs[] = { - /* version agnostic attrs */ - &dev_attr_version.attr, - &dev_attr_capabilities.attr, - &dev_attr_read_typ.attr, - &dev_attr_read_max.attr, - - /* 1.2 attrs */ - &dev_attr_vendor_opcode.attr, - &dev_attr_device_mode.attr, - &dev_attr_media_manager.attr, - &dev_attr_ppa_format.attr, - &dev_attr_media_type.attr, - &dev_attr_flash_media_type.attr, - &dev_attr_num_channels.attr, - &dev_attr_num_luns.attr, - &dev_attr_num_planes.attr, - &dev_attr_num_blocks.attr, - &dev_attr_num_pages.attr, - &dev_attr_page_size.attr, - &dev_attr_hw_sector_size.attr, - &dev_attr_oob_sector_size.attr, - &dev_attr_prog_typ.attr, - &dev_attr_prog_max.attr, - &dev_attr_erase_typ.attr, - &dev_attr_erase_max.attr, - &dev_attr_multiplane_modes.attr, - &dev_attr_media_capabilities.attr, - &dev_attr_max_phys_secs.attr, - - /* 2.0 attrs */ - &dev_attr_groups.attr, - &dev_attr_punits.attr, - &dev_attr_chunks.attr, - &dev_attr_clba.attr, - &dev_attr_ws_min.attr, - &dev_attr_ws_opt.attr, - &dev_attr_maxoc.attr, - &dev_attr_maxocpu.attr, - &dev_attr_mw_cunits.attr, - - &dev_attr_write_typ.attr, - &dev_attr_write_max.attr, - &dev_attr_reset_typ.attr, - &dev_attr_reset_max.attr, - - NULL, -}; - -static umode_t nvm_dev_attrs_visible(struct kobject *kobj, - struct attribute *attr, int index) -{ - struct device *dev = kobj_to_dev(kobj); - struct gendisk *disk = dev_to_disk(dev); - struct nvme_ns *ns = disk->private_data; - struct nvm_dev *ndev = ns->ndev; - struct device_attribute *dev_attr = - container_of(attr, typeof(*dev_attr), attr); - - if (!ndev) - return 0; - - if (dev_attr->show == nvm_dev_attr_show) - return attr->mode; - - switch (ndev->geo.major_ver_id) { - case 1: - if (dev_attr->show == nvm_dev_attr_show_12) - return attr->mode; - break; - case 2: - if (dev_attr->show == nvm_dev_attr_show_20) - return attr->mode; - break; - } - - return 0; -} - -const struct attribute_group nvme_nvm_attr_group = { - .name = "lightnvm", - .attrs = nvm_dev_attrs, - .is_visible = nvm_dev_attrs_visible, -}; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 5cd1fa3b8464..ab803f91ace1 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -92,11 +91,6 @@ enum nvme_quirks { */ NVME_QUIRK_NO_DEEPEST_PS = (1 << 5), - /* - * Supports the LighNVM command set if indicated in vs[1]. - */ - NVME_QUIRK_LIGHTNVM = (1 << 6), - /* * Set MEDIUM priority on SQ creation */ @@ -823,26 +817,6 @@ static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf) } #endif -#ifdef CONFIG_NVM -int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node); -void nvme_nvm_unregister(struct nvme_ns *ns); -extern const struct attribute_group nvme_nvm_attr_group; -int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *argp); -#else -static inline int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, - int node) -{ - return 0; -} - -static inline void nvme_nvm_unregister(struct nvme_ns *ns) {}; -static inline int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, - void __user *argp) -{ - return -ENOTTY; -} -#endif /* CONFIG_NVM */ - static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) { return dev_to_disk(dev)->private_data; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 51852085239e..db7a9bee2014 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3243,12 +3243,6 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1b4b, 0x1092), /* Lexar 256 GB SSD */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, - { PCI_DEVICE(0x1d1d, 0x1f1f), /* LighNVM qemu device */ - .driver_data = NVME_QUIRK_LIGHTNVM, }, - { PCI_DEVICE(0x1d1d, 0x2807), /* CNEX WL */ - .driver_data = NVME_QUIRK_LIGHTNVM, }, - { PCI_DEVICE(0x1d1d, 0x2601), /* CNEX Granby */ - .driver_data = NVME_QUIRK_LIGHTNVM, }, { PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */ diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h deleted file mode 100644 index 0908abda9c1b..000000000000 --- a/include/linux/lightnvm.h +++ /dev/null @@ -1,697 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef NVM_H -#define NVM_H - -#include -#include -#include - -enum { - NVM_IO_OK = 0, - NVM_IO_REQUEUE = 1, - NVM_IO_DONE = 2, - NVM_IO_ERR = 3, - - NVM_IOTYPE_NONE = 0, - NVM_IOTYPE_GC = 1, -}; - -/* common format */ -#define NVM_GEN_CH_BITS (8) -#define NVM_GEN_LUN_BITS (8) -#define NVM_GEN_BLK_BITS (16) -#define NVM_GEN_RESERVED (32) - -/* 1.2 format */ -#define NVM_12_PG_BITS (16) -#define NVM_12_PL_BITS (4) -#define NVM_12_SEC_BITS (4) -#define NVM_12_RESERVED (8) - -/* 2.0 format */ -#define NVM_20_SEC_BITS (24) -#define NVM_20_RESERVED (8) - -enum { - NVM_OCSSD_SPEC_12 = 12, - NVM_OCSSD_SPEC_20 = 20, -}; - -struct ppa_addr { - /* Generic structure for all addresses */ - union { - /* generic device format */ - struct { - u64 ch : NVM_GEN_CH_BITS; - u64 lun : NVM_GEN_LUN_BITS; - u64 blk : NVM_GEN_BLK_BITS; - u64 reserved : NVM_GEN_RESERVED; - } a; - - /* 1.2 device format */ - struct { - u64 ch : NVM_GEN_CH_BITS; - u64 lun : NVM_GEN_LUN_BITS; - u64 blk : NVM_GEN_BLK_BITS; - u64 pg : NVM_12_PG_BITS; - u64 pl : NVM_12_PL_BITS; - u64 sec : NVM_12_SEC_BITS; - u64 reserved : NVM_12_RESERVED; - } g; - - /* 2.0 device format */ - struct { - u64 grp : NVM_GEN_CH_BITS; - u64 pu : NVM_GEN_LUN_BITS; - u64 chk : NVM_GEN_BLK_BITS; - u64 sec : NVM_20_SEC_BITS; - u64 reserved : NVM_20_RESERVED; - } m; - - struct { - u64 line : 63; - u64 is_cached : 1; - } c; - - u64 ppa; - }; -}; - -struct nvm_rq; -struct nvm_id; -struct nvm_dev; -struct nvm_tgt_dev; -struct nvm_chk_meta; - -typedef int (nvm_id_fn)(struct nvm_dev *); -typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, u8 *); -typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct ppa_addr *, int, int); -typedef int (nvm_get_chk_meta_fn)(struct nvm_dev *, sector_t, int, - struct nvm_chk_meta *); -typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *, void *); -typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *, int); -typedef void (nvm_destroy_dma_pool_fn)(void *); -typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t, - dma_addr_t *); -typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t); - -struct nvm_dev_ops { - nvm_id_fn *identity; - nvm_op_bb_tbl_fn *get_bb_tbl; - nvm_op_set_bb_fn *set_bb_tbl; - - nvm_get_chk_meta_fn *get_chk_meta; - - nvm_submit_io_fn *submit_io; - - nvm_create_dma_pool_fn *create_dma_pool; - nvm_destroy_dma_pool_fn *destroy_dma_pool; - nvm_dev_dma_alloc_fn *dev_dma_alloc; - nvm_dev_dma_free_fn *dev_dma_free; -}; - -#ifdef CONFIG_NVM - -#include -#include - -enum { - /* HW Responsibilities */ - NVM_RSP_L2P = 1 << 0, - NVM_RSP_ECC = 1 << 1, - - /* Physical Adressing Mode */ - NVM_ADDRMODE_LINEAR = 0, - NVM_ADDRMODE_CHANNEL = 1, - - /* Plane programming mode for LUN */ - NVM_PLANE_SINGLE = 1, - NVM_PLANE_DOUBLE = 2, - NVM_PLANE_QUAD = 4, - - /* Status codes */ - NVM_RSP_SUCCESS = 0x0, - NVM_RSP_NOT_CHANGEABLE = 0x1, - NVM_RSP_ERR_FAILWRITE = 0x40ff, - NVM_RSP_ERR_EMPTYPAGE = 0x42ff, - NVM_RSP_ERR_FAILECC = 0x4281, - NVM_RSP_ERR_FAILCRC = 0x4004, - NVM_RSP_WARN_HIGHECC = 0x4700, - - /* Device opcodes */ - NVM_OP_PWRITE = 0x91, - NVM_OP_PREAD = 0x92, - NVM_OP_ERASE = 0x90, - - /* PPA Command Flags */ - NVM_IO_SNGL_ACCESS = 0x0, - NVM_IO_DUAL_ACCESS = 0x1, - NVM_IO_QUAD_ACCESS = 0x2, - - /* NAND Access Modes */ - NVM_IO_SUSPEND = 0x80, - NVM_IO_SLC_MODE = 0x100, - NVM_IO_SCRAMBLE_ENABLE = 0x200, - - /* Block Types */ - NVM_BLK_T_FREE = 0x0, - NVM_BLK_T_BAD = 0x1, - NVM_BLK_T_GRWN_BAD = 0x2, - NVM_BLK_T_DEV = 0x4, - NVM_BLK_T_HOST = 0x8, - - /* Memory capabilities */ - NVM_ID_CAP_SLC = 0x1, - NVM_ID_CAP_CMD_SUSPEND = 0x2, - NVM_ID_CAP_SCRAMBLE = 0x4, - NVM_ID_CAP_ENCRYPT = 0x8, - - /* Memory types */ - NVM_ID_FMTYPE_SLC = 0, - NVM_ID_FMTYPE_MLC = 1, - - /* Device capabilities */ - NVM_ID_DCAP_BBLKMGMT = 0x1, - NVM_UD_DCAP_ECC = 0x2, -}; - -struct nvm_id_lp_mlc { - u16 num_pairs; - u8 pairs[886]; -}; - -struct nvm_id_lp_tbl { - __u8 id[8]; - struct nvm_id_lp_mlc mlc; -}; - -struct nvm_addrf_12 { - u8 ch_len; - u8 lun_len; - u8 blk_len; - u8 pg_len; - u8 pln_len; - u8 sec_len; - - u8 ch_offset; - u8 lun_offset; - u8 blk_offset; - u8 pg_offset; - u8 pln_offset; - u8 sec_offset; - - u64 ch_mask; - u64 lun_mask; - u64 blk_mask; - u64 pg_mask; - u64 pln_mask; - u64 sec_mask; -}; - -struct nvm_addrf { - u8 ch_len; - u8 lun_len; - u8 chk_len; - u8 sec_len; - u8 rsv_len[2]; - - u8 ch_offset; - u8 lun_offset; - u8 chk_offset; - u8 sec_offset; - u8 rsv_off[2]; - - u64 ch_mask; - u64 lun_mask; - u64 chk_mask; - u64 sec_mask; - u64 rsv_mask[2]; -}; - -enum { - /* Chunk states */ - NVM_CHK_ST_FREE = 1 << 0, - NVM_CHK_ST_CLOSED = 1 << 1, - NVM_CHK_ST_OPEN = 1 << 2, - NVM_CHK_ST_OFFLINE = 1 << 3, - - /* Chunk types */ - NVM_CHK_TP_W_SEQ = 1 << 0, - NVM_CHK_TP_W_RAN = 1 << 1, - NVM_CHK_TP_SZ_SPEC = 1 << 4, -}; - -/* - * Note: The structure size is linked to nvme_nvm_chk_meta such that the same - * buffer can be used when converting from little endian to cpu addressing. - */ -struct nvm_chk_meta { - u8 state; - u8 type; - u8 wi; - u8 rsvd[5]; - u64 slba; - u64 cnlb; - u64 wp; -}; - -struct nvm_target { - struct list_head list; - struct nvm_tgt_dev *dev; - struct nvm_tgt_type *type; - struct gendisk *disk; -}; - -#define ADDR_EMPTY (~0ULL) - -#define NVM_TARGET_DEFAULT_OP (101) -#define NVM_TARGET_MIN_OP (3) -#define NVM_TARGET_MAX_OP (80) - -#define NVM_VERSION_MAJOR 1 -#define NVM_VERSION_MINOR 0 -#define NVM_VERSION_PATCH 0 - -#define NVM_MAX_VLBA (64) /* max logical blocks in a vector command */ - -struct nvm_rq; -typedef void (nvm_end_io_fn)(struct nvm_rq *); - -struct nvm_rq { - struct nvm_tgt_dev *dev; - - struct bio *bio; - - union { - struct ppa_addr ppa_addr; - dma_addr_t dma_ppa_list; - }; - - struct ppa_addr *ppa_list; - - void *meta_list; - dma_addr_t dma_meta_list; - - nvm_end_io_fn *end_io; - - uint8_t opcode; - uint16_t nr_ppas; - uint16_t flags; - - u64 ppa_status; /* ppa media status */ - int error; - - int is_seq; /* Sequential hint flag. 1.2 only */ - - void *private; -}; - -static inline struct nvm_rq *nvm_rq_from_pdu(void *pdu) -{ - return pdu - sizeof(struct nvm_rq); -} - -static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata) -{ - return rqdata + 1; -} - -static inline struct ppa_addr *nvm_rq_to_ppa_list(struct nvm_rq *rqd) -{ - return (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr; -} - -enum { - NVM_BLK_ST_FREE = 0x1, /* Free block */ - NVM_BLK_ST_TGT = 0x2, /* Block in use by target */ - NVM_BLK_ST_BAD = 0x8, /* Bad block */ -}; - -/* Instance geometry */ -struct nvm_geo { - /* device reported version */ - u8 major_ver_id; - u8 minor_ver_id; - - /* kernel short version */ - u8 version; - - /* instance specific geometry */ - int num_ch; - int num_lun; /* per channel */ - - /* calculated values */ - int all_luns; /* across channels */ - int all_chunks; /* across channels */ - - int op; /* over-provision in instance */ - - sector_t total_secs; /* across channels */ - - /* chunk geometry */ - u32 num_chk; /* chunks per lun */ - u32 clba; /* sectors per chunk */ - u16 csecs; /* sector size */ - u16 sos; /* out-of-band area size */ - bool ext; /* metadata in extended data buffer */ - u32 mdts; /* Max data transfer size*/ - - /* device write constrains */ - u32 ws_min; /* minimum write size */ - u32 ws_opt; /* optimal write size */ - u32 mw_cunits; /* distance required for successful read */ - u32 maxoc; /* maximum open chunks */ - u32 maxocpu; /* maximum open chunks per parallel unit */ - - /* device capabilities */ - u32 mccap; - - /* device timings */ - u32 trdt; /* Avg. Tread (ns) */ - u32 trdm; /* Max Tread (ns) */ - u32 tprt; /* Avg. Tprog (ns) */ - u32 tprm; /* Max Tprog (ns) */ - u32 tbet; /* Avg. Terase (ns) */ - u32 tbem; /* Max Terase (ns) */ - - /* generic address format */ - struct nvm_addrf addrf; - - /* 1.2 compatibility */ - u8 vmnt; - u32 cap; - u32 dom; - - u8 mtype; - u8 fmtype; - - u16 cpar; - u32 mpos; - - u8 num_pln; - u8 pln_mode; - u16 num_pg; - u16 fpg_sz; -}; - -/* sub-device structure */ -struct nvm_tgt_dev { - /* Device information */ - struct nvm_geo geo; - - /* Base ppas for target LUNs */ - struct ppa_addr *luns; - - struct request_queue *q; - - struct nvm_dev *parent; - void *map; -}; - -struct nvm_dev { - struct nvm_dev_ops *ops; - - struct list_head devices; - - /* Device information */ - struct nvm_geo geo; - - unsigned long *lun_map; - void *dma_pool; - - /* Backend device */ - struct request_queue *q; - char name[DISK_NAME_LEN]; - void *private_data; - - struct kref ref; - void *rmap; - - struct mutex mlock; - spinlock_t lock; - - /* target management */ - struct list_head area_list; - struct list_head targets; -}; - -static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev, - struct ppa_addr r) -{ - struct nvm_geo *geo = &dev->geo; - struct ppa_addr l; - - if (geo->version == NVM_OCSSD_SPEC_12) { - struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&geo->addrf; - - l.ppa = ((u64)r.g.ch) << ppaf->ch_offset; - l.ppa |= ((u64)r.g.lun) << ppaf->lun_offset; - l.ppa |= ((u64)r.g.blk) << ppaf->blk_offset; - l.ppa |= ((u64)r.g.pg) << ppaf->pg_offset; - l.ppa |= ((u64)r.g.pl) << ppaf->pln_offset; - l.ppa |= ((u64)r.g.sec) << ppaf->sec_offset; - } else { - struct nvm_addrf *lbaf = &geo->addrf; - - l.ppa = ((u64)r.m.grp) << lbaf->ch_offset; - l.ppa |= ((u64)r.m.pu) << lbaf->lun_offset; - l.ppa |= ((u64)r.m.chk) << lbaf->chk_offset; - l.ppa |= ((u64)r.m.sec) << lbaf->sec_offset; - } - - return l; -} - -static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev, - struct ppa_addr r) -{ - struct nvm_geo *geo = &dev->geo; - struct ppa_addr l; - - l.ppa = 0; - - if (geo->version == NVM_OCSSD_SPEC_12) { - struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&geo->addrf; - - l.g.ch = (r.ppa & ppaf->ch_mask) >> ppaf->ch_offset; - l.g.lun = (r.ppa & ppaf->lun_mask) >> ppaf->lun_offset; - l.g.blk = (r.ppa & ppaf->blk_mask) >> ppaf->blk_offset; - l.g.pg = (r.ppa & ppaf->pg_mask) >> ppaf->pg_offset; - l.g.pl = (r.ppa & ppaf->pln_mask) >> ppaf->pln_offset; - l.g.sec = (r.ppa & ppaf->sec_mask) >> ppaf->sec_offset; - } else { - struct nvm_addrf *lbaf = &geo->addrf; - - l.m.grp = (r.ppa & lbaf->ch_mask) >> lbaf->ch_offset; - l.m.pu = (r.ppa & lbaf->lun_mask) >> lbaf->lun_offset; - l.m.chk = (r.ppa & lbaf->chk_mask) >> lbaf->chk_offset; - l.m.sec = (r.ppa & lbaf->sec_mask) >> lbaf->sec_offset; - } - - return l; -} - -static inline u64 dev_to_chunk_addr(struct nvm_dev *dev, void *addrf, - struct ppa_addr p) -{ - struct nvm_geo *geo = &dev->geo; - u64 caddr; - - if (geo->version == NVM_OCSSD_SPEC_12) { - struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)addrf; - - caddr = (u64)p.g.pg << ppaf->pg_offset; - caddr |= (u64)p.g.pl << ppaf->pln_offset; - caddr |= (u64)p.g.sec << ppaf->sec_offset; - } else { - caddr = p.m.sec; - } - - return caddr; -} - -static inline struct ppa_addr nvm_ppa32_to_ppa64(struct nvm_dev *dev, - void *addrf, u32 ppa32) -{ - struct ppa_addr ppa64; - - ppa64.ppa = 0; - - if (ppa32 == -1) { - ppa64.ppa = ADDR_EMPTY; - } else if (ppa32 & (1U << 31)) { - ppa64.c.line = ppa32 & ((~0U) >> 1); - ppa64.c.is_cached = 1; - } else { - struct nvm_geo *geo = &dev->geo; - - if (geo->version == NVM_OCSSD_SPEC_12) { - struct nvm_addrf_12 *ppaf = addrf; - - ppa64.g.ch = (ppa32 & ppaf->ch_mask) >> - ppaf->ch_offset; - ppa64.g.lun = (ppa32 & ppaf->lun_mask) >> - ppaf->lun_offset; - ppa64.g.blk = (ppa32 & ppaf->blk_mask) >> - ppaf->blk_offset; - ppa64.g.pg = (ppa32 & ppaf->pg_mask) >> - ppaf->pg_offset; - ppa64.g.pl = (ppa32 & ppaf->pln_mask) >> - ppaf->pln_offset; - ppa64.g.sec = (ppa32 & ppaf->sec_mask) >> - ppaf->sec_offset; - } else { - struct nvm_addrf *lbaf = addrf; - - ppa64.m.grp = (ppa32 & lbaf->ch_mask) >> - lbaf->ch_offset; - ppa64.m.pu = (ppa32 & lbaf->lun_mask) >> - lbaf->lun_offset; - ppa64.m.chk = (ppa32 & lbaf->chk_mask) >> - lbaf->chk_offset; - ppa64.m.sec = (ppa32 & lbaf->sec_mask) >> - lbaf->sec_offset; - } - } - - return ppa64; -} - -static inline u32 nvm_ppa64_to_ppa32(struct nvm_dev *dev, - void *addrf, struct ppa_addr ppa64) -{ - u32 ppa32 = 0; - - if (ppa64.ppa == ADDR_EMPTY) { - ppa32 = ~0U; - } else if (ppa64.c.is_cached) { - ppa32 |= ppa64.c.line; - ppa32 |= 1U << 31; - } else { - struct nvm_geo *geo = &dev->geo; - - if (geo->version == NVM_OCSSD_SPEC_12) { - struct nvm_addrf_12 *ppaf = addrf; - - ppa32 |= ppa64.g.ch << ppaf->ch_offset; - ppa32 |= ppa64.g.lun << ppaf->lun_offset; - ppa32 |= ppa64.g.blk << ppaf->blk_offset; - ppa32 |= ppa64.g.pg << ppaf->pg_offset; - ppa32 |= ppa64.g.pl << ppaf->pln_offset; - ppa32 |= ppa64.g.sec << ppaf->sec_offset; - } else { - struct nvm_addrf *lbaf = addrf; - - ppa32 |= ppa64.m.grp << lbaf->ch_offset; - ppa32 |= ppa64.m.pu << lbaf->lun_offset; - ppa32 |= ppa64.m.chk << lbaf->chk_offset; - ppa32 |= ppa64.m.sec << lbaf->sec_offset; - } - } - - return ppa32; -} - -static inline int nvm_next_ppa_in_chk(struct nvm_tgt_dev *dev, - struct ppa_addr *ppa) -{ - struct nvm_geo *geo = &dev->geo; - int last = 0; - - if (geo->version == NVM_OCSSD_SPEC_12) { - int sec = ppa->g.sec; - - sec++; - if (sec == geo->ws_min) { - int pg = ppa->g.pg; - - sec = 0; - pg++; - if (pg == geo->num_pg) { - int pl = ppa->g.pl; - - pg = 0; - pl++; - if (pl == geo->num_pln) - last = 1; - - ppa->g.pl = pl; - } - ppa->g.pg = pg; - } - ppa->g.sec = sec; - } else { - ppa->m.sec++; - if (ppa->m.sec == geo->clba) - last = 1; - } - - return last; -} - -typedef sector_t (nvm_tgt_capacity_fn)(void *); -typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, - int flags); -typedef void (nvm_tgt_exit_fn)(void *, bool); -typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *); -typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *); - -enum { - NVM_TGT_F_DEV_L2P = 0, - NVM_TGT_F_HOST_L2P = 1 << 0, -}; - -struct nvm_tgt_type { - const char *name; - unsigned int version[3]; - int flags; - - /* target entry points */ - const struct block_device_operations *bops; - nvm_tgt_capacity_fn *capacity; - - /* module-specific init/teardown */ - nvm_tgt_init_fn *init; - nvm_tgt_exit_fn *exit; - - /* sysfs */ - nvm_tgt_sysfs_init_fn *sysfs_init; - nvm_tgt_sysfs_exit_fn *sysfs_exit; - - /* For internal use */ - struct list_head list; - struct module *owner; -}; - -extern int nvm_register_tgt_type(struct nvm_tgt_type *); -extern void nvm_unregister_tgt_type(struct nvm_tgt_type *); - -extern void *nvm_dev_dma_alloc(struct nvm_dev *, gfp_t, dma_addr_t *); -extern void nvm_dev_dma_free(struct nvm_dev *, void *, dma_addr_t); - -extern struct nvm_dev *nvm_alloc_dev(int); -extern int nvm_register(struct nvm_dev *); -extern void nvm_unregister(struct nvm_dev *); - -extern int nvm_get_chunk_meta(struct nvm_tgt_dev *, struct ppa_addr, - int, struct nvm_chk_meta *); -extern int nvm_set_chunk_meta(struct nvm_tgt_dev *, struct ppa_addr *, - int, int); -extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *, void *); -extern int nvm_submit_io_sync(struct nvm_tgt_dev *, struct nvm_rq *, void *); -extern void nvm_end_io(struct nvm_rq *); - -#else /* CONFIG_NVM */ -struct nvm_dev_ops; - -static inline struct nvm_dev *nvm_alloc_dev(int node) -{ - return ERR_PTR(-EINVAL); -} -static inline int nvm_register(struct nvm_dev *dev) -{ - return -EINVAL; -} -static inline void nvm_unregister(struct nvm_dev *dev) {} -#endif /* CONFIG_NVM */ -#endif /* LIGHTNVM.H */ diff --git a/include/uapi/linux/lightnvm.h b/include/uapi/linux/lightnvm.h deleted file mode 100644 index 2745afd9b8fa..000000000000 --- a/include/uapi/linux/lightnvm.h +++ /dev/null @@ -1,224 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * Copyright (C) 2015 CNEX Labs. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; see the file COPYING. If not, write to - * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, - * USA. - */ - -#ifndef _UAPI_LINUX_LIGHTNVM_H -#define _UAPI_LINUX_LIGHTNVM_H - -#ifdef __KERNEL__ -#include -#else /* __KERNEL__ */ -#include -#include -#define DISK_NAME_LEN 32 -#endif /* __KERNEL__ */ - -#include -#include - -#define NVM_TTYPE_NAME_MAX 48 -#define NVM_TTYPE_MAX 63 -#define NVM_MMTYPE_LEN 8 - -#define NVM_CTRL_FILE "/dev/lightnvm/control" - -struct nvm_ioctl_info_tgt { - __u32 version[3]; - __u32 reserved; - char tgtname[NVM_TTYPE_NAME_MAX]; -}; - -struct nvm_ioctl_info { - __u32 version[3]; /* in/out - major, minor, patch */ - __u16 tgtsize; /* number of targets */ - __u16 reserved16; /* pad to 4K page */ - __u32 reserved[12]; - struct nvm_ioctl_info_tgt tgts[NVM_TTYPE_MAX]; -}; - -enum { - NVM_DEVICE_ACTIVE = 1 << 0, -}; - -struct nvm_ioctl_device_info { - char devname[DISK_NAME_LEN]; - char bmname[NVM_TTYPE_NAME_MAX]; - __u32 bmversion[3]; - __u32 flags; - __u32 reserved[8]; -}; - -struct nvm_ioctl_get_devices { - __u32 nr_devices; - __u32 reserved[31]; - struct nvm_ioctl_device_info info[31]; -}; - -struct nvm_ioctl_create_simple { - __u32 lun_begin; - __u32 lun_end; -}; - -struct nvm_ioctl_create_extended { - __u16 lun_begin; - __u16 lun_end; - __u16 op; - __u16 rsv; -}; - -enum { - NVM_CONFIG_TYPE_SIMPLE = 0, - NVM_CONFIG_TYPE_EXTENDED = 1, -}; - -struct nvm_ioctl_create_conf { - __u32 type; - union { - struct nvm_ioctl_create_simple s; - struct nvm_ioctl_create_extended e; - }; -}; - -enum { - NVM_TARGET_FACTORY = 1 << 0, /* Init target in factory mode */ -}; - -struct nvm_ioctl_create { - char dev[DISK_NAME_LEN]; /* open-channel SSD device */ - char tgttype[NVM_TTYPE_NAME_MAX]; /* target type name */ - char tgtname[DISK_NAME_LEN]; /* dev to expose target as */ - - __u32 flags; - - struct nvm_ioctl_create_conf conf; -}; - -struct nvm_ioctl_remove { - char tgtname[DISK_NAME_LEN]; - - __u32 flags; -}; - -struct nvm_ioctl_dev_init { - char dev[DISK_NAME_LEN]; /* open-channel SSD device */ - char mmtype[NVM_MMTYPE_LEN]; /* register to media manager */ - - __u32 flags; -}; - -enum { - NVM_FACTORY_ERASE_ONLY_USER = 1 << 0, /* erase only blocks used as - * host blks or grown blks */ - NVM_FACTORY_RESET_HOST_BLKS = 1 << 1, /* remove host blk marks */ - NVM_FACTORY_RESET_GRWN_BBLKS = 1 << 2, /* remove grown blk marks */ - NVM_FACTORY_NR_BITS = 1 << 3, /* stops here */ -}; - -struct nvm_ioctl_dev_factory { - char dev[DISK_NAME_LEN]; - - __u32 flags; -}; - -struct nvm_user_vio { - __u8 opcode; - __u8 flags; - __u16 control; - __u16 nppas; - __u16 rsvd; - __u64 metadata; - __u64 addr; - __u64 ppa_list; - __u32 metadata_len; - __u32 data_len; - __u64 status; - __u32 result; - __u32 rsvd3[3]; -}; - -struct nvm_passthru_vio { - __u8 opcode; - __u8 flags; - __u8 rsvd[2]; - __u32 nsid; - __u32 cdw2; - __u32 cdw3; - __u64 metadata; - __u64 addr; - __u32 metadata_len; - __u32 data_len; - __u64 ppa_list; - __u16 nppas; - __u16 control; - __u32 cdw13; - __u32 cdw14; - __u32 cdw15; - __u64 status; - __u32 result; - __u32 timeout_ms; -}; - -/* The ioctl type, 'L', 0x20 - 0x2F documented in ioctl-number.txt */ -enum { - /* top level cmds */ - NVM_INFO_CMD = 0x20, - NVM_GET_DEVICES_CMD, - - /* device level cmds */ - NVM_DEV_CREATE_CMD, - NVM_DEV_REMOVE_CMD, - - /* Init a device to support LightNVM media managers */ - NVM_DEV_INIT_CMD, - - /* Factory reset device */ - NVM_DEV_FACTORY_CMD, - - /* Vector user I/O */ - NVM_DEV_VIO_ADMIN_CMD = 0x41, - NVM_DEV_VIO_CMD = 0x42, - NVM_DEV_VIO_USER_CMD = 0x43, -}; - -#define NVM_IOCTL 'L' /* 0x4c */ - -#define NVM_INFO _IOWR(NVM_IOCTL, NVM_INFO_CMD, \ - struct nvm_ioctl_info) -#define NVM_GET_DEVICES _IOR(NVM_IOCTL, NVM_GET_DEVICES_CMD, \ - struct nvm_ioctl_get_devices) -#define NVM_DEV_CREATE _IOW(NVM_IOCTL, NVM_DEV_CREATE_CMD, \ - struct nvm_ioctl_create) -#define NVM_DEV_REMOVE _IOW(NVM_IOCTL, NVM_DEV_REMOVE_CMD, \ - struct nvm_ioctl_remove) -#define NVM_DEV_INIT _IOW(NVM_IOCTL, NVM_DEV_INIT_CMD, \ - struct nvm_ioctl_dev_init) -#define NVM_DEV_FACTORY _IOW(NVM_IOCTL, NVM_DEV_FACTORY_CMD, \ - struct nvm_ioctl_dev_factory) - -#define NVME_NVM_IOCTL_IO_VIO _IOWR(NVM_IOCTL, NVM_DEV_VIO_USER_CMD, \ - struct nvm_passthru_vio) -#define NVME_NVM_IOCTL_ADMIN_VIO _IOWR(NVM_IOCTL, NVM_DEV_VIO_ADMIN_CMD,\ - struct nvm_passthru_vio) -#define NVME_NVM_IOCTL_SUBMIT_VIO _IOWR(NVM_IOCTL, NVM_DEV_VIO_CMD,\ - struct nvm_user_vio) - -#define NVM_VERSION_MAJOR 1 -#define NVM_VERSION_MINOR 0 -#define NVM_VERSION_PATCHLEVEL 0 - -#endif -- cgit v1.2.3 From 2c860a43dd77f969bb959336a2f743d7103a8f63 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Sat, 14 Aug 2021 10:57:15 +0900 Subject: bpf: af_unix: Implement BPF iterator for UNIX domain socket. This patch implements the BPF iterator for the UNIX domain socket. Currently, the batch optimisation introduced for the TCP iterator in the commit 04c7820b776f ("bpf: tcp: Bpf iter batching and lock_sock") is not used for the UNIX domain socket. It will require replacing the big lock for the hash table with small locks for each hash list not to block other processes. Signed-off-by: Kuniyuki Iwashima Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210814015718.42704-2-kuniyu@amazon.co.jp --- include/linux/btf_ids.h | 3 +- net/unix/af_unix.c | 93 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 95 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 57890b357f85..bed4b9964581 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -172,7 +172,8 @@ extern struct btf_id_set name; BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ - BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) enum { #define BTF_SOCK_TYPE(name, str) name, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 1c2224f05b51..bad8f19174e3 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -113,6 +113,7 @@ #include #include #include +#include #include "scm.h" @@ -3143,6 +3144,64 @@ static const struct seq_operations unix_seq_ops = { .stop = unix_seq_stop, .show = unix_seq_show, }; + +#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) +struct bpf_iter__unix { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct unix_sock *, unix_sk); + uid_t uid __aligned(8); +}; + +static int unix_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, + struct unix_sock *unix_sk, uid_t uid) +{ + struct bpf_iter__unix ctx; + + meta->seq_num--; /* skip SEQ_START_TOKEN */ + ctx.meta = meta; + ctx.unix_sk = unix_sk; + ctx.uid = uid; + return bpf_iter_run_prog(prog, &ctx); +} + +static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_prog *prog; + struct sock *sk = v; + uid_t uid; + + if (v == SEQ_START_TOKEN) + return 0; + + uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); + meta.seq = seq; + prog = bpf_iter_get_info(&meta, false); + return unix_prog_seq_show(prog, &meta, v, uid); +} + +static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + if (!v) { + meta.seq = seq; + prog = bpf_iter_get_info(&meta, true); + if (prog) + (void)unix_prog_seq_show(prog, &meta, v, 0); + } + + unix_seq_stop(seq, v); +} + +static const struct seq_operations bpf_iter_unix_seq_ops = { + .start = unix_seq_start, + .next = unix_seq_next, + .stop = bpf_iter_unix_seq_stop, + .show = bpf_iter_unix_seq_show, +}; +#endif #endif static const struct net_proto_family unix_family_ops = { @@ -3183,6 +3242,35 @@ static struct pernet_operations unix_net_ops = { .exit = unix_net_exit, }; +#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) +DEFINE_BPF_ITER_FUNC(unix, struct bpf_iter_meta *meta, + struct unix_sock *unix_sk, uid_t uid) + +static const struct bpf_iter_seq_info unix_seq_info = { + .seq_ops = &bpf_iter_unix_seq_ops, + .init_seq_private = bpf_iter_init_seq_net, + .fini_seq_private = bpf_iter_fini_seq_net, + .seq_priv_size = sizeof(struct seq_net_private), +}; + +static struct bpf_iter_reg unix_reg_info = { + .target = "unix", + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__unix, unix_sk), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &unix_seq_info, +}; + +static void __init bpf_iter_register(void) +{ + unix_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UNIX]; + if (bpf_iter_reg_target(&unix_reg_info)) + pr_warn("Warning: could not register bpf iterator unix\n"); +} +#endif + static int __init af_unix_init(void) { int rc = -1; @@ -3198,6 +3286,11 @@ static int __init af_unix_init(void) sock_register(&unix_family_ops); register_pernet_subsys(&unix_net_ops); unix_bpf_build_proto(); + +#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) + bpf_iter_register(); +#endif + out: return rc; } -- cgit v1.2.3 From 18250b43f7b6d0085724bf6fc186f9a107066068 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 11 Aug 2021 10:52:28 +0200 Subject: of: fdt: Remove early_init_dt_reserve_memory_arch() override capability Commit e7ae8d174eec0b3b ("MIPS: replace add_memory_region with memblock") removed the last architecture-specific override of early_init_dt_reserve_memory_arch(). Convert the common implementation from a weak global function to a static function. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/be0140a0183ecfd0a3afa4fe6d2d77ed418102f9.1628671897.git.geert+renesas@glider.be Signed-off-by: Rob Herring --- drivers/of/fdt.c | 32 ++++++++++++++++---------------- include/linux/of_fdt.h | 2 -- 2 files changed, 16 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 5dc0b0310d7c..e25b41591ab2 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -475,6 +475,22 @@ void *initial_boot_params __ro_after_init; static u32 of_fdt_crc32; +static int __init early_init_dt_reserve_memory_arch(phys_addr_t base, + phys_addr_t size, bool nomap) +{ + if (nomap) { + /* + * If the memory is already reserved (by another region), we + * should not allow it to be marked nomap. + */ + if (memblock_is_region_reserved(base, size)) + return -EBUSY; + + return memblock_mark_nomap(base, size); + } + return memblock_reserve(base, size); +} + /* * __reserved_mem_reserve_reg() - reserve all memory described in 'reg' property */ @@ -1147,22 +1163,6 @@ int __init __weak early_init_dt_mark_hotplug_memory_arch(u64 base, u64 size) return memblock_mark_hotplug(base, size); } -int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base, - phys_addr_t size, bool nomap) -{ - if (nomap) { - /* - * If the memory is already reserved (by another region), we - * should not allow it to be marked nomap. - */ - if (memblock_is_region_reserved(base, size)) - return -EBUSY; - - return memblock_mark_nomap(base, size); - } - return memblock_reserve(base, size); -} - static void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) { void *ptr = memblock_alloc(size, align); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index acf820e88952..3b1500a0116f 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -68,8 +68,6 @@ extern void early_init_fdt_reserve_self(void); extern void __init early_init_dt_scan_chosen_arch(unsigned long node); extern void early_init_dt_add_memory_arch(u64 base, u64 size); extern int early_init_dt_mark_hotplug_memory_arch(u64 base, u64 size); -extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size, - bool no_map); extern u64 dt_mem_next_cell(int s, const __be32 **cellp); /* Early flat tree scan hooks */ -- cgit v1.2.3 From 39c6b3a3dd118173c6da32daacd2eed8cfc5951d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 11 Aug 2021 10:53:37 +0200 Subject: of: fdt: Remove weak early_init_dt_mark_hotplug_memory_arch() Commit 41a9ada3e6b4253f ("of/fdt: mark hotpluggable memory") introduced two (for systems with and without memblock) weak versions of early_init_dt_mark_hotplug_memory_arch(), that could be overridden by an architecture-specific version. However, no overrides ever emerged. Later, commit aca52c3983891060 ("mm: remove CONFIG_HAVE_MEMBLOCK") removed the non-memblock version. Remove early_init_dt_mark_hotplug_memory_arch(), and replace it by a direct call to memblock_mark_hotplug(). Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/1a61f75ec50d3c2922fcdbe33337266a58a4125f.1628671960.git.geert+renesas@glider.be Signed-off-by: Rob Herring --- drivers/of/fdt.c | 7 +------ include/linux/of_fdt.h | 1 - 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index e25b41591ab2..09ed7e597eee 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1045,7 +1045,7 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname, if (!hotpluggable) continue; - if (early_init_dt_mark_hotplug_memory_arch(base, size)) + if (memblock_mark_hotplug(base, size)) pr_warn("failed to mark hotplug range 0x%llx - 0x%llx\n", base, base + size); } @@ -1158,11 +1158,6 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size) memblock_add(base, size); } -int __init __weak early_init_dt_mark_hotplug_memory_arch(u64 base, u64 size) -{ - return memblock_mark_hotplug(base, size); -} - static void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) { void *ptr = memblock_alloc(size, align); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 3b1500a0116f..cf6a65b94d40 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -67,7 +67,6 @@ extern void early_init_fdt_scan_reserved_mem(void); extern void early_init_fdt_reserve_self(void); extern void __init early_init_dt_scan_chosen_arch(unsigned long node); extern void early_init_dt_add_memory_arch(u64 base, u64 size); -extern int early_init_dt_mark_hotplug_memory_arch(u64 base, u64 size); extern u64 dt_mem_next_cell(int s, const __be32 **cellp); /* Early flat tree scan hooks */ -- cgit v1.2.3 From 2a14c9ae15a38148484a128b84bff7e9ffd90d68 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 16 Jun 2021 14:19:33 -0700 Subject: params: lift param_set_uint_minmax to common code It is a useful helper hence move it to common code so others can enjoy it. Suggested-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Hannes Reinecke Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/moduleparam.h | 2 ++ kernel/params.c | 18 ++++++++++++++++++ net/sunrpc/xprtsock.c | 18 ------------------ 3 files changed, 20 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index eed280fae433..962cd41a2cb5 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -431,6 +431,8 @@ extern int param_get_int(char *buffer, const struct kernel_param *kp); extern const struct kernel_param_ops param_ops_uint; extern int param_set_uint(const char *val, const struct kernel_param *kp); extern int param_get_uint(char *buffer, const struct kernel_param *kp); +int param_set_uint_minmax(const char *val, const struct kernel_param *kp, + unsigned int min, unsigned int max); #define param_check_uint(name, p) __param_check(name, p, unsigned int) extern const struct kernel_param_ops param_ops_long; diff --git a/kernel/params.c b/kernel/params.c index 2daa2780a92c..8299bd764e42 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -243,6 +243,24 @@ STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); STANDARD_PARAM_DEF(hexint, unsigned int, "%#08x", kstrtouint); +int param_set_uint_minmax(const char *val, const struct kernel_param *kp, + unsigned int min, unsigned int max) +{ + unsigned int num; + int ret; + + if (!val) + return -EINVAL; + ret = kstrtouint(val, 0, &num); + if (ret) + return ret; + if (num < min || num > max) + return -EINVAL; + *((unsigned int *)kp->arg) = num; + return 0; +} +EXPORT_SYMBOL_GPL(param_set_uint_minmax); + int param_set_charp(const char *val, const struct kernel_param *kp) { if (strlen(val) > 1024) { diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index e573dcecdd66..b7dbdcbdeb6c 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -3149,24 +3149,6 @@ void cleanup_socket_xprt(void) xprt_unregister_transport(&xs_bc_tcp_transport); } -static int param_set_uint_minmax(const char *val, - const struct kernel_param *kp, - unsigned int min, unsigned int max) -{ - unsigned int num; - int ret; - - if (!val) - return -EINVAL; - ret = kstrtouint(val, 0, &num); - if (ret) - return ret; - if (num < min || num > max) - return -EINVAL; - *((unsigned int *)kp->arg) = num; - return 0; -} - static int param_set_portnr(const char *val, const struct kernel_param *kp) { return param_set_uint_minmax(val, kp, -- cgit v1.2.3 From c3b1c377f0102e88dea6354d9cdb34a9d1c90971 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Mon, 2 Aug 2021 14:02:34 +0000 Subject: tracing: Fix a typo in tracepoint.h It should be @prev_pid, not @prev_prid. Link: https://lkml.kernel.org/r/20210802140234.5383-1-shijie@os.amperecomputing.com Signed-off-by: Huang Shijie Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index ab58696d0ddd..28031b15f878 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -475,7 +475,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * * * * The declared 'local variable' is called '__entry' * * - * * __field(pid_t, prev_prid) is equivalent to a standard declaration: + * * __field(pid_t, prev_pid) is equivalent to a standard declaration: * * * * pid_t prev_pid; * * -- cgit v1.2.3 From c016baf7dc58e77acdedb2c75dac2b41b77bcf70 Mon Sep 17 00:00:00 2001 From: Rajendra Nayak Date: Thu, 12 Aug 2021 16:57:21 +0530 Subject: PM: domains: Add support for 'required-opps' to set default perf state Some devices within power domains with performance states do not support DVFS, but still need to vote on a default/static state while they are active. They can express this using the 'required-opps' property in device tree, which points to the phandle of the OPP supported by the corresponding power-domains. Add support to parse this information from DT and then set the specified performance state during attach and drop it on detach. runtime suspend/resume callbacks already have logic to drop/set the vote as needed and should take care of dropping the default perf state vote on runtime suspend and restore it back on runtime resume. Signed-off-by: Rajendra Nayak Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 30 ++++++++++++++++++++++++++++-- include/linux/pm_domain.h | 1 + 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index a934c679e6ce..e1c8994ae225 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2598,6 +2598,12 @@ static void genpd_dev_pm_detach(struct device *dev, bool power_off) dev_dbg(dev, "removing from PM domain %s\n", pd->name); + /* Drop the default performance state */ + if (dev_gpd_data(dev)->default_pstate) { + dev_pm_genpd_set_performance_state(dev, 0); + dev_gpd_data(dev)->default_pstate = 0; + } + for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) { ret = genpd_remove_device(pd, dev); if (ret != -EAGAIN) @@ -2637,6 +2643,7 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device *base_dev, { struct of_phandle_args pd_args; struct generic_pm_domain *pd; + int pstate; int ret; ret = of_parse_phandle_with_args(dev->of_node, "power-domains", @@ -2675,10 +2682,29 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device *base_dev, genpd_unlock(pd); } - if (ret) + if (ret) { genpd_remove_device(pd, dev); + return -EPROBE_DEFER; + } - return ret ? -EPROBE_DEFER : 1; + /* Set the default performance state */ + pstate = of_get_required_opp_performance_state(dev->of_node, index); + if (pstate < 0 && pstate != -ENODEV) { + ret = pstate; + goto err; + } else if (pstate > 0) { + ret = dev_pm_genpd_set_performance_state(dev, pstate); + if (ret) + goto err; + dev_gpd_data(dev)->default_pstate = pstate; + } + return 1; + +err: + dev_err(dev, "failed to set required performance state for power-domain %s: %d\n", + pd->name, ret); + genpd_remove_device(pd, dev); + return ret; } /** diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 21a0577305ef..67017c9390c8 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -198,6 +198,7 @@ struct generic_pm_domain_data { struct notifier_block *power_nb; int cpu; unsigned int performance_state; + unsigned int default_pstate; unsigned int rpm_pstate; ktime_t next_wakeup; void *data; -- cgit v1.2.3 From 1113f0b69c6a98ff4e733c306a6658a31f8cbc49 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 4 Aug 2021 11:56:20 +0200 Subject: bvec: add a bvec_virt helper Add a helper to get the virtual address for a bvec. This avoids that all callers need to know about the page + offset representation. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20210804095634.460779-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bvec.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index f9fa43b940ff..0e9bdd42dafb 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -229,4 +229,16 @@ static inline void memzero_bvec(struct bio_vec *bvec) memzero_page(bvec->bv_page, bvec->bv_offset, bvec->bv_len); } +/** + * bvec_virt - return the virtual address for a bvec + * @bvec: bvec to return the virtual address for + * + * Note: the caller must ensure that @bvec->bv_page is not a highmem page. + */ +static inline void *bvec_virt(struct bio_vec *bvec) +{ + WARN_ON_ONCE(PageHighMem(bvec->bv_page)); + return page_address(bvec->bv_page) + bvec->bv_offset; +} + #endif /* __LINUX_BVEC_H */ -- cgit v1.2.3 From 252c651a4c854b328445a536bd1892e999103fca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 17:26:23 +0200 Subject: blk-cgroup: stop using seq_get_buf seq_get_buf is a crutch that undoes all the memory safety of the seq_file interface. Use the normal seq_printf interfaces instead. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20210810152623.1796144-2-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 30 ++++++------------------------ block/blk-iocost.c | 23 +++++++++-------------- block/blk-iolatency.c | 38 +++++++++++++++++++------------------- block/mq-deadline-cgroup.c | 8 +++----- include/linux/blk-cgroup.h | 4 ++-- 5 files changed, 39 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 52aa0540ccaf..b8ec47dcce42 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -877,8 +877,6 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) bool has_stats = false; const char *dname; unsigned seq; - char *buf; - size_t size = seq_get_buf(s, &buf), off = 0; int i; if (!blkg->online) @@ -888,13 +886,7 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) if (!dname) return; - /* - * Hooray string manipulation, count is the size written NOT - * INCLUDING THE \0, so size is now count+1 less than what we - * had before, but we want to start writing the next bit from - * the \0 so we only add count to buf. - */ - off += scnprintf(buf+off, size-off, "%s ", dname); + seq_printf(s, "%s ", dname); do { seq = u64_stats_fetch_begin(&bis->sync); @@ -909,40 +901,30 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) if (rbytes || wbytes || rios || wios) { has_stats = true; - off += scnprintf(buf+off, size-off, - "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", + seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { has_stats = true; - off += scnprintf(buf+off, size-off, " use_delay=%d delay_nsec=%llu", + seq_printf(s, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), atomic64_read(&blkg->delay_nsec)); } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; - size_t written; if (!blkg->pd[i] || !pol->pd_stat_fn) continue; - written = pol->pd_stat_fn(blkg->pd[i], buf+off, size-off); - if (written) + if (pol->pd_stat_fn(blkg->pd[i], s)) has_stats = true; - off += written; } - if (has_stats) { - if (off < size - 1) { - off += scnprintf(buf+off, size-off, "\n"); - seq_commit(s, off); - } else { - seq_commit(s, -1); - } - } + if (has_stats) + seq_printf(s, "\n"); } static int blkcg_print_stat(struct seq_file *sf, void *v) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 5fac3757e6e0..89b21a360b2c 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2988,34 +2988,29 @@ static void ioc_pd_free(struct blkg_policy_data *pd) kfree(iocg); } -static size_t ioc_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size) +static bool ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; - size_t pos = 0; if (!ioc->enabled) - return 0; + return false; if (iocg->level == 0) { unsigned vp10k = DIV64_U64_ROUND_CLOSEST( ioc->vtime_base_rate * 10000, VTIME_PER_USEC); - pos += scnprintf(buf + pos, size - pos, " cost.vrate=%u.%02u", - vp10k / 100, vp10k % 100); + seq_printf(s, " cost.vrate=%u.%02u", vp10k / 100, vp10k % 100); } - pos += scnprintf(buf + pos, size - pos, " cost.usage=%llu", - iocg->last_stat.usage_us); + seq_printf(s, " cost.usage=%llu", iocg->last_stat.usage_us); if (blkcg_debug_stats) - pos += scnprintf(buf + pos, size - pos, - " cost.wait=%llu cost.indebt=%llu cost.indelay=%llu", - iocg->last_stat.wait_us, - iocg->last_stat.indebt_us, - iocg->last_stat.indelay_us); - - return pos; + seq_printf(s, " cost.wait=%llu cost.indebt=%llu cost.indelay=%llu", + iocg->last_stat.wait_us, + iocg->last_stat.indebt_us, + iocg->last_stat.indelay_us); + return true; } static u64 ioc_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd, diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 81be0096411d..4c06fafb7411 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -886,8 +886,7 @@ static int iolatency_print_limit(struct seq_file *sf, void *v) return 0; } -static size_t iolatency_ssd_stat(struct iolatency_grp *iolat, char *buf, - size_t size) +static bool iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s) { struct latency_stat stat; int cpu; @@ -902,39 +901,40 @@ static size_t iolatency_ssd_stat(struct iolatency_grp *iolat, char *buf, preempt_enable(); if (iolat->rq_depth.max_depth == UINT_MAX) - return scnprintf(buf, size, " missed=%llu total=%llu depth=max", - (unsigned long long)stat.ps.missed, - (unsigned long long)stat.ps.total); - return scnprintf(buf, size, " missed=%llu total=%llu depth=%u", - (unsigned long long)stat.ps.missed, - (unsigned long long)stat.ps.total, - iolat->rq_depth.max_depth); + seq_printf(s, " missed=%llu total=%llu depth=max", + (unsigned long long)stat.ps.missed, + (unsigned long long)stat.ps.total); + else + seq_printf(s, " missed=%llu total=%llu depth=%u", + (unsigned long long)stat.ps.missed, + (unsigned long long)stat.ps.total, + iolat->rq_depth.max_depth); + return true; } -static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf, - size_t size) +static bool iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct iolatency_grp *iolat = pd_to_lat(pd); unsigned long long avg_lat; unsigned long long cur_win; if (!blkcg_debug_stats) - return 0; + return false; if (iolat->ssd) - return iolatency_ssd_stat(iolat, buf, size); + return iolatency_ssd_stat(iolat, s); avg_lat = div64_u64(iolat->lat_avg, NSEC_PER_USEC); cur_win = div64_u64(iolat->cur_win_nsec, NSEC_PER_MSEC); if (iolat->rq_depth.max_depth == UINT_MAX) - return scnprintf(buf, size, " depth=max avg_lat=%llu win=%llu", - avg_lat, cur_win); - - return scnprintf(buf, size, " depth=%u avg_lat=%llu win=%llu", - iolat->rq_depth.max_depth, avg_lat, cur_win); + seq_printf(s, " depth=max avg_lat=%llu win=%llu", + avg_lat, cur_win); + else + seq_printf(s, " depth=%u avg_lat=%llu win=%llu", + iolat->rq_depth.max_depth, avg_lat, cur_win); + return true; } - static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg) diff --git a/block/mq-deadline-cgroup.c b/block/mq-deadline-cgroup.c index 3b4bfddec39f..b48a4b962f90 100644 --- a/block/mq-deadline-cgroup.c +++ b/block/mq-deadline-cgroup.c @@ -52,7 +52,7 @@ struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio) return dd_blkcg_from_pd(pd); } -static size_t dd_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size) +static bool dd_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { static const char *const prio_class_name[] = { [IOPRIO_CLASS_NONE] = "NONE", @@ -61,12 +61,10 @@ static size_t dd_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size) [IOPRIO_CLASS_IDLE] = "IDLE", }; struct dd_blkcg *blkcg = dd_blkcg_from_pd(pd); - int res = 0; u8 prio; for (prio = 0; prio < ARRAY_SIZE(blkcg->stats->stats); prio++) - res += scnprintf(buf + res, size - res, - " [%s] dispatched=%u inserted=%u merged=%u", + seq_printf(s, " [%s] dispatched=%u inserted=%u merged=%u", prio_class_name[prio], ddcg_sum(blkcg, dispatched, prio) + ddcg_sum(blkcg, merged, prio) - @@ -75,7 +73,7 @@ static size_t dd_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size) ddcg_sum(blkcg, completed, prio), ddcg_sum(blkcg, merged, prio)); - return res; + return true; } static struct blkg_policy_data *dd_pd_alloc(gfp_t gfp, struct request_queue *q, diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 37048438872c..b4de2010fba5 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -152,8 +152,8 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); -typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf, - size_t size); +typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, + struct seq_file *s); struct blkcg_policy { int plid; -- cgit v1.2.3 From 15538a20579fa4047912508b03b39bcdeec26b05 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 11 Aug 2021 21:14:32 +0100 Subject: notifier: Remove atomic_notifier_call_chain_robust() This now has no more users, remove it. Suggested-by: Sebastian Andrzej Siewior Signed-off-by: Valentin Schneider Acked-by: Sebastian Andrzej Siewior Signed-off-by: Rafael J. Wysocki --- include/linux/notifier.h | 2 -- kernel/notifier.c | 19 ------------------- 2 files changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 2fb373a5c1ed..87069b8459af 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -168,8 +168,6 @@ extern int raw_notifier_call_chain(struct raw_notifier_head *nh, extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v); -extern int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh, - unsigned long val_up, unsigned long val_down, void *v); extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, diff --git a/kernel/notifier.c b/kernel/notifier.c index 1b019cbca594..b8251dc0bc0f 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -172,25 +172,6 @@ int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, } EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister); -int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh, - unsigned long val_up, unsigned long val_down, void *v) -{ - unsigned long flags; - int ret; - - /* - * Musn't use RCU; because then the notifier list can - * change between the up and down traversal. - */ - spin_lock_irqsave(&nh->lock, flags); - ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v); - spin_unlock_irqrestore(&nh->lock, flags); - - return ret; -} -EXPORT_SYMBOL_GPL(atomic_notifier_call_chain_robust); -NOKPROBE_SYMBOL(atomic_notifier_call_chain_robust); - /** * atomic_notifier_call_chain - Call functions in an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain -- cgit v1.2.3 From fb7dd8bca0139fd73d3f4a6cd257b11731317ded Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 15 Aug 2021 00:05:54 -0700 Subject: bpf: Refactor BPF_PROG_RUN into a function Turn BPF_PROG_RUN into a proper always inlined function. No functional and performance changes are intended, but it makes it much easier to understand what's going on with how BPF programs are actually get executed. It's more obvious what types and callbacks are expected. Also extra () around input parameters can be dropped, as well as `__` variable prefixes intended to avoid naming collisions, which makes the code simpler to read and write. This refactoring also highlighted one extra issue. BPF_PROG_RUN is both a macro and an enum value (BPF_PROG_RUN == BPF_PROG_TEST_RUN). Turning BPF_PROG_RUN into a function causes naming conflict compilation error. So rename BPF_PROG_RUN into lower-case bpf_prog_run(), similar to bpf_prog_run_xdp(), bpf_prog_run_pin_on_cpu(), etc. All existing callers of BPF_PROG_RUN, the macro, are switched to bpf_prog_run() explicitly. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210815070609.987780-2-andrii@kernel.org --- Documentation/networking/filter.rst | 4 +-- drivers/media/rc/bpf-lirc.c | 2 +- drivers/net/ppp/ppp_generic.c | 8 ++--- drivers/net/team/team_mode_loadbalance.c | 2 +- include/linux/bpf.h | 2 +- include/linux/filter.h | 61 +++++++++++++++++++------------- kernel/bpf/bpf_iter.c | 2 +- kernel/bpf/cgroup.c | 16 ++++----- kernel/bpf/core.c | 2 +- kernel/bpf/trampoline.c | 2 +- kernel/bpf/verifier.c | 2 +- kernel/events/core.c | 2 +- kernel/trace/bpf_trace.c | 4 +-- lib/test_bpf.c | 2 +- net/bpf/test_run.c | 6 ++-- net/core/filter.c | 4 +-- net/core/ptp_classifier.c | 2 +- net/netfilter/xt_bpf.c | 2 +- net/sched/act_bpf.c | 4 +-- net/sched/cls_bpf.c | 4 +-- 20 files changed, 73 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/filter.rst b/Documentation/networking/filter.rst index 5f13905b12e0..ce2b8e8bb9ab 100644 --- a/Documentation/networking/filter.rst +++ b/Documentation/networking/filter.rst @@ -638,8 +638,8 @@ extension, PTP dissector/classifier, and much more. They are all internally converted by the kernel into the new instruction set representation and run in the eBPF interpreter. For in-kernel handlers, this all works transparently by using bpf_prog_create() for setting up the filter, resp. -bpf_prog_destroy() for destroying it. The macro -BPF_PROG_RUN(filter, ctx) transparently invokes eBPF interpreter or JITed +bpf_prog_destroy() for destroying it. The function +bpf_prog_run(filter, ctx) transparently invokes eBPF interpreter or JITed code to run the filter. 'filter' is a pointer to struct bpf_prog that we got from bpf_prog_create(), and 'ctx' the given context (e.g. skb pointer). All constraints and restrictions from bpf_check_classic() apply diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index afae0afe3f81..bb5a9dc78f1b 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -217,7 +217,7 @@ void lirc_bpf_run(struct rc_dev *rcdev, u32 sample) raw->bpf_sample = sample; if (raw->progs) - BPF_PROG_RUN_ARRAY(raw->progs, &raw->bpf_sample, BPF_PROG_RUN); + BPF_PROG_RUN_ARRAY(raw->progs, &raw->bpf_sample, bpf_prog_run); } /* diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index e9e81573f21e..fb52cd175b45 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1744,7 +1744,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) a four-byte PPP header on each packet */ *(u8 *)skb_push(skb, 2) = 1; if (ppp->pass_filter && - BPF_PROG_RUN(ppp->pass_filter, skb) == 0) { + bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: outbound frame " @@ -1754,7 +1754,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) } /* if this packet passes the active filter, record the time */ if (!(ppp->active_filter && - BPF_PROG_RUN(ppp->active_filter, skb) == 0)) + bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_xmit = jiffies; skb_pull(skb, 2); #else @@ -2468,7 +2468,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) *(u8 *)skb_push(skb, 2) = 0; if (ppp->pass_filter && - BPF_PROG_RUN(ppp->pass_filter, skb) == 0) { + bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: inbound frame " @@ -2477,7 +2477,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) return; } if (!(ppp->active_filter && - BPF_PROG_RUN(ppp->active_filter, skb) == 0)) + bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_recv = jiffies; __skb_pull(skb, 2); } else diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c index 32aef8ac4a14..b095a4b4957b 100644 --- a/drivers/net/team/team_mode_loadbalance.c +++ b/drivers/net/team/team_mode_loadbalance.c @@ -197,7 +197,7 @@ static unsigned int lb_get_skb_hash(struct lb_priv *lb_priv, fp = rcu_dereference_bh(lb_priv->fp); if (unlikely(!fp)) return 0; - lhash = BPF_PROG_RUN(fp, skb); + lhash = bpf_prog_run(fp, skb); c = (char *) &lhash; return c[0] ^ c[1] ^ c[2] ^ c[3]; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c8cc09013210..968fea98087a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1103,7 +1103,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, /* an array of programs to be executed under rcu_lock. * * Typical usage: - * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN); + * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, bpf_prog_run); * * the structure returned by bpf_prog_array_alloc() should be populated * with program pointers and the last pointer must be NULL. diff --git a/include/linux/filter.h b/include/linux/filter.h index 1797e8506929..954373db20e7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -600,25 +600,38 @@ struct sk_filter { DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); -#define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \ - u32 __ret; \ - cant_migrate(); \ - if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ - struct bpf_prog_stats *__stats; \ - u64 __start = sched_clock(); \ - __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ - __stats = this_cpu_ptr(prog->stats); \ - u64_stats_update_begin(&__stats->syncp); \ - __stats->cnt++; \ - __stats->nsecs += sched_clock() - __start; \ - u64_stats_update_end(&__stats->syncp); \ - } else { \ - __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ - } \ - __ret; }) - -#define BPF_PROG_RUN(prog, ctx) \ - __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func) +typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, + const struct bpf_insn *insnsi, + unsigned int (*bpf_func)(const void *, + const struct bpf_insn *)); + +static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, + const void *ctx, + bpf_dispatcher_fn dfunc) +{ + u32 ret; + + cant_migrate(); + if (static_branch_unlikely(&bpf_stats_enabled_key)) { + struct bpf_prog_stats *stats; + u64 start = sched_clock(); + + ret = dfunc(ctx, prog->insnsi, prog->bpf_func); + stats = this_cpu_ptr(prog->stats); + u64_stats_update_begin(&stats->syncp); + stats->cnt++; + stats->nsecs += sched_clock() - start; + u64_stats_update_end(&stats->syncp); + } else { + ret = dfunc(ctx, prog->insnsi, prog->bpf_func); + } + return ret; +} + +static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx) +{ + return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func); +} /* * Use in preemptible and therefore migratable context to make sure that @@ -637,7 +650,7 @@ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, u32 ret; migrate_disable(); - ret = __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func); + ret = bpf_prog_run(prog, ctx); migrate_enable(); return ret; } @@ -742,7 +755,7 @@ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, memset(cb_data, 0, sizeof(cb_saved)); } - res = BPF_PROG_RUN(prog, skb); + res = bpf_prog_run(prog, skb); if (unlikely(prog->cb_access)) memcpy(cb_data, cb_saved, sizeof(cb_saved)); @@ -787,7 +800,7 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, * under local_bh_disable(), which provides the needed RCU protection * for accessing map entries. */ - u32 act = __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); + u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) { if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev)) @@ -1440,7 +1453,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, }; u32 act; - act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); + act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; @@ -1478,7 +1491,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, }; u32 act; - act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); + act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 2e9d47bb40ff..b2ee45064e06 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -686,7 +686,7 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) rcu_read_lock(); migrate_disable(); - ret = BPF_PROG_RUN(prog, ctx); + ret = bpf_prog_run(prog, ctx); migrate_enable(); rcu_read_unlock(); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 9f6070369caa..16dc467adfa0 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1043,7 +1043,7 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); int ret; - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, BPF_PROG_RUN); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, bpf_prog_run); return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -1091,7 +1091,7 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ret = BPF_PROG_RUN_ARRAY_FLAGS(cgrp->bpf.effective[type], &ctx, - BPF_PROG_RUN, flags); + bpf_prog_run, flags); return ret == 1 ? 0 : -EPERM; } @@ -1121,7 +1121,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int ret; ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops, - BPF_PROG_RUN); + bpf_prog_run); return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); @@ -1140,7 +1140,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, rcu_read_lock(); cgrp = task_dfl_cgroup(current); allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, - BPF_PROG_RUN); + bpf_prog_run); rcu_read_unlock(); return !allow; @@ -1271,7 +1271,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, rcu_read_lock(); cgrp = task_dfl_cgroup(current); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, bpf_prog_run); rcu_read_unlock(); kfree(ctx.cur_val); @@ -1386,7 +1386,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, lock_sock(sk); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_SETSOCKOPT], - &ctx, BPF_PROG_RUN); + &ctx, bpf_prog_run); release_sock(sk); if (!ret) { @@ -1496,7 +1496,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, lock_sock(sk); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], - &ctx, BPF_PROG_RUN); + &ctx, bpf_prog_run); release_sock(sk); if (!ret) { @@ -1557,7 +1557,7 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, */ ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], - &ctx, BPF_PROG_RUN); + &ctx, bpf_prog_run); if (!ret) return -EPERM; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 82af6279992d..5ee2ec27c3d4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1879,7 +1879,7 @@ static void bpf_prog_select_func(struct bpf_prog *fp) * @err: pointer to error variable * * Try to JIT eBPF program, if JIT is not available, use interpreter. - * The BPF program will be executed via BPF_PROG_RUN() macro. + * The BPF program will be executed via bpf_prog_run() function. * * Return: the &fp argument along with &err set to 0 for success or * a negative errno code on failure diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index b2535acfe9db..fe1e857324e6 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -548,7 +548,7 @@ static void notrace inc_misses_counter(struct bpf_prog *prog) u64_stats_update_end(&stats->syncp); } -/* The logic is similar to BPF_PROG_RUN, but with an explicit +/* The logic is similar to bpf_prog_run(), but with an explicit * rcu_read_lock() and migrate_disable() which are required * for the trampoline. The macro is split into * call __bpf_prog_enter diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5ea2238a6656..f5a0077c9981 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -12383,7 +12383,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) subprog_end = env->subprog_info[i + 1].start; len = subprog_end - subprog_start; - /* BPF_PROG_RUN doesn't call subprogs directly, + /* bpf_prog_run() doesn't call subprogs directly, * hence main prog stats include the runtime of subprogs. * subprogs don't have IDs and not reachable via prog_get_next_id * func[i]->stats will never be accessed and stays NULL diff --git a/kernel/events/core.c b/kernel/events/core.c index 1cb1f9b8392e..7d20743b48e1 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9913,7 +9913,7 @@ static void bpf_overflow_handler(struct perf_event *event, if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) goto out; rcu_read_lock(); - ret = BPF_PROG_RUN(event->prog, &ctx); + ret = bpf_prog_run(event->prog, &ctx); rcu_read_unlock(); out: __this_cpu_dec(bpf_prog_active); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0da94e1d6af9..05a5a556671d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -124,7 +124,7 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) * out of events when it was updated in between this and the * rcu_dereference() which is accepted risk. */ - ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN); + ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, bpf_prog_run); out: __this_cpu_dec(bpf_prog_active); @@ -1816,7 +1816,7 @@ void __bpf_trace_run(struct bpf_prog *prog, u64 *args) { cant_sleep(); rcu_read_lock(); - (void) BPF_PROG_RUN(prog, args); + (void) bpf_prog_run(prog, args); rcu_read_unlock(); } diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 77fe6fde56c5..830a18ecffc8 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -8616,7 +8616,7 @@ static int __run_one(const struct bpf_prog *fp, const void *data, start = ktime_get_ns(); for (i = 0; i < runs; i++) - ret = BPF_PROG_RUN(fp, data); + ret = bpf_prog_run(fp, data); finish = ktime_get_ns(); migrate_enable(); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 4b855af267b1..2eb0e55ef54d 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -116,7 +116,7 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, if (xdp) *retval = bpf_prog_run_xdp(prog, ctx); else - *retval = BPF_PROG_RUN(prog, ctx); + *retval = bpf_prog_run(prog, ctx); } while (bpf_test_timer_continue(&t, repeat, &ret, time)); bpf_reset_run_ctx(old_ctx); bpf_test_timer_leave(&t); @@ -327,7 +327,7 @@ __bpf_prog_test_run_raw_tp(void *data) struct bpf_raw_tp_test_run_info *info = data; rcu_read_lock(); - info->retval = BPF_PROG_RUN(info->prog, info->ctx); + info->retval = bpf_prog_run(info->prog, info->ctx); rcu_read_unlock(); } @@ -989,7 +989,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat bpf_test_timer_enter(&t); do { ctx.selected_sk = NULL; - retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, BPF_PROG_RUN); + retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, bpf_prog_run); } while (bpf_test_timer_continue(&t, repeat, &ret, &duration)); bpf_test_timer_leave(&t); diff --git a/net/core/filter.c b/net/core/filter.c index 3aca07c44fad..5cf38e8886f1 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -114,7 +114,7 @@ EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user); * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller * than pkt_len we keep whole skb->data. This is the socket level - * wrapper to BPF_PROG_RUN. It returns 0 if the packet should + * wrapper to bpf_prog_run. It returns 0 if the packet should * be accepted or -EPERM if the packet should be tossed. * */ @@ -10115,7 +10115,7 @@ struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, enum sk_action action; bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); - action = BPF_PROG_RUN(prog, &reuse_kern); + action = bpf_prog_run(prog, &reuse_kern); if (action == SK_PASS) return reuse_kern.selected_sk; diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index e33fde06d528..dd4cf01d1e0a 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -103,7 +103,7 @@ static struct bpf_prog *ptp_insns __read_mostly; unsigned int ptp_classify_raw(const struct sk_buff *skb) { - return BPF_PROG_RUN(ptp_insns, skb); + return bpf_prog_run(ptp_insns, skb); } EXPORT_SYMBOL_GPL(ptp_classify_raw); diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 13cf3f9b5938..849ac552a154 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -90,7 +90,7 @@ static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_bpf_info *info = par->matchinfo; - return BPF_PROG_RUN(info->filter, skb); + return bpf_prog_run(info->filter, skb); } static bool bpf_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 040807aa15b9..5c36013339e1 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -47,11 +47,11 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, if (at_ingress) { __skb_push(skb, skb->mac_len); bpf_compute_data_pointers(skb); - filter_res = BPF_PROG_RUN(filter, skb); + filter_res = bpf_prog_run(filter, skb); __skb_pull(skb, skb->mac_len); } else { bpf_compute_data_pointers(skb); - filter_res = BPF_PROG_RUN(filter, skb); + filter_res = bpf_prog_run(filter, skb); } if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) skb_orphan(skb); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 3b472bafdc9d..df19a847829e 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -96,11 +96,11 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); bpf_compute_data_pointers(skb); - filter_res = BPF_PROG_RUN(prog->filter, skb); + filter_res = bpf_prog_run(prog->filter, skb); __skb_pull(skb, skb->mac_len); } else { bpf_compute_data_pointers(skb); - filter_res = BPF_PROG_RUN(prog->filter, skb); + filter_res = bpf_prog_run(prog->filter, skb); } if (prog->exts_integrated) { -- cgit v1.2.3 From 7d08c2c9117113fee118487425ed55efa50cbfa9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 15 Aug 2021 00:05:55 -0700 Subject: bpf: Refactor BPF_PROG_RUN_ARRAY family of macros into functions Similar to BPF_PROG_RUN, turn BPF_PROG_RUN_ARRAY macros into proper functions with all the same readability and maintainability benefits. Making them into functions required shuffling around bpf_set_run_ctx/bpf_reset_run_ctx functions. Also, explicitly specifying the type of the BPF prog run callback required adjusting __bpf_prog_run_save_cb() to accept const void *, casted internally to const struct sk_buff. Further, split out a cgroup-specific BPF_PROG_RUN_ARRAY_CG and BPF_PROG_RUN_ARRAY_CG_FLAGS from the more generic BPF_PROG_RUN_ARRAY due to the differences in bpf_run_ctx used for those two different use cases. I think BPF_PROG_RUN_ARRAY_CG would benefit from further refactoring to accept struct cgroup and enum bpf_attach_type instead of bpf_prog_array, fetching cgrp->bpf.effective[type] and RCU-dereferencing it internally. But that required including include/linux/cgroup-defs.h, which I wasn't sure is ok with everyone. The remaining generic BPF_PROG_RUN_ARRAY function will be extended to pass-through user-provided context value in the next patch. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210815070609.987780-3-andrii@kernel.org --- include/linux/bpf.h | 179 +++++++++++++++++++++++++++-------------------- include/linux/filter.h | 5 +- kernel/bpf/cgroup.c | 32 ++++----- kernel/trace/bpf_trace.c | 2 +- 4 files changed, 124 insertions(+), 94 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 968fea98087a..344e0d4d8ef6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1146,67 +1146,116 @@ struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; - struct bpf_prog_array_item *prog_item; + const struct bpf_prog_array_item *prog_item; }; +static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) +{ + struct bpf_run_ctx *old_ctx = NULL; + +#ifdef CONFIG_BPF_SYSCALL + old_ctx = current->bpf_ctx; + current->bpf_ctx = new_ctx; +#endif + return old_ctx; +} + +static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) +{ +#ifdef CONFIG_BPF_SYSCALL + current->bpf_ctx = old_ctx; +#endif +} + /* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ #define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) /* BPF program asks to set CN on the packet. */ #define BPF_RET_SET_CN (1 << 0) -#define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags) \ - ({ \ - struct bpf_prog_array_item *_item; \ - struct bpf_prog *_prog; \ - struct bpf_prog_array *_array; \ - struct bpf_run_ctx *old_run_ctx; \ - struct bpf_cg_run_ctx run_ctx; \ - u32 _ret = 1; \ - u32 func_ret; \ - migrate_disable(); \ - rcu_read_lock(); \ - _array = rcu_dereference(array); \ - _item = &_array->items[0]; \ - old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); \ - while ((_prog = READ_ONCE(_item->prog))) { \ - run_ctx.prog_item = _item; \ - func_ret = func(_prog, ctx); \ - _ret &= (func_ret & 1); \ - *(ret_flags) |= (func_ret >> 1); \ - _item++; \ - } \ - bpf_reset_run_ctx(old_run_ctx); \ - rcu_read_unlock(); \ - migrate_enable(); \ - _ret; \ - }) - -#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage) \ - ({ \ - struct bpf_prog_array_item *_item; \ - struct bpf_prog *_prog; \ - struct bpf_prog_array *_array; \ - struct bpf_run_ctx *old_run_ctx; \ - struct bpf_cg_run_ctx run_ctx; \ - u32 _ret = 1; \ - migrate_disable(); \ - rcu_read_lock(); \ - _array = rcu_dereference(array); \ - if (unlikely(check_non_null && !_array))\ - goto _out; \ - _item = &_array->items[0]; \ - old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);\ - while ((_prog = READ_ONCE(_item->prog))) { \ - run_ctx.prog_item = _item; \ - _ret &= func(_prog, ctx); \ - _item++; \ - } \ - bpf_reset_run_ctx(old_run_ctx); \ -_out: \ - rcu_read_unlock(); \ - migrate_enable(); \ - _ret; \ - }) +typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); + +static __always_inline u32 +BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog, + u32 *ret_flags) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const struct bpf_prog_array *array; + struct bpf_run_ctx *old_run_ctx; + struct bpf_cg_run_ctx run_ctx; + u32 ret = 1; + u32 func_ret; + + migrate_disable(); + rcu_read_lock(); + array = rcu_dereference(array_rcu); + item = &array->items[0]; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + while ((prog = READ_ONCE(item->prog))) { + run_ctx.prog_item = item; + func_ret = run_prog(prog, ctx); + ret &= (func_ret & 1); + *(ret_flags) |= (func_ret >> 1); + item++; + } + bpf_reset_run_ctx(old_run_ctx); + rcu_read_unlock(); + migrate_enable(); + return ret; +} + +static __always_inline u32 +BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const struct bpf_prog_array *array; + struct bpf_run_ctx *old_run_ctx; + struct bpf_cg_run_ctx run_ctx; + u32 ret = 1; + + migrate_disable(); + rcu_read_lock(); + array = rcu_dereference(array_rcu); + item = &array->items[0]; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + while ((prog = READ_ONCE(item->prog))) { + run_ctx.prog_item = item; + ret &= run_prog(prog, ctx); + item++; + } + bpf_reset_run_ctx(old_run_ctx); + rcu_read_unlock(); + migrate_enable(); + return ret; +} + +static __always_inline u32 +BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const struct bpf_prog_array *array; + u32 ret = 1; + + migrate_disable(); + rcu_read_lock(); + array = rcu_dereference(array_rcu); + if (unlikely(!array)) + goto out; + item = &array->items[0]; + while ((prog = READ_ONCE(item->prog))) { + ret &= run_prog(prog, ctx); + item++; + } +out: + rcu_read_unlock(); + migrate_enable(); + return ret; +} /* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs * so BPF programs can request cwr for TCP packets. @@ -1235,7 +1284,7 @@ _out: \ u32 _flags = 0; \ bool _cn; \ u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, &_flags); \ + _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ if (_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ @@ -1244,12 +1293,6 @@ _out: \ _ret; \ }) -#define BPF_PROG_RUN_ARRAY(array, ctx, func) \ - __BPF_PROG_RUN_ARRAY(array, ctx, func, false, true) - -#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \ - __BPF_PROG_RUN_ARRAY(array, ctx, func, true, false) - #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; @@ -1284,20 +1327,6 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } -static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) -{ - struct bpf_run_ctx *old_ctx; - - old_ctx = current->bpf_ctx; - current->bpf_ctx = new_ctx; - return old_ctx; -} - -static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) -{ - current->bpf_ctx = old_ctx; -} - extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; diff --git a/include/linux/filter.h b/include/linux/filter.h index 954373db20e7..7d248941ecea 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -723,7 +723,7 @@ static inline void bpf_restore_data_end( cb->data_end = saved_data_end; } -static inline u8 *bpf_skb_cb(struct sk_buff *skb) +static inline u8 *bpf_skb_cb(const struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta * data between tail calls. Since this also needs to work with @@ -744,8 +744,9 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) /* Must be invoked with migration disabled */ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, - struct sk_buff *skb) + const void *ctx) { + const struct sk_buff *skb = ctx; u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; u32 res; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 16dc467adfa0..a1dedba4c174 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1012,8 +1012,8 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, ret = BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY( cgrp->bpf.effective[type], skb, __bpf_prog_run_save_cb); } else { - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, - __bpf_prog_run_save_cb); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[type], skb, + __bpf_prog_run_save_cb); ret = (ret == 1 ? 0 : -EPERM); } bpf_restore_data_end(skb, saved_data_end); @@ -1043,7 +1043,7 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); int ret; - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[type], sk, bpf_prog_run); return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -1090,8 +1090,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - ret = BPF_PROG_RUN_ARRAY_FLAGS(cgrp->bpf.effective[type], &ctx, - bpf_prog_run, flags); + ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[type], &ctx, + bpf_prog_run, flags); return ret == 1 ? 0 : -EPERM; } @@ -1120,8 +1120,8 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); int ret; - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops, - bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[type], sock_ops, + bpf_prog_run); return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); @@ -1139,8 +1139,8 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, rcu_read_lock(); cgrp = task_dfl_cgroup(current); - allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, - bpf_prog_run); + allow = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[type], &ctx, + bpf_prog_run); rcu_read_unlock(); return !allow; @@ -1271,7 +1271,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, rcu_read_lock(); cgrp = task_dfl_cgroup(current); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[type], &ctx, bpf_prog_run); rcu_read_unlock(); kfree(ctx.cur_val); @@ -1385,8 +1385,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, } lock_sock(sk); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_SETSOCKOPT], - &ctx, bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[BPF_CGROUP_SETSOCKOPT], + &ctx, bpf_prog_run); release_sock(sk); if (!ret) { @@ -1495,8 +1495,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, } lock_sock(sk); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], - &ctx, bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], + &ctx, bpf_prog_run); release_sock(sk); if (!ret) { @@ -1556,8 +1556,8 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, * be called if that data shouldn't be "exported". */ - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], - &ctx, bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], + &ctx, bpf_prog_run); if (!ret) return -EPERM; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 05a5a556671d..91867b14b222 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -124,7 +124,7 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) * out of events when it was updated in between this and the * rcu_dereference() which is accepted risk. */ - ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY(call->prog_array, ctx, bpf_prog_run); out: __this_cpu_dec(bpf_prog_active); -- cgit v1.2.3 From b89fbfbb854c9afc3047e8273cc3a694650b802e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 15 Aug 2021 00:05:57 -0700 Subject: bpf: Implement minimal BPF perf link Introduce a new type of BPF link - BPF perf link. This brings perf_event-based BPF program attachments (perf_event, tracepoints, kprobes, and uprobes) into the common BPF link infrastructure, allowing to list all active perf_event based attachments, auto-detaching BPF program from perf_event when link's FD is closed, get generic BPF link fdinfo/get_info functionality. BPF_LINK_CREATE command expects perf_event's FD as target_fd. No extra flags are currently supported. Force-detaching and atomic BPF program updates are not yet implemented, but with perf_event-based BPF links we now have common framework for this without the need to extend ioctl()-based perf_event interface. One interesting consideration is a new value for bpf_attach_type, which BPF_LINK_CREATE command expects. Generally, it's either 1-to-1 mapping from bpf_attach_type to bpf_prog_type, or many-to-1 mapping from a subset of bpf_attach_types to one bpf_prog_type (e.g., see BPF_PROG_TYPE_SK_SKB or BPF_PROG_TYPE_CGROUP_SOCK). In this case, though, we have three different program types (KPROBE, TRACEPOINT, PERF_EVENT) using the same perf_event-based mechanism, so it's many bpf_prog_types to one bpf_attach_type. I chose to define a single BPF_PERF_EVENT attach type for all of them and adjust link_create()'s logic for checking correspondence between attach type and program type. The alternative would be to define three new attach types (e.g., BPF_KPROBE, BPF_TRACEPOINT, and BPF_PERF_EVENT), but that seemed like unnecessary overkill and BPF_KPROBE will cause naming conflicts with BPF_KPROBE() macro, defined by libbpf. I chose to not do this to avoid unnecessary proliferation of bpf_attach_type enum values and not have to deal with naming conflicts. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/bpf/20210815070609.987780-5-andrii@kernel.org --- include/linux/bpf_types.h | 3 ++ include/linux/trace_events.h | 3 ++ include/uapi/linux/bpf.h | 2 + kernel/bpf/syscall.c | 105 ++++++++++++++++++++++++++++++++++++++--- kernel/events/core.c | 10 ++-- tools/include/uapi/linux/bpf.h | 2 + 6 files changed, 112 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index ae3ac3a2018c..9c81724e4b98 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -136,3 +136,6 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #endif +#ifdef CONFIG_PERF_EVENTS +BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) +#endif diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index ad413b382a3c..8ac92560d3a3 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -803,6 +803,9 @@ extern void ftrace_profile_free_filter(struct perf_event *event); void perf_trace_buf_update(void *record, u16 type); void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); +int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog); +void perf_event_free_bpf_prog(struct perf_event *event); + void bpf_trace_run1(struct bpf_prog *prog, u64 arg1); void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2); void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2db6925e04f4..94fe8329b28f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -993,6 +993,7 @@ enum bpf_attach_type { BPF_SK_SKB_VERDICT, BPF_SK_REUSEPORT_SELECT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, + BPF_PERF_EVENT, __MAX_BPF_ATTACH_TYPE }; @@ -1006,6 +1007,7 @@ enum bpf_link_type { BPF_LINK_TYPE_ITER = 4, BPF_LINK_TYPE_NETNS = 5, BPF_LINK_TYPE_XDP = 6, + BPF_LINK_TYPE_PERF_EVENT = 7, MAX_BPF_LINK_TYPE, }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 9a2068e39d23..80c03bedd6e6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2906,6 +2906,79 @@ static const struct bpf_link_ops bpf_raw_tp_link_lops = { .fill_link_info = bpf_raw_tp_link_fill_link_info, }; +#ifdef CONFIG_PERF_EVENTS +struct bpf_perf_link { + struct bpf_link link; + struct file *perf_file; +}; + +static void bpf_perf_link_release(struct bpf_link *link) +{ + struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); + struct perf_event *event = perf_link->perf_file->private_data; + + perf_event_free_bpf_prog(event); + fput(perf_link->perf_file); +} + +static void bpf_perf_link_dealloc(struct bpf_link *link) +{ + struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); + + kfree(perf_link); +} + +static const struct bpf_link_ops bpf_perf_link_lops = { + .release = bpf_perf_link_release, + .dealloc = bpf_perf_link_dealloc, +}; + +static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct bpf_perf_link *link; + struct perf_event *event; + struct file *perf_file; + int err; + + if (attr->link_create.flags) + return -EINVAL; + + perf_file = perf_event_get(attr->link_create.target_fd); + if (IS_ERR(perf_file)) + return PTR_ERR(perf_file); + + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto out_put_file; + } + bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog); + link->perf_file = perf_file; + + err = bpf_link_prime(&link->link, &link_primer); + if (err) { + kfree(link); + goto out_put_file; + } + + event = perf_file->private_data; + err = perf_event_set_bpf_prog(event, prog); + if (err) { + bpf_link_cleanup(&link_primer); + goto out_put_file; + } + /* perf_event_set_bpf_prog() doesn't take its own refcnt on prog */ + bpf_prog_inc(prog); + + return bpf_link_settle(&link_primer); + +out_put_file: + fput(perf_file); + return err; +} +#endif /* CONFIG_PERF_EVENTS */ + #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd static int bpf_raw_tracepoint_open(const union bpf_attr *attr) @@ -4147,15 +4220,26 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) if (ret) goto out; - if (prog->type == BPF_PROG_TYPE_EXT) { + switch (prog->type) { + case BPF_PROG_TYPE_EXT: ret = tracing_bpf_link_attach(attr, uattr, prog); goto out; - } - - ptype = attach_type_to_prog_type(attr->link_create.attach_type); - if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) { - ret = -EINVAL; - goto out; + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_TRACEPOINT: + if (attr->link_create.attach_type != BPF_PERF_EVENT) { + ret = -EINVAL; + goto out; + } + ptype = prog->type; + break; + default: + ptype = attach_type_to_prog_type(attr->link_create.attach_type); + if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) { + ret = -EINVAL; + goto out; + } + break; } switch (ptype) { @@ -4179,6 +4263,13 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) case BPF_PROG_TYPE_XDP: ret = bpf_xdp_link_attach(attr, prog); break; +#endif +#ifdef CONFIG_PERF_EVENTS + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_KPROBE: + ret = bpf_perf_link_attach(attr, prog); + break; #endif default: ret = -EINVAL; diff --git a/kernel/events/core.c b/kernel/events/core.c index 2f07718bd41c..9fd65667bcb2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4697,7 +4697,6 @@ errout: } static void perf_event_free_filter(struct perf_event *event); -static void perf_event_free_bpf_prog(struct perf_event *event); static void free_event_rcu(struct rcu_head *head) { @@ -5574,7 +5573,6 @@ static inline int perf_fget_light(int fd, struct fd *p) static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event); static int perf_event_set_filter(struct perf_event *event, void __user *arg); -static int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog); static int perf_copy_attr(struct perf_event_attr __user *uattr, struct perf_event_attr *attr); @@ -10013,7 +10011,7 @@ static inline bool perf_event_is_tracing(struct perf_event *event) return false; } -static int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog) +int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog) { bool is_kprobe, is_tracepoint, is_syscall_tp; @@ -10047,7 +10045,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *pr return perf_event_attach_bpf_prog(event, prog); } -static void perf_event_free_bpf_prog(struct perf_event *event) +void perf_event_free_bpf_prog(struct perf_event *event) { if (!perf_event_is_tracing(event)) { perf_event_free_bpf_handler(event); @@ -10066,12 +10064,12 @@ static void perf_event_free_filter(struct perf_event *event) { } -static int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog) +int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog) { return -ENOENT; } -static void perf_event_free_bpf_prog(struct perf_event *event) +void perf_event_free_bpf_prog(struct perf_event *event) { } #endif /* CONFIG_EVENT_TRACING */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 2db6925e04f4..94fe8329b28f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -993,6 +993,7 @@ enum bpf_attach_type { BPF_SK_SKB_VERDICT, BPF_SK_REUSEPORT_SELECT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, + BPF_PERF_EVENT, __MAX_BPF_ATTACH_TYPE }; @@ -1006,6 +1007,7 @@ enum bpf_link_type { BPF_LINK_TYPE_ITER = 4, BPF_LINK_TYPE_NETNS = 5, BPF_LINK_TYPE_XDP = 6, + BPF_LINK_TYPE_PERF_EVENT = 7, MAX_BPF_LINK_TYPE, }; -- cgit v1.2.3 From 82e6b1eee6a8875ef4eacfd60711cce6965c6b04 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 15 Aug 2021 00:05:58 -0700 Subject: bpf: Allow to specify user-provided bpf_cookie for BPF perf links Add ability for users to specify custom u64 value (bpf_cookie) when creating BPF link for perf_event-backed BPF programs (kprobe/uprobe, perf_event, tracepoints). This is useful for cases when the same BPF program is used for attaching and processing invocation of different tracepoints/kprobes/uprobes in a generic fashion, but such that each invocation is distinguished from each other (e.g., BPF program can look up additional information associated with a specific kernel function without having to rely on function IP lookups). This enables new use cases to be implemented simply and efficiently that previously were possible only through code generation (and thus multiple instances of almost identical BPF program) or compilation at runtime (BCC-style) on target hosts (even more expensive resource-wise). For uprobes it is not even possible in some cases to know function IP before hand (e.g., when attaching to shared library without PID filtering, in which case base load address is not known for a library). This is done by storing u64 bpf_cookie in struct bpf_prog_array_item, corresponding to each attached and run BPF program. Given cgroup BPF programs already use two 8-byte pointers for their needs and cgroup BPF programs don't have (yet?) support for bpf_cookie, reuse that space through union of cgroup_storage and new bpf_cookie field. Make it available to kprobe/tracepoint BPF programs through bpf_trace_run_ctx. This is set by BPF_PROG_RUN_ARRAY, used by kprobe/uprobe/tracepoint BPF program execution code, which luckily is now also split from BPF_PROG_RUN_ARRAY_CG. This run context will be utilized by a new BPF helper giving access to this user-provided cookie value from inside a BPF program. Generic perf_event BPF programs will access this value from perf_event itself through passed in BPF program context. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/bpf/20210815070609.987780-6-andrii@kernel.org --- drivers/media/rc/bpf-lirc.c | 4 ++-- include/linux/bpf.h | 16 +++++++++++++++- include/linux/perf_event.h | 1 + include/linux/trace_events.h | 6 +++--- include/uapi/linux/bpf.h | 7 +++++++ kernel/bpf/core.c | 29 ++++++++++++++++++----------- kernel/bpf/syscall.c | 2 +- kernel/events/core.c | 21 ++++++++++++++------- kernel/trace/bpf_trace.c | 8 +++++--- tools/include/uapi/linux/bpf.h | 7 +++++++ 10 files changed, 73 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index bb5a9dc78f1b..3eff08d7b8e5 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -160,7 +160,7 @@ static int lirc_bpf_attach(struct rc_dev *rcdev, struct bpf_prog *prog) goto unlock; } - ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array); + ret = bpf_prog_array_copy(old_array, NULL, prog, 0, &new_array); if (ret < 0) goto unlock; @@ -193,7 +193,7 @@ static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog) } old_array = lirc_rcu_dereference(raw->progs); - ret = bpf_prog_array_copy(old_array, prog, NULL, &new_array); + ret = bpf_prog_array_copy(old_array, prog, NULL, 0, &new_array); /* * Do not use bpf_prog_array_delete_safe() as we would end up * with a dummy entry in the array, and the we would free the diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 344e0d4d8ef6..83c3cc5e90df 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1114,7 +1114,10 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, */ struct bpf_prog_array_item { struct bpf_prog *prog; - struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; + union { + struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; + u64 bpf_cookie; + }; }; struct bpf_prog_array { @@ -1140,6 +1143,7 @@ int bpf_prog_array_copy_info(struct bpf_prog_array *array, int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, + u64 bpf_cookie, struct bpf_prog_array **new_array); struct bpf_run_ctx {}; @@ -1149,6 +1153,11 @@ struct bpf_cg_run_ctx { const struct bpf_prog_array_item *prog_item; }; +struct bpf_trace_run_ctx { + struct bpf_run_ctx run_ctx; + u64 bpf_cookie; +}; + static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) { struct bpf_run_ctx *old_ctx = NULL; @@ -1239,6 +1248,8 @@ BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; + struct bpf_run_ctx *old_run_ctx; + struct bpf_trace_run_ctx run_ctx; u32 ret = 1; migrate_disable(); @@ -1246,11 +1257,14 @@ BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, array = rcu_dereference(array_rcu); if (unlikely(!array)) goto out; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { + run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; } + bpf_reset_run_ctx(old_run_ctx); out: rcu_read_unlock(); migrate_enable(); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2d510ad750ed..fe156a8170aa 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -762,6 +762,7 @@ struct perf_event { #ifdef CONFIG_BPF_SYSCALL perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; + u64 bpf_cookie; #endif #ifdef CONFIG_EVENT_TRACING diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 8ac92560d3a3..8e0631a4b046 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -675,7 +675,7 @@ trace_trigger_soft_disabled(struct trace_event_file *file) #ifdef CONFIG_BPF_EVENTS unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); -int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog); +int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_detach_bpf_prog(struct perf_event *event); int perf_event_query_prog_array(struct perf_event *event, void __user *info); int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog); @@ -692,7 +692,7 @@ static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *c } static inline int -perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog) +perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie) { return -EOPNOTSUPP; } @@ -803,7 +803,7 @@ extern void ftrace_profile_free_filter(struct perf_event *event); void perf_trace_buf_update(void *record, u16 type); void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); -int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog); +int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_free_bpf_prog(struct perf_event *event); void bpf_trace_run1(struct bpf_prog *prog, u64 arg1); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 94fe8329b28f..63ee482d50e1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1448,6 +1448,13 @@ union bpf_attr { __aligned_u64 iter_info; /* extra bpf_iter_link_info */ __u32 iter_info_len; /* iter_info length */ }; + struct { + /* black box user-provided value passed through + * to BPF program at the execution time and + * accessible through bpf_get_attach_cookie() BPF helper + */ + __u64 bpf_cookie; + } perf_event; }; } link_create; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 5ee2ec27c3d4..91f24c7b38a1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2119,13 +2119,13 @@ int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, + u64 bpf_cookie, struct bpf_prog_array **new_array) { int new_prog_cnt, carry_prog_cnt = 0; - struct bpf_prog_array_item *existing; + struct bpf_prog_array_item *existing, *new; struct bpf_prog_array *array; bool found_exclude = false; - int new_prog_idx = 0; /* Figure out how many existing progs we need to carry over to * the new array. @@ -2162,20 +2162,27 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL); if (!array) return -ENOMEM; + new = array->items; /* Fill in the new prog array */ if (carry_prog_cnt) { existing = old_array->items; - for (; existing->prog; existing++) - if (existing->prog != exclude_prog && - existing->prog != &dummy_bpf_prog.prog) { - array->items[new_prog_idx++].prog = - existing->prog; - } + for (; existing->prog; existing++) { + if (existing->prog == exclude_prog || + existing->prog == &dummy_bpf_prog.prog) + continue; + + new->prog = existing->prog; + new->bpf_cookie = existing->bpf_cookie; + new++; + } } - if (include_prog) - array->items[new_prog_idx++].prog = include_prog; - array->items[new_prog_idx].prog = NULL; + if (include_prog) { + new->prog = include_prog; + new->bpf_cookie = bpf_cookie; + new++; + } + new->prog = NULL; *new_array = array; return 0; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 80c03bedd6e6..7420e1334ab2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2963,7 +2963,7 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro } event = perf_file->private_data; - err = perf_event_set_bpf_prog(event, prog); + err = perf_event_set_bpf_prog(event, prog, attr->link_create.perf_event.bpf_cookie); if (err) { bpf_link_cleanup(&link_primer); goto out_put_file; diff --git a/kernel/events/core.c b/kernel/events/core.c index 9fd65667bcb2..2d1e63dd97f2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5643,7 +5643,7 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon if (IS_ERR(prog)) return PTR_ERR(prog); - err = perf_event_set_bpf_prog(event, prog); + err = perf_event_set_bpf_prog(event, prog, 0); if (err) { bpf_prog_put(prog); return err; @@ -9936,7 +9936,9 @@ out: event->orig_overflow_handler(event, data, regs); } -static int perf_event_set_bpf_handler(struct perf_event *event, struct bpf_prog *prog) +static int perf_event_set_bpf_handler(struct perf_event *event, + struct bpf_prog *prog, + u64 bpf_cookie) { if (event->overflow_handler_context) /* hw breakpoint or kernel counter */ @@ -9966,6 +9968,7 @@ static int perf_event_set_bpf_handler(struct perf_event *event, struct bpf_prog } event->prog = prog; + event->bpf_cookie = bpf_cookie; event->orig_overflow_handler = READ_ONCE(event->overflow_handler); WRITE_ONCE(event->overflow_handler, bpf_overflow_handler); return 0; @@ -9983,7 +9986,9 @@ static void perf_event_free_bpf_handler(struct perf_event *event) bpf_prog_put(prog); } #else -static int perf_event_set_bpf_handler(struct perf_event *event, struct bpf_prog *prog) +static int perf_event_set_bpf_handler(struct perf_event *event, + struct bpf_prog *prog, + u64 bpf_cookie) { return -EOPNOTSUPP; } @@ -10011,12 +10016,13 @@ static inline bool perf_event_is_tracing(struct perf_event *event) return false; } -int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog) +int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, + u64 bpf_cookie) { bool is_kprobe, is_tracepoint, is_syscall_tp; if (!perf_event_is_tracing(event)) - return perf_event_set_bpf_handler(event, prog); + return perf_event_set_bpf_handler(event, prog, bpf_cookie); is_kprobe = event->tp_event->flags & TRACE_EVENT_FL_UKPROBE; is_tracepoint = event->tp_event->flags & TRACE_EVENT_FL_TRACEPOINT; @@ -10042,7 +10048,7 @@ int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog) return -EACCES; } - return perf_event_attach_bpf_prog(event, prog); + return perf_event_attach_bpf_prog(event, prog, bpf_cookie); } void perf_event_free_bpf_prog(struct perf_event *event) @@ -10064,7 +10070,8 @@ static void perf_event_free_filter(struct perf_event *event) { } -int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog) +int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, + u64 bpf_cookie) { return -ENOENT; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 91867b14b222..57879d28f824 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1675,7 +1675,8 @@ static DEFINE_MUTEX(bpf_event_mutex); #define BPF_TRACE_MAX_PROGS 64 int perf_event_attach_bpf_prog(struct perf_event *event, - struct bpf_prog *prog) + struct bpf_prog *prog, + u64 bpf_cookie) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; @@ -1702,12 +1703,13 @@ int perf_event_attach_bpf_prog(struct perf_event *event, goto unlock; } - ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array); + ret = bpf_prog_array_copy(old_array, NULL, prog, bpf_cookie, &new_array); if (ret < 0) goto unlock; /* set the new array to event->tp_event and set event->prog */ event->prog = prog; + event->bpf_cookie = bpf_cookie; rcu_assign_pointer(event->tp_event->prog_array, new_array); bpf_prog_array_free(old_array); @@ -1728,7 +1730,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); - ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array); + ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array); if (ret == -ENOENT) goto unlock; if (ret < 0) { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 94fe8329b28f..63ee482d50e1 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1448,6 +1448,13 @@ union bpf_attr { __aligned_u64 iter_info; /* extra bpf_iter_link_info */ __u32 iter_info_len; /* iter_info length */ }; + struct { + /* black box user-provided value passed through + * to BPF program at the execution time and + * accessible through bpf_get_attach_cookie() BPF helper + */ + __u64 bpf_cookie; + } perf_event; }; } link_create; -- cgit v1.2.3 From 7adfc6c9b315e174cf8743b21b7b691c8766791b Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 15 Aug 2021 00:05:59 -0700 Subject: bpf: Add bpf_get_attach_cookie() BPF helper to access bpf_cookie value Add new BPF helper, bpf_get_attach_cookie(), which can be used by BPF programs to get access to a user-provided bpf_cookie value, specified during BPF program attachment (BPF link creation) time. Naming is hard, though. With the concept being named "BPF cookie", I've considered calling the helper: - bpf_get_cookie() -- seems too unspecific and easily mistaken with socket cookie; - bpf_get_bpf_cookie() -- too much tautology; - bpf_get_link_cookie() -- would be ok, but while we create a BPF link to attach BPF program to BPF hook, it's still an "attachment" and the bpf_cookie is associated with BPF program attachment to a hook, not a BPF link itself. Technically, we could support bpf_cookie with old-style cgroup programs.So I ultimately rejected it in favor of bpf_get_attach_cookie(). Currently all perf_event-backed BPF program types support bpf_get_attach_cookie() helper. Follow-up patches will add support for fentry/fexit programs as well. While at it, mark bpf_tracing_func_proto() as static to make it obvious that it's only used from within the kernel/trace/bpf_trace.c. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210815070609.987780-7-andrii@kernel.org --- include/linux/bpf.h | 3 --- include/uapi/linux/bpf.h | 16 ++++++++++++++++ kernel/trace/bpf_trace.c | 35 ++++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 16 ++++++++++++++++ 4 files changed, 66 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 83c3cc5e90df..f4c16f19f83e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2102,9 +2102,6 @@ extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; -const struct bpf_func_proto *bpf_tracing_func_proto( - enum bpf_func_id func_id, const struct bpf_prog *prog); - const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 63ee482d50e1..c4f7892edb2b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4856,6 +4856,21 @@ union bpf_attr { * Get address of the traced function (for tracing and kprobe programs). * Return * Address of the traced function. + * + * u64 bpf_get_attach_cookie(void *ctx) + * Description + * Get bpf_cookie value provided (optionally) during the program + * attachment. It might be different for each individual + * attachment, even if BPF program itself is the same. + * Expects BPF program context *ctx* as a first argument. + * + * Supported for the following program types: + * - kprobe/uprobe; + * - tracepoint; + * - perf_event. + * Return + * Value specified by user at BPF link creation/attachment time + * or 0, if it was not specified. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5032,6 +5047,7 @@ union bpf_attr { FN(timer_start), \ FN(timer_cancel), \ FN(get_func_ip), \ + FN(get_attach_cookie), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 57879d28f824..cbc73c08c4a4 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -975,7 +975,34 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe = { .arg1_type = ARG_PTR_TO_CTX, }; -const struct bpf_func_proto * +BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx) +{ + struct bpf_trace_run_ctx *run_ctx; + + run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); + return run_ctx->bpf_cookie; +} + +static const struct bpf_func_proto bpf_get_attach_cookie_proto_trace = { + .func = bpf_get_attach_cookie_trace, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +BPF_CALL_1(bpf_get_attach_cookie_pe, struct bpf_perf_event_data_kern *, ctx) +{ + return ctx->event->bpf_cookie; +} + +static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = { + .func = bpf_get_attach_cookie_pe, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { @@ -1109,6 +1136,8 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif case BPF_FUNC_get_func_ip: return &bpf_get_func_ip_proto_kprobe; + case BPF_FUNC_get_attach_cookie: + return &bpf_get_attach_cookie_proto_trace; default: return bpf_tracing_func_proto(func_id, prog); } @@ -1219,6 +1248,8 @@ tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_stackid_proto_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_tp; + case BPF_FUNC_get_attach_cookie: + return &bpf_get_attach_cookie_proto_trace; default: return bpf_tracing_func_proto(func_id, prog); } @@ -1326,6 +1357,8 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_prog_read_value_proto; case BPF_FUNC_read_branch_records: return &bpf_read_branch_records_proto; + case BPF_FUNC_get_attach_cookie: + return &bpf_get_attach_cookie_proto_pe; default: return bpf_tracing_func_proto(func_id, prog); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 63ee482d50e1..c4f7892edb2b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4856,6 +4856,21 @@ union bpf_attr { * Get address of the traced function (for tracing and kprobe programs). * Return * Address of the traced function. + * + * u64 bpf_get_attach_cookie(void *ctx) + * Description + * Get bpf_cookie value provided (optionally) during the program + * attachment. It might be different for each individual + * attachment, even if BPF program itself is the same. + * Expects BPF program context *ctx* as a first argument. + * + * Supported for the following program types: + * - kprobe/uprobe; + * - tracepoint; + * - perf_event. + * Return + * Value specified by user at BPF link creation/attachment time + * or 0, if it was not specified. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5032,6 +5047,7 @@ union bpf_attr { FN(timer_start), \ FN(timer_cancel), \ FN(get_func_ip), \ + FN(get_attach_cookie), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 1d25d0aecfcd480b1a997a709c1b37e56ddc3c38 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 18:33:03 -0700 Subject: iomap: remove the iomap arguments to ->page_{prepare,done} These aren't actually used by the only instance implementing the methods. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/gfs2/bmap.c | 5 ++--- fs/iomap/buffered-io.c | 6 +++--- include/linux/iomap.h | 5 ++--- 3 files changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index ed8b67b21718..5414c2c33580 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1002,7 +1002,7 @@ static void gfs2_write_unlock(struct inode *inode) } static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos, - unsigned len, struct iomap *iomap) + unsigned len) { unsigned int blockmask = i_blocksize(inode) - 1; struct gfs2_sbd *sdp = GFS2_SB(inode); @@ -1013,8 +1013,7 @@ static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos, } static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, - unsigned copied, struct page *page, - struct iomap *iomap) + unsigned copied, struct page *page) { struct gfs2_trans *tr = current->journal_info; struct gfs2_inode *ip = GFS2_I(inode); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 43b9354bac3a..7e794a30806b 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -615,7 +615,7 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, return -EINTR; if (page_ops && page_ops->page_prepare) { - status = page_ops->page_prepare(inode, pos, len, iomap); + status = page_ops->page_prepare(inode, pos, len); if (status) return status; } @@ -648,7 +648,7 @@ out_unlock: out_no_page: if (page_ops && page_ops->page_done) - page_ops->page_done(inode, pos, 0, NULL, iomap); + page_ops->page_done(inode, pos, 0, NULL); return status; } @@ -724,7 +724,7 @@ static size_t iomap_write_end(struct inode *inode, loff_t pos, size_t len, if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); if (page_ops && page_ops->page_done) - page_ops->page_done(inode, pos, ret, page, iomap); + page_ops->page_done(inode, pos, ret, page); put_page(page); if (ret < len) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index b8ec145b2975..72696a55c137 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -126,10 +126,9 @@ static inline bool iomap_inline_data_valid(struct iomap *iomap) * associated page could not be obtained. */ struct iomap_page_ops { - int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len, - struct iomap *iomap); + int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len); void (*page_done)(struct inode *inode, loff_t pos, unsigned copied, - struct page *page, struct iomap *iomap); + struct page *page); }; /* -- cgit v1.2.3 From 66b8165ed4b5a2e7ddb7b9bbf3586b7ccdd86a1c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 18:33:04 -0700 Subject: iomap: mark the iomap argument to iomap_sector const Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 72696a55c137..8030483331d1 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -91,8 +91,7 @@ struct iomap { const struct iomap_page_ops *page_ops; }; -static inline sector_t -iomap_sector(struct iomap *iomap, loff_t pos) +static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos) { return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT; } -- cgit v1.2.3 From 4495c33e4d302b8d3a9eb483c06b2687d27dab9d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 18:33:04 -0700 Subject: iomap: mark the iomap argument to iomap_inline_data const Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8030483331d1..560247130357 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -99,7 +99,7 @@ static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos) /* * Returns the inline data pointer for logical offset @pos. */ -static inline void *iomap_inline_data(struct iomap *iomap, loff_t pos) +static inline void *iomap_inline_data(const struct iomap *iomap, loff_t pos) { return iomap->inline_data + pos - iomap->offset; } -- cgit v1.2.3 From e3c4ffb0c2219e720acdc6072c6ddaccac5cab79 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 18:33:05 -0700 Subject: iomap: mark the iomap argument to iomap_inline_data_valid const Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 560247130357..76bfc5d16ef4 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -109,7 +109,7 @@ static inline void *iomap_inline_data(const struct iomap *iomap, loff_t pos) * This is used to guard against accessing data beyond the page inline_data * points at. */ -static inline bool iomap_inline_data_valid(struct iomap *iomap) +static inline bool iomap_inline_data_valid(const struct iomap *iomap) { return iomap->length <= PAGE_SIZE - offset_in_page(iomap->inline_data); } -- cgit v1.2.3 From f4b896c213f0752adc828ddc11bd55419ffab248 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 18:33:07 -0700 Subject: iomap: add the new iomap_iter model The iomap_iter struct provides a convenient way to package up and maintain all the arguments to the various mapping and operation functions. It is operated on using the iomap_iter() function that is called in loop until the whole range has been processed. Compared to the existing iomap_apply() function this avoid an indirect call for each iteration. For now iomap_iter() calls back into the existing ->iomap_begin and ->iomap_end methods, but in the future this could be further optimized to avoid indirect calls entirely. Based on an earlier patch from Matthew Wilcox . Signed-off-by: Christoph Hellwig [djwong: add to apply.c to preserve git history of iomap loop control] Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/iomap/apply.c | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++- fs/iomap/trace.h | 37 +++++++++++++++++++++++++- include/linux/iomap.h | 56 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 165 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/apply.c b/fs/iomap/apply.c index 26ab6563181f..e82647aef7ea 100644 --- a/fs/iomap/apply.c +++ b/fs/iomap/apply.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. - * Copyright (c) 2016-2018 Christoph Hellwig. + * Copyright (c) 2016-2021 Christoph Hellwig. */ #include #include @@ -97,3 +97,75 @@ out: return written ? written : ret; } + +static inline int iomap_iter_advance(struct iomap_iter *iter) +{ + /* handle the previous iteration (if any) */ + if (iter->iomap.length) { + if (iter->processed <= 0) + return iter->processed; + if (WARN_ON_ONCE(iter->processed > iomap_length(iter))) + return -EIO; + iter->pos += iter->processed; + iter->len -= iter->processed; + if (!iter->len) + return 0; + } + + /* clear the state for the next iteration */ + iter->processed = 0; + memset(&iter->iomap, 0, sizeof(iter->iomap)); + memset(&iter->srcmap, 0, sizeof(iter->srcmap)); + return 1; +} + +static inline void iomap_iter_done(struct iomap_iter *iter) +{ + WARN_ON_ONCE(iter->iomap.offset > iter->pos); + WARN_ON_ONCE(iter->iomap.length == 0); + WARN_ON_ONCE(iter->iomap.offset + iter->iomap.length <= iter->pos); + + trace_iomap_iter_dstmap(iter->inode, &iter->iomap); + if (iter->srcmap.type != IOMAP_HOLE) + trace_iomap_iter_srcmap(iter->inode, &iter->srcmap); +} + +/** + * iomap_iter - iterate over a ranges in a file + * @iter: iteration structue + * @ops: iomap ops provided by the file system + * + * Iterate over filesystem-provided space mappings for the provided file range. + * + * This function handles cleanup of resources acquired for iteration when the + * filesystem indicates there are no more space mappings, which means that this + * function must be called in a loop that continues as long it returns a + * positive value. If 0 or a negative value is returned, the caller must not + * return to the loop body. Within a loop body, there are two ways to break out + * of the loop body: leave @iter.processed unchanged, or set it to a negative + * errno. + */ +int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops) +{ + int ret; + + if (iter->iomap.length && ops->iomap_end) { + ret = ops->iomap_end(iter->inode, iter->pos, iomap_length(iter), + iter->processed > 0 ? iter->processed : 0, + iter->flags, &iter->iomap); + if (ret < 0 && !iter->processed) + return ret; + } + + trace_iomap_iter(iter, ops, _RET_IP_); + ret = iomap_iter_advance(iter); + if (ret <= 0) + return ret; + + ret = ops->iomap_begin(iter->inode, iter->pos, iter->len, iter->flags, + &iter->iomap, &iter->srcmap); + if (ret < 0) + return ret; + iomap_iter_done(iter); + return 1; +} diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index e9cd5cc0d6ba..1012d7af6b68 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Copyright (c) 2009-2019 Christoph Hellwig + * Copyright (c) 2009-2021 Christoph Hellwig * * NOTE: none of these tracepoints shall be considered a stable kernel ABI * as they can change at any time. @@ -140,6 +140,8 @@ DEFINE_EVENT(iomap_class, name, \ TP_ARGS(inode, iomap)) DEFINE_IOMAP_EVENT(iomap_apply_dstmap); DEFINE_IOMAP_EVENT(iomap_apply_srcmap); +DEFINE_IOMAP_EVENT(iomap_iter_dstmap); +DEFINE_IOMAP_EVENT(iomap_iter_srcmap); TRACE_EVENT(iomap_apply, TP_PROTO(struct inode *inode, loff_t pos, loff_t length, @@ -179,6 +181,39 @@ TRACE_EVENT(iomap_apply, __entry->actor) ); +TRACE_EVENT(iomap_iter, + TP_PROTO(struct iomap_iter *iter, const void *ops, + unsigned long caller), + TP_ARGS(iter, ops, caller), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, ino) + __field(loff_t, pos) + __field(loff_t, length) + __field(unsigned int, flags) + __field(const void *, ops) + __field(unsigned long, caller) + ), + TP_fast_assign( + __entry->dev = iter->inode->i_sb->s_dev; + __entry->ino = iter->inode->i_ino; + __entry->pos = iter->pos; + __entry->length = iomap_length(iter); + __entry->flags = iter->flags; + __entry->ops = ops; + __entry->caller = caller; + ), + TP_printk("dev %d:%d ino 0x%llx pos %lld length %lld flags %s (0x%x) ops %ps caller %pS", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->pos, + __entry->length, + __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS), + __entry->flags, + __entry->ops, + (void *)__entry->caller) +); + #endif /* _IOMAP_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 76bfc5d16ef4..aac4176ea164 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -161,6 +161,62 @@ struct iomap_ops { ssize_t written, unsigned flags, struct iomap *iomap); }; +/** + * struct iomap_iter - Iterate through a range of a file + * @inode: Set at the start of the iteration and should not change. + * @pos: The current file position we are operating on. It is updated by + * calls to iomap_iter(). Treat as read-only in the body. + * @len: The remaining length of the file segment we're operating on. + * It is updated at the same time as @pos. + * @processed: The number of bytes processed by the body in the most recent + * iteration, or a negative errno. 0 causes the iteration to stop. + * @flags: Zero or more of the iomap_begin flags above. + * @iomap: Map describing the I/O iteration + * @srcmap: Source map for COW operations + */ +struct iomap_iter { + struct inode *inode; + loff_t pos; + u64 len; + s64 processed; + unsigned flags; + struct iomap iomap; + struct iomap srcmap; +}; + +int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); + +/** + * iomap_length - length of the current iomap iteration + * @iter: iteration structure + * + * Returns the length that the operation applies to for the current iteration. + */ +static inline u64 iomap_length(const struct iomap_iter *iter) +{ + u64 end = iter->iomap.offset + iter->iomap.length; + + if (iter->srcmap.type != IOMAP_HOLE) + end = min(end, iter->srcmap.offset + iter->srcmap.length); + return min(iter->len, end - iter->pos); +} + +/** + * iomap_iter_srcmap - return the source map for the current iomap iteration + * @i: iteration structure + * + * Write operations on file systems with reflink support might require a + * source and a destination map. This function retourns the source map + * for a given operation, which may or may no be identical to the destination + * map in &i->iomap. + */ +static inline struct iomap *iomap_iter_srcmap(struct iomap_iter *i) +{ + if (i->srcmap.type != IOMAP_HOLE) + return &i->srcmap; + return &i->iomap; +} + /* * Main iomap iterator function. */ -- cgit v1.2.3 From a6d3d49587d10d23189675fce11b332a915081ff Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 18:33:10 -0700 Subject: iomap: switch __iomap_dio_rw to use iomap_iter Switch __iomap_dio_rw to use iomap_iter. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/btrfs/inode.c | 5 +- fs/iomap/direct-io.c | 164 +++++++++++++++++++++++++------------------------- include/linux/iomap.h | 4 +- 3 files changed, 86 insertions(+), 87 deletions(-) (limited to 'include/linux') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0117d867ecf8..3b0595e8bdd9 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8194,9 +8194,10 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, return dip; } -static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, +static blk_qc_t btrfs_submit_direct(const struct iomap_iter *iter, struct bio *dio_bio, loff_t file_offset) { + struct inode *inode = iter->inode; const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); const bool raid56 = (btrfs_data_alloc_profile(fs_info) & @@ -8212,7 +8213,7 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, int ret; blk_status_t status; struct btrfs_io_geometry geom; - struct btrfs_dio_data *dio_data = iomap->private; + struct btrfs_dio_data *dio_data = iter->iomap.private; struct extent_map *em = NULL; dip = btrfs_create_dio_private(dio_bio, inode, file_offset); diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 41ccbfc9dc82..4ecd255e0511 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. - * Copyright (c) 2016-2018 Christoph Hellwig. + * Copyright (c) 2016-2021 Christoph Hellwig. */ #include #include @@ -59,19 +59,17 @@ int iomap_dio_iopoll(struct kiocb *kiocb, bool spin) } EXPORT_SYMBOL_GPL(iomap_dio_iopoll); -static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap, - struct bio *bio, loff_t pos) +static void iomap_dio_submit_bio(const struct iomap_iter *iter, + struct iomap_dio *dio, struct bio *bio, loff_t pos) { atomic_inc(&dio->ref); if (dio->iocb->ki_flags & IOCB_HIPRI) bio_set_polled(bio, dio->iocb); - dio->submit.last_queue = bdev_get_queue(iomap->bdev); + dio->submit.last_queue = bdev_get_queue(iter->iomap.bdev); if (dio->dops && dio->dops->submit_io) - dio->submit.cookie = dio->dops->submit_io( - file_inode(dio->iocb->ki_filp), - iomap, bio, pos); + dio->submit.cookie = dio->dops->submit_io(iter, bio, pos); else dio->submit.cookie = submit_bio(bio); } @@ -181,24 +179,23 @@ static void iomap_dio_bio_end_io(struct bio *bio) } } -static void -iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos, - unsigned len) +static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, + loff_t pos, unsigned len) { struct page *page = ZERO_PAGE(0); int flags = REQ_SYNC | REQ_IDLE; struct bio *bio; bio = bio_alloc(GFP_KERNEL, 1); - bio_set_dev(bio, iomap->bdev); - bio->bi_iter.bi_sector = iomap_sector(iomap, pos); + bio_set_dev(bio, iter->iomap.bdev); + bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos); bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; get_page(page); __bio_add_page(bio, page, len, 0); bio_set_op_attrs(bio, REQ_OP_WRITE, flags); - iomap_dio_submit_bio(dio, iomap, bio, pos); + iomap_dio_submit_bio(iter, dio, bio, pos); } /* @@ -206,8 +203,8 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos, * mapping, and whether or not we want FUA. Note that we can end up * clearing the WRITE_FUA flag in the dio request. */ -static inline unsigned int -iomap_dio_bio_opflags(struct iomap_dio *dio, struct iomap *iomap, bool use_fua) +static inline unsigned int iomap_dio_bio_opflags(struct iomap_dio *dio, + const struct iomap *iomap, bool use_fua) { unsigned int opflags = REQ_SYNC | REQ_IDLE; @@ -229,13 +226,16 @@ iomap_dio_bio_opflags(struct iomap_dio *dio, struct iomap *iomap, bool use_fua) return opflags; } -static loff_t -iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, - struct iomap_dio *dio, struct iomap *iomap) +static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, + struct iomap_dio *dio) { + const struct iomap *iomap = &iter->iomap; + struct inode *inode = iter->inode; unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev)); unsigned int fs_block_size = i_blocksize(inode), pad; unsigned int align = iov_iter_alignment(dio->submit.iter); + loff_t length = iomap_length(iter); + loff_t pos = iter->pos; unsigned int bio_opf; struct bio *bio; bool need_zeroout = false; @@ -286,7 +286,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, /* zero out from the start of the block to the write offset */ pad = pos & (fs_block_size - 1); if (pad) - iomap_dio_zero(dio, iomap, pos - pad, pad); + iomap_dio_zero(iter, dio, pos - pad, pad); } /* @@ -339,7 +339,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS); - iomap_dio_submit_bio(dio, iomap, bio, pos); + iomap_dio_submit_bio(iter, dio, bio, pos); pos += n; } while (nr_pages); @@ -355,7 +355,7 @@ zero_tail: /* zero out from the end of the write to the end of the block */ pad = pos & (fs_block_size - 1); if (pad) - iomap_dio_zero(dio, iomap, pos, fs_block_size - pad); + iomap_dio_zero(iter, dio, pos, fs_block_size - pad); } out: /* Undo iter limitation to current extent */ @@ -365,35 +365,38 @@ out: return ret; } -static loff_t -iomap_dio_hole_actor(loff_t length, struct iomap_dio *dio) +static loff_t iomap_dio_hole_iter(const struct iomap_iter *iter, + struct iomap_dio *dio) { - length = iov_iter_zero(length, dio->submit.iter); + loff_t length = iov_iter_zero(iomap_length(iter), dio->submit.iter); + dio->size += length; return length; } -static loff_t -iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length, - struct iomap_dio *dio, struct iomap *iomap) +static loff_t iomap_dio_inline_iter(const struct iomap_iter *iomi, + struct iomap_dio *dio) { + const struct iomap *iomap = &iomi->iomap; struct iov_iter *iter = dio->submit.iter; - void *inline_data = iomap_inline_data(iomap, pos); + void *inline_data = iomap_inline_data(iomap, iomi->pos); + loff_t length = iomap_length(iomi); + loff_t pos = iomi->pos; size_t copied; if (WARN_ON_ONCE(!iomap_inline_data_valid(iomap))) return -EIO; if (dio->flags & IOMAP_DIO_WRITE) { - loff_t size = inode->i_size; + loff_t size = iomi->inode->i_size; if (pos > size) memset(iomap_inline_data(iomap, size), 0, pos - size); copied = copy_from_iter(inline_data, length, iter); if (copied) { if (pos + copied > size) - i_size_write(inode, pos + copied); - mark_inode_dirty(inode); + i_size_write(iomi->inode, pos + copied); + mark_inode_dirty(iomi->inode); } } else { copied = copy_to_iter(inline_data, length, iter); @@ -402,30 +405,27 @@ iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length, return copied; } -static loff_t -iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap, struct iomap *srcmap) +static loff_t iomap_dio_iter(const struct iomap_iter *iter, + struct iomap_dio *dio) { - struct iomap_dio *dio = data; - - switch (iomap->type) { + switch (iter->iomap.type) { case IOMAP_HOLE: if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE)) return -EIO; - return iomap_dio_hole_actor(length, dio); + return iomap_dio_hole_iter(iter, dio); case IOMAP_UNWRITTEN: if (!(dio->flags & IOMAP_DIO_WRITE)) - return iomap_dio_hole_actor(length, dio); - return iomap_dio_bio_actor(inode, pos, length, dio, iomap); + return iomap_dio_hole_iter(iter, dio); + return iomap_dio_bio_iter(iter, dio); case IOMAP_MAPPED: - return iomap_dio_bio_actor(inode, pos, length, dio, iomap); + return iomap_dio_bio_iter(iter, dio); case IOMAP_INLINE: - return iomap_dio_inline_actor(inode, pos, length, dio, iomap); + return iomap_dio_inline_iter(iter, dio); case IOMAP_DELALLOC: /* * DIO is not serialised against mmap() access at all, and so * if the page_mkwrite occurs between the writeback and the - * iomap_apply() call in the DIO path, then it will see the + * iomap_iter() call in the DIO path, then it will see the * DELALLOC block that the page-mkwrite allocated. */ pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s\n", @@ -456,16 +456,19 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); - size_t count = iov_iter_count(iter); - loff_t pos = iocb->ki_pos; - loff_t end = iocb->ki_pos + count - 1, ret = 0; + struct iomap_iter iomi = { + .inode = inode, + .pos = iocb->ki_pos, + .len = iov_iter_count(iter), + .flags = IOMAP_DIRECT, + }; + loff_t end = iomi.pos + iomi.len - 1, ret = 0; bool wait_for_completion = is_sync_kiocb(iocb) || (dio_flags & IOMAP_DIO_FORCE_WAIT); - unsigned int iomap_flags = IOMAP_DIRECT; struct blk_plug plug; struct iomap_dio *dio; - if (!count) + if (!iomi.len) return NULL; dio = kmalloc(sizeof(*dio), GFP_KERNEL); @@ -486,29 +489,30 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->submit.last_queue = NULL; if (iov_iter_rw(iter) == READ) { - if (pos >= dio->i_size) + if (iomi.pos >= dio->i_size) goto out_free_dio; if (iocb->ki_flags & IOCB_NOWAIT) { - if (filemap_range_needs_writeback(mapping, pos, end)) { + if (filemap_range_needs_writeback(mapping, iomi.pos, + end)) { ret = -EAGAIN; goto out_free_dio; } - iomap_flags |= IOMAP_NOWAIT; + iomi.flags |= IOMAP_NOWAIT; } if (iter_is_iovec(iter)) dio->flags |= IOMAP_DIO_DIRTY; } else { - iomap_flags |= IOMAP_WRITE; + iomi.flags |= IOMAP_WRITE; dio->flags |= IOMAP_DIO_WRITE; if (iocb->ki_flags & IOCB_NOWAIT) { - if (filemap_range_has_page(mapping, pos, end)) { + if (filemap_range_has_page(mapping, iomi.pos, end)) { ret = -EAGAIN; goto out_free_dio; } - iomap_flags |= IOMAP_NOWAIT; + iomi.flags |= IOMAP_NOWAIT; } /* for data sync or sync, we need sync completion processing */ @@ -527,12 +531,13 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) { ret = -EAGAIN; - if (pos >= dio->i_size || pos + count > dio->i_size) + if (iomi.pos >= dio->i_size || + iomi.pos + iomi.len > dio->i_size) goto out_free_dio; - iomap_flags |= IOMAP_OVERWRITE_ONLY; + iomi.flags |= IOMAP_OVERWRITE_ONLY; } - ret = filemap_write_and_wait_range(mapping, pos, end); + ret = filemap_write_and_wait_range(mapping, iomi.pos, end); if (ret) goto out_free_dio; @@ -542,9 +547,10 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, * If this invalidation fails, let the caller fall back to * buffered I/O. */ - if (invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, - end >> PAGE_SHIFT)) { - trace_iomap_dio_invalidate_fail(inode, pos, count); + if (invalidate_inode_pages2_range(mapping, + iomi.pos >> PAGE_SHIFT, end >> PAGE_SHIFT)) { + trace_iomap_dio_invalidate_fail(inode, iomi.pos, + iomi.len); ret = -ENOTBLK; goto out_free_dio; } @@ -559,31 +565,23 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, inode_dio_begin(inode); blk_start_plug(&plug); - do { - ret = iomap_apply(inode, pos, count, iomap_flags, ops, dio, - iomap_dio_actor); - if (ret <= 0) { - /* magic error code to fall back to buffered I/O */ - if (ret == -ENOTBLK) { - wait_for_completion = true; - ret = 0; - } - break; - } - pos += ret; - - if (iov_iter_rw(iter) == READ && pos >= dio->i_size) { - /* - * We only report that we've read data up to i_size. - * Revert iter to a state corresponding to that as - * some callers (such as splice code) rely on it. - */ - iov_iter_revert(iter, pos - dio->i_size); - break; - } - } while ((count = iov_iter_count(iter)) > 0); + while ((ret = iomap_iter(&iomi, ops)) > 0) + iomi.processed = iomap_dio_iter(&iomi, dio); blk_finish_plug(&plug); + /* + * We only report that we've read data up to i_size. + * Revert iter to a state corresponding to that as some callers (such + * as the splice code) rely on it. + */ + if (iov_iter_rw(iter) == READ && iomi.pos >= dio->i_size) + iov_iter_revert(iter, iomi.pos - dio->i_size); + + /* magic error code to fall back to buffered I/O */ + if (ret == -ENOTBLK) { + wait_for_completion = true; + ret = 0; + } if (ret < 0) iomap_dio_set_error(dio, ret); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index aac4176ea164..66e04aedd2ca 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -322,8 +322,8 @@ int iomap_writepages(struct address_space *mapping, struct iomap_dio_ops { int (*end_io)(struct kiocb *iocb, ssize_t size, int error, unsigned flags); - blk_qc_t (*submit_io)(struct inode *inode, struct iomap *iomap, - struct bio *bio, loff_t file_offset); + blk_qc_t (*submit_io)(const struct iomap_iter *iter, struct bio *bio, + loff_t file_offset); }; /* -- cgit v1.2.3 From 57320a01fe1ffb61c483f3734f62722f74263521 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 18:33:13 -0700 Subject: iomap: remove iomap_apply iomap_apply is unused now, so remove it. Signed-off-by: Christoph Hellwig [djwong: rebase this patch to preserve git history of iomap loop control] Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/iomap/apply.c | 91 --------------------------------------------------- fs/iomap/trace.h | 40 ---------------------- include/linux/iomap.h | 10 ------ 3 files changed, 141 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/apply.c b/fs/iomap/apply.c index e82647aef7ea..a1c7592d2ade 100644 --- a/fs/iomap/apply.c +++ b/fs/iomap/apply.c @@ -3,101 +3,10 @@ * Copyright (C) 2010 Red Hat, Inc. * Copyright (c) 2016-2021 Christoph Hellwig. */ -#include -#include #include #include #include "trace.h" -/* - * Execute a iomap write on a segment of the mapping that spans a - * contiguous range of pages that have identical block mapping state. - * - * This avoids the need to map pages individually, do individual allocations - * for each page and most importantly avoid the need for filesystem specific - * locking per page. Instead, all the operations are amortised over the entire - * range of pages. It is assumed that the filesystems will lock whatever - * resources they require in the iomap_begin call, and release them in the - * iomap_end call. - */ -loff_t -iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, - const struct iomap_ops *ops, void *data, iomap_actor_t actor) -{ - struct iomap iomap = { .type = IOMAP_HOLE }; - struct iomap srcmap = { .type = IOMAP_HOLE }; - loff_t written = 0, ret; - u64 end; - - trace_iomap_apply(inode, pos, length, flags, ops, actor, _RET_IP_); - - /* - * Need to map a range from start position for length bytes. This can - * span multiple pages - it is only guaranteed to return a range of a - * single type of pages (e.g. all into a hole, all mapped or all - * unwritten). Failure at this point has nothing to undo. - * - * If allocation is required for this range, reserve the space now so - * that the allocation is guaranteed to succeed later on. Once we copy - * the data into the page cache pages, then we cannot fail otherwise we - * expose transient stale data. If the reserve fails, we can safely - * back out at this point as there is nothing to undo. - */ - ret = ops->iomap_begin(inode, pos, length, flags, &iomap, &srcmap); - if (ret) - return ret; - if (WARN_ON(iomap.offset > pos)) { - written = -EIO; - goto out; - } - if (WARN_ON(iomap.length == 0)) { - written = -EIO; - goto out; - } - - trace_iomap_apply_dstmap(inode, &iomap); - if (srcmap.type != IOMAP_HOLE) - trace_iomap_apply_srcmap(inode, &srcmap); - - /* - * Cut down the length to the one actually provided by the filesystem, - * as it might not be able to give us the whole size that we requested. - */ - end = iomap.offset + iomap.length; - if (srcmap.type != IOMAP_HOLE) - end = min(end, srcmap.offset + srcmap.length); - if (pos + length > end) - length = end - pos; - - /* - * Now that we have guaranteed that the space allocation will succeed, - * we can do the copy-in page by page without having to worry about - * failures exposing transient data. - * - * To support COW operations, we read in data for partially blocks from - * the srcmap if the file system filled it in. In that case we the - * length needs to be limited to the earlier of the ends of the iomaps. - * If the file system did not provide a srcmap we pass in the normal - * iomap into the actors so that they don't need to have special - * handling for the two cases. - */ - written = actor(inode, pos, length, data, &iomap, - srcmap.type != IOMAP_HOLE ? &srcmap : &iomap); - -out: - /* - * Now the data has been copied, commit the range we've copied. This - * should not fail unless the filesystem has had a fatal error. - */ - if (ops->iomap_end) { - ret = ops->iomap_end(inode, pos, length, - written > 0 ? written : 0, - flags, &iomap); - } - - return written ? written : ret; -} - static inline int iomap_iter_advance(struct iomap_iter *iter) { /* handle the previous iteration (if any) */ diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index 1012d7af6b68..f1519f9a1403 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -138,49 +138,9 @@ DECLARE_EVENT_CLASS(iomap_class, DEFINE_EVENT(iomap_class, name, \ TP_PROTO(struct inode *inode, struct iomap *iomap), \ TP_ARGS(inode, iomap)) -DEFINE_IOMAP_EVENT(iomap_apply_dstmap); -DEFINE_IOMAP_EVENT(iomap_apply_srcmap); DEFINE_IOMAP_EVENT(iomap_iter_dstmap); DEFINE_IOMAP_EVENT(iomap_iter_srcmap); -TRACE_EVENT(iomap_apply, - TP_PROTO(struct inode *inode, loff_t pos, loff_t length, - unsigned int flags, const void *ops, void *actor, - unsigned long caller), - TP_ARGS(inode, pos, length, flags, ops, actor, caller), - TP_STRUCT__entry( - __field(dev_t, dev) - __field(u64, ino) - __field(loff_t, pos) - __field(loff_t, length) - __field(unsigned int, flags) - __field(const void *, ops) - __field(void *, actor) - __field(unsigned long, caller) - ), - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->pos = pos; - __entry->length = length; - __entry->flags = flags; - __entry->ops = ops; - __entry->actor = actor; - __entry->caller = caller; - ), - TP_printk("dev %d:%d ino 0x%llx pos %lld length %lld flags %s (0x%x) " - "ops %ps caller %pS actor %ps", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->ino, - __entry->pos, - __entry->length, - __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS), - __entry->flags, - __entry->ops, - (void *)__entry->caller, - __entry->actor) -); - TRACE_EVENT(iomap_iter, TP_PROTO(struct iomap_iter *iter, const void *ops, unsigned long caller), diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 66e04aedd2ca..6784a8b64714 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -217,16 +217,6 @@ static inline struct iomap *iomap_iter_srcmap(struct iomap_iter *i) return &i->iomap; } -/* - * Main iomap iterator function. - */ -typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len, - void *data, struct iomap *iomap, struct iomap *srcmap); - -loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, - unsigned flags, const struct iomap_ops *ops, void *data, - iomap_actor_t actor); - ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); -- cgit v1.2.3 From b74b1293e6cae70bade491067f15b9d33e040cad Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 18:33:14 -0700 Subject: iomap: rework unshare flag Instead of another internal flags namespace inside of buffered-io.c, just pass a UNSHARE hint in the main iomap flags field. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 23 +++++++++-------------- include/linux/iomap.h | 1 + 2 files changed, 10 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index d6d1fd0208a9..a0ef7ebe9209 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -508,10 +508,6 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage, EXPORT_SYMBOL_GPL(iomap_migrate_page); #endif /* CONFIG_MIGRATION */ -enum { - IOMAP_WRITE_F_UNSHARE = (1 << 0), -}; - static void iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) { @@ -541,7 +537,7 @@ iomap_read_page_sync(loff_t block_start, struct page *page, unsigned poff, } static int __iomap_write_begin(struct iomap_iter *iter, loff_t pos, - unsigned len, int flags, struct page *page) + unsigned len, struct page *page) { struct iomap *srcmap = iomap_iter_srcmap(iter); struct iomap_page *iop = iomap_page_create(iter->inode, page); @@ -560,13 +556,13 @@ static int __iomap_write_begin(struct iomap_iter *iter, loff_t pos, if (plen == 0) break; - if (!(flags & IOMAP_WRITE_F_UNSHARE) && + if (!(iter->flags & IOMAP_UNSHARE) && (from <= poff || from >= poff + plen) && (to <= poff || to >= poff + plen)) continue; if (iomap_block_needs_zeroing(iter, block_start)) { - if (WARN_ON_ONCE(flags & IOMAP_WRITE_F_UNSHARE)) + if (WARN_ON_ONCE(iter->flags & IOMAP_UNSHARE)) return -EIO; zero_user_segments(page, poff, from, to, poff + plen); } else { @@ -596,7 +592,7 @@ static int iomap_write_begin_inline(struct iomap_iter *iter, } static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, unsigned len, - unsigned flags, struct page **pagep) + struct page **pagep) { const struct iomap_page_ops *page_ops = iter->iomap.page_ops; struct iomap *srcmap = iomap_iter_srcmap(iter); @@ -628,7 +624,7 @@ static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, unsigned len, else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) status = __block_write_begin_int(page, pos, len, NULL, srcmap); else - status = __iomap_write_begin(iter, pos, len, flags, page); + status = __iomap_write_begin(iter, pos, len, page); if (unlikely(status)) goto out_unlock; @@ -759,7 +755,7 @@ again: break; } - status = iomap_write_begin(iter, pos, bytes, 0, &page); + status = iomap_write_begin(iter, pos, bytes, &page); if (unlikely(status)) break; @@ -836,8 +832,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) unsigned long bytes = min_t(loff_t, PAGE_SIZE - offset, length); struct page *page; - status = iomap_write_begin(iter, pos, bytes, - IOMAP_WRITE_F_UNSHARE, &page); + status = iomap_write_begin(iter, pos, bytes, &page); if (unlikely(status)) return status; @@ -865,7 +860,7 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, .inode = inode, .pos = pos, .len = len, - .flags = IOMAP_WRITE, + .flags = IOMAP_WRITE | IOMAP_UNSHARE, }; int ret; @@ -882,7 +877,7 @@ static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) unsigned offset = offset_in_page(pos); unsigned bytes = min_t(u64, PAGE_SIZE - offset, length); - status = iomap_write_begin(iter, pos, bytes, 0, &page); + status = iomap_write_begin(iter, pos, bytes, &page); if (status) return status; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6784a8b64714..f53c40e9d799 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -140,6 +140,7 @@ struct iomap_page_ops { #define IOMAP_DIRECT (1 << 4) /* direct I/O */ #define IOMAP_NOWAIT (1 << 5) /* do not block */ #define IOMAP_OVERWRITE_ONLY (1 << 6) /* only pure overwrites allowed */ +#define IOMAP_UNSHARE (1 << 7) /* unshare_file_range */ struct iomap_ops { /* -- cgit v1.2.3 From fad0a1ab34f777bd8a95c6cebd70ee899b6e159e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 10 Aug 2021 18:33:16 -0700 Subject: iomap: constify iomap_iter_srcmap The srcmap returned from iomap_iter_srcmap is never modified, so mark the iomap returned from it const and constify a lot of code that never modifies the iomap. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 38 +++++++++++++++++++------------------- include/linux/iomap.h | 2 +- 2 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index a0ef7ebe9209..9cc5798423d1 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -205,10 +205,10 @@ struct iomap_readpage_ctx { struct readahead_control *rac; }; -static loff_t iomap_read_inline_data(struct iomap_iter *iter, +static loff_t iomap_read_inline_data(const struct iomap_iter *iter, struct page *page) { - struct iomap *iomap = iomap_iter_srcmap(iter); + const struct iomap *iomap = iomap_iter_srcmap(iter); size_t size = i_size_read(iter->inode) - iomap->offset; size_t poff = offset_in_page(iomap->offset); void *addr; @@ -234,20 +234,20 @@ static loff_t iomap_read_inline_data(struct iomap_iter *iter, return PAGE_SIZE - poff; } -static inline bool iomap_block_needs_zeroing(struct iomap_iter *iter, +static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter, loff_t pos) { - struct iomap *srcmap = iomap_iter_srcmap(iter); + const struct iomap *srcmap = iomap_iter_srcmap(iter); return srcmap->type != IOMAP_MAPPED || (srcmap->flags & IOMAP_F_NEW) || pos >= i_size_read(iter->inode); } -static loff_t iomap_readpage_iter(struct iomap_iter *iter, +static loff_t iomap_readpage_iter(const struct iomap_iter *iter, struct iomap_readpage_ctx *ctx, loff_t offset) { - struct iomap *iomap = &iter->iomap; + const struct iomap *iomap = &iter->iomap; loff_t pos = iter->pos + offset; loff_t length = iomap_length(iter) - offset; struct page *page = ctx->cur_page; @@ -352,7 +352,7 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops) } EXPORT_SYMBOL_GPL(iomap_readpage); -static loff_t iomap_readahead_iter(struct iomap_iter *iter, +static loff_t iomap_readahead_iter(const struct iomap_iter *iter, struct iomap_readpage_ctx *ctx) { loff_t length = iomap_length(iter); @@ -536,10 +536,10 @@ iomap_read_page_sync(loff_t block_start, struct page *page, unsigned poff, return submit_bio_wait(&bio); } -static int __iomap_write_begin(struct iomap_iter *iter, loff_t pos, +static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, unsigned len, struct page *page) { - struct iomap *srcmap = iomap_iter_srcmap(iter); + const struct iomap *srcmap = iomap_iter_srcmap(iter); struct iomap_page *iop = iomap_page_create(iter->inode, page); loff_t block_size = i_blocksize(iter->inode); loff_t block_start = round_down(pos, block_size); @@ -577,7 +577,7 @@ static int __iomap_write_begin(struct iomap_iter *iter, loff_t pos, return 0; } -static int iomap_write_begin_inline(struct iomap_iter *iter, +static int iomap_write_begin_inline(const struct iomap_iter *iter, struct page *page) { int ret; @@ -591,11 +591,11 @@ static int iomap_write_begin_inline(struct iomap_iter *iter, return 0; } -static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, unsigned len, - struct page **pagep) +static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos, + unsigned len, struct page **pagep) { const struct iomap_page_ops *page_ops = iter->iomap.page_ops; - struct iomap *srcmap = iomap_iter_srcmap(iter); + const struct iomap *srcmap = iomap_iter_srcmap(iter); struct page *page; int status = 0; @@ -666,10 +666,10 @@ static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, return copied; } -static size_t iomap_write_end_inline(struct iomap_iter *iter, struct page *page, - loff_t pos, size_t copied) +static size_t iomap_write_end_inline(const struct iomap_iter *iter, + struct page *page, loff_t pos, size_t copied) { - struct iomap *iomap = &iter->iomap; + const struct iomap *iomap = &iter->iomap; void *addr; WARN_ON_ONCE(!PageUptodate(page)); @@ -689,7 +689,7 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, size_t copied, struct page *page) { const struct iomap_page_ops *page_ops = iter->iomap.page_ops; - struct iomap *srcmap = iomap_iter_srcmap(iter); + const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t old_size = iter->inode->i_size; size_t ret; @@ -814,7 +814,7 @@ EXPORT_SYMBOL_GPL(iomap_file_buffered_write); static loff_t iomap_unshare_iter(struct iomap_iter *iter) { struct iomap *iomap = &iter->iomap; - struct iomap *srcmap = iomap_iter_srcmap(iter); + const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); long status = 0; @@ -890,7 +890,7 @@ static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { struct iomap *iomap = &iter->iomap; - struct iomap *srcmap = iomap_iter_srcmap(iter); + const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); loff_t written = 0; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index f53c40e9d799..24f8489583ca 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -211,7 +211,7 @@ static inline u64 iomap_length(const struct iomap_iter *iter) * for a given operation, which may or may no be identical to the destination * map in &i->iomap. */ -static inline struct iomap *iomap_iter_srcmap(struct iomap_iter *i) +static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) { if (i->srcmap.type != IOMAP_HOLE) return &i->srcmap; -- cgit v1.2.3 From 4f911138c8da94bcff84f1d093d28e378703c43f Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 19 Jun 2021 12:26:16 +0300 Subject: fs: add generic helper for filling statx attribute flags The immutable and append-only properties on an inode are published on the inode's i_flags and enforced by the VFS. Create a helper to fill the corresponding STATX_ATTR_ flags in the kstat structure from the inode's i_flags. Only orange was converted to use this helper. Other filesystems could use it in the future. Suggested-by: Miklos Szeredi Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/orangefs/inode.c | 7 +------ fs/stat.c | 18 ++++++++++++++++++ include/linux/fs.h | 1 + include/linux/stat.h | 4 ++++ 4 files changed, 24 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 16ac617df7d7..c1bb4c4b5d67 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -882,12 +882,7 @@ int orangefs_getattr(struct user_namespace *mnt_userns, const struct path *path, if (!(request_mask & STATX_SIZE)) stat->result_mask &= ~STATX_SIZE; - stat->attributes_mask = STATX_ATTR_IMMUTABLE | - STATX_ATTR_APPEND; - if (inode->i_flags & S_IMMUTABLE) - stat->attributes |= STATX_ATTR_IMMUTABLE; - if (inode->i_flags & S_APPEND) - stat->attributes |= STATX_ATTR_APPEND; + generic_fill_statx_attr(inode, stat); } return ret; } diff --git a/fs/stat.c b/fs/stat.c index 1fa38bdec1a6..28d2020ba1f4 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -59,6 +59,24 @@ void generic_fillattr(struct user_namespace *mnt_userns, struct inode *inode, } EXPORT_SYMBOL(generic_fillattr); +/** + * generic_fill_statx_attr - Fill in the statx attributes from the inode flags + * @inode: Inode to use as the source + * @stat: Where to fill in the attribute flags + * + * Fill in the STATX_ATTR_* flags in the kstat structure for properties of the + * inode that are published on i_flags and enforced by the VFS. + */ +void generic_fill_statx_attr(struct inode *inode, struct kstat *stat) +{ + if (inode->i_flags & S_IMMUTABLE) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (inode->i_flags & S_APPEND) + stat->attributes |= STATX_ATTR_APPEND; + stat->attributes_mask |= KSTAT_ATTR_VFS_FLAGS; +} +EXPORT_SYMBOL(generic_fill_statx_attr); + /** * vfs_getattr_nosec - getattr without security checks * @path: file to get attributes from diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..ae6c6c34db94 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3355,6 +3355,7 @@ extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void generic_fillattr(struct user_namespace *, struct inode *, struct kstat *); +void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); diff --git a/include/linux/stat.h b/include/linux/stat.h index fff27e603814..7df06931f25d 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -34,6 +34,10 @@ struct kstat { STATX_ATTR_ENCRYPTED | \ STATX_ATTR_VERITY \ )/* Attrs corresponding to FS_*_FL flags */ +#define KSTAT_ATTR_VFS_FLAGS \ + (STATX_ATTR_IMMUTABLE | \ + STATX_ATTR_APPEND \ + ) /* Attrs corresponding to S_* flags that are enforced by the VFS */ u64 ino; dev_t dev; dev_t rdev; -- cgit v1.2.3 From 1e4f30eaf4b81252bbd462cf7e95a08959f5bebd Mon Sep 17 00:00:00 2001 From: Sebastian Krzyszkowiak Date: Mon, 16 Aug 2021 18:50:13 +0200 Subject: power: supply: max17042_battery: clean up MAX17055_V_empty This register is same as in MAX17047 and MAX17050, so there's no need for custom casing it. Signed-off-by: Sebastian Krzyszkowiak Signed-off-by: Sebastian Reichel --- drivers/power/supply/max17042_battery.c | 4 ---- include/linux/power/max17042_battery.h | 1 - 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/max17042_battery.c b/drivers/power/supply/max17042_battery.c index c6078f179fb3..01e6728a9e2b 100644 --- a/drivers/power/supply/max17042_battery.c +++ b/drivers/power/supply/max17042_battery.c @@ -283,8 +283,6 @@ static int max17042_get_property(struct power_supply *psy, case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042) ret = regmap_read(map, MAX17042_V_empty, &data); - else if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17055) - ret = regmap_read(map, MAX17055_V_empty, &data); else ret = regmap_read(map, MAX17047_V_empty, &data); if (ret < 0) @@ -778,8 +776,6 @@ static inline void max17042_override_por_values(struct max17042_chip *chip) if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042) max17042_override_por(map, MAX17042_V_empty, config->vempty); - if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17055) - max17042_override_por(map, MAX17055_V_empty, config->vempty); else max17042_override_por(map, MAX17047_V_empty, config->vempty); max17042_override_por(map, MAX17042_TempNom, config->temp_nom); diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h index d55c746ac56e..7e5da60cbea3 100644 --- a/include/linux/power/max17042_battery.h +++ b/include/linux/power/max17042_battery.h @@ -113,7 +113,6 @@ enum max17042_register { enum max17055_register { MAX17055_QRes = 0x0C, MAX17055_TTF = 0x20, - MAX17055_V_empty = 0x3A, MAX17055_TIMER = 0x3E, MAX17055_USER_MEM = 0x40, MAX17055_RGAIN = 0x42, -- cgit v1.2.3 From ed0d0a0506025f06061325cedae1bbebd081620a Mon Sep 17 00:00:00 2001 From: Sebastian Krzyszkowiak Date: Mon, 16 Aug 2021 18:50:14 +0200 Subject: power: supply: max17042_battery: fix typo in MAx17042_TOFF Signed-off-by: Sebastian Krzyszkowiak Signed-off-by: Sebastian Reichel --- drivers/power/supply/max17042_battery.c | 2 +- include/linux/power/max17042_battery.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/max17042_battery.c b/drivers/power/supply/max17042_battery.c index 01e6728a9e2b..eeccc365fe54 100644 --- a/drivers/power/supply/max17042_battery.c +++ b/drivers/power/supply/max17042_battery.c @@ -744,7 +744,7 @@ static inline void max17042_override_por_values(struct max17042_chip *chip) struct max17042_config_data *config = chip->pdata->config_data; max17042_override_por(map, MAX17042_TGAIN, config->tgain); - max17042_override_por(map, MAx17042_TOFF, config->toff); + max17042_override_por(map, MAX17042_TOFF, config->toff); max17042_override_por(map, MAX17042_CGAIN, config->cgain); max17042_override_por(map, MAX17042_COFF, config->coff); diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h index 7e5da60cbea3..86f16fc3b694 100644 --- a/include/linux/power/max17042_battery.h +++ b/include/linux/power/max17042_battery.h @@ -69,7 +69,7 @@ enum max17042_register { MAX17042_RelaxCFG = 0x2A, MAX17042_MiscCFG = 0x2B, MAX17042_TGAIN = 0x2C, - MAx17042_TOFF = 0x2D, + MAX17042_TOFF = 0x2D, MAX17042_CGAIN = 0x2E, MAX17042_COFF = 0x2F, -- cgit v1.2.3 From 4bf00434a6183a33c1fa315db7cc4d4a00a76be0 Mon Sep 17 00:00:00 2001 From: Sebastian Krzyszkowiak Date: Mon, 16 Aug 2021 18:50:15 +0200 Subject: power: supply: max17042_battery: more robust chip type checks Prepared by checking the datasheets of max17042, max17047/50 and max170455 for differences in register maps. Signed-off-by: Sebastian Krzyszkowiak Signed-off-by: Sebastian Reichel --- drivers/power/supply/max17042_battery.c | 40 +++++++++++++++++---------------- include/linux/power/max17042_battery.h | 9 +++++--- 2 files changed, 27 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/max17042_battery.c b/drivers/power/supply/max17042_battery.c index eeccc365fe54..e6bcda966476 100644 --- a/drivers/power/supply/max17042_battery.c +++ b/drivers/power/supply/max17042_battery.c @@ -763,34 +763,36 @@ static inline void max17042_override_por_values(struct max17042_chip *chip) max17042_override_por(map, MAX17042_FilterCFG, config->filter_cfg); max17042_override_por(map, MAX17042_RelaxCFG, config->relax_cfg); max17042_override_por(map, MAX17042_MiscCFG, config->misc_cfg); - max17042_override_por(map, MAX17042_MaskSOC, config->masksoc); max17042_override_por(map, MAX17042_FullCAP, config->fullcap); max17042_override_por(map, MAX17042_FullCAPNom, config->fullcapnom); - if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042) - max17042_override_por(map, MAX17042_SOC_empty, - config->socempty); - max17042_override_por(map, MAX17042_LAvg_empty, config->lavg_empty); max17042_override_por(map, MAX17042_dQacc, config->dqacc); max17042_override_por(map, MAX17042_dPacc, config->dpacc); - if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042) - max17042_override_por(map, MAX17042_V_empty, config->vempty); - else - max17042_override_por(map, MAX17047_V_empty, config->vempty); - max17042_override_por(map, MAX17042_TempNom, config->temp_nom); - max17042_override_por(map, MAX17042_TempLim, config->temp_lim); - max17042_override_por(map, MAX17042_FCTC, config->fctc); max17042_override_por(map, MAX17042_RCOMP0, config->rcomp0); max17042_override_por(map, MAX17042_TempCo, config->tcompc0); - if (chip->chip_type && - ((chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042) || + + if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042) { + max17042_override_por(map, MAX17042_MaskSOC, config->masksoc); + max17042_override_por(map, MAX17042_SOC_empty, config->socempty); + max17042_override_por(map, MAX17042_V_empty, config->vempty); + max17042_override_por(map, MAX17042_EmptyTempCo, config->empty_tempco); + max17042_override_por(map, MAX17042_K_empty0, config->kempty0); + } + + if ((chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042) || (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17047) || - (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17050))) { - max17042_override_por(map, MAX17042_EmptyTempCo, - config->empty_tempco); - max17042_override_por(map, MAX17042_K_empty0, - config->kempty0); + (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17050)) { + max17042_override_por(map, MAX17042_LAvg_empty, config->lavg_empty); + max17042_override_por(map, MAX17042_TempNom, config->temp_nom); + max17042_override_por(map, MAX17042_TempLim, config->temp_lim); + max17042_override_por(map, MAX17042_FCTC, config->fctc); + } + + if ((chip->chip_type == MAXIM_DEVICE_TYPE_MAX17047) || + (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17050) || + (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17055)) { + max17042_override_por(map, MAX17047_V_empty, config->vempty); } } diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h index 86f16fc3b694..dd24756a8af7 100644 --- a/include/linux/power/max17042_battery.h +++ b/include/linux/power/max17042_battery.h @@ -110,12 +110,14 @@ enum max17042_register { MAX17042_VFSOC = 0xFF, }; +/* Registers specific to max17055 only */ enum max17055_register { MAX17055_QRes = 0x0C, + MAX17055_RCell = 0x14, MAX17055_TTF = 0x20, - MAX17055_TIMER = 0x3E, + MAX17055_DieTemp = 0x34, MAX17055_USER_MEM = 0x40, - MAX17055_RGAIN = 0x42, + MAX17055_RGAIN = 0x43, MAX17055_ConvgCfg = 0x49, MAX17055_VFRemCap = 0x4A, @@ -154,13 +156,14 @@ enum max17055_register { MAX17055_AtAvCap = 0xDF, }; -/* Registers specific to max17047/50 */ +/* Registers specific to max17047/50/55 */ enum max17047_register { MAX17047_QRTbl00 = 0x12, MAX17047_FullSOCThr = 0x13, MAX17047_QRTbl10 = 0x22, MAX17047_QRTbl20 = 0x32, MAX17047_V_empty = 0x3A, + MAX17047_TIMER = 0x3E, MAX17047_QRTbl30 = 0x42, }; -- cgit v1.2.3 From d8bbd97ad0b99a9394f2cd8410b884c48e218cf0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:27:37 +0200 Subject: locking/local_lock: Add missing owner initialization If CONFIG_DEBUG_LOCK_ALLOC=y is enabled then local_lock_t has an 'owner' member which is checked for consistency, but nothing initialized it to zero explicitly. The static initializer does so implicit, and the run time allocated per CPU storage is usually zero initialized as well, but relying on that is not really good practice. Fixes: 91710728d172 ("locking: Introduce local_lock()") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211301.969975279@linutronix.de --- include/linux/local_lock_internal.h | 42 ++++++++++++++++++++----------------- 1 file changed, 23 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index ded90b097e6e..3f02b818625e 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -14,29 +14,14 @@ typedef struct { } local_lock_t; #ifdef CONFIG_DEBUG_LOCK_ALLOC -# define LL_DEP_MAP_INIT(lockname) \ +# define LOCAL_LOCK_DEBUG_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ - .lock_type = LD_LOCK_PERCPU, \ - } -#else -# define LL_DEP_MAP_INIT(lockname) -#endif - -#define INIT_LOCAL_LOCK(lockname) { LL_DEP_MAP_INIT(lockname) } - -#define __local_lock_init(lock) \ -do { \ - static struct lock_class_key __key; \ - \ - debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ - lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, 0, \ - LD_WAIT_CONFIG, LD_WAIT_INV, \ - LD_LOCK_PERCPU); \ -} while (0) + .lock_type = LD_LOCK_PERCPU, \ + }, \ + .owner = NULL, -#ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); @@ -51,11 +36,30 @@ static inline void local_lock_release(local_lock_t *l) lock_map_release(&l->dep_map); } +static inline void local_lock_debug_init(local_lock_t *l) +{ + l->owner = NULL; +} #else /* CONFIG_DEBUG_LOCK_ALLOC */ +# define LOCAL_LOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } +static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ +#define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } + +#define __local_lock_init(lock) \ +do { \ + static struct lock_class_key __key; \ + \ + debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ + lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ + 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ + LD_LOCK_PERCPU); \ + local_lock_debug_init(lock); \ +} while (0) + #define __local_lock(lock) \ do { \ preempt_disable(); \ -- cgit v1.2.3 From b41cda03765580caf7723b8c1b672d191c71013f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:27:38 +0200 Subject: locking/rtmutex: Set proper wait context for lockdep RT mutexes belong to the LD_WAIT_SLEEP class. Make them so. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211302.031014562@linutronix.de --- include/linux/rtmutex.h | 19 ++++++++++++------- kernel/locking/rtmutex.c | 2 +- 2 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index d1672de9ca89..87b325aec508 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -52,17 +52,22 @@ do { \ } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC -#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \ - , .dep_map = { .name = #mutexname } +#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \ + .dep_map = { \ + .name = #mutexname, \ + .wait_type_inner = LD_WAIT_SLEEP, \ + } #else #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) #endif -#define __RT_MUTEX_INITIALIZER(mutexname) \ - { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ - , .waiters = RB_ROOT_CACHED \ - , .owner = NULL \ - __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)} +#define __RT_MUTEX_INITIALIZER(mutexname) \ +{ \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock), \ + .waiters = RB_ROOT_CACHED, \ + .owner = NULL, \ + __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \ +} #define DEFINE_RT_MUTEX(mutexname) \ struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index ad0db322ed3b..1a7e3f838077 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1556,7 +1556,7 @@ void __sched __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key) { debug_check_no_locks_freed((void *)lock, sizeof(*lock)); - lockdep_init_map(&lock->dep_map, name, key, 0); + lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_SLEEP); __rt_mutex_basic_init(lock); } -- cgit v1.2.3 From cd781d0ce8cb4d491910833c5eec90f150432da3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:27:41 +0200 Subject: sched/wakeup: Introduce the TASK_RTLOCK_WAIT state bit RT kernels have an extra quirk for try_to_wake_up() to handle task state preservation across periods of blocking on a 'sleeping' spin/rwlock. For this to function correctly and under all circumstances try_to_wake_up() must be able to identify whether the wakeup is lock related or not and whether the task is waiting for a lock or not. The original approach was to use a special wake_flag argument for try_to_wake_up() and just use TASK_UNINTERRUPTIBLE for the tasks wait state and the try_to_wake_up() state argument. This works in principle, but due to the fact that try_to_wake_up() cannot determine whether the task is waiting for an RT lock wakeup or for a regular wakeup it's suboptimal. RT kernels save the original task state when blocking on an RT lock and restore it when the lock has been acquired. Any non lock related wakeup is checked against the saved state and if it matches the saved state is set to running so that the wakeup is not lost when the state is restored. While the necessary logic for the wake_flag based solution is trivial, the downside is that any regular wakeup with TASK_UNINTERRUPTIBLE in the state argument set will wake the task despite the fact that it is still blocked on the lock. That's not a fatal problem as the lock wait has do deal with spurious wakeups anyway, but it introduces unnecessary latencies. Introduce the TASK_RTLOCK_WAIT state bit which will be set when a task blocks on an RT lock. The lock wakeup will use wake_up_state(TASK_RTLOCK_WAIT), so both the waiting state and the wakeup state are distinguishable, which avoids spurious wakeups and allows better analysis. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211302.144989915@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ec8d07d88641..9a9f606b02cd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -95,7 +95,9 @@ struct task_group; #define TASK_WAKING 0x0200 #define TASK_NOLOAD 0x0400 #define TASK_NEW 0x0800 -#define TASK_STATE_MAX 0x1000 +/* RT specific auxilliary flag to mark RT lock waiters */ +#define TASK_RTLOCK_WAIT 0x1000 +#define TASK_STATE_MAX 0x2000 /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) -- cgit v1.2.3 From 85019c1674890fa0408e324589e20803b3241755 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:27:43 +0200 Subject: sched/wakeup: Reorganize the current::__state helpers In order to avoid more duplicate implementations for the debug and non-debug variants of the state change macros, split the debug portion out and make that conditional on CONFIG_DEBUG_ATOMIC_SLEEP=y. Suggested-by: Waiman Long Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211302.200898048@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/sched.h | 48 +++++++++++++++++++++++------------------------- 1 file changed, 23 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9a9f606b02cd..4c72cf6aaabf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -123,8 +123,6 @@ struct task_group; #define task_is_stopped_or_traced(task) ((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0) -#ifdef CONFIG_DEBUG_ATOMIC_SLEEP - /* * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). @@ -132,30 +130,24 @@ struct task_group; #define is_special_task_state(state) \ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) -#define __set_current_state(state_value) \ - do { \ - WARN_ON_ONCE(is_special_task_state(state_value));\ - current->task_state_change = _THIS_IP_; \ - WRITE_ONCE(current->__state, (state_value)); \ - } while (0) - -#define set_current_state(state_value) \ - do { \ - WARN_ON_ONCE(is_special_task_state(state_value));\ - current->task_state_change = _THIS_IP_; \ - smp_store_mb(current->__state, (state_value)); \ +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP +# define debug_normal_state_change(state_value) \ + do { \ + WARN_ON_ONCE(is_special_task_state(state_value)); \ + current->task_state_change = _THIS_IP_; \ } while (0) -#define set_special_state(state_value) \ +# define debug_special_state_change(state_value) \ do { \ - unsigned long flags; /* may shadow */ \ WARN_ON_ONCE(!is_special_task_state(state_value)); \ - raw_spin_lock_irqsave(¤t->pi_lock, flags); \ current->task_state_change = _THIS_IP_; \ - WRITE_ONCE(current->__state, (state_value)); \ - raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) + #else +# define debug_normal_state_change(cond) do { } while (0) +# define debug_special_state_change(cond) do { } while (0) +#endif + /* * set_current_state() includes a barrier so that the write of current->state * is correctly serialised wrt the caller's subsequent test of whether to @@ -194,27 +186,33 @@ struct task_group; * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ - WRITE_ONCE(current->__state, (state_value)) + do { \ + debug_normal_state_change((state_value)); \ + WRITE_ONCE(current->__state, (state_value)); \ + } while (0) #define set_current_state(state_value) \ - smp_store_mb(current->__state, (state_value)) + do { \ + debug_normal_state_change((state_value)); \ + smp_store_mb(current->__state, (state_value)); \ + } while (0) /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must - * serialize against wakeups such that any possible in-flight TASK_RUNNING stores - * will not collide with our state change. + * serialize against wakeups such that any possible in-flight TASK_RUNNING + * stores will not collide with our state change. */ #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ + \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ + debug_special_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) -#endif - #define get_current_state() READ_ONCE(current->__state) /* Task command name length: */ -- cgit v1.2.3 From 5f220be21418541422335288b6e2360a5ce0613c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:27:44 +0200 Subject: sched/wakeup: Prepare for RT sleeping spin/rwlocks Waiting for spinlocks and rwlocks on non RT enabled kernels is task::state preserving. Any wakeup which matches the state is valid. RT enabled kernels substitutes them with 'sleeping' spinlocks. This creates an issue vs. task::__state. In order to block on the lock, the task has to overwrite task::__state and a consecutive wakeup issued by the unlocker sets the state back to TASK_RUNNING. As a consequence the task loses the state which was set before the lock acquire and also any regular wakeup targeted at the task while it is blocked on the lock. To handle this gracefully, add a 'saved_state' member to task_struct which is used in the following way: 1) When a task blocks on a 'sleeping' spinlock, the current state is saved in task::saved_state before it is set to TASK_RTLOCK_WAIT. 2) When the task unblocks and after acquiring the lock, it restores the saved state. 3) When a regular wakeup happens for a task while it is blocked then the state change of that wakeup is redirected to operate on task::saved_state. This is also required when the task state is running because the task might have been woken up from the lock wait and has not yet restored the saved state. To make it complete, provide the necessary helpers to save and restore the saved state along with the necessary documentation how the RT lock blocking is supposed to work. For non-RT kernels there is no functional change. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211302.258751046@linutronix.de --- include/linux/sched.h | 66 +++++++++++++++++++++++++++++++++++++++++++++++++++ kernel/sched/core.c | 33 ++++++++++++++++++++++++++ 2 files changed, 99 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4c72cf6aaabf..02714b9a3ff9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -143,9 +143,22 @@ struct task_group; current->task_state_change = _THIS_IP_; \ } while (0) +# define debug_rtlock_wait_set_state() \ + do { \ + current->saved_state_change = current->task_state_change;\ + current->task_state_change = _THIS_IP_; \ + } while (0) + +# define debug_rtlock_wait_restore_state() \ + do { \ + current->task_state_change = current->saved_state_change;\ + } while (0) + #else # define debug_normal_state_change(cond) do { } while (0) # define debug_special_state_change(cond) do { } while (0) +# define debug_rtlock_wait_set_state() do { } while (0) +# define debug_rtlock_wait_restore_state() do { } while (0) #endif /* @@ -213,6 +226,51 @@ struct task_group; raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) +/* + * PREEMPT_RT specific variants for "sleeping" spin/rwlocks + * + * RT's spin/rwlock substitutions are state preserving. The state of the + * task when blocking on the lock is saved in task_struct::saved_state and + * restored after the lock has been acquired. These operations are + * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT + * lock related wakeups while the task is blocked on the lock are + * redirected to operate on task_struct::saved_state to ensure that these + * are not dropped. On restore task_struct::saved_state is set to + * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail. + * + * The lock operation looks like this: + * + * current_save_and_set_rtlock_wait_state(); + * for (;;) { + * if (try_lock()) + * break; + * raw_spin_unlock_irq(&lock->wait_lock); + * schedule_rtlock(); + * raw_spin_lock_irq(&lock->wait_lock); + * set_current_state(TASK_RTLOCK_WAIT); + * } + * current_restore_rtlock_saved_state(); + */ +#define current_save_and_set_rtlock_wait_state() \ + do { \ + lockdep_assert_irqs_disabled(); \ + raw_spin_lock(¤t->pi_lock); \ + current->saved_state = current->__state; \ + debug_rtlock_wait_set_state(); \ + WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \ + raw_spin_unlock(¤t->pi_lock); \ + } while (0); + +#define current_restore_rtlock_saved_state() \ + do { \ + lockdep_assert_irqs_disabled(); \ + raw_spin_lock(¤t->pi_lock); \ + debug_rtlock_wait_restore_state(); \ + WRITE_ONCE(current->__state, current->saved_state); \ + current->saved_state = TASK_RUNNING; \ + raw_spin_unlock(¤t->pi_lock); \ + } while (0); + #define get_current_state() READ_ONCE(current->__state) /* Task command name length: */ @@ -668,6 +726,11 @@ struct task_struct { #endif unsigned int __state; +#ifdef CONFIG_PREEMPT_RT + /* saved state for "spinlock sleepers" */ + unsigned int saved_state; +#endif + /* * This begins the randomizable portion of task_struct. Only * scheduling-critical items should be added above here. @@ -1357,6 +1420,9 @@ struct task_struct { struct kmap_ctrl kmap_ctrl; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; +# ifdef CONFIG_PREEMPT_RT + unsigned long saved_state_change; +# endif #endif int pagefault_disabled; #ifdef CONFIG_MMU diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 961991e06337..e407c6ac4a26 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3566,14 +3566,47 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * * The caller holds p::pi_lock if p != current or has preemption * disabled when p == current. + * + * The rules of PREEMPT_RT saved_state: + * + * The related locking code always holds p::pi_lock when updating + * p::saved_state, which means the code is fully serialized in both cases. + * + * The lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. No other + * bits set. This allows to distinguish all wakeup scenarios. */ static __always_inline bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success) { + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) { + WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) && + state != TASK_RTLOCK_WAIT); + } + if (READ_ONCE(p->__state) & state) { *success = 1; return true; } + +#ifdef CONFIG_PREEMPT_RT + /* + * Saved state preserves the task state across blocking on + * an RT lock. If the state matches, set p::saved_state to + * TASK_RUNNING, but do not wake the task because it waits + * for a lock wakeup. Also indicate success because from + * the regular waker's point of view this has succeeded. + * + * After acquiring the lock the task will restore p::__state + * from p::saved_state which ensures that the regular + * wakeup is not lost. The restore will also set + * p::saved_state to TASK_RUNNING so any further tests will + * not result in false positives vs. @success + */ + if (p->saved_state & state) { + p->saved_state = TASK_RUNNING; + *success = 1; + } +#endif return false; } -- cgit v1.2.3 From 6991436c2b5d91d5358d9914ae2df22b9a1d1dc9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:27:48 +0200 Subject: sched/core: Provide a scheduling point for RT locks RT enabled kernels substitute spin/rwlocks with 'sleeping' variants based on rtmutexes. Blocking on such a lock is similar to preemption versus: - I/O scheduling and worker handling, because these functions might block on another substituted lock, or come from a lock contention within these functions. - RCU considers this like a preemption, because the task might be in a read side critical section. Add a separate scheduling point for this, and hand a new scheduling mode argument to __schedule() which allows, along with separate mode masks, to handle this gracefully from within the scheduler, without proliferating that to other subsystems like RCU. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211302.372319055@linutronix.de --- include/linux/sched.h | 3 +++ kernel/sched/core.c | 20 +++++++++++++++++++- 2 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 02714b9a3ff9..746dfc06a35c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -288,6 +288,9 @@ extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); asmlinkage void preempt_schedule_irq(void); +#ifdef CONFIG_PREEMPT_RT + extern void schedule_rtlock(void); +#endif extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ebc24e136222..c89c1d45dd0b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5829,7 +5829,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) */ #define SM_NONE 0x0 #define SM_PREEMPT 0x1 -#define SM_MASK_PREEMPT (~0U) +#define SM_RTLOCK_WAIT 0x2 + +#ifndef CONFIG_PREEMPT_RT +# define SM_MASK_PREEMPT (~0U) +#else +# define SM_MASK_PREEMPT SM_PREEMPT +#endif /* * __schedule() is the main scheduler function. @@ -6134,6 +6140,18 @@ void __sched schedule_preempt_disabled(void) preempt_disable(); } +#ifdef CONFIG_PREEMPT_RT +void __sched notrace schedule_rtlock(void) +{ + do { + preempt_disable(); + __schedule(SM_RTLOCK_WAIT); + sched_preempt_enable_no_resched(); + } while (need_resched()); +} +NOKPROBE_SYMBOL(schedule_rtlock); +#endif + static void __sched notrace preempt_schedule_common(void) { do { -- cgit v1.2.3 From 2c8bb85151d4bad825f8962792e9f53d22db81db Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:27:49 +0200 Subject: sched/wake_q: Provide WAKE_Q_HEAD_INITIALIZER() The RT specific spin/rwlock implementation requires special handling of the to be woken waiters. Provide a WAKE_Q_HEAD_INITIALIZER(), which can be used by the rtmutex code to implement an RT aware wake_q derivative. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211302.429918071@linutronix.de --- include/linux/sched/wake_q.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 26a2013ac39c..06cd8fb2f409 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -42,8 +42,11 @@ struct wake_q_head { #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) -#define DEFINE_WAKE_Q(name) \ - struct wake_q_head name = { WAKE_Q_TAIL, &name.first } +#define WAKE_Q_HEAD_INITIALIZER(name) \ + { WAKE_Q_TAIL, &name.first } + +#define DEFINE_WAKE_Q(name) \ + struct wake_q_head name = WAKE_Q_HEAD_INITIALIZER(name) static inline void wake_q_init(struct wake_q_head *head) { -- cgit v1.2.3 From f07ec52202ca5bfc79d30ca7c54f86454eb1a9b0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 15 Aug 2021 23:27:52 +0200 Subject: locking/rtmutex: Remove rt_mutex_is_locked() There are no more users left. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211302.552218335@linutronix.de --- include/linux/rtmutex.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 87b325aec508..cb0f441fecb9 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -72,17 +72,6 @@ do { \ #define DEFINE_RT_MUTEX(mutexname) \ struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) -/** - * rt_mutex_is_locked - is the mutex locked - * @lock: the mutex to be queried - * - * Returns 1 if the mutex is locked, 0 if unlocked. - */ -static inline int rt_mutex_is_locked(struct rt_mutex *lock) -{ - return lock->owner != NULL; -} - extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); #ifdef CONFIG_DEBUG_LOCK_ALLOC -- cgit v1.2.3 From 830e6acc8a1cafe153a0d88f9b2455965b396131 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 15 Aug 2021 23:27:58 +0200 Subject: locking/rtmutex: Split out the inner parts of 'struct rtmutex' RT builds substitutions for rwsem, mutex, spinlock and rwlock around rtmutexes. Split the inner working out so each lock substitution can use them with the appropriate lockdep annotations. This avoids having an extra unused lockdep map in the wrapped rtmutex. No functional change. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211302.784739994@linutronix.de --- include/linux/rtmutex.h | 23 +++++++++++---- kernel/futex.c | 4 +-- kernel/locking/rtmutex.c | 64 +++++++++++++++++++++-------------------- kernel/locking/rtmutex_api.c | 41 ++++++++++++++------------ kernel/locking/rtmutex_common.h | 38 ++++++++++++------------ kernel/rcu/tree_plugin.h | 6 ++-- 6 files changed, 97 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index cb0f441fecb9..852740285d71 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -19,6 +19,21 @@ extern int max_lock_depth; /* for sysctl */ +struct rt_mutex_base { + raw_spinlock_t wait_lock; + struct rb_root_cached waiters; + struct task_struct *owner; +}; + +#define __RT_MUTEX_BASE_INITIALIZER(rtbasename) \ +{ \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(rtbasename.wait_lock), \ + .waiters = RB_ROOT_CACHED, \ + .owner = NULL \ +} + +extern void rt_mutex_base_init(struct rt_mutex_base *rtb); + /** * The rt_mutex structure * @@ -28,9 +43,7 @@ extern int max_lock_depth; /* for sysctl */ * @owner: the mutex owner */ struct rt_mutex { - raw_spinlock_t wait_lock; - struct rb_root_cached waiters; - struct task_struct *owner; + struct rt_mutex_base rtmutex; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif @@ -63,9 +76,7 @@ do { \ #define __RT_MUTEX_INITIALIZER(mutexname) \ { \ - .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock), \ - .waiters = RB_ROOT_CACHED, \ - .owner = NULL, \ + .rtmutex = __RT_MUTEX_BASE_INITIALIZER(mutexname.rtmutex), \ __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \ } diff --git a/kernel/futex.c b/kernel/futex.c index 2ecb07575055..6eab24764f28 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -179,7 +179,7 @@ struct futex_pi_state { /* * The PI object: */ - struct rt_mutex pi_mutex; + struct rt_mutex_base pi_mutex; struct task_struct *owner; refcount_t refcount; @@ -3254,7 +3254,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, ret = ret < 0 ? ret : 0; } } else { - struct rt_mutex *pi_mutex; + struct rt_mutex_base *pi_mutex; /* * We have been woken up by futex_unlock_pi(), a timeout, or a diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index cd0e1a43b07a..b31f6cbe3a30 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -48,7 +48,7 @@ */ static __always_inline void -rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner) +rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner) { unsigned long val = (unsigned long)owner; @@ -58,13 +58,13 @@ rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner) WRITE_ONCE(lock->owner, (struct task_struct *)val); } -static __always_inline void clear_rt_mutex_waiters(struct rt_mutex *lock) +static __always_inline void clear_rt_mutex_waiters(struct rt_mutex_base *lock) { lock->owner = (struct task_struct *) ((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS); } -static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex *lock) +static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex_base *lock) { unsigned long owner, *p = (unsigned long *) &lock->owner; @@ -139,14 +139,14 @@ static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex *lock) * set up. */ #ifndef CONFIG_DEBUG_RT_MUTEXES -static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex *lock, +static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex_base *lock, struct task_struct *old, struct task_struct *new) { return try_cmpxchg_acquire(&lock->owner, &old, new); } -static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex *lock, +static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock, struct task_struct *old, struct task_struct *new) { @@ -158,7 +158,7 @@ static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex *lock, * all future threads that attempt to [Rmw] the lock to the slowpath. As such * relaxed semantics suffice. */ -static __always_inline void mark_rt_mutex_waiters(struct rt_mutex *lock) +static __always_inline void mark_rt_mutex_waiters(struct rt_mutex_base *lock) { unsigned long owner, *p = (unsigned long *) &lock->owner; @@ -174,7 +174,7 @@ static __always_inline void mark_rt_mutex_waiters(struct rt_mutex *lock) * 2) Drop lock->wait_lock * 3) Try to unlock the lock with cmpxchg */ -static __always_inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, +static __always_inline bool unlock_rt_mutex_safe(struct rt_mutex_base *lock, unsigned long flags) __releases(lock->wait_lock) { @@ -210,7 +210,7 @@ static __always_inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, } #else -static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex *lock, +static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex_base *lock, struct task_struct *old, struct task_struct *new) { @@ -218,14 +218,14 @@ static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex *lock, } -static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex *lock, +static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock, struct task_struct *old, struct task_struct *new) { return false; } -static __always_inline void mark_rt_mutex_waiters(struct rt_mutex *lock) +static __always_inline void mark_rt_mutex_waiters(struct rt_mutex_base *lock) { lock->owner = (struct task_struct *) ((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS); @@ -234,7 +234,7 @@ static __always_inline void mark_rt_mutex_waiters(struct rt_mutex *lock) /* * Simple slow path only version: lock->owner is protected by lock->wait_lock. */ -static __always_inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, +static __always_inline bool unlock_rt_mutex_safe(struct rt_mutex_base *lock, unsigned long flags) __releases(lock->wait_lock) { @@ -295,13 +295,13 @@ static __always_inline bool __waiter_less(struct rb_node *a, const struct rb_nod } static __always_inline void -rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) +rt_mutex_enqueue(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter) { rb_add_cached(&waiter->tree_entry, &lock->waiters, __waiter_less); } static __always_inline void -rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) +rt_mutex_dequeue(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter) { if (RB_EMPTY_NODE(&waiter->tree_entry)) return; @@ -369,7 +369,7 @@ rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, return chwalk == RT_MUTEX_FULL_CHAINWALK; } -static __always_inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) +static __always_inline struct rt_mutex_base *task_blocked_on_lock(struct task_struct *p) { return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; } @@ -439,15 +439,15 @@ static __always_inline struct rt_mutex *task_blocked_on_lock(struct task_struct */ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task, enum rtmutex_chainwalk chwalk, - struct rt_mutex *orig_lock, - struct rt_mutex *next_lock, + struct rt_mutex_base *orig_lock, + struct rt_mutex_base *next_lock, struct rt_mutex_waiter *orig_waiter, struct task_struct *top_task) { struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter; struct rt_mutex_waiter *prerequeue_top_waiter; int ret = 0, depth = 0; - struct rt_mutex *lock; + struct rt_mutex_base *lock; bool detect_deadlock; bool requeue = true; @@ -795,7 +795,7 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task, * callsite called task_blocked_on_lock(), otherwise NULL */ static int __sched -try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, +try_to_take_rt_mutex(struct rt_mutex_base *lock, struct task_struct *task, struct rt_mutex_waiter *waiter) { lockdep_assert_held(&lock->wait_lock); @@ -913,14 +913,14 @@ takeit: * * This must be called with lock->wait_lock held and interrupts disabled */ -static int __sched task_blocks_on_rt_mutex(struct rt_mutex *lock, +static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter, struct task_struct *task, enum rtmutex_chainwalk chwalk) { struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex_waiter *top_waiter = waiter; - struct rt_mutex *next_lock; + struct rt_mutex_base *next_lock; int chain_walk = 0, res; lockdep_assert_held(&lock->wait_lock); @@ -1003,7 +1003,7 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex *lock, * Called with lock->wait_lock held and interrupts disabled. */ static void __sched mark_wakeup_next_waiter(struct wake_q_head *wake_q, - struct rt_mutex *lock) + struct rt_mutex_base *lock) { struct rt_mutex_waiter *waiter; @@ -1052,12 +1052,12 @@ static void __sched mark_wakeup_next_waiter(struct wake_q_head *wake_q, * Must be called with lock->wait_lock held and interrupts disabled. I must * have just failed to try_to_take_rt_mutex(). */ -static void __sched remove_waiter(struct rt_mutex *lock, +static void __sched remove_waiter(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter) { bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); struct task_struct *owner = rt_mutex_owner(lock); - struct rt_mutex *next_lock; + struct rt_mutex_base *next_lock; lockdep_assert_held(&lock->wait_lock); @@ -1115,7 +1115,8 @@ static void __sched remove_waiter(struct rt_mutex *lock, * * Must be called with lock->wait_lock held and interrupts disabled */ -static int __sched __rt_mutex_slowlock(struct rt_mutex *lock, unsigned int state, +static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock, + unsigned int state, struct hrtimer_sleeper *timeout, struct rt_mutex_waiter *waiter) { @@ -1170,7 +1171,8 @@ static void __sched rt_mutex_handle_deadlock(int res, int detect_deadlock, /* * Slow path lock function: */ -static int __sched rt_mutex_slowlock(struct rt_mutex *lock, unsigned int state, +static int __sched rt_mutex_slowlock(struct rt_mutex_base *lock, + unsigned int state, struct hrtimer_sleeper *timeout, enum rtmutex_chainwalk chwalk) { @@ -1231,7 +1233,7 @@ static int __sched rt_mutex_slowlock(struct rt_mutex *lock, unsigned int state, return ret; } -static __always_inline int __rt_mutex_lock(struct rt_mutex *lock, +static __always_inline int __rt_mutex_lock(struct rt_mutex_base *lock, unsigned int state) { if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) @@ -1240,7 +1242,7 @@ static __always_inline int __rt_mutex_lock(struct rt_mutex *lock, return rt_mutex_slowlock(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); } -static int __sched __rt_mutex_slowtrylock(struct rt_mutex *lock) +static int __sched __rt_mutex_slowtrylock(struct rt_mutex_base *lock) { int ret = try_to_take_rt_mutex(lock, current, NULL); @@ -1256,7 +1258,7 @@ static int __sched __rt_mutex_slowtrylock(struct rt_mutex *lock) /* * Slow path try-lock function: */ -static int __sched rt_mutex_slowtrylock(struct rt_mutex *lock) +static int __sched rt_mutex_slowtrylock(struct rt_mutex_base *lock) { unsigned long flags; int ret; @@ -1282,7 +1284,7 @@ static int __sched rt_mutex_slowtrylock(struct rt_mutex *lock) return ret; } -static __always_inline int __rt_mutex_trylock(struct rt_mutex *lock) +static __always_inline int __rt_mutex_trylock(struct rt_mutex_base *lock) { if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 1; @@ -1293,7 +1295,7 @@ static __always_inline int __rt_mutex_trylock(struct rt_mutex *lock) /* * Slow path to release a rt-mutex. */ -static void __sched rt_mutex_slowunlock(struct rt_mutex *lock) +static void __sched rt_mutex_slowunlock(struct rt_mutex_base *lock) { DEFINE_WAKE_Q(wake_q); unsigned long flags; @@ -1354,7 +1356,7 @@ static void __sched rt_mutex_slowunlock(struct rt_mutex *lock) rt_mutex_postunlock(&wake_q); } -static __always_inline void __rt_mutex_unlock(struct rt_mutex *lock) +static __always_inline void __rt_mutex_unlock(struct rt_mutex_base *lock) { if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) return; diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index fc1322f5b219..38de4b137b9e 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -26,12 +26,18 @@ static __always_inline int __rt_mutex_lock_common(struct rt_mutex *lock, might_sleep(); mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); - ret = __rt_mutex_lock(lock, state); + ret = __rt_mutex_lock(&lock->rtmutex, state); if (ret) mutex_release(&lock->dep_map, _RET_IP_); return ret; } +void rt_mutex_base_init(struct rt_mutex_base *rtb) +{ + __rt_mutex_base_init(rtb); +} +EXPORT_SYMBOL(rt_mutex_base_init); + #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * rt_mutex_lock_nested - lock a rt_mutex @@ -93,7 +99,7 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock) if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task())) return 0; - ret = __rt_mutex_trylock(lock); + ret = __rt_mutex_trylock(&lock->rtmutex); if (ret) mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); @@ -109,19 +115,19 @@ EXPORT_SYMBOL_GPL(rt_mutex_trylock); void __sched rt_mutex_unlock(struct rt_mutex *lock) { mutex_release(&lock->dep_map, _RET_IP_); - __rt_mutex_unlock(lock); + __rt_mutex_unlock(&lock->rtmutex); } EXPORT_SYMBOL_GPL(rt_mutex_unlock); /* * Futex variants, must not use fastpath. */ -int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) +int __sched rt_mutex_futex_trylock(struct rt_mutex_base *lock) { return rt_mutex_slowtrylock(lock); } -int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) +int __sched __rt_mutex_futex_trylock(struct rt_mutex_base *lock) { return __rt_mutex_slowtrylock(lock); } @@ -133,7 +139,7 @@ int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) * @lock: The rt_mutex to be unlocked * @wake_q: The wake queue head from which to get the next lock waiter */ -bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, +bool __sched __rt_mutex_futex_unlock(struct rt_mutex_base *lock, struct wake_q_head *wake_q) { lockdep_assert_held(&lock->wait_lock); @@ -156,7 +162,7 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, return true; /* call postunlock() */ } -void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) +void __sched rt_mutex_futex_unlock(struct rt_mutex_base *lock) { DEFINE_WAKE_Q(wake_q); unsigned long flags; @@ -182,12 +188,11 @@ void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) * Initializing of a locked rt_mutex is not allowed */ void __sched __rt_mutex_init(struct rt_mutex *lock, const char *name, - struct lock_class_key *key) + struct lock_class_key *key) { debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + __rt_mutex_base_init(&lock->rtmutex); lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_SLEEP); - - __rt_mutex_basic_init(lock); } EXPORT_SYMBOL_GPL(__rt_mutex_init); @@ -205,10 +210,10 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init); * possible at this point because the pi_state which contains the rtmutex * is not yet visible to other tasks. */ -void __sched rt_mutex_init_proxy_locked(struct rt_mutex *lock, +void __sched rt_mutex_init_proxy_locked(struct rt_mutex_base *lock, struct task_struct *proxy_owner) { - __rt_mutex_basic_init(lock); + __rt_mutex_base_init(lock); rt_mutex_set_owner(lock, proxy_owner); } @@ -224,7 +229,7 @@ void __sched rt_mutex_init_proxy_locked(struct rt_mutex *lock, * possible because it belongs to the pi_state which is about to be freed * and it is not longer visible to other tasks. */ -void __sched rt_mutex_proxy_unlock(struct rt_mutex *lock) +void __sched rt_mutex_proxy_unlock(struct rt_mutex_base *lock) { debug_rt_mutex_proxy_unlock(lock); rt_mutex_set_owner(lock, NULL); @@ -249,7 +254,7 @@ void __sched rt_mutex_proxy_unlock(struct rt_mutex *lock) * * Special API call for PI-futex support. */ -int __sched __rt_mutex_start_proxy_lock(struct rt_mutex *lock, +int __sched __rt_mutex_start_proxy_lock(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter, struct task_struct *task) { @@ -296,7 +301,7 @@ int __sched __rt_mutex_start_proxy_lock(struct rt_mutex *lock, * * Special API call for PI-futex support. */ -int __sched rt_mutex_start_proxy_lock(struct rt_mutex *lock, +int __sched rt_mutex_start_proxy_lock(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter, struct task_struct *task) { @@ -328,7 +333,7 @@ int __sched rt_mutex_start_proxy_lock(struct rt_mutex *lock, * * Special API call for PI-futex support */ -int __sched rt_mutex_wait_proxy_lock(struct rt_mutex *lock, +int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, struct hrtimer_sleeper *to, struct rt_mutex_waiter *waiter) { @@ -368,7 +373,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex *lock, * * Special API call for PI-futex support */ -bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, +bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter) { bool cleanup = false; @@ -413,7 +418,7 @@ bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, void __sched rt_mutex_adjust_pi(struct task_struct *task) { struct rt_mutex_waiter *waiter; - struct rt_mutex *next_lock; + struct rt_mutex_base *next_lock; unsigned long flags; raw_spin_lock_irqsave(&task->pi_lock, flags); diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 0f314a21d6ca..548285a5ed19 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -32,7 +32,7 @@ struct rt_mutex_waiter { struct rb_node tree_entry; struct rb_node pi_tree_entry; struct task_struct *task; - struct rt_mutex *lock; + struct rt_mutex_base *lock; int prio; u64 deadline; }; @@ -40,26 +40,26 @@ struct rt_mutex_waiter { /* * PI-futex support (proxy locking functions, etc.): */ -extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, +extern void rt_mutex_init_proxy_locked(struct rt_mutex_base *lock, struct task_struct *proxy_owner); -extern void rt_mutex_proxy_unlock(struct rt_mutex *lock); -extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, +extern void rt_mutex_proxy_unlock(struct rt_mutex_base *lock); +extern int __rt_mutex_start_proxy_lock(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter, struct task_struct *task); -extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock, +extern int rt_mutex_start_proxy_lock(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter, struct task_struct *task); -extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, +extern int rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, struct hrtimer_sleeper *to, struct rt_mutex_waiter *waiter); -extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, +extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter); -extern int rt_mutex_futex_trylock(struct rt_mutex *l); -extern int __rt_mutex_futex_trylock(struct rt_mutex *l); +extern int rt_mutex_futex_trylock(struct rt_mutex_base *l); +extern int __rt_mutex_futex_trylock(struct rt_mutex_base *l); -extern void rt_mutex_futex_unlock(struct rt_mutex *lock); -extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, +extern void rt_mutex_futex_unlock(struct rt_mutex_base *lock); +extern bool __rt_mutex_futex_unlock(struct rt_mutex_base *lock, struct wake_q_head *wake_q); extern void rt_mutex_postunlock(struct wake_q_head *wake_q); @@ -69,12 +69,12 @@ extern void rt_mutex_postunlock(struct wake_q_head *wake_q); * unconditionally. */ #ifdef CONFIG_RT_MUTEXES -static inline int rt_mutex_has_waiters(struct rt_mutex *lock) +static inline int rt_mutex_has_waiters(struct rt_mutex_base *lock) { return !RB_EMPTY_ROOT(&lock->waiters.rb_root); } -static inline struct rt_mutex_waiter *rt_mutex_top_waiter(struct rt_mutex *lock) +static inline struct rt_mutex_waiter *rt_mutex_top_waiter(struct rt_mutex_base *lock) { struct rb_node *leftmost = rb_first_cached(&lock->waiters); struct rt_mutex_waiter *w = NULL; @@ -99,7 +99,7 @@ static inline struct rt_mutex_waiter *task_top_pi_waiter(struct task_struct *p) #define RT_MUTEX_HAS_WAITERS 1UL -static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) +static inline struct task_struct *rt_mutex_owner(struct rt_mutex_base *lock) { unsigned long owner = (unsigned long) READ_ONCE(lock->owner); @@ -121,21 +121,21 @@ enum rtmutex_chainwalk { RT_MUTEX_FULL_CHAINWALK, }; -static inline void __rt_mutex_basic_init(struct rt_mutex *lock) +static inline void __rt_mutex_base_init(struct rt_mutex_base *lock) { - lock->owner = NULL; raw_spin_lock_init(&lock->wait_lock); lock->waiters = RB_ROOT_CACHED; + lock->owner = NULL; } /* Debug functions */ -static inline void debug_rt_mutex_unlock(struct rt_mutex *lock) +static inline void debug_rt_mutex_unlock(struct rt_mutex_base *lock) { if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) DEBUG_LOCKS_WARN_ON(rt_mutex_owner(lock) != current); } -static inline void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock) +static inline void debug_rt_mutex_proxy_unlock(struct rt_mutex_base *lock) { if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) DEBUG_LOCKS_WARN_ON(!rt_mutex_owner(lock)); @@ -163,7 +163,7 @@ static inline void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) #else /* CONFIG_RT_MUTEXES */ /* Used in rcu/tree_plugin.h */ -static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) +static inline struct task_struct *rt_mutex_owner(struct rt_mutex_base *lock) { return NULL; } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index de1dc3bb7f70..0ff5e4fb933e 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -559,7 +559,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) WRITE_ONCE(rnp->exp_tasks, np); if (IS_ENABLED(CONFIG_RCU_BOOST)) { /* Snapshot ->boost_mtx ownership w/rnp->lock held. */ - drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t; + drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx.rtmutex) == t; if (&t->rcu_node_entry == rnp->boost_tasks) WRITE_ONCE(rnp->boost_tasks, np); } @@ -586,7 +586,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) /* Unboost if we were boosted. */ if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) - rt_mutex_futex_unlock(&rnp->boost_mtx); + rt_mutex_futex_unlock(&rnp->boost_mtx.rtmutex); /* * If this was the last task on the expedited lists, @@ -1083,7 +1083,7 @@ static int rcu_boost(struct rcu_node *rnp) * section. */ t = container_of(tb, struct task_struct, rcu_node_entry); - rt_mutex_init_proxy_locked(&rnp->boost_mtx, t); + rt_mutex_init_proxy_locked(&rnp->boost_mtx.rtmutex, t); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* Lock only for side effect: boosts task t's priority. */ rt_mutex_lock(&rnp->boost_mtx); -- cgit v1.2.3 From 6bc8996add9f82d0153b0be44efe282bd45dc702 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:02 +0200 Subject: locking/rtmutex: Provide rt_mutex_base_is_locked() Provide rt_mutex_base_is_locked(), which will be used for various wrapped locking primitives for RT. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211302.899572818@linutronix.de --- include/linux/rtmutex.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 852740285d71..174419ee58e9 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -13,6 +13,7 @@ #ifndef __LINUX_RT_MUTEX_H #define __LINUX_RT_MUTEX_H +#include #include #include #include @@ -32,6 +33,17 @@ struct rt_mutex_base { .owner = NULL \ } +/** + * rt_mutex_base_is_locked - is the rtmutex locked + * @lock: the mutex to be queried + * + * Returns true if the mutex is locked, false if unlocked. + */ +static inline bool rt_mutex_base_is_locked(struct rt_mutex_base *lock) +{ + return READ_ONCE(lock->owner) != NULL; +} + extern void rt_mutex_base_init(struct rt_mutex_base *rtb); /** -- cgit v1.2.3 From 943f0edb754fac195043c620b44f920e4fb76ec8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:03 +0200 Subject: locking/rt: Add base code for RT rw_semaphore and rwlock On PREEMPT_RT, rw_semaphores and rwlocks are substituted with an rtmutex and a reader count. The implementation is writer unfair, as it is not feasible to do priority inheritance on multiple readers, but experience has shown that real-time workloads are not the typical workloads which are sensitive to writer starvation. The inner workings of rw_semaphores and rwlocks on RT are almost identical except for the task state and signal handling. rw_semaphores are not state preserving over a contention, they are expected to enter and leave with state == TASK_RUNNING. rwlocks have a mechanism to preserve the state of the task at entry and restore it after unblocking taking potential non-lock related wakeups into account. rw_semaphores can also be subject to signal handling interrupting a blocked state, while rwlocks ignore signals. To avoid code duplication, provide a shared implementation which takes the small difference vs. state and signals into account. The code is included into the relevant rw_semaphore/rwlock base code and compiled for each use case separately. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211302.957920571@linutronix.de --- include/linux/rwbase_rt.h | 39 +++++++ kernel/locking/rwbase_rt.c | 263 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 302 insertions(+) create mode 100644 include/linux/rwbase_rt.h create mode 100644 kernel/locking/rwbase_rt.c (limited to 'include/linux') diff --git a/include/linux/rwbase_rt.h b/include/linux/rwbase_rt.h new file mode 100644 index 000000000000..1d264dd08625 --- /dev/null +++ b/include/linux/rwbase_rt.h @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef _LINUX_RWBASE_RT_H +#define _LINUX_RWBASE_RT_H + +#include +#include + +#define READER_BIAS (1U << 31) +#define WRITER_BIAS (1U << 30) + +struct rwbase_rt { + atomic_t readers; + struct rt_mutex_base rtmutex; +}; + +#define __RWBASE_INITIALIZER(name) \ +{ \ + .readers = ATOMIC_INIT(READER_BIAS), \ + .rtmutex = __RT_MUTEX_BASE_INITIALIZER(name.rtmutex), \ +} + +#define init_rwbase_rt(rwbase) \ + do { \ + rt_mutex_base_init(&(rwbase)->rtmutex); \ + atomic_set(&(rwbase)->readers, READER_BIAS); \ + } while (0) + + +static __always_inline bool rw_base_is_locked(struct rwbase_rt *rwb) +{ + return atomic_read(&rwb->readers) != READER_BIAS; +} + +static __always_inline bool rw_base_is_contended(struct rwbase_rt *rwb) +{ + return atomic_read(&rwb->readers) > 0; +} + +#endif /* _LINUX_RWBASE_RT_H */ diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c new file mode 100644 index 000000000000..4ba15088e640 --- /dev/null +++ b/kernel/locking/rwbase_rt.c @@ -0,0 +1,263 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * RT-specific reader/writer semaphores and reader/writer locks + * + * down_write/write_lock() + * 1) Lock rtmutex + * 2) Remove the reader BIAS to force readers into the slow path + * 3) Wait until all readers have left the critical section + * 4) Mark it write locked + * + * up_write/write_unlock() + * 1) Remove the write locked marker + * 2) Set the reader BIAS, so readers can use the fast path again + * 3) Unlock rtmutex, to release blocked readers + * + * down_read/read_lock() + * 1) Try fast path acquisition (reader BIAS is set) + * 2) Take tmutex::wait_lock, which protects the writelocked flag + * 3) If !writelocked, acquire it for read + * 4) If writelocked, block on tmutex + * 5) unlock rtmutex, goto 1) + * + * up_read/read_unlock() + * 1) Try fast path release (reader count != 1) + * 2) Wake the writer waiting in down_write()/write_lock() #3 + * + * down_read/read_lock()#3 has the consequence, that rw semaphores and rw + * locks on RT are not writer fair, but writers, which should be avoided in + * RT tasks (think mmap_sem), are subject to the rtmutex priority/DL + * inheritance mechanism. + * + * It's possible to make the rw primitives writer fair by keeping a list of + * active readers. A blocked writer would force all newly incoming readers + * to block on the rtmutex, but the rtmutex would have to be proxy locked + * for one reader after the other. We can't use multi-reader inheritance + * because there is no way to support that with SCHED_DEADLINE. + * Implementing the one by one reader boosting/handover mechanism is a + * major surgery for a very dubious value. + * + * The risk of writer starvation is there, but the pathological use cases + * which trigger it are not necessarily the typical RT workloads. + * + * Common code shared between RT rw_semaphore and rwlock + */ + +static __always_inline int rwbase_read_trylock(struct rwbase_rt *rwb) +{ + int r; + + /* + * Increment reader count, if sem->readers < 0, i.e. READER_BIAS is + * set. + */ + for (r = atomic_read(&rwb->readers); r < 0;) { + if (likely(atomic_try_cmpxchg(&rwb->readers, &r, r + 1))) + return 1; + } + return 0; +} + +static int __sched __rwbase_read_lock(struct rwbase_rt *rwb, + unsigned int state) +{ + struct rt_mutex_base *rtm = &rwb->rtmutex; + int ret; + + raw_spin_lock_irq(&rtm->wait_lock); + /* + * Allow readers, as long as the writer has not completely + * acquired the semaphore for write. + */ + if (atomic_read(&rwb->readers) != WRITER_BIAS) { + atomic_inc(&rwb->readers); + raw_spin_unlock_irq(&rtm->wait_lock); + return 0; + } + + /* + * Call into the slow lock path with the rtmutex->wait_lock + * held, so this can't result in the following race: + * + * Reader1 Reader2 Writer + * down_read() + * down_write() + * rtmutex_lock(m) + * wait() + * down_read() + * unlock(m->wait_lock) + * up_read() + * wake(Writer) + * lock(m->wait_lock) + * sem->writelocked=true + * unlock(m->wait_lock) + * + * up_write() + * sem->writelocked=false + * rtmutex_unlock(m) + * down_read() + * down_write() + * rtmutex_lock(m) + * wait() + * rtmutex_lock(m) + * + * That would put Reader1 behind the writer waiting on + * Reader2 to call up_read(), which might be unbound. + */ + + /* + * For rwlocks this returns 0 unconditionally, so the below + * !ret conditionals are optimized out. + */ + ret = rwbase_rtmutex_slowlock_locked(rtm, state); + + /* + * On success the rtmutex is held, so there can't be a writer + * active. Increment the reader count and immediately drop the + * rtmutex again. + * + * rtmutex->wait_lock has to be unlocked in any case of course. + */ + if (!ret) + atomic_inc(&rwb->readers); + raw_spin_unlock_irq(&rtm->wait_lock); + if (!ret) + rwbase_rtmutex_unlock(rtm); + return ret; +} + +static __always_inline int rwbase_read_lock(struct rwbase_rt *rwb, + unsigned int state) +{ + if (rwbase_read_trylock(rwb)) + return 0; + + return __rwbase_read_lock(rwb, state); +} + +static void __sched __rwbase_read_unlock(struct rwbase_rt *rwb, + unsigned int state) +{ + struct rt_mutex_base *rtm = &rwb->rtmutex; + struct task_struct *owner; + + raw_spin_lock_irq(&rtm->wait_lock); + /* + * Wake the writer, i.e. the rtmutex owner. It might release the + * rtmutex concurrently in the fast path (due to a signal), but to + * clean up rwb->readers it needs to acquire rtm->wait_lock. The + * worst case which can happen is a spurious wakeup. + */ + owner = rt_mutex_owner(rtm); + if (owner) + wake_up_state(owner, state); + + raw_spin_unlock_irq(&rtm->wait_lock); +} + +static __always_inline void rwbase_read_unlock(struct rwbase_rt *rwb, + unsigned int state) +{ + /* + * rwb->readers can only hit 0 when a writer is waiting for the + * active readers to leave the critical section. + */ + if (unlikely(atomic_dec_and_test(&rwb->readers))) + __rwbase_read_unlock(rwb, state); +} + +static inline void __rwbase_write_unlock(struct rwbase_rt *rwb, int bias, + unsigned long flags) +{ + struct rt_mutex_base *rtm = &rwb->rtmutex; + + atomic_add(READER_BIAS - bias, &rwb->readers); + raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); + rwbase_rtmutex_unlock(rtm); +} + +static inline void rwbase_write_unlock(struct rwbase_rt *rwb) +{ + struct rt_mutex_base *rtm = &rwb->rtmutex; + unsigned long flags; + + raw_spin_lock_irqsave(&rtm->wait_lock, flags); + __rwbase_write_unlock(rwb, WRITER_BIAS, flags); +} + +static inline void rwbase_write_downgrade(struct rwbase_rt *rwb) +{ + struct rt_mutex_base *rtm = &rwb->rtmutex; + unsigned long flags; + + raw_spin_lock_irqsave(&rtm->wait_lock, flags); + /* Release it and account current as reader */ + __rwbase_write_unlock(rwb, WRITER_BIAS - 1, flags); +} + +static int __sched rwbase_write_lock(struct rwbase_rt *rwb, + unsigned int state) +{ + struct rt_mutex_base *rtm = &rwb->rtmutex; + unsigned long flags; + + /* Take the rtmutex as a first step */ + if (rwbase_rtmutex_lock_state(rtm, state)) + return -EINTR; + + /* Force readers into slow path */ + atomic_sub(READER_BIAS, &rwb->readers); + + raw_spin_lock_irqsave(&rtm->wait_lock, flags); + /* + * set_current_state() for rw_semaphore + * current_save_and_set_rtlock_wait_state() for rwlock + */ + rwbase_set_and_save_current_state(state); + + /* Block until all readers have left the critical section. */ + for (; atomic_read(&rwb->readers);) { + /* Optimized out for rwlocks */ + if (rwbase_signal_pending_state(state, current)) { + __set_current_state(TASK_RUNNING); + __rwbase_write_unlock(rwb, 0, flags); + return -EINTR; + } + raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); + + /* + * Schedule and wait for the readers to leave the critical + * section. The last reader leaving it wakes the waiter. + */ + if (atomic_read(&rwb->readers) != 0) + rwbase_schedule(); + set_current_state(state); + raw_spin_lock_irqsave(&rtm->wait_lock, flags); + } + + atomic_set(&rwb->readers, WRITER_BIAS); + rwbase_restore_current_state(); + raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); + return 0; +} + +static inline int rwbase_write_trylock(struct rwbase_rt *rwb) +{ + struct rt_mutex_base *rtm = &rwb->rtmutex; + unsigned long flags; + + if (!rwbase_rtmutex_trylock(rtm)) + return 0; + + atomic_sub(READER_BIAS, &rwb->readers); + + raw_spin_lock_irqsave(&rtm->wait_lock, flags); + if (!atomic_read(&rwb->readers)) { + atomic_set(&rwb->readers, WRITER_BIAS); + raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); + return 1; + } + __rwbase_write_unlock(rwb, 0, flags); + return 0; +} -- cgit v1.2.3 From 42254105dfe871a0dc4f9d376106aeb010e54341 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:05 +0200 Subject: locking/rwsem: Add rtmutex based R/W semaphore implementation The RT specific R/W semaphore implementation used to restrict the number of readers to one, because a writer cannot block on multiple readers and inherit its priority or budget. The single reader restricting was painful in various ways: - Performance bottleneck for multi-threaded applications in the page fault path (mmap sem) - Progress blocker for drivers which are carefully crafted to avoid the potential reader/writer deadlock in mainline. The analysis of the writer code paths shows that properly written RT tasks should not take them. Syscalls like mmap(), file access which take mmap sem write locked have unbound latencies, which are completely unrelated to mmap sem. Other R/W sem users like graphics drivers are not suitable for RT tasks either. So there is little risk to hurt RT tasks when the RT rwsem implementation is done in the following way: - Allow concurrent readers - Make writers block until the last reader left the critical section. This blocking is not subject to priority/budget inheritance. - Readers blocked on a writer inherit their priority/budget in the normal way. There is a drawback with this scheme: R/W semaphores become writer unfair though the applications which have triggered writer starvation (mostly on mmap_sem) in the past are not really the typical workloads running on a RT system. So while it's unlikely to hit writer starvation, it's possible. If there are unexpected workloads on RT systems triggering it, the problem has to be revisited. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211303.016885947@linutronix.de --- include/linux/rwsem.h | 78 ++++++++++++++++++++++++++++++----- kernel/locking/rwsem.c | 108 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 176 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index a66038d88878..426e98e0b675 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -16,6 +16,19 @@ #include #include #include + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define __RWSEM_DEP_MAP_INIT(lockname) \ + .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_SLEEP, \ + }, +#else +# define __RWSEM_DEP_MAP_INIT(lockname) +#endif + +#ifndef CONFIG_PREEMPT_RT + #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #include #endif @@ -64,16 +77,6 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem) /* Common initializer macros and functions */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __RWSEM_DEP_MAP_INIT(lockname) \ - .dep_map = { \ - .name = #lockname, \ - .wait_type_inner = LD_WAIT_SLEEP, \ - }, -#else -# define __RWSEM_DEP_MAP_INIT(lockname) -#endif - #ifdef CONFIG_DEBUG_RWSEMS # define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname, #else @@ -119,6 +122,61 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem) return !list_empty(&sem->wait_list); } +#else /* !CONFIG_PREEMPT_RT */ + +#include + +struct rw_semaphore { + struct rwbase_rt rwbase; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __RWSEM_INITIALIZER(name) \ + { \ + .rwbase = __RWBASE_INITIALIZER(name), \ + __RWSEM_DEP_MAP_INIT(name) \ + } + +#define DECLARE_RWSEM(lockname) \ + struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void __rwsem_init(struct rw_semaphore *rwsem, const char *name, + struct lock_class_key *key); +#else +static inline void __rwsem_init(struct rw_semaphore *rwsem, const char *name, + struct lock_class_key *key) +{ +} +#endif + +#define init_rwsem(sem) \ +do { \ + static struct lock_class_key __key; \ + \ + init_rwbase_rt(&(sem)->rwbase); \ + __rwsem_init((sem), #sem, &__key); \ +} while (0) + +static __always_inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return rw_base_is_locked(&sem->rwbase); +} + +static __always_inline int rwsem_is_contended(struct rw_semaphore *sem) +{ + return rw_base_is_contended(&sem->rwbase); +} + +#endif /* CONFIG_PREEMPT_RT */ + +/* + * The functions below are the same for all rwsem implementations including + * the RT specific variant. + */ + /* * lock for reading */ diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 8a595b60ca9b..c017f9f2874b 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -28,6 +28,7 @@ #include #include +#ifndef CONFIG_PREEMPT_RT #include "lock_events.h" /* @@ -1344,6 +1345,113 @@ static inline void __downgrade_write(struct rw_semaphore *sem) rwsem_downgrade_wake(sem); } +#else /* !CONFIG_PREEMPT_RT */ + +#include "rtmutex.c" + +#define rwbase_set_and_save_current_state(state) \ + set_current_state(state) + +#define rwbase_restore_current_state() \ + __set_current_state(TASK_RUNNING) + +#define rwbase_rtmutex_lock_state(rtm, state) \ + __rt_mutex_lock(rtm, state) + +#define rwbase_rtmutex_slowlock_locked(rtm, state) \ + __rt_mutex_slowlock_locked(rtm, state) + +#define rwbase_rtmutex_unlock(rtm) \ + __rt_mutex_unlock(rtm) + +#define rwbase_rtmutex_trylock(rtm) \ + __rt_mutex_trylock(rtm) + +#define rwbase_signal_pending_state(state, current) \ + signal_pending_state(state, current) + +#define rwbase_schedule() \ + schedule() + +#include "rwbase_rt.c" + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __rwsem_init(struct rw_semaphore *sem, const char *name, + struct lock_class_key *key) +{ + debug_check_no_locks_freed((void *)sem, sizeof(*sem)); + lockdep_init_map_wait(&sem->dep_map, name, key, 0, LD_WAIT_SLEEP); +} +EXPORT_SYMBOL(__rwsem_init); +#endif + +static inline void __down_read(struct rw_semaphore *sem) +{ + rwbase_read_lock(&sem->rwbase, TASK_UNINTERRUPTIBLE); +} + +static inline int __down_read_interruptible(struct rw_semaphore *sem) +{ + return rwbase_read_lock(&sem->rwbase, TASK_INTERRUPTIBLE); +} + +static inline int __down_read_killable(struct rw_semaphore *sem) +{ + return rwbase_read_lock(&sem->rwbase, TASK_KILLABLE); +} + +static inline int __down_read_trylock(struct rw_semaphore *sem) +{ + return rwbase_read_trylock(&sem->rwbase); +} + +static inline void __up_read(struct rw_semaphore *sem) +{ + rwbase_read_unlock(&sem->rwbase, TASK_NORMAL); +} + +static inline void __sched __down_write(struct rw_semaphore *sem) +{ + rwbase_write_lock(&sem->rwbase, TASK_UNINTERRUPTIBLE); +} + +static inline int __sched __down_write_killable(struct rw_semaphore *sem) +{ + return rwbase_write_lock(&sem->rwbase, TASK_KILLABLE); +} + +static inline int __down_write_trylock(struct rw_semaphore *sem) +{ + return rwbase_write_trylock(&sem->rwbase); +} + +static inline void __up_write(struct rw_semaphore *sem) +{ + rwbase_write_unlock(&sem->rwbase); +} + +static inline void __downgrade_write(struct rw_semaphore *sem) +{ + rwbase_write_downgrade(&sem->rwbase); +} + +/* Debug stubs for the common API */ +#define DEBUG_RWSEMS_WARN_ON(c, sem) + +static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem, + struct task_struct *owner) +{ +} + +static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem) +{ + int count = atomic_read(&sem->rwbase.readers); + + return count < 0 && count != READER_BIAS; +} + +#endif /* CONFIG_PREEMPT_RT */ + /* * lock for reading */ -- cgit v1.2.3 From 4f084ca74c3f0eb321ab50e69afd27c8fcb96a99 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:14 +0200 Subject: locking/spinlock: Split the lock types header, and move the raw types into Move raw_spinlock into its own file. Prepare for RT 'sleeping spinlocks', to avoid header recursion, as RT locks require rtmutex.h, which in turn requires the raw spinlock types. No functional change. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211303.371269088@linutronix.de --- include/linux/rwlock_types.h | 4 +++ include/linux/spinlock.h | 4 +++ include/linux/spinlock_types.h | 59 +--------------------------------- include/linux/spinlock_types_raw.h | 65 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 74 insertions(+), 58 deletions(-) create mode 100644 include/linux/spinlock_types_raw.h (limited to 'include/linux') diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h index 3bd03e18061c..0ad226b5d8fd 100644 --- a/include/linux/rwlock_types.h +++ b/include/linux/rwlock_types.h @@ -1,6 +1,10 @@ #ifndef __LINUX_RWLOCK_TYPES_H #define __LINUX_RWLOCK_TYPES_H +#if !defined(__LINUX_SPINLOCK_TYPES_H) +# error "Do not include directly, include spinlock_types.h" +#endif + /* * include/linux/rwlock_types.h - generic rwlock type definitions * and initializers diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 79897841a2cc..5803b56622a8 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -12,6 +12,8 @@ * asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the * initializers * + * linux/spinlock_types_raw: + * The raw types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * @@ -31,6 +33,8 @@ * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * + * linux/spinlock_types_raw: + * The raw RT types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index b981caafe8bf..42be1116e051 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -9,64 +9,7 @@ * Released under the General Public License (GPL). */ -#if defined(CONFIG_SMP) -# include -#else -# include -#endif - -#include - -typedef struct raw_spinlock { - arch_spinlock_t raw_lock; -#ifdef CONFIG_DEBUG_SPINLOCK - unsigned int magic, owner_cpu; - void *owner; -#endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -} raw_spinlock_t; - -#define SPINLOCK_MAGIC 0xdead4ead - -#define SPINLOCK_OWNER_INIT ((void *)-1L) - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define RAW_SPIN_DEP_MAP_INIT(lockname) \ - .dep_map = { \ - .name = #lockname, \ - .wait_type_inner = LD_WAIT_SPIN, \ - } -# define SPIN_DEP_MAP_INIT(lockname) \ - .dep_map = { \ - .name = #lockname, \ - .wait_type_inner = LD_WAIT_CONFIG, \ - } -#else -# define RAW_SPIN_DEP_MAP_INIT(lockname) -# define SPIN_DEP_MAP_INIT(lockname) -#endif - -#ifdef CONFIG_DEBUG_SPINLOCK -# define SPIN_DEBUG_INIT(lockname) \ - .magic = SPINLOCK_MAGIC, \ - .owner_cpu = -1, \ - .owner = SPINLOCK_OWNER_INIT, -#else -# define SPIN_DEBUG_INIT(lockname) -#endif - -#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ - { \ - .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ - SPIN_DEBUG_INIT(lockname) \ - RAW_SPIN_DEP_MAP_INIT(lockname) } - -#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ - (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) - -#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) +#include typedef struct spinlock { union { diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h new file mode 100644 index 000000000000..a8a4330d7b78 --- /dev/null +++ b/include/linux/spinlock_types_raw.h @@ -0,0 +1,65 @@ +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H +#define __LINUX_SPINLOCK_TYPES_RAW_H + +#include + +#if defined(CONFIG_SMP) +# include +#else +# include +#endif + +#include + +typedef struct raw_spinlock { + arch_spinlock_t raw_lock; +#ifdef CONFIG_DEBUG_SPINLOCK + unsigned int magic, owner_cpu; + void *owner; +#endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} raw_spinlock_t; + +#define SPINLOCK_MAGIC 0xdead4ead + +#define SPINLOCK_OWNER_INIT ((void *)-1L) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define RAW_SPIN_DEP_MAP_INIT(lockname) \ + .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_SPIN, \ + } +# define SPIN_DEP_MAP_INIT(lockname) \ + .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_CONFIG, \ + } +#else +# define RAW_SPIN_DEP_MAP_INIT(lockname) +# define SPIN_DEP_MAP_INIT(lockname) +#endif + +#ifdef CONFIG_DEBUG_SPINLOCK +# define SPIN_DEBUG_INIT(lockname) \ + .magic = SPINLOCK_MAGIC, \ + .owner_cpu = -1, \ + .owner = SPINLOCK_OWNER_INIT, +#else +# define SPIN_DEBUG_INIT(lockname) +#endif + +#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ +{ \ + .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ + SPIN_DEBUG_INIT(lockname) \ + RAW_SPIN_DEP_MAP_INIT(lockname) } + +#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ + (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) + +#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) + +#endif /* __LINUX_SPINLOCK_TYPES_RAW_H */ -- cgit v1.2.3 From a403abbdc715986760821e67731d60ff65bde4bd Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 15 Aug 2021 23:28:16 +0200 Subject: locking/rtmutex: Prevent future include recursion hell rtmutex only needs raw_spinlock_t, but it includes spinlock_types.h, which is not a problem on an non RT enabled kernel. RT kernels substitute regular spinlocks with 'sleeping' spinlocks, which are based on rtmutexes, and therefore must be able to include rtmutex.h. Include instead. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211303.428224188@linutronix.de --- include/linux/rtmutex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 174419ee58e9..4be97aee02bf 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -16,7 +16,7 @@ #include #include #include -#include +#include extern int max_lock_depth; /* for sysctl */ -- cgit v1.2.3 From cbcebf5bd3d056d7a0ae332118888d867ac346c0 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 15 Aug 2021 23:28:17 +0200 Subject: locking/lockdep: Reduce header dependencies in The inclusion of printk.h leads to a circular dependency if spinlock_t is based on rtmutexes on RT enabled kernels. Include only atomic.h (xchg()) and cache.h (__read_mostly) which is all what debug_locks.h requires. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211303.484161136@linutronix.de --- include/linux/debug_locks.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index edb5c186b0b7..3f49e65169c6 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -3,8 +3,7 @@ #define __LINUX_DEBUG_LOCKING_H #include -#include -#include +#include struct task_struct; -- cgit v1.2.3 From 089050cafa10f408c9e18ad53965db839b894840 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 15 Aug 2021 23:28:19 +0200 Subject: rbtree: Split out the rbtree type definitions into So we have this header dependency problem on RT: - needs the definition of 'struct rb_root_cached'. - includes , which includes . That works nicely for non-RT enabled kernels, but on RT enabled kernels spinlocks are based on rtmutexes, which creates another circular header dependency, as will require . Split out the type definitions and move them into their own header file so the rtmutex header can include just those. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211303.542123501@linutronix.de --- include/linux/rbtree.h | 31 ++----------------------------- include/linux/rbtree_types.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+), 29 deletions(-) create mode 100644 include/linux/rbtree_types.h (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index d31ecaf4fdd3..235047d7a1b5 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -17,24 +17,14 @@ #ifndef _LINUX_RBTREE_H #define _LINUX_RBTREE_H +#include + #include #include #include -struct rb_node { - unsigned long __rb_parent_color; - struct rb_node *rb_right; - struct rb_node *rb_left; -} __attribute__((aligned(sizeof(long)))); - /* The alignment might seem pointless, but allegedly CRIS needs it */ - -struct rb_root { - struct rb_node *rb_node; -}; - #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) -#define RB_ROOT (struct rb_root) { NULL, } #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) @@ -112,23 +102,6 @@ static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent typeof(*pos), field); 1; }); \ pos = n) -/* - * Leftmost-cached rbtrees. - * - * We do not cache the rightmost node based on footprint - * size vs number of potential users that could benefit - * from O(1) rb_last(). Just not worth it, users that want - * this feature can always implement the logic explicitly. - * Furthermore, users that want to cache both pointers may - * find it a bit asymmetric, but that's ok. - */ -struct rb_root_cached { - struct rb_root rb_root; - struct rb_node *rb_leftmost; -}; - -#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } - /* Same as rb_first(), but O(1) */ #define rb_first_cached(root) (root)->rb_leftmost diff --git a/include/linux/rbtree_types.h b/include/linux/rbtree_types.h new file mode 100644 index 000000000000..45b6ecde3665 --- /dev/null +++ b/include/linux/rbtree_types.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_RBTREE_TYPES_H +#define _LINUX_RBTREE_TYPES_H + +struct rb_node { + unsigned long __rb_parent_color; + struct rb_node *rb_right; + struct rb_node *rb_left; +} __attribute__((aligned(sizeof(long)))); +/* The alignment might seem pointless, but allegedly CRIS needs it */ + +struct rb_root { + struct rb_node *rb_node; +}; + +/* + * Leftmost-cached rbtrees. + * + * We do not cache the rightmost node based on footprint + * size vs number of potential users that could benefit + * from O(1) rb_last(). Just not worth it, users that want + * this feature can always implement the logic explicitly. + * Furthermore, users that want to cache both pointers may + * find it a bit asymmetric, but that's ok. + */ +struct rb_root_cached { + struct rb_root rb_root; + struct rb_node *rb_leftmost; +}; + +#define RB_ROOT (struct rb_root) { NULL, } +#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } + +#endif -- cgit v1.2.3 From e4e17af3b7f8841279b5a429de14907e26845c39 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 15 Aug 2021 23:28:20 +0200 Subject: locking/rtmutex: Reduce header dependencies, only include We have the following header dependency problem on RT: - needs the definition of 'struct rb_root_cached'. - includes , which includes That works nicely for non-RT enabled kernels, but on RT enabled kernels spinlocks are based on rtmutexes, which creates another circular header dependency as will require . Include instead. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211303.598003167@linutronix.de --- include/linux/rtmutex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 4be97aee02bf..9deedfeec2b1 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -15,7 +15,7 @@ #include #include -#include +#include #include extern int max_lock_depth; /* for sysctl */ -- cgit v1.2.3 From 051790eecc03aff6978763791d38c1daea94c2f8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:22 +0200 Subject: locking/spinlock: Provide RT specific spinlock_t RT replaces spinlocks with a simple wrapper around an rtmutex, which turns spinlocks on RT into 'sleeping' spinlocks. The actual implementation of the spinlock API differs from a regular rtmutex, as it does neither handle timeouts nor signals and it is state preserving across the lock operation. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211303.654230709@linutronix.de --- include/linux/spinlock_types.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index 42be1116e051..8a9aadbaf293 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -11,6 +11,9 @@ #include +#ifndef CONFIG_PREEMPT_RT + +/* Non PREEMPT_RT kernels map spinlock to raw_spinlock */ typedef struct spinlock { union { struct raw_spinlock rlock; @@ -39,6 +42,29 @@ typedef struct spinlock { #define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) +#else /* !CONFIG_PREEMPT_RT */ + +/* PREEMPT_RT kernels map spinlock to rt_mutex */ +#include + +typedef struct spinlock { + struct rt_mutex_base lock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} spinlock_t; + +#define __SPIN_LOCK_UNLOCKED(name) \ + { \ + .lock = __RT_MUTEX_BASE_INITIALIZER(name.lock), \ + SPIN_DEP_MAP_INIT(name) \ + } + +#define DEFINE_SPINLOCK(name) \ + spinlock_t name = __SPIN_LOCK_UNLOCKED(name) + +#endif /* CONFIG_PREEMPT_RT */ + #include #endif /* __LINUX_SPINLOCK_TYPES_H */ -- cgit v1.2.3 From 342a93247e0837101f27bbcca26f402902df98dc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:23 +0200 Subject: locking/spinlock: Provide RT variant header: Provide the necessary wrappers around the actual rtmutex based spinlock implementation. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211303.712897671@linutronix.de --- include/linux/spinlock.h | 11 ++- include/linux/spinlock_api_smp.h | 3 + include/linux/spinlock_rt.h | 149 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 162 insertions(+), 1 deletion(-) create mode 100644 include/linux/spinlock_rt.h (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 5803b56622a8..45310ea1b1d7 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -312,8 +312,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) 1 : ({ local_irq_restore(flags); 0; }); \ }) -/* Include rwlock functions */ +#ifndef CONFIG_PREEMPT_RT +/* Include rwlock functions for !RT */ #include +#endif /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: @@ -324,6 +326,9 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) # include #endif +/* Non PREEMPT_RT kernel, map to raw spinlocks: */ +#ifndef CONFIG_PREEMPT_RT + /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ @@ -458,6 +463,10 @@ static __always_inline int spin_is_contended(spinlock_t *lock) #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) +#else /* !CONFIG_PREEMPT_RT */ +# include +#endif /* CONFIG_PREEMPT_RT */ + /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 19a9be9d97ee..6b8e1a0b137b 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -187,6 +187,9 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock) return 0; } +/* PREEMPT_RT has its own rwlock implementation */ +#ifndef CONFIG_PREEMPT_RT #include +#endif #endif /* __LINUX_SPINLOCK_API_SMP_H */ diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h new file mode 100644 index 000000000000..21228d3362f7 --- /dev/null +++ b/include/linux/spinlock_rt.h @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_SPINLOCK_RT_H +#define __LINUX_SPINLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_H +#error Do not include directly. Use spinlock.h +#endif + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void __rt_spin_lock_init(spinlock_t *lock, const char *name, + struct lock_class_key *key); +#else +static inline void __rt_spin_lock_init(spinlock_t *lock, const char *name, + struct lock_class_key *key) +{ +} +#endif + +#define spin_lock_init(slock) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_base_init(&(slock)->lock); \ + __rt_spin_lock_init(slock, #slock, &__key); \ +} while (0) + +extern void rt_spin_lock(spinlock_t *lock); +extern void rt_spin_lock_nested(spinlock_t *lock, int subclass); +extern void rt_spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *nest_lock); +extern void rt_spin_unlock(spinlock_t *lock); +extern void rt_spin_lock_unlock(spinlock_t *lock); +extern int rt_spin_trylock_bh(spinlock_t *lock); +extern int rt_spin_trylock(spinlock_t *lock); + +static __always_inline void spin_lock(spinlock_t *lock) +{ + rt_spin_lock(lock); +} + +#ifdef CONFIG_LOCKDEP +# define __spin_lock_nested(lock, subclass) \ + rt_spin_lock_nested(lock, subclass) + +# define __spin_lock_nest_lock(lock, nest_lock) \ + do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ + rt_spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ + } while (0) +# define __spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + __spin_lock_nested(lock, subclass); \ + } while (0) + +#else + /* + * Always evaluate the 'subclass' argument to avoid that the compiler + * warns about set-but-not-used variables when building with + * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1. + */ +# define __spin_lock_nested(lock, subclass) spin_lock(((void)(subclass), (lock))) +# define __spin_lock_nest_lock(lock, subclass) spin_lock(((void)(subclass), (lock))) +# define __spin_lock_irqsave_nested(lock, flags, subclass) \ + spin_lock_irqsave(((void)(subclass), (lock)), flags) +#endif + +#define spin_lock_nested(lock, subclass) \ + __spin_lock_nested(lock, subclass) + +#define spin_lock_nest_lock(lock, nest_lock) \ + __spin_lock_nest_lock(lock, nest_lock) + +#define spin_lock_irqsave_nested(lock, flags, subclass) \ + __spin_lock_irqsave_nested(lock, flags, subclass) + +static __always_inline void spin_lock_bh(spinlock_t *lock) +{ + /* Investigate: Drop bh when blocking ? */ + local_bh_disable(); + rt_spin_lock(lock); +} + +static __always_inline void spin_lock_irq(spinlock_t *lock) +{ + rt_spin_lock(lock); +} + +#define spin_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + spin_lock(lock); \ + } while (0) + +static __always_inline void spin_unlock(spinlock_t *lock) +{ + rt_spin_unlock(lock); +} + +static __always_inline void spin_unlock_bh(spinlock_t *lock) +{ + rt_spin_unlock(lock); + local_bh_enable(); +} + +static __always_inline void spin_unlock_irq(spinlock_t *lock) +{ + rt_spin_unlock(lock); +} + +static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, + unsigned long flags) +{ + rt_spin_unlock(lock); +} + +#define spin_trylock(lock) \ + __cond_lock(lock, rt_spin_trylock(lock)) + +#define spin_trylock_bh(lock) \ + __cond_lock(lock, rt_spin_trylock_bh(lock)) + +#define spin_trylock_irq(lock) \ + __cond_lock(lock, rt_spin_trylock(lock)) + +#define __spin_trylock_irqsave(lock, flags) \ +({ \ + int __locked; \ + \ + typecheck(unsigned long, flags); \ + flags = 0; \ + __locked = spin_trylock(lock); \ + __locked; \ +}) + +#define spin_trylock_irqsave(lock, flags) \ + __cond_lock(lock, __spin_trylock_irqsave(lock, flags)) + +#define spin_is_contended(lock) (((void)(lock), 0)) + +static inline int spin_is_locked(spinlock_t *lock) +{ + return rt_mutex_base_is_locked(&lock->lock); +} + +#define assert_spin_locked(lock) BUG_ON(!spin_is_locked(lock)) + +#endif -- cgit v1.2.3 From 2f0f88f42f2eab0421ed37d7494de9124fdf0d34 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 1 Jul 2021 10:03:10 -0400 Subject: SUNRPC: Add svc_rqst_replace_page() API Replacing a page in rq_pages[] requires a get_page(), which is a bus-locked operation, and a put_page(), which can be even more costly. To reduce the cost of replacing a page in rq_pages[], batch the put_page() operations by collecting "freed" pages in a pagevec, and then release those pages when the pagevec is full. This pagevec is also emptied when each RPC completes. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 4 ++++ net/sunrpc/svc.c | 21 +++++++++++++++++++++ net/sunrpc/svc_xprt.c | 3 +++ 3 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index e91d51ea028b..ab9afbf0a0d8 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -19,6 +19,7 @@ #include #include #include +#include /* statistics for svc_pool structures */ struct svc_pool_stats { @@ -256,6 +257,7 @@ struct svc_rqst { struct page * *rq_next_page; /* next reply page to use */ struct page * *rq_page_end; /* one past the last page */ + struct pagevec rq_pvec; struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */ struct bio_vec rq_bvec[RPCSVC_MAXPAGES]; @@ -502,6 +504,8 @@ struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node); +void svc_rqst_replace_page(struct svc_rqst *rqstp, + struct page *page); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); unsigned int svc_pool_map_get(void); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 0de918cb3d90..d2d412d43827 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -838,6 +838,27 @@ svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrser } EXPORT_SYMBOL_GPL(svc_set_num_threads_sync); +/** + * svc_rqst_replace_page - Replace one page in rq_pages[] + * @rqstp: svc_rqst with pages to replace + * @page: replacement page + * + * When replacing a page in rq_pages, batch the release of the + * replaced pages to avoid hammering the page allocator. + */ +void svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page) +{ + if (*rqstp->rq_next_page) { + if (!pagevec_space(&rqstp->rq_pvec)) + __pagevec_release(&rqstp->rq_pvec); + pagevec_add(&rqstp->rq_pvec, *rqstp->rq_next_page); + } + + get_page(page); + *(rqstp->rq_next_page++) = page; +} +EXPORT_SYMBOL_GPL(svc_rqst_replace_page); + /* * Called from a server thread as it's exiting. Caller must hold the "service * mutex" for the service. diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index d66a8e44a1ae..682058a5ec13 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -539,6 +539,7 @@ static void svc_xprt_release(struct svc_rqst *rqstp) kfree(rqstp->rq_deferred); rqstp->rq_deferred = NULL; + pagevec_release(&rqstp->rq_pvec); svc_free_res_pages(rqstp); rqstp->rq_res.page_len = 0; rqstp->rq_res.page_base = 0; @@ -664,6 +665,8 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) struct xdr_buf *arg = &rqstp->rq_arg; unsigned long pages, filled; + pagevec_init(&rqstp->rq_pvec); + pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT; if (pages > RPCSVC_MAXPAGES) { pr_warn_once("svc: warning: pages=%lu > RPCSVC_MAXPAGES=%lu\n", -- cgit v1.2.3 From 6c8c84f525100a1cade5698320b4abe43062e159 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 7 Jul 2021 14:57:28 -0400 Subject: svcrdma: Fewer calls to wake_up() in Send completion handler Because wake_up() takes an IRQ-safe lock, it can be expensive, especially to call inside of a single-threaded completion handler. What's more, the Send wait queue almost never has waiters, so most of the time, this is an expensive no-op. As always, the goal is to reduce the average overhead of each completion, because a transport's completion handlers are single- threaded on one CPU core. This change reduces CPU utilization of the Send completion thread by 2-3% on my server. Signed-off-by: Chuck Lever Reviewed-By: Tom Talpey --- include/linux/sunrpc/svc_rdma.h | 1 + net/sunrpc/xprtrdma/svc_rdma_rw.c | 7 ++----- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 18 +++++++++++++++--- 3 files changed, 18 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 3184465de3a0..57c60ffe76dd 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -207,6 +207,7 @@ extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *sctxt, struct svc_rdma_recv_ctxt *rctxt, int status); +extern void svc_rdma_wake_send_waiters(struct svcxprt_rdma *rdma, int avail); extern int svc_rdma_sendto(struct svc_rqst *); extern int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset, unsigned int length); diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 1e651447dc4e..3d1b119f6e3e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -248,8 +248,7 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) trace_svcrdma_wc_write(wc, &cc->cc_cid); - atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); - wake_up(&rdma->sc_send_wait); + svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount); if (unlikely(wc->status != IB_WC_SUCCESS)) svc_xprt_deferred_close(&rdma->sc_xprt); @@ -304,9 +303,7 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) trace_svcrdma_wc_read(wc, &cc->cc_cid); - atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); - wake_up(&rdma->sc_send_wait); - + svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount); cc->cc_status = wc->status; complete(&cc->cc_done); return; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index d6bbafb773e1..fba2ee4eb607 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -258,6 +258,20 @@ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, spin_unlock(&rdma->sc_send_lock); } +/** + * svc_rdma_wake_send_waiters - manage Send Queue accounting + * @rdma: controlling transport + * @avail: Number of additional SQEs that are now available + * + */ +void svc_rdma_wake_send_waiters(struct svcxprt_rdma *rdma, int avail) +{ + atomic_add(avail, &rdma->sc_sq_avail); + smp_mb__after_atomic(); + if (unlikely(waitqueue_active(&rdma->sc_send_wait))) + wake_up(&rdma->sc_send_wait); +} + /** * svc_rdma_wc_send - Invoked by RDMA provider for each polled Send WC * @cq: Completion Queue context @@ -275,11 +289,9 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) trace_svcrdma_wc_send(wc, &ctxt->sc_cid); + svc_rdma_wake_send_waiters(rdma, 1); complete(&ctxt->sc_done); - atomic_inc(&rdma->sc_sq_avail); - wake_up(&rdma->sc_send_wait); - if (unlikely(wc->status != IB_WC_SUCCESS)) svc_xprt_deferred_close(&rdma->sc_xprt); } -- cgit v1.2.3 From b6c2bfea096ba22583f1071c10ce0745804b9b95 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 9 Feb 2021 10:32:20 -0500 Subject: svcrdma: Relieve contention on sc_send_lock. /proc/lock_stat indicates the the sc_send_lock is heavily contended when the server is under load from a single client. To address this, convert the send_ctxt free list to an llist. Returning an item to the send_ctxt cache is now waitless, which reduces the instruction path length in the single-threaded Send handler (svc_rdma_wc_send). The goal is to enable the ib_comp_wq worker to handle a higher RPC/RDMA Send completion rate given the same CPU resources. This change reduces CPU utilization of Send completion by 2-3% on my server. Signed-off-by: Chuck Lever Reviewed-By: Tom Talpey --- include/linux/sunrpc/svc_rdma.h | 4 ++-- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 23 ++++++++--------------- net/sunrpc/xprtrdma/svc_rdma_transport.c | 2 +- 3 files changed, 11 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 57c60ffe76dd..5f8d5af6556c 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -90,7 +90,7 @@ struct svcxprt_rdma { struct ib_pd *sc_pd; spinlock_t sc_send_lock; - struct list_head sc_send_ctxts; + struct llist_head sc_send_ctxts; spinlock_t sc_rw_ctxt_lock; struct list_head sc_rw_ctxts; @@ -150,7 +150,7 @@ struct svc_rdma_recv_ctxt { }; struct svc_rdma_send_ctxt { - struct list_head sc_list; + struct llist_node sc_node; struct rpc_rdma_cid sc_cid; struct ib_send_wr sc_send_wr; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index fba2ee4eb607..599021b2391d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -113,13 +113,6 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc); -static inline struct svc_rdma_send_ctxt * -svc_rdma_next_send_ctxt(struct list_head *list) -{ - return list_first_entry_or_null(list, struct svc_rdma_send_ctxt, - sc_list); -} - static void svc_rdma_send_cid_init(struct svcxprt_rdma *rdma, struct rpc_rdma_cid *cid) { @@ -182,9 +175,10 @@ fail0: void svc_rdma_send_ctxts_destroy(struct svcxprt_rdma *rdma) { struct svc_rdma_send_ctxt *ctxt; + struct llist_node *node; - while ((ctxt = svc_rdma_next_send_ctxt(&rdma->sc_send_ctxts))) { - list_del(&ctxt->sc_list); + while ((node = llist_del_first(&rdma->sc_send_ctxts)) != NULL) { + ctxt = llist_entry(node, struct svc_rdma_send_ctxt, sc_node); ib_dma_unmap_single(rdma->sc_pd->device, ctxt->sc_sges[0].addr, rdma->sc_max_req_size, @@ -204,12 +198,13 @@ void svc_rdma_send_ctxts_destroy(struct svcxprt_rdma *rdma) struct svc_rdma_send_ctxt *svc_rdma_send_ctxt_get(struct svcxprt_rdma *rdma) { struct svc_rdma_send_ctxt *ctxt; + struct llist_node *node; spin_lock(&rdma->sc_send_lock); - ctxt = svc_rdma_next_send_ctxt(&rdma->sc_send_ctxts); - if (!ctxt) + node = llist_del_first(&rdma->sc_send_ctxts); + if (!node) goto out_empty; - list_del(&ctxt->sc_list); + ctxt = llist_entry(node, struct svc_rdma_send_ctxt, sc_node); spin_unlock(&rdma->sc_send_lock); out: @@ -253,9 +248,7 @@ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, ctxt->sc_sges[i].length); } - spin_lock(&rdma->sc_send_lock); - list_add(&ctxt->sc_list, &rdma->sc_send_ctxts); - spin_unlock(&rdma->sc_send_lock); + llist_add(&ctxt->sc_node, &rdma->sc_send_ctxts); } /** diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index d94b7759ada1..99474078c304 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -136,7 +136,7 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv, svc_xprt_init(net, &svc_rdma_class, &cma_xprt->sc_xprt, serv); INIT_LIST_HEAD(&cma_xprt->sc_accept_q); INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q); - INIT_LIST_HEAD(&cma_xprt->sc_send_ctxts); + init_llist_head(&cma_xprt->sc_send_ctxts); init_llist_head(&cma_xprt->sc_recv_ctxts); INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts); init_waitqueue_head(&cma_xprt->sc_send_wait); -- cgit v1.2.3 From 07a92d009f0b1557d3d58905ce18821a483be2e1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 8 Feb 2021 15:33:16 -0500 Subject: svcrdma: Convert rdma->sc_rw_ctxts to llist Relieve contention on sc_rw_ctxt_lock by converting rdma->sc_rw_ctxts to an llist. The goal is to reduce the average overhead of Send completions, because a transport's completion handlers are single-threaded on one CPU core. This change reduces CPU utilization of each Send completion by 2-3% on my server. Signed-off-by: Chuck Lever Reviewed-By: Tom Talpey --- include/linux/sunrpc/svc_rdma.h | 2 +- net/sunrpc/xprtrdma/svc_rdma_rw.c | 49 +++++++++++++++++++++++--------- net/sunrpc/xprtrdma/svc_rdma_transport.c | 2 +- 3 files changed, 37 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 5f8d5af6556c..24aa159d29a7 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -92,7 +92,7 @@ struct svcxprt_rdma { spinlock_t sc_send_lock; struct llist_head sc_send_ctxts; spinlock_t sc_rw_ctxt_lock; - struct list_head sc_rw_ctxts; + struct llist_head sc_rw_ctxts; u32 sc_pending_recvs; u32 sc_recv_batch; diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 3d1b119f6e3e..e27433f08ca7 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -35,6 +35,7 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc); * controlling svcxprt_rdma is destroyed. */ struct svc_rdma_rw_ctxt { + struct llist_node rw_node; struct list_head rw_list; struct rdma_rw_ctx rw_ctx; unsigned int rw_nents; @@ -53,19 +54,19 @@ static struct svc_rdma_rw_ctxt * svc_rdma_get_rw_ctxt(struct svcxprt_rdma *rdma, unsigned int sges) { struct svc_rdma_rw_ctxt *ctxt; + struct llist_node *node; spin_lock(&rdma->sc_rw_ctxt_lock); - - ctxt = svc_rdma_next_ctxt(&rdma->sc_rw_ctxts); - if (ctxt) { - list_del(&ctxt->rw_list); - spin_unlock(&rdma->sc_rw_ctxt_lock); + node = llist_del_first(&rdma->sc_rw_ctxts); + spin_unlock(&rdma->sc_rw_ctxt_lock); + if (node) { + ctxt = llist_entry(node, struct svc_rdma_rw_ctxt, rw_node); } else { - spin_unlock(&rdma->sc_rw_ctxt_lock); ctxt = kmalloc(struct_size(ctxt, rw_first_sgl, SG_CHUNK_SIZE), GFP_KERNEL); if (!ctxt) goto out_noctx; + INIT_LIST_HEAD(&ctxt->rw_list); } @@ -83,14 +84,18 @@ out_noctx: return NULL; } -static void svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, - struct svc_rdma_rw_ctxt *ctxt) +static void __svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, + struct svc_rdma_rw_ctxt *ctxt, + struct llist_head *list) { sg_free_table_chained(&ctxt->rw_sg_table, SG_CHUNK_SIZE); + llist_add(&ctxt->rw_node, list); +} - spin_lock(&rdma->sc_rw_ctxt_lock); - list_add(&ctxt->rw_list, &rdma->sc_rw_ctxts); - spin_unlock(&rdma->sc_rw_ctxt_lock); +static void svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, + struct svc_rdma_rw_ctxt *ctxt) +{ + __svc_rdma_put_rw_ctxt(rdma, ctxt, &rdma->sc_rw_ctxts); } /** @@ -101,9 +106,10 @@ static void svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma) { struct svc_rdma_rw_ctxt *ctxt; + struct llist_node *node; - while ((ctxt = svc_rdma_next_ctxt(&rdma->sc_rw_ctxts)) != NULL) { - list_del(&ctxt->rw_list); + while ((node = llist_del_first(&rdma->sc_rw_ctxts)) != NULL) { + ctxt = llist_entry(node, struct svc_rdma_rw_ctxt, rw_node); kfree(ctxt); } } @@ -171,20 +177,35 @@ static void svc_rdma_cc_init(struct svcxprt_rdma *rdma, cc->cc_sqecount = 0; } +/* + * The consumed rw_ctx's are cleaned and placed on a local llist so + * that only one atomic llist operation is needed to put them all + * back on the free list. + */ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc, enum dma_data_direction dir) { struct svcxprt_rdma *rdma = cc->cc_rdma; + struct llist_node *first, *last; struct svc_rdma_rw_ctxt *ctxt; + LLIST_HEAD(free); + first = last = NULL; while ((ctxt = svc_rdma_next_ctxt(&cc->cc_rwctxts)) != NULL) { list_del(&ctxt->rw_list); rdma_rw_ctx_destroy(&ctxt->rw_ctx, rdma->sc_qp, rdma->sc_port_num, ctxt->rw_sg_table.sgl, ctxt->rw_nents, dir); - svc_rdma_put_rw_ctxt(rdma, ctxt); + __svc_rdma_put_rw_ctxt(rdma, ctxt, &free); + + ctxt->rw_node.next = first; + first = &ctxt->rw_node; + if (!last) + last = first; } + if (first) + llist_add_batch(first, last, &rdma->sc_rw_ctxts); } /* State for sending a Write or Reply chunk. diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 99474078c304..d1faa522c3dd 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -138,7 +138,7 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv, INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q); init_llist_head(&cma_xprt->sc_send_ctxts); init_llist_head(&cma_xprt->sc_recv_ctxts); - INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts); + init_llist_head(&cma_xprt->sc_rw_ctxts); init_waitqueue_head(&cma_xprt->sc_send_wait); spin_lock_init(&cma_xprt->sc_lock); -- cgit v1.2.3 From 5c11720767f70d34357d00a15ba5a0ad052c40fe Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 5 Aug 2021 15:11:24 -0400 Subject: SUNRPC: Fix a NULL pointer deref in trace_svc_stats_latency() Some paths through svc_process() leave rqst->rq_procinfo set to NULL, which triggers a crash if tracing happens to be enabled. Fixes: 89ff87494c6e ("SUNRPC: Display RPC procedure names instead of proc numbers") Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 1 + include/trace/events/sunrpc.h | 8 ++++---- net/sunrpc/svc.c | 15 +++++++++++++++ 3 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index ab9afbf0a0d8..f0f846fa396e 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -527,6 +527,7 @@ void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); struct svc_pool * svc_pool_for_cpu(struct svc_serv *serv, int cpu); char * svc_print_addr(struct svc_rqst *, char *, size_t); +const char * svc_proc_name(const struct svc_rqst *rqstp); int svc_encode_result_payload(struct svc_rqst *rqstp, unsigned int offset, unsigned int length); diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 861f199896c6..d323f5a049c8 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1642,7 +1642,7 @@ TRACE_EVENT(svc_process, __field(u32, vers) __field(u32, proc) __string(service, name) - __string(procedure, rqst->rq_procinfo->pc_name) + __string(procedure, svc_proc_name(rqst)) __string(addr, rqst->rq_xprt ? rqst->rq_xprt->xpt_remotebuf : "(null)") ), @@ -1652,7 +1652,7 @@ TRACE_EVENT(svc_process, __entry->vers = rqst->rq_vers; __entry->proc = rqst->rq_proc; __assign_str(service, name); - __assign_str(procedure, rqst->rq_procinfo->pc_name); + __assign_str(procedure, svc_proc_name(rqst)); __assign_str(addr, rqst->rq_xprt ? rqst->rq_xprt->xpt_remotebuf : "(null)"); ), @@ -1918,7 +1918,7 @@ TRACE_EVENT(svc_stats_latency, TP_STRUCT__entry( __field(u32, xid) __field(unsigned long, execute) - __string(procedure, rqst->rq_procinfo->pc_name) + __string(procedure, svc_proc_name(rqst)) __string(addr, rqst->rq_xprt->xpt_remotebuf) ), @@ -1926,7 +1926,7 @@ TRACE_EVENT(svc_stats_latency, __entry->xid = be32_to_cpu(rqst->rq_xid); __entry->execute = ktime_to_us(ktime_sub(ktime_get(), rqst->rq_stime)); - __assign_str(procedure, rqst->rq_procinfo->pc_name); + __assign_str(procedure, svc_proc_name(rqst)); __assign_str(addr, rqst->rq_xprt->xpt_remotebuf); ), diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index d2d412d43827..5aa263326b6a 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1650,6 +1650,21 @@ u32 svc_max_payload(const struct svc_rqst *rqstp) } EXPORT_SYMBOL_GPL(svc_max_payload); +/** + * svc_proc_name - Return RPC procedure name in string form + * @rqstp: svc_rqst to operate on + * + * Return value: + * Pointer to a NUL-terminated string + */ +const char *svc_proc_name(const struct svc_rqst *rqstp) +{ + if (rqstp && rqstp->rq_procinfo) + return rqstp->rq_procinfo->pc_name; + return "unknown"; +} + + /** * svc_encode_result_payload - mark a range of bytes as a result payload * @rqstp: svc_rqst to operate on -- cgit v1.2.3 From a2071573d6346819cc4e5787b4206f2184985160 Mon Sep 17 00:00:00 2001 From: Jia He Date: Tue, 3 Aug 2021 12:59:36 +0200 Subject: sysctl: introduce new proc handler proc_dobool This is to let bool variable could be correctly displayed in big/little endian sysctl procfs. sizeof(bool) is arch dependent, proc_dobool should work in all arches. Suggested-by: Pan Xinhui Signed-off-by: Jia He [thuth: rebased the patch to the current kernel version] Signed-off-by: Thomas Huth Signed-off-by: Chuck Lever --- include/linux/sysctl.h | 2 ++ kernel/sysctl.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index d99ca99837de..1fa2b69c6fc3 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -48,6 +48,8 @@ typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_dostring(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dobool(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); int proc_dointvec(struct ctl_table *, int, void *, size_t *, loff_t *); int proc_douintvec(struct ctl_table *, int, void *, size_t *, loff_t *); int proc_dointvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 272f4a272f8c..25e49b4d8049 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -536,6 +536,21 @@ static void proc_put_char(void **buf, size_t *size, char c) } } +static int do_proc_dobool_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + if (write) { + *(bool *)valp = *lvalp; + } else { + int val = *(bool *)valp; + + *lvalp = (unsigned long)val; + *negp = false; + } + return 0; +} + static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, int *valp, int write, void *data) @@ -798,6 +813,26 @@ static int do_proc_douintvec(struct ctl_table *table, int write, buffer, lenp, ppos, conv, data); } +/** + * proc_dobool - read/write a bool + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) integer + * values from/to the user buffer, treated as an ASCII string. + * + * Returns 0 on success. + */ +int proc_dobool(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table, write, buffer, lenp, ppos, + do_proc_dobool_conv, NULL); +} + /** * proc_dointvec - read a vector of integers * @table: the sysctl table @@ -1630,6 +1665,12 @@ int proc_dostring(struct ctl_table *table, int write, return -ENOSYS; } +int proc_dobool(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -3425,6 +3466,7 @@ int __init sysctl_init(void) * No sense putting this after each symbol definition, twice, * exception granted :-) */ +EXPORT_SYMBOL(proc_dobool); EXPORT_SYMBOL(proc_dointvec); EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); -- cgit v1.2.3 From b4ab2fea7c797b0b8b92332c7e315703c12d37d8 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 30 Jul 2021 16:07:36 -0400 Subject: SUNRPC: Add RPC_AUTH_TLS protocol numbers Shared by client and server. See: https://www.iana.org/assignments/rpc-authentication-numbers/rpc-authentication-numbers.xhtml Signed-off-by: Chuck Lever --- include/linux/sunrpc/msg_prot.h | 1 + include/linux/sunrpc/xdr.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 938c2bf29db8..02117ed0fa2e 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -20,6 +20,7 @@ enum rpc_auth_flavors { RPC_AUTH_DES = 3, RPC_AUTH_KRB = 4, RPC_AUTH_GSS = 6, + RPC_AUTH_TLS = 7, RPC_AUTH_MAXFLAVOR = 8, /* pseudoflavors: */ RPC_AUTH_GSS_KRB5 = 390003, diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index a965cbc136ad..b519609af1d0 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -95,6 +95,7 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) #define rpc_auth_unix cpu_to_be32(RPC_AUTH_UNIX) #define rpc_auth_short cpu_to_be32(RPC_AUTH_SHORT) #define rpc_auth_gss cpu_to_be32(RPC_AUTH_GSS) +#define rpc_auth_tls cpu_to_be32(RPC_AUTH_TLS) #define rpc_call cpu_to_be32(RPC_CALL) #define rpc_reply cpu_to_be32(RPC_REPLY) -- cgit v1.2.3 From 8282947f67345246b4a6344dbceb07484d3d4dad Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:28 +0200 Subject: locking/rwlock: Provide RT variant Similar to rw_semaphores, on RT the rwlock substitution is not writer fair, because it's not feasible to have a writer inherit its priority to multiple readers. Readers blocked on a writer follow the normal rules of priority inheritance. Like RT spinlocks, RT rwlocks are state preserving across the slow lock operations (contended case). Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211303.882793524@linutronix.de --- include/linux/rwlock_rt.h | 140 ++++++++++++++++++++++++++++++++++++++++ include/linux/rwlock_types.h | 49 ++++++++++---- include/linux/spinlock_rt.h | 2 + kernel/Kconfig.locks | 2 +- kernel/locking/spinlock.c | 7 ++ kernel/locking/spinlock_debug.c | 5 ++ kernel/locking/spinlock_rt.c | 131 +++++++++++++++++++++++++++++++++++++ 7 files changed, 323 insertions(+), 13 deletions(-) create mode 100644 include/linux/rwlock_rt.h (limited to 'include/linux') diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h new file mode 100644 index 000000000000..49c1f3842ed5 --- /dev/null +++ b/include/linux/rwlock_rt.h @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_RWLOCK_RT_H +#define __LINUX_RWLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_RT_H +#error Do not #include directly. Use . +#endif + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void __rt_rwlock_init(rwlock_t *rwlock, const char *name, + struct lock_class_key *key); +#else +static inline void __rt_rwlock_init(rwlock_t *rwlock, char *name, + struct lock_class_key *key) +{ +} +#endif + +#define rwlock_init(rwl) \ +do { \ + static struct lock_class_key __key; \ + \ + init_rwbase_rt(&(rwl)->rwbase); \ + __rt_rwlock_init(rwl, #rwl, &__key); \ +} while (0) + +extern void rt_read_lock(rwlock_t *rwlock); +extern int rt_read_trylock(rwlock_t *rwlock); +extern void rt_read_unlock(rwlock_t *rwlock); +extern void rt_write_lock(rwlock_t *rwlock); +extern int rt_write_trylock(rwlock_t *rwlock); +extern void rt_write_unlock(rwlock_t *rwlock); + +static __always_inline void read_lock(rwlock_t *rwlock) +{ + rt_read_lock(rwlock); +} + +static __always_inline void read_lock_bh(rwlock_t *rwlock) +{ + local_bh_disable(); + rt_read_lock(rwlock); +} + +static __always_inline void read_lock_irq(rwlock_t *rwlock) +{ + rt_read_lock(rwlock); +} + +#define read_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + rt_read_lock(lock); \ + flags = 0; \ + } while (0) + +#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) + +static __always_inline void read_unlock(rwlock_t *rwlock) +{ + rt_read_unlock(rwlock); +} + +static __always_inline void read_unlock_bh(rwlock_t *rwlock) +{ + rt_read_unlock(rwlock); + local_bh_enable(); +} + +static __always_inline void read_unlock_irq(rwlock_t *rwlock) +{ + rt_read_unlock(rwlock); +} + +static __always_inline void read_unlock_irqrestore(rwlock_t *rwlock, + unsigned long flags) +{ + rt_read_unlock(rwlock); +} + +static __always_inline void write_lock(rwlock_t *rwlock) +{ + rt_write_lock(rwlock); +} + +static __always_inline void write_lock_bh(rwlock_t *rwlock) +{ + local_bh_disable(); + rt_write_lock(rwlock); +} + +static __always_inline void write_lock_irq(rwlock_t *rwlock) +{ + rt_write_lock(rwlock); +} + +#define write_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + rt_write_lock(lock); \ + flags = 0; \ + } while (0) + +#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) + +#define write_trylock_irqsave(lock, flags) \ +({ \ + int __locked; \ + \ + typecheck(unsigned long, flags); \ + flags = 0; \ + __locked = write_trylock(lock); \ + __locked; \ +}) + +static __always_inline void write_unlock(rwlock_t *rwlock) +{ + rt_write_unlock(rwlock); +} + +static __always_inline void write_unlock_bh(rwlock_t *rwlock) +{ + rt_write_unlock(rwlock); + local_bh_enable(); +} + +static __always_inline void write_unlock_irq(rwlock_t *rwlock) +{ + rt_write_unlock(rwlock); +} + +static __always_inline void write_unlock_irqrestore(rwlock_t *rwlock, + unsigned long flags) +{ + rt_write_unlock(rwlock); +} + +#define rwlock_is_contended(lock) (((void)(lock), 0)) + +#endif /* __LINUX_RWLOCK_RT_H */ diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h index 0ad226b5d8fd..1948442e7750 100644 --- a/include/linux/rwlock_types.h +++ b/include/linux/rwlock_types.h @@ -5,9 +5,19 @@ # error "Do not include directly, include spinlock_types.h" #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define RW_DEP_MAP_INIT(lockname) \ + .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_CONFIG, \ + } +#else +# define RW_DEP_MAP_INIT(lockname) +#endif + +#ifndef CONFIG_PREEMPT_RT /* - * include/linux/rwlock_types.h - generic rwlock type definitions - * and initializers + * generic rwlock type definitions and initializers * * portions Copyright 2005, Red Hat, Inc., Ingo Molnar * Released under the General Public License (GPL). @@ -25,16 +35,6 @@ typedef struct { #define RWLOCK_MAGIC 0xdeaf1eed -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define RW_DEP_MAP_INIT(lockname) \ - .dep_map = { \ - .name = #lockname, \ - .wait_type_inner = LD_WAIT_CONFIG, \ - } -#else -# define RW_DEP_MAP_INIT(lockname) -#endif - #ifdef CONFIG_DEBUG_SPINLOCK #define __RW_LOCK_UNLOCKED(lockname) \ (rwlock_t) { .raw_lock = __ARCH_RW_LOCK_UNLOCKED, \ @@ -50,4 +50,29 @@ typedef struct { #define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x) +#else /* !CONFIG_PREEMPT_RT */ + +#include + +typedef struct { + struct rwbase_rt rwbase; + atomic_t readers; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} rwlock_t; + +#define __RWLOCK_RT_INITIALIZER(name) \ +{ \ + .rwbase = __RWBASE_INITIALIZER(name), \ + RW_DEP_MAP_INIT(name) \ +} + +#define __RW_LOCK_UNLOCKED(name) __RWLOCK_RT_INITIALIZER(name) + +#define DEFINE_RWLOCK(name) \ + rwlock_t name = __RW_LOCK_UNLOCKED(name) + +#endif /* CONFIG_PREEMPT_RT */ + #endif /* __LINUX_RWLOCK_TYPES_H */ diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h index 21228d3362f7..4fc72199cc9d 100644 --- a/include/linux/spinlock_rt.h +++ b/include/linux/spinlock_rt.h @@ -146,4 +146,6 @@ static inline int spin_is_locked(spinlock_t *lock) #define assert_spin_locked(lock) BUG_ON(!spin_is_locked(lock)) +#include + #endif diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 3de8fd11873b..4198f0273ecd 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -251,7 +251,7 @@ config ARCH_USE_QUEUED_RWLOCKS config QUEUED_RWLOCKS def_bool y if ARCH_USE_QUEUED_RWLOCKS - depends on SMP + depends on SMP && !PREEMPT_RT config ARCH_HAS_MMIOWB bool diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index c8d7ad9fb9b2..c5830cfa379a 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -124,8 +124,11 @@ void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock) \ * __[spin|read|write]_lock_bh() */ BUILD_LOCK_OPS(spin, raw_spinlock); + +#ifndef CONFIG_PREEMPT_RT BUILD_LOCK_OPS(read, rwlock); BUILD_LOCK_OPS(write, rwlock); +#endif #endif @@ -209,6 +212,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock) EXPORT_SYMBOL(_raw_spin_unlock_bh); #endif +#ifndef CONFIG_PREEMPT_RT + #ifndef CONFIG_INLINE_READ_TRYLOCK int __lockfunc _raw_read_trylock(rwlock_t *lock) { @@ -353,6 +358,8 @@ void __lockfunc _raw_write_unlock_bh(rwlock_t *lock) EXPORT_SYMBOL(_raw_write_unlock_bh); #endif +#endif /* !CONFIG_PREEMPT_RT */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index b9d93087ee66..14235671a1a7 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, EXPORT_SYMBOL(__raw_spin_lock_init); +#ifndef CONFIG_PREEMPT_RT void __rwlock_init(rwlock_t *lock, const char *name, struct lock_class_key *key) { @@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const char *name, } EXPORT_SYMBOL(__rwlock_init); +#endif static void spin_dump(raw_spinlock_t *lock, const char *msg) { @@ -139,6 +141,7 @@ void do_raw_spin_unlock(raw_spinlock_t *lock) arch_spin_unlock(&lock->raw_lock); } +#ifndef CONFIG_PREEMPT_RT static void rwlock_bug(rwlock_t *lock, const char *msg) { if (!debug_locks_off()) @@ -228,3 +231,5 @@ void do_raw_write_unlock(rwlock_t *lock) debug_write_unlock(lock); arch_write_unlock(&lock->raw_lock); } + +#endif /* !CONFIG_PREEMPT_RT */ diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c index edfa7b5776d7..c36648bd765d 100644 --- a/kernel/locking/spinlock_rt.c +++ b/kernel/locking/spinlock_rt.c @@ -127,3 +127,134 @@ void __rt_spin_lock_init(spinlock_t *lock, const char *name, } EXPORT_SYMBOL(__rt_spin_lock_init); #endif + +/* + * RT-specific reader/writer locks + */ +#define rwbase_set_and_save_current_state(state) \ + current_save_and_set_rtlock_wait_state() + +#define rwbase_restore_current_state() \ + current_restore_rtlock_saved_state() + +static __always_inline int +rwbase_rtmutex_lock_state(struct rt_mutex_base *rtm, unsigned int state) +{ + if (unlikely(!rt_mutex_cmpxchg_acquire(rtm, NULL, current))) + rtlock_slowlock(rtm); + return 0; +} + +static __always_inline int +rwbase_rtmutex_slowlock_locked(struct rt_mutex_base *rtm, unsigned int state) +{ + rtlock_slowlock_locked(rtm); + return 0; +} + +static __always_inline void rwbase_rtmutex_unlock(struct rt_mutex_base *rtm) +{ + if (likely(rt_mutex_cmpxchg_acquire(rtm, current, NULL))) + return; + + rt_mutex_slowunlock(rtm); +} + +static __always_inline int rwbase_rtmutex_trylock(struct rt_mutex_base *rtm) +{ + if (likely(rt_mutex_cmpxchg_acquire(rtm, NULL, current))) + return 1; + + return rt_mutex_slowtrylock(rtm); +} + +#define rwbase_signal_pending_state(state, current) (0) + +#define rwbase_schedule() \ + schedule_rtlock() + +#include "rwbase_rt.c" +/* + * The common functions which get wrapped into the rwlock API. + */ +int __sched rt_read_trylock(rwlock_t *rwlock) +{ + int ret; + + ret = rwbase_read_trylock(&rwlock->rwbase); + if (ret) { + rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_); + rcu_read_lock(); + migrate_disable(); + } + return ret; +} +EXPORT_SYMBOL(rt_read_trylock); + +int __sched rt_write_trylock(rwlock_t *rwlock) +{ + int ret; + + ret = rwbase_write_trylock(&rwlock->rwbase); + if (ret) { + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + rcu_read_lock(); + migrate_disable(); + } + return ret; +} +EXPORT_SYMBOL(rt_write_trylock); + +void __sched rt_read_lock(rwlock_t *rwlock) +{ + ___might_sleep(__FILE__, __LINE__, 0); + rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); + rwbase_read_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_read_lock); + +void __sched rt_write_lock(rwlock_t *rwlock) +{ + ___might_sleep(__FILE__, __LINE__, 0); + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + rwbase_write_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_write_lock); + +void __sched rt_read_unlock(rwlock_t *rwlock) +{ + rwlock_release(&rwlock->dep_map, _RET_IP_); + migrate_enable(); + rcu_read_unlock(); + rwbase_read_unlock(&rwlock->rwbase, TASK_RTLOCK_WAIT); +} +EXPORT_SYMBOL(rt_read_unlock); + +void __sched rt_write_unlock(rwlock_t *rwlock) +{ + rwlock_release(&rwlock->dep_map, _RET_IP_); + rcu_read_unlock(); + migrate_enable(); + rwbase_write_unlock(&rwlock->rwbase); +} +EXPORT_SYMBOL(rt_write_unlock); + +int __sched rt_rwlock_is_contended(rwlock_t *rwlock) +{ + return rw_base_is_contended(&rwlock->rwbase); +} +EXPORT_SYMBOL(rt_rwlock_is_contended); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __rt_rwlock_init(rwlock_t *rwlock, const char *name, + struct lock_class_key *key) +{ + debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock)); + lockdep_init_map_wait(&rwlock->dep_map, name, key, 0, LD_WAIT_CONFIG); +} +EXPORT_SYMBOL(__rt_rwlock_init); +#endif -- cgit v1.2.3 From 43d2d52d704e025518d35c3079fcbff744623166 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:33 +0200 Subject: locking/mutex: Move the 'struct mutex_waiter' definition from to the internal header Move the mutex waiter declaration from the public header to the internal kernel/locking/mutex.h header. There is no reason to expose it outside of the core code. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211304.054325923@linutronix.de --- include/linux/mutex.h | 13 ------------- kernel/locking/mutex.h | 13 +++++++++++++ 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index e19323521f9c..62bafee747e9 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -74,19 +74,6 @@ struct ww_mutex { #endif }; -/* - * This is the control structure for tasks blocked on mutex, - * which resides on the blocked task's kernel stack: - */ -struct mutex_waiter { - struct list_head list; - struct task_struct *task; - struct ww_acquire_ctx *ww_ctx; -#ifdef CONFIG_DEBUG_MUTEXES - void *magic; -#endif -}; - #ifdef CONFIG_DEBUG_MUTEXES #define __DEBUG_MUTEX_INITIALIZER(lockname) \ diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index 586e4f1f6ebf..0b2a79c4013b 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -7,6 +7,19 @@ * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar */ +/* + * This is the control structure for tasks blocked on mutex, which resides + * on the blocked task's kernel stack: + */ +struct mutex_waiter { + struct list_head list; + struct task_struct *task; + struct ww_acquire_ctx *ww_ctx; +#ifdef CONFIG_DEBUG_MUTEXES + void *magic; +#endif +}; + #ifdef CONFIG_DEBUG_MUTEXES extern void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter); -- cgit v1.2.3 From 4f1893ec8cfb4b17e3b89158a1e3e550a9a9bf3c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:34 +0200 Subject: locking/ww_mutex: Move the ww_mutex definitions from into Move the ww_mutex definitions into the ww_mutex specific header where they belong. Preparatory change to allow compiling ww_mutexes standalone. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211304.110216293@linutronix.de --- include/linux/mutex.h | 11 ----------- include/linux/ww_mutex.h | 8 ++++++++ 2 files changed, 8 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 62bafee747e9..db3367586a06 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -20,9 +20,6 @@ #include #include -struct ww_class; -struct ww_acquire_ctx; - /* * Simple, straightforward mutexes with strict semantics: * @@ -66,14 +63,6 @@ struct mutex { #endif }; -struct ww_mutex { - struct mutex base; - struct ww_acquire_ctx *ctx; -#ifdef CONFIG_DEBUG_MUTEXES - struct ww_class *ww_class; -#endif -}; - #ifdef CONFIG_DEBUG_MUTEXES #define __DEBUG_MUTEX_INITIALIZER(lockname) \ diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index b77f39f319ad..590aaa207757 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -28,6 +28,14 @@ struct ww_class { unsigned int is_wait_die; }; +struct ww_mutex { + struct mutex base; + struct ww_acquire_ctx *ctx; +#ifdef CONFIG_DEBUG_MUTEXES + struct ww_class *ww_class; +#endif +}; + struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; -- cgit v1.2.3 From ebf4c55c1ddbabaea120fe8d48ce25b4f5da93a1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:36 +0200 Subject: locking/mutex: Make mutex::wait_lock raw The wait_lock of mutex is really a low level lock. Convert it to a raw_spinlock like the wait_lock of rtmutex. [ mingo: backmerged the test_lockup.c build fix by bigeasy. ] Co-developed-by: Sebastian Andrzej Siewior Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211304.166863404@linutronix.de --- include/linux/mutex.h | 4 ++-- kernel/locking/mutex.c | 22 +++++++++++----------- lib/test_lockup.c | 2 +- 3 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index db3367586a06..0bbc872ba72b 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -50,7 +50,7 @@ */ struct mutex { atomic_long_t owner; - spinlock_t wait_lock; + raw_spinlock_t wait_lock; #ifdef CONFIG_MUTEX_SPIN_ON_OWNER struct optimistic_spin_queue osq; /* Spinner MCS lock */ #endif @@ -105,7 +105,7 @@ do { \ #define __MUTEX_INITIALIZER(lockname) \ { .owner = ATOMIC_LONG_INIT(0) \ - , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ + , .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ , .wait_list = LIST_HEAD_INIT(lockname.wait_list) \ __DEBUG_MUTEX_INITIALIZER(lockname) \ __DEP_MAP_MUTEX_INITIALIZER(lockname) } diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index acbe43d92836..17c194b81b9e 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -42,7 +42,7 @@ void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { atomic_long_set(&lock->owner, 0); - spin_lock_init(&lock->wait_lock); + raw_spin_lock_init(&lock->wait_lock); INIT_LIST_HEAD(&lock->wait_list); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER osq_lock_init(&lock->osq); @@ -486,9 +486,9 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * Uh oh, we raced in fastpath, check if any of the waiters need to * die or wound us. */ - spin_lock(&lock->base.wait_lock); + raw_spin_lock(&lock->base.wait_lock); __ww_mutex_check_waiters(&lock->base, ctx); - spin_unlock(&lock->base.wait_lock); + raw_spin_unlock(&lock->base.wait_lock); } #ifdef CONFIG_MUTEX_SPIN_ON_OWNER @@ -966,7 +966,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas return 0; } - spin_lock(&lock->wait_lock); + raw_spin_lock(&lock->wait_lock); /* * After waiting to acquire the wait_lock, try again. */ @@ -1032,7 +1032,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas goto err; } - spin_unlock(&lock->wait_lock); + raw_spin_unlock(&lock->wait_lock); schedule_preempt_disabled(); first = __mutex_waiter_is_first(lock, &waiter); @@ -1047,9 +1047,9 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas (first && mutex_optimistic_spin(lock, ww_ctx, &waiter))) break; - spin_lock(&lock->wait_lock); + raw_spin_lock(&lock->wait_lock); } - spin_lock(&lock->wait_lock); + raw_spin_lock(&lock->wait_lock); acquired: __set_current_state(TASK_RUNNING); @@ -1074,7 +1074,7 @@ skip_wait: if (ww_ctx) ww_mutex_lock_acquired(ww, ww_ctx); - spin_unlock(&lock->wait_lock); + raw_spin_unlock(&lock->wait_lock); preempt_enable(); return 0; @@ -1082,7 +1082,7 @@ err: __set_current_state(TASK_RUNNING); __mutex_remove_waiter(lock, &waiter); err_early_kill: - spin_unlock(&lock->wait_lock); + raw_spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, ip); preempt_enable(); @@ -1243,7 +1243,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne } } - spin_lock(&lock->wait_lock); + raw_spin_lock(&lock->wait_lock); debug_mutex_unlock(lock); if (!list_empty(&lock->wait_list)) { /* get the first entry from the wait-list: */ @@ -1260,7 +1260,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne if (owner & MUTEX_FLAG_HANDOFF) __mutex_handoff(lock, next); - spin_unlock(&lock->wait_lock); + raw_spin_unlock(&lock->wait_lock); wake_up_q(&wake_q); } diff --git a/lib/test_lockup.c b/lib/test_lockup.c index 864554e76973..4d93b02f81bb 100644 --- a/lib/test_lockup.c +++ b/lib/test_lockup.c @@ -502,7 +502,7 @@ static int __init test_lockup_init(void) offsetof(rwlock_t, magic), RWLOCK_MAGIC) || test_magic(lock_mutex_ptr, - offsetof(struct mutex, wait_lock.rlock.magic), + offsetof(struct mutex, wait_lock.magic), SPINLOCK_MAGIC) || test_magic(lock_rwsem_ptr, offsetof(struct rw_semaphore, wait_lock.magic), -- cgit v1.2.3 From 653a5b0bd9b405db999d5f4bfe08d34691e2c55a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:28:52 +0200 Subject: locking/ww_mutex: Abstract out internal lock accesses Accessing the internal wait_lock of mutex and rtmutex is slightly different. Provide helper functions for that. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211304.734635961@linutronix.de --- include/linux/ww_mutex.h | 13 +++++++++---- kernel/locking/ww_mutex.h | 23 +++++++++++++++++++---- 2 files changed, 28 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 590aaa207757..3438e302a52a 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -19,6 +19,11 @@ #include +#define WW_MUTEX_BASE mutex +#define ww_mutex_base_init(l,n,k) __mutex_init(l,n,k) +#define ww_mutex_base_trylock(l) mutex_trylock(l) +#define ww_mutex_base_is_locked(b) mutex_is_locked((b)) + struct ww_class { atomic_long_t stamp; struct lock_class_key acquire_key; @@ -29,7 +34,7 @@ struct ww_class { }; struct ww_mutex { - struct mutex base; + struct WW_MUTEX_BASE base; struct ww_acquire_ctx *ctx; #ifdef CONFIG_DEBUG_MUTEXES struct ww_class *ww_class; @@ -82,7 +87,7 @@ struct ww_acquire_ctx { static inline void ww_mutex_init(struct ww_mutex *lock, struct ww_class *ww_class) { - __mutex_init(&lock->base, ww_class->mutex_name, &ww_class->mutex_key); + ww_mutex_base_init(&lock->base, ww_class->mutex_name, &ww_class->mutex_key); lock->ctx = NULL; #ifdef CONFIG_DEBUG_MUTEXES lock->ww_class = ww_class; @@ -330,7 +335,7 @@ extern void ww_mutex_unlock(struct ww_mutex *lock); */ static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock) { - return mutex_trylock(&lock->base); + return ww_mutex_base_trylock(&lock->base); } /*** @@ -354,7 +359,7 @@ static inline void ww_mutex_destroy(struct ww_mutex *lock) */ static inline bool ww_mutex_is_locked(struct ww_mutex *lock) { - return mutex_is_locked(&lock->base); + return ww_mutex_base_is_locked(&lock->base); } #endif diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h index 31b075f03660..309f3e4d814a 100644 --- a/kernel/locking/ww_mutex.h +++ b/kernel/locking/ww_mutex.h @@ -68,6 +68,21 @@ __ww_mutex_has_waiters(struct mutex *lock) return atomic_long_read(&lock->owner) & MUTEX_FLAG_WAITERS; } +static inline void lock_wait_lock(struct mutex *lock) +{ + raw_spin_lock(&lock->wait_lock); +} + +static inline void unlock_wait_lock(struct mutex *lock) +{ + raw_spin_unlock(&lock->wait_lock); +} + +static inline void lockdep_assert_wait_lock_held(struct mutex *lock) +{ + lockdep_assert_held(&lock->wait_lock); +} + /* * Wait-Die: * The newer transactions are killed when: @@ -174,7 +189,7 @@ static bool __ww_mutex_wound(struct MUTEX *lock, { struct task_struct *owner = __ww_mutex_owner(lock); - lockdep_assert_held(&lock->wait_lock); + lockdep_assert_wait_lock_held(lock); /* * Possible through __ww_mutex_add_waiter() when we race with @@ -227,7 +242,7 @@ __ww_mutex_check_waiters(struct MUTEX *lock, struct ww_acquire_ctx *ww_ctx) { struct MUTEX_WAITER *cur; - lockdep_assert_held(&lock->wait_lock); + lockdep_assert_wait_lock_held(lock); for (cur = __ww_waiter_first(lock); cur; cur = __ww_waiter_next(lock, cur)) { @@ -275,9 +290,9 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * Uh oh, we raced in fastpath, check if any of the waiters need to * die or wound us. */ - raw_spin_lock(&lock->base.wait_lock); + lock_wait_lock(&lock->base); __ww_mutex_check_waiters(&lock->base, ctx); - raw_spin_unlock(&lock->base.wait_lock); + unlock_wait_lock(&lock->base); } static __always_inline int -- cgit v1.2.3 From 2408f7a3782a6bfa69a573f5408b3a9666db78ca Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 15 Aug 2021 23:28:56 +0200 Subject: locking/ww_mutex: Add rt_mutex based lock type and accessors Provide the defines for RT mutex based ww_mutexes and fix up the debug logic so it's either enabled by DEBUG_MUTEXES or DEBUG_RT_MUTEXES on RT kernels. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211304.908012566@linutronix.de --- include/linux/ww_mutex.h | 33 ++++++++++++++++++++++++--------- kernel/locking/ww_mutex.h | 6 +++--- 2 files changed, 27 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 3438e302a52a..29db736af86d 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -18,11 +18,24 @@ #define __LINUX_WW_MUTEX_H #include +#include +#if defined(CONFIG_DEBUG_MUTEXES) || \ + (defined(CONFIG_PREEMPT_RT) && defined(CONFIG_DEBUG_RT_MUTEXES)) +#define DEBUG_WW_MUTEXES +#endif + +#ifndef CONFIG_PREEMPT_RT #define WW_MUTEX_BASE mutex #define ww_mutex_base_init(l,n,k) __mutex_init(l,n,k) #define ww_mutex_base_trylock(l) mutex_trylock(l) #define ww_mutex_base_is_locked(b) mutex_is_locked((b)) +#else +#define WW_MUTEX_BASE rt_mutex +#define ww_mutex_base_init(l,n,k) __rt_mutex_init(l,n,k) +#define ww_mutex_base_trylock(l) rt_mutex_trylock(l) +#define ww_mutex_base_is_locked(b) rt_mutex_base_is_locked(&(b)->rtmutex) +#endif struct ww_class { atomic_long_t stamp; @@ -36,7 +49,7 @@ struct ww_class { struct ww_mutex { struct WW_MUTEX_BASE base; struct ww_acquire_ctx *ctx; -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES struct ww_class *ww_class; #endif }; @@ -47,10 +60,10 @@ struct ww_acquire_ctx { unsigned int acquired; unsigned short wounded; unsigned short is_wait_die; -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES unsigned int done_acquire; struct ww_class *ww_class; - struct ww_mutex *contending_lock; + void *contending_lock; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; @@ -89,7 +102,7 @@ static inline void ww_mutex_init(struct ww_mutex *lock, { ww_mutex_base_init(&lock->base, ww_class->mutex_name, &ww_class->mutex_key); lock->ctx = NULL; -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES lock->ww_class = ww_class; #endif } @@ -126,7 +139,7 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, ctx->acquired = 0; ctx->wounded = false; ctx->is_wait_die = ww_class->is_wait_die; -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES ctx->ww_class = ww_class; ctx->done_acquire = 0; ctx->contending_lock = NULL; @@ -156,7 +169,7 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, */ static inline void ww_acquire_done(struct ww_acquire_ctx *ctx) { -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES lockdep_assert_held(ctx); DEBUG_LOCKS_WARN_ON(ctx->done_acquire); @@ -176,7 +189,7 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) #ifdef CONFIG_DEBUG_LOCK_ALLOC mutex_release(&ctx->dep_map, _THIS_IP_); #endif -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES DEBUG_LOCKS_WARN_ON(ctx->acquired); if (!IS_ENABLED(CONFIG_PROVE_LOCKING)) /* @@ -282,7 +295,7 @@ static inline void ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { int ret; -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES DEBUG_LOCKS_WARN_ON(!ctx->contending_lock); #endif ret = ww_mutex_lock(lock, ctx); @@ -318,7 +331,7 @@ static inline int __must_check ww_mutex_lock_slow_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES DEBUG_LOCKS_WARN_ON(!ctx->contending_lock); #endif return ww_mutex_lock_interruptible(lock, ctx); @@ -348,7 +361,9 @@ static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock) */ static inline void ww_mutex_destroy(struct ww_mutex *lock) { +#ifndef CONFIG_PREEMPT_RT mutex_destroy(&lock->base); +#endif } /** diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h index 2dce4f0b0d1c..56f139201f24 100644 --- a/kernel/locking/ww_mutex.h +++ b/kernel/locking/ww_mutex.h @@ -180,7 +180,7 @@ static inline void lockdep_assert_wait_lock_held(struct rt_mutex *lock) static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) { -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES /* * If this WARN_ON triggers, you used ww_mutex_lock to acquire, * but released with a normal mutex_unlock in this call. @@ -413,7 +413,7 @@ static __always_inline int __ww_mutex_kill(struct MUTEX *lock, struct ww_acquire_ctx *ww_ctx) { if (ww_ctx->acquired > 0) { -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES struct ww_mutex *ww; ww = container_of(lock, struct ww_mutex, base); @@ -559,7 +559,7 @@ __ww_mutex_add_waiter(struct MUTEX_WAITER *waiter, static inline void __ww_mutex_unlock(struct ww_mutex *lock) { if (lock->ctx) { -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef DEBUG_WW_MUTEXES DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); #endif if (lock->ctx->acquired > 0) -- cgit v1.2.3 From bb630f9f7a7d43869e4e7f5e4c002207396aea59 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:29:01 +0200 Subject: locking/rtmutex: Add mutex variant for RT Add the necessary defines, helpers and API functions for replacing struct mutex on a PREEMPT_RT enabled kernel with an rtmutex based variant. No functional change when CONFIG_PREEMPT_RT=n Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211305.081517417@linutronix.de --- include/linux/mutex.h | 66 +++++++++++++++++++---- kernel/locking/mutex.c | 4 +- kernel/locking/rtmutex_api.c | 122 +++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 11 ++-- 4 files changed, 187 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 0bbc872ba72b..8f226d460f51 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -20,6 +20,18 @@ #include #include +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ + , .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_SLEEP, \ + } +#else +# define __DEP_MAP_MUTEX_INITIALIZER(lockname) +#endif + +#ifndef CONFIG_PREEMPT_RT + /* * Simple, straightforward mutexes with strict semantics: * @@ -93,16 +105,6 @@ do { \ __mutex_init((mutex), #mutex, &__key); \ } while (0) -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ - , .dep_map = { \ - .name = #lockname, \ - .wait_type_inner = LD_WAIT_SLEEP, \ - } -#else -# define __DEP_MAP_MUTEX_INITIALIZER(lockname) -#endif - #define __MUTEX_INITIALIZER(lockname) \ { .owner = ATOMIC_LONG_INIT(0) \ , .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ @@ -124,6 +126,50 @@ extern void __mutex_init(struct mutex *lock, const char *name, */ extern bool mutex_is_locked(struct mutex *lock); +#else /* !CONFIG_PREEMPT_RT */ +/* + * Preempt-RT variant based on rtmutexes. + */ +#include + +struct mutex { + struct rt_mutex_base rtmutex; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __MUTEX_INITIALIZER(mutexname) \ +{ \ + .rtmutex = __RT_MUTEX_BASE_INITIALIZER(mutexname.rtmutex) \ + __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ +} + +#define DEFINE_MUTEX(mutexname) \ + struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) + +extern void __mutex_rt_init(struct mutex *lock, const char *name, + struct lock_class_key *key); +extern int mutex_trylock(struct mutex *lock); + +static inline void mutex_destroy(struct mutex *lock) { } + +#define mutex_is_locked(l) rt_mutex_base_is_locked(&(l)->rtmutex) + +#define __mutex_init(mutex, name, key) \ +do { \ + rt_mutex_base_init(&(mutex)->rtmutex); \ + __mutex_rt_init((mutex), name, key); \ +} while (0) + +#define mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + \ + __mutex_init((mutex), #mutex, &__key); \ +} while (0) +#endif /* CONFIG_PREEMPT_RT */ + /* * See kernel/locking/mutex.c for detailed documentation of these APIs. * Also see Documentation/locking/mutex-design.rst. diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 9906ca6cc912..3a65bf4bacfd 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -30,6 +30,7 @@ #include #include +#ifndef CONFIG_PREEMPT_RT #include "mutex.h" #ifdef CONFIG_DEBUG_MUTEXES @@ -1066,7 +1067,8 @@ ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) } EXPORT_SYMBOL(ww_mutex_lock_interruptible); -#endif +#endif /* !CONFIG_DEBUG_LOCK_ALLOC */ +#endif /* !CONFIG_PREEMPT_RT */ /** * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 16126fcb55ef..92b7d289a8af 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -454,3 +454,125 @@ void rt_mutex_debug_task_free(struct task_struct *task) DEBUG_LOCKS_WARN_ON(task->pi_blocked_on); } #endif + +#ifdef CONFIG_PREEMPT_RT +/* Mutexes */ +void __mutex_rt_init(struct mutex *mutex, const char *name, + struct lock_class_key *key) +{ + debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); + lockdep_init_map_wait(&mutex->dep_map, name, key, 0, LD_WAIT_SLEEP); +} +EXPORT_SYMBOL(__mutex_rt_init); + +static __always_inline int __mutex_lock_common(struct mutex *lock, + unsigned int state, + unsigned int subclass, + struct lockdep_map *nest_lock, + unsigned long ip) +{ + int ret; + + might_sleep(); + mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); + ret = __rt_mutex_lock(&lock->rtmutex, state); + if (ret) + mutex_release(&lock->dep_map, ip); + else + lock_acquired(&lock->dep_map, ip); + return ret; +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) +{ + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_); +} +EXPORT_SYMBOL_GPL(mutex_lock_nested); + +void __sched _mutex_lock_nest_lock(struct mutex *lock, + struct lockdep_map *nest_lock) +{ + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, nest_lock, _RET_IP_); +} +EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); + +int __sched mutex_lock_interruptible_nested(struct mutex *lock, + unsigned int subclass) +{ + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_); +} +EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); + +int __sched mutex_lock_killable_nested(struct mutex *lock, + unsigned int subclass) +{ + return __mutex_lock_common(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_); +} +EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); + +void __sched mutex_lock_io_nested(struct mutex *lock, unsigned int subclass) +{ + int token; + + might_sleep(); + + token = io_schedule_prepare(); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_); + io_schedule_finish(token); +} +EXPORT_SYMBOL_GPL(mutex_lock_io_nested); + +#else /* CONFIG_DEBUG_LOCK_ALLOC */ + +void __sched mutex_lock(struct mutex *lock) +{ + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_); +} +EXPORT_SYMBOL(mutex_lock); + +int __sched mutex_lock_interruptible(struct mutex *lock) +{ + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_); +} +EXPORT_SYMBOL(mutex_lock_interruptible); + +int __sched mutex_lock_killable(struct mutex *lock) +{ + return __mutex_lock_common(lock, TASK_KILLABLE, 0, NULL, _RET_IP_); +} +EXPORT_SYMBOL(mutex_lock_killable); + +void __sched mutex_lock_io(struct mutex *lock) +{ + int token = io_schedule_prepare(); + + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_); + io_schedule_finish(token); +} +EXPORT_SYMBOL(mutex_lock_io); +#endif /* !CONFIG_DEBUG_LOCK_ALLOC */ + +int __sched mutex_trylock(struct mutex *lock) +{ + int ret; + + if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task())) + return 0; + + ret = __rt_mutex_trylock(&lock->rtmutex); + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + + return ret; +} +EXPORT_SYMBOL(mutex_trylock); + +void __sched mutex_unlock(struct mutex *lock) +{ + mutex_release(&lock->dep_map, _RET_IP_); + __rt_mutex_unlock(&lock->rtmutex); +} +EXPORT_SYMBOL(mutex_unlock); + +#endif /* CONFIG_PREEMPT_RT */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 5ddd575159fb..e5cdf98f50c2 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1235,7 +1235,7 @@ config PROVE_LOCKING depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT select LOCKDEP select DEBUG_SPINLOCK - select DEBUG_MUTEXES + select DEBUG_MUTEXES if !PREEMPT_RT select DEBUG_RT_MUTEXES if RT_MUTEXES select DEBUG_RWSEMS select DEBUG_WW_MUTEX_SLOWPATH @@ -1299,7 +1299,7 @@ config LOCK_STAT depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT select LOCKDEP select DEBUG_SPINLOCK - select DEBUG_MUTEXES + select DEBUG_MUTEXES if !PREEMPT_RT select DEBUG_RT_MUTEXES if RT_MUTEXES select DEBUG_LOCK_ALLOC default n @@ -1335,7 +1335,7 @@ config DEBUG_SPINLOCK config DEBUG_MUTEXES bool "Mutex debugging: basic checks" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && !PREEMPT_RT help This feature allows mutex semantics violations to be detected and reported. @@ -1345,7 +1345,8 @@ config DEBUG_WW_MUTEX_SLOWPATH depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT select DEBUG_LOCK_ALLOC select DEBUG_SPINLOCK - select DEBUG_MUTEXES + select DEBUG_MUTEXES if !PREEMPT_RT + select DEBUG_RT_MUTEXES if PREEMPT_RT help This feature enables slowpath testing for w/w mutex users by injecting additional -EDEADLK wound/backoff cases. Together with @@ -1368,7 +1369,7 @@ config DEBUG_LOCK_ALLOC bool "Lock debugging: detect incorrect freeing of live locks" depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT select DEBUG_SPINLOCK - select DEBUG_MUTEXES + select DEBUG_MUTEXES if !PREEMPT_RT select DEBUG_RT_MUTEXES if RT_MUTEXES select LOCKDEP help -- cgit v1.2.3 From 015680aa4c5d784513d0a9728bc52ec7c4a64227 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:29:22 +0200 Subject: preempt: Adjust PREEMPT_LOCK_OFFSET for RT On PREEMPT_RT regular spinlocks and rwlocks are substituted with rtmutex based constructs. spin/rwlock held regions are preemptible on PREEMPT_RT, so PREEMPT_LOCK_OFFSET has to be 0 to make the various cond_resched_*lock() functions work correctly. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211305.804246275@linutronix.de --- include/linux/preempt.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 9881eac0698f..4d244e295e85 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -121,7 +121,11 @@ /* * The preempt_count offset after spin_lock() */ +#if !defined(CONFIG_PREEMPT_RT) #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET +#else +#define PREEMPT_LOCK_OFFSET 0 +#endif /* * The preempt_count offset needed for things like: -- cgit v1.2.3 From 31552385f8e9d0869117014bf8e55ba0497e3ec8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:29:27 +0200 Subject: locking/spinlock/rt: Prepare for RT local_lock Add the static and runtime initializer mechanics to support the RT variant of local_lock, which requires the lock type in the lockdep map to be set to LD_LOCK_PERCPU. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211305.967526724@linutronix.de --- include/linux/spinlock_rt.h | 24 ++++++++++++++++-------- include/linux/spinlock_types.h | 6 ++++++ include/linux/spinlock_types_raw.h | 8 ++++++++ kernel/locking/spinlock_rt.c | 7 +++++-- 4 files changed, 35 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h index 4fc72199cc9d..835aedaf68ac 100644 --- a/include/linux/spinlock_rt.h +++ b/include/linux/spinlock_rt.h @@ -8,20 +8,28 @@ #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void __rt_spin_lock_init(spinlock_t *lock, const char *name, - struct lock_class_key *key); + struct lock_class_key *key, bool percpu); #else static inline void __rt_spin_lock_init(spinlock_t *lock, const char *name, - struct lock_class_key *key) + struct lock_class_key *key, bool percpu) { } #endif -#define spin_lock_init(slock) \ -do { \ - static struct lock_class_key __key; \ - \ - rt_mutex_base_init(&(slock)->lock); \ - __rt_spin_lock_init(slock, #slock, &__key); \ +#define spin_lock_init(slock) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_base_init(&(slock)->lock); \ + __rt_spin_lock_init(slock, #slock, &__key, false); \ +} while (0) + +#define local_spin_lock_init(slock) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_base_init(&(slock)->lock); \ + __rt_spin_lock_init(slock, #slock, &__key, true); \ } while (0) extern void rt_spin_lock(spinlock_t *lock); diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index 8a9aadbaf293..2dfa35ffec76 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -60,6 +60,12 @@ typedef struct spinlock { SPIN_DEP_MAP_INIT(name) \ } +#define __LOCAL_SPIN_LOCK_UNLOCKED(name) \ + { \ + .lock = __RT_MUTEX_BASE_INITIALIZER(name.lock), \ + LOCAL_SPIN_DEP_MAP_INIT(name) \ + } + #define DEFINE_SPINLOCK(name) \ spinlock_t name = __SPIN_LOCK_UNLOCKED(name) diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h index a8a4330d7b78..91cb36b65a17 100644 --- a/include/linux/spinlock_types_raw.h +++ b/include/linux/spinlock_types_raw.h @@ -37,9 +37,17 @@ typedef struct raw_spinlock { .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ } + +# define LOCAL_SPIN_DEP_MAP_INIT(lockname) \ + .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_CONFIG, \ + .lock_type = LD_LOCK_PERCPU, \ + } #else # define RAW_SPIN_DEP_MAP_INIT(lockname) # define SPIN_DEP_MAP_INIT(lockname) +# define LOCAL_SPIN_DEP_MAP_INIT(lockname) #endif #ifdef CONFIG_DEBUG_SPINLOCK diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c index c36648bd765d..d2912e44d61f 100644 --- a/kernel/locking/spinlock_rt.c +++ b/kernel/locking/spinlock_rt.c @@ -120,10 +120,13 @@ EXPORT_SYMBOL(rt_spin_trylock_bh); #ifdef CONFIG_DEBUG_LOCK_ALLOC void __rt_spin_lock_init(spinlock_t *lock, const char *name, - struct lock_class_key *key) + struct lock_class_key *key, bool percpu) { + u8 type = percpu ? LD_LOCK_PERCPU : LD_LOCK_NORMAL; + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); - lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_CONFIG); + lockdep_init_map_type(&lock->dep_map, name, key, 0, LD_WAIT_CONFIG, + LD_WAIT_INV, type); } EXPORT_SYMBOL(__rt_spin_lock_init); #endif -- cgit v1.2.3 From 026659b9774e4c586baeb457557fcfc4e0ad144b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:29:28 +0200 Subject: locking/local_lock: Add PREEMPT_RT support On PREEMPT_RT enabled kernels local_lock maps to a per CPU 'sleeping' spinlock which protects the critical section while staying preemptible. CPU locality is established by disabling migration. Provide the necessary types and macros to substitute the non-RT variant. Co-developed-by: Sebastian Andrzej Siewior Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211306.023630962@linutronix.de --- include/linux/local_lock_internal.h | 44 +++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 3f02b818625e..975e33b793a7 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -6,6 +6,8 @@ #include #include +#ifndef CONFIG_PREEMPT_RT + typedef struct { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; @@ -95,3 +97,45 @@ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_restore(flags); \ } while (0) + +#else /* !CONFIG_PREEMPT_RT */ + +/* + * On PREEMPT_RT local_lock maps to a per CPU spinlock, which protects the + * critical section while staying preemptible. + */ +typedef spinlock_t local_lock_t; + +#define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) + +#define __local_lock_init(l) \ + do { \ + local_spin_lock_init((l)); \ + } while (0) + +#define __local_lock(__lock) \ + do { \ + migrate_disable(); \ + spin_lock(this_cpu_ptr((__lock))); \ + } while (0) + +#define __local_lock_irq(lock) __local_lock(lock) + +#define __local_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + __local_lock(lock); \ + } while (0) + +#define __local_unlock(__lock) \ + do { \ + spin_unlock(this_cpu_ptr((__lock))); \ + migrate_enable(); \ + } while (0) + +#define __local_unlock_irq(lock) __local_unlock(lock) + +#define __local_unlock_irqrestore(lock, flags) __local_unlock(lock) + +#endif /* CONFIG_PREEMPT_RT */ -- cgit v1.2.3 From 9ae6ab27f44ee0da47520011afc04218f90e8b12 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 5 Aug 2021 17:49:54 +0200 Subject: static_call: Update API documentation Update the comment with the new features. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Steven Rostedt (VMware) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/YQwIorQBHEq+s73b@hirez.programming.kicks-ass.net --- include/linux/static_call.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index fc94faa53b5b..3e56a9751c06 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -17,11 +17,17 @@ * DECLARE_STATIC_CALL(name, func); * DEFINE_STATIC_CALL(name, func); * DEFINE_STATIC_CALL_NULL(name, typename); + * DEFINE_STATIC_CALL_RET0(name, typename); + * + * __static_call_return0; + * * static_call(name)(args...); * static_call_cond(name)(args...); * static_call_update(name, func); * static_call_query(name); * + * EXPORT_STATIC_CALL{,_TRAMP}{,_GPL}() + * * Usage example: * * # Start with the following functions (with identical prototypes): @@ -96,6 +102,33 @@ * To query which function is currently set to be called, use: * * func = static_call_query(name); + * + * + * DEFINE_STATIC_CALL_RET0 / __static_call_return0: + * + * Just like how DEFINE_STATIC_CALL_NULL() / static_call_cond() optimize the + * conditional void function call, DEFINE_STATIC_CALL_RET0 / + * __static_call_return0 optimize the do nothing return 0 function. + * + * This feature is strictly UB per the C standard (since it casts a function + * pointer to a different signature) and relies on the architecture ABI to + * make things work. In particular it relies on Caller Stack-cleanup and the + * whole return register being clobbered for short return values. All normal + * CDECL style ABIs conform. + * + * In particular the x86_64 implementation replaces the 5 byte CALL + * instruction at the callsite with a 5 byte clear of the RAX register, + * completely eliding any function call overhead. + * + * Notably argument setup is unconditional. + * + * + * EXPORT_STATIC_CALL() vs EXPORT_STATIC_CALL_TRAMP(): + * + * The difference is that the _TRAMP variant tries to only export the + * trampoline with the result that a module can use static_call{,_cond}() but + * not static_call_update(). + * */ #include -- cgit v1.2.3 From f97a4a1a3f8769e3452885967955e21c88f3f263 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 17 Aug 2021 09:32:34 +0800 Subject: workqueue: Rename "delayed" (delayed by active management) to "inactive" There are two kinds of "delayed" work items in workqueue subsystem. One is for timer-delayed work items which are visible to workqueue users. The other kind is for work items delayed by active management which can not be directly visible to workqueue users. We mixed the word "delayed" for both kinds and caused somewhat ambiguity. This patch renames the later one (delayed by active management) to "inactive", because it is used for workqueue active management and most of its related symbols are named with "active" or "activate". All "delayed" and "DELAYED" are carefully checked and renamed one by one to avoid accidentally changing the name of the other kind for timer-delayed. No functional change intended. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 4 ++-- kernel/workqueue.c | 58 +++++++++++++++++++++++------------------------ 2 files changed, 31 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 5fcf3d048a5a..3d4edd072a9b 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -29,7 +29,7 @@ void delayed_work_timer_fn(struct timer_list *t); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */ + WORK_STRUCT_INACTIVE_BIT= 1, /* work item is inactive */ WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */ WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK @@ -42,7 +42,7 @@ enum { WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, - WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT, + WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9bce39dba297..9a00ba096032 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -207,7 +207,7 @@ struct pool_workqueue { /* L: nr of in_flight works */ int nr_active; /* L: nr of active works */ int max_active; /* L: max active works */ - struct list_head delayed_works; /* L: delayed works */ + struct list_head inactive_works; /* L: inactive works */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ @@ -1136,7 +1136,7 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) } } -static void pwq_activate_delayed_work(struct work_struct *work) +static void pwq_activate_inactive_work(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); @@ -1144,16 +1144,16 @@ static void pwq_activate_delayed_work(struct work_struct *work) if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); - __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); + __clear_bit(WORK_STRUCT_INACTIVE_BIT, work_data_bits(work)); pwq->nr_active++; } -static void pwq_activate_first_delayed(struct pool_workqueue *pwq) +static void pwq_activate_first_inactive(struct pool_workqueue *pwq) { - struct work_struct *work = list_first_entry(&pwq->delayed_works, + struct work_struct *work = list_first_entry(&pwq->inactive_works, struct work_struct, entry); - pwq_activate_delayed_work(work); + pwq_activate_inactive_work(work); } /** @@ -1176,10 +1176,10 @@ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color) pwq->nr_in_flight[color]--; pwq->nr_active--; - if (!list_empty(&pwq->delayed_works)) { - /* one down, submit a delayed one */ + if (!list_empty(&pwq->inactive_works)) { + /* one down, submit an inactive one */ if (pwq->nr_active < pwq->max_active) - pwq_activate_first_delayed(pwq); + pwq_activate_first_inactive(pwq); } /* is flush in progress and are we at the flushing tip? */ @@ -1281,14 +1281,14 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, debug_work_deactivate(work); /* - * A delayed work item cannot be grabbed directly because + * An inactive work item cannot be grabbed directly because * it might have linked NO_COLOR work items which, if left - * on the delayed_list, will confuse pwq->nr_active + * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Make sure the work * item is activated before grabbing. */ - if (*work_data_bits(work) & WORK_STRUCT_DELAYED) - pwq_activate_delayed_work(work); + if (*work_data_bits(work) & WORK_STRUCT_INACTIVE) + pwq_activate_inactive_work(work); list_del_init(&work->entry); pwq_dec_nr_in_flight(pwq, get_work_color(work)); @@ -1490,8 +1490,8 @@ retry: if (list_empty(worklist)) pwq->pool->watchdog_ts = jiffies; } else { - work_flags |= WORK_STRUCT_DELAYED; - worklist = &pwq->delayed_works; + work_flags |= WORK_STRUCT_INACTIVE; + worklist = &pwq->inactive_works; } debug_work_activate(work); @@ -2530,7 +2530,7 @@ repeat: /* * The above execution of rescued work items could * have created more to rescue through - * pwq_activate_first_delayed() or chained + * pwq_activate_first_inactive() or chained * queueing. Let's put @pwq back on mayday list so * that such back-to-back work items, which may be * being used to relieve memory pressure, don't @@ -2956,7 +2956,7 @@ reflush: bool drained; raw_spin_lock_irq(&pwq->pool->lock); - drained = !pwq->nr_active && list_empty(&pwq->delayed_works); + drained = !pwq->nr_active && list_empty(&pwq->inactive_works); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) @@ -3712,7 +3712,7 @@ static void pwq_unbound_release_workfn(struct work_struct *work) * @pwq: target pool_workqueue * * If @pwq isn't freezing, set @pwq->max_active to the associated - * workqueue's saved_max_active and activate delayed work items + * workqueue's saved_max_active and activate inactive work items * accordingly. If @pwq is freezing, clear @pwq->max_active to zero. */ static void pwq_adjust_max_active(struct pool_workqueue *pwq) @@ -3741,9 +3741,9 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq) pwq->max_active = wq->saved_max_active; - while (!list_empty(&pwq->delayed_works) && + while (!list_empty(&pwq->inactive_works) && pwq->nr_active < pwq->max_active) { - pwq_activate_first_delayed(pwq); + pwq_activate_first_inactive(pwq); kick = true; } @@ -3774,7 +3774,7 @@ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; - INIT_LIST_HEAD(&pwq->delayed_works); + INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn); @@ -4361,7 +4361,7 @@ static bool pwq_busy(struct pool_workqueue *pwq) if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1)) return true; - if (pwq->nr_active || !list_empty(&pwq->delayed_works)) + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) return true; return false; @@ -4557,7 +4557,7 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) else pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); - ret = !list_empty(&pwq->delayed_works); + ret = !list_empty(&pwq->inactive_works); preempt_enable(); rcu_read_unlock(); @@ -4753,11 +4753,11 @@ static void show_pwq(struct pool_workqueue *pwq) pr_cont("\n"); } - if (!list_empty(&pwq->delayed_works)) { + if (!list_empty(&pwq->inactive_works)) { bool comma = false; - pr_info(" delayed:"); - list_for_each_entry(work, &pwq->delayed_works, entry) { + pr_info(" inactive:"); + list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } @@ -4787,7 +4787,7 @@ void show_workqueue_state(void) bool idle = true; for_each_pwq(pwq, wq) { - if (pwq->nr_active || !list_empty(&pwq->delayed_works)) { + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { idle = false; break; } @@ -4799,7 +4799,7 @@ void show_workqueue_state(void) for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, flags); - if (pwq->nr_active || !list_empty(&pwq->delayed_works)) + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) show_pwq(pwq); raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); /* @@ -5182,7 +5182,7 @@ EXPORT_SYMBOL_GPL(work_on_cpu_safe); * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable - * workqueues will queue new works to their delayed_works list instead of + * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: -- cgit v1.2.3 From bdb0a6548d2233dada752109a71bcf4c9b8ae6d6 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 17 Aug 2021 09:32:39 +0800 Subject: workqueue: Remove unused WORK_NO_COLOR WORK_NO_COLOR has no user now, just remove it. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 3d4edd072a9b..2ebef6b1a3d6 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -51,19 +51,14 @@ enum { WORK_STRUCT_STATIC = 0, #endif - /* - * The last color is no color used for works which don't - * participate in workqueue flushing. - */ - WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1, - WORK_NO_COLOR = WORK_NR_COLORS, + WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS), /* not bound to any CPU, prefer the local CPU */ WORK_CPU_UNBOUND = NR_CPUS, /* * Reserve 8 bits off of pwq pointer w/ debugobjects turned off. - * This makes pwqs aligned to 256 bytes and allows 15 workqueue + * This makes pwqs aligned to 256 bytes and allows 16 workqueue * flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + -- cgit v1.2.3 From 69139244806537f9d51364f37fe146bb2ee88a05 Mon Sep 17 00:00:00 2001 From: Amey Narkhede Date: Tue, 17 Aug 2021 23:34:52 +0530 Subject: PCI: Cache PCIe Device Capabilities register Add a new member called devcap in struct pci_dev for caching the PCIe Device Capabilities register to avoid reading PCI_EXP_DEVCAP multiple times. Refactor pcie_has_flr() to use cached device capabilities. Link: https://lore.kernel.org/r/20210817180500.1253-2-ameynarkhede03@gmail.com Signed-off-by: Amey Narkhede Signed-off-by: Bjorn Helgaas Reviewed-by: Raphael Norwitz --- drivers/pci/pci.c | 6 ++---- drivers/pci/probe.c | 5 +++-- include/linux/pci.h | 1 + 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index aacf575c15cf..b7a9f680c513 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "pci.h" DEFINE_MUTEX(pci_slot_mutex); @@ -4630,13 +4631,10 @@ EXPORT_SYMBOL(pci_wait_for_pending_transaction); */ bool pcie_has_flr(struct pci_dev *dev) { - u32 cap; - if (dev->dev_flags & PCI_DEV_FLAGS_NO_FLR_RESET) return false; - pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap); - return cap & PCI_EXP_DEVCAP_FLR; + return FIELD_GET(PCI_EXP_DEVCAP_FLR, dev->devcap) == 1; } EXPORT_SYMBOL_GPL(pcie_has_flr); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 79177ac37880..81eb88ae4301 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "pci.h" #define CARDBUS_LATENCY_TIMER 176 /* secondary latency timer */ @@ -1498,8 +1499,8 @@ void set_pcie_port_type(struct pci_dev *pdev) pdev->pcie_cap = pos; pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, ®16); pdev->pcie_flags_reg = reg16; - pci_read_config_word(pdev, pos + PCI_EXP_DEVCAP, ®16); - pdev->pcie_mpss = reg16 & PCI_EXP_DEVCAP_PAYLOAD; + pci_read_config_dword(pdev, pos + PCI_EXP_DEVCAP, &pdev->devcap); + pdev->pcie_mpss = FIELD_GET(PCI_EXP_DEVCAP_PAYLOAD, pdev->devcap); parent = pci_upstream_bridge(pdev); if (!parent) diff --git a/include/linux/pci.h b/include/linux/pci.h index 540b377ca8f6..1179c0ee2bfb 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -333,6 +333,7 @@ struct pci_dev { struct rcec_ea *rcec_ea; /* RCEC cached endpoint association */ struct pci_dev *rcec; /* Associated RCEC device */ #endif + u32 devcap; /* PCIe Device Capabilities */ u8 pcie_cap; /* PCIe capability offset */ u8 msi_cap; /* MSI capability offset */ u8 msix_cap; /* MSI-X capability offset */ -- cgit v1.2.3 From 56f107d7813f116484019617043393a7753ffcbf Mon Sep 17 00:00:00 2001 From: Amey Narkhede Date: Tue, 17 Aug 2021 23:34:53 +0530 Subject: PCI: Add pcie_reset_flr() with 'probe' argument Most reset methods are of the form "pci_*_reset(dev, probe)". pcie_flr() was an exception because it relied on a separate pcie_has_flr() function instead of taking a "probe" argument. Add "pcie_reset_flr(dev, probe)" to follow the convention. Remove pcie_has_flr(). Some pcie_flr() callers that did not use pcie_has_flr() remain. [bhelgaas: commit log, rework pcie_reset_flr() to use dev->devcap directly] Link: https://lore.kernel.org/r/20210817180500.1253-3-ameynarkhede03@gmail.com Signed-off-by: Amey Narkhede Signed-off-by: Bjorn Helgaas Reviewed-by: Raphael Norwitz --- drivers/crypto/cavium/nitrox/nitrox_main.c | 4 +-- drivers/pci/pci.c | 56 ++++++++++++++++-------------- drivers/pci/pcie/aer.c | 12 +++---- drivers/pci/quirks.c | 9 ++--- include/linux/pci.h | 2 +- 5 files changed, 40 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/crypto/cavium/nitrox/nitrox_main.c b/drivers/crypto/cavium/nitrox/nitrox_main.c index 96bc7b5c6532..2db3fd5815c8 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_main.c +++ b/drivers/crypto/cavium/nitrox/nitrox_main.c @@ -306,9 +306,7 @@ static int nitrox_device_flr(struct pci_dev *pdev) return -ENOMEM; } - /* check flr support */ - if (pcie_has_flr(pdev)) - pcie_flr(pdev); + pcie_reset_flr(pdev, 0); pci_restore_state(pdev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b7a9f680c513..b0a63bdf8207 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4622,29 +4622,12 @@ int pci_wait_for_pending_transaction(struct pci_dev *dev) } EXPORT_SYMBOL(pci_wait_for_pending_transaction); -/** - * pcie_has_flr - check if a device supports function level resets - * @dev: device to check - * - * Returns true if the device advertises support for PCIe function level - * resets. - */ -bool pcie_has_flr(struct pci_dev *dev) -{ - if (dev->dev_flags & PCI_DEV_FLAGS_NO_FLR_RESET) - return false; - - return FIELD_GET(PCI_EXP_DEVCAP_FLR, dev->devcap) == 1; -} -EXPORT_SYMBOL_GPL(pcie_has_flr); - /** * pcie_flr - initiate a PCIe function level reset * @dev: device to reset * - * Initiate a function level reset on @dev. The caller should ensure the - * device supports FLR before calling this function, e.g. by using the - * pcie_has_flr() helper. + * Initiate a function level reset unconditionally on @dev without + * checking any flags and DEVCAP */ int pcie_flr(struct pci_dev *dev) { @@ -4667,6 +4650,28 @@ int pcie_flr(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pcie_flr); +/** + * pcie_reset_flr - initiate a PCIe function level reset + * @dev: device to reset + * @probe: If set, only check if the device can be reset this way. + * + * Initiate a function level reset on @dev. + */ +int pcie_reset_flr(struct pci_dev *dev, int probe) +{ + if (dev->dev_flags & PCI_DEV_FLAGS_NO_FLR_RESET) + return -ENOTTY; + + if (!(dev->devcap & PCI_EXP_DEVCAP_FLR)) + return -ENOTTY; + + if (probe) + return 0; + + return pcie_flr(dev); +} +EXPORT_SYMBOL_GPL(pcie_reset_flr); + static int pci_af_flr(struct pci_dev *dev, int probe) { int pos; @@ -5149,11 +5154,9 @@ int __pci_reset_function_locked(struct pci_dev *dev) rc = pci_dev_specific_reset(dev, 0); if (rc != -ENOTTY) return rc; - if (pcie_has_flr(dev)) { - rc = pcie_flr(dev); - if (rc != -ENOTTY) - return rc; - } + rc = pcie_reset_flr(dev, 0); + if (rc != -ENOTTY) + return rc; rc = pci_af_flr(dev, 0); if (rc != -ENOTTY) return rc; @@ -5184,8 +5187,9 @@ int pci_probe_reset_function(struct pci_dev *dev) rc = pci_dev_specific_reset(dev, 1); if (rc != -ENOTTY) return rc; - if (pcie_has_flr(dev)) - return 0; + rc = pcie_reset_flr(dev, 1); + if (rc != -ENOTTY) + return rc; rc = pci_af_flr(dev, 1); if (rc != -ENOTTY) return rc; diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index df4ba9b384c2..031379deb130 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -1407,13 +1407,11 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) } if (type == PCI_EXP_TYPE_RC_EC || type == PCI_EXP_TYPE_RC_END) { - if (pcie_has_flr(dev)) { - rc = pcie_flr(dev); - pci_info(dev, "has been reset (%d)\n", rc); - } else { - pci_info(dev, "not reset (no FLR support)\n"); - rc = -ENOTTY; - } + rc = pcie_reset_flr(dev, 0); + if (!rc) + pci_info(dev, "has been reset\n"); + else + pci_info(dev, "not reset (no FLR support: %d)\n", rc); } else { rc = pci_bus_error_reset(dev); pci_info(dev, "%s Port link has been reset (%d)\n", diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 6d74386eadc2..a8a167bbc1d7 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3852,7 +3852,7 @@ static int nvme_disable_and_flr(struct pci_dev *dev, int probe) u32 cfg; if (dev->class != PCI_CLASS_STORAGE_EXPRESS || - !pcie_has_flr(dev) || !pci_resource_start(dev, 0)) + pcie_reset_flr(dev, 1) || !pci_resource_start(dev, 0)) return -ENOTTY; if (probe) @@ -3921,13 +3921,10 @@ static int nvme_disable_and_flr(struct pci_dev *dev, int probe) */ static int delay_250ms_after_flr(struct pci_dev *dev, int probe) { - if (!pcie_has_flr(dev)) - return -ENOTTY; - if (probe) - return 0; + return pcie_reset_flr(dev, 1); - pcie_flr(dev); + pcie_reset_flr(dev, 0); msleep(250); diff --git a/include/linux/pci.h b/include/linux/pci.h index 1179c0ee2bfb..1de37e3fc29d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1229,7 +1229,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, enum pci_bus_speed *speed, enum pcie_link_width *width); void pcie_print_link_status(struct pci_dev *dev); -bool pcie_has_flr(struct pci_dev *dev); +int pcie_reset_flr(struct pci_dev *dev, int probe); int pcie_flr(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); -- cgit v1.2.3 From e20afa06244eb5d7fa850f9fe2a78ae17ba96f81 Mon Sep 17 00:00:00 2001 From: Amey Narkhede Date: Tue, 17 Aug 2021 23:34:54 +0530 Subject: PCI: Add array to track reset method ordering Add reset_methods[] in struct pci_dev to keep track of reset mechanisms supported by the device and their ordering. Refactor probing and reset functions to take advantage of calling convention of reset functions. Co-developed-by: Alex Williamson Link: https://lore.kernel.org/r/20210817180500.1253-4-ameynarkhede03@gmail.com Signed-off-by: Alex Williamson Signed-off-by: Amey Narkhede Signed-off-by: Bjorn Helgaas Reviewed-by: Raphael Norwitz --- drivers/pci/pci.c | 94 ++++++++++++++++++++++++++++++----------------------- drivers/pci/pci.h | 8 ++++- drivers/pci/probe.c | 5 ++- include/linux/pci.h | 6 ++++ 4 files changed, 69 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b0a63bdf8207..43a823f8dd69 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -73,6 +73,11 @@ static void pci_dev_d3_sleep(struct pci_dev *dev) msleep(delay); } +bool pci_reset_supported(struct pci_dev *dev) +{ + return dev->reset_methods[0] != 0; +} + #ifdef CONFIG_PCI_DOMAINS int pci_domains_supported = 1; #endif @@ -5117,6 +5122,16 @@ static void pci_dev_restore(struct pci_dev *dev) err_handler->reset_done(dev); } +/* dev->reset_methods[] is a 0-terminated list of indices into this array */ +static const struct pci_reset_fn_method pci_reset_fn_methods[] = { + { }, + { pci_dev_specific_reset, .name = "device_specific" }, + { pcie_reset_flr, .name = "flr" }, + { pci_af_flr, .name = "af_flr" }, + { pci_pm_reset, .name = "pm" }, + { pci_reset_bus_function, .name = "bus" }, +}; + /** * __pci_reset_function_locked - reset a PCI device function while holding * the @dev mutex lock. @@ -5139,65 +5154,64 @@ static void pci_dev_restore(struct pci_dev *dev) */ int __pci_reset_function_locked(struct pci_dev *dev) { - int rc; + int i, m, rc = -ENOTTY; might_sleep(); /* - * A reset method returns -ENOTTY if it doesn't support this device - * and we should try the next method. + * A reset method returns -ENOTTY if it doesn't support this device and + * we should try the next method. * - * If it returns 0 (success), we're finished. If it returns any - * other error, we're also finished: this indicates that further - * reset mechanisms might be broken on the device. + * If it returns 0 (success), we're finished. If it returns any other + * error, we're also finished: this indicates that further reset + * mechanisms might be broken on the device. */ - rc = pci_dev_specific_reset(dev, 0); - if (rc != -ENOTTY) - return rc; - rc = pcie_reset_flr(dev, 0); - if (rc != -ENOTTY) - return rc; - rc = pci_af_flr(dev, 0); - if (rc != -ENOTTY) - return rc; - rc = pci_pm_reset(dev, 0); - if (rc != -ENOTTY) - return rc; - return pci_reset_bus_function(dev, 0); + for (i = 0; i < PCI_NUM_RESET_METHODS; i++) { + m = dev->reset_methods[i]; + if (!m) + return -ENOTTY; + + rc = pci_reset_fn_methods[m].reset_fn(dev, 0); + if (!rc) + return 0; + if (rc != -ENOTTY) + return rc; + } + + return -ENOTTY; } EXPORT_SYMBOL_GPL(__pci_reset_function_locked); /** - * pci_probe_reset_function - check whether the device can be safely reset - * @dev: PCI device to reset + * pci_init_reset_methods - check whether device can be safely reset + * and store supported reset mechanisms. + * @dev: PCI device to check for reset mechanisms * * Some devices allow an individual function to be reset without affecting - * other functions in the same device. The PCI device must be responsive - * to PCI config space in order to use this function. + * other functions in the same device. The PCI device must be in D0-D3hot + * state. * - * Returns 0 if the device function can be reset or negative if the - * device doesn't support resetting a single function. + * Stores reset mechanisms supported by device in reset_methods byte array + * which is a member of struct pci_dev. */ -int pci_probe_reset_function(struct pci_dev *dev) +void pci_init_reset_methods(struct pci_dev *dev) { - int rc; + int m, i, rc; + + BUILD_BUG_ON(ARRAY_SIZE(pci_reset_fn_methods) != PCI_NUM_RESET_METHODS); might_sleep(); - rc = pci_dev_specific_reset(dev, 1); - if (rc != -ENOTTY) - return rc; - rc = pcie_reset_flr(dev, 1); - if (rc != -ENOTTY) - return rc; - rc = pci_af_flr(dev, 1); - if (rc != -ENOTTY) - return rc; - rc = pci_pm_reset(dev, 1); - if (rc != -ENOTTY) - return rc; + i = 0; + for (m = 1; m < PCI_NUM_RESET_METHODS; m++) { + rc = pci_reset_fn_methods[m].reset_fn(dev, 1); + if (!rc) + dev->reset_methods[i++] = m; + else if (rc != -ENOTTY) + break; + } - return pci_reset_bus_function(dev, 1); + dev->reset_methods[i] = 0; } /** diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 93dcdd431072..ebeacb3dbe1e 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -33,7 +33,8 @@ enum pci_mmap_api { int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vmai, enum pci_mmap_api mmap_api); -int pci_probe_reset_function(struct pci_dev *dev); +bool pci_reset_supported(struct pci_dev *dev); +void pci_init_reset_methods(struct pci_dev *dev); int pci_bridge_secondary_bus_reset(struct pci_dev *dev); int pci_bus_error_reset(struct pci_dev *dev); @@ -610,6 +611,11 @@ struct pci_dev_reset_methods { int (*reset)(struct pci_dev *dev, int probe); }; +struct pci_reset_fn_method { + int (*reset_fn)(struct pci_dev *pdev, int probe); + char *name; +}; + #ifdef CONFIG_PCI_QUIRKS int pci_dev_specific_reset(struct pci_dev *dev, int probe); #else diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 81eb88ae4301..817ad149ebd1 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2429,9 +2429,8 @@ static void pci_init_capabilities(struct pci_dev *dev) pci_rcec_init(dev); /* Root Complex Event Collector */ pcie_report_downtraining(dev); - - if (pci_probe_reset_function(dev) == 0) - dev->reset_fn = 1; + pci_init_reset_methods(dev); + dev->reset_fn = pci_reset_supported(dev); } /* diff --git a/include/linux/pci.h b/include/linux/pci.h index 1de37e3fc29d..2faf517d20c1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -49,6 +49,9 @@ PCI_STATUS_SIG_TARGET_ABORT | \ PCI_STATUS_PARITY) +/* Number of reset methods used in pci_reset_fn_methods array in pci.c */ +#define PCI_NUM_RESET_METHODS 6 + /* * The PCI interface treats multi-function devices as independent * devices. The slot/function address of each device is encoded @@ -506,6 +509,9 @@ struct pci_dev { char *driver_override; /* Driver name to force a match */ unsigned long priv_flags; /* Private flags for the PCI driver */ + + /* These methods index pci_reset_fn_methods[] */ + u8 reset_methods[PCI_NUM_RESET_METHODS]; /* In priority order */ }; static inline struct pci_dev *pci_physfn(struct pci_dev *dev) -- cgit v1.2.3 From 4ec36dfeb155b72da8d28ab006a46f2f8b981eac Mon Sep 17 00:00:00 2001 From: Amey Narkhede Date: Tue, 17 Aug 2021 23:34:55 +0530 Subject: PCI: Remove reset_fn field from pci_dev "reset_fn" indicates whether the device supports any reset mechanism. Remove the use of reset_fn in favor of the reset_methods array that tracks supported reset mechanisms of a device and their ordering. The octeon driver incorrectly used reset_fn to detect whether the device supports FLR or not. Use pcie_reset_flr() to probe whether it supports FLR. Co-developed-by: Alex Williamson Link: https://lore.kernel.org/r/20210817180500.1253-5-ameynarkhede03@gmail.com Signed-off-by: Alex Williamson Signed-off-by: Amey Narkhede Signed-off-by: Bjorn Helgaas Reviewed-by: Alex Williamson Reviewed-by: Raphael Norwitz --- drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 2 +- drivers/pci/pci-sysfs.c | 2 +- drivers/pci/pci.c | 6 +++--- drivers/pci/probe.c | 1 - drivers/pci/quirks.c | 2 +- drivers/pci/remove.c | 1 - include/linux/pci.h | 1 - 7 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index ffddb3126a32..d185df5acea6 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -526,7 +526,7 @@ static void octeon_destroy_resources(struct octeon_device *oct) oct->irq_name_storage = NULL; } /* Soft reset the octeon device before exiting */ - if (oct->pci_dev->reset_fn) + if (!pcie_reset_flr(oct->pci_dev, 1)) octeon_pci_flr(oct); else cn23xx_vf_ask_pf_to_do_flr(oct); diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 5d63df7c1820..a1d9b0e83615 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -1367,7 +1367,7 @@ static umode_t pci_dev_reset_attr_is_visible(struct kobject *kobj, { struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj)); - if (!pdev->reset_fn) + if (!pci_reset_supported(pdev)) return 0; return a->mode; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 43a823f8dd69..5ead8826c702 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5234,7 +5234,7 @@ int pci_reset_function(struct pci_dev *dev) { int rc; - if (!dev->reset_fn) + if (!pci_reset_supported(dev)) return -ENOTTY; pci_dev_lock(dev); @@ -5270,7 +5270,7 @@ int pci_reset_function_locked(struct pci_dev *dev) { int rc; - if (!dev->reset_fn) + if (!pci_reset_supported(dev)) return -ENOTTY; pci_dev_save_and_disable(dev); @@ -5293,7 +5293,7 @@ int pci_try_reset_function(struct pci_dev *dev) { int rc; - if (!dev->reset_fn) + if (!pci_reset_supported(dev)) return -ENOTTY; if (!pci_dev_trylock(dev)) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 817ad149ebd1..3325d4682cd6 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2430,7 +2430,6 @@ static void pci_init_capabilities(struct pci_dev *dev) pcie_report_downtraining(dev); pci_init_reset_methods(dev); - dev->reset_fn = pci_reset_supported(dev); } /* diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index a8a167bbc1d7..a1b57b63c624 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5626,7 +5626,7 @@ static void quirk_reset_lenovo_thinkpad_p50_nvgpu(struct pci_dev *pdev) if (pdev->subsystem_vendor != PCI_VENDOR_ID_LENOVO || pdev->subsystem_device != 0x222e || - !pdev->reset_fn) + !pci_reset_supported(pdev)) return; if (pci_enable_device_mem(pdev)) diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index dd12c2fcc7dc..4c54c75050dc 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -19,7 +19,6 @@ static void pci_stop_dev(struct pci_dev *dev) pci_pme_active(dev, false); if (pci_dev_is_added(dev)) { - dev->reset_fn = 0; device_release_driver(&dev->dev); pci_proc_detach_device(dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index 2faf517d20c1..d1f4d248617b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -431,7 +431,6 @@ struct pci_dev { unsigned int state_saved:1; unsigned int is_physfn:1; unsigned int is_virtfn:1; - unsigned int reset_fn:1; unsigned int is_hotplug_bridge:1; unsigned int shpc_managed:1; /* SHPC owned by shpchp */ unsigned int is_thunderbolt:1; /* Thunderbolt controller */ -- cgit v1.2.3 From 791bc41163c51f870972d6c6b82d971ce951096c Mon Sep 17 00:00:00 2001 From: Denis Osterland-Heim Date: Tue, 8 Jun 2021 08:35:53 +0200 Subject: leds: move default_state read from fwnode to core This patch introduces a new function to read initial default_state from fwnode. Suggested-by: Pavel Machek Signed-off-by: Denis Osterland-Heim Signed-off-by: Pavel Machek --- drivers/leds/led-core.c | 15 +++++++++++++++ drivers/leds/leds-gpio.c | 12 ++---------- drivers/leds/leds.h | 1 + include/linux/leds.h | 12 +++++++++--- 4 files changed, 27 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c index 8eb8054ef9c6..4a97cb745788 100644 --- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -477,3 +477,18 @@ int led_compose_name(struct device *dev, struct led_init_data *init_data, return 0; } EXPORT_SYMBOL_GPL(led_compose_name); + +enum led_default_state led_init_default_state_get(struct fwnode_handle *fwnode) +{ + const char *state = NULL; + + if (!fwnode_property_read_string(fwnode, "default-state", &state)) { + if (!strcmp(state, "keep")) + return LEDS_DEFSTATE_KEEP; + if (!strcmp(state, "on")) + return LEDS_DEFSTATE_ON; + } + + return LEDS_DEFSTATE_OFF; +} +EXPORT_SYMBOL_GPL(led_init_default_state_get); diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c index b5d5e22d2d1e..092eb59a7d32 100644 --- a/drivers/leds/leds-gpio.c +++ b/drivers/leds/leds-gpio.c @@ -16,6 +16,7 @@ #include #include #include +#include "leds.h" struct gpio_led_data { struct led_classdev cdev; @@ -144,7 +145,6 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev) device_for_each_child_node(dev, child) { struct gpio_led_data *led_dat = &priv->leds[priv->num_leds]; struct gpio_led led = {}; - const char *state = NULL; /* * Acquire gpiod from DT with uninitialized label, which @@ -161,15 +161,7 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev) led_dat->gpiod = led.gpiod; - if (!fwnode_property_read_string(child, "default-state", - &state)) { - if (!strcmp(state, "keep")) - led.default_state = LEDS_GPIO_DEFSTATE_KEEP; - else if (!strcmp(state, "on")) - led.default_state = LEDS_GPIO_DEFSTATE_ON; - else - led.default_state = LEDS_GPIO_DEFSTATE_OFF; - } + led.default_state = led_init_default_state_get(child); if (fwnode_property_present(child, "retain-state-suspended")) led.retain_state_suspended = 1; diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h index 345062ccabda..aa64757a4d89 100644 --- a/drivers/leds/leds.h +++ b/drivers/leds/leds.h @@ -27,6 +27,7 @@ ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, ssize_t led_trigger_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count); +enum led_default_state led_init_default_state_get(struct fwnode_handle *fwnode); extern struct rw_semaphore leds_list_lock; extern struct list_head leds_list; diff --git a/include/linux/leds.h b/include/linux/leds.h index 329fd914cf24..a0b730be40ad 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -33,6 +33,12 @@ enum led_brightness { LED_FULL = 255, }; +enum led_default_state { + LEDS_DEFSTATE_OFF = 0, + LEDS_DEFSTATE_ON = 1, + LEDS_DEFSTATE_KEEP = 2, +}; + struct led_init_data { /* device fwnode handle */ struct fwnode_handle *fwnode; @@ -520,9 +526,9 @@ struct gpio_led { /* default_state should be one of LEDS_GPIO_DEFSTATE_(ON|OFF|KEEP) */ struct gpio_desc *gpiod; }; -#define LEDS_GPIO_DEFSTATE_OFF 0 -#define LEDS_GPIO_DEFSTATE_ON 1 -#define LEDS_GPIO_DEFSTATE_KEEP 2 +#define LEDS_GPIO_DEFSTATE_OFF LEDS_DEFSTATE_OFF +#define LEDS_GPIO_DEFSTATE_ON LEDS_DEFSTATE_ON +#define LEDS_GPIO_DEFSTATE_KEEP LEDS_DEFSTATE_KEEP struct gpio_led_platform_data { int num_leds; -- cgit v1.2.3 From de3438c47a8ddc75548e62a03736a9321c2b7bac Mon Sep 17 00:00:00 2001 From: Thara Gopinath Date: Mon, 9 Aug 2021 15:15:59 -0400 Subject: firmware: qcom_scm: Introduce SCM calls to access LMh Introduce SCM calls to access/configure limits management hardware(LMH). Reviewed-by: Bjorn Andersson Signed-off-by: Thara Gopinath Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20210809191605.3742979-2-thara.gopinath@linaro.org --- drivers/firmware/qcom_scm.c | 58 +++++++++++++++++++++++++++++++++++++++++++++ drivers/firmware/qcom_scm.h | 4 ++++ include/linux/qcom_scm.h | 14 +++++++++++ 3 files changed, 76 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index 47ea2bd42b10..8a503753fe2a 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -1147,6 +1147,64 @@ int qcom_scm_qsmmu500_wait_safe_toggle(bool en) } EXPORT_SYMBOL(qcom_scm_qsmmu500_wait_safe_toggle); +bool qcom_scm_lmh_dcvsh_available(void) +{ + return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_LMH, QCOM_SCM_LMH_LIMIT_DCVSH); +} +EXPORT_SYMBOL(qcom_scm_lmh_dcvsh_available); + +int qcom_scm_lmh_profile_change(u32 profile_id) +{ + struct qcom_scm_desc desc = { + .svc = QCOM_SCM_SVC_LMH, + .cmd = QCOM_SCM_LMH_LIMIT_PROFILE_CHANGE, + .arginfo = QCOM_SCM_ARGS(1, QCOM_SCM_VAL), + .args[0] = profile_id, + .owner = ARM_SMCCC_OWNER_SIP, + }; + + return qcom_scm_call(__scm->dev, &desc, NULL); +} +EXPORT_SYMBOL(qcom_scm_lmh_profile_change); + +int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, + u64 limit_node, u32 node_id, u64 version) +{ + dma_addr_t payload_phys; + u32 *payload_buf; + int ret, payload_size = 5 * sizeof(u32); + + struct qcom_scm_desc desc = { + .svc = QCOM_SCM_SVC_LMH, + .cmd = QCOM_SCM_LMH_LIMIT_DCVSH, + .arginfo = QCOM_SCM_ARGS(5, QCOM_SCM_RO, QCOM_SCM_VAL, QCOM_SCM_VAL, + QCOM_SCM_VAL, QCOM_SCM_VAL), + .args[1] = payload_size, + .args[2] = limit_node, + .args[3] = node_id, + .args[4] = version, + .owner = ARM_SMCCC_OWNER_SIP, + }; + + payload_buf = dma_alloc_coherent(__scm->dev, payload_size, &payload_phys, GFP_KERNEL); + if (!payload_buf) + return -ENOMEM; + + payload_buf[0] = payload_fn; + payload_buf[1] = 0; + payload_buf[2] = payload_reg; + payload_buf[3] = 1; + payload_buf[4] = payload_val; + + desc.args[0] = payload_phys; + + ret = qcom_scm_call(__scm->dev, &desc, NULL); + + dma_free_coherent(__scm->dev, payload_size, payload_buf, payload_phys); + return ret; +} +EXPORT_SYMBOL(qcom_scm_lmh_dcvsh); + static int qcom_scm_find_dload_address(struct device *dev, u64 *addr) { struct device_node *tcsr; diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h index 632fe3142462..d92156ceb3ac 100644 --- a/drivers/firmware/qcom_scm.h +++ b/drivers/firmware/qcom_scm.h @@ -114,6 +114,10 @@ extern int scm_legacy_call(struct device *dev, const struct qcom_scm_desc *desc, #define QCOM_SCM_SVC_HDCP 0x11 #define QCOM_SCM_HDCP_INVOKE 0x01 +#define QCOM_SCM_SVC_LMH 0x13 +#define QCOM_SCM_LMH_LIMIT_PROFILE_CHANGE 0x01 +#define QCOM_SCM_LMH_LIMIT_DCVSH 0x10 + #define QCOM_SCM_SVC_SMMU_PROGRAM 0x15 #define QCOM_SCM_SMMU_CONFIG_ERRATA1 0x03 #define QCOM_SCM_SMMU_CONFIG_ERRATA1_CLIENT_ALL 0x02 diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 0165824c5128..c0475d1c9885 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -109,6 +109,12 @@ extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp); extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en); + +extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, + u64 limit_node, u32 node_id, u64 version); +extern int qcom_scm_lmh_profile_change(u32 profile_id); +extern bool qcom_scm_lmh_dcvsh_available(void); + #else #include @@ -170,5 +176,13 @@ static inline int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en) { return -ENODEV; } + +static inline int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, + u64 limit_node, u32 node_id, u64 version) + { return -ENODEV; } + +static inline int qcom_scm_lmh_profile_change(u32 profile_id) { return -ENODEV; } + +static inline bool qcom_scm_lmh_dcvsh_available(void) { return -ENODEV; } #endif #endif -- cgit v1.2.3 From 994d2cbb08ca05e3c1af954ec63a3ae32a862ac5 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 17 Aug 2021 17:58:47 +0300 Subject: net: dsa: tag_sja1105: be dsa_loop-safe Add support for tag_sja1105 running on non-sja1105 DSA ports, by making sure that every time we dereference dp->priv, we check the switch's dsa_switch_ops (otherwise we access a struct sja1105_port structure that is in fact something else). This adds an unconditional build-time dependency between sja1105 being built as module => tag_sja1105 must also be built as module. This was there only for PTP before. Some sane defaults must also take place when not running on sja1105 hardware. These are: - sja1105_xmit_tpid: the sja1105 driver uses different VLAN protocols depending on VLAN awareness and switch revision (when an encapsulated VLAN must be sent). Default to 0x8100. - sja1105_rcv_meta_state_machine: this aggregates PTP frames with their metadata timestamp frames. When running on non-sja1105 hardware, don't do that and accept all frames unmodified. - sja1105_defer_xmit: calls sja1105_port_deferred_xmit in sja1105_main.c which writes a management route over SPI. When not running on sja1105 hardware, bypass the SPI write and send the frame as-is. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 5 ++--- include/linux/dsa/sja1105.h | 18 ++++++++++++++++ net/dsa/Kconfig | 2 +- net/dsa/tag_sja1105.c | 39 +++++++++++++++++++++++----------- 4 files changed, 48 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index fe894dc18335..05ba65042b5f 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -28,8 +28,6 @@ #define SJA1105_UNKNOWN_MULTICAST 0x010000000000ull #define SJA1105_DEFAULT_VLAN (VLAN_N_VID - 1) -static const struct dsa_switch_ops sja1105_switch_ops; - static void sja1105_hw_reset(struct gpio_desc *gpio, unsigned int pulse_len, unsigned int startup_delay) { @@ -3100,7 +3098,7 @@ static void sja1105_teardown(struct dsa_switch *ds) sja1105_static_config_free(&priv->static_config); } -static const struct dsa_switch_ops sja1105_switch_ops = { +const struct dsa_switch_ops sja1105_switch_ops = { .get_tag_protocol = sja1105_get_tag_protocol, .setup = sja1105_setup, .teardown = sja1105_teardown, @@ -3149,6 +3147,7 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .port_bridge_tx_fwd_offload = dsa_tag_8021q_bridge_tx_fwd_offload, .port_bridge_tx_fwd_unoffload = dsa_tag_8021q_bridge_tx_fwd_unoffload, }; +EXPORT_SYMBOL_GPL(sja1105_switch_ops); static const struct of_device_id sja1105_dt_ids[]; diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 0eadc7ac44ec..6b0dc9ff92d1 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -88,4 +88,22 @@ static inline void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, #endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ +#if IS_ENABLED(CONFIG_NET_DSA_SJA1105) + +extern const struct dsa_switch_ops sja1105_switch_ops; + +static inline bool dsa_port_is_sja1105(struct dsa_port *dp) +{ + return dp->ds->ops == &sja1105_switch_ops; +} + +#else + +static inline bool dsa_port_is_sja1105(struct dsa_port *dp) +{ + return false; +} + +#endif + #endif /* _NET_DSA_SJA1105_H */ diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 970906eb5b2c..548285539752 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -138,7 +138,7 @@ config NET_DSA_TAG_LAN9303 config NET_DSA_TAG_SJA1105 tristate "Tag driver for NXP SJA1105 switches" - depends on (NET_DSA_SJA1105 && NET_DSA_SJA1105_PTP) || !NET_DSA_SJA1105 || !NET_DSA_SJA1105_PTP + depends on NET_DSA_SJA1105 || !NET_DSA_SJA1105 select PACKING help Say Y or M if you want to enable support for tagging frames with the diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 1406bc41d345..5b80a9049e2c 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -116,9 +116,14 @@ static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) } /* Calls sja1105_port_deferred_xmit in sja1105_main.c */ -static struct sk_buff *sja1105_defer_xmit(struct sja1105_port *sp, +static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) { + struct sja1105_port *sp = dp->priv; + + if (!dsa_port_is_sja1105(dp)) + return skb; + /* Increase refcount so the kfree_skb in dsa_slave_xmit * won't really free the packet. */ @@ -128,8 +133,13 @@ static struct sk_buff *sja1105_defer_xmit(struct sja1105_port *sp, return NULL; } -static u16 sja1105_xmit_tpid(struct sja1105_port *sp) +static u16 sja1105_xmit_tpid(struct dsa_port *dp) { + struct sja1105_port *sp = dp->priv; + + if (unlikely(!dsa_port_is_sja1105(dp))) + return ETH_P_8021Q; + return sp->xmit_tpid; } @@ -155,7 +165,7 @@ static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, */ tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(dp->bridge_num); - return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), tx_vid); + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), tx_vid); } static struct sk_buff *sja1105_xmit(struct sk_buff *skb, @@ -174,9 +184,9 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, * is the .port_deferred_xmit driver callback. */ if (unlikely(sja1105_is_link_local(skb))) - return sja1105_defer_xmit(dp->priv, skb); + return sja1105_defer_xmit(dp, skb); - return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); } @@ -200,7 +210,7 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb, * tag_8021q TX VLANs. */ if (likely(!sja1105_is_link_local(skb))) - return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); skb_push(skb, SJA1110_HEADER_LEN); @@ -265,16 +275,16 @@ static struct sk_buff bool is_link_local, bool is_meta) { - struct sja1105_port *sp; - struct dsa_port *dp; - - dp = dsa_slave_to_port(skb->dev); - sp = dp->priv; - /* Step 1: A timestampable frame was received. * Buffer it until we get its meta frame. */ if (is_link_local) { + struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct sja1105_port *sp = dp->priv; + + if (unlikely(!dsa_port_is_sja1105(dp))) + return skb; + if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) /* Do normal processing. */ return skb; @@ -307,8 +317,13 @@ static struct sk_buff * frame, which serves no further purpose). */ } else if (is_meta) { + struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct sja1105_port *sp = dp->priv; struct sk_buff *stampable_skb; + if (unlikely(!dsa_port_is_sja1105(dp))) + return skb; + /* Drop the meta frame if we're not in the right state * to process it. */ -- cgit v1.2.3 From 4b1327be9fe57443295ae86fe0fcf24a18469e9f Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 17 Aug 2021 12:40:03 -0700 Subject: net-memcg: pass in gfp_t mask to mem_cgroup_charge_skmem() Add gfp_t mask as an input parameter to mem_cgroup_charge_skmem(), to give more control to the networking stack and enable it to change memcg charging behavior. In the future, the networking stack may decide to avoid oom-kills when fallbacks are more appropriate. One behavior change in mem_cgroup_charge_skmem() by this patch is to avoid force charging by default and let the caller decide when and if force charging is needed through the presence or absence of __GFP_NOFAIL. Signed-off-by: Wei Wang Reviewed-by: Shakeel Butt Signed-off-by: David S. Miller --- include/linux/memcontrol.h | 3 ++- include/net/sock.h | 5 +++++ mm/memcontrol.c | 24 +++++++++++------------- net/core/sock.c | 16 ++++++++++++---- net/ipv4/inet_connection_sock.c | 3 ++- net/ipv4/tcp_output.c | 3 ++- 6 files changed, 34 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bfe5c486f4ad..f0ee30881ca9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1581,7 +1581,8 @@ static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; -bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); +bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages, + gfp_t gfp_mask); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; diff --git a/include/net/sock.h b/include/net/sock.h index 6e761451c927..95b25777b53e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2400,6 +2400,11 @@ static inline gfp_t gfp_any(void) return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } +static inline gfp_t gfp_memcg_charge(void) +{ + return in_softirq() ? GFP_NOWAIT : GFP_KERNEL; +} + static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_rcvtimeo; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8ef06f9e0db1..be585ceaba98 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -7048,14 +7048,14 @@ void mem_cgroup_sk_free(struct sock *sk) * mem_cgroup_charge_skmem - charge socket memory * @memcg: memcg to charge * @nr_pages: number of pages to charge + * @gfp_mask: reclaim mode * * Charges @nr_pages to @memcg. Returns %true if the charge fit within - * @memcg's configured limit, %false if the charge had to be forced. + * @memcg's configured limit, %false if it doesn't. */ -bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) +bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages, + gfp_t gfp_mask) { - gfp_t gfp_mask = GFP_KERNEL; - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { struct page_counter *fail; @@ -7063,21 +7063,19 @@ bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) memcg->tcpmem_pressure = 0; return true; } - page_counter_charge(&memcg->tcpmem, nr_pages); memcg->tcpmem_pressure = 1; + if (gfp_mask & __GFP_NOFAIL) { + page_counter_charge(&memcg->tcpmem, nr_pages); + return true; + } return false; } - /* Don't block in the packet receive path */ - if (in_softirq()) - gfp_mask = GFP_NOWAIT; - - mod_memcg_state(memcg, MEMCG_SOCK, nr_pages); - - if (try_charge(memcg, gfp_mask, nr_pages) == 0) + if (try_charge(memcg, gfp_mask, nr_pages) == 0) { + mod_memcg_state(memcg, MEMCG_SOCK, nr_pages); return true; + } - try_charge(memcg, gfp_mask|__GFP_NOFAIL, nr_pages); return false; } diff --git a/net/core/sock.c b/net/core/sock.c index aada649e07e8..950f1e70dbf5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2728,10 +2728,12 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { struct proto *prot = sk->sk_prot; long allocated = sk_memory_allocated_add(sk, amt); + bool memcg_charge = mem_cgroup_sockets_enabled && sk->sk_memcg; bool charged = true; - if (mem_cgroup_sockets_enabled && sk->sk_memcg && - !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt))) + if (memcg_charge && + !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt, + gfp_memcg_charge()))) goto suppress_allocation; /* Under limit. */ @@ -2785,8 +2787,14 @@ suppress_allocation: /* Fail only if socket is _under_ its sndbuf. * In this case we cannot block, so that we have to fail. */ - if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) + if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) { + /* Force charge with __GFP_NOFAIL */ + if (memcg_charge && !charged) { + mem_cgroup_charge_skmem(sk->sk_memcg, amt, + gfp_memcg_charge() | __GFP_NOFAIL); + } return 1; + } } if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged)) @@ -2794,7 +2802,7 @@ suppress_allocation: sk_memory_allocated_sub(sk, amt); - if (mem_cgroup_sockets_enabled && sk->sk_memcg) + if (memcg_charge && charged) mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); return 0; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 754013fa393b..f25d02ad4a8a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -534,7 +534,8 @@ out: atomic_read(&newsk->sk_rmem_alloc)); mem_cgroup_sk_alloc(newsk); if (newsk->sk_memcg && amt) - mem_cgroup_charge_skmem(newsk->sk_memcg, amt); + mem_cgroup_charge_skmem(newsk->sk_memcg, amt, + GFP_KERNEL | __GFP_NOFAIL); release_sock(newsk); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 29553fce8502..6d72f3ea48c4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3373,7 +3373,8 @@ void sk_forced_mem_schedule(struct sock *sk, int size) sk_memory_allocated_add(sk, amt); if (mem_cgroup_sockets_enabled && sk->sk_memcg) - mem_cgroup_charge_skmem(sk->sk_memcg, amt); + mem_cgroup_charge_skmem(sk->sk_memcg, amt, + gfp_memcg_charge() | __GFP_NOFAIL); } /* Send a FIN. The caller locks the socket for us. -- cgit v1.2.3 From 46983fcd67ac5a830d41ebe3755314db67a6dd16 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 11 Aug 2021 13:21:15 +0100 Subject: iommu: Pull IOVA cookie management into the core Now that everyone has converged on iommu-dma for IOMMU_DOMAIN_DMA support, we can abandon the notion of drivers being responsible for the cookie type, and consolidate all the management into the core code. CC: Yong Wu CC: Chunyan Zhang CC: Maxime Ripard Tested-by: Heiko Stuebner Tested-by: Marek Szyprowski Tested-by: Yoshihiro Shimoda Reviewed-by: Jean-Philippe Brucker Reviewed-by: Lu Baolu Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/46a2c0e7419c7d1d931762dc7b6a69fa082d199a.1628682048.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 7 +++++++ include/linux/iommu.h | 3 ++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index f2cda9950bd5..b65fcc66ffa4 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) "iommu: " fmt #include +#include #include #include #include @@ -1946,6 +1947,11 @@ static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, /* Assume all sizes by default; the driver may override this later */ domain->pgsize_bitmap = bus->iommu_ops->pgsize_bitmap; + /* Temporarily avoid -EEXIST while drivers still get their own cookies */ + if (type == IOMMU_DOMAIN_DMA && !domain->iova_cookie && iommu_get_dma_cookie(domain)) { + iommu_domain_free(domain); + domain = NULL; + } return domain; } @@ -1957,6 +1963,7 @@ EXPORT_SYMBOL_GPL(iommu_domain_alloc); void iommu_domain_free(struct iommu_domain *domain) { + iommu_put_dma_cookie(domain); domain->ops->domain_free(domain); } EXPORT_SYMBOL_GPL(iommu_domain_free); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 4997c78e2670..141779d76035 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -40,6 +40,7 @@ struct iommu_domain; struct notifier_block; struct iommu_sva; struct iommu_fault_event; +struct iommu_dma_cookie; /* iommu fault flags */ #define IOMMU_FAULT_READ 0x0 @@ -86,7 +87,7 @@ struct iommu_domain { iommu_fault_handler_t handler; void *handler_token; struct iommu_domain_geometry geometry; - void *iova_cookie; + struct iommu_dma_cookie *iova_cookie; }; enum iommu_cap { -- cgit v1.2.3 From 7a7c5badf85806eab75e31ab8d45021f1545b0e3 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 11 Aug 2021 13:21:28 +0100 Subject: iommu: Indicate queued flushes via gather data Since iommu_iotlb_gather exists to help drivers optimise flushing for a given unmap request, it is also the logical place to indicate whether the unmap is strict or not, and thus help them further optimise for whether to expect a sync or a flush_all subsequently. As part of that, it also seems fair to make the flush queue code take responsibility for enforcing the really subtle ordering requirement it brings, so that we don't need to worry about forgetting that if new drivers want to add flush queue support, and can consolidate the existing versions. While we're adding to the kerneldoc, also fill in some info for @freelist which was overlooked previously. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/bf5f8e2ad84e48c712ccbf80fa8c610594c7595f.1628682049.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 1 + drivers/iommu/iova.c | 7 +++++++ include/linux/iommu.h | 8 +++++++- 3 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index afaa1f9b5935..1eacbbdf601c 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -481,6 +481,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr, dma_addr -= iova_off; size = iova_align(iovad, size + iova_off); iommu_iotlb_gather_init(&iotlb_gather); + iotlb_gather.queued = cookie->fq_domain; unmapped = iommu_unmap_fast(domain, dma_addr, size, &iotlb_gather); WARN_ON(unmapped != size); diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index b6cf5f16123b..2ad73fb2e94e 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -637,6 +637,13 @@ void queue_iova(struct iova_domain *iovad, unsigned long flags; unsigned idx; + /* + * Order against the IOMMU driver's pagetable update from unmapping + * @pte, to guarantee that iova_domain_flush() observes that if called + * from a different CPU before we release the lock below. + */ + smp_wmb(); + spin_lock_irqsave(&fq->lock, flags); /* diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 141779d76035..f7679f6684b1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -161,16 +161,22 @@ enum iommu_dev_features { * @start: IOVA representing the start of the range to be flushed * @end: IOVA representing the end of the range to be flushed (inclusive) * @pgsize: The interval at which to perform the flush + * @freelist: Removed pages to free after sync + * @queued: Indicates that the flush will be queued * * This structure is intended to be updated by multiple calls to the * ->unmap() function in struct iommu_ops before eventually being passed - * into ->iotlb_sync(). + * into ->iotlb_sync(). Drivers can add pages to @freelist to be freed after + * ->iotlb_sync() or ->iotlb_flush_all() have cleared all cached references to + * them. @queued is set to indicate when ->iotlb_flush_all() will be called + * later instead of ->iotlb_sync(), so drivers may optimise accordingly. */ struct iommu_iotlb_gather { unsigned long start; unsigned long end; size_t pgsize; struct page *freelist; + bool queued; }; /** -- cgit v1.2.3 From a8e5f04458c4e496eada2b029ce96713bb6c388d Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 11 Aug 2021 13:21:29 +0100 Subject: iommu/io-pgtable: Remove non-strict quirk IO_PGTABLE_QUIRK_NON_STRICT was never a very comfortable fit, since it's not a quirk of the pagetable format itself. Now that we have a more appropriate way to convey non-strict unmaps, though, this last of the non-quirk quirks can also go, and with the flush queue code also now enforcing its own ordering we can have a lovely cleanup all round. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/155b5c621cd8936472e273a8b07a182f62c6c20d.1628682049.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 3 --- drivers/iommu/arm/arm-smmu/arm-smmu.c | 3 --- drivers/iommu/io-pgtable-arm-v7s.c | 12 ++---------- drivers/iommu/io-pgtable-arm.c | 12 ++---------- include/linux/io-pgtable.h | 5 ----- 5 files changed, 4 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index ee53a841815e..69801866090c 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2174,9 +2174,6 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain, .iommu_dev = smmu->dev, }; - if (!iommu_get_dma_strict(domain)) - pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT; - pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain); if (!pgtbl_ops) return -ENOMEM; diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 970d9e4dcd69..a325d4769c17 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -765,9 +765,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, .iommu_dev = smmu->dev, }; - if (!iommu_get_dma_strict(domain)) - pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT; - if (smmu->impl && smmu->impl->init_context) { ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg, dev); if (ret) diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 5db90d7ce2ec..e84478d39705 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -700,14 +700,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, ARM_V7S_BLOCK_SIZE(lvl + 1)); ptep = iopte_deref(pte[i], lvl, data); __arm_v7s_free_table(ptep, lvl + 1, data); - } else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) { - /* - * Order the PTE update against queueing the IOVA, to - * guarantee that a flush callback from a different CPU - * has observed it before the TLBIALL can be issued. - */ - smp_wmb(); - } else { + } else if (!gather->queued) { io_pgtable_tlb_add_page(iop, gather, iova, blk_size); } iova += blk_size; @@ -791,8 +784,7 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_PERMS | - IO_PGTABLE_QUIRK_ARM_MTK_EXT | - IO_PGTABLE_QUIRK_NON_STRICT)) + IO_PGTABLE_QUIRK_ARM_MTK_EXT)) return NULL; /* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */ diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 053df4048a29..48a5bd8f571d 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -638,14 +638,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, io_pgtable_tlb_flush_walk(iop, iova + i * size, size, ARM_LPAE_GRANULE(data)); __arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data)); - } else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) { - /* - * Order the PTE update against queueing the IOVA, to - * guarantee that a flush callback from a different CPU - * has observed it before the TLBIALL can be issued. - */ - smp_wmb(); - } else { + } else if (!gather->queued) { io_pgtable_tlb_add_page(iop, gather, iova + i * size, size); } @@ -825,7 +818,6 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) bool tg1; if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | - IO_PGTABLE_QUIRK_NON_STRICT | IO_PGTABLE_QUIRK_ARM_TTBR1 | IO_PGTABLE_QUIRK_ARM_OUTER_WBWA)) return NULL; @@ -929,7 +921,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) typeof(&cfg->arm_lpae_s2_cfg.vtcr) vtcr = &cfg->arm_lpae_s2_cfg.vtcr; /* The NS quirk doesn't apply at stage 2 */ - if (cfg->quirks & ~(IO_PGTABLE_QUIRK_NON_STRICT)) + if (cfg->quirks) return NULL; data = arm_lpae_alloc_pgtable(cfg); diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index c43f3b899d2a..9ba6d9ea316e 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -73,10 +73,6 @@ struct io_pgtable_cfg { * to support up to 35 bits PA where the bit32, bit33 and bit34 are * encoded in the bit9, bit4 and bit5 of the PTE respectively. * - * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs - * on unmap, for DMA domains using the flush queue mechanism for - * delayed invalidation. - * * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table * for use in the upper half of a split address space. * @@ -86,7 +82,6 @@ struct io_pgtable_cfg { #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) #define IO_PGTABLE_QUIRK_ARM_MTK_EXT BIT(3) - #define IO_PGTABLE_QUIRK_NON_STRICT BIT(4) #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) #define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA BIT(6) unsigned long quirks; -- cgit v1.2.3 From bf3aed4660c6e3c44c69f07d8927ee5a22a952ac Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 11 Aug 2021 13:21:30 +0100 Subject: iommu: Introduce explicit type for non-strict DMA domains Promote the difference between strict and non-strict DMA domains from an internal detail to a distinct domain feature and type, to pave the road for exposing it through the sysfs default domain interface. Reviewed-by: Lu Baolu Reviewed-by: Jean-Philippe Brucker Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/08cd2afaf6b63c58ad49acec3517c9b32c2bb946.1628682049.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 2 +- drivers/iommu/iommu.c | 8 ++++++-- include/linux/iommu.h | 11 +++++++++++ 3 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 1eacbbdf601c..17ac3dd4f23e 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1319,7 +1319,7 @@ void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit) * The IOMMU core code allocates the default DMA domain, which the * underlying IOMMU driver needs to support via the dma-iommu layer. */ - if (domain->type == IOMMU_DOMAIN_DMA) { + if (iommu_is_dma_domain(domain)) { if (iommu_dma_init_domain(domain, dma_base, dma_limit, dev)) goto out_err; dev->dma_ops = &iommu_dma_ops; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index b65fcc66ffa4..17d6728f5a09 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -115,6 +115,7 @@ static const char *iommu_domain_type_str(unsigned int t) case IOMMU_DOMAIN_UNMANAGED: return "Unmanaged"; case IOMMU_DOMAIN_DMA: + case IOMMU_DOMAIN_DMA_FQ: return "Translated"; default: return "Unknown"; @@ -552,6 +553,9 @@ static ssize_t iommu_group_show_type(struct iommu_group *group, case IOMMU_DOMAIN_DMA: type = "DMA\n"; break; + case IOMMU_DOMAIN_DMA_FQ: + type = "DMA-FQ\n"; + break; } } mutex_unlock(&group->mutex); @@ -765,7 +769,7 @@ static int iommu_create_device_direct_mappings(struct iommu_group *group, unsigned long pg_size; int ret = 0; - if (!domain || domain->type != IOMMU_DOMAIN_DMA) + if (!domain || !iommu_is_dma_domain(domain)) return 0; BUG_ON(!domain->pgsize_bitmap); @@ -1948,7 +1952,7 @@ static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, domain->pgsize_bitmap = bus->iommu_ops->pgsize_bitmap; /* Temporarily avoid -EEXIST while drivers still get their own cookies */ - if (type == IOMMU_DOMAIN_DMA && !domain->iova_cookie && iommu_get_dma_cookie(domain)) { + if (iommu_is_dma_domain(domain) && !domain->iova_cookie && iommu_get_dma_cookie(domain)) { iommu_domain_free(domain); domain = NULL; } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index f7679f6684b1..5629ae42951f 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -61,6 +61,7 @@ struct iommu_domain_geometry { #define __IOMMU_DOMAIN_DMA_API (1U << 1) /* Domain for use in DMA-API implementation */ #define __IOMMU_DOMAIN_PT (1U << 2) /* Domain is identity mapped */ +#define __IOMMU_DOMAIN_DMA_FQ (1U << 3) /* DMA-API uses flush queue */ /* * This are the possible domain-types @@ -73,12 +74,17 @@ struct iommu_domain_geometry { * IOMMU_DOMAIN_DMA - Internally used for DMA-API implementations. * This flag allows IOMMU drivers to implement * certain optimizations for these domains + * IOMMU_DOMAIN_DMA_FQ - As above, but definitely using batched TLB + * invalidation. */ #define IOMMU_DOMAIN_BLOCKED (0U) #define IOMMU_DOMAIN_IDENTITY (__IOMMU_DOMAIN_PT) #define IOMMU_DOMAIN_UNMANAGED (__IOMMU_DOMAIN_PAGING) #define IOMMU_DOMAIN_DMA (__IOMMU_DOMAIN_PAGING | \ __IOMMU_DOMAIN_DMA_API) +#define IOMMU_DOMAIN_DMA_FQ (__IOMMU_DOMAIN_PAGING | \ + __IOMMU_DOMAIN_DMA_API | \ + __IOMMU_DOMAIN_DMA_FQ) struct iommu_domain { unsigned type; @@ -90,6 +96,11 @@ struct iommu_domain { struct iommu_dma_cookie *iova_cookie; }; +static inline bool iommu_is_dma_domain(struct iommu_domain *domain) +{ + return domain->type & __IOMMU_DOMAIN_DMA_API; +} + enum iommu_cap { IOMMU_CAP_CACHE_COHERENCY, /* IOMMU can enforce cache coherent DMA transactions */ -- cgit v1.2.3 From c208916fe6c7b84e3ec95cd91853039596eeb2cf Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 11 Aug 2021 13:21:34 +0100 Subject: iommu: Express DMA strictness via the domain type Eliminate the iommu_get_dma_strict() indirection and pipe the information through the domain type from the beginning. Besides the flow simplification this also has several nice side-effects: - Automatically implies strict mode for untrusted devices by virtue of their IOMMU_DOMAIN_DMA override. - Ensures that we only end up using flush queues for drivers which are aware of them and can actually benefit. - Allows us to handle flush queue init failure by falling back to strict mode instead of leaving it to possibly blow up later. Reviewed-by: Lu Baolu Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/47083d69155577f1367877b1594921948c366eb3.1628682049.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 10 ++++++---- drivers/iommu/iommu.c | 14 +++++--------- include/linux/iommu.h | 1 - 3 files changed, 11 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 17ac3dd4f23e..b7ae855c1e89 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -370,13 +370,15 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, init_iova_domain(iovad, 1UL << order, base_pfn); - if (!cookie->fq_domain && !dev_is_untrusted(dev) && - domain->ops->flush_iotlb_all && !iommu_get_dma_strict(domain)) { + /* If the FQ fails we can simply fall back to strict mode */ + if (domain->type == IOMMU_DOMAIN_DMA_FQ && !cookie->fq_domain) { if (init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all, - iommu_dma_entry_dtor)) + iommu_dma_entry_dtor)) { pr_warn("iova flush queue initialization failed\n"); - else + domain->type = IOMMU_DOMAIN_DMA; + } else { cookie->fq_domain = domain; + } } return iova_reserve_iommu_regions(dev, domain); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 17d6728f5a09..e09f0d433683 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -136,6 +136,9 @@ static int __init iommu_subsys_init(void) } } + if (!iommu_default_passthrough() && !iommu_dma_strict) + iommu_def_domain_type = IOMMU_DOMAIN_DMA_FQ; + pr_info("Default domain type: %s %s\n", iommu_domain_type_str(iommu_def_domain_type), (iommu_cmd_line & IOMMU_CMD_LINE_DMA_API) ? @@ -355,17 +358,10 @@ early_param("iommu.strict", iommu_dma_setup); void iommu_set_dma_strict(void) { iommu_dma_strict = true; + if (iommu_def_domain_type == IOMMU_DOMAIN_DMA_FQ) + iommu_def_domain_type = IOMMU_DOMAIN_DMA; } -bool iommu_get_dma_strict(struct iommu_domain *domain) -{ - /* only allow lazy flushing for DMA domains */ - if (domain->type == IOMMU_DOMAIN_DMA) - return iommu_dma_strict; - return true; -} -EXPORT_SYMBOL_GPL(iommu_get_dma_strict); - static ssize_t iommu_group_attr_show(struct kobject *kobj, struct attribute *__attr, char *buf) { diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5629ae42951f..923a8d1c5e39 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -504,7 +504,6 @@ int iommu_set_pgtable_quirks(struct iommu_domain *domain, unsigned long quirks); void iommu_set_dma_strict(void); -bool iommu_get_dma_strict(struct iommu_domain *domain); extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags); -- cgit v1.2.3 From 452e69b58c2889e5546edb92d9e66285410f7463 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 11 Aug 2021 13:21:38 +0100 Subject: iommu: Allow enabling non-strict mode dynamically Allocating and enabling a flush queue is in fact something we can reasonably do while a DMA domain is active, without having to rebuild it from scratch. Thus we can allow a strict -> non-strict transition from sysfs without requiring to unbind the device's driver, which is of particular interest to users who want to make selective relaxations to critical devices like the one serving their root filesystem. Disabling and draining a queue also seems technically possible to achieve without rebuilding the whole domain, but would certainly be more involved. Furthermore there's not such a clear use-case for tightening up security *after* the device may already have done whatever it is that you don't trust it not to do, so we only consider the relaxation case. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/d652966348c78457c38bf18daf369272a4ebc2c9.1628682049.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 47 ++++++++++++++++++++++++++++++++--------------- drivers/iommu/iommu.c | 17 +++++++++++++---- drivers/iommu/iova.c | 11 ++++++----- include/linux/dma-iommu.h | 6 ++++++ 4 files changed, 57 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index b7ae855c1e89..bac7370ead3e 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -317,6 +317,30 @@ static bool dev_is_untrusted(struct device *dev) return dev_is_pci(dev) && to_pci_dev(dev)->untrusted; } +/* sysfs updates are serialised by the mutex of the group owning @domain */ +int iommu_dma_init_fq(struct iommu_domain *domain) +{ + struct iommu_dma_cookie *cookie = domain->iova_cookie; + int ret; + + if (cookie->fq_domain) + return 0; + + ret = init_iova_flush_queue(&cookie->iovad, iommu_dma_flush_iotlb_all, + iommu_dma_entry_dtor); + if (ret) { + pr_warn("iova flush queue initialization failed\n"); + return ret; + } + /* + * Prevent incomplete iovad->fq being observable. Pairs with path from + * __iommu_dma_unmap() through iommu_dma_free_iova() to queue_iova() + */ + smp_wmb(); + WRITE_ONCE(cookie->fq_domain, domain); + return 0; +} + /** * iommu_dma_init_domain - Initialise a DMA mapping domain * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() @@ -371,15 +395,8 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, init_iova_domain(iovad, 1UL << order, base_pfn); /* If the FQ fails we can simply fall back to strict mode */ - if (domain->type == IOMMU_DOMAIN_DMA_FQ && !cookie->fq_domain) { - if (init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all, - iommu_dma_entry_dtor)) { - pr_warn("iova flush queue initialization failed\n"); - domain->type = IOMMU_DOMAIN_DMA; - } else { - cookie->fq_domain = domain; - } - } + if (domain->type == IOMMU_DOMAIN_DMA_FQ && iommu_dma_init_fq(domain)) + domain->type = IOMMU_DOMAIN_DMA; return iova_reserve_iommu_regions(dev, domain); } @@ -454,17 +471,17 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain, } static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie, - dma_addr_t iova, size_t size, struct page *freelist) + dma_addr_t iova, size_t size, struct iommu_iotlb_gather *gather) { struct iova_domain *iovad = &cookie->iovad; /* The MSI case is only ever cleaning up its most recent allocation */ if (cookie->type == IOMMU_DMA_MSI_COOKIE) cookie->msi_iova -= size; - else if (cookie->fq_domain) /* non-strict mode */ + else if (gather && gather->queued) queue_iova(iovad, iova_pfn(iovad, iova), size >> iova_shift(iovad), - (unsigned long)freelist); + (unsigned long)gather->freelist); else free_iova_fast(iovad, iova_pfn(iovad, iova), size >> iova_shift(iovad)); @@ -483,14 +500,14 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr, dma_addr -= iova_off; size = iova_align(iovad, size + iova_off); iommu_iotlb_gather_init(&iotlb_gather); - iotlb_gather.queued = cookie->fq_domain; + iotlb_gather.queued = READ_ONCE(cookie->fq_domain); unmapped = iommu_unmap_fast(domain, dma_addr, size, &iotlb_gather); WARN_ON(unmapped != size); - if (!cookie->fq_domain) + if (!iotlb_gather.queued) iommu_iotlb_sync(domain, &iotlb_gather); - iommu_dma_free_iova(cookie, dma_addr, size, iotlb_gather.freelist); + iommu_dma_free_iova(cookie, dma_addr, size, &iotlb_gather); } static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr, diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 0e1f791873fa..feb66d937c9c 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -3204,6 +3204,14 @@ static int iommu_change_dev_def_domain(struct iommu_group *group, goto out; } + /* We can bring up a flush queue without tearing down the domain */ + if (type == IOMMU_DOMAIN_DMA_FQ && prev_dom->type == IOMMU_DOMAIN_DMA) { + ret = iommu_dma_init_fq(prev_dom); + if (!ret) + prev_dom->type = IOMMU_DOMAIN_DMA_FQ; + goto out; + } + /* Sets group->default_domain to the newly allocated domain */ ret = iommu_group_alloc_default_domain(dev->bus, group, type); if (ret) @@ -3244,9 +3252,9 @@ out: } /* - * Changing the default domain through sysfs requires the users to ubind the - * drivers from the devices in the iommu group. Return failure if this doesn't - * meet. + * Changing the default domain through sysfs requires the users to unbind the + * drivers from the devices in the iommu group, except for a DMA -> DMA-FQ + * transition. Return failure if this isn't met. * * We need to consider the race between this and the device release path. * device_lock(dev) is used here to guarantee that the device release path @@ -3322,7 +3330,8 @@ static ssize_t iommu_group_store_type(struct iommu_group *group, /* Check if the device in the group still has a driver bound to it */ device_lock(dev); - if (device_is_bound(dev)) { + if (device_is_bound(dev) && !(req_type == IOMMU_DOMAIN_DMA_FQ && + group->default_domain->type == IOMMU_DOMAIN_DMA)) { pr_err_ratelimited("Device is still bound to driver\n"); ret = -EBUSY; goto out; diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 2ad73fb2e94e..0af42fb93a49 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -121,8 +121,6 @@ int init_iova_flush_queue(struct iova_domain *iovad, spin_lock_init(&fq->lock); } - smp_wmb(); - iovad->fq = queue; timer_setup(&iovad->fq_timer, fq_flush_timeout, 0); @@ -633,17 +631,20 @@ void queue_iova(struct iova_domain *iovad, unsigned long pfn, unsigned long pages, unsigned long data) { - struct iova_fq *fq = raw_cpu_ptr(iovad->fq); + struct iova_fq *fq; unsigned long flags; unsigned idx; /* * Order against the IOMMU driver's pagetable update from unmapping * @pte, to guarantee that iova_domain_flush() observes that if called - * from a different CPU before we release the lock below. + * from a different CPU before we release the lock below. Full barrier + * so it also pairs with iommu_dma_init_fq() to avoid seeing partially + * written fq state here. */ - smp_wmb(); + smp_mb(); + fq = raw_cpu_ptr(iovad->fq); spin_lock_irqsave(&fq->lock, flags); /* diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index 758ca4694257..24607dc3c2ac 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -20,6 +20,7 @@ void iommu_put_dma_cookie(struct iommu_domain *domain); /* Setup call for arch DMA mapping code */ void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); +int iommu_dma_init_fq(struct iommu_domain *domain); /* The DMA API isn't _quite_ the whole story, though... */ /* @@ -54,6 +55,11 @@ static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, { } +static inline int iommu_dma_init_fq(struct iommu_domain *domain) +{ + return -EINVAL; +} + static inline int iommu_get_dma_cookie(struct iommu_domain *domain) { return -ENODEV; -- cgit v1.2.3 From c049742fbc71129c481a6d5e52392b9aa482cc9e Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Wed, 18 Aug 2021 07:18:19 +0300 Subject: regulator: Minor regulator documentation fixes. The newly added regulator ramp-delay specifiers in regulator desc lacked the documentation. Add some. Also fix a typo. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/20210818041513.GA2408290@dc7vkhyh15000m40t6jht-3.rev.dnainternet.fi Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 5447a6b33fa0..92bf7584a2f0 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -337,6 +337,12 @@ enum regulator_type { * @pull_down_val_on: Enabling value for control when using regmap * set_pull_down * + * @ramp_reg: Register for controlling the regulator ramp-rate. + * @ramp_mask: Bitmask for the ramp-rate control register. + * @ramp_delay_table: Table for mapping the regulator ramp-rate values. Values + * should be given in units of V/S (uV/uS). See the + * regulator_set_ramp_delay_regmap(). + * * @enable_time: Time taken for initial enable of regulator (in uS). * @off_on_delay: guard time (in uS), before re-enabling a regulator * @@ -462,7 +468,7 @@ struct regulator_err_state { }; /** - * struct regulator_irq_data - regulator error/notification status date + * struct regulator_irq_data - regulator error/notification status data * * @states: Status structs for each of the associated regulators. * @num_states: Amount of associated regulators. -- cgit v1.2.3 From d633b8a702ab2eb4ef9263f1ab1610bb8cdf71a5 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 16 Aug 2021 10:44:53 +0900 Subject: libata: print feature list on device scan Print a list of features supported by a drive when it is configured in ata_dev_configure() using the new function ata_dev_print_features(). The features printed are not already advertized and are: trusted send-recev support, device attention support, device sleep support, NCQ send-recv support and NCQ priority support. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20210816014456.2191776-9-damien.lemoal@wdc.com Signed-off-by: Jens Axboe --- drivers/ata/libata-core.c | 17 +++++++++++++++++ include/linux/libata.h | 4 ++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 5befe6ce6039..b8459c54f739 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2433,6 +2433,20 @@ static void ata_dev_config_devslp(struct ata_device *dev) } } +static void ata_dev_print_features(struct ata_device *dev) +{ + if (!(dev->flags & ATA_DFLAG_FEATURES_MASK)) + return; + + ata_dev_info(dev, + "Features:%s%s%s%s%s\n", + dev->flags & ATA_DFLAG_TRUSTED ? " Trust" : "", + dev->flags & ATA_DFLAG_DA ? " Dev-Attention" : "", + dev->flags & ATA_DFLAG_DEVSLP ? " Dev-Sleep" : "", + dev->flags & ATA_DFLAG_NCQ_SEND_RECV ? " NCQ-sndrcv" : "", + dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : ""); +} + /** * ata_dev_configure - Configure the specified ATA/ATAPI device * @dev: Target device to configure @@ -2595,6 +2609,9 @@ int ata_dev_configure(struct ata_device *dev) ata_dev_config_zac(dev); ata_dev_config_trusted(dev); dev->cdb_len = 32; + + if (ata_msg_drv(ap) && print_info) + ata_dev_print_features(dev); } /* ATAPI-specific feature tests */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 3fcd24236793..b23f28cfc8e0 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -161,6 +161,10 @@ enum { ATA_DFLAG_D_SENSE = (1 << 29), /* Descriptor sense requested */ ATA_DFLAG_ZAC = (1 << 30), /* ZAC device */ + ATA_DFLAG_FEATURES_MASK = ATA_DFLAG_TRUSTED | ATA_DFLAG_DA | \ + ATA_DFLAG_DEVSLP | ATA_DFLAG_NCQ_SEND_RECV | \ + ATA_DFLAG_NCQ_PRIO, + ATA_DEV_UNKNOWN = 0, /* unknown device */ ATA_DEV_ATA = 1, /* ATA device */ ATA_DEV_ATA_UNSUP = 2, /* ATA device (unsupported) */ -- cgit v1.2.3 From 5f91b8f54874300a8e3c6c89f39ce5a74a449f2c Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 16 Aug 2021 10:44:54 +0900 Subject: libata: Introduce ncq_prio_supported sysfs sttribute Currently, the only way a user can determine if a SATA device supports NCQ priority is to try to enable the use of this feature using the ncq_prio_enable sysfs device attribute. If enabling the feature fails, it is because the device does not support NCQ priority. Otherwise, the feature is enabled and success indicates that the device supports NCQ priority. Improve this odd interface by introducing the read-only ncq_prio_supported sysfs device attribute to indicate if a SATA device supports NCQ priority. The value of this attribute reflects the status of device flag ATA_DFLAG_NCQ_PRIO, which is set only for devices supporting NCQ priority. Add this new sysfs attribute to the device attributes group of libahci and libata-sata. Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20210816014456.2191776-10-damien.lemoal@wdc.com Signed-off-by: Jens Axboe --- drivers/ata/libahci.c | 1 + drivers/ata/libata-sata.c | 25 +++++++++++++++++++++++++ include/linux/libata.h | 1 + 3 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index fec2e9754aed..5b3fa2cbe722 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -125,6 +125,7 @@ EXPORT_SYMBOL_GPL(ahci_shost_attrs); struct device_attribute *ahci_sdev_attrs[] = { &dev_attr_sw_activity, &dev_attr_unload_heads, + &dev_attr_ncq_prio_supported, &dev_attr_ncq_prio_enable, NULL }; diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index dc397ebda089..8f3ff830ab0c 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -834,6 +834,30 @@ DEVICE_ATTR(link_power_management_policy, S_IRUGO | S_IWUSR, ata_scsi_lpm_show, ata_scsi_lpm_store); EXPORT_SYMBOL_GPL(dev_attr_link_power_management_policy); +static ssize_t ata_ncq_prio_supported_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct scsi_device *sdev = to_scsi_device(device); + struct ata_port *ap = ata_shost_to_port(sdev->host); + struct ata_device *dev; + bool ncq_prio_supported; + int rc = 0; + + spin_lock_irq(ap->lock); + dev = ata_scsi_find_dev(ap, sdev); + if (!dev) + rc = -ENODEV; + else + ncq_prio_supported = dev->flags & ATA_DFLAG_NCQ_PRIO; + spin_unlock_irq(ap->lock); + + return rc ? rc : sysfs_emit(buf, "%u\n", ncq_prio_supported); +} + +DEVICE_ATTR(ncq_prio_supported, S_IRUGO, ata_ncq_prio_supported_show, NULL); +EXPORT_SYMBOL_GPL(dev_attr_ncq_prio_supported); + static ssize_t ata_ncq_prio_enable_show(struct device *device, struct device_attribute *attr, char *buf) @@ -901,6 +925,7 @@ EXPORT_SYMBOL_GPL(dev_attr_ncq_prio_enable); struct device_attribute *ata_ncq_sdev_attrs[] = { &dev_attr_unload_heads, &dev_attr_ncq_prio_enable, + &dev_attr_ncq_prio_supported, NULL }; EXPORT_SYMBOL_GPL(ata_ncq_sdev_attrs); diff --git a/include/linux/libata.h b/include/linux/libata.h index b23f28cfc8e0..a2d1bae7900b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -539,6 +539,7 @@ typedef void (*ata_postreset_fn_t)(struct ata_link *link, unsigned int *classes) extern struct device_attribute dev_attr_unload_heads; #ifdef CONFIG_SATA_HOST extern struct device_attribute dev_attr_link_power_management_policy; +extern struct device_attribute dev_attr_ncq_prio_supported; extern struct device_attribute dev_attr_ncq_prio_enable; extern struct device_attribute dev_attr_em_message_type; extern struct device_attribute dev_attr_em_message; -- cgit v1.2.3 From a553a835ca57668b0d9907d8ec2507ec51292d9a Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 11 Aug 2021 12:36:59 +0900 Subject: block: change ioprio_valid() to an inline function Change the ioprio_valid() macro in include/usapi/linux/ioprio.h to an inline function declared on the kernel side in include/linux/ioprio.h. Also improve checks on the class value by checking the upper bound value. Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20210811033702.368488-4-damien.lemoal@wdc.com Signed-off-by: Jens Axboe --- include/linux/ioprio.h | 10 ++++++++++ include/uapi/linux/ioprio.h | 2 -- 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index ef9ad4fb245f..2ee3373684b1 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -8,6 +8,16 @@ #include +/* + * Check that a priority value has a valid class. + */ +static inline bool ioprio_valid(unsigned short ioprio) +{ + unsigned short class = IOPRIO_PRIO_CLASS(ioprio); + + return class > IOPRIO_CLASS_NONE && class <= IOPRIO_CLASS_IDLE; +} + /* * if process has set io priority explicitly, use that. if not, convert * the cpu scheduler nice value to an io priority diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h index 6b735854aebd..5064e230374c 100644 --- a/include/uapi/linux/ioprio.h +++ b/include/uapi/linux/ioprio.h @@ -27,8 +27,6 @@ enum { IOPRIO_CLASS_IDLE, }; -#define ioprio_valid(mask) (IOPRIO_PRIO_CLASS((mask)) != IOPRIO_CLASS_NONE) - /* * 8 best effort priority levels are supported */ -- cgit v1.2.3 From e70344c05995a190a56bbd1a23dc2218bcc8c924 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 11 Aug 2021 12:37:02 +0900 Subject: block: fix default IO priority handling The default IO priority is the best effort (BE) class with the normal priority level IOPRIO_NORM (4). However, get_task_ioprio() returns IOPRIO_CLASS_NONE/IOPRIO_NORM as the default priority and get_current_ioprio() returns IOPRIO_CLASS_NONE/0. Let's be consistent with the defined default and have both of these functions return the default priority IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM) when the user did not define another default IO priority for the task. In include/uapi/linux/ioprio.h, introduce the IOPRIO_BE_NORM macro as an alias to IOPRIO_NORM to clarify that this default level applies to the BE priotity class. In include/linux/ioprio.h, define the macro IOPRIO_DEFAULT as IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM) and use this new macro when setting a priority to the default. Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20210811033702.368488-7-damien.lemoal@wdc.com [axboe: drop unnecessary lightnvm change] Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 2 +- block/ioprio.c | 6 +++--- include/linux/ioprio.h | 7 ++++++- include/uapi/linux/ioprio.h | 5 +++-- 4 files changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 4b434369e411..e92bc0348433 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5411,7 +5411,7 @@ static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd, case IOPRIO_CLASS_RT: return &bfqg->async_bfqq[0][ioprio]; case IOPRIO_CLASS_NONE: - ioprio = IOPRIO_NORM; + ioprio = IOPRIO_BE_NORM; fallthrough; case IOPRIO_CLASS_BE: return &bfqg->async_bfqq[1][ioprio]; diff --git a/block/ioprio.c b/block/ioprio.c index ca6b136c5586..0e4ff245f2bf 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -170,7 +170,7 @@ static int get_task_ioprio(struct task_struct *p) ret = security_task_getioprio(p); if (ret) goto out; - ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM); + ret = IOPRIO_DEFAULT; task_lock(p); if (p->io_context) ret = p->io_context->ioprio; @@ -182,9 +182,9 @@ out: int ioprio_best(unsigned short aprio, unsigned short bprio) { if (!ioprio_valid(aprio)) - aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + aprio = IOPRIO_DEFAULT; if (!ioprio_valid(bprio)) - bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + bprio = IOPRIO_DEFAULT; return min(aprio, bprio); } diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 2ee3373684b1..3f53bc27a19b 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -8,6 +8,11 @@ #include +/* + * Default IO priority. + */ +#define IOPRIO_DEFAULT IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM) + /* * Check that a priority value has a valid class. */ @@ -51,7 +56,7 @@ static inline int get_current_ioprio(void) if (ioc) return ioc->ioprio; - return IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); + return IOPRIO_DEFAULT; } /* diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h index aac39338d02c..f70f2596a6bf 100644 --- a/include/uapi/linux/ioprio.h +++ b/include/uapi/linux/ioprio.h @@ -44,8 +44,9 @@ enum { }; /* - * Fallback BE priority + * Fallback BE priority level. */ -#define IOPRIO_NORM (4) +#define IOPRIO_NORM 4 +#define IOPRIO_BE_NORM IOPRIO_NORM #endif /* _UAPI_LINUX_IOPRIO_H */ -- cgit v1.2.3 From bd1e336aa8535a99f339e2d66a611984262221ce Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Tue, 17 Aug 2021 13:24:49 +0300 Subject: driver core: platform: Remove platform_device_add_properties() There are no more users for it. The last place where it's called is in platform_device_register_full(). Replacing that call with device_create_managed_software_node() and removing the function. Reviewed-by: Andy Shevchenko Reviewed-by: Thierry Reding Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20210817102449.39994-3-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/platform.c | 20 ++------------------ include/linux/platform_device.h | 2 -- 2 files changed, 2 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/platform.c b/drivers/base/platform.c index a94b7f454881..652531f67135 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -641,22 +641,6 @@ int platform_device_add_data(struct platform_device *pdev, const void *data, } EXPORT_SYMBOL_GPL(platform_device_add_data); -/** - * platform_device_add_properties - add built-in properties to a platform device - * @pdev: platform device to add properties to - * @properties: null terminated array of properties to add - * - * The function will take deep copy of @properties and attach the copy to the - * platform device. The memory associated with properties will be freed when the - * platform device is released. - */ -int platform_device_add_properties(struct platform_device *pdev, - const struct property_entry *properties) -{ - return device_add_properties(&pdev->dev, properties); -} -EXPORT_SYMBOL_GPL(platform_device_add_properties); - /** * platform_device_add - add a platform device to device hierarchy * @pdev: platform device we're adding @@ -842,8 +826,8 @@ struct platform_device *platform_device_register_full( goto err; if (pdevinfo->properties) { - ret = platform_device_add_properties(pdev, - pdevinfo->properties); + ret = device_create_managed_software_node(&pdev->dev, + pdevinfo->properties, NULL); if (ret) goto err; } diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index ed42ea9f60ba..7c96f169d274 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -197,8 +197,6 @@ extern int platform_device_add_resources(struct platform_device *pdev, unsigned int num); extern int platform_device_add_data(struct platform_device *pdev, const void *data, size_t size); -extern int platform_device_add_properties(struct platform_device *pdev, - const struct property_entry *properties); extern int platform_device_add(struct platform_device *pdev); extern void platform_device_del(struct platform_device *pdev); extern void platform_device_put(struct platform_device *pdev); -- cgit v1.2.3 From 39a2d3506b2d53c569a6db13d65b2f3728c4feec Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 23 Jun 2021 16:05:05 +0200 Subject: dma-mapping: add a dma_init_global_coherent helper Add a new helper to initialize the global coherent pool. This both cleans up the existing initialization which indirects through the reserved_mem_ops that are normally only used for struct device, and also allows using the global pool for non-devicetree architectures. Signed-off-by: Christoph Hellwig Tested-by: Dillon Min --- include/linux/dma-map-ops.h | 2 +- kernel/dma/coherent.c | 32 ++++++++++++++------------------ 2 files changed, 15 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 2f842498c448..068f1b11a6a4 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -177,7 +177,7 @@ void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, int dma_release_from_global_coherent(int order, void *vaddr); int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr, size_t size, int *ret); - +int dma_init_global_coherent(phys_addr_t phys_addr, size_t size); #else static inline int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size) diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index ab397ebfd5ad..160d4e246ecb 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -300,6 +300,18 @@ int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr, vaddr, size, ret); } +int dma_init_global_coherent(phys_addr_t phys_addr, size_t size) +{ + struct dma_coherent_mem *mem; + + mem = dma_init_coherent_memory(phys_addr, phys_addr, size, true); + if (IS_ERR(mem)) + return PTR_ERR(mem); + dma_coherent_default_memory = mem; + pr_info("DMA: default coherent area is set\n"); + return 0; +} + /* * Support for reserved memory regions defined in device tree */ @@ -367,26 +379,10 @@ static int __init rmem_dma_setup(struct reserved_mem *rmem) static int __init dma_init_reserved_memory(void) { - const struct reserved_mem_ops *ops; - int ret; - if (!dma_reserved_default_memory) return -ENOMEM; - - ops = dma_reserved_default_memory->ops; - - /* - * We rely on rmem_dma_device_init() does not propagate error of - * dma_assign_coherent_memory() for "NULL" device. - */ - ret = ops->device_init(dma_reserved_default_memory, NULL); - - if (!ret) { - dma_coherent_default_memory = dma_reserved_default_memory->priv; - pr_info("DMA: default coherent area is set\n"); - } - - return ret; + return dma_init_global_coherent(dma_reserved_default_memory->base, + dma_reserved_default_memory->size); } core_initcall(dma_init_reserved_memory); -- cgit v1.2.3 From 3b844826b6c6affa80755254da322b017358a2f4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 5 Aug 2021 10:04:43 -0700 Subject: pipe: avoid unnecessary EPOLLET wakeups under normal loads I had forgotten just how sensitive hackbench is to extra pipe wakeups, and commit 3a34b13a88ca ("pipe: make pipe writes always wake up readers") ended up causing a quite noticeable regression on larger machines. Now, hackbench isn't necessarily a hugely meaningful benchmark, and it's not clear that this matters in real life all that much, but as Mel points out, it's used often enough when comparing kernels and so the performance regression shows up like a sore thumb. It's easy enough to fix at least for the common cases where pipes are used purely for data transfer, and you never have any exciting poll usage at all. So set a special 'poll_usage' flag when there is polling activity, and make the ugly "EPOLLET has crazy legacy expectations" semantics explicit to only that case. I would love to limit it to just the broken EPOLLET case, but the pipe code can't see the difference between epoll and regular select/poll, so any non-read/write waiting will trigger the extra wakeup behavior. That is sufficient for at least the hackbench case. Apart from making the odd extra wakeup cases more explicitly about EPOLLET, this also makes the extra wakeup be at the _end_ of the pipe write, not at the first write chunk. That is actually much saner semantics (as much as you can call any of the legacy edge-triggered expectations for EPOLLET "sane") since it means that you know the wakeup will happen once the write is done, rather than possibly in the middle of one. [ For stable people: I'm putting a "Fixes" tag on this, but I leave it up to you to decide whether you actually want to backport it or not. It likely has no impact outside of synthetic benchmarks - Linus ] Link: https://lore.kernel.org/lkml/20210802024945.GA8372@xsang-OptiPlex-9020/ Fixes: 3a34b13a88ca ("pipe: make pipe writes always wake up readers") Reported-by: kernel test robot Tested-by: Sandeep Patil Tested-by: Mel Gorman Signed-off-by: Linus Torvalds --- fs/pipe.c | 15 +++++++++------ include/linux/pipe_fs_i.h | 2 ++ 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/pipe.c b/fs/pipe.c index 8e6ef62aeb1c..678dee2a8228 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -444,9 +444,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) #endif /* - * Epoll nonsensically wants a wakeup whether the pipe - * was already empty or not. - * * If it wasn't empty we try to merge new data into * the last buffer. * @@ -455,9 +452,9 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) * spanning multiple pages. */ head = pipe->head; - was_empty = true; + was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); - if (chars && !pipe_empty(head, pipe->tail)) { + if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; @@ -590,8 +587,11 @@ out: * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs + * + * Epoll nonsensically wants a wakeup whether the pipe + * was already empty or not. */ - if (was_empty) { + if (was_empty || pipe->poll_usage) { wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } @@ -654,6 +654,9 @@ pipe_poll(struct file *filp, poll_table *wait) struct pipe_inode_info *pipe = filp->private_data; unsigned int head, tail; + /* Epoll has some historical nasty semantics, this enables them */ + pipe->poll_usage = 1; + /* * Reading pipe state only -- no need for acquiring the semaphore. * diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 5d2705f1d01c..fc5642431b92 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -48,6 +48,7 @@ struct pipe_buffer { * @files: number of struct file referring this pipe (protected by ->i_lock) * @r_counter: reader counter * @w_counter: writer counter + * @poll_usage: is this pipe used for epoll, which has crazy wakeups? * @fasync_readers: reader side fasync * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers @@ -70,6 +71,7 @@ struct pipe_inode_info { unsigned int files; unsigned int r_counter; unsigned int w_counter; + unsigned int poll_usage; struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; -- cgit v1.2.3 From 0cad6246621b5887d5b33fea84219d2a71f2f99a Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Aug 2021 22:08:24 +0200 Subject: vfs: add rcu argument to ->get_acl() callback Add a rcu argument to the ->get_acl() callback to allow get_cached_acl_rcu() to call the ->get_acl() method in the next patch. Signed-off-by: Miklos Szeredi --- Documentation/filesystems/locking.rst | 2 +- Documentation/filesystems/vfs.rst | 2 +- fs/9p/acl.c | 5 ++++- fs/9p/acl.h | 2 +- fs/bad_inode.c | 2 +- fs/btrfs/acl.c | 5 ++++- fs/btrfs/ctree.h | 2 +- fs/ceph/acl.c | 5 ++++- fs/ceph/super.h | 2 +- fs/erofs/xattr.c | 5 ++++- fs/erofs/xattr.h | 2 +- fs/ext2/acl.c | 5 ++++- fs/ext2/acl.h | 2 +- fs/ext4/acl.c | 5 ++++- fs/ext4/acl.h | 2 +- fs/f2fs/acl.c | 5 ++++- fs/f2fs/acl.h | 2 +- fs/fuse/acl.c | 5 ++++- fs/fuse/fuse_i.h | 2 +- fs/gfs2/acl.c | 5 ++++- fs/gfs2/acl.h | 2 +- fs/jffs2/acl.c | 5 ++++- fs/jffs2/acl.h | 2 +- fs/jfs/acl.c | 5 ++++- fs/jfs/jfs_acl.h | 2 +- fs/nfs/nfs3_fs.h | 2 +- fs/nfs/nfs3acl.c | 5 ++++- fs/ocfs2/acl.c | 5 ++++- fs/ocfs2/acl.h | 2 +- fs/orangefs/acl.c | 5 ++++- fs/orangefs/orangefs-kernel.h | 2 +- fs/overlayfs/inode.c | 5 ++++- fs/overlayfs/overlayfs.h | 2 +- fs/posix_acl.c | 2 +- fs/reiserfs/acl.h | 2 +- fs/reiserfs/xattr_acl.c | 5 ++++- fs/xfs/xfs_acl.c | 5 ++++- fs/xfs/xfs_acl.h | 4 ++-- include/linux/fs.h | 2 +- 39 files changed, 91 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 2183fd8cc350..899fa9aba01a 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -70,7 +70,7 @@ prototypes:: const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *); void (*truncate) (struct inode *); int (*permission) (struct inode *, int, unsigned int); - int (*get_acl)(struct inode *, int); + struct posix_acl * (*get_acl)(struct inode *, int, bool); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 14c31eced416..bf5c48066fac 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -432,7 +432,7 @@ As of kernel 2.6.22, the following members are defined: const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct user_namespace *, struct inode *, int); - int (*get_acl)(struct inode *, int); + struct posix_acl * (*get_acl)(struct inode *, int, bool); int (*setattr) (struct user_namespace *, struct dentry *, struct iattr *); int (*getattr) (struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); diff --git a/fs/9p/acl.c b/fs/9p/acl.c index bb1b286c49ae..c381499f5416 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -97,10 +97,13 @@ static struct posix_acl *v9fs_get_cached_acl(struct inode *inode, int type) return acl; } -struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type) +struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type, bool rcu) { struct v9fs_session_info *v9ses; + if (rcu) + return ERR_PTR(-ECHILD); + v9ses = v9fs_inode2v9ses(inode); if (((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) || ((v9ses->flags & V9FS_ACL_MASK) != V9FS_POSIX_ACL)) { diff --git a/fs/9p/acl.h b/fs/9p/acl.h index e4f7e882272b..d43c8949e807 100644 --- a/fs/9p/acl.h +++ b/fs/9p/acl.h @@ -16,7 +16,7 @@ #ifdef CONFIG_9P_FS_POSIX_ACL extern int v9fs_get_acl(struct inode *, struct p9_fid *); -extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type); +extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type, bool rcu); extern int v9fs_acl_chmod(struct inode *, struct p9_fid *); extern int v9fs_set_create_acl(struct inode *, struct p9_fid *, struct posix_acl *, struct posix_acl *); diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 48e16144c1f7..12b8fdcc445b 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -121,7 +121,7 @@ static const char *bad_inode_get_link(struct dentry *dentry, return ERR_PTR(-EIO); } -static struct posix_acl *bad_inode_get_acl(struct inode *inode, int type) +static struct posix_acl *bad_inode_get_acl(struct inode *inode, int type, bool rcu) { return ERR_PTR(-EIO); } diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index d95eb5c8cb37..3d00bb5deded 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -16,13 +16,16 @@ #include "btrfs_inode.h" #include "xattr.h" -struct posix_acl *btrfs_get_acl(struct inode *inode, int type) +struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu) { int size; const char *name; char *value = NULL; struct posix_acl *acl; + if (rcu) + return ERR_PTR(-ECHILD); + switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index e5e53e592d4f..ca5c7cb1b729 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3686,7 +3686,7 @@ static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag) /* acl.c */ #ifdef CONFIG_BTRFS_FS_POSIX_ACL -struct posix_acl *btrfs_get_acl(struct inode *inode, int type); +struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu); int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); int btrfs_init_acl(struct btrfs_trans_handle *trans, diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 529af59d9fd3..f4fc8e0b847c 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -29,7 +29,7 @@ static inline void ceph_set_cached_acl(struct inode *inode, spin_unlock(&ci->i_ceph_lock); } -struct posix_acl *ceph_get_acl(struct inode *inode, int type) +struct posix_acl *ceph_get_acl(struct inode *inode, int type, bool rcu) { int size; unsigned int retry_cnt = 0; @@ -37,6 +37,9 @@ struct posix_acl *ceph_get_acl(struct inode *inode, int type) char *value = NULL; struct posix_acl *acl; + if (rcu) + return ERR_PTR(-ECHILD); + switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 9215a2f4535c..b9512684e150 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1087,7 +1087,7 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx); /* acl.c */ #ifdef CONFIG_CEPH_FS_POSIX_ACL -struct posix_acl *ceph_get_acl(struct inode *, int); +struct posix_acl *ceph_get_acl(struct inode *, int, bool); int ceph_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); int ceph_pre_init_acls(struct inode *dir, umode_t *mode, diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index 8dd54b420a1d..778f2c52295d 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -673,12 +673,15 @@ ssize_t erofs_listxattr(struct dentry *dentry, } #ifdef CONFIG_EROFS_FS_POSIX_ACL -struct posix_acl *erofs_get_acl(struct inode *inode, int type) +struct posix_acl *erofs_get_acl(struct inode *inode, int type, bool rcu) { struct posix_acl *acl; int prefix, rc; char *value = NULL; + if (rcu) + return ERR_PTR(-ECHILD); + switch (type) { case ACL_TYPE_ACCESS: prefix = EROFS_XATTR_INDEX_POSIX_ACL_ACCESS; diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h index 366dcb400525..94090c74b3f7 100644 --- a/fs/erofs/xattr.h +++ b/fs/erofs/xattr.h @@ -80,7 +80,7 @@ static inline int erofs_getxattr(struct inode *inode, int index, #endif /* !CONFIG_EROFS_FS_XATTR */ #ifdef CONFIG_EROFS_FS_POSIX_ACL -struct posix_acl *erofs_get_acl(struct inode *inode, int type); +struct posix_acl *erofs_get_acl(struct inode *inode, int type, bool rcu); #else #define erofs_get_acl (NULL) #endif diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index b9a9db98e94b..bf298967c5b8 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -141,13 +141,16 @@ fail: * inode->i_mutex: don't care */ struct posix_acl * -ext2_get_acl(struct inode *inode, int type) +ext2_get_acl(struct inode *inode, int type, bool rcu) { int name_index; char *value = NULL; struct posix_acl *acl; int retval; + if (rcu) + return ERR_PTR(-ECHILD); + switch (type) { case ACL_TYPE_ACCESS: name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h index 917db5f6630a..925ab6287d35 100644 --- a/fs/ext2/acl.h +++ b/fs/ext2/acl.h @@ -55,7 +55,7 @@ static inline int ext2_acl_count(size_t size) #ifdef CONFIG_EXT2_FS_POSIX_ACL /* acl.c */ -extern struct posix_acl *ext2_get_acl(struct inode *inode, int type); +extern struct posix_acl *ext2_get_acl(struct inode *inode, int type, bool rcu); extern int ext2_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); extern int ext2_init_acl (struct inode *, struct inode *); diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index c5eaffccecc3..0613dfcbfd4a 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -142,13 +142,16 @@ fail: * inode->i_mutex: don't care */ struct posix_acl * -ext4_get_acl(struct inode *inode, int type) +ext4_get_acl(struct inode *inode, int type, bool rcu) { int name_index; char *value = NULL; struct posix_acl *acl; int retval; + if (rcu) + return ERR_PTR(-ECHILD); + switch (type) { case ACL_TYPE_ACCESS: name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index 84b8942a57f2..3219669732bf 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -55,7 +55,7 @@ static inline int ext4_acl_count(size_t size) #ifdef CONFIG_EXT4_FS_POSIX_ACL /* acl.c */ -struct posix_acl *ext4_get_acl(struct inode *inode, int type); +struct posix_acl *ext4_get_acl(struct inode *inode, int type, bool rcu); int ext4_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 239ad9453b99..16e826e01f09 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -196,8 +196,11 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type, return acl; } -struct posix_acl *f2fs_get_acl(struct inode *inode, int type) +struct posix_acl *f2fs_get_acl(struct inode *inode, int type, bool rcu) { + if (rcu) + return ERR_PTR(-ECHILD); + return __f2fs_get_acl(inode, type, NULL); } diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h index 986fd1bc780b..a26e33cab4ff 100644 --- a/fs/f2fs/acl.h +++ b/fs/f2fs/acl.h @@ -33,7 +33,7 @@ struct f2fs_acl_header { #ifdef CONFIG_F2FS_FS_POSIX_ACL -extern struct posix_acl *f2fs_get_acl(struct inode *, int); +extern struct posix_acl *f2fs_get_acl(struct inode *, int, bool); extern int f2fs_set_acl(struct user_namespace *, struct inode *, struct posix_acl *, int); extern int f2fs_init_acl(struct inode *, struct inode *, struct page *, diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c index 52b165319be1..337cb29a8dd5 100644 --- a/fs/fuse/acl.c +++ b/fs/fuse/acl.c @@ -11,7 +11,7 @@ #include #include -struct posix_acl *fuse_get_acl(struct inode *inode, int type) +struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu) { struct fuse_conn *fc = get_fuse_conn(inode); int size; @@ -19,6 +19,9 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type) void *value = NULL; struct posix_acl *acl; + if (rcu) + return ERR_PTR(-ECHILD); + if (fuse_is_bad(inode)) return ERR_PTR(-EIO); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 07829ce78695..f4140943311a 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1216,7 +1216,7 @@ extern const struct xattr_handler *fuse_acl_xattr_handlers[]; extern const struct xattr_handler *fuse_no_acl_xattr_handlers[]; struct posix_acl; -struct posix_acl *fuse_get_acl(struct inode *inode, int type); +struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu); int fuse_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 9165d70ead07..734d1f05d823 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -57,13 +57,16 @@ static struct posix_acl *__gfs2_get_acl(struct inode *inode, int type) return acl; } -struct posix_acl *gfs2_get_acl(struct inode *inode, int type) +struct posix_acl *gfs2_get_acl(struct inode *inode, int type, bool rcu) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder gh; bool need_unlock = false; struct posix_acl *acl; + if (rcu) + return ERR_PTR(-ECHILD); + if (!gfs2_glock_is_locked_by_me(ip->i_gl)) { int ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh); diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h index eccc6a43326c..cd180ca7c959 100644 --- a/fs/gfs2/acl.h +++ b/fs/gfs2/acl.h @@ -11,7 +11,7 @@ #define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12) -extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type); +extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type, bool rcu); extern int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type); extern int gfs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 55a79df70d24..e945e3484788 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -173,12 +173,15 @@ static void *jffs2_acl_to_medium(const struct posix_acl *acl, size_t *size) return ERR_PTR(-EINVAL); } -struct posix_acl *jffs2_get_acl(struct inode *inode, int type) +struct posix_acl *jffs2_get_acl(struct inode *inode, int type, bool rcu) { struct posix_acl *acl; char *value = NULL; int rc, xprefix; + if (rcu) + return ERR_PTR(-ECHILD); + switch (type) { case ACL_TYPE_ACCESS: xprefix = JFFS2_XPREFIX_ACL_ACCESS; diff --git a/fs/jffs2/acl.h b/fs/jffs2/acl.h index 62c50da9d493..9d9fb7cf093e 100644 --- a/fs/jffs2/acl.h +++ b/fs/jffs2/acl.h @@ -27,7 +27,7 @@ struct jffs2_acl_header { #ifdef CONFIG_JFFS2_FS_POSIX_ACL -struct posix_acl *jffs2_get_acl(struct inode *inode, int type); +struct posix_acl *jffs2_get_acl(struct inode *inode, int type, bool rcu); int jffs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); extern int jffs2_init_acl_pre(struct inode *, struct inode *, umode_t *); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 43c285c3d2a7..a653f34c6e26 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -14,13 +14,16 @@ #include "jfs_xattr.h" #include "jfs_acl.h" -struct posix_acl *jfs_get_acl(struct inode *inode, int type) +struct posix_acl *jfs_get_acl(struct inode *inode, int type, bool rcu) { struct posix_acl *acl; char *ea_name; int size; char *value = NULL; + if (rcu) + return ERR_PTR(-ECHILD); + switch(type) { case ACL_TYPE_ACCESS: ea_name = XATTR_NAME_POSIX_ACL_ACCESS; diff --git a/fs/jfs/jfs_acl.h b/fs/jfs/jfs_acl.h index 7ae389a7a366..3de40286d31f 100644 --- a/fs/jfs/jfs_acl.h +++ b/fs/jfs/jfs_acl.h @@ -7,7 +7,7 @@ #ifdef CONFIG_JFS_POSIX_ACL -struct posix_acl *jfs_get_acl(struct inode *inode, int type); +struct posix_acl *jfs_get_acl(struct inode *inode, int type, bool rcu); int jfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); int jfs_init_acl(tid_t, struct inode *, struct inode *); diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h index c8a192802dda..03a4e679fd99 100644 --- a/fs/nfs/nfs3_fs.h +++ b/fs/nfs/nfs3_fs.h @@ -11,7 +11,7 @@ * nfs3acl.c */ #ifdef CONFIG_NFS_V3_ACL -extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type); +extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu); extern int nfs3_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 9ec560aa4a50..93de0b58647a 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -44,7 +44,7 @@ static void nfs3_abort_get_acl(struct posix_acl **p) cmpxchg(p, sentinel, ACL_NOT_CACHED); } -struct posix_acl *nfs3_get_acl(struct inode *inode, int type) +struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu) { struct nfs_server *server = NFS_SERVER(inode); struct page *pages[NFSACL_MAXPAGES] = { }; @@ -62,6 +62,9 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type) }; int status, count; + if (rcu) + return ERR_PTR(-ECHILD); + if (!nfs_server_capable(inode, NFS_CAP_ACLS)) return ERR_PTR(-EOPNOTSUPP); diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 5c72a7e6d6c5..23a72a423955 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -289,7 +289,7 @@ unlock: return status; } -struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type) +struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type, bool rcu) { struct ocfs2_super *osb; struct buffer_head *di_bh = NULL; @@ -297,6 +297,9 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type) int had_lock; struct ocfs2_lock_holder oh; + if (rcu) + return ERR_PTR(-ECHILD); + osb = OCFS2_SB(inode->i_sb); if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL)) return NULL; diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h index f59d8d0a61fa..95a57c888ab6 100644 --- a/fs/ocfs2/acl.h +++ b/fs/ocfs2/acl.h @@ -16,7 +16,7 @@ struct ocfs2_acl_entry { __le32 e_id; }; -struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type); +struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type, bool rcu); int ocfs2_iop_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *); diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c index 18852b9ed82b..605e5a3506ec 100644 --- a/fs/orangefs/acl.c +++ b/fs/orangefs/acl.c @@ -10,12 +10,15 @@ #include "orangefs-bufmap.h" #include -struct posix_acl *orangefs_get_acl(struct inode *inode, int type) +struct posix_acl *orangefs_get_acl(struct inode *inode, int type, bool rcu) { struct posix_acl *acl; int ret; char *key = NULL, *value = NULL; + if (rcu) + return ERR_PTR(-ECHILD); + switch (type) { case ACL_TYPE_ACCESS: key = XATTR_NAME_POSIX_ACL_ACCESS; diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 0e6b97682e41..b5940ec1836a 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -106,7 +106,7 @@ enum orangefs_vfs_op_states { extern int orangefs_init_acl(struct inode *inode, struct inode *dir); extern const struct xattr_handler *orangefs_xattr_handlers[]; -extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type); +extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type, bool rcu); extern int orangefs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 7d52e5ef2ac7..ea335d3e55cf 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -446,12 +446,15 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) return res; } -struct posix_acl *ovl_get_acl(struct inode *inode, int type) +struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) { struct inode *realinode = ovl_inode_real(inode); const struct cred *old_cred; struct posix_acl *acl; + if (rcu) + return ERR_PTR(-ECHILD); + if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode)) return NULL; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index e9b3e7880fc0..3894f3347955 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -498,7 +498,7 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); -struct posix_acl *ovl_get_acl(struct inode *inode, int type); +struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu); int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags); bool ovl_is_private_xattr(struct super_block *sb, const char *name); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index f3309a7edb49..4f1ef826e040 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -138,7 +138,7 @@ struct posix_acl *get_acl(struct inode *inode, int type) set_cached_acl(inode, type, NULL); return NULL; } - acl = inode->i_op->get_acl(inode, type); + acl = inode->i_op->get_acl(inode, type, false); if (IS_ERR(acl)) { /* diff --git a/fs/reiserfs/acl.h b/fs/reiserfs/acl.h index fd58618da360..d9052b8ce6dd 100644 --- a/fs/reiserfs/acl.h +++ b/fs/reiserfs/acl.h @@ -48,7 +48,7 @@ static inline int reiserfs_acl_count(size_t size) } #ifdef CONFIG_REISERFS_FS_POSIX_ACL -struct posix_acl *reiserfs_get_acl(struct inode *inode, int type); +struct posix_acl *reiserfs_get_acl(struct inode *inode, int type, bool rcu); int reiserfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); int reiserfs_acl_chmod(struct inode *inode); diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index a9547144a099..d6fcddc46f5b 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -190,13 +190,16 @@ fail: * inode->i_mutex: down * BKL held [before 2.5.x] */ -struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) +struct posix_acl *reiserfs_get_acl(struct inode *inode, int type, bool rcu) { char *name, *value; struct posix_acl *acl; int size; int retval; + if (rcu) + return ERR_PTR(-ECHILD); + switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index d02bef24b32b..9e8ac9fa9666 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -125,7 +125,7 @@ xfs_acl_to_disk(struct xfs_acl *aclp, const struct posix_acl *acl) } struct posix_acl * -xfs_get_acl(struct inode *inode, int type) +xfs_get_acl(struct inode *inode, int type, bool rcu) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; @@ -137,6 +137,9 @@ xfs_get_acl(struct inode *inode, int type) }; int error; + if (rcu) + return ERR_PTR(-ECHILD); + trace_xfs_get_acl(ip); switch (type) { diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index 7bdb3a4ed798..bb6abdcb265d 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -10,13 +10,13 @@ struct inode; struct posix_acl; #ifdef CONFIG_XFS_POSIX_ACL -extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); +extern struct posix_acl *xfs_get_acl(struct inode *inode, int type, bool rcu); extern int xfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type); extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); void xfs_forget_acl(struct inode *inode, const char *name); #else -static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type) +static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type, bool rcu) { return NULL; } diff --git a/include/linux/fs.h b/include/linux/fs.h index ae6c6c34db94..73376dfe28d0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2065,7 +2065,7 @@ struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct user_namespace *, struct inode *, int); - struct posix_acl * (*get_acl)(struct inode *, int); + struct posix_acl * (*get_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); -- cgit v1.2.3 From 332f606b32b6291a944c8cf23b91f53a6e676525 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Aug 2021 22:08:24 +0200 Subject: ovl: enable RCU'd ->get_acl() Overlayfs does not cache ACL's (to avoid double caching). Instead it just calls the underlying filesystem's i_op->get_acl(), which will return the cached value, if possible. In rcu path walk, however, get_cached_acl_rcu() is employed to get the value from the cache, which will fail on overlayfs resulting in dropping out of rcu walk mode. This can result in a big performance hit in certain situations. Fix by calling ->get_acl() with rcu=true in case of ACL_DONT_CACHE (which indicates pass-through) Reported-by: garyhuang Signed-off-by: Miklos Szeredi --- fs/overlayfs/inode.c | 7 ++++--- fs/posix_acl.c | 13 ++++++++++++- include/linux/fs.h | 5 +++++ include/linux/posix_acl.h | 3 ++- 4 files changed, 23 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index ea335d3e55cf..832b17589733 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "overlayfs.h" @@ -452,12 +453,12 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) const struct cred *old_cred; struct posix_acl *acl; - if (rcu) - return ERR_PTR(-ECHILD); - if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode)) return NULL; + if (rcu) + return get_cached_acl_rcu(realinode, type); + old_cred = ovl_override_creds(inode->i_sb); acl = get_acl(realinode, type); revert_creds(old_cred); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 4f1ef826e040..f5c25f580dd9 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -22,6 +22,7 @@ #include #include #include +#include static struct posix_acl **acl_by_type(struct inode *inode, int type) { @@ -56,7 +57,17 @@ EXPORT_SYMBOL(get_cached_acl); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type) { - return rcu_dereference(*acl_by_type(inode, type)); + struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type)); + + if (acl == ACL_DONT_CACHE) { + struct posix_acl *ret; + + ret = inode->i_op->get_acl(inode, type, LOOKUP_RCU); + if (!IS_ERR(ret)) + acl = ret; + } + + return acl; } EXPORT_SYMBOL(get_cached_acl_rcu); diff --git a/include/linux/fs.h b/include/linux/fs.h index 73376dfe28d0..c6e5bcbff0c0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -581,6 +581,11 @@ static inline void mapping_allow_writable(struct address_space *mapping) struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) +/* + * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to + * cache the ACL. This also means that ->get_acl() can be called in RCU mode + * with the LOOKUP_RCU flag. + */ #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 307094ebb88c..b65c877d92b8 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -72,6 +72,8 @@ extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct user_namespace *, struct inode *, int, struct posix_acl *); +struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); + #ifdef CONFIG_FS_POSIX_ACL int posix_acl_chmod(struct user_namespace *, struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, @@ -84,7 +86,6 @@ extern int simple_set_acl(struct user_namespace *, struct inode *, extern int simple_acl_create(struct inode *, struct inode *); struct posix_acl *get_cached_acl(struct inode *inode, int type); -struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); -- cgit v1.2.3 From 72dd1843232c9de48e21dc1c85d169fe5328e52e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 18 Aug 2021 10:30:17 -0700 Subject: USB: EHCI: Add register array bounds to HCS ports The original EHCI register struct used a trailing 0-element array for addressing the N_PORTS-many available registers. However, after commit a46af4ebf9ff ("USB: EHCI: define extension registers like normal ones") the 0-element array started to overlap the USBMODE extension register. To avoid future compile-time warnings about accessing indexes within a 0-element array, rearrange the struct to actually describe the expected layout (max 15 registers) with a union. All offsets remain the same, and bounds checking becomes possible on accesses to port_status and hostpc. There are no binary differences, and struct offsets continue to match. "pahole --hex -C ehci_regs" before: struct ehci_regs { u32 command; /* 0 0x4 */ u32 status; /* 0x4 0x4 */ u32 intr_enable; /* 0x8 0x4 */ u32 frame_index; /* 0xc 0x4 */ u32 segment; /* 0x10 0x4 */ u32 frame_list; /* 0x14 0x4 */ u32 async_next; /* 0x18 0x4 */ u32 reserved1[2]; /* 0x1c 0x8 */ u32 txfill_tuning; /* 0x24 0x4 */ u32 reserved2[6]; /* 0x28 0x18 */ /* --- cacheline 1 boundary (64 bytes) --- */ u32 configured_flag; /* 0x40 0x4 */ u32 port_status[0]; /* 0x44 0 */ u32 reserved3[9]; /* 0x44 0x24 */ u32 usbmode; /* 0x68 0x4 */ u32 reserved4[6]; /* 0x6c 0x18 */ /* --- cacheline 2 boundary (128 bytes) was 4 bytes ago --- */ u32 hostpc[0]; /* 0x84 0 */ u32 reserved5[17]; /* 0x84 0x44 */ /* --- cacheline 3 boundary (192 bytes) was 8 bytes ago --- */ u32 usbmode_ex; /* 0xc8 0x4 */ /* size: 204, cachelines: 4, members: 18 */ /* last cacheline: 12 bytes */ }; after: struct ehci_regs { u32 command; /* 0 0x4 */ u32 status; /* 0x4 0x4 */ u32 intr_enable; /* 0x8 0x4 */ u32 frame_index; /* 0xc 0x4 */ u32 segment; /* 0x10 0x4 */ u32 frame_list; /* 0x14 0x4 */ u32 async_next; /* 0x18 0x4 */ u32 reserved1[2]; /* 0x1c 0x8 */ u32 txfill_tuning; /* 0x24 0x4 */ u32 reserved2[6]; /* 0x28 0x18 */ /* --- cacheline 1 boundary (64 bytes) --- */ u32 configured_flag; /* 0x40 0x4 */ union { u32 port_status[15]; /* 0x44 0x3c */ struct { u32 reserved3[9]; /* 0x44 0x24 */ u32 usbmode; /* 0x68 0x4 */ }; /* 0x44 0x28 */ }; /* 0x44 0x3c */ /* --- cacheline 2 boundary (128 bytes) --- */ u32 reserved4; /* 0x80 0x4 */ u32 hostpc[15]; /* 0x84 0x3c */ /* --- cacheline 3 boundary (192 bytes) --- */ u32 reserved5[2]; /* 0xc0 0x8 */ u32 usbmode_ex; /* 0xc8 0x4 */ /* size: 204, cachelines: 4, members: 16 */ /* last cacheline: 12 bytes */ }; With this fixed, adding -Wzero-length-bounds to the build no longer produces several warnings like this: In file included from drivers/usb/host/ehci-hcd.c:306: drivers/usb/host/ehci-hub.c: In function 'ehci_port_handed_over': drivers/usb/host/ehci-hub.c:1194:8: warning: array subscript '' is outside the bounds of an interior zero-length array 'u32[0]' {aka 'unsigned int[]'} [-Wzero-length-bounds] 1194 | reg = &ehci->regs->port_status[portnum - 1]; | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from drivers/usb/host/ehci.h:274, from drivers/usb/host/ehci-hcd.c:97: ./include/linux/usb/ehci_def.h:130:7: note: while referencing 'port_status' 130 | u32 port_status[0]; /* up to N_PORTS */ | ^~~~~~~~~~~ Cc: Greg Kroah-Hartman Cc: Arnd Bergmann Cc: Al Cooper Cc: Alan Stern Cc: linux-usb@vger.kernel.org Acked-by: Alan Stern Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20210818173018.2259231-2-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ehci_def.h | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h index 78e006355557..dcbe2b068569 100644 --- a/include/linux/usb/ehci_def.h +++ b/include/linux/usb/ehci_def.h @@ -45,6 +45,7 @@ struct ehci_caps { #define HCS_PORTROUTED(p) ((p)&(1 << 7)) /* true: port routing */ #define HCS_PPC(p) ((p)&(1 << 4)) /* true: port power control */ #define HCS_N_PORTS(p) (((p)>>0)&0xf) /* bits 3:0, ports on HC */ +#define HCS_N_PORTS_MAX 15 /* N_PORTS valid 0x1-0xF */ u32 hcc_params; /* HCCPARAMS - offset 0x8 */ /* EHCI 1.1 addendum */ @@ -126,8 +127,9 @@ struct ehci_regs { u32 configured_flag; #define FLAG_CF (1<<0) /* true: we'll support "high speed" */ - /* PORTSC: offset 0x44 */ - u32 port_status[0]; /* up to N_PORTS */ + union { + /* PORTSC: offset 0x44 */ + u32 port_status[HCS_N_PORTS_MAX]; /* up to N_PORTS */ /* EHCI 1.1 addendum */ #define PORTSC_SUSPEND_STS_ACK 0 #define PORTSC_SUSPEND_STS_NYET 1 @@ -164,28 +166,28 @@ struct ehci_regs { #define PORT_CSC (1<<1) /* connect status change */ #define PORT_CONNECT (1<<0) /* device connected */ #define PORT_RWC_BITS (PORT_CSC | PORT_PEC | PORT_OCC) - - u32 reserved3[9]; - - /* USBMODE: offset 0x68 */ - u32 usbmode; /* USB Device mode */ + struct { + u32 reserved3[9]; + /* USBMODE: offset 0x68 */ + u32 usbmode; /* USB Device mode */ + }; #define USBMODE_SDIS (1<<3) /* Stream disable */ #define USBMODE_BE (1<<2) /* BE/LE endianness select */ #define USBMODE_CM_HC (3<<0) /* host controller mode */ #define USBMODE_CM_IDLE (0<<0) /* idle state */ - - u32 reserved4[6]; + }; + u32 reserved4; /* Moorestown has some non-standard registers, partially due to the fact that * its EHCI controller has both TT and LPM support. HOSTPCx are extensions to * PORTSCx */ /* HOSTPC: offset 0x84 */ - u32 hostpc[0]; /* HOSTPC extension */ + u32 hostpc[HCS_N_PORTS_MAX]; #define HOSTPC_PHCD (1<<22) /* Phy clock disable */ #define HOSTPC_PSPD (3<<25) /* Port speed detection */ - u32 reserved5[17]; + u32 reserved5[2]; /* USBMODE_EX: offset 0xc8 */ u32 usbmode_ex; /* USB Device mode extension */ -- cgit v1.2.3 From e4788edc730a0d2b26e1ae1f08fbb3f635b92dbb Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 18 Aug 2021 10:30:18 -0700 Subject: USB: EHCI: Add alias for Broadcom INSNREG Refactor struct ehci_regs to avoid accessing beyond the end of port_status. This change results in no difference in the final object code. Avoids several warnings when building with -Warray-bounds: drivers/usb/host/ehci-brcm.c: In function 'ehci_brcm_reset': drivers/usb/host/ehci-brcm.c:113:32: warning: array subscript 16 is above array bounds of 'u32[15]' {aka 'unsigned int[15]'} [-Warray-bounds] 113 | ehci_writel(ehci, 0x00800040, &ehci->regs->port_status[0x10]); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from drivers/usb/host/ehci.h:274, from drivers/usb/host/ehci-brcm.c:15: ./include/linux/usb/ehci_def.h:132:7: note: while referencing 'port_status' 132 | u32 port_status[HCS_N_PORTS_MAX]; | ^~~~~~~~~~~ Note that the documentation around this proprietary register was confusing. If "USB_EHCI_INSNREG00" is at port_status[0x0f], its offset would be 0x80 (not 0x90). The comments have been adjusted to fix this apparent typo. Fixes: 9df231511bd6 ("usb: ehci: Add new EHCI driver for Broadcom STB SoC's") Cc: Al Cooper Cc: Alan Stern Cc: Greg Kroah-Hartman Cc: linux-usb@vger.kernel.org Cc: bcm-kernel-feedback-list@broadcom.com Suggested-by: Arnd Bergmann Acked-by: Alan Stern Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20210818173018.2259231-3-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/ehci-brcm.c | 11 ++++------- include/linux/usb/ehci_def.h | 13 ++++++++++--- 2 files changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/host/ehci-brcm.c b/drivers/usb/host/ehci-brcm.c index 3e0ebe8cc649..d3626bfa966b 100644 --- a/drivers/usb/host/ehci-brcm.c +++ b/drivers/usb/host/ehci-brcm.c @@ -108,10 +108,9 @@ static int ehci_brcm_reset(struct usb_hcd *hcd) /* * SWLINUX-1705: Avoid OUT packet underflows during high memory * bus usage - * port_status[0x0f] = Broadcom-proprietary USB_EHCI_INSNREG00 @ 0x90 */ - ehci_writel(ehci, 0x00800040, &ehci->regs->port_status[0x10]); - ehci_writel(ehci, 0x00000001, &ehci->regs->port_status[0x12]); + ehci_writel(ehci, 0x00800040, &ehci->regs->brcm_insnreg[1]); + ehci_writel(ehci, 0x00000001, &ehci->regs->brcm_insnreg[3]); return ehci_setup(hcd); } @@ -223,11 +222,9 @@ static int __maybe_unused ehci_brcm_resume(struct device *dev) /* * SWLINUX-1705: Avoid OUT packet underflows during high memory * bus usage - * port_status[0x0f] = Broadcom-proprietary USB_EHCI_INSNREG00 - * @ 0x90 */ - ehci_writel(ehci, 0x00800040, &ehci->regs->port_status[0x10]); - ehci_writel(ehci, 0x00000001, &ehci->regs->port_status[0x12]); + ehci_writel(ehci, 0x00800040, &ehci->regs->brcm_insnreg[1]); + ehci_writel(ehci, 0x00000001, &ehci->regs->brcm_insnreg[3]); ehci_resume(hcd, false); diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h index dcbe2b068569..c892c5bc6638 100644 --- a/include/linux/usb/ehci_def.h +++ b/include/linux/usb/ehci_def.h @@ -176,16 +176,23 @@ struct ehci_regs { #define USBMODE_CM_HC (3<<0) /* host controller mode */ #define USBMODE_CM_IDLE (0<<0) /* idle state */ }; - u32 reserved4; /* Moorestown has some non-standard registers, partially due to the fact that * its EHCI controller has both TT and LPM support. HOSTPCx are extensions to * PORTSCx */ - /* HOSTPC: offset 0x84 */ - u32 hostpc[HCS_N_PORTS_MAX]; + union { + struct { + u32 reserved4; + /* HOSTPC: offset 0x84 */ + u32 hostpc[HCS_N_PORTS_MAX]; #define HOSTPC_PHCD (1<<22) /* Phy clock disable */ #define HOSTPC_PSPD (3<<25) /* Port speed detection */ + }; + + /* Broadcom-proprietary USB_EHCI_INSNREG00 @ 0x80 */ + u32 brcm_insnreg[4]; + }; u32 reserved5[2]; -- cgit v1.2.3 From 42ff700f3112babac129f4ae33023a7b7ce40a29 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Wed, 18 Aug 2021 13:40:13 -0600 Subject: coresight: syscfg: Add registration and feature loading for cs devices API for individual devices to register with the syscfg management system is added. Devices register with matching information, and any features or configurations that match will be loaded into the device. The feature and configuration loading is extended so that on load these are loaded into any currently registered devices. This allows configuration loading after devices have been registered. Link: https://lore.kernel.org/r/20210723165444.1048-3-mike.leach@linaro.org Signed-off-by: Mike Leach Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210818194022.379573-3-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-config.h | 98 +++++++ drivers/hwtracing/coresight/coresight-syscfg.c | 338 ++++++++++++++++++++++++- drivers/hwtracing/coresight/coresight-syscfg.h | 19 ++ include/linux/coresight.h | 7 + 4 files changed, 461 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-config.h b/drivers/hwtracing/coresight/coresight-config.h index 21aa7464dcdc..685fb46ce893 100644 --- a/drivers/hwtracing/coresight/coresight-config.h +++ b/drivers/hwtracing/coresight/coresight-config.h @@ -139,4 +139,102 @@ struct cscfg_config_desc { const u64 *presets; /* nr_presets * nr_total_params */ }; +/** + * config register instance - part of a loaded feature. + * maps register values to csdev driver structures + * + * @reg_desc: value to use when setting feature on device / store for + * readback of volatile values. + * @driver_regval: pointer to internal driver element used to set the value + * in hardware. + */ +struct cscfg_regval_csdev { + struct cscfg_regval_desc reg_desc; + void *driver_regval; +}; + +/** + * config parameter instance - part of a loaded feature. + * + * @feat_csdev: parent feature + * @reg_csdev: register value updated by this parameter. + * @current_value: current value of parameter - may be set by user via + * sysfs, or modified during device operation. + * @val64: true if 64 bit value + */ +struct cscfg_parameter_csdev { + struct cscfg_feature_csdev *feat_csdev; + struct cscfg_regval_csdev *reg_csdev; + u64 current_value; + bool val64; +}; + +/** + * Feature instance loaded into a CoreSight device. + * + * When a feature is loaded into a specific device, then this structure holds + * the connections between the register / parameter values used and the + * internal data structures that are written when the feature is enabled. + * + * Since applying a feature modifies internal data structures in the device, + * then we have a reference to the device spinlock to protect access to these + * structures (@drv_spinlock). + * + * @feat_desc: pointer to the static descriptor for this feature. + * @csdev: parent CoreSight device instance. + * @node: list entry into feature list for this device. + * @drv_spinlock: device spinlock for access to driver register data. + * @nr_params: number of parameters. + * @params_csdev: current parameter values on this device + * @nr_regs: number of registers to be programmed. + * @regs_csdev: Programming details for the registers + */ +struct cscfg_feature_csdev { + const struct cscfg_feature_desc *feat_desc; + struct coresight_device *csdev; + struct list_head node; + spinlock_t *drv_spinlock; + int nr_params; + struct cscfg_parameter_csdev *params_csdev; + int nr_regs; + struct cscfg_regval_csdev *regs_csdev; +}; + +/** + * Configuration instance when loaded into a CoreSight device. + * + * The instance contains references to loaded features on this device that are + * used by the configuration. + * + * @config_desc:reference to the descriptor for this configuration + * @csdev: parent coresight device for this configuration instance. + * @enabled: true if configuration is enabled on this device. + * @node: list entry within the coresight device + * @nr_feat: Number of features on this device that are used in the + * configuration. + * @feats_csdev:references to the device features to enable. + */ +struct cscfg_config_csdev { + const struct cscfg_config_desc *config_desc; + struct coresight_device *csdev; + bool enabled; + struct list_head node; + int nr_feat; + struct cscfg_feature_csdev *feats_csdev[0]; +}; + +/** + * Coresight device operations. + * + * Registered coresight devices provide these operations to manage feature + * instances compatible with the device hardware and drivers + * + * @load_feat: Pass a feature descriptor into the device and create the + * loaded feature instance (struct cscfg_feature_csdev). + */ +struct cscfg_csdev_feat_ops { + int (*load_feat)(struct coresight_device *csdev, + struct cscfg_feature_csdev *feat_csdev); +}; + #endif /* _CORESIGHT_CORESIGHT_CONFIG_H */ diff --git a/drivers/hwtracing/coresight/coresight-syscfg.c b/drivers/hwtracing/coresight/coresight-syscfg.c index 417db3f92c2f..2c0d4906e226 100644 --- a/drivers/hwtracing/coresight/coresight-syscfg.c +++ b/drivers/hwtracing/coresight/coresight-syscfg.c @@ -25,6 +25,198 @@ static struct cscfg_manager *cscfg_mgr; /* load features and configuations into the lists */ +/* get name feature instance from a coresight device list of features */ +static struct cscfg_feature_csdev * +cscfg_get_feat_csdev(struct coresight_device *csdev, const char *name) +{ + struct cscfg_feature_csdev *feat_csdev = NULL; + + list_for_each_entry(feat_csdev, &csdev->feature_csdev_list, node) { + if (strcmp(feat_csdev->feat_desc->name, name) == 0) + return feat_csdev; + } + return NULL; +} + +/* allocate the device config instance - with max number of used features */ +static struct cscfg_config_csdev * +cscfg_alloc_csdev_cfg(struct coresight_device *csdev, int nr_feats) +{ + struct cscfg_config_csdev *config_csdev = NULL; + struct device *dev = csdev->dev.parent; + + /* this is being allocated using the devm for the coresight device */ + config_csdev = devm_kzalloc(dev, + offsetof(struct cscfg_config_csdev, feats_csdev[nr_feats]), + GFP_KERNEL); + if (!config_csdev) + return NULL; + + config_csdev->csdev = csdev; + return config_csdev; +} + +/* Load a config into a device if there are any feature matches between config and device */ +static int cscfg_add_csdev_cfg(struct coresight_device *csdev, + struct cscfg_config_desc *config_desc) +{ + struct cscfg_config_csdev *config_csdev = NULL; + struct cscfg_feature_csdev *feat_csdev; + unsigned long flags; + int i; + + /* look at each required feature and see if it matches any feature on the device */ + for (i = 0; i < config_desc->nr_feat_refs; i++) { + /* look for a matching name */ + feat_csdev = cscfg_get_feat_csdev(csdev, config_desc->feat_ref_names[i]); + if (feat_csdev) { + /* + * At least one feature on this device matches the config + * add a config instance to the device and a reference to the feature. + */ + if (!config_csdev) { + config_csdev = cscfg_alloc_csdev_cfg(csdev, + config_desc->nr_feat_refs); + if (!config_csdev) + return -ENOMEM; + config_csdev->config_desc = config_desc; + } + config_csdev->feats_csdev[config_csdev->nr_feat++] = feat_csdev; + } + } + /* if matched features, add config to device.*/ + if (config_csdev) { + spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + list_add(&config_csdev->node, &csdev->config_csdev_list); + spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + } + + return 0; +} + +/* + * Add the config to the set of registered devices - call with mutex locked. + * Iterates through devices - any device that matches one or more of the + * configuration features will load it, the others will ignore it. + */ +static int cscfg_add_cfg_to_csdevs(struct cscfg_config_desc *config_desc) +{ + struct cscfg_registered_csdev *csdev_item; + int err; + + list_for_each_entry(csdev_item, &cscfg_mgr->csdev_desc_list, item) { + err = cscfg_add_csdev_cfg(csdev_item->csdev, config_desc); + if (err) + return err; + } + return 0; +} + +/* + * Allocate a feature object for load into a csdev. + * memory allocated using the csdev->dev object using devm managed allocator. + */ +static struct cscfg_feature_csdev * +cscfg_alloc_csdev_feat(struct coresight_device *csdev, struct cscfg_feature_desc *feat_desc) +{ + struct cscfg_feature_csdev *feat_csdev = NULL; + struct device *dev = csdev->dev.parent; + int i; + + feat_csdev = devm_kzalloc(dev, sizeof(struct cscfg_feature_csdev), GFP_KERNEL); + if (!feat_csdev) + return NULL; + + /* parameters are optional - could be 0 */ + feat_csdev->nr_params = feat_desc->nr_params; + + /* + * if we need parameters, zero alloc the space here, the load routine in + * the csdev device driver will fill out some information according to + * feature descriptor. + */ + if (feat_csdev->nr_params) { + feat_csdev->params_csdev = devm_kcalloc(dev, feat_csdev->nr_params, + sizeof(struct cscfg_parameter_csdev), + GFP_KERNEL); + if (!feat_csdev->params_csdev) + return NULL; + + /* + * fill in the feature reference in the param - other fields + * handled by loader in csdev. + */ + for (i = 0; i < feat_csdev->nr_params; i++) + feat_csdev->params_csdev[i].feat_csdev = feat_csdev; + } + + /* + * Always have registers to program - again the load routine in csdev device + * will fill out according to feature descriptor and device requirements. + */ + feat_csdev->nr_regs = feat_desc->nr_regs; + feat_csdev->regs_csdev = devm_kcalloc(dev, feat_csdev->nr_regs, + sizeof(struct cscfg_regval_csdev), + GFP_KERNEL); + if (!feat_csdev->regs_csdev) + return NULL; + + /* load the feature default values */ + feat_csdev->feat_desc = feat_desc; + feat_csdev->csdev = csdev; + + return feat_csdev; +} + +/* load one feature into one coresight device */ +static int cscfg_load_feat_csdev(struct coresight_device *csdev, + struct cscfg_feature_desc *feat_desc, + struct cscfg_csdev_feat_ops *ops) +{ + struct cscfg_feature_csdev *feat_csdev; + unsigned long flags; + int err; + + if (!ops->load_feat) + return -EINVAL; + + feat_csdev = cscfg_alloc_csdev_feat(csdev, feat_desc); + if (!feat_csdev) + return -ENOMEM; + + /* load the feature into the device */ + err = ops->load_feat(csdev, feat_csdev); + if (err) + return err; + + /* add to internal csdev feature list */ + spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + list_add(&feat_csdev->node, &csdev->feature_csdev_list); + spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + + return 0; +} + +/* + * Add feature to any matching devices - call with mutex locked. + * Iterates through devices - any device that matches the feature will be + * called to load it. + */ +static int cscfg_add_feat_to_csdevs(struct cscfg_feature_desc *feat_desc) +{ + struct cscfg_registered_csdev *csdev_item; + int err; + + list_for_each_entry(csdev_item, &cscfg_mgr->csdev_desc_list, item) { + if (csdev_item->match_flags & feat_desc->match_flags) { + err = cscfg_load_feat_csdev(csdev_item->csdev, feat_desc, &csdev_item->ops); + if (err) + return err; + } + } + return 0; +} + /* check feature list for a named feature - call with mutex locked. */ static bool cscfg_match_list_feat(const char *name) { @@ -53,8 +245,14 @@ static int cscfg_check_feat_for_cfg(struct cscfg_config_desc *config_desc) */ static int cscfg_load_feat(struct cscfg_feature_desc *feat_desc) { - list_add(&feat_desc->item, &cscfg_mgr->feat_desc_list); + int err; + + /* add feature to any matching registered devices */ + err = cscfg_add_feat_to_csdevs(feat_desc); + if (err) + return err; + list_add(&feat_desc->item, &cscfg_mgr->feat_desc_list); return 0; } @@ -71,6 +269,11 @@ static int cscfg_load_config(struct cscfg_config_desc *config_desc) if (err) return err; + /* add config to any matching registered device */ + err = cscfg_add_cfg_to_csdevs(config_desc); + if (err) + return err; + list_add(&config_desc->item, &cscfg_mgr->config_desc_list); return 0; } @@ -125,6 +328,139 @@ exit_unlock: } EXPORT_SYMBOL_GPL(cscfg_load_config_sets); +/* Handle coresight device registration and add configs and features to devices */ + +/* iterate through config lists and load matching configs to device */ +static int cscfg_add_cfgs_csdev(struct coresight_device *csdev) +{ + struct cscfg_config_desc *config_desc; + int err = 0; + + list_for_each_entry(config_desc, &cscfg_mgr->config_desc_list, item) { + err = cscfg_add_csdev_cfg(csdev, config_desc); + if (err) + break; + } + return err; +} + +/* iterate through feature lists and load matching features to device */ +static int cscfg_add_feats_csdev(struct coresight_device *csdev, + u32 match_flags, + struct cscfg_csdev_feat_ops *ops) +{ + struct cscfg_feature_desc *feat_desc; + int err = 0; + + if (!ops->load_feat) + return -EINVAL; + + list_for_each_entry(feat_desc, &cscfg_mgr->feat_desc_list, item) { + if (feat_desc->match_flags & match_flags) { + err = cscfg_load_feat_csdev(csdev, feat_desc, ops); + if (err) + break; + } + } + return err; +} + +/* Add coresight device to list and copy its matching info */ +static int cscfg_list_add_csdev(struct coresight_device *csdev, + u32 match_flags, + struct cscfg_csdev_feat_ops *ops) +{ + struct cscfg_registered_csdev *csdev_item; + + /* allocate the list entry structure */ + csdev_item = kzalloc(sizeof(struct cscfg_registered_csdev), GFP_KERNEL); + if (!csdev_item) + return -ENOMEM; + + csdev_item->csdev = csdev; + csdev_item->match_flags = match_flags; + csdev_item->ops.load_feat = ops->load_feat; + list_add(&csdev_item->item, &cscfg_mgr->csdev_desc_list); + + INIT_LIST_HEAD(&csdev->feature_csdev_list); + INIT_LIST_HEAD(&csdev->config_csdev_list); + spin_lock_init(&csdev->cscfg_csdev_lock); + + return 0; +} + +/* remove a coresight device from the list and free data */ +static void cscfg_list_remove_csdev(struct coresight_device *csdev) +{ + struct cscfg_registered_csdev *csdev_item, *tmp; + + list_for_each_entry_safe(csdev_item, tmp, &cscfg_mgr->csdev_desc_list, item) { + if (csdev_item->csdev == csdev) { + list_del(&csdev_item->item); + kfree(csdev_item); + break; + } + } +} + +/** + * cscfg_register_csdev - register a coresight device with the syscfg manager. + * + * Registers the coresight device with the system. @match_flags used to check + * if the device is a match for registered features. Any currently registered + * configurations and features that match the device will be loaded onto it. + * + * @csdev: The coresight device to register. + * @match_flags: Matching information to load features. + * @ops: Standard operations supported by the device. + */ +int cscfg_register_csdev(struct coresight_device *csdev, + u32 match_flags, + struct cscfg_csdev_feat_ops *ops) +{ + int ret = 0; + + mutex_lock(&cscfg_mutex); + + /* add device to list of registered devices */ + ret = cscfg_list_add_csdev(csdev, match_flags, ops); + if (ret) + goto reg_csdev_unlock; + + /* now load any registered features and configs matching the device. */ + ret = cscfg_add_feats_csdev(csdev, match_flags, ops); + if (ret) { + cscfg_list_remove_csdev(csdev); + goto reg_csdev_unlock; + } + + ret = cscfg_add_cfgs_csdev(csdev); + if (ret) { + cscfg_list_remove_csdev(csdev); + goto reg_csdev_unlock; + } + + pr_info("CSCFG registered %s", dev_name(&csdev->dev)); + +reg_csdev_unlock: + mutex_unlock(&cscfg_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(cscfg_register_csdev); + +/** + * cscfg_unregister_csdev - remove coresight device from syscfg manager. + * + * @csdev: Device to remove. + */ +void cscfg_unregister_csdev(struct coresight_device *csdev) +{ + mutex_lock(&cscfg_mutex); + cscfg_list_remove_csdev(csdev); + mutex_unlock(&cscfg_mutex); +} +EXPORT_SYMBOL_GPL(cscfg_unregister_csdev); + /* Initialise system configuration management device. */ struct device *cscfg_device(void) diff --git a/drivers/hwtracing/coresight/coresight-syscfg.h b/drivers/hwtracing/coresight/coresight-syscfg.h index 18be9b58cd0b..5bcae3b374c6 100644 --- a/drivers/hwtracing/coresight/coresight-syscfg.h +++ b/drivers/hwtracing/coresight/coresight-syscfg.h @@ -35,6 +35,22 @@ struct cscfg_manager { /* get reference to dev in cscfg_manager */ struct device *cscfg_device(void); +/** + * List entry for Coresight devices that are registered as supporting complex + * config operations. + * + * @csdev: The registered device. + * @match_flags: The matching type information for adding features. + * @ops: Operations supported by the registered device. + * @item: list entry. + */ +struct cscfg_registered_csdev { + struct coresight_device *csdev; + u32 match_flags; + struct cscfg_csdev_feat_ops ops; + struct list_head item; +}; + /* internal core operations for cscfg */ int __init cscfg_init(void); void cscfg_exit(void); @@ -42,5 +58,8 @@ void cscfg_exit(void); /* syscfg manager external API */ int cscfg_load_config_sets(struct cscfg_config_desc **cfg_descs, struct cscfg_feature_desc **feat_descs); +int cscfg_register_csdev(struct coresight_device *csdev, u32 match_flags, + struct cscfg_csdev_feat_ops *ops); +void cscfg_unregister_csdev(struct coresight_device *csdev); #endif /* CORESIGHT_SYSCFG_H */ diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 85008a65e21f..16544ae2b532 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -220,6 +220,9 @@ struct coresight_sysfs_link { * @nr_links: number of sysfs links created to other components from this * device. These will appear in the "connections" group. * @has_conns_grp: Have added a "connections" group for sysfs links. + * @feature_csdev_list: List of complex feature programming added to the device. + * @config_csdev_list: List of system configurations added to the device. + * @cscfg_csdev_lock: Protect the lists of configurations and features. */ struct coresight_device { struct coresight_platform_data *pdata; @@ -241,6 +244,10 @@ struct coresight_device { int nr_links; bool has_conns_grp; bool ect_enabled; /* true only if associated ect device is enabled */ + /* system configuration and feature lists */ + struct list_head feature_csdev_list; + struct list_head config_csdev_list; + spinlock_t cscfg_csdev_lock; }; /* -- cgit v1.2.3 From f8cce2ff3c04361b8843d8489620fda8880f668b Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Wed, 18 Aug 2021 13:40:16 -0600 Subject: coresight: syscfg: Add API to activate and enable configurations Configurations are first activated, then when any coresight device is enabled, the active configurations are checked and any matching one is enabled. This patch provides the activation / enable API. Link: https://lore.kernel.org/r/20210723165444.1048-6-mike.leach@linaro.org Signed-off-by: Mike Leach Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210818194022.379573-6-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-config.h | 2 + drivers/hwtracing/coresight/coresight-syscfg.c | 215 +++++++++++++++++++++++++ drivers/hwtracing/coresight/coresight-syscfg.h | 8 + include/linux/coresight.h | 2 + 4 files changed, 227 insertions(+) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-config.h b/drivers/hwtracing/coresight/coresight-config.h index 0667581822c1..25eb6c632692 100644 --- a/drivers/hwtracing/coresight/coresight-config.h +++ b/drivers/hwtracing/coresight/coresight-config.h @@ -127,6 +127,7 @@ struct cscfg_feature_desc { * @nr_total_params: Sum of all parameters declared by used features * @presets: Array of preset values. * @event_ea: Extended attribute for perf event value + * @active_cnt: ref count for activate on this configuration. * */ struct cscfg_config_desc { @@ -139,6 +140,7 @@ struct cscfg_config_desc { int nr_total_params; const u64 *presets; /* nr_presets * nr_total_params */ struct dev_ext_attribute *event_ea; + atomic_t active_cnt; }; /** diff --git a/drivers/hwtracing/coresight/coresight-syscfg.c b/drivers/hwtracing/coresight/coresight-syscfg.c index b93f2b4a777e..795dba576fea 100644 --- a/drivers/hwtracing/coresight/coresight-syscfg.c +++ b/drivers/hwtracing/coresight/coresight-syscfg.c @@ -282,6 +282,7 @@ static int cscfg_load_config(struct cscfg_config_desc *config_desc) return err; list_add(&config_desc->item, &cscfg_mgr->config_desc_list); + atomic_set(&config_desc->active_cnt, 0); return 0; } @@ -468,6 +469,219 @@ void cscfg_unregister_csdev(struct coresight_device *csdev) } EXPORT_SYMBOL_GPL(cscfg_unregister_csdev); +/** + * cscfg_csdev_reset_feats - reset features for a CoreSight device. + * + * Resets all parameters and register values for any features loaded + * into @csdev to their default values. + * + * @csdev: The CoreSight device. + */ +void cscfg_csdev_reset_feats(struct coresight_device *csdev) +{ + struct cscfg_feature_csdev *feat_csdev; + unsigned long flags; + + spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + if (list_empty(&csdev->feature_csdev_list)) + goto unlock_exit; + + list_for_each_entry(feat_csdev, &csdev->feature_csdev_list, node) + cscfg_reset_feat(feat_csdev); + +unlock_exit: + spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); +} +EXPORT_SYMBOL_GPL(cscfg_csdev_reset_feats); + +/** + * cscfg_activate_config - Mark a configuration descriptor as active. + * + * This will be seen when csdev devices are enabled in the system. + * Only activated configurations can be enabled on individual devices. + * Activation protects the configuration from alteration or removal while + * active. + * + * Selection by hash value - generated from the configuration name when it + * was loaded and added to the cs_etm/configurations file system for selection + * by perf. + * + * Increments the configuration descriptor active count and the global active + * count. + * + * @cfg_hash: Hash value of the selected configuration name. + */ +int cscfg_activate_config(unsigned long cfg_hash) +{ + struct cscfg_config_desc *config_desc; + int err = -EINVAL; + + mutex_lock(&cscfg_mutex); + + list_for_each_entry(config_desc, &cscfg_mgr->config_desc_list, item) { + if ((unsigned long)config_desc->event_ea->var == cfg_hash) { + /* + * increment the global active count - control changes to + * active configurations + */ + atomic_inc(&cscfg_mgr->sys_active_cnt); + + /* + * mark the descriptor as active so enable config on a + * device instance will use it + */ + atomic_inc(&config_desc->active_cnt); + + err = 0; + dev_dbg(cscfg_device(), "Activate config %s.\n", config_desc->name); + break; + } + } + mutex_unlock(&cscfg_mutex); + + return err; +} +EXPORT_SYMBOL_GPL(cscfg_activate_config); + +/** + * cscfg_deactivate_config - Mark a config descriptor as inactive. + * + * Decrement the configuration and global active counts. + * + * @cfg_hash: Hash value of the selected configuration name. + */ +void cscfg_deactivate_config(unsigned long cfg_hash) +{ + struct cscfg_config_desc *config_desc; + + mutex_lock(&cscfg_mutex); + + list_for_each_entry(config_desc, &cscfg_mgr->config_desc_list, item) { + if ((unsigned long)config_desc->event_ea->var == cfg_hash) { + atomic_dec(&config_desc->active_cnt); + atomic_dec(&cscfg_mgr->sys_active_cnt); + dev_dbg(cscfg_device(), "Deactivate config %s.\n", config_desc->name); + break; + } + } + mutex_unlock(&cscfg_mutex); +} +EXPORT_SYMBOL_GPL(cscfg_deactivate_config); + +/** + * cscfg_csdev_enable_active_config - Enable matching active configuration for device. + * + * Enables the configuration selected by @cfg_hash if the configuration is supported + * on the device and has been activated. + * + * If active and supported the CoreSight device @csdev will be programmed with the + * configuration, using @preset parameters. + * + * Should be called before driver hardware enable for the requested device, prior to + * programming and enabling the physical hardware. + * + * @csdev: CoreSight device to program. + * @cfg_hash: Selector for the configuration. + * @preset: Preset parameter values to use, 0 for current / default values. + */ +int cscfg_csdev_enable_active_config(struct coresight_device *csdev, + unsigned long cfg_hash, int preset) +{ + struct cscfg_config_csdev *config_csdev_active = NULL, *config_csdev_item; + const struct cscfg_config_desc *config_desc; + unsigned long flags; + int err = 0; + + /* quickly check global count */ + if (!atomic_read(&cscfg_mgr->sys_active_cnt)) + return 0; + + /* + * Look for matching configuration - set the active configuration + * context if found. + */ + spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + list_for_each_entry(config_csdev_item, &csdev->config_csdev_list, node) { + config_desc = config_csdev_item->config_desc; + if ((atomic_read(&config_desc->active_cnt)) && + ((unsigned long)config_desc->event_ea->var == cfg_hash)) { + config_csdev_active = config_csdev_item; + csdev->active_cscfg_ctxt = (void *)config_csdev_active; + break; + } + } + spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + + /* + * If found, attempt to enable + */ + if (config_csdev_active) { + /* + * Call the generic routine that will program up the internal + * driver structures prior to programming up the hardware. + * This routine takes the driver spinlock saved in the configs. + */ + err = cscfg_csdev_enable_config(config_csdev_active, preset); + if (!err) { + /* + * Successful programming. Check the active_cscfg_ctxt + * pointer to ensure no pre-emption disabled it via + * cscfg_csdev_disable_active_config() before + * we could start. + * + * Set enabled if OK, err if not. + */ + spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + if (csdev->active_cscfg_ctxt) + config_csdev_active->enabled = true; + else + err = -EBUSY; + spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + } + } + return err; +} +EXPORT_SYMBOL_GPL(cscfg_csdev_enable_active_config); + +/** + * cscfg_csdev_disable_active_config - disable an active config on the device. + * + * Disables the active configuration on the CoreSight device @csdev. + * Disable will save the values of any registers marked in the configurations + * as save on disable. + * + * Should be called after driver hardware disable for the requested device, + * after disabling the physical hardware and reading back registers. + * + * @csdev: The CoreSight device. + */ +void cscfg_csdev_disable_active_config(struct coresight_device *csdev) +{ + struct cscfg_config_csdev *config_csdev; + unsigned long flags; + + /* + * Check if we have an active config, and that it was successfully enabled. + * If it was not enabled, we have no work to do, otherwise mark as disabled. + * Clear the active config pointer. + */ + spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + config_csdev = (struct cscfg_config_csdev *)csdev->active_cscfg_ctxt; + if (config_csdev) { + if (!config_csdev->enabled) + config_csdev = NULL; + else + config_csdev->enabled = false; + } + csdev->active_cscfg_ctxt = NULL; + spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + + /* true if there was an enabled active config */ + if (config_csdev) + cscfg_csdev_disable_config(config_csdev); +} +EXPORT_SYMBOL_GPL(cscfg_csdev_disable_active_config); + /* Initialise system configuration management device. */ struct device *cscfg_device(void) @@ -536,6 +750,7 @@ int __init cscfg_init(void) INIT_LIST_HEAD(&cscfg_mgr->csdev_desc_list); INIT_LIST_HEAD(&cscfg_mgr->feat_desc_list); INIT_LIST_HEAD(&cscfg_mgr->config_desc_list); + atomic_set(&cscfg_mgr->sys_active_cnt, 0); dev_info(cscfg_device(), "CoreSight Configuration manager initialised"); return 0; diff --git a/drivers/hwtracing/coresight/coresight-syscfg.h b/drivers/hwtracing/coresight/coresight-syscfg.h index 5bcae3b374c6..a52775890670 100644 --- a/drivers/hwtracing/coresight/coresight-syscfg.h +++ b/drivers/hwtracing/coresight/coresight-syscfg.h @@ -24,12 +24,14 @@ * @csdev_desc_list: List of coresight devices registered with the configuration manager. * @feat_desc_list: List of feature descriptors to load into registered devices. * @config_desc_list: List of system configuration descriptors to load into registered devices. + * @sys_active_cnt: Total number of active config descriptor references. */ struct cscfg_manager { struct device dev; struct list_head csdev_desc_list; struct list_head feat_desc_list; struct list_head config_desc_list; + atomic_t sys_active_cnt; }; /* get reference to dev in cscfg_manager */ @@ -61,5 +63,11 @@ int cscfg_load_config_sets(struct cscfg_config_desc **cfg_descs, int cscfg_register_csdev(struct coresight_device *csdev, u32 match_flags, struct cscfg_csdev_feat_ops *ops); void cscfg_unregister_csdev(struct coresight_device *csdev); +int cscfg_activate_config(unsigned long cfg_hash); +void cscfg_deactivate_config(unsigned long cfg_hash); +void cscfg_csdev_reset_feats(struct coresight_device *csdev); +int cscfg_csdev_enable_active_config(struct coresight_device *csdev, + unsigned long cfg_hash, int preset); +void cscfg_csdev_disable_active_config(struct coresight_device *csdev); #endif /* CORESIGHT_SYSCFG_H */ diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 16544ae2b532..93a2922b7653 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -223,6 +223,7 @@ struct coresight_sysfs_link { * @feature_csdev_list: List of complex feature programming added to the device. * @config_csdev_list: List of system configurations added to the device. * @cscfg_csdev_lock: Protect the lists of configurations and features. + * @active_cscfg_ctxt: Context information for current active system configuration. */ struct coresight_device { struct coresight_platform_data *pdata; @@ -248,6 +249,7 @@ struct coresight_device { struct list_head feature_csdev_list; struct list_head config_csdev_list; spinlock_t cscfg_csdev_lock; + void *active_cscfg_ctxt; }; /* -- cgit v1.2.3 From 8b0e6c744fef6462382041b30878c91f15069fc6 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 16 Aug 2021 23:42:56 -0400 Subject: tracing: Add DYNAMIC flag for dynamic events To differentiate between static and dynamic events, add a new flag DYNAMIC to the event flags that all dynamic events have set. This will allow to differentiate when attaching to a dynamic event from a static event. Static events have a mod pointer that references the module they were created in (or NULL for core kernel). This can be incremented when the event has something attached to it. But there exists no such mechanism for dynamic events. This is dangerous as the dynamic events may now disappear without the "attachment" knowing that it no longer exists. To enforce the dynamic flag, change dyn_event_add() to pass the event that is being created such that it can set the DYNAMIC flag of the event. This helps make sure that no location that creates a dynamic event misses setting this flag. Link: https://lore.kernel.org/linux-trace-devel/20210813004448.51c7de69ce432d338f4d226b@kernel.org/ Link: https://lkml.kernel.org/r/20210817035026.936958254@goodmis.org Suggested-by: Masami Hiramatsu Acked-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 3 +++ kernel/trace/trace_dynevent.h | 4 +++- kernel/trace/trace_events_synth.c | 2 +- kernel/trace/trace_kprobe.c | 4 ++-- kernel/trace/trace_uprobe.c | 4 ++-- 5 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index ad413b382a3c..53c9dffd87fd 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -310,6 +310,7 @@ enum { TRACE_EVENT_FL_NO_SET_FILTER_BIT, TRACE_EVENT_FL_IGNORE_ENABLE_BIT, TRACE_EVENT_FL_TRACEPOINT_BIT, + TRACE_EVENT_FL_DYNAMIC_BIT, TRACE_EVENT_FL_KPROBE_BIT, TRACE_EVENT_FL_UPROBE_BIT, }; @@ -321,6 +322,7 @@ enum { * NO_SET_FILTER - Set when filter has error and is to be ignored * IGNORE_ENABLE - For trace internal events, do not enable with debugfs file * TRACEPOINT - Event is a tracepoint + * DYNAMIC - Event is a dynamic event (created at run time) * KPROBE - Event is a kprobe * UPROBE - Event is a uprobe */ @@ -330,6 +332,7 @@ enum { TRACE_EVENT_FL_NO_SET_FILTER = (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT), TRACE_EVENT_FL_IGNORE_ENABLE = (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT), TRACE_EVENT_FL_TRACEPOINT = (1 << TRACE_EVENT_FL_TRACEPOINT_BIT), + TRACE_EVENT_FL_DYNAMIC = (1 << TRACE_EVENT_FL_DYNAMIC_BIT), TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), TRACE_EVENT_FL_UPROBE = (1 << TRACE_EVENT_FL_UPROBE_BIT), }; diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h index 7754936b57ee..936477a111d3 100644 --- a/kernel/trace/trace_dynevent.h +++ b/kernel/trace/trace_dynevent.h @@ -76,13 +76,15 @@ int dyn_event_init(struct dyn_event *ev, struct dyn_event_operations *ops) return 0; } -static inline int dyn_event_add(struct dyn_event *ev) +static inline int dyn_event_add(struct dyn_event *ev, + struct trace_event_call *call) { lockdep_assert_held(&event_mutex); if (!ev || !ev->ops) return -EINVAL; + call->flags |= TRACE_EVENT_FL_DYNAMIC; list_add_tail(&ev->list, &dyn_event_list); return 0; } diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 9315fc03e303..f4f5489e1e28 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -1298,7 +1298,7 @@ static int __create_synth_event(const char *name, const char *raw_fields) } ret = register_synth_event(event); if (!ret) - dyn_event_add(&event->devent); + dyn_event_add(&event->devent, &event->call); else free_synth_event(event); out: diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index ea6178cb5e33..bfef43bfce37 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -618,7 +618,7 @@ static int append_trace_kprobe(struct trace_kprobe *tk, struct trace_kprobe *to) if (ret) trace_probe_unlink(&tk->tp); else - dyn_event_add(&tk->devent); + dyn_event_add(&tk->devent, trace_probe_event_call(&tk->tp)); return ret; } @@ -661,7 +661,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk) if (ret < 0) unregister_kprobe_event(tk); else - dyn_event_add(&tk->devent); + dyn_event_add(&tk->devent, trace_probe_event_call(&tk->tp)); end: mutex_unlock(&event_mutex); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 9b50869a5ddb..50eca53b8d22 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -455,7 +455,7 @@ static int append_trace_uprobe(struct trace_uprobe *tu, struct trace_uprobe *to) /* Append to existing event */ ret = trace_probe_append(&tu->tp, &to->tp); if (!ret) - dyn_event_add(&tu->devent); + dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp)); return ret; } @@ -518,7 +518,7 @@ static int register_trace_uprobe(struct trace_uprobe *tu) goto end; } - dyn_event_add(&tu->devent); + dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp)); end: mutex_unlock(&event_mutex); -- cgit v1.2.3 From 1d18538e6a09265003a0a94ca779d7a6127cb76c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 16 Aug 2021 23:42:57 -0400 Subject: tracing: Have dynamic events have a ref counter As dynamic events are not created by modules, if something is attached to one, calling "try_module_get()" on its "mod" field, is not going to keep the dynamic event from going away. Since dynamic events do not need the "mod" pointer of the event structure, make a union out of it in order to save memory (there's one structure for each of the thousand+ events in the kernel), and have any event with the DYNAMIC flag set to use a ref counter instead. Link: https://lore.kernel.org/linux-trace-devel/20210813004448.51c7de69ce432d338f4d226b@kernel.org/ Link: https://lkml.kernel.org/r/20210817035027.174869074@goodmis.org Suggested-by: Masami Hiramatsu Acked-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 45 ++++++++++++++++++++++++++++++++++++- kernel/trace/trace.c | 4 ++-- kernel/trace/trace_dynevent.c | 38 +++++++++++++++++++++++++++++++ kernel/trace/trace_event_perf.c | 6 ++--- kernel/trace/trace_events.c | 22 +++++++++++------- kernel/trace/trace_events_synth.c | 19 ++++++++++------ kernel/trace/trace_events_trigger.c | 6 ++--- kernel/trace/trace_kprobe.c | 4 ++++ kernel/trace/trace_uprobe.c | 4 ++++ 9 files changed, 124 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 53c9dffd87fd..9564c4d9a3b6 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -350,7 +350,14 @@ struct trace_event_call { struct trace_event event; char *print_fmt; struct event_filter *filter; - void *mod; + /* + * Static events can disappear with modules, + * where as dynamic ones need their own ref count. + */ + union { + void *module; + atomic_t refcnt; + }; void *data; /* See the TRACE_EVENT_FL_* flags above */ @@ -366,6 +373,42 @@ struct trace_event_call { #endif }; +#ifdef CONFIG_DYNAMIC_EVENTS +bool trace_event_dyn_try_get_ref(struct trace_event_call *call); +void trace_event_dyn_put_ref(struct trace_event_call *call); +bool trace_event_dyn_busy(struct trace_event_call *call); +#else +static inline bool trace_event_dyn_try_get_ref(struct trace_event_call *call) +{ + /* Without DYNAMIC_EVENTS configured, nothing should be calling this */ + return false; +} +static inline void trace_event_dyn_put_ref(struct trace_event_call *call) +{ +} +static inline bool trace_event_dyn_busy(struct trace_event_call *call) +{ + /* Nothing should call this without DYNAIMIC_EVENTS configured. */ + return true; +} +#endif + +static inline bool trace_event_try_get_ref(struct trace_event_call *call) +{ + if (call->flags & TRACE_EVENT_FL_DYNAMIC) + return trace_event_dyn_try_get_ref(call); + else + return try_module_get(call->module); +} + +static inline void trace_event_put_ref(struct trace_event_call *call) +{ + if (call->flags & TRACE_EVENT_FL_DYNAMIC) + trace_event_dyn_put_ref(call); + else + module_put(call->module); +} + #ifdef CONFIG_PERF_EVENTS static inline bool bpf_prog_array_valid(struct trace_event_call *call) { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index be0169594de5..8425c3d70895 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3697,11 +3697,11 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str) return false; event = container_of(trace_event, struct trace_event_call, event); - if (!event->mod) + if ((event->flags & TRACE_EVENT_FL_DYNAMIC) || !event->module) return false; /* Would rather have rodata, but this will suffice */ - if (within_module_core(addr, event->mod)) + if (within_module_core(addr, event->module)) return true; return false; diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index e57cc0870892..1110112e55bd 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -13,11 +13,49 @@ #include #include "trace.h" +#include "trace_output.h" /* for trace_event_sem */ #include "trace_dynevent.h" static DEFINE_MUTEX(dyn_event_ops_mutex); static LIST_HEAD(dyn_event_ops_list); +bool trace_event_dyn_try_get_ref(struct trace_event_call *dyn_call) +{ + struct trace_event_call *call; + bool ret = false; + + if (WARN_ON_ONCE(!(dyn_call->flags & TRACE_EVENT_FL_DYNAMIC))) + return false; + + down_read(&trace_event_sem); + list_for_each_entry(call, &ftrace_events, list) { + if (call == dyn_call) { + atomic_inc(&dyn_call->refcnt); + ret = true; + } + } + up_read(&trace_event_sem); + return ret; +} + +void trace_event_dyn_put_ref(struct trace_event_call *call) +{ + if (WARN_ON_ONCE(!(call->flags & TRACE_EVENT_FL_DYNAMIC))) + return; + + if (WARN_ON_ONCE(atomic_read(&call->refcnt) <= 0)) { + atomic_set(&call->refcnt, 0); + return; + } + + atomic_dec(&call->refcnt); +} + +bool trace_event_dyn_busy(struct trace_event_call *call) +{ + return atomic_read(&call->refcnt) != 0; +} + int dyn_event_register(struct dyn_event_operations *ops) { if (!ops || !ops->create || !ops->show || !ops->is_busy || diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 03be4435d103..6aed10e2f7ce 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -177,7 +177,7 @@ static void perf_trace_event_unreg(struct perf_event *p_event) } } out: - module_put(tp_event->mod); + trace_event_put_ref(tp_event); } static int perf_trace_event_open(struct perf_event *p_event) @@ -224,10 +224,10 @@ int perf_trace_init(struct perf_event *p_event) list_for_each_entry(tp_event, &ftrace_events, list) { if (tp_event->event.type == event_id && tp_event->class && tp_event->class->reg && - try_module_get(tp_event->mod)) { + trace_event_try_get_ref(tp_event)) { ret = perf_trace_event_init(tp_event, p_event); if (ret) - module_put(tp_event->mod); + trace_event_put_ref(tp_event); break; } } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 80e96989770e..1349b6de5eeb 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2525,7 +2525,10 @@ __register_event(struct trace_event_call *call, struct module *mod) return ret; list_add(&call->list, &ftrace_events); - call->mod = mod; + if (call->flags & TRACE_EVENT_FL_DYNAMIC) + atomic_set(&call->refcnt, 0); + else + call->module = mod; return 0; } @@ -2839,7 +2842,9 @@ static void trace_module_remove_events(struct module *mod) down_write(&trace_event_sem); list_for_each_entry_safe(call, p, &ftrace_events, list) { - if (call->mod == mod) + if ((call->flags & TRACE_EVENT_FL_DYNAMIC) || !call->module) + continue; + if (call->module == mod) __trace_remove_event_call(call); } up_write(&trace_event_sem); @@ -2982,7 +2987,7 @@ struct trace_event_file *trace_get_event_file(const char *instance, } /* Don't let event modules unload while in use */ - ret = try_module_get(file->event_call->mod); + ret = trace_event_try_get_ref(file->event_call); if (!ret) { trace_array_put(tr); ret = -EBUSY; @@ -3012,7 +3017,7 @@ EXPORT_SYMBOL_GPL(trace_get_event_file); void trace_put_event_file(struct trace_event_file *file) { mutex_lock(&event_mutex); - module_put(file->event_call->mod); + trace_event_put_ref(file->event_call); mutex_unlock(&event_mutex); trace_array_put(file->tr); @@ -3147,7 +3152,7 @@ static int free_probe_data(void *data) if (!edata->ref) { /* Remove the SOFT_MODE flag */ __ftrace_event_enable_disable(edata->file, 0, 1); - module_put(edata->file->event_call->mod); + trace_event_put_ref(edata->file->event_call); kfree(edata); } return 0; @@ -3280,7 +3285,7 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, out_reg: /* Don't let event modules unload while probe registered */ - ret = try_module_get(file->event_call->mod); + ret = trace_event_try_get_ref(file->event_call); if (!ret) { ret = -EBUSY; goto out_free; @@ -3310,7 +3315,7 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, out_disable: __ftrace_event_enable_disable(file, 0, 1); out_put: - module_put(file->event_call->mod); + trace_event_put_ref(file->event_call); out_free: kfree(data); goto out; @@ -3376,7 +3381,8 @@ void __trace_early_add_events(struct trace_array *tr) list_for_each_entry(call, &ftrace_events, list) { /* Early boot up should not have any modules loaded */ - if (WARN_ON_ONCE(call->mod)) + if (!(call->flags & TRACE_EVENT_FL_DYNAMIC) && + WARN_ON_ONCE(call->module)) continue; ret = __trace_early_add_new_event(call, tr); diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index f4f5489e1e28..d54094b7a9d7 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -1369,13 +1369,15 @@ static int destroy_synth_event(struct synth_event *se) int ret; if (se->ref) - ret = -EBUSY; - else { - ret = unregister_synth_event(se); - if (!ret) { - dyn_event_remove(&se->devent); - free_synth_event(se); - } + return -EBUSY; + + if (trace_event_dyn_busy(&se->call)) + return -EBUSY; + + ret = unregister_synth_event(se); + if (!ret) { + dyn_event_remove(&se->devent); + free_synth_event(se); } return ret; @@ -2102,6 +2104,9 @@ static int synth_event_release(struct dyn_event *ev) if (event->ref) return -EBUSY; + if (trace_event_dyn_busy(&event->call)) + return -EBUSY; + ret = unregister_synth_event(event); if (ret) return ret; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index cf84d0f6583a..6b11e335a62e 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1334,7 +1334,7 @@ void event_enable_trigger_free(struct event_trigger_ops *ops, if (!data->ref) { /* Remove the SOFT_MODE flag */ trace_event_enable_disable(enable_data->file, 0, 1); - module_put(enable_data->file->event_call->mod); + trace_event_put_ref(enable_data->file->event_call); trigger_data_free(data); kfree(enable_data); } @@ -1481,7 +1481,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, out_reg: /* Don't let event modules unload while probe registered */ - ret = try_module_get(event_enable_file->event_call->mod); + ret = trace_event_try_get_ref(event_enable_file->event_call); if (!ret) { ret = -EBUSY; goto out_free; @@ -1510,7 +1510,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, out_disable: trace_event_enable_disable(event_enable_file, 0, 1); out_put: - module_put(event_enable_file->event_call->mod); + trace_event_put_ref(event_enable_file->event_call); out_free: if (cmd_ops->set_filter) cmd_ops->set_filter(NULL, trigger_data, NULL); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index bfef43bfce37..82c3b86013b2 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -543,6 +543,10 @@ static int unregister_trace_kprobe(struct trace_kprobe *tk) if (trace_probe_is_enabled(&tk->tp)) return -EBUSY; + /* If there's a reference to the dynamic event */ + if (trace_event_dyn_busy(trace_probe_event_call(&tk->tp))) + return -EBUSY; + /* Will fail if probe is being used by ftrace or perf */ if (unregister_kprobe_event(tk)) return -EBUSY; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 50eca53b8d22..1e2a92e7607d 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -393,6 +393,10 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu) if (trace_probe_has_sibling(&tu->tp)) goto unreg; + /* If there's a reference to the dynamic event */ + if (trace_event_dyn_busy(trace_probe_event_call(&tu->tp))) + return -EBUSY; + ret = unregister_uprobe_event(tu); if (ret) return ret; -- cgit v1.2.3 From 6937b7dd434962377e00efc04adac0390c287199 Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Tue, 17 Aug 2021 23:34:59 +0530 Subject: PCI: Add support for ACPI _RST reset method _RST is a standard ACPI method that performs a function level reset of a device (ACPI v6.3, sec 7.3.25). Add pci_dev_acpi_reset() to probe for _RST method and execute if present. The default priority of this reset is set to below device-specific and above hardware resets. Suggested-by: Alex Williamson Link: https://lore.kernel.org/r/20210817180500.1253-9-ameynarkhede03@gmail.com Signed-off-by: Shanker Donthineni Signed-off-by: Bjorn Helgaas Reviewed-by: Sinan Kaya Reviewed-by: Alex Williamson --- drivers/pci/pci-acpi.c | 23 +++++++++++++++++++++++ drivers/pci/pci.c | 1 + drivers/pci/pci.h | 6 ++++++ include/linux/pci.h | 2 +- 4 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index c27dbb2294e3..b63db75a3dbf 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -941,6 +941,29 @@ void pci_set_acpi_fwnode(struct pci_dev *dev) acpi_pci_find_companion(&dev->dev)); } +/** + * pci_dev_acpi_reset - do a function level reset using _RST method + * @dev: device to reset + * @probe: check if _RST method is included in the acpi_device context. + */ +int pci_dev_acpi_reset(struct pci_dev *dev, int probe) +{ + acpi_handle handle = ACPI_HANDLE(&dev->dev); + + if (!handle || !acpi_has_method(handle, "_RST")) + return -ENOTTY; + + if (probe) + return 0; + + if (ACPI_FAILURE(acpi_evaluate_object(handle, "_RST", NULL, NULL))) { + pci_warn(dev, "ACPI _RST failed\n"); + return -ENOTTY; + } + + return 0; +} + static bool acpi_pci_power_manageable(struct pci_dev *dev) { struct acpi_device *adev = ACPI_COMPANION(&dev->dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 6da5f6d87f6a..4d9828160c48 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5126,6 +5126,7 @@ static void pci_dev_restore(struct pci_dev *dev) static const struct pci_reset_fn_method pci_reset_fn_methods[] = { { }, { pci_dev_specific_reset, .name = "device_specific" }, + { pci_dev_acpi_reset, .name = "acpi" }, { pcie_reset_flr, .name = "flr" }, { pci_af_flr, .name = "af_flr" }, { pci_pm_reset, .name = "pm" }, diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 232047e58b73..87cfd8db8827 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -708,7 +708,13 @@ static inline int pci_aer_raw_clear_status(struct pci_dev *dev) { return -EINVAL int pci_acpi_program_hp_params(struct pci_dev *dev); extern const struct attribute_group pci_dev_acpi_attr_group; void pci_set_acpi_fwnode(struct pci_dev *dev); +int pci_dev_acpi_reset(struct pci_dev *dev, int probe); #else +static inline int pci_dev_acpi_reset(struct pci_dev *dev, int probe) +{ + return -ENOTTY; +} + static inline void pci_set_acpi_fwnode(struct pci_dev *dev) {} static inline int pci_acpi_program_hp_params(struct pci_dev *dev) { diff --git a/include/linux/pci.h b/include/linux/pci.h index d1f4d248617b..98718f46a61c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -50,7 +50,7 @@ PCI_STATUS_PARITY) /* Number of reset methods used in pci_reset_fn_methods array in pci.c */ -#define PCI_NUM_RESET_METHODS 6 +#define PCI_NUM_RESET_METHODS 7 /* * The PCI interface treats multi-function devices as independent -- cgit v1.2.3 From 9bdc81ce440ec6ea899b236879aee470ec388020 Mon Sep 17 00:00:00 2001 From: Amey Narkhede Date: Tue, 17 Aug 2021 23:35:00 +0530 Subject: PCI: Change the type of probe argument in reset functions Change the type of probe argument in functions which implement reset methods from int to bool to make the context and intent clear. Suggested-by: Alex Williamson Link: https://lore.kernel.org/r/20210817180500.1253-10-ameynarkhede03@gmail.com Signed-off-by: Amey Narkhede Signed-off-by: Bjorn Helgaas --- drivers/crypto/cavium/nitrox/nitrox_main.c | 2 +- drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 2 +- drivers/pci/hotplug/pciehp.h | 2 +- drivers/pci/hotplug/pciehp_hpc.c | 2 +- drivers/pci/hotplug/pnv_php.c | 2 +- drivers/pci/pci-acpi.c | 4 +- drivers/pci/pci.c | 44 +++++++++++----------- drivers/pci/pci.h | 12 +++--- drivers/pci/pcie/aer.c | 2 +- drivers/pci/quirks.c | 20 +++++----- include/linux/pci.h | 5 ++- include/linux/pci_hotplug.h | 2 +- 12 files changed, 51 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/drivers/crypto/cavium/nitrox/nitrox_main.c b/drivers/crypto/cavium/nitrox/nitrox_main.c index 2db3fd5815c8..6c61817996a3 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_main.c +++ b/drivers/crypto/cavium/nitrox/nitrox_main.c @@ -306,7 +306,7 @@ static int nitrox_device_flr(struct pci_dev *pdev) return -ENOMEM; } - pcie_reset_flr(pdev, 0); + pcie_reset_flr(pdev, PCI_RESET_DO_RESET); pci_restore_state(pdev); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index d185df5acea6..ac821c5532a4 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -526,7 +526,7 @@ static void octeon_destroy_resources(struct octeon_device *oct) oct->irq_name_storage = NULL; } /* Soft reset the octeon device before exiting */ - if (!pcie_reset_flr(oct->pci_dev, 1)) + if (!pcie_reset_flr(oct->pci_dev, PCI_RESET_PROBE)) octeon_pci_flr(oct); else cn23xx_vf_ask_pf_to_do_flr(oct); diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index d4a930881054..69fd401691be 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -184,7 +184,7 @@ void pciehp_release_ctrl(struct controller *ctrl); int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot); int pciehp_sysfs_disable_slot(struct hotplug_slot *hotplug_slot); -int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, int probe); +int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, bool probe); int pciehp_get_attention_status(struct hotplug_slot *hotplug_slot, u8 *status); int pciehp_set_raw_indicator_status(struct hotplug_slot *h_slot, u8 status); int pciehp_get_raw_indicator_status(struct hotplug_slot *h_slot, u8 *status); diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 9d06939736c0..3024d7e85e6a 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -870,7 +870,7 @@ void pcie_disable_interrupt(struct controller *ctrl) * momentarily, if we see that they could interfere. Also, clear any spurious * events after. */ -int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, int probe) +int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, bool probe) { struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl_dev(ctrl); diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index 04565162a449..f4c2e6e01be0 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -526,7 +526,7 @@ scan: return 0; } -static int pnv_php_reset_slot(struct hotplug_slot *slot, int probe) +static int pnv_php_reset_slot(struct hotplug_slot *slot, bool probe) { struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); struct pci_dev *bridge = php_slot->pdev; diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index b63db75a3dbf..fe286c861187 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -944,9 +944,9 @@ void pci_set_acpi_fwnode(struct pci_dev *dev) /** * pci_dev_acpi_reset - do a function level reset using _RST method * @dev: device to reset - * @probe: check if _RST method is included in the acpi_device context. + * @probe: if true, return 0 if device supports _RST */ -int pci_dev_acpi_reset(struct pci_dev *dev, int probe) +int pci_dev_acpi_reset(struct pci_dev *dev, bool probe) { acpi_handle handle = ACPI_HANDLE(&dev->dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 4d9828160c48..b87bac5e4572 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4658,11 +4658,11 @@ EXPORT_SYMBOL_GPL(pcie_flr); /** * pcie_reset_flr - initiate a PCIe function level reset * @dev: device to reset - * @probe: If set, only check if the device can be reset this way. + * @probe: if true, return 0 if device can be reset this way * * Initiate a function level reset on @dev. */ -int pcie_reset_flr(struct pci_dev *dev, int probe) +int pcie_reset_flr(struct pci_dev *dev, bool probe) { if (dev->dev_flags & PCI_DEV_FLAGS_NO_FLR_RESET) return -ENOTTY; @@ -4677,7 +4677,7 @@ int pcie_reset_flr(struct pci_dev *dev, int probe) } EXPORT_SYMBOL_GPL(pcie_reset_flr); -static int pci_af_flr(struct pci_dev *dev, int probe) +static int pci_af_flr(struct pci_dev *dev, bool probe) { int pos; u8 cap; @@ -4724,7 +4724,7 @@ static int pci_af_flr(struct pci_dev *dev, int probe) /** * pci_pm_reset - Put device into PCI_D3 and back into PCI_D0. * @dev: Device to reset. - * @probe: If set, only check if the device can be reset this way. + * @probe: if true, return 0 if the device can be reset this way. * * If @dev supports native PCI PM and its PCI_PM_CTRL_NO_SOFT_RESET flag is * unset, it will be reinitialized internally when going from PCI_D3hot to @@ -4736,7 +4736,7 @@ static int pci_af_flr(struct pci_dev *dev, int probe) * by default (i.e. unless the @dev's d3hot_delay field has a different value). * Moreover, only devices in D0 can be reset by this function. */ -static int pci_pm_reset(struct pci_dev *dev, int probe) +static int pci_pm_reset(struct pci_dev *dev, bool probe) { u16 csr; @@ -4996,7 +4996,7 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_bridge_secondary_bus_reset); -static int pci_parent_bus_reset(struct pci_dev *dev, int probe) +static int pci_parent_bus_reset(struct pci_dev *dev, bool probe) { struct pci_dev *pdev; @@ -5014,7 +5014,7 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe) return pci_bridge_secondary_bus_reset(dev->bus->self); } -static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, int probe) +static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, bool probe) { int rc = -ENOTTY; @@ -5029,7 +5029,7 @@ static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, int probe) return rc; } -static int pci_dev_reset_slot_function(struct pci_dev *dev, int probe) +static int pci_dev_reset_slot_function(struct pci_dev *dev, bool probe) { if (dev->multifunction || dev->subordinate || !dev->slot || dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET) @@ -5038,7 +5038,7 @@ static int pci_dev_reset_slot_function(struct pci_dev *dev, int probe) return pci_reset_hotplug_slot(dev->slot->hotplug, probe); } -static int pci_reset_bus_function(struct pci_dev *dev, int probe) +static int pci_reset_bus_function(struct pci_dev *dev, bool probe) { int rc; @@ -5204,7 +5204,7 @@ static ssize_t reset_method_store(struct device *dev, goto error; } - if (pci_reset_fn_methods[m].reset_fn(pdev, 1)) { + if (pci_reset_fn_methods[m].reset_fn(pdev, PCI_RESET_PROBE)) { pci_err(pdev, "Unsupported reset method '%s'", name); goto error; } @@ -5220,7 +5220,7 @@ static ssize_t reset_method_store(struct device *dev, reset_methods[n] = 0; /* Warn if dev-specific supported but not highest priority */ - if (pci_reset_fn_methods[1].reset_fn(pdev, 1) == 0 && + if (pci_reset_fn_methods[1].reset_fn(pdev, PCI_RESET_PROBE) == 0 && reset_methods[0] != 1) pci_warn(pdev, "Device-specific reset disabled/de-prioritized by user"); memcpy(pdev->reset_methods, reset_methods, sizeof(pdev->reset_methods)); @@ -5294,7 +5294,7 @@ int __pci_reset_function_locked(struct pci_dev *dev) if (!m) return -ENOTTY; - rc = pci_reset_fn_methods[m].reset_fn(dev, 0); + rc = pci_reset_fn_methods[m].reset_fn(dev, PCI_RESET_DO_RESET); if (!rc) return 0; if (rc != -ENOTTY) @@ -5327,7 +5327,7 @@ void pci_init_reset_methods(struct pci_dev *dev) i = 0; for (m = 1; m < PCI_NUM_RESET_METHODS; m++) { - rc = pci_reset_fn_methods[m].reset_fn(dev, 1); + rc = pci_reset_fn_methods[m].reset_fn(dev, PCI_RESET_PROBE); if (!rc) dev->reset_methods[i++] = m; else if (rc != -ENOTTY) @@ -5644,7 +5644,7 @@ static void pci_slot_restore_locked(struct pci_slot *slot) } } -static int pci_slot_reset(struct pci_slot *slot, int probe) +static int pci_slot_reset(struct pci_slot *slot, bool probe) { int rc; @@ -5672,7 +5672,7 @@ static int pci_slot_reset(struct pci_slot *slot, int probe) */ int pci_probe_reset_slot(struct pci_slot *slot) { - return pci_slot_reset(slot, 1); + return pci_slot_reset(slot, PCI_RESET_PROBE); } EXPORT_SYMBOL_GPL(pci_probe_reset_slot); @@ -5695,14 +5695,14 @@ static int __pci_reset_slot(struct pci_slot *slot) { int rc; - rc = pci_slot_reset(slot, 1); + rc = pci_slot_reset(slot, PCI_RESET_PROBE); if (rc) return rc; if (pci_slot_trylock(slot)) { pci_slot_save_and_disable_locked(slot); might_sleep(); - rc = pci_reset_hotplug_slot(slot->hotplug, 0); + rc = pci_reset_hotplug_slot(slot->hotplug, PCI_RESET_DO_RESET); pci_slot_restore_locked(slot); pci_slot_unlock(slot); } else @@ -5711,7 +5711,7 @@ static int __pci_reset_slot(struct pci_slot *slot) return rc; } -static int pci_bus_reset(struct pci_bus *bus, int probe) +static int pci_bus_reset(struct pci_bus *bus, bool probe) { int ret; @@ -5757,14 +5757,14 @@ int pci_bus_error_reset(struct pci_dev *bridge) goto bus_reset; list_for_each_entry(slot, &bus->slots, list) - if (pci_slot_reset(slot, 0)) + if (pci_slot_reset(slot, PCI_RESET_DO_RESET)) goto bus_reset; mutex_unlock(&pci_slot_mutex); return 0; bus_reset: mutex_unlock(&pci_slot_mutex); - return pci_bus_reset(bridge->subordinate, 0); + return pci_bus_reset(bridge->subordinate, PCI_RESET_DO_RESET); } /** @@ -5775,7 +5775,7 @@ bus_reset: */ int pci_probe_reset_bus(struct pci_bus *bus) { - return pci_bus_reset(bus, 1); + return pci_bus_reset(bus, PCI_RESET_PROBE); } EXPORT_SYMBOL_GPL(pci_probe_reset_bus); @@ -5789,7 +5789,7 @@ static int __pci_reset_bus(struct pci_bus *bus) { int rc; - rc = pci_bus_reset(bus, 1); + rc = pci_bus_reset(bus, PCI_RESET_PROBE); if (rc) return rc; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 87cfd8db8827..05b7e7e04246 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -608,18 +608,18 @@ static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) struct pci_dev_reset_methods { u16 vendor; u16 device; - int (*reset)(struct pci_dev *dev, int probe); + int (*reset)(struct pci_dev *dev, bool probe); }; struct pci_reset_fn_method { - int (*reset_fn)(struct pci_dev *pdev, int probe); + int (*reset_fn)(struct pci_dev *pdev, bool probe); char *name; }; #ifdef CONFIG_PCI_QUIRKS -int pci_dev_specific_reset(struct pci_dev *dev, int probe); +int pci_dev_specific_reset(struct pci_dev *dev, bool probe); #else -static inline int pci_dev_specific_reset(struct pci_dev *dev, int probe) +static inline int pci_dev_specific_reset(struct pci_dev *dev, bool probe) { return -ENOTTY; } @@ -708,9 +708,9 @@ static inline int pci_aer_raw_clear_status(struct pci_dev *dev) { return -EINVAL int pci_acpi_program_hp_params(struct pci_dev *dev); extern const struct attribute_group pci_dev_acpi_attr_group; void pci_set_acpi_fwnode(struct pci_dev *dev); -int pci_dev_acpi_reset(struct pci_dev *dev, int probe); +int pci_dev_acpi_reset(struct pci_dev *dev, bool probe); #else -static inline int pci_dev_acpi_reset(struct pci_dev *dev, int probe) +static inline int pci_dev_acpi_reset(struct pci_dev *dev, bool probe) { return -ENOTTY; } diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 031379deb130..9784fdcf3006 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -1407,7 +1407,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) } if (type == PCI_EXP_TYPE_RC_EC || type == PCI_EXP_TYPE_RC_END) { - rc = pcie_reset_flr(dev, 0); + rc = pcie_reset_flr(dev, PCI_RESET_DO_RESET); if (!rc) pci_info(dev, "has been reset\n"); else diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index a1b57b63c624..e7657b8c8a33 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3702,7 +3702,7 @@ DECLARE_PCI_FIXUP_SUSPEND_LATE(PCI_VENDOR_ID_INTEL, * reset a single function if other methods (e.g. FLR, PM D0->D3) are * not available. */ -static int reset_intel_82599_sfp_virtfn(struct pci_dev *dev, int probe) +static int reset_intel_82599_sfp_virtfn(struct pci_dev *dev, bool probe) { /* * http://www.intel.com/content/dam/doc/datasheet/82599-10-gbe-controller-datasheet.pdf @@ -3724,7 +3724,7 @@ static int reset_intel_82599_sfp_virtfn(struct pci_dev *dev, int probe) #define NSDE_PWR_STATE 0xd0100 #define IGD_OPERATION_TIMEOUT 10000 /* set timeout 10 seconds */ -static int reset_ivb_igd(struct pci_dev *dev, int probe) +static int reset_ivb_igd(struct pci_dev *dev, bool probe) { void __iomem *mmio_base; unsigned long timeout; @@ -3767,7 +3767,7 @@ reset_complete: } /* Device-specific reset method for Chelsio T4-based adapters */ -static int reset_chelsio_generic_dev(struct pci_dev *dev, int probe) +static int reset_chelsio_generic_dev(struct pci_dev *dev, bool probe) { u16 old_command; u16 msix_flags; @@ -3845,14 +3845,14 @@ static int reset_chelsio_generic_dev(struct pci_dev *dev, int probe) * Chapter 3: NVMe control registers * Chapter 7.3: Reset behavior */ -static int nvme_disable_and_flr(struct pci_dev *dev, int probe) +static int nvme_disable_and_flr(struct pci_dev *dev, bool probe) { void __iomem *bar; u16 cmd; u32 cfg; if (dev->class != PCI_CLASS_STORAGE_EXPRESS || - pcie_reset_flr(dev, 1) || !pci_resource_start(dev, 0)) + pcie_reset_flr(dev, PCI_RESET_PROBE) || !pci_resource_start(dev, 0)) return -ENOTTY; if (probe) @@ -3919,12 +3919,12 @@ static int nvme_disable_and_flr(struct pci_dev *dev, int probe) * device too soon after FLR. A 250ms delay after FLR has heuristically * proven to produce reliably working results for device assignment cases. */ -static int delay_250ms_after_flr(struct pci_dev *dev, int probe) +static int delay_250ms_after_flr(struct pci_dev *dev, bool probe) { if (probe) - return pcie_reset_flr(dev, 1); + return pcie_reset_flr(dev, PCI_RESET_PROBE); - pcie_reset_flr(dev, 0); + pcie_reset_flr(dev, PCI_RESET_DO_RESET); msleep(250); @@ -3939,7 +3939,7 @@ static int delay_250ms_after_flr(struct pci_dev *dev, int probe) #define HINIC_OPERATION_TIMEOUT 15000 /* 15 seconds */ /* Device-specific reset method for Huawei Intelligent NIC virtual functions */ -static int reset_hinic_vf_dev(struct pci_dev *pdev, int probe) +static int reset_hinic_vf_dev(struct pci_dev *pdev, bool probe) { unsigned long timeout; void __iomem *bar; @@ -4016,7 +4016,7 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = { * because when a host assigns a device to a guest VM, the host may need * to reset the device but probably doesn't have a driver for it. */ -int pci_dev_specific_reset(struct pci_dev *dev, int probe) +int pci_dev_specific_reset(struct pci_dev *dev, bool probe) { const struct pci_dev_reset_methods *i; diff --git a/include/linux/pci.h b/include/linux/pci.h index 98718f46a61c..a46363f29b68 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -52,6 +52,9 @@ /* Number of reset methods used in pci_reset_fn_methods array in pci.c */ #define PCI_NUM_RESET_METHODS 7 +#define PCI_RESET_PROBE true +#define PCI_RESET_DO_RESET false + /* * The PCI interface treats multi-function devices as independent * devices. The slot/function address of each device is encoded @@ -1234,7 +1237,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, enum pci_bus_speed *speed, enum pcie_link_width *width); void pcie_print_link_status(struct pci_dev *dev); -int pcie_reset_flr(struct pci_dev *dev, int probe); +int pcie_reset_flr(struct pci_dev *dev, bool probe); int pcie_flr(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 2dac431d94ac..3a10d6ec3ee7 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -44,7 +44,7 @@ struct hotplug_slot_ops { int (*get_attention_status) (struct hotplug_slot *slot, u8 *value); int (*get_latch_status) (struct hotplug_slot *slot, u8 *value); int (*get_adapter_status) (struct hotplug_slot *slot, u8 *value); - int (*reset_slot) (struct hotplug_slot *slot, int probe); + int (*reset_slot) (struct hotplug_slot *slot, bool probe); }; /** -- cgit v1.2.3 From 39f75da7bcc829ddc4d40bb60d0e95520de7898b Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 2 Aug 2021 23:40:31 +0300 Subject: isystem: trim/fixup stdarg.h and other headers Delete/fixup few includes in anticipation of global -isystem compile option removal. Note: crypto/aegis128-neon-inner.c keeps due to redefinition of uintptr_t error (one definition comes from , another from ). Signed-off-by: Alexey Dobriyan Signed-off-by: Masahiro Yamada --- arch/arm/kernel/process.c | 2 -- arch/arm/mach-bcm/bcm_kona_smc.c | 2 -- arch/arm64/kernel/process.c | 3 --- arch/openrisc/kernel/process.c | 2 -- arch/parisc/kernel/process.c | 3 --- arch/powerpc/kernel/prom.c | 1 - arch/sparc/kernel/process_32.c | 3 --- arch/sparc/kernel/process_64.c | 3 --- arch/um/drivers/rtc_user.c | 1 + arch/um/drivers/vector_user.c | 1 + arch/um/include/shared/irq_user.h | 1 - arch/um/include/shared/os.h | 1 - arch/um/os-Linux/signal.c | 2 +- arch/um/os-Linux/util.c | 1 + drivers/block/xen-blkback/xenbus.c | 1 - drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 1 - drivers/gpu/drm/msm/disp/msm_disp_snapshot.h | 1 - drivers/macintosh/macio-adb.c | 1 - drivers/macintosh/via-macii.c | 2 -- drivers/net/wireless/intersil/orinoco/hermes.c | 1 - drivers/net/wwan/iosm/iosm_ipc_imem.h | 1 - drivers/pinctrl/aspeed/pinmux-aspeed.h | 1 - drivers/scsi/elx/efct/efct_driver.h | 1 - drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h | 2 -- drivers/xen/xen-scsiback.c | 2 -- include/linux/filter.h | 2 -- include/linux/mISDNif.h | 1 - kernel/debug/kdb/kdb_support.c | 1 - sound/aoa/codecs/onyx.h | 1 - sound/aoa/codecs/tas.c | 1 - sound/core/info.c | 1 - 31 files changed, 4 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index fc9e8b37eaa8..bb5ad8a6a4c3 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -5,8 +5,6 @@ * Copyright (C) 1996-2000 Russell King - Converted to ARM. * Original Copyright (C) 1995 Linus Torvalds */ -#include - #include #include #include diff --git a/arch/arm/mach-bcm/bcm_kona_smc.c b/arch/arm/mach-bcm/bcm_kona_smc.c index 43a16f922b53..43829e49ad93 100644 --- a/arch/arm/mach-bcm/bcm_kona_smc.c +++ b/arch/arm/mach-bcm/bcm_kona_smc.c @@ -10,8 +10,6 @@ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ - -#include #include #include #include diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index c8989b999250..5f7ac9a0f9a3 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -6,9 +6,6 @@ * Copyright (C) 1996-2000 Russell King - Converted to ARM. * Copyright (C) 2012 ARM Ltd. */ - -#include - #include #include #include diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index eb62429681fc..b0698d9ce14f 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -14,8 +14,6 @@ */ #define __KERNEL_SYSCALLS__ -#include - #include #include #include diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 184ec3c1eae4..38ec4ae81239 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -17,9 +17,6 @@ * Copyright (C) 2001-2014 Helge Deller * Copyright (C) 2002 Randolph Chung */ - -#include - #include #include #include diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f620e04dc9bf..a1e7ba0fad09 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -11,7 +11,6 @@ #undef DEBUG -#include #include #include #include diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index 93983d6d431d..bbbe0cfef746 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -8,9 +8,6 @@ /* * This file handles the architecture-dependent parts of process handling.. */ - -#include - #include #include #include diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index d33c58a58d4f..0cabcdfb23fd 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -9,9 +9,6 @@ /* * This file handles the architecture-dependent parts of process handling.. */ - -#include - #include #include #include diff --git a/arch/um/drivers/rtc_user.c b/arch/um/drivers/rtc_user.c index 4016bc1d577e..7c3cec4c68cf 100644 --- a/arch/um/drivers/rtc_user.c +++ b/arch/um/drivers/rtc_user.c @@ -3,6 +3,7 @@ * Copyright (C) 2020 Intel Corporation * Author: Johannes Berg */ +#include #include #include #include diff --git a/arch/um/drivers/vector_user.c b/arch/um/drivers/vector_user.c index bae53220ce26..e4ffeb9a1fa4 100644 --- a/arch/um/drivers/vector_user.c +++ b/arch/um/drivers/vector_user.c @@ -3,6 +3,7 @@ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) */ +#include #include #include #include diff --git a/arch/um/include/shared/irq_user.h b/arch/um/include/shared/irq_user.h index 065829f443ae..86a8a573b65c 100644 --- a/arch/um/include/shared/irq_user.h +++ b/arch/um/include/shared/irq_user.h @@ -7,7 +7,6 @@ #define __IRQ_USER_H__ #include -#include enum um_irq_type { IRQ_READ, diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index 60b84edc8a68..96d400387c93 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -8,7 +8,6 @@ #ifndef __OS_H__ #define __OS_H__ -#include #include #include #include diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c index 6de99bb16113..6cf098c23a39 100644 --- a/arch/um/os-Linux/signal.c +++ b/arch/um/os-Linux/signal.c @@ -67,7 +67,7 @@ int signals_enabled; #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT static int signals_blocked; #else -#define signals_blocked false +#define signals_blocked 0 #endif static unsigned int signals_pending; static unsigned int signals_active = 0; diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index 07327425d06e..41297ec404bf 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -3,6 +3,7 @@ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) */ +#include #include #include #include diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 125b22205d38..33eba3df4dd9 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -8,7 +8,6 @@ #define pr_fmt(fmt) "xen-blkback: " fmt -#include #include #include #include diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 7c4734f905d9..68fd451aca23 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -39,7 +39,6 @@ #include #include #include -#include #include "atomfirmware.h" diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h index c92a9508c8d3..0f9a5364cd86 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h @@ -25,7 +25,6 @@ #include #include #include -#include #include "msm_kms.h" #define MSM_DISP_SNAPSHOT_MAX_BLKS 10 diff --git a/drivers/macintosh/macio-adb.c b/drivers/macintosh/macio-adb.c index d4759db002c6..dc634c2932fd 100644 --- a/drivers/macintosh/macio-adb.c +++ b/drivers/macintosh/macio-adb.c @@ -2,7 +2,6 @@ /* * Driver for the ADB controller in the Mac I/O (Hydra) chip. */ -#include #include #include #include diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c index 060e03f2264b..db9270da5b8e 100644 --- a/drivers/macintosh/via-macii.c +++ b/drivers/macintosh/via-macii.c @@ -23,8 +23,6 @@ * Apple's "ADB Analyzer" bus sniffer is invaluable: * ftp://ftp.apple.com/developer/Tool_Chest/Devices_-_Hardware/Apple_Desktop_Bus/ */ - -#include #include #include #include diff --git a/drivers/net/wireless/intersil/orinoco/hermes.c b/drivers/net/wireless/intersil/orinoco/hermes.c index 6d4b7f64efcf..256946552742 100644 --- a/drivers/net/wireless/intersil/orinoco/hermes.c +++ b/drivers/net/wireless/intersil/orinoco/hermes.c @@ -79,7 +79,6 @@ #undef HERMES_DEBUG #ifdef HERMES_DEBUG -#include #define DEBUG(lvl, stuff...) if ((lvl) <= HERMES_DEBUG) DMSG(stuff) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h index 0d2f10e4cbc8..dc65b0712261 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h @@ -7,7 +7,6 @@ #define IOSM_IPC_IMEM_H #include -#include #include "iosm_ipc_mmio.h" #include "iosm_ipc_pcie.h" diff --git a/drivers/pinctrl/aspeed/pinmux-aspeed.h b/drivers/pinctrl/aspeed/pinmux-aspeed.h index b69ba6b360a2..4d7548686f39 100644 --- a/drivers/pinctrl/aspeed/pinmux-aspeed.h +++ b/drivers/pinctrl/aspeed/pinmux-aspeed.h @@ -5,7 +5,6 @@ #define ASPEED_PINMUX_H #include -#include /* * The ASPEED SoCs provide typically more than 200 pins for GPIO and other diff --git a/drivers/scsi/elx/efct/efct_driver.h b/drivers/scsi/elx/efct/efct_driver.h index dab8eac4f243..0e3c931db7c2 100644 --- a/drivers/scsi/elx/efct/efct_driver.h +++ b/drivers/scsi/elx/efct/efct_driver.h @@ -10,7 +10,6 @@ /*************************************************************************** * OS specific includes */ -#include #include #include #include diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h b/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h index eceeb5d160ad..4dbec4063b3d 100644 --- a/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h +++ b/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h @@ -16,8 +16,6 @@ #ifndef __ISP_LOCAL_H_INCLUDED__ #define __ISP_LOCAL_H_INCLUDED__ -#include - #include "isp_global.h" #include diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 61ce0d142eea..0c5e565aa8cf 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -33,8 +33,6 @@ #define pr_fmt(fmt) "xen-pvscsi: " fmt -#include - #include #include #include diff --git a/include/linux/filter.h b/include/linux/filter.h index 83b896044e79..c1711c9f9439 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -5,8 +5,6 @@ #ifndef __LINUX_FILTER_H__ #define __LINUX_FILTER_H__ -#include - #include #include #include diff --git a/include/linux/mISDNif.h b/include/linux/mISDNif.h index a7330eb3ec64..7dd1f01ec4f9 100644 --- a/include/linux/mISDNif.h +++ b/include/linux/mISDNif.h @@ -18,7 +18,6 @@ #ifndef mISDNIF_H #define mISDNIF_H -#include #include #include #include diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 9f50d22d68e6..4f9950678e7b 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -10,7 +10,6 @@ * 03/02/13 added new 2.5 kallsyms */ -#include #include #include #include diff --git a/sound/aoa/codecs/onyx.h b/sound/aoa/codecs/onyx.h index 8a32c3c3d716..6c31b7373b78 100644 --- a/sound/aoa/codecs/onyx.h +++ b/sound/aoa/codecs/onyx.h @@ -6,7 +6,6 @@ */ #ifndef __SND_AOA_CODEC_ONYX_H #define __SND_AOA_CODEC_ONYX_H -#include #include #include #include diff --git a/sound/aoa/codecs/tas.c b/sound/aoa/codecs/tas.c index ac246dd3ab49..ab19a37e2a68 100644 --- a/sound/aoa/codecs/tas.c +++ b/sound/aoa/codecs/tas.c @@ -58,7 +58,6 @@ * and up to the hardware designer to not wire * them up in some weird unusable way. */ -#include #include #include #include diff --git a/sound/core/info.c b/sound/core/info.c index 9fec3070f8ba..a451b24199c3 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -16,7 +16,6 @@ #include #include #include -#include int snd_info_check_reserved_words(const char *str) { -- cgit v1.2.3 From c0891ac15f0428ffa81b2e818d416bdf3cb74ab6 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 2 Aug 2021 23:40:32 +0300 Subject: isystem: ship and use stdarg.h Ship minimal stdarg.h (1 type, 4 macros) as . stdarg.h is the only userspace header commonly used in the kernel. GPL 2 version of can be extracted from http://archive.debian.org/debian/pool/main/g/gcc-4.2/gcc-4.2_4.2.4.orig.tar.gz Signed-off-by: Alexey Dobriyan Acked-by: Rafael J. Wysocki Acked-by: Ard Biesheuvel Signed-off-by: Masahiro Yamada --- arch/parisc/kernel/firmware.c | 2 +- arch/powerpc/kernel/prom_init.c | 2 +- arch/powerpc/kernel/rtas.c | 2 +- arch/powerpc/kernel/udbg.c | 2 +- arch/s390/boot/pgm_check_info.c | 2 +- arch/x86/boot/boot.h | 2 +- drivers/firmware/efi/libstub/efi-stub-helper.c | 2 +- drivers/firmware/efi/libstub/vsprintf.c | 2 +- drivers/gpu/drm/amd/display/dc/dc_helper.c | 2 +- drivers/gpu/drm/drm_print.c | 2 +- drivers/isdn/capi/capiutil.c | 2 +- drivers/macintosh/via-cuda.c | 2 +- drivers/macintosh/via-pmu.c | 2 +- .../media/atomisp/pci/hive_isp_css_include/print_support.h | 2 +- drivers/staging/media/atomisp/pci/ia_css_env.h | 2 +- .../media/atomisp/pci/runtime/debug/interface/ia_css_debug.h | 2 +- drivers/staging/media/atomisp/pci/sh_css_internal.h | 2 +- fs/befs/debug.c | 2 +- fs/reiserfs/prints.c | 2 +- fs/ufs/super.c | 2 +- include/acpi/platform/acgcc.h | 2 +- include/linux/kernel.h | 2 +- include/linux/printk.h | 2 +- include/linux/stdarg.h | 11 +++++++++++ include/linux/string.h | 2 +- lib/debug_info.c | 3 +-- lib/kasprintf.c | 2 +- lib/kunit/string-stream.h | 2 +- lib/vsprintf.c | 2 +- mm/kfence/report.c | 2 +- net/batman-adv/log.c | 2 +- 31 files changed, 41 insertions(+), 31 deletions(-) create mode 100644 include/linux/stdarg.h (limited to 'include/linux') diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 665b70086685..7034227dbdf3 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -51,7 +51,7 @@ * prumpf 991016 */ -#include +#include #include #include diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index a5bf355ce1d6..10664633f7e3 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -14,7 +14,7 @@ /* we cannot use FORTIFY as it brings in new symbols */ #define __NO_FORTIFY -#include +#include #include #include #include diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 99f2cce635fb..ff80bbad22a5 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -7,7 +7,7 @@ * Copyright (C) 2001 IBM. */ -#include +#include #include #include #include diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index 01595e8cafe7..b1544b2f6321 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -5,7 +5,7 @@ * c 2001 PPC 64 Team, IBM Corp */ -#include +#include #include #include #include diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c index 3a46abed2549..b7d8dd88bbf2 100644 --- a/arch/s390/boot/pgm_check_info.c +++ b/arch/s390/boot/pgm_check_info.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include #include @@ -8,7 +9,6 @@ #include #include #include -#include #include "boot.h" const char hex_asc[] = "0123456789abcdef"; diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index ca866f1cca2e..34c9dbb6a47d 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -18,7 +18,7 @@ #ifndef __ASSEMBLY__ -#include +#include #include #include #include diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index ae87dded989d..d489bdc645fe 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -7,7 +7,7 @@ * Copyright 2011 Intel Corporation; author Matt Fleming */ -#include +#include #include #include diff --git a/drivers/firmware/efi/libstub/vsprintf.c b/drivers/firmware/efi/libstub/vsprintf.c index 1088e288c04d..71c71c222346 100644 --- a/drivers/firmware/efi/libstub/vsprintf.c +++ b/drivers/firmware/efi/libstub/vsprintf.c @@ -10,7 +10,7 @@ * Oh, it's a waste of space, but oh-so-yummy for debugging. */ -#include +#include #include #include diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c index a612ba6dc389..ab6bc5d79012 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c @@ -28,9 +28,9 @@ */ #include +#include #include "dm_services.h" -#include #include "dc.h" #include "dc_dmub_srv.h" diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 111b932cf2a9..f783d4963d4b 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -25,7 +25,7 @@ #define DEBUG /* for pr_debug() */ -#include +#include #include #include diff --git a/drivers/isdn/capi/capiutil.c b/drivers/isdn/capi/capiutil.c index f26bf3c66d7e..d7ae42edc4a8 100644 --- a/drivers/isdn/capi/capiutil.c +++ b/drivers/isdn/capi/capiutil.c @@ -379,7 +379,7 @@ static char *pnames[] = /*2f */ "Useruserdata" }; -#include +#include /*-------------------------------------------------------*/ static _cdebbuf *bufprint(_cdebbuf *cdb, char *fmt, ...) diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c index 3581abfb0c6a..cd267392289c 100644 --- a/drivers/macintosh/via-cuda.c +++ b/drivers/macintosh/via-cuda.c @@ -9,7 +9,7 @@ * * Copyright (C) 1996 Paul Mackerras. */ -#include +#include #include #include #include diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index 4bdd4c45e7a7..4b98bc26a94b 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -18,7 +18,7 @@ * a sleep or a freq. switch * */ -#include +#include #include #include #include diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h b/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h index 540b405cc0f7..a3c7f3de6d17 100644 --- a/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h +++ b/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h @@ -16,7 +16,7 @@ #ifndef __PRINT_SUPPORT_H_INCLUDED__ #define __PRINT_SUPPORT_H_INCLUDED__ -#include +#include extern int (*sh_css_printf)(const char *fmt, va_list args); /* depends on host supplied print function in ia_css_init() */ diff --git a/drivers/staging/media/atomisp/pci/ia_css_env.h b/drivers/staging/media/atomisp/pci/ia_css_env.h index 6b38723b27cd..3b89bbd837a0 100644 --- a/drivers/staging/media/atomisp/pci/ia_css_env.h +++ b/drivers/staging/media/atomisp/pci/ia_css_env.h @@ -17,7 +17,7 @@ #define __IA_CSS_ENV_H #include -#include /* va_list */ +#include /* va_list */ #include "ia_css_types.h" #include "ia_css_acc_types.h" diff --git a/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h b/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h index 5e6e7447ae00..e37ef4232c55 100644 --- a/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h +++ b/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h @@ -19,7 +19,7 @@ /*! \file */ #include -#include +#include #include "ia_css_types.h" #include "ia_css_binary.h" #include "ia_css_frame_public.h" diff --git a/drivers/staging/media/atomisp/pci/sh_css_internal.h b/drivers/staging/media/atomisp/pci/sh_css_internal.h index 3c669ec79b68..496faa7297a5 100644 --- a/drivers/staging/media/atomisp/pci/sh_css_internal.h +++ b/drivers/staging/media/atomisp/pci/sh_css_internal.h @@ -20,7 +20,7 @@ #include #include #include -#include +#include #if !defined(ISP2401) #include "input_formatter.h" diff --git a/fs/befs/debug.c b/fs/befs/debug.c index eb7bd6c692c7..02fa66fb82c2 100644 --- a/fs/befs/debug.c +++ b/fs/befs/debug.c @@ -14,7 +14,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #ifdef __KERNEL__ -#include +#include #include #include #include diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index 500f2000eb41..30319dc33c18 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -8,7 +8,7 @@ #include #include -#include +#include static char error_buf[1024]; static char fmt_buf[1024]; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 74028b5a7b0a..00a01471ea05 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -70,7 +70,7 @@ #include #include -#include +#include #include diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h index f6656be81760..fb172a03a753 100644 --- a/include/acpi/platform/acgcc.h +++ b/include/acpi/platform/acgcc.h @@ -22,7 +22,7 @@ typedef __builtin_va_list va_list; #define va_arg(v, l) __builtin_va_arg(v, l) #define va_copy(d, s) __builtin_va_copy(d, s) #else -#include +#include #endif #endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 1b2f0a7e00d6..2776423a587e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -2,7 +2,7 @@ #ifndef _LINUX_KERNEL_H #define _LINUX_KERNEL_H -#include +#include #include #include #include diff --git a/include/linux/printk.h b/include/linux/printk.h index e834d78f0478..9f3f29ea348e 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -2,7 +2,7 @@ #ifndef __KERNEL_PRINTK__ #define __KERNEL_PRINTK__ -#include +#include #include #include #include diff --git a/include/linux/stdarg.h b/include/linux/stdarg.h new file mode 100644 index 000000000000..c8dc7f4f390c --- /dev/null +++ b/include/linux/stdarg.h @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#ifndef _LINUX_STDARG_H +#define _LINUX_STDARG_H + +typedef __builtin_va_list va_list; +#define va_start(v, l) __builtin_va_start(v, l) +#define va_end(v) __builtin_va_end(v) +#define va_arg(v, T) __builtin_va_arg(v, T) +#define va_copy(d, s) __builtin_va_copy(d, s) + +#endif diff --git a/include/linux/string.h b/include/linux/string.h index b48d2d28e0b1..5e96d656be7a 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -6,7 +6,7 @@ #include /* for size_t */ #include /* for NULL */ #include /* for E2BIG */ -#include +#include #include extern char *strndup_user(const char __user *, long); diff --git a/lib/debug_info.c b/lib/debug_info.c index 36daf753293c..cc4723c74af5 100644 --- a/lib/debug_info.c +++ b/lib/debug_info.c @@ -5,8 +5,6 @@ * CONFIG_DEBUG_INFO_REDUCED. Please do not add actual code. However, * adding appropriate #includes is fine. */ -#include - #include #include #include @@ -22,6 +20,7 @@ #include #include #include +#include #include #include #include diff --git a/lib/kasprintf.c b/lib/kasprintf.c index bacf7b83ccf0..cd2f5974ed98 100644 --- a/lib/kasprintf.c +++ b/lib/kasprintf.c @@ -5,7 +5,7 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#include +#include #include #include #include diff --git a/lib/kunit/string-stream.h b/lib/kunit/string-stream.h index 5e94b623454f..43f9508a55b4 100644 --- a/lib/kunit/string-stream.h +++ b/lib/kunit/string-stream.h @@ -11,7 +11,7 @@ #include #include -#include +#include struct string_stream_fragment { struct kunit *test; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 26c83943748a..3bcb7be03f93 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -17,7 +17,7 @@ * - scnprintf and vscnprintf */ -#include +#include #include #include #include diff --git a/mm/kfence/report.c b/mm/kfence/report.c index 2a319c21c939..4b891dd75650 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -5,7 +5,7 @@ * Copyright (C) 2020, Google LLC. */ -#include +#include #include #include diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index f0e5d1429662..7a93a1e94c40 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -7,7 +7,7 @@ #include "log.h" #include "main.h" -#include +#include #include "trace.h" -- cgit v1.2.3 From 22f9feb49950885cdb6e37513f134d154175e743 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Jun 2021 19:37:00 +0200 Subject: dma-mapping: make the global coherent pool conditional Only build the code to support the global coherent pool if support for it is enabled. Signed-off-by: Christoph Hellwig Tested-by: Dillon Min --- include/linux/dma-map-ops.h | 18 +++++++++-------- kernel/dma/coherent.c | 49 +++++++++++++++++++++++++-------------------- 2 files changed, 37 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 068f1b11a6a4..0d5b06b3a4a6 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -171,13 +171,6 @@ int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr); int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, size_t size, int *ret); - -void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, - dma_addr_t *dma_handle); -int dma_release_from_global_coherent(int order, void *vaddr); -int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr, - size_t size, int *ret); -int dma_init_global_coherent(phys_addr_t phys_addr, size_t size); #else static inline int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size) @@ -187,7 +180,16 @@ static inline int dma_declare_coherent_memory(struct device *dev, #define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0) #define dma_release_from_dev_coherent(dev, order, vaddr) (0) #define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0) +#endif /* CONFIG_DMA_DECLARE_COHERENT */ +#ifdef CONFIG_DMA_GLOBAL_POOL +void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, + dma_addr_t *dma_handle); +int dma_release_from_global_coherent(int order, void *vaddr); +int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr, + size_t size, int *ret); +int dma_init_global_coherent(phys_addr_t phys_addr, size_t size); +#else static inline void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle) { @@ -202,7 +204,7 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, { return 0; } -#endif /* CONFIG_DMA_DECLARE_COHERENT */ +#endif /* CONFIG_DMA_GLOBAL_POOL */ /* * This is the actual return value from the ->alloc_noncontiguous method. diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index 160d4e246ecb..25fc85a7aebe 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -20,8 +20,6 @@ struct dma_coherent_mem { bool use_dev_dma_pfn_offset; }; -static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init; - static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev) { if (dev && dev->dma_mem) @@ -191,16 +189,6 @@ int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, return 1; } -void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, - dma_addr_t *dma_handle) -{ - if (!dma_coherent_default_memory) - return NULL; - - return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size, - dma_handle); -} - static int __dma_release_from_coherent(struct dma_coherent_mem *mem, int order, void *vaddr) { @@ -236,15 +224,6 @@ int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr) return __dma_release_from_coherent(mem, order, vaddr); } -int dma_release_from_global_coherent(int order, void *vaddr) -{ - if (!dma_coherent_default_memory) - return 0; - - return __dma_release_from_coherent(dma_coherent_default_memory, order, - vaddr); -} - static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem, struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) { @@ -290,6 +269,28 @@ int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret); } +#ifdef CONFIG_DMA_GLOBAL_POOL +static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init; + +void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, + dma_addr_t *dma_handle) +{ + if (!dma_coherent_default_memory) + return NULL; + + return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size, + dma_handle); +} + +int dma_release_from_global_coherent(int order, void *vaddr) +{ + if (!dma_coherent_default_memory) + return 0; + + return __dma_release_from_coherent(dma_coherent_default_memory, order, + vaddr); +} + int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) { @@ -311,6 +312,7 @@ int dma_init_global_coherent(phys_addr_t phys_addr, size_t size) pr_info("DMA: default coherent area is set\n"); return 0; } +#endif /* CONFIG_DMA_GLOBAL_POOL */ /* * Support for reserved memory regions defined in device tree @@ -320,7 +322,9 @@ int dma_init_global_coherent(phys_addr_t phys_addr, size_t size) #include #include +#ifdef CONFIG_DMA_GLOBAL_POOL static struct reserved_mem *dma_reserved_default_memory __initdata; +#endif static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev) { @@ -377,6 +381,7 @@ static int __init rmem_dma_setup(struct reserved_mem *rmem) return 0; } +#ifdef CONFIG_DMA_GLOBAL_POOL static int __init dma_init_reserved_memory(void) { if (!dma_reserved_default_memory) @@ -384,8 +389,8 @@ static int __init dma_init_reserved_memory(void) return dma_init_global_coherent(dma_reserved_default_memory->base, dma_reserved_default_memory->size); } - core_initcall(dma_init_reserved_memory); +#endif /* CONFIG_DMA_GLOBAL_POOL */ RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup); #endif -- cgit v1.2.3 From 4d99efb229e63928c6b03a756a2e38cd4777fbe8 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 18 Aug 2021 21:48:44 +0800 Subject: iommu/vt-d: Update the virtual command related registers The VT-d spec Revision 3.3 updated the virtual command registers, virtual command opcode B register, virtual command response register and virtual command capability register (Section 10.4.43, 10.4.44, 10.4.45, 10.4.46). This updates the virtual command interface implementation in the Intel IOMMU driver accordingly. Fixes: 24f27d32ab6b7 ("iommu/vt-d: Enlightened PASID allocation") Signed-off-by: Lu Baolu Cc: Ashok Raj Cc: Sanjay Kumar Cc: Kevin Tian Link: https://lore.kernel.org/r/20210713042649.3547403-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20210818134852.1847070-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/pasid.h | 10 +++++----- include/linux/intel-iommu.h | 6 +++--- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index 5ff61c3d401f..8c2efb85fb3b 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -28,12 +28,12 @@ #define VCMD_CMD_ALLOC 0x1 #define VCMD_CMD_FREE 0x2 #define VCMD_VRSP_IP 0x1 -#define VCMD_VRSP_SC(e) (((e) >> 1) & 0x3) +#define VCMD_VRSP_SC(e) (((e) & 0xff) >> 1) #define VCMD_VRSP_SC_SUCCESS 0 -#define VCMD_VRSP_SC_NO_PASID_AVAIL 2 -#define VCMD_VRSP_SC_INVALID_PASID 2 -#define VCMD_VRSP_RESULT_PASID(e) (((e) >> 8) & 0xfffff) -#define VCMD_CMD_OPERAND(e) ((e) << 8) +#define VCMD_VRSP_SC_NO_PASID_AVAIL 16 +#define VCMD_VRSP_SC_INVALID_PASID 16 +#define VCMD_VRSP_RESULT_PASID(e) (((e) >> 16) & 0xfffff) +#define VCMD_CMD_OPERAND(e) ((e) << 16) /* * Domain ID reserved for pasid entries programmed for first-level * only and pass-through transfer modes. diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index d0fa0b31994d..05a65eb155f7 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -124,9 +124,9 @@ #define DMAR_MTRR_PHYSMASK8_REG 0x208 #define DMAR_MTRR_PHYSBASE9_REG 0x210 #define DMAR_MTRR_PHYSMASK9_REG 0x218 -#define DMAR_VCCAP_REG 0xe00 /* Virtual command capability register */ -#define DMAR_VCMD_REG 0xe10 /* Virtual command register */ -#define DMAR_VCRSP_REG 0xe20 /* Virtual command response register */ +#define DMAR_VCCAP_REG 0xe30 /* Virtual command capability register */ +#define DMAR_VCMD_REG 0xe00 /* Virtual command register */ +#define DMAR_VCRSP_REG 0xe10 /* Virtual command response register */ #define DMAR_IQER_REG_IQEI(reg) FIELD_GET(GENMASK_ULL(3, 0), reg) #define DMAR_IQER_REG_ITESID(reg) FIELD_GET(GENMASK_ULL(47, 32), reg) -- cgit v1.2.3 From 48811c44349ffbb778d3e36b53beb03ad43a979c Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 18 Aug 2021 21:48:49 +0800 Subject: iommu/vt-d: Allow devices to have more than 32 outstanding PRs The minimum per-IOMMU PRQ queue size is one 4K page, this is more entries than the hardcoded limit of 32 in the current VT-d code. Some devices can support up to 512 outstanding PRQs but underutilized by this limit of 32. Although, 32 gives some rough fairness when multiple devices share the same IOMMU PRQ queue, but far from optimal for customized use case. This extends the per-IOMMU PRQ queue size to four 4K pages and let the devices have as many outstanding page requests as they can. Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210720013856.4143880-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20210818134852.1847070-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 3 ++- drivers/iommu/intel/svm.c | 4 ---- include/linux/intel-svm.h | 5 +++++ 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 8d4d49e12c51..d75f59ae28e6 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -1541,7 +1542,7 @@ static void iommu_enable_dev_iotlb(struct device_domain_info *info) if (info->pri_supported && (info->pasid_enabled ? pci_prg_resp_pasid_required(pdev) : 1) && - !pci_reset_pri(pdev) && !pci_enable_pri(pdev, 32)) + !pci_reset_pri(pdev) && !pci_enable_pri(pdev, PRQ_DEPTH)) info->pri_enabled = 1; #endif if (info->ats_supported && pci_ats_page_aligned(pdev) && diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 9b0f22bc0514..813438a07b62 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -31,8 +31,6 @@ static irqreturn_t prq_event_thread(int irq, void *d); static void intel_svm_drain_prq(struct device *dev, u32 pasid); #define to_intel_svm_dev(handle) container_of(handle, struct intel_svm_dev, sva) -#define PRQ_ORDER 0 - static DEFINE_XARRAY_ALLOC(pasid_private_array); static int pasid_private_add(ioasid_t pasid, void *priv) { @@ -724,8 +722,6 @@ struct page_req_dsc { u64 priv_data[2]; }; -#define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) - static bool is_canonical_address(u64 addr) { int shift = 64 - (__VIRTUAL_MASK_SHIFT + 1); diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 10fa80eef13a..57cceecbe37f 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -14,6 +14,11 @@ #define SVM_REQ_EXEC (1<<1) #define SVM_REQ_PRIV (1<<0) +/* Page Request Queue depth */ +#define PRQ_ORDER 2 +#define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) +#define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) + /* * The SVM_FLAG_SUPERVISOR_MODE flag requests a PASID which can be used only * for access to kernel addresses. No IOTLB flushes are automatically done -- cgit v1.2.3 From e1c6b9e1669e44fb7f9688e34e460b759e3b9187 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 2 Aug 2021 19:28:08 +0000 Subject: entry: KVM: Allow use of generic KVM entry w/o full generic support Some architectures (e.g. arm64) have yet to adopt the generic entry infrastructure. Despite that, it would be nice to use some common plumbing for guest entry/exit handling. For example, KVM/arm64 currently does not handle TIF_NOTIFY_PENDING correctly. Allow use of only the generic KVM entry code by tightening up the include list. No functional change intended. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210802192809.1851010-3-oupton@google.com --- include/linux/entry-kvm.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 136b8d97d8c0..0d7865a0731c 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -2,7 +2,11 @@ #ifndef __LINUX_ENTRYKVM_H #define __LINUX_ENTRYKVM_H -#include +#include +#include +#include +#include +#include #include /* Transfer to guest mode work */ -- cgit v1.2.3 From 2274af1d60fee3fe35f341fc5d4dbf99ab78fb2f Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Wed, 18 Aug 2021 18:07:09 +0300 Subject: net: mii: make mii_ethtool_gset() return void mii_ethtool_gset() does not return any errors. Since there are no users of this function that rely on its return value, it can be made void. Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/mii.c | 6 +----- include/linux/mii.h | 2 +- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mii.c b/drivers/net/mii.c index 779c3a96dba7..22680f47385d 100644 --- a/drivers/net/mii.c +++ b/drivers/net/mii.c @@ -49,10 +49,8 @@ static u32 mii_get_an(struct mii_if_info *mii, u16 addr) * * The @ecmd parameter is expected to have been cleared before calling * mii_ethtool_gset(). - * - * Returns 0 for success, negative on error. */ -int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd) +void mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd) { struct net_device *dev = mii->dev; u16 bmcr, bmsr, ctrl1000 = 0, stat1000 = 0; @@ -131,8 +129,6 @@ int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd) mii->full_duplex = ecmd->duplex; /* ignore maxtxpkt, maxrxpkt for now */ - - return 0; } /** diff --git a/include/linux/mii.h b/include/linux/mii.h index 219b93cad1dd..12ea29e04293 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -32,7 +32,7 @@ struct mii_if_info { extern int mii_link_ok (struct mii_if_info *mii); extern int mii_nway_restart (struct mii_if_info *mii); -extern int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); +extern void mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); extern void mii_ethtool_get_link_ksettings( struct mii_if_info *mii, struct ethtool_link_ksettings *cmd); extern int mii_ethtool_sset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); -- cgit v1.2.3 From 6e86a1543c378f2e8837ad88f361b7bf606c80f7 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 18 Aug 2021 09:12:32 +0200 Subject: can: dev: provide optional GPIO based termination support For CAN buses to work, a termination resistor has to be present at both ends of the bus. This resistor is usually 120 Ohms, other values may be required for special bus topologies. This patch adds support for a generic GPIO based CAN termination. The resistor value has to be specified via device tree, and it can only be attached to or detached from the bus. By default the termination is not active. Link: https://lore.kernel.org/r/20210818071232.20585-4-o.rempel@pengutronix.de Signed-off-by: Oleksij Rempel Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/dev.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/can/dev.h | 8 ++++++ 2 files changed, 74 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index 311d8564d611..e3d840b81357 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #define MOD_DESC "CAN device driver interface" @@ -400,10 +401,69 @@ void close_candev(struct net_device *dev) } EXPORT_SYMBOL_GPL(close_candev); +static int can_set_termination(struct net_device *ndev, u16 term) +{ + struct can_priv *priv = netdev_priv(ndev); + int set; + + if (term == priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_ENABLED]) + set = 1; + else + set = 0; + + gpiod_set_value(priv->termination_gpio, set); + + return 0; +} + +static int can_get_termination(struct net_device *ndev) +{ + struct can_priv *priv = netdev_priv(ndev); + struct device *dev = ndev->dev.parent; + struct gpio_desc *gpio; + u32 term; + int ret; + + /* Disabling termination by default is the safe choice: Else if many + * bus participants enable it, no communication is possible at all. + */ + gpio = devm_gpiod_get_optional(dev, "termination", GPIOD_OUT_LOW); + if (IS_ERR(gpio)) + return dev_err_probe(dev, PTR_ERR(gpio), + "Cannot get termination-gpios\n"); + + if (!gpio) + return 0; + + ret = device_property_read_u32(dev, "termination-ohms", &term); + if (ret) { + netdev_err(ndev, "Cannot get termination-ohms: %pe\n", + ERR_PTR(ret)); + return ret; + } + + if (term > U16_MAX) { + netdev_err(ndev, "Invalid termination-ohms value (%u > %u)\n", + term, U16_MAX); + return -EINVAL; + } + + priv->termination_const_cnt = ARRAY_SIZE(priv->termination_gpio_ohms); + priv->termination_const = priv->termination_gpio_ohms; + priv->termination_gpio = gpio; + priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_DISABLED] = + CAN_TERMINATION_DISABLED; + priv->termination_gpio_ohms[CAN_TERMINATION_GPIO_ENABLED] = term; + priv->do_set_termination = can_set_termination; + + return 0; +} + /* Register the CAN network device */ int register_candev(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); + int err; /* Ensure termination_const, termination_const_cnt and * do_set_termination consistency. All must be either set or @@ -419,6 +479,12 @@ int register_candev(struct net_device *dev) if (!priv->data_bitrate_const != !priv->data_bitrate_const_cnt) return -EINVAL; + if (!priv->termination_const) { + err = can_get_termination(dev); + if (err) + return err; + } + dev->rtnl_link_ops = &can_link_ops; netif_carrier_off(dev); diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 27b275e463da..2413253e54c7 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -32,6 +32,12 @@ enum can_mode { CAN_MODE_SLEEP }; +enum can_termination_gpio { + CAN_TERMINATION_GPIO_DISABLED = 0, + CAN_TERMINATION_GPIO_ENABLED, + CAN_TERMINATION_GPIO_MAX, +}; + /* * CAN common private data */ @@ -55,6 +61,8 @@ struct can_priv { unsigned int termination_const_cnt; const u16 *termination_const; u16 termination; + struct gpio_desc *termination_gpio; + u16 termination_gpio_ohms[CAN_TERMINATION_GPIO_MAX]; enum can_state state; -- cgit v1.2.3 From 1cf362e907f36f104b9cf590ee6ced786226b388 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Thu, 19 Aug 2021 18:03:37 +0530 Subject: PCI: endpoint: Add support to add virtual function in endpoint core Add support to add virtual function in endpoint core. The virtual function can only be associated with a physical function instead of a endpoint controller. Provide APIs to associate a virtual function with a physical function here. [weiyongjun1@huawei.com: PCI: endpoint: Fix missing unlock on error in pci_epf_add_vepf() - Reported-by: Hulk Robot ] Link: https://lore.kernel.org/r/20210819123343.1951-3-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Wei Yongjun Signed-off-by: Lorenzo Pieralisi --- drivers/pci/endpoint/pci-epc-core.c | 2 +- drivers/pci/endpoint/pci-epf-core.c | 98 ++++++++++++++++++++++++++++++++++++- include/linux/pci-epf.h | 16 +++++- 3 files changed, 113 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index adec9bee72cf..01c58ca84dcc 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -548,7 +548,7 @@ int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf, u32 func_no; int ret = 0; - if (IS_ERR_OR_NULL(epc)) + if (IS_ERR_OR_NULL(epc) || epf->is_vf) return -EINVAL; if (type == PRIMARY_INTERFACE && epf->epc) diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index e9289d10f822..296479659aa2 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -62,13 +62,20 @@ EXPORT_SYMBOL_GPL(pci_epf_type_add_cfs); */ void pci_epf_unbind(struct pci_epf *epf) { + struct pci_epf *epf_vf; + if (!epf->driver) { dev_WARN(&epf->dev, "epf device not bound to driver\n"); return; } mutex_lock(&epf->lock); - epf->driver->ops->unbind(epf); + list_for_each_entry(epf_vf, &epf->pci_vepf, list) { + if (epf_vf->is_bound) + epf_vf->driver->ops->unbind(epf_vf); + } + if (epf->is_bound) + epf->driver->ops->unbind(epf); mutex_unlock(&epf->lock); module_put(epf->driver->owner); } @@ -83,6 +90,7 @@ EXPORT_SYMBOL_GPL(pci_epf_unbind); */ int pci_epf_bind(struct pci_epf *epf) { + struct pci_epf *epf_vf; int ret; if (!epf->driver) { @@ -94,13 +102,97 @@ int pci_epf_bind(struct pci_epf *epf) return -EAGAIN; mutex_lock(&epf->lock); + list_for_each_entry(epf_vf, &epf->pci_vepf, list) { + epf_vf->func_no = epf->func_no; + epf_vf->epc = epf->epc; + epf_vf->sec_epc = epf->sec_epc; + ret = epf_vf->driver->ops->bind(epf_vf); + if (ret) + goto ret; + epf_vf->is_bound = true; + } + ret = epf->driver->ops->bind(epf); + if (ret) + goto ret; + epf->is_bound = true; + + mutex_unlock(&epf->lock); + return 0; + +ret: mutex_unlock(&epf->lock); + pci_epf_unbind(epf); return ret; } EXPORT_SYMBOL_GPL(pci_epf_bind); +/** + * pci_epf_add_vepf() - associate virtual EP function to physical EP function + * @epf_pf: the physical EP function to which the virtual EP function should be + * associated + * @epf_vf: the virtual EP function to be added + * + * A physical endpoint function can be associated with multiple virtual + * endpoint functions. Invoke pci_epf_add_epf() to add a virtual PCI endpoint + * function to a physical PCI endpoint function. + */ +int pci_epf_add_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf) +{ + u32 vfunc_no; + + if (IS_ERR_OR_NULL(epf_pf) || IS_ERR_OR_NULL(epf_vf)) + return -EINVAL; + + if (epf_pf->epc || epf_vf->epc || epf_vf->epf_pf) + return -EBUSY; + + if (epf_pf->sec_epc || epf_vf->sec_epc) + return -EBUSY; + + mutex_lock(&epf_pf->lock); + vfunc_no = find_first_zero_bit(&epf_pf->vfunction_num_map, + BITS_PER_LONG); + if (vfunc_no >= BITS_PER_LONG) { + mutex_unlock(&epf_pf->lock); + return -EINVAL; + } + + set_bit(vfunc_no, &epf_pf->vfunction_num_map); + epf_vf->vfunc_no = vfunc_no; + + epf_vf->epf_pf = epf_pf; + epf_vf->is_vf = true; + + list_add_tail(&epf_vf->list, &epf_pf->pci_vepf); + mutex_unlock(&epf_pf->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(pci_epf_add_vepf); + +/** + * pci_epf_remove_vepf() - remove virtual EP function from physical EP function + * @epf_pf: the physical EP function from which the virtual EP function should + * be removed + * @epf_vf: the virtual EP function to be removed + * + * Invoke to remove a virtual endpoint function from the physcial endpoint + * function. + */ +void pci_epf_remove_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf) +{ + if (IS_ERR_OR_NULL(epf_pf) || IS_ERR_OR_NULL(epf_vf)) + return; + + mutex_lock(&epf_pf->lock); + clear_bit(epf_vf->vfunc_no, &epf_pf->vfunction_num_map); + list_del(&epf_vf->list); + mutex_unlock(&epf_pf->lock); +} +EXPORT_SYMBOL_GPL(pci_epf_remove_vepf); + /** * pci_epf_free_space() - free the allocated PCI EPF register space * @epf: the EPF device from whom to free the memory @@ -317,6 +409,10 @@ struct pci_epf *pci_epf_create(const char *name) return ERR_PTR(-ENOMEM); } + /* VFs are numbered starting with 1. So set BIT(0) by default */ + epf->vfunction_num_map = 1; + INIT_LIST_HEAD(&epf->pci_vepf); + dev = &epf->dev; device_initialize(dev); dev->bus = &pci_epf_bus_type; diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 2debc27ba95e..043b4c9c7188 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -121,8 +121,10 @@ struct pci_epf_bar { * @bar: represents the BAR of EPF device * @msi_interrupts: number of MSI interrupts required by this function * @msix_interrupts: number of MSI-X interrupts required by this function - * @func_no: unique function number within this endpoint device + * @func_no: unique (physical) function number within this endpoint device + * @vfunc_no: unique virtual function number within a physical function * @epc: the EPC device to which this EPF device is bound + * @epf_pf: the physical EPF device to which this virtual EPF device is bound * @driver: the EPF driver to which this EPF device is bound * @list: to add pci_epf as a list of PCI endpoint functions to pci_epc * @nb: notifier block to notify EPF of any EPC events (like linkup) @@ -133,6 +135,10 @@ struct pci_epf_bar { * @sec_epc_bar: represents the BAR of EPF device associated with secondary EPC * @sec_epc_func_no: unique (physical) function number within the secondary EPC * @group: configfs group associated with the EPF device + * @is_bound: indicates if bind notification to function driver has been invoked + * @is_vf: true - virtual function, false - physical function + * @vfunction_num_map: bitmap to manage virtual function number + * @pci_vepf: list of virtual endpoint functions associated with this function */ struct pci_epf { struct device dev; @@ -142,8 +148,10 @@ struct pci_epf { u8 msi_interrupts; u16 msix_interrupts; u8 func_no; + u8 vfunc_no; struct pci_epc *epc; + struct pci_epf *epf_pf; struct pci_epf_driver *driver; struct list_head list; struct notifier_block nb; @@ -156,6 +164,10 @@ struct pci_epf { struct pci_epf_bar sec_epc_bar[6]; u8 sec_epc_func_no; struct config_group *group; + unsigned int is_bound; + unsigned int is_vf; + unsigned long vfunction_num_map; + struct list_head pci_vepf; }; /** @@ -199,4 +211,6 @@ int pci_epf_bind(struct pci_epf *epf); void pci_epf_unbind(struct pci_epf *epf); struct config_group *pci_epf_type_add_cfs(struct pci_epf *epf, struct config_group *group); +int pci_epf_add_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf); +void pci_epf_remove_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf); #endif /* __LINUX_PCI_EPF_H */ -- cgit v1.2.3 From 53fd3cbe5e9d791d6bb6059f73a3851f155ce7c6 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Thu, 19 Aug 2021 18:03:39 +0530 Subject: PCI: endpoint: Add virtual function number in pci_epc ops Add virtual function number in pci_epc ops. EPC controller driver can perform virtual function specific initialization based on the virtual function number. Link: https://lore.kernel.org/r/20210819123343.1951-5-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/cadence/pcie-cadence-ep.c | 44 ++++---- drivers/pci/controller/dwc/pcie-designware-ep.c | 36 +++---- drivers/pci/controller/pcie-rcar-ep.c | 19 ++-- drivers/pci/controller/pcie-rockchip-ep.c | 18 ++-- drivers/pci/endpoint/functions/pci-epf-ntb.c | 89 +++++++++------ drivers/pci/endpoint/functions/pci-epf-test.c | 74 +++++++------ drivers/pci/endpoint/pci-epc-core.c | 132 ++++++++++++++++------- drivers/pci/endpoint/pci-epf-core.c | 48 ++++++++- include/linux/pci-epc.h | 57 +++++----- 9 files changed, 328 insertions(+), 189 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c index 897cdde02bd8..912a15be8bfd 100644 --- a/drivers/pci/controller/cadence/pcie-cadence-ep.c +++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c @@ -16,7 +16,7 @@ #define CDNS_PCIE_EP_IRQ_PCI_ADDR_NONE 0x1 #define CDNS_PCIE_EP_IRQ_PCI_ADDR_LEGACY 0x3 -static int cdns_pcie_ep_write_header(struct pci_epc *epc, u8 fn, +static int cdns_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_header *hdr) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); @@ -47,7 +47,7 @@ static int cdns_pcie_ep_write_header(struct pci_epc *epc, u8 fn, return 0; } -static int cdns_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, +static int cdns_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_bar *epf_bar) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); @@ -117,7 +117,7 @@ static int cdns_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, return 0; } -static void cdns_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, +static void cdns_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_bar *epf_bar) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); @@ -147,8 +147,8 @@ static void cdns_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, epf->epf_bar[bar] = NULL; } -static int cdns_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, phys_addr_t addr, - u64 pci_addr, size_t size) +static int cdns_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr, u64 pci_addr, size_t size) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); struct cdns_pcie *pcie = &ep->pcie; @@ -169,7 +169,7 @@ static int cdns_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, phys_addr_t addr, return 0; } -static void cdns_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, +static void cdns_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, phys_addr_t addr) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); @@ -189,7 +189,7 @@ static void cdns_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, clear_bit(r, &ep->ob_region_map); } -static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 mmc) +static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 mmc) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); struct cdns_pcie *pcie = &ep->pcie; @@ -209,7 +209,7 @@ static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 mmc) return 0; } -static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) +static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); struct cdns_pcie *pcie = &ep->pcie; @@ -230,7 +230,7 @@ static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) return mme; } -static int cdns_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no) +static int cdns_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); struct cdns_pcie *pcie = &ep->pcie; @@ -247,8 +247,9 @@ static int cdns_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no) return val; } -static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u16 interrupts, - enum pci_barno bir, u32 offset) +static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn, + u16 interrupts, enum pci_barno bir, + u32 offset) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); struct cdns_pcie *pcie = &ep->pcie; @@ -317,7 +318,8 @@ static void cdns_pcie_ep_assert_intx(struct cdns_pcie_ep *ep, u8 fn, writel(0, ep->irq_cpu_addr + offset); } -static int cdns_pcie_ep_send_legacy_irq(struct cdns_pcie_ep *ep, u8 fn, u8 intx) +static int cdns_pcie_ep_send_legacy_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn, + u8 intx) { u16 cmd; @@ -334,7 +336,7 @@ static int cdns_pcie_ep_send_legacy_irq(struct cdns_pcie_ep *ep, u8 fn, u8 intx) return 0; } -static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn, +static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn, u8 interrupt_num) { struct cdns_pcie *pcie = &ep->pcie; @@ -382,7 +384,7 @@ static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn, return 0; } -static int cdns_pcie_ep_map_msi_irq(struct pci_epc *epc, u8 fn, +static int cdns_pcie_ep_map_msi_irq(struct pci_epc *epc, u8 fn, u8 vfn, phys_addr_t addr, u8 interrupt_num, u32 entry_size, u32 *msi_data, u32 *msi_addr_offset) @@ -419,7 +421,7 @@ static int cdns_pcie_ep_map_msi_irq(struct pci_epc *epc, u8 fn, pci_addr &= GENMASK_ULL(63, 2); for (i = 0; i < interrupt_num; i++) { - ret = cdns_pcie_ep_map_addr(epc, fn, addr, + ret = cdns_pcie_ep_map_addr(epc, fn, vfn, addr, pci_addr & ~pci_addr_mask, entry_size); if (ret) @@ -433,7 +435,7 @@ static int cdns_pcie_ep_map_msi_irq(struct pci_epc *epc, u8 fn, return 0; } -static int cdns_pcie_ep_send_msix_irq(struct cdns_pcie_ep *ep, u8 fn, +static int cdns_pcie_ep_send_msix_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn, u16 interrupt_num) { u32 cap = CDNS_PCIE_EP_FUNC_MSIX_CAP_OFFSET; @@ -478,7 +480,7 @@ static int cdns_pcie_ep_send_msix_irq(struct cdns_pcie_ep *ep, u8 fn, return 0; } -static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, +static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn, enum pci_epc_irq_type type, u16 interrupt_num) { @@ -486,13 +488,13 @@ static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, switch (type) { case PCI_EPC_IRQ_LEGACY: - return cdns_pcie_ep_send_legacy_irq(ep, fn, 0); + return cdns_pcie_ep_send_legacy_irq(ep, fn, vfn, 0); case PCI_EPC_IRQ_MSI: - return cdns_pcie_ep_send_msi_irq(ep, fn, interrupt_num); + return cdns_pcie_ep_send_msi_irq(ep, fn, vfn, interrupt_num); case PCI_EPC_IRQ_MSIX: - return cdns_pcie_ep_send_msix_irq(ep, fn, interrupt_num); + return cdns_pcie_ep_send_msix_irq(ep, fn, vfn, interrupt_num); default: break; @@ -531,7 +533,7 @@ static const struct pci_epc_features cdns_pcie_epc_features = { }; static const struct pci_epc_features* -cdns_pcie_ep_get_features(struct pci_epc *epc, u8 func_no) +cdns_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { return &cdns_pcie_epc_features; } diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 8d028a88b375..998b698f4085 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -125,7 +125,7 @@ static u8 dw_pcie_ep_find_capability(struct dw_pcie_ep *ep, u8 func_no, u8 cap) return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap); } -static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, +static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_header *hdr) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); @@ -202,7 +202,7 @@ static int dw_pcie_ep_outbound_atu(struct dw_pcie_ep *ep, u8 func_no, return 0; } -static void dw_pcie_ep_clear_bar(struct pci_epc *epc, u8 func_no, +static void dw_pcie_ep_clear_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); @@ -217,7 +217,7 @@ static void dw_pcie_ep_clear_bar(struct pci_epc *epc, u8 func_no, ep->epf_bar[bar] = NULL; } -static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, +static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar) { int ret; @@ -276,7 +276,7 @@ static int dw_pcie_find_index(struct dw_pcie_ep *ep, phys_addr_t addr, return -EINVAL; } -static void dw_pcie_ep_unmap_addr(struct pci_epc *epc, u8 func_no, +static void dw_pcie_ep_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t addr) { int ret; @@ -292,9 +292,8 @@ static void dw_pcie_ep_unmap_addr(struct pci_epc *epc, u8 func_no, clear_bit(atu_index, ep->ob_window_map); } -static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, - phys_addr_t addr, - u64 pci_addr, size_t size) +static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + phys_addr_t addr, u64 pci_addr, size_t size) { int ret; struct dw_pcie_ep *ep = epc_get_drvdata(epc); @@ -309,7 +308,7 @@ static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, return 0; } -static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no) +static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); @@ -333,7 +332,8 @@ static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no) return val; } -static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts) +static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + u8 interrupts) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); @@ -358,7 +358,7 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts) return 0; } -static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no) +static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); @@ -382,8 +382,8 @@ static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no) return val; } -static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts, - enum pci_barno bir, u32 offset) +static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + u16 interrupts, enum pci_barno bir, u32 offset) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); @@ -418,7 +418,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts, return 0; } -static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no, +static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no, enum pci_epc_irq_type type, u16 interrupt_num) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); @@ -450,7 +450,7 @@ static int dw_pcie_ep_start(struct pci_epc *epc) } static const struct pci_epc_features* -dw_pcie_ep_get_features(struct pci_epc *epc, u8 func_no) +dw_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); @@ -525,14 +525,14 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, aligned_offset = msg_addr_lower & (epc->mem->window.page_size - 1); msg_addr = ((u64)msg_addr_upper) << 32 | (msg_addr_lower & ~aligned_offset); - ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr, + ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, epc->mem->window.page_size); if (ret) return ret; writel(msg_data | (interrupt_num - 1), ep->msi_mem + aligned_offset); - dw_pcie_ep_unmap_addr(epc, func_no, ep->msi_mem_phys); + dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); return 0; } @@ -593,14 +593,14 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, } aligned_offset = msg_addr & (epc->mem->window.page_size - 1); - ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr, + ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, epc->mem->window.page_size); if (ret) return ret; writel(msg_data, ep->msi_mem + aligned_offset); - dw_pcie_ep_unmap_addr(epc, func_no, ep->msi_mem_phys); + dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); return 0; } diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c index b4a288e24aaf..6cee4e09acca 100644 --- a/drivers/pci/controller/pcie-rcar-ep.c +++ b/drivers/pci/controller/pcie-rcar-ep.c @@ -159,7 +159,7 @@ static int rcar_pcie_ep_get_pdata(struct rcar_pcie_endpoint *ep, return 0; } -static int rcar_pcie_ep_write_header(struct pci_epc *epc, u8 fn, +static int rcar_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_header *hdr) { struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); @@ -195,7 +195,7 @@ static int rcar_pcie_ep_write_header(struct pci_epc *epc, u8 fn, return 0; } -static int rcar_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, +static int rcar_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar) { int flags = epf_bar->flags | LAR_ENABLE | LAM_64BIT; @@ -246,7 +246,7 @@ static int rcar_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, return 0; } -static void rcar_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, +static void rcar_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_bar *epf_bar) { struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); @@ -259,7 +259,8 @@ static void rcar_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, clear_bit(atu_index + 1, ep->ib_window_map); } -static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 interrupts) +static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, + u8 interrupts) { struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); struct rcar_pcie *pcie = &ep->pcie; @@ -272,7 +273,7 @@ static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 interrupts) return 0; } -static int rcar_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) +static int rcar_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) { struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); struct rcar_pcie *pcie = &ep->pcie; @@ -285,7 +286,7 @@ static int rcar_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) return ((flags & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET); } -static int rcar_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, +static int rcar_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, phys_addr_t addr, u64 pci_addr, size_t size) { struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); @@ -322,7 +323,7 @@ static int rcar_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, return 0; } -static void rcar_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, +static void rcar_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, phys_addr_t addr) { struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); @@ -403,7 +404,7 @@ static int rcar_pcie_ep_assert_msi(struct rcar_pcie *pcie, return 0; } -static int rcar_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, +static int rcar_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn, enum pci_epc_irq_type type, u16 interrupt_num) { @@ -451,7 +452,7 @@ static const struct pci_epc_features rcar_pcie_epc_features = { }; static const struct pci_epc_features* -rcar_pcie_ep_get_features(struct pci_epc *epc, u8 func_no) +rcar_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { return &rcar_pcie_epc_features; } diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index 7631dc3961c1..5fb9ce6e536e 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -122,7 +122,7 @@ static void rockchip_pcie_prog_ep_ob_atu(struct rockchip_pcie *rockchip, u8 fn, ROCKCHIP_PCIE_AT_OB_REGION_CPU_ADDR1(r)); } -static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, +static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_header *hdr) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); @@ -159,7 +159,7 @@ static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, return 0; } -static int rockchip_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, +static int rockchip_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_bar *epf_bar) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); @@ -227,7 +227,7 @@ static int rockchip_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, return 0; } -static void rockchip_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, +static void rockchip_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_bar *epf_bar) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); @@ -256,7 +256,7 @@ static void rockchip_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar)); } -static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, +static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, phys_addr_t addr, u64 pci_addr, size_t size) { @@ -284,7 +284,7 @@ static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, return 0; } -static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, +static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, phys_addr_t addr) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); @@ -308,7 +308,7 @@ static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, clear_bit(r, &ep->ob_region_map); } -static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, +static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 multi_msg_cap) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); @@ -329,7 +329,7 @@ static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, return 0; } -static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) +static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; @@ -471,7 +471,7 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn, return 0; } -static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, +static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn, enum pci_epc_irq_type type, u16 interrupt_num) { @@ -510,7 +510,7 @@ static const struct pci_epc_features rockchip_pcie_epc_features = { }; static const struct pci_epc_features* -rockchip_pcie_ep_get_features(struct pci_epc *epc, u8 func_no) +rockchip_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { return &rockchip_pcie_epc_features; } diff --git a/drivers/pci/endpoint/functions/pci-epf-ntb.c b/drivers/pci/endpoint/functions/pci-epf-ntb.c index bce274d02dcf..8b4756159f15 100644 --- a/drivers/pci/endpoint/functions/pci-epf-ntb.c +++ b/drivers/pci/endpoint/functions/pci-epf-ntb.c @@ -87,6 +87,7 @@ struct epf_ntb { struct epf_ntb_epc { u8 func_no; + u8 vfunc_no; bool linkup; bool is_msix; int msix_bar; @@ -143,14 +144,15 @@ static int epf_ntb_link_up(struct epf_ntb *ntb, bool link_up) struct epf_ntb_epc *ntb_epc; struct epf_ntb_ctrl *ctrl; struct pci_epc *epc; + u8 func_no, vfunc_no; bool is_msix; - u8 func_no; int ret; for (type = PRIMARY_INTERFACE; type <= SECONDARY_INTERFACE; type++) { ntb_epc = ntb->epc[type]; epc = ntb_epc->epc; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; is_msix = ntb_epc->is_msix; ctrl = ntb_epc->reg; if (link_up) @@ -158,7 +160,7 @@ static int epf_ntb_link_up(struct epf_ntb *ntb, bool link_up) else ctrl->link_status &= ~LINK_STATUS_UP; irq_type = is_msix ? PCI_EPC_IRQ_MSIX : PCI_EPC_IRQ_MSI; - ret = pci_epc_raise_irq(epc, func_no, irq_type, 1); + ret = pci_epc_raise_irq(epc, func_no, vfunc_no, irq_type, 1); if (ret) { dev_err(&epc->dev, "%s intf: Failed to raise Link Up IRQ\n", @@ -238,10 +240,10 @@ static int epf_ntb_configure_mw(struct epf_ntb *ntb, enum pci_barno peer_barno; struct epf_ntb_ctrl *ctrl; phys_addr_t phys_addr; + u8 func_no, vfunc_no; struct pci_epc *epc; u64 addr, size; int ret = 0; - u8 func_no; ntb_epc = ntb->epc[type]; epc = ntb_epc->epc; @@ -267,8 +269,9 @@ static int epf_ntb_configure_mw(struct epf_ntb *ntb, } func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; - ret = pci_epc_map_addr(epc, func_no, phys_addr, addr, size); + ret = pci_epc_map_addr(epc, func_no, vfunc_no, phys_addr, addr, size); if (ret) dev_err(&epc->dev, "%s intf: Failed to map memory window %d address\n", @@ -296,8 +299,8 @@ static void epf_ntb_teardown_mw(struct epf_ntb *ntb, enum pci_barno peer_barno; struct epf_ntb_ctrl *ctrl; phys_addr_t phys_addr; + u8 func_no, vfunc_no; struct pci_epc *epc; - u8 func_no; ntb_epc = ntb->epc[type]; epc = ntb_epc->epc; @@ -311,8 +314,9 @@ static void epf_ntb_teardown_mw(struct epf_ntb *ntb, if (mw + NTB_MW_OFFSET == BAR_DB_MW1) phys_addr += ctrl->mw1_offset; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; - pci_epc_unmap_addr(epc, func_no, phys_addr); + pci_epc_unmap_addr(epc, func_no, vfunc_no, phys_addr); } /** @@ -385,8 +389,8 @@ static int epf_ntb_configure_msi(struct epf_ntb *ntb, struct epf_ntb_ctrl *peer_ctrl; enum pci_barno peer_barno; phys_addr_t phys_addr; + u8 func_no, vfunc_no; struct pci_epc *epc; - u8 func_no; int ret, i; ntb_epc = ntb->epc[type]; @@ -400,8 +404,9 @@ static int epf_ntb_configure_msi(struct epf_ntb *ntb, phys_addr = peer_epf_bar->phys_addr; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; - ret = pci_epc_map_msi_irq(epc, func_no, phys_addr, db_count, + ret = pci_epc_map_msi_irq(epc, func_no, vfunc_no, phys_addr, db_count, db_entry_size, &db_data, &db_offset); if (ret) { dev_err(&epc->dev, "%s intf: Failed to map MSI IRQ\n", @@ -491,10 +496,10 @@ static int epf_ntb_configure_msix(struct epf_ntb *ntb, u32 db_entry_size, msg_data; enum pci_barno peer_barno; phys_addr_t phys_addr; + u8 func_no, vfunc_no; struct pci_epc *epc; size_t align; u64 msg_addr; - u8 func_no; int ret, i; ntb_epc = ntb->epc[type]; @@ -512,12 +517,13 @@ static int epf_ntb_configure_msix(struct epf_ntb *ntb, align = epc_features->align; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; db_entry_size = peer_ctrl->db_entry_size; for (i = 0; i < db_count; i++) { msg_addr = ALIGN_DOWN(msix_tbl[i].msg_addr, align); msg_data = msix_tbl[i].msg_data; - ret = pci_epc_map_addr(epc, func_no, phys_addr, msg_addr, + ret = pci_epc_map_addr(epc, func_no, vfunc_no, phys_addr, msg_addr, db_entry_size); if (ret) { dev_err(&epc->dev, @@ -586,8 +592,8 @@ epf_ntb_teardown_db(struct epf_ntb *ntb, enum pci_epc_interface_type type) struct pci_epf_bar *peer_epf_bar; enum pci_barno peer_barno; phys_addr_t phys_addr; + u8 func_no, vfunc_no; struct pci_epc *epc; - u8 func_no; ntb_epc = ntb->epc[type]; epc = ntb_epc->epc; @@ -597,8 +603,9 @@ epf_ntb_teardown_db(struct epf_ntb *ntb, enum pci_epc_interface_type type) peer_epf_bar = &peer_ntb_epc->epf_bar[peer_barno]; phys_addr = peer_epf_bar->phys_addr; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; - pci_epc_unmap_addr(epc, func_no, phys_addr); + pci_epc_unmap_addr(epc, func_no, vfunc_no, phys_addr); } /** @@ -728,14 +735,15 @@ static void epf_ntb_peer_spad_bar_clear(struct epf_ntb_epc *ntb_epc) { struct pci_epf_bar *epf_bar; enum pci_barno barno; + u8 func_no, vfunc_no; struct pci_epc *epc; - u8 func_no; epc = ntb_epc->epc; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; barno = ntb_epc->epf_ntb_bar[BAR_PEER_SPAD]; epf_bar = &ntb_epc->epf_bar[barno]; - pci_epc_clear_bar(epc, func_no, epf_bar); + pci_epc_clear_bar(epc, func_no, vfunc_no, epf_bar); } /** @@ -775,9 +783,9 @@ static int epf_ntb_peer_spad_bar_set(struct epf_ntb *ntb, struct pci_epf_bar *peer_epf_bar, *epf_bar; enum pci_barno peer_barno, barno; u32 peer_spad_offset; + u8 func_no, vfunc_no; struct pci_epc *epc; struct device *dev; - u8 func_no; int ret; dev = &ntb->epf->dev; @@ -790,6 +798,7 @@ static int epf_ntb_peer_spad_bar_set(struct epf_ntb *ntb, barno = ntb_epc->epf_ntb_bar[BAR_PEER_SPAD]; epf_bar = &ntb_epc->epf_bar[barno]; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; epc = ntb_epc->epc; peer_spad_offset = peer_ntb_epc->reg->spad_offset; @@ -798,7 +807,7 @@ static int epf_ntb_peer_spad_bar_set(struct epf_ntb *ntb, epf_bar->barno = barno; epf_bar->flags = PCI_BASE_ADDRESS_MEM_TYPE_32; - ret = pci_epc_set_bar(epc, func_no, epf_bar); + ret = pci_epc_set_bar(epc, func_no, vfunc_no, epf_bar); if (ret) { dev_err(dev, "%s intf: peer SPAD BAR set failed\n", pci_epc_interface_string(type)); @@ -842,14 +851,15 @@ static void epf_ntb_config_sspad_bar_clear(struct epf_ntb_epc *ntb_epc) { struct pci_epf_bar *epf_bar; enum pci_barno barno; + u8 func_no, vfunc_no; struct pci_epc *epc; - u8 func_no; epc = ntb_epc->epc; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; barno = ntb_epc->epf_ntb_bar[BAR_CONFIG]; epf_bar = &ntb_epc->epf_bar[barno]; - pci_epc_clear_bar(epc, func_no, epf_bar); + pci_epc_clear_bar(epc, func_no, vfunc_no, epf_bar); } /** @@ -886,10 +896,10 @@ static int epf_ntb_config_sspad_bar_set(struct epf_ntb_epc *ntb_epc) { struct pci_epf_bar *epf_bar; enum pci_barno barno; + u8 func_no, vfunc_no; struct epf_ntb *ntb; struct pci_epc *epc; struct device *dev; - u8 func_no; int ret; ntb = ntb_epc->epf_ntb; @@ -897,10 +907,11 @@ static int epf_ntb_config_sspad_bar_set(struct epf_ntb_epc *ntb_epc) epc = ntb_epc->epc; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; barno = ntb_epc->epf_ntb_bar[BAR_CONFIG]; epf_bar = &ntb_epc->epf_bar[barno]; - ret = pci_epc_set_bar(epc, func_no, epf_bar); + ret = pci_epc_set_bar(epc, func_no, vfunc_no, epf_bar); if (ret) { dev_err(dev, "%s inft: Config/Status/SPAD BAR set failed\n", pci_epc_interface_string(ntb_epc->type)); @@ -1214,17 +1225,18 @@ static void epf_ntb_db_mw_bar_clear(struct epf_ntb_epc *ntb_epc) struct pci_epf_bar *epf_bar; enum epf_ntb_bar bar; enum pci_barno barno; + u8 func_no, vfunc_no; struct pci_epc *epc; - u8 func_no; epc = ntb_epc->epc; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; for (bar = BAR_DB_MW1; bar < BAR_MW4; bar++) { barno = ntb_epc->epf_ntb_bar[bar]; epf_bar = &ntb_epc->epf_bar[barno]; - pci_epc_clear_bar(epc, func_no, epf_bar); + pci_epc_clear_bar(epc, func_no, vfunc_no, epf_bar); } } @@ -1263,10 +1275,10 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb, const struct pci_epc_features *epc_features; bool msix_capable, msi_capable; struct epf_ntb_epc *ntb_epc; + u8 func_no, vfunc_no; struct pci_epc *epc; struct device *dev; u32 db_count; - u8 func_no; int ret; ntb_epc = ntb->epc[type]; @@ -1282,6 +1294,7 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb, } func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; db_count = ntb->db_count; if (db_count > MAX_DB_COUNT) { @@ -1293,7 +1306,7 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb, epc = ntb_epc->epc; if (msi_capable) { - ret = pci_epc_set_msi(epc, func_no, db_count); + ret = pci_epc_set_msi(epc, func_no, vfunc_no, db_count); if (ret) { dev_err(dev, "%s intf: MSI configuration failed\n", pci_epc_interface_string(type)); @@ -1302,7 +1315,7 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb, } if (msix_capable) { - ret = pci_epc_set_msix(epc, func_no, db_count, + ret = pci_epc_set_msix(epc, func_no, vfunc_no, db_count, ntb_epc->msix_bar, ntb_epc->msix_table_offset); if (ret) { @@ -1423,11 +1436,11 @@ static int epf_ntb_db_mw_bar_init(struct epf_ntb *ntb, u32 num_mws, db_count; enum epf_ntb_bar bar; enum pci_barno barno; + u8 func_no, vfunc_no; struct pci_epc *epc; struct device *dev; size_t align; int ret, i; - u8 func_no; u64 size; ntb_epc = ntb->epc[type]; @@ -1437,6 +1450,7 @@ static int epf_ntb_db_mw_bar_init(struct epf_ntb *ntb, epc_features = ntb_epc->epc_features; align = epc_features->align; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; epc = ntb_epc->epc; num_mws = ntb->num_mws; db_count = ntb->db_count; @@ -1464,7 +1478,7 @@ static int epf_ntb_db_mw_bar_init(struct epf_ntb *ntb, barno = ntb_epc->epf_ntb_bar[bar]; epf_bar = &ntb_epc->epf_bar[barno]; - ret = pci_epc_set_bar(epc, func_no, epf_bar); + ret = pci_epc_set_bar(epc, func_no, vfunc_no, epf_bar); if (ret) { dev_err(dev, "%s intf: DoorBell BAR set failed\n", pci_epc_interface_string(type)); @@ -1536,9 +1550,9 @@ static int epf_ntb_epc_create_interface(struct epf_ntb *ntb, const struct pci_epc_features *epc_features; struct pci_epf_bar *epf_bar; struct epf_ntb_epc *ntb_epc; + u8 func_no, vfunc_no; struct pci_epf *epf; struct device *dev; - u8 func_no; dev = &ntb->epf->dev; @@ -1547,6 +1561,7 @@ static int epf_ntb_epc_create_interface(struct epf_ntb *ntb, return -ENOMEM; epf = ntb->epf; + vfunc_no = epf->vfunc_no; if (type == PRIMARY_INTERFACE) { func_no = epf->func_no; epf_bar = epf->bar; @@ -1558,11 +1573,12 @@ static int epf_ntb_epc_create_interface(struct epf_ntb *ntb, ntb_epc->linkup = false; ntb_epc->epc = epc; ntb_epc->func_no = func_no; + ntb_epc->vfunc_no = vfunc_no; ntb_epc->type = type; ntb_epc->epf_bar = epf_bar; ntb_epc->epf_ntb = ntb; - epc_features = pci_epc_get_features(epc, func_no); + epc_features = pci_epc_get_features(epc, func_no, vfunc_no); if (!epc_features) return -EINVAL; ntb_epc->epc_features = epc_features; @@ -1702,10 +1718,10 @@ static int epf_ntb_epc_init_interface(struct epf_ntb *ntb, enum pci_epc_interface_type type) { struct epf_ntb_epc *ntb_epc; + u8 func_no, vfunc_no; struct pci_epc *epc; struct pci_epf *epf; struct device *dev; - u8 func_no; int ret; ntb_epc = ntb->epc[type]; @@ -1713,6 +1729,7 @@ static int epf_ntb_epc_init_interface(struct epf_ntb *ntb, dev = &epf->dev; epc = ntb_epc->epc; func_no = ntb_epc->func_no; + vfunc_no = ntb_epc->vfunc_no; ret = epf_ntb_config_sspad_bar_set(ntb->epc[type]); if (ret) { @@ -1742,11 +1759,13 @@ static int epf_ntb_epc_init_interface(struct epf_ntb *ntb, goto err_db_mw_bar_init; } - ret = pci_epc_write_header(epc, func_no, epf->header); - if (ret) { - dev_err(dev, "%s intf: Configuration header write failed\n", - pci_epc_interface_string(type)); - goto err_write_header; + if (vfunc_no <= 1) { + ret = pci_epc_write_header(epc, func_no, vfunc_no, epf->header); + if (ret) { + dev_err(dev, "%s intf: Configuration header write failed\n", + pci_epc_interface_string(type)); + goto err_write_header; + } } INIT_DELAYED_WORK(&ntb->epc[type]->cmd_handler, epf_ntb_cmd_handler); diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index d2708ca4bece..90d84d3bc868 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -247,8 +247,8 @@ static int pci_epf_test_copy(struct pci_epf_test *epf_test) goto err; } - ret = pci_epc_map_addr(epc, epf->func_no, src_phys_addr, reg->src_addr, - reg->size); + ret = pci_epc_map_addr(epc, epf->func_no, epf->vfunc_no, src_phys_addr, + reg->src_addr, reg->size); if (ret) { dev_err(dev, "Failed to map source address\n"); reg->status = STATUS_SRC_ADDR_INVALID; @@ -263,8 +263,8 @@ static int pci_epf_test_copy(struct pci_epf_test *epf_test) goto err_src_map_addr; } - ret = pci_epc_map_addr(epc, epf->func_no, dst_phys_addr, reg->dst_addr, - reg->size); + ret = pci_epc_map_addr(epc, epf->func_no, epf->vfunc_no, dst_phys_addr, + reg->dst_addr, reg->size); if (ret) { dev_err(dev, "Failed to map destination address\n"); reg->status = STATUS_DST_ADDR_INVALID; @@ -291,13 +291,13 @@ static int pci_epf_test_copy(struct pci_epf_test *epf_test) pci_epf_test_print_rate("COPY", reg->size, &start, &end, use_dma); err_map_addr: - pci_epc_unmap_addr(epc, epf->func_no, dst_phys_addr); + pci_epc_unmap_addr(epc, epf->func_no, epf->vfunc_no, dst_phys_addr); err_dst_addr: pci_epc_mem_free_addr(epc, dst_phys_addr, dst_addr, reg->size); err_src_map_addr: - pci_epc_unmap_addr(epc, epf->func_no, src_phys_addr); + pci_epc_unmap_addr(epc, epf->func_no, epf->vfunc_no, src_phys_addr); err_src_addr: pci_epc_mem_free_addr(epc, src_phys_addr, src_addr, reg->size); @@ -331,8 +331,8 @@ static int pci_epf_test_read(struct pci_epf_test *epf_test) goto err; } - ret = pci_epc_map_addr(epc, epf->func_no, phys_addr, reg->src_addr, - reg->size); + ret = pci_epc_map_addr(epc, epf->func_no, epf->vfunc_no, phys_addr, + reg->src_addr, reg->size); if (ret) { dev_err(dev, "Failed to map address\n"); reg->status = STATUS_SRC_ADDR_INVALID; @@ -386,7 +386,7 @@ err_dma_map: kfree(buf); err_map_addr: - pci_epc_unmap_addr(epc, epf->func_no, phys_addr); + pci_epc_unmap_addr(epc, epf->func_no, epf->vfunc_no, phys_addr); err_addr: pci_epc_mem_free_addr(epc, phys_addr, src_addr, reg->size); @@ -419,8 +419,8 @@ static int pci_epf_test_write(struct pci_epf_test *epf_test) goto err; } - ret = pci_epc_map_addr(epc, epf->func_no, phys_addr, reg->dst_addr, - reg->size); + ret = pci_epc_map_addr(epc, epf->func_no, epf->vfunc_no, phys_addr, + reg->dst_addr, reg->size); if (ret) { dev_err(dev, "Failed to map address\n"); reg->status = STATUS_DST_ADDR_INVALID; @@ -479,7 +479,7 @@ err_dma_map: kfree(buf); err_map_addr: - pci_epc_unmap_addr(epc, epf->func_no, phys_addr); + pci_epc_unmap_addr(epc, epf->func_no, epf->vfunc_no, phys_addr); err_addr: pci_epc_mem_free_addr(epc, phys_addr, dst_addr, reg->size); @@ -501,13 +501,16 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq_type, switch (irq_type) { case IRQ_TYPE_LEGACY: - pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_LEGACY, 0); + pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, + PCI_EPC_IRQ_LEGACY, 0); break; case IRQ_TYPE_MSI: - pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, irq); + pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, + PCI_EPC_IRQ_MSI, irq); break; case IRQ_TYPE_MSIX: - pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSIX, irq); + pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, + PCI_EPC_IRQ_MSIX, irq); break; default: dev_err(dev, "Failed to raise IRQ, unknown type\n"); @@ -542,7 +545,8 @@ static void pci_epf_test_cmd_handler(struct work_struct *work) if (command & COMMAND_RAISE_LEGACY_IRQ) { reg->status = STATUS_IRQ_RAISED; - pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_LEGACY, 0); + pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, + PCI_EPC_IRQ_LEGACY, 0); goto reset_handler; } @@ -580,22 +584,22 @@ static void pci_epf_test_cmd_handler(struct work_struct *work) } if (command & COMMAND_RAISE_MSI_IRQ) { - count = pci_epc_get_msi(epc, epf->func_no); + count = pci_epc_get_msi(epc, epf->func_no, epf->vfunc_no); if (reg->irq_number > count || count <= 0) goto reset_handler; reg->status = STATUS_IRQ_RAISED; - pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, - reg->irq_number); + pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, + PCI_EPC_IRQ_MSI, reg->irq_number); goto reset_handler; } if (command & COMMAND_RAISE_MSIX_IRQ) { - count = pci_epc_get_msix(epc, epf->func_no); + count = pci_epc_get_msix(epc, epf->func_no, epf->vfunc_no); if (reg->irq_number > count || count <= 0) goto reset_handler; reg->status = STATUS_IRQ_RAISED; - pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSIX, - reg->irq_number); + pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, + PCI_EPC_IRQ_MSIX, reg->irq_number); goto reset_handler; } @@ -618,7 +622,8 @@ static void pci_epf_test_unbind(struct pci_epf *epf) epf_bar = &epf->bar[bar]; if (epf_test->reg[bar]) { - pci_epc_clear_bar(epc, epf->func_no, epf_bar); + pci_epc_clear_bar(epc, epf->func_no, epf->vfunc_no, + epf_bar); pci_epf_free_space(epf, epf_test->reg[bar], bar, PRIMARY_INTERFACE); } @@ -650,7 +655,8 @@ static int pci_epf_test_set_bar(struct pci_epf *epf) if (!!(epc_features->reserved_bar & (1 << bar))) continue; - ret = pci_epc_set_bar(epc, epf->func_no, epf_bar); + ret = pci_epc_set_bar(epc, epf->func_no, epf->vfunc_no, + epf_bar); if (ret) { pci_epf_free_space(epf, epf_test->reg[bar], bar, PRIMARY_INTERFACE); @@ -674,16 +680,18 @@ static int pci_epf_test_core_init(struct pci_epf *epf) bool msi_capable = true; int ret; - epc_features = pci_epc_get_features(epc, epf->func_no); + epc_features = pci_epc_get_features(epc, epf->func_no, epf->vfunc_no); if (epc_features) { msix_capable = epc_features->msix_capable; msi_capable = epc_features->msi_capable; } - ret = pci_epc_write_header(epc, epf->func_no, header); - if (ret) { - dev_err(dev, "Configuration header write failed\n"); - return ret; + if (epf->vfunc_no <= 1) { + ret = pci_epc_write_header(epc, epf->func_no, epf->vfunc_no, header); + if (ret) { + dev_err(dev, "Configuration header write failed\n"); + return ret; + } } ret = pci_epf_test_set_bar(epf); @@ -691,7 +699,8 @@ static int pci_epf_test_core_init(struct pci_epf *epf) return ret; if (msi_capable) { - ret = pci_epc_set_msi(epc, epf->func_no, epf->msi_interrupts); + ret = pci_epc_set_msi(epc, epf->func_no, epf->vfunc_no, + epf->msi_interrupts); if (ret) { dev_err(dev, "MSI configuration failed\n"); return ret; @@ -699,7 +708,8 @@ static int pci_epf_test_core_init(struct pci_epf *epf) } if (msix_capable) { - ret = pci_epc_set_msix(epc, epf->func_no, epf->msix_interrupts, + ret = pci_epc_set_msix(epc, epf->func_no, epf->vfunc_no, + epf->msix_interrupts, epf_test->test_reg_bar, epf_test->msix_table_offset); if (ret) { @@ -832,7 +842,7 @@ static int pci_epf_test_bind(struct pci_epf *epf) if (WARN_ON_ONCE(!epc)) return -EINVAL; - epc_features = pci_epc_get_features(epc, epf->func_no); + epc_features = pci_epc_get_features(epc, epf->func_no, epf->vfunc_no); if (!epc_features) { dev_err(&epf->dev, "epc_features not implemented\n"); return -EOPNOTSUPP; diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 01c58ca84dcc..ecbb0fb3b653 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -137,24 +137,29 @@ EXPORT_SYMBOL_GPL(pci_epc_get_next_free_bar); * @epc: the features supported by *this* EPC device will be returned * @func_no: the features supported by the EPC device specific to the * endpoint function with func_no will be returned + * @vfunc_no: the features supported by the EPC device specific to the + * virtual endpoint function with vfunc_no will be returned * * Invoke to get the features provided by the EPC which may be * specific to an endpoint function. Returns pci_epc_features on success * and NULL for any failures. */ const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc, - u8 func_no) + u8 func_no, u8 vfunc_no) { const struct pci_epc_features *epc_features; if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions) return NULL; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return NULL; + if (!epc->ops->get_features) return NULL; mutex_lock(&epc->lock); - epc_features = epc->ops->get_features(epc, func_no); + epc_features = epc->ops->get_features(epc, func_no, vfunc_no); mutex_unlock(&epc->lock); return epc_features; @@ -205,13 +210,14 @@ EXPORT_SYMBOL_GPL(pci_epc_start); /** * pci_epc_raise_irq() - interrupt the host system * @epc: the EPC device which has to interrupt the host - * @func_no: the endpoint function number in the EPC device + * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * @type: specify the type of interrupt; legacy, MSI or MSI-X * @interrupt_num: the MSI or MSI-X interrupt number * * Invoke to raise an legacy, MSI or MSI-X interrupt */ -int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, +int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no, enum pci_epc_irq_type type, u16 interrupt_num) { int ret; @@ -219,11 +225,14 @@ int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions) return -EINVAL; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return -EINVAL; + if (!epc->ops->raise_irq) return 0; mutex_lock(&epc->lock); - ret = epc->ops->raise_irq(epc, func_no, type, interrupt_num); + ret = epc->ops->raise_irq(epc, func_no, vfunc_no, type, interrupt_num); mutex_unlock(&epc->lock); return ret; @@ -235,6 +244,7 @@ EXPORT_SYMBOL_GPL(pci_epc_raise_irq); * MSI data * @epc: the EPC device which has the MSI capability * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * @phys_addr: the physical address of the outbound region * @interrupt_num: the MSI interrupt number * @entry_size: Size of Outbound address region for each interrupt @@ -250,21 +260,25 @@ EXPORT_SYMBOL_GPL(pci_epc_raise_irq); * physical address (in outbound region) of the other interface to ring * doorbell. */ -int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, phys_addr_t phys_addr, - u8 interrupt_num, u32 entry_size, u32 *msi_data, - u32 *msi_addr_offset) +int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + phys_addr_t phys_addr, u8 interrupt_num, u32 entry_size, + u32 *msi_data, u32 *msi_addr_offset) { int ret; if (IS_ERR_OR_NULL(epc)) return -EINVAL; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return -EINVAL; + if (!epc->ops->map_msi_irq) return -EINVAL; mutex_lock(&epc->lock); - ret = epc->ops->map_msi_irq(epc, func_no, phys_addr, interrupt_num, - entry_size, msi_data, msi_addr_offset); + ret = epc->ops->map_msi_irq(epc, func_no, vfunc_no, phys_addr, + interrupt_num, entry_size, msi_data, + msi_addr_offset); mutex_unlock(&epc->lock); return ret; @@ -274,22 +288,26 @@ EXPORT_SYMBOL_GPL(pci_epc_map_msi_irq); /** * pci_epc_get_msi() - get the number of MSI interrupt numbers allocated * @epc: the EPC device to which MSI interrupts was requested - * @func_no: the endpoint function number in the EPC device + * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * * Invoke to get the number of MSI interrupts allocated by the RC */ -int pci_epc_get_msi(struct pci_epc *epc, u8 func_no) +int pci_epc_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { int interrupt; if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions) return 0; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return 0; + if (!epc->ops->get_msi) return 0; mutex_lock(&epc->lock); - interrupt = epc->ops->get_msi(epc, func_no); + interrupt = epc->ops->get_msi(epc, func_no, vfunc_no); mutex_unlock(&epc->lock); if (interrupt < 0) @@ -304,12 +322,13 @@ EXPORT_SYMBOL_GPL(pci_epc_get_msi); /** * pci_epc_set_msi() - set the number of MSI interrupt numbers required * @epc: the EPC device on which MSI has to be configured - * @func_no: the endpoint function number in the EPC device + * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * @interrupts: number of MSI interrupts required by the EPF * * Invoke to set the required number of MSI interrupts. */ -int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts) +int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u8 interrupts) { int ret; u8 encode_int; @@ -318,13 +337,16 @@ int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts) interrupts > 32) return -EINVAL; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return -EINVAL; + if (!epc->ops->set_msi) return 0; encode_int = order_base_2(interrupts); mutex_lock(&epc->lock); - ret = epc->ops->set_msi(epc, func_no, encode_int); + ret = epc->ops->set_msi(epc, func_no, vfunc_no, encode_int); mutex_unlock(&epc->lock); return ret; @@ -334,22 +356,26 @@ EXPORT_SYMBOL_GPL(pci_epc_set_msi); /** * pci_epc_get_msix() - get the number of MSI-X interrupt numbers allocated * @epc: the EPC device to which MSI-X interrupts was requested - * @func_no: the endpoint function number in the EPC device + * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * * Invoke to get the number of MSI-X interrupts allocated by the RC */ -int pci_epc_get_msix(struct pci_epc *epc, u8 func_no) +int pci_epc_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { int interrupt; if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions) return 0; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return 0; + if (!epc->ops->get_msix) return 0; mutex_lock(&epc->lock); - interrupt = epc->ops->get_msix(epc, func_no); + interrupt = epc->ops->get_msix(epc, func_no, vfunc_no); mutex_unlock(&epc->lock); if (interrupt < 0) @@ -362,15 +388,16 @@ EXPORT_SYMBOL_GPL(pci_epc_get_msix); /** * pci_epc_set_msix() - set the number of MSI-X interrupt numbers required * @epc: the EPC device on which MSI-X has to be configured - * @func_no: the endpoint function number in the EPC device + * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * @interrupts: number of MSI-X interrupts required by the EPF * @bir: BAR where the MSI-X table resides * @offset: Offset pointing to the start of MSI-X table * * Invoke to set the required number of MSI-X interrupts. */ -int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts, - enum pci_barno bir, u32 offset) +int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + u16 interrupts, enum pci_barno bir, u32 offset) { int ret; @@ -378,11 +405,15 @@ int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts, interrupts < 1 || interrupts > 2048) return -EINVAL; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return -EINVAL; + if (!epc->ops->set_msix) return 0; mutex_lock(&epc->lock); - ret = epc->ops->set_msix(epc, func_no, interrupts - 1, bir, offset); + ret = epc->ops->set_msix(epc, func_no, vfunc_no, interrupts - 1, bir, + offset); mutex_unlock(&epc->lock); return ret; @@ -392,22 +423,26 @@ EXPORT_SYMBOL_GPL(pci_epc_set_msix); /** * pci_epc_unmap_addr() - unmap CPU address from PCI address * @epc: the EPC device on which address is allocated - * @func_no: the endpoint function number in the EPC device + * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * @phys_addr: physical address of the local system * * Invoke to unmap the CPU address from PCI address. */ -void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, +void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t phys_addr) { if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions) return; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return; + if (!epc->ops->unmap_addr) return; mutex_lock(&epc->lock); - epc->ops->unmap_addr(epc, func_no, phys_addr); + epc->ops->unmap_addr(epc, func_no, vfunc_no, phys_addr); mutex_unlock(&epc->lock); } EXPORT_SYMBOL_GPL(pci_epc_unmap_addr); @@ -415,14 +450,15 @@ EXPORT_SYMBOL_GPL(pci_epc_unmap_addr); /** * pci_epc_map_addr() - map CPU address to PCI address * @epc: the EPC device on which address is allocated - * @func_no: the endpoint function number in the EPC device + * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * @phys_addr: physical address of the local system * @pci_addr: PCI address to which the physical address should be mapped * @size: the size of the allocation * * Invoke to map CPU address with PCI address. */ -int pci_epc_map_addr(struct pci_epc *epc, u8 func_no, +int pci_epc_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t phys_addr, u64 pci_addr, size_t size) { int ret; @@ -430,11 +466,15 @@ int pci_epc_map_addr(struct pci_epc *epc, u8 func_no, if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions) return -EINVAL; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return -EINVAL; + if (!epc->ops->map_addr) return 0; mutex_lock(&epc->lock); - ret = epc->ops->map_addr(epc, func_no, phys_addr, pci_addr, size); + ret = epc->ops->map_addr(epc, func_no, vfunc_no, phys_addr, pci_addr, + size); mutex_unlock(&epc->lock); return ret; @@ -444,12 +484,13 @@ EXPORT_SYMBOL_GPL(pci_epc_map_addr); /** * pci_epc_clear_bar() - reset the BAR * @epc: the EPC device for which the BAR has to be cleared - * @func_no: the endpoint function number in the EPC device + * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * @epf_bar: the struct epf_bar that contains the BAR information * * Invoke to reset the BAR of the endpoint device. */ -void pci_epc_clear_bar(struct pci_epc *epc, u8 func_no, +void pci_epc_clear_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar) { if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions || @@ -457,11 +498,14 @@ void pci_epc_clear_bar(struct pci_epc *epc, u8 func_no, epf_bar->flags & PCI_BASE_ADDRESS_MEM_TYPE_64)) return; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return; + if (!epc->ops->clear_bar) return; mutex_lock(&epc->lock); - epc->ops->clear_bar(epc, func_no, epf_bar); + epc->ops->clear_bar(epc, func_no, vfunc_no, epf_bar); mutex_unlock(&epc->lock); } EXPORT_SYMBOL_GPL(pci_epc_clear_bar); @@ -469,12 +513,13 @@ EXPORT_SYMBOL_GPL(pci_epc_clear_bar); /** * pci_epc_set_bar() - configure BAR in order for host to assign PCI addr space * @epc: the EPC device on which BAR has to be configured - * @func_no: the endpoint function number in the EPC device + * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * @epf_bar: the struct epf_bar that contains the BAR information * * Invoke to configure the BAR of the endpoint device. */ -int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, +int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar) { int ret; @@ -489,11 +534,14 @@ int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, !(flags & PCI_BASE_ADDRESS_MEM_TYPE_64))) return -EINVAL; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return -EINVAL; + if (!epc->ops->set_bar) return 0; mutex_lock(&epc->lock); - ret = epc->ops->set_bar(epc, func_no, epf_bar); + ret = epc->ops->set_bar(epc, func_no, vfunc_no, epf_bar); mutex_unlock(&epc->lock); return ret; @@ -503,7 +551,8 @@ EXPORT_SYMBOL_GPL(pci_epc_set_bar); /** * pci_epc_write_header() - write standard configuration header * @epc: the EPC device to which the configuration header should be written - * @func_no: the endpoint function number in the EPC device + * @func_no: the physical endpoint function number in the EPC device + * @vfunc_no: the virtual endpoint function number in the physical function * @header: standard configuration header fields * * Invoke to write the configuration header to the endpoint controller. Every @@ -511,7 +560,7 @@ EXPORT_SYMBOL_GPL(pci_epc_set_bar); * configuration header would be written. The callback function should write * the header fields to this dedicated location. */ -int pci_epc_write_header(struct pci_epc *epc, u8 func_no, +int pci_epc_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_header *header) { int ret; @@ -519,11 +568,18 @@ int pci_epc_write_header(struct pci_epc *epc, u8 func_no, if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions) return -EINVAL; + if (vfunc_no > 0 && (!epc->max_vfs || vfunc_no > epc->max_vfs[func_no])) + return -EINVAL; + + /* Only Virtual Function #1 has deviceID */ + if (vfunc_no > 1) + return -EINVAL; + if (!epc->ops->write_header) return 0; mutex_lock(&epc->lock); - ret = epc->ops->write_header(epc, func_no, header); + ret = epc->ops->write_header(epc, func_no, vfunc_no, header); mutex_unlock(&epc->lock); return ret; diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 296479659aa2..af691b317f74 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -90,11 +90,14 @@ EXPORT_SYMBOL_GPL(pci_epf_unbind); */ int pci_epf_bind(struct pci_epf *epf) { + struct device *dev = &epf->dev; struct pci_epf *epf_vf; + u8 func_no, vfunc_no; + struct pci_epc *epc; int ret; if (!epf->driver) { - dev_WARN(&epf->dev, "epf device not bound to driver\n"); + dev_WARN(dev, "epf device not bound to driver\n"); return -EINVAL; } @@ -103,7 +106,50 @@ int pci_epf_bind(struct pci_epf *epf) mutex_lock(&epf->lock); list_for_each_entry(epf_vf, &epf->pci_vepf, list) { + vfunc_no = epf_vf->vfunc_no; + + if (vfunc_no < 1) { + dev_err(dev, "Invalid virtual function number\n"); + ret = -EINVAL; + goto ret; + } + + epc = epf->epc; + func_no = epf->func_no; + if (!IS_ERR_OR_NULL(epc)) { + if (!epc->max_vfs) { + dev_err(dev, "No support for virt function\n"); + ret = -EINVAL; + goto ret; + } + + if (vfunc_no > epc->max_vfs[func_no]) { + dev_err(dev, "PF%d: Exceeds max vfunc number\n", + func_no); + ret = -EINVAL; + goto ret; + } + } + + epc = epf->sec_epc; + func_no = epf->sec_epc_func_no; + if (!IS_ERR_OR_NULL(epc)) { + if (!epc->max_vfs) { + dev_err(dev, "No support for virt function\n"); + ret = -EINVAL; + goto ret; + } + + if (vfunc_no > epc->max_vfs[func_no]) { + dev_err(dev, "PF%d: Exceeds max vfunc number\n", + func_no); + ret = -EINVAL; + goto ret; + } + } + epf_vf->func_no = epf->func_no; + epf_vf->sec_epc_func_no = epf->sec_epc_func_no; epf_vf->epc = epf->epc; epf_vf->sec_epc = epf->sec_epc; ret = epf_vf->driver->ops->bind(epf_vf); diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 50a649d33e68..a48778e1a4ee 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -62,31 +62,32 @@ pci_epc_interface_string(enum pci_epc_interface_type type) * @owner: the module owner containing the ops */ struct pci_epc_ops { - int (*write_header)(struct pci_epc *epc, u8 func_no, + int (*write_header)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_header *hdr); - int (*set_bar)(struct pci_epc *epc, u8 func_no, + int (*set_bar)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar); - void (*clear_bar)(struct pci_epc *epc, u8 func_no, + void (*clear_bar)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar); - int (*map_addr)(struct pci_epc *epc, u8 func_no, + int (*map_addr)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t addr, u64 pci_addr, size_t size); - void (*unmap_addr)(struct pci_epc *epc, u8 func_no, + void (*unmap_addr)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t addr); - int (*set_msi)(struct pci_epc *epc, u8 func_no, u8 interrupts); - int (*get_msi)(struct pci_epc *epc, u8 func_no); - int (*set_msix)(struct pci_epc *epc, u8 func_no, u16 interrupts, - enum pci_barno, u32 offset); - int (*get_msix)(struct pci_epc *epc, u8 func_no); - int (*raise_irq)(struct pci_epc *epc, u8 func_no, + int (*set_msi)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + u8 interrupts); + int (*get_msi)(struct pci_epc *epc, u8 func_no, u8 vfunc_no); + int (*set_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + u16 interrupts, enum pci_barno, u32 offset); + int (*get_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no); + int (*raise_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, enum pci_epc_irq_type type, u16 interrupt_num); - int (*map_msi_irq)(struct pci_epc *epc, u8 func_no, + int (*map_msi_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t phys_addr, u8 interrupt_num, u32 entry_size, u32 *msi_data, u32 *msi_addr_offset); int (*start)(struct pci_epc *epc); void (*stop)(struct pci_epc *epc); const struct pci_epc_features* (*get_features)(struct pci_epc *epc, - u8 func_no); + u8 func_no, u8 vfunc_no); struct module *owner; }; @@ -128,6 +129,8 @@ struct pci_epc_mem { * single window. * @num_windows: number of windows supported by device * @max_functions: max number of functions that can be configured in this EPC + * @max_vfs: Array indicating the maximum number of virtual functions that can + * be associated with each physical function * @group: configfs group representing the PCI EPC device * @lock: mutex to protect pci_epc ops * @function_num_map: bitmap to manage physical function number @@ -141,6 +144,7 @@ struct pci_epc { struct pci_epc_mem *mem; unsigned int num_windows; u8 max_functions; + u8 *max_vfs; struct config_group *group; /* mutex to protect against concurrent access of EP controller */ struct mutex lock; @@ -208,31 +212,32 @@ void pci_epc_linkup(struct pci_epc *epc); void pci_epc_init_notify(struct pci_epc *epc); void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf, enum pci_epc_interface_type type); -int pci_epc_write_header(struct pci_epc *epc, u8 func_no, +int pci_epc_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_header *hdr); -int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, +int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar); -void pci_epc_clear_bar(struct pci_epc *epc, u8 func_no, +void pci_epc_clear_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar); -int pci_epc_map_addr(struct pci_epc *epc, u8 func_no, +int pci_epc_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t phys_addr, u64 pci_addr, size_t size); -void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, +void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t phys_addr); -int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts); -int pci_epc_get_msi(struct pci_epc *epc, u8 func_no); -int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts, - enum pci_barno, u32 offset); -int pci_epc_get_msix(struct pci_epc *epc, u8 func_no); -int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, +int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + u8 interrupts); +int pci_epc_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no); +int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + u16 interrupts, enum pci_barno, u32 offset); +int pci_epc_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no); +int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t phys_addr, u8 interrupt_num, u32 entry_size, u32 *msi_data, u32 *msi_addr_offset); -int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, +int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no, enum pci_epc_irq_type type, u16 interrupt_num); int pci_epc_start(struct pci_epc *epc); void pci_epc_stop(struct pci_epc *epc); const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc, - u8 func_no); + u8 func_no, u8 vfunc_no); enum pci_barno pci_epc_get_first_free_bar(const struct pci_epc_features *epc_features); enum pci_barno pci_epc_get_next_free_bar(const struct pci_epc_features -- cgit v1.2.3 From 44779a4b85abd1d1dab9e5b90bd5e6adcfc8143a Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 18 Aug 2021 16:52:16 -0700 Subject: bpf: Use kvmalloc for map keys in syscalls Same as previous patch but for the keys. memdup_bpfptr is renamed to kvmemdup_bpfptr (and converted to kvmalloc). Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210818235216.1159202-2-sdf@google.com --- include/linux/bpfptr.h | 12 ++++++++++-- kernel/bpf/syscall.c | 34 +++++++++++++++++----------------- 2 files changed, 27 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h index 5cdeab497cb3..546e27fc6d46 100644 --- a/include/linux/bpfptr.h +++ b/include/linux/bpfptr.h @@ -62,9 +62,17 @@ static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); } -static inline void *memdup_bpfptr(bpfptr_t src, size_t len) +static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len) { - return memdup_sockptr((sockptr_t) src, len); + void *p = kvmalloc(len, GFP_USER | __GFP_NOWARN); + + if (!p) + return ERR_PTR(-ENOMEM); + if (copy_from_bpfptr(p, src, len)) { + kvfree(p); + return ERR_PTR(-EFAULT); + } + return p; } static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 075f650d297a..4e50c0bfdb7d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1013,7 +1013,7 @@ int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) static void *__bpf_copy_key(void __user *ukey, u64 key_size) { if (key_size) - return memdup_user(ukey, key_size); + return vmemdup_user(ukey, key_size); if (ukey) return ERR_PTR(-EINVAL); @@ -1024,7 +1024,7 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size) static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) { if (key_size) - return memdup_bpfptr(ukey, key_size); + return kvmemdup_bpfptr(ukey, key_size); if (!bpfptr_is_null(ukey)) return ERR_PTR(-EINVAL); @@ -1093,7 +1093,7 @@ static int map_lookup_elem(union bpf_attr *attr) free_value: kvfree(value); free_key: - kfree(key); + kvfree(key); err_put: fdput(f); return err; @@ -1153,7 +1153,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) free_value: kvfree(value); free_key: - kfree(key); + kvfree(key); err_put: fdput(f); return err; @@ -1205,7 +1205,7 @@ static int map_delete_elem(union bpf_attr *attr) bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); out: - kfree(key); + kvfree(key); err_put: fdput(f); return err; @@ -1247,7 +1247,7 @@ static int map_get_next_key(union bpf_attr *attr) } err = -ENOMEM; - next_key = kmalloc(map->key_size, GFP_USER); + next_key = kvmalloc(map->key_size, GFP_USER); if (!next_key) goto free_key; @@ -1270,9 +1270,9 @@ out: err = 0; free_next_key: - kfree(next_key); + kvfree(next_key); free_key: - kfree(key); + kvfree(key); err_put: fdput(f); return err; @@ -1299,7 +1299,7 @@ int generic_map_delete_batch(struct bpf_map *map, if (!max_count) return 0; - key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; @@ -1326,7 +1326,7 @@ int generic_map_delete_batch(struct bpf_map *map, if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; - kfree(key); + kvfree(key); return err; } @@ -1357,13 +1357,13 @@ int generic_map_update_batch(struct bpf_map *map, if (!max_count) return 0; - key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) { - kfree(key); + kvfree(key); return -ENOMEM; } @@ -1385,7 +1385,7 @@ int generic_map_update_batch(struct bpf_map *map, err = -EFAULT; kvfree(value); - kfree(key); + kvfree(key); return err; } @@ -1419,13 +1419,13 @@ int generic_map_lookup_batch(struct bpf_map *map, if (put_user(0, &uattr->batch.count)) return -EFAULT; - buf_prevkey = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + buf_prevkey = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!buf_prevkey) return -ENOMEM; buf = kvmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); if (!buf) { - kfree(buf_prevkey); + kvfree(buf_prevkey); return -ENOMEM; } @@ -1485,7 +1485,7 @@ int generic_map_lookup_batch(struct bpf_map *map, err = -EFAULT; free_buf: - kfree(buf_prevkey); + kvfree(buf_prevkey); kvfree(buf); return err; } @@ -1575,7 +1575,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) free_value: kvfree(value); free_key: - kfree(key); + kvfree(key); err_put: fdput(f); return err; -- cgit v1.2.3 From 1ae258f8b343a0c4316c5545bfaf21010e4f0c73 Mon Sep 17 00:00:00 2001 From: Dmytro Linkin Date: Mon, 31 May 2021 17:08:14 +0300 Subject: net/mlx5: E-switch, Introduce rate limiting groups API Extend eswitch API with rate limiting groups: - Define new struct mlx5_esw_rate_group that is used to hold all internal group data. - Implement functions that allow creation, destruction and cleanup of groups. - Assign all vports to internal unlimited zero group by default. This commit lays the groundwork for group rate limiting by implementing devlink_ops->rate_node_{new|del}() callbacks to support creating and deleting groups through devlink rate node objects. APIs that allows setting rates and adding/removing members are implemented in following patches. Co-developed-by: Vlad Buslov Signed-off-by: Vlad Buslov Signed-off-by: Dmytro Linkin Reviewed-by: Huy Nguyen Reviewed-by: Mark Bloch Reviewed-by: Parav Pandit Reviewed-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 + drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 141 +++++++++++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h | 4 + drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 1 + include/linux/mlx5/mlx5_ifc.h | 3 +- 5 files changed, 145 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index f4cd2573d4ea..ef87d0bf983b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -295,6 +295,8 @@ static const struct devlink_ops mlx5_devlink_ops = { .port_function_hw_addr_set = mlx5_devlink_port_function_hw_addr_set, .rate_leaf_tx_share_set = mlx5_esw_devlink_rate_leaf_tx_share_set, .rate_leaf_tx_max_set = mlx5_esw_devlink_rate_leaf_tx_max_set, + .rate_node_new = mlx5_esw_devlink_rate_node_new, + .rate_node_del = mlx5_esw_devlink_rate_node_del, #endif #ifdef CONFIG_MLX5_SF_MANAGER .port_new = mlx5_devlink_sf_port_new, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index fcdcddf4a710..c9081d39fa8a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -11,6 +11,13 @@ #define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \ min_t(u32, max_t(u32, DIV_ROUND_UP(rate, divider), MLX5_MIN_BW_SHARE), limit) +struct mlx5_esw_rate_group { + u32 tsar_ix; + u32 max_rate; + u32 min_rate; + u32 bw_share; +}; + static int esw_qos_vport_config(struct mlx5_eswitch *esw, struct mlx5_vport *vport, u32 max_rate, u32 bw_share, @@ -159,6 +166,54 @@ int mlx5_esw_qos_set_vport_max_rate(struct mlx5_eswitch *esw, return err; } +static struct mlx5_esw_rate_group * +esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) +{ + u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_esw_rate_group *group; + int err; + + if (!MLX5_CAP_QOS(esw->dev, log_esw_max_sched_depth)) + return ERR_PTR(-EOPNOTSUPP); + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + + MLX5_SET(scheduling_context, tsar_ctx, parent_element_id, + esw->qos.root_tsar_ix); + err = mlx5_create_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + tsar_ctx, + &group->tsar_ix); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "E-Switch create TSAR for group failed"); + goto err_sched_elem; + } + + return group; + +err_sched_elem: + kfree(group); + return ERR_PTR(err); +} + +static int esw_qos_destroy_rate_group(struct mlx5_eswitch *esw, + struct mlx5_esw_rate_group *group, + struct netlink_ext_ack *extack) +{ + int err; + + err = mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + group->tsar_ix); + if (err) + NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR_ID failed"); + + kfree(group); + return err; +} + static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type) { switch (type) { @@ -191,8 +246,9 @@ void mlx5_esw_qos_create(struct mlx5_eswitch *esw) if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR)) return; + mutex_lock(&esw->state_lock); if (esw->qos.enabled) - return; + goto unlock; MLX5_SET(scheduling_context, tsar_ctx, element_type, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); @@ -205,27 +261,54 @@ void mlx5_esw_qos_create(struct mlx5_eswitch *esw) tsar_ctx, &esw->qos.root_tsar_ix); if (err) { - esw_warn(dev, "E-Switch create TSAR failed (%d)\n", err); - return; + esw_warn(dev, "E-Switch create root TSAR failed (%d)\n", err); + goto unlock; } + if (MLX5_CAP_QOS(dev, log_esw_max_sched_depth)) { + esw->qos.group0 = esw_qos_create_rate_group(esw, NULL); + if (IS_ERR(esw->qos.group0)) { + esw_warn(dev, "E-Switch create rate group 0 failed (%ld)\n", + PTR_ERR(esw->qos.group0)); + goto err_group0; + } + } esw->qos.enabled = true; +unlock: + mutex_unlock(&esw->state_lock); + return; + +err_group0: + err = mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + esw->qos.root_tsar_ix); + if (err) + esw_warn(esw->dev, "E-Switch destroy root TSAR failed (%d)\n", err); + mutex_unlock(&esw->state_lock); } void mlx5_esw_qos_destroy(struct mlx5_eswitch *esw) { + struct devlink *devlink = priv_to_devlink(esw->dev); int err; + devlink_rate_nodes_destroy(devlink); + mutex_lock(&esw->state_lock); if (!esw->qos.enabled) - return; + goto unlock; + + if (esw->qos.group0) + esw_qos_destroy_rate_group(esw, esw->qos.group0, NULL); err = mlx5_destroy_scheduling_element_cmd(esw->dev, SCHEDULING_HIERARCHY_E_SWITCH, esw->qos.root_tsar_ix); if (err) - esw_warn(esw->dev, "E-Switch destroy TSAR failed (%d)\n", err); + esw_warn(esw->dev, "E-Switch destroy root TSAR failed (%d)\n", err); esw->qos.enabled = false; +unlock: + mutex_unlock(&esw->state_lock); } int mlx5_esw_qos_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport, @@ -386,3 +469,51 @@ int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void * mutex_unlock(&esw->state_lock); return err; } + +int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_rate_group *group; + struct mlx5_eswitch *esw; + int err = 0; + + esw = mlx5_devlink_eswitch_get(rate_node->devlink); + if (IS_ERR(esw)) + return PTR_ERR(esw); + + mutex_lock(&esw->state_lock); + if (esw->mode != MLX5_ESWITCH_OFFLOADS) { + NL_SET_ERR_MSG_MOD(extack, + "Rate node creation supported only in switchdev mode"); + err = -EOPNOTSUPP; + goto unlock; + } + + group = esw_qos_create_rate_group(esw, extack); + if (IS_ERR(group)) { + err = PTR_ERR(group); + goto unlock; + } + + *priv = group; +unlock: + mutex_unlock(&esw->state_lock); + return err; +} + +int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_rate_group *group = priv; + struct mlx5_eswitch *esw; + int err; + + esw = mlx5_devlink_eswitch_get(rate_node->devlink); + if (IS_ERR(esw)) + return PTR_ERR(esw); + + mutex_lock(&esw->state_lock); + err = esw_qos_destroy_rate_group(esw, group, extack); + mutex_unlock(&esw->state_lock); + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h index 507c7e017834..ab9fd8621cca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h @@ -24,6 +24,10 @@ int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void u64 tx_share, struct netlink_ext_ack *extack); int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *priv, u64 tx_max, struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv, + struct netlink_ext_ack *extack); +int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv, + struct netlink_ext_ack *extack); #endif #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index ebeccee38a57..3580901ae548 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -306,6 +306,7 @@ struct mlx5_eswitch { struct { bool enabled; u32 root_tsar_ix; + struct mlx5_esw_rate_group *group0; } qos; struct mlx5_esw_bridge_offloads *br_offloads; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fce3cbae0b99..f3638d09ba77 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -865,7 +865,8 @@ struct mlx5_ifc_qos_cap_bits { u8 nic_bw_share[0x1]; u8 nic_rate_limit[0x1]; u8 packet_pacing_uid[0x1]; - u8 reserved_at_c[0x14]; + u8 log_esw_max_sched_depth[0x4]; + u8 reserved_at_10[0x10]; u8 reserved_at_20[0xb]; u8 log_max_qos_nic_queue_group[0x5]; -- cgit v1.2.3 From 9ae606bc74dd0e58d4de894e3c5cbb9d45599267 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Jul 2021 12:24:28 +0100 Subject: sched: Introduce task_cpu_possible_mask() to limit fallback rq selection Asymmetric systems may not offer the same level of userspace ISA support across all CPUs, meaning that some applications cannot be executed by some CPUs. As a concrete example, upcoming arm64 big.LITTLE designs do not feature support for 32-bit applications on both clusters. On such a system, we must take care not to migrate a task to an unsupported CPU when forcefully moving tasks in select_fallback_rq() in response to a CPU hot-unplug operation. Introduce a task_cpu_possible_mask() hook which, given a task argument, allows an architecture to return a cpumask of CPUs that are capable of executing that task. The default implementation returns the cpu_possible_mask, since sane machines do not suffer from per-cpu ISA limitations that affect scheduling. The new mask is used when selecting the fallback runqueue as a last resort before forcing a migration to the first active CPU. Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Reviewed-by: Quentin Perret Link: https://lore.kernel.org/r/20210730112443.23245-2-will@kernel.org --- include/linux/mmu_context.h | 14 ++++++++++++++ kernel/sched/core.c | 9 +++------ 2 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index 03dee12d2b61..b9b970f7ab45 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -14,4 +14,18 @@ static inline void leave_mm(int cpu) { } #endif +/* + * CPUs that are capable of running user task @p. Must contain at least one + * active CPU. It is assumed that the kernel can run on all CPUs, so calling + * this for a kernel thread is pointless. + * + * By default, we assume a sane, homogeneous system. + */ +#ifndef task_cpu_possible_mask +# define task_cpu_possible_mask(p) cpu_possible_mask +# define task_cpu_possible(cpu, p) true +#else +# define task_cpu_possible(cpu, p) cpumask_test_cpu((cpu), task_cpu_possible_mask(p)) +#endif + #endif diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7fa6ce74f40e..6f31267c4beb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2173,7 +2173,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) /* Non kernel threads are not allowed during either online or offline. */ if (!(p->flags & PF_KTHREAD)) - return cpu_active(cpu); + return cpu_active(cpu) && task_cpu_possible(cpu, p); /* KTHREAD_IS_PER_CPU is always allowed. */ if (kthread_is_per_cpu(p)) @@ -3124,9 +3124,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) /* Look for allowed, online CPU in same node. */ for_each_cpu(dest_cpu, nodemask) { - if (!cpu_active(dest_cpu)) - continue; - if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) + if (is_cpu_allowed(p, dest_cpu)) return dest_cpu; } } @@ -3156,10 +3154,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) * * More yuck to audit. */ - do_set_cpus_allowed(p, cpu_possible_mask); + do_set_cpus_allowed(p, task_cpu_possible_mask(p)); state = fail; break; - case fail: BUG(); break; -- cgit v1.2.3 From d4b96fb92ae7fe7533e11e662504d96161928575 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Jul 2021 12:24:29 +0100 Subject: cpuset: Don't use the cpu_possible_mask as a last resort for cgroup v1 If the scheduler cannot find an allowed CPU for a task, cpuset_cpus_allowed_fallback() will widen the affinity to cpu_possible_mask if cgroup v1 is in use. In preparation for allowing architectures to provide their own fallback mask, just return early if we're either using cgroup v1 or we're using cgroup v2 with a mask that contains invalid CPUs. This will allow select_fallback_rq() to figure out the mask by itself. Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Reviewed-by: Quentin Perret Link: https://lkml.kernel.org/r/20210730112443.23245-3-will@kernel.org --- include/linux/cpuset.h | 1 + kernel/cgroup/cpuset.c | 8 ++++++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 04c20de66afc..ed6ec677dd6b 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #ifdef CONFIG_CPUSETS diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index adb5190c4429..a8693783f385 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3322,9 +3322,13 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) void cpuset_cpus_allowed_fallback(struct task_struct *tsk) { + const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); + const struct cpumask *cs_mask; + rcu_read_lock(); - do_set_cpus_allowed(tsk, is_in_v2_mode() ? - task_cs(tsk)->cpus_allowed : cpu_possible_mask); + cs_mask = task_cs(tsk)->cpus_allowed; + if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) + do_set_cpus_allowed(tsk, cs_mask); rcu_read_unlock(); /* -- cgit v1.2.3 From 431c69fac05baa7477d61a44f2708e069f2bed6c Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Jul 2021 12:24:30 +0100 Subject: cpuset: Honour task_cpu_possible_mask() in guarantee_online_cpus() Asymmetric systems may not offer the same level of userspace ISA support across all CPUs, meaning that some applications cannot be executed by some CPUs. As a concrete example, upcoming arm64 big.LITTLE designs do not feature support for 32-bit applications on both clusters. Modify guarantee_online_cpus() to take task_cpu_possible_mask() into account when trying to find a suitable set of online CPUs for a given task. This will avoid passing an invalid mask to set_cpus_allowed_ptr() during ->attach() and will subsequently allow the cpuset hierarchy to be taken into account when forcefully overriding the affinity mask for a task which requires migration to a compatible CPU. Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Link: https://lkml.kernel.org/r/20210730112443.23245-4-will@kernel.org --- include/linux/cpuset.h | 2 +- kernel/cgroup/cpuset.c | 43 ++++++++++++++++++++++++++----------------- 2 files changed, 27 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index ed6ec677dd6b..414a8e694413 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -185,7 +185,7 @@ static inline void cpuset_read_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { - cpumask_copy(mask, cpu_possible_mask); + cpumask_copy(mask, task_cpu_possible_mask(p)); } static inline void cpuset_cpus_allowed_fallback(struct task_struct *p) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a8693783f385..391813245cb2 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -372,18 +372,29 @@ static inline bool is_in_v2_mode(void) } /* - * Return in pmask the portion of a cpusets's cpus_allowed that - * are online. If none are online, walk up the cpuset hierarchy - * until we find one that does have some online cpus. + * Return in pmask the portion of a task's cpusets's cpus_allowed that + * are online and are capable of running the task. If none are found, + * walk up the cpuset hierarchy until we find one that does have some + * appropriate cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * * Call with callback_lock or cpuset_mutex held. */ -static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) +static void guarantee_online_cpus(struct task_struct *tsk, + struct cpumask *pmask) { - while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) { + const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); + struct cpuset *cs; + + if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask))) + cpumask_copy(pmask, cpu_online_mask); + + rcu_read_lock(); + cs = task_cs(tsk); + + while (!cpumask_intersects(cs->effective_cpus, pmask)) { cs = parent_cs(cs); if (unlikely(!cs)) { /* @@ -393,11 +404,13 @@ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) * cpuset's effective_cpus is on its way to be * identical to cpu_online_mask. */ - cpumask_copy(pmask, cpu_online_mask); - return; + goto out_unlock; } } - cpumask_and(pmask, cs->effective_cpus, cpu_online_mask); + cpumask_and(pmask, pmask, cs->effective_cpus); + +out_unlock: + rcu_read_unlock(); } /* @@ -2199,15 +2212,13 @@ static void cpuset_attach(struct cgroup_taskset *tset) percpu_down_write(&cpuset_rwsem); - /* prepare for attach */ - if (cs == &top_cpuset) - cpumask_copy(cpus_attach, cpu_possible_mask); - else - guarantee_online_cpus(cs, cpus_attach); - guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cgroup_taskset_for_each(task, css, tset) { + if (cs != &top_cpuset) + guarantee_online_cpus(task, cpus_attach); + else + cpumask_copy(cpus_attach, task_cpu_possible_mask(task)); /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here @@ -3302,9 +3313,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) unsigned long flags; spin_lock_irqsave(&callback_lock, flags); - rcu_read_lock(); - guarantee_online_cpus(task_cs(tsk), pmask); - rcu_read_unlock(); + guarantee_online_cpus(tsk, pmask); spin_unlock_irqrestore(&callback_lock, flags); } -- cgit v1.2.3 From 97c0054dbe2c3c59d1156fd233f2d44e91981c8e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Jul 2021 12:24:31 +0100 Subject: cpuset: Cleanup cpuset_cpus_allowed_fallback() use in select_fallback_rq() select_fallback_rq() only needs to recheck for an allowed CPU if the affinity mask of the task has changed since the last check. Return a 'bool' from cpuset_cpus_allowed_fallback() to indicate whether the affinity mask was updated, and use this to elide the allowed check when the mask has been left alone. No functional change. Suggested-by: Valentin Schneider Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Link: https://lore.kernel.org/r/20210730112443.23245-5-will@kernel.org --- include/linux/cpuset.h | 5 +++-- kernel/cgroup/cpuset.c | 10 ++++++++-- kernel/sched/core.c | 3 +-- 3 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 414a8e694413..d2b9c41c8edf 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -59,7 +59,7 @@ extern void cpuset_wait_for_hotplug(void); extern void cpuset_read_lock(void); extern void cpuset_read_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); -extern void cpuset_cpus_allowed_fallback(struct task_struct *p); +extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); @@ -188,8 +188,9 @@ static inline void cpuset_cpus_allowed(struct task_struct *p, cpumask_copy(mask, task_cpu_possible_mask(p)); } -static inline void cpuset_cpus_allowed_fallback(struct task_struct *p) +static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) { + return false; } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 391813245cb2..6500cbe0ce16 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3327,17 +3327,22 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) * which will not contain a sane cpumask during cases such as cpu hotplugging. * This is the absolute last resort for the scheduler and it is only used if * _every_ other avenue has been traveled. + * + * Returns true if the affinity of @tsk was changed, false otherwise. **/ -void cpuset_cpus_allowed_fallback(struct task_struct *tsk) +bool cpuset_cpus_allowed_fallback(struct task_struct *tsk) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); const struct cpumask *cs_mask; + bool changed = false; rcu_read_lock(); cs_mask = task_cs(tsk)->cpus_allowed; - if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) + if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) { do_set_cpus_allowed(tsk, cs_mask); + changed = true; + } rcu_read_unlock(); /* @@ -3357,6 +3362,7 @@ void cpuset_cpus_allowed_fallback(struct task_struct *tsk) * select_fallback_rq() will fix things ups and set cpu_possible_mask * if required. */ + return changed; } void __init cpuset_init_current_mems_allowed(void) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6f31267c4beb..b9d4bae922a8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3141,8 +3141,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) /* No more Mr. Nice Guy. */ switch (state) { case cpuset: - if (IS_ENABLED(CONFIG_CPUSETS)) { - cpuset_cpus_allowed_fallback(p); + if (cpuset_cpus_allowed_fallback(p)) { state = possible; break; } -- cgit v1.2.3 From b90ca8badbd11488e5f762346b028666808164e7 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Jul 2021 12:24:33 +0100 Subject: sched: Introduce task_struct::user_cpus_ptr to track requested affinity In preparation for saving and restoring the user-requested CPU affinity mask of a task, add a new cpumask_t pointer to 'struct task_struct'. If the pointer is non-NULL, then the mask is copied across fork() and freed on task exit. Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Link: https://lore.kernel.org/r/20210730112443.23245-7-will@kernel.org --- include/linux/sched.h | 13 +++++++++++++ init/init_task.c | 1 + kernel/fork.c | 2 ++ kernel/sched/core.c | 20 ++++++++++++++++++++ 4 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 50db9496c99d..2c5d638daaad 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -748,6 +748,7 @@ struct task_struct { unsigned int policy; int nr_cpus_allowed; const cpumask_t *cpus_ptr; + cpumask_t *user_cpus_ptr; cpumask_t cpus_mask; void *migration_pending; #ifdef CONFIG_SMP @@ -1706,6 +1707,8 @@ extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_ #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); +extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); +extern void release_user_cpus_ptr(struct task_struct *p); #else static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { @@ -1716,6 +1719,16 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpuma return -EINVAL; return 0; } +static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) +{ + if (src->user_cpus_ptr) + return -EINVAL; + return 0; +} +static inline void release_user_cpus_ptr(struct task_struct *p) +{ + WARN_ON(p->user_cpus_ptr); +} #endif extern int yield_to(struct task_struct *p, bool preempt); diff --git a/init/init_task.c b/init/init_task.c index 562f2ef8d157..2d024066e27b 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -80,6 +80,7 @@ struct task_struct init_task .normal_prio = MAX_PRIO - 20, .policy = SCHED_NORMAL, .cpus_ptr = &init_task.cpus_mask, + .user_cpus_ptr = NULL, .cpus_mask = CPU_MASK_ALL, .nr_cpus_allowed= NR_CPUS, .mm = NULL, diff --git a/kernel/fork.c b/kernel/fork.c index 1a9af73b47c1..5d7addf0c41a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -446,6 +446,7 @@ void put_task_stack(struct task_struct *tsk) void free_task(struct task_struct *tsk) { + release_user_cpus_ptr(tsk); scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK @@ -919,6 +920,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; + dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8cec0d24c88c..360a3ec6d03b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2480,6 +2480,26 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) __do_set_cpus_allowed(p, new_mask, 0); } +int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, + int node) +{ + if (!src->user_cpus_ptr) + return 0; + + dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node); + if (!dst->user_cpus_ptr) + return -ENOMEM; + + cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr); + return 0; +} + +void release_user_cpus_ptr(struct task_struct *p) +{ + kfree(p->user_cpus_ptr); + p->user_cpus_ptr = NULL; +} + /* * This function is wildly self concurrent; here be dragons. * -- cgit v1.2.3 From 07ec77a1d4e82526e1588979fff2f024f8e96df2 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Jul 2021 12:24:35 +0100 Subject: sched: Allow task CPU affinity to be restricted on asymmetric systems Asymmetric systems may not offer the same level of userspace ISA support across all CPUs, meaning that some applications cannot be executed by some CPUs. As a concrete example, upcoming arm64 big.LITTLE designs do not feature support for 32-bit applications on both clusters. Although userspace can carefully manage the affinity masks for such tasks, one place where it is particularly problematic is execve() because the CPU on which the execve() is occurring may be incompatible with the new application image. In such a situation, it is desirable to restrict the affinity mask of the task and ensure that the new image is entered on a compatible CPU. From userspace's point of view, this looks the same as if the incompatible CPUs have been hotplugged off in the task's affinity mask. Similarly, if a subsequent execve() reverts to a compatible image, then the old affinity is restored if it is still valid. In preparation for restricting the affinity mask for compat tasks on arm64 systems without uniform support for 32-bit applications, introduce {force,relax}_compatible_cpus_allowed_ptr(), which respectively restrict and restore the affinity mask for a task based on the compatible CPUs. Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Reviewed-by: Quentin Perret Link: https://lore.kernel.org/r/20210730112443.23245-9-will@kernel.org --- include/linux/sched.h | 2 + kernel/sched/core.c | 198 +++++++++++++++++++++++++++++++++++++++++++++----- kernel/sched/sched.h | 1 + 3 files changed, 183 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c5d638daaad..ce2d5cfc331e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1709,6 +1709,8 @@ extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); extern void release_user_cpus_ptr(struct task_struct *p); +extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); +extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); #else static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 672d0fcbf2ef..6ee197049c9c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2494,10 +2494,18 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, return 0; } +static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p) +{ + struct cpumask *user_mask = NULL; + + swap(p->user_cpus_ptr, user_mask); + + return user_mask; +} + void release_user_cpus_ptr(struct task_struct *p) { - kfree(p->user_cpus_ptr); - p->user_cpus_ptr = NULL; + kfree(clear_user_cpus_ptr(p)); } /* @@ -2717,27 +2725,23 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag } /* - * Change a given task's CPU affinity. Migrate the thread to a - * proper CPU and schedule it away if the CPU it's executing on - * is removed from the allowed bitmask. - * - * NOTE: the caller must have a valid reference to the task, the - * task must not exit() & deallocate itself prematurely. The - * call is not atomic; no spinlocks may be held. + * Called with both p->pi_lock and rq->lock held; drops both before returning. */ -static int __set_cpus_allowed_ptr(struct task_struct *p, - const struct cpumask *new_mask, - u32 flags) +static int __set_cpus_allowed_ptr_locked(struct task_struct *p, + const struct cpumask *new_mask, + u32 flags, + struct rq *rq, + struct rq_flags *rf) + __releases(rq->lock) + __releases(p->pi_lock) { const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p); const struct cpumask *cpu_valid_mask = cpu_active_mask; bool kthread = p->flags & PF_KTHREAD; + struct cpumask *user_mask = NULL; unsigned int dest_cpu; - struct rq_flags rf; - struct rq *rq; int ret = 0; - rq = task_rq_lock(p, &rf); update_rq_clock(rq); if (kthread || is_migration_disabled(p)) { @@ -2793,20 +2797,178 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, __do_set_cpus_allowed(p, new_mask, flags); - return affine_move_task(rq, p, &rf, dest_cpu, flags); + if (flags & SCA_USER) + user_mask = clear_user_cpus_ptr(p); + + ret = affine_move_task(rq, p, rf, dest_cpu, flags); + + kfree(user_mask); + + return ret; out: - task_rq_unlock(rq, p, &rf); + task_rq_unlock(rq, p, rf); return ret; } +/* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on + * is removed from the allowed bitmask. + * + * NOTE: the caller must have a valid reference to the task, the + * task must not exit() & deallocate itself prematurely. The + * call is not atomic; no spinlocks may be held. + */ +static int __set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask, u32 flags) +{ + struct rq_flags rf; + struct rq *rq; + + rq = task_rq_lock(p, &rf); + return __set_cpus_allowed_ptr_locked(p, new_mask, flags, rq, &rf); +} + int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { return __set_cpus_allowed_ptr(p, new_mask, 0); } EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); +/* + * Change a given task's CPU affinity to the intersection of its current + * affinity mask and @subset_mask, writing the resulting mask to @new_mask + * and pointing @p->user_cpus_ptr to a copy of the old mask. + * If the resulting mask is empty, leave the affinity unchanged and return + * -EINVAL. + */ +static int restrict_cpus_allowed_ptr(struct task_struct *p, + struct cpumask *new_mask, + const struct cpumask *subset_mask) +{ + struct cpumask *user_mask = NULL; + struct rq_flags rf; + struct rq *rq; + int err; + + if (!p->user_cpus_ptr) { + user_mask = kmalloc(cpumask_size(), GFP_KERNEL); + if (!user_mask) + return -ENOMEM; + } + + rq = task_rq_lock(p, &rf); + + /* + * Forcefully restricting the affinity of a deadline task is + * likely to cause problems, so fail and noisily override the + * mask entirely. + */ + if (task_has_dl_policy(p) && dl_bandwidth_enabled()) { + err = -EPERM; + goto err_unlock; + } + + if (!cpumask_and(new_mask, &p->cpus_mask, subset_mask)) { + err = -EINVAL; + goto err_unlock; + } + + /* + * We're about to butcher the task affinity, so keep track of what + * the user asked for in case we're able to restore it later on. + */ + if (user_mask) { + cpumask_copy(user_mask, p->cpus_ptr); + p->user_cpus_ptr = user_mask; + } + + return __set_cpus_allowed_ptr_locked(p, new_mask, 0, rq, &rf); + +err_unlock: + task_rq_unlock(rq, p, &rf); + kfree(user_mask); + return err; +} + +/* + * Restrict the CPU affinity of task @p so that it is a subset of + * task_cpu_possible_mask() and point @p->user_cpu_ptr to a copy of the + * old affinity mask. If the resulting mask is empty, we warn and walk + * up the cpuset hierarchy until we find a suitable mask. + */ +void force_compatible_cpus_allowed_ptr(struct task_struct *p) +{ + cpumask_var_t new_mask; + const struct cpumask *override_mask = task_cpu_possible_mask(p); + + alloc_cpumask_var(&new_mask, GFP_KERNEL); + + /* + * __migrate_task() can fail silently in the face of concurrent + * offlining of the chosen destination CPU, so take the hotplug + * lock to ensure that the migration succeeds. + */ + cpus_read_lock(); + if (!cpumask_available(new_mask)) + goto out_set_mask; + + if (!restrict_cpus_allowed_ptr(p, new_mask, override_mask)) + goto out_free_mask; + + /* + * We failed to find a valid subset of the affinity mask for the + * task, so override it based on its cpuset hierarchy. + */ + cpuset_cpus_allowed(p, new_mask); + override_mask = new_mask; + +out_set_mask: + if (printk_ratelimit()) { + printk_deferred("Overriding affinity for process %d (%s) to CPUs %*pbl\n", + task_pid_nr(p), p->comm, + cpumask_pr_args(override_mask)); + } + + WARN_ON(set_cpus_allowed_ptr(p, override_mask)); +out_free_mask: + cpus_read_unlock(); + free_cpumask_var(new_mask); +} + +static int +__sched_setaffinity(struct task_struct *p, const struct cpumask *mask); + +/* + * Restore the affinity of a task @p which was previously restricted by a + * call to force_compatible_cpus_allowed_ptr(). This will clear (and free) + * @p->user_cpus_ptr. + * + * It is the caller's responsibility to serialise this with any calls to + * force_compatible_cpus_allowed_ptr(@p). + */ +void relax_compatible_cpus_allowed_ptr(struct task_struct *p) +{ + struct cpumask *user_mask = p->user_cpus_ptr; + unsigned long flags; + + /* + * Try to restore the old affinity mask. If this fails, then + * we free the mask explicitly to avoid it being inherited across + * a subsequent fork(). + */ + if (!user_mask || !__sched_setaffinity(p, user_mask)) + return; + + raw_spin_lock_irqsave(&p->pi_lock, flags); + user_mask = clear_user_cpus_ptr(p); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + kfree(user_mask); +} + void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { #ifdef CONFIG_SCHED_DEBUG @@ -7629,7 +7791,7 @@ __sched_setaffinity(struct task_struct *p, const struct cpumask *mask) } #endif again: - retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK); + retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK | SCA_USER); if (retval) goto out_free_new_mask; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 5fa02902c143..e7e2bba5b520 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2244,6 +2244,7 @@ extern struct task_struct *pick_next_task_idle(struct rq *rq); #define SCA_CHECK 0x01 #define SCA_MIGRATE_DISABLE 0x02 #define SCA_MIGRATE_ENABLE 0x04 +#define SCA_USER 0x08 #ifdef CONFIG_SMP -- cgit v1.2.3 From 234b8ab6476c5edd5262e2ff563de9498d60044a Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 30 Jul 2021 12:24:36 +0100 Subject: sched: Introduce dl_task_check_affinity() to check proposed affinity In preparation for restricting the affinity of a task during execve() on arm64, introduce a new dl_task_check_affinity() helper function to give an indication as to whether the restricted mask is admissible for a deadline task. Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Daniel Bristot de Oliveira Link: https://lore.kernel.org/r/20210730112443.23245-10-will@kernel.org --- include/linux/sched.h | 6 ++++++ kernel/sched/core.c | 46 +++++++++++++++++++++++++++++----------------- 2 files changed, 35 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ce2d5cfc331e..3bb9fecfdaa1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1709,6 +1709,7 @@ extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); extern void release_user_cpus_ptr(struct task_struct *p); +extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask); extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); #else @@ -1731,6 +1732,11 @@ static inline void release_user_cpus_ptr(struct task_struct *p) { WARN_ON(p->user_cpus_ptr); } + +static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) +{ + return 0; +} #endif extern int yield_to(struct task_struct *p, bool preempt); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6ee197049c9c..a22cc3c156ce 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7756,6 +7756,32 @@ out_unlock: return retval; } +#ifdef CONFIG_SMP +int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) +{ + int ret = 0; + + /* + * If the task isn't a deadline task or admission control is + * disabled then we don't care about affinity changes. + */ + if (!task_has_dl_policy(p) || !dl_bandwidth_enabled()) + return 0; + + /* + * Since bandwidth control happens on root_domain basis, + * if admission test is enabled, we only admit -deadline + * tasks allowed to run on all the CPUs in the task's + * root_domain. + */ + rcu_read_lock(); + if (!cpumask_subset(task_rq(p)->rd->span, mask)) + ret = -EBUSY; + rcu_read_unlock(); + return ret; +} +#endif + static int __sched_setaffinity(struct task_struct *p, const struct cpumask *mask) { @@ -7773,23 +7799,9 @@ __sched_setaffinity(struct task_struct *p, const struct cpumask *mask) cpuset_cpus_allowed(p, cpus_allowed); cpumask_and(new_mask, mask, cpus_allowed); - /* - * Since bandwidth control happens on root_domain basis, - * if admission test is enabled, we only admit -deadline - * tasks allowed to run on all the CPUs in the task's - * root_domain. - */ -#ifdef CONFIG_SMP - if (task_has_dl_policy(p) && dl_bandwidth_enabled()) { - rcu_read_lock(); - if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) { - retval = -EBUSY; - rcu_read_unlock(); - goto out_free_new_mask; - } - rcu_read_unlock(); - } -#endif + retval = dl_task_check_affinity(p, new_mask); + if (retval) + goto out_free_new_mask; again: retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK | SCA_USER); if (retval) -- cgit v1.2.3 From 249dbe74d3c4b568a623fb55c56cddf19fdf0b89 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 11 Aug 2021 08:30:22 +0100 Subject: ARM: 9108/1: oabi-compat: rework epoll_wait/epoll_pwait emulation The epoll_wait() system call wrapper is one of the remaining users of the set_fs() infrasturcture for Arm. Changing it to not require set_fs() is rather complex unfortunately. The approach I'm taking here is to allow architectures to override the code that copies the output to user space, and let the oabi-compat implementation check whether it is getting called from an EABI or OABI system call based on the thread_info->syscall value. The in_oabi_syscall() check here mirrors the in_compat_syscall() and in_x32_syscall() helpers for 32-bit compat implementations on other architectures. Overall, the amount of code goes down, at least with the newly added sys_oabi_epoll_pwait() helper getting removed again. The downside is added complexity in the source code for the native implementation. There should be no difference in runtime performance except for Arm kernels with CONFIG_OABI_COMPAT enabled that now have to go through an external function call to check which of the two variants to use. Acked-by: Christoph Hellwig Signed-off-by: Arnd Bergmann Signed-off-by: Russell King (Oracle) --- arch/arm/include/asm/syscall.h | 11 ++++++ arch/arm/kernel/sys_oabi-compat.c | 83 ++++++++------------------------------- arch/arm/tools/syscall.tbl | 4 +- fs/eventpoll.c | 5 +-- include/linux/eventpoll.h | 18 +++++++++ 5 files changed, 49 insertions(+), 72 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index f055e846a5cc..24c19d63ff0a 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -28,6 +28,17 @@ static inline int syscall_get_nr(struct task_struct *task, return task_thread_info(task)->abi_syscall & __NR_SYSCALL_MASK; } +static inline bool __in_oabi_syscall(struct task_struct *task) +{ + return IS_ENABLED(CONFIG_OABI_COMPAT) && + (task_thread_info(task)->abi_syscall & __NR_OABI_SYSCALL_BASE); +} + +static inline bool in_oabi_syscall(void) +{ + return __in_oabi_syscall(current); +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 443203fafb6b..1f6a433200f1 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -83,6 +83,8 @@ #include #include +#include + struct oldabi_stat64 { unsigned long long st_dev; unsigned int __pad1; @@ -264,87 +266,34 @@ asmlinkage long sys_oabi_epoll_ctl(int epfd, int op, int fd, return do_epoll_ctl(epfd, op, fd, &kernel, false); } - -static long do_oabi_epoll_wait(int epfd, struct oabi_epoll_event __user *events, - int maxevents, int timeout) -{ - struct epoll_event *kbuf; - struct oabi_epoll_event e; - mm_segment_t fs; - long ret, err, i; - - if (maxevents <= 0 || - maxevents > (INT_MAX/sizeof(*kbuf)) || - maxevents > (INT_MAX/sizeof(*events))) - return -EINVAL; - if (!access_ok(events, sizeof(*events) * maxevents)) - return -EFAULT; - kbuf = kmalloc_array(maxevents, sizeof(*kbuf), GFP_KERNEL); - if (!kbuf) - return -ENOMEM; - fs = get_fs(); - set_fs(KERNEL_DS); - ret = sys_epoll_wait(epfd, kbuf, maxevents, timeout); - set_fs(fs); - err = 0; - for (i = 0; i < ret; i++) { - e.events = kbuf[i].events; - e.data = kbuf[i].data; - err = __copy_to_user(events, &e, sizeof(e)); - if (err) - break; - events++; - } - kfree(kbuf); - return err ? -EFAULT : ret; -} #else asmlinkage long sys_oabi_epoll_ctl(int epfd, int op, int fd, struct oabi_epoll_event __user *event) { return -EINVAL; } - -asmlinkage long sys_oabi_epoll_wait(int epfd, - struct oabi_epoll_event __user *events, - int maxevents, int timeout) -{ - return -EINVAL; -} #endif -SYSCALL_DEFINE4(oabi_epoll_wait, int, epfd, - struct oabi_epoll_event __user *, events, - int, maxevents, int, timeout) +struct epoll_event __user * +epoll_put_uevent(__poll_t revents, __u64 data, + struct epoll_event __user *uevent) { - return do_oabi_epoll_wait(epfd, events, maxevents, timeout); -} + if (in_oabi_syscall()) { + struct oabi_epoll_event __user *oevent = (void __user *)uevent; -/* - * Implement the event wait interface for the eventpoll file. It is the kernel - * part of the user space epoll_pwait(2). - */ -SYSCALL_DEFINE6(oabi_epoll_pwait, int, epfd, - struct oabi_epoll_event __user *, events, int, maxevents, - int, timeout, const sigset_t __user *, sigmask, - size_t, sigsetsize) -{ - int error; + if (__put_user(revents, &oevent->events) || + __put_user(data, &oevent->data)) + return NULL; - /* - * If the caller wants a certain signal mask to be set during the wait, - * we apply it here. - */ - error = set_user_sigmask(sigmask, sigsetsize); - if (error) - return error; + return (void __user *)(oevent+1); + } - error = do_oabi_epoll_wait(epfd, events, maxevents, timeout); - restore_saved_sigmask_unless(error == -EINTR); + if (__put_user(revents, &uevent->events) || + __put_user(data, &uevent->data)) + return NULL; - return error; + return uevent+1; } -#endif struct oabi_sembuf { unsigned short sem_num; diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 11d0b960b2c2..344424a9611f 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -266,7 +266,7 @@ 249 common lookup_dcookie sys_lookup_dcookie 250 common epoll_create sys_epoll_create 251 common epoll_ctl sys_epoll_ctl sys_oabi_epoll_ctl -252 common epoll_wait sys_epoll_wait sys_oabi_epoll_wait +252 common epoll_wait sys_epoll_wait 253 common remap_file_pages sys_remap_file_pages # 254 for set_thread_area # 255 for get_thread_area @@ -360,7 +360,7 @@ 343 common vmsplice sys_vmsplice 344 common move_pages sys_move_pages 345 common getcpu sys_getcpu -346 common epoll_pwait sys_epoll_pwait sys_oabi_epoll_pwait +346 common epoll_pwait sys_epoll_pwait 347 common kexec_load sys_kexec_load 348 common utimensat sys_utimensat_time32 349 common signalfd sys_signalfd diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 1e596e1d0bba..c90c4352325e 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1684,8 +1684,8 @@ static int ep_send_events(struct eventpoll *ep, if (!revents) continue; - if (__put_user(revents, &events->events) || - __put_user(epi->event.data, &events->data)) { + events = epoll_put_uevent(revents, epi->event.data, events); + if (!events) { list_add(&epi->rdllink, &txlist); ep_pm_stay_awake(epi); if (!res) @@ -1693,7 +1693,6 @@ static int ep_send_events(struct eventpoll *ep, break; } res++; - events++; if (epi->event.events & EPOLLONESHOT) epi->event.events &= EP_PRIVATE_BITS; else if (!(epi->event.events & EPOLLET)) { diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 593322c946e6..3337745d81bd 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -68,4 +68,22 @@ static inline void eventpoll_release(struct file *file) {} #endif +#if defined(CONFIG_ARM) && defined(CONFIG_OABI_COMPAT) +/* ARM OABI has an incompatible struct layout and needs a special handler */ +extern struct epoll_event __user * +epoll_put_uevent(__poll_t revents, __u64 data, + struct epoll_event __user *uevent); +#else +static inline struct epoll_event __user * +epoll_put_uevent(__poll_t revents, __u64 data, + struct epoll_event __user *uevent) +{ + if (__put_user(revents, &uevent->events) || + __put_user(data, &uevent->data)) + return NULL; + + return uevent+1; +} +#endif + #endif /* #ifndef _LINUX_EVENTPOLL_H */ -- cgit v1.2.3 From bdec0145286f7e6be9b3134aa35f0f335fa27c38 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 11 Aug 2021 08:30:23 +0100 Subject: ARM: 9114/1: oabi-compat: rework sys_semtimedop emulation sys_oabi_semtimedop() is one of the last users of set_fs() on Arm. To remove this one, expose the internal code of the actual implementation that operates on a kernel pointer and call it directly after copying. There should be no measurable impact on the normal execution of this function, and it makes the overly long function a little shorter, which may help readability. While reworking the oabi version, make it behave a little more like the native one, using kvmalloc_array() and restructure the code flow in a similar way. The naming of __do_semtimedop() is not very good, I hope someone can come up with a better name. One regression was spotted by kernel test robot and fixed before the first mailing list submission. Acked-by: Christoph Hellwig Signed-off-by: Arnd Bergmann Signed-off-by: Russell King (Oracle) --- arch/arm/kernel/sys_oabi-compat.c | 60 ++++++++++++++++++++-------- include/linux/syscalls.h | 3 ++ ipc/sem.c | 84 ++++++++++++++++++++++++--------------- 3 files changed, 99 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 1f6a433200f1..5ea365c35ca5 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -80,6 +80,7 @@ #include #include #include +#include #include #include @@ -302,46 +303,52 @@ struct oabi_sembuf { unsigned short __pad; }; +#define sc_semopm sem_ctls[2] + +#ifdef CONFIG_SYSVIPC asmlinkage long sys_oabi_semtimedop(int semid, struct oabi_sembuf __user *tsops, unsigned nsops, const struct old_timespec32 __user *timeout) { + struct ipc_namespace *ns; struct sembuf *sops; - struct old_timespec32 local_timeout; long err; int i; + ns = current->nsproxy->ipc_ns; + if (nsops > ns->sc_semopm) + return -E2BIG; if (nsops < 1 || nsops > SEMOPM) return -EINVAL; - if (!access_ok(tsops, sizeof(*tsops) * nsops)) - return -EFAULT; - sops = kmalloc_array(nsops, sizeof(*sops), GFP_KERNEL); + sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL); if (!sops) return -ENOMEM; err = 0; for (i = 0; i < nsops; i++) { struct oabi_sembuf osb; - err |= __copy_from_user(&osb, tsops, sizeof(osb)); + err |= copy_from_user(&osb, tsops, sizeof(osb)); sops[i].sem_num = osb.sem_num; sops[i].sem_op = osb.sem_op; sops[i].sem_flg = osb.sem_flg; tsops++; } - if (timeout) { - /* copy this as well before changing domain protection */ - err |= copy_from_user(&local_timeout, timeout, sizeof(*timeout)); - timeout = &local_timeout; - } if (err) { err = -EFAULT; - } else { - mm_segment_t fs = get_fs(); - set_fs(KERNEL_DS); - err = sys_semtimedop_time32(semid, sops, nsops, timeout); - set_fs(fs); + goto out; + } + + if (timeout) { + struct timespec64 ts; + err = get_old_timespec32(&ts, timeout); + if (err) + goto out; + err = __do_semtimedop(semid, sops, nsops, &ts, ns); + goto out; } - kfree(sops); + err = __do_semtimedop(semid, sops, nsops, NULL, ns); +out: + kvfree(sops); return err; } @@ -368,6 +375,27 @@ asmlinkage int sys_oabi_ipc(uint call, int first, int second, int third, return sys_ipc(call, first, second, third, ptr, fifth); } } +#else +asmlinkage long sys_oabi_semtimedop(int semid, + struct oabi_sembuf __user *tsops, + unsigned nsops, + const struct old_timespec32 __user *timeout) +{ + return -ENOSYS; +} + +asmlinkage long sys_oabi_semop(int semid, struct oabi_sembuf __user *tsops, + unsigned nsops) +{ + return -ENOSYS; +} + +asmlinkage int sys_oabi_ipc(uint call, int first, int second, int third, + void __user *ptr, long fifth) +{ + return -ENOSYS; +} +#endif asmlinkage long sys_oabi_bind(int fd, struct sockaddr __user *addr, int addrlen) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 69c9a7010081..6c6fc3fd5b72 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1373,6 +1373,9 @@ long ksys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, unsigned int nsops, const struct old_timespec32 __user *timeout); +long __do_semtimedop(int semid, struct sembuf *tsems, unsigned int nsops, + const struct timespec64 *timeout, + struct ipc_namespace *ns); int __sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen); diff --git a/ipc/sem.c b/ipc/sem.c index 971e75d28364..ae8d9104b0a0 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1984,46 +1984,34 @@ out: return un; } -static long do_semtimedop(int semid, struct sembuf __user *tsops, - unsigned nsops, const struct timespec64 *timeout) +long __do_semtimedop(int semid, struct sembuf *sops, + unsigned nsops, const struct timespec64 *timeout, + struct ipc_namespace *ns) { int error = -EINVAL; struct sem_array *sma; - struct sembuf fast_sops[SEMOPM_FAST]; - struct sembuf *sops = fast_sops, *sop; + struct sembuf *sop; struct sem_undo *un; int max, locknum; bool undos = false, alter = false, dupsop = false; struct sem_queue queue; unsigned long dup = 0, jiffies_left = 0; - struct ipc_namespace *ns; - - ns = current->nsproxy->ipc_ns; if (nsops < 1 || semid < 0) return -EINVAL; if (nsops > ns->sc_semopm) return -E2BIG; - if (nsops > SEMOPM_FAST) { - sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL); - if (sops == NULL) - return -ENOMEM; - } - - if (copy_from_user(sops, tsops, nsops * sizeof(*tsops))) { - error = -EFAULT; - goto out_free; - } if (timeout) { if (timeout->tv_sec < 0 || timeout->tv_nsec < 0 || timeout->tv_nsec >= 1000000000L) { error = -EINVAL; - goto out_free; + goto out; } jiffies_left = timespec64_to_jiffies(timeout); } + max = 0; for (sop = sops; sop < sops + nsops; sop++) { unsigned long mask = 1ULL << ((sop->sem_num) % BITS_PER_LONG); @@ -2052,7 +2040,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, un = find_alloc_undo(ns, semid); if (IS_ERR(un)) { error = PTR_ERR(un); - goto out_free; + goto out; } } else { un = NULL; @@ -2063,25 +2051,25 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, if (IS_ERR(sma)) { rcu_read_unlock(); error = PTR_ERR(sma); - goto out_free; + goto out; } error = -EFBIG; if (max >= sma->sem_nsems) { rcu_read_unlock(); - goto out_free; + goto out; } error = -EACCES; if (ipcperms(ns, &sma->sem_perm, alter ? S_IWUGO : S_IRUGO)) { rcu_read_unlock(); - goto out_free; + goto out; } error = security_sem_semop(&sma->sem_perm, sops, nsops, alter); if (error) { rcu_read_unlock(); - goto out_free; + goto out; } error = -EIDRM; @@ -2095,7 +2083,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, * entangled here and why it's RMID race safe on comments at sem_lock() */ if (!ipc_valid_object(&sma->sem_perm)) - goto out_unlock_free; + goto out_unlock; /* * semid identifiers are not unique - find_alloc_undo may have * allocated an undo structure, it was invalidated by an RMID @@ -2104,7 +2092,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, * "un" itself is guaranteed by rcu. */ if (un && un->semid == -1) - goto out_unlock_free; + goto out_unlock; queue.sops = sops; queue.nsops = nsops; @@ -2130,10 +2118,10 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, rcu_read_unlock(); wake_up_q(&wake_q); - goto out_free; + goto out; } if (error < 0) /* non-blocking error path */ - goto out_unlock_free; + goto out_unlock; /* * We need to sleep on this operation, so we put the current @@ -2198,14 +2186,14 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, if (error != -EINTR) { /* see SEM_BARRIER_2 for purpose/pairing */ smp_acquire__after_ctrl_dep(); - goto out_free; + goto out; } rcu_read_lock(); locknum = sem_lock(sma, sops, nsops); if (!ipc_valid_object(&sma->sem_perm)) - goto out_unlock_free; + goto out_unlock; /* * No necessity for any barrier: We are protect by sem_lock() @@ -2217,7 +2205,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, * Leave without unlink_queue(), but with sem_unlock(). */ if (error != -EINTR) - goto out_unlock_free; + goto out_unlock; /* * If an interrupt occurred we have to clean up the queue. @@ -2228,13 +2216,45 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, unlink_queue(sma, &queue); -out_unlock_free: +out_unlock: sem_unlock(sma, locknum); rcu_read_unlock(); +out: + return error; +} + +static long do_semtimedop(int semid, struct sembuf __user *tsops, + unsigned nsops, const struct timespec64 *timeout) +{ + struct sembuf fast_sops[SEMOPM_FAST]; + struct sembuf *sops = fast_sops; + struct ipc_namespace *ns; + int ret; + + ns = current->nsproxy->ipc_ns; + if (nsops > ns->sc_semopm) + return -E2BIG; + if (nsops < 1) + return -EINVAL; + + if (nsops > SEMOPM_FAST) { + sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL); + if (sops == NULL) + return -ENOMEM; + } + + if (copy_from_user(sops, tsops, nsops * sizeof(*tsops))) { + ret = -EFAULT; + goto out_free; + } + + ret = __do_semtimedop(semid, sops, nsops, timeout, ns); + out_free: if (sops != fast_sops) kvfree(sops); - return error; + + return ret; } long ksys_semtimedop(int semid, struct sembuf __user *tsops, -- cgit v1.2.3 From f7403abf5f06f407c50252e003f5fb332325147b Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 20 Aug 2021 14:14:42 +0100 Subject: iommu/io-pgtable: Abstract iommu_iotlb_gather access Previously io-pgtable merely passed the iommu_iotlb_gather pointer through to helpers, but now it has grown its own direct dereference. This turns out to break the build for !IOMMU_API configs where the structure only has a dummy definition. It will probably also crash drivers who don't use the gather mechanism and simply pass in NULL. Wrap this dereference in a suitable helper which can both be stubbed out for !IOMMU_API and encapsulate a NULL check otherwise. Fixes: 7a7c5badf858 ("iommu: Indicate queued flushes via gather data") Reported-by: kernel test robot Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/83672ee76f6405c82845a55c148fa836f56fbbc1.1629465282.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/io-pgtable-arm-v7s.c | 2 +- drivers/iommu/io-pgtable-arm.c | 2 +- include/linux/iommu.h | 10 ++++++++++ 3 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index e84478d39705..bfb6acb651e5 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -700,7 +700,7 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, ARM_V7S_BLOCK_SIZE(lvl + 1)); ptep = iopte_deref(pte[i], lvl, data); __arm_v7s_free_table(ptep, lvl + 1, data); - } else if (!gather->queued) { + } else if (!iommu_iotlb_gather_queued(gather)) { io_pgtable_tlb_add_page(iop, gather, iova, blk_size); } iova += blk_size; diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 48a5bd8f571d..9697721f7e3a 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -638,7 +638,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, io_pgtable_tlb_flush_walk(iop, iova + i * size, size, ARM_LPAE_GRANULE(data)); __arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data)); - } else if (!gather->queued) { + } else if (!iommu_iotlb_gather_queued(gather)) { io_pgtable_tlb_add_page(iop, gather, iova + i * size, size); } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 923a8d1c5e39..a23779c093c7 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -548,6 +548,11 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, gather->start = start; } +static inline bool iommu_iotlb_gather_queued(struct iommu_iotlb_gather *gather) +{ + return gather && gather->queued; +} + /* PCI device grouping function */ extern struct iommu_group *pci_device_group(struct device *dev); /* Generic device grouping function */ @@ -896,6 +901,11 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, { } +static inline bool iommu_iotlb_gather_queued(struct iommu_iotlb_gather *gather) +{ + return false; +} + static inline void iommu_device_unregister(struct iommu_device *iommu) { } -- cgit v1.2.3 From a4ae308143961bf688e1c8a62f6604e62b491120 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 5 Aug 2021 10:25:49 -0400 Subject: SUNRPC: Move client-side disconnect injection Disconnect injection stress-tests the ability for both client and server implementations to behave resiliently in the face of network instability. Convert the existing client-side disconnect injection infrastructure to use the kernel's generic error injection facility. The generic facility has a richer set of injection criteria. Signed-off-by: Chuck Lever --- include/linux/sunrpc/xprt.h | 18 ----------- net/sunrpc/debugfs.c | 78 ++++++++------------------------------------- net/sunrpc/fail.h | 2 ++ net/sunrpc/xprt.c | 14 ++++++++ 4 files changed, 30 insertions(+), 82 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index c8c39f22d3b1..b15c1f07162d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -288,7 +288,6 @@ struct rpc_xprt { const char *address_strings[RPC_DISPLAY_MAX]; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct dentry *debugfs; /* debugfs directory */ - atomic_t inject_disconnect; #endif struct rcu_head rcu; const struct xprt_class *xprt_class; @@ -502,21 +501,4 @@ static inline int xprt_test_and_set_binding(struct rpc_xprt *xprt) return test_and_set_bit(XPRT_BINDING, &xprt->state); } -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -extern unsigned int rpc_inject_disconnect; -static inline void xprt_inject_disconnect(struct rpc_xprt *xprt) -{ - if (!rpc_inject_disconnect) - return; - if (atomic_dec_return(&xprt->inject_disconnect)) - return; - atomic_set(&xprt->inject_disconnect, rpc_inject_disconnect); - xprt->ops->inject_disconnect(xprt); -} -#else -static inline void xprt_inject_disconnect(struct rpc_xprt *xprt) -{ -} -#endif - #endif /* _LINUX_SUNRPC_XPRT_H */ diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c index eaeb51f83abd..04e453ad3508 100644 --- a/net/sunrpc/debugfs.c +++ b/net/sunrpc/debugfs.c @@ -16,8 +16,6 @@ static struct dentry *topdir; static struct dentry *rpc_clnt_dir; static struct dentry *rpc_xprt_dir; -unsigned int rpc_inject_disconnect; - static int tasks_show(struct seq_file *f, void *v) { @@ -237,8 +235,6 @@ rpc_xprt_debugfs_register(struct rpc_xprt *xprt) /* make tasks file */ debugfs_create_file("info", S_IFREG | 0400, xprt->debugfs, xprt, &xprt_info_fops); - - atomic_set(&xprt->inject_disconnect, rpc_inject_disconnect); } void @@ -248,62 +244,26 @@ rpc_xprt_debugfs_unregister(struct rpc_xprt *xprt) xprt->debugfs = NULL; } -static int -fault_open(struct inode *inode, struct file *filp) -{ - filp->private_data = kmalloc(128, GFP_KERNEL); - if (!filp->private_data) - return -ENOMEM; - return 0; -} +#if IS_ENABLED(CONFIG_FAIL_SUNRPC) +struct fail_sunrpc_attr fail_sunrpc = { + .attr = FAULT_ATTR_INITIALIZER, +}; +EXPORT_SYMBOL_GPL(fail_sunrpc); -static int -fault_release(struct inode *inode, struct file *filp) +static void fail_sunrpc_init(void) { - kfree(filp->private_data); - return 0; -} + struct dentry *dir; -static ssize_t -fault_disconnect_read(struct file *filp, char __user *user_buf, - size_t len, loff_t *offset) -{ - char *buffer = (char *)filp->private_data; - size_t size; + dir = fault_create_debugfs_attr("fail_sunrpc", NULL, + &fail_sunrpc.attr); - size = sprintf(buffer, "%u\n", rpc_inject_disconnect); - return simple_read_from_buffer(user_buf, len, offset, buffer, size); + debugfs_create_bool("ignore-client-disconnect", S_IFREG | 0600, dir, + &fail_sunrpc.ignore_client_disconnect); } - -static ssize_t -fault_disconnect_write(struct file *filp, const char __user *user_buf, - size_t len, loff_t *offset) +#else +static void fail_sunrpc_init(void) { - char buffer[16]; - - if (len >= sizeof(buffer)) - len = sizeof(buffer) - 1; - if (copy_from_user(buffer, user_buf, len)) - return -EFAULT; - buffer[len] = '\0'; - if (kstrtouint(buffer, 10, &rpc_inject_disconnect)) - return -EINVAL; - return len; } - -static const struct file_operations fault_disconnect_fops = { - .owner = THIS_MODULE, - .open = fault_open, - .read = fault_disconnect_read, - .write = fault_disconnect_write, - .release = fault_release, -}; - -#if IS_ENABLED(CONFIG_FAIL_SUNRPC) -struct fail_sunrpc_attr fail_sunrpc = { - .attr = FAULT_ATTR_INITIALIZER, -}; -EXPORT_SYMBOL_GPL(fail_sunrpc); #endif void __exit @@ -318,21 +278,11 @@ sunrpc_debugfs_exit(void) void __init sunrpc_debugfs_init(void) { - struct dentry *rpc_fault_dir; - topdir = debugfs_create_dir("sunrpc", NULL); rpc_clnt_dir = debugfs_create_dir("rpc_clnt", topdir); rpc_xprt_dir = debugfs_create_dir("rpc_xprt", topdir); - rpc_fault_dir = debugfs_create_dir("inject_fault", topdir); - - debugfs_create_file("disconnect", S_IFREG | 0400, rpc_fault_dir, NULL, - &fault_disconnect_fops); - -#if IS_ENABLED(CONFIG_FAIL_SUNRPC) - fault_create_debugfs_attr("fail_sunrpc", NULL, - &fail_sunrpc.attr); -#endif + fail_sunrpc_init(); } diff --git a/net/sunrpc/fail.h b/net/sunrpc/fail.h index 1d402b0d3453..62c1b9fd59e2 100644 --- a/net/sunrpc/fail.h +++ b/net/sunrpc/fail.h @@ -12,6 +12,8 @@ struct fail_sunrpc_attr { struct fault_attr attr; + + bool ignore_client_disconnect; }; extern struct fail_sunrpc_attr fail_sunrpc; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index fb6db09725c7..05abe344a269 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -56,6 +56,7 @@ #include "sunrpc.h" #include "sysfs.h" +#include "fail.h" /* * Local variables @@ -855,6 +856,19 @@ xprt_init_autodisconnect(struct timer_list *t) queue_work(xprtiod_workqueue, &xprt->task_cleanup); } +#if IS_ENABLED(CONFIG_FAIL_SUNRPC) +static void xprt_inject_disconnect(struct rpc_xprt *xprt) +{ + if (!fail_sunrpc.ignore_client_disconnect && + should_fail(&fail_sunrpc.attr, 1)) + xprt->ops->inject_disconnect(xprt); +} +#else +static inline void xprt_inject_disconnect(struct rpc_xprt *xprt) +{ +} +#endif + bool xprt_lock_connect(struct rpc_xprt *xprt, struct rpc_task *task, void *cookie) -- cgit v1.2.3 From 7491e2c442781a1860181adb5ab472a52075f393 Mon Sep 17 00:00:00 2001 From: "Tzvetomir Stoyanov (VMware)" Date: Thu, 19 Aug 2021 11:26:06 -0400 Subject: tracing: Add a probe that attaches to trace events A new dynamic event is introduced: event probe. The event is attached to an existing tracepoint and uses its fields as arguments. The user can specify custom format string of the new event, select what tracepoint arguments will be printed and how to print them. An event probe is created by writing configuration string in 'dynamic_events' ftrace file: e[:[SNAME/]ENAME] SYSTEM/EVENT [FETCHARGS] - Set an event probe -:SNAME/ENAME - Delete an event probe Where: SNAME - System name, if omitted 'eprobes' is used. ENAME - Name of the new event in SNAME, if omitted the SYSTEM_EVENT is used. SYSTEM - Name of the system, where the tracepoint is defined, mandatory. EVENT - Name of the tracepoint event in SYSTEM, mandatory. FETCHARGS - Arguments: =$[:TYPE] - Fetch given filed of the tracepoint and print it as given TYPE with given name. Supported types are: (u8/u16/u32/u64/s8/s16/s32/s64), basic type (x8/x16/x32/x64), hexadecimal types "string", "ustring" and bitfield. Example, attach an event probe on openat system call and print name of the file that will be opened: echo "e:esys/eopen syscalls/sys_enter_openat file=\$filename:string" >> dynamic_events A new dynamic event is created in events/esys/eopen/ directory. It can be deleted with: echo "-:esys/eopen" >> dynamic_events Filters, triggers and histograms can be attached to the new event, it can be matched in synthetic events. There is one limitation - an event probe can not be attached to kprobe, uprobe or another event probe. Link: https://lkml.kernel.org/r/20210812145805.2292326-1-tz.stoyanov@gmail.com Link: https://lkml.kernel.org/r/20210819152825.142428383@goodmis.org Acked-by: Masami Hiramatsu Co-developed-by: Steven Rostedt (VMware) Signed-off-by: Tzvetomir Stoyanov (VMware) Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 4 + kernel/trace/Makefile | 1 + kernel/trace/trace.c | 5 +- kernel/trace/trace.h | 18 + kernel/trace/trace_eprobe.c | 903 ++++++++++++++++++++++++++++++++++++ kernel/trace/trace_events_trigger.c | 14 +- kernel/trace/trace_kprobe.c | 8 - kernel/trace/trace_probe.c | 16 +- kernel/trace/trace_probe.h | 6 +- 9 files changed, 962 insertions(+), 13 deletions(-) create mode 100644 kernel/trace/trace_eprobe.c (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 9564c4d9a3b6..0a0144580bbd 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -313,6 +313,7 @@ enum { TRACE_EVENT_FL_DYNAMIC_BIT, TRACE_EVENT_FL_KPROBE_BIT, TRACE_EVENT_FL_UPROBE_BIT, + TRACE_EVENT_FL_EPROBE_BIT, }; /* @@ -325,6 +326,7 @@ enum { * DYNAMIC - Event is a dynamic event (created at run time) * KPROBE - Event is a kprobe * UPROBE - Event is a uprobe + * EPROBE - Event is an event probe */ enum { TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), @@ -335,6 +337,7 @@ enum { TRACE_EVENT_FL_DYNAMIC = (1 << TRACE_EVENT_FL_DYNAMIC_BIT), TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), TRACE_EVENT_FL_UPROBE = (1 << TRACE_EVENT_FL_UPROBE_BIT), + TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) @@ -680,6 +683,7 @@ enum event_trigger_type { ETT_EVENT_ENABLE = (1 << 3), ETT_EVENT_HIST = (1 << 4), ETT_HIST_ENABLE = (1 << 5), + ETT_EVENT_EPROBE = (1 << 6), }; extern int filter_match_preds(struct event_filter *filter, void *rec); diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index b1c47ccf4f73..6de5d4d63165 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -77,6 +77,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o +obj-$(CONFIG_PROBE_EVENTS) += trace_eprobe.o obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8425c3d70895..489924cde4f8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5543,6 +5543,7 @@ static const char readme_msg[] = #ifdef CONFIG_HIST_TRIGGERS "\t s:[synthetic/] []\n" #endif + "\t e[:[/]] . []\n" "\t -:[/]\n" #ifdef CONFIG_KPROBE_EVENTS "\t place: [:][+]|\n" @@ -5552,7 +5553,7 @@ static const char readme_msg[] = " place (uprobe): :[%return][(ref_ctr_offset)]\n" #endif "\t args: =fetcharg[:type]\n" - "\t fetcharg: %, @
, @[+|-],\n" + "\t fetcharg: (%|$), @
, @[+|-],\n" #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API "\t $stack, $stack, $retval, $comm, $arg,\n" #else @@ -5567,6 +5568,8 @@ static const char readme_msg[] = "\t stype: u8/u16/u32/u64, s8/s16/s32/s64, pid_t,\n" "\t [unsigned] char/int/long\n" #endif + "\t efield: For event probes ('e' types), the field is on of the fields\n" + "\t of the /.\n" #endif " events/\t\t- Directory containing all trace event subsystems:\n" " enable\t\t- Write 0/1 to enable/disable tracing of all events\n" diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 4a0e693000c6..b7c0f8e160fb 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -126,6 +126,11 @@ struct kprobe_trace_entry_head { unsigned long ip; }; +struct eprobe_trace_entry_head { + struct trace_entry ent; + unsigned int type; +}; + struct kretprobe_trace_entry_head { struct trace_entry ent; unsigned long func; @@ -1508,9 +1513,14 @@ static inline int register_trigger_hist_enable_disable_cmds(void) { return 0; } extern int register_trigger_cmds(void); extern void clear_event_triggers(struct trace_array *tr); +enum { + EVENT_TRIGGER_FL_PROBE = BIT(0), +}; + struct event_trigger_data { unsigned long count; int ref; + int flags; struct event_trigger_ops *ops; struct event_command *cmd_ops; struct event_filter __rcu *filter; @@ -1918,6 +1928,14 @@ static inline bool is_good_name(const char *name) return true; } +/* Convert certain expected symbols into '_' when generating event names */ +static inline void sanitize_event_name(char *name) +{ + while (*name++ != '\0') + if (*name == ':' || *name == '.') + *name = '_'; +} + /* * This is a generic way to read and write a u64 value from a file in tracefs. * diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c new file mode 100644 index 000000000000..56a96e9750cf --- /dev/null +++ b/kernel/trace/trace_eprobe.c @@ -0,0 +1,903 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * event probes + * + * Part of this code was copied from kernel/trace/trace_kprobe.c written by + * Masami Hiramatsu + * + * Copyright (C) 2021, VMware Inc, Steven Rostedt + * Copyright (C) 2021, VMware Inc, Tzvetomir Stoyanov tz.stoyanov@gmail.com> + * + */ +#include +#include +#include + +#include "trace_dynevent.h" +#include "trace_probe.h" +#include "trace_probe_tmpl.h" + +#define EPROBE_EVENT_SYSTEM "eprobes" + +struct trace_eprobe { + /* tracepoint system */ + const char *event_system; + + /* tracepoint event */ + const char *event_name; + + struct trace_event_call *event; + + struct dyn_event devent; + struct trace_probe tp; +}; + +struct eprobe_data { + struct trace_event_file *file; + struct trace_eprobe *ep; +}; + +static int __trace_eprobe_create(int argc, const char *argv[]); + +static void trace_event_probe_cleanup(struct trace_eprobe *ep) +{ + if (!ep) + return; + trace_probe_cleanup(&ep->tp); + kfree(ep->event_name); + kfree(ep->event_system); + if (ep->event) + trace_event_put_ref(ep->event); + kfree(ep); +} + +static struct trace_eprobe *to_trace_eprobe(struct dyn_event *ev) +{ + return container_of(ev, struct trace_eprobe, devent); +} + +static int eprobe_dyn_event_create(const char *raw_command) +{ + return trace_probe_create(raw_command, __trace_eprobe_create); +} + +static int eprobe_dyn_event_show(struct seq_file *m, struct dyn_event *ev) +{ + struct trace_eprobe *ep = to_trace_eprobe(ev); + int i; + + seq_printf(m, "e:%s/%s", trace_probe_group_name(&ep->tp), + trace_probe_name(&ep->tp)); + seq_printf(m, " %s.%s", ep->event_system, ep->event_name); + + for (i = 0; i < ep->tp.nr_args; i++) + seq_printf(m, " %s=%s", ep->tp.args[i].name, ep->tp.args[i].comm); + seq_putc(m, '\n'); + + return 0; +} + +static int unregister_trace_eprobe(struct trace_eprobe *ep) +{ + /* If other probes are on the event, just unregister eprobe */ + if (trace_probe_has_sibling(&ep->tp)) + goto unreg; + + /* Enabled event can not be unregistered */ + if (trace_probe_is_enabled(&ep->tp)) + return -EBUSY; + + /* Will fail if probe is being used by ftrace or perf */ + if (trace_probe_unregister_event_call(&ep->tp)) + return -EBUSY; + +unreg: + dyn_event_remove(&ep->devent); + trace_probe_unlink(&ep->tp); + + return 0; +} + +static int eprobe_dyn_event_release(struct dyn_event *ev) +{ + struct trace_eprobe *ep = to_trace_eprobe(ev); + int ret = unregister_trace_eprobe(ep); + + if (!ret) + trace_event_probe_cleanup(ep); + return ret; +} + +static bool eprobe_dyn_event_is_busy(struct dyn_event *ev) +{ + struct trace_eprobe *ep = to_trace_eprobe(ev); + + return trace_probe_is_enabled(&ep->tp); +} + +static bool eprobe_dyn_event_match(const char *system, const char *event, + int argc, const char **argv, struct dyn_event *ev) +{ + struct trace_eprobe *ep = to_trace_eprobe(ev); + + return strcmp(trace_probe_name(&ep->tp), event) == 0 && + (!system || strcmp(trace_probe_group_name(&ep->tp), system) == 0) && + trace_probe_match_command_args(&ep->tp, argc, argv); +} + +static struct dyn_event_operations eprobe_dyn_event_ops = { + .create = eprobe_dyn_event_create, + .show = eprobe_dyn_event_show, + .is_busy = eprobe_dyn_event_is_busy, + .free = eprobe_dyn_event_release, + .match = eprobe_dyn_event_match, +}; + +static struct trace_eprobe *alloc_event_probe(const char *group, + const char *this_event, + struct trace_event_call *event, + int nargs) +{ + struct trace_eprobe *ep; + const char *event_name; + const char *sys_name; + int ret = -ENOMEM; + + if (!event) + return ERR_PTR(-ENODEV); + + sys_name = event->class->system; + event_name = trace_event_name(event); + + ep = kzalloc(struct_size(ep, tp.args, nargs), GFP_KERNEL); + if (!ep) { + trace_event_put_ref(ep->event); + goto error; + } + ep->event = event; + ep->event_name = kstrdup(event_name, GFP_KERNEL); + if (!ep->event_name) + goto error; + ep->event_system = kstrdup(sys_name, GFP_KERNEL); + if (!ep->event_system) + goto error; + + ret = trace_probe_init(&ep->tp, this_event, group, false); + if (ret < 0) + goto error; + + dyn_event_init(&ep->devent, &eprobe_dyn_event_ops); + return ep; +error: + trace_event_probe_cleanup(ep); + return ERR_PTR(ret); +} + +static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i) +{ + struct probe_arg *parg = &ep->tp.args[i]; + struct ftrace_event_field *field; + struct list_head *head; + + head = trace_get_fields(ep->event); + list_for_each_entry(field, head, link) { + if (!strcmp(parg->code->data, field->name)) { + kfree(parg->code->data); + parg->code->data = field; + return 0; + } + } + kfree(parg->code->data); + parg->code->data = NULL; + return -ENOENT; +} + +static int eprobe_event_define_fields(struct trace_event_call *event_call) +{ + int ret; + struct eprobe_trace_entry_head field; + struct trace_probe *tp; + + tp = trace_probe_primary_from_call(event_call); + if (WARN_ON_ONCE(!tp)) + return -ENOENT; + + DEFINE_FIELD(unsigned int, type, FIELD_STRING_TYPE, 0); + + return traceprobe_define_arg_fields(event_call, sizeof(field), tp); +} + +static struct trace_event_fields eprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = eprobe_event_define_fields }, + {} +}; + +/* Event entry printers */ +static enum print_line_t +print_eprobe_event(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct eprobe_trace_entry_head *field; + struct trace_event_call *pevent; + struct trace_event *probed_event; + struct trace_seq *s = &iter->seq; + struct trace_probe *tp; + + field = (struct eprobe_trace_entry_head *)iter->ent; + tp = trace_probe_primary_from_call( + container_of(event, struct trace_event_call, event)); + if (WARN_ON_ONCE(!tp)) + goto out; + + trace_seq_printf(s, "%s: (", trace_probe_name(tp)); + + probed_event = ftrace_find_event(field->type); + if (probed_event) { + pevent = container_of(probed_event, struct trace_event_call, event); + trace_seq_printf(s, "%s.%s", pevent->class->system, + trace_event_name(pevent)); + } else { + trace_seq_printf(s, "%u", field->type); + } + + trace_seq_putc(s, ')'); + + if (print_probe_args(s, tp->args, tp->nr_args, + (u8 *)&field[1], field) < 0) + goto out; + + trace_seq_putc(s, '\n'); + out: + return trace_handle_return(s); +} + +static unsigned long get_event_field(struct fetch_insn *code, void *rec) +{ + struct ftrace_event_field *field = code->data; + unsigned long val; + void *addr; + + addr = rec + field->offset; + + switch (field->size) { + case 1: + if (field->is_signed) + val = *(char *)addr; + else + val = *(unsigned char *)addr; + break; + case 2: + if (field->is_signed) + val = *(short *)addr; + else + val = *(unsigned short *)addr; + break; + case 4: + if (field->is_signed) + val = *(int *)addr; + else + val = *(unsigned int *)addr; + break; + default: + if (field->is_signed) + val = *(long *)addr; + else + val = *(unsigned long *)addr; + break; + } + return val; +} + +static int get_eprobe_size(struct trace_probe *tp, void *rec) +{ + struct probe_arg *arg; + int i, len, ret = 0; + + for (i = 0; i < tp->nr_args; i++) { + arg = tp->args + i; + if (unlikely(arg->dynamic)) { + unsigned long val; + + val = get_event_field(arg->code, rec); + len = process_fetch_insn_bottom(arg->code + 1, val, NULL, NULL); + if (len > 0) + ret += len; + } + } + + return ret; +} + +/* Kprobe specific fetch functions */ + +/* Note that we don't verify it, since the code does not come from user space */ +static int +process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, + void *base) +{ + unsigned long val; + + val = get_event_field(code, rec); + return process_fetch_insn_bottom(code + 1, val, dest, base); +} +NOKPROBE_SYMBOL(process_fetch_insn) + +/* Return the length of string -- including null terminal byte */ +static nokprobe_inline int +fetch_store_strlen_user(unsigned long addr) +{ + const void __user *uaddr = (__force const void __user *)addr; + + return strnlen_user_nofault(uaddr, MAX_STRING_SIZE); +} + +/* Return the length of string -- including null terminal byte */ +static nokprobe_inline int +fetch_store_strlen(unsigned long addr) +{ + int ret, len = 0; + u8 c; + +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + if (addr < TASK_SIZE) + return fetch_store_strlen_user(addr); +#endif + + do { + ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1); + len++; + } while (c && ret == 0 && len < MAX_STRING_SIZE); + + return (ret < 0) ? ret : len; +} + +/* + * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf + * with max length and relative data location. + */ +static nokprobe_inline int +fetch_store_string_user(unsigned long addr, void *dest, void *base) +{ + const void __user *uaddr = (__force const void __user *)addr; + int maxlen = get_loc_len(*(u32 *)dest); + void *__dest; + long ret; + + if (unlikely(!maxlen)) + return -ENOMEM; + + __dest = get_loc_data(dest, base); + + ret = strncpy_from_user_nofault(__dest, uaddr, maxlen); + if (ret >= 0) + *(u32 *)dest = make_data_loc(ret, __dest - base); + + return ret; +} + +/* + * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max + * length and relative data location. + */ +static nokprobe_inline int +fetch_store_string(unsigned long addr, void *dest, void *base) +{ + int maxlen = get_loc_len(*(u32 *)dest); + void *__dest; + long ret; + +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + if ((unsigned long)addr < TASK_SIZE) + return fetch_store_string_user(addr, dest, base); +#endif + + if (unlikely(!maxlen)) + return -ENOMEM; + + __dest = get_loc_data(dest, base); + + /* + * Try to get string again, since the string can be changed while + * probing. + */ + ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen); + if (ret >= 0) + *(u32 *)dest = make_data_loc(ret, __dest - base); + + return ret; +} + +static nokprobe_inline int +probe_mem_read_user(void *dest, void *src, size_t size) +{ + const void __user *uaddr = (__force const void __user *)src; + + return copy_from_user_nofault(dest, uaddr, size); +} + +static nokprobe_inline int +probe_mem_read(void *dest, void *src, size_t size) +{ +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + if ((unsigned long)src < TASK_SIZE) + return probe_mem_read_user(dest, src, size); +#endif + return copy_from_kernel_nofault(dest, src, size); +} + +/* eprobe handler */ +static inline void +__eprobe_trace_func(struct eprobe_data *edata, void *rec) +{ + struct eprobe_trace_entry_head *entry; + struct trace_event_call *call = trace_probe_event_call(&edata->ep->tp); + struct trace_event_buffer fbuffer; + int dsize; + + if (WARN_ON_ONCE(call != edata->file->event_call)) + return; + + if (trace_trigger_soft_disabled(edata->file)) + return; + + fbuffer.trace_ctx = tracing_gen_ctx(); + fbuffer.trace_file = edata->file; + + dsize = get_eprobe_size(&edata->ep->tp, rec); + fbuffer.regs = NULL; + + fbuffer.event = + trace_event_buffer_lock_reserve(&fbuffer.buffer, edata->file, + call->event.type, + sizeof(*entry) + edata->ep->tp.size + dsize, + fbuffer.trace_ctx); + if (!fbuffer.event) + return; + + entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); + if (edata->ep->event) + entry->type = edata->ep->event->event.type; + else + entry->type = 0; + store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize); + + trace_event_buffer_commit(&fbuffer); +} + +/* + * The event probe implementation uses event triggers to get access to + * the event it is attached to, but is not an actual trigger. The below + * functions are just stubs to fulfill what is needed to use the trigger + * infrastructure. + */ +static int eprobe_trigger_init(struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + return 0; +} + +static void eprobe_trigger_free(struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + +} + +static int eprobe_trigger_print(struct seq_file *m, + struct event_trigger_ops *ops, + struct event_trigger_data *data) +{ + /* Do not print eprobe event triggers */ + return 0; +} + +static void eprobe_trigger_func(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, + struct ring_buffer_event *rbe) +{ + struct eprobe_data *edata = data->private_data; + + __eprobe_trace_func(edata, rec); +} + +static struct event_trigger_ops eprobe_trigger_ops = { + .func = eprobe_trigger_func, + .print = eprobe_trigger_print, + .init = eprobe_trigger_init, + .free = eprobe_trigger_free, +}; + +static int eprobe_trigger_cmd_func(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, char *cmd, char *param) +{ + return -1; +} + +static int eprobe_trigger_reg_func(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *data, + struct trace_event_file *file) +{ + return -1; +} + +static void eprobe_trigger_unreg_func(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *data, + struct trace_event_file *file) +{ + +} + +static struct event_trigger_ops *eprobe_trigger_get_ops(char *cmd, + char *param) +{ + return &eprobe_trigger_ops; +} + +static struct event_command event_trigger_cmd = { + .name = "eprobe", + .trigger_type = ETT_EVENT_EPROBE, + .flags = EVENT_CMD_FL_NEEDS_REC, + .func = eprobe_trigger_cmd_func, + .reg = eprobe_trigger_reg_func, + .unreg = eprobe_trigger_unreg_func, + .unreg_all = NULL, + .get_trigger_ops = eprobe_trigger_get_ops, + .set_filter = NULL, +}; + +static struct event_trigger_data * +new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file) +{ + struct event_trigger_data *trigger; + struct eprobe_data *edata; + + edata = kzalloc(sizeof(*edata), GFP_KERNEL); + trigger = kzalloc(sizeof(*trigger), GFP_KERNEL); + if (!trigger || !edata) { + kfree(edata); + kfree(trigger); + return ERR_PTR(-ENOMEM); + } + + trigger->flags = EVENT_TRIGGER_FL_PROBE; + trigger->count = -1; + trigger->ops = &eprobe_trigger_ops; + + /* + * EVENT PROBE triggers are not registered as commands with + * register_event_command(), as they are not controlled by the user + * from the trigger file + */ + trigger->cmd_ops = &event_trigger_cmd; + + INIT_LIST_HEAD(&trigger->list); + RCU_INIT_POINTER(trigger->filter, NULL); + + edata->file = file; + edata->ep = ep; + trigger->private_data = edata; + + return trigger; +} + +static int enable_eprobe(struct trace_eprobe *ep, + struct trace_event_file *eprobe_file) +{ + struct event_trigger_data *trigger; + struct trace_event_file *file; + struct trace_array *tr = eprobe_file->tr; + + file = find_event_file(tr, ep->event_system, ep->event_name); + if (!file) + return -ENOENT; + trigger = new_eprobe_trigger(ep, eprobe_file); + if (IS_ERR(trigger)) + return PTR_ERR(trigger); + + list_add_tail_rcu(&trigger->list, &file->triggers); + + trace_event_trigger_enable_disable(file, 1); + update_cond_flag(file); + + return 0; +} + +static struct trace_event_functions eprobe_funcs = { + .trace = print_eprobe_event +}; + +static int disable_eprobe(struct trace_eprobe *ep, + struct trace_array *tr) +{ + struct event_trigger_data *trigger; + struct trace_event_file *file; + struct eprobe_data *edata; + + file = find_event_file(tr, ep->event_system, ep->event_name); + if (!file) + return -ENOENT; + + list_for_each_entry(trigger, &file->triggers, list) { + if (!(trigger->flags & EVENT_TRIGGER_FL_PROBE)) + continue; + edata = trigger->private_data; + if (edata->ep == ep) + break; + } + if (list_entry_is_head(trigger, &file->triggers, list)) + return -ENODEV; + + list_del_rcu(&trigger->list); + + trace_event_trigger_enable_disable(file, 0); + update_cond_flag(file); + return 0; +} + +static int enable_trace_eprobe(struct trace_event_call *call, + struct trace_event_file *file) +{ + struct trace_probe *pos, *tp; + struct trace_eprobe *ep; + bool enabled; + int ret = 0; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + enabled = trace_probe_is_enabled(tp); + + /* This also changes "enabled" state */ + if (file) { + ret = trace_probe_add_file(tp, file); + if (ret) + return ret; + } else + trace_probe_set_flag(tp, TP_FLAG_PROFILE); + + if (enabled) + return 0; + + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + ep = container_of(pos, struct trace_eprobe, tp); + ret = enable_eprobe(ep, file); + if (ret) + break; + enabled = true; + } + + if (ret) { + /* Failed to enable one of them. Roll back all */ + if (enabled) + disable_eprobe(ep, file->tr); + if (file) + trace_probe_remove_file(tp, file); + else + trace_probe_clear_flag(tp, TP_FLAG_PROFILE); + } + + return ret; +} + +static int disable_trace_eprobe(struct trace_event_call *call, + struct trace_event_file *file) +{ + struct trace_probe *pos, *tp; + struct trace_eprobe *ep; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + + if (file) { + if (!trace_probe_get_file_link(tp, file)) + return -ENOENT; + if (!trace_probe_has_single_file(tp)) + goto out; + trace_probe_clear_flag(tp, TP_FLAG_TRACE); + } else + trace_probe_clear_flag(tp, TP_FLAG_PROFILE); + + if (!trace_probe_is_enabled(tp)) { + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + ep = container_of(pos, struct trace_eprobe, tp); + disable_eprobe(ep, file->tr); + } + } + + out: + if (file) + /* + * Synchronization is done in below function. For perf event, + * file == NULL and perf_trace_event_unreg() calls + * tracepoint_synchronize_unregister() to ensure synchronize + * event. We don't need to care about it. + */ + trace_probe_remove_file(tp, file); + + return 0; +} + +static int eprobe_register(struct trace_event_call *event, + enum trace_reg type, void *data) +{ + struct trace_event_file *file = data; + + switch (type) { + case TRACE_REG_REGISTER: + return enable_trace_eprobe(event, file); + case TRACE_REG_UNREGISTER: + return disable_trace_eprobe(event, file); +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + case TRACE_REG_PERF_UNREGISTER: + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: + return 0; +#endif + } + return 0; +} + +static inline void init_trace_eprobe_call(struct trace_eprobe *ep) +{ + struct trace_event_call *call = trace_probe_event_call(&ep->tp); + + call->flags = TRACE_EVENT_FL_EPROBE; + call->event.funcs = &eprobe_funcs; + call->class->fields_array = eprobe_fields_array; + call->class->reg = eprobe_register; +} + +static struct trace_event_call * +find_and_get_event(const char *system, const char *event_name) +{ + struct trace_event_call *tp_event; + const char *name; + + list_for_each_entry(tp_event, &ftrace_events, list) { + /* Skip other probes and ftrace events */ + if (tp_event->flags & + (TRACE_EVENT_FL_IGNORE_ENABLE | + TRACE_EVENT_FL_KPROBE | + TRACE_EVENT_FL_UPROBE | + TRACE_EVENT_FL_EPROBE)) + continue; + if (!tp_event->class->system || + strcmp(system, tp_event->class->system)) + continue; + name = trace_event_name(tp_event); + if (!name || strcmp(event_name, name)) + continue; + if (!trace_event_try_get_ref(tp_event)) { + return NULL; + break; + } + return tp_event; + break; + } + return NULL; +} + +static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[], int i) +{ + unsigned int flags = TPARG_FL_KERNEL | TPARG_FL_TPOINT; + int ret; + + ret = traceprobe_parse_probe_arg(&ep->tp, i, argv[i], flags); + if (ret) + return ret; + + if (ep->tp.args[i].code->op == FETCH_OP_TP_ARG) + ret = trace_eprobe_tp_arg_update(ep, i); + + return ret; +} + +static int __trace_eprobe_create(int argc, const char *argv[]) +{ + /* + * Argument syntax: + * e[:[GRP/]ENAME] SYSTEM.EVENT [FETCHARGS] + * Fetch args: + * =$[:TYPE] + */ + const char *event = NULL, *group = EPROBE_EVENT_SYSTEM; + const char *sys_event = NULL, *sys_name = NULL; + struct trace_event_call *event_call; + struct trace_eprobe *ep = NULL; + char buf1[MAX_EVENT_NAME_LEN]; + char buf2[MAX_EVENT_NAME_LEN]; + int ret = 0; + int i; + + if (argc < 2 || argv[0][0] != 'e') + return -ECANCELED; + + trace_probe_log_init("event_probe", argc, argv); + + event = strchr(&argv[0][1], ':'); + if (event) { + event++; + ret = traceprobe_parse_event_name(&event, &group, buf1, + event - argv[0]); + if (ret) + goto parse_error; + } else { + strscpy(buf1, argv[1], MAX_EVENT_NAME_LEN); + sanitize_event_name(buf1); + event = buf1; + } + if (!is_good_name(event) || !is_good_name(group)) + goto parse_error; + + sys_event = argv[1]; + ret = traceprobe_parse_event_name(&sys_event, &sys_name, buf2, + sys_event - argv[1]); + if (ret || !sys_name) + goto parse_error; + if (!is_good_name(sys_event) || !is_good_name(sys_name)) + goto parse_error; + + mutex_lock(&event_mutex); + event_call = find_and_get_event(sys_name, sys_event); + ep = alloc_event_probe(group, event, event_call, argc - 2); + mutex_unlock(&event_mutex); + + if (IS_ERR(ep)) { + ret = PTR_ERR(ep); + /* This must return -ENOMEM, else there is a bug */ + WARN_ON_ONCE(ret != -ENOMEM); + goto error; /* We know ep is not allocated */ + } + + argc -= 2; argv += 2; + /* parse arguments */ + for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + trace_probe_log_set_index(i + 2); + ret = trace_eprobe_tp_update_arg(ep, argv, i); + if (ret) + goto error; + } + ret = traceprobe_set_print_fmt(&ep->tp, PROBE_PRINT_EVENT); + if (ret < 0) + goto error; + init_trace_eprobe_call(ep); + mutex_lock(&event_mutex); + ret = trace_probe_register_event_call(&ep->tp); + if (ret) { + if (ret == -EEXIST) { + trace_probe_log_set_index(0); + trace_probe_log_err(0, EVENT_EXIST); + } + mutex_unlock(&event_mutex); + goto error; + } + ret = dyn_event_add(&ep->devent, &ep->tp.event->call); + mutex_unlock(&event_mutex); + return ret; +parse_error: + ret = -EINVAL; +error: + trace_event_probe_cleanup(ep); + return ret; +} + +/* + * Register dynevent at core_initcall. This allows kernel to setup eprobe + * events in postcore_initcall without tracefs. + */ +static __init int trace_events_eprobe_init_early(void) +{ + int err = 0; + + err = dyn_event_register(&eprobe_dyn_event_ops); + if (err) + pr_warn("Could not register eprobe_dyn_event_ops\n"); + + return err; +} +core_initcall(trace_events_eprobe_init_early); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 6b11e335a62e..3d5c07239a2a 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -124,6 +124,18 @@ static void *trigger_next(struct seq_file *m, void *t, loff_t *pos) return seq_list_next(t, &event_file->triggers, pos); } +static bool check_user_trigger(struct trace_event_file *file) +{ + struct event_trigger_data *data; + + list_for_each_entry_rcu(data, &file->triggers, list) { + if (data->flags & EVENT_TRIGGER_FL_PROBE) + continue; + return true; + } + return false; +} + static void *trigger_start(struct seq_file *m, loff_t *pos) { struct trace_event_file *event_file; @@ -134,7 +146,7 @@ static void *trigger_start(struct seq_file *m, loff_t *pos) if (unlikely(!event_file)) return ERR_PTR(-ENODEV); - if (list_empty(&event_file->triggers)) + if (list_empty(&event_file->triggers) || !check_user_trigger(event_file)) return *pos == 0 ? SHOW_AVAILABLE_TRIGGERS : NULL; return seq_list_start(&event_file->triggers, *pos); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 882c27044029..3a64ba4bbad6 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -707,14 +707,6 @@ static struct notifier_block trace_kprobe_module_nb = { .priority = 1 /* Invoked after kprobe module callback */ }; -/* Convert certain expected symbols into '_' when generating event names */ -static inline void sanitize_event_name(char *name) -{ - while (*name++ != '\0') - if (*name == ':' || *name == '.') - *name = '_'; -} - static int __trace_kprobe_create(int argc, const char *argv[]) { /* diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 782c00eb6859..3ed2a3f37297 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -319,6 +319,13 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, code->op = FETCH_OP_ARG; code->param = (unsigned int)param - 1; #endif + } else if (flags & TPARG_FL_TPOINT) { + if (code->data) + return -EFAULT; + code->data = kstrdup(arg, GFP_KERNEL); + if (!code->data) + return -ENOMEM; + code->op = FETCH_OP_TP_ARG; } else goto inval_var; @@ -646,13 +653,14 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, !strcmp(parg->type->name, "ustring")) { if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_UDEREF && code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM && - code->op != FETCH_OP_DATA) { + code->op != FETCH_OP_DATA && code->op != FETCH_OP_TP_ARG) { trace_probe_log_err(offset + (t ? (t - arg) : 0), BAD_STRING); goto fail; } if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM || - code->op == FETCH_OP_DATA) || parg->count) { + code->op == FETCH_OP_DATA) || code->op == FETCH_OP_TP_ARG || + parg->count) { /* * IMM, DATA and COMM is pointing actual address, those * must be kept, and if parg->count != 0, this is an @@ -867,6 +875,10 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, fmt = "(%lx <- %lx)"; arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP; break; + case PROBE_PRINT_EVENT: + fmt = "(%u)"; + arg = "REC->" FIELD_STRING_TYPE; + break; default: WARN_ON_ONCE(1); return 0; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 66701a92d186..99e7a5df025e 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -38,6 +38,7 @@ #define FIELD_STRING_IP "__probe_ip" #define FIELD_STRING_RETIP "__probe_ret_ip" #define FIELD_STRING_FUNC "__probe_func" +#define FIELD_STRING_TYPE "__probe_type" #undef DEFINE_FIELD #define DEFINE_FIELD(type, item, name, is_signed) \ @@ -102,6 +103,7 @@ enum fetch_op { FETCH_OP_MOD_BF, /* Bitfield: .basesize, .lshift, .rshift */ // Stage 5 (loop) op FETCH_OP_LP_ARRAY, /* Array: .param = loop count */ + FETCH_OP_TP_ARG, /* Trace Point argument */ FETCH_OP_END, FETCH_NOP_SYMBOL, /* Unresolved Symbol holder */ }; @@ -351,7 +353,8 @@ int trace_probe_create(const char *raw_command, int (*createfn)(int, const char #define TPARG_FL_RETURN BIT(0) #define TPARG_FL_KERNEL BIT(1) #define TPARG_FL_FENTRY BIT(2) -#define TPARG_FL_MASK GENMASK(2, 0) +#define TPARG_FL_TPOINT BIT(3) +#define TPARG_FL_MASK GENMASK(3, 0) extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, const char *argv, unsigned int flags); @@ -366,6 +369,7 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup, enum probe_print_type { PROBE_PRINT_NORMAL, PROBE_PRINT_RETURN, + PROBE_PRINT_EVENT, }; extern int traceprobe_set_print_fmt(struct trace_probe *tp, enum probe_print_type ptype); -- cgit v1.2.3 From f56ce412a59d7d938b81de8878faef128812482c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 19 Aug 2021 19:04:21 -0700 Subject: mm: memcontrol: fix occasional OOMs due to proportional memory.low reclaim We've noticed occasional OOM killing when memory.low settings are in effect for cgroups. This is unexpected and undesirable as memory.low is supposed to express non-OOMing memory priorities between cgroups. The reason for this is proportional memory.low reclaim. When cgroups are below their memory.low threshold, reclaim passes them over in the first round, and then retries if it couldn't find pages anywhere else. But when cgroups are slightly above their memory.low setting, page scan force is scaled down and diminished in proportion to the overage, to the point where it can cause reclaim to fail as well - only in that case we currently don't retry, and instead trigger OOM. To fix this, hook proportional reclaim into the same retry logic we have in place for when cgroups are skipped entirely. This way if reclaim fails and some cgroups were scanned with diminished pressure, we'll try another full-force cycle before giving up and OOMing. [akpm@linux-foundation.org: coding-style fixes] Link: https://lkml.kernel.org/r/20210817180506.220056-1-hannes@cmpxchg.org Fixes: 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim") Signed-off-by: Johannes Weiner Reported-by: Leon Yang Reviewed-by: Rik van Riel Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Chris Down Acked-by: Michal Hocko Cc: [5.4+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 29 +++++++++++++++-------------- mm/vmscan.c | 27 +++++++++++++++++++-------- 2 files changed, 34 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bfe5c486f4ad..24797929d8a1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -612,12 +612,15 @@ static inline bool mem_cgroup_disabled(void) return !cgroup_subsys_enabled(memory_cgrp_subsys); } -static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, - struct mem_cgroup *memcg, - bool in_low_reclaim) +static inline void mem_cgroup_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg, + unsigned long *min, + unsigned long *low) { + *min = *low = 0; + if (mem_cgroup_disabled()) - return 0; + return; /* * There is no reclaim protection applied to a targeted reclaim. @@ -653,13 +656,10 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, * */ if (root == memcg) - return 0; - - if (in_low_reclaim) - return READ_ONCE(memcg->memory.emin); + return; - return max(READ_ONCE(memcg->memory.emin), - READ_ONCE(memcg->memory.elow)); + *min = READ_ONCE(memcg->memory.emin); + *low = READ_ONCE(memcg->memory.elow); } void mem_cgroup_calculate_protection(struct mem_cgroup *root, @@ -1147,11 +1147,12 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, { } -static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, - struct mem_cgroup *memcg, - bool in_low_reclaim) +static inline void mem_cgroup_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg, + unsigned long *min, + unsigned long *low) { - return 0; + *min = *low = 0; } static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, diff --git a/mm/vmscan.c b/mm/vmscan.c index 4620df62f0ff..b0202ab5e136 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -100,9 +100,12 @@ struct scan_control { unsigned int may_swap:1; /* - * Cgroups are not reclaimed below their configured memory.low, - * unless we threaten to OOM. If any cgroups are skipped due to - * memory.low and nothing was reclaimed, go back for memory.low. + * Cgroup memory below memory.low is protected as long as we + * don't threaten to OOM. If any cgroup is reclaimed at + * reduced force or passed over entirely due to its memory.low + * setting (memcg_low_skipped), and nothing is reclaimed as a + * result, then go back for one more cycle that reclaims the protected + * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; @@ -2537,15 +2540,14 @@ out: for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; + unsigned long low, min; unsigned long scan; - unsigned long protection; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - protection = mem_cgroup_protection(sc->target_mem_cgroup, - memcg, - sc->memcg_low_reclaim); + mem_cgroup_protection(sc->target_mem_cgroup, memcg, + &min, &low); - if (protection) { + if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min @@ -2576,6 +2578,15 @@ out: * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); + unsigned long protection; + + /* memory.low scaling, make sure we retry before OOM */ + if (!sc->memcg_low_reclaim && low > min) { + protection = low; + sc->memcg_low_skipped = 1; + } else { + protection = min; + } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); -- cgit v1.2.3 From a7cb5d23eaea148f8582229846f8dfff192f05c3 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 19 Aug 2021 19:04:30 -0700 Subject: kfence: fix is_kfence_address() for addresses below KFENCE_POOL_SIZE Originally the addr != NULL check was meant to take care of the case where __kfence_pool == NULL (KFENCE is disabled). However, this does not work for addresses where addr > 0 && addr < KFENCE_POOL_SIZE. This can be the case on NULL-deref where addr > 0 && addr < PAGE_SIZE or any other faulting access with addr < KFENCE_POOL_SIZE. While the kernel would likely crash, the stack traces and report might be confusing due to double faults upon KFENCE's attempt to unprotect such an address. Fix it by just checking that __kfence_pool != NULL instead. Link: https://lkml.kernel.org/r/20210818130300.2482437-1-elver@google.com Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure") Signed-off-by: Marco Elver Reported-by: Kuan-Ying Lee Acked-by: Alexander Potapenko Cc: Dmitry Vyukov Cc: [5.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfence.h b/include/linux/kfence.h index a70d1ea03532..3fe6dd8a18c1 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -51,10 +51,11 @@ extern atomic_t kfence_allocation_gate; static __always_inline bool is_kfence_address(const void *addr) { /* - * The non-NULL check is required in case the __kfence_pool pointer was - * never initialized; keep it in the slow-path after the range-check. + * The __kfence_pool != NULL check is required to deal with the case + * where __kfence_pool == NULL && addr < KFENCE_POOL_SIZE. Keep it in + * the slow-path after the range-check! */ - return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && addr); + return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && __kfence_pool); } /** -- cgit v1.2.3 From edb298c663fccad65fe99fcec6a4f96cc344520d Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 10 Aug 2021 23:52:39 +0300 Subject: KVM: x86/mmu: bump mmu notifier count in kvm_zap_gfn_range This together with previous patch, ensures that kvm_zap_gfn_range doesn't race with page fault running on another vcpu, and will make this page fault code retry instead. This is based on a patch suggested by Sean Christopherson: https://lkml.org/lkml/2021/7/22/1025 Suggested-by: Sean Christopherson Signed-off-by: Maxim Levitsky Message-Id: <20210810205251.424103-5-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 4 ++++ include/linux/kvm_host.h | 5 +++++ virt/kvm/kvm_main.c | 7 +++++-- 3 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e53d09534113..916083eb4036 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5688,6 +5688,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) write_lock(&kvm->mmu_lock); + kvm_inc_notifier_count(kvm, gfn_start, gfn_end); + if (kvm_memslots_have_rmaps(kvm)) { for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); @@ -5723,6 +5725,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) if (flush) kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end); + kvm_dec_notifier_count(kvm, gfn_start, gfn_end); + write_unlock(&kvm->mmu_lock); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f50bfcf225f0..4e43843fe0d7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -991,6 +991,11 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc); void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); #endif +void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start, + unsigned long end); +void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start, + unsigned long end); + long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vcpu_ioctl(struct file *filp, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3e81b5d8b709..8563d9b725af 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -610,7 +610,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn); } -static void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start, +void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start, unsigned long end) { /* @@ -638,6 +638,7 @@ static void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start, max(kvm->mmu_notifier_range_end, end); } } +EXPORT_SYMBOL_GPL(kvm_inc_notifier_count); static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, const struct mmu_notifier_range *range) @@ -672,7 +673,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, return 0; } -static void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start, +void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start, unsigned long end) { /* @@ -689,6 +690,8 @@ static void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start, */ kvm->mmu_notifier_count--; } +EXPORT_SYMBOL_GPL(kvm_dec_notifier_count); + static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, const struct mmu_notifier_range *range) -- cgit v1.2.3 From f95937ccf5bd5e0a6bbac2b8e65a87982ffae403 Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Mon, 2 Aug 2021 16:56:29 +0000 Subject: KVM: stats: Support linear and logarithmic histogram statistics Add new types of KVM stats, linear and logarithmic histogram. Histogram are very useful for observing the value distribution of time or size related stats. Signed-off-by: Jing Zhang Message-Id: <20210802165633.1866976-2-jingzhangos@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/guest.c | 4 --- arch/mips/kvm/mips.c | 4 --- arch/powerpc/kvm/book3s.c | 4 --- arch/powerpc/kvm/booke.c | 4 --- arch/s390/kvm/kvm-s390.c | 4 --- arch/x86/kvm/x86.c | 4 --- include/linux/kvm_host.h | 90 +++++++++++++++++++++++++++++++++++++++-------- include/uapi/linux/kvm.h | 11 +++--- 8 files changed, 82 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 1dfb83578277..5188184d25d0 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -31,8 +31,6 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; -static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == - sizeof(struct kvm_vm_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, @@ -52,8 +50,6 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, mmio_exit_kernel), STATS_DESC_COUNTER(VCPU, exits) }; -static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == - sizeof(struct kvm_vcpu_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index af9dd029a4e1..75c6f264c626 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -41,8 +41,6 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; -static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == - sizeof(struct kvm_vm_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, @@ -85,8 +83,6 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, vz_cpucfg_exits), #endif }; -static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == - sizeof(struct kvm_vcpu_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 79833f78d1da..5cc6e90095b0 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -43,8 +43,6 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { STATS_DESC_ICOUNTER(VM, num_2M_pages), STATS_DESC_ICOUNTER(VM, num_1G_pages) }; -static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == - sizeof(struct kvm_vm_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, @@ -88,8 +86,6 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, pthru_host), STATS_DESC_COUNTER(VCPU, pthru_bad_aff) }; -static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == - sizeof(struct kvm_vcpu_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 551b30d84aee..5ed6c235e059 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -41,8 +41,6 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { STATS_DESC_ICOUNTER(VM, num_2M_pages), STATS_DESC_ICOUNTER(VM, num_1G_pages) }; -static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == - sizeof(struct kvm_vm_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, @@ -79,8 +77,6 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, pthru_host), STATS_DESC_COUNTER(VCPU, pthru_bad_aff) }; -static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == - sizeof(struct kvm_vcpu_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 02574d7b3612..4dc7e966a720 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -66,8 +66,6 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { STATS_DESC_COUNTER(VM, inject_service_signal), STATS_DESC_COUNTER(VM, inject_virtio) }; -static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == - sizeof(struct kvm_vm_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, @@ -174,8 +172,6 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, instruction_diagnose_other), STATS_DESC_COUNTER(VCPU, pfault_sync) }; -static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == - sizeof(struct kvm_vcpu_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bf8cb1021d11..9425589f34ca 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -238,8 +238,6 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { STATS_DESC_PCOUNTER(VM, max_mmu_rmap_size), STATS_DESC_PCOUNTER(VM, max_mmu_page_hash_collisions) }; -static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == - sizeof(struct kvm_vm_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, @@ -279,8 +277,6 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, directed_yield_successful), STATS_DESC_ICOUNTER(VCPU, guest_mode) }; -static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == - sizeof(struct kvm_vcpu_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4e43843fe0d7..09fc0274b1eb 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1356,56 +1356,66 @@ struct _kvm_stats_desc { char name[KVM_STATS_NAME_SIZE]; }; -#define STATS_DESC_COMMON(type, unit, base, exp) \ +#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ .flags = type | unit | base | \ BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ .exponent = exp, \ - .size = 1 + .size = sz, \ + .bucket_size = bsz -#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp) \ +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ - STATS_DESC_COMMON(type, unit, base, exp), \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vm_stat, generic.stat) \ }, \ .name = #stat, \ } -#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp) \ +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ - STATS_DESC_COMMON(type, unit, base, exp), \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ }, \ .name = #stat, \ } -#define VM_STATS_DESC(stat, type, unit, base, exp) \ +#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ - STATS_DESC_COMMON(type, unit, base, exp), \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vm_stat, stat) \ }, \ .name = #stat, \ } -#define VCPU_STATS_DESC(stat, type, unit, base, exp) \ +#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ { \ - STATS_DESC_COMMON(type, unit, base, exp), \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vcpu_stat, stat) \ }, \ .name = #stat, \ } /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ -#define STATS_DESC(SCOPE, stat, type, unit, base, exp) \ - SCOPE##_STATS_DESC(stat, type, unit, base, exp) +#define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ + SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) #define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \ - STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, unit, base, exponent) + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, \ + unit, base, exponent, 1, 0) #define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \ - STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, unit, base, exponent) + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, \ + unit, base, exponent, 1, 0) #define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \ - STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, unit, base, exponent) + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, \ + unit, base, exponent, 1, 0) +#define STATS_DESC_LINEAR_HIST(SCOPE, name, unit, base, exponent, sz, bsz) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LINEAR_HIST, \ + unit, base, exponent, sz, bsz) +#define STATS_DESC_LOG_HIST(SCOPE, name, unit, base, exponent, sz) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LOG_HIST, \ + unit, base, exponent, sz, 0) /* Cumulative counter, read/write */ #define STATS_DESC_COUNTER(SCOPE, name) \ @@ -1424,6 +1434,14 @@ struct _kvm_stats_desc { #define STATS_DESC_TIME_NSEC(SCOPE, name) \ STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9) +/* Linear histogram for time in nanosecond */ +#define STATS_DESC_LINHIST_TIME_NSEC(SCOPE, name, sz, bsz) \ + STATS_DESC_LINEAR_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9, sz, bsz) +/* Logarithmic histogram for time in nanosecond */ +#define STATS_DESC_LOGHIST_TIME_NSEC(SCOPE, name, sz) \ + STATS_DESC_LOG_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9, sz) #define KVM_GENERIC_VM_STATS() \ STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush) @@ -1437,10 +1455,52 @@ struct _kvm_stats_desc { STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns) extern struct dentry *kvm_debugfs_dir; + ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, const struct _kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset); + +/** + * kvm_stats_linear_hist_update() - Update bucket value for linear histogram + * statistics data. + * + * @data: start address of the stats data + * @size: the number of bucket of the stats data + * @value: the new value used to update the linear histogram's bucket + * @bucket_size: the size (width) of a bucket + */ +static inline void kvm_stats_linear_hist_update(u64 *data, size_t size, + u64 value, size_t bucket_size) +{ + size_t index = div64_u64(value, bucket_size); + + index = min(index, size - 1); + ++data[index]; +} + +/** + * kvm_stats_log_hist_update() - Update bucket value for logarithmic histogram + * statistics data. + * + * @data: start address of the stats data + * @size: the number of bucket of the stats data + * @value: the new value used to update the logarithmic histogram's bucket + */ +static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) +{ + size_t index = fls64(value); + + index = min(index, size - 1); + ++data[index]; +} + +#define KVM_STATS_LINEAR_HIST_UPDATE(array, value, bsize) \ + kvm_stats_linear_hist_update(array, ARRAY_SIZE(array), value, bsize) +#define KVM_STATS_LOG_HIST_UPDATE(array, value) \ + kvm_stats_log_hist_update(array, ARRAY_SIZE(array), value) + + extern const struct kvm_stats_header kvm_vm_stats_header; extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d9e4aabcb31a..a067410ebea5 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1965,7 +1965,9 @@ struct kvm_stats_header { #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) #define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT) -#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_PEAK +#define KVM_STATS_TYPE_LINEAR_HIST (0x3 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_LOG_HIST (0x4 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_LOG_HIST #define KVM_STATS_UNIT_SHIFT 4 #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) @@ -1988,8 +1990,9 @@ struct kvm_stats_header { * @size: The number of data items for this stats. * Every data item is of type __u64. * @offset: The offset of the stats to the start of stat structure in - * struture kvm or kvm_vcpu. - * @unused: Unused field for future usage. Always 0 for now. + * structure kvm or kvm_vcpu. + * @bucket_size: A parameter value used for histogram stats. It is only used + * for linear histogram stats, specifying the size of the bucket; * @name: The name string for the stats. Its size is indicated by the * &kvm_stats_header->name_size. */ @@ -1998,7 +2001,7 @@ struct kvm_stats_desc { __s16 exponent; __u16 size; __u32 offset; - __u32 unused; + __u32 bucket_size; char name[]; }; -- cgit v1.2.3 From 87bcc5fa092f82a9890f9e73e4f4c7016ef64049 Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Mon, 2 Aug 2021 16:56:32 +0000 Subject: KVM: stats: Add halt_wait_ns stats for all architectures Add simple stats halt_wait_ns to record the time a VCPU has spent on waiting for all architectures (not just powerpc). Signed-off-by: Jing Zhang Message-Id: <20210802165633.1866976-5-jingzhangos@google.com> Signed-off-by: Paolo Bonzini --- arch/powerpc/include/asm/kvm_host.h | 1 - arch/powerpc/kvm/book3s.c | 1 - arch/powerpc/kvm/book3s_hv.c | 2 +- arch/powerpc/kvm/booke.c | 1 - include/linux/kvm_host.h | 3 ++- include/linux/kvm_types.h | 1 + virt/kvm/kvm_main.c | 4 ++++ 7 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 9f52f282b1aa..4931d03e5799 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -103,7 +103,6 @@ struct kvm_vcpu_stat { u64 emulated_inst_exits; u64 dec_exits; u64 ext_intr_exits; - u64 halt_wait_ns; u64 halt_successful_wait; u64 dbell_exits; u64 gdbell_exits; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 5cc6e90095b0..b785f6772391 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -69,7 +69,6 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, emulated_inst_exits), STATS_DESC_COUNTER(VCPU, dec_exits), STATS_DESC_COUNTER(VCPU, ext_intr_exits), - STATS_DESC_TIME_NSEC(VCPU, halt_wait_ns), STATS_DESC_COUNTER(VCPU, halt_successful_wait), STATS_DESC_COUNTER(VCPU, dbell_exits), STATS_DESC_COUNTER(VCPU, gdbell_exits), diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 1d1fcc290fca..813ca155561b 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4144,7 +4144,7 @@ out: /* Attribute wait time */ if (do_sleep) { - vc->runner->stat.halt_wait_ns += + vc->runner->stat.generic.halt_wait_ns += ktime_to_ns(cur) - ktime_to_ns(start_wait); /* Attribute failed poll time */ if (vc->halt_poll_ns) diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 5ed6c235e059..977801c83aff 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -67,7 +67,6 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, emulated_inst_exits), STATS_DESC_COUNTER(VCPU, dec_exits), STATS_DESC_COUNTER(VCPU, ext_intr_exits), - STATS_DESC_TIME_NSEC(VCPU, halt_wait_ns), STATS_DESC_COUNTER(VCPU, halt_successful_wait), STATS_DESC_COUNTER(VCPU, dbell_exits), STATS_DESC_COUNTER(VCPU, gdbell_exits), diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 09fc0274b1eb..58a8ffee265e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1452,7 +1452,8 @@ struct _kvm_stats_desc { STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid), \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \ - STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns) + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns) extern struct dentry *kvm_debugfs_dir; diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index ed6a985c5680..291ef55125b2 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -87,6 +87,7 @@ struct kvm_vcpu_stat_generic { u64 halt_wakeup; u64 halt_poll_success_ns; u64 halt_poll_fail_ns; + u64 halt_wait_ns; }; #define KVM_STATS_NAME_SIZE 48 diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8563d9b725af..e6fc579bb454 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3241,6 +3241,10 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) } finish_rcuwait(&vcpu->wait); cur = ktime_get(); + if (waited) { + vcpu->stat.generic.halt_wait_ns += + ktime_to_ns(cur) - ktime_to_ns(poll_end); + } out: kvm_arch_vcpu_unblocking(vcpu); block_ns = ktime_to_ns(cur) - ktime_to_ns(start); -- cgit v1.2.3 From 8ccba534a1a5c6565220c81113d6157571f380cb Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Mon, 2 Aug 2021 16:56:33 +0000 Subject: KVM: stats: Add halt polling related histogram stats Add three log histogram stats to record the distribution of time spent on successful polling, failed polling and VCPU wait. halt_poll_success_hist: Distribution of spent time for a successful poll. halt_poll_fail_hist: Distribution of spent time for a failed poll. halt_wait_hist: Distribution of time a VCPU has spent on waiting. Signed-off-by: Jing Zhang Message-Id: <20210802165633.1866976-6-jingzhangos@google.com> Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/book3s_hv.c | 16 ++++++++++++++-- include/linux/kvm_host.h | 8 +++++++- include/linux/kvm_types.h | 5 +++++ virt/kvm/kvm_main.c | 12 ++++++++++++ 4 files changed, 38 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 813ca155561b..6d63c8e6d4f0 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4146,17 +4146,29 @@ out: if (do_sleep) { vc->runner->stat.generic.halt_wait_ns += ktime_to_ns(cur) - ktime_to_ns(start_wait); + KVM_STATS_LOG_HIST_UPDATE( + vc->runner->stat.generic.halt_wait_hist, + ktime_to_ns(cur) - ktime_to_ns(start_wait)); /* Attribute failed poll time */ - if (vc->halt_poll_ns) + if (vc->halt_poll_ns) { vc->runner->stat.generic.halt_poll_fail_ns += ktime_to_ns(start_wait) - ktime_to_ns(start_poll); + KVM_STATS_LOG_HIST_UPDATE( + vc->runner->stat.generic.halt_poll_fail_hist, + ktime_to_ns(start_wait) - + ktime_to_ns(start_poll)); + } } else { /* Attribute successful poll time */ - if (vc->halt_poll_ns) + if (vc->halt_poll_ns) { vc->runner->stat.generic.halt_poll_success_ns += ktime_to_ns(cur) - ktime_to_ns(start_poll); + KVM_STATS_LOG_HIST_UPDATE( + vc->runner->stat.generic.halt_poll_success_hist, + ktime_to_ns(cur) - ktime_to_ns(start_poll)); + } } /* Adjust poll time */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 58a8ffee265e..e4d712e9f760 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1453,7 +1453,13 @@ struct _kvm_stats_desc { STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns), \ - STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns) + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns), \ + STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_success_hist, \ + HALT_POLL_HIST_COUNT), \ + STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ + HALT_POLL_HIST_COUNT), \ + STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ + HALT_POLL_HIST_COUNT) extern struct dentry *kvm_debugfs_dir; diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 291ef55125b2..de7fb5f364d8 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -76,6 +76,8 @@ struct kvm_mmu_memory_cache { }; #endif +#define HALT_POLL_HIST_COUNT 32 + struct kvm_vm_stat_generic { u64 remote_tlb_flush; }; @@ -88,6 +90,9 @@ struct kvm_vcpu_stat_generic { u64 halt_poll_success_ns; u64 halt_poll_fail_ns; u64 halt_wait_ns; + u64 halt_poll_success_hist[HALT_POLL_HIST_COUNT]; + u64 halt_poll_fail_hist[HALT_POLL_HIST_COUNT]; + u64 halt_wait_hist[HALT_POLL_HIST_COUNT]; }; #define KVM_STATS_NAME_SIZE 48 diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e6fc579bb454..3e67c93ca403 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3222,13 +3222,23 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) ++vcpu->stat.generic.halt_successful_poll; if (!vcpu_valid_wakeup(vcpu)) ++vcpu->stat.generic.halt_poll_invalid; + + KVM_STATS_LOG_HIST_UPDATE( + vcpu->stat.generic.halt_poll_success_hist, + ktime_to_ns(ktime_get()) - + ktime_to_ns(start)); goto out; } cpu_relax(); poll_end = cur = ktime_get(); } while (kvm_vcpu_can_poll(cur, stop)); + + KVM_STATS_LOG_HIST_UPDATE( + vcpu->stat.generic.halt_poll_fail_hist, + ktime_to_ns(ktime_get()) - ktime_to_ns(start)); } + prepare_to_rcuwait(&vcpu->wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); @@ -3244,6 +3254,8 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) if (waited) { vcpu->stat.generic.halt_wait_ns += ktime_to_ns(cur) - ktime_to_ns(poll_end); + KVM_STATS_LOG_HIST_UPDATE(vcpu->stat.generic.halt_wait_hist, + ktime_to_ns(cur) - ktime_to_ns(poll_end)); } out: kvm_arch_vcpu_unblocking(vcpu); -- cgit v1.2.3 From 76f3c032adad86aad26f8ad3eebc993b4ba32138 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 18 Aug 2021 20:59:31 +0200 Subject: PCI/VPD: Add pci_vpd_alloc() Several users of the VPD API use a fixed-size buffer and read the VPD into it for further usage. This requires special handling for the case that the buffer isn't big enough to hold the full VPD data. Also the buffer is often allocated on the stack, which isn't too nice. Add pci_vpd_alloc() to dynamically allocate buffer of the correct size and read VPD into it. Link: https://lore.kernel.org/r/955ff598-0021-8446-f856-0c2c077635d7@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- drivers/pci/vpd.c | 26 ++++++++++++++++++++++++++ include/linux/pci.h | 9 +++++++++ 2 files changed, 35 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 3b0425fb49f5..7c3a097379bb 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -270,6 +270,32 @@ const struct attribute_group pci_dev_vpd_attr_group = { .is_bin_visible = vpd_attr_is_visible, }; +void *pci_vpd_alloc(struct pci_dev *dev, unsigned int *size) +{ + unsigned int len = dev->vpd.len; + void *buf; + int cnt; + + if (!dev->vpd.cap) + return ERR_PTR(-ENODEV); + + buf = kmalloc(len, GFP_KERNEL); + if (!buf) + return ERR_PTR(-ENOMEM); + + cnt = pci_read_vpd(dev, 0, len, buf); + if (cnt != len) { + kfree(buf); + return ERR_PTR(-EIO); + } + + if (size) + *size = len; + + return buf; +} +EXPORT_SYMBOL_GPL(pci_vpd_alloc); + int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt) { int i = 0; diff --git a/include/linux/pci.h b/include/linux/pci.h index e752cc39a1fe..8c681e24be8b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2330,6 +2330,15 @@ static inline u8 pci_vpd_info_field_size(const u8 *info_field) return info_field[2]; } +/** + * pci_vpd_alloc - Allocate buffer and read VPD into it + * @dev: PCI device + * @size: pointer to field where VPD length is returned + * + * Returns pointer to allocated buffer or an ERR_PTR in case of failure + */ +void *pci_vpd_alloc(struct pci_dev *dev, unsigned int *size); + /** * pci_vpd_find_tag - Locates the Resource Data Type tag provided * @buf: Pointer to buffered vpd data -- cgit v1.2.3 From 9e515c9f6c0b6f0ace6f5cf2202b527d745b494d Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 18 Aug 2021 21:00:57 +0200 Subject: PCI/VPD: Add pci_vpd_find_ro_info_keyword() All users of pci_vpd_find_info_keyword() are interested in the VPD RO section only. In addition all calls are followed by the same activities to calculate start of tag data area and size of the data area. Add pci_vpd_find_ro_info_keyword() that combines these functionalities. pci_vpd_find_info_keyword() can be phased out once all users are converted. [bhelgaas: split pci_vpd_check_csum() to separate patch] Link: https://lore.kernel.org/r/1643bd7a-088e-1028-c9b0-9d112cf48d63@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- drivers/pci/vpd.c | 33 +++++++++++++++++++++++++++++++++ include/linux/pci.h | 13 +++++++++++++ 2 files changed, 46 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 7c3a097379bb..b1d012900f1e 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -380,6 +380,39 @@ ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void } EXPORT_SYMBOL(pci_write_vpd); +int pci_vpd_find_ro_info_keyword(const void *buf, unsigned int len, + const char *kw, unsigned int *size) +{ + int ro_start, infokw_start; + unsigned int ro_len, infokw_size; + + ro_start = pci_vpd_find_tag(buf, len, PCI_VPD_LRDT_RO_DATA); + if (ro_start < 0) + return ro_start; + + ro_len = pci_vpd_lrdt_size(buf + ro_start); + ro_start += PCI_VPD_LRDT_TAG_SIZE; + + if (ro_start + ro_len > len) + ro_len = len - ro_start; + + infokw_start = pci_vpd_find_info_keyword(buf, ro_start, ro_len, kw); + if (infokw_start < 0) + return infokw_start; + + infokw_size = pci_vpd_info_field_size(buf + infokw_start); + infokw_start += PCI_VPD_INFO_FLD_HDR_SIZE; + + if (infokw_start + infokw_size > len) + return -EINVAL; + + if (size) + *size = infokw_size; + + return infokw_start; +} +EXPORT_SYMBOL_GPL(pci_vpd_find_ro_info_keyword); + #ifdef CONFIG_PCI_QUIRKS /* * Quirk non-zero PCI functions to route VPD access through function 0 for diff --git a/include/linux/pci.h b/include/linux/pci.h index 8c681e24be8b..9e3b60963a52 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2363,6 +2363,19 @@ int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt); int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, unsigned int len, const char *kw); +/** + * pci_vpd_find_ro_info_keyword - Locate info field keyword in VPD RO section + * @buf: Pointer to buffered VPD data + * @len: The length of the buffer area in which to search + * @kw: The keyword to search for + * @size: Pointer to field where length of found keyword data is returned + * + * Returns the index of the information field keyword data or -ENOENT if + * not found. + */ +int pci_vpd_find_ro_info_keyword(const void *buf, unsigned int len, + const char *kw, unsigned int *size); + /* PCI <-> OF binding helpers */ #ifdef CONFIG_OF struct device_node; -- cgit v1.2.3 From 6107e5cb907cffc5576cc1297847f9fc69a8d5d9 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 20 Aug 2021 15:32:42 -0500 Subject: PCI/VPD: Add pci_vpd_check_csum() VPD checksum information and checksum calculation are specified by PCIe r5.0, sec 6.28.2.2. Therefore checksum handling can and should be moved into the PCI VPD core. Add pci_vpd_check_csum() to validate the VPD checksum. [bhelgaas: split to separate patch] Link: https://lore.kernel.org/r/1643bd7a-088e-1028-c9b0-9d112cf48d63@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- drivers/pci/vpd.c | 23 +++++++++++++++++++++++ include/linux/pci.h | 9 +++++++++ 2 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index b1d012900f1e..01e57594781e 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -413,6 +413,29 @@ int pci_vpd_find_ro_info_keyword(const void *buf, unsigned int len, } EXPORT_SYMBOL_GPL(pci_vpd_find_ro_info_keyword); +int pci_vpd_check_csum(const void *buf, unsigned int len) +{ + const u8 *vpd = buf; + unsigned int size; + u8 csum = 0; + int rv_start; + + rv_start = pci_vpd_find_ro_info_keyword(buf, len, PCI_VPD_RO_KEYWORD_CHKSUM, &size); + if (rv_start == -ENOENT) /* no checksum in VPD */ + return 1; + else if (rv_start < 0) + return rv_start; + + if (!size) + return -EINVAL; + + while (rv_start >= 0) + csum += vpd[rv_start--]; + + return csum ? -EILSEQ : 0; +} +EXPORT_SYMBOL_GPL(pci_vpd_check_csum); + #ifdef CONFIG_PCI_QUIRKS /* * Quirk non-zero PCI functions to route VPD access through function 0 for diff --git a/include/linux/pci.h b/include/linux/pci.h index 9e3b60963a52..827b7eefd550 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2376,6 +2376,15 @@ int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, int pci_vpd_find_ro_info_keyword(const void *buf, unsigned int len, const char *kw, unsigned int *size); +/** + * pci_vpd_check_csum - Check VPD checksum + * @buf: Pointer to buffered VPD data + * @len: VPD size + * + * Returns 1 if VPD has no checksum, otherwise 0 or an errno + */ +int pci_vpd_check_csum(const void *buf, unsigned int len); + /* PCI <-> OF binding helpers */ #ifdef CONFIG_OF struct device_node; -- cgit v1.2.3 From f0ab00174eb7574732737fc0734d4b406aed6231 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 2 Aug 2021 17:17:28 -0500 Subject: PCI: Make saved capability state private to core Interfaces and structs for saving and restoring PCI Capability state were declared in include/linux/pci.h, but aren't needed outside drivers/pci/. Move these to drivers/pci/pci.h: struct pci_cap_saved_data struct pci_cap_saved_state void pci_allocate_cap_save_buffers() void pci_free_cap_save_buffers() int pci_add_cap_save_buffer() int pci_add_ext_cap_save_buffer() struct pci_cap_saved_state *pci_find_saved_cap() struct pci_cap_saved_state *pci_find_saved_ext_cap() Link: https://lore.kernel.org/r/20210802221728.1469304-1-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Alex Williamson --- drivers/pci/pci.h | 23 +++++++++++++++++++++-- include/linux/pci.h | 18 ------------------ 2 files changed, 21 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 93dcdd431072..288126062a38 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -37,6 +37,27 @@ int pci_probe_reset_function(struct pci_dev *dev); int pci_bridge_secondary_bus_reset(struct pci_dev *dev); int pci_bus_error_reset(struct pci_dev *dev); +struct pci_cap_saved_data { + u16 cap_nr; + bool cap_extended; + unsigned int size; + u32 data[]; +}; + +struct pci_cap_saved_state { + struct hlist_node next; + struct pci_cap_saved_data cap; +}; + +void pci_allocate_cap_save_buffers(struct pci_dev *dev); +void pci_free_cap_save_buffers(struct pci_dev *dev); +int pci_add_cap_save_buffer(struct pci_dev *dev, char cap, unsigned int size); +int pci_add_ext_cap_save_buffer(struct pci_dev *dev, + u16 cap, unsigned int size); +struct pci_cap_saved_state *pci_find_saved_cap(struct pci_dev *dev, char cap); +struct pci_cap_saved_state *pci_find_saved_ext_cap(struct pci_dev *dev, + u16 cap); + #define PCI_PM_D2_DELAY 200 /* usec; see PCIe r4.0, sec 5.9.1 */ #define PCI_PM_D3HOT_WAIT 10 /* msec */ #define PCI_PM_D3COLD_WAIT 100 /* msec */ @@ -100,8 +121,6 @@ void pci_pm_init(struct pci_dev *dev); void pci_ea_init(struct pci_dev *dev); void pci_msi_init(struct pci_dev *dev); void pci_msix_init(struct pci_dev *dev); -void pci_allocate_cap_save_buffers(struct pci_dev *dev); -void pci_free_cap_save_buffers(struct pci_dev *dev); bool pci_bridge_d3_possible(struct pci_dev *dev); void pci_bridge_d3_update(struct pci_dev *dev); void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index 540b377ca8f6..fd35327812af 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -288,18 +288,6 @@ enum pci_bus_speed { enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev); enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev); -struct pci_cap_saved_data { - u16 cap_nr; - bool cap_extended; - unsigned int size; - u32 data[]; -}; - -struct pci_cap_saved_state { - struct hlist_node next; - struct pci_cap_saved_data cap; -}; - struct irq_affinity; struct pcie_link_state; struct pci_vpd; @@ -1278,12 +1266,6 @@ int pci_load_saved_state(struct pci_dev *dev, struct pci_saved_state *state); int pci_load_and_free_saved_state(struct pci_dev *dev, struct pci_saved_state **state); -struct pci_cap_saved_state *pci_find_saved_cap(struct pci_dev *dev, char cap); -struct pci_cap_saved_state *pci_find_saved_ext_cap(struct pci_dev *dev, - u16 cap); -int pci_add_cap_save_buffer(struct pci_dev *dev, char cap, unsigned int size); -int pci_add_ext_cap_save_buffer(struct pci_dev *dev, - u16 cap, unsigned int size); int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); -- cgit v1.2.3 From ca32b5310a1a3835f81f498367f1bb7450c8b67b Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Tue, 13 Jul 2021 15:22:36 +0800 Subject: PCI: Optimize pci_resource_len() to reduce kernel size pci_resource_end() can be 0 only when pci_resource_start() is 0. Otherwise, it is definitely an error. In this case, pci_resource_len() should be regarded as 0. Therefore, determining whether pci_resource_start() and pci_resource_end() are both 0 can be reduced to determining only whether pci_resource_end() is 0. Although only one condition judgment is reduced, the macro function pci_resource_len() is widely referenced in the kernel. I used defconfig to compile the latest kernel on X86, and its binary code size was reduced by about 3KB. Before: [ 2] .rela.text RELA 0000000000000000 093bfcb0 0000000001a67168 0000000000000018 I 68 1 8 After: [ 2] .rela.text RELA 0000000000000000 093bfcb0 0000000001a66598 0000000000000018 I 68 1 8 Link: https://lore.kernel.org/r/20210713072236.3043-1-thunder.leizhen@huawei.com Signed-off-by: Zhen Lei Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 540b377ca8f6..23ef1a15eb5d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1881,9 +1881,7 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma); #define pci_resource_end(dev, bar) ((dev)->resource[(bar)].end) #define pci_resource_flags(dev, bar) ((dev)->resource[(bar)].flags) #define pci_resource_len(dev,bar) \ - ((pci_resource_start((dev), (bar)) == 0 && \ - pci_resource_end((dev), (bar)) == \ - pci_resource_start((dev), (bar))) ? 0 : \ + ((pci_resource_end((dev), (bar)) == 0) ? 0 : \ \ (pci_resource_end((dev), (bar)) - \ pci_resource_start((dev), (bar)) + 1)) -- cgit v1.2.3 From 817f9916a6e96ae43acdd4e75459ef4f92d96eb1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 13 Aug 2021 18:36:19 +0300 Subject: PCI: Sync __pci_register_driver() stub for CONFIG_PCI=n The CONFIG_PCI=y case got a new parameter long time ago. Sync the stub as well. [bhelgaas: add parameter names] Fixes: 725522b5453d ("PCI: add the sysfs driver name to all modules") Link: https://lore.kernel.org/r/20210813153619.89574-1-andriy.shevchenko@linux.intel.com Reported-by: kernel test robot Signed-off-by: Andy Shevchenko Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index fd35327812af..a662f6c1f120 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1722,8 +1722,9 @@ static inline void pci_disable_device(struct pci_dev *dev) { } static inline int pcim_enable_device(struct pci_dev *pdev) { return -EIO; } static inline int pci_assign_resource(struct pci_dev *dev, int i) { return -EBUSY; } -static inline int __pci_register_driver(struct pci_driver *drv, - struct module *owner) +static inline int __must_check __pci_register_driver(struct pci_driver *drv, + struct module *owner, + const char *mod_name) { return 0; } static inline int pci_register_driver(struct pci_driver *drv) { return 0; } -- cgit v1.2.3 From d2587c57ffd8dcad04171dfd203dcc4ff98e4782 Mon Sep 17 00:00:00 2001 From: Angus Ainslie Date: Thu, 12 Aug 2021 09:52:17 -0700 Subject: brcmfmac: add 43752 SDIO ids and initialization Add HW and SDIO ids for use with the SparkLan AP6275S Add the firmware mapping structures for the BRCM43752 chipset. The 43752 needs some things setup similar to the 43012 chipset. The WATERMARK shows better performance when initialized to the 4373 value. Signed-off-by: Angus Ainslie Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20210812165218.2508258-2-angus@akkea.ca --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c | 1 + drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c | 3 +++ drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c | 8 ++++++-- drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h | 1 + include/linux/mmc/sdio_ids.h | 1 + 5 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index 720c7fec22ac..ac02244a6fdf 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -991,6 +991,7 @@ static const struct sdio_device_id brcmf_sdmmc_ids[] = { BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4359), BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373), BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_43012), + BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752), BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_89359), { /* end: all zeroes */ } }; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c index 4faab0170ffa..1ee49f9e325d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c @@ -729,6 +729,8 @@ static u32 brcmf_chip_tcm_rambase(struct brcmf_chip_priv *ci) case BRCM_CC_4364_CHIP_ID: case CY_CC_4373_CHIP_ID: return 0x160000; + case CY_CC_43752_CHIP_ID: + return 0x170000; default: brcmf_err("unknown chip: %s\n", ci->pub.name); break; @@ -1421,6 +1423,7 @@ bool brcmf_chip_sr_capable(struct brcmf_chip *pub) reg = chip->ops->read32(chip->ctx, addr); return (reg & CC_SR_CTL0_ENABLE_MASK) != 0; case BRCM_CC_4359_CHIP_ID: + case CY_CC_43752_CHIP_ID: case CY_CC_43012_CHIP_ID: addr = CORE_CC_REG(pmu->base, retention_ctl); reg = chip->ops->read32(chip->ctx, addr); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index baf36d79ed43..8effeb7a7269 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -625,6 +625,7 @@ BRCMF_FW_CLM_DEF(4356, "brcmfmac4356-sdio"); BRCMF_FW_DEF(4359, "brcmfmac4359-sdio"); BRCMF_FW_CLM_DEF(4373, "brcmfmac4373-sdio"); BRCMF_FW_CLM_DEF(43012, "brcmfmac43012-sdio"); +BRCMF_FW_CLM_DEF(43752, "brcmfmac43752-sdio"); /* firmware config files */ MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-sdio.*.txt"); @@ -655,7 +656,8 @@ static const struct brcmf_firmware_mapping brcmf_sdio_fwnames[] = { BRCMF_FW_ENTRY(BRCM_CC_4356_CHIP_ID, 0xFFFFFFFF, 4356), BRCMF_FW_ENTRY(BRCM_CC_4359_CHIP_ID, 0xFFFFFFFF, 4359), BRCMF_FW_ENTRY(CY_CC_4373_CHIP_ID, 0xFFFFFFFF, 4373), - BRCMF_FW_ENTRY(CY_CC_43012_CHIP_ID, 0xFFFFFFFF, 43012) + BRCMF_FW_ENTRY(CY_CC_43012_CHIP_ID, 0xFFFFFFFF, 43012), + BRCMF_FW_ENTRY(CY_CC_43752_CHIP_ID, 0xFFFFFFFF, 43752) }; #define TXCTL_CREDITS 2 @@ -3421,7 +3423,8 @@ err: static bool brcmf_sdio_aos_no_decode(struct brcmf_sdio *bus) { - if (bus->ci->chip == CY_CC_43012_CHIP_ID) + if (bus->ci->chip == CY_CC_43012_CHIP_ID || + bus->ci->chip == CY_CC_43752_CHIP_ID) return true; else return false; @@ -4266,6 +4269,7 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err, switch (sdiod->func1->device) { case SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373: + case SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752: brcmf_dbg(INFO, "set F2 watermark to 0x%x*4 bytes\n", CY_4373_F2_WATERMARK); brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK, diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h index 00309b272a0e..9d81320164ce 100644 --- a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h +++ b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h @@ -52,6 +52,7 @@ #define BRCM_CC_4371_CHIP_ID 0x4371 #define CY_CC_4373_CHIP_ID 0x4373 #define CY_CC_43012_CHIP_ID 43012 +#define CY_CC_43752_CHIP_ID 43752 /* USB Device IDs */ #define BRCM_USB_43143_DEVICE_ID 0xbd1e diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 12036619346c..a85c9f0bd470 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -75,6 +75,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 #define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752 0xaae8 #define SDIO_VENDOR_ID_MARVELL 0x02df #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 -- cgit v1.2.3 From 60bcd91aafd22ef62cef9ae2037fa2e1d4da2fb3 Mon Sep 17 00:00:00 2001 From: Grzegorz Jaszczyk Date: Fri, 18 Jun 2021 21:50:32 +0200 Subject: watchdog: introduce watchdog_dev_suspend/resume The watchdog drivers often disable wdog clock during suspend and then enable it again during resume. Nevertheless the ping worker is still running and can issue low-level ping while the wdog clock is disabled causing the system hang. To prevent such condition register pm notifier in the watchdog core which will call watchdog_dev_suspend/resume and actually cancel ping worker during suspend and restore it back, if needed, during resume. Signed-off-by: Grzegorz Jaszczyk Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20210618195033.3209598-2-grzegorz.jaszczyk@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/watchdog_core.c | 37 +++++++++++++++++++++++++++++++ drivers/watchdog/watchdog_dev.c | 47 ++++++++++++++++++++++++++++++++++++++++ include/linux/watchdog.h | 10 +++++++++ 3 files changed, 94 insertions(+) (limited to 'include/linux') diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c index 5df0a22e2cb4..3fe8a7edc252 100644 --- a/drivers/watchdog/watchdog_core.c +++ b/drivers/watchdog/watchdog_core.c @@ -34,6 +34,7 @@ #include /* For ida_* macros */ #include /* For IS_ERR macros */ #include /* For of_get_timeout_sec */ +#include #include "watchdog_core.h" /* For watchdog_dev_register/... */ @@ -185,6 +186,33 @@ static int watchdog_restart_notifier(struct notifier_block *nb, return NOTIFY_DONE; } +static int watchdog_pm_notifier(struct notifier_block *nb, unsigned long mode, + void *data) +{ + struct watchdog_device *wdd; + int ret = 0; + + wdd = container_of(nb, struct watchdog_device, pm_nb); + + switch (mode) { + case PM_HIBERNATION_PREPARE: + case PM_RESTORE_PREPARE: + case PM_SUSPEND_PREPARE: + ret = watchdog_dev_suspend(wdd); + break; + case PM_POST_HIBERNATION: + case PM_POST_RESTORE: + case PM_POST_SUSPEND: + ret = watchdog_dev_resume(wdd); + break; + } + + if (ret) + return NOTIFY_BAD; + + return NOTIFY_DONE; +} + /** * watchdog_set_restart_priority - Change priority of restart handler * @wdd: watchdog device @@ -292,6 +320,15 @@ static int __watchdog_register_device(struct watchdog_device *wdd) wdd->id, ret); } + if (test_bit(WDOG_NO_PING_ON_SUSPEND, &wdd->status)) { + wdd->pm_nb.notifier_call = watchdog_pm_notifier; + + ret = register_pm_notifier(&wdd->pm_nb); + if (ret) + pr_warn("watchdog%d: Cannot register pm handler (%d)\n", + wdd->id, ret); + } + return 0; } diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index f408967ff1a4..597cf16ea4ba 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -1228,6 +1228,53 @@ void __exit watchdog_dev_exit(void) kthread_destroy_worker(watchdog_kworker); } +int watchdog_dev_suspend(struct watchdog_device *wdd) +{ + struct watchdog_core_data *wd_data = wdd->wd_data; + int ret = 0; + + if (!wdd->wd_data) + return -ENODEV; + + /* ping for the last time before suspend */ + mutex_lock(&wd_data->lock); + if (watchdog_worker_should_ping(wd_data)) + ret = __watchdog_ping(wd_data->wdd); + mutex_unlock(&wd_data->lock); + + if (ret) + return ret; + + /* + * make sure that watchdog worker will not kick in when the wdog is + * suspended + */ + hrtimer_cancel(&wd_data->timer); + kthread_cancel_work_sync(&wd_data->work); + + return 0; +} + +int watchdog_dev_resume(struct watchdog_device *wdd) +{ + struct watchdog_core_data *wd_data = wdd->wd_data; + int ret = 0; + + if (!wdd->wd_data) + return -ENODEV; + + /* + * __watchdog_ping will also retrigger hrtimer and therefore restore the + * ping worker if needed. + */ + mutex_lock(&wd_data->lock); + if (watchdog_worker_should_ping(wd_data)) + ret = __watchdog_ping(wd_data->wdd); + mutex_unlock(&wd_data->lock); + + return ret; +} + module_param(handle_boot_enabled, bool, 0444); MODULE_PARM_DESC(handle_boot_enabled, "Watchdog core auto-updates boot enabled watchdogs before userspace takes over (default=" diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 9b19e6bb68b5..99660197a36c 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -107,6 +107,7 @@ struct watchdog_device { unsigned int max_hw_heartbeat_ms; struct notifier_block reboot_nb; struct notifier_block restart_nb; + struct notifier_block pm_nb; void *driver_data; struct watchdog_core_data *wd_data; unsigned long status; @@ -116,6 +117,7 @@ struct watchdog_device { #define WDOG_STOP_ON_REBOOT 2 /* Should be stopped on reboot */ #define WDOG_HW_RUNNING 3 /* True if HW watchdog running */ #define WDOG_STOP_ON_UNREGISTER 4 /* Should be stopped on unregister */ +#define WDOG_NO_PING_ON_SUSPEND 5 /* Ping worker should be stopped on suspend */ struct list_head deferred; }; @@ -156,6 +158,12 @@ static inline void watchdog_stop_on_unregister(struct watchdog_device *wdd) set_bit(WDOG_STOP_ON_UNREGISTER, &wdd->status); } +/* Use the following function to stop the wdog ping worker when suspending */ +static inline void watchdog_stop_ping_on_suspend(struct watchdog_device *wdd) +{ + set_bit(WDOG_NO_PING_ON_SUSPEND, &wdd->status); +} + /* Use the following function to check if a timeout value is invalid */ static inline bool watchdog_timeout_invalid(struct watchdog_device *wdd, unsigned int t) { @@ -209,6 +217,8 @@ extern int watchdog_init_timeout(struct watchdog_device *wdd, unsigned int timeout_parm, struct device *dev); extern int watchdog_register_device(struct watchdog_device *); extern void watchdog_unregister_device(struct watchdog_device *); +int watchdog_dev_suspend(struct watchdog_device *wdd); +int watchdog_dev_resume(struct watchdog_device *wdd); int watchdog_set_last_hw_keepalive(struct watchdog_device *, unsigned int); -- cgit v1.2.3 From 6e7c1770a212239e88ec01ddc7a741505bfd10e5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jul 2021 16:23:21 -0400 Subject: fs: simplify get_filesystem_list / get_all_fs_names Just output the '\0' separate list of supported file systems for block devices directly rather than going through a pointless round of string manipulation. Based on an earlier patch from Al Viro . Vivek: Modified list_bdev_fs_names() and split_fs_names() to return number of null terminted strings to caller. Callers now use that information to loop through all the strings instead of relying on one extra null char being present at the end. Signed-off-by: Christoph Hellwig Signed-off-by: Vivek Goyal Signed-off-by: Al Viro --- fs/filesystems.c | 27 +++++++++++++++++---------- include/linux/fs.h | 2 +- init/do_mounts.c | 49 +++++++++++++++++++++---------------------------- 3 files changed, 39 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/fs/filesystems.c b/fs/filesystems.c index 90b8d879fbaf..58b9067b2391 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -209,21 +209,28 @@ SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2) } #endif -int __init get_filesystem_list(char *buf) +int __init list_bdev_fs_names(char *buf, size_t size) { - int len = 0; - struct file_system_type * tmp; + struct file_system_type *p; + size_t len; + int count = 0; read_lock(&file_systems_lock); - tmp = file_systems; - while (tmp && len < PAGE_SIZE - 80) { - len += sprintf(buf+len, "%s\t%s\n", - (tmp->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev", - tmp->name); - tmp = tmp->next; + for (p = file_systems; p; p = p->next) { + if (!(p->fs_flags & FS_REQUIRES_DEV)) + continue; + len = strlen(p->name) + 1; + if (len > size) { + pr_warn("%s: truncating file system list\n", __func__); + break; + } + memcpy(buf, p->name, len); + buf += len; + size -= len; + count++; } read_unlock(&file_systems_lock); - return len; + return count; } #ifdef CONFIG_PROC_FS diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..c76dfc01cf9d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3622,7 +3622,7 @@ int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_inodes(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int __init get_filesystem_list(char *buf); +int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) diff --git a/init/do_mounts.c b/init/do_mounts.c index bdeb90b8d669..9b4a1f877e47 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -338,32 +338,22 @@ __setup("rootflags=", root_data_setup); __setup("rootfstype=", fs_names_setup); __setup("rootdelay=", root_delay_setup); -static void __init split_fs_names(char *page, char *names) +static int __init split_fs_names(char *page, char *names) { - strcpy(page, root_fs_names); - while (*page++) { - if (page[-1] == ',') - page[-1] = '\0'; - } - *page = '\0'; -} - -static void __init get_all_fs_names(char *page) -{ - int len = get_filesystem_list(page); - char *s = page, *p, *next; + int count = 0; + char *p = page; - page[len] = '\0'; - for (p = page - 1; p; p = next) { - next = strchr(++p, '\n'); - if (*p++ != '\t') - continue; - while ((*s++ = *p++) != '\n') - ; - s[-1] = '\0'; + strcpy(p, root_fs_names); + while (*p++) { + if (p[-1] == ',') + p[-1] = '\0'; } + *p = '\0'; + + for (p = page; *p; p += strlen(p)+1) + count++; - *s = '\0'; + return count; } static int __init do_mount_root(const char *name, const char *fs, @@ -409,15 +399,16 @@ void __init mount_block_root(char *name, int flags) char *fs_names = page_address(page); char *p; char b[BDEVNAME_SIZE]; + int num_fs, i; scnprintf(b, BDEVNAME_SIZE, "unknown-block(%u,%u)", MAJOR(ROOT_DEV), MINOR(ROOT_DEV)); if (root_fs_names) - split_fs_names(fs_names, root_fs_names); + num_fs = split_fs_names(fs_names, root_fs_names); else - get_all_fs_names(fs_names); + num_fs = list_bdev_fs_names(fs_names, PAGE_SIZE); retry: - for (p = fs_names; *p; p += strlen(p)+1) { + for (i = 0, p = fs_names; i < num_fs; i++, p += strlen(p)+1) { int err = do_mount_root(name, p, flags, root_mount_data); switch (err) { case 0: @@ -450,7 +441,7 @@ retry: printk("List of all partitions:\n"); printk_all_partitions(); printk("No filesystem could mount root, tried: "); - for (p = fs_names; *p; p += strlen(p)+1) + for (i = 0, p = fs_names; i < num_fs; i++, p += strlen(p)+1) printk(" %s", p); printk("\n"); panic("VFS: Unable to mount root fs on %s", b); @@ -551,13 +542,15 @@ static int __init mount_nodev_root(void) { char *fs_names, *fstype; int err = -EINVAL; + int num_fs, i; fs_names = (void *)__get_free_page(GFP_KERNEL); if (!fs_names) return -EINVAL; - split_fs_names(fs_names, root_fs_names); + num_fs = split_fs_names(fs_names, root_fs_names); - for (fstype = fs_names; *fstype; fstype += strlen(fstype) + 1) { + for (i = 0, fstype = fs_names; i < num_fs; + i++, fstype += strlen(fstype) + 1) { if (!fs_is_nodev(fstype)) continue; err = do_mount_root(root_device_name, fstype, root_mountflags, -- cgit v1.2.3 From e5e26d80840b69c1bcea4f5b0cb7ed4026a8f6a3 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 21 Aug 2021 00:58:21 +0200 Subject: gpio: max730x: Use the right include despite the placement of the header, is used by drivers/gpio/gpio-max730*. The include needs struct gpio_chip and needs to include not the legacy include. Signed-off-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- include/linux/spi/max7301.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/max7301.h b/include/linux/spi/max7301.h index 433c20e2f46e..21449067aedb 100644 --- a/include/linux/spi/max7301.h +++ b/include/linux/spi/max7301.h @@ -2,7 +2,7 @@ #ifndef LINUX_SPI_MAX7301_H #define LINUX_SPI_MAX7301_H -#include +#include /* * Some registers must be read back to modify. -- cgit v1.2.3 From 15d82ca23c996d50062286d27ed6a42a8105c04a Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 27 Jul 2021 02:06:50 +0800 Subject: PCI: Introduce domain_nr in pci_host_bridge Currently we retrieve the PCI domain number of the host bridge from the bus sysdata (or pci_config_window if PCI_DOMAINS_GENERIC=y). Actually we have the information at PCI host bridge probing time, and it makes sense that we store it into pci_host_bridge. One benefit of doing so is the requirement for supporting PCI on Hyper-V for ARM64, because the host bridge of Hyper-V doesn't have pci_config_window, whereas ARM64 is a PCI_DOMAINS_GENERIC=y arch, so we cannot retrieve the PCI domain number from pci_config_window on ARM64 Hyper-V guest. As the preparation for ARM64 Hyper-V PCI support, we introduce the domain_nr in pci_host_bridge and a sentinel value to allow drivers to set domain numbers properly at probing time. Currently CONFIG_PCI_DOMAINS_GENERIC=y archs are only users of this newly-introduced field. Link: https://lore.kernel.org/r/20210726180657.142727-2-boqun.feng@gmail.com Signed-off-by: Boqun Feng Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas --- drivers/pci/probe.c | 6 +++++- include/linux/pci.h | 11 +++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 79177ac37880..60c50d4f156f 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -594,6 +594,7 @@ static void pci_init_host_bridge(struct pci_host_bridge *bridge) bridge->native_pme = 1; bridge->native_ltr = 1; bridge->native_dpc = 1; + bridge->domain_nr = PCI_DOMAIN_NR_NOT_SET; device_initialize(&bridge->dev); } @@ -898,7 +899,10 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge) bus->ops = bridge->ops; bus->number = bus->busn_res.start = bridge->busnr; #ifdef CONFIG_PCI_DOMAINS_GENERIC - bus->domain_nr = pci_bus_find_domain_nr(bus, parent); + if (bridge->domain_nr == PCI_DOMAIN_NR_NOT_SET) + bus->domain_nr = pci_bus_find_domain_nr(bus, parent); + else + bus->domain_nr = bridge->domain_nr; #endif b = pci_find_bus(pci_domain_nr(bus), bridge->busnr); diff --git a/include/linux/pci.h b/include/linux/pci.h index 540b377ca8f6..01aa201e1df0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -526,6 +526,16 @@ static inline int pci_channel_offline(struct pci_dev *pdev) return (pdev->error_state != pci_channel_io_normal); } +/* + * Currently in ACPI spec, for each PCI host bridge, PCI Segment + * Group number is limited to a 16-bit value, therefore (int)-1 is + * not a valid PCI domain number, and can be used as a sentinel + * value indicating ->domain_nr is not set by the driver (and + * CONFIG_PCI_DOMAINS_GENERIC=y archs will set it with + * pci_bus_find_domain_nr()). + */ +#define PCI_DOMAIN_NR_NOT_SET (-1) + struct pci_host_bridge { struct device dev; struct pci_bus *bus; /* Root bus */ @@ -533,6 +543,7 @@ struct pci_host_bridge { struct pci_ops *child_ops; void *sysdata; int busnr; + int domain_nr; struct list_head windows; /* resource_entry */ struct list_head dma_ranges; /* dma ranges resource list */ u8 (*swizzle_irq)(struct pci_dev *, u8 *); /* Platform IRQ swizzler */ -- cgit v1.2.3 From ad3ead1efe057029bf112e13d7ef5901915d6abd Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 23 Aug 2021 10:56:51 +0300 Subject: regulator: Documentation fix for regulator error notification helper The helper to send IRQ notification for regulator errors had still old description mentioning calling BUG() as a last resort when error status reading has kept failing for more times than a given threshold. The impementation calling BUG() did never end-up in-tree but was replaced by hopefully more sophisticated handler trying to power-off the system. Fix the documentation to reflect actual behaviour. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/20210823075651.GA3717293@localhost.localdomain Signed-off-by: Mark Brown --- drivers/regulator/irq_helpers.c | 2 +- include/linux/regulator/driver.h | 7 ++++--- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/irq_helpers.c b/drivers/regulator/irq_helpers.c index fabe2e53093e..522764435575 100644 --- a/drivers/regulator/irq_helpers.c +++ b/drivers/regulator/irq_helpers.c @@ -184,7 +184,7 @@ static irqreturn_t regulator_notifier_isr(int irq, void *data) * If retry_count exceeds the given safety limit we call IC specific die * handler which can try disabling regulator(s). * - * If no die handler is given we will just bug() as a last resort. + * If no die handler is given we will just power-off as a last resort. * * We could try disabling all associated rdevs - but we might shoot * ourselves in the head and leave the problematic regulator enabled. So diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 92bf7584a2f0..bd7a73db2e66 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -527,8 +527,8 @@ struct regulator_irq_data { * active events as core does not clean the map data. * REGULATOR_FAILED_RETRY can be returned to indicate that the * status reading from IC failed. If this is repeated for - * fatal_cnt times the core will call die() callback or BUG() - * as a last resort to protect the HW. + * fatal_cnt times the core will call die() callback or power-off + * the system as a last resort to protect the HW. * @renable: Optional callback to check status (if HW supports that) before * re-enabling IRQ. If implemented this should clear the error * flags so that errors fetched by regulator_get_error_flags() @@ -537,7 +537,8 @@ struct regulator_irq_data { * REGULATOR_FAILED_RETRY can be returned to * indicate that the status reading from IC failed. If this is * repeated for 'fatal_cnt' times the core will call die() - * callback or BUG() as a last resort to protect the HW. + * callback or if die() is not populated then attempt to power-off + * the system as a last resort to protect the HW. * Returning zero indicates that the problem in HW has been solved * and IRQ will be re-enabled. Returning REGULATOR_ERROR_ON * indicates the error condition is still active and keeps IRQ -- cgit v1.2.3 From f7e33bdbd6d1bdf9c3df8bba5abcf3399f957ac3 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 19 Aug 2021 14:56:38 -0400 Subject: fs: remove mandatory file locking support We added CONFIG_MANDATORY_FILE_LOCKING in 2015, and soon after turned it off in Fedora and RHEL8. Several other distros have followed suit. I've heard of one problem in all that time: Someone migrated from an older distro that supported "-o mand" to one that didn't, and the host had a fstab entry with "mand" in it which broke on reboot. They didn't actually _use_ mandatory locking so they just removed the mount option and moved on. This patch rips out mandatory locking support wholesale from the kernel, along with the Kconfig option and the Documentation file. It also changes the mount code to ignore the "mand" mount option instead of erroring out, and to throw a big, ugly warning. Signed-off-by: Jeff Layton --- Documentation/filesystems/mandatory-locking.rst | 188 ------------------------ fs/9p/vfs_file.c | 13 -- fs/Kconfig | 10 -- fs/afs/flock.c | 4 - fs/ceph/locks.c | 3 - fs/gfs2/file.c | 3 - fs/locks.c | 117 +-------------- fs/namei.c | 4 +- fs/namespace.c | 29 ++-- fs/nfs/file.c | 4 - fs/nfsd/nfs4state.c | 14 -- fs/nfsd/vfs.c | 23 +-- fs/ocfs2/locks.c | 4 - fs/open.c | 8 +- fs/read_write.c | 7 - fs/remap_range.c | 12 -- include/linux/fs.h | 84 ----------- mm/mmap.c | 6 - mm/nommu.c | 3 - 19 files changed, 15 insertions(+), 521 deletions(-) delete mode 100644 Documentation/filesystems/mandatory-locking.rst (limited to 'include/linux') diff --git a/Documentation/filesystems/mandatory-locking.rst b/Documentation/filesystems/mandatory-locking.rst deleted file mode 100644 index 9ce73544a8f0..000000000000 --- a/Documentation/filesystems/mandatory-locking.rst +++ /dev/null @@ -1,188 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -===================================================== -Mandatory File Locking For The Linux Operating System -===================================================== - - Andy Walker - - 15 April 1996 - - (Updated September 2007) - -0. Why you should avoid mandatory locking ------------------------------------------ - -The Linux implementation is prey to a number of difficult-to-fix race -conditions which in practice make it not dependable: - - - The write system call checks for a mandatory lock only once - at its start. It is therefore possible for a lock request to - be granted after this check but before the data is modified. - A process may then see file data change even while a mandatory - lock was held. - - Similarly, an exclusive lock may be granted on a file after - the kernel has decided to proceed with a read, but before the - read has actually completed, and the reading process may see - the file data in a state which should not have been visible - to it. - - Similar races make the claimed mutual exclusion between lock - and mmap similarly unreliable. - -1. What is mandatory locking? ------------------------------- - -Mandatory locking is kernel enforced file locking, as opposed to the more usual -cooperative file locking used to guarantee sequential access to files among -processes. File locks are applied using the flock() and fcntl() system calls -(and the lockf() library routine which is a wrapper around fcntl().) It is -normally a process' responsibility to check for locks on a file it wishes to -update, before applying its own lock, updating the file and unlocking it again. -The most commonly used example of this (and in the case of sendmail, the most -troublesome) is access to a user's mailbox. The mail user agent and the mail -transfer agent must guard against updating the mailbox at the same time, and -prevent reading the mailbox while it is being updated. - -In a perfect world all processes would use and honour a cooperative, or -"advisory" locking scheme. However, the world isn't perfect, and there's -a lot of poorly written code out there. - -In trying to address this problem, the designers of System V UNIX came up -with a "mandatory" locking scheme, whereby the operating system kernel would -block attempts by a process to write to a file that another process holds a -"read" -or- "shared" lock on, and block attempts to both read and write to a -file that a process holds a "write " -or- "exclusive" lock on. - -The System V mandatory locking scheme was intended to have as little impact as -possible on existing user code. The scheme is based on marking individual files -as candidates for mandatory locking, and using the existing fcntl()/lockf() -interface for applying locks just as if they were normal, advisory locks. - -.. Note:: - - 1. In saying "file" in the paragraphs above I am actually not telling - the whole truth. System V locking is based on fcntl(). The granularity of - fcntl() is such that it allows the locking of byte ranges in files, in - addition to entire files, so the mandatory locking rules also have byte - level granularity. - - 2. POSIX.1 does not specify any scheme for mandatory locking, despite - borrowing the fcntl() locking scheme from System V. The mandatory locking - scheme is defined by the System V Interface Definition (SVID) Version 3. - -2. Marking a file for mandatory locking ---------------------------------------- - -A file is marked as a candidate for mandatory locking by setting the group-id -bit in its file mode but removing the group-execute bit. This is an otherwise -meaningless combination, and was chosen by the System V implementors so as not -to break existing user programs. - -Note that the group-id bit is usually automatically cleared by the kernel when -a setgid file is written to. This is a security measure. The kernel has been -modified to recognize the special case of a mandatory lock candidate and to -refrain from clearing this bit. Similarly the kernel has been modified not -to run mandatory lock candidates with setgid privileges. - -3. Available implementations ----------------------------- - -I have considered the implementations of mandatory locking available with -SunOS 4.1.x, Solaris 2.x and HP-UX 9.x. - -Generally I have tried to make the most sense out of the behaviour exhibited -by these three reference systems. There are many anomalies. - -All the reference systems reject all calls to open() for a file on which -another process has outstanding mandatory locks. This is in direct -contravention of SVID 3, which states that only calls to open() with the -O_TRUNC flag set should be rejected. The Linux implementation follows the SVID -definition, which is the "Right Thing", since only calls with O_TRUNC can -modify the contents of the file. - -HP-UX even disallows open() with O_TRUNC for a file with advisory locks, not -just mandatory locks. That would appear to contravene POSIX.1. - -mmap() is another interesting case. All the operating systems mentioned -prevent mandatory locks from being applied to an mmap()'ed file, but HP-UX -also disallows advisory locks for such a file. SVID actually specifies the -paranoid HP-UX behaviour. - -In my opinion only MAP_SHARED mappings should be immune from locking, and then -only from mandatory locks - that is what is currently implemented. - -SunOS is so hopeless that it doesn't even honour the O_NONBLOCK flag for -mandatory locks, so reads and writes to locked files always block when they -should return EAGAIN. - -I'm afraid that this is such an esoteric area that the semantics described -below are just as valid as any others, so long as the main points seem to -agree. - -4. Semantics ------------- - -1. Mandatory locks can only be applied via the fcntl()/lockf() locking - interface - in other words the System V/POSIX interface. BSD style - locks using flock() never result in a mandatory lock. - -2. If a process has locked a region of a file with a mandatory read lock, then - other processes are permitted to read from that region. If any of these - processes attempts to write to the region it will block until the lock is - released, unless the process has opened the file with the O_NONBLOCK - flag in which case the system call will return immediately with the error - status EAGAIN. - -3. If a process has locked a region of a file with a mandatory write lock, all - attempts to read or write to that region block until the lock is released, - unless a process has opened the file with the O_NONBLOCK flag in which case - the system call will return immediately with the error status EAGAIN. - -4. Calls to open() with O_TRUNC, or to creat(), on a existing file that has - any mandatory locks owned by other processes will be rejected with the - error status EAGAIN. - -5. Attempts to apply a mandatory lock to a file that is memory mapped and - shared (via mmap() with MAP_SHARED) will be rejected with the error status - EAGAIN. - -6. Attempts to create a shared memory map of a file (via mmap() with MAP_SHARED) - that has any mandatory locks in effect will be rejected with the error status - EAGAIN. - -5. Which system calls are affected? ------------------------------------ - -Those which modify a file's contents, not just the inode. That gives read(), -write(), readv(), writev(), open(), creat(), mmap(), truncate() and -ftruncate(). truncate() and ftruncate() are considered to be "write" actions -for the purposes of mandatory locking. - -The affected region is usually defined as stretching from the current position -for the total number of bytes read or written. For the truncate calls it is -defined as the bytes of a file removed or added (we must also consider bytes -added, as a lock can specify just "the whole file", rather than a specific -range of bytes.) - -Note 3: I may have overlooked some system calls that need mandatory lock -checking in my eagerness to get this code out the door. Please let me know, or -better still fix the system calls yourself and submit a patch to me or Linus. - -6. Warning! ------------ - -Not even root can override a mandatory lock, so runaway processes can wreak -havoc if they lock crucial files. The way around it is to change the file -permissions (remove the setgid bit) before trying to read or write to it. -Of course, that might be a bit tricky if the system is hung :-( - -7. The "mand" mount option --------------------------- -Mandatory locking is disabled on all filesystems by default, and must be -administratively enabled by mounting with "-o mand". That mount option -is only allowed if the mounting task has the CAP_SYS_ADMIN capability. - -Since kernel v4.5, it is possible to disable mandatory locking -altogether by setting CONFIG_MANDATORY_FILE_LOCKING to "n". A kernel -with this disabled will reject attempts to mount filesystems with the -"mand" mount option with the error status EPERM. diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 59c32c9b799f..c4a2dc41beac 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -121,10 +121,6 @@ static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl) p9_debug(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl); - /* No mandatory locks */ - if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) - return -ENOLCK; - if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) { filemap_write_and_wait(inode->i_mapping); invalidate_mapping_pages(&inode->i_data, 0, -1); @@ -312,10 +308,6 @@ static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl) p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n", filp, cmd, fl, filp); - /* No mandatory locks */ - if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) - goto out_err; - if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) { filemap_write_and_wait(inode->i_mapping); invalidate_mapping_pages(&inode->i_data, 0, -1); @@ -327,7 +319,6 @@ static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl) ret = v9fs_file_getlock(filp, fl); else ret = -EINVAL; -out_err: return ret; } @@ -348,10 +339,6 @@ static int v9fs_file_flock_dotl(struct file *filp, int cmd, p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n", filp, cmd, fl, filp); - /* No mandatory locks */ - if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) - goto out_err; - if (!(fl->fl_flags & FL_FLOCK)) goto out_err; diff --git a/fs/Kconfig b/fs/Kconfig index a7749c126b8e..949128bf86c9 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -101,16 +101,6 @@ config FILE_LOCKING for filesystems like NFS and for the flock() system call. Disabling this option saves about 11k. -config MANDATORY_FILE_LOCKING - bool "Enable Mandatory file locking" - depends on FILE_LOCKING - default y - help - This option enables files appropriately marked files on appropriely - mounted filesystems to support mandatory locking. - - To the best of my knowledge this is dead code that no one cares about. - source "fs/crypto/Kconfig" source "fs/verity/Kconfig" diff --git a/fs/afs/flock.c b/fs/afs/flock.c index cb3054c7843e..c4210a3964d8 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -772,10 +772,6 @@ int afs_lock(struct file *file, int cmd, struct file_lock *fl) fl->fl_type, fl->fl_flags, (long long) fl->fl_start, (long long) fl->fl_end); - /* AFS doesn't support mandatory locks */ - if (__mandatory_lock(&vnode->vfs_inode) && fl->fl_type != F_UNLCK) - return -ENOLCK; - if (IS_GETLK(cmd)) return afs_do_getlk(file, fl); diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index fa8a847743d0..bdeb271f47d9 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -240,9 +240,6 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_POSIX)) return -ENOLCK; - /* No mandatory locks */ - if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK) - return -ENOLCK; dout("ceph_lock, fl_owner: %p\n", fl->fl_owner); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 84ec053d43b4..c559827cb6f9 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1237,9 +1237,6 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_POSIX)) return -ENOLCK; - if (__mandatory_lock(&ip->i_inode) && fl->fl_type != F_UNLCK) - return -ENOLCK; - if (cmd == F_CANCELLK) { /* Hack: */ cmd = F_SETLK; diff --git a/fs/locks.c b/fs/locks.c index 74b2a1dfe8d8..3d6fb4ae847b 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1397,103 +1397,6 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) return error; } -#ifdef CONFIG_MANDATORY_FILE_LOCKING -/** - * locks_mandatory_locked - Check for an active lock - * @file: the file to check - * - * Searches the inode's list of locks to find any POSIX locks which conflict. - * This function is called from locks_verify_locked() only. - */ -int locks_mandatory_locked(struct file *file) -{ - int ret; - struct inode *inode = locks_inode(file); - struct file_lock_context *ctx; - struct file_lock *fl; - - ctx = smp_load_acquire(&inode->i_flctx); - if (!ctx || list_empty_careful(&ctx->flc_posix)) - return 0; - - /* - * Search the lock list for this inode for any POSIX locks. - */ - spin_lock(&ctx->flc_lock); - ret = 0; - list_for_each_entry(fl, &ctx->flc_posix, fl_list) { - if (fl->fl_owner != current->files && - fl->fl_owner != file) { - ret = -EAGAIN; - break; - } - } - spin_unlock(&ctx->flc_lock); - return ret; -} - -/** - * locks_mandatory_area - Check for a conflicting lock - * @inode: the file to check - * @filp: how the file was opened (if it was) - * @start: first byte in the file to check - * @end: lastbyte in the file to check - * @type: %F_WRLCK for a write lock, else %F_RDLCK - * - * Searches the inode's list of locks to find any POSIX locks which conflict. - */ -int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start, - loff_t end, unsigned char type) -{ - struct file_lock fl; - int error; - bool sleep = false; - - locks_init_lock(&fl); - fl.fl_pid = current->tgid; - fl.fl_file = filp; - fl.fl_flags = FL_POSIX | FL_ACCESS; - if (filp && !(filp->f_flags & O_NONBLOCK)) - sleep = true; - fl.fl_type = type; - fl.fl_start = start; - fl.fl_end = end; - - for (;;) { - if (filp) { - fl.fl_owner = filp; - fl.fl_flags &= ~FL_SLEEP; - error = posix_lock_inode(inode, &fl, NULL); - if (!error) - break; - } - - if (sleep) - fl.fl_flags |= FL_SLEEP; - fl.fl_owner = current->files; - error = posix_lock_inode(inode, &fl, NULL); - if (error != FILE_LOCK_DEFERRED) - break; - error = wait_event_interruptible(fl.fl_wait, - list_empty(&fl.fl_blocked_member)); - if (!error) { - /* - * If we've been sleeping someone might have - * changed the permissions behind our back. - */ - if (__mandatory_lock(inode)) - continue; - } - - break; - } - locks_delete_block(&fl); - - return error; -} -EXPORT_SYMBOL(locks_mandatory_area); -#endif /* CONFIG_MANDATORY_FILE_LOCKING */ - static void lease_clear_pending(struct file_lock *fl, int arg) { switch (arg) { @@ -2486,14 +2389,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, if (file_lock == NULL) return -ENOLCK; - /* Don't allow mandatory locks on files that may be memory mapped - * and shared. - */ - if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) { - error = -EAGAIN; - goto out; - } - error = flock_to_posix_lock(filp, file_lock, flock); if (error) goto out; @@ -2611,21 +2506,12 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *file_lock = locks_alloc_lock(); - struct inode *inode = locks_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; - /* Don't allow mandatory locks on files that may be memory mapped - * and shared. - */ - if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) { - error = -EAGAIN; - goto out; - } - error = flock64_to_posix_lock(filp, file_lock, flock); if (error) goto out; @@ -2857,8 +2743,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, seq_puts(f, "POSIX "); seq_printf(f, " %s ", - (inode == NULL) ? "*NOINODE*" : - mandatory_lock(inode) ? "MANDATORY" : "ADVISORY "); + (inode == NULL) ? "*NOINODE*" : "ADVISORY "); } else if (IS_FLOCK(fl)) { if (fl->fl_type & LOCK_MAND) { seq_puts(f, "FLOCK MSNFS "); diff --git a/fs/namei.c b/fs/namei.c index bf6d8a738c59..471eb9fead6e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3023,9 +3023,7 @@ static int handle_truncate(struct user_namespace *mnt_userns, struct file *filp) /* * Refuse to truncate files with mandatory locks held on them. */ - error = locks_verify_locked(filp); - if (!error) - error = security_path_truncate(path); + error = security_path_truncate(path); if (!error) { error = do_truncate(mnt_userns, path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, diff --git a/fs/namespace.c b/fs/namespace.c index 97adcb5ab5d5..20caa4b4c539 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1715,22 +1715,14 @@ static inline bool may_mount(void) return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } -#ifdef CONFIG_MANDATORY_FILE_LOCKING -static bool may_mandlock(void) +static void warn_mandlock(void) { - pr_warn_once("======================================================\n" - "WARNING: the mand mount option is being deprecated and\n" - " will be removed in v5.15!\n" - "======================================================\n"); - return capable(CAP_SYS_ADMIN); + pr_warn_once("=======================================================\n" + "WARNING: The mand mount option has been deprecated and\n" + " and is ignored by this kernel. Remove the mand\n" + " option from the mount to silence this warning.\n" + "=======================================================\n"); } -#else -static inline bool may_mandlock(void) -{ - pr_warn("VFS: \"mand\" mount option not supported"); - return false; -} -#endif static int can_umount(const struct path *path, int flags) { @@ -3197,8 +3189,8 @@ int path_mount(const char *dev_name, struct path *path, return ret; if (!may_mount()) return -EPERM; - if ((flags & SB_MANDLOCK) && !may_mandlock()) - return -EPERM; + if (flags & SB_MANDLOCK) + warn_mandlock(); /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) @@ -3581,9 +3573,8 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) goto err_unlock; - ret = -EPERM; - if ((fc->sb_flags & SB_MANDLOCK) && !may_mandlock()) - goto err_unlock; + if (fc->sb_flags & SB_MANDLOCK) + warn_mandlock(); newmount.mnt = vfs_create_mount(fc); if (IS_ERR(newmount.mnt)) { diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 1fef107961bc..514be5d28d70 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -806,10 +806,6 @@ int nfs_lock(struct file *filp, int cmd, struct file_lock *fl) nfs_inc_stats(inode, NFSIOS_VFSLOCK); - /* No mandatory locks over NFS */ - if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) - goto out_err; - if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL) is_local = 1; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index fa67ecd5fe63..8313e1dbb5dc 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5735,16 +5735,6 @@ check_special_stateids(struct net *net, svc_fh *current_fh, stateid_t *stateid, NFS4_SHARE_DENY_READ); } -/* - * Allow READ/WRITE during grace period on recovered state only for files - * that are not able to provide mandatory locking. - */ -static inline int -grace_disallows_io(struct net *net, struct inode *inode) -{ - return opens_in_grace(net) && mandatory_lock(inode); -} - static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_session) { /* @@ -6026,7 +6016,6 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, stateid_t *stateid, int flags, struct nfsd_file **nfp, struct nfs4_stid **cstid) { - struct inode *ino = d_inode(fhp->fh_dentry); struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfs4_stid *s = NULL; @@ -6035,9 +6024,6 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, if (nfp) *nfp = NULL; - if (grace_disallows_io(net, ino)) - return nfserr_grace; - if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { status = check_special_stateids(net, fhp, stateid, flags); goto done; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index a224a5e23cc1..92e77f92268a 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -333,7 +333,6 @@ nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap) { struct inode *inode = d_inode(fhp->fh_dentry); - int host_err; if (iap->ia_size < inode->i_size) { __be32 err; @@ -343,20 +342,7 @@ nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp, if (err) return err; } - - host_err = get_write_access(inode); - if (host_err) - goto out_nfserrno; - - host_err = locks_verify_truncate(inode, NULL, iap->ia_size); - if (host_err) - goto out_put_write_access; - return 0; - -out_put_write_access: - put_write_access(inode); -out_nfserrno: - return nfserrno(host_err); + return nfserrno(get_write_access(inode)); } /* @@ -750,13 +736,6 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, err = nfserr_perm; if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE)) goto out; - /* - * We must ignore files (but only files) which might have mandatory - * locks on them because there is no way to know if the accesser has - * the lock. - */ - if (S_ISREG((inode)->i_mode) && mandatory_lock(inode)) - goto out; if (!inode->i_fop) goto out; diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c index fab7c6a4a7d0..73a3854b2afb 100644 --- a/fs/ocfs2/locks.c +++ b/fs/ocfs2/locks.c @@ -101,8 +101,6 @@ int ocfs2_flock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; - if (__mandatory_lock(inode)) - return -ENOLCK; if ((osb->s_mount_opt & OCFS2_MOUNT_LOCALFLOCKS) || ocfs2_mount_local(osb)) @@ -121,8 +119,6 @@ int ocfs2_lock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_POSIX)) return -ENOLCK; - if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) - return -ENOLCK; return ocfs2_plock(osb->cconn, OCFS2_I(inode)->ip_blkno, file, cmd, fl); } diff --git a/fs/open.c b/fs/open.c index 94bef26ff1b6..daa324606a41 100644 --- a/fs/open.c +++ b/fs/open.c @@ -105,9 +105,7 @@ long vfs_truncate(const struct path *path, loff_t length) if (error) goto put_write_and_out; - error = locks_verify_truncate(inode, NULL, length); - if (!error) - error = security_path_truncate(path); + error = security_path_truncate(path); if (!error) error = do_truncate(mnt_userns, path->dentry, length, 0, NULL); @@ -189,9 +187,7 @@ long do_sys_ftruncate(unsigned int fd, loff_t length, int small) if (IS_APPEND(file_inode(f.file))) goto out_putf; sb_start_write(inode->i_sb); - error = locks_verify_truncate(inode, f.file, length); - if (!error) - error = security_path_truncate(&f.file->f_path); + error = security_path_truncate(&f.file->f_path); if (!error) error = do_truncate(file_mnt_user_ns(f.file), dentry, length, ATTR_MTIME | ATTR_CTIME, f.file); diff --git a/fs/read_write.c b/fs/read_write.c index 9db7adf160d2..ffe821b8588e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -388,13 +388,6 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t if (!unsigned_offsets(file)) return retval; } - - if (unlikely(inode->i_flctx && mandatory_lock(inode))) { - retval = locks_mandatory_area(inode, file, pos, pos + count - 1, - read_write == READ ? F_RDLCK : F_WRLCK); - if (retval < 0) - return retval; - } } return security_file_permission(file, diff --git a/fs/remap_range.c b/fs/remap_range.c index e4a5fdd7ad7b..6d4a9beaa097 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -99,24 +99,12 @@ static int generic_remap_checks(struct file *file_in, loff_t pos_in, static int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write) { - struct inode *inode = file_inode(file); - if (unlikely(pos < 0 || len < 0)) return -EINVAL; if (unlikely((loff_t) (pos + len) < 0)) return -EINVAL; - if (unlikely(inode->i_flctx && mandatory_lock(inode))) { - loff_t end = len ? pos + len - 1 : OFFSET_MAX; - int retval; - - retval = locks_mandatory_area(inode, file, pos, end, - write ? F_WRLCK : F_RDLCK); - if (retval < 0) - return retval; - } - return security_file_permission(file, write ? MAY_WRITE : MAY_READ); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..f51c63b37636 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2570,90 +2570,6 @@ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) -#ifdef CONFIG_MANDATORY_FILE_LOCKING -extern int locks_mandatory_locked(struct file *); -extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char); - -/* - * Candidates for mandatory locking have the setgid bit set - * but no group execute bit - an otherwise meaningless combination. - */ - -static inline int __mandatory_lock(struct inode *ino) -{ - return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID; -} - -/* - * ... and these candidates should be on SB_MANDLOCK mounted fs, - * otherwise these will be advisory locks - */ - -static inline int mandatory_lock(struct inode *ino) -{ - return IS_MANDLOCK(ino) && __mandatory_lock(ino); -} - -static inline int locks_verify_locked(struct file *file) -{ - if (mandatory_lock(locks_inode(file))) - return locks_mandatory_locked(file); - return 0; -} - -static inline int locks_verify_truncate(struct inode *inode, - struct file *f, - loff_t size) -{ - if (!inode->i_flctx || !mandatory_lock(inode)) - return 0; - - if (size < inode->i_size) { - return locks_mandatory_area(inode, f, size, inode->i_size - 1, - F_WRLCK); - } else { - return locks_mandatory_area(inode, f, inode->i_size, size - 1, - F_WRLCK); - } -} - -#else /* !CONFIG_MANDATORY_FILE_LOCKING */ - -static inline int locks_mandatory_locked(struct file *file) -{ - return 0; -} - -static inline int locks_mandatory_area(struct inode *inode, struct file *filp, - loff_t start, loff_t end, unsigned char type) -{ - return 0; -} - -static inline int __mandatory_lock(struct inode *inode) -{ - return 0; -} - -static inline int mandatory_lock(struct inode *inode) -{ - return 0; -} - -static inline int locks_verify_locked(struct file *file) -{ - return 0; -} - -static inline int locks_verify_truncate(struct inode *inode, struct file *filp, - size_t size) -{ - return 0; -} - -#endif /* CONFIG_MANDATORY_FILE_LOCKING */ - - #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { diff --git a/mm/mmap.c b/mm/mmap.c index ca54d36d203a..181a113b545d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1517,12 +1517,6 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; - /* - * Make sure there are no mandatory locks on the file. - */ - if (locks_verify_locked(file)) - return -EAGAIN; - vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); diff --git a/mm/nommu.c b/mm/nommu.c index 3a93d4054810..9d0ad98f838c 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -826,9 +826,6 @@ static int validate_mmap_request(struct file *file, (file->f_mode & FMODE_WRITE)) return -EACCES; - if (locks_verify_locked(file)) - return -EAGAIN; - if (!(capabilities & NOMMU_MAP_DIRECT)) return -ENODEV; -- cgit v1.2.3 From 5a798493b8f30121363359bba834392f044c169b Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 14 Jul 2021 14:47:22 -0400 Subject: fs: add a filemap_fdatawrite_wbc helper Btrfs sometimes needs to flush dirty pages on a bunch of dirty inodes in order to reclaim metadata reservations. Unfortunately most helpers in this area are too smart for us: 1) The normal filemap_fdata* helpers only take range and sync modes, and don't give any indication of how much was written, so we can only flush full inodes, which isn't what we want in most cases. 2) The normal writeback path requires us to have the s_umount sem held, but we can't unconditionally take it in this path because we could deadlock. 3) The normal writeback path also skips inodes with I_SYNC set if we write with WB_SYNC_NONE. This isn't the behavior we want under heavy ENOSPC pressure, we want to actually make sure the pages are under writeback before returning, and if another thread is in the middle of writing the file we may return before they're under writeback and miss our ordered extents and not properly wait for completion. 4) sync_inode() uses the normal writeback path and has the same problem as #3. What we really want is to call do_writepages() with our wbc. This way we can make sure that writeback is actually started on the pages, and we can control how many pages are written as a whole as we write many inodes using the same wbc. Accomplish this with a new helper that does just that so we can use it for our ENOSPC flushing infrastructure. Reviewed-by: Nikolay Borisov Reviewed-by: Christoph Hellwig Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 2 ++ mm/filemap.c | 36 +++++++++++++++++++++++++++--------- 2 files changed, 29 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..452cd4843843 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2891,6 +2891,8 @@ extern int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); extern int filemap_check_errors(struct address_space *mapping); extern void __filemap_set_wb_err(struct address_space *mapping, int err); +int filemap_fdatawrite_wbc(struct address_space *mapping, + struct writeback_control *wbc); static inline int filemap_write_and_wait(struct address_space *mapping) { diff --git a/mm/filemap.c b/mm/filemap.c index d1458ecf2f51..034d370d4ebb 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -377,6 +377,32 @@ static int filemap_check_and_keep_errors(struct address_space *mapping) return 0; } +/** + * filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range + * @mapping: address space structure to write + * @wbc: the writeback_control controlling the writeout + * + * Call writepages on the mapping using the provided wbc to control the + * writeout. + * + * Return: %0 on success, negative error code otherwise. + */ +int filemap_fdatawrite_wbc(struct address_space *mapping, + struct writeback_control *wbc) +{ + int ret; + + if (!mapping_can_writeback(mapping) || + !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + return 0; + + wbc_attach_fdatawrite_inode(wbc, mapping->host); + ret = do_writepages(mapping, wbc); + wbc_detach_inode(wbc); + return ret; +} +EXPORT_SYMBOL(filemap_fdatawrite_wbc); + /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write @@ -397,7 +423,6 @@ static int filemap_check_and_keep_errors(struct address_space *mapping) int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { - int ret; struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, @@ -405,14 +430,7 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, .range_end = end, }; - if (!mapping_can_writeback(mapping) || - !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) - return 0; - - wbc_attach_fdatawrite_inode(&wbc, mapping->host); - ret = do_writepages(mapping, &wbc); - wbc_detach_inode(&wbc); - return ret; + return filemap_fdatawrite_wbc(mapping, &wbc); } static inline int __filemap_fdatawrite(struct address_space *mapping, -- cgit v1.2.3 From 5662c967c69dfd162a0667d69bad776939bedf85 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 14 Jul 2021 14:47:25 -0400 Subject: fs: kill sync_inode Now that all users of sync_inode() have been deleted, remove sync_inode(). Reviewed-by: Christoph Hellwig Reviewed-by: Nikolay Borisov Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/fs-writeback.c | 19 +------------------ include/linux/fs.h | 1 - 2 files changed, 1 insertion(+), 19 deletions(-) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4c3370548982..eb57dade6076 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2729,23 +2729,6 @@ int write_inode_now(struct inode *inode, int sync) } EXPORT_SYMBOL(write_inode_now); -/** - * sync_inode - write an inode and its pages to disk. - * @inode: the inode to sync - * @wbc: controls the writeback mode - * - * sync_inode() will write an inode and its pages to disk. It will also - * correctly update the inode on its superblock's dirty inode lists and will - * update inode->i_state. - * - * The caller must have a ref on the inode. - */ -int sync_inode(struct inode *inode, struct writeback_control *wbc) -{ - return writeback_single_inode(inode, wbc); -} -EXPORT_SYMBOL(sync_inode); - /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync @@ -2762,6 +2745,6 @@ int sync_inode_metadata(struct inode *inode, int wait) .nr_to_write = 0, /* metadata-only */ }; - return sync_inode(inode, &wbc); + return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata); diff --git a/include/linux/fs.h b/include/linux/fs.h index 452cd4843843..1751addcb36e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2457,7 +2457,6 @@ static inline void file_accessed(struct file *file) extern int file_modified(struct file *file); -int sync_inode(struct inode *inode, struct writeback_control *wbc); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { -- cgit v1.2.3 From e83502ca5f1e1f03fb1393008ec22d17e7dc9882 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 21 Jul 2021 21:43:32 +0900 Subject: block: fix argument type of bio_trim() The function bio_trim has offset and size arguments that are declared as int. The callers of this function use sector_t type when passing the offset and size, e.g. drivers/md/raid1.c:narrow_write_error() and drivers/md/raid1.c:narrow_write_error(). Change offset and size arguments to sector_t type for bio_trim(). Also, add WARN_ON_ONCE() to catch their overflow. Reviewed-by: Christoph Hellwig Signed-off-by: Chaitanya Kulkarni Signed-off-by: Naohiro Aota Reviewed-by: David Sterba Signed-off-by: David Sterba --- block/bio.c | 12 +++++++----- include/linux/bio.h | 2 +- include/linux/blk_types.h | 1 + 3 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 1fab762e079b..77cadcba93b9 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1463,12 +1463,15 @@ EXPORT_SYMBOL(bio_split); * @bio: bio to trim * @offset: number of sectors to trim from the front of @bio * @size: size we want to trim @bio to, in sectors + * + * This function is typically used for bios that are cloned and submitted + * to the underlying device in parts. */ -void bio_trim(struct bio *bio, int offset, int size) +void bio_trim(struct bio *bio, sector_t offset, sector_t size) { - /* 'bio' is a cloned bio which we need to trim to match - * the given offset and size. - */ + if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS || + offset + size > bio->bi_iter.bi_size)) + return; size <<= 9; if (offset == 0 && size == bio->bi_iter.bi_size) @@ -1479,7 +1482,6 @@ void bio_trim(struct bio *bio, int offset, int size) if (bio_integrity(bio)) bio_integrity_trim(bio); - } EXPORT_SYMBOL_GPL(bio_trim); diff --git a/include/linux/bio.h b/include/linux/bio.h index 2203b686e1f0..8a451d77b573 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -375,7 +375,7 @@ static inline void bip_set_seed(struct bio_integrity_payload *bip, #endif /* CONFIG_BLK_DEV_INTEGRITY */ -extern void bio_trim(struct bio *bio, int offset, int size); +void bio_trim(struct bio *bio, sector_t offset, sector_t size); extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 290f9061b29a..bca4d33876d4 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -281,6 +281,7 @@ struct bio { }; #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) +#define BIO_MAX_SECTORS (UINT_MAX >> SECTOR_SHIFT) /* * bio flags -- cgit v1.2.3 From c2fd68b6b2b00f0a6280b5971028c10c8f0ba70f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 27 Jul 2021 12:48:40 +0200 Subject: namei: add mapping aware lookup helper Various filesystems rely on the lookup_one_len() helper to lookup a single path component relative to a well-known starting point. Allow such filesystems to support idmapped mounts by adding a version of this helper to take the idmap into account when calling inode_permission(). This change is a required to let btrfs (and other filesystems) support idmapped mounts. Cc: Christoph Hellwig Cc: Al Viro Cc: Matthew Wilcox (Oracle) Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Josef Bacik Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner Signed-off-by: David Sterba --- fs/namei.c | 43 +++++++++++++++++++++++++++++++++++++------ include/linux/namei.h | 1 + 2 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index bf6d8a738c59..902df46e7dd3 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2575,8 +2575,9 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, } EXPORT_SYMBOL(vfs_path_lookup); -static int lookup_one_len_common(const char *name, struct dentry *base, - int len, struct qstr *this) +static int lookup_one_common(struct user_namespace *mnt_userns, + const char *name, struct dentry *base, int len, + struct qstr *this) { this->name = name; this->len = len; @@ -2604,7 +2605,7 @@ static int lookup_one_len_common(const char *name, struct dentry *base, return err; } - return inode_permission(&init_user_ns, base->d_inode, MAY_EXEC); + return inode_permission(mnt_userns, base->d_inode, MAY_EXEC); } /** @@ -2628,7 +2629,7 @@ struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len WARN_ON_ONCE(!inode_is_locked(base->d_inode)); - err = lookup_one_len_common(name, base, len, &this); + err = lookup_one_common(&init_user_ns, name, base, len, &this); if (err) return ERR_PTR(err); @@ -2655,7 +2656,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) WARN_ON_ONCE(!inode_is_locked(base->d_inode)); - err = lookup_one_len_common(name, base, len, &this); + err = lookup_one_common(&init_user_ns, name, base, len, &this); if (err) return ERR_PTR(err); @@ -2664,6 +2665,36 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) } EXPORT_SYMBOL(lookup_one_len); +/** + * lookup_one - filesystem helper to lookup single pathname component + * @mnt_userns: user namespace of the mount the lookup is performed from + * @name: pathname component to lookup + * @base: base directory to lookup from + * @len: maximum length @len should be interpreted to + * + * Note that this routine is purely a helper for filesystem usage and should + * not be called by generic code. + * + * The caller must hold base->i_mutex. + */ +struct dentry *lookup_one(struct user_namespace *mnt_userns, const char *name, + struct dentry *base, int len) +{ + struct dentry *dentry; + struct qstr this; + int err; + + WARN_ON_ONCE(!inode_is_locked(base->d_inode)); + + err = lookup_one_common(mnt_userns, name, base, len, &this); + if (err) + return ERR_PTR(err); + + dentry = lookup_dcache(&this, base, 0); + return dentry ? dentry : __lookup_slow(&this, base, 0); +} +EXPORT_SYMBOL(lookup_one); + /** * lookup_one_len_unlocked - filesystem helper to lookup single pathname component * @name: pathname component to lookup @@ -2683,7 +2714,7 @@ struct dentry *lookup_one_len_unlocked(const char *name, int err; struct dentry *ret; - err = lookup_one_len_common(name, base, len, &this); + err = lookup_one_common(&init_user_ns, name, base, len, &this); if (err) return ERR_PTR(err); diff --git a/include/linux/namei.h b/include/linux/namei.h index be9a2b349ca7..e89329bb3134 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -68,6 +68,7 @@ extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); +struct dentry *lookup_one(struct user_namespace *, const char *, struct dentry *, int); extern int follow_down_one(struct path *); extern int follow_down(struct path *); -- cgit v1.2.3 From 2dc6f19e4f438d4c14987cb17aee38aaf7304e7f Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 23 Aug 2021 12:01:18 -0400 Subject: nlm: minor nlm_lookup_file argument change It'll come in handy to get the whole nlm_lock. Signed-off-by: J. Bruce Fields Signed-off-by: Chuck Lever --- fs/lockd/svc4proc.c | 3 ++- fs/lockd/svcproc.c | 2 +- fs/lockd/svcsubs.c | 15 ++++++++------- include/linux/lockd/lockd.h | 2 +- 4 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 4c10fb5138f1..bc496bbd696b 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -40,7 +40,8 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, /* Obtain file pointer. Not used by FREE_ALL call. */ if (filp != NULL) { - if ((error = nlm_lookup_file(rqstp, &file, &lock->fh)) != 0) + error = nlm_lookup_file(rqstp, &file, lock); + if (error) goto no_locks; *filp = file; diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 4ae4b63b5392..f4e5e0eb30fd 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -69,7 +69,7 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, /* Obtain file pointer. Not used by FREE_ALL call. */ if (filp != NULL) { - error = cast_status(nlm_lookup_file(rqstp, &file, &lock->fh)); + error = cast_status(nlm_lookup_file(rqstp, &file, lock)); if (error != 0) goto no_locks; *filp = file; diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 028fc152da22..2d62633b39e5 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -82,31 +82,31 @@ static inline unsigned int file_hash(struct nfs_fh *f) */ __be32 nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, - struct nfs_fh *f) + struct nlm_lock *lock) { struct nlm_file *file; unsigned int hash; __be32 nfserr; - nlm_debug_print_fh("nlm_lookup_file", f); + nlm_debug_print_fh("nlm_lookup_file", &lock->fh); - hash = file_hash(f); + hash = file_hash(&lock->fh); /* Lock file table */ mutex_lock(&nlm_file_mutex); hlist_for_each_entry(file, &nlm_files[hash], f_list) - if (!nfs_compare_fh(&file->f_handle, f)) + if (!nfs_compare_fh(&file->f_handle, &lock->fh)) goto found; - nlm_debug_print_fh("creating file for", f); + nlm_debug_print_fh("creating file for", &lock->fh); nfserr = nlm_lck_denied_nolocks; file = kzalloc(sizeof(*file), GFP_KERNEL); if (!file) goto out_unlock; - memcpy(&file->f_handle, f, sizeof(struct nfs_fh)); + memcpy(&file->f_handle, &lock->fh, sizeof(struct nfs_fh)); mutex_init(&file->f_mutex); INIT_HLIST_NODE(&file->f_list); INIT_LIST_HEAD(&file->f_blocks); @@ -117,7 +117,8 @@ nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, * We have to make sure we have the right credential to open * the file. */ - if ((nfserr = nlmsvc_ops->fopen(rqstp, f, &file->f_file)) != 0) { + nfserr = nlmsvc_ops->fopen(rqstp, &lock->fh, &file->f_file); + if (nfserr) { dprintk("lockd: open failed (error %d)\n", nfserr); goto out_free; } diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 666f5f310a04..81b71ad2040a 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -286,7 +286,7 @@ void nlmsvc_locks_init_private(struct file_lock *, struct nlm_host *, pid_t); * File handling for the server personality */ __be32 nlm_lookup_file(struct svc_rqst *, struct nlm_file **, - struct nfs_fh *); + struct nlm_lock *); void nlm_release_file(struct nlm_file *); void nlmsvc_release_lockowner(struct nlm_lock *); void nlmsvc_mark_resources(struct net *); -- cgit v1.2.3 From 4dcc4874deb41a11ece9c6e8858385235463c1ac Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Aug 2021 15:19:05 +0200 Subject: block: cleanup the lockdep handling in *alloc_disk Pass the lockdep name to the low-level __blk_alloc_disk helper and hardcode the name for it given that the number of minors or node_id are not very useful information. While this passes a pointless argument for non-lockdep builds that is not really an issue as disk allocation is a probe time only slow path. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210816131910.615153-5-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq.c | 5 +++-- block/genhd.c | 8 +++++--- include/linux/blk-mq.h | 10 +++------- include/linux/genhd.h | 23 ++++++----------------- 4 files changed, 17 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index d2725f94491d..4c56e43e6992 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3133,7 +3133,8 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) } EXPORT_SYMBOL(blk_mq_init_queue); -struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata) +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, + struct lock_class_key *lkclass) { struct request_queue *q; struct gendisk *disk; @@ -3142,7 +3143,7 @@ struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata) if (IS_ERR(q)) return ERR_CAST(q); - disk = __alloc_disk_node(0, set->numa_node); + disk = __alloc_disk_node(0, set->numa_node, lkclass); if (!disk) { blk_cleanup_queue(q); return ERR_PTR(-ENOMEM); diff --git a/block/genhd.c b/block/genhd.c index 731a46063132..2ad2b25dfc87 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1254,7 +1254,8 @@ dev_t blk_lookup_devt(const char *name, int partno) return devt; } -struct gendisk *__alloc_disk_node(int minors, int node_id) +struct gendisk *__alloc_disk_node(int minors, int node_id, + struct lock_class_key *lkclass) { struct gendisk *disk; @@ -1282,6 +1283,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) disk_to_dev(disk)->type = &disk_type; device_initialize(disk_to_dev(disk)); inc_diskseq(disk); + lockdep_init_map(&disk->lockdep_map, "(bio completion)", lkclass, 0); #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED INIT_LIST_HEAD(&disk->slave_bdevs); #endif @@ -1298,7 +1300,7 @@ out_free_disk: } EXPORT_SYMBOL(__alloc_disk_node); -struct gendisk *__blk_alloc_disk(int node) +struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass) { struct request_queue *q; struct gendisk *disk; @@ -1307,7 +1309,7 @@ struct gendisk *__blk_alloc_disk(int node) if (!q) return NULL; - disk = __alloc_disk_node(0, node); + disk = __alloc_disk_node(0, node, lkclass); if (!disk) { blk_cleanup_queue(q); return NULL; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 22215db36122..13ba1861e688 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -432,18 +432,14 @@ enum { ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, + struct lock_class_key *lkclass); #define blk_mq_alloc_disk(set, queuedata) \ ({ \ static struct lock_class_key __key; \ - struct gendisk *__disk = __blk_mq_alloc_disk(set, queuedata); \ \ - if (!IS_ERR(__disk)) \ - lockdep_init_map(&__disk->lockdep_map, \ - "(bio completion)", &__key, 0); \ - __disk; \ + __blk_mq_alloc_disk(set, queuedata, &__key); \ }) -struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, - void *queuedata); struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index b47e297cd551..3d2e5ee30677 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -259,27 +259,21 @@ static inline sector_t get_capacity(struct gendisk *disk) int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); -extern struct gendisk *__alloc_disk_node(int minors, int node_id); +struct gendisk *__alloc_disk_node(int minors, int node_id, + struct lock_class_key *lkclass); extern void put_disk(struct gendisk *disk); #define alloc_disk_node(minors, node_id) \ ({ \ static struct lock_class_key __key; \ - const char *__name; \ - struct gendisk *__disk; \ \ - __name = "(gendisk_completion)"#minors"("#node_id")"; \ - \ - __disk = __alloc_disk_node(minors, node_id); \ - \ - if (__disk) \ - lockdep_init_map(&__disk->lockdep_map, __name, &__key, 0); \ - \ - __disk; \ + __alloc_disk_node(minors, node_id, &__key); \ }) #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) +struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); + /** * blk_alloc_disk - allocate a gendisk structure * @node_id: numa node to allocate on @@ -291,15 +285,10 @@ extern void put_disk(struct gendisk *disk); */ #define blk_alloc_disk(node_id) \ ({ \ - struct gendisk *__disk = __blk_alloc_disk(node_id); \ static struct lock_class_key __key; \ \ - if (__disk) \ - lockdep_init_map(&__disk->lockdep_map, \ - "(bio completion)", &__key, 0); \ - __disk; \ + __blk_alloc_disk(node_id, &__key); \ }) -struct gendisk *__blk_alloc_disk(int node); void blk_cleanup_disk(struct gendisk *disk); int __register_blkdev(unsigned int major, const char *name, -- cgit v1.2.3 From 9c2b9dbafc067e173db30c4fd0636392d27944e8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Aug 2021 15:19:06 +0200 Subject: block: remove alloc_disk and alloc_disk_node Most drivers should use and have been converted to use blk_alloc_disk and blk_mq_alloc_disk. Only the scsi ULPs and dasd still allocate a disk separately from the request_queue, so don't bother with convenience macros for something that should not see significant new users and remove these wrappers. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210816131910.615153-6-hch@lst.de Signed-off-by: Jens Axboe --- drivers/s390/block/dasd_genhd.c | 5 ++++- drivers/scsi/sd.c | 3 ++- drivers/scsi/sr.c | 4 +++- include/linux/genhd.h | 10 ---------- 4 files changed, 9 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 493e8469893c..07a69b19dd31 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -24,6 +24,8 @@ #include "dasd_int.h" +static struct lock_class_key dasd_bio_compl_lkclass; + /* * Allocate and register gendisk structure for device. */ @@ -38,7 +40,8 @@ int dasd_gendisk_alloc(struct dasd_block *block) if (base->devindex >= DASD_PER_MAJOR) return -EBUSY; - gdp = alloc_disk(1 << DASD_PARTN_BITS); + gdp = __alloc_disk_node(1 << DASD_PARTN_BITS, NUMA_NO_NODE, + &dasd_bio_compl_lkclass); if (!gdp) return -ENOMEM; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 5b5b8266e142..a9535c6484de 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -129,6 +129,7 @@ static DEFINE_MUTEX(sd_ref_mutex); static struct kmem_cache *sd_cdb_cache; static mempool_t *sd_cdb_pool; static mempool_t *sd_page_pool; +static struct lock_class_key sd_bio_compl_lkclass; static const char *sd_cache_types[] = { "write through", "none", "write back", @@ -3408,7 +3409,7 @@ static int sd_probe(struct device *dev) if (!sdkp) goto out; - gd = alloc_disk(SD_MINORS); + gd = __alloc_disk_node(SD_MINORS, NUMA_NO_NODE, &sd_bio_compl_lkclass); if (!gd) goto out_free; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 94c254e9012e..fee2bdfe6132 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -106,6 +106,8 @@ static struct scsi_driver sr_template = { static unsigned long sr_index_bits[SR_DISKS / BITS_PER_LONG]; static DEFINE_SPINLOCK(sr_index_lock); +static struct lock_class_key sr_bio_compl_lkclass; + /* This semaphore is used to mediate the 0->1 reference get in the * face of object destruction (i.e. we can't allow a get on an * object after last put) */ @@ -712,7 +714,7 @@ static int sr_probe(struct device *dev) kref_init(&cd->kref); - disk = alloc_disk(1); + disk = __alloc_disk_node(1, NUMA_NO_NODE, &sr_bio_compl_lkclass); if (!disk) goto fail_free; mutex_init(&cd->lock); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 3d2e5ee30677..ceda9b255dba 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -262,16 +262,6 @@ void blk_drop_partitions(struct gendisk *disk); struct gendisk *__alloc_disk_node(int minors, int node_id, struct lock_class_key *lkclass); extern void put_disk(struct gendisk *disk); - -#define alloc_disk_node(minors, node_id) \ -({ \ - static struct lock_class_key __key; \ - \ - __alloc_disk_node(minors, node_id, &__key); \ -}) - -#define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) - struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); /** -- cgit v1.2.3 From a58bd7683fcb60ae24c8572f932b48bc65719b7c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Aug 2021 15:19:07 +0200 Subject: block: remove the minors argument to __alloc_disk_node This was a leftover from the legacy alloc_disk interface. Switch the scsi ULPs and dasd to set ->minors directly like all other drivers and remove the argument. Signed-off-by: Christoph Hellwig Reviewed-by: Stefan Haberland [dasd] Link: https://lore.kernel.org/r/20210816131910.615153-7-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq.c | 2 +- block/genhd.c | 6 ++---- drivers/s390/block/dasd_genhd.c | 4 ++-- drivers/scsi/sd.c | 3 ++- drivers/scsi/sr.c | 3 ++- include/linux/genhd.h | 3 +-- 6 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 4c56e43e6992..8ac30c343c06 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3143,7 +3143,7 @@ struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, if (IS_ERR(q)) return ERR_CAST(q); - disk = __alloc_disk_node(0, set->numa_node, lkclass); + disk = __alloc_disk_node(set->numa_node, lkclass); if (!disk) { blk_cleanup_queue(q); return ERR_PTR(-ENOMEM); diff --git a/block/genhd.c b/block/genhd.c index 2ad2b25dfc87..caeda726189c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1254,8 +1254,7 @@ dev_t blk_lookup_devt(const char *name, int partno) return devt; } -struct gendisk *__alloc_disk_node(int minors, int node_id, - struct lock_class_key *lkclass) +struct gendisk *__alloc_disk_node(int node_id, struct lock_class_key *lkclass) { struct gendisk *disk; @@ -1277,7 +1276,6 @@ struct gendisk *__alloc_disk_node(int minors, int node_id, if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL)) goto out_destroy_part_tbl; - disk->minors = minors; rand_initialize_disk(disk); disk_to_dev(disk)->class = &block_class; disk_to_dev(disk)->type = &disk_type; @@ -1309,7 +1307,7 @@ struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass) if (!q) return NULL; - disk = __alloc_disk_node(0, node, lkclass); + disk = __alloc_disk_node(node, lkclass); if (!disk) { blk_cleanup_queue(q); return NULL; diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 07a69b19dd31..6e44515b4d33 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -40,14 +40,14 @@ int dasd_gendisk_alloc(struct dasd_block *block) if (base->devindex >= DASD_PER_MAJOR) return -EBUSY; - gdp = __alloc_disk_node(1 << DASD_PARTN_BITS, NUMA_NO_NODE, - &dasd_bio_compl_lkclass); + gdp = __alloc_disk_node(NUMA_NO_NODE, &dasd_bio_compl_lkclass); if (!gdp) return -ENOMEM; /* Initialize gendisk structure. */ gdp->major = DASD_MAJOR; gdp->first_minor = base->devindex << DASD_PARTN_BITS; + gdp->minors = 1 << DASD_PARTN_BITS; gdp->fops = &dasd_device_operations; /* diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index a9535c6484de..1c6b8f012219 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3409,7 +3409,7 @@ static int sd_probe(struct device *dev) if (!sdkp) goto out; - gd = __alloc_disk_node(SD_MINORS, NUMA_NO_NODE, &sd_bio_compl_lkclass); + gd = __alloc_disk_node(NUMA_NO_NODE, &sd_bio_compl_lkclass); if (!gd) goto out_free; @@ -3455,6 +3455,7 @@ static int sd_probe(struct device *dev) gd->major = sd_major((index & 0xf0) >> 4); gd->first_minor = ((index & 0xf) << 4) | (index & 0xfff00); + gd->minors = SD_MINORS; gd->fops = &sd_fops; gd->private_data = &sdkp->driver; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index fee2bdfe6132..2c45b4140e67 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -714,7 +714,7 @@ static int sr_probe(struct device *dev) kref_init(&cd->kref); - disk = __alloc_disk_node(1, NUMA_NO_NODE, &sr_bio_compl_lkclass); + disk = __alloc_disk_node(NUMA_NO_NODE, &sr_bio_compl_lkclass); if (!disk) goto fail_free; mutex_init(&cd->lock); @@ -731,6 +731,7 @@ static int sr_probe(struct device *dev) disk->major = SCSI_CDROM_MAJOR; disk->first_minor = minor; + disk->minors = 1; sprintf(disk->disk_name, "sr%d", minor); disk->fops = &sr_bdops; disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index ceda9b255dba..d20f101be758 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -259,8 +259,7 @@ static inline sector_t get_capacity(struct gendisk *disk) int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); -struct gendisk *__alloc_disk_node(int minors, int node_id, - struct lock_class_key *lkclass); +struct gendisk *__alloc_disk_node(int node_id, struct lock_class_key *lkclass); extern void put_disk(struct gendisk *disk); struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); -- cgit v1.2.3 From 4a1fa41d304c7129328d4d5c7f31715b95e23b29 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Aug 2021 15:19:08 +0200 Subject: block: pass a request_queue to __blk_alloc_disk Pass in a request_queue and assign disk->queue in __blk_alloc_disk to ensure struct gendisk always has a valid ->queue pointer. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210816131910.615153-8-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq.c | 3 +-- block/genhd.c | 7 ++++--- drivers/s390/block/dasd_genhd.c | 4 ++-- drivers/scsi/sd.c | 4 ++-- drivers/scsi/sr.c | 4 ++-- include/linux/genhd.h | 3 ++- 6 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 8ac30c343c06..2ca7e7c94b18 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3143,12 +3143,11 @@ struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, if (IS_ERR(q)) return ERR_CAST(q); - disk = __alloc_disk_node(set->numa_node, lkclass); + disk = __alloc_disk_node(q, set->numa_node, lkclass); if (!disk) { blk_cleanup_queue(q); return ERR_PTR(-ENOMEM); } - disk->queue = q; return disk; } EXPORT_SYMBOL(__blk_mq_alloc_disk); diff --git a/block/genhd.c b/block/genhd.c index caeda726189c..f18122ee2778 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1254,7 +1254,8 @@ dev_t blk_lookup_devt(const char *name, int partno) return devt; } -struct gendisk *__alloc_disk_node(int node_id, struct lock_class_key *lkclass) +struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, + struct lock_class_key *lkclass) { struct gendisk *disk; @@ -1281,6 +1282,7 @@ struct gendisk *__alloc_disk_node(int node_id, struct lock_class_key *lkclass) disk_to_dev(disk)->type = &disk_type; device_initialize(disk_to_dev(disk)); inc_diskseq(disk); + disk->queue = q; lockdep_init_map(&disk->lockdep_map, "(bio completion)", lkclass, 0); #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED INIT_LIST_HEAD(&disk->slave_bdevs); @@ -1307,12 +1309,11 @@ struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass) if (!q) return NULL; - disk = __alloc_disk_node(node, lkclass); + disk = __alloc_disk_node(q, node, lkclass); if (!disk) { blk_cleanup_queue(q); return NULL; } - disk->queue = q; return disk; } EXPORT_SYMBOL(__blk_alloc_disk); diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 6e44515b4d33..fa966e0db6ca 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -40,7 +40,8 @@ int dasd_gendisk_alloc(struct dasd_block *block) if (base->devindex >= DASD_PER_MAJOR) return -EBUSY; - gdp = __alloc_disk_node(NUMA_NO_NODE, &dasd_bio_compl_lkclass); + gdp = __alloc_disk_node(block->request_queue, NUMA_NO_NODE, + &dasd_bio_compl_lkclass); if (!gdp) return -ENOMEM; @@ -76,7 +77,6 @@ int dasd_gendisk_alloc(struct dasd_block *block) test_bit(DASD_FLAG_DEVICE_RO, &base->flags)) set_disk_ro(gdp, 1); dasd_add_link_to_gendisk(gdp, base); - gdp->queue = block->request_queue; block->gdp = gdp; set_capacity(block->gdp, 0); device_add_disk(&base->cdev->dev, block->gdp, NULL); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 1c6b8f012219..610ebba0d66e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3409,7 +3409,8 @@ static int sd_probe(struct device *dev) if (!sdkp) goto out; - gd = __alloc_disk_node(NUMA_NO_NODE, &sd_bio_compl_lkclass); + gd = __alloc_disk_node(sdp->request_queue, NUMA_NO_NODE, + &sd_bio_compl_lkclass); if (!gd) goto out_free; @@ -3459,7 +3460,6 @@ static int sd_probe(struct device *dev) gd->fops = &sd_fops; gd->private_data = &sdkp->driver; - gd->queue = sdkp->device->request_queue; /* defaults, until the device tells us otherwise */ sdp->sector_size = 512; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 2c45b4140e67..a0df27db4d61 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -714,7 +714,8 @@ static int sr_probe(struct device *dev) kref_init(&cd->kref); - disk = __alloc_disk_node(NUMA_NO_NODE, &sr_bio_compl_lkclass); + disk = __alloc_disk_node(sdev->request_queue, NUMA_NO_NODE, + &sr_bio_compl_lkclass); if (!disk) goto fail_free; mutex_init(&cd->lock); @@ -765,7 +766,6 @@ static int sr_probe(struct device *dev) set_capacity(disk, cd->capacity); disk->private_data = &cd->driver; - disk->queue = sdev->request_queue; if (register_cdrom(disk, &cd->cdi)) goto fail_minor; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index d20f101be758..13e90e6231d8 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -259,7 +259,8 @@ static inline sector_t get_capacity(struct gendisk *disk) int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); -struct gendisk *__alloc_disk_node(int node_id, struct lock_class_key *lkclass); +struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, + struct lock_class_key *lkclass); extern void put_disk(struct gendisk *disk); struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); -- cgit v1.2.3 From 61a35cfc26334fe1c8e970ca8fafeae2daae257d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Aug 2021 15:19:09 +0200 Subject: block: hold a request_queue reference for the lifetime of struct gendisk Acquire the queue ref dropped in disk_release in __blk_alloc_disk so any allocate gendisk always has a queue reference. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210816131910.615153-9-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 19 +++++++------------ include/linux/genhd.h | 1 - 2 files changed, 7 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index f18122ee2778..6294517cebe6 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -551,15 +551,6 @@ void device_add_disk(struct device *parent, struct gendisk *disk, register_disk(parent, disk, groups); blk_register_queue(disk); - /* - * Take an extra ref on queue which will be put on disk_release() - * so that it sticks around as long as @disk is there. - */ - if (blk_get_queue(disk->queue)) - set_bit(GD_QUEUE_REF, &disk->state); - else - WARN_ON_ONCE(1); - disk_add_events(disk); blk_integrity_add(disk); } @@ -1087,8 +1078,7 @@ static void disk_release(struct device *dev) disk_release_events(disk); kfree(disk->random); xa_destroy(&disk->part_tbl); - if (test_bit(GD_QUEUE_REF, &disk->state) && disk->queue) - blk_put_queue(disk->queue); + blk_put_queue(disk->queue); iput(disk->part0->bd_inode); /* frees the disk */ } @@ -1259,9 +1249,12 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, { struct gendisk *disk; + if (!blk_get_queue(q)) + return NULL; + disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id); if (!disk) - return NULL; + goto out_put_queue; disk->bdi = bdi_alloc(node_id); if (!disk->bdi) @@ -1296,6 +1289,8 @@ out_free_bdi: bdi_put(disk->bdi); out_free_disk: kfree(disk); +out_put_queue: + blk_put_queue(q); return NULL; } EXPORT_SYMBOL(__alloc_disk_node); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 13e90e6231d8..55acefdd8a20 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -149,7 +149,6 @@ struct gendisk { unsigned long state; #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 -#define GD_QUEUE_REF 2 struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ -- cgit v1.2.3 From d152c682f03ceb65c0d9663d4ba6ee2d46aa784d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Aug 2021 15:46:24 +0200 Subject: block: add an explicit ->disk backpointer to the request_queue Replace the magic lookup through the kobject tree with an explicit backpointer, given that the device model links are set up and torn down at times when I/O is still possible, leading to potential NULL or invalid pointer dereferences. Fixes: edb0872f44ec ("block: move the bdi from the request_queue to the gendisk") Reported-by: syzbot Signed-off-by: Christoph Hellwig Tested-by: Sven Schnelle Link: https://lore.kernel.org/r/20210816134624.GA24234@lst.de Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 2 +- block/blk-cgroup.c | 4 ++-- block/blk-mq.c | 2 +- block/blk-settings.c | 8 ++++---- block/blk-sysfs.c | 13 ++++++------- block/blk-wbt.c | 10 +++++----- block/genhd.c | 2 ++ include/linux/blkdev.h | 5 ++--- include/trace/events/kyber.h | 6 +++--- 9 files changed, 26 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index e92bc0348433..480e1a134859 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5269,7 +5269,7 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) switch (ioprio_class) { default: pr_err("bdi %s: bfq: bad prio class %d\n", - bdi_dev_name(queue_to_disk(bfqq->bfqd->queue)->bdi), + bdi_dev_name(bfqq->bfqd->queue->disk->bdi), ioprio_class); fallthrough; case IOPRIO_CLASS_NONE: diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index b8ec47dcce42..f575aa42922b 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -489,9 +489,9 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, const char *blkg_dev_name(struct blkcg_gq *blkg) { - if (!queue_has_disk(blkg->q) || !queue_to_disk(blkg->q)->bdi->dev) + if (!blkg->q->disk || !blkg->q->disk->bdi->dev) return NULL; - return bdi_dev_name(queue_to_disk(blkg->q)->bdi); + return bdi_dev_name(blkg->q->disk->bdi); } /** diff --git a/block/blk-mq.c b/block/blk-mq.c index 2ca7e7c94b18..0a33d16a7298 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -525,7 +525,7 @@ void blk_mq_free_request(struct request *rq) __blk_mq_dec_active_requests(hctx); if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) - laptop_io_completion(queue_to_disk(q)->bdi); + laptop_io_completion(q->disk->bdi); rq_qos_done(q, rq); diff --git a/block/blk-settings.c b/block/blk-settings.c index 3613d2cc0688..a7c857ad7d10 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -141,9 +141,9 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto limits->logical_block_size >> SECTOR_SHIFT); limits->max_sectors = max_sectors; - if (!queue_has_disk(q)) + if (!q->disk) return; - queue_to_disk(q)->bdi->io_pages = max_sectors >> (PAGE_SHIFT - 9); + q->disk->bdi->io_pages = max_sectors >> (PAGE_SHIFT - 9); } EXPORT_SYMBOL(blk_queue_max_hw_sectors); @@ -475,9 +475,9 @@ EXPORT_SYMBOL(blk_limits_io_opt); void blk_queue_io_opt(struct request_queue *q, unsigned int opt) { blk_limits_io_opt(&q->limits, opt); - if (!queue_has_disk(q)) + if (!q->disk) return; - queue_to_disk(q)->bdi->ra_pages = + q->disk->bdi->ra_pages = max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES); } EXPORT_SYMBOL(blk_queue_io_opt); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 586507a5b8c2..7fd99487300c 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -90,9 +90,9 @@ static ssize_t queue_ra_show(struct request_queue *q, char *page) { unsigned long ra_kb; - if (!queue_has_disk(q)) + if (!q->disk) return -EINVAL; - ra_kb = queue_to_disk(q)->bdi->ra_pages << (PAGE_SHIFT - 10); + ra_kb = q->disk->bdi->ra_pages << (PAGE_SHIFT - 10); return queue_var_show(ra_kb, page); } @@ -102,12 +102,12 @@ queue_ra_store(struct request_queue *q, const char *page, size_t count) unsigned long ra_kb; ssize_t ret; - if (!queue_has_disk(q)) + if (!q->disk) return -EINVAL; ret = queue_var_store(&ra_kb, page, count); if (ret < 0) return ret; - queue_to_disk(q)->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); + q->disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); return ret; } @@ -254,9 +254,8 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) spin_lock_irq(&q->queue_lock); q->limits.max_sectors = max_sectors_kb << 1; - if (queue_has_disk(q)) - queue_to_disk(q)->bdi->io_pages = - max_sectors_kb >> (PAGE_SHIFT - 10); + if (q->disk) + q->disk->bdi->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10); spin_unlock_irq(&q->queue_lock); return ret; diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 31086afaad9c..874c1c37bf0c 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -97,7 +97,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) */ static bool wb_recent_wait(struct rq_wb *rwb) { - struct bdi_writeback *wb = &queue_to_disk(rwb->rqos.q)->bdi->wb; + struct bdi_writeback *wb = &rwb->rqos.q->disk->bdi->wb; return time_before(jiffies, wb->dirty_sleep + HZ); } @@ -234,7 +234,7 @@ enum { static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) { - struct backing_dev_info *bdi = queue_to_disk(rwb->rqos.q)->bdi; + struct backing_dev_info *bdi = rwb->rqos.q->disk->bdi; struct rq_depth *rqd = &rwb->rq_depth; u64 thislat; @@ -287,7 +287,7 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) static void rwb_trace_step(struct rq_wb *rwb, const char *msg) { - struct backing_dev_info *bdi = queue_to_disk(rwb->rqos.q)->bdi; + struct backing_dev_info *bdi = rwb->rqos.q->disk->bdi; struct rq_depth *rqd = &rwb->rq_depth; trace_wbt_step(bdi, msg, rqd->scale_step, rwb->cur_win_nsec, @@ -359,8 +359,8 @@ static void wb_timer_fn(struct blk_stat_callback *cb) status = latency_exceeded(rwb, cb->stat); - trace_wbt_timer(queue_to_disk(rwb->rqos.q)->bdi, status, - rqd->scale_step, inflight); + trace_wbt_timer(rwb->rqos.q->disk->bdi, status, rqd->scale_step, + inflight); /* * If we exceeded the latency target, step down. If we did not, diff --git a/block/genhd.c b/block/genhd.c index 6294517cebe6..02cd9ec93e52 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1078,6 +1078,7 @@ static void disk_release(struct device *dev) disk_release_events(disk); kfree(disk->random); xa_destroy(&disk->part_tbl); + disk->queue->disk = NULL; blk_put_queue(disk->queue); iput(disk->part0->bd_inode); /* frees the disk */ } @@ -1276,6 +1277,7 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, device_initialize(disk_to_dev(disk)); inc_diskseq(disk); disk->queue = q; + q->disk = disk; lockdep_init_map(&disk->lockdep_map, "(bio completion)", lkclass, 0); #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED INIT_LIST_HEAD(&disk->slave_bdevs); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index df404c1fb087..22b5b8502d2a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -421,6 +421,8 @@ struct request_queue { spinlock_t queue_lock; + struct gendisk *disk; + /* * queue kobject */ @@ -661,9 +663,6 @@ extern void blk_clear_pm_only(struct request_queue *q); dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ (dir), (attrs)) -#define queue_has_disk(q) ((q)->kobj.parent != NULL) -#define queue_to_disk(q) (dev_to_disk(kobj_to_dev((q)->kobj.parent))) - static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; diff --git a/include/trace/events/kyber.h b/include/trace/events/kyber.h index f9802562edf6..491098a0d8ed 100644 --- a/include/trace/events/kyber.h +++ b/include/trace/events/kyber.h @@ -30,7 +30,7 @@ TRACE_EVENT(kyber_latency, ), TP_fast_assign( - __entry->dev = disk_devt(queue_to_disk(q)); + __entry->dev = disk_devt(q->disk); strlcpy(__entry->domain, domain, sizeof(__entry->domain)); strlcpy(__entry->type, type, sizeof(__entry->type)); __entry->percentile = percentile; @@ -59,7 +59,7 @@ TRACE_EVENT(kyber_adjust, ), TP_fast_assign( - __entry->dev = disk_devt(queue_to_disk(q)); + __entry->dev = disk_devt(q->disk); strlcpy(__entry->domain, domain, sizeof(__entry->domain)); __entry->depth = depth; ), @@ -81,7 +81,7 @@ TRACE_EVENT(kyber_throttled, ), TP_fast_assign( - __entry->dev = disk_devt(queue_to_disk(q)); + __entry->dev = disk_devt(q->disk); strlcpy(__entry->domain, domain, sizeof(__entry->domain)); ), -- cgit v1.2.3 From 83cbce9574462c6b4eed6797bdaf18fae6859ab3 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Wed, 18 Aug 2021 16:45:40 +0200 Subject: block: add error handling for device_add_disk / add_disk Properly unwind on errors in device_add_disk. This is the initial work as drivers are not converted yet, which will follow in separate patches. Signed-off-by: Luis Chamberlain [hch: major rebase. All bugs are probably mine] Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20210818144542.19305-10-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 92 ++++++++++++++++++++++++++++++++------------------- include/linux/genhd.h | 8 ++--- 2 files changed, 62 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index a54b4849242c..a925f773145f 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -417,11 +417,8 @@ static void disk_scan_partitions(struct gendisk *disk) * * This function registers the partitioning information in @disk * with the kernel. - * - * FIXME: error handling */ - -void device_add_disk(struct device *parent, struct gendisk *disk, +int device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups) { @@ -444,7 +441,8 @@ void device_add_disk(struct device *parent, struct gendisk *disk, * and all partitions from the extended dev_t space. */ if (disk->major) { - WARN_ON(!disk->minors); + if (WARN_ON(!disk->minors)) + return -EINVAL; if (disk->minors > DISK_MAX_PARTS) { pr_err("block: can't allocate more than %d partitions\n", @@ -452,19 +450,20 @@ void device_add_disk(struct device *parent, struct gendisk *disk, disk->minors = DISK_MAX_PARTS; } } else { - WARN_ON(disk->minors); + if (WARN_ON(disk->minors)) + return -EINVAL; ret = blk_alloc_ext_minor(); - if (ret < 0) { - WARN_ON(1); - return; - } + if (ret < 0) + return ret; disk->major = BLOCK_EXT_MAJOR; disk->first_minor = MINOR(ret); disk->flags |= GENHD_FL_EXT_DEVT; } - disk_alloc_events(disk); + ret = disk_alloc_events(disk); + if (ret) + goto out_free_ext_minor; /* delay uevents, until we scanned partition table */ dev_set_uevent_suppress(ddev, 1); @@ -474,15 +473,14 @@ void device_add_disk(struct device *parent, struct gendisk *disk, dev_set_name(ddev, "%s", disk->disk_name); if (!(disk->flags & GENHD_FL_HIDDEN)) ddev->devt = MKDEV(disk->major, disk->first_minor); - if (device_add(ddev)) - return; + ret = device_add(ddev); + if (ret) + goto out_disk_release_events; if (!sysfs_deprecated) { ret = sysfs_create_link(block_depr, &ddev->kobj, kobject_name(&ddev->kobj)); - if (ret) { - device_del(ddev); - return; - } + if (ret) + goto out_device_del; } /* @@ -492,23 +490,25 @@ void device_add_disk(struct device *parent, struct gendisk *disk, */ pm_runtime_set_memalloc_noio(ddev, true); - blk_integrity_add(disk); + ret = blk_integrity_add(disk); + if (ret) + goto out_del_block_link; disk->part0->bd_holder_dir = kobject_create_and_add("holders", &ddev->kobj); + if (!disk->part0->bd_holder_dir) + goto out_del_integrity; disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); + if (!disk->slave_dir) + goto out_put_holder_dir; - /* - * XXX: this is a mess, can't wait for real error handling in add_disk. - * Make sure ->slave_dir is NULL if we failed some of the registration - * so that the cleanup in bd_unlink_disk_holder works properly. - */ - if (bd_register_pending_holders(disk) < 0) { - kobject_put(disk->slave_dir); - disk->slave_dir = NULL; - } + ret = bd_register_pending_holders(disk); + if (ret < 0) + goto out_put_slave_dir; - blk_register_queue(disk); + ret = blk_register_queue(disk); + if (ret) + goto out_put_slave_dir; if (disk->flags & GENHD_FL_HIDDEN) { /* @@ -520,13 +520,13 @@ void device_add_disk(struct device *parent, struct gendisk *disk, } else { ret = bdi_register(disk->bdi, "%u:%u", disk->major, disk->first_minor); - WARN_ON(ret); + if (ret) + goto out_unregister_queue; bdi_set_owner(disk->bdi, ddev); - if (disk->bdi->dev) { - ret = sysfs_create_link(&ddev->kobj, - &disk->bdi->dev->kobj, "bdi"); - WARN_ON(ret); - } + ret = sysfs_create_link(&ddev->kobj, + &disk->bdi->dev->kobj, "bdi"); + if (ret) + goto out_unregister_bdi; bdev_add(disk->part0, ddev->devt); disk_scan_partitions(disk); @@ -541,6 +541,30 @@ void device_add_disk(struct device *parent, struct gendisk *disk, disk_update_readahead(disk); disk_add_events(disk); + return 0; + +out_unregister_bdi: + if (!(disk->flags & GENHD_FL_HIDDEN)) + bdi_unregister(disk->bdi); +out_unregister_queue: + blk_unregister_queue(disk); +out_put_slave_dir: + kobject_put(disk->slave_dir); +out_put_holder_dir: + kobject_put(disk->part0->bd_holder_dir); +out_del_integrity: + blk_integrity_del(disk); +out_del_block_link: + if (!sysfs_deprecated) + sysfs_remove_link(block_depr, dev_name(ddev)); +out_device_del: + device_del(ddev); +out_disk_release_events: + disk_release_events(disk); +out_free_ext_minor: + if (disk->major == BLOCK_EXT_MAJOR) + blk_free_ext_minor(disk->first_minor); + return WARN_ON_ONCE(ret); /* keep until all callers handle errors */ } EXPORT_SYMBOL(device_add_disk); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 55acefdd8a20..c68d83c87f83 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -214,11 +214,11 @@ static inline dev_t disk_devt(struct gendisk *disk) void disk_uevent(struct gendisk *disk, enum kobject_action action); /* block/genhd.c */ -extern void device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups); -static inline void add_disk(struct gendisk *disk) +int device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups); +static inline int add_disk(struct gendisk *disk) { - device_add_disk(NULL, disk, NULL); + return device_add_disk(NULL, disk, NULL); } extern void del_gendisk(struct gendisk *gp); -- cgit v1.2.3 From a4aadd11ea4932588e6530ecd021ffe39f9d5adf Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Thu, 12 Aug 2021 12:14:34 +0800 Subject: io_uring: extract io_uring_files_cancel() in io_uring_task_cancel() Extract io_uring_files_cancel() call in io_uring_task_cancel() to make io_uring_files_cancel() and io_uring_task_cancel() coherent and easy to read. Signed-off-by: Hao Xu Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 04b650bcbbe5..ed13304e764c 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -17,7 +17,8 @@ static inline void io_uring_files_cancel(struct files_struct *files) } static inline void io_uring_task_cancel(void) { - return io_uring_files_cancel(NULL); + if (current->io_uring) + __io_uring_cancel(NULL); } static inline void io_uring_free(struct task_struct *tsk) { -- cgit v1.2.3 From f552a27afe67f05c47bb0c33b92af2a23b684c31 Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Thu, 12 Aug 2021 12:14:35 +0800 Subject: io_uring: remove files pointer in cancellation functions When doing cancellation, we use a parameter to indicate where it's from do_exit or exec. So a boolean value is good enough for this, remove the struct files* as it is not necessary. Signed-off-by: Hao Xu [axboe: fixup io_uring_files_cancel for !CONFIG_IO_URING] Signed-off-by: Jens Axboe --- fs/io_uring.c | 4 ++-- include/linux/io_uring.h | 10 +++++----- kernel/exit.c | 2 +- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 4f5a00707644..7626cad93f60 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9213,9 +9213,9 @@ static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) } } -void __io_uring_cancel(struct files_struct *files) +void __io_uring_cancel(bool cancel_all) { - io_uring_cancel_generic(!files, NULL); + io_uring_cancel_generic(cancel_all, NULL); } static void *io_uring_validate_mmap_request(struct file *file, diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index ed13304e764c..649a4d7c241b 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -7,18 +7,18 @@ #if defined(CONFIG_IO_URING) struct sock *io_uring_get_socket(struct file *file); -void __io_uring_cancel(struct files_struct *files); +void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); -static inline void io_uring_files_cancel(struct files_struct *files) +static inline void io_uring_files_cancel(void) { if (current->io_uring) - __io_uring_cancel(files); + __io_uring_cancel(false); } static inline void io_uring_task_cancel(void) { if (current->io_uring) - __io_uring_cancel(NULL); + __io_uring_cancel(true); } static inline void io_uring_free(struct task_struct *tsk) { @@ -33,7 +33,7 @@ static inline struct sock *io_uring_get_socket(struct file *file) static inline void io_uring_task_cancel(void) { } -static inline void io_uring_files_cancel(struct files_struct *files) +static inline void io_uring_files_cancel(void) { } static inline void io_uring_free(struct task_struct *tsk) diff --git a/kernel/exit.c b/kernel/exit.c index 9a89e7f36acb..91a43e57a32e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -777,7 +777,7 @@ void __noreturn do_exit(long code) schedule(); } - io_uring_files_cancel(tsk->files); + io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ /* sync mm's RSS info before statistics gathering */ -- cgit v1.2.3 From 8228e2c313194f13f1d1806ed5734a26c38d49ac Mon Sep 17 00:00:00 2001 From: Dmitry Kadashev Date: Thu, 8 Jul 2021 13:34:42 +0700 Subject: namei: add getname_uflags() There are a couple of places where we already open-code the (flags & AT_EMPTY_PATH) check and io_uring will likely add another one in the future. Let's just add a simple helper getname_uflags() that handles this directly and use it. Cc: Al Viro Cc: Christian Brauner Acked-by: Linus Torvalds Link: https://lore.kernel.org/io-uring/20210415100815.edrn4a7cy26wkowe@wittgenstein/ Signed-off-by: Christian Brauner Signed-off-by: Dmitry Kadashev Acked-by: Christian Brauner Link: https://lore.kernel.org/r/20210708063447.3556403-7-dkadashev@gmail.com Signed-off-by: Jens Axboe --- fs/exec.c | 8 ++------ fs/namei.c | 8 ++++++++ include/linux/fs.h | 1 + 3 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 38f63451b928..3b78b22addfb 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -2070,10 +2070,8 @@ SYSCALL_DEFINE5(execveat, const char __user *const __user *, envp, int, flags) { - int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; - return do_execveat(fd, - getname_flags(filename, lookup_flags, NULL), + getname_uflags(filename, flags), argv, envp, flags); } @@ -2091,10 +2089,8 @@ COMPAT_SYSCALL_DEFINE5(execveat, int, fd, const compat_uptr_t __user *, envp, int, flags) { - int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; - return compat_do_execveat(fd, - getname_flags(filename, lookup_flags, NULL), + getname_uflags(filename, flags), argv, envp, flags); } #endif diff --git a/fs/namei.c b/fs/namei.c index 522c35b33fea..41f58dabe84c 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -203,6 +203,14 @@ getname_flags(const char __user *filename, int flags, int *empty) return result; } +struct filename * +getname_uflags(const char __user *filename, int uflags) +{ + int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; + + return getname_flags(filename, flags, NULL); +} + struct filename * getname(const char __user * filename) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..26d41a445e81 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2786,6 +2786,7 @@ static inline struct file *file_clone_open(struct file *file) extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); +extern struct filename *getname_uflags(const char __user *, int); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern void putname(struct filename *name); -- cgit v1.2.3 From 6c7ef543df909dbdcd8cb24ef30627cba62a4e91 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 10 Aug 2021 09:29:55 -0600 Subject: fs: add kiocb alloc cache flag If this kiocb can safely use the polled bio allocation cache, then this flag must be set. Generally this can be set for polled IO, where we will not see IRQ completions of the request. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..0dcc5de779c9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -319,6 +319,8 @@ enum rw_hint { /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) +/* can use bio alloc cache */ +#define IOCB_ALLOC_CACHE (1 << 21) struct kiocb { struct file *ki_filp; -- cgit v1.2.3 From be4d234d7aebbfe0c233bc20b9cdef7ab3408ff4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 8 Mar 2021 11:37:47 -0700 Subject: bio: add allocation cache abstraction Add a per-cpu bio_set cache for bio allocations, enabling us to quickly recycle them instead of going through the slab allocator. This cache isn't IRQ safe, and hence is only really suitable for polled IO. Very simple - keeps a count of bio's in the cache, and maintains a max of 512 with a slack of 64. If we get above max + slack, we drop slack number of bio's. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/bio.c | 134 ++++++++++++++++++++++++++++++++++++++++----- include/linux/bio.h | 13 +++++ include/linux/blk_types.h | 1 + include/linux/cpuhotplug.h | 1 + 4 files changed, 135 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 6fa5c653283b..dbb0bc8e1ef7 100644 --- a/block/bio.c +++ b/block/bio.c @@ -25,6 +25,11 @@ #include "blk.h" #include "blk-rq-qos.h" +struct bio_alloc_cache { + struct bio_list free_list; + unsigned int nr; +}; + static struct biovec_slab { int nr_vecs; char *name; @@ -619,6 +624,53 @@ void guard_bio_eod(struct bio *bio) bio_truncate(bio, maxsector << 9); } +#define ALLOC_CACHE_MAX 512 +#define ALLOC_CACHE_SLACK 64 + +static void bio_alloc_cache_prune(struct bio_alloc_cache *cache, + unsigned int nr) +{ + unsigned int i = 0; + struct bio *bio; + + while ((bio = bio_list_pop(&cache->free_list)) != NULL) { + cache->nr--; + bio_free(bio); + if (++i == nr) + break; + } +} + +static int bio_cpu_dead(unsigned int cpu, struct hlist_node *node) +{ + struct bio_set *bs; + + bs = hlist_entry_safe(node, struct bio_set, cpuhp_dead); + if (bs->cache) { + struct bio_alloc_cache *cache = per_cpu_ptr(bs->cache, cpu); + + bio_alloc_cache_prune(cache, -1U); + } + return 0; +} + +static void bio_alloc_cache_destroy(struct bio_set *bs) +{ + int cpu; + + if (!bs->cache) + return; + + cpuhp_state_remove_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead); + for_each_possible_cpu(cpu) { + struct bio_alloc_cache *cache; + + cache = per_cpu_ptr(bs->cache, cpu); + bio_alloc_cache_prune(cache, -1U); + } + free_percpu(bs->cache); +} + /** * bio_put - release a reference to a bio * @bio: bio to release reference to @@ -629,16 +681,23 @@ void guard_bio_eod(struct bio *bio) **/ void bio_put(struct bio *bio) { - if (!bio_flagged(bio, BIO_REFFED)) - bio_free(bio); - else { + if (unlikely(bio_flagged(bio, BIO_REFFED))) { BIO_BUG_ON(!atomic_read(&bio->__bi_cnt)); + if (!atomic_dec_and_test(&bio->__bi_cnt)) + return; + } - /* - * last put frees it - */ - if (atomic_dec_and_test(&bio->__bi_cnt)) - bio_free(bio); + if (bio_flagged(bio, BIO_PERCPU_CACHE)) { + struct bio_alloc_cache *cache; + + bio_uninit(bio); + cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu()); + bio_list_add_head(&cache->free_list, bio); + if (++cache->nr > ALLOC_CACHE_MAX + ALLOC_CACHE_SLACK) + bio_alloc_cache_prune(cache, ALLOC_CACHE_SLACK); + put_cpu(); + } else { + bio_free(bio); } } EXPORT_SYMBOL(bio_put); @@ -1530,6 +1589,7 @@ int biovec_init_pool(mempool_t *pool, int pool_entries) */ void bioset_exit(struct bio_set *bs) { + bio_alloc_cache_destroy(bs); if (bs->rescue_workqueue) destroy_workqueue(bs->rescue_workqueue); bs->rescue_workqueue = NULL; @@ -1591,12 +1651,18 @@ int bioset_init(struct bio_set *bs, biovec_init_pool(&bs->bvec_pool, pool_size)) goto bad; - if (!(flags & BIOSET_NEED_RESCUER)) - return 0; - - bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0); - if (!bs->rescue_workqueue) - goto bad; + if (flags & BIOSET_NEED_RESCUER) { + bs->rescue_workqueue = alloc_workqueue("bioset", + WQ_MEM_RECLAIM, 0); + if (!bs->rescue_workqueue) + goto bad; + } + if (flags & BIOSET_PERCPU_CACHE) { + bs->cache = alloc_percpu(struct bio_alloc_cache); + if (!bs->cache) + goto bad; + cpuhp_state_add_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead); + } return 0; bad: @@ -1623,6 +1689,43 @@ int bioset_init_from_src(struct bio_set *bs, struct bio_set *src) } EXPORT_SYMBOL(bioset_init_from_src); +/** + * bio_alloc_kiocb - Allocate a bio from bio_set based on kiocb + * @kiocb: kiocb describing the IO + * @bs: bio_set to allocate from + * + * Description: + * Like @bio_alloc_bioset, but pass in the kiocb. The kiocb is only + * used to check if we should dip into the per-cpu bio_set allocation + * cache. The allocation uses GFP_KERNEL internally. + * + */ +struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs, + struct bio_set *bs) +{ + struct bio_alloc_cache *cache; + struct bio *bio; + + if (!(kiocb->ki_flags & IOCB_ALLOC_CACHE) || nr_vecs > BIO_INLINE_VECS) + return bio_alloc_bioset(GFP_KERNEL, nr_vecs, bs); + + cache = per_cpu_ptr(bs->cache, get_cpu()); + bio = bio_list_pop(&cache->free_list); + if (bio) { + cache->nr--; + put_cpu(); + bio_init(bio, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs); + bio->bi_pool = bs; + bio_set_flag(bio, BIO_PERCPU_CACHE); + return bio; + } + put_cpu(); + bio = bio_alloc_bioset(GFP_KERNEL, nr_vecs, bs); + bio_set_flag(bio, BIO_PERCPU_CACHE); + return bio; +} +EXPORT_SYMBOL_GPL(bio_alloc_kiocb); + static int __init init_bio(void) { int i; @@ -1637,6 +1740,9 @@ static int __init init_bio(void) SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); } + cpuhp_setup_state_multi(CPUHP_BIO_DEAD, "block/bio:dead", NULL, + bio_cpu_dead); + if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS)) panic("bio: can't allocate bios\n"); diff --git a/include/linux/bio.h b/include/linux/bio.h index 2203b686e1f0..89ad28213b1d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -401,6 +401,7 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors, enum { BIOSET_NEED_BVECS = BIT(0), BIOSET_NEED_RESCUER = BIT(1), + BIOSET_PERCPU_CACHE = BIT(2), }; extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); extern void bioset_exit(struct bio_set *); @@ -409,6 +410,8 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(gfp_t gfp, unsigned short nr_iovecs, struct bio_set *bs); +struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs, + struct bio_set *bs); struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); extern void bio_put(struct bio *); @@ -699,6 +702,11 @@ struct bio_set { struct kmem_cache *bio_slab; unsigned int front_pad; + /* + * per-cpu bio alloc cache + */ + struct bio_alloc_cache __percpu *cache; + mempool_t bio_pool; mempool_t bvec_pool; #if defined(CONFIG_BLK_DEV_INTEGRITY) @@ -715,6 +723,11 @@ struct bio_set { struct bio_list rescue_list; struct work_struct rescue_work; struct workqueue_struct *rescue_workqueue; + + /* + * Hot un-plug notifier for the per-cpu cache, if used + */ + struct hlist_node cpuhp_dead; }; static inline bool bioset_initialized(struct bio_set *bs) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 290f9061b29a..f68d4e8c775e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -301,6 +301,7 @@ enum { BIO_TRACKED, /* set if bio goes through the rq_qos path */ BIO_REMAPPED, BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ + BIO_PERCPU_CACHE, /* can participate in per-cpu alloc cache */ BIO_FLAG_LAST }; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f39b34b13871..fe72c8d6c980 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -46,6 +46,7 @@ enum cpuhp_state { CPUHP_ARM_OMAP_WAKE_DEAD, CPUHP_IRQ_POLL_DEAD, CPUHP_BLOCK_SOFTIRQ_DEAD, + CPUHP_BIO_DEAD, CPUHP_ACPI_CPUDRV_DEAD, CPUHP_S390_PFAULT_DEAD, CPUHP_BLK_MQ_DEAD, -- cgit v1.2.3 From 7f024fcd5c97dc70bb9121c80407cf3cf9be7159 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 23 Aug 2021 16:44:00 -0400 Subject: Keep read and write fds with each nlm_file We shouldn't really be using a read-only file descriptor to take a write lock. Most filesystems will put up with it. But NFS, for example, won't. Signed-off-by: J. Bruce Fields Signed-off-by: Chuck Lever --- fs/lockd/svc4proc.c | 4 +- fs/lockd/svclock.c | 25 ++++++++--- fs/lockd/svcproc.c | 4 +- fs/lockd/svcsubs.c | 102 ++++++++++++++++++++++++++++++-------------- fs/nfsd/lockd.c | 8 +++- include/linux/lockd/bind.h | 3 +- include/linux/lockd/lockd.h | 9 +++- 7 files changed, 111 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index bc496bbd696b..e10ae2c41279 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -40,13 +40,15 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, /* Obtain file pointer. Not used by FREE_ALL call. */ if (filp != NULL) { + int mode = lock_to_openmode(&lock->fl); + error = nlm_lookup_file(rqstp, &file, lock); if (error) goto no_locks; *filp = file; /* Set up the missing parts of the file_lock structure */ - lock->fl.fl_file = file->f_file; + lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; lock->fl.fl_lmops = &nlmsvc_lock_operations; nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid); diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index bcd180ba9957..a7b4c51667ad 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -471,6 +471,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, { struct nlm_block *block = NULL; int error; + int mode; __be32 ret; dprintk("lockd: nlmsvc_lock(%s/%ld, ty=%d, pi=%d, %Ld-%Ld, bl=%d)\n", @@ -524,7 +525,8 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, if (!wait) lock->fl.fl_flags &= ~FL_SLEEP; - error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL); + mode = lock_to_openmode(&lock->fl); + error = vfs_lock_file(file->f_file[mode], F_SETLK, &lock->fl, NULL); lock->fl.fl_flags &= ~FL_SLEEP; dprintk("lockd: vfs_lock_file returned %d\n", error); @@ -577,6 +579,7 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, struct nlm_lock *conflock, struct nlm_cookie *cookie) { int error; + int mode; __be32 ret; struct nlm_lockowner *test_owner; @@ -595,7 +598,8 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, /* If there's a conflicting lock, remember to clean up the test lock */ test_owner = (struct nlm_lockowner *)lock->fl.fl_owner; - error = vfs_test_lock(file->f_file, &lock->fl); + mode = lock_to_openmode(&lock->fl); + error = vfs_test_lock(file->f_file[mode], &lock->fl); if (error) { /* We can't currently deal with deferred test requests */ if (error == FILE_LOCK_DEFERRED) @@ -641,7 +645,7 @@ out: __be32 nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock) { - int error; + int error = 0; dprintk("lockd: nlmsvc_unlock(%s/%ld, pi=%d, %Ld-%Ld)\n", nlmsvc_file_inode(file)->i_sb->s_id, @@ -654,7 +658,12 @@ nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock) nlmsvc_cancel_blocked(net, file, lock); lock->fl.fl_type = F_UNLCK; - error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL); + if (file->f_file[O_RDONLY]) + error = vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, + &lock->fl, NULL); + if (file->f_file[O_WRONLY]) + error = vfs_lock_file(file->f_file[O_WRONLY], F_SETLK, + &lock->fl, NULL); return (error < 0)? nlm_lck_denied_nolocks : nlm_granted; } @@ -671,6 +680,7 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l { struct nlm_block *block; int status = 0; + int mode; dprintk("lockd: nlmsvc_cancel(%s/%ld, pi=%d, %Ld-%Ld)\n", nlmsvc_file_inode(file)->i_sb->s_id, @@ -686,7 +696,8 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l block = nlmsvc_lookup_block(file, lock); mutex_unlock(&file->f_mutex); if (block != NULL) { - vfs_cancel_lock(block->b_file->f_file, + mode = lock_to_openmode(&lock->fl); + vfs_cancel_lock(block->b_file->f_file[mode], &block->b_call->a_args.lock.fl); status = nlmsvc_unlink_block(block); nlmsvc_release_block(block); @@ -803,6 +814,7 @@ nlmsvc_grant_blocked(struct nlm_block *block) { struct nlm_file *file = block->b_file; struct nlm_lock *lock = &block->b_call->a_args.lock; + int mode; int error; loff_t fl_start, fl_end; @@ -828,7 +840,8 @@ nlmsvc_grant_blocked(struct nlm_block *block) lock->fl.fl_flags |= FL_SLEEP; fl_start = lock->fl.fl_start; fl_end = lock->fl.fl_end; - error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL); + mode = lock_to_openmode(&lock->fl); + error = vfs_lock_file(file->f_file[mode], F_SETLK, &lock->fl, NULL); lock->fl.fl_flags &= ~FL_SLEEP; lock->fl.fl_start = fl_start; lock->fl.fl_end = fl_end; diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index f4e5e0eb30fd..99696d3f6dd6 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -55,6 +55,7 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, struct nlm_host *host = NULL; struct nlm_file *file = NULL; struct nlm_lock *lock = &argp->lock; + int mode; __be32 error = 0; /* nfsd callbacks must have been installed for this procedure */ @@ -75,7 +76,8 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, *filp = file; /* Set up the missing parts of the file_lock structure */ - lock->fl.fl_file = file->f_file; + mode = lock_to_openmode(&lock->fl); + lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; lock->fl.fl_lmops = &nlmsvc_lock_operations; nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid); diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 13e6ffc219ec..cb3a7512c33e 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -71,14 +71,35 @@ static inline unsigned int file_hash(struct nfs_fh *f) return tmp & (FILE_NRHASH - 1); } +int lock_to_openmode(struct file_lock *lock) +{ + return (lock->fl_type == F_WRLCK) ? O_WRONLY : O_RDONLY; +} + +/* + * Open the file. Note that if we're reexporting, for example, + * this could block the lockd thread for a while. + * + * We have to make sure we have the right credential to open + * the file. + */ +static __be32 nlm_do_fopen(struct svc_rqst *rqstp, + struct nlm_file *file, int mode) +{ + struct file **fp = &file->f_file[mode]; + __be32 nfserr; + + if (*fp) + return 0; + nfserr = nlmsvc_ops->fopen(rqstp, &file->f_handle, fp, mode); + if (nfserr) + dprintk("lockd: open failed (error %d)\n", nfserr); + return nfserr; +} + /* * Lookup file info. If it doesn't exist, create a file info struct * and open a (VFS) file for the given inode. - * - * FIXME: - * Note that we open the file O_RDONLY even when creating write locks. - * This is not quite right, but for now, we assume the client performs - * the proper R/W checking. */ __be32 nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, @@ -87,42 +108,38 @@ nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, struct nlm_file *file; unsigned int hash; __be32 nfserr; + int mode; nlm_debug_print_fh("nlm_lookup_file", &lock->fh); hash = file_hash(&lock->fh); + mode = lock_to_openmode(&lock->fl); /* Lock file table */ mutex_lock(&nlm_file_mutex); hlist_for_each_entry(file, &nlm_files[hash], f_list) - if (!nfs_compare_fh(&file->f_handle, &lock->fh)) + if (!nfs_compare_fh(&file->f_handle, &lock->fh)) { + mutex_lock(&file->f_mutex); + nfserr = nlm_do_fopen(rqstp, file, mode); + mutex_unlock(&file->f_mutex); goto found; - + } nlm_debug_print_fh("creating file for", &lock->fh); nfserr = nlm_lck_denied_nolocks; file = kzalloc(sizeof(*file), GFP_KERNEL); if (!file) - goto out_unlock; + goto out_free; memcpy(&file->f_handle, &lock->fh, sizeof(struct nfs_fh)); mutex_init(&file->f_mutex); INIT_HLIST_NODE(&file->f_list); INIT_LIST_HEAD(&file->f_blocks); - /* - * Open the file. Note that if we're reexporting, for example, - * this could block the lockd thread for a while. - * - * We have to make sure we have the right credential to open - * the file. - */ - nfserr = nlmsvc_ops->fopen(rqstp, &lock->fh, &file->f_file); - if (nfserr) { - dprintk("lockd: open failed (error %d)\n", nfserr); - goto out_free; - } + nfserr = nlm_do_fopen(rqstp, file, mode); + if (nfserr) + goto out_unlock; hlist_add_head(&file->f_list, &nlm_files[hash]); @@ -130,7 +147,6 @@ found: dprintk("lockd: found file %p (count %d)\n", file, file->f_count); *result = file; file->f_count++; - nfserr = 0; out_unlock: mutex_unlock(&nlm_file_mutex); @@ -150,13 +166,34 @@ nlm_delete_file(struct nlm_file *file) nlm_debug_print_file("closing file", file); if (!hlist_unhashed(&file->f_list)) { hlist_del(&file->f_list); - nlmsvc_ops->fclose(file->f_file); + if (file->f_file[O_RDONLY]) + nlmsvc_ops->fclose(file->f_file[O_RDONLY]); + if (file->f_file[O_WRONLY]) + nlmsvc_ops->fclose(file->f_file[O_WRONLY]); kfree(file); } else { printk(KERN_WARNING "lockd: attempt to release unknown file!\n"); } } +static int nlm_unlock_files(struct nlm_file *file) +{ + struct file_lock lock; + struct file *f; + + lock.fl_type = F_UNLCK; + lock.fl_start = 0; + lock.fl_end = OFFSET_MAX; + for (f = file->f_file[0]; f <= file->f_file[1]; f++) { + if (f && vfs_lock_file(f, F_SETLK, &lock, NULL) < 0) { + pr_warn("lockd: unlock failure in %s:%d\n", + __FILE__, __LINE__); + return 1; + } + } + return 0; +} + /* * Loop over all locks on the given file and perform the specified * action. @@ -184,17 +221,10 @@ again: lockhost = ((struct nlm_lockowner *)fl->fl_owner)->host; if (match(lockhost, host)) { - struct file_lock lock = *fl; spin_unlock(&flctx->flc_lock); - lock.fl_type = F_UNLCK; - lock.fl_start = 0; - lock.fl_end = OFFSET_MAX; - if (vfs_lock_file(file->f_file, F_SETLK, &lock, NULL) < 0) { - printk("lockd: unlock failure in %s:%d\n", - __FILE__, __LINE__); + if (nlm_unlock_files(file)) return 1; - } goto again; } } @@ -248,6 +278,15 @@ nlm_file_inuse(struct nlm_file *file) return 0; } +static void nlm_close_files(struct nlm_file *file) +{ + struct file *f; + + for (f = file->f_file[0]; f <= file->f_file[1]; f++) + if (f) + nlmsvc_ops->fclose(f); +} + /* * Loop over all files in the file table. */ @@ -278,7 +317,7 @@ nlm_traverse_files(void *data, nlm_host_match_fn_t match, if (list_empty(&file->f_blocks) && !file->f_locks && !file->f_shares && !file->f_count) { hlist_del(&file->f_list); - nlmsvc_ops->fclose(file->f_file); + nlm_close_files(file); kfree(file); } } @@ -412,6 +451,7 @@ nlmsvc_invalidate_all(void) nlm_traverse_files(NULL, nlmsvc_is_client, NULL); } + static int nlmsvc_match_sb(void *datap, struct nlm_file *file) { diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 3f5b3d7b62b7..606fa155c28a 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -25,9 +25,11 @@ * Note: we hold the dentry use count while the file is open. */ static __be32 -nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp) +nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp, + int mode) { __be32 nfserr; + int access; struct svc_fh fh; /* must initialize before using! but maxsize doesn't matter */ @@ -36,7 +38,9 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp) memcpy((char*)&fh.fh_handle.fh_base, f->data, f->size); fh.fh_export = NULL; - nfserr = nfsd_open(rqstp, &fh, S_IFREG, NFSD_MAY_LOCK, filp); + access = (mode == O_WRONLY) ? NFSD_MAY_WRITE : NFSD_MAY_READ; + access |= NFSD_MAY_LOCK; + nfserr = nfsd_open(rqstp, &fh, S_IFREG, access, filp); fh_put(&fh); /* We return nlm error codes as nlm doesn't know * about nfsd, but nfsd does know about nlm.. diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index 0520c0cd73f4..3bc9f7410e21 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -27,7 +27,8 @@ struct rpc_task; struct nlmsvc_binding { __be32 (*fopen)(struct svc_rqst *, struct nfs_fh *, - struct file **); + struct file **, + int mode); void (*fclose)(struct file *); }; diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 81b71ad2040a..c4ae6506b8b3 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -10,6 +10,8 @@ #ifndef LINUX_LOCKD_LOCKD_H #define LINUX_LOCKD_LOCKD_H +/* XXX: a lot of this should really be under fs/lockd. */ + #include #include #include @@ -154,7 +156,8 @@ struct nlm_rqst { struct nlm_file { struct hlist_node f_list; /* linked list */ struct nfs_fh f_handle; /* NFS file handle */ - struct file * f_file; /* VFS file pointer */ + struct file * f_file[2]; /* VFS file pointers, + indexed by O_ flags */ struct nlm_share * f_shares; /* DOS shares */ struct list_head f_blocks; /* blocked locks */ unsigned int f_locks; /* guesstimate # of locks */ @@ -267,6 +270,7 @@ typedef int (*nlm_host_match_fn_t)(void *cur, struct nlm_host *ref); /* * Server-side lock handling */ +int lock_to_openmode(struct file_lock *); __be32 nlmsvc_lock(struct svc_rqst *, struct nlm_file *, struct nlm_host *, struct nlm_lock *, int, struct nlm_cookie *, int); @@ -301,7 +305,8 @@ int nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr); static inline struct inode *nlmsvc_file_inode(struct nlm_file *file) { - return locks_inode(file->f_file); + return locks_inode(file->f_file[O_RDONLY] ? + file->f_file[O_RDONLY] : file->f_file[O_WRONLY]); } static inline int __nlm_privileged_request4(const struct sockaddr *sap) -- cgit v1.2.3 From 6fc88c354f3af83ffa2c285b86e76c759755693f Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Thu, 19 Aug 2021 02:24:20 -0700 Subject: bpf: Migrate cgroup_bpf to internal cgroup_bpf_attach_type enum Add an enum (cgroup_bpf_attach_type) containing only valid cgroup_bpf attach types and a function to map bpf_attach_type values to the new enum. Inspired by netns_bpf_attach_type. Then, migrate cgroup_bpf to use cgroup_bpf_attach_type wherever possible. Functionality is unchanged as attach_type_to_prog_type switches in bpf/syscall.c were preventing non-cgroup programs from making use of the invalid cgroup_bpf array slots. As a result struct cgroup_bpf uses 504 fewer bytes relative to when its arrays were sized using MAX_BPF_ATTACH_TYPE. bpf_cgroup_storage is notably not migrated as struct bpf_cgroup_storage_key is part of uapi and contains a bpf_attach_type member which is not meant to be opaque. Similarly, bpf_cgroup_link continues to report its bpf_attach_type member to userspace via fdinfo and bpf_link_info. To ease disambiguation, bpf_attach_type variables are renamed from 'type' to 'atype' when changed to cgroup_bpf_attach_type. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210819092420.1984861-2-davemarchevsky@fb.com --- include/linux/bpf-cgroup.h | 182 ++++++++++++++++++++++++++++------------- include/uapi/linux/bpf.h | 2 +- kernel/bpf/cgroup.c | 156 +++++++++++++++++++++-------------- net/ipv4/af_inet.c | 6 +- net/ipv4/udp.c | 2 +- net/ipv6/af_inet6.c | 6 +- net/ipv6/udp.c | 2 +- tools/include/uapi/linux/bpf.h | 2 +- 8 files changed, 226 insertions(+), 132 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a74cd1c3bd87..2746fd804216 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,9 +23,73 @@ struct ctl_table_header; struct task_struct; #ifdef CONFIG_CGROUP_BPF +enum cgroup_bpf_attach_type { + CGROUP_BPF_ATTACH_TYPE_INVALID = -1, + CGROUP_INET_INGRESS = 0, + CGROUP_INET_EGRESS, + CGROUP_INET_SOCK_CREATE, + CGROUP_SOCK_OPS, + CGROUP_DEVICE, + CGROUP_INET4_BIND, + CGROUP_INET6_BIND, + CGROUP_INET4_CONNECT, + CGROUP_INET6_CONNECT, + CGROUP_INET4_POST_BIND, + CGROUP_INET6_POST_BIND, + CGROUP_UDP4_SENDMSG, + CGROUP_UDP6_SENDMSG, + CGROUP_SYSCTL, + CGROUP_UDP4_RECVMSG, + CGROUP_UDP6_RECVMSG, + CGROUP_GETSOCKOPT, + CGROUP_SETSOCKOPT, + CGROUP_INET4_GETPEERNAME, + CGROUP_INET6_GETPEERNAME, + CGROUP_INET4_GETSOCKNAME, + CGROUP_INET6_GETSOCKNAME, + CGROUP_INET_SOCK_RELEASE, + MAX_CGROUP_BPF_ATTACH_TYPE +}; + +#define CGROUP_ATYPE(type) \ + case BPF_##type: return type + +static inline enum cgroup_bpf_attach_type +to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type) +{ + switch (attach_type) { + CGROUP_ATYPE(CGROUP_INET_INGRESS); + CGROUP_ATYPE(CGROUP_INET_EGRESS); + CGROUP_ATYPE(CGROUP_INET_SOCK_CREATE); + CGROUP_ATYPE(CGROUP_SOCK_OPS); + CGROUP_ATYPE(CGROUP_DEVICE); + CGROUP_ATYPE(CGROUP_INET4_BIND); + CGROUP_ATYPE(CGROUP_INET6_BIND); + CGROUP_ATYPE(CGROUP_INET4_CONNECT); + CGROUP_ATYPE(CGROUP_INET6_CONNECT); + CGROUP_ATYPE(CGROUP_INET4_POST_BIND); + CGROUP_ATYPE(CGROUP_INET6_POST_BIND); + CGROUP_ATYPE(CGROUP_UDP4_SENDMSG); + CGROUP_ATYPE(CGROUP_UDP6_SENDMSG); + CGROUP_ATYPE(CGROUP_SYSCTL); + CGROUP_ATYPE(CGROUP_UDP4_RECVMSG); + CGROUP_ATYPE(CGROUP_UDP6_RECVMSG); + CGROUP_ATYPE(CGROUP_GETSOCKOPT); + CGROUP_ATYPE(CGROUP_SETSOCKOPT); + CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME); + CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME); + CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME); + CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME); + CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE); + default: + return CGROUP_BPF_ATTACH_TYPE_INVALID; + } +} + +#undef CGROUP_ATYPE -extern struct static_key_false cgroup_bpf_enabled_key[MAX_BPF_ATTACH_TYPE]; -#define cgroup_bpf_enabled(type) static_branch_unlikely(&cgroup_bpf_enabled_key[type]) +extern struct static_key_false cgroup_bpf_enabled_key[MAX_CGROUP_BPF_ATTACH_TYPE]; +#define cgroup_bpf_enabled(atype) static_branch_unlikely(&cgroup_bpf_enabled_key[atype]) #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -67,15 +131,15 @@ struct bpf_prog_array; struct cgroup_bpf { /* array of effective progs in this cgroup */ - struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE]; + struct bpf_prog_array __rcu *effective[MAX_CGROUP_BPF_ATTACH_TYPE]; /* attached progs to this cgroup and attach flags * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will * have either zero or one element * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS */ - struct list_head progs[MAX_BPF_ATTACH_TYPE]; - u32 flags[MAX_BPF_ATTACH_TYPE]; + struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; + u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; /* list of cgroup shared storages */ struct list_head storages; @@ -115,28 +179,28 @@ int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, - enum bpf_attach_type type); + enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sk(struct sock *sk, - enum bpf_attach_type type); + enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type, + enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, - enum bpf_attach_type type); + enum cgroup_bpf_attach_type atype); int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, - short access, enum bpf_attach_type type); + short access, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, char **buf, size_t *pcount, loff_t *ppos, - enum bpf_attach_type type); + enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, int *optname, char __user *optval, @@ -179,9 +243,9 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_INET_INGRESS)) \ + if (cgroup_bpf_enabled(CGROUP_INET_INGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ - BPF_CGROUP_INET_INGRESS); \ + CGROUP_INET_INGRESS); \ \ __ret; \ }) @@ -189,54 +253,54 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ + if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ if (sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ - BPF_CGROUP_INET_EGRESS); \ + CGROUP_INET_EGRESS); \ } \ __ret; \ }) -#define BPF_CGROUP_RUN_SK_PROG(sk, type) \ +#define BPF_CGROUP_RUN_SK_PROG(sk, atype) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(type)) { \ - __ret = __cgroup_bpf_run_filter_sk(sk, type); \ + if (cgroup_bpf_enabled(atype)) { \ + __ret = __cgroup_bpf_run_filter_sk(sk, atype); \ } \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \ - BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_CREATE) + BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET_SOCK_CREATE) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) \ - BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_RELEASE) + BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET_SOCK_RELEASE) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) \ - BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET4_POST_BIND) + BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET4_POST_BIND) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) \ - BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET6_POST_BIND) + BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND) -#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \ +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \ ({ \ u32 __unused_flags; \ int __ret = 0; \ - if (cgroup_bpf_enabled(type)) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + if (cgroup_bpf_enabled(atype)) \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ NULL, \ &__unused_flags); \ __ret; \ }) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \ ({ \ u32 __unused_flags; \ int __ret = 0; \ - if (cgroup_bpf_enabled(type)) { \ + if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ t_ctx, \ &__unused_flags); \ release_sock(sk); \ @@ -249,13 +313,13 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). */ -#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, bind_flags) \ +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, bind_flags) \ ({ \ u32 __flags = 0; \ int __ret = 0; \ - if (cgroup_bpf_enabled(type)) { \ + if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ NULL, &__flags); \ release_sock(sk); \ if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ @@ -265,33 +329,33 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ - ((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) || \ - cgroup_bpf_enabled(BPF_CGROUP_INET6_CONNECT)) && \ + ((cgroup_bpf_enabled(CGROUP_INET4_CONNECT) || \ + cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) && \ (sk)->sk_prot->pre_connect) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_CONNECT) + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET4_CONNECT) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_CONNECT) + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET6_CONNECT) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT, NULL) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET4_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT, NULL) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET6_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_SENDMSG, t_ctx) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_SENDMSG, t_ctx) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_RECVMSG, NULL) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_RECVMSG, NULL) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_RECVMSG, NULL) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_RECVMSG, NULL) /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by @@ -311,33 +375,33 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS)) \ + if (cgroup_bpf_enabled(CGROUP_SOCK_OPS)) \ __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ sock_ops, \ - BPF_CGROUP_SOCK_OPS); \ + CGROUP_SOCK_OPS); \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS) && (sock_ops)->sk) { \ + if (cgroup_bpf_enabled(CGROUP_SOCK_OPS) && (sock_ops)->sk) { \ typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ if (__sk && sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ sock_ops, \ - BPF_CGROUP_SOCK_OPS); \ + CGROUP_SOCK_OPS); \ } \ __ret; \ }) -#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access) \ +#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_DEVICE)) \ - __ret = __cgroup_bpf_check_dev_permission(type, major, minor, \ + if (cgroup_bpf_enabled(CGROUP_DEVICE)) \ + __ret = __cgroup_bpf_check_dev_permission(atype, major, minor, \ access, \ - BPF_CGROUP_DEVICE); \ + CGROUP_DEVICE); \ \ __ret; \ }) @@ -346,10 +410,10 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_SYSCTL)) \ + if (cgroup_bpf_enabled(CGROUP_SYSCTL)) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ buf, count, pos, \ - BPF_CGROUP_SYSCTL); \ + CGROUP_SYSCTL); \ __ret; \ }) @@ -357,7 +421,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, kernel_optval) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_SETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ @@ -368,7 +432,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ get_user(__ret, optlen); \ __ret; \ }) @@ -377,7 +441,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, max_optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ @@ -392,7 +456,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ sock, level, optname, optval, optlen, retval); \ __ret; \ @@ -451,14 +515,14 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, return 0; } -#define cgroup_bpf_enabled(type) (0) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) ({ 0; }) +#define cgroup_bpf_enabled(atype) (0) +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, flags) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; }) @@ -470,7 +534,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c4f7892edb2b..191f0b286ee3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -84,7 +84,7 @@ struct bpf_lpm_trie_key { struct bpf_cgroup_storage_key { __u64 cgroup_inode_id; /* cgroup inode id */ - __u32 attach_type; /* program attach type */ + __u32 attach_type; /* program attach type (enum bpf_attach_type) */ }; union bpf_iter_link_info { diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 8e9d99e2ade4..03145d45e3d5 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -19,7 +19,7 @@ #include "../cgroup/cgroup-internal.h" -DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_BPF_ATTACH_TYPE); +DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_CGROUP_BPF_ATTACH_TYPE); EXPORT_SYMBOL(cgroup_bpf_enabled_key); void cgroup_bpf_offline(struct cgroup *cgrp) @@ -113,12 +113,12 @@ static void cgroup_bpf_release(struct work_struct *work) struct list_head *storages = &cgrp->bpf.storages; struct bpf_cgroup_storage *storage, *stmp; - unsigned int type; + unsigned int atype; mutex_lock(&cgroup_mutex); - for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { - struct list_head *progs = &cgrp->bpf.progs[type]; + for (atype = 0; atype < ARRAY_SIZE(cgrp->bpf.progs); atype++) { + struct list_head *progs = &cgrp->bpf.progs[atype]; struct bpf_prog_list *pl, *pltmp; list_for_each_entry_safe(pl, pltmp, progs, node) { @@ -128,10 +128,10 @@ static void cgroup_bpf_release(struct work_struct *work) if (pl->link) bpf_cgroup_link_auto_detach(pl->link); kfree(pl); - static_branch_dec(&cgroup_bpf_enabled_key[type]); + static_branch_dec(&cgroup_bpf_enabled_key[atype]); } old_array = rcu_dereference_protected( - cgrp->bpf.effective[type], + cgrp->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); bpf_prog_array_free(old_array); } @@ -196,7 +196,7 @@ static u32 prog_list_length(struct list_head *head) * if parent has overridable or multi-prog, allow attaching */ static bool hierarchy_allows_attach(struct cgroup *cgrp, - enum bpf_attach_type type) + enum cgroup_bpf_attach_type atype) { struct cgroup *p; @@ -204,12 +204,12 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp, if (!p) return true; do { - u32 flags = p->bpf.flags[type]; + u32 flags = p->bpf.flags[atype]; u32 cnt; if (flags & BPF_F_ALLOW_MULTI) return true; - cnt = prog_list_length(&p->bpf.progs[type]); + cnt = prog_list_length(&p->bpf.progs[atype]); WARN_ON_ONCE(cnt > 1); if (cnt == 1) return !!(flags & BPF_F_ALLOW_OVERRIDE); @@ -225,7 +225,7 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp, * to programs in this cgroup */ static int compute_effective_progs(struct cgroup *cgrp, - enum bpf_attach_type type, + enum cgroup_bpf_attach_type atype, struct bpf_prog_array **array) { struct bpf_prog_array_item *item; @@ -236,8 +236,8 @@ static int compute_effective_progs(struct cgroup *cgrp, /* count number of effective programs by walking parents */ do { - if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) - cnt += prog_list_length(&p->bpf.progs[type]); + if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) + cnt += prog_list_length(&p->bpf.progs[atype]); p = cgroup_parent(p); } while (p); @@ -249,10 +249,10 @@ static int compute_effective_progs(struct cgroup *cgrp, cnt = 0; p = cgrp; do { - if (cnt > 0 && !(p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; - list_for_each_entry(pl, &p->bpf.progs[type], node) { + list_for_each_entry(pl, &p->bpf.progs[atype], node) { if (!prog_list_prog(pl)) continue; @@ -269,10 +269,10 @@ static int compute_effective_progs(struct cgroup *cgrp, } static void activate_effective_progs(struct cgroup *cgrp, - enum bpf_attach_type type, + enum cgroup_bpf_attach_type atype, struct bpf_prog_array *old_array) { - old_array = rcu_replace_pointer(cgrp->bpf.effective[type], old_array, + old_array = rcu_replace_pointer(cgrp->bpf.effective[atype], old_array, lockdep_is_held(&cgroup_mutex)); /* free prog array after grace period, since __cgroup_bpf_run_*() * might be still walking the array @@ -328,7 +328,7 @@ cleanup: } static int update_effective_progs(struct cgroup *cgrp, - enum bpf_attach_type type) + enum cgroup_bpf_attach_type atype) { struct cgroup_subsys_state *css; int err; @@ -340,7 +340,7 @@ static int update_effective_progs(struct cgroup *cgrp, if (percpu_ref_is_zero(&desc->bpf.refcnt)) continue; - err = compute_effective_progs(desc, type, &desc->bpf.inactive); + err = compute_effective_progs(desc, atype, &desc->bpf.inactive); if (err) goto cleanup; } @@ -357,7 +357,7 @@ static int update_effective_progs(struct cgroup *cgrp, continue; } - activate_effective_progs(desc, type, desc->bpf.inactive); + activate_effective_progs(desc, atype, desc->bpf.inactive); desc->bpf.inactive = NULL; } @@ -436,11 +436,12 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, enum bpf_attach_type type, u32 flags) { u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)); - struct list_head *progs = &cgrp->bpf.progs[type]; struct bpf_prog *old_prog = NULL; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; + enum cgroup_bpf_attach_type atype; struct bpf_prog_list *pl; + struct list_head *progs; int err; if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) || @@ -454,10 +455,16 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, /* replace_prog implies BPF_F_REPLACE, and vice versa */ return -EINVAL; - if (!hierarchy_allows_attach(cgrp, type)) + atype = to_cgroup_bpf_attach_type(type); + if (atype < 0) + return -EINVAL; + + progs = &cgrp->bpf.progs[atype]; + + if (!hierarchy_allows_attach(cgrp, atype)) return -EPERM; - if (!list_empty(progs) && cgrp->bpf.flags[type] != saved_flags) + if (!list_empty(progs) && cgrp->bpf.flags[atype] != saved_flags) /* Disallow attaching non-overridable on top * of existing overridable in this cgroup. * Disallow attaching multi-prog if overridable or none @@ -490,16 +497,16 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, pl->prog = prog; pl->link = link; bpf_cgroup_storages_assign(pl->storage, storage); - cgrp->bpf.flags[type] = saved_flags; + cgrp->bpf.flags[atype] = saved_flags; - err = update_effective_progs(cgrp, type); + err = update_effective_progs(cgrp, atype); if (err) goto cleanup; if (old_prog) bpf_prog_put(old_prog); else - static_branch_inc(&cgroup_bpf_enabled_key[type]); + static_branch_inc(&cgroup_bpf_enabled_key[atype]); bpf_cgroup_storages_link(new_storage, cgrp, type); return 0; @@ -520,7 +527,7 @@ cleanup: * all descendant cgroups. This function is guaranteed to succeed. */ static void replace_effective_prog(struct cgroup *cgrp, - enum bpf_attach_type type, + enum cgroup_bpf_attach_type atype, struct bpf_cgroup_link *link) { struct bpf_prog_array_item *item; @@ -539,10 +546,10 @@ static void replace_effective_prog(struct cgroup *cgrp, /* find position of link in effective progs array */ for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { - if (pos && !(cg->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; - head = &cg->bpf.progs[type]; + head = &cg->bpf.progs[atype]; list_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; @@ -554,7 +561,7 @@ static void replace_effective_prog(struct cgroup *cgrp, found: BUG_ON(!cg); progs = rcu_dereference_protected( - desc->bpf.effective[type], + desc->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); item = &progs->items[pos]; WRITE_ONCE(item->prog, link->link.prog); @@ -574,11 +581,18 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, struct bpf_prog *new_prog) { - struct list_head *progs = &cgrp->bpf.progs[link->type]; + enum cgroup_bpf_attach_type atype; struct bpf_prog *old_prog; struct bpf_prog_list *pl; + struct list_head *progs; bool found = false; + atype = to_cgroup_bpf_attach_type(link->type); + if (atype < 0) + return -EINVAL; + + progs = &cgrp->bpf.progs[atype]; + if (link->link.prog->type != new_prog->type) return -EINVAL; @@ -592,7 +606,7 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp, return -ENOENT; old_prog = xchg(&link->link.prog, new_prog); - replace_effective_prog(cgrp, link->type, link); + replace_effective_prog(cgrp, atype, link); bpf_prog_put(old_prog); return 0; } @@ -667,12 +681,20 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs, int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_cgroup_link *link, enum bpf_attach_type type) { - struct list_head *progs = &cgrp->bpf.progs[type]; - u32 flags = cgrp->bpf.flags[type]; - struct bpf_prog_list *pl; + enum cgroup_bpf_attach_type atype; struct bpf_prog *old_prog; + struct bpf_prog_list *pl; + struct list_head *progs; + u32 flags; int err; + atype = to_cgroup_bpf_attach_type(type); + if (atype < 0) + return -EINVAL; + + progs = &cgrp->bpf.progs[atype]; + flags = cgrp->bpf.flags[atype]; + if (prog && link) /* only one of prog or link can be specified */ return -EINVAL; @@ -686,7 +708,7 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, pl->prog = NULL; pl->link = NULL; - err = update_effective_progs(cgrp, type); + err = update_effective_progs(cgrp, atype); if (err) goto cleanup; @@ -695,10 +717,10 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, kfree(pl); if (list_empty(progs)) /* last program was detached, reset flags to zero */ - cgrp->bpf.flags[type] = 0; + cgrp->bpf.flags[atype] = 0; if (old_prog) bpf_prog_put(old_prog); - static_branch_dec(&cgroup_bpf_enabled_key[type]); + static_branch_dec(&cgroup_bpf_enabled_key[atype]); return 0; cleanup: @@ -714,13 +736,21 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); enum bpf_attach_type type = attr->query.attach_type; - struct list_head *progs = &cgrp->bpf.progs[type]; - u32 flags = cgrp->bpf.flags[type]; + enum cgroup_bpf_attach_type atype; struct bpf_prog_array *effective; + struct list_head *progs; struct bpf_prog *prog; int cnt, ret = 0, i; + u32 flags; + + atype = to_cgroup_bpf_attach_type(type); + if (atype < 0) + return -EINVAL; + + progs = &cgrp->bpf.progs[atype]; + flags = cgrp->bpf.flags[atype]; - effective = rcu_dereference_protected(cgrp->bpf.effective[type], + effective = rcu_dereference_protected(cgrp->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) @@ -925,14 +955,14 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) link->cgroup = cgrp; link->type = attr->link_create.attach_type; - err = bpf_link_prime(&link->link, &link_primer); + err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_cgroup; } - err = cgroup_bpf_attach(cgrp, NULL, NULL, link, link->type, - BPF_F_ALLOW_MULTI); + err = cgroup_bpf_attach(cgrp, NULL, NULL, link, + link->type, BPF_F_ALLOW_MULTI); if (err) { bpf_link_cleanup(&link_primer); goto out_put_cgroup; @@ -986,7 +1016,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, */ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, - enum bpf_attach_type type) + enum cgroup_bpf_attach_type atype) { unsigned int offset = skb->data - skb_network_header(skb); struct sock *save_sk; @@ -1008,11 +1038,11 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, /* compute pointers for the bpf prog */ bpf_compute_and_save_data_end(skb, &saved_data_end); - if (type == BPF_CGROUP_INET_EGRESS) { + if (atype == CGROUP_INET_EGRESS) { ret = BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY( - cgrp->bpf.effective[type], skb, __bpf_prog_run_save_cb); + cgrp->bpf.effective[atype], skb, __bpf_prog_run_save_cb); } else { - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[type], skb, + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], skb, __bpf_prog_run_save_cb); ret = (ret == 1 ? 0 : -EPERM); } @@ -1038,12 +1068,12 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); * and if it returned != 1 during execution. In all other cases, 0 is returned. */ int __cgroup_bpf_run_filter_sk(struct sock *sk, - enum bpf_attach_type type) + enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); int ret; - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[type], sk, bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk, bpf_prog_run); return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -1065,7 +1095,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); */ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type, + enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags) { @@ -1090,7 +1120,7 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[type], &ctx, + ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx, bpf_prog_run, flags); return ret == 1 ? 0 : -EPERM; @@ -1115,19 +1145,19 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); */ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, - enum bpf_attach_type type) + enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); int ret; - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[type], sock_ops, + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops, bpf_prog_run); return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, - short access, enum bpf_attach_type type) + short access, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp; struct bpf_cgroup_dev_ctx ctx = { @@ -1139,7 +1169,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, rcu_read_lock(); cgrp = task_dfl_cgroup(current); - allow = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[type], &ctx, + allow = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, bpf_prog_run); rcu_read_unlock(); @@ -1231,7 +1261,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, char **buf, size_t *pcount, loff_t *ppos, - enum bpf_attach_type type) + enum cgroup_bpf_attach_type atype) { struct bpf_sysctl_kern ctx = { .head = head, @@ -1271,7 +1301,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, rcu_read_lock(); cgrp = task_dfl_cgroup(current); - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[type], &ctx, bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, bpf_prog_run); rcu_read_unlock(); kfree(ctx.cur_val); @@ -1289,7 +1319,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, #ifdef CONFIG_NET static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp, - enum bpf_attach_type attach_type) + enum cgroup_bpf_attach_type attach_type) { struct bpf_prog_array *prog_array; bool empty; @@ -1364,7 +1394,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, * attached to the hook so we don't waste time allocating * memory and locking the socket. */ - if (__cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT)) + if (__cgroup_bpf_prog_array_is_empty(cgrp, CGROUP_SETSOCKOPT)) return 0; /* Allocate a bit more than the initial user buffer for @@ -1385,7 +1415,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, } lock_sock(sk); - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[BPF_CGROUP_SETSOCKOPT], + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_SETSOCKOPT], &ctx, bpf_prog_run); release_sock(sk); @@ -1460,7 +1490,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, * attached to the hook so we don't waste time allocating * memory and locking the socket. */ - if (__cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT)) + if (__cgroup_bpf_prog_array_is_empty(cgrp, CGROUP_GETSOCKOPT)) return retval; ctx.optlen = max_optlen; @@ -1495,7 +1525,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, } lock_sock(sk); - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT], &ctx, bpf_prog_run); release_sock(sk); @@ -1556,7 +1586,7 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, * be called if that data shouldn't be "exported". */ - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT], &ctx, bpf_prog_run); if (!ret) return -EPERM; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0e4d758c2585..1d816a5fd3eb 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -452,7 +452,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, - BPF_CGROUP_INET4_BIND, &flags); + CGROUP_INET4_BIND, &flags); if (err) return err; @@ -781,7 +781,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - BPF_CGROUP_INET4_GETPEERNAME, + CGROUP_INET4_GETPEERNAME, NULL); } else { __be32 addr = inet->inet_rcv_saddr; @@ -790,7 +790,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - BPF_CGROUP_INET4_GETSOCKNAME, + CGROUP_INET4_GETSOCKNAME, NULL); } memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1a742b710e54..8851c9463b4b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1143,7 +1143,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rcu_read_unlock(); } - if (cgroup_bpf_enabled(BPF_CGROUP_UDP4_SENDMSG) && !connected) { + if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, (struct sockaddr *)usin, &ipc.addr); if (err) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d92c90d97763..b5878bb8e419 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -455,7 +455,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, - BPF_CGROUP_INET6_BIND, &flags); + CGROUP_INET6_BIND, &flags); if (err) return err; @@ -532,7 +532,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, if (np->sndflow) sin->sin6_flowinfo = np->flow_label; BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - BPF_CGROUP_INET6_GETPEERNAME, + CGROUP_INET6_GETPEERNAME, NULL); } else { if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) @@ -541,7 +541,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_addr = sk->sk_v6_rcv_saddr; sin->sin6_port = inet->inet_sport; BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - BPF_CGROUP_INET6_GETSOCKNAME, + CGROUP_INET6_GETSOCKNAME, NULL); } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index c5e15e94bb00..ea53847b5b7e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1475,7 +1475,7 @@ do_udp_sendmsg: fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; - if (cgroup_bpf_enabled(BPF_CGROUP_UDP6_SENDMSG) && !connected) { + if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, (struct sockaddr *)sin6, &fl6.saddr); if (err) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c4f7892edb2b..191f0b286ee3 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -84,7 +84,7 @@ struct bpf_lpm_trie_key { struct bpf_cgroup_storage_key { __u64 cgroup_inode_id; /* cgroup inode id */ - __u32 attach_type; /* program attach type */ + __u32 attach_type; /* program attach type (enum bpf_attach_type) */ }; union bpf_iter_link_info { -- cgit v1.2.3 From 2f170814bdd26289e9daaa4ae359290f854e5dcf Mon Sep 17 00:00:00 2001 From: Barry Song Date: Fri, 13 Aug 2021 15:56:27 +1200 Subject: genirq/msi: Move MSI sysfs handling from PCI to MSI core Move PCI's MSI sysfs code to the irq core so that other busses such as platform can reuse it. Signed-off-by: Barry Song Signed-off-by: Thomas Gleixner Acked-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20210813035628.6844-2-21cnbao@gmail.com --- drivers/pci/msi.c | 125 ++++-------------------------------------------- include/linux/msi.h | 4 ++ kernel/irq/msi.c | 134 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 148 insertions(+), 115 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index ce841f327ff6..6eb0ae39deae 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -363,9 +363,7 @@ static void free_msi_irqs(struct pci_dev *dev) { struct list_head *msi_list = dev_to_msi_list(&dev->dev); struct msi_desc *entry, *tmp; - struct attribute **msi_attrs; - struct device_attribute *dev_attr; - int i, count = 0; + int i; for_each_pci_msi_entry(entry, dev) if (entry->irq) @@ -385,18 +383,7 @@ static void free_msi_irqs(struct pci_dev *dev) } if (dev->msi_irq_groups) { - sysfs_remove_groups(&dev->dev.kobj, dev->msi_irq_groups); - msi_attrs = dev->msi_irq_groups[0]->attrs; - while (msi_attrs[count]) { - dev_attr = container_of(msi_attrs[count], - struct device_attribute, attr); - kfree(dev_attr->attr.name); - kfree(dev_attr); - ++count; - } - kfree(msi_attrs); - kfree(dev->msi_irq_groups[0]); - kfree(dev->msi_irq_groups); + msi_destroy_sysfs(&dev->dev, dev->msi_irq_groups); dev->msi_irq_groups = NULL; } } @@ -476,102 +463,6 @@ void pci_restore_msi_state(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_restore_msi_state); -static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct msi_desc *entry; - unsigned long irq; - int retval; - - retval = kstrtoul(attr->attr.name, 10, &irq); - if (retval) - return retval; - - entry = irq_get_msi_desc(irq); - if (!entry) - return -ENODEV; - - return sysfs_emit(buf, "%s\n", - entry->msi_attrib.is_msix ? "msix" : "msi"); -} - -static int populate_msi_sysfs(struct pci_dev *pdev) -{ - struct attribute **msi_attrs; - struct attribute *msi_attr; - struct device_attribute *msi_dev_attr; - struct attribute_group *msi_irq_group; - const struct attribute_group **msi_irq_groups; - struct msi_desc *entry; - int ret = -ENOMEM; - int num_msi = 0; - int count = 0; - int i; - - /* Determine how many msi entries we have */ - for_each_pci_msi_entry(entry, pdev) - num_msi += entry->nvec_used; - if (!num_msi) - return 0; - - /* Dynamically create the MSI attributes for the PCI device */ - msi_attrs = kcalloc(num_msi + 1, sizeof(void *), GFP_KERNEL); - if (!msi_attrs) - return -ENOMEM; - for_each_pci_msi_entry(entry, pdev) { - for (i = 0; i < entry->nvec_used; i++) { - msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL); - if (!msi_dev_attr) - goto error_attrs; - msi_attrs[count] = &msi_dev_attr->attr; - - sysfs_attr_init(&msi_dev_attr->attr); - msi_dev_attr->attr.name = kasprintf(GFP_KERNEL, "%d", - entry->irq + i); - if (!msi_dev_attr->attr.name) - goto error_attrs; - msi_dev_attr->attr.mode = S_IRUGO; - msi_dev_attr->show = msi_mode_show; - ++count; - } - } - - msi_irq_group = kzalloc(sizeof(*msi_irq_group), GFP_KERNEL); - if (!msi_irq_group) - goto error_attrs; - msi_irq_group->name = "msi_irqs"; - msi_irq_group->attrs = msi_attrs; - - msi_irq_groups = kcalloc(2, sizeof(void *), GFP_KERNEL); - if (!msi_irq_groups) - goto error_irq_group; - msi_irq_groups[0] = msi_irq_group; - - ret = sysfs_create_groups(&pdev->dev.kobj, msi_irq_groups); - if (ret) - goto error_irq_groups; - pdev->msi_irq_groups = msi_irq_groups; - - return 0; - -error_irq_groups: - kfree(msi_irq_groups); -error_irq_group: - kfree(msi_irq_group); -error_attrs: - count = 0; - msi_attr = msi_attrs[count]; - while (msi_attr) { - msi_dev_attr = container_of(msi_attr, struct device_attribute, attr); - kfree(msi_attr->name); - kfree(msi_dev_attr); - ++count; - msi_attr = msi_attrs[count]; - } - kfree(msi_attrs); - return ret; -} - static struct msi_desc * msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd) { @@ -667,9 +558,11 @@ static int msi_capability_init(struct pci_dev *dev, int nvec, if (ret) goto err; - ret = populate_msi_sysfs(dev); - if (ret) + dev->msi_irq_groups = msi_populate_sysfs(&dev->dev); + if (IS_ERR(dev->msi_irq_groups)) { + ret = PTR_ERR(dev->msi_irq_groups); goto err; + } /* Set MSI enabled bits */ pci_intx_for_msi(dev, 0); @@ -834,9 +727,11 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, msix_update_entries(dev, entries); - ret = populate_msi_sysfs(dev); - if (ret) + dev->msi_irq_groups = msi_populate_sysfs(&dev->dev); + if (IS_ERR(dev->msi_irq_groups)) { + ret = PTR_ERR(dev->msi_irq_groups); goto out_free; + } /* Set MSI-X enabled bits and unmask the function */ pci_intx_for_msi(dev, 0); diff --git a/include/linux/msi.h b/include/linux/msi.h index a20dc66b9946..49cf6eb222e7 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -239,6 +239,10 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); +const struct attribute_group **msi_populate_sysfs(struct device *dev); +void msi_destroy_sysfs(struct device *dev, + const struct attribute_group **msi_irq_groups); + /* * The arch hooks to setup up msi irqs. Default functions are implemented * as weak symbols so that they /can/ be overriden by architecture specific diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index bb18040efbe8..48ef144649e3 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "internals.h" @@ -71,6 +72,139 @@ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) } EXPORT_SYMBOL_GPL(get_cached_msi_msg); +static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct msi_desc *entry; + bool is_msix = false; + unsigned long irq; + int retval; + + retval = kstrtoul(attr->attr.name, 10, &irq); + if (retval) + return retval; + + entry = irq_get_msi_desc(irq); + if (!entry) + return -ENODEV; + + if (dev_is_pci(dev)) + is_msix = entry->msi_attrib.is_msix; + + return sysfs_emit(buf, "%s\n", is_msix ? "msix" : "msi"); +} + +/** + * msi_populate_sysfs - Populate msi_irqs sysfs entries for devices + * @dev: The device(PCI, platform etc) who will get sysfs entries + * + * Return attribute_group ** so that specific bus MSI can save it to + * somewhere during initilizing msi irqs. If devices has no MSI irq, + * return NULL; if it fails to populate sysfs, return ERR_PTR + */ +const struct attribute_group **msi_populate_sysfs(struct device *dev) +{ + const struct attribute_group **msi_irq_groups; + struct attribute **msi_attrs, *msi_attr; + struct device_attribute *msi_dev_attr; + struct attribute_group *msi_irq_group; + struct msi_desc *entry; + int ret = -ENOMEM; + int num_msi = 0; + int count = 0; + int i; + + /* Determine how many msi entries we have */ + for_each_msi_entry(entry, dev) + num_msi += entry->nvec_used; + if (!num_msi) + return NULL; + + /* Dynamically create the MSI attributes for the device */ + msi_attrs = kcalloc(num_msi + 1, sizeof(void *), GFP_KERNEL); + if (!msi_attrs) + return ERR_PTR(-ENOMEM); + + for_each_msi_entry(entry, dev) { + for (i = 0; i < entry->nvec_used; i++) { + msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL); + if (!msi_dev_attr) + goto error_attrs; + msi_attrs[count] = &msi_dev_attr->attr; + + sysfs_attr_init(&msi_dev_attr->attr); + msi_dev_attr->attr.name = kasprintf(GFP_KERNEL, "%d", + entry->irq + i); + if (!msi_dev_attr->attr.name) + goto error_attrs; + msi_dev_attr->attr.mode = 0444; + msi_dev_attr->show = msi_mode_show; + ++count; + } + } + + msi_irq_group = kzalloc(sizeof(*msi_irq_group), GFP_KERNEL); + if (!msi_irq_group) + goto error_attrs; + msi_irq_group->name = "msi_irqs"; + msi_irq_group->attrs = msi_attrs; + + msi_irq_groups = kcalloc(2, sizeof(void *), GFP_KERNEL); + if (!msi_irq_groups) + goto error_irq_group; + msi_irq_groups[0] = msi_irq_group; + + ret = sysfs_create_groups(&dev->kobj, msi_irq_groups); + if (ret) + goto error_irq_groups; + + return msi_irq_groups; + +error_irq_groups: + kfree(msi_irq_groups); +error_irq_group: + kfree(msi_irq_group); +error_attrs: + count = 0; + msi_attr = msi_attrs[count]; + while (msi_attr) { + msi_dev_attr = container_of(msi_attr, struct device_attribute, attr); + kfree(msi_attr->name); + kfree(msi_dev_attr); + ++count; + msi_attr = msi_attrs[count]; + } + kfree(msi_attrs); + return ERR_PTR(ret); +} + +/** + * msi_destroy_sysfs - Destroy msi_irqs sysfs entries for devices + * @dev: The device(PCI, platform etc) who will remove sysfs entries + * @msi_irq_groups: attribute_group for device msi_irqs entries + */ +void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_irq_groups) +{ + struct device_attribute *dev_attr; + struct attribute **msi_attrs; + int count = 0; + + if (msi_irq_groups) { + sysfs_remove_groups(&dev->kobj, msi_irq_groups); + msi_attrs = msi_irq_groups[0]->attrs; + while (msi_attrs[count]) { + dev_attr = container_of(msi_attrs[count], + struct device_attribute, attr); + kfree(dev_attr->attr.name); + kfree(dev_attr); + ++count; + } + kfree(msi_attrs); + kfree(msi_irq_groups[0]); + kfree(msi_irq_groups); + } +} + #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN static inline void irq_chip_write_msi_msg(struct irq_data *data, struct msi_msg *msg) -- cgit v1.2.3 From dab2ea6c680f87add6d2f7007ce46b6b9e3857f7 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 23 Aug 2021 20:02:38 +0200 Subject: ieee80211: add TWT element definitions Introduce TWT definitions and TWT Information element structure in ieee80211.h Tested-by: Peter Chiu Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/71d8b581fe4b5abc5b92f8d77ac2de3e2f7591b6.1629741512.git.lorenzo@kernel.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 62 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a6730072d13a..2e8953d80d4b 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1088,6 +1088,48 @@ struct ieee80211_ext { } u; } __packed __aligned(2); +#define IEEE80211_TWT_CONTROL_NDP BIT(0) +#define IEEE80211_TWT_CONTROL_RESP_MODE BIT(1) +#define IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST BIT(3) +#define IEEE80211_TWT_CONTROL_RX_DISABLED BIT(4) +#define IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT BIT(5) + +#define IEEE80211_TWT_REQTYPE_REQUEST BIT(0) +#define IEEE80211_TWT_REQTYPE_SETUP_CMD GENMASK(3, 1) +#define IEEE80211_TWT_REQTYPE_TRIGGER BIT(4) +#define IEEE80211_TWT_REQTYPE_IMPLICIT BIT(5) +#define IEEE80211_TWT_REQTYPE_FLOWTYPE BIT(6) +#define IEEE80211_TWT_REQTYPE_FLOWID GENMASK(9, 7) +#define IEEE80211_TWT_REQTYPE_WAKE_INT_EXP GENMASK(14, 10) +#define IEEE80211_TWT_REQTYPE_PROTECTION BIT(15) + +enum ieee80211_twt_setup_cmd { + TWT_SETUP_CMD_REQUEST, + TWT_SETUP_CMD_SUGGEST, + TWT_SETUP_CMD_DEMAND, + TWT_SETUP_CMD_GROUPING, + TWT_SETUP_CMD_ACCEPT, + TWT_SETUP_CMD_ALTERNATE, + TWT_SETUP_CMD_DICTATE, + TWT_SETUP_CMD_REJECT, +}; + +struct ieee80211_twt_params { + __le16 req_type; + __le64 twt; + u8 min_twt_dur; + __le16 mantissa; + u8 channel; +} __packed; + +struct ieee80211_twt_setup { + u8 dialog_token; + u8 element_id; + u8 length; + u8 control; + u8 params[]; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -1252,6 +1294,10 @@ struct ieee80211_mgmt { __le16 toa_error; u8 variable[0]; } __packed ftm; + struct { + u8 action_code; + u8 variable[]; + } __packed s1g; } u; } __packed action; } u; @@ -2881,6 +2927,7 @@ enum ieee80211_eid { WLAN_EID_AID_RESPONSE = 211, WLAN_EID_S1G_BCN_COMPAT = 213, WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214, + WLAN_EID_S1G_TWT = 216, WLAN_EID_S1G_CAPABILITIES = 217, WLAN_EID_VENDOR_SPECIFIC = 221, WLAN_EID_QOS_PARAMETER = 222, @@ -2950,6 +2997,7 @@ enum ieee80211_category { WLAN_CATEGORY_FST = 18, WLAN_CATEGORY_UNPROT_DMG = 20, WLAN_CATEGORY_VHT = 21, + WLAN_CATEGORY_S1G = 22, WLAN_CATEGORY_VENDOR_SPECIFIC_PROTECTED = 126, WLAN_CATEGORY_VENDOR_SPECIFIC = 127, }; @@ -3023,6 +3071,20 @@ enum ieee80211_key_len { WLAN_KEY_LEN_BIP_GMAC_256 = 32, }; +enum ieee80211_s1g_actioncode { + WLAN_S1G_AID_SWITCH_REQUEST, + WLAN_S1G_AID_SWITCH_RESPONSE, + WLAN_S1G_SYNC_CONTROL, + WLAN_S1G_STA_INFO_ANNOUNCE, + WLAN_S1G_EDCA_PARAM_SET, + WLAN_S1G_EL_OPERATION, + WLAN_S1G_TWT_SETUP, + WLAN_S1G_TWT_TEARDOWN, + WLAN_S1G_SECT_GROUP_ID_LIST, + WLAN_S1G_SECT_ID_FEEDBACK, + WLAN_S1G_TWT_INFORMATION = 11, +}; + #define IEEE80211_WEP_IV_LEN 4 #define IEEE80211_WEP_ICV_LEN 4 #define IEEE80211_CCMP_HDR_LEN 8 -- cgit v1.2.3 From 4a11cc647d7c07388ef00f231fb07c9b01b1db5b Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Mon, 19 Jul 2021 16:34:13 -0300 Subject: mmc: sdhci-esdhc-imx: Remove unneeded mmc-esdhc-imx.h header After the i.MX conversion to a DT-only platform, the mmc-esdhc-imx.h header file is no longer used outside the driver, so move its content to the sdhci-esdhc-imx driver and remove the header. Signed-off-by: Fabio Estevam Link: https://lore.kernel.org/r/20210719193413.3792615-1-festevam@gmail.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-esdhc-imx.c | 33 ++++++++++++++++++++++- include/linux/platform_data/mmc-esdhc-imx.h | 42 ----------------------------- 2 files changed, 32 insertions(+), 43 deletions(-) delete mode 100644 include/linux/platform_data/mmc-esdhc-imx.h (limited to 'include/linux') diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 72c0bf0c1887..57b19ca1ad6d 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include "sdhci-pltfm.h" #include "sdhci-esdhc.h" @@ -191,6 +190,38 @@ */ #define ESDHC_FLAG_BROKEN_AUTO_CMD23 BIT(16) +enum wp_types { + ESDHC_WP_NONE, /* no WP, neither controller nor gpio */ + ESDHC_WP_CONTROLLER, /* mmc controller internal WP */ + ESDHC_WP_GPIO, /* external gpio pin for WP */ +}; + +enum cd_types { + ESDHC_CD_NONE, /* no CD, neither controller nor gpio */ + ESDHC_CD_CONTROLLER, /* mmc controller internal CD */ + ESDHC_CD_GPIO, /* external gpio pin for CD */ + ESDHC_CD_PERMANENT, /* no CD, card permanently wired to host */ +}; + +/* + * struct esdhc_platform_data - platform data for esdhc on i.MX + * + * ESDHC_WP(CD)_CONTROLLER type is not available on i.MX25/35. + * + * @wp_type: type of write_protect method (see wp_types enum above) + * @cd_type: type of card_detect method (see cd_types enum above) + */ + +struct esdhc_platform_data { + enum wp_types wp_type; + enum cd_types cd_type; + int max_bus_width; + unsigned int delay_line; + unsigned int tuning_step; /* The delay cell steps in tuning procedure */ + unsigned int tuning_start_tap; /* The start delay cell point in tuning procedure */ + unsigned int strobe_dll_delay_target; /* The delay cell for strobe pad (read clock) */ +}; + struct esdhc_soc_data { u32 flags; }; diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h deleted file mode 100644 index cba1184b364c..000000000000 --- a/include/linux/platform_data/mmc-esdhc-imx.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2010 Wolfram Sang - */ - -#ifndef __ASM_ARCH_IMX_ESDHC_H -#define __ASM_ARCH_IMX_ESDHC_H - -#include - -enum wp_types { - ESDHC_WP_NONE, /* no WP, neither controller nor gpio */ - ESDHC_WP_CONTROLLER, /* mmc controller internal WP */ - ESDHC_WP_GPIO, /* external gpio pin for WP */ -}; - -enum cd_types { - ESDHC_CD_NONE, /* no CD, neither controller nor gpio */ - ESDHC_CD_CONTROLLER, /* mmc controller internal CD */ - ESDHC_CD_GPIO, /* external gpio pin for CD */ - ESDHC_CD_PERMANENT, /* no CD, card permanently wired to host */ -}; - -/** - * struct esdhc_platform_data - platform data for esdhc on i.MX - * - * ESDHC_WP(CD)_CONTROLLER type is not available on i.MX25/35. - * - * @wp_type: type of write_protect method (see wp_types enum above) - * @cd_type: type of card_detect method (see cd_types enum above) - */ - -struct esdhc_platform_data { - enum wp_types wp_type; - enum cd_types cd_type; - int max_bus_width; - unsigned int delay_line; - unsigned int tuning_step; /* The delay cell steps in tuning procedure */ - unsigned int tuning_start_tap; /* The start delay cell point in tuning procedure */ - unsigned int strobe_dll_delay_target; /* The delay cell for strobe pad (read clock) */ -}; -#endif /* __ASM_ARCH_IMX_ESDHC_H */ -- cgit v1.2.3 From 86c639ce08266ed521974038f0592739fec1c11a Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 21 Jul 2021 08:47:38 -0700 Subject: mmc: core: Store pointer to bio_crypt_ctx in mmc_request Make 'struct mmc_request' contain a pointer to the request's 'struct bio_crypt_ctx' directly, instead of extracting a 32-bit DUN from it which is a cqhci-crypto specific detail. This keeps the cqhci crypto specific details in the cqhci module, and it makes mmc_core and mmc_block ready for MMC crypto hardware that accepts the DUN and/or key in a way that is more flexible than that which will be specified by the eMMC v5.2 standard. Exynos SoCs are an example of such hardware, as their inline encryption hardware takes keys directly (it has no concept of keyslots) and supports 128-bit DUNs. Note that the 32-bit DUN length specified by the standard is very restrictive, so it is likely that more hardware will support longer DUNs despite it not following the standard. Thus, limiting the scope of the 32-bit DUN assumption to the place that actually needs it is warranted. Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20210721154738.3966463-1-ebiggers@kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/core/crypto.c | 15 ++++----------- drivers/mmc/host/cqhci-crypto.h | 7 +++++-- include/linux/mmc/core.h | 3 +-- 3 files changed, 10 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/crypto.c b/drivers/mmc/core/crypto.c index 419a368f8402..67557808cada 100644 --- a/drivers/mmc/core/crypto.c +++ b/drivers/mmc/core/crypto.c @@ -31,18 +31,11 @@ void mmc_crypto_prepare_req(struct mmc_queue_req *mqrq) struct request *req = mmc_queue_req_to_req(mqrq); struct mmc_request *mrq = &mqrq->brq.mrq; - if (!req->crypt_keyslot) + if (!req->crypt_ctx) return; - mrq->crypto_enabled = true; - mrq->crypto_key_slot = blk_ksm_get_slot_idx(req->crypt_keyslot); - - /* - * For now we assume that all MMC drivers set max_dun_bytes_supported=4, - * which is the limit for CQHCI crypto. So all DUNs should be 32-bit. - */ - WARN_ON_ONCE(req->crypt_ctx->bc_dun[0] > U32_MAX); - - mrq->data_unit_num = req->crypt_ctx->bc_dun[0]; + mrq->crypto_ctx = req->crypt_ctx; + if (req->crypt_keyslot) + mrq->crypto_key_slot = blk_ksm_get_slot_idx(req->crypt_keyslot); } EXPORT_SYMBOL_GPL(mmc_crypto_prepare_req); diff --git a/drivers/mmc/host/cqhci-crypto.h b/drivers/mmc/host/cqhci-crypto.h index 60b58ee0e625..d7fb084f563b 100644 --- a/drivers/mmc/host/cqhci-crypto.h +++ b/drivers/mmc/host/cqhci-crypto.h @@ -22,12 +22,15 @@ int cqhci_crypto_init(struct cqhci_host *host); */ static inline u64 cqhci_crypto_prep_task_desc(struct mmc_request *mrq) { - if (!mrq->crypto_enabled) + if (!mrq->crypto_ctx) return 0; + /* We set max_dun_bytes_supported=4, so all DUNs should be 32-bit. */ + WARN_ON_ONCE(mrq->crypto_ctx->bc_dun[0] > U32_MAX); + return CQHCI_CRYPTO_ENABLE_BIT | CQHCI_CRYPTO_KEYSLOT(mrq->crypto_key_slot) | - mrq->data_unit_num; + mrq->crypto_ctx->bc_dun[0]; } #else /* CONFIG_MMC_CRYPTO */ diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index ab19245e9945..71101d1ec825 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -164,9 +164,8 @@ struct mmc_request { int tag; #ifdef CONFIG_MMC_CRYPTO - bool crypto_enabled; + const struct bio_crypt_ctx *crypto_ctx; int crypto_key_slot; - u32 data_unit_num; #endif }; -- cgit v1.2.3 From 291ee9d5da535f8c72408850a413074c4719c8d3 Mon Sep 17 00:00:00 2001 From: Mårten Lindahl Date: Mon, 16 Aug 2021 17:30:54 +0200 Subject: mmc: core: Update ->card_busy() callback comment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to SD specification checking state of DAT0 only, is enough while polling for card busy completion. Let's update the comment in the header file to correct this, as the comment says DAT[0:3]. Signed-off-by: Mårten Lindahl Link: https://lore.kernel.org/r/20210816153054.24082-1-marten.lindahl@axis.com Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 0abd47e9ef9b..ff1a251bb0bc 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -153,7 +153,7 @@ struct mmc_host_ops { int (*start_signal_voltage_switch)(struct mmc_host *host, struct mmc_ios *ios); - /* Check if the card is pulling dat[0:3] low */ + /* Check if the card is pulling dat[0] low */ int (*card_busy)(struct mmc_host *host); /* The tuning command opcode value is different for SD and eMMC cards */ -- cgit v1.2.3 From 95d1d2490c278ea316a4350f4c24818275fb989c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 23 Aug 2021 11:01:35 -0700 Subject: netdevice: move xdp_rxq within netdev_rx_queue Both struct netdev_rx_queue and struct xdp_rxq_info are cacheline aligned. This causes extra padding before and after the xdp_rxq member. Move the member upfront, so that it's naturally aligned. Before: /* size: 256, cachelines: 4, members: 6 */ /* sum members: 160, holes: 1, sum holes: 40 */ /* padding: 56 */ /* paddings: 1, sum paddings: 36 */ /* forced alignments: 1, forced holes: 1, sum forced holes: 40 */ After: /* size: 192, cachelines: 3, members: 6 */ /* padding: 32 */ /* paddings: 1, sum paddings: 36 */ /* forced alignments: 1 */ Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20210823180135.1153608-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2f03cd9e371a..b88ad5aef7fe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -722,13 +722,13 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { + struct xdp_rxq_info xdp_rxq; #ifdef CONFIG_RPS struct rps_map __rcu *rps_map; struct rps_dev_flow_table __rcu *rps_flow_table; #endif struct kobject kobj; struct net_device *dev; - struct xdp_rxq_info xdp_rxq; #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif -- cgit v1.2.3 From 029ee6b14356b94120bedb852dcdaefc0a282cf1 Mon Sep 17 00:00:00 2001 From: Yufeng Mo Date: Fri, 20 Aug 2021 15:35:17 +0800 Subject: ethtool: add two coalesce attributes for CQE mode Currently, there are many drivers who support CQE mode configuration, some configure it as a fixed when initialized, some provide an interface to change it by ethtool private flags. In order to make it more generic, add two new 'ETHTOOL_A_COALESCE_USE_CQE_TX' and 'ETHTOOL_A_COALESCE_USE_CQE_RX' coalesce attributes, then these parameters can be accessed by ethtool netlink coalesce uAPI. Also add an new structure kernel_ethtool_coalesce, then the new parameter can be added into this struct. Signed-off-by: Yufeng Mo Signed-off-by: Huazhong Tan Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 15 +++++++++++++++ include/linux/ethtool.h | 11 ++++++++++- include/uapi/linux/ethtool_netlink.h | 2 ++ net/ethtool/coalesce.c | 19 +++++++++++++++++-- net/ethtool/netlink.h | 2 +- 5 files changed, 45 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index c690bb37430d..d9b55b7a1a4d 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -947,12 +947,25 @@ Kernel response contents: ``ETHTOOL_A_COALESCE_TX_USECS_HIGH`` u32 delay (us), high Tx ``ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH`` u32 max packets, high Tx ``ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL`` u32 rate sampling interval + ``ETHTOOL_A_COALESCE_USE_CQE_TX`` bool timer reset mode, Tx + ``ETHTOOL_A_COALESCE_USE_CQE_RX`` bool timer reset mode, Rx =========================================== ====== ======================= Attributes are only included in reply if their value is not zero or the corresponding bit in ``ethtool_ops::supported_coalesce_params`` is set (i.e. they are declared as supported by driver). +Timer reset mode (``ETHTOOL_A_COALESCE_USE_CQE_TX`` and +``ETHTOOL_A_COALESCE_USE_CQE_RX``) controls the interaction between packet +arrival and the various time based delay parameters. By default timers are +expected to limit the max delay between any packet arrival/departure and a +corresponding interrupt. In this mode timer should be started by packet +arrival (sometimes delivery of previous interrupt) and reset when interrupt +is delivered. +Setting the appropriate attribute to 1 will enable ``CQE`` mode, where +each packet event resets the timer. In this mode timer is used to force +the interrupt if queue goes idle, while busy queues depend on the packet +limit to trigger interrupts. COALESCE_SET ============ @@ -985,6 +998,8 @@ Request contents: ``ETHTOOL_A_COALESCE_TX_USECS_HIGH`` u32 delay (us), high Tx ``ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH`` u32 max packets, high Tx ``ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL`` u32 rate sampling interval + ``ETHTOOL_A_COALESCE_USE_CQE_TX`` bool timer reset mode, Tx + ``ETHTOOL_A_COALESCE_USE_CQE_RX`` bool timer reset mode, Rx =========================================== ====== ======================= Request is rejected if it attributes declared as unsupported by driver (i.e. diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 4711b96dae0c..a9d77a6a3e00 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -172,6 +172,11 @@ extern int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); +struct kernel_ethtool_coalesce { + u8 use_cqe_mode_tx; + u8 use_cqe_mode_rx; +}; + /** * ethtool_intersect_link_masks - Given two link masks, AND them together * @dst: first mask and where result is stored @@ -211,7 +216,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_TX_USECS_HIGH BIT(19) #define ETHTOOL_COALESCE_TX_MAX_FRAMES_HIGH BIT(20) #define ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL BIT(21) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(21, 0) +#define ETHTOOL_COALESCE_USE_CQE_RX BIT(22) +#define ETHTOOL_COALESCE_USE_CQE_TX BIT(23) +#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(23, 0) #define ETHTOOL_COALESCE_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) @@ -237,6 +244,8 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, ETHTOOL_COALESCE_RX_USECS_LOW | ETHTOOL_COALESCE_RX_USECS_HIGH | \ ETHTOOL_COALESCE_PKT_RATE_LOW | ETHTOOL_COALESCE_PKT_RATE_HIGH | \ ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL) +#define ETHTOOL_COALESCE_USE_CQE \ + (ETHTOOL_COALESCE_USE_CQE_RX | ETHTOOL_COALESCE_USE_CQE_TX) #define ETHTOOL_STAT_NOT_SET (~0ULL) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index b3b93710eff7..5545f1ca9237 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -377,6 +377,8 @@ enum { ETHTOOL_A_COALESCE_TX_USECS_HIGH, /* u32 */ ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, /* u32 */ ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, /* u32 */ + ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, /* u8 */ + ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, /* u8 */ /* add new constants above here */ __ETHTOOL_A_COALESCE_CNT, diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 1d6bc132aa4d..e6bc53634e68 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -10,6 +10,7 @@ struct coalesce_req_info { struct coalesce_reply_data { struct ethnl_reply_data base; struct ethtool_coalesce coalesce; + struct kernel_ethtool_coalesce kernel_coalesce; u32 supported_params; }; @@ -100,7 +101,9 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_HIGH */ nla_total_size(sizeof(u32)) + /* _TX_USECS_HIGH */ nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_HIGH */ - nla_total_size(sizeof(u32)); /* _RATE_SAMPLE_INTERVAL */ + nla_total_size(sizeof(u32)) + /* _RATE_SAMPLE_INTERVAL */ + nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_TX */ + nla_total_size(sizeof(u8)); /* _USE_CQE_MODE_RX */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, @@ -124,6 +127,7 @@ static int coalesce_fill_reply(struct sk_buff *skb, const struct ethnl_reply_data *reply_base) { const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); + const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce; const struct ethtool_coalesce *coal = &data->coalesce; u32 supported = data->supported_params; @@ -170,7 +174,11 @@ static int coalesce_fill_reply(struct sk_buff *skb, coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, coal->tx_max_coalesced_frames_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, - coal->rate_sample_interval, supported)) + coal->rate_sample_interval, supported) || + coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, + kcoal->use_cqe_mode_tx, supported) || + coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, + kcoal->use_cqe_mode_rx, supported)) return -EMSGSIZE; return 0; @@ -215,10 +223,13 @@ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_TX_USECS_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_USE_CQE_MODE_TX] = NLA_POLICY_MAX(NLA_U8, 1), + [ETHTOOL_A_COALESCE_USE_CQE_MODE_RX] = NLA_POLICY_MAX(NLA_U8, 1), }; int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) { + struct kernel_ethtool_coalesce kernel_coalesce = {}; struct ethtool_coalesce coalesce = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; @@ -303,6 +314,10 @@ int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH], &mod); ethnl_update_u32(&coalesce.rate_sample_interval, tb[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL], &mod); + ethnl_update_u8(&kernel_coalesce.use_cqe_mode_tx, + tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_TX], &mod); + ethnl_update_u8(&kernel_coalesce.use_cqe_mode_rx, + tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_RX], &mod); ret = 0; if (!mod) goto out_ops; diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 077aac3929a8..e8987e28036f 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -359,7 +359,7 @@ extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_TX + 1]; extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1]; extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1]; extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; -extern const struct nla_policy ethnl_coalesce_set_policy[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL + 1]; +extern const struct nla_policy ethnl_coalesce_set_policy[ETHTOOL_A_COALESCE_MAX + 1]; extern const struct nla_policy ethnl_pause_get_policy[ETHTOOL_A_PAUSE_HEADER + 1]; extern const struct nla_policy ethnl_pause_set_policy[ETHTOOL_A_PAUSE_TX + 1]; extern const struct nla_policy ethnl_eee_get_policy[ETHTOOL_A_EEE_HEADER + 1]; -- cgit v1.2.3 From f3ccfda1931977b80267ba54070a1aeafa18f6ca Mon Sep 17 00:00:00 2001 From: Yufeng Mo Date: Fri, 20 Aug 2021 15:35:18 +0800 Subject: ethtool: extend coalesce setting uAPI with CQE mode In order to support more coalesce parameters through netlink, add two new parameter kernel_coal and extack for .set_coalesce and .get_coalesce, then some extra info can return to user with the netlink API. Signed-off-by: Yufeng Mo Signed-off-by: Huazhong Tan Signed-off-by: Jakub Kicinski --- drivers/infiniband/ulp/ipoib/ipoib_ethtool.c | 8 ++++++-- drivers/net/ethernet/amazon/ena/ena_ethtool.c | 8 ++++++-- drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c | 8 ++++++-- drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c | 8 ++++++-- drivers/net/ethernet/broadcom/bcmsysport.c | 8 ++++++-- drivers/net/ethernet/broadcom/bnx2.c | 12 ++++++++---- drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 8 ++++++-- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 8 ++++++-- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 ++++++-- drivers/net/ethernet/broadcom/tg3.c | 10 ++++++++-- drivers/net/ethernet/brocade/bna/bnad_ethtool.c | 12 ++++++++---- drivers/net/ethernet/cavium/liquidio/lio_ethtool.c | 8 ++++++-- drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c | 4 +++- drivers/net/ethernet/chelsio/cxgb/cxgb2.c | 8 ++++++-- drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 8 ++++++-- drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 8 ++++++-- drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c | 8 ++++++-- drivers/net/ethernet/cisco/enic/enic_ethtool.c | 8 ++++++-- drivers/net/ethernet/cortina/gemini.c | 8 ++++++-- drivers/net/ethernet/emulex/benet/be_ethtool.c | 8 ++++++-- drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c | 8 ++++++-- drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 8 ++++++-- drivers/net/ethernet/freescale/fec_main.c | 14 +++++++++----- drivers/net/ethernet/freescale/gianfar_ethtool.c | 8 ++++++-- drivers/net/ethernet/hisilicon/hip04_eth.c | 8 ++++++-- drivers/net/ethernet/hisilicon/hns/hns_ethtool.c | 12 ++++++++++-- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 8 ++++++-- drivers/net/ethernet/huawei/hinic/hinic_ethtool.c | 8 ++++++-- drivers/net/ethernet/intel/e1000/e1000_ethtool.c | 8 ++++++-- drivers/net/ethernet/intel/e1000e/ethtool.c | 8 ++++++-- drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c | 8 ++++++-- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 12 ++++++++++-- drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 12 ++++++++++-- drivers/net/ethernet/intel/ice/ice_ethtool.c | 12 ++++++++---- drivers/net/ethernet/intel/igb/igb_ethtool.c | 8 ++++++-- drivers/net/ethernet/intel/igbvf/ethtool.c | 8 ++++++-- drivers/net/ethernet/intel/igc/igc_ethtool.c | 8 ++++++-- drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 8 ++++++-- drivers/net/ethernet/intel/ixgbevf/ethtool.c | 8 ++++++-- drivers/net/ethernet/jme.c | 12 ++++++++---- drivers/net/ethernet/marvell/mv643xx_eth.c | 12 ++++++++---- drivers/net/ethernet/marvell/mvneta.c | 14 ++++++++++---- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 14 ++++++++++---- .../net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c | 8 ++++++-- drivers/net/ethernet/marvell/skge.c | 8 ++++++-- drivers/net/ethernet/marvell/sky2.c | 8 ++++++-- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 8 ++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 8 ++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 8 ++++++-- .../net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c | 8 ++++++-- drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 12 ++++++++---- drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 8 ++++++-- drivers/net/ethernet/ni/nixge.c | 14 ++++++++++---- drivers/net/ethernet/pensando/ionic/ionic_ethtool.c | 8 ++++++-- .../net/ethernet/qlogic/netxen/netxen_nic_ethtool.c | 8 ++++++-- drivers/net/ethernet/qlogic/qede/qede.h | 4 +++- drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 8 ++++++-- drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c | 8 ++++++-- drivers/net/ethernet/realtek/r8169_main.c | 10 ++++++++-- drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c | 8 ++++++-- drivers/net/ethernet/sfc/ethtool.c | 8 ++++++-- drivers/net/ethernet/sfc/falcon/ethtool.c | 8 ++++++-- drivers/net/ethernet/socionext/netsec.c | 10 +++++++--- drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 8 ++++++-- drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c | 14 ++++++++++---- drivers/net/ethernet/tehuti/tehuti.c | 12 ++++++++---- drivers/net/ethernet/ti/cpsw.c | 2 +- drivers/net/ethernet/ti/cpsw_ethtool.c | 8 ++++++-- drivers/net/ethernet/ti/cpsw_new.c | 2 +- drivers/net/ethernet/ti/cpsw_priv.h | 8 ++++++-- drivers/net/ethernet/ti/davinci_emac.c | 14 +++++++++++--- drivers/net/ethernet/via/via-velocity.c | 8 ++++++-- drivers/net/ethernet/xilinx/ll_temac_main.c | 14 ++++++++++---- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 18 ++++++++++++++---- drivers/net/netdevsim/ethtool.c | 8 ++++++-- drivers/net/tun.c | 8 ++++++-- drivers/net/usb/r8152.c | 8 ++++++-- drivers/net/virtio_net.c | 8 ++++++-- drivers/net/vmxnet3/vmxnet3_ethtool.c | 12 ++++++++---- drivers/net/wireless/ath/wil6210/ethtool.c | 14 ++++++++++---- drivers/s390/net/qeth_ethtool.c | 4 +++- drivers/staging/qlge/qlge_ethtool.c | 10 ++++++++-- include/linux/ethtool.h | 11 +++++++++-- net/ethtool/coalesce.c | 10 +++++++--- net/ethtool/ioctl.c | 15 ++++++++++++--- 85 files changed, 576 insertions(+), 202 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c index 823f6831e7ea..a09ca21f7dff 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c @@ -72,7 +72,9 @@ static void ipoib_get_drvinfo(struct net_device *netdev, } static int ipoib_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -83,7 +85,9 @@ static int ipoib_get_coalesce(struct net_device *dev, } static int ipoib_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret; diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index 27dae632efcb..13e745cf3781 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -357,7 +357,9 @@ static int ena_get_link_ksettings(struct net_device *netdev, } static int ena_get_coalesce(struct net_device *net_dev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ena_adapter *adapter = netdev_priv(net_dev); struct ena_com_dev *ena_dev = adapter->ena_dev; @@ -402,7 +404,9 @@ static void ena_update_rx_rings_nonadaptive_intr_moderation(struct ena_adapter * } static int ena_set_coalesce(struct net_device *net_dev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ena_adapter *adapter = netdev_priv(net_dev); struct ena_com_dev *ena_dev = adapter->ena_dev; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index 61f39a0e04f9..bafc51c34e0b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -428,7 +428,9 @@ static void xgbe_set_msglevel(struct net_device *netdev, u32 msglevel) } static int xgbe_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct xgbe_prv_data *pdata = netdev_priv(netdev); @@ -443,7 +445,9 @@ static int xgbe_get_coalesce(struct net_device *netdev, } static int xgbe_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index de2a9348bc3f..a9ef0544e30f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -547,7 +547,9 @@ static int aq_ethtool_set_rxnfc(struct net_device *ndev, } static int aq_ethtool_get_coalesce(struct net_device *ndev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct aq_nic_s *aq_nic = netdev_priv(ndev); struct aq_nic_cfg_s *cfg; @@ -571,7 +573,9 @@ static int aq_ethtool_get_coalesce(struct net_device *ndev, } static int aq_ethtool_set_coalesce(struct net_device *ndev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct aq_nic_s *aq_nic = netdev_priv(ndev); struct aq_nic_cfg_s *cfg; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index d9f0f0df8f7b..7fa1b695400d 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -607,7 +607,9 @@ static void bcm_sysport_set_tx_coalesce(struct bcm_sysport_tx_ring *ring, } static int bcm_sysport_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bcm_sysport_priv *priv = netdev_priv(dev); u32 reg; @@ -627,7 +629,9 @@ static int bcm_sysport_get_coalesce(struct net_device *dev, } static int bcm_sysport_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bcm_sysport_priv *priv = netdev_priv(dev); struct dim_cq_moder moder; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index dc3ee576360b..a705e2615307 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -7242,8 +7242,10 @@ bnx2_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, return rc; } -static int -bnx2_get_coalesce(struct net_device *dev, struct ethtool_coalesce *coal) +static int bnx2_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bnx2 *bp = netdev_priv(dev); @@ -7264,8 +7266,10 @@ bnx2_get_coalesce(struct net_device *dev, struct ethtool_coalesce *coal) return 0; } -static int -bnx2_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal) +static int bnx2_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bnx2 *bp = netdev_priv(dev); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 32245bbe88a8..472a3a478038 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1878,7 +1878,9 @@ static int bnx2x_set_eeprom(struct net_device *dev, } static int bnx2x_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bnx2x *bp = netdev_priv(dev); @@ -1891,7 +1893,9 @@ static int bnx2x_get_coalesce(struct net_device *dev, } static int bnx2x_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bnx2x *bp = netdev_priv(dev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 364460ef8db7..9f8c72d95228 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -49,7 +49,9 @@ static void bnxt_set_msglevel(struct net_device *dev, u32 value) } static int bnxt_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bnxt *bp = netdev_priv(dev); struct bnxt_coal *hw_coal; @@ -79,7 +81,9 @@ static int bnxt_get_coalesce(struct net_device *dev, } static int bnxt_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bnxt *bp = netdev_priv(dev); bool update_stats = false; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 8507198992df..23c7595d2a1d 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -828,7 +828,9 @@ static void bcmgenet_set_msglevel(struct net_device *dev, u32 level) } static int bcmgenet_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bcmgenet_priv *priv = netdev_priv(dev); struct bcmgenet_rx_ring *ring; @@ -890,7 +892,9 @@ static void bcmgenet_set_ring_rx_coalesce(struct bcmgenet_rx_ring *ring, } static int bcmgenet_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bcmgenet_priv *priv = netdev_priv(dev); unsigned int i; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index eefb070a68d2..8a238e349e02 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -14037,7 +14037,10 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EOPNOTSUPP; } -static int tg3_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) +static int tg3_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct tg3 *tp = netdev_priv(dev); @@ -14045,7 +14048,10 @@ static int tg3_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) return 0; } -static int tg3_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) +static int tg3_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct tg3 *tp = netdev_priv(dev); u32 max_rxcoal_tick_int = 0, max_txcoal_tick_int = 0; diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c index 265c2fa6bbe0..391b85f25141 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c +++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c @@ -307,8 +307,10 @@ bnad_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wolinfo) wolinfo->wolopts = 0; } -static int -bnad_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *coalesce) +static int bnad_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bnad *bnad = netdev_priv(netdev); unsigned long flags; @@ -328,8 +330,10 @@ bnad_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *coalesce) return 0; } -static int -bnad_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *coalesce) +static int bnad_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct bnad *bnad = netdev_priv(netdev); unsigned long flags; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 66f2c553370c..2b9747867d4c 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -2108,7 +2108,9 @@ static int octnet_set_intrmod_cfg(struct lio *lio, } static int lio_get_intr_coalesce(struct net_device *netdev, - struct ethtool_coalesce *intr_coal) + struct ethtool_coalesce *intr_coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; @@ -2412,7 +2414,9 @@ oct_cfg_tx_intrcnt(struct lio *lio, } static int lio_set_intr_coalesce(struct net_device *netdev, - struct ethtool_coalesce *intr_coal) + struct ethtool_coalesce *intr_coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct lio *lio = GET_LIO(netdev); int ret; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index 2f218fbfed06..7f2882109b16 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -456,7 +456,9 @@ static void nicvf_get_regs(struct net_device *dev, } static int nicvf_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *cmd) + struct ethtool_coalesce *cmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct nicvf *nic = netdev_priv(netdev); diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c index e7575d41f4f5..73c016166f06 100644 --- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c +++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c @@ -748,7 +748,9 @@ static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e) return 0; } -static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c) +static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct adapter *adapter = dev->ml_priv; @@ -759,7 +761,9 @@ static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c) return 0; } -static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) +static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct adapter *adapter = dev->ml_priv; diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 538f737af4fa..38e47703f9ab 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -1996,7 +1996,9 @@ static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e) return 0; } -static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c) +static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; @@ -2017,7 +2019,9 @@ static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c) return 0; } -static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) +static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 83ed10ac8660..5903bdb78916 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -1147,7 +1147,9 @@ static int set_dbqtimer_tickval(struct net_device *dev, } static int set_coalesce(struct net_device *dev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { int ret; @@ -1163,7 +1165,9 @@ static int set_coalesce(struct net_device *dev, coalesce->tx_coalesce_usecs); } -static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) +static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { const struct port_info *pi = netdev_priv(dev); const struct adapter *adap = pi->adapter; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index e5882df551ec..49b76fd47daa 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -1647,7 +1647,9 @@ static int cxgb4vf_set_ringparam(struct net_device *dev, * interrupt holdoff timer to be read on all of the device's Queue Sets. */ static int cxgb4vf_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { const struct port_info *pi = netdev_priv(dev); const struct adapter *adapter = pi->adapter; @@ -1667,7 +1669,9 @@ static int cxgb4vf_get_coalesce(struct net_device *dev, * the interrupt holdoff timer on any of the device's Queue Sets. */ static int cxgb4vf_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { const struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c index 1a9803f2073e..12ffc14fbecd 100644 --- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -298,7 +298,9 @@ static void enic_set_msglevel(struct net_device *netdev, u32 value) } static int enic_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ecmd) + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct enic *enic = netdev_priv(netdev); struct enic_rx_coal *rxcoal = &enic->rx_coalesce_setting; @@ -343,7 +345,9 @@ static int enic_coalesce_valid(struct enic *enic, } static int enic_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ecmd) + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct enic *enic = netdev_priv(netdev); u32 tx_coalesce_usecs; diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index c2ebb3388789..6e745ca4c433 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2144,7 +2144,9 @@ static int gmac_set_ringparam(struct net_device *netdev, } static int gmac_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ecmd) + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct gemini_ethernet_port *port = netdev_priv(netdev); @@ -2156,7 +2158,9 @@ static int gmac_get_coalesce(struct net_device *netdev, } static int gmac_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ecmd) + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct gemini_ethernet_port *port = netdev_priv(netdev); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 99cc1c46fb30..f9955308b93d 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -315,7 +315,9 @@ static int be_read_dump_data(struct be_adapter *adapter, u32 dump_len, } static int be_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *et) + struct ethtool_coalesce *et, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct be_adapter *adapter = netdev_priv(netdev); struct be_aic_obj *aic = &adapter->aic_obj[0]; @@ -338,7 +340,9 @@ static int be_get_coalesce(struct net_device *netdev, * eqd cmd is issued in the worker thread. */ static int be_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *et) + struct ethtool_coalesce *et, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct be_adapter *adapter = netdev_priv(netdev); struct be_aic_obj *aic = &adapter->aic_obj[0]; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 1268996b7030..763d2c7b5fb1 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -513,7 +513,9 @@ static int dpaa_get_ts_info(struct net_device *net_dev, } static int dpaa_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *c) + struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct qman_portal *portal; u32 period; @@ -530,7 +532,9 @@ static int dpaa_get_coalesce(struct net_device *dev, } static int dpaa_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *c) + struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { const cpumask_t *cpus = qman_affine_cpus(); bool needs_revert[NR_CPUS] = {false}; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index ebccaf02411c..9690e36e9e85 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -585,7 +585,9 @@ static void enetc_get_ringparam(struct net_device *ndev, } static int enetc_get_coalesce(struct net_device *ndev, - struct ethtool_coalesce *ic) + struct ethtool_coalesce *ic, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_int_vector *v = priv->int_vector[0]; @@ -602,7 +604,9 @@ static int enetc_get_coalesce(struct net_device *ndev, } static int enetc_set_coalesce(struct net_device *ndev, - struct ethtool_coalesce *ic) + struct ethtool_coalesce *ic, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct enetc_ndev_priv *priv = netdev_priv(ndev); u32 rx_ictt, tx_ictt; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 83ab34b1d735..80bd5c629fa0 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2654,8 +2654,10 @@ static void fec_enet_itr_coal_set(struct net_device *ndev) } } -static int -fec_enet_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec) +static int fec_enet_get_coalesce(struct net_device *ndev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct fec_enet_private *fep = netdev_priv(ndev); @@ -2671,8 +2673,10 @@ fec_enet_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec) return 0; } -static int -fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec) +static int fec_enet_set_coalesce(struct net_device *ndev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct fec_enet_private *fep = netdev_priv(ndev); struct device *dev = &fep->pdev->dev; @@ -2724,7 +2728,7 @@ static void fec_enet_itr_coal_init(struct net_device *ndev) ec.tx_coalesce_usecs = FEC_ITR_ICTT_DEFAULT; ec.tx_max_coalesced_frames = FEC_ITR_ICFT_DEFAULT; - fec_enet_set_coalesce(ndev, &ec); + fec_enet_set_coalesce(ndev, &ec, NULL, NULL); } static int fec_enet_get_tunable(struct net_device *netdev, diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index cc7d4f93da54..7b32ed29bf4c 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -243,7 +243,9 @@ static unsigned int gfar_ticks2usecs(struct gfar_private *priv, /* Get the coalescing parameters, and put them in the cvals * structure. */ static int gfar_gcoalesce(struct net_device *dev, - struct ethtool_coalesce *cvals) + struct ethtool_coalesce *cvals, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct gfar_private *priv = netdev_priv(dev); struct gfar_priv_rx_q *rx_queue = NULL; @@ -280,7 +282,9 @@ static int gfar_gcoalesce(struct net_device *dev, * in order for coalescing to be active */ static int gfar_scoalesce(struct net_device *dev, - struct ethtool_coalesce *cvals) + struct ethtool_coalesce *cvals, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct gfar_private *priv = netdev_priv(dev); int i, err = 0; diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index e53512f6878a..37b605fed32c 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -796,7 +796,9 @@ static void hip04_tx_timeout_task(struct work_struct *work) } static int hip04_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct hip04_priv *priv = netdev_priv(netdev); @@ -807,7 +809,9 @@ static int hip04_get_coalesce(struct net_device *netdev, } static int hip04_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct hip04_priv *priv = netdev_priv(netdev); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 7e62dcff2426..ab7390225942 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -730,11 +730,15 @@ static int hns_set_pauseparam(struct net_device *net_dev, * hns_get_coalesce - get coalesce info. * @net_dev: net device * @ec: coalesce info. + * @kernel_coal: ethtool CQE mode setting structure + * @extack: extack for reporting error messages * * Return 0 on success, negative on failure. */ static int hns_get_coalesce(struct net_device *net_dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct hns_nic_priv *priv = netdev_priv(net_dev); struct hnae_ae_ops *ops; @@ -774,11 +778,15 @@ static int hns_get_coalesce(struct net_device *net_dev, * hns_set_coalesce - set coalesce info. * @net_dev: net device * @ec: coalesce info. + * @kernel_coal: ethtool CQE mode setting structure + * @extack: extack for reporting error messages * * Return 0 on success, negative on failure. */ static int hns_set_coalesce(struct net_device *net_dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct hns_nic_priv *priv = netdev_priv(net_dev); struct hnae_ae_ops *ops; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 835105015763..049be076fd18 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1179,7 +1179,9 @@ static void hns3_get_channels(struct net_device *netdev, } static int hns3_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *cmd) + struct ethtool_coalesce *cmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct hns3_nic_priv *priv = netdev_priv(netdev); struct hns3_enet_coalesce *tx_coal = &priv->tx_coal; @@ -1361,7 +1363,9 @@ static void hns3_set_coalesce_per_queue(struct net_device *netdev, } static int hns3_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *cmd) + struct ethtool_coalesce *cmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct hnae3_handle *h = hns3_get_handle(netdev); struct hns3_nic_priv *priv = netdev_priv(netdev); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index 162d3c330dec..b431c300ef1b 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -795,13 +795,17 @@ static int __hinic_set_coalesce(struct net_device *netdev, } static int hinic_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { return __hinic_get_coalesce(netdev, coal, COALESCE_ALL_QUEUE); } static int hinic_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { return __hinic_set_coalesce(netdev, coal, COALESCE_ALL_QUEUE); } diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index 3c51ee94fa00..0a57172dfcbc 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -1739,7 +1739,9 @@ static int e1000_set_phys_id(struct net_device *netdev, } static int e1000_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct e1000_adapter *adapter = netdev_priv(netdev); @@ -1755,7 +1757,9 @@ static int e1000_get_coalesce(struct net_device *netdev, } static int e1000_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 7256b43b7a65..8515e00d1b40 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -1993,7 +1993,9 @@ static int e1000_set_phys_id(struct net_device *netdev, } static int e1000_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct e1000_adapter *adapter = netdev_priv(netdev); @@ -2006,7 +2008,9 @@ static int e1000_get_coalesce(struct net_device *netdev, } static int e1000_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct e1000_adapter *adapter = netdev_priv(netdev); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 66776ba7bfb6..0d37f011d0ce 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -632,7 +632,9 @@ clear_reset: } static int fm10k_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct fm10k_intfc *interface = netdev_priv(dev); @@ -646,7 +648,9 @@ static int fm10k_get_coalesce(struct net_device *dev, } static int fm10k_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct fm10k_intfc *interface = netdev_priv(dev); u16 tx_itr, rx_itr; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 2c9e4eeb7270..513ba6974355 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2812,13 +2812,17 @@ static int __i40e_get_coalesce(struct net_device *netdev, * i40e_get_coalesce - get a netdev's coalesce settings * @netdev: the netdev to check * @ec: ethtool coalesce data structure + * @kernel_coal: ethtool CQE mode setting structure + * @extack: extack for reporting error messages * * Gets the coalesce settings for a particular netdev. Note that if user has * modified per-queue settings, this only guarantees to represent queue 0. See * __i40e_get_coalesce for more details. **/ static int i40e_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { return __i40e_get_coalesce(netdev, ec, -1); } @@ -2986,11 +2990,15 @@ static int __i40e_set_coalesce(struct net_device *netdev, * i40e_set_coalesce - set coalesce settings for every queue on the netdev * @netdev: the netdev to change * @ec: ethtool coalesce settings + * @kernel_coal: ethtool CQE mode setting structure + * @extack: extack for reporting error messages * * This will set each queue to the same coalesce settings. **/ static int i40e_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { return __i40e_set_coalesce(netdev, ec, -1); } diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index edbeb27213f8..5a359a0a20ec 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -685,6 +685,8 @@ static int __iavf_get_coalesce(struct net_device *netdev, * iavf_get_coalesce - Get interrupt coalescing settings * @netdev: network interface device structure * @ec: ethtool coalesce structure + * @kernel_coal: ethtool CQE mode setting structure + * @extack: extack for reporting error messages * * Returns current coalescing settings. This is referred to elsewhere in the * driver as Interrupt Throttle Rate, as this is how the hardware describes @@ -692,7 +694,9 @@ static int __iavf_get_coalesce(struct net_device *netdev, * only represents the settings of queue 0. **/ static int iavf_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { return __iavf_get_coalesce(netdev, ec, -1); } @@ -804,11 +808,15 @@ static int __iavf_set_coalesce(struct net_device *netdev, * iavf_set_coalesce - Set interrupt coalescing settings * @netdev: network interface device structure * @ec: ethtool coalesce structure + * @kernel_coal: ethtool CQE mode setting structure + * @extack: extack for reporting error messages * * Change current coalescing settings for every queue. **/ static int iavf_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { return __iavf_set_coalesce(netdev, ec, -1); } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index d95a5daca114..c451cf401e63 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3568,8 +3568,10 @@ __ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, return 0; } -static int -ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec) +static int ice_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { return __ice_get_coalesce(netdev, ec, -1); } @@ -3787,8 +3789,10 @@ set_complete: return 0; } -static int -ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec) +static int ice_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { return __ice_set_coalesce(netdev, ec, -1); } diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 17f5c003c3df..fb1029352c3e 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2182,7 +2182,9 @@ static int igb_set_phys_id(struct net_device *netdev, } static int igb_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct igb_adapter *adapter = netdev_priv(netdev); int i; @@ -2238,7 +2240,9 @@ static int igb_set_coalesce(struct net_device *netdev, } static int igb_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct igb_adapter *adapter = netdev_priv(netdev); diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c index f4835eb62fee..06e5bd646a0e 100644 --- a/drivers/net/ethernet/intel/igbvf/ethtool.c +++ b/drivers/net/ethernet/intel/igbvf/ethtool.c @@ -314,7 +314,9 @@ static int igbvf_set_wol(struct net_device *netdev, } static int igbvf_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct igbvf_adapter *adapter = netdev_priv(netdev); @@ -327,7 +329,9 @@ static int igbvf_get_coalesce(struct net_device *netdev, } static int igbvf_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct igbvf_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index d3e84416248e..e0a76ac1bbbc 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -862,7 +862,9 @@ static void igc_ethtool_get_stats(struct net_device *netdev, } static int igc_ethtool_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct igc_adapter *adapter = netdev_priv(netdev); @@ -882,7 +884,9 @@ static int igc_ethtool_get_coalesce(struct net_device *netdev, } static int igc_ethtool_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct igc_adapter *adapter = netdev_priv(netdev); int i; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 4ceaca0f6ce3..fc26e4ddeb0d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2358,7 +2358,9 @@ static int ixgbe_set_phys_id(struct net_device *netdev, } static int ixgbe_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ixgbe_adapter *adapter = netdev_priv(netdev); @@ -2412,7 +2414,9 @@ static bool ixgbe_update_rsc(struct ixgbe_adapter *adapter) } static int ixgbe_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_q_vector *q_vector; diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index e49fb1cd9a99..8380f905e708 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -787,7 +787,9 @@ static int ixgbevf_nway_reset(struct net_device *netdev) } static int ixgbevf_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); @@ -811,7 +813,9 @@ static int ixgbevf_get_coalesce(struct net_device *netdev, } static int ixgbevf_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbevf_q_vector *q_vector; diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 438c5602fbc5..1bdc4f23e1e5 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -2385,8 +2385,10 @@ jme_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) mdio_memcpy(jme, p32, JME_PHY_REG_NR); } -static int -jme_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecmd) +static int jme_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct jme_adapter *jme = netdev_priv(netdev); @@ -2422,8 +2424,10 @@ jme_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecmd) return 0; } -static int -jme_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecmd) +static int jme_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct jme_adapter *jme = netdev_priv(netdev); struct dynpcc_info *dpi = &(jme->dpi); diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 6502c5c2ebca..28d5ad296646 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1611,8 +1611,10 @@ static void mv643xx_eth_get_drvinfo(struct net_device *dev, strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); } -static int -mv643xx_eth_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) +static int mv643xx_eth_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mv643xx_eth_private *mp = netdev_priv(dev); @@ -1622,8 +1624,10 @@ mv643xx_eth_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) return 0; } -static int -mv643xx_eth_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) +static int mv643xx_eth_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mv643xx_eth_private *mp = netdev_priv(dev); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 5d1007e1b5c9..0e6d40701862 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4500,8 +4500,11 @@ static int mvneta_ethtool_nway_reset(struct net_device *dev) } /* Set interrupt coalescing for ethtools */ -static int mvneta_ethtool_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *c) +static int +mvneta_ethtool_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mvneta_port *pp = netdev_priv(dev); int queue; @@ -4524,8 +4527,11 @@ static int mvneta_ethtool_set_coalesce(struct net_device *dev, } /* get coalescing for ethtools */ -static int mvneta_ethtool_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *c) +static int +mvneta_ethtool_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mvneta_port *pp = netdev_priv(dev); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 744f58f41ecc..d5c92e43f89e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5367,8 +5367,11 @@ static int mvpp2_ethtool_nway_reset(struct net_device *dev) } /* Set interrupt coalescing for ethtools */ -static int mvpp2_ethtool_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *c) +static int +mvpp2_ethtool_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mvpp2_port *port = netdev_priv(dev); int queue; @@ -5400,8 +5403,11 @@ static int mvpp2_ethtool_set_coalesce(struct net_device *dev, } /* get coalescing for ethtools */ -static int mvpp2_ethtool_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *c) +static int +mvpp2_ethtool_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mvpp2_port *port = netdev_priv(dev); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 0151d6d939d4..5ce087686a1f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -412,7 +412,9 @@ static int otx2_set_ringparam(struct net_device *netdev, } static int otx2_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *cmd) + struct ethtool_coalesce *cmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct otx2_nic *pfvf = netdev_priv(netdev); struct otx2_hw *hw = &pfvf->hw; @@ -426,7 +428,9 @@ static int otx2_get_coalesce(struct net_device *netdev, } static int otx2_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct otx2_nic *pfvf = netdev_priv(netdev); struct otx2_hw *hw = &pfvf->hw; diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 150c06ee3627..051dd3fb5b03 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -615,7 +615,9 @@ static inline u32 skge_usecs2clk(const struct skge_hw *hw, u32 usec) } static int skge_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *ecmd) + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct skge_port *skge = netdev_priv(dev); struct skge_hw *hw = skge->hw; @@ -639,7 +641,9 @@ static int skge_get_coalesce(struct net_device *dev, /* Note: interrupt timer is per board, but can turn on/off per port */ static int skge_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *ecmd) + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct skge_port *skge = netdev_priv(dev); struct skge_hw *hw = skge->hw; diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index dc9dd77d1ea0..e9fc74e54b22 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4052,7 +4052,9 @@ static int sky2_set_pauseparam(struct net_device *dev, } static int sky2_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *ecmd) + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct sky2_port *sky2 = netdev_priv(dev); struct sky2_hw *hw = sky2->hw; @@ -4087,7 +4089,9 @@ static int sky2_get_coalesce(struct net_device *dev, /* Note: this affect both ports */ static int sky2_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *ecmd) + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct sky2_port *sky2 = netdev_priv(dev); struct sky2_hw *hw = sky2->hw; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 3616b77caa0a..ef518b1040f7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -998,7 +998,9 @@ mlx4_en_set_link_ksettings(struct net_device *dev, } static int mlx4_en_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -1020,7 +1022,9 @@ static int mlx4_en_get_coalesce(struct net_device *dev, } static int mlx4_en_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx4_en_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 5696d3f1baaf..2cfd12953909 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -534,7 +534,9 @@ int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv, } static int mlx5e_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -652,7 +654,9 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, } static int mlx5e_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index eb83f27850c7..ae71a17fdb27 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -251,7 +251,9 @@ static int mlx5e_rep_set_channels(struct net_device *dev, } static int mlx5e_rep_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -259,7 +261,9 @@ static int mlx5e_rep_get_coalesce(struct net_device *netdev, } static int mlx5e_rep_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 0e487ec57d5c..0c8594c7df21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -99,7 +99,9 @@ static void mlx5i_get_channels(struct net_device *dev, } static int mlx5i_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); @@ -107,7 +109,9 @@ static int mlx5i_set_coalesce(struct net_device *netdev, } static int mlx5i_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 7359a8b768e9..c1a75b08ced7 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -1652,8 +1652,10 @@ myri10ge_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info) strlcpy(info->bus_info, pci_name(mgp->pdev), sizeof(info->bus_info)); } -static int -myri10ge_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *coal) +static int myri10ge_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct myri10ge_priv *mgp = netdev_priv(netdev); @@ -1661,8 +1663,10 @@ myri10ge_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *coal) return 0; } -static int -myri10ge_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *coal) +static int myri10ge_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct myri10ge_priv *mgp = netdev_priv(netdev); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 0bf2ff5717bc..0685ece1f155 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1078,7 +1078,9 @@ static void nfp_net_get_regs(struct net_device *netdev, } static int nfp_net_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct nfp_net *nn = netdev_priv(netdev); @@ -1330,7 +1332,9 @@ exit_close_nsp: } static int nfp_net_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct nfp_net *nn = netdev_priv(netdev); unsigned int factor; diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 2d097dcb7bda..36fe2c0f31ff 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -993,8 +993,11 @@ static void nixge_ethtools_get_drvinfo(struct net_device *ndev, strlcpy(ed->bus_info, "platform", sizeof(ed->bus_info)); } -static int nixge_ethtools_get_coalesce(struct net_device *ndev, - struct ethtool_coalesce *ecoalesce) +static int +nixge_ethtools_get_coalesce(struct net_device *ndev, + struct ethtool_coalesce *ecoalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct nixge_priv *priv = netdev_priv(ndev); u32 regval = 0; @@ -1008,8 +1011,11 @@ static int nixge_ethtools_get_coalesce(struct net_device *ndev, return 0; } -static int nixge_ethtools_set_coalesce(struct net_device *ndev, - struct ethtool_coalesce *ecoalesce) +static int +nixge_ethtools_set_coalesce(struct net_device *ndev, + struct ethtool_coalesce *ecoalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct nixge_priv *priv = netdev_priv(ndev); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index adc9fdb03e86..e91b4874a57f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -420,7 +420,9 @@ static int ionic_set_fecparam(struct net_device *netdev, } static int ionic_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ionic_lif *lif = netdev_priv(netdev); @@ -438,7 +440,9 @@ static int ionic_get_coalesce(struct net_device *netdev, } static int ionic_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ionic_lif *lif = netdev_priv(netdev); struct ionic_identity *ident; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c index dd22cb056d03..a075643f5826 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c @@ -731,7 +731,9 @@ netxen_nic_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) * firmware coalescing to default. */ static int netxen_set_intr_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ethcoal) + struct ethtool_coalesce *ethcoal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct netxen_adapter *adapter = netdev_priv(netdev); @@ -775,7 +777,9 @@ static int netxen_set_intr_coalesce(struct net_device *netdev, } static int netxen_get_intr_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ethcoal) + struct ethtool_coalesce *ethcoal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct netxen_adapter *adapter = netdev_priv(netdev); diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 66c69f0f9af1..f90dcfe9ee68 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -580,7 +580,9 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, struct flow_cls_offload *f); void qede_forced_speed_maps_init(void); -int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal); +int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack); int qede_set_per_coalesce(struct net_device *dev, u32 queue, struct ethtool_coalesce *coal); diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 9c6aa6859646..8284c4c1528f 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -760,7 +760,9 @@ static int qede_flash_device(struct net_device *dev, } static int qede_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { void *rx_handle = NULL, *tx_handle = NULL; struct qede_dev *edev = netdev_priv(dev); @@ -819,7 +821,9 @@ out: return rc; } -int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal) +int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct qede_dev *edev = netdev_priv(dev); struct qede_fastpath *fp; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index f6b6651decf3..fc364b4ab6eb 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -1527,7 +1527,9 @@ qlcnic_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) * firmware coalescing to default. */ static int qlcnic_set_intr_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ethcoal) + struct ethtool_coalesce *ethcoal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct qlcnic_adapter *adapter = netdev_priv(netdev); int err; @@ -1551,7 +1553,9 @@ static int qlcnic_set_intr_coalesce(struct net_device *netdev, } static int qlcnic_get_intr_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ethcoal) + struct ethtool_coalesce *ethcoal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct qlcnic_adapter *adapter = netdev_priv(netdev); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 9ea59efd0fd6..1225d27330f8 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1749,7 +1749,10 @@ rtl_coalesce_info(struct rtl8169_private *tp) return ERR_PTR(-ELNRNG); } -static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) +static int rtl_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct rtl8169_private *tp = netdev_priv(dev); const struct rtl_coalesce_info *ci; @@ -1807,7 +1810,10 @@ static int rtl_coalesce_choose_scale(struct rtl8169_private *tp, u32 usec, return -ERANGE; } -static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) +static int rtl_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct rtl8169_private *tp = netdev_priv(dev); u32 tx_fr = ec->tx_max_coalesced_frames; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c index 7f8b10c49660..98edb01024f0 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c @@ -274,7 +274,9 @@ static u32 sxgbe_usec2riwt(u32 usec, struct sxgbe_priv_data *priv) } static int sxgbe_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct sxgbe_priv_data *priv = netdev_priv(dev); @@ -285,7 +287,9 @@ static int sxgbe_get_coalesce(struct net_device *dev, } static int sxgbe_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct sxgbe_priv_data *priv = netdev_priv(dev); unsigned int rx_riwt; diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 058d9fe41d99..e002ce21788d 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -97,7 +97,9 @@ static void efx_ethtool_get_regs(struct net_device *net_dev, */ static int efx_ethtool_get_coalesce(struct net_device *net_dev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct efx_nic *efx = netdev_priv(net_dev); unsigned int tx_usecs, rx_usecs; @@ -115,7 +117,9 @@ static int efx_ethtool_get_coalesce(struct net_device *net_dev, } static int efx_ethtool_set_coalesce(struct net_device *net_dev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct efx_nic *efx = netdev_priv(net_dev); struct efx_channel *channel; diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c index a6bae6a234ba..137e8a7aeaa1 100644 --- a/drivers/net/ethernet/sfc/falcon/ethtool.c +++ b/drivers/net/ethernet/sfc/falcon/ethtool.c @@ -577,7 +577,9 @@ static int ef4_ethtool_nway_reset(struct net_device *net_dev) */ static int ef4_ethtool_get_coalesce(struct net_device *net_dev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ef4_nic *efx = netdev_priv(net_dev); unsigned int tx_usecs, rx_usecs; @@ -595,7 +597,9 @@ static int ef4_ethtool_get_coalesce(struct net_device *net_dev, } static int ef4_ethtool_set_coalesce(struct net_device *net_dev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ef4_nic *efx = netdev_priv(net_dev); struct ef4_channel *channel; diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index d15f7b3a3f10..1f46af136aa8 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -532,7 +532,9 @@ static void netsec_et_get_drvinfo(struct net_device *net_device, } static int netsec_et_get_coalesce(struct net_device *net_device, - struct ethtool_coalesce *et_coalesce) + struct ethtool_coalesce *et_coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct netsec_priv *priv = netdev_priv(net_device); @@ -542,7 +544,9 @@ static int netsec_et_get_coalesce(struct net_device *net_device, } static int netsec_et_set_coalesce(struct net_device *net_device, - struct ethtool_coalesce *et_coalesce) + struct ethtool_coalesce *et_coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct netsec_priv *priv = netdev_priv(net_device); @@ -1544,7 +1548,7 @@ static int netsec_start_gmac(struct netsec_priv *priv) netsec_write(priv, NETSEC_REG_NRM_RX_INTEN_CLR, ~0); netsec_write(priv, NETSEC_REG_NRM_TX_INTEN_CLR, ~0); - netsec_et_set_coalesce(priv->ndev, &priv->et_coalesce); + netsec_et_set_coalesce(priv->ndev, &priv->et_coalesce, NULL, NULL); if (netsec_mac_write(priv, GMAC_REG_OMR, value)) return -ETIMEDOUT; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 595c3ccdcbb7..d89455803bed 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -874,7 +874,9 @@ static int __stmmac_get_coalesce(struct net_device *dev, } static int stmmac_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { return __stmmac_get_coalesce(dev, ec, -1); } @@ -958,7 +960,9 @@ static int __stmmac_set_coalesce(struct net_device *dev, } static int stmmac_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { return __stmmac_set_coalesce(dev, ec, -1); } diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c index bc198eadfcab..49f8c6be9459 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-ethtool.c @@ -146,8 +146,11 @@ static void xlgmac_ethtool_get_channels(struct net_device *netdev, channel->tx_count = pdata->tx_q_count; } -static int xlgmac_ethtool_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) +static int +xlgmac_ethtool_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct xlgmac_pdata *pdata = netdev_priv(netdev); @@ -158,8 +161,11 @@ static int xlgmac_ethtool_get_coalesce(struct net_device *netdev, return 0; } -static int xlgmac_ethtool_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) +static int +xlgmac_ethtool_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct xlgmac_pdata *pdata = netdev_priv(netdev); struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops; diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 8f6abaec41d1..6b409f9c5863 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -2151,8 +2151,10 @@ bdx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) * @netdev * @ecoal */ -static int -bdx_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecoal) +static int bdx_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ecoal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { u32 rdintcm; u32 tdintcm; @@ -2180,8 +2182,10 @@ bdx_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecoal) * @netdev * @ecoal */ -static int -bdx_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecoal) +static int bdx_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ecoal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { u32 rdintcm; u32 tdintcm; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 9f70e40779f6..66f7ddd9b1f9 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -845,7 +845,7 @@ static int cpsw_ndo_open(struct net_device *ndev) struct ethtool_coalesce coal; coal.rx_coalesce_usecs = cpsw->coal_intvl; - cpsw_set_coalesce(ndev, &coal); + cpsw_set_coalesce(ndev, &coal, NULL, NULL); } cpdma_ctlr_start(cpsw->dma); diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c index 4619c3a950b0..158c8d3793f4 100644 --- a/drivers/net/ethernet/ti/cpsw_ethtool.c +++ b/drivers/net/ethernet/ti/cpsw_ethtool.c @@ -152,7 +152,9 @@ void cpsw_set_msglevel(struct net_device *ndev, u32 value) priv->msg_enable = value; } -int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal) +int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct cpsw_common *cpsw = ndev_to_cpsw(ndev); @@ -160,7 +162,9 @@ int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal) return 0; } -int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal) +int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct cpsw_priv *priv = netdev_priv(ndev); u32 int_ctrl; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 534d39f729e2..7968f24d99c8 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -894,7 +894,7 @@ static int cpsw_ndo_open(struct net_device *ndev) struct ethtool_coalesce coal; coal.rx_coalesce_usecs = cpsw->coal_intvl; - cpsw_set_coalesce(ndev, &coal); + cpsw_set_coalesce(ndev, &coal, NULL, NULL); } cpdma_ctlr_start(cpsw->dma); diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index 2951fb7b9dae..435668ee542d 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -464,8 +464,12 @@ void cpsw_mqprio_resume(struct cpsw_slave *slave, struct cpsw_priv *priv); /* ethtool */ u32 cpsw_get_msglevel(struct net_device *ndev); void cpsw_set_msglevel(struct net_device *ndev, u32 value); -int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal); -int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal); +int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack); +int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack); int cpsw_get_sset_count(struct net_device *ndev, int sset); void cpsw_get_strings(struct net_device *ndev, u32 stringset, u8 *data); void cpsw_get_ethtool_stats(struct net_device *ndev, diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index b1c5cbe7478b..e8291d848839 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -383,12 +383,16 @@ static void emac_get_drvinfo(struct net_device *ndev, * emac_get_coalesce - Get interrupt coalesce settings for this device * @ndev : The DaVinci EMAC network adapter * @coal : ethtool coalesce settings structure + * @kernel_coal: ethtool CQE mode setting structure + * @extack: extack for reporting error messages * * Fetch the current interrupt coalesce settings * */ static int emac_get_coalesce(struct net_device *ndev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct emac_priv *priv = netdev_priv(ndev); @@ -401,12 +405,16 @@ static int emac_get_coalesce(struct net_device *ndev, * emac_set_coalesce - Set interrupt coalesce settings for this device * @ndev : The DaVinci EMAC network adapter * @coal : ethtool coalesce settings structure + * @kernel_coal: ethtool CQE mode setting structure + * @extack: extack for reporting error messages * * Set interrupt coalesce parameters * */ static int emac_set_coalesce(struct net_device *ndev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct emac_priv *priv = netdev_priv(ndev); u32 int_ctrl, num_interrupts = 0; @@ -1462,7 +1470,7 @@ static int emac_dev_open(struct net_device *ndev) struct ethtool_coalesce coal; coal.rx_coalesce_usecs = (priv->coal_intvl << 4); - emac_set_coalesce(ndev, &coal); + emac_set_coalesce(ndev, &coal, NULL, NULL); } cpdma_ctlr_start(priv->dma); diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index 6a08ea658816..4b9c30f735b5 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -3518,7 +3518,9 @@ static void set_pending_timer_val(int *val, u32 us) static int velocity_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *ecmd) + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct velocity_info *vptr = netdev_priv(dev); @@ -3532,7 +3534,9 @@ static int velocity_get_coalesce(struct net_device *dev, } static int velocity_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *ecmd) + struct ethtool_coalesce *ecmd, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct velocity_info *vptr = netdev_priv(dev); int max_us = 0x3f * 64; diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index db1994fb51c5..463094ced104 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1310,8 +1310,11 @@ static int ll_temac_ethtools_set_ringparam(struct net_device *ndev, return 0; } -static int ll_temac_ethtools_get_coalesce(struct net_device *ndev, - struct ethtool_coalesce *ec) +static int +ll_temac_ethtools_get_coalesce(struct net_device *ndev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct temac_local *lp = netdev_priv(ndev); @@ -1322,8 +1325,11 @@ static int ll_temac_ethtools_get_coalesce(struct net_device *ndev, return 0; } -static int ll_temac_ethtools_set_coalesce(struct net_device *ndev, - struct ethtool_coalesce *ec) +static int +ll_temac_ethtools_set_coalesce(struct net_device *ndev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct temac_local *lp = netdev_priv(ndev); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 348c0ba5edcf..871b5ec3183d 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1400,6 +1400,8 @@ axienet_ethtools_set_pauseparam(struct net_device *ndev, * axienet_ethtools_get_coalesce - Get DMA interrupt coalescing count. * @ndev: Pointer to net_device structure * @ecoalesce: Pointer to ethtool_coalesce structure + * @kernel_coal: ethtool CQE mode setting structure + * @extack: extack for reporting error messages * * This implements ethtool command for getting the DMA interrupt coalescing * count on Tx and Rx paths. Issue "ethtool -c ethX" under linux prompt to @@ -1407,8 +1409,11 @@ axienet_ethtools_set_pauseparam(struct net_device *ndev, * * Return: 0 always */ -static int axienet_ethtools_get_coalesce(struct net_device *ndev, - struct ethtool_coalesce *ecoalesce) +static int +axienet_ethtools_get_coalesce(struct net_device *ndev, + struct ethtool_coalesce *ecoalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { u32 regval = 0; struct axienet_local *lp = netdev_priv(ndev); @@ -1425,6 +1430,8 @@ static int axienet_ethtools_get_coalesce(struct net_device *ndev, * axienet_ethtools_set_coalesce - Set DMA interrupt coalescing count. * @ndev: Pointer to net_device structure * @ecoalesce: Pointer to ethtool_coalesce structure + * @kernel_coal: ethtool CQE mode setting structure + * @extack: extack for reporting error messages * * This implements ethtool command for setting the DMA interrupt coalescing * count on Tx and Rx paths. Issue "ethtool -C ethX rx-frames 5" under linux @@ -1432,8 +1439,11 @@ static int axienet_ethtools_get_coalesce(struct net_device *ndev, * * Return: 0, on success, Non-zero error value on failure. */ -static int axienet_ethtools_set_coalesce(struct net_device *ndev, - struct ethtool_coalesce *ecoalesce) +static int +axienet_ethtools_set_coalesce(struct net_device *ndev, + struct ethtool_coalesce *ecoalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct axienet_local *lp = netdev_priv(ndev); diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index c9ae52595a8f..b03a0513eb7e 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -43,7 +43,9 @@ nsim_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) } static int nsim_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct netdevsim *ns = netdev_priv(dev); @@ -52,7 +54,9 @@ static int nsim_get_coalesce(struct net_device *dev, } static int nsim_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct netdevsim *ns = netdev_priv(dev); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2ced021f4faf..fecc9a1d293a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3510,7 +3510,9 @@ static void tun_set_msglevel(struct net_device *dev, u32 value) } static int tun_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); @@ -3520,7 +3522,9 @@ static int tun_get_coalesce(struct net_device *dev, } static int tun_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index aa66671c484d..60ba9b734055 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -8848,7 +8848,9 @@ out: } static int rtl8152_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct r8152 *tp = netdev_priv(netdev); @@ -8867,7 +8869,9 @@ static int rtl8152_get_coalesce(struct net_device *netdev, } static int rtl8152_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *coalesce) + struct ethtool_coalesce *coalesce, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct r8152 *tp = netdev_priv(netdev); int ret; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index c8c9ad7ca2b5..b4ae2ac8a249 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2320,7 +2320,9 @@ static int virtnet_get_link_ksettings(struct net_device *dev, } static int virtnet_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); int i, napi_weight; @@ -2341,7 +2343,9 @@ static int virtnet_set_coalesce(struct net_device *dev, } static int virtnet_get_coalesce(struct net_device *dev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct ethtool_coalesce ec_default = { .cmd = ETHTOOL_GCOALESCE, diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index a3e2f2ba68b5..5dd8360b21a0 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -1053,8 +1053,10 @@ vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key, } #endif -static int -vmxnet3_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec) +static int vmxnet3_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); @@ -1088,8 +1090,10 @@ vmxnet3_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec) return 0; } -static int -vmxnet3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec) +static int vmxnet3_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); struct Vmxnet3_DriverShared *shared = adapter->shared; diff --git a/drivers/net/wireless/ath/wil6210/ethtool.c b/drivers/net/wireless/ath/wil6210/ethtool.c index e481674485c2..29a9f17c2df0 100644 --- a/drivers/net/wireless/ath/wil6210/ethtool.c +++ b/drivers/net/wireless/ath/wil6210/ethtool.c @@ -11,8 +11,11 @@ #include "wil6210.h" -static int wil_ethtoolops_get_coalesce(struct net_device *ndev, - struct ethtool_coalesce *cp) +static int +wil_ethtoolops_get_coalesce(struct net_device *ndev, + struct ethtool_coalesce *cp, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct wil6210_priv *wil = ndev_to_wil(ndev); u32 tx_itr_en, tx_itr_val = 0; @@ -45,8 +48,11 @@ out: return ret; } -static int wil_ethtoolops_set_coalesce(struct net_device *ndev, - struct ethtool_coalesce *cp) +static int +wil_ethtoolops_set_coalesce(struct net_device *ndev, + struct ethtool_coalesce *cp, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct wil6210_priv *wil = ndev_to_wil(ndev); struct wireless_dev *wdev = ndev->ieee80211_ptr; diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c index 3937986f159a..46d0fe0d0e8a 100644 --- a/drivers/s390/net/qeth_ethtool.c +++ b/drivers/s390/net/qeth_ethtool.c @@ -123,7 +123,9 @@ static void __qeth_set_coalesce(struct net_device *dev, } static int qeth_set_coalesce(struct net_device *dev, - struct ethtool_coalesce *coal) + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct qeth_card *card = dev->ml_priv; struct qeth_qdio_out_q *queue; diff --git a/drivers/staging/qlge/qlge_ethtool.c b/drivers/staging/qlge/qlge_ethtool.c index 87d60115ac67..12efcd1057ba 100644 --- a/drivers/staging/qlge/qlge_ethtool.c +++ b/drivers/staging/qlge/qlge_ethtool.c @@ -621,7 +621,10 @@ static void qlge_get_regs(struct net_device *ndev, regs->len = sizeof(struct qlge_reg_dump); } -static int qlge_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *c) +static int qlge_get_coalesce(struct net_device *ndev, + struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct qlge_adapter *qdev = netdev_to_qdev(ndev); @@ -644,7 +647,10 @@ static int qlge_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *c return 0; } -static int qlge_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *c) +static int qlge_set_coalesce(struct net_device *ndev, + struct ethtool_coalesce *c, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct qlge_adapter *qdev = netdev_to_qdev(ndev); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a9d77a6a3e00..849524b55d89 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -15,6 +15,7 @@ #include #include +#include #include struct compat_ethtool_rx_flow_spec { @@ -611,8 +612,14 @@ struct ethtool_ops { struct ethtool_eeprom *, u8 *); int (*set_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); - int (*get_coalesce)(struct net_device *, struct ethtool_coalesce *); - int (*set_coalesce)(struct net_device *, struct ethtool_coalesce *); + int (*get_coalesce)(struct net_device *, + struct ethtool_coalesce *, + struct kernel_ethtool_coalesce *, + struct netlink_ext_ack *); + int (*set_coalesce)(struct net_device *, + struct ethtool_coalesce *, + struct kernel_ethtool_coalesce *, + struct netlink_ext_ack *); void (*get_ringparam)(struct net_device *, struct ethtool_ringparam *); int (*set_ringparam)(struct net_device *, diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index e6bc53634e68..46776ea42a92 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -62,6 +62,7 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, struct genl_info *info) { struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); + struct netlink_ext_ack *extack = info ? info->extack : NULL; struct net_device *dev = reply_base->dev; int ret; @@ -71,7 +72,8 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, ret = ethnl_ops_begin(dev); if (ret < 0) return ret; - ret = dev->ethtool_ops->get_coalesce(dev, &data->coalesce); + ret = dev->ethtool_ops->get_coalesce(dev, &data->coalesce, + &data->kernel_coalesce, extack); ethnl_ops_complete(dev); return ret; @@ -266,7 +268,8 @@ int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) ret = ethnl_ops_begin(dev); if (ret < 0) goto out_rtnl; - ret = ops->get_coalesce(dev, &coalesce); + ret = ops->get_coalesce(dev, &coalesce, &kernel_coalesce, + info->extack); if (ret < 0) goto out_ops; @@ -322,7 +325,8 @@ int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) if (!mod) goto out_ops; - ret = dev->ethtool_ops->set_coalesce(dev, &coalesce); + ret = dev->ethtool_ops->set_coalesce(dev, &coalesce, &kernel_coalesce, + info->extack); if (ret < 0) goto out_ops; ethtool_notify(dev, ETHTOOL_MSG_COALESCE_NTF, NULL); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 81fa36a4c9c4..f2abc3152888 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1619,12 +1619,14 @@ static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, void __user *useraddr) { struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; + struct kernel_ethtool_coalesce kernel_coalesce = {}; int ret; if (!dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; - ret = dev->ethtool_ops->get_coalesce(dev, &coalesce); + ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce, + NULL); if (ret) return ret; @@ -1691,19 +1693,26 @@ ethtool_set_coalesce_supported(struct net_device *dev, static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) { + struct kernel_ethtool_coalesce kernel_coalesce = {}; struct ethtool_coalesce coalesce; int ret; - if (!dev->ethtool_ops->set_coalesce) + if (!dev->ethtool_ops->set_coalesce && !dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; + ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce, + NULL); + if (ret) + return ret; + if (copy_from_user(&coalesce, useraddr, sizeof(coalesce))) return -EFAULT; if (!ethtool_set_coalesce_supported(dev, &coalesce)) return -EOPNOTSUPP; - ret = dev->ethtool_ops->set_coalesce(dev, &coalesce); + ret = dev->ethtool_ops->set_coalesce(dev, &coalesce, &kernel_coalesce, + NULL); if (!ret) ethtool_notify(dev, ETHTOOL_MSG_COALESCE_NTF, NULL); return ret; -- cgit v1.2.3 From 0bdfbca8a623e262e0f343b143151000a300cbaf Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Fri, 20 Aug 2021 03:45:33 +0300 Subject: block: Add alternative_gpt_sector() operation Add alternative_gpt_sector() block device operation which specifies alternative location of a GPT entry. This allows us to support Android devices that have GPT entry at a non-standard location and can't be repartitioned easily. Reviewed-by: Christoph Hellwig Suggested-by: Christoph Hellwig Signed-off-by: Dmitry Osipenko Reviewed-by: Ulf Hansson Link: https://lore.kernel.org/r/20210820004536.15791-2-digetx@gmail.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 22b5b8502d2a..c9cb12483e12 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1872,6 +1872,13 @@ struct block_device_operations { char *(*devnode)(struct gendisk *disk, umode_t *mode); struct module *owner; const struct pr_ops *pr_ops; + + /* + * Special callback for probing GPT entry at a given sector. + * Needed by Android devices, used by GPT scanner and MMC blk + * driver. + */ + int (*alternative_gpt_sector)(struct gendisk *disk, sector_t *sector); }; #ifdef CONFIG_COMPAT -- cgit v1.2.3 From dc913385dd74e625271482c30aefedd1e5af7b8c Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Fri, 20 Aug 2021 03:45:35 +0300 Subject: mmc: block: Support alternative_gpt_sector() operation Support generic alternative_gpt_sector() block device operation. It calculates location of GPT entry for eMMC of NVIDIA Tegra Android devices. Add new MMC_CAP2_ALT_GPT_TEGRA flag that enables scanning of alternative GPT sector and add raw_boot_mult field to mmc_ext_csd which allows to get size of the boot partitions that is needed for the calculation. Signed-off-by: Dmitry Osipenko Reviewed-by: Ulf Hansson Link: https://lore.kernel.org/r/20210820004536.15791-4-digetx@gmail.com Signed-off-by: Jens Axboe --- drivers/mmc/core/block.c | 21 +++++++++++++++++++++ drivers/mmc/core/core.c | 35 +++++++++++++++++++++++++++++++++++ drivers/mmc/core/core.h | 2 ++ drivers/mmc/core/mmc.c | 2 ++ include/linux/mmc/card.h | 1 + include/linux/mmc/host.h | 1 + 6 files changed, 62 insertions(+) (limited to 'include/linux') diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 4c11f171e56d..6a15fdf6e5f2 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -831,6 +831,26 @@ static int mmc_blk_compat_ioctl(struct block_device *bdev, fmode_t mode, } #endif +static int mmc_blk_alternative_gpt_sector(struct gendisk *disk, + sector_t *sector) +{ + struct mmc_blk_data *md; + int ret; + + md = mmc_blk_get(disk); + if (!md) + return -EINVAL; + + if (md->queue.card) + ret = mmc_card_alternative_gpt_sector(md->queue.card, sector); + else + ret = -ENODEV; + + mmc_blk_put(md); + + return ret; +} + static const struct block_device_operations mmc_bdops = { .open = mmc_blk_open, .release = mmc_blk_release, @@ -840,6 +860,7 @@ static const struct block_device_operations mmc_bdops = { #ifdef CONFIG_COMPAT .compat_ioctl = mmc_blk_compat_ioctl, #endif + .alternative_gpt_sector = mmc_blk_alternative_gpt_sector, }; static int mmc_blk_part_switch_pre(struct mmc_card *card, diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 95fedcf56e4a..605f5e8648c1 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -2149,6 +2149,41 @@ int mmc_detect_card_removed(struct mmc_host *host) } EXPORT_SYMBOL(mmc_detect_card_removed); +int mmc_card_alternative_gpt_sector(struct mmc_card *card, sector_t *gpt_sector) +{ + unsigned int boot_sectors_num; + + if ((!(card->host->caps2 & MMC_CAP2_ALT_GPT_TEGRA))) + return -EOPNOTSUPP; + + /* filter out unrelated cards */ + if (card->ext_csd.rev < 3 || + !mmc_card_mmc(card) || + !mmc_card_is_blockaddr(card) || + mmc_card_is_removable(card->host)) + return -ENOENT; + + /* + * eMMC storage has two special boot partitions in addition to the + * main one. NVIDIA's bootloader linearizes eMMC boot0->boot1->main + * accesses, this means that the partition table addresses are shifted + * by the size of boot partitions. In accordance with the eMMC + * specification, the boot partition size is calculated as follows: + * + * boot partition size = 128K byte x BOOT_SIZE_MULT + * + * Calculate number of sectors occupied by the both boot partitions. + */ + boot_sectors_num = card->ext_csd.raw_boot_mult * SZ_128K / + SZ_512 * MMC_NUM_BOOT_PARTITION; + + /* Defined by NVIDIA and used by Android devices. */ + *gpt_sector = card->ext_csd.sectors - boot_sectors_num - 1; + + return 0; +} +EXPORT_SYMBOL(mmc_card_alternative_gpt_sector); + void mmc_rescan(struct work_struct *work) { struct mmc_host *host = diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h index 0c4de2030b3f..7931a4f0137d 100644 --- a/drivers/mmc/core/core.h +++ b/drivers/mmc/core/core.h @@ -119,6 +119,8 @@ void mmc_release_host(struct mmc_host *host); void mmc_get_card(struct mmc_card *card, struct mmc_ctx *ctx); void mmc_put_card(struct mmc_card *card, struct mmc_ctx *ctx); +int mmc_card_alternative_gpt_sector(struct mmc_card *card, sector_t *sector); + /** * mmc_claim_host - exclusively claim a host * @host: mmc host to claim diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 838726b68ff3..29e58ffae379 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -418,6 +418,8 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) ext_csd[EXT_CSD_ERASE_TIMEOUT_MULT]; card->ext_csd.raw_hc_erase_grp_size = ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE]; + card->ext_csd.raw_boot_mult = + ext_csd[EXT_CSD_BOOT_MULT]; if (card->ext_csd.rev >= 3) { u8 sa_shift = ext_csd[EXT_CSD_S_A_TIMEOUT]; card->ext_csd.part_config = ext_csd[EXT_CSD_PART_CONFIG]; diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 74e6c0624d27..37f975875102 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -109,6 +109,7 @@ struct mmc_ext_csd { u8 raw_hc_erase_gap_size; /* 221 */ u8 raw_erase_timeout_mult; /* 223 */ u8 raw_hc_erase_grp_size; /* 224 */ + u8 raw_boot_mult; /* 226 */ u8 raw_sec_trim_mult; /* 229 */ u8 raw_sec_erase_mult; /* 230 */ u8 raw_sec_feature_support;/* 231 */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 0abd47e9ef9b..78dadf86b38f 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -398,6 +398,7 @@ struct mmc_host { #else #define MMC_CAP2_CRYPTO 0 #endif +#define MMC_CAP2_ALT_GPT_TEGRA (1 << 28) /* Host with eMMC that has GPT entry at a non-standard location */ int fixed_drv_type; /* fixed driver type for non-removable media */ -- cgit v1.2.3 From 158ee7b65653d9f841823c249014c2d0dfdeeb8f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Aug 2021 17:18:23 +0200 Subject: block: mark blkdev_fsync static MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit blkdev_fsync is only used inside of block_dev.c since the removal of the raw drіver. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210824151823.1575100-1-hch@lst.de Signed-off-by: Jens Axboe --- fs/block_dev.c | 4 ++-- include/linux/fs.h | 4 ---- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/block_dev.c b/fs/block_dev.c index d3a8062302a0..1f21ac984253 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -687,7 +687,8 @@ static loff_t block_llseek(struct file *file, loff_t offset, int whence) return retval; } -int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) +static int blkdev_fsync(struct file *filp, loff_t start, loff_t end, + int datasync) { struct inode *bd_inode = bdev_file_inode(filp); struct block_device *bdev = I_BDEV(bd_inode); @@ -708,7 +709,6 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) return error; } -EXPORT_SYMBOL(blkdev_fsync); /** * bdev_read_page() - Start reading a page from a block device diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..9220cdf648b0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3246,10 +3246,6 @@ ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); -/* fs/block_dev.c */ -extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end, - int datasync); - /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); -- cgit v1.2.3 From 62283c6c9d4c1018badcd0b9c5b6ca66d978fa0d Mon Sep 17 00:00:00 2001 From: Jing Yangyang Date: Mon, 23 Aug 2021 23:07:02 -0700 Subject: include:libata: fix boolreturn.cocci warnings ./include/linux/libata.h:1462:8-9:WARNING: return of 0/1 in function 'ata_is_host_link' with return type bool Return statements in functions returning bool should use true/false instead of 1/0. Generated by: scripts/coccinelle/misc/boolreturn.cocci Reported-by: Zeal Robot Signed-off-by: Jing Yangyang Link: https://lore.kernel.org/r/20210824060702.59006-1-deng.changcheng@zte.com.cn Signed-off-by: Jens Axboe --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index a2d1bae7900b..860e63f5667b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1459,7 +1459,7 @@ static inline bool sata_pmp_attached(struct ata_port *ap) static inline bool ata_is_host_link(const struct ata_link *link) { - return 1; + return true; } #endif /* CONFIG_SATA_PMP */ -- cgit v1.2.3 From 1d71eb53e45187f58089d32b51e27784c791d90e Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Mon, 26 Jul 2021 20:36:54 -0700 Subject: Revert "PCI: Make pci_enable_ptm() private" Make pci_enable_ptm() accessible from the drivers. Exposing this to the driver enables the driver to use the 'ptm_enabled' field of 'pci_dev' to check if PTM is enabled or not. This reverts commit ac6c26da29c1 ("PCI: Make pci_enable_ptm() private"). Signed-off-by: Vinicius Costa Gomes Acked-by: Bjorn Helgaas Signed-off-by: Tony Nguyen --- drivers/pci/pci.h | 3 --- include/linux/pci.h | 7 +++++++ 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 93dcdd431072..2f52110cac97 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -597,11 +597,8 @@ static inline void pcie_ecrc_get_policy(char *str) { } #ifdef CONFIG_PCIE_PTM void pci_ptm_init(struct pci_dev *dev); -int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); #else static inline void pci_ptm_init(struct pci_dev *dev) { } -static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) -{ return -EINVAL; } #endif struct pci_dev_reset_methods { diff --git a/include/linux/pci.h b/include/linux/pci.h index 540b377ca8f6..21a9d244e4e4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1620,6 +1620,13 @@ static inline bool pci_aer_available(void) { return false; } bool pci_ats_disabled(void); +#ifdef CONFIG_PCIE_PTM +int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); +#else +static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) +{ return -EINVAL; } +#endif + void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); -- cgit v1.2.3 From 90e7a6de62781c27d6a111fccfb19b807f9b6887 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 24 Aug 2021 17:25:29 +0300 Subject: lib/scatterlist: Provide a dedicated function to support table append RDMA is the only in-kernel user that uses __sg_alloc_table_from_pages to append pages dynamically. In the next patch. That mode will be extended and that function will get more parameters. So separate it into a unique function to make such change more clear. Link: https://lore.kernel.org/r/20210824142531.3877007-2-maorg@nvidia.com Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/drm_prime.c | 13 +++++----- drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 11 +++----- drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 14 ++++------- drivers/infiniband/core/umem.c | 4 +-- include/linux/scatterlist.h | 39 ++++++++++++++++++++++++++--- lib/scatterlist.c | 36 ++++++++++++++------------ tools/testing/scatterlist/main.c | 25 ++++++++++++------ 7 files changed, 90 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 2a54f86856af..cf3278041f9c 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -807,8 +807,8 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, struct page **pages, unsigned int nr_pages) { struct sg_table *sg; - struct scatterlist *sge; size_t max_segment = 0; + int err; sg = kmalloc(sizeof(struct sg_table), GFP_KERNEL); if (!sg) @@ -818,13 +818,12 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, max_segment = dma_max_mapping_size(dev->dev); if (max_segment == 0) max_segment = UINT_MAX; - sge = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0, - nr_pages << PAGE_SHIFT, - max_segment, - NULL, 0, GFP_KERNEL); - if (IS_ERR(sge)) { + err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0, + nr_pages << PAGE_SHIFT, + max_segment, GFP_KERNEL); + if (err) { kfree(sg); - sg = ERR_CAST(sge); + sg = ERR_PTR(err); } return sg; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 7487bab11f0b..458f797a9e1e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -133,7 +133,6 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) unsigned int max_segment = i915_sg_segment_size(); struct sg_table *st; unsigned int sg_page_sizes; - struct scatterlist *sg; struct page **pvec; int ret; @@ -153,13 +152,11 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) spin_unlock(&i915->mm.notifier_lock); alloc_table: - sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0, - num_pages << PAGE_SHIFT, max_segment, - NULL, 0, GFP_KERNEL); - if (IS_ERR(sg)) { - ret = PTR_ERR(sg); + ret = sg_alloc_table_from_pages_segment(st, pvec, num_pages, 0, + num_pages << PAGE_SHIFT, + max_segment, GFP_KERNEL); + if (ret) goto err; - } ret = i915_gem_gtt_prepare_pages(obj, st); if (ret) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 0488042fb287..fc372d2e52a1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -363,7 +363,6 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) int ret = 0; static size_t sgl_size; static size_t sgt_size; - struct scatterlist *sg; if (vmw_tt->mapped) return 0; @@ -386,15 +385,12 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) if (unlikely(ret != 0)) return ret; - sg = __sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages, - vsgt->num_pages, 0, - (unsigned long) vsgt->num_pages << PAGE_SHIFT, - dma_get_max_seg_size(dev_priv->drm.dev), - NULL, 0, GFP_KERNEL); - if (IS_ERR(sg)) { - ret = PTR_ERR(sg); + ret = sg_alloc_table_from_pages_segment( + &vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0, + (unsigned long)vsgt->num_pages << PAGE_SHIFT, + dma_get_max_seg_size(dev_priv->drm.dev), GFP_KERNEL); + if (ret) goto out_sg_alloc_fail; - } if (vsgt->num_pages > vmw_tt->sgt.orig_nents) { uint64_t over_alloc = diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 0eb40025075f..b741758e528f 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -226,8 +226,8 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, cur_base += ret * PAGE_SIZE; npages -= ret; - sg = __sg_alloc_table_from_pages(&umem->sg_head, page_list, ret, - 0, ret << PAGE_SHIFT, + sg = sg_alloc_append_table_from_pages(&umem->sg_head, page_list, + ret, 0, ret << PAGE_SHIFT, ib_dma_max_seg_size(device), sg, npages, GFP_KERNEL); umem->sg_nents = umem->sg_head.nents; diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index ecf87484814f..5c700f2a0d18 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -285,14 +285,45 @@ void sg_free_table(struct sg_table *); int __sg_alloc_table(struct sg_table *, unsigned int, unsigned int, struct scatterlist *, unsigned int, gfp_t, sg_alloc_fn *); int sg_alloc_table(struct sg_table *, unsigned int, gfp_t); -struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt, +struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, struct scatterlist *prv, unsigned int left_pages, gfp_t gfp_mask); -int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, - unsigned int n_pages, unsigned int offset, - unsigned long size, gfp_t gfp_mask); +int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, + unsigned int n_pages, unsigned int offset, + unsigned long size, + unsigned int max_segment, gfp_t gfp_mask); + +/** + * sg_alloc_table_from_pages - Allocate and initialize an sg table from + * an array of pages + * @sgt: The sg table header to use + * @pages: Pointer to an array of page pointers + * @n_pages: Number of pages in the pages array + * @offset: Offset from start of the first page to the start of a buffer + * @size: Number of valid bytes in the buffer (after offset) + * @gfp_mask: GFP allocation mask + * + * Description: + * Allocate and initialize an sg table from a list of pages. Contiguous + * ranges of the pages are squashed into a single scatterlist node. A user + * may provide an offset at a start and a size of valid data in a buffer + * specified by the page array. The returned sg table is released by + * sg_free_table. + * + * Returns: + * 0 on success, negative error on failure + */ +static inline int sg_alloc_table_from_pages(struct sg_table *sgt, + struct page **pages, + unsigned int n_pages, + unsigned int offset, + unsigned long size, gfp_t gfp_mask) +{ + return sg_alloc_table_from_pages_segment(sgt, pages, n_pages, offset, + size, UINT_MAX, gfp_mask); +} #ifdef CONFIG_SGL_ALLOC struct scatterlist *sgl_alloc_order(unsigned long long length, diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 27efa6178153..611c63d4a958 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -397,7 +397,7 @@ static struct scatterlist *get_next_sg(struct sg_table *table, } /** - * __sg_alloc_table_from_pages - Allocate and initialize an sg table from + * sg_alloc_append_table_from_pages - Allocate and initialize an sg table from * an array of pages * @sgt: The sg table header to use * @pages: Pointer to an array of page pointers @@ -425,7 +425,7 @@ static struct scatterlist *get_next_sg(struct sg_table *table, * If this function returns non-0 (eg failure), the caller must call * sg_free_table() to cleanup any leftover allocations. */ -struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt, +struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, struct scatterlist *prv, unsigned int left_pages, @@ -520,36 +520,40 @@ out: sg_mark_end(s); return s; } -EXPORT_SYMBOL(__sg_alloc_table_from_pages); +EXPORT_SYMBOL(sg_alloc_append_table_from_pages); /** - * sg_alloc_table_from_pages - Allocate and initialize an sg table from - * an array of pages + * sg_alloc_table_from_pages_segment - Allocate and initialize an sg table from + * an array of pages and given maximum + * segment. * @sgt: The sg table header to use * @pages: Pointer to an array of page pointers * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) + * @max_segment: Maximum size of a scatterlist element in bytes * @gfp_mask: GFP allocation mask * * Description: * Allocate and initialize an sg table from a list of pages. Contiguous - * ranges of the pages are squashed into a single scatterlist node. A user - * may provide an offset at a start and a size of valid data in a buffer - * specified by the page array. The returned sg table is released by - * sg_free_table. + * ranges of the pages are squashed into a single scatterlist node up to the + * maximum size specified in @max_segment. A user may provide an offset at a + * start and a size of valid data in a buffer specified by the page array. * - * Returns: + * The returned sg table is released by sg_free_table. + * + * Returns: * 0 on success, negative error on failure */ -int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, - unsigned int n_pages, unsigned int offset, - unsigned long size, gfp_t gfp_mask) +int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, + unsigned int n_pages, unsigned int offset, + unsigned long size, unsigned int max_segment, + gfp_t gfp_mask) { - return PTR_ERR_OR_ZERO(__sg_alloc_table_from_pages(sgt, pages, n_pages, - offset, size, UINT_MAX, NULL, 0, gfp_mask)); + return PTR_ERR_OR_ZERO(sg_alloc_append_table_from_pages(sgt, pages, + n_pages, offset, size, max_segment, NULL, 0, gfp_mask)); } -EXPORT_SYMBOL(sg_alloc_table_from_pages); +EXPORT_SYMBOL(sg_alloc_table_from_pages_segment); #ifdef CONFIG_SGL_ALLOC diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c index 652254754b4c..c2ff9179c2cc 100644 --- a/tools/testing/scatterlist/main.c +++ b/tools/testing/scatterlist/main.c @@ -87,28 +87,39 @@ int main(void) int left_pages = test->pfn_app ? test->num_pages : 0; struct page *pages[MAX_PAGES]; struct sg_table st; - struct scatterlist *sg; + struct scatterlist *sg = NULL; + int ret; set_pages(pages, test->pfn, test->num_pages); - sg = __sg_alloc_table_from_pages(&st, pages, test->num_pages, 0, - test->size, test->max_seg, NULL, left_pages, GFP_KERNEL); - assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret); + if (test->pfn_app) { + sg = sg_alloc_append_table_from_pages( + &st, pages, test->num_pages, 0, test->size, + test->max_seg, NULL, left_pages, GFP_KERNEL); + assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret); + } else { + ret = sg_alloc_table_from_pages_segment( + &st, pages, test->num_pages, 0, test->size, + test->max_seg, GFP_KERNEL); + assert(ret == test->alloc_ret); + } if (test->alloc_ret) continue; if (test->pfn_app) { set_pages(pages, test->pfn_app, test->num_pages); - sg = __sg_alloc_table_from_pages(&st, pages, test->num_pages, 0, - test->size, test->max_seg, sg, 0, GFP_KERNEL); + sg = sg_alloc_append_table_from_pages( + &st, pages, test->num_pages, 0, test->size, + test->max_seg, sg, 0, GFP_KERNEL); assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret); } VALIDATE(st.nents == test->expected_segments, &st, test); if (!test->pfn_app) - VALIDATE(st.orig_nents == test->expected_segments, &st, test); + VALIDATE(st.orig_nents == test->expected_segments, &st, + test); sg_free_table(&st); } -- cgit v1.2.3 From 014408cd624e9fd2820f4a593b710325ee05fec9 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Mon, 26 Jul 2021 20:36:55 -0700 Subject: PCI: Add pcie_ptm_enabled() Add a predicate that returns if PCIe PTM (Precision Time Measurement) is enabled. It will only return true if it's enabled in all the ports in the path from the device to the root. Signed-off-by: Vinicius Costa Gomes Acked-by: Bjorn Helgaas Signed-off-by: Tony Nguyen --- drivers/pci/pcie/ptm.c | 9 +++++++++ include/linux/pci.h | 3 +++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index 95d4eef2c9e8..8a4ad974c5ac 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -204,3 +204,12 @@ int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) return 0; } EXPORT_SYMBOL(pci_enable_ptm); + +bool pcie_ptm_enabled(struct pci_dev *dev) +{ + if (!dev) + return false; + + return dev->ptm_enabled; +} +EXPORT_SYMBOL(pcie_ptm_enabled); diff --git a/include/linux/pci.h b/include/linux/pci.h index 21a9d244e4e4..947430637cac 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1622,9 +1622,12 @@ bool pci_ats_disabled(void); #ifdef CONFIG_PCIE_PTM int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); +bool pcie_ptm_enabled(struct pci_dev *dev); #else static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) { return -EINVAL; } +static inline bool pcie_ptm_enabled(struct pci_dev *dev) +{ return false; } #endif void pci_cfg_access_lock(struct pci_dev *dev); -- cgit v1.2.3 From 33709413014cd5b8e54d4d9efa07a30ba028e1db Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 11 Aug 2021 10:51:00 +0200 Subject: crash_dump: Make elfcorehdr address/size symbols always visible Make the forward declarations of elfcorehdr_addr and elfcorehdr_size, and the definitions of ELFCORE_ADDR_MAX and ELFCORE_ADDR_ERR always available, like is done for phys_initrd_start and phys_initrd_size. Code referring to these symbols can then just check for IS_ENABLED(CONFIG_CRASH_DUMP), instead of requiring conditional compilation using an #ifdef, thus preparing to increase compile coverage. Suggested-by: Rob Herring Signed-off-by: Geert Uytterhoeven Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/ba965ca613c0cc82c1ec2fe353ee34fb13b36474.1628670468.git.geert+renesas@glider.be --- include/linux/crash_dump.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index a5192b718dbe..2618577a4d6d 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -10,13 +10,14 @@ #include /* for pgprot_t */ -#ifdef CONFIG_CRASH_DUMP +/* For IS_ENABLED(CONFIG_CRASH_DUMP) */ #define ELFCORE_ADDR_MAX (-1ULL) #define ELFCORE_ADDR_ERR (-2ULL) extern unsigned long long elfcorehdr_addr; extern unsigned long long elfcorehdr_size; +#ifdef CONFIG_CRASH_DUMP extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size); extern void elfcorehdr_free(unsigned long long addr); extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos); -- cgit v1.2.3 From 3e302dbc6774a27edaea39a1d5107f0c12e35cf2 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 24 Aug 2021 17:25:30 +0300 Subject: lib/scatterlist: Fix wrong update of orig_nents orig_nents should represent the number of entries with pages, but __sg_alloc_table_from_pages sets orig_nents as the number of total entries in the table. This is wrong when the API is used for dynamic allocation where not all the table entries are mapped with pages. It wasn't observed until now, since RDMA umem who uses this API in the dynamic form doesn't use orig_nents implicit or explicit by the scatterlist APIs. Fix it by changing the append API to track the SG append table state and have an API to free the append table according to the total number of entries in the table. Now all APIs set orig_nents as number of enries with pages. Fixes: 07da1223ec93 ("lib/scatterlist: Add support in dynamic allocation of SG table from pages") Link: https://lore.kernel.org/r/20210824142531.3877007-3-maorg@nvidia.com Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/umem.c | 34 ++++++----- include/linux/scatterlist.h | 19 ++++-- include/rdma/ib_umem.h | 1 + lib/scatterlist.c | 127 ++++++++++++++++++++++++--------------- lib/sg_pool.c | 3 +- tools/testing/scatterlist/main.c | 45 +++++++------- 6 files changed, 136 insertions(+), 93 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index b741758e528f..42481e7a72e8 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -59,7 +59,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d unpin_user_page_range_dirty_lock(sg_page(sg), DIV_ROUND_UP(sg->length, PAGE_SIZE), make_dirty); - sg_free_table(&umem->sg_head); + sg_free_append_table(&umem->sgt_append); } /** @@ -155,8 +155,7 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, unsigned long dma_attr = 0; struct mm_struct *mm; unsigned long npages; - int ret; - struct scatterlist *sg = NULL; + int pinned, ret; unsigned int gup_flags = FOLL_WRITE; /* @@ -216,28 +215,33 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, while (npages) { cond_resched(); - ret = pin_user_pages_fast(cur_base, + pinned = pin_user_pages_fast(cur_base, min_t(unsigned long, npages, PAGE_SIZE / sizeof(struct page *)), gup_flags | FOLL_LONGTERM, page_list); - if (ret < 0) + if (pinned < 0) { + ret = pinned; goto umem_release; + } - cur_base += ret * PAGE_SIZE; - npages -= ret; - sg = sg_alloc_append_table_from_pages(&umem->sg_head, page_list, - ret, 0, ret << PAGE_SHIFT, - ib_dma_max_seg_size(device), sg, npages, - GFP_KERNEL); - umem->sg_nents = umem->sg_head.nents; - if (IS_ERR(sg)) { - unpin_user_pages_dirty_lock(page_list, ret, 0); - ret = PTR_ERR(sg); + cur_base += pinned * PAGE_SIZE; + npages -= pinned; + ret = sg_alloc_append_table_from_pages( + &umem->sgt_append, page_list, pinned, 0, + pinned << PAGE_SHIFT, ib_dma_max_seg_size(device), + npages, GFP_KERNEL); + umem->sg_nents = umem->sgt_append.sgt.nents; + if (ret) { + memcpy(&umem->sg_head.sgl, &umem->sgt_append.sgt, + sizeof(umem->sgt_append.sgt)); + unpin_user_pages_dirty_lock(page_list, pinned, 0); goto umem_release; } } + memcpy(&umem->sg_head.sgl, &umem->sgt_append.sgt, + sizeof(umem->sgt_append.sgt)); if (access & IB_ACCESS_RELAXED_ORDERING) dma_attr |= DMA_ATTR_WEAK_ORDERING; diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 5c700f2a0d18..266754a55327 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -39,6 +39,12 @@ struct sg_table { unsigned int orig_nents; /* original size of list */ }; +struct sg_append_table { + struct sg_table sgt; /* The scatter list table */ + struct scatterlist *prv; /* last populated sge in the table */ + unsigned int total_nents; /* Total entries in the table */ +}; + /* * Notes on SG table design. * @@ -280,16 +286,17 @@ typedef struct scatterlist *(sg_alloc_fn)(unsigned int, gfp_t); typedef void (sg_free_fn)(struct scatterlist *, unsigned int); void __sg_free_table(struct sg_table *, unsigned int, unsigned int, - sg_free_fn *); + sg_free_fn *, unsigned int); void sg_free_table(struct sg_table *); +void sg_free_append_table(struct sg_append_table *sgt); int __sg_alloc_table(struct sg_table *, unsigned int, unsigned int, struct scatterlist *, unsigned int, gfp_t, sg_alloc_fn *); int sg_alloc_table(struct sg_table *, unsigned int, gfp_t); -struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, - struct page **pages, unsigned int n_pages, unsigned int offset, - unsigned long size, unsigned int max_segment, - struct scatterlist *prv, unsigned int left_pages, - gfp_t gfp_mask); +int sg_alloc_append_table_from_pages(struct sg_append_table *sgt, + struct page **pages, unsigned int n_pages, + unsigned int offset, unsigned long size, + unsigned int max_segment, + unsigned int left_pages, gfp_t gfp_mask); int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index 676c57f5ca80..33cb23b2ee3c 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -26,6 +26,7 @@ struct ib_umem { u32 is_odp : 1; u32 is_dmabuf : 1; struct work_struct work; + struct sg_append_table sgt_append; struct sg_table sg_head; int nmap; unsigned int sg_nents; diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 611c63d4a958..f4b1ff78ab2d 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -182,6 +182,7 @@ static void sg_kfree(struct scatterlist *sg, unsigned int nents) * @nents_first_chunk: Number of entries int the (preallocated) first * scatterlist chunk, 0 means no such preallocated first chunk * @free_fn: Free function + * @num_ents: Number of entries in the table * * Description: * Free an sg table previously allocated and setup with @@ -190,7 +191,8 @@ static void sg_kfree(struct scatterlist *sg, unsigned int nents) * **/ void __sg_free_table(struct sg_table *table, unsigned int max_ents, - unsigned int nents_first_chunk, sg_free_fn *free_fn) + unsigned int nents_first_chunk, sg_free_fn *free_fn, + unsigned int num_ents) { struct scatterlist *sgl, *next; unsigned curr_max_ents = nents_first_chunk ?: max_ents; @@ -199,8 +201,8 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, return; sgl = table->sgl; - while (table->orig_nents) { - unsigned int alloc_size = table->orig_nents; + while (num_ents) { + unsigned int alloc_size = num_ents; unsigned int sg_size; /* @@ -218,7 +220,7 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, next = NULL; } - table->orig_nents -= sg_size; + num_ents -= sg_size; if (nents_first_chunk) nents_first_chunk = 0; else @@ -231,6 +233,19 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, } EXPORT_SYMBOL(__sg_free_table); +/** + * sg_free_append_table - Free a previously allocated append sg table. + * @table: The mapped sg append table header + * + **/ +void sg_free_append_table(struct sg_append_table *table) +{ + __sg_free_table(&table->sgt, SG_MAX_SINGLE_ALLOC, false, sg_kfree, + table->total_nents); +} +EXPORT_SYMBOL(sg_free_append_table); + + /** * sg_free_table - Free a previously allocated sg table * @table: The mapped sg table header @@ -238,7 +253,8 @@ EXPORT_SYMBOL(__sg_free_table); **/ void sg_free_table(struct sg_table *table) { - __sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree); + __sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree, + table->orig_nents); } EXPORT_SYMBOL(sg_free_table); @@ -359,13 +375,12 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask) ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC, NULL, 0, gfp_mask, sg_kmalloc); if (unlikely(ret)) - __sg_free_table(table, SG_MAX_SINGLE_ALLOC, 0, sg_kfree); - + sg_free_table(table); return ret; } EXPORT_SYMBOL(sg_alloc_table); -static struct scatterlist *get_next_sg(struct sg_table *table, +static struct scatterlist *get_next_sg(struct sg_append_table *table, struct scatterlist *cur, unsigned long needed_sges, gfp_t gfp_mask) @@ -386,54 +401,52 @@ static struct scatterlist *get_next_sg(struct sg_table *table, return ERR_PTR(-ENOMEM); sg_init_table(new_sg, alloc_size); if (cur) { + table->total_nents += alloc_size - 1; __sg_chain(next_sg, new_sg); - table->orig_nents += alloc_size - 1; } else { - table->sgl = new_sg; - table->orig_nents = alloc_size; - table->nents = 0; + table->sgt.sgl = new_sg; + table->total_nents = alloc_size; } return new_sg; } /** - * sg_alloc_append_table_from_pages - Allocate and initialize an sg table from - * an array of pages - * @sgt: The sg table header to use - * @pages: Pointer to an array of page pointers - * @n_pages: Number of pages in the pages array + * sg_alloc_append_table_from_pages - Allocate and initialize an append sg + * table from an array of pages + * @sgt_append: The sg append table to use + * @pages: Pointer to an array of page pointers + * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) * @max_segment: Maximum size of a scatterlist element in bytes - * @prv: Last populated sge in sgt * @left_pages: Left pages caller have to set after this call * @gfp_mask: GFP allocation mask * * Description: - * If @prv is NULL, allocate and initialize an sg table from a list of pages, - * else reuse the scatterlist passed in at @prv. - * Contiguous ranges of the pages are squashed into a single scatterlist - * entry up to the maximum size specified in @max_segment. A user may - * provide an offset at a start and a size of valid data in a buffer - * specified by the page array. + * In the first call it allocate and initialize an sg table from a list of + * pages, else reuse the scatterlist from sgt_append. Contiguous ranges of + * the pages are squashed into a single scatterlist entry up to the maximum + * size specified in @max_segment. A user may provide an offset at a start + * and a size of valid data in a buffer specified by the page array. The + * returned sg table is released by sg_free_append_table * * Returns: - * Last SGE in sgt on success, PTR_ERR on otherwise. - * The allocation in @sgt must be released by sg_free_table. + * 0 on success, negative error on failure * * Notes: * If this function returns non-0 (eg failure), the caller must call - * sg_free_table() to cleanup any leftover allocations. + * sg_free_append_table() to cleanup any leftover allocations. + * + * In the fist call, sgt_append must by initialized. */ -struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, +int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, - struct scatterlist *prv, unsigned int left_pages, - gfp_t gfp_mask) + unsigned int left_pages, gfp_t gfp_mask) { unsigned int chunks, cur_page, seg_len, i, prv_len = 0; unsigned int added_nents = 0; - struct scatterlist *s = prv; + struct scatterlist *s = sgt_append->prv; /* * The algorithm below requires max_segment to be aligned to PAGE_SIZE @@ -441,25 +454,26 @@ struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, */ max_segment = ALIGN_DOWN(max_segment, PAGE_SIZE); if (WARN_ON(max_segment < PAGE_SIZE)) - return ERR_PTR(-EINVAL); + return -EINVAL; - if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && prv) - return ERR_PTR(-EOPNOTSUPP); + if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && sgt_append->prv) + return -EOPNOTSUPP; - if (prv) { - unsigned long paddr = (page_to_pfn(sg_page(prv)) * PAGE_SIZE + - prv->offset + prv->length) / - PAGE_SIZE; + if (sgt_append->prv) { + unsigned long paddr = + (page_to_pfn(sg_page(sgt_append->prv)) * PAGE_SIZE + + sgt_append->prv->offset + sgt_append->prv->length) / + PAGE_SIZE; if (WARN_ON(offset)) - return ERR_PTR(-EINVAL); + return -EINVAL; /* Merge contiguous pages into the last SG */ - prv_len = prv->length; + prv_len = sgt_append->prv->length; while (n_pages && page_to_pfn(pages[0]) == paddr) { - if (prv->length + PAGE_SIZE > max_segment) + if (sgt_append->prv->length + PAGE_SIZE > max_segment) break; - prv->length += PAGE_SIZE; + sgt_append->prv->length += PAGE_SIZE; paddr++; pages++; n_pages--; @@ -496,15 +510,16 @@ struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, } /* Pass how many chunks might be left */ - s = get_next_sg(sgt, s, chunks - i + left_pages, gfp_mask); + s = get_next_sg(sgt_append, s, chunks - i + left_pages, + gfp_mask); if (IS_ERR(s)) { /* * Adjust entry length to be as before function was * called. */ - if (prv) - prv->length = prv_len; - return s; + if (sgt_append->prv) + sgt_append->prv->length = prv_len; + return PTR_ERR(s); } chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset; sg_set_page(s, pages[cur_page], @@ -514,11 +529,13 @@ struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, offset = 0; cur_page = j; } - sgt->nents += added_nents; + sgt_append->sgt.nents += added_nents; + sgt_append->sgt.orig_nents = sgt_append->sgt.nents; + sgt_append->prv = s; out: if (!left_pages) sg_mark_end(s); - return s; + return 0; } EXPORT_SYMBOL(sg_alloc_append_table_from_pages); @@ -550,8 +567,18 @@ int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, unsigned long size, unsigned int max_segment, gfp_t gfp_mask) { - return PTR_ERR_OR_ZERO(sg_alloc_append_table_from_pages(sgt, pages, - n_pages, offset, size, max_segment, NULL, 0, gfp_mask)); + struct sg_append_table append = {}; + int err; + + err = sg_alloc_append_table_from_pages(&append, pages, n_pages, offset, + size, max_segment, 0, gfp_mask); + if (err) { + sg_free_append_table(&append); + return err; + } + memcpy(sgt, &append.sgt, sizeof(*sgt)); + WARN_ON(append.total_nents != sgt->orig_nents); + return 0; } EXPORT_SYMBOL(sg_alloc_table_from_pages_segment); diff --git a/lib/sg_pool.c b/lib/sg_pool.c index db29e5c1f790..a0b1a52cd6f7 100644 --- a/lib/sg_pool.c +++ b/lib/sg_pool.c @@ -90,7 +90,8 @@ void sg_free_table_chained(struct sg_table *table, if (nents_first_chunk == 1) nents_first_chunk = 0; - __sg_free_table(table, SG_CHUNK_SIZE, nents_first_chunk, sg_pool_free); + __sg_free_table(table, SG_CHUNK_SIZE, nents_first_chunk, sg_pool_free, + table->orig_nents); } EXPORT_SYMBOL_GPL(sg_free_table_chained); diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c index c2ff9179c2cc..08465a701cd5 100644 --- a/tools/testing/scatterlist/main.c +++ b/tools/testing/scatterlist/main.c @@ -85,43 +85,46 @@ int main(void) for (i = 0, test = tests; test->expected_segments; test++, i++) { int left_pages = test->pfn_app ? test->num_pages : 0; + struct sg_append_table append = {}; struct page *pages[MAX_PAGES]; - struct sg_table st; - struct scatterlist *sg = NULL; int ret; set_pages(pages, test->pfn, test->num_pages); - if (test->pfn_app) { - sg = sg_alloc_append_table_from_pages( - &st, pages, test->num_pages, 0, test->size, - test->max_seg, NULL, left_pages, GFP_KERNEL); - assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret); - } else { + if (test->pfn_app) + ret = sg_alloc_append_table_from_pages( + &append, pages, test->num_pages, 0, test->size, + test->max_seg, left_pages, GFP_KERNEL); + else ret = sg_alloc_table_from_pages_segment( - &st, pages, test->num_pages, 0, test->size, - test->max_seg, GFP_KERNEL); - assert(ret == test->alloc_ret); - } + &append.sgt, pages, test->num_pages, 0, + test->size, test->max_seg, GFP_KERNEL); + + assert(ret == test->alloc_ret); if (test->alloc_ret) continue; if (test->pfn_app) { set_pages(pages, test->pfn_app, test->num_pages); - sg = sg_alloc_append_table_from_pages( - &st, pages, test->num_pages, 0, test->size, - test->max_seg, sg, 0, GFP_KERNEL); + ret = sg_alloc_append_table_from_pages( + &append, pages, test->num_pages, 0, test->size, + test->max_seg, 0, GFP_KERNEL); - assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret); + assert(ret == test->alloc_ret); } - VALIDATE(st.nents == test->expected_segments, &st, test); + VALIDATE(append.sgt.nents == test->expected_segments, + &append.sgt, test); if (!test->pfn_app) - VALIDATE(st.orig_nents == test->expected_segments, &st, - test); - - sg_free_table(&st); + VALIDATE(append.sgt.orig_nents == + test->expected_segments, + &append.sgt, test); + + if (test->pfn_app) + sg_free_append_table(&append); + else + sg_free_table(&append.sgt); } assert(i == (sizeof(tests) / sizeof(tests[0])) - 1); -- cgit v1.2.3 From 406f42fa0d3cbcea3766c3111d79ac5afe711c5b Mon Sep 17 00:00:00 2001 From: Gilad Naaman Date: Thu, 19 Aug 2021 10:17:27 +0300 Subject: net-next: When a bond have a massive amount of VLANs with IPv6 addresses, performance of changing link state, attaching a VRF, changing an IPv6 address, etc. go down dramtically. The source of most of the slow down is the `dev_addr_lists.c` module, which mainatins a linked list of HW addresses. When using IPv6, this list grows for each IPv6 address added on a VLAN, since each IPv6 address has a multicast HW address associated with it. When performing any modification to the involved links, this list is traversed many times, often for nothing, all while holding the RTNL lock. Instead, this patch adds an auxilliary rbtree which cuts down traversal time significantly. Performance can be seen with the following script: #!/bin/bash ip netns del test || true 2>/dev/null ip netns add test echo 1 | ip netns exec test tee /proc/sys/net/ipv6/conf/all/keep_addr_on_down > /dev/null set -e ip -n test link add foo type veth peer name bar ip -n test link add b1 type bond ip -n test link add florp type vrf table 10 ip -n test link set bar master b1 ip -n test link set foo up ip -n test link set bar up ip -n test link set b1 up ip -n test link set florp up VLAN_COUNT=1500 BASE_DEV=b1 echo Creating vlans ip netns exec test time -p bash -c "for i in \$(seq 1 $VLAN_COUNT); do ip -n test link add link $BASE_DEV name foo.\$i type vlan id \$i; done" echo Bringing them up ip netns exec test time -p bash -c "for i in \$(seq 1 $VLAN_COUNT); do ip -n test link set foo.\$i up; done" echo Assiging IPv6 Addresses ip netns exec test time -p bash -c "for i in \$(seq 1 $VLAN_COUNT); do ip -n test address add dev foo.\$i 2000::\$i/64; done" echo Attaching to VRF ip netns exec test time -p bash -c "for i in \$(seq 1 $VLAN_COUNT); do ip -n test link set foo.\$i master florp; done" On an Intel(R) Xeon(R) CPU E5-2650 v3 @ 2.30GHz machine, the performance before the patch is (truncated): Creating vlans real 108.35 Bringing them up real 4.96 Assiging IPv6 Addresses real 19.22 Attaching to VRF real 458.84 After the patch: Creating vlans real 5.59 Bringing them up real 5.07 Assiging IPv6 Addresses real 5.64 Attaching to VRF real 25.37 Cc: David S. Miller Cc: Jakub Kicinski Cc: Lu Wei Cc: Xiongfeng Wang Cc: Taehee Yoo Signed-off-by: Gilad Naaman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ++ net/core/dev_addr_lists.c | 144 +++++++++++++++++++++++++++++++--------------- 2 files changed, 103 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b88ad5aef7fe..6fd3a4d42668 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -47,6 +47,7 @@ #include #include #include +#include struct netpoll_info; struct device; @@ -208,6 +209,7 @@ struct sk_buff; struct netdev_hw_addr { struct list_head list; + struct rb_node node; unsigned char addr[MAX_ADDR_LEN]; unsigned char type; #define NETDEV_HW_ADDR_T_LAN 1 @@ -224,6 +226,9 @@ struct netdev_hw_addr { struct netdev_hw_addr_list { struct list_head list; int count; + + /* Auxiliary tree for faster lookup on addition and deletion */ + struct rb_root tree; }; #define netdev_hw_addr_list_count(l) ((l)->count) diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 45ae6eeb2964..8c39283c26ae 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -16,10 +16,9 @@ * General list handling functions */ -static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, - const unsigned char *addr, int addr_len, - unsigned char addr_type, bool global, - bool sync) +static struct netdev_hw_addr* +__hw_addr_create(const unsigned char *addr, int addr_len, + unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha; int alloc_size; @@ -29,32 +28,44 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, alloc_size = L1_CACHE_BYTES; ha = kmalloc(alloc_size, GFP_ATOMIC); if (!ha) - return -ENOMEM; + return NULL; memcpy(ha->addr, addr, addr_len); ha->type = addr_type; ha->refcount = 1; ha->global_use = global; ha->synced = sync ? 1 : 0; ha->sync_cnt = 0; - list_add_tail_rcu(&ha->list, &list->list); - list->count++; - return 0; + return ha; } static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync, - int sync_count) + int sync_count, bool exclusive) { + struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; if (addr_len > MAX_ADDR_LEN) return -EINVAL; - list_for_each_entry(ha, &list->list, list) { - if (ha->type == addr_type && - !memcmp(ha->addr, addr, addr_len)) { + while (*ins_point) { + int diff; + + ha = rb_entry(*ins_point, struct netdev_hw_addr, node); + diff = memcmp(addr, ha->addr, addr_len); + if (diff == 0) + diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); + + parent = *ins_point; + if (diff < 0) { + ins_point = &parent->rb_left; + } else if (diff > 0) { + ins_point = &parent->rb_right; + } else { + if (exclusive) + return -EEXIST; if (global) { /* check if addr is already used as global */ if (ha->global_use) @@ -73,8 +84,25 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, } } - return __hw_addr_create_ex(list, addr, addr_len, addr_type, global, - sync); + ha = __hw_addr_create(addr, addr_len, addr_type, global, sync); + if (!ha) + return -ENOMEM; + + /* The first address in dev->dev_addrs is pointed to by dev->dev_addr + * and mutated freely by device drivers and netdev ops, so if we insert + * it into the tree we'll end up with an invalid rbtree. + */ + if (list->count > 0) { + rb_link_node(&ha->node, parent, ins_point); + rb_insert_color(&ha->node, &list->tree); + } else { + RB_CLEAR_NODE(&ha->node); + } + + list_add_tail_rcu(&ha->list, &list->list); + list->count++; + + return 0; } static int __hw_addr_add(struct netdev_hw_addr_list *list, @@ -82,7 +110,7 @@ static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char addr_type) { return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, - 0); + 0, false); } static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, @@ -103,24 +131,61 @@ static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, if (--ha->refcount) return 0; + + if (!RB_EMPTY_NODE(&ha->node)) + rb_erase(&ha->node, &list->tree); + list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); list->count--; return 0; } +static struct netdev_hw_addr *__hw_addr_lookup(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) +{ + struct netdev_hw_addr *ha; + struct rb_node *node; + + /* The first address isn't inserted into the tree because in the dev->dev_addrs + * list it's the address pointed to by dev->dev_addr which is freely mutated + * in place, so we need to check it separately. + */ + ha = list_first_entry(&list->list, struct netdev_hw_addr, list); + if (ha && !memcmp(addr, ha->addr, addr_len) && + (!addr_type || addr_type == ha->type)) + return ha; + + node = list->tree.rb_node; + + while (node) { + struct netdev_hw_addr *ha = rb_entry(node, struct netdev_hw_addr, node); + int diff = memcmp(addr, ha->addr, addr_len); + + if (diff == 0 && addr_type) + diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); + + if (diff < 0) + node = node->rb_left; + else if (diff > 0) + node = node->rb_right; + else + return ha; + } + + return NULL; +} + static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { - struct netdev_hw_addr *ha; + struct netdev_hw_addr *ha = __hw_addr_lookup(list, addr, addr_len, addr_type); - list_for_each_entry(ha, &list->list, list) { - if (!memcmp(ha->addr, addr, addr_len) && - (ha->type == addr_type || !addr_type)) - return __hw_addr_del_entry(list, ha, global, sync); - } - return -ENOENT; + if (!ha) + return -ENOENT; + return __hw_addr_del_entry(list, ha, global, sync); } static int __hw_addr_del(struct netdev_hw_addr_list *list, @@ -137,7 +202,7 @@ static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, int err; err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, - false, true, ha->sync_cnt); + false, true, ha->sync_cnt, false); if (err && err != -EEXIST) return err; @@ -407,6 +472,7 @@ static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; + list->tree = RB_ROOT; list_for_each_entry_safe(ha, tmp, &list->list, list) { list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); @@ -418,6 +484,7 @@ void __hw_addr_init(struct netdev_hw_addr_list *list) { INIT_LIST_HEAD(&list->list); list->count = 0; + list->tree = RB_ROOT; } EXPORT_SYMBOL(__hw_addr_init); @@ -552,22 +619,14 @@ EXPORT_SYMBOL(dev_addr_del); */ int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { - struct netdev_hw_addr *ha; int err; netif_addr_lock_bh(dev); - list_for_each_entry(ha, &dev->uc.list, list) { - if (!memcmp(ha->addr, addr, dev->addr_len) && - ha->type == NETDEV_HW_ADDR_T_UNICAST) { - err = -EEXIST; - goto out; - } - } - err = __hw_addr_create_ex(&dev->uc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_UNICAST, true, false); + err = __hw_addr_add_ex(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST, true, false, + 0, true); if (!err) __dev_set_rx_mode(dev); -out: netif_addr_unlock_bh(dev); return err; } @@ -745,22 +804,14 @@ EXPORT_SYMBOL(dev_uc_init); */ int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) { - struct netdev_hw_addr *ha; int err; netif_addr_lock_bh(dev); - list_for_each_entry(ha, &dev->mc.list, list) { - if (!memcmp(ha->addr, addr, dev->addr_len) && - ha->type == NETDEV_HW_ADDR_T_MULTICAST) { - err = -EEXIST; - goto out; - } - } - err = __hw_addr_create_ex(&dev->mc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_MULTICAST, true, false); + err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, true, false, + 0, true); if (!err) __dev_set_rx_mode(dev); -out: netif_addr_unlock_bh(dev); return err; } @@ -773,7 +824,8 @@ static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_MULTICAST, global, false, 0); + NETDEV_HW_ADDR_T_MULTICAST, global, false, + 0, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); -- cgit v1.2.3 From b0b8c67eaa5c65f8426017e78fcce12dc7d85110 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 24 Aug 2021 20:15:01 +0300 Subject: net: dsa: sja1105: drop untagged packets on the CPU and DSA ports The sja1105 driver is a bit special in its use of VLAN headers as DSA tags. This is because in VLAN-aware mode, the VLAN headers use an actual TPID of 0x8100, which is understood even by the DSA master as an actual VLAN header. Furthermore, control packets such as PTP and STP are transmitted with no VLAN header as a DSA tag, because, depending on switch generation, there are ways to steer these control packets towards a precise egress port other than VLAN tags. Transmitting control packets as untagged means leaving a door open for traffic in general to be transmitted as untagged from the DSA master, and for it to traverse the switch and exit a random switch port according to the FDB lookup. This behavior is a bit out of line with other DSA drivers which have native support for DSA tagging. There, it is to be expected that the switch only accepts DSA-tagged packets on its CPU port, dropping everything that does not match this pattern. We perhaps rely a bit too much on the switches' hardware dropping on the CPU port, and place no other restrictions in the kernel data path to avoid that. For example, sja1105 is also a bit special in that STP/PTP packets are transmitted using "management routes" (sja1105_port_deferred_xmit): when sending a link-local packet from the CPU, we must first write a SPI message to the switch to tell it to expect a packet towards multicast MAC DA 01-80-c2-00-00-0e, and to route it towards port 3 when it gets it. This entry expires as soon as it matches a packet received by the switch, and it needs to be reinstalled for the next packet etc. All in all quite a ghetto mechanism, but it is all that the sja1105 switches offer for injecting a control packet. The driver takes a mutex for serializing control packets and making the pairs of SPI writes of a management route and its associated skb atomic, but to be honest, a mutex is only relevant as long as all parties agree to take it. With the DSA design, it is possible to open an AF_PACKET socket on the DSA master net device, and blast packets towards 01-80-c2-00-00-0e, and whatever locking the DSA switch driver might use, it all goes kaput because management routes installed by the driver will match skbs sent by the DSA master, and not skbs generated by the driver itself. So they will end up being routed on the wrong port. So through the lens of that, maybe it would make sense to avoid that from happening by doing something in the network stack, like: introduce a new bit in struct sk_buff, like xmit_from_dsa. Then, somewhere around dev_hard_start_xmit(), introduce the following check: if (netdev_uses_dsa(dev) && !skb->xmit_from_dsa) kfree_skb(skb); Ok, maybe that is a bit drastic, but that would at least prevent a bunch of problems. For example, right now, even though the majority of DSA switches drop packets without DSA tags sent by the DSA master (and therefore the majority of garbage that user space daemons like avahi and udhcpcd and friends create), it is still conceivable that an aggressive user space program can open an AF_PACKET socket and inject a spoofed DSA tag directly on the DSA master. We have no protection against that; the packet will be understood by the switch and be routed wherever user space says. Furthermore: there are some DSA switches where we even have register access over Ethernet, using DSA tags. So even user space drivers are possible in this way. This is a huge hole. However, the biggest thing that bothers me is that udhcpcd attempts to ask for an IP address on all interfaces by default, and with sja1105, it will attempt to get a valid IP address on both the DSA master as well as on sja1105 switch ports themselves. So with IP addresses in the same subnet on multiple interfaces, the routing table will be messed up and the system will be unusable for traffic until it is configured manually to not ask for an IP address on the DSA master itself. It turns out that it is possible to avoid that in the sja1105 driver, at least very superficially, by requesting the switch to drop VLAN-untagged packets on the CPU port. With the exception of control packets, all traffic originated from tag_sja1105.c is already VLAN-tagged, so only STP and PTP packets need to be converted. For that, we need to uphold the equivalence between an untagged and a pvid-tagged packet, and to remember that the CPU port of sja1105 uses a pvid of 4095. Now that we drop untagged traffic on the CPU port, non-aggressive user space applications like udhcpcd stop bothering us, and sja1105 effectively becomes just as vulnerable to the aggressive kind of user space programs as other DSA switches are (ok, users can also create 8021q uppers on top of the DSA master in the case of sja1105, but in future patches we can easily deny that, but it still doesn't change the fact that VLAN-tagged packets can still be injected over raw sockets). Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 10 ++++++++- include/linux/dsa/sja1105.h | 2 ++ net/dsa/tag_sja1105.c | 41 +++++++++++++++++++++++++++++++++- 3 files changed, 51 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 6be9fed50ed5..976f06462223 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -26,7 +26,6 @@ #include "sja1105_tas.h" #define SJA1105_UNKNOWN_MULTICAST 0x010000000000ull -#define SJA1105_DEFAULT_VLAN (VLAN_N_VID - 1) static void sja1105_hw_reset(struct gpio_desc *gpio, unsigned int pulse_len, unsigned int startup_delay) @@ -136,6 +135,9 @@ static int sja1105_commit_pvid(struct dsa_switch *ds, int port) drop_untagged = true; } + if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) + drop_untagged = true; + return sja1105_drop_untagged(ds, port, drop_untagged); } @@ -217,6 +219,12 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv) */ if (dsa_port_is_dsa(dp)) dp->learning = true; + + /* Disallow untagged packets from being received on the + * CPU and DSA ports. + */ + if (dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)) + mac[dp->index].drpuntag = true; } return 0; diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 6b0dc9ff92d1..8c5601f1c979 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -16,6 +16,8 @@ #define ETH_P_SJA1105_META 0x0008 #define ETH_P_SJA1110 0xdadc +#define SJA1105_DEFAULT_VLAN (VLAN_N_VID - 1) + /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ #define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull #define SJA1105_LINKLOCAL_FILTER_A_MASK 0xFFFFFF000000ull diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 5b80a9049e2c..a49308fbd19f 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -168,6 +168,36 @@ static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), tx_vid); } +/* Transform untagged control packets into pvid-tagged control packets so that + * all packets sent by this tagger are VLAN-tagged and we can configure the + * switch to drop untagged packets coming from the DSA master. + */ +static struct sk_buff *sja1105_pvid_tag_control_pkt(struct dsa_port *dp, + struct sk_buff *skb, u8 pcp) +{ + __be16 xmit_tpid = htons(sja1105_xmit_tpid(dp)); + struct vlan_ethhdr *hdr; + + /* If VLAN tag is in hwaccel area, move it to the payload + * to deal with both cases uniformly and to ensure that + * the VLANs are added in the right order. + */ + if (unlikely(skb_vlan_tag_present(skb))) { + skb = __vlan_hwaccel_push_inside(skb); + if (!skb) + return NULL; + } + + hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + + /* If skb is already VLAN-tagged, leave that VLAN ID in place */ + if (hdr->h_vlan_proto == xmit_tpid) + return skb; + + return vlan_insert_tag(skb, xmit_tpid, (pcp << VLAN_PRIO_SHIFT) | + SJA1105_DEFAULT_VLAN); +} + static struct sk_buff *sja1105_xmit(struct sk_buff *skb, struct net_device *netdev) { @@ -183,8 +213,13 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, * but instead SPI-installed management routes. Part 2 of this * is the .port_deferred_xmit driver callback. */ - if (unlikely(sja1105_is_link_local(skb))) + if (unlikely(sja1105_is_link_local(skb))) { + skb = sja1105_pvid_tag_control_pkt(dp, skb, pcp); + if (!skb) + return NULL; + return sja1105_defer_xmit(dp, skb); + } return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); @@ -213,6 +248,10 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb, return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); + skb = sja1105_pvid_tag_control_pkt(dp, skb, pcp); + if (!skb) + return NULL; + skb_push(skb, SJA1110_HEADER_LEN); dsa_alloc_etype_header(skb, SJA1110_HEADER_LEN); -- cgit v1.2.3 From 8ded9160928e545c2e694b77a87263fa078ff4c6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 24 Aug 2021 20:15:02 +0300 Subject: net: dsa: tag_sja1105: stop asking the sja1105 driver in sja1105_xmit_tpid Introduced in commit 38b5beeae7a4 ("net: dsa: sja1105: prepare tagger for handling DSA tags and VLAN simultaneously"), the sja1105_xmit_tpid function solved quite a different problem than our needs are now. Then, we used best-effort VLAN filtering and we were using the xmit_tpid to tunnel packets coming from an 8021q upper through the TX VLAN allocated by tag_8021q to that egress port. The need for a different VLAN protocol depending on switch revision came from the fact that this in itself was more of a hack to trick the hardware into accepting tunneled VLANs in the first place. Right now, we deny 8021q uppers (see sja1105_prechangeupper). Even if we supported them again, we would not do that using the same method of {tunneling the VLAN on egress, retagging the VLAN on ingress} that we had in the best-effort VLAN filtering mode. It seems rather simpler that we just allocate a VLAN in the VLAN table that is simply not used by the bridge at all, or by any other port. Anyway, I have 2 gripes with the current sja1105_xmit_tpid: 1. When sending packets on behalf of a VLAN-aware bridge (with the new TX forwarding offload framework) plus untagged (with the tag_8021q VLAN added by the tagger) packets, we can see that on SJA1105P/Q/R/S and later (which have a qinq_tpid of ETH_P_8021AD), some packets sent through the DSA master have a VLAN protocol of 0x8100 and others of 0x88a8. This is strange and there is no reason for it now. If we have a bridge and are therefore forced to send using that bridge's TPID, we can as well blend with that bridge's VLAN protocol for all packets. 2. The sja1105_xmit_tpid introduces a dependency on the sja1105 driver, because it looks inside dp->priv. It is desirable to keep as much separation between taggers and switch drivers as possible. Now it doesn't do that anymore. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105.h | 6 ------ drivers/net/dsa/sja1105/sja1105_main.c | 10 --------- drivers/net/dsa/sja1105/sja1105_spi.c | 10 --------- include/linux/dsa/sja1105.h | 1 - net/dsa/tag_sja1105.c | 38 ++++++++++++++++++++++++++++++---- 5 files changed, 34 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 2e899c9f036d..5e5d24e7c02b 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -115,12 +115,6 @@ struct sja1105_info { const struct sja1105_dynamic_table_ops *dyn_ops; const struct sja1105_table_ops *static_ops; const struct sja1105_regs *regs; - /* Both E/T and P/Q/R/S have quirks when it comes to popping the S-Tag - * from double-tagged frames. E/T will pop it only when it's equal to - * TPID from the General Parameters Table, while P/Q/R/S will only - * pop it when it's equal to TPID2. - */ - u16 qinq_tpid; bool can_limit_mcast_flood; int (*reset_cmd)(struct dsa_switch *ds); int (*setup_rgmii_delay)(const void *ctx, int port); diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 976f06462223..2f8cc6686c38 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2295,15 +2295,6 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, tpid2 = ETH_P_SJA1105; } - for (port = 0; port < ds->num_ports; port++) { - struct sja1105_port *sp = &priv->ports[port]; - - if (enabled) - sp->xmit_tpid = priv->info->qinq_tpid; - else - sp->xmit_tpid = ETH_P_SJA1105; - } - if (priv->vlan_aware == enabled) return 0; @@ -2988,7 +2979,6 @@ static int sja1105_setup_ports(struct sja1105_private *priv) } sp->xmit_worker = worker; skb_queue_head_init(&sp->xmit_queue); - sp->xmit_tpid = ETH_P_SJA1105; } return 0; diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index 08cc5dbf2fa6..d60a530d0272 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -575,7 +575,6 @@ const struct sja1105_info sja1105e_info = { .part_no = SJA1105ET_PART_NO, .static_ops = sja1105e_table_ops, .dyn_ops = sja1105et_dyn_ops, - .qinq_tpid = ETH_P_8021Q, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = false, .ptp_ts_bits = 24, @@ -608,7 +607,6 @@ const struct sja1105_info sja1105t_info = { .part_no = SJA1105ET_PART_NO, .static_ops = sja1105t_table_ops, .dyn_ops = sja1105et_dyn_ops, - .qinq_tpid = ETH_P_8021Q, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = false, .ptp_ts_bits = 24, @@ -641,7 +639,6 @@ const struct sja1105_info sja1105p_info = { .part_no = SJA1105P_PART_NO, .static_ops = sja1105p_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, @@ -675,7 +672,6 @@ const struct sja1105_info sja1105q_info = { .part_no = SJA1105Q_PART_NO, .static_ops = sja1105q_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, @@ -709,7 +705,6 @@ const struct sja1105_info sja1105r_info = { .part_no = SJA1105R_PART_NO, .static_ops = sja1105r_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, @@ -747,7 +742,6 @@ const struct sja1105_info sja1105s_info = { .static_ops = sja1105s_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .regs = &sja1105pqrs_regs, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, @@ -784,7 +778,6 @@ const struct sja1105_info sja1110a_info = { .static_ops = sja1110_table_ops, .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, @@ -835,7 +828,6 @@ const struct sja1105_info sja1110b_info = { .static_ops = sja1110_table_ops, .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, @@ -886,7 +878,6 @@ const struct sja1105_info sja1110c_info = { .static_ops = sja1110_table_ops, .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, @@ -937,7 +928,6 @@ const struct sja1105_info sja1110d_info = { .static_ops = sja1110_table_ops, .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 8c5601f1c979..171106202fe5 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -67,7 +67,6 @@ struct sja1105_port { struct sja1105_tagger_data *data; struct dsa_port *dp; bool hwts_tx_en; - u16 xmit_tpid; }; enum sja1110_meta_tstamp { diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index a49308fbd19f..c054f48541c8 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -133,14 +133,44 @@ static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, return NULL; } +/* Send VLAN tags with a TPID that blends in with whatever VLAN protocol a + * bridge spanning ports of this switch might have. + */ static u16 sja1105_xmit_tpid(struct dsa_port *dp) { - struct sja1105_port *sp = dp->priv; + struct dsa_switch *ds = dp->ds; + struct dsa_port *other_dp; + u16 proto; + + /* Since VLAN awareness is global, then if this port is VLAN-unaware, + * all ports are. Use the VLAN-unaware TPID used for tag_8021q. + */ + if (!dsa_port_is_vlan_filtering(dp)) + return ETH_P_SJA1105; + + /* Port is VLAN-aware, so there is a bridge somewhere (a single one, + * we're sure about that). It may not be on this port though, so we + * need to find it. + */ + list_for_each_entry(other_dp, &ds->dst->ports, list) { + if (other_dp->ds != ds) + continue; + + if (!other_dp->bridge_dev) + continue; + + /* Error is returned only if CONFIG_BRIDGE_VLAN_FILTERING, + * which seems pointless to handle, as our port cannot become + * VLAN-aware in that case. + */ + br_vlan_get_proto(other_dp->bridge_dev, &proto); + + return proto; + } - if (unlikely(!dsa_port_is_sja1105(dp))) - return ETH_P_8021Q; + WARN_ONCE(1, "Port is VLAN-aware but cannot find associated bridge!\n"); - return sp->xmit_tpid; + return ETH_P_SJA1105; } static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, -- cgit v1.2.3 From d32f89da7fa8ccc8b3fb8f909d61e42b9bc39329 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 25 Aug 2021 12:25:44 +0100 Subject: net: add accept helper not installing fd Introduce and reuse a helper that acts similarly to __sys_accept4_file() but returns struct file instead of installing file descriptor. Will be used by io_uring. Signed-off-by: Pavel Begunkov Acked-by: Jakub Kicinski Signed-off-by: Jens Axboe Acked-by: David S. Miller Link: https://lore.kernel.org/r/c57b9e8e818d93683a3d24f8ca50ca038d1da8c4.1629888991.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/socket.h | 3 +++ net/socket.c | 71 ++++++++++++++++++++++++++------------------------ 2 files changed, 40 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 0d8e3dcb7f88..d3c1a42a2edd 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -421,6 +421,9 @@ extern int __sys_accept4_file(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags, unsigned long nofile); +extern struct file *do_accept(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); diff --git a/net/socket.c b/net/socket.c index 0b2dad3bdf7f..532fff5a3684 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1722,32 +1722,22 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) return __sys_listen(fd, backlog); } -int __sys_accept4_file(struct file *file, unsigned file_flags, +struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile) + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; - int err, len, newfd; + int err, len; struct sockaddr_storage address; - if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) - return -EINVAL; - - if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) - flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - sock = sock_from_file(file); - if (!sock) { - err = -ENOTSOCK; - goto out; - } + if (!sock) + return ERR_PTR(-ENOTSOCK); - err = -ENFILE; newsock = sock_alloc(); if (!newsock) - goto out; + return ERR_PTR(-ENFILE); newsock->type = sock->type; newsock->ops = sock->ops; @@ -1758,18 +1748,9 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, */ __module_get(newsock->ops->owner); - newfd = __get_unused_fd_flags(flags, nofile); - if (unlikely(newfd < 0)) { - err = newfd; - sock_release(newsock); - goto out; - } newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); - if (IS_ERR(newfile)) { - err = PTR_ERR(newfile); - put_unused_fd(newfd); - goto out; - } + if (IS_ERR(newfile)) + return newfile; err = security_socket_accept(sock, newsock); if (err) @@ -1794,16 +1775,38 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, } /* File flags are not inherited via accept() unlike another OSes. */ - - fd_install(newfd, newfile); - err = newfd; -out: - return err; + return newfile; out_fd: fput(newfile); - put_unused_fd(newfd); - goto out; + return ERR_PTR(err); +} + +int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags, + unsigned long nofile) +{ + struct file *newfile; + int newfd; + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + + newfd = __get_unused_fd_flags(flags, nofile); + if (unlikely(newfd < 0)) + return newfd; + + newfile = do_accept(file, file_flags, upeer_sockaddr, upeer_addrlen, + flags); + if (IS_ERR(newfile)) { + put_unused_fd(newfd); + return PTR_ERR(newfile); + } + fd_install(newfd, newfile); + return newfd; } /* -- cgit v1.2.3 From a7e20e31f6c063d928868ecc8e2effb7d4b9fe1b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 12 May 2021 14:10:09 +0100 Subject: netfs: Move cookie debug ID to struct netfs_cache_resources Move the cookie debug ID from struct netfs_read_request to struct netfs_cache_resources and drop the 'cookie_' prefix. This makes it available for things that want to use netfs_cache_resources without having a netfs_read_request. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/162431190784.2908479.13386972676539789127.stgit@warthog.procyon.org.uk/ --- fs/cachefiles/io.c | 2 +- include/linux/netfs.h | 2 +- include/trace/events/netfs.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index b13fb45fc3f3..ca68bb97ca00 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -410,7 +410,7 @@ int cachefiles_begin_read_operation(struct netfs_read_request *rreq, rreq->cache_resources.cache_priv = op; rreq->cache_resources.cache_priv2 = file; rreq->cache_resources.ops = &cachefiles_netfs_cache_ops; - rreq->cookie_debug_id = object->fscache.debug_id; + rreq->cache_resources.debug_id = object->fscache.debug_id; _leave(""); return 0; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 9062adfa2fb9..5d6a4158a9a6 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -102,6 +102,7 @@ struct netfs_cache_resources { const struct netfs_cache_ops *ops; void *cache_priv; void *cache_priv2; + unsigned int debug_id; /* Cookie debug ID */ }; /* @@ -137,7 +138,6 @@ struct netfs_read_request { struct list_head subrequests; /* Requests to fetch I/O from disk or net */ void *netfs_priv; /* Private data for the netfs */ unsigned int debug_id; - unsigned int cookie_debug_id; atomic_t nr_rd_ops; /* Number of read ops in progress */ atomic_t nr_wr_ops; /* Number of write ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index de1c64635e42..4d470bffd9f1 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -139,7 +139,7 @@ TRACE_EVENT(netfs_read, TP_fast_assign( __entry->rreq = rreq->debug_id; - __entry->cookie = rreq->cookie_debug_id; + __entry->cookie = rreq->cache_resources.debug_id; __entry->start = start; __entry->len = len; __entry->what = what; -- cgit v1.2.3 From 1b07d00a15d6a96d1a36b6a284c4fd5f2e2fa383 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Mon, 23 Aug 2021 19:43:46 -0700 Subject: bpf: Add BTF_ID_LIST_GLOBAL_SINGLE macro Same as BTF_ID_LIST_SINGLE macro except defines a global ID. Signed-off-by: Daniel Xu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/a867a97517df42fd3953eeb5454402b57e74538f.1629772842.git.dxu@dxuuu.xyz --- include/linux/btf_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index bed4b9964581..6d1395030616 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -82,6 +82,9 @@ __BTF_ID_LIST(name, globl) #define BTF_ID_LIST_SINGLE(name, prefix, typename) \ BTF_ID_LIST(name) \ BTF_ID(prefix, typename) +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) \ + BTF_ID_LIST_GLOBAL(name) \ + BTF_ID(prefix, typename) /* * The BTF_ID_UNUSED macro defines 4 zero bytes. -- cgit v1.2.3 From 33c5cb36015ac1034b50b823fae367e908d05147 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Mon, 23 Aug 2021 19:43:47 -0700 Subject: bpf: Consolidate task_struct BTF_ID declarations No need to have it defined 5 times. Once is enough. Signed-off-by: Daniel Xu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/6dcefa5bed26fe1226f26683f36819bb53ec19a2.1629772842.git.dxu@dxuuu.xyz --- include/linux/btf_ids.h | 2 ++ kernel/bpf/bpf_task_storage.c | 6 ++---- kernel/bpf/stackmap.c | 4 +--- kernel/bpf/task_iter.c | 11 +++++------ kernel/trace/bpf_trace.c | 4 ++-- 5 files changed, 12 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 6d1395030616..93d881ab0d48 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -188,4 +188,6 @@ MAX_BTF_SOCK_TYPE, extern u32 btf_sock_ids[]; #endif +extern u32 btf_task_struct_ids[]; + #endif diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index 3ce75758d394..ebfa8bc90892 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -317,15 +317,13 @@ const struct bpf_map_ops task_storage_map_ops = { .map_owner_storage_ptr = task_storage_ptr, }; -BTF_ID_LIST_SINGLE(bpf_task_storage_btf_ids, struct, task_struct) - const struct bpf_func_proto bpf_task_storage_get_proto = { .func = bpf_task_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, - .arg2_btf_id = &bpf_task_storage_btf_ids[0], + .arg2_btf_id = &btf_task_struct_ids[0], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; @@ -336,5 +334,5 @@ const struct bpf_func_proto bpf_task_storage_delete_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, - .arg2_btf_id = &bpf_task_storage_btf_ids[0], + .arg2_btf_id = &btf_task_struct_ids[0], }; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 6fbc2abe9c91..e8eefdf8cf3e 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -530,14 +530,12 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, return res; } -BTF_ID_LIST_SINGLE(bpf_get_task_stack_btf_ids, struct, task_struct) - const struct bpf_func_proto bpf_get_task_stack_proto = { .func = bpf_get_task_stack, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, - .arg1_btf_id = &bpf_get_task_stack_btf_ids[0], + .arg1_btf_id = &btf_task_struct_ids[0], .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index b68cb5d6d6eb..b48750bfba5a 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -525,7 +525,6 @@ static const struct seq_operations task_vma_seq_ops = { }; BTF_ID_LIST(btf_task_file_ids) -BTF_ID(struct, task_struct) BTF_ID(struct, file) BTF_ID(struct, vm_area_struct) @@ -591,19 +590,19 @@ static int __init task_iter_init(void) { int ret; - task_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0]; + task_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; ret = bpf_iter_reg_target(&task_reg_info); if (ret) return ret; - task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0]; - task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1]; + task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; + task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[0]; ret = bpf_iter_reg_target(&task_file_reg_info); if (ret) return ret; - task_vma_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0]; - task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[2]; + task_vma_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; + task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1]; return bpf_iter_reg_target(&task_vma_reg_info); } late_initcall(task_iter_init); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cbc73c08c4a4..50d055fc2327 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -714,13 +714,13 @@ BPF_CALL_0(bpf_get_current_task_btf) return (unsigned long) current; } -BTF_ID_LIST_SINGLE(bpf_get_current_btf_ids, struct, task_struct) +BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) static const struct bpf_func_proto bpf_get_current_task_btf_proto = { .func = bpf_get_current_task_btf, .gpl_only = true, .ret_type = RET_PTR_TO_BTF_ID, - .ret_btf_id = &bpf_get_current_btf_ids[0], + .ret_btf_id = &btf_task_struct_ids[0], }; BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) -- cgit v1.2.3 From 3d2b50e0e7682b2453ccfac775ad7c2c1d5ceb45 Mon Sep 17 00:00:00 2001 From: Steve French Date: Fri, 20 Aug 2021 18:10:36 -0500 Subject: oid_registry: Add OIDs for missing Spnego auth mechanisms to Macs In testing mounts to Macs, noticed that the OIDS for some GSSAPI/SPNEGO auth mechanisms sent by the server were not recognized and were missing from the header. Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- include/linux/oid_registry.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 3d8db1f6a5db..0f4a8903922a 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -70,6 +70,9 @@ enum OID { OID_spnego, /* 1.3.6.1.5.5.2 */ + OID_IAKerb, /* 1.3.6.1.5.2.5 */ + OID_PKU2U, /* 1.3.5.1.5.2.7 */ + OID_Scram, /* 1.3.6.1.5.5.14 */ OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ @@ -104,6 +107,10 @@ enum OID { OID_authorityKeyIdentifier, /* 2.5.29.35 */ OID_extKeyUsage, /* 2.5.29.37 */ + /* Heimdal mechanisms */ + OID_NetlogonMechanism, /* 1.2.752.43.14.2 */ + OID_appleLocalKdcSupported, /* 1.2.752.43.14.3 */ + /* EC-RDSA */ OID_gostCPSignA, /* 1.2.643.2.2.35.1 */ OID_gostCPSignB, /* 1.2.643.2.2.35.2 */ -- cgit v1.2.3 From eb529c5b10b9401a0f2d1f469e82c6a0ba98082c Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Wed, 25 Aug 2021 18:48:31 -0700 Subject: bpf: Fix bpf-next builds without CONFIG_BPF_EVENTS This commit fixes linker errors along the lines of: s390-linux-ld: task_iter.c:(.init.text+0xa4): undefined reference to `btf_task_struct_ids'` Fix by defining btf_task_struct_ids unconditionally in kernel/bpf/btf.c since there exists code that unconditionally uses btf_task_struct_ids. Reported-by: kernel test robot Signed-off-by: Daniel Xu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/05d94748d9f4b3eecedc4fddd6875418a396e23c.1629942444.git.dxu@dxuuu.xyz --- include/linux/btf_ids.h | 1 + kernel/bpf/btf.c | 2 ++ kernel/trace/bpf_trace.c | 2 -- 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 93d881ab0d48..47d9abfbdb55 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -151,6 +151,7 @@ extern struct btf_id_set name; #define BTF_ID_UNUSED #define BTF_ID_LIST_GLOBAL(name) u32 name[1]; #define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; #define BTF_SET_START(name) static struct btf_id_set name = { 0 }; #define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; #define BTF_SET_END(name) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index c395024610ed..dfe61df4f974 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6213,3 +6213,5 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; + +BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 580e14ee7ff9..8e2eb950aa82 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -714,8 +714,6 @@ BPF_CALL_0(bpf_get_current_task_btf) return (unsigned long) current; } -BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) - const struct bpf_func_proto bpf_get_current_task_btf_proto = { .func = bpf_get_current_task_btf, .gpl_only = true, -- cgit v1.2.3 From a1ef61825469b874920f4afb889e1a92353680ff Mon Sep 17 00:00:00 2001 From: Wen Gong Date: Fri, 20 Aug 2021 08:20:35 -0400 Subject: ieee80211: add definition of regulatory info in 6 GHz operation information MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit IEEE Std 802.11ax™-2021 added regulatory info subfield in HE operation element, add it to the header file. Signed-off-by: Wen Gong Link: https://lore.kernel.org/r/20210820122041.12157-3-wgong@codeaurora.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2e8953d80d4b..f91cb15a74e7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2312,6 +2312,9 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 +#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 +#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 + /** * ieee80211_he_6ghz_oper - HE 6 GHz operation Information field * @primary: primary channel @@ -2328,6 +2331,7 @@ struct ieee80211_he_6ghz_oper { #define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ 2 #define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ 3 #define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON 0x4 +#define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO 0x38 u8 control; u8 ccfs0; u8 ccfs1; -- cgit v1.2.3 From ad31393b98e4addbc5f1ccc484bfbb8d07c92056 Mon Sep 17 00:00:00 2001 From: Wen Gong Date: Fri, 20 Aug 2021 08:20:39 -0400 Subject: ieee80211: add definition for transmit power envelope element MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit IEEE Std 802.11ax™-2021 makes changes to the transmit power envelope element, adjust the code accordingly. Signed-off-by: Wen Gong Link: https://lore.kernel.org/r/20210820122041.12157-7-wgong@codeaurora.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 40 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 39 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f91cb15a74e7..694264503119 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2338,6 +2338,44 @@ struct ieee80211_he_6ghz_oper { u8 minrate; } __packed; +/* + * In "9.4.2.161 Transmit Power Envelope element" of "IEEE Std 802.11ax-2021", + * it show four types in "Table 9-275a-Maximum Transmit Power Interpretation + * subfield encoding", and two category for each type in "Table E-12-Regulatory + * Info subfield encoding in the United States". + * So it it totally max 8 Transmit Power Envelope element. + */ +#define IEEE80211_TPE_MAX_IE_COUNT 8 +/* + * In "Table 9-277—Meaning of Maximum Transmit Power Count subfield" + * of "IEEE Std 802.11ax™‐2021", the max power level is 8. + */ +#define IEEE80211_MAX_NUM_PWR_LEVEL 8 + +#define IEEE80211_TPE_MAX_POWER_COUNT 8 + +/* transmit power interpretation type of transmit power envelope element */ +enum ieee80211_tx_power_intrpt_type { + IEEE80211_TPE_LOCAL_EIRP, + IEEE80211_TPE_LOCAL_EIRP_PSD, + IEEE80211_TPE_REG_CLIENT_EIRP, + IEEE80211_TPE_REG_CLIENT_EIRP_PSD, +}; + +/** + * struct ieee80211_tx_pwr_env + * + * This structure represents the "Transmit Power Envelope element" + */ +struct ieee80211_tx_pwr_env { + u8 tx_power_info; + s8 tx_power[IEEE80211_TPE_MAX_POWER_COUNT]; +} __packed; + +#define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7 +#define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38 +#define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0 + /* * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size * @he_oper_ie: byte data of the He Operations IE, stating from the byte @@ -2919,7 +2957,7 @@ enum ieee80211_eid { WLAN_EID_VHT_OPERATION = 192, WLAN_EID_EXTENDED_BSS_LOAD = 193, WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194, - WLAN_EID_VHT_TX_POWER_ENVELOPE = 195, + WLAN_EID_TX_POWER_ENVELOPE = 195, WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196, WLAN_EID_AID = 197, WLAN_EID_QUIET_CHANNEL = 198, -- cgit v1.2.3 From 67021f25d95292d285dd213c58401642b98eaf24 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 25 Aug 2021 23:50:40 +0300 Subject: regmap: teach regmap to use raw spinlocks if requested in the config Some drivers might access regmap in a context where a raw spinlock is held. An example is drivers/irqchip/irq-ls-extirq.c, which calls regmap_update_bits() from struct irq_chip :: irq_set_type, which is a method called by __irq_set_trigger() under the desc->lock raw spin lock. Since desc->lock is a raw spin lock and the regmap internal lock for mmio is a plain spinlock (which can become sleepable on RT), this is an invalid locking scheme and we get a splat stating that this is a "[ BUG: Invalid wait context ]". It seems reasonable for regmap to have an option use a raw spinlock too, so add that in the config such that drivers can request it. Suggested-by: Mark Brown Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20210825205041.927788-2-vladimir.oltean@nxp.com Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 4 ++++ drivers/base/regmap/regmap.c | 35 ++++++++++++++++++++++++++++++----- include/linux/regmap.h | 2 ++ 3 files changed, 36 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 0097696c31de..b1905916f7af 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -53,6 +53,10 @@ struct regmap { spinlock_t spinlock; unsigned long spinlock_flags; }; + struct { + raw_spinlock_t raw_spinlock; + unsigned long raw_spinlock_flags; + }; }; regmap_lock lock; regmap_unlock unlock; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 297e95be25b3..d8510708ec54 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -523,6 +523,23 @@ __releases(&map->spinlock) spin_unlock_irqrestore(&map->spinlock, map->spinlock_flags); } +static void regmap_lock_raw_spinlock(void *__map) +__acquires(&map->raw_spinlock) +{ + struct regmap *map = __map; + unsigned long flags; + + raw_spin_lock_irqsave(&map->raw_spinlock, flags); + map->raw_spinlock_flags = flags; +} + +static void regmap_unlock_raw_spinlock(void *__map) +__releases(&map->raw_spinlock) +{ + struct regmap *map = __map; + raw_spin_unlock_irqrestore(&map->raw_spinlock, map->raw_spinlock_flags); +} + static void dev_get_regmap_release(struct device *dev, void *res) { /* @@ -760,11 +777,19 @@ struct regmap *__regmap_init(struct device *dev, } else { if ((bus && bus->fast_io) || config->fast_io) { - spin_lock_init(&map->spinlock); - map->lock = regmap_lock_spinlock; - map->unlock = regmap_unlock_spinlock; - lockdep_set_class_and_name(&map->spinlock, - lock_key, lock_name); + if (config->use_raw_spinlock) { + raw_spin_lock_init(&map->raw_spinlock); + map->lock = regmap_lock_raw_spinlock; + map->unlock = regmap_unlock_raw_spinlock; + lockdep_set_class_and_name(&map->raw_spinlock, + lock_key, lock_name); + } else { + spin_lock_init(&map->spinlock); + map->lock = regmap_lock_spinlock; + map->unlock = regmap_unlock_spinlock; + lockdep_set_class_and_name(&map->spinlock, + lock_key, lock_name); + } } else { mutex_init(&map->mutex); map->lock = regmap_lock_mutex; diff --git a/include/linux/regmap.h b/include/linux/regmap.h index f87a11a5cc4a..ed57b7c5b468 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -343,6 +343,7 @@ typedef void (*regmap_unlock)(void *); * @ranges: Array of configuration entries for virtual address ranges. * @num_ranges: Number of range configuration entries. * @use_hwlock: Indicate if a hardware spinlock should be used. + * @use_raw_spinlock: Indicate if a raw spinlock should be used. * @hwlock_id: Specify the hardware spinlock id. * @hwlock_mode: The hardware spinlock mode, should be HWLOCK_IRQSTATE, * HWLOCK_IRQ or 0. @@ -402,6 +403,7 @@ struct regmap_config { unsigned int num_ranges; bool use_hwlock; + bool use_raw_spinlock; unsigned int hwlock_id; unsigned int hwlock_mode; -- cgit v1.2.3 From 307d522f5eb86cd6ac8c905f5b0577dedac54ec5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 23 Jun 2021 16:44:32 -0500 Subject: signal/seccomp: Refactor seccomp signal and coredump generation Factor out force_sig_seccomp from the seccomp signal generation and place it in kernel/signal.c. The function force_sig_seccomp takes a parameter force_coredump to indicate that the sigaction field should be reset to SIGDFL so that a coredump will be generated when the signal is delivered. force_sig_seccomp is then used to replace both seccomp_send_sigsys and seccomp_init_siginfo. force_sig_info_to_task gains an extra parameter to force using the default signal action. With this change seccomp is no longer a special case and there becomes exactly one place do_coredump is called from. Further it no longer becomes necessary for __seccomp_filter to call do_group_exit. Acked-by: Kees Cook Link: https://lkml.kernel.org/r/87r1gr6qc4.fsf_-_@disp2133 Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 1 + kernel/seccomp.c | 40 ++++++---------------------------------- kernel/signal.c | 30 ++++++++++++++++++++++++++---- 3 files changed, 33 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index b9126fe06c3f..e3c933facd86 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -329,6 +329,7 @@ int force_sig_pkuerr(void __user *addr, u32 pkey); int force_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); +int force_sig_seccomp(int syscall, int reason, bool force_coredump); extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 057e17f3215d..abcbd3d2ba54 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -922,30 +922,6 @@ void get_seccomp_filter(struct task_struct *tsk) refcount_inc(&orig->users); } -static void seccomp_init_siginfo(kernel_siginfo_t *info, int syscall, int reason) -{ - clear_siginfo(info); - info->si_signo = SIGSYS; - info->si_code = SYS_SECCOMP; - info->si_call_addr = (void __user *)KSTK_EIP(current); - info->si_errno = reason; - info->si_arch = syscall_get_arch(current); - info->si_syscall = syscall; -} - -/** - * seccomp_send_sigsys - signals the task to allow in-process syscall emulation - * @syscall: syscall number to send to userland - * @reason: filter-supplied reason code to send to userland (via si_errno) - * - * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info. - */ -static void seccomp_send_sigsys(int syscall, int reason) -{ - struct kernel_siginfo info; - seccomp_init_siginfo(&info, syscall, reason); - force_sig_info(&info); -} #endif /* CONFIG_SECCOMP_FILTER */ /* For use with seccomp_actions_logged */ @@ -1218,7 +1194,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, /* Show the handler the original registers. */ syscall_rollback(current, current_pt_regs()); /* Let the filter pass back 16 bits of data. */ - seccomp_send_sigsys(this_syscall, data); + force_sig_seccomp(this_syscall, data, false); goto skip; case SECCOMP_RET_TRACE: @@ -1289,18 +1265,14 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, /* Dump core only if this is the last remaining thread. */ if (action != SECCOMP_RET_KILL_THREAD || get_nr_threads(current) == 1) { - kernel_siginfo_t info; - /* Show the original registers in the dump. */ syscall_rollback(current, current_pt_regs()); - /* Trigger a manual coredump since do_exit skips it. */ - seccomp_init_siginfo(&info, this_syscall, data); - do_coredump(&info); - } - if (action == SECCOMP_RET_KILL_THREAD) + /* Trigger a coredump with SIGSYS */ + force_sig_seccomp(this_syscall, data, true); + } else { do_exit(SIGSYS); - else - do_group_exit(SIGSYS); + } + return -1; /* skip the syscall go directly to signal handling */ } unreachable(); diff --git a/kernel/signal.c b/kernel/signal.c index a3229add4455..fbf941b80dd4 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -54,6 +54,7 @@ #include #include #include +#include /* for syscall_get_* */ /* * SLAB caches for signal bits. @@ -1322,7 +1323,7 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p * that is why we also clear SIGNAL_UNKILLABLE. */ static int -force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t) +force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool sigdfl) { unsigned long int flags; int ret, blocked, ignored; @@ -1333,7 +1334,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t) action = &t->sighand->action[sig-1]; ignored = action->sa.sa_handler == SIG_IGN; blocked = sigismember(&t->blocked, sig); - if (blocked || ignored) { + if (blocked || ignored || sigdfl) { action->sa.sa_handler = SIG_DFL; if (blocked) { sigdelset(&t->blocked, sig); @@ -1354,7 +1355,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t) int force_sig_info(struct kernel_siginfo *info) { - return force_sig_info_to_task(info, current); + return force_sig_info_to_task(info, current, false); } /* @@ -1685,7 +1686,7 @@ int force_sig_fault_to_task(int sig, int code, void __user *addr info.si_flags = flags; info.si_isr = isr; #endif - return force_sig_info_to_task(&info, t); + return force_sig_info_to_task(&info, t, false); } int force_sig_fault(int sig, int code, void __user *addr @@ -1793,6 +1794,27 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data) return force_sig_info(&info); } +/** + * force_sig_seccomp - signals the task to allow in-process syscall emulation + * @syscall: syscall number to send to userland + * @reason: filter-supplied reason code to send to userland (via si_errno) + * + * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info. + */ +int force_sig_seccomp(int syscall, int reason, bool force_coredump) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = SIGSYS; + info.si_code = SYS_SECCOMP; + info.si_call_addr = (void __user *)KSTK_EIP(current); + info.si_errno = reason; + info.si_arch = syscall_get_arch(current); + info.si_syscall = syscall; + return force_sig_info_to_task(&info, current, force_coredump); +} + /* For the crazy architectures that include trap information in * the errno field, instead of an actual errno value. */ -- cgit v1.2.3 From 343b7258687ecfbb363bfda8833a7cf641aac524 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 26 Aug 2021 13:39:08 +0300 Subject: PCI: Add 'override_only' field to struct pci_device_id Add 'override_only' field to struct pci_device_id to be used as part of pci_match_device(). When set, a driver only matches the entry when dev->driver_override is set to that driver. In addition, add a helper macro named 'PCI_DEVICE_DRIVER_OVERRIDE' to enable setting some data on it. Next patch from this series will use the above functionality. Signed-off-by: Max Gurtovoy Signed-off-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20210826103912.128972-10-yishaih@nvidia.com Signed-off-by: Alex Williamson --- Documentation/PCI/pci.rst | 1 + drivers/pci/pci-driver.c | 28 +++++++++++++++++++++------- include/linux/mod_devicetable.h | 2 ++ include/linux/pci.h | 15 +++++++++++++++ 4 files changed, 39 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/Documentation/PCI/pci.rst b/Documentation/PCI/pci.rst index fa651e25d98c..87c6f4a6ca32 100644 --- a/Documentation/PCI/pci.rst +++ b/Documentation/PCI/pci.rst @@ -103,6 +103,7 @@ need pass only as many optional fields as necessary: - subvendor and subdevice fields default to PCI_ANY_ID (FFFFFFFF) - class and classmask fields default to 0 - driver_data defaults to 0UL. + - override_only field defaults to 0. Note that driver_data must match the value used by any of the pci_device_id entries defined in the driver. This makes the driver_data field mandatory diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 3a72352aa5cf..123c590ebe1d 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -136,7 +136,7 @@ static const struct pci_device_id *pci_match_device(struct pci_driver *drv, struct pci_dev *dev) { struct pci_dynid *dynid; - const struct pci_device_id *found_id = NULL; + const struct pci_device_id *found_id = NULL, *ids; /* When driver_override is set, only bind to the matching driver */ if (dev->driver_override && strcmp(dev->driver_override, drv->name)) @@ -152,14 +152,28 @@ static const struct pci_device_id *pci_match_device(struct pci_driver *drv, } spin_unlock(&drv->dynids.lock); - if (!found_id) - found_id = pci_match_id(drv->id_table, dev); + if (found_id) + return found_id; - /* driver_override will always match, send a dummy id */ - if (!found_id && dev->driver_override) - found_id = &pci_device_id_any; + for (ids = drv->id_table; (found_id = pci_match_id(ids, dev)); + ids = found_id + 1) { + /* + * The match table is split based on driver_override. + * In case override_only was set, enforce driver_override + * matching. + */ + if (found_id->override_only) { + if (dev->driver_override) + return found_id; + } else { + return found_id; + } + } - return found_id; + /* driver_override will always match, send a dummy id */ + if (dev->driver_override) + return &pci_device_id_any; + return NULL; } /** diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 8e291cfdaf06..2e3ba6d9ece0 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -34,12 +34,14 @@ typedef unsigned long kernel_ulong_t; * Best practice is to use driver_data as an index * into a static list of equivalent device types, * instead of using it as a pointer. + * @override_only: Match only when dev->driver_override is this driver. */ struct pci_device_id { __u32 vendor, device; /* Vendor and device ID or PCI_ANY_ID*/ __u32 subvendor, subdevice; /* Subsystem ID's or PCI_ANY_ID */ __u32 class, class_mask; /* (class,subclass,prog-if) triplet */ kernel_ulong_t driver_data; /* Data private to the driver */ + __u32 override_only; }; diff --git a/include/linux/pci.h b/include/linux/pci.h index 540b377ca8f6..0506b1a8c921 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -901,6 +901,21 @@ struct pci_driver { .vendor = (vend), .device = (dev), \ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID +/** + * PCI_DEVICE_DRIVER_OVERRIDE - macro used to describe a PCI device with + * override_only flags. + * @vend: the 16 bit PCI Vendor ID + * @dev: the 16 bit PCI Device ID + * @driver_override: the 32 bit PCI Device override_only + * + * This macro is used to create a struct pci_device_id that matches only a + * driver_override device. The subvendor and subdevice fields will be set to + * PCI_ANY_ID. + */ +#define PCI_DEVICE_DRIVER_OVERRIDE(vend, dev, driver_override) \ + .vendor = (vend), .device = (dev), .subvendor = PCI_ANY_ID, \ + .subdevice = PCI_ANY_ID, .override_only = (driver_override) + /** * PCI_DEVICE_SUB - macro used to describe a specific PCI device with subsystem * @vend: the 16 bit PCI Vendor ID -- cgit v1.2.3 From cc6711b0bf36de068b10490198d05ac168377989 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 26 Aug 2021 13:39:09 +0300 Subject: PCI / VFIO: Add 'override_only' support for VFIO PCI sub system Expose an 'override_only' helper macro (i.e. PCI_DRIVER_OVERRIDE_DEVICE_VFIO) for VFIO PCI sub system and add the required code to prefix its matching entries with "vfio_" in modules.alias file. It allows VFIO device drivers to include match entries in the modules.alias file produced by kbuild that are not used for normal driver autoprobing and module autoloading. Drivers using these match entries can be connected to the PCI device manually, by userspace, using the existing driver_override sysfs. For example the resulting modules.alias may have: alias pci:v000015B3d00001021sv*sd*bc*sc*i* mlx5_core alias vfio_pci:v000015B3d00001021sv*sd*bc*sc*i* mlx5_vfio_pci alias vfio_pci:v*d*sv*sd*bc*sc*i* vfio_pci In this example mlx5_core and mlx5_vfio_pci match to the same PCI device. The kernel will autoload and autobind to mlx5_core but the kernel and udev mechanisms will ignore mlx5_vfio_pci. When userspace wants to change a device to the VFIO subsystem it can implement a generic algorithm: 1) Identify the sysfs path to the device: /sys/devices/pci0000:00/0000:00:01.0/0000:01:00.0 2) Get the modalias string from the kernel: $ cat /sys/bus/pci/devices/0000:01:00.0/modalias pci:v000015B3d00001021sv000015B3sd00000001bc02sc00i00 3) Prefix it with vfio_: vfio_pci:v000015B3d00001021sv000015B3sd00000001bc02sc00i00 4) Search modules.alias for the above string and select the entry that has the fewest *'s: alias vfio_pci:v000015B3d00001021sv*sd*bc*sc*i* mlx5_vfio_pci 5) modprobe the matched module name: $ modprobe mlx5_vfio_pci 6) cat the matched module name to driver_override: echo mlx5_vfio_pci > /sys/bus/pci/devices/0000:01:00.0/driver_override 7) unbind device from original module echo 0000:01:00.0 > /sys/bus/pci/devices/0000:01:00.0/driver/unbind 8) probe PCI drivers (or explicitly bind to mlx5_vfio_pci) echo 0000:01:00.0 > /sys/bus/pci/drivers_probe The algorithm is independent of bus type. In future the other buses with VFIO device drivers, like platform and ACPI, can use this algorithm as well. This patch is the infrastructure to provide the information in the modules.alias to userspace. Convert the only VFIO pci_driver which results in one new line in the modules.alias: alias vfio_pci:v*d*sv*sd*bc*sc*i* vfio_pci Later series introduce additional HW specific VFIO PCI drivers, such as mlx5_vfio_pci. Signed-off-by: Max Gurtovoy Signed-off-by: Jason Gunthorpe Acked-by: Bjorn Helgaas # for pci.h Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20210826103912.128972-11-yishaih@nvidia.com Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci.c | 9 ++++++++- include/linux/mod_devicetable.h | 4 ++++ include/linux/pci.h | 14 ++++++++++++++ scripts/mod/devicetable-offsets.c | 1 + scripts/mod/file2alias.c | 17 +++++++++++++++-- 5 files changed, 42 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 163e560c4495..85fd638a5955 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -178,9 +178,16 @@ static int vfio_pci_sriov_configure(struct pci_dev *pdev, int nr_virtfn) return vfio_pci_core_sriov_configure(pdev, nr_virtfn); } +static const struct pci_device_id vfio_pci_table[] = { + { PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_ANY_ID, PCI_ANY_ID) }, /* match all by default */ + {} +}; + +MODULE_DEVICE_TABLE(pci, vfio_pci_table); + static struct pci_driver vfio_pci_driver = { .name = "vfio-pci", - .id_table = NULL, /* only dynamic ids */ + .id_table = vfio_pci_table, .probe = vfio_pci_probe, .remove = vfio_pci_remove, .sriov_configure = vfio_pci_sriov_configure, diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 2e3ba6d9ece0..ae2e75d15b21 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -16,6 +16,10 @@ typedef unsigned long kernel_ulong_t; #define PCI_ANY_ID (~0) +enum { + PCI_ID_F_VFIO_DRIVER_OVERRIDE = 1, +}; + /** * struct pci_device_id - PCI device ID structure * @vendor: Vendor ID to match (or PCI_ANY_ID) diff --git a/include/linux/pci.h b/include/linux/pci.h index 0506b1a8c921..527a1dfd1d06 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -916,6 +916,20 @@ struct pci_driver { .vendor = (vend), .device = (dev), .subvendor = PCI_ANY_ID, \ .subdevice = PCI_ANY_ID, .override_only = (driver_override) +/** + * PCI_DRIVER_OVERRIDE_DEVICE_VFIO - macro used to describe a VFIO + * "driver_override" PCI device. + * @vend: the 16 bit PCI Vendor ID + * @dev: the 16 bit PCI Device ID + * + * This macro is used to create a struct pci_device_id that matches a + * specific device. The subvendor and subdevice fields will be set to + * PCI_ANY_ID and the driver_override will be set to + * PCI_ID_F_VFIO_DRIVER_OVERRIDE. + */ +#define PCI_DRIVER_OVERRIDE_DEVICE_VFIO(vend, dev) \ + PCI_DEVICE_DRIVER_OVERRIDE(vend, dev, PCI_ID_F_VFIO_DRIVER_OVERRIDE) + /** * PCI_DEVICE_SUB - macro used to describe a specific PCI device with subsystem * @vend: the 16 bit PCI Vendor ID diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index 9bb6c7edccc4..cc3625617a0e 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -42,6 +42,7 @@ int main(void) DEVID_FIELD(pci_device_id, subdevice); DEVID_FIELD(pci_device_id, class); DEVID_FIELD(pci_device_id, class_mask); + DEVID_FIELD(pci_device_id, override_only); DEVID(ccw_device_id); DEVID_FIELD(ccw_device_id, match_flags); diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 7c97fa8e36bc..49aba862073e 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -426,7 +426,7 @@ static int do_ieee1394_entry(const char *filename, return 1; } -/* Looks like: pci:vNdNsvNsdNbcNscNiN. */ +/* Looks like: pci:vNdNsvNsdNbcNscNiN or _pci:vNdNsvNsdNbcNscNiN. */ static int do_pci_entry(const char *filename, void *symval, char *alias) { @@ -440,8 +440,21 @@ static int do_pci_entry(const char *filename, DEF_FIELD(symval, pci_device_id, subdevice); DEF_FIELD(symval, pci_device_id, class); DEF_FIELD(symval, pci_device_id, class_mask); + DEF_FIELD(symval, pci_device_id, override_only); + + switch (override_only) { + case 0: + strcpy(alias, "pci:"); + break; + case PCI_ID_F_VFIO_DRIVER_OVERRIDE: + strcpy(alias, "vfio_pci:"); + break; + default: + warn("Unknown PCI driver_override alias %08X\n", + override_only); + return 0; + } - strcpy(alias, "pci:"); ADD(alias, "v", vendor != PCI_ANY_ID, vendor); ADD(alias, "d", device != PCI_ANY_ID, device); ADD(alias, "sv", subvendor != PCI_ANY_ID, subvendor); -- cgit v1.2.3 From 7fa005caa35ed92563b9e9d88d319b2623763a77 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 26 Aug 2021 13:39:12 +0300 Subject: vfio/pci: Introduce vfio_pci_core.ko Now that vfio_pci has been split into two source modules, one focusing on the "struct pci_driver" (vfio_pci.c) and a toolbox library of code (vfio_pci_core.c), complete the split and move them into two different kernel modules. As before vfio_pci.ko continues to present the same interface under sysfs and this change will have no functional impact. Splitting into another module and adding exports allows creating new HW specific VFIO PCI drivers that can implement device specific functionality, such as VFIO migration interfaces or specialized device requirements. Signed-off-by: Max Gurtovoy Signed-off-by: Jason Gunthorpe Reviewed-by: Christoph Hellwig Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20210826103912.128972-14-yishaih@nvidia.com Signed-off-by: Alex Williamson --- MAINTAINERS | 1 + drivers/vfio/pci/Kconfig | 33 ++--- drivers/vfio/pci/Makefile | 8 +- drivers/vfio/pci/vfio_pci.c | 14 +-- drivers/vfio/pci/vfio_pci_config.c | 2 +- drivers/vfio/pci/vfio_pci_core.c | 39 +++++- drivers/vfio/pci/vfio_pci_core.h | 241 ------------------------------------- drivers/vfio/pci/vfio_pci_igd.c | 2 +- drivers/vfio/pci/vfio_pci_intrs.c | 2 +- drivers/vfio/pci/vfio_pci_rdwr.c | 2 +- drivers/vfio/pci/vfio_pci_zdev.c | 2 +- include/linux/vfio_pci_core.h | 239 ++++++++++++++++++++++++++++++++++++ 12 files changed, 304 insertions(+), 281 deletions(-) delete mode 100644 drivers/vfio/pci/vfio_pci_core.h create mode 100644 include/linux/vfio_pci_core.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index c9467d2839f5..7f0fcaa8ee67 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19466,6 +19466,7 @@ T: git git://github.com/awilliam/linux-vfio.git F: Documentation/driver-api/vfio.rst F: drivers/vfio/ F: include/linux/vfio.h +F: include/linux/vfio_pci_core.h F: include/uapi/linux/vfio.h VFIO FSL-MC DRIVER diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index afdab7d71e98..860424ccda1b 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -1,19 +1,28 @@ # SPDX-License-Identifier: GPL-2.0-only -config VFIO_PCI - tristate "VFIO support for PCI devices" - depends on PCI - depends on MMU +if PCI && MMU +config VFIO_PCI_CORE + tristate select VFIO_VIRQFD select IRQ_BYPASS_MANAGER + +config VFIO_PCI_MMAP + def_bool y if !S390 + +config VFIO_PCI_INTX + def_bool y if !S390 + +config VFIO_PCI + tristate "Generic VFIO support for any PCI device" + select VFIO_PCI_CORE help - Support for the PCI VFIO bus driver. This is required to make - use of PCI drivers using the VFIO framework. + Support for the generic PCI VFIO bus driver which can connect any + PCI device to the VFIO framework. If you don't know what to do here, say N. if VFIO_PCI config VFIO_PCI_VGA - bool "VFIO PCI support for VGA devices" + bool "Generic VFIO PCI support for VGA devices" depends on X86 && VGA_ARB help Support for VGA extension to VFIO PCI. This exposes an additional @@ -22,14 +31,8 @@ config VFIO_PCI_VGA If you don't know what to do here, say N. -config VFIO_PCI_MMAP - def_bool y if !S390 - -config VFIO_PCI_INTX - def_bool y if !S390 - config VFIO_PCI_IGD - bool "VFIO PCI extensions for Intel graphics (GVT-d)" + bool "Generic VFIO PCI extensions for Intel graphics (GVT-d)" depends on X86 default y help @@ -39,5 +42,5 @@ config VFIO_PCI_IGD and LPC bridge config space. To enable Intel IGD assignment through vfio-pci, say Y. - +endif endif diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 8aa517b4b671..349d68d242b4 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -1,7 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only -vfio-pci-y := vfio_pci.o vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o -vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o -vfio-pci-$(CONFIG_S390) += vfio_pci_zdev.o +vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o +vfio-pci-core-$(CONFIG_S390) += vfio_pci_zdev.o +obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o +vfio-pci-y := vfio_pci.o +vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 85fd638a5955..a5ce92beb655 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -25,7 +25,7 @@ #include #include -#include "vfio_pci_core.h" +#include #define DRIVER_AUTHOR "Alex Williamson " #define DRIVER_DESC "VFIO PCI - User Level meta-driver" @@ -153,6 +153,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = vfio_pci_core_register_device(vdev); if (ret) goto out_free; + dev_set_drvdata(&pdev->dev, vdev); return 0; out_free: @@ -246,14 +247,10 @@ static int __init vfio_pci_init(void) vfio_pci_core_set_params(nointxmask, is_disable_vga, disable_idle_d3); - ret = vfio_pci_core_init(); - if (ret) - return ret; - /* Register and scan for devices */ ret = pci_register_driver(&vfio_pci_driver); if (ret) - goto out; + return ret; vfio_pci_fill_ids(); @@ -261,17 +258,12 @@ static int __init vfio_pci_init(void) pr_warn("device denylist disabled.\n"); return 0; - -out: - vfio_pci_core_cleanup(); - return ret; } module_init(vfio_pci_init); static void __exit vfio_pci_cleanup(void) { pci_unregister_driver(&vfio_pci_driver); - vfio_pci_core_cleanup(); } module_exit(vfio_pci_cleanup); diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 1f034f768a27..6e58b4bf7a60 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -26,7 +26,7 @@ #include #include -#include "vfio_pci_core.h" +#include /* Fake capability ID for standard config space */ #define PCI_CAP_ID_BASIC 0 diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 65eafaafb2e0..675616e08897 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -8,6 +8,8 @@ * Author: Tom Lyon, pugs@cisco.com */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include #include #include @@ -25,7 +27,10 @@ #include #include -#include "vfio_pci_core.h" +#include + +#define DRIVER_AUTHOR "Alex Williamson " +#define DRIVER_DESC "core driver for VFIO based PCI devices" static bool nointxmask; static bool disable_vga; @@ -306,6 +311,7 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) return 0; } +EXPORT_SYMBOL_GPL(vfio_pci_core_enable); void vfio_pci_core_disable(struct vfio_pci_core_device *vdev) { @@ -403,6 +409,7 @@ out: if (!vfio_pci_dev_set_try_reset(vdev->vdev.dev_set) && !disable_idle_d3) vfio_pci_set_power_state(vdev, PCI_D3hot); } +EXPORT_SYMBOL_GPL(vfio_pci_core_disable); static struct vfio_pci_core_device *get_pf_vdev(struct vfio_pci_core_device *vdev) { @@ -459,6 +466,7 @@ void vfio_pci_core_close_device(struct vfio_device *core_vdev) } mutex_unlock(&vdev->igate); } +EXPORT_SYMBOL_GPL(vfio_pci_core_close_device); void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev) { @@ -466,6 +474,7 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev) vfio_spapr_pci_eeh_open(vdev->pdev); vfio_pci_vf_token_user_add(vdev, 1); } +EXPORT_SYMBOL_GPL(vfio_pci_core_finish_enable); static int vfio_pci_get_irq_count(struct vfio_pci_core_device *vdev, int irq_type) { @@ -624,6 +633,7 @@ int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev, return 0; } +EXPORT_SYMBOL_GPL(vfio_pci_register_dev_region); long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, unsigned long arg) @@ -1168,6 +1178,7 @@ hot_reset_release: return -ENOTTY; } +EXPORT_SYMBOL_GPL(vfio_pci_core_ioctl); static ssize_t vfio_pci_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite) @@ -1211,6 +1222,7 @@ ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, return vfio_pci_rw(vdev, buf, count, ppos, false); } +EXPORT_SYMBOL_GPL(vfio_pci_core_read); ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, size_t count, loff_t *ppos) @@ -1223,6 +1235,7 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu return vfio_pci_rw(vdev, (char __user *)buf, count, ppos, true); } +EXPORT_SYMBOL_GPL(vfio_pci_core_write); /* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */ static int vfio_pci_zap_and_vma_lock(struct vfio_pci_core_device *vdev, bool try) @@ -1501,6 +1514,7 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma return 0; } +EXPORT_SYMBOL_GPL(vfio_pci_core_mmap); void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count) { @@ -1523,6 +1537,7 @@ void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count) mutex_unlock(&vdev->igate); } +EXPORT_SYMBOL_GPL(vfio_pci_core_request); static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, bool vf_token, uuid_t *uuid) @@ -1667,6 +1682,7 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf) return 1; /* Match */ } +EXPORT_SYMBOL_GPL(vfio_pci_core_match); static int vfio_pci_bus_notifier(struct notifier_block *nb, unsigned long action, void *data) @@ -1775,6 +1791,7 @@ void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, INIT_LIST_HEAD(&vdev->vma_list); init_rwsem(&vdev->memory_lock); } +EXPORT_SYMBOL_GPL(vfio_pci_core_init_device); void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev) { @@ -1785,6 +1802,7 @@ void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev) kfree(vdev->region); kfree(vdev->pm_save); } +EXPORT_SYMBOL_GPL(vfio_pci_core_uninit_device); int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) { @@ -1852,7 +1870,6 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) ret = vfio_register_group_dev(&vdev->vdev); if (ret) goto out_power; - dev_set_drvdata(&pdev->dev, vdev); return 0; out_power: @@ -1864,6 +1881,7 @@ out_group_put: vfio_iommu_group_put(group, &pdev->dev); return ret; } +EXPORT_SYMBOL_GPL(vfio_pci_core_register_device); void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev) { @@ -1881,6 +1899,7 @@ void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev) if (!disable_idle_d3) vfio_pci_set_power_state(vdev, PCI_D0); } +EXPORT_SYMBOL_GPL(vfio_pci_core_unregister_device); static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev, pci_channel_state_t state) @@ -1924,10 +1943,12 @@ int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn) return ret < 0 ? ret : nr_virtfn; } +EXPORT_SYMBOL_GPL(vfio_pci_core_sriov_configure); const struct pci_error_handlers vfio_pci_core_err_handlers = { .error_detected = vfio_pci_aer_err_detected, }; +EXPORT_SYMBOL_GPL(vfio_pci_core_err_handlers); static bool vfio_dev_in_groups(struct vfio_pci_core_device *vdev, struct vfio_pci_group_info *groups) @@ -2116,16 +2137,22 @@ void vfio_pci_core_set_params(bool is_nointxmask, bool is_disable_vga, disable_vga = is_disable_vga; disable_idle_d3 = is_disable_idle_d3; } +EXPORT_SYMBOL_GPL(vfio_pci_core_set_params); -/* This will become the __exit function of vfio_pci_core.ko */ -void vfio_pci_core_cleanup(void) +static void vfio_pci_core_cleanup(void) { vfio_pci_uninit_perm_bits(); } -/* This will become the __init function of vfio_pci_core.ko */ -int __init vfio_pci_core_init(void) +static int __init vfio_pci_core_init(void) { /* Allocate shared config space permission data used by all devices */ return vfio_pci_init_perm_bits(); } + +module_init(vfio_pci_core_init); +module_exit(vfio_pci_core_cleanup); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR(DRIVER_AUTHOR); +MODULE_DESCRIPTION(DRIVER_DESC); diff --git a/drivers/vfio/pci/vfio_pci_core.h b/drivers/vfio/pci/vfio_pci_core.h deleted file mode 100644 index 7a2da1e14de3..000000000000 --- a/drivers/vfio/pci/vfio_pci_core.h +++ /dev/null @@ -1,241 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 Red Hat, Inc. All rights reserved. - * Author: Alex Williamson - * - * Derived from original vfio: - * Copyright 2010 Cisco Systems, Inc. All rights reserved. - * Author: Tom Lyon, pugs@cisco.com - */ - -#include -#include -#include -#include -#include -#include -#include - -#ifndef VFIO_PCI_CORE_H -#define VFIO_PCI_CORE_H - -#define VFIO_PCI_OFFSET_SHIFT 40 - -#define VFIO_PCI_OFFSET_TO_INDEX(off) (off >> VFIO_PCI_OFFSET_SHIFT) -#define VFIO_PCI_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_PCI_OFFSET_SHIFT) -#define VFIO_PCI_OFFSET_MASK (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1) - -/* Special capability IDs predefined access */ -#define PCI_CAP_ID_INVALID 0xFF /* default raw access */ -#define PCI_CAP_ID_INVALID_VIRT 0xFE /* default virt access */ - -/* Cap maximum number of ioeventfds per device (arbitrary) */ -#define VFIO_PCI_IOEVENTFD_MAX 1000 - -struct vfio_pci_ioeventfd { - struct list_head next; - struct vfio_pci_core_device *vdev; - struct virqfd *virqfd; - void __iomem *addr; - uint64_t data; - loff_t pos; - int bar; - int count; - bool test_mem; -}; - -struct vfio_pci_irq_ctx { - struct eventfd_ctx *trigger; - struct virqfd *unmask; - struct virqfd *mask; - char *name; - bool masked; - struct irq_bypass_producer producer; -}; - -struct vfio_pci_core_device; -struct vfio_pci_region; - -struct vfio_pci_regops { - ssize_t (*rw)(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); - void (*release)(struct vfio_pci_core_device *vdev, - struct vfio_pci_region *region); - int (*mmap)(struct vfio_pci_core_device *vdev, - struct vfio_pci_region *region, - struct vm_area_struct *vma); - int (*add_capability)(struct vfio_pci_core_device *vdev, - struct vfio_pci_region *region, - struct vfio_info_cap *caps); -}; - -struct vfio_pci_region { - u32 type; - u32 subtype; - const struct vfio_pci_regops *ops; - void *data; - size_t size; - u32 flags; -}; - -struct vfio_pci_dummy_resource { - struct resource resource; - int index; - struct list_head res_next; -}; - -struct vfio_pci_vf_token { - struct mutex lock; - uuid_t uuid; - int users; -}; - -struct vfio_pci_mmap_vma { - struct vm_area_struct *vma; - struct list_head vma_next; -}; - -struct vfio_pci_core_device { - struct vfio_device vdev; - struct pci_dev *pdev; - void __iomem *barmap[PCI_STD_NUM_BARS]; - bool bar_mmap_supported[PCI_STD_NUM_BARS]; - u8 *pci_config_map; - u8 *vconfig; - struct perm_bits *msi_perm; - spinlock_t irqlock; - struct mutex igate; - struct vfio_pci_irq_ctx *ctx; - int num_ctx; - int irq_type; - int num_regions; - struct vfio_pci_region *region; - u8 msi_qmax; - u8 msix_bar; - u16 msix_size; - u32 msix_offset; - u32 rbar[7]; - bool pci_2_3; - bool virq_disabled; - bool reset_works; - bool extended_caps; - bool bardirty; - bool has_vga; - bool needs_reset; - bool nointx; - bool needs_pm_restore; - struct pci_saved_state *pci_saved_state; - struct pci_saved_state *pm_save; - int ioeventfds_nr; - struct eventfd_ctx *err_trigger; - struct eventfd_ctx *req_trigger; - struct list_head dummy_resources_list; - struct mutex ioeventfds_lock; - struct list_head ioeventfds_list; - struct vfio_pci_vf_token *vf_token; - struct notifier_block nb; - struct mutex vma_lock; - struct list_head vma_list; - struct rw_semaphore memory_lock; -}; - -#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) -#define is_msi(vdev) (vdev->irq_type == VFIO_PCI_MSI_IRQ_INDEX) -#define is_msix(vdev) (vdev->irq_type == VFIO_PCI_MSIX_IRQ_INDEX) -#define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev))) -#define irq_is(vdev, type) (vdev->irq_type == type) - -extern void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev); -extern void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev); - -extern int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, - uint32_t flags, unsigned index, - unsigned start, unsigned count, void *data); - -extern ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, - char __user *buf, size_t count, - loff_t *ppos, bool iswrite); - -extern ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); - -extern ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); - -extern long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, - uint64_t data, int count, int fd); - -extern int vfio_pci_init_perm_bits(void); -extern void vfio_pci_uninit_perm_bits(void); - -extern int vfio_config_init(struct vfio_pci_core_device *vdev); -extern void vfio_config_free(struct vfio_pci_core_device *vdev); - -extern int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev, - unsigned int type, unsigned int subtype, - const struct vfio_pci_regops *ops, - size_t size, u32 flags, void *data); - -extern int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, - pci_power_t state); - -extern bool __vfio_pci_memory_enabled(struct vfio_pci_core_device *vdev); -extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device - *vdev); -extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev); -extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, - u16 cmd); - -#ifdef CONFIG_VFIO_PCI_IGD -extern int vfio_pci_igd_init(struct vfio_pci_core_device *vdev); -#else -static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev) -{ - return -ENODEV; -} -#endif - -#ifdef CONFIG_S390 -extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, - struct vfio_info_cap *caps); -#else -static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, - struct vfio_info_cap *caps) -{ - return -ENODEV; -} -#endif - -/* Will be exported for vfio pci drivers usage */ -void vfio_pci_core_cleanup(void); -int vfio_pci_core_init(void); -void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga, - bool is_disable_idle_d3); -void vfio_pci_core_close_device(struct vfio_device *core_vdev); -void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, - struct pci_dev *pdev, - const struct vfio_device_ops *vfio_pci_ops); -int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev); -void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev); -void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev); -int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn); -extern const struct pci_error_handlers vfio_pci_core_err_handlers; -long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, - unsigned long arg); -ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, - size_t count, loff_t *ppos); -ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, - size_t count, loff_t *ppos); -int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma); -void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count); -int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); -int vfio_pci_core_enable(struct vfio_pci_core_device *vdev); -void vfio_pci_core_disable(struct vfio_pci_core_device *vdev); -void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); - -static inline bool vfio_pci_is_vga(struct pci_dev *pdev) -{ - return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA; -} - -#endif /* VFIO_PCI_CORE_H */ diff --git a/drivers/vfio/pci/vfio_pci_igd.c b/drivers/vfio/pci/vfio_pci_igd.c index a324ca7e6b5a..7ca4109bba48 100644 --- a/drivers/vfio/pci/vfio_pci_igd.c +++ b/drivers/vfio/pci/vfio_pci_igd.c @@ -15,7 +15,7 @@ #include #include -#include "vfio_pci_core.h" +#include #define OPREGION_SIGNATURE "IntelGraphicsMem" #define OPREGION_SIZE (8 * 1024) diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 945ddbdf4d11..6069a11fb51a 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -20,7 +20,7 @@ #include #include -#include "vfio_pci_core.h" +#include /* * INTx diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 8fff4689dd44..57d3b2cbbd8e 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -17,7 +17,7 @@ #include #include -#include "vfio_pci_core.h" +#include #ifdef __LITTLE_ENDIAN #define vfio_ioread64 ioread64 diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c index 2ffbdc11f089..fe4def9ffffb 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -19,7 +19,7 @@ #include #include -#include "vfio_pci_core.h" +#include /* * Add the Base PCI Function information to the device info region. diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h new file mode 100644 index 000000000000..ef9a44b6cf5d --- /dev/null +++ b/include/linux/vfio_pci_core.h @@ -0,0 +1,239 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Red Hat, Inc. All rights reserved. + * Author: Alex Williamson + * + * Derived from original vfio: + * Copyright 2010 Cisco Systems, Inc. All rights reserved. + * Author: Tom Lyon, pugs@cisco.com + */ + +#include +#include +#include +#include +#include +#include +#include + +#ifndef VFIO_PCI_CORE_H +#define VFIO_PCI_CORE_H + +#define VFIO_PCI_OFFSET_SHIFT 40 + +#define VFIO_PCI_OFFSET_TO_INDEX(off) (off >> VFIO_PCI_OFFSET_SHIFT) +#define VFIO_PCI_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_PCI_OFFSET_SHIFT) +#define VFIO_PCI_OFFSET_MASK (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1) + +/* Special capability IDs predefined access */ +#define PCI_CAP_ID_INVALID 0xFF /* default raw access */ +#define PCI_CAP_ID_INVALID_VIRT 0xFE /* default virt access */ + +/* Cap maximum number of ioeventfds per device (arbitrary) */ +#define VFIO_PCI_IOEVENTFD_MAX 1000 + +struct vfio_pci_ioeventfd { + struct list_head next; + struct vfio_pci_core_device *vdev; + struct virqfd *virqfd; + void __iomem *addr; + uint64_t data; + loff_t pos; + int bar; + int count; + bool test_mem; +}; + +struct vfio_pci_irq_ctx { + struct eventfd_ctx *trigger; + struct virqfd *unmask; + struct virqfd *mask; + char *name; + bool masked; + struct irq_bypass_producer producer; +}; + +struct vfio_pci_core_device; +struct vfio_pci_region; + +struct vfio_pci_regops { + ssize_t (*rw)(struct vfio_pci_core_device *vdev, char __user *buf, + size_t count, loff_t *ppos, bool iswrite); + void (*release)(struct vfio_pci_core_device *vdev, + struct vfio_pci_region *region); + int (*mmap)(struct vfio_pci_core_device *vdev, + struct vfio_pci_region *region, + struct vm_area_struct *vma); + int (*add_capability)(struct vfio_pci_core_device *vdev, + struct vfio_pci_region *region, + struct vfio_info_cap *caps); +}; + +struct vfio_pci_region { + u32 type; + u32 subtype; + const struct vfio_pci_regops *ops; + void *data; + size_t size; + u32 flags; +}; + +struct vfio_pci_dummy_resource { + struct resource resource; + int index; + struct list_head res_next; +}; + +struct vfio_pci_vf_token { + struct mutex lock; + uuid_t uuid; + int users; +}; + +struct vfio_pci_mmap_vma { + struct vm_area_struct *vma; + struct list_head vma_next; +}; + +struct vfio_pci_core_device { + struct vfio_device vdev; + struct pci_dev *pdev; + void __iomem *barmap[PCI_STD_NUM_BARS]; + bool bar_mmap_supported[PCI_STD_NUM_BARS]; + u8 *pci_config_map; + u8 *vconfig; + struct perm_bits *msi_perm; + spinlock_t irqlock; + struct mutex igate; + struct vfio_pci_irq_ctx *ctx; + int num_ctx; + int irq_type; + int num_regions; + struct vfio_pci_region *region; + u8 msi_qmax; + u8 msix_bar; + u16 msix_size; + u32 msix_offset; + u32 rbar[7]; + bool pci_2_3; + bool virq_disabled; + bool reset_works; + bool extended_caps; + bool bardirty; + bool has_vga; + bool needs_reset; + bool nointx; + bool needs_pm_restore; + struct pci_saved_state *pci_saved_state; + struct pci_saved_state *pm_save; + int ioeventfds_nr; + struct eventfd_ctx *err_trigger; + struct eventfd_ctx *req_trigger; + struct list_head dummy_resources_list; + struct mutex ioeventfds_lock; + struct list_head ioeventfds_list; + struct vfio_pci_vf_token *vf_token; + struct notifier_block nb; + struct mutex vma_lock; + struct list_head vma_list; + struct rw_semaphore memory_lock; +}; + +#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) +#define is_msi(vdev) (vdev->irq_type == VFIO_PCI_MSI_IRQ_INDEX) +#define is_msix(vdev) (vdev->irq_type == VFIO_PCI_MSIX_IRQ_INDEX) +#define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev))) +#define irq_is(vdev, type) (vdev->irq_type == type) + +extern void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev); +extern void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev); + +extern int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, + uint32_t flags, unsigned index, + unsigned start, unsigned count, void *data); + +extern ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, + char __user *buf, size_t count, + loff_t *ppos, bool iswrite); + +extern ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, + size_t count, loff_t *ppos, bool iswrite); + +extern ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, + size_t count, loff_t *ppos, bool iswrite); + +extern long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, + uint64_t data, int count, int fd); + +extern int vfio_pci_init_perm_bits(void); +extern void vfio_pci_uninit_perm_bits(void); + +extern int vfio_config_init(struct vfio_pci_core_device *vdev); +extern void vfio_config_free(struct vfio_pci_core_device *vdev); + +extern int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev, + unsigned int type, unsigned int subtype, + const struct vfio_pci_regops *ops, + size_t size, u32 flags, void *data); + +extern int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, + pci_power_t state); + +extern bool __vfio_pci_memory_enabled(struct vfio_pci_core_device *vdev); +extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device + *vdev); +extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev); +extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, + u16 cmd); + +#ifdef CONFIG_VFIO_PCI_IGD +extern int vfio_pci_igd_init(struct vfio_pci_core_device *vdev); +#else +static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev) +{ + return -ENODEV; +} +#endif + +#ifdef CONFIG_S390 +extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, + struct vfio_info_cap *caps); +#else +static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, + struct vfio_info_cap *caps) +{ + return -ENODEV; +} +#endif + +/* Will be exported for vfio pci drivers usage */ +void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga, + bool is_disable_idle_d3); +void vfio_pci_core_close_device(struct vfio_device *core_vdev); +void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, + struct pci_dev *pdev, + const struct vfio_device_ops *vfio_pci_ops); +int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev); +void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev); +void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev); +int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn); +extern const struct pci_error_handlers vfio_pci_core_err_handlers; +long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, + unsigned long arg); +ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, + size_t count, loff_t *ppos); +ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, + size_t count, loff_t *ppos); +int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma); +void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count); +int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); +int vfio_pci_core_enable(struct vfio_pci_core_device *vdev); +void vfio_pci_core_disable(struct vfio_pci_core_device *vdev); +void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); + +static inline bool vfio_pci_is_vga(struct pci_dev *pdev) +{ + return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA; +} + +#endif /* VFIO_PCI_CORE_H */ -- cgit v1.2.3 From 9ebc2758d0bbed951511d1709be0717178ec2660 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Thu, 26 Aug 2021 20:28:16 +0300 Subject: Revert "net: really fix the build..." This reverts commit ce78ffa3ef1681065ba451cfd545da6126f5ca88. Wren and Nicolas reported that ath11k was failing to initialise QCA6390 Wi-Fi 6 device with error: qcom_mhi_qrtr: probe of mhi0_IPCR failed with error -22 Commit ce78ffa3ef16 ("net: really fix the build..."), introduced in v5.14-rc5, caused this regression in qrtr. Most likely all ath11k devices are broken, but I only tested QCA6390. Let's revert the broken commit so that ath11k works again. Reported-by: Wren Turkal Reported-by: Nicolas Schichan Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20210826172816.24478-1-kvalo@codeaurora.org Signed-off-by: Jakub Kicinski --- drivers/bus/mhi/core/internal.h | 2 +- drivers/bus/mhi/core/main.c | 9 +++------ drivers/net/mhi/net.c | 2 +- drivers/net/wwan/mhi_wwan_ctrl.c | 2 +- include/linux/mhi.h | 7 +------ net/qrtr/mhi.c | 16 +--------------- 6 files changed, 8 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h index bc239a11aa69..5b9ea66b92dc 100644 --- a/drivers/bus/mhi/core/internal.h +++ b/drivers/bus/mhi/core/internal.h @@ -682,7 +682,7 @@ void mhi_rddm_prepare(struct mhi_controller *mhi_cntrl, struct image_info *img_info); void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl); int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan, unsigned int flags); + struct mhi_chan *mhi_chan); int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan); void mhi_deinit_chan_ctxt(struct mhi_controller *mhi_cntrl, diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index 84448233f64c..fc9196f11cb7 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -1430,7 +1430,7 @@ exit_unprepare_channel: } int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan, unsigned int flags) + struct mhi_chan *mhi_chan) { int ret = 0; struct device *dev = &mhi_chan->mhi_dev->dev; @@ -1455,9 +1455,6 @@ int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, if (ret) goto error_pm_state; - if (mhi_chan->dir == DMA_FROM_DEVICE) - mhi_chan->pre_alloc = !!(flags & MHI_CH_INBOUND_ALLOC_BUFS); - /* Pre-allocate buffer for xfer ring */ if (mhi_chan->pre_alloc) { int nr_el = get_nr_avail_ring_elements(mhi_cntrl, @@ -1613,7 +1610,7 @@ void mhi_reset_chan(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan) } /* Move channel to start state */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags) +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) { int ret, dir; struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl; @@ -1624,7 +1621,7 @@ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags) if (!mhi_chan) continue; - ret = mhi_prepare_channel(mhi_cntrl, mhi_chan, flags); + ret = mhi_prepare_channel(mhi_cntrl, mhi_chan); if (ret) goto error_open_chan; } diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index 11be6bcdd551..e60e38c1f09d 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -335,7 +335,7 @@ static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id, u64_stats_init(&mhi_netdev->stats.tx_syncp); /* Start MHI channels */ - err = mhi_prepare_for_transfer(mhi_dev, 0); + err = mhi_prepare_for_transfer(mhi_dev); if (err) goto out_err; diff --git a/drivers/net/wwan/mhi_wwan_ctrl.c b/drivers/net/wwan/mhi_wwan_ctrl.c index d0a98f34c54d..e4d0f696687f 100644 --- a/drivers/net/wwan/mhi_wwan_ctrl.c +++ b/drivers/net/wwan/mhi_wwan_ctrl.c @@ -110,7 +110,7 @@ static int mhi_wwan_ctrl_start(struct wwan_port *port) int ret; /* Start mhi device's channel(s) */ - ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev, 0); + ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev); if (ret) return ret; diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 5e08468854db..944aa3aa3035 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -719,13 +719,8 @@ void mhi_device_put(struct mhi_device *mhi_dev); * host and device execution environments match and * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels - * @flags: MHI channel flags */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, - unsigned int flags); - -/* Automatically allocate and queue inbound buffers */ -#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0) +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c index 1dc955ca57d3..fa611678af05 100644 --- a/net/qrtr/mhi.c +++ b/net/qrtr/mhi.c @@ -15,7 +15,6 @@ struct qrtr_mhi_dev { struct qrtr_endpoint ep; struct mhi_device *mhi_dev; struct device *dev; - struct completion ready; }; /* From MHI to QRTR */ @@ -51,10 +50,6 @@ static int qcom_mhi_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb) struct qrtr_mhi_dev *qdev = container_of(ep, struct qrtr_mhi_dev, ep); int rc; - rc = wait_for_completion_interruptible(&qdev->ready); - if (rc) - goto free_skb; - if (skb->sk) sock_hold(skb->sk); @@ -84,7 +79,7 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, int rc; /* start channels */ - rc = mhi_prepare_for_transfer(mhi_dev, 0); + rc = mhi_prepare_for_transfer(mhi_dev); if (rc) return rc; @@ -101,15 +96,6 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, if (rc) return rc; - /* start channels */ - rc = mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS); - if (rc) { - qrtr_endpoint_unregister(&qdev->ep); - dev_set_drvdata(&mhi_dev->dev, NULL); - return rc; - } - - complete_all(&qdev->ready); dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n"); return 0; -- cgit v1.2.3 From b3636a3a2c51715736d3ec45f635ed03191962ce Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sat, 31 Jul 2021 22:50:32 +0300 Subject: PM: runtime: add devm_pm_runtime_enable helper A typical code pattern for pm_runtime_enable() call is to call it in the _probe function and to call pm_runtime_disable() both from _probe error path and from _remove function. For some drivers the whole remove function would consist of the call to pm_remove_disable(). Add helper function to replace this bolierplate piece of code. Calling devm_pm_runtime_enable() removes the need for calling pm_runtime_disable() both in the probe()'s error path and in the remove() function. Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20210731195034.979084-2-dmitry.baryshkov@linaro.org Acked-by: Rafael J. Wysocki Signed-off-by: Stephen Boyd --- drivers/base/power/runtime.c | 17 +++++++++++++++++ include/linux/pm_runtime.h | 4 ++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 8a66eaf731e4..ec94049442b9 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1447,6 +1447,23 @@ void pm_runtime_enable(struct device *dev) } EXPORT_SYMBOL_GPL(pm_runtime_enable); +static void pm_runtime_disable_action(void *data) +{ + pm_runtime_disable(data); +} + +/** + * devm_pm_runtime_enable - devres-enabled version of pm_runtime_enable. + * @dev: Device to handle. + */ +int devm_pm_runtime_enable(struct device *dev) +{ + pm_runtime_enable(dev); + + return devm_add_action_or_reset(dev, pm_runtime_disable_action, dev); +} +EXPORT_SYMBOL_GPL(devm_pm_runtime_enable); + /** * pm_runtime_forbid - Block runtime PM of a device. * @dev: Device to handle. diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index aab8b35e9f8a..222da43b7096 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -59,6 +59,8 @@ extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); +extern int devm_pm_runtime_enable(struct device *dev); + /** * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. * @dev: Target device. @@ -253,6 +255,8 @@ static inline void __pm_runtime_disable(struct device *dev, bool c) {} static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} +static inline int devm_pm_runtime_enable(struct device *dev) { return 0; } + static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} -- cgit v1.2.3 From a649136b17af6361355874a10e9219390c266a2c Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sat, 31 Jul 2021 22:50:33 +0300 Subject: PM: runtime: add devm_pm_clk_create helper A typical code pattern for pm_clk_create() call is to call it in the _probe function and to call pm_clk_destroy() both from _probe error path and from _remove function. For some drivers the whole remove function would consist of the call to pm_remove_disable(). Add helper function to replace this bolierplate piece of code. Calling devm_pm_clk_create() removes the need for calling pm_clk_destroy() both in the probe()'s error path and in the remove() function. Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20210731195034.979084-3-dmitry.baryshkov@linaro.org Acked-by: Rafael J. Wysocki Signed-off-by: Stephen Boyd --- drivers/base/power/clock_ops.c | 17 +++++++++++++++++ include/linux/pm_clock.h | 5 +++++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c index 0251f3e6e61d..4110c19c08dc 100644 --- a/drivers/base/power/clock_ops.c +++ b/drivers/base/power/clock_ops.c @@ -519,6 +519,23 @@ void pm_clk_destroy(struct device *dev) } EXPORT_SYMBOL_GPL(pm_clk_destroy); +static void pm_clk_destroy_action(void *data) +{ + pm_clk_destroy(data); +} + +int devm_pm_clk_create(struct device *dev) +{ + int ret; + + ret = pm_clk_create(dev); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, pm_clk_destroy_action, dev); +} +EXPORT_SYMBOL_GPL(devm_pm_clk_create); + /** * pm_clk_suspend - Disable clocks in a device's PM clock list. * @dev: Device to disable the clocks for. diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h index 8ddc7860e131..ada3a0ab10bf 100644 --- a/include/linux/pm_clock.h +++ b/include/linux/pm_clock.h @@ -47,6 +47,7 @@ extern void pm_clk_remove(struct device *dev, const char *con_id); extern void pm_clk_remove_clk(struct device *dev, struct clk *clk); extern int pm_clk_suspend(struct device *dev); extern int pm_clk_resume(struct device *dev); +extern int devm_pm_clk_create(struct device *dev); #else static inline bool pm_clk_no_clocks(struct device *dev) { @@ -83,6 +84,10 @@ static inline void pm_clk_remove(struct device *dev, const char *con_id) static inline void pm_clk_remove_clk(struct device *dev, struct clk *clk) { } +static inline int devm_pm_clk_create(struct device *dev) +{ + return -EINVAL; +} #endif #ifdef CONFIG_HAVE_CLK -- cgit v1.2.3 From 8c09e896cef8d908dd9a20a9f2a5c3fcb9799de3 Mon Sep 17 00:00:00 2001 From: Zhangfei Gao Date: Tue, 13 Jul 2021 10:54:34 +0800 Subject: PCI: Allow PASID on fake PCIe devices without TLP prefixes Some systems, e.g., HiSilicon KunPeng920 and KunPeng930, have devices that appear as PCI but are actually on the AMBA bus. Some of these fake PCI devices support a PASID-like feature and they do have a working PASID capability even though they do not use the PCIe Transport Layer Protocol and do not support TLP prefixes. Add a pasid_no_tlp bit for this "PASID works without TLP prefixes" case and update pci_enable_pasid() so it can enable PASID on these devices. Set this bit for HiSilicon KunPeng920 and KunPeng930. [bhelgaas: squashed, commit log] Suggested-by: Bjorn Helgaas Link: https://lore.kernel.org/r/1626144876-11352-2-git-send-email-zhangfei.gao@linaro.org Link: https://lore.kernel.org/r/1626144876-11352-3-git-send-email-zhangfei.gao@linaro.org Signed-off-by: Zhangfei Gao Signed-off-by: Jean-Philippe Brucker Signed-off-by: Zhou Wang Signed-off-by: Bjorn Helgaas --- drivers/pci/ats.c | 2 +- drivers/pci/quirks.c | 14 ++++++++++++++ include/linux/pci.h | 1 + 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index 6d7d64939f82..c967ad6e2626 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -376,7 +376,7 @@ int pci_enable_pasid(struct pci_dev *pdev, int features) if (WARN_ON(pdev->pasid_enabled)) return -EBUSY; - if (!pdev->eetlp_prefix_path) + if (!pdev->eetlp_prefix_path && !pdev->pasid_no_tlp) return -EINVAL; if (!pasid) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 6d74386eadc2..5d46ac697218 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -1821,6 +1821,20 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7525_MCH, quir DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_HUAWEI, 0x1610, PCI_CLASS_BRIDGE_PCI, 8, quirk_pcie_mch); +static void quirk_huawei_pcie_sva(struct pci_dev *pdev) +{ + if (pdev->revision != 0x21 && pdev->revision != 0x30) + return; + + pdev->pasid_no_tlp = 1; +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa250, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa251, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa255, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa256, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa258, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa259, quirk_huawei_pcie_sva); + /* * It's possible for the MSI to get corrupted if SHPC and ACPI are used * together on certain PXH-based systems. diff --git a/include/linux/pci.h b/include/linux/pci.h index 540b377ca8f6..28165dc5b221 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -388,6 +388,7 @@ struct pci_dev { supported from root to here */ u16 l1ss; /* L1SS Capability pointer */ #endif + unsigned int pasid_no_tlp:1; /* PASID works without TLP Prefix */ unsigned int eetlp_prefix_path:1; /* End-to-End TLP Prefix */ pci_channel_state_t error_state; /* Current connectivity state */ -- cgit v1.2.3 From f657f8eef3ff870552c9fd2839e0061046f44618 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 20 Aug 2021 17:02:04 -0400 Subject: nfs: don't atempt blocking locks on nfs reexports NFS implements blocking locks by blocking inside its lock method. In the reexport case, this blocks the nfs server thread, which could lead to deadlocks since an nfs server thread might be required to unlock the conflicting lock. It also causes a crash, since the nfs server thread assumes it can free the lock when its lm_notify lock callback is called. Ideal would be to make the nfs lock method return without blocking in this case, but for now it works just not to attempt blocking locks. The difference is just that the original client will have to poll (as it does in the v4.0 case) instead of getting a callback when the lock's available. Signed-off-by: J. Bruce Fields Acked-by: Anna Schumaker Signed-off-by: Chuck Lever --- fs/nfs/export.c | 2 +- fs/nfsd/nfs4state.c | 8 ++++++-- include/linux/exportfs.h | 2 ++ 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/export.c b/fs/nfs/export.c index 37a1a88df771..d772c20bbfd1 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -180,5 +180,5 @@ const struct export_operations nfs_export_ops = { .fetch_iversion = nfs_fetch_iversion, .flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK| EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS| - EXPORT_OP_NOATOMIC_ATTR, + EXPORT_OP_NOATOMIC_ATTR|EXPORT_OP_SYNC_LOCKS, }; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 2bedc7839ec5..d0b2041c4d75 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -6835,6 +6835,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_blocked_lock *nbl = NULL; struct file_lock *file_lock = NULL; struct file_lock *conflock = NULL; + struct super_block *sb; __be32 status = 0; int lkflg; int err; @@ -6856,6 +6857,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfsd4_lock: permission denied!\n"); return status; } + sb = cstate->current_fh.fh_dentry->d_sb; if (lock->lk_is_new) { if (nfsd4_has_session(cstate)) @@ -6904,7 +6906,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: - if (nfsd4_has_session(cstate)) + if (nfsd4_has_session(cstate) && + !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS)) fl_flags |= FL_SLEEP; fallthrough; case NFS4_READ_LT: @@ -6916,7 +6919,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fl_type = F_RDLCK; break; case NFS4_WRITEW_LT: - if (nfsd4_has_session(cstate)) + if (nfsd4_has_session(cstate) && + !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS)) fl_flags |= FL_SLEEP; fallthrough; case NFS4_WRITE_LT: diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index fe848901fcc3..3260fe714846 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -221,6 +221,8 @@ struct export_operations { #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ +#define EXPORT_OP_SYNC_LOCKS (0x20) /* Filesystem can't do + asychronous blocking locks */ unsigned long flags; }; -- cgit v1.2.3 From bb0a55bb7148a49e549ee992200860e7a040d3a5 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 20 Aug 2021 17:02:06 -0400 Subject: nfs: don't allow reexport reclaims In the reexport case, nfsd is currently passing along locks with the reclaim bit set. The client sends a new lock request, which is granted if there's currently no conflict--even if it's possible a conflicting lock could have been briefly held in the interim. We don't currently have any way to safely grant reclaim, so for now let's just deny them all. I'm doing this by passing the reclaim bit to nfs and letting it fail the call, with the idea that eventually the client might be able to do something more forgiving here. Signed-off-by: J. Bruce Fields Acked-by: Anna Schumaker Signed-off-by: Chuck Lever --- fs/nfs/file.c | 3 +++ fs/nfsd/nfs4state.c | 3 +++ fs/nfsd/nfsproc.c | 1 + include/linux/errno.h | 1 + include/linux/fs.h | 1 + 5 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 1fef107961bc..7411658f8b05 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -806,6 +806,9 @@ int nfs_lock(struct file *filp, int cmd, struct file_lock *fl) nfs_inc_stats(inode, NFSIOS_VFSLOCK); + if (fl->fl_flags & FL_RECLAIM) + return -ENOGRACE; + /* No mandatory locks over NFS */ if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) goto out_err; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index d0b2041c4d75..1b6a7f48982e 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -6903,6 +6903,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (!locks_in_grace(net) && lock->lk_reclaim) goto out; + if (lock->lk_reclaim) + fl_flags |= FL_RECLAIM; + fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 60d7c59e7935..90fcd6178823 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -881,6 +881,7 @@ nfserrno (int errno) { nfserr_serverfault, -ENFILE }, { nfserr_io, -EUCLEAN }, { nfserr_perm, -ENOKEY }, + { nfserr_no_grace, -ENOGRACE}, }; int i; diff --git a/include/linux/errno.h b/include/linux/errno.h index d73f597a2484..8b0c754bab02 100644 --- a/include/linux/errno.h +++ b/include/linux/errno.h @@ -31,5 +31,6 @@ #define EJUKEBOX 528 /* Request initiated, but will not complete before timeout */ #define EIOCBQUEUED 529 /* iocb queued, will get completion event */ #define ERECALLCONFLICT 530 /* conflict with recalled state */ +#define ENOGRACE 531 /* NFS file lock reclaim refused */ #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..1f5c3dbce1da 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -997,6 +997,7 @@ static inline struct file *get_file(struct file *f) #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ +#define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) -- cgit v1.2.3 From 1b7646014e0d838b06be7288e2dec3262948cc56 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Aug 2021 15:55:05 +0200 Subject: dax: mark dax_get_by_host static And move the code around a bit to avoid a forward declaration. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20210826135510.6293-5-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 109 ++++++++++++++++++++++++++-------------------------- include/linux/dax.h | 5 --- 2 files changed, 54 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 3e6d7e9ee34f..e13fde57c33e 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -17,6 +17,24 @@ #include #include "dax-private.h" +/** + * struct dax_device - anchor object for dax services + * @inode: core vfs + * @cdev: optional character interface for "device dax" + * @host: optional name for lookups where the device path is not available + * @private: dax driver private data + * @flags: state and boolean properties + */ +struct dax_device { + struct hlist_node list; + struct inode inode; + struct cdev cdev; + const char *host; + void *private; + unsigned long flags; + const struct dax_operations *ops; +}; + static dev_t dax_devt; DEFINE_STATIC_SRCU(dax_srcu); static struct vfsmount *dax_mnt; @@ -40,6 +58,42 @@ void dax_read_unlock(int id) } EXPORT_SYMBOL_GPL(dax_read_unlock); +static int dax_host_hash(const char *host) +{ + return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE; +} + +/** + * dax_get_by_host() - temporary lookup mechanism for filesystem-dax + * @host: alternate name for the device registered by a dax driver + */ +static struct dax_device *dax_get_by_host(const char *host) +{ + struct dax_device *dax_dev, *found = NULL; + int hash, id; + + if (!host) + return NULL; + + hash = dax_host_hash(host); + + id = dax_read_lock(); + spin_lock(&dax_host_lock); + hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) { + if (!dax_alive(dax_dev) + || strcmp(host, dax_dev->host) != 0) + continue; + + if (igrab(&dax_dev->inode)) + found = dax_dev; + break; + } + spin_unlock(&dax_host_lock); + dax_read_unlock(id); + + return found; +} + #ifdef CONFIG_BLOCK #include @@ -202,24 +256,6 @@ enum dax_device_flags { DAXDEV_SYNC, }; -/** - * struct dax_device - anchor object for dax services - * @inode: core vfs - * @cdev: optional character interface for "device dax" - * @host: optional name for lookups where the device path is not available - * @private: dax driver private data - * @flags: state and boolean properties - */ -struct dax_device { - struct hlist_node list; - struct inode inode; - struct cdev cdev; - const char *host; - void *private; - unsigned long flags; - const struct dax_operations *ops; -}; - static ssize_t write_cache_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -417,11 +453,6 @@ bool dax_alive(struct dax_device *dax_dev) } EXPORT_SYMBOL_GPL(dax_alive); -static int dax_host_hash(const char *host) -{ - return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE; -} - /* * Note, rcu is not protecting the liveness of dax_dev, rcu is ensuring * that any fault handlers or operations that might have seen @@ -618,38 +649,6 @@ void put_dax(struct dax_device *dax_dev) } EXPORT_SYMBOL_GPL(put_dax); -/** - * dax_get_by_host() - temporary lookup mechanism for filesystem-dax - * @host: alternate name for the device registered by a dax driver - */ -struct dax_device *dax_get_by_host(const char *host) -{ - struct dax_device *dax_dev, *found = NULL; - int hash, id; - - if (!host) - return NULL; - - hash = dax_host_hash(host); - - id = dax_read_lock(); - spin_lock(&dax_host_lock); - hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) { - if (!dax_alive(dax_dev) - || strcmp(host, dax_dev->host) != 0) - continue; - - if (igrab(&dax_dev->inode)) - found = dax_dev; - break; - } - spin_unlock(&dax_host_lock); - dax_read_unlock(id); - - return found; -} -EXPORT_SYMBOL_GPL(dax_get_by_host); - /** * inode_dax: convert a public inode into its dax_dev * @inode: An inode with i_cdev pointing to a dax_dev diff --git a/include/linux/dax.h b/include/linux/dax.h index b52f084aa643..379739b55408 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -41,7 +41,6 @@ struct dax_operations { extern struct attribute_group dax_attribute_group; #if IS_ENABLED(CONFIG_DAX) -struct dax_device *dax_get_by_host(const char *host); struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags); void put_dax(struct dax_device *dax_dev); @@ -73,10 +72,6 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, return dax_synchronous(dax_dev); } #else -static inline struct dax_device *dax_get_by_host(const char *host) -{ - return NULL; -} static inline struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags) { -- cgit v1.2.3 From cd93a2a4d1b076f5c73d70d836c202bbcbeea49e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Aug 2021 15:55:07 +0200 Subject: dax: remove __generic_fsdax_supported Just implement generic_fsdax_supported directly out of line instead of adding a wrapper. Given that generic_fsdax_supported is only supplied for CONFIG_FS_DAX builds this also allows to not provide it at all for !CONFIG_FS_DAX builds. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20210826135510.6293-7-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 8 ++++---- include/linux/dax.h | 16 ++-------------- 2 files changed, 6 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 0f74f83101ab..8e8ccb3e956b 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -119,9 +119,8 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) return dax_get_by_host(bdev->bd_disk->disk_name); } EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev); -#endif -bool __generic_fsdax_supported(struct dax_device *dax_dev, +bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors) { @@ -201,7 +200,8 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev, } return true; } -EXPORT_SYMBOL_GPL(__generic_fsdax_supported); +EXPORT_SYMBOL_GPL(generic_fsdax_supported); +#endif /* CONFIG_FS_DAX */ /** * __bdev_dax_supported() - Check if the device supports dax for filesystem @@ -360,7 +360,7 @@ bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, return false; id = dax_read_lock(); - if (dax_alive(dax_dev)) + if (dax_alive(dax_dev) && dax_dev->ops->dax_supported) ret = dax_dev->ops->dax_supported(dax_dev, bdev, blocksize, start, len); dax_read_unlock(id); diff --git a/include/linux/dax.h b/include/linux/dax.h index 379739b55408..0a3ef9701e03 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -123,16 +123,9 @@ static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) return __bdev_dax_supported(bdev, blocksize); } -bool __generic_fsdax_supported(struct dax_device *dax_dev, +bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors); -static inline bool generic_fsdax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t sectors) -{ - return __generic_fsdax_supported(dax_dev, bdev, blocksize, start, - sectors); -} static inline void fs_put_dax(struct dax_device *dax_dev) { @@ -154,12 +147,7 @@ static inline bool bdev_dax_supported(struct block_device *bdev, return false; } -static inline bool generic_fsdax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t sectors) -{ - return false; -} +#define generic_fsdax_supported NULL static inline void fs_put_dax(struct dax_device *dax_dev) { -- cgit v1.2.3 From 60b8340f0d6587d7b51990689fcdae567f309fbf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Aug 2021 15:55:08 +0200 Subject: dax: stub out dax_supported for !CONFIG_FS_DAX dax_supported calls into ->dax_supported which checks for fsdax support. Don't bother building it for !CONFIG_FS_DAX as it will always return false. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20210826135510.6293-8-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 36 ++++++++++++++++++------------------ include/linux/dax.h | 18 ++++++++++-------- 2 files changed, 28 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 8e8ccb3e956b..eed02729add3 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -201,6 +201,24 @@ bool generic_fsdax_supported(struct dax_device *dax_dev, return true; } EXPORT_SYMBOL_GPL(generic_fsdax_supported); + +bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, + int blocksize, sector_t start, sector_t len) +{ + bool ret = false; + int id; + + if (!dax_dev) + return false; + + id = dax_read_lock(); + if (dax_alive(dax_dev) && dax_dev->ops->dax_supported) + ret = dax_dev->ops->dax_supported(dax_dev, bdev, blocksize, + start, len); + dax_read_unlock(id); + return ret; +} +EXPORT_SYMBOL_GPL(dax_supported); #endif /* CONFIG_FS_DAX */ /** @@ -350,24 +368,6 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, } EXPORT_SYMBOL_GPL(dax_direct_access); -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len) -{ - bool ret = false; - int id; - - if (!dax_dev) - return false; - - id = dax_read_lock(); - if (dax_alive(dax_dev) && dax_dev->ops->dax_supported) - ret = dax_dev->ops->dax_supported(dax_dev, bdev, blocksize, - start, len); - dax_read_unlock(id); - return ret; -} -EXPORT_SYMBOL_GPL(dax_supported); - size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { diff --git a/include/linux/dax.h b/include/linux/dax.h index 0a3ef9701e03..32dce5763f2c 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -57,8 +57,6 @@ static inline void set_dax_synchronous(struct dax_device *dax_dev) { __set_dax_synchronous(dax_dev); } -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); /* * Check if given mapping is supported by the file / underlying device. */ @@ -101,12 +99,6 @@ static inline bool dax_synchronous(struct dax_device *dax_dev) static inline void set_dax_synchronous(struct dax_device *dax_dev) { } -static inline bool dax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t len) -{ - return false; -} static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { @@ -127,6 +119,9 @@ bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors); +bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, + int blocksize, sector_t start, sector_t len); + static inline void fs_put_dax(struct dax_device *dax_dev) { put_dax(dax_dev); @@ -149,6 +144,13 @@ static inline bool bdev_dax_supported(struct block_device *bdev, #define generic_fsdax_supported NULL +static inline bool dax_supported(struct dax_device *dax_dev, + struct block_device *bdev, int blocksize, sector_t start, + sector_t len) +{ + return false; +} + static inline void fs_put_dax(struct dax_device *dax_dev) { } -- cgit v1.2.3 From bdd3c50d83bf7f6acc869b48d02670d19030ae03 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Aug 2021 15:55:10 +0200 Subject: dax: remove bdev_dax_supported All callers already have a dax_device obtained from fs_dax_get_by_bdev at hand, so just pass that to dax_supported() insted of doing another lookup. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20210826135510.6293-10-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 42 +----------------------------------------- fs/ext2/super.c | 3 ++- fs/ext4/super.c | 3 ++- fs/xfs/xfs_super.c | 3 ++- include/linux/dax.h | 12 ------------ 5 files changed, 7 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index eed02729add3..fc89e91beea7 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -220,47 +220,7 @@ bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, } EXPORT_SYMBOL_GPL(dax_supported); #endif /* CONFIG_FS_DAX */ - -/** - * __bdev_dax_supported() - Check if the device supports dax for filesystem - * @bdev: block device to check - * @blocksize: The block size of the device - * - * This is a library function for filesystems to check if the block device - * can be mounted with dax option. - * - * Return: true if supported, false if unsupported - */ -bool __bdev_dax_supported(struct block_device *bdev, int blocksize) -{ - struct dax_device *dax_dev; - struct request_queue *q; - char buf[BDEVNAME_SIZE]; - bool ret; - - q = bdev_get_queue(bdev); - if (!q || !blk_queue_dax(q)) { - pr_debug("%s: error: request queue doesn't support dax\n", - bdevname(bdev, buf)); - return false; - } - - dax_dev = dax_get_by_host(bdev->bd_disk->disk_name); - if (!dax_dev) { - pr_debug("%s: error: device does not support dax\n", - bdevname(bdev, buf)); - return false; - } - - ret = dax_supported(dax_dev, bdev, blocksize, 0, - i_size_read(bdev->bd_inode) / 512); - - put_dax(dax_dev); - - return ret; -} -EXPORT_SYMBOL_GPL(__bdev_dax_supported); -#endif +#endif /* CONFIG_BLOCK */ enum dax_device_flags { /* !alive + rcu grace period == no new operations / mappings */ diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 21e09fbaa46f..26e69e48d7e0 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -949,7 +949,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); if (test_opt(sb, DAX)) { - if (!bdev_dax_supported(sb->s_bdev, blocksize)) { + if (!dax_supported(dax_dev, sb->s_bdev, blocksize, 0, + bdev_nr_sectors(sb->s_bdev))) { ext2_msg(sb, KERN_ERR, "DAX unsupported by block device. Turning off DAX."); clear_opt(sbi->s_mount_opt, DAX); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index dfa09a277b56..a1726a8debce 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4435,7 +4435,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (bdev_dax_supported(sb->s_bdev, blocksize)) + if (dax_supported(dax_dev, sb->s_bdev, blocksize, 0, + bdev_nr_sectors(sb->s_bdev))) set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) { diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 5a89bf601d97..f4384974e52a 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -319,7 +319,8 @@ xfs_buftarg_is_dax( struct super_block *sb, struct xfs_buftarg *bt) { - return bdev_dax_supported(bt->bt_bdev, sb->s_blocksize); + return dax_supported(bt->bt_daxdev, bt->bt_bdev, sb->s_blocksize, 0, + bdev_nr_sectors(bt->bt_bdev)); } STATIC int diff --git a/include/linux/dax.h b/include/linux/dax.h index 32dce5763f2c..2619d94c308d 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -109,12 +109,6 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct writeback_control; int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) -bool __bdev_dax_supported(struct block_device *bdev, int blocksize); -static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) -{ - return __bdev_dax_supported(bdev, blocksize); -} - bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors); @@ -136,12 +130,6 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t st dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); #else -static inline bool bdev_dax_supported(struct block_device *bdev, - int blocksize) -{ - return false; -} - #define generic_fsdax_supported NULL static inline bool dax_supported(struct dax_device *dax_dev, -- cgit v1.2.3 From d0efb16294d145d157432feda83877ae9d7cdf37 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 26 Aug 2021 12:46:01 -0700 Subject: net: don't unconditionally copy_from_user a struct ifreq for socket ioctls A common implementation of isatty(3) involves calling a ioctl passing a dummy struct argument and checking whether the syscall failed -- bionic and glibc use TCGETS (passing a struct termios), and musl uses TIOCGWINSZ (passing a struct winsize). If the FD is a socket, we will copy sizeof(struct ifreq) bytes of data from the argument and return -EFAULT if that fails. The result is that the isatty implementations may return a non-POSIX-compliant value in errno in the case where part of the dummy struct argument is inaccessible, as both struct termios and struct winsize are smaller than struct ifreq (at least on arm64). Although there is usually enough stack space following the argument on the stack that this did not present a practical problem up to now, with MTE stack instrumentation it's more likely for the copy to fail, as the memory following the struct may have a different tag. Fix the problem by adding an early check for whether the ioctl is a valid socket ioctl, and return -ENOTTY if it isn't. Fixes: 44c02a2c3dc5 ("dev_ioctl(): move copyin/copyout to callers") Link: https://linux-review.googlesource.com/id/I869da6cf6daabc3e4b7b82ac979683ba05e27d4d Signed-off-by: Peter Collingbourne Cc: # 4.19 Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ net/socket.c | 6 +++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eaf5bb008aa9..d65ce093e5a7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4012,6 +4012,10 @@ int netdev_rx_handler_register(struct net_device *dev, void netdev_rx_handler_unregister(struct net_device *dev); bool dev_valid_name(const char *name); +static inline bool is_socket_ioctl_cmd(unsigned int cmd) +{ + return _IOC_TYPE(cmd) == SOCK_IOC_TYPE; +} int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf *, int); diff --git a/net/socket.c b/net/socket.c index 0b2dad3bdf7f..8808b3617dac 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1109,7 +1109,7 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, rtnl_unlock(); if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf))) err = -EFAULT; - } else { + } else if (is_socket_ioctl_cmd(cmd)) { struct ifreq ifr; bool need_copyout; if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) @@ -1118,6 +1118,8 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, if (!err && need_copyout) if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; + } else { + err = -ENOTTY; } return err; } @@ -3306,6 +3308,8 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct ifreq ifreq; u32 data32; + if (!is_socket_ioctl_cmd(cmd)) + return -ENOTTY; if (copy_from_user(ifreq.ifr_name, u_ifreq32->ifr_name, IFNAMSIZ)) return -EFAULT; if (get_user(data32, &u_ifreq32->ifr_data)) -- cgit v1.2.3 From 2908f5e101e3fb1d478cff1c556966e1af816641 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 10 Feb 2020 10:00:22 +0000 Subject: fscache: Add a cookie debug ID and use that in traces Add a cookie debug ID and use that in traces and in procfiles rather than displaying the (hashed) pointer to the cookie. This is easier to correlate and we don't lose anything when interpreting oops output since that shows unhashed addresses and registers that aren't comparable to the hashed values. Changes: ver #2: - Fix the fscache_op tracepoint to handle a NULL cookie pointer. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/158861210988.340223.11688464116498247790.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/159465769844.1376105.14119502774019865432.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/160588459097.3465195.1273313637721852165.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162431193544.2908479.17556704572948300790.stgit@warthog.procyon.org.uk/ --- fs/fscache/cookie.c | 29 +++++++--- fs/fscache/fsdef.c | 1 + fs/fscache/object-list.c | 14 ++--- include/linux/fscache.h | 1 + include/trace/events/cachefiles.h | 68 +++++++++++----------- include/trace/events/fscache.h | 116 +++++++++++++++++++------------------- 6 files changed, 121 insertions(+), 108 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 751bc5b1cddf..f2be98d2c64d 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -29,21 +29,29 @@ static int fscache_attach_object(struct fscache_cookie *cookie, static void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) { - struct hlist_node *object; + struct fscache_object *object; + struct hlist_node *o; const u8 *k; unsigned loop; - pr_err("%c-cookie c=%p [p=%p fl=%lx nc=%u na=%u]\n", - prefix, cookie, cookie->parent, cookie->flags, + pr_err("%c-cookie c=%08x [p=%08x fl=%lx nc=%u na=%u]\n", + prefix, + cookie->debug_id, + cookie->parent ? cookie->parent->debug_id : 0, + cookie->flags, atomic_read(&cookie->n_children), atomic_read(&cookie->n_active)); - pr_err("%c-cookie d=%p n=%p\n", - prefix, cookie->def, cookie->netfs_data); + pr_err("%c-cookie d=%p{%s} n=%p\n", + prefix, + cookie->def, + cookie->def ? cookie->def->name : "?", + cookie->netfs_data); - object = READ_ONCE(cookie->backing_objects.first); - if (object) - pr_err("%c-cookie o=%p\n", - prefix, hlist_entry(object, struct fscache_object, cookie_link)); + o = READ_ONCE(cookie->backing_objects.first); + if (o) { + object = hlist_entry(o, struct fscache_object, cookie_link); + pr_err("%c-cookie o=%u\n", prefix, object->debug_id); + } pr_err("%c-key=[%u] '", prefix, cookie->key_len); k = (cookie->key_len <= sizeof(cookie->inline_key)) ? @@ -129,6 +137,8 @@ static long fscache_compare_cookie(const struct fscache_cookie *a, return memcmp(ka, kb, a->key_len); } +static atomic_t fscache_cookie_debug_id = ATOMIC_INIT(1); + /* * Allocate a cookie. */ @@ -163,6 +173,7 @@ struct fscache_cookie *fscache_alloc_cookie( atomic_set(&cookie->usage, 1); atomic_set(&cookie->n_children, 0); + cookie->debug_id = atomic_inc_return(&fscache_cookie_debug_id); /* We keep the active count elevated until relinquishment to prevent an * attempt to wake up every time the object operations queue quiesces. diff --git a/fs/fscache/fsdef.c b/fs/fscache/fsdef.c index 09ed8795ad86..5f8f6fe243fe 100644 --- a/fs/fscache/fsdef.c +++ b/fs/fscache/fsdef.c @@ -45,6 +45,7 @@ static struct fscache_cookie_def fscache_fsdef_index_def = { }; struct fscache_cookie fscache_fsdef_index = { + .debug_id = 1, .usage = ATOMIC_INIT(1), .n_active = ATOMIC_INIT(1), .lock = __SPIN_LOCK_UNLOCKED(fscache_fsdef_index.lock), diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index e106a1a1600d..1a0dc32c0a33 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -170,7 +170,7 @@ static int fscache_objlist_show(struct seq_file *m, void *v) if ((unsigned long) v == 1) { seq_puts(m, "OBJECT PARENT STAT CHLDN OPS OOP IPR EX READS" " EM EV FL S" - " | NETFS_COOKIE_DEF TY FL NETFS_DATA"); + " | COOKIE NETFS_COOKIE_DEF TY FL NETFS_DATA"); if (config & (FSCACHE_OBJLIST_CONFIG_KEY | FSCACHE_OBJLIST_CONFIG_AUX)) seq_puts(m, " "); @@ -189,7 +189,7 @@ static int fscache_objlist_show(struct seq_file *m, void *v) if ((unsigned long) v == 2) { seq_puts(m, "======== ======== ==== ===== === === === == =====" " == == == =" - " | ================ == == ================"); + " | ======== ================ == === ================"); if (config & (FSCACHE_OBJLIST_CONFIG_KEY | FSCACHE_OBJLIST_CONFIG_AUX)) seq_puts(m, " ================"); @@ -231,9 +231,9 @@ static int fscache_objlist_show(struct seq_file *m, void *v) } seq_printf(m, - "%8x %8x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %2lx %1x | ", + "%08x %08x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %2lx %1x | ", obj->debug_id, - obj->parent ? obj->parent->debug_id : -1, + obj->parent ? obj->parent->debug_id : UINT_MAX, obj->state->short_name, obj->n_children, obj->n_ops, @@ -246,7 +246,7 @@ static int fscache_objlist_show(struct seq_file *m, void *v) obj->flags, work_busy(&obj->work)); - if (fscache_use_cookie(obj)) { + if (obj->cookie) { uint16_t keylen = 0, auxlen = 0; switch (cookie->type) { @@ -263,7 +263,8 @@ static int fscache_objlist_show(struct seq_file *m, void *v) break; } - seq_printf(m, "%-16s %s %2lx %16p", + seq_printf(m, "%08x %-16s %s %3lx %16p", + cookie->debug_id, cookie->def->name, type, cookie->flags, @@ -292,7 +293,6 @@ static int fscache_objlist_show(struct seq_file *m, void *v) } seq_puts(m, "\n"); - fscache_unuse_cookie(obj); } else { seq_puts(m, "\n"); } diff --git a/include/linux/fscache.h b/include/linux/fscache.h index abc1c4737fb8..ba58c427cf9a 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -126,6 +126,7 @@ struct fscache_cookie { atomic_t usage; /* number of users of this cookie */ atomic_t n_children; /* number of children of this cookie */ atomic_t n_active; /* number of active users of netfs ptrs */ + unsigned int debug_id; spinlock_t lock; spinlock_t stores_lock; /* lock on page store tree */ struct hlist_head backing_objects; /* object(s) backing this file/index */ diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 5d9de24cb9c0..9a448fe9355d 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -78,20 +78,20 @@ TRACE_EVENT(cachefiles_ref, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(struct cachefiles_object *, obj ) - __field(struct fscache_cookie *, cookie ) + __field(unsigned int, obj ) + __field(unsigned int, cookie ) __field(enum cachefiles_obj_ref_trace, why ) __field(int, usage ) ), TP_fast_assign( - __entry->obj = obj; - __entry->cookie = cookie; + __entry->obj = obj->fscache.debug_id; + __entry->cookie = cookie->debug_id; __entry->usage = usage; __entry->why = why; ), - TP_printk("c=%p o=%p u=%d %s", + TP_printk("c=%08x o=%08x u=%d %s", __entry->cookie, __entry->obj, __entry->usage, __print_symbolic(__entry->why, cachefiles_obj_ref_traces)) ); @@ -104,18 +104,18 @@ TRACE_EVENT(cachefiles_lookup, TP_ARGS(obj, de, inode), TP_STRUCT__entry( - __field(struct cachefiles_object *, obj ) + __field(unsigned int, obj ) __field(struct dentry *, de ) __field(struct inode *, inode ) ), TP_fast_assign( - __entry->obj = obj; + __entry->obj = obj->fscache.debug_id; __entry->de = de; __entry->inode = inode; ), - TP_printk("o=%p d=%p i=%p", + TP_printk("o=%08x d=%p i=%p", __entry->obj, __entry->de, __entry->inode) ); @@ -126,18 +126,18 @@ TRACE_EVENT(cachefiles_mkdir, TP_ARGS(obj, de, ret), TP_STRUCT__entry( - __field(struct cachefiles_object *, obj ) + __field(unsigned int, obj ) __field(struct dentry *, de ) __field(int, ret ) ), TP_fast_assign( - __entry->obj = obj; + __entry->obj = obj->fscache.debug_id; __entry->de = de; __entry->ret = ret; ), - TP_printk("o=%p d=%p r=%u", + TP_printk("o=%08x d=%p r=%u", __entry->obj, __entry->de, __entry->ret) ); @@ -148,18 +148,18 @@ TRACE_EVENT(cachefiles_create, TP_ARGS(obj, de, ret), TP_STRUCT__entry( - __field(struct cachefiles_object *, obj ) + __field(unsigned int, obj ) __field(struct dentry *, de ) __field(int, ret ) ), TP_fast_assign( - __entry->obj = obj; + __entry->obj = obj->fscache.debug_id; __entry->de = de; __entry->ret = ret; ), - TP_printk("o=%p d=%p r=%u", + TP_printk("o=%08x d=%p r=%u", __entry->obj, __entry->de, __entry->ret) ); @@ -172,18 +172,18 @@ TRACE_EVENT(cachefiles_unlink, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(struct cachefiles_object *, obj ) + __field(unsigned int, obj ) __field(struct dentry *, de ) __field(enum fscache_why_object_killed, why ) ), TP_fast_assign( - __entry->obj = obj; + __entry->obj = obj->fscache.debug_id; __entry->de = de; __entry->why = why; ), - TP_printk("o=%p d=%p w=%s", + TP_printk("o=%08x d=%p w=%s", __entry->obj, __entry->de, __print_symbolic(__entry->why, cachefiles_obj_kill_traces)) ); @@ -198,20 +198,20 @@ TRACE_EVENT(cachefiles_rename, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(struct cachefiles_object *, obj ) + __field(unsigned int, obj ) __field(struct dentry *, de ) __field(struct dentry *, to ) __field(enum fscache_why_object_killed, why ) ), TP_fast_assign( - __entry->obj = obj; + __entry->obj = obj->fscache.debug_id; __entry->de = de; __entry->to = to; __entry->why = why; ), - TP_printk("o=%p d=%p t=%p w=%s", + TP_printk("o=%08x d=%p t=%p w=%s", __entry->obj, __entry->de, __entry->to, __print_symbolic(__entry->why, cachefiles_obj_kill_traces)) ); @@ -224,16 +224,16 @@ TRACE_EVENT(cachefiles_mark_active, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(struct cachefiles_object *, obj ) + __field(unsigned int, obj ) __field(struct dentry *, de ) ), TP_fast_assign( - __entry->obj = obj; + __entry->obj = obj->fscache.debug_id; __entry->de = de; ), - TP_printk("o=%p d=%p", + TP_printk("o=%08x d=%p", __entry->obj, __entry->de) ); @@ -246,22 +246,22 @@ TRACE_EVENT(cachefiles_wait_active, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(struct cachefiles_object *, obj ) + __field(unsigned int, obj ) + __field(unsigned int, xobj ) __field(struct dentry *, de ) - __field(struct cachefiles_object *, xobj ) __field(u16, flags ) __field(u16, fsc_flags ) ), TP_fast_assign( - __entry->obj = obj; + __entry->obj = obj->fscache.debug_id; __entry->de = de; - __entry->xobj = xobj; + __entry->xobj = xobj->fscache.debug_id; __entry->flags = xobj->flags; __entry->fsc_flags = xobj->fscache.flags; ), - TP_printk("o=%p d=%p wo=%p wf=%x wff=%x", + TP_printk("o=%08x d=%p wo=%08x wf=%x wff=%x", __entry->obj, __entry->de, __entry->xobj, __entry->flags, __entry->fsc_flags) ); @@ -275,18 +275,18 @@ TRACE_EVENT(cachefiles_mark_inactive, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(struct cachefiles_object *, obj ) + __field(unsigned int, obj ) __field(struct dentry *, de ) __field(struct inode *, inode ) ), TP_fast_assign( - __entry->obj = obj; + __entry->obj = obj->fscache.debug_id; __entry->de = de; __entry->inode = inode; ), - TP_printk("o=%p d=%p i=%p", + TP_printk("o=%08x d=%p i=%p", __entry->obj, __entry->de, __entry->inode) ); @@ -299,18 +299,18 @@ TRACE_EVENT(cachefiles_mark_buried, /* Note that obj may be NULL */ TP_STRUCT__entry( - __field(struct cachefiles_object *, obj ) + __field(unsigned int, obj ) __field(struct dentry *, de ) __field(enum fscache_why_object_killed, why ) ), TP_fast_assign( - __entry->obj = obj; + __entry->obj = obj->fscache.debug_id; __entry->de = de; __entry->why = why; ), - TP_printk("o=%p d=%p w=%s", + TP_printk("o=%08x d=%p w=%s", __entry->obj, __entry->de, __print_symbolic(__entry->why, cachefiles_obj_kill_traces)) ); diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index d16fe6ed78a2..33d1fd5d0383 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -167,8 +167,8 @@ TRACE_EVENT(fscache_cookie, TP_ARGS(cookie, where, usage), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) - __field(struct fscache_cookie *, parent ) + __field(unsigned int, cookie ) + __field(unsigned int, parent ) __field(enum fscache_cookie_trace, where ) __field(int, usage ) __field(int, n_children ) @@ -177,8 +177,8 @@ TRACE_EVENT(fscache_cookie, ), TP_fast_assign( - __entry->cookie = cookie; - __entry->parent = cookie->parent; + __entry->cookie = cookie->debug_id; + __entry->parent = cookie->parent ? cookie->parent->debug_id : 0; __entry->where = where; __entry->usage = usage; __entry->n_children = atomic_read(&cookie->n_children); @@ -186,7 +186,7 @@ TRACE_EVENT(fscache_cookie, __entry->flags = cookie->flags; ), - TP_printk("%s c=%p u=%d p=%p Nc=%d Na=%d f=%02x", + TP_printk("%s c=%08x u=%d p=%08x Nc=%d Na=%d f=%02x", __print_symbolic(__entry->where, fscache_cookie_traces), __entry->cookie, __entry->usage, __entry->parent, __entry->n_children, __entry->n_active, @@ -199,17 +199,17 @@ TRACE_EVENT(fscache_netfs, TP_ARGS(netfs), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) + __field(unsigned int, cookie ) __array(char, name, 8 ) ), TP_fast_assign( - __entry->cookie = netfs->primary_index; + __entry->cookie = netfs->primary_index->debug_id; strncpy(__entry->name, netfs->name, 8); __entry->name[7] = 0; ), - TP_printk("c=%p n=%s", + TP_printk("c=%08x n=%s", __entry->cookie, __entry->name) ); @@ -219,8 +219,8 @@ TRACE_EVENT(fscache_acquire, TP_ARGS(cookie), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) - __field(struct fscache_cookie *, parent ) + __field(unsigned int, cookie ) + __field(unsigned int, parent ) __array(char, name, 8 ) __field(int, p_usage ) __field(int, p_n_children ) @@ -228,8 +228,8 @@ TRACE_EVENT(fscache_acquire, ), TP_fast_assign( - __entry->cookie = cookie; - __entry->parent = cookie->parent; + __entry->cookie = cookie->debug_id; + __entry->parent = cookie->parent->debug_id; __entry->p_usage = atomic_read(&cookie->parent->usage); __entry->p_n_children = atomic_read(&cookie->parent->n_children); __entry->p_flags = cookie->parent->flags; @@ -237,7 +237,7 @@ TRACE_EVENT(fscache_acquire, __entry->name[7] = 0; ), - TP_printk("c=%p p=%p pu=%d pc=%d pf=%02x n=%s", + TP_printk("c=%08x p=%08x pu=%d pc=%d pf=%02x n=%s", __entry->cookie, __entry->parent, __entry->p_usage, __entry->p_n_children, __entry->p_flags, __entry->name) ); @@ -248,8 +248,8 @@ TRACE_EVENT(fscache_relinquish, TP_ARGS(cookie, retire), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) - __field(struct fscache_cookie *, parent ) + __field(unsigned int, cookie ) + __field(unsigned int, parent ) __field(int, usage ) __field(int, n_children ) __field(int, n_active ) @@ -258,8 +258,8 @@ TRACE_EVENT(fscache_relinquish, ), TP_fast_assign( - __entry->cookie = cookie; - __entry->parent = cookie->parent; + __entry->cookie = cookie->debug_id; + __entry->parent = cookie->parent->debug_id; __entry->usage = atomic_read(&cookie->usage); __entry->n_children = atomic_read(&cookie->n_children); __entry->n_active = atomic_read(&cookie->n_active); @@ -267,7 +267,7 @@ TRACE_EVENT(fscache_relinquish, __entry->retire = retire; ), - TP_printk("c=%p u=%d p=%p Nc=%d Na=%d f=%02x r=%u", + TP_printk("c=%08x u=%d p=%08x Nc=%d Na=%d f=%02x r=%u", __entry->cookie, __entry->usage, __entry->parent, __entry->n_children, __entry->n_active, __entry->flags, __entry->retire) @@ -279,7 +279,7 @@ TRACE_EVENT(fscache_enable, TP_ARGS(cookie), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) + __field(unsigned int, cookie ) __field(int, usage ) __field(int, n_children ) __field(int, n_active ) @@ -287,14 +287,14 @@ TRACE_EVENT(fscache_enable, ), TP_fast_assign( - __entry->cookie = cookie; + __entry->cookie = cookie->debug_id; __entry->usage = atomic_read(&cookie->usage); __entry->n_children = atomic_read(&cookie->n_children); __entry->n_active = atomic_read(&cookie->n_active); __entry->flags = cookie->flags; ), - TP_printk("c=%p u=%d Nc=%d Na=%d f=%02x", + TP_printk("c=%08x u=%d Nc=%d Na=%d f=%02x", __entry->cookie, __entry->usage, __entry->n_children, __entry->n_active, __entry->flags) ); @@ -305,7 +305,7 @@ TRACE_EVENT(fscache_disable, TP_ARGS(cookie), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) + __field(unsigned int, cookie ) __field(int, usage ) __field(int, n_children ) __field(int, n_active ) @@ -313,14 +313,14 @@ TRACE_EVENT(fscache_disable, ), TP_fast_assign( - __entry->cookie = cookie; + __entry->cookie = cookie->debug_id; __entry->usage = atomic_read(&cookie->usage); __entry->n_children = atomic_read(&cookie->n_children); __entry->n_active = atomic_read(&cookie->n_active); __entry->flags = cookie->flags; ), - TP_printk("c=%p u=%d Nc=%d Na=%d f=%02x", + TP_printk("c=%08x u=%d Nc=%d Na=%d f=%02x", __entry->cookie, __entry->usage, __entry->n_children, __entry->n_active, __entry->flags) ); @@ -333,8 +333,8 @@ TRACE_EVENT(fscache_osm, TP_ARGS(object, state, wait, oob, event_num), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) - __field(struct fscache_object *, object ) + __field(unsigned int, cookie ) + __field(unsigned int, object ) __array(char, state, 8 ) __field(bool, wait ) __field(bool, oob ) @@ -342,15 +342,15 @@ TRACE_EVENT(fscache_osm, ), TP_fast_assign( - __entry->cookie = object->cookie; - __entry->object = object; + __entry->cookie = object->cookie->debug_id; + __entry->object = object->debug_id; __entry->wait = wait; __entry->oob = oob; __entry->event_num = event_num; memcpy(__entry->state, state->short_name, 8); ), - TP_printk("c=%p o=%p %s %s%sev=%d", + TP_printk("c=%08x o=%08d %s %s%sev=%d", __entry->cookie, __entry->object, __entry->state, @@ -370,18 +370,18 @@ TRACE_EVENT(fscache_page, TP_ARGS(cookie, page, why), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) + __field(unsigned int, cookie ) __field(pgoff_t, page ) __field(enum fscache_page_trace, why ) ), TP_fast_assign( - __entry->cookie = cookie; + __entry->cookie = cookie->debug_id; __entry->page = page->index; __entry->why = why; ), - TP_printk("c=%p %s pg=%lx", + TP_printk("c=%08x %s pg=%lx", __entry->cookie, __print_symbolic(__entry->why, fscache_page_traces), __entry->page) @@ -394,20 +394,20 @@ TRACE_EVENT(fscache_check_page, TP_ARGS(cookie, page, val, n), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) + __field(unsigned int, cookie ) __field(void *, page ) __field(void *, val ) __field(int, n ) ), TP_fast_assign( - __entry->cookie = cookie; + __entry->cookie = cookie->debug_id; __entry->page = page; __entry->val = val; __entry->n = n; ), - TP_printk("c=%p pg=%p val=%p n=%d", + TP_printk("c=%08x pg=%p val=%p n=%d", __entry->cookie, __entry->page, __entry->val, __entry->n) ); @@ -417,14 +417,14 @@ TRACE_EVENT(fscache_wake_cookie, TP_ARGS(cookie), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) + __field(unsigned int, cookie ) ), TP_fast_assign( - __entry->cookie = cookie; + __entry->cookie = cookie->debug_id; ), - TP_printk("c=%p", __entry->cookie) + TP_printk("c=%08x", __entry->cookie) ); TRACE_EVENT(fscache_op, @@ -434,18 +434,18 @@ TRACE_EVENT(fscache_op, TP_ARGS(cookie, op, why), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) - __field(struct fscache_operation *, op ) + __field(unsigned int, cookie ) + __field(unsigned int, op ) __field(enum fscache_op_trace, why ) ), TP_fast_assign( - __entry->cookie = cookie; - __entry->op = op; + __entry->cookie = cookie ? cookie->debug_id : 0; + __entry->op = op->debug_id; __entry->why = why; ), - TP_printk("c=%p op=%p %s", + TP_printk("c=%08x op=%08x %s", __entry->cookie, __entry->op, __print_symbolic(__entry->why, fscache_op_traces)) ); @@ -457,20 +457,20 @@ TRACE_EVENT(fscache_page_op, TP_ARGS(cookie, page, op, what), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) + __field(unsigned int, cookie ) + __field(unsigned int, op ) __field(pgoff_t, page ) - __field(struct fscache_operation *, op ) __field(enum fscache_page_op_trace, what ) ), TP_fast_assign( - __entry->cookie = cookie; + __entry->cookie = cookie->debug_id; __entry->page = page ? page->index : 0; - __entry->op = op; + __entry->op = op->debug_id; __entry->what = what; ), - TP_printk("c=%p %s pg=%lx op=%p", + TP_printk("c=%08x %s pg=%lx op=%08x", __entry->cookie, __print_symbolic(__entry->what, fscache_page_op_traces), __entry->page, __entry->op) @@ -483,20 +483,20 @@ TRACE_EVENT(fscache_wrote_page, TP_ARGS(cookie, page, op, ret), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) + __field(unsigned int, cookie ) + __field(unsigned int, op ) __field(pgoff_t, page ) - __field(struct fscache_operation *, op ) __field(int, ret ) ), TP_fast_assign( - __entry->cookie = cookie; + __entry->cookie = cookie->debug_id; __entry->page = page->index; - __entry->op = op; + __entry->op = op->debug_id; __entry->ret = ret; ), - TP_printk("c=%p pg=%lx op=%p ret=%d", + TP_printk("c=%08x pg=%lx op=%08x ret=%d", __entry->cookie, __entry->page, __entry->op, __entry->ret) ); @@ -507,22 +507,22 @@ TRACE_EVENT(fscache_gang_lookup, TP_ARGS(cookie, op, results, n, store_limit), TP_STRUCT__entry( - __field(struct fscache_cookie *, cookie ) - __field(struct fscache_operation *, op ) + __field(unsigned int, cookie ) + __field(unsigned int, op ) __field(pgoff_t, results0 ) __field(int, n ) __field(pgoff_t, store_limit ) ), TP_fast_assign( - __entry->cookie = cookie; - __entry->op = op; + __entry->cookie = cookie->debug_id; + __entry->op = op->debug_id; __entry->results0 = results[0] ? ((struct page *)results[0])->index : (pgoff_t)-1; __entry->n = n; __entry->store_limit = store_limit; ), - TP_printk("c=%p op=%p r0=%lx n=%d sl=%lx", + TP_printk("c=%08x op=%08x r0=%lx n=%d sl=%lx", __entry->cookie, __entry->op, __entry->results0, __entry->n, __entry->store_limit) ); -- cgit v1.2.3 From 884a76881fc5f5c9c04de1b640bed2c340929842 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 10 Feb 2020 10:00:22 +0000 Subject: fscache: Procfile to display cookies Add /proc/fs/fscache/cookies to display active cookies. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/158861211871.340223.7223853943667440807.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/159465771021.1376105.6933857529128238020.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/160588460994.3465195.16963417803501149328.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162431194785.2908479.786917990782538164.stgit@warthog.procyon.org.uk/ --- fs/fscache/cookie.c | 103 ++++++++++++++++++++++++++++++++++++++++++++++++ fs/fscache/internal.h | 1 + fs/fscache/proc.c | 7 ++++ include/linux/fscache.h | 1 + 4 files changed, 112 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index f2be98d2c64d..c7047544972b 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -19,6 +19,8 @@ static atomic_t fscache_object_debug_id = ATOMIC_INIT(0); #define fscache_cookie_hash_shift 15 static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; +static LIST_HEAD(fscache_cookies); +static DEFINE_RWLOCK(fscache_cookies_lock); static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie, loff_t object_size); @@ -65,6 +67,9 @@ void fscache_free_cookie(struct fscache_cookie *cookie) { if (cookie) { BUG_ON(!hlist_empty(&cookie->backing_objects)); + write_lock(&fscache_cookies_lock); + list_del(&cookie->proc_link); + write_unlock(&fscache_cookies_lock); if (cookie->aux_len > sizeof(cookie->inline_aux)) kfree(cookie->aux); if (cookie->key_len > sizeof(cookie->inline_key)) @@ -192,6 +197,10 @@ struct fscache_cookie *fscache_alloc_cookie( /* radix tree insertion won't use the preallocation pool unless it's * told it may not wait */ INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); + + write_lock(&fscache_cookies_lock); + list_add_tail(&cookie->proc_link, &fscache_cookies); + write_unlock(&fscache_cookies_lock); return cookie; nomem: @@ -969,3 +978,97 @@ inconsistent: return -ESTALE; } EXPORT_SYMBOL(__fscache_check_consistency); + +/* + * Generate a list of extant cookies in /proc/fs/fscache/cookies + */ +static int fscache_cookies_seq_show(struct seq_file *m, void *v) +{ + struct fscache_cookie *cookie; + unsigned int keylen = 0, auxlen = 0; + char _type[3], *type; + u8 *p; + + if (v == &fscache_cookies) { + seq_puts(m, + "COOKIE PARENT USAGE CHILD ACT TY FL DEF NETFS_DATA\n" + "======== ======== ===== ===== === == === ================ ==========\n" + ); + return 0; + } + + cookie = list_entry(v, struct fscache_cookie, proc_link); + + switch (cookie->type) { + case 0: + type = "IX"; + break; + case 1: + type = "DT"; + break; + default: + snprintf(_type, sizeof(_type), "%02u", + cookie->type); + type = _type; + break; + } + + seq_printf(m, + "%08x %08x %5u %5u %3u %s %03lx %-16s %px", + cookie->debug_id, + cookie->parent ? cookie->parent->debug_id : 0, + atomic_read(&cookie->usage), + atomic_read(&cookie->n_children), + atomic_read(&cookie->n_active), + type, + cookie->flags, + cookie->def->name, + cookie->netfs_data); + + keylen = cookie->key_len; + auxlen = cookie->aux_len; + + if (keylen > 0 || auxlen > 0) { + seq_puts(m, " "); + p = keylen <= sizeof(cookie->inline_key) ? + cookie->inline_key : cookie->key; + for (; keylen > 0; keylen--) + seq_printf(m, "%02x", *p++); + if (auxlen > 0) { + seq_puts(m, ", "); + p = auxlen <= sizeof(cookie->inline_aux) ? + cookie->inline_aux : cookie->aux; + for (; auxlen > 0; auxlen--) + seq_printf(m, "%02x", *p++); + } + } + + seq_puts(m, "\n"); + return 0; +} + +static void *fscache_cookies_seq_start(struct seq_file *m, loff_t *_pos) + __acquires(fscache_cookies_lock) +{ + read_lock(&fscache_cookies_lock); + return seq_list_start_head(&fscache_cookies, *_pos); +} + +static void *fscache_cookies_seq_next(struct seq_file *m, void *v, loff_t *_pos) +{ + return seq_list_next(v, &fscache_cookies, _pos); +} + +static void fscache_cookies_seq_stop(struct seq_file *m, void *v) + __releases(rcu) +{ + read_unlock(&fscache_cookies_lock); +} + + +const struct seq_operations fscache_cookies_seq_ops = { + .start = fscache_cookies_seq_start, + .next = fscache_cookies_seq_next, + .stop = fscache_cookies_seq_stop, + .show = fscache_cookies_seq_show, +}; diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index c483863b740a..207a6bc81ca9 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -45,6 +45,7 @@ extern struct fscache_cache *fscache_select_cache_for_object( * cookie.c */ extern struct kmem_cache *fscache_cookie_jar; +extern const struct seq_operations fscache_cookies_seq_ops; extern void fscache_free_cookie(struct fscache_cookie *); extern struct fscache_cookie *fscache_alloc_cookie(struct fscache_cookie *, diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index 90a7bc22f7e1..da51fdfc8641 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -21,6 +21,10 @@ int __init fscache_proc_init(void) if (!proc_mkdir("fs/fscache", NULL)) goto error_dir; + if (!proc_create_seq("fs/fscache/cookies", S_IFREG | 0444, NULL, + &fscache_cookies_seq_ops)) + goto error_cookies; + #ifdef CONFIG_FSCACHE_STATS if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, fscache_stats_show)) @@ -53,6 +57,8 @@ error_histogram: remove_proc_entry("fs/fscache/stats", NULL); error_stats: #endif + remove_proc_entry("fs/fscache/cookies", NULL); +error_cookies: remove_proc_entry("fs/fscache", NULL); error_dir: _leave(" = -ENOMEM"); @@ -73,5 +79,6 @@ void fscache_proc_cleanup(void) #ifdef CONFIG_FSCACHE_STATS remove_proc_entry("fs/fscache/stats", NULL); #endif + remove_proc_entry("fs/fscache/cookies", NULL); remove_proc_entry("fs/fscache", NULL); } diff --git a/include/linux/fscache.h b/include/linux/fscache.h index ba58c427cf9a..ea61e54a6bc5 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -133,6 +133,7 @@ struct fscache_cookie { const struct fscache_cookie_def *def; /* definition */ struct fscache_cookie *parent; /* parent of this entry */ struct hlist_bl_node hash_link; /* Link in hash table */ + struct list_head proc_link; /* Link in proc list */ void *netfs_data; /* back pointer to netfs */ struct radix_tree_root stores; /* pages to be stored on this cookie */ #define FSCACHE_COOKIE_PENDING_TAG 0 /* pages tag: pending write to cache */ -- cgit v1.2.3 From 6ae9bd8bb037b7c422bafde746f2338a716f6058 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 12 May 2021 09:40:19 +0100 Subject: fscache, cachefiles: Remove the histogram stuff Remove the histogram stuff as it's mostly going to be outdated. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/162431195953.2908479.16770977195634296638.stgit@warthog.procyon.org.uk/ --- fs/cachefiles/Kconfig | 19 ------- fs/cachefiles/Makefile | 2 - fs/cachefiles/internal.h | 25 --------- fs/cachefiles/main.c | 7 --- fs/cachefiles/namei.c | 13 ----- fs/cachefiles/proc.c | 114 ------------------------------------------ fs/fscache/Kconfig | 17 ------- fs/fscache/Makefile | 1 - fs/fscache/histogram.c | 87 -------------------------------- fs/fscache/internal.h | 24 --------- fs/fscache/object.c | 5 -- fs/fscache/operation.c | 3 -- fs/fscache/page.c | 6 --- fs/fscache/proc.c | 13 ----- include/linux/fscache-cache.h | 1 - 15 files changed, 337 deletions(-) delete mode 100644 fs/cachefiles/proc.c delete mode 100644 fs/fscache/histogram.c (limited to 'include/linux') diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig index ff9ca55a9ae9..6827b40f7ddc 100644 --- a/fs/cachefiles/Kconfig +++ b/fs/cachefiles/Kconfig @@ -19,22 +19,3 @@ config CACHEFILES_DEBUG caching on files module. If this is set, the debugging output may be enabled by setting bits in /sys/modules/cachefiles/parameter/debug or by including a debugging specifier in /etc/cachefilesd.conf. - -config CACHEFILES_HISTOGRAM - bool "Gather latency information on CacheFiles" - depends on CACHEFILES && PROC_FS - help - - This option causes latency information to be gathered on CacheFiles - operation and exported through file: - - /proc/fs/cachefiles/histogram - - The generation of this histogram adds a certain amount of overhead to - execution as there are a number of points at which data is gathered, - and on a multi-CPU system these may be on cachelines that keep - bouncing between CPUs. On the other hand, the histogram may be - useful for debugging purposes. Saying 'N' here is recommended. - - See Documentation/filesystems/caching/cachefiles.rst for more - information. diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile index 2227dc2d5498..02fd17731769 100644 --- a/fs/cachefiles/Makefile +++ b/fs/cachefiles/Makefile @@ -15,6 +15,4 @@ cachefiles-y := \ security.o \ xattr.o -cachefiles-$(CONFIG_CACHEFILES_HISTOGRAM) += proc.o - obj-$(CONFIG_CACHEFILES) := cachefiles.o diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 4ed83aa5253b..0a511c36dab8 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -180,31 +180,6 @@ extern int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir, extern int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir, char *filename); -/* - * proc.c - */ -#ifdef CONFIG_CACHEFILES_HISTOGRAM -extern atomic_t cachefiles_lookup_histogram[HZ]; -extern atomic_t cachefiles_mkdir_histogram[HZ]; -extern atomic_t cachefiles_create_histogram[HZ]; - -extern int __init cachefiles_proc_init(void); -extern void cachefiles_proc_cleanup(void); -static inline -void cachefiles_hist(atomic_t histogram[], unsigned long start_jif) -{ - unsigned long jif = jiffies - start_jif; - if (jif >= HZ) - jif = HZ - 1; - atomic_inc(&histogram[jif]); -} - -#else -#define cachefiles_proc_init() (0) -#define cachefiles_proc_cleanup() do {} while (0) -#define cachefiles_hist(hist, start_jif) do {} while (0) -#endif - /* * rdwr.c */ diff --git a/fs/cachefiles/main.c b/fs/cachefiles/main.c index ddf0cd58d60c..9c8d34c49b12 100644 --- a/fs/cachefiles/main.c +++ b/fs/cachefiles/main.c @@ -69,15 +69,9 @@ static int __init cachefiles_init(void) goto error_object_jar; } - ret = cachefiles_proc_init(); - if (ret < 0) - goto error_proc; - pr_info("Loaded\n"); return 0; -error_proc: - kmem_cache_destroy(cachefiles_object_jar); error_object_jar: misc_deregister(&cachefiles_dev); error_dev: @@ -94,7 +88,6 @@ static void __exit cachefiles_exit(void) { pr_info("Unloading\n"); - cachefiles_proc_cleanup(); kmem_cache_destroy(cachefiles_object_jar); misc_deregister(&cachefiles_dev); } diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 7bf0732ae25c..92aa550dae7e 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -496,7 +496,6 @@ int cachefiles_walk_to_object(struct cachefiles_object *parent, struct dentry *dir, *next = NULL; struct inode *inode; struct path path; - unsigned long start; const char *name; int ret, nlen; @@ -535,9 +534,7 @@ lookup_again: inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); - start = jiffies; next = lookup_one_len(name, dir, nlen); - cachefiles_hist(cachefiles_lookup_histogram, start); if (IS_ERR(next)) { trace_cachefiles_lookup(object, next, NULL); goto lookup_error; @@ -568,9 +565,7 @@ lookup_again: ret = security_path_mkdir(&path, next, 0); if (ret < 0) goto create_error; - start = jiffies; ret = vfs_mkdir(&init_user_ns, d_inode(dir), next, 0); - cachefiles_hist(cachefiles_mkdir_histogram, start); if (!key) trace_cachefiles_mkdir(object, next, ret); if (ret < 0) @@ -604,10 +599,8 @@ lookup_again: ret = security_path_mknod(&path, next, S_IFREG, 0); if (ret < 0) goto create_error; - start = jiffies; ret = vfs_create(&init_user_ns, d_inode(dir), next, S_IFREG, true); - cachefiles_hist(cachefiles_create_histogram, start); trace_cachefiles_create(object, next, ret); if (ret < 0) goto create_error; @@ -765,7 +758,6 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, const char *dirname) { struct dentry *subdir; - unsigned long start; struct path path; int ret; @@ -775,9 +767,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, inode_lock(d_inode(dir)); retry: - start = jiffies; subdir = lookup_one_len(dirname, dir, strlen(dirname)); - cachefiles_hist(cachefiles_lookup_histogram, start); if (IS_ERR(subdir)) { if (PTR_ERR(subdir) == -ENOMEM) goto nomem_d_alloc; @@ -876,7 +866,6 @@ static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache, struct cachefiles_object *object; struct rb_node *_n; struct dentry *victim; - unsigned long start; int ret; //_enter(",%pd/,%s", @@ -885,9 +874,7 @@ static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache, /* look up the victim */ inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); - start = jiffies; victim = lookup_one_len(filename, dir, strlen(filename)); - cachefiles_hist(cachefiles_lookup_histogram, start); if (IS_ERR(victim)) goto lookup_error; diff --git a/fs/cachefiles/proc.c b/fs/cachefiles/proc.c deleted file mode 100644 index 6e67aea0f24e..000000000000 --- a/fs/cachefiles/proc.c +++ /dev/null @@ -1,114 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* CacheFiles statistics - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include -#include -#include -#include "internal.h" - -atomic_t cachefiles_lookup_histogram[HZ]; -atomic_t cachefiles_mkdir_histogram[HZ]; -atomic_t cachefiles_create_histogram[HZ]; - -/* - * display the latency histogram - */ -static int cachefiles_histogram_show(struct seq_file *m, void *v) -{ - unsigned long index; - unsigned x, y, z, t; - - switch ((unsigned long) v) { - case 1: - seq_puts(m, "JIFS SECS LOOKUPS MKDIRS CREATES\n"); - return 0; - case 2: - seq_puts(m, "===== ===== ========= ========= =========\n"); - return 0; - default: - index = (unsigned long) v - 3; - x = atomic_read(&cachefiles_lookup_histogram[index]); - y = atomic_read(&cachefiles_mkdir_histogram[index]); - z = atomic_read(&cachefiles_create_histogram[index]); - if (x == 0 && y == 0 && z == 0) - return 0; - - t = (index * 1000) / HZ; - - seq_printf(m, "%4lu 0.%03u %9u %9u %9u\n", index, t, x, y, z); - return 0; - } -} - -/* - * set up the iterator to start reading from the first line - */ -static void *cachefiles_histogram_start(struct seq_file *m, loff_t *_pos) -{ - if ((unsigned long long)*_pos >= HZ + 2) - return NULL; - if (*_pos == 0) - *_pos = 1; - return (void *)(unsigned long) *_pos; -} - -/* - * move to the next line - */ -static void *cachefiles_histogram_next(struct seq_file *m, void *v, loff_t *pos) -{ - (*pos)++; - return (unsigned long long)*pos > HZ + 2 ? - NULL : (void *)(unsigned long) *pos; -} - -/* - * clean up after reading - */ -static void cachefiles_histogram_stop(struct seq_file *m, void *v) -{ -} - -static const struct seq_operations cachefiles_histogram_ops = { - .start = cachefiles_histogram_start, - .stop = cachefiles_histogram_stop, - .next = cachefiles_histogram_next, - .show = cachefiles_histogram_show, -}; - -/* - * initialise the /proc/fs/cachefiles/ directory - */ -int __init cachefiles_proc_init(void) -{ - _enter(""); - - if (!proc_mkdir("fs/cachefiles", NULL)) - goto error_dir; - - if (!proc_create_seq("fs/cachefiles/histogram", S_IFREG | 0444, NULL, - &cachefiles_histogram_ops)) - goto error_histogram; - - _leave(" = 0"); - return 0; - -error_histogram: - remove_proc_entry("fs/cachefiles", NULL); -error_dir: - _leave(" = -ENOMEM"); - return -ENOMEM; -} - -/* - * clean up the /proc/fs/cachefiles/ directory - */ -void cachefiles_proc_cleanup(void) -{ - remove_proc_entry("fs/cachefiles/histogram", NULL); - remove_proc_entry("fs/cachefiles", NULL); -} diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 92c87d8e0913..5e3a5b3f950d 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -29,23 +29,6 @@ config FSCACHE_STATS See Documentation/filesystems/caching/fscache.rst for more information. -config FSCACHE_HISTOGRAM - bool "Gather latency information on local caching" - depends on FSCACHE && PROC_FS - help - This option causes latency information to be gathered on local - caching and exported through file: - - /proc/fs/fscache/histogram - - The generation of this histogram adds a certain amount of overhead to - execution as there are a number of points at which data is gathered, - and on a multi-CPU system these may be on cachelines that keep - bouncing between CPUs. On the other hand, the histogram may be - useful for debugging purposes. Saying 'N' here is recommended. - - See Documentation/filesystems/caching/fscache.rst for more information. - config FSCACHE_DEBUG bool "Debug FS-Cache" depends on FSCACHE diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index 3b2ffa93ac18..45d5235a449b 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -16,7 +16,6 @@ fscache-y := \ fscache-$(CONFIG_PROC_FS) += proc.o fscache-$(CONFIG_FSCACHE_STATS) += stats.o -fscache-$(CONFIG_FSCACHE_HISTOGRAM) += histogram.o fscache-$(CONFIG_FSCACHE_OBJECT_LIST) += object-list.o obj-$(CONFIG_FSCACHE) := fscache.o diff --git a/fs/fscache/histogram.c b/fs/fscache/histogram.c deleted file mode 100644 index 4e5beeaaf454..000000000000 --- a/fs/fscache/histogram.c +++ /dev/null @@ -1,87 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* FS-Cache latency histogram - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL THREAD -#include -#include -#include -#include "internal.h" - -atomic_t fscache_obj_instantiate_histogram[HZ]; -atomic_t fscache_objs_histogram[HZ]; -atomic_t fscache_ops_histogram[HZ]; -atomic_t fscache_retrieval_delay_histogram[HZ]; -atomic_t fscache_retrieval_histogram[HZ]; - -/* - * display the time-taken histogram - */ -static int fscache_histogram_show(struct seq_file *m, void *v) -{ - unsigned long index; - unsigned n[5], t; - - switch ((unsigned long) v) { - case 1: - seq_puts(m, "JIFS SECS OBJ INST OP RUNS OBJ RUNS RETRV DLY RETRIEVLS\n"); - return 0; - case 2: - seq_puts(m, "===== ===== ========= ========= ========= ========= =========\n"); - return 0; - default: - index = (unsigned long) v - 3; - n[0] = atomic_read(&fscache_obj_instantiate_histogram[index]); - n[1] = atomic_read(&fscache_ops_histogram[index]); - n[2] = atomic_read(&fscache_objs_histogram[index]); - n[3] = atomic_read(&fscache_retrieval_delay_histogram[index]); - n[4] = atomic_read(&fscache_retrieval_histogram[index]); - if (!(n[0] | n[1] | n[2] | n[3] | n[4])) - return 0; - - t = (index * 1000) / HZ; - - seq_printf(m, "%4lu 0.%03u %9u %9u %9u %9u %9u\n", - index, t, n[0], n[1], n[2], n[3], n[4]); - return 0; - } -} - -/* - * set up the iterator to start reading from the first line - */ -static void *fscache_histogram_start(struct seq_file *m, loff_t *_pos) -{ - if ((unsigned long long)*_pos >= HZ + 2) - return NULL; - if (*_pos == 0) - *_pos = 1; - return (void *)(unsigned long) *_pos; -} - -/* - * move to the next line - */ -static void *fscache_histogram_next(struct seq_file *m, void *v, loff_t *pos) -{ - (*pos)++; - return (unsigned long long)*pos > HZ + 2 ? - NULL : (void *)(unsigned long) *pos; -} - -/* - * clean up after reading - */ -static void fscache_histogram_stop(struct seq_file *m, void *v) -{ -} - -const struct seq_operations fscache_histogram_ops = { - .start = fscache_histogram_start, - .stop = fscache_histogram_stop, - .next = fscache_histogram_next, - .show = fscache_histogram_show, -}; diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 207a6bc81ca9..796678b2b32a 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -63,30 +63,6 @@ extern void fscache_cookie_put(struct fscache_cookie *, extern struct fscache_cookie fscache_fsdef_index; extern struct fscache_cookie_def fscache_fsdef_netfs_def; -/* - * histogram.c - */ -#ifdef CONFIG_FSCACHE_HISTOGRAM -extern atomic_t fscache_obj_instantiate_histogram[HZ]; -extern atomic_t fscache_objs_histogram[HZ]; -extern atomic_t fscache_ops_histogram[HZ]; -extern atomic_t fscache_retrieval_delay_histogram[HZ]; -extern atomic_t fscache_retrieval_histogram[HZ]; - -static inline void fscache_hist(atomic_t histogram[], unsigned long start_jif) -{ - unsigned long jif = jiffies - start_jif; - if (jif >= HZ) - jif = HZ - 1; - atomic_inc(&histogram[jif]); -} - -extern const struct seq_operations fscache_histogram_ops; - -#else -#define fscache_hist(hist, start_jif) do {} while (0) -#endif - /* * main.c */ diff --git a/fs/fscache/object.c b/fs/fscache/object.c index cb2146e02cd5..5dbaab2e1262 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -277,13 +277,10 @@ static void fscache_object_work_func(struct work_struct *work) { struct fscache_object *object = container_of(work, struct fscache_object, work); - unsigned long start; _enter("{OBJ%x}", object->debug_id); - start = jiffies; fscache_object_sm_dispatcher(object); - fscache_hist(fscache_objs_histogram, start); fscache_put_object(object, fscache_obj_put_work); } @@ -436,7 +433,6 @@ static const struct fscache_state *fscache_parent_ready(struct fscache_object *o spin_lock(&parent->lock); parent->n_ops++; parent->n_obj_ops++; - object->lookup_jif = jiffies; spin_unlock(&parent->lock); _leave(""); @@ -596,7 +592,6 @@ static const struct fscache_state *fscache_object_available(struct fscache_objec object->cache->ops->lookup_complete(object); fscache_stat_d(&fscache_n_cop_lookup_complete); - fscache_hist(fscache_obj_instantiate_histogram, object->lookup_jif); fscache_stat(&fscache_n_object_avail); _leave(""); diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index 4a5651d4904e..433877107700 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -616,7 +616,6 @@ void fscache_op_work_func(struct work_struct *work) { struct fscache_operation *op = container_of(work, struct fscache_operation, work); - unsigned long start; _enter("{OBJ%x OP%x,%d}", op->object->debug_id, op->debug_id, atomic_read(&op->usage)); @@ -624,9 +623,7 @@ void fscache_op_work_func(struct work_struct *work) trace_fscache_op(op->object->cookie, op, fscache_op_work); ASSERT(op->processor != NULL); - start = jiffies; op->processor(op); - fscache_hist(fscache_ops_histogram, start); fscache_put_operation(op); _leave(""); diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 991b0a871744..27df94ef0e0b 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -289,7 +289,6 @@ static void fscache_release_retrieval_op(struct fscache_operation *_op) ASSERTIFCMP(op->op.state != FSCACHE_OP_ST_INITIALISED, atomic_read(&op->n_pages), ==, 0); - fscache_hist(fscache_retrieval_histogram, op->start_time); if (op->context) fscache_put_context(op->cookie, op->context); @@ -324,7 +323,6 @@ struct fscache_retrieval *fscache_alloc_retrieval( op->mapping = mapping; op->end_io_func = end_io_func; op->context = context; - op->start_time = jiffies; INIT_LIST_HEAD(&op->to_do); /* Pin the netfs read context in case we need to do the actual netfs @@ -340,8 +338,6 @@ struct fscache_retrieval *fscache_alloc_retrieval( */ int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) { - unsigned long jif; - _enter(""); if (!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) { @@ -351,7 +347,6 @@ int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) fscache_stat(&fscache_n_retrievals_wait); - jif = jiffies; if (wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP, TASK_INTERRUPTIBLE) != 0) { fscache_stat(&fscache_n_retrievals_intr); @@ -362,7 +357,6 @@ int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) ASSERT(!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)); smp_rmb(); - fscache_hist(fscache_retrieval_delay_histogram, jif); _leave(" = 0 [dly]"); return 0; } diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index da51fdfc8641..061df8f61ffc 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -31,12 +31,6 @@ int __init fscache_proc_init(void) goto error_stats; #endif -#ifdef CONFIG_FSCACHE_HISTOGRAM - if (!proc_create_seq("fs/fscache/histogram", S_IFREG | 0444, NULL, - &fscache_histogram_ops)) - goto error_histogram; -#endif - #ifdef CONFIG_FSCACHE_OBJECT_LIST if (!proc_create("fs/fscache/objects", S_IFREG | 0444, NULL, &fscache_objlist_proc_ops)) @@ -49,10 +43,6 @@ int __init fscache_proc_init(void) #ifdef CONFIG_FSCACHE_OBJECT_LIST error_objects: #endif -#ifdef CONFIG_FSCACHE_HISTOGRAM - remove_proc_entry("fs/fscache/histogram", NULL); -error_histogram: -#endif #ifdef CONFIG_FSCACHE_STATS remove_proc_entry("fs/fscache/stats", NULL); error_stats: @@ -73,9 +63,6 @@ void fscache_proc_cleanup(void) #ifdef CONFIG_FSCACHE_OBJECT_LIST remove_proc_entry("fs/fscache/objects", NULL); #endif -#ifdef CONFIG_FSCACHE_HISTOGRAM - remove_proc_entry("fs/fscache/histogram", NULL); -#endif #ifdef CONFIG_FSCACHE_STATS remove_proc_entry("fs/fscache/stats", NULL); #endif diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 3235ddbdcc09..fbff0b7e3ef1 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -147,7 +147,6 @@ struct fscache_retrieval { fscache_rw_complete_t end_io_func; /* function to call on I/O completion */ void *context; /* netfs read context (pinned) */ struct list_head to_do; /* list of things to be done by the backend */ - unsigned long start_time; /* time at which retrieval started */ atomic_t n_pages; /* number of pages to be retrieved */ }; -- cgit v1.2.3 From 58f386a73f16cea1f78e8466cc5c402eb7f6fcf8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 12 May 2021 09:59:17 +0100 Subject: fscache: Remove the object list procfile Remove the object list procfile from fscache as objects will become entirely internal to the cache. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/162431198332.2908479.5847286163455099669.stgit@warthog.procyon.org.uk/ --- fs/fscache/Kconfig | 7 - fs/fscache/Makefile | 1 - fs/fscache/cache.c | 1 - fs/fscache/cookie.c | 2 - fs/fscache/internal.h | 13 -- fs/fscache/object-list.c | 414 ------------------------------------------ fs/fscache/object.c | 2 - include/linux/fscache-cache.h | 3 - 8 files changed, 443 deletions(-) delete mode 100644 fs/fscache/object-list.c (limited to 'include/linux') diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 5e3a5b3f950d..b313a978ae0a 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -38,10 +38,3 @@ config FSCACHE_DEBUG enabled by setting bits in /sys/modules/fscache/parameter/debug. See Documentation/filesystems/caching/fscache.rst for more information. - -config FSCACHE_OBJECT_LIST - bool "Maintain global object list for debugging purposes" - depends on FSCACHE && PROC_FS - help - Maintain a global list of active fscache objects that can be - retrieved through /proc/fs/fscache/objects for debugging purposes diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index 45d5235a449b..03a871d689bb 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -16,6 +16,5 @@ fscache-y := \ fscache-$(CONFIG_PROC_FS) += proc.o fscache-$(CONFIG_FSCACHE_STATS) += stats.o -fscache-$(CONFIG_FSCACHE_OBJECT_LIST) += object-list.o obj-$(CONFIG_FSCACHE) := fscache.o diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index fcc136361415..8a6ffcac867f 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -261,7 +261,6 @@ int fscache_add_cache(struct fscache_cache *cache, spin_lock(&cache->object_list_lock); list_add_tail(&ifsdef->cache_link, &cache->object_list); spin_unlock(&cache->object_list_lock); - fscache_objlist_add(ifsdef); /* add the cache's netfs definition index object to the top level index * cookie as a known backing object */ diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index c7047544972b..2f4d5271ad2e 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -620,8 +620,6 @@ static int fscache_attach_object(struct fscache_cookie *cookie, /* Attach to the cookie. The object already has a ref on it. */ hlist_add_head(&object->cookie_link, &cookie->backing_objects); - - fscache_objlist_add(object); ret = 0; cant_attach_object: diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 796678b2b32a..200082cafdda 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -84,19 +84,6 @@ static inline bool fscache_object_congested(void) */ extern void fscache_enqueue_object(struct fscache_object *); -/* - * object-list.c - */ -#ifdef CONFIG_FSCACHE_OBJECT_LIST -extern const struct proc_ops fscache_objlist_proc_ops; - -extern void fscache_objlist_add(struct fscache_object *); -extern void fscache_objlist_remove(struct fscache_object *); -#else -#define fscache_objlist_add(object) do {} while(0) -#define fscache_objlist_remove(object) do {} while(0) -#endif - /* * operation.c */ diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c deleted file mode 100644 index 1a0dc32c0a33..000000000000 --- a/fs/fscache/object-list.c +++ /dev/null @@ -1,414 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Global fscache object list maintainer and viewer - * - * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL COOKIE -#include -#include -#include -#include -#include -#include -#include "internal.h" - -static struct rb_root fscache_object_list; -static DEFINE_RWLOCK(fscache_object_list_lock); - -struct fscache_objlist_data { - unsigned long config; /* display configuration */ -#define FSCACHE_OBJLIST_CONFIG_KEY 0x00000001 /* show object keys */ -#define FSCACHE_OBJLIST_CONFIG_AUX 0x00000002 /* show object auxdata */ -#define FSCACHE_OBJLIST_CONFIG_COOKIE 0x00000004 /* show objects with cookies */ -#define FSCACHE_OBJLIST_CONFIG_NOCOOKIE 0x00000008 /* show objects without cookies */ -#define FSCACHE_OBJLIST_CONFIG_BUSY 0x00000010 /* show busy objects */ -#define FSCACHE_OBJLIST_CONFIG_IDLE 0x00000020 /* show idle objects */ -#define FSCACHE_OBJLIST_CONFIG_PENDWR 0x00000040 /* show objects with pending writes */ -#define FSCACHE_OBJLIST_CONFIG_NOPENDWR 0x00000080 /* show objects without pending writes */ -#define FSCACHE_OBJLIST_CONFIG_READS 0x00000100 /* show objects with active reads */ -#define FSCACHE_OBJLIST_CONFIG_NOREADS 0x00000200 /* show objects without active reads */ -#define FSCACHE_OBJLIST_CONFIG_EVENTS 0x00000400 /* show objects with events */ -#define FSCACHE_OBJLIST_CONFIG_NOEVENTS 0x00000800 /* show objects without no events */ -#define FSCACHE_OBJLIST_CONFIG_WORK 0x00001000 /* show objects with work */ -#define FSCACHE_OBJLIST_CONFIG_NOWORK 0x00002000 /* show objects without work */ -}; - -/* - * Add an object to the object list - * - we use the address of the fscache_object structure as the key into the - * tree - */ -void fscache_objlist_add(struct fscache_object *obj) -{ - struct fscache_object *xobj; - struct rb_node **p = &fscache_object_list.rb_node, *parent = NULL; - - ASSERT(RB_EMPTY_NODE(&obj->objlist_link)); - - write_lock(&fscache_object_list_lock); - - while (*p) { - parent = *p; - xobj = rb_entry(parent, struct fscache_object, objlist_link); - - if (obj < xobj) - p = &(*p)->rb_left; - else if (obj > xobj) - p = &(*p)->rb_right; - else - BUG(); - } - - rb_link_node(&obj->objlist_link, parent, p); - rb_insert_color(&obj->objlist_link, &fscache_object_list); - - write_unlock(&fscache_object_list_lock); -} - -/* - * Remove an object from the object list. - */ -void fscache_objlist_remove(struct fscache_object *obj) -{ - if (RB_EMPTY_NODE(&obj->objlist_link)) - return; - - write_lock(&fscache_object_list_lock); - - BUG_ON(RB_EMPTY_ROOT(&fscache_object_list)); - rb_erase(&obj->objlist_link, &fscache_object_list); - - write_unlock(&fscache_object_list_lock); -} - -/* - * find the object in the tree on or after the specified index - */ -static struct fscache_object *fscache_objlist_lookup(loff_t *_pos) -{ - struct fscache_object *pobj, *obj = NULL, *minobj = NULL; - struct rb_node *p; - unsigned long pos; - - if (*_pos >= (unsigned long) ERR_PTR(-ENOENT)) - return NULL; - pos = *_pos; - - /* banners (can't represent line 0 by pos 0 as that would involve - * returning a NULL pointer) */ - if (pos == 0) - return (struct fscache_object *)(long)++(*_pos); - if (pos < 3) - return (struct fscache_object *)pos; - - pobj = (struct fscache_object *)pos; - p = fscache_object_list.rb_node; - while (p) { - obj = rb_entry(p, struct fscache_object, objlist_link); - if (pobj < obj) { - if (!minobj || minobj > obj) - minobj = obj; - p = p->rb_left; - } else if (pobj > obj) { - p = p->rb_right; - } else { - minobj = obj; - break; - } - obj = NULL; - } - - if (!minobj) - *_pos = (unsigned long) ERR_PTR(-ENOENT); - else if (minobj != obj) - *_pos = (unsigned long) minobj; - return minobj; -} - -/* - * set up the iterator to start reading from the first line - */ -static void *fscache_objlist_start(struct seq_file *m, loff_t *_pos) - __acquires(&fscache_object_list_lock) -{ - read_lock(&fscache_object_list_lock); - return fscache_objlist_lookup(_pos); -} - -/* - * move to the next line - */ -static void *fscache_objlist_next(struct seq_file *m, void *v, loff_t *_pos) -{ - (*_pos)++; - return fscache_objlist_lookup(_pos); -} - -/* - * clean up after reading - */ -static void fscache_objlist_stop(struct seq_file *m, void *v) - __releases(&fscache_object_list_lock) -{ - read_unlock(&fscache_object_list_lock); -} - -/* - * display an object - */ -static int fscache_objlist_show(struct seq_file *m, void *v) -{ - struct fscache_objlist_data *data = m->private; - struct fscache_object *obj = v; - struct fscache_cookie *cookie; - unsigned long config = data->config; - char _type[3], *type; - u8 *p; - - if ((unsigned long) v == 1) { - seq_puts(m, "OBJECT PARENT STAT CHLDN OPS OOP IPR EX READS" - " EM EV FL S" - " | COOKIE NETFS_COOKIE_DEF TY FL NETFS_DATA"); - if (config & (FSCACHE_OBJLIST_CONFIG_KEY | - FSCACHE_OBJLIST_CONFIG_AUX)) - seq_puts(m, " "); - if (config & FSCACHE_OBJLIST_CONFIG_KEY) - seq_puts(m, "OBJECT_KEY"); - if ((config & (FSCACHE_OBJLIST_CONFIG_KEY | - FSCACHE_OBJLIST_CONFIG_AUX)) == - (FSCACHE_OBJLIST_CONFIG_KEY | FSCACHE_OBJLIST_CONFIG_AUX)) - seq_puts(m, ", "); - if (config & FSCACHE_OBJLIST_CONFIG_AUX) - seq_puts(m, "AUX_DATA"); - seq_puts(m, "\n"); - return 0; - } - - if ((unsigned long) v == 2) { - seq_puts(m, "======== ======== ==== ===== === === === == =====" - " == == == =" - " | ======== ================ == === ================"); - if (config & (FSCACHE_OBJLIST_CONFIG_KEY | - FSCACHE_OBJLIST_CONFIG_AUX)) - seq_puts(m, " ================"); - seq_puts(m, "\n"); - return 0; - } - - /* filter out any unwanted objects */ -#define FILTER(criterion, _yes, _no) \ - do { \ - unsigned long yes = FSCACHE_OBJLIST_CONFIG_##_yes; \ - unsigned long no = FSCACHE_OBJLIST_CONFIG_##_no; \ - if (criterion) { \ - if (!(config & yes)) \ - return 0; \ - } else { \ - if (!(config & no)) \ - return 0; \ - } \ - } while(0) - - cookie = obj->cookie; - if (~config) { - FILTER(cookie->def, - COOKIE, NOCOOKIE); - FILTER(fscache_object_is_active(obj) || - obj->n_ops != 0 || - obj->n_obj_ops != 0 || - obj->flags || - !list_empty(&obj->dependents), - BUSY, IDLE); - FILTER(test_bit(FSCACHE_OBJECT_PENDING_WRITE, &obj->flags), - PENDWR, NOPENDWR); - FILTER(atomic_read(&obj->n_reads), - READS, NOREADS); - FILTER(obj->events & obj->event_mask, - EVENTS, NOEVENTS); - FILTER(work_busy(&obj->work), WORK, NOWORK); - } - - seq_printf(m, - "%08x %08x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %2lx %1x | ", - obj->debug_id, - obj->parent ? obj->parent->debug_id : UINT_MAX, - obj->state->short_name, - obj->n_children, - obj->n_ops, - obj->n_obj_ops, - obj->n_in_progress, - obj->n_exclusive, - atomic_read(&obj->n_reads), - obj->event_mask, - obj->events, - obj->flags, - work_busy(&obj->work)); - - if (obj->cookie) { - uint16_t keylen = 0, auxlen = 0; - - switch (cookie->type) { - case 0: - type = "IX"; - break; - case 1: - type = "DT"; - break; - default: - snprintf(_type, sizeof(_type), "%02u", - cookie->type); - type = _type; - break; - } - - seq_printf(m, "%08x %-16s %s %3lx %16p", - cookie->debug_id, - cookie->def->name, - type, - cookie->flags, - cookie->netfs_data); - - if (config & FSCACHE_OBJLIST_CONFIG_KEY) - keylen = cookie->key_len; - - if (config & FSCACHE_OBJLIST_CONFIG_AUX) - auxlen = cookie->aux_len; - - if (keylen > 0 || auxlen > 0) { - seq_puts(m, " "); - p = keylen <= sizeof(cookie->inline_key) ? - cookie->inline_key : cookie->key; - for (; keylen > 0; keylen--) - seq_printf(m, "%02x", *p++); - if (auxlen > 0) { - if (config & FSCACHE_OBJLIST_CONFIG_KEY) - seq_puts(m, ", "); - p = auxlen <= sizeof(cookie->inline_aux) ? - cookie->inline_aux : cookie->aux; - for (; auxlen > 0; auxlen--) - seq_printf(m, "%02x", *p++); - } - } - - seq_puts(m, "\n"); - } else { - seq_puts(m, "\n"); - } - return 0; -} - -static const struct seq_operations fscache_objlist_ops = { - .start = fscache_objlist_start, - .stop = fscache_objlist_stop, - .next = fscache_objlist_next, - .show = fscache_objlist_show, -}; - -/* - * get the configuration for filtering the list - */ -static void fscache_objlist_config(struct fscache_objlist_data *data) -{ -#ifdef CONFIG_KEYS - const struct user_key_payload *confkey; - unsigned long config; - struct key *key; - const char *buf; - int len; - - key = request_key(&key_type_user, "fscache:objlist", NULL); - if (IS_ERR(key)) - goto no_config; - - config = 0; - rcu_read_lock(); - - confkey = user_key_payload_rcu(key); - if (!confkey) { - /* key was revoked */ - rcu_read_unlock(); - key_put(key); - goto no_config; - } - - buf = confkey->data; - - for (len = confkey->datalen - 1; len >= 0; len--) { - switch (buf[len]) { - case 'K': config |= FSCACHE_OBJLIST_CONFIG_KEY; break; - case 'A': config |= FSCACHE_OBJLIST_CONFIG_AUX; break; - case 'C': config |= FSCACHE_OBJLIST_CONFIG_COOKIE; break; - case 'c': config |= FSCACHE_OBJLIST_CONFIG_NOCOOKIE; break; - case 'B': config |= FSCACHE_OBJLIST_CONFIG_BUSY; break; - case 'b': config |= FSCACHE_OBJLIST_CONFIG_IDLE; break; - case 'W': config |= FSCACHE_OBJLIST_CONFIG_PENDWR; break; - case 'w': config |= FSCACHE_OBJLIST_CONFIG_NOPENDWR; break; - case 'R': config |= FSCACHE_OBJLIST_CONFIG_READS; break; - case 'r': config |= FSCACHE_OBJLIST_CONFIG_NOREADS; break; - case 'S': config |= FSCACHE_OBJLIST_CONFIG_WORK; break; - case 's': config |= FSCACHE_OBJLIST_CONFIG_NOWORK; break; - } - } - - rcu_read_unlock(); - key_put(key); - - if (!(config & (FSCACHE_OBJLIST_CONFIG_COOKIE | FSCACHE_OBJLIST_CONFIG_NOCOOKIE))) - config |= FSCACHE_OBJLIST_CONFIG_COOKIE | FSCACHE_OBJLIST_CONFIG_NOCOOKIE; - if (!(config & (FSCACHE_OBJLIST_CONFIG_BUSY | FSCACHE_OBJLIST_CONFIG_IDLE))) - config |= FSCACHE_OBJLIST_CONFIG_BUSY | FSCACHE_OBJLIST_CONFIG_IDLE; - if (!(config & (FSCACHE_OBJLIST_CONFIG_PENDWR | FSCACHE_OBJLIST_CONFIG_NOPENDWR))) - config |= FSCACHE_OBJLIST_CONFIG_PENDWR | FSCACHE_OBJLIST_CONFIG_NOPENDWR; - if (!(config & (FSCACHE_OBJLIST_CONFIG_READS | FSCACHE_OBJLIST_CONFIG_NOREADS))) - config |= FSCACHE_OBJLIST_CONFIG_READS | FSCACHE_OBJLIST_CONFIG_NOREADS; - if (!(config & (FSCACHE_OBJLIST_CONFIG_EVENTS | FSCACHE_OBJLIST_CONFIG_NOEVENTS))) - config |= FSCACHE_OBJLIST_CONFIG_EVENTS | FSCACHE_OBJLIST_CONFIG_NOEVENTS; - if (!(config & (FSCACHE_OBJLIST_CONFIG_WORK | FSCACHE_OBJLIST_CONFIG_NOWORK))) - config |= FSCACHE_OBJLIST_CONFIG_WORK | FSCACHE_OBJLIST_CONFIG_NOWORK; - - data->config = config; - return; - -no_config: -#endif - data->config = ULONG_MAX; -} - -/* - * open "/proc/fs/fscache/objects" to provide a list of active objects - * - can be configured by a user-defined key added to the caller's keyrings - */ -static int fscache_objlist_open(struct inode *inode, struct file *file) -{ - struct fscache_objlist_data *data; - - data = __seq_open_private(file, &fscache_objlist_ops, sizeof(*data)); - if (!data) - return -ENOMEM; - - /* get the configuration key */ - fscache_objlist_config(data); - - return 0; -} - -/* - * clean up on close - */ -static int fscache_objlist_release(struct inode *inode, struct file *file) -{ - struct seq_file *m = file->private_data; - - kfree(m->private); - m->private = NULL; - return seq_release(inode, file); -} - -const struct proc_ops fscache_objlist_proc_ops = { - .proc_open = fscache_objlist_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = fscache_objlist_release, -}; diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 5dbaab2e1262..b3853274733f 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -794,8 +794,6 @@ static void fscache_put_object(struct fscache_object *object, */ void fscache_object_destroy(struct fscache_object *object) { - fscache_objlist_remove(object); - /* We can get rid of the cookie now */ fscache_cookie_put(object->cookie, fscache_cookie_put_object); object->cookie = NULL; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index fbff0b7e3ef1..8d39491c5f9f 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -384,9 +384,6 @@ struct fscache_object { struct list_head dependents; /* FIFO of dependent objects */ struct list_head dep_link; /* link in parent's dependents list */ struct list_head pending_ops; /* unstarted operations on this object */ -#ifdef CONFIG_FSCACHE_OBJECT_LIST - struct rb_node objlist_link; /* link in global object list */ -#endif pgoff_t store_limit; /* current storage limit */ loff_t store_limit_l; /* current storage limit */ }; -- cgit v1.2.3 From 20ec197bfa13c5b799fc9527790ea7b5374fc8f2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 29 Mar 2021 13:53:50 +0100 Subject: fscache: Use refcount_t for the cookie refcount instead of atomic_t Use refcount_t for the fscache_cookie refcount instead of atomic_t and rename the 'usage' member to 'ref' in such cases. The tracepoints that reference it change from showing "u=%d" to "r=%d". Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/162431204358.2908479.8006938388213098079.stgit@warthog.procyon.org.uk/ --- fs/fscache/cache.c | 2 +- fs/fscache/cookie.c | 31 +++++++++++++++++++---------- fs/fscache/fsdef.c | 2 +- fs/fscache/internal.h | 17 ++++++++-------- include/linux/fscache.h | 2 +- include/trace/events/fscache.h | 44 +++++++++++++++++++++--------------------- 6 files changed, 55 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index e7a5d7ab4085..bd4f44c1cce0 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -269,7 +269,7 @@ int fscache_add_cache(struct fscache_cache *cache, hlist_add_head(&ifsdef->cookie_link, &fscache_fsdef_index.backing_objects); - atomic_inc(&fscache_fsdef_index.usage); + refcount_inc(&fscache_fsdef_index.ref); /* done */ spin_unlock(&fscache_fsdef_index.lock); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 6df3732cf1b4..cd42be646ed3 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -164,7 +164,7 @@ struct fscache_cookie *fscache_alloc_cookie( goto nomem; } - atomic_set(&cookie->usage, 1); + refcount_set(&cookie->ref, 1); atomic_set(&cookie->n_children, 0); cookie->debug_id = atomic_inc_return(&fscache_cookie_debug_id); @@ -225,7 +225,7 @@ struct fscache_cookie *fscache_hash_cookie(struct fscache_cookie *candidate) collision: if (test_and_set_bit(FSCACHE_COOKIE_ACQUIRED, &cursor->flags)) { - trace_fscache_cookie(cursor->debug_id, atomic_read(&cursor->usage), + trace_fscache_cookie(cursor->debug_id, refcount_read(&cursor->ref), fscache_cookie_collision); pr_err("Duplicate cookie detected\n"); fscache_print_cookie(cursor, 'O'); @@ -826,13 +826,12 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, BUG_ON(!radix_tree_empty(&cookie->stores)); if (cookie->parent) { - ASSERTCMP(atomic_read(&cookie->parent->usage), >, 0); + ASSERTCMP(refcount_read(&cookie->parent->ref), >, 0); ASSERTCMP(atomic_read(&cookie->parent->n_children), >, 0); atomic_dec(&cookie->parent->n_children); } /* Dispose of the netfs's link to the cookie */ - ASSERTCMP(atomic_read(&cookie->usage), >, 0); fscache_cookie_put(cookie, fscache_cookie_put_relinquish); _leave(""); @@ -862,18 +861,17 @@ void fscache_cookie_put(struct fscache_cookie *cookie, enum fscache_cookie_trace where) { struct fscache_cookie *parent; - int usage; + int ref; _enter("%x", cookie->debug_id); do { unsigned int cookie_debug_id = cookie->debug_id; - usage = atomic_dec_return(&cookie->usage); - trace_fscache_cookie(cookie_debug_id, usage, where); + bool zero = __refcount_dec_and_test(&cookie->ref, &ref); - if (usage > 0) + trace_fscache_cookie(cookie_debug_id, ref - 1, where); + if (!zero) return; - BUG_ON(usage < 0); parent = cookie->parent; fscache_unhash_cookie(cookie); @@ -886,6 +884,19 @@ void fscache_cookie_put(struct fscache_cookie *cookie, _leave(""); } +/* + * Get a reference to a cookie. + */ +struct fscache_cookie *fscache_cookie_get(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + int ref; + + __refcount_inc(&cookie->ref, &ref); + trace_fscache_cookie(cookie->debug_id, ref + 1, where); + return cookie; +} + /* * check the consistency between the netfs inode and the backing cache * @@ -1003,7 +1014,7 @@ static int fscache_cookies_seq_show(struct seq_file *m, void *v) "%08x %08x %5u %5u %3u %s %03lx %-16s %px", cookie->debug_id, cookie->parent ? cookie->parent->debug_id : 0, - atomic_read(&cookie->usage), + refcount_read(&cookie->ref), atomic_read(&cookie->n_children), atomic_read(&cookie->n_active), type, diff --git a/fs/fscache/fsdef.c b/fs/fscache/fsdef.c index 5f8f6fe243fe..0402673c680e 100644 --- a/fs/fscache/fsdef.c +++ b/fs/fscache/fsdef.c @@ -46,7 +46,7 @@ static struct fscache_cookie_def fscache_fsdef_index_def = { struct fscache_cookie fscache_fsdef_index = { .debug_id = 1, - .usage = ATOMIC_INIT(1), + .ref = REFCOUNT_INIT(1), .n_active = ATOMIC_INIT(1), .lock = __SPIN_LOCK_UNLOCKED(fscache_fsdef_index.lock), .backing_objects = HLIST_HEAD_INIT, diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 345105dbbfd1..c3e4804b8fcb 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -54,9 +54,18 @@ extern struct fscache_cookie *fscache_alloc_cookie(struct fscache_cookie *, const void *, size_t, void *, loff_t); extern struct fscache_cookie *fscache_hash_cookie(struct fscache_cookie *); +extern struct fscache_cookie *fscache_cookie_get(struct fscache_cookie *, + enum fscache_cookie_trace); extern void fscache_cookie_put(struct fscache_cookie *, enum fscache_cookie_trace); +static inline void fscache_cookie_see(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref), + where); +} + /* * fsdef.c */ @@ -286,14 +295,6 @@ static inline void fscache_raise_event(struct fscache_object *object, fscache_enqueue_object(object); } -static inline void fscache_cookie_get(struct fscache_cookie *cookie, - enum fscache_cookie_trace where) -{ - int usage = atomic_inc_return(&cookie->usage); - - trace_fscache_cookie(cookie->debug_id, usage, where); -} - /* * get an extra reference to a netfs retrieval context */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index ea61e54a6bc5..a4dab5998613 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -123,7 +123,7 @@ struct fscache_netfs { * - indices are created on disk just-in-time */ struct fscache_cookie { - atomic_t usage; /* number of users of this cookie */ + refcount_t ref; /* number of users of this cookie */ atomic_t n_children; /* number of children of this cookie */ atomic_t n_active; /* number of active users of netfs ptrs */ unsigned int debug_id; diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 19d65d9d4357..446392f5ba83 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -161,26 +161,26 @@ fscache_cookie_traces; TRACE_EVENT(fscache_cookie, TP_PROTO(unsigned int cookie_debug_id, - int usage, + int ref, enum fscache_cookie_trace where), - TP_ARGS(cookie_debug_id, usage, where), + TP_ARGS(cookie_debug_id, ref, where), TP_STRUCT__entry( __field(unsigned int, cookie ) __field(enum fscache_cookie_trace, where ) - __field(int, usage ) + __field(int, ref ) ), TP_fast_assign( __entry->cookie = cookie_debug_id; __entry->where = where; - __entry->usage = usage; + __entry->ref = ref; ), - TP_printk("%s c=%08x u=%d", + TP_printk("%s c=%08x r=%d", __print_symbolic(__entry->where, fscache_cookie_traces), - __entry->cookie, __entry->usage) + __entry->cookie, __entry->ref) ); TRACE_EVENT(fscache_netfs, @@ -212,7 +212,7 @@ TRACE_EVENT(fscache_acquire, __field(unsigned int, cookie ) __field(unsigned int, parent ) __array(char, name, 8 ) - __field(int, p_usage ) + __field(int, p_ref ) __field(int, p_n_children ) __field(u8, p_flags ) ), @@ -220,15 +220,15 @@ TRACE_EVENT(fscache_acquire, TP_fast_assign( __entry->cookie = cookie->debug_id; __entry->parent = cookie->parent->debug_id; - __entry->p_usage = atomic_read(&cookie->parent->usage); + __entry->p_ref = refcount_read(&cookie->parent->ref); __entry->p_n_children = atomic_read(&cookie->parent->n_children); __entry->p_flags = cookie->parent->flags; memcpy(__entry->name, cookie->def->name, 8); __entry->name[7] = 0; ), - TP_printk("c=%08x p=%08x pu=%d pc=%d pf=%02x n=%s", - __entry->cookie, __entry->parent, __entry->p_usage, + TP_printk("c=%08x p=%08x pr=%d pc=%d pf=%02x n=%s", + __entry->cookie, __entry->parent, __entry->p_ref, __entry->p_n_children, __entry->p_flags, __entry->name) ); @@ -240,7 +240,7 @@ TRACE_EVENT(fscache_relinquish, TP_STRUCT__entry( __field(unsigned int, cookie ) __field(unsigned int, parent ) - __field(int, usage ) + __field(int, ref ) __field(int, n_children ) __field(int, n_active ) __field(u8, flags ) @@ -250,15 +250,15 @@ TRACE_EVENT(fscache_relinquish, TP_fast_assign( __entry->cookie = cookie->debug_id; __entry->parent = cookie->parent->debug_id; - __entry->usage = atomic_read(&cookie->usage); + __entry->ref = refcount_read(&cookie->ref); __entry->n_children = atomic_read(&cookie->n_children); __entry->n_active = atomic_read(&cookie->n_active); __entry->flags = cookie->flags; __entry->retire = retire; ), - TP_printk("c=%08x u=%d p=%08x Nc=%d Na=%d f=%02x r=%u", - __entry->cookie, __entry->usage, + TP_printk("c=%08x r=%d p=%08x Nc=%d Na=%d f=%02x r=%u", + __entry->cookie, __entry->ref, __entry->parent, __entry->n_children, __entry->n_active, __entry->flags, __entry->retire) ); @@ -270,7 +270,7 @@ TRACE_EVENT(fscache_enable, TP_STRUCT__entry( __field(unsigned int, cookie ) - __field(int, usage ) + __field(int, ref ) __field(int, n_children ) __field(int, n_active ) __field(u8, flags ) @@ -278,14 +278,14 @@ TRACE_EVENT(fscache_enable, TP_fast_assign( __entry->cookie = cookie->debug_id; - __entry->usage = atomic_read(&cookie->usage); + __entry->ref = refcount_read(&cookie->ref); __entry->n_children = atomic_read(&cookie->n_children); __entry->n_active = atomic_read(&cookie->n_active); __entry->flags = cookie->flags; ), - TP_printk("c=%08x u=%d Nc=%d Na=%d f=%02x", - __entry->cookie, __entry->usage, + TP_printk("c=%08x r=%d Nc=%d Na=%d f=%02x", + __entry->cookie, __entry->ref, __entry->n_children, __entry->n_active, __entry->flags) ); @@ -296,7 +296,7 @@ TRACE_EVENT(fscache_disable, TP_STRUCT__entry( __field(unsigned int, cookie ) - __field(int, usage ) + __field(int, ref ) __field(int, n_children ) __field(int, n_active ) __field(u8, flags ) @@ -304,14 +304,14 @@ TRACE_EVENT(fscache_disable, TP_fast_assign( __entry->cookie = cookie->debug_id; - __entry->usage = atomic_read(&cookie->usage); + __entry->ref = refcount_read(&cookie->ref); __entry->n_children = atomic_read(&cookie->n_children); __entry->n_active = atomic_read(&cookie->n_active); __entry->flags = cookie->flags; ), - TP_printk("c=%08x u=%d Nc=%d Na=%d f=%02x", - __entry->cookie, __entry->usage, + TP_printk("c=%08x r=%d Nc=%d Na=%d f=%02x", + __entry->cookie, __entry->ref, __entry->n_children, __entry->n_active, __entry->flags) ); -- cgit v1.2.3 From 0dc3ad3f859d3a65b335c861ec342d31d91e8bc8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 27 Aug 2021 21:21:25 +0200 Subject: Revert "bus: mhi: Add inbound buffers allocation flag" This reverts commit 0092a1e3f7636ff4e202a41b0320690699247e22 This should be reverted in the char-misc-next branch to make merging with Linus's branch possible due to issues with the mhi code that was found in the networking tree. Link: https://lore.kernel.org/r/20210827175852.GB15018@thinkpad Reported-by: Manivannan Sadhasivam Reported-by: Stephen Rothwell Cc: Arnd Bergmann Cc: Bhaumik Bhatt Cc: Hemant Kumar Cc: Jakub Kicinski Cc: Kalle Valo Cc: Loic Poulain Cc: Manivannan Sadhasivam Signed-off-by: Greg Kroah-Hartman --- drivers/bus/mhi/core/internal.h | 2 +- drivers/bus/mhi/core/main.c | 9 +++------ drivers/net/mhi/net.c | 2 +- drivers/net/wwan/mhi_wwan_ctrl.c | 2 +- include/linux/mhi.h | 7 +------ net/qrtr/mhi.c | 2 +- 6 files changed, 8 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h index 721739c5e0d5..3a732afaf73e 100644 --- a/drivers/bus/mhi/core/internal.h +++ b/drivers/bus/mhi/core/internal.h @@ -682,7 +682,7 @@ void mhi_rddm_prepare(struct mhi_controller *mhi_cntrl, struct image_info *img_info); void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl); int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan, unsigned int flags); + struct mhi_chan *mhi_chan); int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan); void mhi_deinit_chan_ctxt(struct mhi_controller *mhi_cntrl, diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index c01ec2fef02c..b15c5bc37dd4 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -1430,7 +1430,7 @@ exit_unprepare_channel: } int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan, unsigned int flags) + struct mhi_chan *mhi_chan) { int ret = 0; struct device *dev = &mhi_chan->mhi_dev->dev; @@ -1455,9 +1455,6 @@ int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, if (ret) goto error_pm_state; - if (mhi_chan->dir == DMA_FROM_DEVICE) - mhi_chan->pre_alloc = !!(flags & MHI_CH_INBOUND_ALLOC_BUFS); - /* Pre-allocate buffer for xfer ring */ if (mhi_chan->pre_alloc) { int nr_el = get_nr_avail_ring_elements(mhi_cntrl, @@ -1613,7 +1610,7 @@ void mhi_reset_chan(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan) } /* Move channel to start state */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags) +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) { int ret, dir; struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl; @@ -1624,7 +1621,7 @@ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags) if (!mhi_chan) continue; - ret = mhi_prepare_channel(mhi_cntrl, mhi_chan, flags); + ret = mhi_prepare_channel(mhi_cntrl, mhi_chan); if (ret) goto error_open_chan; } diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index 11be6bcdd551..e60e38c1f09d 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -335,7 +335,7 @@ static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id, u64_stats_init(&mhi_netdev->stats.tx_syncp); /* Start MHI channels */ - err = mhi_prepare_for_transfer(mhi_dev, 0); + err = mhi_prepare_for_transfer(mhi_dev); if (err) goto out_err; diff --git a/drivers/net/wwan/mhi_wwan_ctrl.c b/drivers/net/wwan/mhi_wwan_ctrl.c index d0a98f34c54d..e4d0f696687f 100644 --- a/drivers/net/wwan/mhi_wwan_ctrl.c +++ b/drivers/net/wwan/mhi_wwan_ctrl.c @@ -110,7 +110,7 @@ static int mhi_wwan_ctrl_start(struct wwan_port *port) int ret; /* Start mhi device's channel(s) */ - ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev, 0); + ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev); if (ret) return ret; diff --git a/include/linux/mhi.h b/include/linux/mhi.h index b8ca6943f0b7..9c347f558b8c 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -721,13 +721,8 @@ void mhi_device_put(struct mhi_device *mhi_dev); * host and device execution environments match and * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels - * @flags: MHI channel flags */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, - unsigned int flags); - -/* Automatically allocate and queue inbound buffers */ -#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0) +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c index c609cb724c25..c269c539d1c4 100644 --- a/net/qrtr/mhi.c +++ b/net/qrtr/mhi.c @@ -84,7 +84,7 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, int rc; /* start channels */ - rc = mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS); + rc = mhi_prepare_for_transfer(mhi_dev); if (rc) return rc; -- cgit v1.2.3 From 3a3f976639f267823e443fdd8bffa03848fa1c3f Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Fri, 27 Aug 2021 14:37:14 -0400 Subject: SUNRPC keep track of number of transports to unique addresses Currently, xprt_switch keeps a number of all xprts (xps_nxprts) that were added to the switch regardless of whethere it's an nconnect transport or a transport to a trunkable address. Introduce a new counter to keep track of transports to unique destination addresses per xprt_switch. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xprtmultipath.h | 1 + net/sunrpc/clnt.c | 2 +- net/sunrpc/xprtmultipath.c | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h index b19addc8b715..bbb8a5fa0816 100644 --- a/include/linux/sunrpc/xprtmultipath.h +++ b/include/linux/sunrpc/xprtmultipath.h @@ -18,6 +18,7 @@ struct rpc_xprt_switch { unsigned int xps_id; unsigned int xps_nxprts; unsigned int xps_nactive; + unsigned int xps_nunique_destaddr_xprts; atomic_long_t xps_queuelen; struct list_head xps_xprt_list; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index a5b7f6e34d15..451ac7d031db 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2799,7 +2799,7 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, task = rpc_call_null_helper(clnt, xprt, NULL, RPC_TASK_ASYNC, &rpc_cb_add_xprt_call_ops, data); - + data->xps->xps_nunique_destaddr_xprts++; rpc_put_task(task); success: return 1; diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c index c60820e45082..1693f81aae37 100644 --- a/net/sunrpc/xprtmultipath.c +++ b/net/sunrpc/xprtmultipath.c @@ -139,6 +139,7 @@ struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt, xps->xps_iter_ops = &rpc_xprt_iter_singular; rpc_sysfs_xprt_switch_setup(xps, xprt, gfp_flags); xprt_switch_add_xprt_locked(xps, xprt); + xps->xps_nunique_destaddr_xprts = 1; rpc_sysfs_xprt_setup(xps, xprt, gfp_flags); } -- cgit v1.2.3 From 7e134205f62955369619021a695cd78fefd32451 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Fri, 27 Aug 2021 14:37:17 -0400 Subject: NFSv4 introduce max_connect mount options This option will control up to how many xprts can the client establish to the server with a distinct address (that means nconnect connections are not counted towards this new limit). This patch is setting up nfs structures to keeep track of the max_connect limit (does not enforce it). The default value is kept at 1 so that no current mounts that don't want any additional connections would be effected. The maximum value is set at 16. Mounts to DS are not limited to default value of 1 but instead set to the maximum default value of 16 (NFS_MAX_TRANSPORTS). Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- fs/nfs/client.c | 1 + fs/nfs/fs_context.c | 7 +++++++ fs/nfs/internal.h | 2 ++ fs/nfs/nfs4client.c | 12 ++++++++++-- fs/nfs/super.c | 2 ++ include/linux/nfs_fs.h | 5 +++++ include/linux/nfs_fs_sb.h | 1 + 7 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 330f65727c45..486dec59972b 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -179,6 +179,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) clp->cl_proto = cl_init->proto; clp->cl_nconnect = cl_init->nconnect; + clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1; clp->cl_net = get_net(cl_init->net); clp->cl_principal = "*"; diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index d95c9a39bc70..0d444a90f513 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -60,6 +60,7 @@ enum nfs_param { Opt_mountvers, Opt_namelen, Opt_nconnect, + Opt_max_connect, Opt_port, Opt_posix, Opt_proto, @@ -158,6 +159,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_u32 ("mountvers", Opt_mountvers), fsparam_u32 ("namlen", Opt_namelen), fsparam_u32 ("nconnect", Opt_nconnect), + fsparam_u32 ("max_connect", Opt_max_connect), fsparam_string("nfsvers", Opt_vers), fsparam_u32 ("port", Opt_port), fsparam_flag_no("posix", Opt_posix), @@ -770,6 +772,11 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, goto out_of_bounds; ctx->nfs_server.nconnect = result.uint_32; break; + case Opt_max_connect: + if (result.uint_32 < 1 || result.uint_32 > NFS_MAX_TRANSPORTS) + goto out_of_bounds; + ctx->nfs_server.max_connect = result.uint_32; + break; case Opt_lookupcache: switch (result.uint_32) { case Opt_lookupcache_all: diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index a36af04188c2..66fc936834f2 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -67,6 +67,7 @@ struct nfs_client_initdata { int proto; u32 minorversion; unsigned int nconnect; + unsigned int max_connect; struct net *net; const struct rpc_timeout *timeparms; const struct cred *cred; @@ -121,6 +122,7 @@ struct nfs_fs_context { int port; unsigned short protocol; unsigned short nconnect; + unsigned short max_connect; unsigned short export_path_len; } nfs_server; diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 28431acd1230..270caa1805a2 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -865,6 +865,7 @@ static int nfs4_set_client(struct nfs_server *server, const char *ip_addr, int proto, const struct rpc_timeout *timeparms, u32 minorversion, unsigned int nconnect, + unsigned int max_connect, struct net *net) { struct nfs_client_initdata cl_init = { @@ -883,6 +884,8 @@ static int nfs4_set_client(struct nfs_server *server, if (minorversion == 0) __set_bit(NFS_CS_REUSEPORT, &cl_init.init_flags); + else + cl_init.max_connect = max_connect; if (proto == XPRT_TRANSPORT_TCP) cl_init.nconnect = nconnect; @@ -952,8 +955,10 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, return ERR_PTR(-EINVAL); cl_init.hostname = buf; - if (mds_clp->cl_nconnect > 1 && ds_proto == XPRT_TRANSPORT_TCP) + if (mds_clp->cl_nconnect > 1 && ds_proto == XPRT_TRANSPORT_TCP) { cl_init.nconnect = mds_clp->cl_nconnect; + cl_init.max_connect = NFS_MAX_TRANSPORTS; + } if (mds_srv->flags & NFS_MOUNT_NORESVPORT) __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); @@ -1122,6 +1127,7 @@ static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc) &timeparms, ctx->minorversion, ctx->nfs_server.nconnect, + ctx->nfs_server.max_connect, fc->net_ns); if (error < 0) return error; @@ -1211,6 +1217,7 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc) parent_server->client->cl_timeout, parent_client->cl_mvops->minor_version, parent_client->cl_nconnect, + parent_client->cl_max_connect, parent_client->cl_net); if (!error) goto init_server; @@ -1226,6 +1233,7 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc) parent_server->client->cl_timeout, parent_client->cl_mvops->minor_version, parent_client->cl_nconnect, + parent_client->cl_max_connect, parent_client->cl_net); if (error < 0) goto error; @@ -1323,7 +1331,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, error = nfs4_set_client(server, hostname, sap, salen, buf, clp->cl_proto, clnt->cl_timeout, clp->cl_minorversion, - clp->cl_nconnect, net); + clp->cl_nconnect, clp->cl_max_connect, net); clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); if (error != 0) { nfs_server_insert_lists(server); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index fe58525cfed4..e65c83494c05 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -480,6 +480,8 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, if (clp->cl_nconnect > 0) seq_printf(m, ",nconnect=%u", clp->cl_nconnect); if (version == 4) { + if (clp->cl_max_connect > 1) + seq_printf(m, ",max_connect=%u", clp->cl_max_connect); if (nfss->port != NFS_PORT) seq_printf(m, ",port=%u", nfss->port); } else diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index ce6474594872..b9a8b925db43 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -40,6 +40,11 @@ #include +/* + * These are the default for number of transports to different server IPs + */ +#define NFS_MAX_TRANSPORTS 16 + /* * These are the default flags for swap requests */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index d71a0e90faeb..2a9acbfe00f0 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -62,6 +62,7 @@ struct nfs_client { u32 cl_minorversion;/* NFSv4 minorversion */ unsigned int cl_nconnect; /* Number of connections */ + unsigned int cl_max_connect; /* max number of xprts allowed */ const char * cl_principal; /* used for machine cred */ #if IS_ENABLED(CONFIG_NFS_V4) -- cgit v1.2.3 From dc48e0abee245e2f0361bd8d4e3b00f70450fab2 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Fri, 27 Aug 2021 14:37:18 -0400 Subject: SUNRPC enforce creation of no more than max_connect xprts If we are adding new transports via rpc_clnt_test_and_add_xprt() then check if we've reached the limit. Currently only pnfs path adds transports via that function but this is done in preparation when the client would add new transports when session trunking is detected. A warning is logged if the limit is reached. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- fs/nfs/client.c | 1 + include/linux/sunrpc/clnt.h | 2 ++ net/sunrpc/clnt.c | 9 +++++++++ 3 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 486dec59972b..23e165d5ec9c 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -541,6 +541,7 @@ int nfs_create_rpc_client(struct nfs_client *clp, clnt->cl_principal = clp->cl_principal; clp->cl_rpcclient = clnt; + clnt->cl_max_connect = clp->cl_max_connect; return 0; } EXPORT_SYMBOL_GPL(nfs_create_rpc_client); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index b2edd5fc2f0c..a4661646adc9 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -82,6 +82,7 @@ struct rpc_clnt { struct work_struct cl_work; }; const struct cred *cl_cred; + unsigned int cl_max_connect; /* max number of transports not to the same IP */ }; /* @@ -136,6 +137,7 @@ struct rpc_create_args { char *client_name; struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ const struct cred *cred; + unsigned int max_connect; }; struct rpc_add_xprt_test { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 451ac7d031db..f056ff931444 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2787,6 +2787,15 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, struct rpc_cb_add_xprt_calldata *data; struct rpc_task *task; + if (xps->xps_nunique_destaddr_xprts + 1 > clnt->cl_max_connect) { + rcu_read_lock(); + pr_warn("SUNRPC: reached max allowed number (%d) did not add " + "transport to server: %s\n", clnt->cl_max_connect, + rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR)); + rcu_read_unlock(); + return -EINVAL; + } + data = kmalloc(sizeof(*data), GFP_NOFS); if (!data) return -ENOMEM; -- cgit v1.2.3 From 25572c818d2e40b5d7231a9dc49bd45a6b6c3dfa Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 27 Aug 2021 15:15:26 -0500 Subject: hwmon: (k10temp) Add support for yellow carp Yellow carp matches same behavior as green sardine and other Zen3 products, but have different CCD offsets. Signed-off-by: Mario Limonciello Acked-by: Borislav Petkov Link: https://lore.kernel.org/r/20210827201527.24454-3-mario.limonciello@amd.com Signed-off-by: Guenter Roeck --- arch/x86/kernel/amd_nb.c | 5 +++++ drivers/hwmon/k10temp.c | 5 +++++ include/linux/pci_ids.h | 1 + 3 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 23dda362dc0f..c92c9c774c0e 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -25,6 +25,8 @@ #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 #define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 +#define PCI_DEVICE_ID_AMD_19H_M40H_ROOT 0x14b5 +#define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4 0x167d #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e /* Protect the PCI config register pairs used for SMN and DF indirect access. */ @@ -37,6 +39,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_ROOT) }, {} }; @@ -58,6 +61,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, {} }; @@ -74,6 +78,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 159dbad73d82..38bc35ac8135 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -459,6 +459,10 @@ static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id) data->ccd_offset = 0x154; k10temp_get_ccd_support(pdev, data, 8); break; + case 0x40 ... 0x4f: /* Yellow Carp */ + data->ccd_offset = 0x300; + k10temp_get_ccd_support(pdev, data, 8); + break; } } else { data->read_htcreg = read_htcreg_pci; @@ -499,6 +503,7 @@ static const struct pci_device_id k10temp_id_table[] = { { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, { PCI_VDEVICE(HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) }, {} diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 4bac1831de80..3d50d5bbf037 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -555,6 +555,7 @@ #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443 #define PCI_DEVICE_ID_AMD_19H_DF_F3 0x1653 +#define PCI_DEVICE_ID_AMD_19H_M40H_DF_F3 0x167c #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F3 0x166d #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 -- cgit v1.2.3 From b542e383d8c005f06a131e2b40d5889b812f19c6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 13:01:59 +0200 Subject: eventfd: Make signal recursion protection a task bit The recursion protection for eventfd_signal() is based on a per CPU variable and relies on the !RT semantics of spin_lock_irqsave() for protecting this per CPU variable. On RT kernels spin_lock_irqsave() neither disables preemption nor interrupts which allows the spin lock held section to be preempted. If the preempting task invokes eventfd_signal() as well, then the recursion warning triggers. Paolo suggested to protect the per CPU variable with a local lock, but that's heavyweight and actually not necessary. The goal of this protection is to prevent the task stack from overflowing, which can be achieved with a per task recursion protection as well. Replace the per CPU variable with a per task bit similar to other recursion protection bits like task_struct::in_page_owner. This works on both !RT and RT kernels and removes as a side effect the extra per CPU storage. No functional change for !RT kernels. Reported-by: Daniel Bristot de Oliveira Signed-off-by: Thomas Gleixner Tested-by: Daniel Bristot de Oliveira Acked-by: Jason Wang Cc: Al Viro Link: https://lore.kernel.org/r/87wnp9idso.ffs@tglx --- fs/aio.c | 2 +- fs/eventfd.c | 12 +++++------- include/linux/eventfd.h | 11 +++++------ include/linux/sched.h | 4 ++++ 4 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/aio.c b/fs/aio.c index 76ce0cc3ee4e..51b08ab01dff 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1695,7 +1695,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); req->done = true; - if (iocb->ki_eventfd && eventfd_signal_count()) { + if (iocb->ki_eventfd && eventfd_signal_allowed()) { iocb = NULL; INIT_WORK(&req->work, aio_poll_put_work); schedule_work(&req->work); diff --git a/fs/eventfd.c b/fs/eventfd.c index e265b6dd4f34..3627dd7d25db 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -25,8 +25,6 @@ #include #include -DEFINE_PER_CPU(int, eventfd_wake_count); - static DEFINE_IDA(eventfd_ida); struct eventfd_ctx { @@ -67,21 +65,21 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) * Deadlock or stack overflow issues can happen if we recurse here * through waitqueue wakeup handlers. If the caller users potentially * nested waitqueues with custom wakeup handlers, then it should - * check eventfd_signal_count() before calling this function. If - * it returns true, the eventfd_signal() call should be deferred to a + * check eventfd_signal_allowed() before calling this function. If + * it returns false, the eventfd_signal() call should be deferred to a * safe context. */ - if (WARN_ON_ONCE(this_cpu_read(eventfd_wake_count))) + if (WARN_ON_ONCE(current->in_eventfd_signal)) return 0; spin_lock_irqsave(&ctx->wqh.lock, flags); - this_cpu_inc(eventfd_wake_count); + current->in_eventfd_signal = 1; if (ULLONG_MAX - ctx->count < n) n = ULLONG_MAX - ctx->count; ctx->count += n; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLIN); - this_cpu_dec(eventfd_wake_count); + current->in_eventfd_signal = 0; spin_unlock_irqrestore(&ctx->wqh.lock, flags); return n; diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index fa0a524baed0..305d5f19093b 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -14,6 +14,7 @@ #include #include #include +#include /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining @@ -43,11 +44,9 @@ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *w __u64 *cnt); void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt); -DECLARE_PER_CPU(int, eventfd_wake_count); - -static inline bool eventfd_signal_count(void) +static inline bool eventfd_signal_allowed(void) { - return this_cpu_read(eventfd_wake_count); + return !current->in_eventfd_signal; } #else /* CONFIG_EVENTFD */ @@ -78,9 +77,9 @@ static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, return -ENOSYS; } -static inline bool eventfd_signal_count(void) +static inline bool eventfd_signal_allowed(void) { - return false; + return true; } static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) diff --git a/include/linux/sched.h b/include/linux/sched.h index 3bb9fecfdaa1..6421a9a8b4ca 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -864,6 +864,10 @@ struct task_struct { /* Used by page_owner=on to detect recursion in page tracking. */ unsigned in_page_owner:1; #endif +#ifdef CONFIG_EVENTFD + /* Recursion prevention for eventfd_signal() */ + unsigned in_eventfd_signal:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ -- cgit v1.2.3 From 81f9ebd43659320a88cae8ed5124c50b4d47ab66 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 22 Aug 2021 01:58:00 +0200 Subject: ssb: Drop legacy header include The SSB header only uses the legacy header to get struct gpio_chip so inluce which is the right include to deal with gpio_chip. Cc: Michael Buesch Cc: Kalle Valo Signed-off-by: Linus Walleij Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20210821235800.138817-1-linus.walleij@linaro.org --- include/linux/ssb/ssb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 0d5a2691e7e9..f9b53acb4e02 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -7,7 +7,7 @@ #include #include #include -#include +#include #include #include #include -- cgit v1.2.3 From 8d4be124062bddbb2bcb887702a0601b790b9a83 Mon Sep 17 00:00:00 2001 From: Jing Yangyang Date: Mon, 23 Aug 2021 23:13:41 -0700 Subject: ssb: fix boolreturn.cocci warning ./include/linux/ssb/ssb_driver_extif.h:200:8-9:WARNING: return of 0/1 in function 'ssb_extif_available' with return type bool Return statements in functions returning bool should use true/false instead of 1/0. Generated by: scripts/coccinelle/misc/boolreturn.cocci Reported-by: Zeal Robot Signed-off-by: Jing Yangyang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20210824061341.59255-1-deng.changcheng@zte.com.cn --- include/linux/ssb/ssb_driver_extif.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb_driver_extif.h b/include/linux/ssb/ssb_driver_extif.h index 3f8bc973d67d..19253bfacd1a 100644 --- a/include/linux/ssb/ssb_driver_extif.h +++ b/include/linux/ssb/ssb_driver_extif.h @@ -197,7 +197,7 @@ struct ssb_extif { static inline bool ssb_extif_available(struct ssb_extif *extif) { - return 0; + return false; } static inline -- cgit v1.2.3 From ab959c7d4ea086852f35c7ff20ecd79b7471cfad Mon Sep 17 00:00:00 2001 From: Biju Das Date: Fri, 6 Aug 2021 10:53:21 +0100 Subject: dmaengine: Extend the dma_slave_width for 128 bytes Add DMA_SLAVE_BUSWIDTH_128_BYTES to dma_slave_width for DMA engines and users to select 128 bytes as bus width. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210806095322.2326-3-biju.das.jz@bp.renesas.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 93c3ca5fdafd..e5c2c9e71bf1 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -380,6 +380,7 @@ enum dma_slave_buswidth { DMA_SLAVE_BUSWIDTH_16_BYTES = 16, DMA_SLAVE_BUSWIDTH_32_BYTES = 32, DMA_SLAVE_BUSWIDTH_64_BYTES = 64, + DMA_SLAVE_BUSWIDTH_128_BYTES = 128, }; /** @@ -398,7 +399,7 @@ enum dma_slave_buswidth { * @src_addr_width: this is the width in bytes of the source (RX) * register where DMA data shall be read. If the source * is memory this may be ignored depending on architecture. - * Legal values: 1, 2, 3, 4, 8, 16, 32, 64. + * Legal values: 1, 2, 3, 4, 8, 16, 32, 64, 128. * @dst_addr_width: same as src_addr_width but for destination * target (TX) mutatis mutandis. * @src_maxburst: the maximum number of words (note: words, as in -- cgit v1.2.3 From d7e7747ac5c2496c98291944c6066adaa9f3b975 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 26 Aug 2021 15:54:22 +0200 Subject: netfilter: refuse insertion if chain has grown too large Also add a stat counter for this that gets exported both via old /proc interface and ctnetlink. Assuming the old default size of 16536 buckets and max hash occupancy of 64k, this results in 128k insertions (origin+reply), so ~8 entries per chain on average. The revised settings in this series will result in about two entries per bucket on average. This allows a hard-limit ceiling of 64. This is not tunable at the moment, but its possible to either increase nf_conntrack_buckets or decrease nf_conntrack_max to reduce average lengths. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 1 + include/uapi/linux/netfilter/nfnetlink_conntrack.h | 1 + net/netfilter/nf_conntrack_core.c | 42 ++++++++++++++++++---- net/netfilter/nf_conntrack_netlink.c | 4 ++- net/netfilter/nf_conntrack_standalone.c | 4 +-- 5 files changed, 42 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 0c7d8d1e945d..700ea077ce2d 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -18,6 +18,7 @@ struct ip_conntrack_stat { unsigned int expect_create; unsigned int expect_delete; unsigned int search_restart; + unsigned int chaintoolong; }; #define NFCT_INFOMASK 7UL diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index d8484be72fdc..5ade231f497b 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -257,6 +257,7 @@ enum ctattr_stats_cpu { CTA_STATS_ERROR, CTA_STATS_SEARCH_RESTART, CTA_STATS_CLASH_RESOLVE, + CTA_STATS_CHAIN_TOOLONG, __CTA_STATS_MAX, }; #define CTA_STATS_MAX (__CTA_STATS_MAX - 1) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index da2650f872e1..94e18fb9690d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -77,6 +77,8 @@ static __read_mostly bool nf_conntrack_locks_all; #define GC_SCAN_INTERVAL (120u * HZ) #define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) +#define MAX_CHAINLEN 64u + static struct conntrack_gc_work conntrack_gc_work; void nf_conntrack_lock(spinlock_t *lock) __acquires(lock) @@ -840,7 +842,9 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; + unsigned int chainlen = 0; unsigned int sequence; + int err = -EEXIST; zone = nf_ct_zone(ct); @@ -854,15 +858,24 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); /* See if there's one in the list already, including reverse */ - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode) + if (chainlen++ > MAX_CHAINLEN) + goto chaintoolong; + } + + chainlen = 0; + + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; + if (chainlen++ > MAX_CHAINLEN) + goto chaintoolong; + } smp_wmb(); /* The caller holds a reference to this object */ @@ -872,11 +885,13 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) NF_CT_STAT_INC(net, insert); local_bh_enable(); return 0; - +chaintoolong: + NF_CT_STAT_INC(net, chaintoolong); + err = -ENOSPC; out: nf_conntrack_double_unlock(hash, reply_hash); local_bh_enable(); - return -EEXIST; + return err; } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); @@ -1089,6 +1104,7 @@ int __nf_conntrack_confirm(struct sk_buff *skb) { const struct nf_conntrack_zone *zone; + unsigned int chainlen = 0, sequence; unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; @@ -1096,7 +1112,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; - unsigned int sequence; int ret = NF_DROP; ct = nf_ct_get(skb, &ctinfo); @@ -1156,15 +1171,28 @@ __nf_conntrack_confirm(struct sk_buff *skb) /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're not in the hash. If there is, we lost race. */ - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; + if (chainlen++ > MAX_CHAINLEN) + goto chaintoolong; + } - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode) + chainlen = 0; + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; + if (chainlen++ > MAX_CHAINLEN) { +chaintoolong: + nf_ct_add_to_dying_list(ct); + NF_CT_STAT_INC(net, chaintoolong); + NF_CT_STAT_INC(net, insert_failed); + ret = NF_DROP; + goto dying; + } + } /* Timer relative to confirmation time, not original setting time, otherwise we'd get timer wrap in diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index e81af33b233b..3f081ae08266 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2484,7 +2484,9 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, nla_put_be32(skb, CTA_STATS_SEARCH_RESTART, htonl(st->search_restart)) || nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE, - htonl(st->clash_resolve))) + htonl(st->clash_resolve)) || + nla_put_be32(skb, CTA_STATS_CHAIN_TOOLONG, + htonl(st->chaintoolong))) goto nla_put_failure; nlmsg_end(skb, nlh); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index e84b499b7bfa..f94ebd5194b5 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -429,7 +429,7 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) unsigned int nr_conntracks; if (v == SEQ_START_TOKEN) { - seq_puts(seq, "entries clashres found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n"); + seq_puts(seq, "entries clashres found new invalid ignore delete chainlength insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n"); return 0; } @@ -444,7 +444,7 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) st->invalid, 0, 0, - 0, + st->chaintoolong, st->insert, st->insert_failed, st->drop, -- cgit v1.2.3 From a61590892ef097c180144fa469abe2256b9ae715 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 26 Aug 2021 20:53:42 +0200 Subject: PCI/VPD: Stop exporting pci_vpd_find_tag() Now that the last users have been migrated to pci_vpd_find_ro_keyword() we can stop exporting this function. It's still used in VPD core code. Link: https://lore.kernel.org/r/71131eca-0502-7878-365f-30b6614161cf@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- drivers/pci/vpd.c | 3 +-- include/linux/pci.h | 11 ----------- 2 files changed, 1 insertion(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 01e57594781e..5726fbb7a03f 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -296,7 +296,7 @@ void *pci_vpd_alloc(struct pci_dev *dev, unsigned int *size) } EXPORT_SYMBOL_GPL(pci_vpd_alloc); -int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt) +static int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt) { int i = 0; @@ -310,7 +310,6 @@ int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt) return -ENOENT; } -EXPORT_SYMBOL_GPL(pci_vpd_find_tag); int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, unsigned int len, const char *kw) diff --git a/include/linux/pci.h b/include/linux/pci.h index 827b7eefd550..4fb233e374c5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2339,17 +2339,6 @@ static inline u8 pci_vpd_info_field_size(const u8 *info_field) */ void *pci_vpd_alloc(struct pci_dev *dev, unsigned int *size); -/** - * pci_vpd_find_tag - Locates the Resource Data Type tag provided - * @buf: Pointer to buffered vpd data - * @len: The length of the vpd buffer - * @rdt: The Resource Data Type to search for - * - * Returns the index where the Resource Data Type was found or - * -ENOENT otherwise. - */ -int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt); - /** * pci_vpd_find_info_keyword - Locates an information field keyword in the VPD * @buf: Pointer to buffered vpd data -- cgit v1.2.3 From 59b83b29bb5532bbff54a271e0b4f321e28b954f Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 26 Aug 2021 20:54:23 +0200 Subject: PCI/VPD: Stop exporting pci_vpd_find_info_keyword() Now that the last users have been migrated to pci_vpd_find_ro_keyword() we can stop exporting this function. It's still used in VPD core code. Link: https://lore.kernel.org/r/96ca2a56-383e-9b61-9cba-4f1e5611dc15@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- drivers/pci/vpd.c | 3 +-- include/linux/pci.h | 13 ------------- 2 files changed, 1 insertion(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 5726fbb7a03f..0e7a5e8a8f17 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -311,7 +311,7 @@ static int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt) return -ENOENT; } -int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, +static int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, unsigned int len, const char *kw) { int i; @@ -327,7 +327,6 @@ int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, return -ENOENT; } -EXPORT_SYMBOL_GPL(pci_vpd_find_info_keyword); /** * pci_read_vpd - Read one entry from Vital Product Data diff --git a/include/linux/pci.h b/include/linux/pci.h index 4fb233e374c5..196cbf4c76a1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2339,19 +2339,6 @@ static inline u8 pci_vpd_info_field_size(const u8 *info_field) */ void *pci_vpd_alloc(struct pci_dev *dev, unsigned int *size); -/** - * pci_vpd_find_info_keyword - Locates an information field keyword in the VPD - * @buf: Pointer to buffered vpd data - * @off: The offset into the buffer at which to begin the search - * @len: The length of the buffer area, relative to off, in which to search - * @kw: The keyword to search for - * - * Returns the index where the information field keyword was found or - * -ENOENT otherwise. - */ -int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, - unsigned int len, const char *kw); - /** * pci_vpd_find_ro_info_keyword - Locate info field keyword in VPD RO section * @buf: Pointer to buffered VPD data -- cgit v1.2.3 From acfbb1b8a494d7bfd316dfb363a820e6df637e8d Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 26 Aug 2021 20:55:43 +0200 Subject: PCI/VPD: Add pci_vpd_find_id_string() Add a pci_vpd_find_id_string() API function to retrieve the ID string from VPD. This way callers don't need pci_vpd_lrdt_size() any longer, and it can be made private to the VPD core. Link: https://lore.kernel.org/r/c5225bf6-8d29-970d-e271-0d7b52252630@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- drivers/pci/vpd.c | 6 ++++++ include/linux/pci.h | 10 ++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index b7bf014ccc5f..79712b3d17b6 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -320,6 +320,12 @@ static int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt, unsigned in return -ENOENT; } +int pci_vpd_find_id_string(const u8 *buf, unsigned int len, unsigned int *size) +{ + return pci_vpd_find_tag(buf, len, PCI_VPD_LRDT_ID_STRING, size); +} +EXPORT_SYMBOL_GPL(pci_vpd_find_id_string); + static int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, unsigned int len, const char *kw) { diff --git a/include/linux/pci.h b/include/linux/pci.h index 196cbf4c76a1..ea330ca0501a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2339,6 +2339,16 @@ static inline u8 pci_vpd_info_field_size(const u8 *info_field) */ void *pci_vpd_alloc(struct pci_dev *dev, unsigned int *size); +/** + * pci_vpd_find_id_string - Locate id string in VPD + * @buf: Pointer to buffered VPD data + * @len: The length of the buffer area in which to search + * @size: Pointer to field where length of id string is returned + * + * Returns the index of the id string or -ENOENT if not found. + */ +int pci_vpd_find_id_string(const u8 *buf, unsigned int len, unsigned int *size); + /** * pci_vpd_find_ro_info_keyword - Locate info field keyword in VPD RO section * @buf: Pointer to buffered VPD data -- cgit v1.2.3 From 06e1913d457121a98ee276179734c34dab30f388 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 26 Aug 2021 20:57:01 +0200 Subject: PCI/VPD: Clean up public VPD defines and inline functions After recent introduction of new VPD API functions and user migration these defines and inline functions aren't used outside VPD core any longer. Link: https://lore.kernel.org/r/d33e06bf-bc5e-ece7-bf35-7245ae224d1b@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- drivers/pci/vpd.c | 26 ++++++++++++++++++++ include/linux/pci.h | 69 ----------------------------------------------------- 2 files changed, 26 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 79712b3d17b6..ff600dff4557 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -11,6 +11,32 @@ #include #include "pci.h" +#define PCI_VPD_LRDT_TAG_SIZE 3 +#define PCI_VPD_SRDT_LEN_MASK 0x07 +#define PCI_VPD_SRDT_TAG_SIZE 1 +#define PCI_VPD_STIN_END 0x0f +#define PCI_VPD_INFO_FLD_HDR_SIZE 3 + +static u16 pci_vpd_lrdt_size(const u8 *lrdt) +{ + return (u16)lrdt[1] + ((u16)lrdt[2] << 8); +} + +static u8 pci_vpd_srdt_tag(const u8 *srdt) +{ + return *srdt >> 3; +} + +static u8 pci_vpd_srdt_size(const u8 *srdt) +{ + return *srdt & PCI_VPD_SRDT_LEN_MASK; +} + +static u8 pci_vpd_info_field_size(const u8 *info_field) +{ + return info_field[2]; +} + /* VPD access through PCI 2.2+ VPD capability */ static struct pci_dev *pci_get_func0_dev(struct pci_dev *dev) diff --git a/include/linux/pci.h b/include/linux/pci.h index ea330ca0501a..303034d03c33 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2255,81 +2255,12 @@ int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask); #define PCI_VPD_LRDT_RO_DATA PCI_VPD_LRDT_ID(PCI_VPD_LTIN_RO_DATA) #define PCI_VPD_LRDT_RW_DATA PCI_VPD_LRDT_ID(PCI_VPD_LTIN_RW_DATA) -/* Small Resource Data Type Tag Item Names */ -#define PCI_VPD_STIN_END 0x0f /* End */ - -#define PCI_VPD_SRDT_END (PCI_VPD_STIN_END << 3) - -#define PCI_VPD_SRDT_TIN_MASK 0x78 -#define PCI_VPD_SRDT_LEN_MASK 0x07 -#define PCI_VPD_LRDT_TIN_MASK 0x7f - -#define PCI_VPD_LRDT_TAG_SIZE 3 -#define PCI_VPD_SRDT_TAG_SIZE 1 - -#define PCI_VPD_INFO_FLD_HDR_SIZE 3 - #define PCI_VPD_RO_KEYWORD_PARTNO "PN" #define PCI_VPD_RO_KEYWORD_SERIALNO "SN" #define PCI_VPD_RO_KEYWORD_MFR_ID "MN" #define PCI_VPD_RO_KEYWORD_VENDOR0 "V0" #define PCI_VPD_RO_KEYWORD_CHKSUM "RV" -/** - * pci_vpd_lrdt_size - Extracts the Large Resource Data Type length - * @lrdt: Pointer to the beginning of the Large Resource Data Type tag - * - * Returns the extracted Large Resource Data Type length. - */ -static inline u16 pci_vpd_lrdt_size(const u8 *lrdt) -{ - return (u16)lrdt[1] + ((u16)lrdt[2] << 8); -} - -/** - * pci_vpd_lrdt_tag - Extracts the Large Resource Data Type Tag Item - * @lrdt: Pointer to the beginning of the Large Resource Data Type tag - * - * Returns the extracted Large Resource Data Type Tag item. - */ -static inline u16 pci_vpd_lrdt_tag(const u8 *lrdt) -{ - return (u16)(lrdt[0] & PCI_VPD_LRDT_TIN_MASK); -} - -/** - * pci_vpd_srdt_size - Extracts the Small Resource Data Type length - * @srdt: Pointer to the beginning of the Small Resource Data Type tag - * - * Returns the extracted Small Resource Data Type length. - */ -static inline u8 pci_vpd_srdt_size(const u8 *srdt) -{ - return (*srdt) & PCI_VPD_SRDT_LEN_MASK; -} - -/** - * pci_vpd_srdt_tag - Extracts the Small Resource Data Type Tag Item - * @srdt: Pointer to the beginning of the Small Resource Data Type tag - * - * Returns the extracted Small Resource Data Type Tag Item. - */ -static inline u8 pci_vpd_srdt_tag(const u8 *srdt) -{ - return ((*srdt) & PCI_VPD_SRDT_TIN_MASK) >> 3; -} - -/** - * pci_vpd_info_field_size - Extracts the information field length - * @info_field: Pointer to the beginning of an information field header - * - * Returns the extracted information field length. - */ -static inline u8 pci_vpd_info_field_size(const u8 *info_field) -{ - return info_field[2]; -} - /** * pci_vpd_alloc - Allocate buffer and read VPD into it * @dev: PCI device -- cgit v1.2.3 From 4b92d4add5f6dcf21275185c997d6ecb800054cd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 31 Aug 2021 13:48:34 +0200 Subject: drivers: base: cacheinfo: Get rid of DEFINE_SMP_CALL_CACHE_FUNCTION() DEFINE_SMP_CALL_CACHE_FUNCTION() was usefel before the CPU hotplug rework to ensure that the cache related functions are called on the upcoming CPU because the notifier itself could run on any online CPU. The hotplug state machine guarantees that the callbacks are invoked on the upcoming CPU. So there is no need to have this SMP function call obfuscation. That indirection was missed when the hotplug notifiers were converted. This also solves the problem of ARM64 init_cache_level() invoking ACPI functions which take a semaphore in that context. That's invalid as SMP function calls run with interrupts disabled. Running it just from the callback in context of the CPU hotplug thread solves this. Fixes: 8571890e1513 ("arm64: Add support for ACPI based firmware tables") Reported-by: Guenter Roeck Signed-off-by: Thomas Gleixner Tested-by: Guenter Roeck Acked-by: Will Deacon Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/871r69ersb.ffs@tglx --- arch/arm64/kernel/cacheinfo.c | 7 ++----- arch/mips/kernel/cacheinfo.c | 7 ++----- arch/riscv/kernel/cacheinfo.c | 7 ++----- arch/x86/kernel/cpu/cacheinfo.c | 7 ++----- include/linux/cacheinfo.h | 18 ------------------ 5 files changed, 8 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index 7fa6828bb488..587543c6c51c 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -43,7 +43,7 @@ static void ci_leaf_init(struct cacheinfo *this_leaf, this_leaf->type = type; } -static int __init_cache_level(unsigned int cpu) +int init_cache_level(unsigned int cpu) { unsigned int ctype, level, leaves, fw_level; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); @@ -78,7 +78,7 @@ static int __init_cache_level(unsigned int cpu) return 0; } -static int __populate_cache_leaves(unsigned int cpu) +int populate_cache_leaves(unsigned int cpu) { unsigned int level, idx; enum cache_type type; @@ -97,6 +97,3 @@ static int __populate_cache_leaves(unsigned int cpu) } return 0; } - -DEFINE_SMP_CALL_CACHE_FUNCTION(init_cache_level) -DEFINE_SMP_CALL_CACHE_FUNCTION(populate_cache_leaves) diff --git a/arch/mips/kernel/cacheinfo.c b/arch/mips/kernel/cacheinfo.c index 53d8ea7d36e6..495dd058231d 100644 --- a/arch/mips/kernel/cacheinfo.c +++ b/arch/mips/kernel/cacheinfo.c @@ -17,7 +17,7 @@ do { \ leaf++; \ } while (0) -static int __init_cache_level(unsigned int cpu) +int init_cache_level(unsigned int cpu) { struct cpuinfo_mips *c = ¤t_cpu_data; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); @@ -74,7 +74,7 @@ static void fill_cpumask_cluster(int cpu, cpumask_t *cpu_map) cpumask_set_cpu(cpu1, cpu_map); } -static int __populate_cache_leaves(unsigned int cpu) +int populate_cache_leaves(unsigned int cpu) { struct cpuinfo_mips *c = ¤t_cpu_data; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); @@ -114,6 +114,3 @@ static int __populate_cache_leaves(unsigned int cpu) return 0; } - -DEFINE_SMP_CALL_CACHE_FUNCTION(init_cache_level) -DEFINE_SMP_CALL_CACHE_FUNCTION(populate_cache_leaves) diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index d86781357044..90deabfe63ea 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -113,7 +113,7 @@ static void fill_cacheinfo(struct cacheinfo **this_leaf, } } -static int __init_cache_level(unsigned int cpu) +int init_cache_level(unsigned int cpu) { struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); struct device_node *np = of_cpu_device_node_get(cpu); @@ -155,7 +155,7 @@ static int __init_cache_level(unsigned int cpu) return 0; } -static int __populate_cache_leaves(unsigned int cpu) +int populate_cache_leaves(unsigned int cpu) { struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); struct cacheinfo *this_leaf = this_cpu_ci->info_list; @@ -187,6 +187,3 @@ static int __populate_cache_leaves(unsigned int cpu) return 0; } - -DEFINE_SMP_CALL_CACHE_FUNCTION(init_cache_level) -DEFINE_SMP_CALL_CACHE_FUNCTION(populate_cache_leaves) diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index d66af2950e06..b5e36bd0425b 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -985,7 +985,7 @@ static void ci_leaf_init(struct cacheinfo *this_leaf, this_leaf->priv = base->nb; } -static int __init_cache_level(unsigned int cpu) +int init_cache_level(unsigned int cpu) { struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); @@ -1014,7 +1014,7 @@ static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs) id4_regs->id = c->apicid >> index_msb; } -static int __populate_cache_leaves(unsigned int cpu) +int populate_cache_leaves(unsigned int cpu) { unsigned int idx, ret; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); @@ -1033,6 +1033,3 @@ static int __populate_cache_leaves(unsigned int cpu) return 0; } - -DEFINE_SMP_CALL_CACHE_FUNCTION(init_cache_level) -DEFINE_SMP_CALL_CACHE_FUNCTION(populate_cache_leaves) diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 4f72b47973c3..2f909ed084c6 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -79,24 +79,6 @@ struct cpu_cacheinfo { bool cpu_map_populated; }; -/* - * Helpers to make sure "func" is executed on the cpu whose cache - * attributes are being detected - */ -#define DEFINE_SMP_CALL_CACHE_FUNCTION(func) \ -static inline void _##func(void *ret) \ -{ \ - int cpu = smp_processor_id(); \ - *(int *)ret = __##func(cpu); \ -} \ - \ -int func(unsigned int cpu) \ -{ \ - int ret; \ - smp_call_function_single(cpu, _##func, &ret, true); \ - return ret; \ -} - struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu); int init_cache_level(unsigned int cpu); int populate_cache_leaves(unsigned int cpu); -- cgit v1.2.3 From ef6c8da71eaffe4e251b0ff2a1d0da96f89fe6b0 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Wed, 1 Sep 2021 15:25:50 +0530 Subject: octeontx2-pf: cn10K: Reserve LMTST lines per core This patch reserves the LMTST lines per cpu instead of separate LMTST lines for NPA(buffer free) and NIX(sqe flush). LMTST line of the core on which SQ or RQ is processed is used for LMTST operation. This patch also replace STEOR with STEORL release semantics and updates driver name in ethtool file. Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c | 42 ++++++++++------------ .../ethernet/marvell/octeontx2/nic/otx2_common.c | 5 --- .../ethernet/marvell/octeontx2/nic/otx2_common.h | 28 ++++++++------- .../ethernet/marvell/octeontx2/nic/otx2_ethtool.c | 4 +-- .../net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 12 +++---- .../net/ethernet/marvell/octeontx2/nic/otx2_txrx.h | 2 -- include/linux/soc/marvell/octeontx2/asm.h | 11 ++++-- 7 files changed, 49 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index 3cc76f14d2fd..95f21dfdba48 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -27,7 +27,8 @@ int cn10k_lmtst_init(struct otx2_nic *pfvf) { struct lmtst_tbl_setup_req *req; - int qcount, err; + struct otx2_lmt_info *lmt_info; + int err, cpu; if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) { pfvf->hw_ops = &otx2_hw_ops; @@ -35,15 +36,9 @@ int cn10k_lmtst_init(struct otx2_nic *pfvf) } pfvf->hw_ops = &cn10k_hw_ops; - qcount = pfvf->hw.max_queues; - /* LMTST lines allocation - * qcount = num_online_cpus(); - * NPA = TX + RX + XDP. - * NIX = TX * 32 (For Burst SQE flush). - */ - pfvf->tot_lmt_lines = (qcount * 3) + (qcount * 32); - pfvf->npa_lmt_lines = qcount * 3; - pfvf->nix_lmt_size = LMT_BURST_SIZE * LMT_LINE_SIZE; + /* Total LMTLINES = num_online_cpus() * 32 (For Burst flush).*/ + pfvf->tot_lmt_lines = (num_online_cpus() * LMT_BURST_SIZE); + pfvf->hw.lmt_info = alloc_percpu(struct otx2_lmt_info); mutex_lock(&pfvf->mbox.lock); req = otx2_mbox_alloc_msg_lmtst_tbl_setup(&pfvf->mbox); @@ -66,6 +61,13 @@ int cn10k_lmtst_init(struct otx2_nic *pfvf) err = otx2_sync_mbox_msg(&pfvf->mbox); mutex_unlock(&pfvf->mbox.lock); + for_each_possible_cpu(cpu) { + lmt_info = per_cpu_ptr(pfvf->hw.lmt_info, cpu); + lmt_info->lmt_addr = ((u64)pfvf->hw.lmt_base + + (cpu * LMT_BURST_SIZE * LMT_LINE_SIZE)); + lmt_info->lmt_id = cpu * LMT_BURST_SIZE; + } + return 0; } EXPORT_SYMBOL(cn10k_lmtst_init); @@ -74,13 +76,6 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) { struct nix_cn10k_aq_enq_req *aq; struct otx2_nic *pfvf = dev; - struct otx2_snd_queue *sq; - - sq = &pfvf->qset.sq[qidx]; - sq->lmt_addr = (u64 *)((u64)pfvf->hw.nix_lmt_base + - (qidx * pfvf->nix_lmt_size)); - - sq->lmt_id = pfvf->npa_lmt_lines + (qidx * LMT_BURST_SIZE); /* Get memory to put this msg */ aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox); @@ -125,8 +120,7 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) if (otx2_alloc_buffer(pfvf, cq, &bufptr)) { if (num_ptrs--) __cn10k_aura_freeptr(pfvf, cq->cq_idx, ptrs, - num_ptrs, - cq->rbpool->lmt_addr); + num_ptrs); break; } cq->pool_ptrs--; @@ -134,8 +128,7 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) num_ptrs++; if (num_ptrs == NPA_MAX_BURST || cq->pool_ptrs == 0) { __cn10k_aura_freeptr(pfvf, cq->cq_idx, ptrs, - num_ptrs, - cq->rbpool->lmt_addr); + num_ptrs); num_ptrs = 1; } } @@ -143,20 +136,23 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx) { + struct otx2_lmt_info *lmt_info; + struct otx2_nic *pfvf = dev; u64 val = 0, tar_addr = 0; + lmt_info = per_cpu_ptr(pfvf->hw.lmt_info, smp_processor_id()); /* FIXME: val[0:10] LMT_ID. * [12:15] no of LMTST - 1 in the burst. * [19:63] data size of each LMTST in the burst except first. */ - val = (sq->lmt_id & 0x7FF); + val = (lmt_info->lmt_id & 0x7FF); /* Target address for LMTST flush tells HW how many 128bit * words are present. * tar_addr[6:4] size of first LMTST - 1 in units of 128b. */ tar_addr |= sq->io_addr | (((size / 16) - 1) & 0x7) << 4; dma_wmb(); - memcpy(sq->lmt_addr, sq->sqe_base, size); + memcpy((u64 *)lmt_info->lmt_addr, sq->sqe_base, size); cn10k_lmt_flush(val, tar_addr); sq->head++; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index ce25c2744435..78df173e6df2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1230,11 +1230,6 @@ static int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, pool->rbsize = buf_size; - /* Set LMTST addr for NPA batch free */ - if (test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) - pool->lmt_addr = (__force u64 *)((u64)pfvf->hw.npa_lmt_base + - (pool_id * LMT_LINE_SIZE)); - /* Initialize this pool's context via AF */ aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox); if (!aq) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 48227cec06ee..a51ecd771d07 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -53,6 +53,10 @@ enum arua_mapped_qtypes { /* Send skid of 2000 packets required for CQ size of 4K CQEs. */ #define SEND_CQ_SKID 2000 +struct otx2_lmt_info { + u64 lmt_addr; + u16 lmt_id; +}; /* RSS configuration */ struct otx2_rss_ctx { u8 ind_tbl[MAX_RSS_INDIR_TBL_SIZE]; @@ -224,8 +228,7 @@ struct otx2_hw { #define LMT_LINE_SIZE 128 #define LMT_BURST_SIZE 32 /* 32 LMTST lines for burst SQE flush */ u64 *lmt_base; - u64 *npa_lmt_base; - u64 *nix_lmt_base; + struct otx2_lmt_info __percpu *lmt_info; }; enum vfperm { @@ -407,17 +410,18 @@ static inline bool is_96xx_B0(struct pci_dev *pdev) */ #define PCI_REVISION_ID_96XX 0x00 #define PCI_REVISION_ID_95XX 0x10 -#define PCI_REVISION_ID_LOKI 0x20 +#define PCI_REVISION_ID_95XXN 0x20 #define PCI_REVISION_ID_98XX 0x30 #define PCI_REVISION_ID_95XXMM 0x40 +#define PCI_REVISION_ID_95XXO 0xE0 static inline bool is_dev_otx2(struct pci_dev *pdev) { u8 midr = pdev->revision & 0xF0; return (midr == PCI_REVISION_ID_96XX || midr == PCI_REVISION_ID_95XX || - midr == PCI_REVISION_ID_LOKI || midr == PCI_REVISION_ID_98XX || - midr == PCI_REVISION_ID_95XXMM); + midr == PCI_REVISION_ID_95XXN || midr == PCI_REVISION_ID_98XX || + midr == PCI_REVISION_ID_95XXMM || midr == PCI_REVISION_ID_95XXO); } static inline void otx2_setup_dev_hw_settings(struct otx2_nic *pfvf) @@ -562,15 +566,16 @@ static inline u64 otx2_atomic64_add(u64 incr, u64 *ptr) #endif static inline void __cn10k_aura_freeptr(struct otx2_nic *pfvf, u64 aura, - u64 *ptrs, u64 num_ptrs, - u64 *lmt_addr) + u64 *ptrs, u64 num_ptrs) { + struct otx2_lmt_info *lmt_info; u64 size = 0, count_eot = 0; u64 tar_addr, val = 0; + lmt_info = per_cpu_ptr(pfvf->hw.lmt_info, smp_processor_id()); tar_addr = (__force u64)otx2_get_regaddr(pfvf, NPA_LF_AURA_BATCH_FREE0); /* LMTID is same as AURA Id */ - val = (aura & 0x7FF) | BIT_ULL(63); + val = (lmt_info->lmt_id & 0x7FF) | BIT_ULL(63); /* Set if [127:64] of last 128bit word has a valid pointer */ count_eot = (num_ptrs % 2) ? 0ULL : 1ULL; /* Set AURA ID to free pointer */ @@ -586,7 +591,7 @@ static inline void __cn10k_aura_freeptr(struct otx2_nic *pfvf, u64 aura, size++; tar_addr |= ((size - 1) & 0x7) << 4; } - memcpy(lmt_addr, ptrs, sizeof(u64) * num_ptrs); + memcpy((u64 *)lmt_info->lmt_addr, ptrs, sizeof(u64) * num_ptrs); /* Perform LMTST flush */ cn10k_lmt_flush(val, tar_addr); } @@ -594,12 +599,11 @@ static inline void __cn10k_aura_freeptr(struct otx2_nic *pfvf, u64 aura, static inline void cn10k_aura_freeptr(void *dev, int aura, u64 buf) { struct otx2_nic *pfvf = dev; - struct otx2_pool *pool; u64 ptrs[2]; - pool = &pfvf->qset.pool[aura]; ptrs[1] = buf; - __cn10k_aura_freeptr(pfvf, aura, ptrs, 2, pool->lmt_addr); + /* Free only one buffer at time during init and teardown */ + __cn10k_aura_freeptr(pfvf, aura, ptrs, 2); } /* Alloc pointer from pool/aura */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 799486c72177..dbfa3bc39e34 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -16,8 +16,8 @@ #include "otx2_common.h" #include "otx2_ptp.h" -#define DRV_NAME "octeontx2-nicpf" -#define DRV_VF_NAME "octeontx2-nicvf" +#define DRV_NAME "rvu-nicpf" +#define DRV_VF_NAME "rvu-nicvf" struct otx2_stat { char name[ETH_GSTRING_LEN]; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 2f2e8a3d7924..53df7fff92c4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1533,14 +1533,6 @@ int otx2_open(struct net_device *netdev) if (!qset->rq) goto err_free_mem; - if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) { - /* Reserve LMT lines for NPA AURA batch free */ - pf->hw.npa_lmt_base = pf->hw.lmt_base; - /* Reserve LMT lines for NIX TX */ - pf->hw.nix_lmt_base = (u64 *)((u64)pf->hw.npa_lmt_base + - (pf->npa_lmt_lines * LMT_LINE_SIZE)); - } - err = otx2_init_hw_resources(pf); if (err) goto err_free_mem; @@ -2668,6 +2660,8 @@ err_del_mcam_entries: err_ptp_destroy: otx2_ptp_destroy(pf); err_detach_rsrc: + if (pf->hw.lmt_info) + free_percpu(pf->hw.lmt_info); if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) qmem_free(pf->dev, pf->dync_lmt); otx2_detach_resources(&pf->mbox); @@ -2811,6 +2805,8 @@ static void otx2_remove(struct pci_dev *pdev) otx2_mcam_flow_del(pf); otx2_shutdown_tc(pf); otx2_detach_resources(&pf->mbox); + if (pf->hw.lmt_info) + free_percpu(pf->hw.lmt_info); if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) qmem_free(pf->dev, pf->dync_lmt); otx2_disable_mbox_intr(pf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index 869de5f59e73..3ff1ad79c001 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -80,7 +80,6 @@ struct otx2_snd_queue { u16 num_sqbs; u16 sqe_thresh; u8 sqe_per_sqb; - u32 lmt_id; u64 io_addr; u64 *aura_fc_addr; u64 *lmt_addr; @@ -111,7 +110,6 @@ struct otx2_cq_poll { struct otx2_pool { struct qmem *stack; struct qmem *fc_addr; - u64 *lmt_addr; u16 rbsize; }; diff --git a/include/linux/soc/marvell/octeontx2/asm.h b/include/linux/soc/marvell/octeontx2/asm.h index 28c04d918f0f..fa1d6af0164e 100644 --- a/include/linux/soc/marvell/octeontx2/asm.h +++ b/include/linux/soc/marvell/octeontx2/asm.h @@ -22,12 +22,17 @@ : [rs]"r" (ioaddr)); \ (result); \ }) +/* + * STEORL store to memory with release semantics. + * This will avoid using DMB barrier after each LMTST + * operation. + */ #define cn10k_lmt_flush(val, addr) \ ({ \ __asm__ volatile(".cpu generic+lse\n" \ - "steor %x[rf],[%[rs]]" \ - : [rf]"+r"(val) \ - : [rs]"r"(addr)); \ + "steorl %x[rf],[%[rs]]" \ + : [rf] "+r"(val) \ + : [rs] "r"(addr)); \ }) #else #define otx2_lmt_flush(ioaddr) ({ 0; }) -- cgit v1.2.3 From 59dc33252ee777e02332774fbdf3381b1d5d5f5d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 24 Aug 2021 16:43:55 +0200 Subject: PCI: VMD: ACPI: Make ACPI companion lookup work for VMD bus On some systems, in order to get to the deepest low-power state of the platform (which may be necessary to save significant enough amounts of energy while suspended to idle. for example), devices on the PCI bus exposed by the VMD driver need to be power-managed via ACPI. However, the layout of the ACPI namespace below the VMD controller device object does not reflect the layout of the PCI bus under the VMD host bridge, so in order to identify the ACPI companion objects for the devices on that bus, it is necessary to use a special _ADR encoding on the ACPI side. In other words, acpi_pci_find_companion() does not work for these devices, so it needs to be amended with a special lookup logic specific to the VMD bus. Address this issue by allowing the VMD driver to temporarily install an ACPI companion lookup hook containing the code matching the devices on the VMD PCI bus with the corresponding objects in the ACPI namespace. Signed-off-by: Rafael J. Wysocki Acked-by: Jon Derrick --- drivers/pci/controller/vmd.c | 55 ++++++++++++++++++++++++++++++++ drivers/pci/host-bridge.c | 1 + drivers/pci/pci-acpi.c | 74 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci-acpi.h | 3 ++ 4 files changed, 133 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index e3fcdfec58b3..a5987e52700e 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -447,6 +448,56 @@ static struct pci_ops vmd_ops = { .write = vmd_pci_write, }; +#ifdef CONFIG_ACPI +static struct acpi_device *vmd_acpi_find_companion(struct pci_dev *pci_dev) +{ + struct pci_host_bridge *bridge; + u32 busnr, addr; + + if (pci_dev->bus->ops != &vmd_ops) + return NULL; + + bridge = pci_find_host_bridge(pci_dev->bus); + busnr = pci_dev->bus->number - bridge->bus->number; + /* + * The address computation below is only applicable to relative bus + * numbers below 32. + */ + if (busnr > 31) + return NULL; + + addr = (busnr << 24) | ((u32)pci_dev->devfn << 16) | 0x8000FFFFU; + + dev_dbg(&pci_dev->dev, "Looking for ACPI companion (address 0x%x)\n", + addr); + + return acpi_find_child_device(ACPI_COMPANION(bridge->dev.parent), addr, + false); +} + +static bool hook_installed; + +static void vmd_acpi_begin(void) +{ + if (pci_acpi_set_companion_lookup_hook(vmd_acpi_find_companion)) + return; + + hook_installed = true; +} + +static void vmd_acpi_end(void) +{ + if (!hook_installed) + return; + + pci_acpi_clear_companion_lookup_hook(); + hook_installed = false; +} +#else +static inline void vmd_acpi_begin(void) { } +static inline void vmd_acpi_end(void) { } +#endif /* CONFIG_ACPI */ + static void vmd_attach_resources(struct vmd_dev *vmd) { vmd->dev->resource[VMD_MEMBAR1].child = &vmd->resources[1]; @@ -747,6 +798,8 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) if (vmd->irq_domain) dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain); + vmd_acpi_begin(); + pci_scan_child_bus(vmd->bus); pci_assign_unassigned_bus_resources(vmd->bus); @@ -760,6 +813,8 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) pci_bus_add_devices(vmd->bus); + vmd_acpi_end(); + WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj, "domain"), "Can't create symlink to domain\n"); return 0; diff --git a/drivers/pci/host-bridge.c b/drivers/pci/host-bridge.c index e01d53f5b32f..afa50b446567 100644 --- a/drivers/pci/host-bridge.c +++ b/drivers/pci/host-bridge.c @@ -23,6 +23,7 @@ struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus) return to_pci_host_bridge(root_bus->bridge); } +EXPORT_SYMBOL_GPL(pci_find_host_bridge); struct device *pci_get_host_bridge_device(struct pci_dev *dev) { diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 36bc23e21759..825988a5c074 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "pci.h" /* @@ -1159,6 +1160,69 @@ void acpi_pci_remove_bus(struct pci_bus *bus) } /* ACPI bus type */ + + +static DECLARE_RWSEM(pci_acpi_companion_lookup_sem); +static struct acpi_device *(*pci_acpi_find_companion_hook)(struct pci_dev *); + +/** + * pci_acpi_set_companion_lookup_hook - Set ACPI companion lookup callback. + * @func: ACPI companion lookup callback pointer or NULL. + * + * Set a special ACPI companion lookup callback for PCI devices whose companion + * objects in the ACPI namespace have _ADR with non-standard bus-device-function + * encodings. + * + * Return 0 on success or a negative error code on failure (in which case no + * changes are made). + * + * The caller is responsible for the appropriate ordering of the invocations of + * this function with respect to the enumeration of the PCI devices needing the + * callback installed by it. + */ +int pci_acpi_set_companion_lookup_hook(struct acpi_device *(*func)(struct pci_dev *)) +{ + int ret; + + if (!func) + return -EINVAL; + + down_write(&pci_acpi_companion_lookup_sem); + + if (pci_acpi_find_companion_hook) { + ret = -EBUSY; + } else { + pci_acpi_find_companion_hook = func; + ret = 0; + } + + up_write(&pci_acpi_companion_lookup_sem); + + return ret; +} +EXPORT_SYMBOL_GPL(pci_acpi_set_companion_lookup_hook); + +/** + * pci_acpi_clear_companion_lookup_hook - Clear ACPI companion lookup callback. + * + * Clear the special ACPI companion lookup callback previously set by + * pci_acpi_set_companion_lookup_hook(). Block until the last running instance + * of the callback returns before clearing it. + * + * The caller is responsible for the appropriate ordering of the invocations of + * this function with respect to the enumeration of the PCI devices needing the + * callback cleared by it. + */ +void pci_acpi_clear_companion_lookup_hook(void) +{ + down_write(&pci_acpi_companion_lookup_sem); + + pci_acpi_find_companion_hook = NULL; + + up_write(&pci_acpi_companion_lookup_sem); +} +EXPORT_SYMBOL_GPL(pci_acpi_clear_companion_lookup_hook); + static struct acpi_device *acpi_pci_find_companion(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); @@ -1166,6 +1230,16 @@ static struct acpi_device *acpi_pci_find_companion(struct device *dev) bool check_children; u64 addr; + down_read(&pci_acpi_companion_lookup_sem); + + adev = pci_acpi_find_companion_hook ? + pci_acpi_find_companion_hook(pci_dev) : NULL; + + up_read(&pci_acpi_companion_lookup_sem); + + if (adev) + return adev; + check_children = pci_is_bridge(pci_dev); /* Please ref to ACPI spec for the syntax of _ADR */ addr = (PCI_SLOT(pci_dev->devfn) << 16) | PCI_FUNC(pci_dev->devfn); diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 5ba475ca9078..f16de399d2de 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -122,6 +122,9 @@ static inline void pci_acpi_add_edr_notifier(struct pci_dev *pdev) { } static inline void pci_acpi_remove_edr_notifier(struct pci_dev *pdev) { } #endif /* CONFIG_PCIE_EDR */ +int pci_acpi_set_companion_lookup_hook(struct acpi_device *(*func)(struct pci_dev *)); +void pci_acpi_clear_companion_lookup_hook(void); + #else /* CONFIG_ACPI */ static inline void acpi_pci_add_bus(struct pci_bus *bus) { } static inline void acpi_pci_remove_bus(struct pci_bus *bus) { } -- cgit v1.2.3 From 4bf8e582119ed9767f907abb6dc62ef9dddf10df Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 1 Sep 2021 14:41:57 +0530 Subject: cpufreq: Remove ready() callback This isn't used anymore, get rid of it. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- Documentation/cpu-freq/cpu-drivers.rst | 3 --- Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst | 2 -- drivers/cpufreq/cpufreq.c | 4 ---- include/linux/cpufreq.h | 3 --- 4 files changed, 12 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cpu-freq/cpu-drivers.rst b/Documentation/cpu-freq/cpu-drivers.rst index d84ededb66f9..3b32336a7803 100644 --- a/Documentation/cpu-freq/cpu-drivers.rst +++ b/Documentation/cpu-freq/cpu-drivers.rst @@ -75,9 +75,6 @@ And optionally .resume - A pointer to a per-policy resume function which is called with interrupts disabled and _before_ the governor is started again. - .ready - A pointer to a per-policy ready function which is called after - the policy is fully initialized. - .attr - A pointer to a NULL-terminated list of "struct freq_attr" which allow to export values to sysfs. diff --git a/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst b/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst index 5ae9cfa2ec55..334f30ae198b 100644 --- a/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst +++ b/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst @@ -80,8 +80,6 @@ CPUfreq核心层注册一个cpufreq_driver结构体。 .resume - 一个指向per-policy恢复函数的指针，该函数在关中断且在调节器再一次开始前被 调用。 - .ready - 一个指向per-policy准备函数的指针，该函数在策略完全初始化之后被调用。 - .attr - 一个指向NULL结尾的"struct freq_attr"列表的指针，该函数允许导出值到 sysfs。 diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 7d5f170ecad1..5782b15a8caa 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1517,10 +1517,6 @@ static int cpufreq_online(unsigned int cpu) kobject_uevent(&policy->kobj, KOBJ_ADD); - /* Callback for handling stuff after policy is ready */ - if (cpufreq_driver->ready) - cpufreq_driver->ready(policy); - if (cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c65a1d7385f8..fe6acc04e5e5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -367,9 +367,6 @@ struct cpufreq_driver { int (*suspend)(struct cpufreq_policy *policy); int (*resume)(struct cpufreq_policy *policy); - /* Will be called after the driver is fully initialized */ - void (*ready)(struct cpufreq_policy *policy); - struct freq_attr **attr; /* platform specific boost support code */ -- cgit v1.2.3 From 8083f58d08fd52f547c0a62c0f4e448e15e6726b Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Wed, 7 Jul 2021 18:28:35 +0200 Subject: pwm: Make pwmchip_remove() return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since some time pwmchip_remove() always returns 0 so the return value isn't usefull. Now that all callers are converted to ignore its value the function can be changed to return void. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/core.c | 4 +--- include/linux/pwm.h | 2 +- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 35e894f4a379..4527f09a5c50 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -304,7 +304,7 @@ EXPORT_SYMBOL_GPL(pwmchip_add); * * Returns: 0 on success or a negative error code on failure. */ -int pwmchip_remove(struct pwm_chip *chip) +void pwmchip_remove(struct pwm_chip *chip) { pwmchip_sysfs_unexport(chip); @@ -318,8 +318,6 @@ int pwmchip_remove(struct pwm_chip *chip) free_pwms(chip); mutex_unlock(&pwm_lock); - - return 0; } EXPORT_SYMBOL_GPL(pwmchip_remove); diff --git a/include/linux/pwm.h b/include/linux/pwm.h index a0b7e43049d5..725c9b784e60 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -404,7 +404,7 @@ int pwm_set_chip_data(struct pwm_device *pwm, void *data); void *pwm_get_chip_data(struct pwm_device *pwm); int pwmchip_add(struct pwm_chip *chip); -int pwmchip_remove(struct pwm_chip *chip); +void pwmchip_remove(struct pwm_chip *chip); int devm_pwmchip_add(struct device *dev, struct pwm_chip *chip); -- cgit v1.2.3 From 15eb7c888e749fbd1cc0370f3d38de08ad903700 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 31 Aug 2021 08:38:19 +0200 Subject: locking/rwsem: Add missing __init_rwsem() for PREEMPT_RT 730633f0b7f95 became the first direct caller of __init_rwsem() vs the usual init_rwsem(), exposing PREEMPT_RT's lack thereof. Add it. [ tglx: Move it out of line ] Signed-off-by: Mike Galbraith Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/50a936b7d8f12277d6ec7ed2ef0421a381056909.camel@gmx.de --- include/linux/rwsem.h | 12 ++---------- kernel/locking/rwsem.c | 10 ++++++---- 2 files changed, 8 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 426e98e0b675..352c6127cb90 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -142,22 +142,14 @@ struct rw_semaphore { #define DECLARE_RWSEM(lockname) \ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) -#ifdef CONFIG_DEBUG_LOCK_ALLOC -extern void __rwsem_init(struct rw_semaphore *rwsem, const char *name, +extern void __init_rwsem(struct rw_semaphore *rwsem, const char *name, struct lock_class_key *key); -#else -static inline void __rwsem_init(struct rw_semaphore *rwsem, const char *name, - struct lock_class_key *key) -{ -} -#endif #define init_rwsem(sem) \ do { \ static struct lock_class_key __key; \ \ - init_rwbase_rt(&(sem)->rwbase); \ - __rwsem_init((sem), #sem, &__key); \ + __init_rwsem((sem), #sem, &__key); \ } while (0) static __always_inline int rwsem_is_locked(struct rw_semaphore *sem) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 9215b4d6a9de..000e8d5a2884 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1376,15 +1376,17 @@ static inline void __downgrade_write(struct rw_semaphore *sem) #include "rwbase_rt.c" -#ifdef CONFIG_DEBUG_LOCK_ALLOC -void __rwsem_init(struct rw_semaphore *sem, const char *name, +void __init_rwsem(struct rw_semaphore *sem, const char *name, struct lock_class_key *key) { + init_rwbase_rt(&(sem)->rwbase); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC debug_check_no_locks_freed((void *)sem, sizeof(*sem)); lockdep_init_map_wait(&sem->dep_map, name, key, 0, LD_WAIT_SLEEP); -} -EXPORT_SYMBOL(__rwsem_init); #endif +} +EXPORT_SYMBOL(__init_rwsem); static inline void __down_read(struct rw_semaphore *sem) { -- cgit v1.2.3 From d095559ce4100f0c02aea229705230deac329c97 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Mon, 5 Jul 2021 09:22:56 +0800 Subject: ceph: flush mdlog before umounting Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 25 +++++++++++++++++++++++++ fs/ceph/mds_client.h | 1 + fs/ceph/strings.c | 1 + include/linux/ceph/ceph_fs.h | 1 + 4 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 926971822174..d98a3eda0d4c 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4693,6 +4693,30 @@ static void wait_requests(struct ceph_mds_client *mdsc) dout("wait_requests done\n"); } +void send_flush_mdlog(struct ceph_mds_session *s) +{ + struct ceph_msg *msg; + + /* + * Pre-luminous MDS crashes when it sees an unknown session request + */ + if (!CEPH_HAVE_FEATURE(s->s_con.peer_features, SERVER_LUMINOUS)) + return; + + mutex_lock(&s->s_mutex); + dout("request mdlog flush to mds%d (%s)s seq %lld\n", s->s_mds, + ceph_session_state_name(s->s_state), s->s_seq); + msg = ceph_create_session_msg(CEPH_SESSION_REQUEST_FLUSH_MDLOG, + s->s_seq); + if (!msg) { + pr_err("failed to request mdlog flush to mds%d (%s) seq %lld\n", + s->s_mds, ceph_session_state_name(s->s_state), s->s_seq); + } else { + ceph_con_send(&s->s_con, msg); + } + mutex_unlock(&s->s_mutex); +} + /* * called before mount is ro, and before dentries are torn down. * (hmm, does this still race with new lookups?) @@ -4702,6 +4726,7 @@ void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc) dout("pre_umount\n"); mdsc->stopping = 1; + ceph_mdsc_iterate_sessions(mdsc, send_flush_mdlog, true); ceph_mdsc_iterate_sessions(mdsc, lock_unlock_session, false); ceph_flush_dirty_caps(mdsc); wait_requests(mdsc); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 4a75a14c2a88..97c7f7bfa55f 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -522,6 +522,7 @@ static inline void ceph_mdsc_put_request(struct ceph_mds_request *req) kref_put(&req->r_kref, ceph_mdsc_release_request); } +extern void send_flush_mdlog(struct ceph_mds_session *s); extern void ceph_mdsc_iterate_sessions(struct ceph_mds_client *mdsc, void (*cb)(struct ceph_mds_session *), bool check_state); diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c index 4a79f3632260..573bb9556fb5 100644 --- a/fs/ceph/strings.c +++ b/fs/ceph/strings.c @@ -46,6 +46,7 @@ const char *ceph_session_op_name(int op) case CEPH_SESSION_FLUSHMSG_ACK: return "flushmsg_ack"; case CEPH_SESSION_FORCE_RO: return "force_ro"; case CEPH_SESSION_REJECT: return "reject"; + case CEPH_SESSION_REQUEST_FLUSH_MDLOG: return "flush_mdlog"; } return "???"; } diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index e41a811026f6..bc2699feddbe 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -299,6 +299,7 @@ enum { CEPH_SESSION_FLUSHMSG_ACK, CEPH_SESSION_FORCE_RO, CEPH_SESSION_REJECT, + CEPH_SESSION_REQUEST_FLUSH_MDLOG, }; extern const char *ceph_session_op_name(int op); -- cgit v1.2.3 From 7a8526a5cd51cf5f070310c6c37dd7293334ac49 Mon Sep 17 00:00:00 2001 From: Kate Hsuan Date: Fri, 3 Sep 2021 17:44:11 +0800 Subject: libata: Add ATA_HORKAGE_NO_NCQ_ON_ATI for Samsung 860 and 870 SSD. Many users are reporting that the Samsung 860 and 870 SSD are having various issues when combined with AMD/ATI (vendor ID 0x1002) SATA controllers and only completely disabling NCQ helps to avoid these issues. Always disabling NCQ for Samsung 860/870 SSDs regardless of the host SATA adapter vendor will cause I/O performance degradation with well behaved adapters. To limit the performance impact to ATI adapters, introduce the ATA_HORKAGE_NO_NCQ_ON_ATI flag to force disable NCQ only for these adapters. Also, two libata.force parameters (noncqati and ncqati) are introduced to disable and enable the NCQ for the system which equipped with ATI SATA adapter and Samsung 860 and 870 SSDs. The user can determine NCQ function to be enabled or disabled according to the demand. After verifying the chipset from the user reports, the issue appears on AMD/ATI SB7x0/SB8x0/SB9x0 SATA Controllers and does not appear on recent AMD SATA adapters. The vendor ID of ATI should be 0x1002. Therefore, ATA_HORKAGE_NO_NCQ_ON_AMD was modified to ATA_HORKAGE_NO_NCQ_ON_ATI. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=201693 Signed-off-by: Kate Hsuan Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210903094411.58749-1-hpa@redhat.com Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- drivers/ata/libata-core.c | 34 ++++++++++++++++++++++++++++++++-- include/linux/libata.h | 1 + 2 files changed, 33 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index ff08862c35b5..eed65311b5d1 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2186,6 +2186,25 @@ not_supported: dev->flags &= ~ATA_DFLAG_NCQ_PRIO; } +static bool ata_dev_check_adapter(struct ata_device *dev, + unsigned short vendor_id) +{ + struct pci_dev *pcidev = NULL; + struct device *parent_dev = NULL; + + for (parent_dev = dev->tdev.parent; parent_dev != NULL; + parent_dev = parent_dev->parent) { + if (dev_is_pci(parent_dev)) { + pcidev = to_pci_dev(parent_dev); + if (pcidev->vendor == vendor_id) + return true; + break; + } + } + + return false; +} + static int ata_dev_config_ncq(struct ata_device *dev, char *desc, size_t desc_sz) { @@ -2204,6 +2223,13 @@ static int ata_dev_config_ncq(struct ata_device *dev, snprintf(desc, desc_sz, "NCQ (not used)"); return 0; } + + if (dev->horkage & ATA_HORKAGE_NO_NCQ_ON_ATI && + ata_dev_check_adapter(dev, PCI_VENDOR_ID_ATI)) { + snprintf(desc, desc_sz, "NCQ (not used)"); + return 0; + } + if (ap->flags & ATA_FLAG_NCQ) { hdepth = min(ap->scsi_host->can_queue, ATA_MAX_QUEUE); dev->flags |= ATA_DFLAG_NCQ; @@ -3971,9 +3997,11 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 860*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM | + ATA_HORKAGE_NO_NCQ_ON_ATI, }, { "Samsung SSD 870*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM | + ATA_HORKAGE_NO_NCQ_ON_ATI, }, { "FCCT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, @@ -6128,6 +6156,8 @@ static int __init ata_parse_force_one(char **cur, { "ncq", .horkage_off = ATA_HORKAGE_NONCQ }, { "noncqtrim", .horkage_on = ATA_HORKAGE_NO_NCQ_TRIM }, { "ncqtrim", .horkage_off = ATA_HORKAGE_NO_NCQ_TRIM }, + { "noncqati", .horkage_on = ATA_HORKAGE_NO_NCQ_ON_ATI }, + { "ncqati", .horkage_off = ATA_HORKAGE_NO_NCQ_ON_ATI }, { "dump_id", .horkage_on = ATA_HORKAGE_DUMP_ID }, { "pio0", .xfer_mask = 1 << (ATA_SHIFT_PIO + 0) }, { "pio1", .xfer_mask = 1 << (ATA_SHIFT_PIO + 1) }, diff --git a/include/linux/libata.h b/include/linux/libata.h index 860e63f5667b..c0c64f03e107 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -426,6 +426,7 @@ enum { ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ + ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 35d7bdc86031a2c1ae05ac27dfa93b2acdcbaecc Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 23 Apr 2021 10:20:25 +0200 Subject: kernel/fork: factor out replacing the current MM exe_file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Let's factor the main logic out into replace_mm_exe_file(), such that all mm->exe_file logic is contained in kernel/fork.c. While at it, perform some simple cleanups that are possible now that we're simplifying the individual functions. Acked-by: Christian Brauner Acked-by: "Eric W. Biederman" Acked-by: Christian König Signed-off-by: David Hildenbrand --- include/linux/mm.h | 1 + kernel/fork.c | 44 +++++++++++++++++++++++++++++++++++++++++--- kernel/sys.c | 33 +-------------------------------- 3 files changed, 43 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7ca22e6e694a..48c6fa9ab792 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2581,6 +2581,7 @@ extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); +extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); extern struct file *get_task_exe_file(struct task_struct *task); diff --git a/kernel/fork.c b/kernel/fork.c index 44f4c2d83763..f4ac883c4a1e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1148,9 +1148,7 @@ void mmput_async(struct mm_struct *mm) * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve task is single - * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the - * mm->exe_file, but does so without using set_mm_exe_file() in order - * to avoid the need for any locks. + * threaded. */ void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { @@ -1170,6 +1168,46 @@ void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) fput(old_exe_file); } +/** + * replace_mm_exe_file - replace a reference to the mm's executable file + * + * This changes mm's executable file (shown as symlink /proc/[pid]/exe), + * dealing with concurrent invocation and without grabbing the mmap lock in + * write mode. + * + * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). + */ +int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) +{ + struct vm_area_struct *vma; + struct file *old_exe_file; + int ret = 0; + + /* Forbid mm->exe_file change if old file still mapped. */ + old_exe_file = get_mm_exe_file(mm); + if (old_exe_file) { + mmap_read_lock(mm); + for (vma = mm->mmap; vma && !ret; vma = vma->vm_next) { + if (!vma->vm_file) + continue; + if (path_equal(&vma->vm_file->f_path, + &old_exe_file->f_path)) + ret = -EBUSY; + } + mmap_read_unlock(mm); + fput(old_exe_file); + if (ret) + return ret; + } + + /* set the new file, lockless */ + get_file(new_exe_file); + old_exe_file = xchg(&mm->exe_file, new_exe_file); + if (old_exe_file) + fput(old_exe_file); + return 0; +} + /** * get_mm_exe_file - acquire a reference to the mm's executable file * diff --git a/kernel/sys.c b/kernel/sys.c index ef1a78f5d71c..30c12e54585a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1846,7 +1846,6 @@ SYSCALL_DEFINE1(umask, int, mask) static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) { struct fd exe; - struct file *old_exe, *exe_file; struct inode *inode; int err; @@ -1869,40 +1868,10 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) if (err) goto exit; - /* - * Forbid mm->exe_file change if old file still mapped. - */ - exe_file = get_mm_exe_file(mm); - err = -EBUSY; - if (exe_file) { - struct vm_area_struct *vma; - - mmap_read_lock(mm); - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (!vma->vm_file) - continue; - if (path_equal(&vma->vm_file->f_path, - &exe_file->f_path)) - goto exit_err; - } - - mmap_read_unlock(mm); - fput(exe_file); - } - - err = 0; - /* set the new file, lockless */ - get_file(exe.file); - old_exe = xchg(&mm->exe_file, exe.file); - if (old_exe) - fput(old_exe); + err = replace_mm_exe_file(mm, exe.file); exit: fdput(exe); return err; -exit_err: - mmap_read_unlock(mm); - fput(exe_file); - goto exit; } /* -- cgit v1.2.3 From fe69d560b5bd9ec77b5d5749bd7027344daef47e Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 23 Apr 2021 10:29:59 +0200 Subject: kernel/fork: always deny write access to current MM exe_file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We want to remove VM_DENYWRITE only currently only used when mapping the executable during exec. During exec, we already deny_write_access() the executable, however, after exec completes the VMAs mapped with VM_DENYWRITE effectively keeps write access denied via deny_write_access(). Let's deny write access when setting or replacing the MM exe_file. With this change, we can remove VM_DENYWRITE for mapping executables. Make set_mm_exe_file() return an error in case deny_write_access() fails; note that this should never happen, because exec code does a deny_write_access() early and keeps write access denied when calling set_mm_exe_file. However, it makes the code easier to read and makes set_mm_exe_file() and replace_mm_exe_file() look more similar. This represents a minor user space visible change: sys_prctl(PR_SET_MM_MAP/EXE_FILE) can now fail if the file is already opened writable. Also, after sys_prctl(PR_SET_MM_MAP/EXE_FILE) the file cannot be opened writable. Note that we can already fail with -EACCES if the file doesn't have execute permissions. Acked-by: "Eric W. Biederman" Acked-by: Christian König Signed-off-by: David Hildenbrand --- fs/exec.c | 4 +++- include/linux/mm.h | 2 +- kernel/fork.c | 50 ++++++++++++++++++++++++++++++++++++++++++++------ 3 files changed, 48 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 38f63451b928..9294049f5487 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1270,7 +1270,9 @@ int begin_new_exec(struct linux_binprm * bprm) * not visibile until then. This also enables the update * to be lockless. */ - set_mm_exe_file(bprm->mm, bprm->file); + retval = set_mm_exe_file(bprm->mm, bprm->file); + if (retval) + goto out; /* If the binary is not readable then enforce mm->dumpable=0 */ would_dump(bprm, bprm->file); diff --git a/include/linux/mm.h b/include/linux/mm.h index 48c6fa9ab792..56b1cd41db61 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2580,7 +2580,7 @@ static inline int check_data_rlimit(unsigned long rlim, extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); -extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); +extern int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); extern struct file *get_task_exe_file(struct task_struct *task); diff --git a/kernel/fork.c b/kernel/fork.c index f4ac883c4a1e..7677f897ecb6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -470,6 +470,20 @@ void free_task(struct task_struct *tsk) } EXPORT_SYMBOL(free_task); +static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) +{ + struct file *exe_file; + + exe_file = get_mm_exe_file(oldmm); + RCU_INIT_POINTER(mm->exe_file, exe_file); + /* + * We depend on the oldmm having properly denied write access to the + * exe_file already. + */ + if (exe_file && deny_write_access(exe_file)) + pr_warn_once("deny_write_access() failed in %s\n", __func__); +} + #ifdef CONFIG_MMU static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) @@ -493,7 +507,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ - RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm)); + dup_mm_exe_file(mm, oldmm); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; @@ -639,7 +653,7 @@ static inline void mm_free_pgd(struct mm_struct *mm) static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { mmap_write_lock(oldmm); - RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm)); + dup_mm_exe_file(mm, oldmm); mmap_write_unlock(oldmm); return 0; } @@ -1149,8 +1163,10 @@ void mmput_async(struct mm_struct *mm) * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve task is single * threaded. + * + * Can only fail if new_exe_file != NULL. */ -void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) +int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; @@ -1161,11 +1177,21 @@ void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) */ old_exe_file = rcu_dereference_raw(mm->exe_file); - if (new_exe_file) + if (new_exe_file) { + /* + * We expect the caller (i.e., sys_execve) to already denied + * write access, so this is unlikely to fail. + */ + if (unlikely(deny_write_access(new_exe_file))) + return -EACCES; get_file(new_exe_file); + } rcu_assign_pointer(mm->exe_file, new_exe_file); - if (old_exe_file) + if (old_exe_file) { + allow_write_access(old_exe_file); fput(old_exe_file); + } + return 0; } /** @@ -1201,10 +1227,22 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) } /* set the new file, lockless */ + ret = deny_write_access(new_exe_file); + if (ret) + return -EACCES; get_file(new_exe_file); + old_exe_file = xchg(&mm->exe_file, new_exe_file); - if (old_exe_file) + if (old_exe_file) { + /* + * Don't race with dup_mmap() getting the file and disallowing + * write access while someone might open the file writable. + */ + mmap_read_lock(mm); + allow_write_access(old_exe_file); fput(old_exe_file); + mmap_read_unlock(mm); + } return 0; } -- cgit v1.2.3 From 8d0920bde5eb8ec7e567939b85e65a0596c8580d Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 22 Apr 2021 12:08:20 +0200 Subject: mm: remove VM_DENYWRITE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All in-tree users of MAP_DENYWRITE are gone. MAP_DENYWRITE cannot be set from user space, so all users are gone; let's remove it. Acked-by: "Eric W. Biederman" Acked-by: Christian König Signed-off-by: David Hildenbrand --- fs/proc/task_mmu.c | 1 - include/linux/mm.h | 1 - include/linux/mman.h | 1 - include/trace/events/mmflags.h | 1 - kernel/events/core.c | 2 -- kernel/fork.c | 3 --- lib/test_printf.c | 5 ++--- mm/mmap.c | 27 +++------------------------ 8 files changed, 5 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index eb97468dfe4c..cf25be3e0321 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -619,7 +619,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_MAYSHARE)] = "ms", [ilog2(VM_GROWSDOWN)] = "gd", [ilog2(VM_PFNMAP)] = "pf", - [ilog2(VM_DENYWRITE)] = "dw", [ilog2(VM_LOCKED)] = "lo", [ilog2(VM_IO)] = "io", [ilog2(VM_SEQ_READ)] = "sr", diff --git a/include/linux/mm.h b/include/linux/mm.h index 56b1cd41db61..257995f62e83 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -281,7 +281,6 @@ extern unsigned int kobjsize(const void *objp); #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ -#define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ #define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ #define VM_LOCKED 0x00002000 diff --git a/include/linux/mman.h b/include/linux/mman.h index ebb09a964272..bd9aadda047b 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -153,7 +153,6 @@ static inline unsigned long calc_vm_flag_bits(unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | - _calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | arch_calc_vm_flag_bits(flags); diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index f160484afc5c..0b53e855c4ac 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -165,7 +165,6 @@ IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison") {VM_UFFD_MISSING, "uffd_missing" }, \ IF_HAVE_UFFD_MINOR(VM_UFFD_MINOR, "uffd_minor" ) \ {VM_PFNMAP, "pfnmap" }, \ - {VM_DENYWRITE, "denywrite" }, \ {VM_UFFD_WP, "uffd_wp" }, \ {VM_LOCKED, "locked" }, \ {VM_IO, "io" }, \ diff --git a/kernel/events/core.c b/kernel/events/core.c index 1cb1f9b8392e..19767bb9933c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8307,8 +8307,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) else flags = MAP_PRIVATE; - if (vma->vm_flags & VM_DENYWRITE) - flags |= MAP_DENYWRITE; if (vma->vm_flags & VM_LOCKED) flags |= MAP_LOCKED; if (is_vm_hugetlb_page(vma)) diff --git a/kernel/fork.c b/kernel/fork.c index 7677f897ecb6..feef1057081d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -570,12 +570,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT); file = tmp->vm_file; if (file) { - struct inode *inode = file_inode(file); struct address_space *mapping = file->f_mapping; get_file(file); - if (tmp->vm_flags & VM_DENYWRITE) - put_write_access(inode); i_mmap_lock_write(mapping); if (tmp->vm_flags & VM_SHARED) mapping_allow_writable(mapping); diff --git a/lib/test_printf.c b/lib/test_printf.c index 8ac71aee46af..8a48b61c3763 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -675,9 +675,8 @@ flags(void) "uptodate|dirty|lru|active|swapbacked", cmp_buffer); - flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC - | VM_DENYWRITE; - test("read|exec|mayread|maywrite|mayexec|denywrite", "%pGv", &flags); + flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; + test("read|exec|mayread|maywrite|mayexec", "%pGv", &flags); gfp = GFP_TRANSHUGE; test("GFP_TRANSHUGE", "%pGg", &gfp); diff --git a/mm/mmap.c b/mm/mmap.c index ca54d36d203a..589dc1dc13db 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -148,8 +148,6 @@ void vma_set_page_prot(struct vm_area_struct *vma) static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct file *file, struct address_space *mapping) { - if (vma->vm_flags & VM_DENYWRITE) - allow_write_access(file); if (vma->vm_flags & VM_SHARED) mapping_unmap_writable(mapping); @@ -666,8 +664,6 @@ static void __vma_link_file(struct vm_area_struct *vma) if (file) { struct address_space *mapping = file->f_mapping; - if (vma->vm_flags & VM_DENYWRITE) - put_write_access(file_inode(file)); if (vma->vm_flags & VM_SHARED) mapping_allow_writable(mapping); @@ -1788,22 +1784,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma->vm_pgoff = pgoff; if (file) { - if (vm_flags & VM_DENYWRITE) { - error = deny_write_access(file); - if (error) - goto free_vma; - } if (vm_flags & VM_SHARED) { error = mapping_map_writable(file->f_mapping); if (error) - goto allow_write_and_free_vma; + goto free_vma; } - /* ->mmap() can change vma->vm_file, but must guarantee that - * vma_link() below can deny write-access if VM_DENYWRITE is set - * and map writably if VM_SHARED is set. This usually means the - * new file must not have been exposed to user-space, yet. - */ vma->vm_file = get_file(file); error = call_mmap(file, vma); if (error) @@ -1860,13 +1846,9 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma_link(mm, vma, prev, rb_link, rb_parent); /* Once vma denies write, undo our temporary denial count */ - if (file) { unmap_writable: - if (vm_flags & VM_SHARED) - mapping_unmap_writable(file->f_mapping); - if (vm_flags & VM_DENYWRITE) - allow_write_access(file); - } + if (file && vm_flags & VM_SHARED) + mapping_unmap_writable(file->f_mapping); file = vma->vm_file; out: perf_event_mmap(vma); @@ -1906,9 +1888,6 @@ unmap_and_free_vma: charged = 0; if (vm_flags & VM_SHARED) mapping_unmap_writable(file->f_mapping); -allow_write_and_free_vma: - if (vm_flags & VM_DENYWRITE) - allow_write_access(file); free_vma: vm_area_free(vma); unacct_error: -- cgit v1.2.3 From 6128b3af2a5e42386aa7faf37609b57f39fb7d00 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 23 Apr 2021 09:38:14 +0200 Subject: mm: ignore MAP_DENYWRITE in ksys_mmap_pgoff() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Let's also remove masking off MAP_DENYWRITE from ksys_mmap_pgoff(): the last in-tree occurrence of MAP_DENYWRITE is now in LEGACY_MAP_MASK, which accepts the flag e.g., for MAP_SHARED_VALIDATE; however, the flag is ignored throughout the kernel now. Add a comment to LEGACY_MAP_MASK stating that MAP_DENYWRITE is ignored. Acked-by: "Eric W. Biederman" Acked-by: Christian König Signed-off-by: David Hildenbrand --- include/linux/mman.h | 3 ++- mm/mmap.c | 2 -- mm/nommu.c | 2 -- 3 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mman.h b/include/linux/mman.h index bd9aadda047b..b66e91b8176c 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -32,7 +32,8 @@ * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. * - * MAP_EXECUTABLE is completely ignored throughout the kernel. + * MAP_EXECUTABLE and MAP_DENYWRITE are completely ignored throughout the + * kernel. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ diff --git a/mm/mmap.c b/mm/mmap.c index 589dc1dc13db..bf11fc6e8311 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1626,8 +1626,6 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, return PTR_ERR(file); } - flags &= ~MAP_DENYWRITE; - retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: if (file) diff --git a/mm/nommu.c b/mm/nommu.c index 3a93d4054810..0987d131bdfc 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1296,8 +1296,6 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, goto out; } - flags &= ~MAP_DENYWRITE; - retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); if (file) -- cgit v1.2.3 From 592ca09be8333bd226f50100328a905bfc377133 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 23 Apr 2021 09:45:45 +0200 Subject: fs: update documentation of get_write_access() and friends MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As VM_DENYWRITE does no longer exists, let's spring-clean the documentation of get_write_access() and friends. Acked-by: "Eric W. Biederman" Acked-by: Christian König Signed-off-by: David Hildenbrand --- include/linux/fs.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..e0dc3e96ed72 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3055,15 +3055,20 @@ static inline void file_end_write(struct file *file) } /* + * This is used for regular files where some users -- especially the + * currently executed binary in a process, previously handled via + * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap + * read-write shared) accesses. + * * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. - * This is used for regular files. - * We cannot support write (and maybe mmap read-write shared) accesses and - * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode - * can have the following values: - * 0: no writers, no VM_DENYWRITE mappings - * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist - * > 0: (i_writecount) users are writing to the file. + * deny_write_access() denies write access to a file. + * allow_write_access() re-enables write access to a file. + * + * The i_writecount field of an inode can have the following values: + * 0: no write access, no denied write access + * < 0: (-i_writecount) users that denied write access to the file. + * > 0: (i_writecount) users that have write access to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to -- cgit v1.2.3 From 4f3eaf452a14ff3982f71c1ca8bdf757254231fa Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 2 Sep 2021 14:52:58 -0700 Subject: mm: report a more useful address for reclaim acquisition A recent lockdep report included these lines: [ 96.177910] 3 locks held by containerd/770: [ 96.177934] #0: ffff88810815ea28 (&mm->mmap_lock#2){++++}-{3:3}, at: do_user_addr_fault+0x115/0x770 [ 96.177999] #1: ffffffff82915020 (rcu_read_lock){....}-{1:2}, at: get_swap_device+0x33/0x140 [ 96.178057] #2: ffffffff82955ba0 (fs_reclaim){+.+.}-{0:0}, at: __fs_reclaim_acquire+0x5/0x30 While it was not useful to that bug report to know where the reclaim lock had been acquired, it might be useful under other circumstances. Allow the caller of __fs_reclaim_acquire to specify the instruction pointer to use. Link: https://lkml.kernel.org/r/20210719185709.1755149-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Omar Sandoval Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Boqun Feng Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 8 ++++---- mm/page_alloc.c | 12 ++++++------ mm/vmscan.c | 8 ++++---- 3 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index e24b1fe348e3..8894825cc4db 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -174,13 +174,13 @@ static inline gfp_t current_gfp_context(gfp_t flags) } #ifdef CONFIG_LOCKDEP -extern void __fs_reclaim_acquire(void); -extern void __fs_reclaim_release(void); +extern void __fs_reclaim_acquire(unsigned long ip); +extern void __fs_reclaim_release(unsigned long ip); extern void fs_reclaim_acquire(gfp_t gfp_mask); extern void fs_reclaim_release(gfp_t gfp_mask); #else -static inline void __fs_reclaim_acquire(void) { } -static inline void __fs_reclaim_release(void) { } +static inline void __fs_reclaim_acquire(unsigned long ip) { } +static inline void __fs_reclaim_release(unsigned long ip) { } static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index eeb3a9cb36bb..51c17bf7b127 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4549,14 +4549,14 @@ static bool __need_reclaim(gfp_t gfp_mask) return true; } -void __fs_reclaim_acquire(void) +void __fs_reclaim_acquire(unsigned long ip) { - lock_map_acquire(&__fs_reclaim_map); + lock_acquire_exclusive(&__fs_reclaim_map, 0, 0, NULL, ip); } -void __fs_reclaim_release(void) +void __fs_reclaim_release(unsigned long ip) { - lock_map_release(&__fs_reclaim_map); + lock_release(&__fs_reclaim_map, ip); } void fs_reclaim_acquire(gfp_t gfp_mask) @@ -4565,7 +4565,7 @@ void fs_reclaim_acquire(gfp_t gfp_mask) if (__need_reclaim(gfp_mask)) { if (gfp_mask & __GFP_FS) - __fs_reclaim_acquire(); + __fs_reclaim_acquire(_RET_IP_); #ifdef CONFIG_MMU_NOTIFIER lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); @@ -4582,7 +4582,7 @@ void fs_reclaim_release(gfp_t gfp_mask) if (__need_reclaim(gfp_mask)) { if (gfp_mask & __GFP_FS) - __fs_reclaim_release(); + __fs_reclaim_release(_RET_IP_); } } EXPORT_SYMBOL_GPL(fs_reclaim_release); diff --git a/mm/vmscan.c b/mm/vmscan.c index eeae2f6bc532..17c4b3fdd7dd 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3812,7 +3812,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); - __fs_reclaim_acquire(); + __fs_reclaim_acquire(_THIS_IP_); count_vm_event(PAGEOUTRUN); @@ -3938,9 +3938,9 @@ restart: wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ - __fs_reclaim_release(); + __fs_reclaim_release(_THIS_IP_); ret = try_to_freeze(); - __fs_reclaim_acquire(); + __fs_reclaim_acquire(_THIS_IP_); if (ret || kthread_should_stop()) break; @@ -3992,7 +3992,7 @@ out: } snapshot_refaults(NULL, pgdat); - __fs_reclaim_release(); + __fs_reclaim_release(_THIS_IP_); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); -- cgit v1.2.3 From 633a2abb9e1cd5c95f3b600f4b2c12cce22ae4a0 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Sep 2021 14:53:04 -0700 Subject: writeback: track number of inodes under writeback Patch series "writeback: Fix bandwidth estimates", v4. Fix estimate of writeback throughput when device is not fully busy doing writeback. Michael Stapelberg has reported that such workload (e.g. generated by linking) tends to push estimated throughput down to 0 and as a result writeback on the device is practically stalled. The first three patches fix the reported issue, the remaining two patches are unrelated cleanups of problems I've noticed when reading the code. This patch (of 4): Track number of inodes under writeback for each bdi_writeback structure. We will use this to decide whether wb does any IO and so we can estimate its writeback throughput. In principle we could use number of pages under writeback (WB_WRITEBACK counter) for this however normal percpu counter reads are too inaccurate for our purposes and summing the counter is too expensive. Link: https://lkml.kernel.org/r/20210713104519.16394-1-jack@suse.cz Link: https://lkml.kernel.org/r/20210713104716.22868-1-jack@suse.cz Signed-off-by: Jan Kara Cc: Wu Fengguang Cc: Michael Stapelberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fs-writeback.c | 5 +++++ include/linux/backing-dev-defs.h | 1 + mm/backing-dev.c | 1 + mm/page-writeback.c | 22 ++++++++++++++++++++-- 4 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4c3370548982..7439ecd44ac9 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -406,6 +406,11 @@ static bool inode_do_switch_wbs(struct inode *inode, inc_wb_stat(new_wb, WB_WRITEBACK); } + if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) { + atomic_dec(&old_wb->writeback_inodes); + atomic_inc(&new_wb->writeback_inodes); + } + wb_get(new_wb); /* diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 1d7edad9914f..06fb8e13f6bc 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -116,6 +116,7 @@ struct bdi_writeback { struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ + atomic_t writeback_inodes; /* number of inodes under writeback */ struct percpu_counter stat[NR_WB_STAT_ITEMS]; unsigned long congested; /* WB_[a]sync_congested flags */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index f5561ea7d90a..b4c707ddedb1 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -293,6 +293,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, INIT_LIST_HEAD(&wb->b_dirty_time); spin_lock_init(&wb->list_lock); + atomic_set(&wb->writeback_inodes, 0); wb->bw_time_stamp = jiffies; wb->balanced_dirty_ratelimit = INIT_BW; wb->dirty_ratelimit = INIT_BW; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 9f63548f247c..e1aa1c9d8e36 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2731,6 +2731,16 @@ int clear_page_dirty_for_io(struct page *page) } EXPORT_SYMBOL(clear_page_dirty_for_io); +static void wb_inode_writeback_start(struct bdi_writeback *wb) +{ + atomic_inc(&wb->writeback_inodes); +} + +static void wb_inode_writeback_end(struct bdi_writeback *wb) +{ + atomic_dec(&wb->writeback_inodes); +} + int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); @@ -2752,6 +2762,9 @@ int test_clear_page_writeback(struct page *page) dec_wb_stat(wb, WB_WRITEBACK); __wb_writeout_inc(wb); + if (!mapping_tagged(mapping, + PAGECACHE_TAG_WRITEBACK)) + wb_inode_writeback_end(wb); } } @@ -2794,8 +2807,13 @@ int __test_set_page_writeback(struct page *page, bool keep_write) PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); - if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) - inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); + if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { + struct bdi_writeback *wb = inode_to_wb(inode); + + inc_wb_stat(wb, WB_WRITEBACK); + if (!on_wblist) + wb_inode_writeback_start(wb); + } /* * We can come through here when swapping anonymous -- cgit v1.2.3 From fee468fdf41cdf36ba6b5a780e2474d0a3e066ac Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Sep 2021 14:53:06 -0700 Subject: writeback: reliably update bandwidth estimation Currently we trigger writeback bandwidth estimation from balance_dirty_pages() and from wb_writeback(). However neither of these need to trigger when the system is relatively idle and writeback is triggered e.g. from fsync(2). Make sure writeback estimates happen reliably by triggering them from do_writepages(). Link: https://lkml.kernel.org/r/20210713104716.22868-2-jack@suse.cz Signed-off-by: Jan Kara Cc: Michael Stapelberg Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fs-writeback.c | 3 --- include/linux/backing-dev.h | 19 +++++++++++++++++++ include/linux/writeback.h | 1 - mm/page-writeback.c | 39 +++++++++++++++++++++++++++------------ 4 files changed, 46 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 7439ecd44ac9..867984e778c3 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2004,7 +2004,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { - unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; @@ -2058,8 +2057,6 @@ static long wb_writeback(struct bdi_writeback *wb, progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); - wb_update_bandwidth(wb, wb_start); - /* * Did we write something? Try for more * diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 44df4fcef65c..8a886bca51e5 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -288,6 +288,17 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) return inode->i_wb; } +static inline struct bdi_writeback *inode_to_wb_wbc( + struct inode *inode, + struct writeback_control *wbc) +{ + /* + * If wbc does not have inode attached, it means cgroup writeback was + * disabled when wbc started. Just use the default wb in that case. + */ + return wbc->wb ? wbc->wb : &inode_to_bdi(inode)->wb; +} + /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode @@ -366,6 +377,14 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode) return &inode_to_bdi(inode)->wb; } +static inline struct bdi_writeback *inode_to_wb_wbc( + struct inode *inode, + struct writeback_control *wbc) +{ + return inode_to_wb(inode); +} + + static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 667e86cfbdcf..2480322c06a7 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -379,7 +379,6 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); -void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time); void balance_dirty_pages_ratelimited(struct address_space *mapping); bool wb_over_bg_thresh(struct bdi_writeback *wb); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e1aa1c9d8e36..e4a381b8944b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1332,7 +1332,6 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, struct dirty_throttle_control *mdtc, - unsigned long start_time, bool update_ratelimit) { struct bdi_writeback *wb = gdtc->wb; @@ -1352,13 +1351,6 @@ static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); - /* - * Skip quiet periods when disk bandwidth is under-utilized. - * (at least 1s idle time between two flusher runs) - */ - if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time)) - goto snapshot; - if (update_ratelimit) { domain_update_bandwidth(gdtc, now); wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); @@ -1374,17 +1366,36 @@ static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, } wb_update_write_bandwidth(wb, elapsed, written); -snapshot: wb->dirtied_stamp = dirtied; wb->written_stamp = written; wb->bw_time_stamp = now; } -void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time) +static void wb_update_bandwidth(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; - __wb_update_bandwidth(&gdtc, NULL, start_time, false); + spin_lock(&wb->list_lock); + __wb_update_bandwidth(&gdtc, NULL, false); + spin_unlock(&wb->list_lock); +} + +/* Interval after which we consider wb idle and don't estimate bandwidth */ +#define WB_BANDWIDTH_IDLE_JIF (HZ) + +static void wb_bandwidth_estimate_start(struct bdi_writeback *wb) +{ + unsigned long now = jiffies; + unsigned long elapsed = now - READ_ONCE(wb->bw_time_stamp); + + if (elapsed > WB_BANDWIDTH_IDLE_JIF && + !atomic_read(&wb->writeback_inodes)) { + spin_lock(&wb->list_lock); + wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED); + wb->written_stamp = wb_stat(wb, WB_WRITTEN); + wb->bw_time_stamp = now; + spin_unlock(&wb->list_lock); + } } /* @@ -1713,7 +1724,7 @@ free_running: if (time_is_before_jiffies(wb->bw_time_stamp + BANDWIDTH_INTERVAL)) { spin_lock(&wb->list_lock); - __wb_update_bandwidth(gdtc, mdtc, start_time, true); + __wb_update_bandwidth(gdtc, mdtc, true); spin_unlock(&wb->list_lock); } @@ -2347,9 +2358,12 @@ EXPORT_SYMBOL(generic_writepages); int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; + struct bdi_writeback *wb; if (wbc->nr_to_write <= 0) return 0; + wb = inode_to_wb_wbc(mapping->host, wbc); + wb_bandwidth_estimate_start(wb); while (1) { if (mapping->a_ops->writepages) ret = mapping->a_ops->writepages(mapping, wbc); @@ -2360,6 +2374,7 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) cond_resched(); congestion_wait(BLK_RW_ASYNC, HZ/50); } + wb_update_bandwidth(wb); return ret; } -- cgit v1.2.3 From 45a2966fd64147518dc5bca25f447bd0fb5359ac Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Sep 2021 14:53:09 -0700 Subject: writeback: fix bandwidth estimate for spiky workload Michael Stapelberg has reported that for workload with short big spikes of writes (GCC linker seem to trigger this frequently) the write throughput is heavily underestimated and tends to steadily sink until it reaches zero. This has rather bad impact on writeback throttling (causing stalls). The problem is that writeback throughput estimate gets updated at most once per 200 ms. One update happens early after we submit pages for writeback (at that point writeout of only small fraction of pages is completed and thus observed throughput is tiny). Next update happens only during the next write spike (updates happen only from inode writeback and dirty throttling code) and if that is more than 1s after previous spike, we decide system was idle and just ignore whatever was written until this moment. Fix the problem by making sure writeback throughput estimate is also updated shortly after writeback completes to get reasonable estimate of throughput for spiky workloads. [jack@suse.cz: avoid division by 0 in wb_update_dirty_ratelimit()] Link: https://lore.kernel.org/lkml/20210617095309.3542373-1-stapelberg+linux@google.com Link: https://lkml.kernel.org/r/20210713104716.22868-3-jack@suse.cz Signed-off-by: Jan Kara Reported-by: Michael Stapelberg Tested-by: Michael Stapelberg Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 1 + include/linux/writeback.h | 1 + mm/backing-dev.c | 10 ++++++++++ mm/page-writeback.c | 39 +++++++++++++++++++++++++-------------- 4 files changed, 37 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 06fb8e13f6bc..33207004cfde 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -143,6 +143,7 @@ struct bdi_writeback { spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ + struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ unsigned long dirty_sleep; /* last wait */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 2480322c06a7..cbaef099645e 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -379,6 +379,7 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); +void wb_update_bandwidth(struct bdi_writeback *wb); void balance_dirty_pages_ratelimited(struct address_space *mapping); bool wb_over_bg_thresh(struct bdi_writeback *wb); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index b4c707ddedb1..6122c78ce914 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -271,6 +271,14 @@ void wb_wakeup_delayed(struct bdi_writeback *wb) spin_unlock_bh(&wb->work_lock); } +static void wb_update_bandwidth_workfn(struct work_struct *work) +{ + struct bdi_writeback *wb = container_of(to_delayed_work(work), + struct bdi_writeback, bw_dwork); + + wb_update_bandwidth(wb); +} + /* * Initial write bandwidth: 100 MB/s */ @@ -303,6 +311,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); + INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); wb->dirty_sleep = jiffies; err = fprop_local_init_percpu(&wb->completions, gfp); @@ -351,6 +360,7 @@ static void wb_shutdown(struct bdi_writeback *wb) mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); + flush_delayed_work(&wb->bw_dwork); } static void wb_exit(struct bdi_writeback *wb) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e4a381b8944b..156f5888c09d 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1336,18 +1336,19 @@ static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; - unsigned long elapsed = now - wb->bw_time_stamp; + unsigned long elapsed; unsigned long dirtied; unsigned long written; - lockdep_assert_held(&wb->list_lock); + spin_lock(&wb->list_lock); /* - * rate-limit, only update once every 200ms. + * Lockless checks for elapsed time are racy and delayed update after + * IO completion doesn't do it at all (to make sure written pages are + * accounted reasonably quickly). Make sure elapsed >= 1 to avoid + * division errors. */ - if (elapsed < BANDWIDTH_INTERVAL) - return; - + elapsed = max(now - wb->bw_time_stamp, 1UL); dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); @@ -1369,15 +1370,14 @@ static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, wb->dirtied_stamp = dirtied; wb->written_stamp = written; wb->bw_time_stamp = now; + spin_unlock(&wb->list_lock); } -static void wb_update_bandwidth(struct bdi_writeback *wb) +void wb_update_bandwidth(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; - spin_lock(&wb->list_lock); __wb_update_bandwidth(&gdtc, NULL, false); - spin_unlock(&wb->list_lock); } /* Interval after which we consider wb idle and don't estimate bandwidth */ @@ -1722,11 +1722,8 @@ free_running: wb->dirty_exceeded = 1; if (time_is_before_jiffies(wb->bw_time_stamp + - BANDWIDTH_INTERVAL)) { - spin_lock(&wb->list_lock); + BANDWIDTH_INTERVAL)) __wb_update_bandwidth(gdtc, mdtc, true); - spin_unlock(&wb->list_lock); - } /* throttle according to the chosen dtc */ dirty_ratelimit = wb->dirty_ratelimit; @@ -2374,7 +2371,13 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) cond_resched(); congestion_wait(BLK_RW_ASYNC, HZ/50); } - wb_update_bandwidth(wb); + /* + * Usually few pages are written by now from those we've just submitted + * but if there's constant writeback being submitted, this makes sure + * writeback bandwidth is updated once in a while. + */ + if (time_is_before_jiffies(wb->bw_time_stamp + BANDWIDTH_INTERVAL)) + wb_update_bandwidth(wb); return ret; } @@ -2754,6 +2757,14 @@ static void wb_inode_writeback_start(struct bdi_writeback *wb) static void wb_inode_writeback_end(struct bdi_writeback *wb) { atomic_dec(&wb->writeback_inodes); + /* + * Make sure estimate of writeback throughput gets updated after + * writeback completed. We delay the update by BANDWIDTH_INTERVAL + * (which is the interval other bandwidth updates use for batching) so + * that if multiple inodes end writeback at a similar time, they get + * batched into one bandwidth update. + */ + queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); } int test_clear_page_writeback(struct page *page) -- cgit v1.2.3 From 7490a2d248145d8694e1e9828801b496250fd697 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 2 Sep 2021 14:53:27 -0700 Subject: writeback: memcg: simplify cgroup_writeback_by_id Currently cgroup_writeback_by_id calls mem_cgroup_wb_stats() to get dirty pages for a memcg. However mem_cgroup_wb_stats() does a lot more than just get the number of dirty pages. Just directly get the number of dirty pages instead of calling mem_cgroup_wb_stats(). Also cgroup_writeback_by_id() is only called for best-effort dirty flushing, so remove the unused 'nr' parameter and no need to explicitly flush memcg stats. Link: https://lkml.kernel.org/r/20210722182627.2267368-1-shakeelb@google.com Signed-off-by: Shakeel Butt Reviewed-by: Jan Kara Cc: Tejun Heo Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fs-writeback.c | 20 +++++++++----------- include/linux/memcontrol.h | 15 +++++++++++++++ include/linux/writeback.h | 2 +- mm/memcontrol.c | 13 +------------ 4 files changed, 26 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 867984e778c3..35894a2dba75 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1039,20 +1039,20 @@ restart: * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id - * @nr: number of pages to write, 0 for best-effort dirty flushing * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ -int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr, +int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; + unsigned long dirty; int ret; /* lookup bdi and memcg */ @@ -1081,24 +1081,22 @@ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr, } /* - * If @nr is zero, the caller is attempting to write out most of + * The caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. + * + * BTW the memcg stats are flushed periodically and this is best-effort + * estimation, so some potential error is ok. */ - if (!nr) { - unsigned long filepages, headroom, dirty, writeback; - - mem_cgroup_wb_stats(wb, &filepages, &headroom, &dirty, - &writeback); - nr = dirty * 10 / 8; - } + dirty = memcg_page_state(mem_cgroup_from_css(memcg_css), NR_FILE_DIRTY); + dirty = dirty * 10 / 8; /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { - work->nr_pages = nr; + work->nr_pages = dirty; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 24797929d8a1..3403ec77528a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -955,6 +955,16 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, local_irq_restore(flags); } +static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) +{ + long x = READ_ONCE(memcg->vmstats.state[idx]); +#ifdef CONFIG_SMP + if (x < 0) + x = 0; +#endif + return x; +} + static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { @@ -1391,6 +1401,11 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, { } +static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) +{ + return 0; +} + static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { diff --git a/include/linux/writeback.h b/include/linux/writeback.h index cbaef099645e..aeda2c0c9986 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -218,7 +218,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes); -int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr_pages, +int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done); void cgroup_writeback_umount(void); bool cleanup_offline_cgwb(struct bdi_writeback *wb); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 702a81dfe72d..1047f0271ff8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -645,17 +645,6 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id()); } -/* idx can be of type enum memcg_stat_item or node_stat_item. */ -static unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) -{ - long x = READ_ONCE(memcg->vmstats.state[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; -} - /* idx can be of type enum memcg_stat_item or node_stat_item. */ static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { @@ -4668,7 +4657,7 @@ void mem_cgroup_flush_foreign(struct bdi_writeback *wb) atomic_read(&frn->done.cnt) == 1) { frn->at = 0; trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id); - cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, 0, + cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, WB_REASON_FOREIGN_FLUSH, &frn->done); } -- cgit v1.2.3 From 6de522d1667f628376517e4b177af10c739d745b Mon Sep 17 00:00:00 2001 From: Jing Yangyang Date: Thu, 2 Sep 2021 14:53:30 -0700 Subject: include/linux/buffer_head.h: fix boolreturn.cocci warnings ./include/linux/buffer_head.h:412:64-65:WARNING:return of 0/1 in function 'has_bh_in_lru' with return type bool Return statements in functions returning bool should use true/false instead of 1/0. Generated by: scripts/coccinelle/misc/boolreturn.cocci Link: https://lkml.kernel.org/r/20210824055828.58783-1-deng.changcheng@zte.com.cn Signed-off-by: Jing Yangyang Reported-by: Zeal Robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index e7e99da31349..6486d3c19463 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -409,7 +409,7 @@ static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } static inline void invalidate_bh_lrus_cpu(int cpu) {} -static inline bool has_bh_in_lru(int cpu, void *dummy) { return 0; } +static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; } #define buffer_heads_over_limit 0 #endif /* CONFIG_BLOCK */ -- cgit v1.2.3 From 54d516b1d62ff8f17cee2da06e5e4706a0d00b8a Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 2 Sep 2021 14:53:51 -0700 Subject: mm/gup: small refactoring: simplify try_grab_page() try_grab_page() does the same thing as try_grab_compound_head(..., refs=1, ...), just with a different API. So there is a lot of code duplication there. Change try_grab_page() to call try_grab_compound_head(), while keeping the API contract identical for callers. Also, now that try_grab_compound_head() always has a caller, remove the __maybe_unused annotation. Link: https://lkml.kernel.org/r/20210813044133.1536842-3-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Christian Borntraeger Cc: Heiko Carstens Cc: Vasily Gorbik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- mm/gup.c | 35 +++++------------------------------ 2 files changed, 7 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7ca22e6e694a..af4845e81b84 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1214,8 +1214,8 @@ static inline void get_page(struct page *page) } bool __must_check try_grab_page(struct page *page, unsigned int flags); -__maybe_unused struct page *try_grab_compound_head(struct page *page, int refs, - unsigned int flags); +struct page *try_grab_compound_head(struct page *page, int refs, + unsigned int flags); static inline __must_check bool try_get_page(struct page *page) diff --git a/mm/gup.c b/mm/gup.c index 26ce6bb52044..d60419ed9262 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -124,8 +124,8 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) * considered failure, and furthermore, a likely bug in the caller, so a warning * is also emitted. */ -__maybe_unused struct page *try_grab_compound_head(struct page *page, - int refs, unsigned int flags) +struct page *try_grab_compound_head(struct page *page, + int refs, unsigned int flags) { if (flags & FOLL_GET) return try_get_compound_head(page, refs); @@ -208,35 +208,10 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags) */ bool __must_check try_grab_page(struct page *page, unsigned int flags) { - WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN)); + if (!(flags & (FOLL_GET | FOLL_PIN))) + return true; - if (flags & FOLL_GET) - return try_get_page(page); - else if (flags & FOLL_PIN) { - int refs = 1; - - page = compound_head(page); - - if (WARN_ON_ONCE(page_ref_count(page) <= 0)) - return false; - - if (hpage_pincount_available(page)) - hpage_pincount_add(page, 1); - else - refs = GUP_PIN_COUNTING_BIAS; - - /* - * Similar to try_grab_compound_head(): even if using the - * hpage_pincount_add/_sub() routines, be sure to - * *also* increment the normal page refcount field at least - * once, so that the page really is pinned. - */ - page_ref_add(page, refs); - - mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1); - } - - return true; + return try_grab_compound_head(page, 1, flags); } /** -- cgit v1.2.3 From 9857a17f206ff374aea78bccfb687f145368be2e Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 2 Sep 2021 14:53:54 -0700 Subject: mm/gup: remove try_get_page(), call try_get_compound_head() directly try_get_page() is very similar to try_get_compound_head(), and in fact try_get_page() has fallen a little behind in terms of maintenance: try_get_compound_head() handles speculative page references more thoroughly. There are only two try_get_page() callsites, so just call try_get_compound_head() directly from those, and remove try_get_page() entirely. Also, seeing as how this changes try_get_compound_head() into a non-static function, provide some kerneldoc documentation for it. Link: https://lkml.kernel.org/r/20210813044133.1536842-4-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Christian Borntraeger Cc: Heiko Carstens Cc: Vasily Gorbik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/mm/fault.c | 2 +- fs/pipe.c | 2 +- include/linux/mm.h | 10 +--------- mm/gup.c | 21 +++++++++++++++++---- 4 files changed, 20 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e33c43b38afe..81d760749987 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -817,7 +817,7 @@ void do_secure_storage_access(struct pt_regs *regs) break; case KERNEL_FAULT: page = phys_to_page(addr); - if (unlikely(!try_get_page(page))) + if (unlikely(!try_get_compound_head(page, 1))) break; rc = arch_make_page_accessible(page); put_page(page); diff --git a/fs/pipe.c b/fs/pipe.c index 6d4342bad9f1..1fa1f52763f0 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -191,7 +191,7 @@ EXPORT_SYMBOL(generic_pipe_buf_try_steal); */ bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - return try_get_page(buf->page); + return try_get_compound_head(buf->page, 1); } EXPORT_SYMBOL(generic_pipe_buf_get); diff --git a/include/linux/mm.h b/include/linux/mm.h index af4845e81b84..d3439dd4f4ba 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1217,15 +1217,7 @@ bool __must_check try_grab_page(struct page *page, unsigned int flags); struct page *try_grab_compound_head(struct page *page, int refs, unsigned int flags); - -static inline __must_check bool try_get_page(struct page *page) -{ - page = compound_head(page); - if (WARN_ON_ONCE(page_ref_count(page) <= 0)) - return false; - page_ref_inc(page); - return true; -} +struct page *try_get_compound_head(struct page *page, int refs); static inline void put_page(struct page *page) { diff --git a/mm/gup.c b/mm/gup.c index d60419ed9262..1c7f4ec6990b 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -62,11 +62,24 @@ static void put_page_refs(struct page *page, int refs) put_page(page); } -/* - * Return the compound head page with ref appropriately incremented, - * or NULL if that failed. +/** + * try_get_compound_head() - return the compound head page with refcount + * appropriately incremented, or NULL if that failed. + * + * This handles potential refcount overflow correctly. It also works correctly + * for various lockless get_user_pages()-related callers, due to the use of + * page_cache_add_speculative(). + * + * Even though the name includes "compound_head", this function is still + * appropriate for callers that have a non-compound @page to get. + * + * @page: pointer to page to be gotten + * @refs: the value to add to the page's refcount + * + * Return: head page (with refcount appropriately incremented) for success, or + * NULL upon failure. */ -static inline struct page *try_get_compound_head(struct page *page, int refs) +struct page *try_get_compound_head(struct page *page, int refs) { struct page *head = compound_head(page); -- cgit v1.2.3 From 3969b1a654fb09b7915efc1aa4ad45daf932e12f Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 2 Sep 2021 14:54:00 -0700 Subject: mm: delete unused get_kernel_page() get_kernel_page() was added in 2012 by [1]. It was used for a while for NFS, but then in 2014, a refactoring [2] removed all callers, and it has apparently not been used since. Remove get_kernel_page() because it has no callers. [1] commit 18022c5d8627 ("mm: add get_kernel_page[s] for pinning of kernel addresses for I/O") [2] commit 91f79c43d1b5 ("new helper: iov_iter_get_pages_alloc()") Link: https://lkml.kernel.org/r/20210729221847.1165665-1-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: David Hildenbrand Cc: Mel Gorman Cc: Rik van Riel Cc: David S. Miller Cc: Eric B Munson Cc: Eric Paris Cc: James Morris Cc: Mike Christie Cc: Neil Brown Cc: Peter Zijlstra Cc: Sebastian Andrzej Siewior Cc: Trond Myklebust Cc: Xiaotian Feng Cc: Mark Salter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - mm/swap.c | 22 ---------------------- 2 files changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d3439dd4f4ba..35bbac32b6f6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1839,7 +1839,6 @@ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); -int get_kernel_page(unsigned long start, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); diff --git a/mm/swap.c b/mm/swap.c index 19600430e536..897200d27dd0 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -179,28 +179,6 @@ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, } EXPORT_SYMBOL_GPL(get_kernel_pages); -/* - * get_kernel_page() - pin a kernel page in memory - * @start: starting kernel address - * @write: pinning for read/write, currently ignored - * @pages: array that receives pointer to the page pinned. - * Must be at least nr_segs long. - * - * Returns 1 if page is pinned. If the page was not pinned, returns - * -errno. The page returned must be released with a put_page() call - * when it is finished with. - */ -int get_kernel_page(unsigned long start, int write, struct page **pages) -{ - const struct kvec kiov = { - .iov_base = (void *)start, - .iov_len = PAGE_SIZE - }; - - return get_kernel_pages(&kiov, 1, write, pages); -} -EXPORT_SYMBOL_GPL(get_kernel_page); - static void pagevec_lru_move_fn(struct pagevec *pvec, void (*move_fn)(struct page *page, struct lruvec *lruvec)) { -- cgit v1.2.3 From bf11b9a8e9a93c1fc0ebfc2929622d5cf7d43888 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 2 Sep 2021 14:54:03 -0700 Subject: shmem: use raw_spinlock_t for ->stat_lock Each CPU has SHMEM_INO_BATCH inodes available in `->ino_batch' which is per-CPU. Access here is serialized by disabling preemption. If the pool is empty, it gets reloaded from `->next_ino'. Access here is serialized by ->stat_lock which is a spinlock_t and can not be acquired with disabled preemption. One way around it would make per-CPU ino_batch struct containing the inode number a local_lock_t. Another solution is to promote ->stat_lock to a raw_spinlock_t. The critical sections are short. The mpol_put() must be moved outside of the critical section to avoid invoking the destructor with disabled preemption. Link: https://lkml.kernel.org/r/20210806142916.jdwkb5bx62q5fwfo@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 2 +- mm/shmem.c | 31 +++++++++++++++++-------------- 2 files changed, 18 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 8e775ce517bb..0a8499fb9c3c 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -31,7 +31,7 @@ struct shmem_sb_info { struct percpu_counter used_blocks; /* How many are allocated */ unsigned long max_inodes; /* How many inodes are allowed */ unsigned long free_inodes; /* How many are left for allocation */ - spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ + raw_spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ umode_t mode; /* Mount mode for root directory */ unsigned char huge; /* Whether to try for hugepages */ kuid_t uid; /* Mount uid for root directory */ diff --git a/mm/shmem.c b/mm/shmem.c index dacda7463d54..7eec13e39ac3 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -278,10 +278,10 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) ino_t ino; if (!(sb->s_flags & SB_KERNMOUNT)) { - spin_lock(&sbinfo->stat_lock); + raw_spin_lock(&sbinfo->stat_lock); if (sbinfo->max_inodes) { if (!sbinfo->free_inodes) { - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); return -ENOSPC; } sbinfo->free_inodes--; @@ -304,7 +304,7 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) } *inop = ino; } - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); } else if (inop) { /* * __shmem_file_setup, one of our callers, is lock-free: it @@ -319,13 +319,14 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) * to worry about things like glibc compatibility. */ ino_t *next_ino; + next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu()); ino = *next_ino; if (unlikely(ino % SHMEM_INO_BATCH == 0)) { - spin_lock(&sbinfo->stat_lock); + raw_spin_lock(&sbinfo->stat_lock); ino = sbinfo->next_ino; sbinfo->next_ino += SHMEM_INO_BATCH; - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); if (unlikely(is_zero_ino(ino))) ino++; } @@ -341,9 +342,9 @@ static void shmem_free_inode(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); + raw_spin_lock(&sbinfo->stat_lock); sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); } } @@ -1453,10 +1454,10 @@ static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { struct mempolicy *mpol = NULL; if (sbinfo->mpol) { - spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ + raw_spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ mpol = sbinfo->mpol; mpol_get(mpol); - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); } return mpol; } @@ -3488,9 +3489,10 @@ static int shmem_reconfigure(struct fs_context *fc) struct shmem_options *ctx = fc->fs_private; struct shmem_sb_info *sbinfo = SHMEM_SB(fc->root->d_sb); unsigned long inodes; + struct mempolicy *mpol = NULL; const char *err; - spin_lock(&sbinfo->stat_lock); + raw_spin_lock(&sbinfo->stat_lock); inodes = sbinfo->max_inodes - sbinfo->free_inodes; if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) { if (!sbinfo->max_blocks) { @@ -3535,14 +3537,15 @@ static int shmem_reconfigure(struct fs_context *fc) * Preserve previous mempolicy unless mpol remount option was specified. */ if (ctx->mpol) { - mpol_put(sbinfo->mpol); + mpol = sbinfo->mpol; sbinfo->mpol = ctx->mpol; /* transfers initial ref */ ctx->mpol = NULL; } - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); + mpol_put(mpol); return 0; out: - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); return invalfc(fc, "%s", err); } @@ -3659,7 +3662,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) sbinfo->mpol = ctx->mpol; ctx->mpol = NULL; - spin_lock_init(&sbinfo->stat_lock); + raw_spin_lock_init(&sbinfo->stat_lock); if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL)) goto failed; spin_lock_init(&sbinfo->shrinklist_lock); -- cgit v1.2.3 From d144bf6205342a4b5fed5d204ae18849a4de741b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 2 Sep 2021 14:54:21 -0700 Subject: huge tmpfs: fix split_huge_page() after FALLOC_FL_KEEP_SIZE A successful shmem_fallocate() guarantees that the extent has been reserved, even beyond i_size when the FALLOC_FL_KEEP_SIZE flag was used. But that guarantee is broken by shmem_unused_huge_shrink()'s attempts to split huge pages and free their excess beyond i_size; and by other uses of split_huge_page() near i_size. It's sad to add a shmem inode field just for this, but I did not find a better way to keep the guarantee. A flag to say KEEP_SIZE has been used would be cheaper, but I'm averse to unclearable flags. The fallocend field is not perfect either (many disjoint ranges might be fallocated), but good enough; and gains another use later on. Link: https://lkml.kernel.org/r/ca9a146-3a59-6cd3-7f28-e9a044bb1052@google.com Fixes: 779750d20b93 ("shmem: split huge pages beyond i_size under memory pressure") Signed-off-by: Hugh Dickins Reviewed-by: Yang Shi Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Michal Hocko Cc: Mike Kravetz Cc: Rik van Riel Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 13 +++++++++++++ mm/huge_memory.c | 6 ++++-- mm/shmem.c | 15 ++++++++++++++- 3 files changed, 31 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 0a8499fb9c3c..bfc5899d18e0 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -18,6 +18,7 @@ struct shmem_inode_info { unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ + pgoff_t fallocend; /* highest fallocate endindex */ struct list_head shrinklist; /* shrinkable hpage inodes */ struct list_head swaplist; /* chain of maybes on swap */ struct shared_policy policy; /* NUMA memory alloc policy */ @@ -119,6 +120,18 @@ static inline bool shmem_file(struct file *file) return shmem_mapping(file->f_mapping); } +/* + * If fallocate(FALLOC_FL_KEEP_SIZE) has been used, there may be pages + * beyond i_size's notion of EOF, which fallocate has committed to reserving: + * which split_huge_page() must therefore not delete. This use of a single + * "fallocend" per inode errs on the side of not deleting a reservation when + * in doubt: there are plenty of cases when it preserves unreserved pages. + */ +static inline pgoff_t shmem_fallocend(struct inode *inode, pgoff_t eof) +{ + return max(eof, SHMEM_I(inode)->fallocend); +} + extern bool shmem_charge(struct inode *inode, long pages); extern void shmem_uncharge(struct inode *inode, long pages); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index afff3ac87067..890fb73ac89b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2454,11 +2454,11 @@ static void __split_huge_page(struct page *page, struct list_head *list, for (i = nr - 1; i >= 1; i--) { __split_huge_page_tail(head, i, lruvec, list); - /* Some pages can be beyond i_size: drop them from page cache */ + /* Some pages can be beyond EOF: drop them from page cache */ if (head[i].index >= end) { ClearPageDirty(head + i); __delete_from_page_cache(head + i, NULL); - if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head)) + if (shmem_mapping(head->mapping)) shmem_uncharge(head->mapping->host, 1); put_page(head + i); } else if (!PageAnon(page)) { @@ -2686,6 +2686,8 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) * head page lock is good enough to serialize the trimming. */ end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); + if (shmem_mapping(mapping)) + end = shmem_fallocend(mapping->host, end); } /* diff --git a/mm/shmem.c b/mm/shmem.c index 9ef579f6cab3..e391325dfc21 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -902,6 +902,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (lend == -1) end = -1; /* unsigned, so actually very big */ + if (info->fallocend > start && info->fallocend <= end && !unfalloc) + info->fallocend = start; + pagevec_init(&pvec); index = start; while (index < end && find_lock_entries(mapping, index, end - 1, @@ -2650,7 +2653,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_falloc shmem_falloc; - pgoff_t start, index, end; + pgoff_t start, index, end, undo_fallocend; int error; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) @@ -2719,6 +2722,15 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, inode->i_private = &shmem_falloc; spin_unlock(&inode->i_lock); + /* + * info->fallocend is only relevant when huge pages might be + * involved: to prevent split_huge_page() freeing fallocated + * pages when FALLOC_FL_KEEP_SIZE committed beyond i_size. + */ + undo_fallocend = info->fallocend; + if (info->fallocend < end) + info->fallocend = end; + for (index = start; index < end; ) { struct page *page; @@ -2733,6 +2745,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, else error = shmem_getpage(inode, index, &page, SGP_FALLOC); if (error) { + info->fallocend = undo_fallocend; /* Remove the !PageUptodate pages we added */ if (index > start) { shmem_undo_range(inode, -- cgit v1.2.3 From acdd9f8e0fed9f1bd7e83a8ff934694bb4c9a72b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 2 Sep 2021 14:54:34 -0700 Subject: huge tmpfs: SGP_NOALLOC to stop collapse_file() on race khugepaged's collapse_file() currently uses SGP_NOHUGE to tell shmem_getpage() not to try allocating a huge page, in the very unlikely event that a racing hole-punch removes the swapped or fallocated page as soon as i_pages lock is dropped. We want to consolidate shmem's huge decisions, removing SGP_HUGE and SGP_NOHUGE; but cannot quite persuade ourselves that it's okay to regress the protection in this case - Yang Shi points out that the huge page would remain indefinitely, charged to root instead of the intended memcg. collapse_file() should not even allocate a small page in this case: why proceed if someone is punching a hole? SGP_READ is almost the right flag here, except that it optimizes away from a fallocated page, with NULL to tell caller to fill with zeroes (like a hole); whereas collapse_file()'s sequence relies on using a cache page. Add SGP_NOALLOC just for this. There are too many consecutive "if (page"s there in shmem_getpage_gfp(): group it better; and fix the outdated "bring it back from swap" comment. Link: https://lkml.kernel.org/r/1355343b-acf-4653-ef79-6aee40214ac5@google.com Signed-off-by: Hugh Dickins Reviewed-by: Yang Shi Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Michal Hocko Cc: Mike Kravetz Cc: Rik van Riel Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 1 + mm/khugepaged.c | 2 +- mm/shmem.c | 29 +++++++++++++++++------------ 3 files changed, 19 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index bfc5899d18e0..a3f4502ec8a9 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -94,6 +94,7 @@ extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, /* Flag allocation requirements to shmem_getpage */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ + SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ SGP_NOHUGE, /* like SGP_CACHE, but no huge pages */ SGP_HUGE, /* like SGP_CACHE, huge pages preferred */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index b0412be08fa2..045cc579f724 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1721,7 +1721,7 @@ static void collapse_file(struct mm_struct *mm, xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_getpage(mapping->host, index, &page, - SGP_NOHUGE)) { + SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; } diff --git a/mm/shmem.c b/mm/shmem.c index 2df6a5370cd7..867cb404090a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1854,26 +1854,31 @@ repeat: return error; } - if (page) + if (page) { hindex = page->index; - if (page && sgp == SGP_WRITE) - mark_page_accessed(page); - - /* fallocated page? */ - if (page && !PageUptodate(page)) { + if (sgp == SGP_WRITE) + mark_page_accessed(page); + if (PageUptodate(page)) + goto out; + /* fallocated page */ if (sgp != SGP_READ) goto clear; unlock_page(page); put_page(page); - page = NULL; - hindex = index; } - if (page || sgp == SGP_READ) - goto out; /* - * Fast cache lookup did not find it: - * bring it back from swap or allocate. + * SGP_READ: succeed on hole, with NULL page, letting caller zero. + * SGP_NOALLOC: fail on hole, with NULL page, letting caller fail. + */ + *pagep = NULL; + if (sgp == SGP_READ) + return 0; + if (sgp == SGP_NOALLOC) + return -ENOENT; + + /* + * Fast cache lookup and swap lookup did not find it: allocate. */ if (vma && userfaultfd_missing(vma)) { -- cgit v1.2.3 From 5e6e5a12a44ca5ff2b130d8d39aaf9b8c026de94 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 2 Sep 2021 14:54:37 -0700 Subject: huge tmpfs: shmem_is_huge(vma, inode, index) Extend shmem_huge_enabled(vma) to shmem_is_huge(vma, inode, index), so that a consistent set of checks can be applied, even when the inode is accessed through read/write syscalls (with NULL vma) instead of mmaps (the index argument is seldom of interest, but required by mount option "huge=within_size"). Clean up and rearrange the checks a little. This then replaces the checks which shmem_fault() and shmem_getpage_gfp() were making, and eliminates the SGP_HUGE and SGP_NOHUGE modes. Replace a couple of 0s by explicit SHMEM_HUGE_NEVERs; and replace the obscure !shmem_mapping() symlink check by explicit S_ISLNK() - nothing else needs that symlink check, so leave it there in shmem_getpage_gfp(). Link: https://lkml.kernel.org/r/23a77889-2ddc-b030-75cd-44ca27fd4d1@google.com Signed-off-by: Hugh Dickins Reviewed-by: Yang Shi Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Michal Hocko Cc: Mike Kravetz Cc: Rik van Riel Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 9 ++++-- mm/shmem.c | 84 ++++++++++++++---------------------------------- 2 files changed, 31 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index a3f4502ec8a9..166158b6e917 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -86,7 +86,12 @@ extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); extern int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse); -extern bool shmem_huge_enabled(struct vm_area_struct *vma); +extern bool shmem_is_huge(struct vm_area_struct *vma, + struct inode *inode, pgoff_t index); +static inline bool shmem_huge_enabled(struct vm_area_struct *vma) +{ + return shmem_is_huge(vma, file_inode(vma->vm_file), vma->vm_pgoff); +} extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); @@ -96,8 +101,6 @@ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ - SGP_NOHUGE, /* like SGP_CACHE, but no huge pages */ - SGP_HUGE, /* like SGP_CACHE, huge pages preferred */ SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */ SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; diff --git a/mm/shmem.c b/mm/shmem.c index 867cb404090a..69c9788a0094 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -471,39 +471,35 @@ static bool shmem_confirm_swap(struct address_space *mapping, #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* ifdef here to avoid bloating shmem.o when not necessary */ -static int shmem_huge __read_mostly; +static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER; -bool shmem_huge_enabled(struct vm_area_struct *vma) +bool shmem_is_huge(struct vm_area_struct *vma, + struct inode *inode, pgoff_t index) { - struct inode *inode = file_inode(vma->vm_file); - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); loff_t i_size; - pgoff_t off; - if ((vma->vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - return false; - if (shmem_huge == SHMEM_HUGE_FORCE) - return true; if (shmem_huge == SHMEM_HUGE_DENY) return false; - switch (sbinfo->huge) { - case SHMEM_HUGE_NEVER: + if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))) return false; + if (shmem_huge == SHMEM_HUGE_FORCE) + return true; + + switch (SHMEM_SB(inode->i_sb)->huge) { case SHMEM_HUGE_ALWAYS: return true; case SHMEM_HUGE_WITHIN_SIZE: - off = round_up(vma->vm_pgoff, HPAGE_PMD_NR); + index = round_up(index, HPAGE_PMD_NR); i_size = round_up(i_size_read(inode), PAGE_SIZE); - if (i_size >= HPAGE_PMD_SIZE && - i_size >> PAGE_SHIFT >= off) + if (i_size >= HPAGE_PMD_SIZE && (i_size >> PAGE_SHIFT) >= index) return true; fallthrough; case SHMEM_HUGE_ADVISE: - /* TODO: implement fadvise() hints */ - return (vma->vm_flags & VM_HUGEPAGE); + if (vma && (vma->vm_flags & VM_HUGEPAGE)) + return true; + fallthrough; default: - VM_BUG_ON(1); return false; } } @@ -677,6 +673,12 @@ static long shmem_unused_huge_count(struct super_block *sb, #define shmem_huge SHMEM_HUGE_DENY +bool shmem_is_huge(struct vm_area_struct *vma, + struct inode *inode, pgoff_t index) +{ + return false; +} + static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { @@ -1812,7 +1814,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct shmem_sb_info *sbinfo; struct mm_struct *charge_mm; struct page *page; - enum sgp_type sgp_huge = sgp; pgoff_t hindex = index; gfp_t huge_gfp; int error; @@ -1821,8 +1822,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; - if (sgp == SGP_NOHUGE || sgp == SGP_HUGE) - sgp = SGP_CACHE; repeat: if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { @@ -1886,36 +1885,12 @@ repeat: return 0; } - /* shmem_symlink() */ - if (!shmem_mapping(mapping)) - goto alloc_nohuge; - if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE) + /* Never use a huge page for shmem_symlink() */ + if (S_ISLNK(inode->i_mode)) goto alloc_nohuge; - if (shmem_huge == SHMEM_HUGE_FORCE) - goto alloc_huge; - switch (sbinfo->huge) { - case SHMEM_HUGE_NEVER: + if (!shmem_is_huge(vma, inode, index)) goto alloc_nohuge; - case SHMEM_HUGE_WITHIN_SIZE: { - loff_t i_size; - pgoff_t off; - - off = round_up(index, HPAGE_PMD_NR); - i_size = round_up(i_size_read(inode), PAGE_SIZE); - if (i_size >= HPAGE_PMD_SIZE && - i_size >> PAGE_SHIFT >= off) - goto alloc_huge; - fallthrough; - } - case SHMEM_HUGE_ADVISE: - if (sgp_huge == SGP_HUGE) - goto alloc_huge; - /* TODO: implement fadvise() hints */ - goto alloc_nohuge; - } - -alloc_huge: huge_gfp = vma_thp_gfp_mask(vma); huge_gfp = limit_gfp_mask(huge_gfp, gfp); page = shmem_alloc_and_acct_page(huge_gfp, inode, index, true); @@ -2071,7 +2046,6 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct inode *inode = file_inode(vma->vm_file); gfp_t gfp = mapping_gfp_mask(inode->i_mapping); - enum sgp_type sgp; int err; vm_fault_t ret = VM_FAULT_LOCKED; @@ -2134,15 +2108,7 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf) spin_unlock(&inode->i_lock); } - sgp = SGP_CACHE; - - if ((vma->vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - sgp = SGP_NOHUGE; - else if (vma->vm_flags & VM_HUGEPAGE) - sgp = SGP_HUGE; - - err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp, + err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, SGP_CACHE, gfp, vma, vmf, &ret); if (err) return vmf_error(err); @@ -3950,7 +3916,7 @@ int __init shmem_init(void) if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; else - shmem_huge = 0; /* just in case it was patched */ + shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */ #endif return 0; -- cgit v1.2.3 From 2c8d8f97ae2272f1455ee31a5af62b326772eb31 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 2 Sep 2021 14:54:50 -0700 Subject: mm, memcg: inline mem_cgroup_{charge/uncharge} to improve disabled memcg config Inline mem_cgroup_{charge/uncharge} and mem_cgroup_uncharge_list functions functions to perform mem_cgroup_disabled static key check inline before calling the main body of the function. This minimizes the memcg overhead in the pagefault and exit_mmap paths when memcgs are disabled using cgroup_disable=memory command-line option. This change results in ~0.4% overhead reduction when running PFT test [1] comparing {CONFIG_MEMCG=n} against {CONFIG_MEMCG=y, cgroup_disable=memory} configuration on an 8-core ARM64 Android device. [1] https://lkml.org/lkml/2006/8/29/294 also used in mmtests suite Link: https://lkml.kernel.org/r/20210713010934.299876-2-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Shakeel Butt Reviewed-by: Muchun Song Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Alex Shi Cc: Alistair Popple Cc: David Hildenbrand Cc: Jens Axboe Cc: Joonsoo Kim Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Minchan Kim Cc: Roman Gushchin Cc: Tejun Heo Cc: Wei Yang Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 28 +++++++++++++++++++++++++--- mm/memcontrol.c | 33 ++++++++++++--------------------- 2 files changed, 37 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3403ec77528a..a00bf337567b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -693,13 +693,35 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) page_counter_read(&memcg->memory); } -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); +int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask); +static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask) +{ + if (mem_cgroup_disabled()) + return 0; + return __mem_cgroup_charge(page, mm, gfp_mask); +} + int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); -void mem_cgroup_uncharge(struct page *page); -void mem_cgroup_uncharge_list(struct list_head *page_list); +void __mem_cgroup_uncharge(struct page *page); +static inline void mem_cgroup_uncharge(struct page *page) +{ + if (mem_cgroup_disabled()) + return; + __mem_cgroup_uncharge(page); +} + +void __mem_cgroup_uncharge_list(struct list_head *page_list); +static inline void mem_cgroup_uncharge_list(struct list_head *page_list) +{ + if (mem_cgroup_disabled()) + return; + __mem_cgroup_uncharge_list(page_list); +} void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 211f3911228f..33bb8434eea0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6693,8 +6693,7 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root, atomic_long_read(&parent->memory.children_low_usage))); } -static int __mem_cgroup_charge(struct page *page, struct mem_cgroup *memcg, - gfp_t gfp) +static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) { unsigned int nr_pages = thp_nr_pages(page); int ret; @@ -6715,7 +6714,7 @@ out: } /** - * mem_cgroup_charge - charge a newly allocated page to a cgroup + * __mem_cgroup_charge - charge a newly allocated page to a cgroup * @page: page to charge * @mm: mm context of the victim * @gfp_mask: reclaim mode @@ -6728,16 +6727,14 @@ out: * * Returns 0 on success. Otherwise, an error code is returned. */ -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) +int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask) { struct mem_cgroup *memcg; int ret; - if (mem_cgroup_disabled()) - return 0; - memcg = get_mem_cgroup_from_mm(mm); - ret = __mem_cgroup_charge(page, memcg, gfp_mask); + ret = charge_memcg(page, memcg, gfp_mask); css_put(&memcg->css); return ret; @@ -6772,7 +6769,7 @@ int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, memcg = get_mem_cgroup_from_mm(mm); rcu_read_unlock(); - ret = __mem_cgroup_charge(page, memcg, gfp); + ret = charge_memcg(page, memcg, gfp); css_put(&memcg->css); return ret; @@ -6908,18 +6905,15 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) } /** - * mem_cgroup_uncharge - uncharge a page + * __mem_cgroup_uncharge - uncharge a page * @page: page to uncharge * - * Uncharge a page previously charged with mem_cgroup_charge(). + * Uncharge a page previously charged with __mem_cgroup_charge(). */ -void mem_cgroup_uncharge(struct page *page) +void __mem_cgroup_uncharge(struct page *page) { struct uncharge_gather ug; - if (mem_cgroup_disabled()) - return; - /* Don't touch page->lru of any random page, pre-check: */ if (!page_memcg(page)) return; @@ -6930,20 +6924,17 @@ void mem_cgroup_uncharge(struct page *page) } /** - * mem_cgroup_uncharge_list - uncharge a list of page + * __mem_cgroup_uncharge_list - uncharge a list of page * @page_list: list of pages to uncharge * * Uncharge a list of pages previously charged with - * mem_cgroup_charge(). + * __mem_cgroup_charge(). */ -void mem_cgroup_uncharge_list(struct list_head *page_list) +void __mem_cgroup_uncharge_list(struct list_head *page_list) { struct uncharge_gather ug; struct page *page; - if (mem_cgroup_disabled()) - return; - uncharge_gather_clear(&ug); list_for_each_entry(page, page_list, lru) uncharge_page(page, &ug); -- cgit v1.2.3 From 01c4b28cd2e600160566a7d83b4703800381dae1 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 2 Sep 2021 14:54:54 -0700 Subject: mm, memcg: inline swap-related functions to improve disabled memcg config Inline mem_cgroup_try_charge_swap, mem_cgroup_uncharge_swap and cgroup_throttle_swaprate functions to perform mem_cgroup_disabled static key check inline before calling the main body of the function. This minimizes the memcg overhead in the pagefault and exit_mmap paths when memcgs are disabled using cgroup_disable=memory command-line option. This change results in ~1% overhead reduction when running PFT test [1] comparing {CONFIG_MEMCG=n} against {CONFIG_MEMCG=y, cgroup_disable=memory} configuration on an 8-core ARM64 Android device. [1] https://lkml.org/lkml/2006/8/29/294 also used in mmtests suite Link: https://lkml.kernel.org/r/20210713010934.299876-3-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Shakeel Butt Reviewed-by: Muchun Song Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Tejun Heo Cc: Roman Gushchin Cc: Yang Shi Cc: Alex Shi Cc: Wei Yang Cc: Jens Axboe Cc: Joonsoo Kim Cc: David Hildenbrand Cc: Matthew Wilcox (Oracle) Cc: Alistair Popple Cc: Minchan Kim Cc: Miaohe Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 26 +++++++++++++++++++++++--- mm/memcontrol.c | 14 ++++---------- mm/swapfile.c | 5 +---- 3 files changed, 28 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6f5a43251593..f30d26b0f71d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -721,7 +721,13 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -extern void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); +extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); +static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) +{ + if (mem_cgroup_disabled()) + return; + __cgroup_throttle_swaprate(page, gfp_mask); +} #else static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { @@ -730,8 +736,22 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) #ifdef CONFIG_MEMCG_SWAP extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); -extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); -extern void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); +extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); +static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) +{ + if (mem_cgroup_disabled()) + return 0; + return __mem_cgroup_try_charge_swap(page, entry); +} + +extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); +static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) +{ + if (mem_cgroup_disabled()) + return; + __mem_cgroup_uncharge_swap(entry, nr_pages); +} + extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct page *page); #else diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 33bb8434eea0..81e15a67391b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -7226,7 +7226,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) } /** - * mem_cgroup_try_charge_swap - try charging swap space for a page + * __mem_cgroup_try_charge_swap - try charging swap space for a page * @page: page being added to swap * @entry: swap entry to charge * @@ -7234,16 +7234,13 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * * Returns 0 on success, -ENOMEM on failure. */ -int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) +int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) { unsigned int nr_pages = thp_nr_pages(page); struct page_counter *counter; struct mem_cgroup *memcg; unsigned short oldid; - if (mem_cgroup_disabled()) - return 0; - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return 0; @@ -7279,18 +7276,15 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) } /** - * mem_cgroup_uncharge_swap - uncharge swap space + * __mem_cgroup_uncharge_swap - uncharge swap space * @entry: swap entry to uncharge * @nr_pages: the amount of swap space to uncharge */ -void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) +void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { struct mem_cgroup *memcg; unsigned short id; - if (mem_cgroup_disabled()) - return; - id = swap_cgroup_record(entry, 0, nr_pages); rcu_read_lock(); memcg = mem_cgroup_from_id(id); diff --git a/mm/swapfile.c b/mm/swapfile.c index 627b16aed1dc..22d10f713848 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3779,14 +3779,11 @@ static void free_swap_count_continuations(struct swap_info_struct *si) } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) +void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { struct swap_info_struct *si, *next; int nid = page_to_nid(page); - if (mem_cgroup_disabled()) - return; - if (!(gfp_mask & __GFP_IO)) return; -- cgit v1.2.3 From 7e1c0d6f58207e7e60674647d3935f446f05613c Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 2 Sep 2021 14:55:00 -0700 Subject: memcg: switch lruvec stats to rstat MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The commit 2d146aa3aa84 ("mm: memcontrol: switch to rstat") switched memcg stats to rstat infrastructure but skipped the conversion of the lruvec stats as such stats are read in the performance critical code paths and flushing stats may have impacted the performances of the applications. This patch converts the lruvec stats to rstat and later patches add mechanisms to keep the performance impact to minimum. The rstat conversion comes with the price i.e. memory cost. Effectively this patch reverts the savings done by the commit f3344adf38bd ("mm: memcontrol: optimize per-lruvec stats counter memory usage"). However this cost is justified due to negative impact of the inaccurate lruvec stats on many heuristics. One such case is reported in [1]. The memory reclaim code is filled with plethora of heuristics and many of those heuristics reads the lruvec stats. So, inaccurate stats can make such heuristics ineffective. [1] reports the impact of inaccurate lruvec stats on the "cache trim mode" heuristic. Inaccurate lruvec stats can impact the deactivation and aging anon heuristics as well. [1] https://lore.kernel.org/linux-mm/20210311004449.1170308-1-ying.huang@intel.com/ Link: https://lkml.kernel.org/r/20210716212137.1391164-1-shakeelb@google.com Link: https://lkml.kernel.org/r/20210714013948.270662-1-shakeelb@google.com Signed-off-by: Shakeel Butt Cc: Tejun Heo Cc: Johannes Weiner Cc: Muchun Song Cc: Michal Hocko Cc: Roman Gushchin Cc: Huang Ying Cc: Hillf Danton Cc: Michal Koutný Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 42 ++++++++--------- mm/memcontrol.c | 114 +++++++++++++++------------------------------ 2 files changed, 58 insertions(+), 98 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a00bf337567b..47d35bef9f6e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -105,14 +105,6 @@ struct mem_cgroup_reclaim_iter { unsigned int generation; }; -struct lruvec_stat { - long count[NR_VM_NODE_STAT_ITEMS]; -}; - -struct batched_lruvec_stat { - s32 count[NR_VM_NODE_STAT_ITEMS]; -}; - /* * Bitmap and deferred work of shrinker::id corresponding to memcg-aware * shrinkers, which have elements charged to this memcg. @@ -123,24 +115,30 @@ struct shrinker_info { unsigned long *map; }; +struct lruvec_stats_percpu { + /* Local (CPU and cgroup) state */ + long state[NR_VM_NODE_STAT_ITEMS]; + + /* Delta calculation for lockless upward propagation */ + long state_prev[NR_VM_NODE_STAT_ITEMS]; +}; + +struct lruvec_stats { + /* Aggregated (CPU and subtree) state */ + long state[NR_VM_NODE_STAT_ITEMS]; + + /* Pending child counts during tree propagation */ + long state_pending[NR_VM_NODE_STAT_ITEMS]; +}; + /* * per-node information in memory controller. */ struct mem_cgroup_per_node { struct lruvec lruvec; - /* - * Legacy local VM stats. This should be struct lruvec_stat and - * cannot be optimized to struct batched_lruvec_stat. Because - * the threshold of the lruvec_stat_cpu can be as big as - * MEMCG_CHARGE_BATCH * PAGE_SIZE. It can fit into s32. But this - * filed has no upper limit. - */ - struct lruvec_stat __percpu *lruvec_stat_local; - - /* Subtree VM stats (batched updates) */ - struct batched_lruvec_stat __percpu *lruvec_stat_cpu; - atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS]; + struct lruvec_stats_percpu __percpu *lruvec_stats_percpu; + struct lruvec_stats lruvec_stats; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; @@ -997,7 +995,7 @@ static inline unsigned long lruvec_page_state(struct lruvec *lruvec, return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - x = atomic_long_read(&pn->lruvec_stat[idx]); + x = READ_ONCE(pn->lruvec_stats.state[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; @@ -1017,7 +1015,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); for_each_possible_cpu(cpu) - x += per_cpu(pn->lruvec_stat_local->count[idx], cpu); + x += per_cpu(pn->lruvec_stats_percpu->state[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 81e15a67391b..400d210e030a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -660,23 +660,11 @@ static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) return x; } -static struct mem_cgroup_per_node * -parent_nodeinfo(struct mem_cgroup_per_node *pn, int nid) -{ - struct mem_cgroup *parent; - - parent = parent_mem_cgroup(pn->memcg); - if (!parent) - return NULL; - return parent->nodeinfo[nid]; -} - void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { struct mem_cgroup_per_node *pn; struct mem_cgroup *memcg; - long x, threshold = MEMCG_CHARGE_BATCH; pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); memcg = pn->memcg; @@ -685,21 +673,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, __mod_memcg_state(memcg, idx, val); /* Update lruvec */ - __this_cpu_add(pn->lruvec_stat_local->count[idx], val); - - if (vmstat_item_in_bytes(idx)) - threshold <<= PAGE_SHIFT; - - x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]); - if (unlikely(abs(x) > threshold)) { - pg_data_t *pgdat = lruvec_pgdat(lruvec); - struct mem_cgroup_per_node *pi; - - for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id)) - atomic_long_add(x, &pi->lruvec_stat[idx]); - x = 0; - } - __this_cpu_write(pn->lruvec_stat_cpu->count[idx], x); + __this_cpu_add(pn->lruvec_stats_percpu->state[idx], val); } /** @@ -2278,40 +2252,13 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) mutex_unlock(&percpu_charge_mutex); } -static void memcg_flush_lruvec_page_state(struct mem_cgroup *memcg, int cpu) -{ - int nid; - - for_each_node(nid) { - struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid]; - unsigned long stat[NR_VM_NODE_STAT_ITEMS]; - struct batched_lruvec_stat *lstatc; - int i; - - lstatc = per_cpu_ptr(pn->lruvec_stat_cpu, cpu); - for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { - stat[i] = lstatc->count[i]; - lstatc->count[i] = 0; - } - - do { - for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) - atomic_long_add(stat[i], &pn->lruvec_stat[i]); - } while ((pn = parent_nodeinfo(pn, nid))); - } -} - static int memcg_hotplug_cpu_dead(unsigned int cpu) { struct memcg_stock_pcp *stock; - struct mem_cgroup *memcg; stock = &per_cpu(memcg_stock, cpu); drain_stock(stock); - for_each_mem_cgroup(memcg) - memcg_flush_lruvec_page_state(memcg, cpu); - return 0; } @@ -5118,17 +5065,9 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) if (!pn) return 1; - pn->lruvec_stat_local = alloc_percpu_gfp(struct lruvec_stat, - GFP_KERNEL_ACCOUNT); - if (!pn->lruvec_stat_local) { - kfree(pn); - return 1; - } - - pn->lruvec_stat_cpu = alloc_percpu_gfp(struct batched_lruvec_stat, - GFP_KERNEL_ACCOUNT); - if (!pn->lruvec_stat_cpu) { - free_percpu(pn->lruvec_stat_local); + pn->lruvec_stats_percpu = alloc_percpu_gfp(struct lruvec_stats_percpu, + GFP_KERNEL_ACCOUNT); + if (!pn->lruvec_stats_percpu) { kfree(pn); return 1; } @@ -5149,8 +5088,7 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) if (!pn) return; - free_percpu(pn->lruvec_stat_cpu); - free_percpu(pn->lruvec_stat_local); + free_percpu(pn->lruvec_stats_percpu); kfree(pn); } @@ -5166,15 +5104,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) static void mem_cgroup_free(struct mem_cgroup *memcg) { - int cpu; - memcg_wb_domain_exit(memcg); - /* - * Flush percpu lruvec stats to guarantee the value - * correctness on parent's and all ancestor levels. - */ - for_each_online_cpu(cpu) - memcg_flush_lruvec_page_state(memcg, cpu); __mem_cgroup_free(memcg); } @@ -5407,7 +5337,7 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) struct mem_cgroup *parent = parent_mem_cgroup(memcg); struct memcg_vmstats_percpu *statc; long delta, v; - int i; + int i, nid; statc = per_cpu_ptr(memcg->vmstats_percpu, cpu); @@ -5455,6 +5385,36 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) if (parent) parent->vmstats.events_pending[i] += delta; } + + for_each_node_state(nid, N_MEMORY) { + struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid]; + struct mem_cgroup_per_node *ppn = NULL; + struct lruvec_stats_percpu *lstatc; + + if (parent) + ppn = parent->nodeinfo[nid]; + + lstatc = per_cpu_ptr(pn->lruvec_stats_percpu, cpu); + + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { + delta = pn->lruvec_stats.state_pending[i]; + if (delta) + pn->lruvec_stats.state_pending[i] = 0; + + v = READ_ONCE(lstatc->state[i]); + if (v != lstatc->state_prev[i]) { + delta += v - lstatc->state_prev[i]; + lstatc->state_prev[i] = v; + } + + if (!delta) + continue; + + pn->lruvec_stats.state[i] += delta; + if (ppn) + ppn->lruvec_stats.state_pending[i] += delta; + } + } } #ifdef CONFIG_MMU @@ -6388,6 +6348,8 @@ static int memory_numa_stat_show(struct seq_file *m, void *v) int i; struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + cgroup_rstat_flush(memcg->css.cgroup); + for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { int nid; -- cgit v1.2.3 From aa48e47e3906c332eaf1e5d7b58be11d3509ad9f Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 2 Sep 2021 14:55:04 -0700 Subject: memcg: infrastructure to flush memcg stats MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit At the moment memcg stats are read in four contexts: 1. memcg stat user interfaces 2. dirty throttling 3. page fault 4. memory reclaim Currently the kernel flushes the stats for first two cases. Flushing the stats for remaining two casese may have performance impact. Always flushing the memcg stats on the page fault code path may negatively impacts the performance of the applications. In addition flushing in the memory reclaim code path, though treated as slowpath, can become the source of contention for the global lock taken for stat flushing because when system or memcg is under memory pressure, many tasks may enter the reclaim path. This patch uses following mechanisms to solve these challenges: 1. Periodically flush the stats from root memcg every 2 seconds. This will time limit the out of sync stats. 2. Asynchronously flush the stats after fixed number of stat updates. In the worst case the stat can be out of sync by O(nr_cpus * BATCH) for 2 seconds. 3. For avoiding thundering herd to flush the stats particularly from the memory reclaim context, introduce memcg local spinlock and let only one flusher active at a time. This could have been done through cgroup_rstat_lock lock but that lock is used by other subsystem and for userspace reading memcg stats. So, it is better to keep flushers introduced by this patch decoupled from cgroup_rstat_lock. However we would have to use irqsafe version of rstat flush but that is fine as this code path will be flushing for whole tree and do the work for everyone. No one will be waiting for that worker. [shakeelb@google.com: fix sleep-in-wrong context bug] Link: https://lkml.kernel.org/r/20210716212137.1391164-2-shakeelb@google.com Link: https://lkml.kernel.org/r/20210714013948.270662-2-shakeelb@google.com Signed-off-by: Shakeel Butt Tested-by: Marek Szyprowski Cc: Hillf Danton Cc: Huang Ying Cc: Johannes Weiner Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++++++ mm/memcontrol.c | 34 ++++++++++++++++++++++++++++++++++ mm/vmscan.c | 6 ++++++ 3 files changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 47d35bef9f6e..c4c5b652d3af 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1023,6 +1023,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, return x; } +void mem_cgroup_flush_stats(void); + void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); @@ -1438,6 +1440,10 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, return node_page_state(lruvec_pgdat(lruvec), idx); } +static inline void mem_cgroup_flush_stats(void) +{ +} + static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 400d210e030a..4d8c9afecf98 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -103,6 +103,14 @@ static bool do_memsw_account(void) return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_noswap; } +/* memcg and lruvec stats flushing */ +static void flush_memcg_stats_dwork(struct work_struct *w); +static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); +static void flush_memcg_stats_work(struct work_struct *w); +static DECLARE_WORK(stats_flush_work, flush_memcg_stats_work); +static DEFINE_PER_CPU(unsigned int, stats_flush_threshold); +static DEFINE_SPINLOCK(stats_flush_lock); + #define THRESHOLDS_EVENTS_TARGET 128 #define SOFTLIMIT_EVENTS_TARGET 1024 @@ -674,6 +682,8 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, /* Update lruvec */ __this_cpu_add(pn->lruvec_stats_percpu->state[idx], val); + if (!(__this_cpu_inc_return(stats_flush_threshold) % MEMCG_CHARGE_BATCH)) + queue_work(system_unbound_wq, &stats_flush_work); } /** @@ -5240,6 +5250,10 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) /* Online state pins memcg ID, memcg ID pins CSS */ refcount_set(&memcg->id.ref, 1); css_get(css); + + if (unlikely(mem_cgroup_is_root(memcg))) + queue_delayed_work(system_unbound_wq, &stats_flush_dwork, + 2UL*HZ); return 0; } @@ -5331,6 +5345,26 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) memcg_wb_domain_size_changed(memcg); } +void mem_cgroup_flush_stats(void) +{ + if (!spin_trylock(&stats_flush_lock)) + return; + + cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup); + spin_unlock(&stats_flush_lock); +} + +static void flush_memcg_stats_dwork(struct work_struct *w) +{ + mem_cgroup_flush_stats(); + queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ); +} + +static void flush_memcg_stats_work(struct work_struct *w) +{ + mem_cgroup_flush_stats(); +} + static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); diff --git a/mm/vmscan.c b/mm/vmscan.c index 268ad6570751..6c401b44a245 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2897,6 +2897,12 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: + /* + * Flush the memory cgroup stats, so that we read accurate per-memcg + * lruvec stats for heuristics. + */ + mem_cgroup_flush_stats(); + memset(&sc->nr, 0, sizeof(sc->nr)); nr_reclaimed = sc->nr_reclaimed; -- cgit v1.2.3 From 96e51ccf1af33e82f429a0d6baebba29c6448d0f Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 2 Sep 2021 14:55:46 -0700 Subject: memcg: cleanup racy sum avoidance code We used to have per-cpu memcg and lruvec stats and the readers have to traverse and sum the stats from each cpu. This summing was racy and may expose transient negative values. So, an explicit check was added to avoid such scenarios. Now these stats are moved to rstat infrastructure and are no more per-cpu, so we can remove the fixup for transient negative values. Link: https://lkml.kernel.org/r/20210728012243.3369123-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Roman Gushchin Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c4c5b652d3af..2ee20509ac71 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -977,30 +977,19 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { - long x = READ_ONCE(memcg->vmstats.state[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; + return READ_ONCE(memcg->vmstats.state[idx]); } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; - long x; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - x = READ_ONCE(pn->lruvec_stats.state[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; + return READ_ONCE(pn->lruvec_stats.state[idx]); } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, -- cgit v1.2.3 From 55a68c823951855f3ec313fdb85100db84284505 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 2 Sep 2021 14:55:49 -0700 Subject: memcg: replace in_interrupt() by !in_task() in active_memcg() set_active_memcg() uses in_interrupt() check to select proper storage for cgroup: pointer on task struct or per-cpu pointer. It isn't fully correct: obsoleted in_interrupt() includes tasks with disabled BH. It's better to use '!in_task()' instead. Link: https://lkml.org/lkml/2021/7/26/487 Link: https://lkml.kernel.org/r/ed4448b0-4970-616f-7368-ef9dd3cb628d@virtuozzo.com Fixes: 37d5985c003d ("mm: kmem: prepare remote memcg charging infra for interrupt contexts") Signed-off-by: Vasily Averin Reviewed-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Cc: Roman Gushchin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 2 +- mm/memcontrol.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 8894825cc4db..5561486fddef 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -306,7 +306,7 @@ set_active_memcg(struct mem_cgroup *memcg) { struct mem_cgroup *old; - if (in_interrupt()) { + if (!in_task()) { old = this_cpu_read(int_active_memcg); this_cpu_write(int_active_memcg, memcg); } else { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4d8c9afecf98..b09f2639f28b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -878,7 +878,7 @@ EXPORT_SYMBOL(mem_cgroup_from_task); static __always_inline struct mem_cgroup *active_memcg(void) { - if (in_interrupt()) + if (!in_task()) return this_cpu_read(int_active_memcg); else return current->active_memcg; -- cgit v1.2.3 From bec49c067c679e9b7ca7c1aac50b56618c12d879 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 2 Sep 2021 14:55:56 -0700 Subject: mm, memcg: remove unused functions Since commit 2d146aa3aa84 ("mm: memcontrol: switch to rstat"), last user of memcg_stat_item_in_bytes() is gone. And since commit fa40d1ee9f15 ("mm: vmscan: memcontrol: remove mem_cgroup_select_victim_node()"), only the declaration of mem_cgroup_select_victim_node() is remained here. Remove them. Link: https://lkml.kernel.org/r/20210807082835.61281-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Shakeel Butt Reviewed-by: Muchun Song Acked-by: Roman Gushchin Acked-by: Michal Hocko Cc: Alex Shi Cc: Matthew Wilcox (Oracle) Cc: Vladimir Davydov Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2ee20509ac71..69e6c5462c43 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -593,13 +593,6 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) } #endif -static __always_inline bool memcg_stat_item_in_bytes(int idx) -{ - if (idx == MEMCG_PERCPU_B) - return true; - return vmstat_item_in_bytes(idx); -} - static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); @@ -904,11 +897,6 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg) return !!(memcg->css.flags & CSS_ONLINE); } -/* - * For memory reclaim. - */ -int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); - void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages); -- cgit v1.2.3 From f358afc52c3066f4e8cd7b3a2d75b31e822519e9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 2 Sep 2021 14:56:36 -0700 Subject: mm: remove flush_kernel_dcache_page flush_kernel_dcache_page is a rather confusing interface that implements a subset of flush_dcache_page by not being able to properly handle page cache mapped pages. The only callers left are in the exec code as all other previous callers were incorrect as they could have dealt with page cache pages. Replace the calls to flush_kernel_dcache_page with calls to flush_dcache_page, which for all architectures does either exactly the same thing, can contains one or more of the following: 1) an optimization to defer the cache flush for page cache pages not mapped into userspace 2) additional flushing for mapped page cache pages if cache aliases are possible Link: https://lkml.kernel.org/r/20210712060928.4161649-7-hch@lst.de Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds Reviewed-by: Ira Weiny Cc: Alex Shi Cc: Geoff Levand Cc: Greentime Hu Cc: Guo Ren Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Nick Hu Cc: Paul Cercueil Cc: Rich Felker Cc: Russell King Cc: Thomas Bogendoerfer Cc: Ulf Hansson Cc: Vincent Chen Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/core-api/cachetlb.rst | 86 ++++++++++------------ .../translations/zh_CN/core-api/cachetlb.rst | 9 --- arch/arm/include/asm/cacheflush.h | 4 +- arch/arm/mm/flush.c | 33 --------- arch/arm/mm/nommu.c | 6 -- arch/csky/abiv1/cacheflush.c | 11 --- arch/csky/abiv1/inc/abi/cacheflush.h | 4 +- arch/mips/include/asm/cacheflush.h | 8 +- arch/nds32/include/asm/cacheflush.h | 3 +- arch/nds32/mm/cacheflush.c | 9 --- arch/parisc/include/asm/cacheflush.h | 8 +- arch/parisc/kernel/cache.c | 3 +- arch/sh/include/asm/cacheflush.h | 8 +- block/blk-map.c | 2 +- fs/exec.c | 6 +- include/linux/highmem.h | 5 +- tools/testing/scatterlist/linux/mm.h | 1 - 17 files changed, 51 insertions(+), 155 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/cachetlb.rst b/Documentation/core-api/cachetlb.rst index fe4290e26729..8aed9103e48a 100644 --- a/Documentation/core-api/cachetlb.rst +++ b/Documentation/core-api/cachetlb.rst @@ -271,10 +271,15 @@ maps this page at its virtual address. ``void flush_dcache_page(struct page *page)`` - Any time the kernel writes to a page cache page, _OR_ - the kernel is about to read from a page cache page and - user space shared/writable mappings of this page potentially - exist, this routine is called. + This routines must be called when: + + a) the kernel did write to a page that is in the page cache page + and / or in high memory + b) the kernel is about to read from a page cache page and user space + shared/writable mappings of this page potentially exist. Note + that {get,pin}_user_pages{_fast} already call flush_dcache_page + on any page found in the user address space and thus driver + code rarely needs to take this into account. .. note:: @@ -284,38 +289,34 @@ maps this page at its virtual address. handling vfs symlinks in the page cache need not call this interface at all. - The phrase "kernel writes to a page cache page" means, - specifically, that the kernel executes store instructions - that dirty data in that page at the page->virtual mapping - of that page. It is important to flush here to handle - D-cache aliasing, to make sure these kernel stores are - visible to user space mappings of that page. - - The corollary case is just as important, if there are users - which have shared+writable mappings of this file, we must make - sure that kernel reads of these pages will see the most recent - stores done by the user. - - If D-cache aliasing is not an issue, this routine may - simply be defined as a nop on that architecture. - - There is a bit set aside in page->flags (PG_arch_1) as - "architecture private". The kernel guarantees that, - for pagecache pages, it will clear this bit when such - a page first enters the pagecache. - - This allows these interfaces to be implemented much more - efficiently. It allows one to "defer" (perhaps indefinitely) - the actual flush if there are currently no user processes - mapping this page. See sparc64's flush_dcache_page and - update_mmu_cache implementations for an example of how to go - about doing this. - - The idea is, first at flush_dcache_page() time, if - page->mapping->i_mmap is an empty tree, just mark the architecture - private page flag bit. Later, in update_mmu_cache(), a check is - made of this flag bit, and if set the flush is done and the flag - bit is cleared. + The phrase "kernel writes to a page cache page" means, specifically, + that the kernel executes store instructions that dirty data in that + page at the page->virtual mapping of that page. It is important to + flush here to handle D-cache aliasing, to make sure these kernel stores + are visible to user space mappings of that page. + + The corollary case is just as important, if there are users which have + shared+writable mappings of this file, we must make sure that kernel + reads of these pages will see the most recent stores done by the user. + + If D-cache aliasing is not an issue, this routine may simply be defined + as a nop on that architecture. + + There is a bit set aside in page->flags (PG_arch_1) as "architecture + private". The kernel guarantees that, for pagecache pages, it will + clear this bit when such a page first enters the pagecache. + + This allows these interfaces to be implemented much more efficiently. + It allows one to "defer" (perhaps indefinitely) the actual flush if + there are currently no user processes mapping this page. See sparc64's + flush_dcache_page and update_mmu_cache implementations for an example + of how to go about doing this. + + The idea is, first at flush_dcache_page() time, if page_file_mapping() + returns a mapping, and mapping_mapped on that mapping returns %false, + just mark the architecture private page flag bit. Later, in + update_mmu_cache(), a check is made of this flag bit, and if set the + flush is done and the flag bit is cleared. .. important:: @@ -351,19 +352,6 @@ maps this page at its virtual address. architectures). For incoherent architectures, it should flush the cache of the page at vmaddr. - ``void flush_kernel_dcache_page(struct page *page)`` - - When the kernel needs to modify a user page is has obtained - with kmap, it calls this function after all modifications are - complete (but before kunmapping it) to bring the underlying - page up to date. It is assumed here that the user has no - incoherent cached copies (i.e. the original page was obtained - from a mechanism like get_user_pages()). The default - implementation is a nop and should remain so on all coherent - architectures. On incoherent architectures, this should flush - the kernel cache for page (using page_address(page)). - - ``void flush_icache_range(unsigned long start, unsigned long end)`` When the kernel stores into addresses that it will execute diff --git a/Documentation/translations/zh_CN/core-api/cachetlb.rst b/Documentation/translations/zh_CN/core-api/cachetlb.rst index 8376485a534d..55827b8a7c53 100644 --- a/Documentation/translations/zh_CN/core-api/cachetlb.rst +++ b/Documentation/translations/zh_CN/core-api/cachetlb.rst @@ -298,15 +298,6 @@ HyperSparc cpu就是这样一个具有这种属性的cpu。 用。默认的实现是nop（对于所有相干的架构应该保持这样）。对于不一致性 的架构，它应该刷新vmaddr处的页面缓存。 - ``void flush_kernel_dcache_page(struct page *page)`` - - 当内核需要修改一个用kmap获得的用户页时，它会在所有修改完成后（但在 - kunmapping之前）调用这个函数，以使底层页面达到最新状态。这里假定用 - 户没有不一致性的缓存副本（即原始页面是从类似get_user_pages()的机制 - 中获得的）。默认的实现是一个nop，在所有相干的架构上都应该如此。在不 - 一致性的架构上，这应该刷新内核缓存中的页面（使用page_address(page)）。 - - ``void flush_icache_range(unsigned long start, unsigned long end)`` 当内核存储到它将执行的地址中时（例如在加载模块时），这个函数被调用。 diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 2e24e765e6d3..5e56288e343b 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -291,6 +291,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) { if ((cache_is_vivt() || cache_is_vipt_aliasing())) @@ -312,9 +313,6 @@ static inline void flush_anon_page(struct vm_area_struct *vma, __flush_anon_page(vma, page, vmaddr); } -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -extern void flush_kernel_dcache_page(struct page *); - #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 6d89db7895d1..7ff9feea13a6 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -345,39 +345,6 @@ void flush_dcache_page(struct page *page) } EXPORT_SYMBOL(flush_dcache_page); -/* - * Ensure cache coherency for the kernel mapping of this page. We can - * assume that the page is pinned via kmap. - * - * If the page only exists in the page cache and there are no user - * space mappings, this is a no-op since the page was already marked - * dirty at creation. Otherwise, we need to flush the dirty kernel - * cache lines directly. - */ -void flush_kernel_dcache_page(struct page *page) -{ - if (cache_is_vivt() || cache_is_vipt_aliasing()) { - struct address_space *mapping; - - mapping = page_mapping_file(page); - - if (!mapping || mapping_mapped(mapping)) { - void *addr; - - addr = page_address(page); - /* - * kmap_atomic() doesn't set the page virtual - * address for highmem pages, and - * kunmap_atomic() takes care of cache - * flushing already. - */ - if (!IS_ENABLED(CONFIG_HIGHMEM) || addr) - __cpuc_flush_dcache_area(addr, PAGE_SIZE); - } - } -} -EXPORT_SYMBOL(flush_kernel_dcache_page); - /* * Flush an anonymous page so that users of get_user_pages() * can safely access the data. The expected sequence is: diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 8b3d7191e2b8..2658f52903da 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -166,12 +166,6 @@ void flush_dcache_page(struct page *page) } EXPORT_SYMBOL(flush_dcache_page); -void flush_kernel_dcache_page(struct page *page) -{ - __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE); -} -EXPORT_SYMBOL(flush_kernel_dcache_page); - void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) diff --git a/arch/csky/abiv1/cacheflush.c b/arch/csky/abiv1/cacheflush.c index 07ff17ea33de..fb91b069dc69 100644 --- a/arch/csky/abiv1/cacheflush.c +++ b/arch/csky/abiv1/cacheflush.c @@ -56,17 +56,6 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, } } -void flush_kernel_dcache_page(struct page *page) -{ - struct address_space *mapping; - - mapping = page_mapping_file(page); - - if (!mapping || mapping_mapped(mapping)) - dcache_wbinv_all(); -} -EXPORT_SYMBOL(flush_kernel_dcache_page); - void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h index 6cab7afae962..ed62e2066ba7 100644 --- a/arch/csky/abiv1/inc/abi/cacheflush.h +++ b/arch/csky/abiv1/inc/abi/cacheflush.h @@ -14,12 +14,10 @@ extern void flush_dcache_page(struct page *); #define flush_cache_page(vma, page, pfn) cache_wbinv_all() #define flush_cache_dup_mm(mm) cache_wbinv_all() -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -extern void flush_kernel_dcache_page(struct page *); - #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) { dcache_wbinv_all(); diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index d687b40b9fbb..b3dc9c589442 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -125,13 +125,7 @@ static inline void kunmap_noncoherent(void) kunmap_coherent(); } -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -static inline void flush_kernel_dcache_page(struct page *page) -{ - BUG_ON(cpu_has_dc_aliases && PageHighMem(page)); - flush_dcache_page(page); -} - +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 /* * For now flush_kernel_vmap_range and invalidate_kernel_vmap_range both do a * cache writeback and invalidate operation. diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index 7d6824f7c0e8..c2a222ebfa2a 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -36,8 +36,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page, void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr); -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -void flush_kernel_dcache_page(struct page *page); +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 void flush_kernel_vmap_range(void *addr, int size); void invalidate_kernel_vmap_range(void *addr, int size); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&(mapping)->i_pages) diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c index ad5344ef5d33..07aac65d1cab 100644 --- a/arch/nds32/mm/cacheflush.c +++ b/arch/nds32/mm/cacheflush.c @@ -318,15 +318,6 @@ void flush_anon_page(struct vm_area_struct *vma, local_irq_restore(flags); } -void flush_kernel_dcache_page(struct page *page) -{ - unsigned long flags; - local_irq_save(flags); - cpu_dcache_wbinval_page((unsigned long)page_address(page)); - local_irq_restore(flags); -} -EXPORT_SYMBOL(flush_kernel_dcache_page); - void flush_kernel_vmap_range(void *addr, int size) { unsigned long flags; diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 99663fc1f997..eef0096db5f8 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -36,16 +36,12 @@ void flush_cache_all_local(void); void flush_cache_all(void); void flush_cache_mm(struct mm_struct *mm); -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE void flush_kernel_dcache_page_addr(void *addr); -static inline void flush_kernel_dcache_page(struct page *page) -{ - flush_kernel_dcache_page_addr(page_address(page)); -} #define flush_kernel_dcache_range(start,size) \ flush_kernel_dcache_range_asm((start), (start)+(size)); +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 void flush_kernel_vmap_range(void *vaddr, int size); void invalidate_kernel_vmap_range(void *vaddr, int size); @@ -59,7 +55,7 @@ extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) #define flush_icache_page(vma,page) do { \ - flush_kernel_dcache_page(page); \ + flush_kernel_dcache_page_addr(page_address(page)); \ flush_kernel_icache_page(page_address(page)); \ } while (0) diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 86a1a63563fd..39e02227e231 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -334,7 +334,7 @@ void flush_dcache_page(struct page *page) return; } - flush_kernel_dcache_page(page); + flush_kernel_dcache_page_addr(page_address(page)); if (!mapping) return; @@ -375,7 +375,6 @@ EXPORT_SYMBOL(flush_dcache_page); /* Defined in arch/parisc/kernel/pacache.S */ EXPORT_SYMBOL(flush_kernel_dcache_range_asm); -EXPORT_SYMBOL(flush_kernel_dcache_page_asm); EXPORT_SYMBOL(flush_data_cache_local); EXPORT_SYMBOL(flush_kernel_icache_range_asm); diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index 4486a865ff62..372afa82fee6 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -63,6 +63,8 @@ static inline void flush_anon_page(struct vm_area_struct *vma, if (boot_cpu_data.dcache.n_aliases && PageAnon(page)) __flush_anon_page(page, vmaddr); } + +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) { __flush_wback_region(addr, size); @@ -72,12 +74,6 @@ static inline void invalidate_kernel_vmap_range(void *addr, int size) __flush_invalidate_region(addr, size); } -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -static inline void flush_kernel_dcache_page(struct page *page) -{ - flush_dcache_page(page); -} - extern void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, const void *src, unsigned long len); diff --git a/block/blk-map.c b/block/blk-map.c index 3743158ddaeb..4639bc6b5c62 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -309,7 +309,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, static void bio_invalidate_vmalloc_pages(struct bio *bio) { -#ifdef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE +#ifdef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE if (bio->bi_private && !op_is_write(bio_op(bio))) { unsigned long i, len = 0; diff --git a/fs/exec.c b/fs/exec.c index 38f63451b928..41a888d4edde 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -574,7 +574,7 @@ static int copy_strings(int argc, struct user_arg_ptr argv, } if (kmapped_page) { - flush_kernel_dcache_page(kmapped_page); + flush_dcache_page(kmapped_page); kunmap(kmapped_page); put_arg_page(kmapped_page); } @@ -592,7 +592,7 @@ static int copy_strings(int argc, struct user_arg_ptr argv, ret = 0; out: if (kmapped_page) { - flush_kernel_dcache_page(kmapped_page); + flush_dcache_page(kmapped_page); kunmap(kmapped_page); put_arg_page(kmapped_page); } @@ -634,7 +634,7 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm) kaddr = kmap_atomic(page); flush_arg_page(bprm, pos & PAGE_MASK, page); memcpy(kaddr + offset_in_page(pos), arg, bytes_to_copy); - flush_kernel_dcache_page(page); + flush_dcache_page(page); kunmap_atomic(kaddr); put_arg_page(page); } diff --git a/include/linux/highmem.h b/include/linux/highmem.h index d9a606a9fc64..b4c49f9cc379 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -130,10 +130,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page } #endif -#ifndef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -static inline void flush_kernel_dcache_page(struct page *page) -{ -} +#ifndef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE static inline void flush_kernel_vmap_range(void *vaddr, int size) { } diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h index f9a12005fcea..16ec895bbe5f 100644 --- a/tools/testing/scatterlist/linux/mm.h +++ b/tools/testing/scatterlist/linux/mm.h @@ -127,7 +127,6 @@ kmalloc_array(unsigned int n, unsigned int size, unsigned int flags) #define kmemleak_free(a) #define PageSlab(p) (0) -#define flush_kernel_dcache_page(p) #define MAX_ERRNO 4095 -- cgit v1.2.3 From e15710bf04063766f428048f4dad7b73b646203f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 2 Sep 2021 14:56:43 -0700 Subject: mm: change fault_in_pages_* to have an unsigned size parameter fault_in_pages_writeable() and fault_in_pages_readable() treat the size parameter as unsigned, doing pointer math with the value, so make this explicit and set it to be a size_t type which all callers currently treat it as anyway. This solves the issue where static checkers get nervous seeing pointer arithmetic happening with a signed value. Link: https://lkml.kernel.org/r/20210727111136.457638-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman Reported-by: Jordy Zomer Cc: Matthew Wilcox Cc: David Howells Cc: William Kucharski Cc: "Darrick J. Wong" Cc: Hugh Dickins Cc: Mauro Carvalho Chehab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ed02aa522263..5dcf446f42e5 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -736,7 +736,7 @@ extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter); /* * Fault everything in given userspace address range in. */ -static inline int fault_in_pages_writeable(char __user *uaddr, int size) +static inline int fault_in_pages_writeable(char __user *uaddr, size_t size) { char __user *end = uaddr + size - 1; @@ -763,7 +763,7 @@ static inline int fault_in_pages_writeable(char __user *uaddr, int size) return 0; } -static inline int fault_in_pages_readable(const char __user *uaddr, int size) +static inline int fault_in_pages_readable(const char __user *uaddr, size_t size) { volatile char c; const char __user *end = uaddr + size - 1; -- cgit v1.2.3 From fc1f5e980a463325cf41d39ac6a69aa3cca73995 Mon Sep 17 00:00:00 2001 From: Ohhoon Kwon Date: Thu, 2 Sep 2021 14:57:01 -0700 Subject: mm: sparse: pass section_nr to find_memory_block With CONFIG_SPARSEMEM_EXTREME enabled, __section_nr() which converts mem_section to section_nr could be costly since it iterates all section roots to check if the given mem_section is in its range. On the other hand, __nr_to_section() which converts section_nr to mem_section can be done in O(1). Let's pass section_nr instead of mem_section ptr to find_memory_block() in order to reduce needless iterations. Link: https://lkml.kernel.org/r/20210707150212.855-3-ohoono.kwon@samsung.com Signed-off-by: Ohhoon Kwon Acked-by: Michal Hocko Acked-by: Mike Rapoport Reviewed-by: David Hildenbrand Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/pseries/hotplug-memory.c | 4 +--- drivers/base/memory.c | 4 ++-- include/linux/memory.h | 2 +- 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 377d852f5a9a..d4f28ee4d5dc 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -211,13 +211,11 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb) static struct memory_block *lmb_to_memblock(struct drmem_lmb *lmb) { unsigned long section_nr; - struct mem_section *mem_sect; struct memory_block *mem_block; section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); - mem_sect = __nr_to_section(section_nr); - mem_block = find_memory_block(mem_sect); + mem_block = find_memory_block(section_nr); return mem_block; } diff --git a/drivers/base/memory.c b/drivers/base/memory.c index aa31a21f33d7..e3fd2dbf4eea 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -578,9 +578,9 @@ static struct memory_block *find_memory_block_by_id(unsigned long block_id) /* * Called under device_hotplug_lock. */ -struct memory_block *find_memory_block(struct mem_section *section) +struct memory_block *find_memory_block(unsigned long section_nr) { - unsigned long block_id = memory_block_id(__section_nr(section)); + unsigned long block_id = memory_block_id(section_nr); return find_memory_block_by_id(block_id); } diff --git a/include/linux/memory.h b/include/linux/memory.h index 97e92e8b556a..d9a0b61cd432 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -90,7 +90,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size, void remove_memory_block_devices(unsigned long start, unsigned long size); extern void memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); -extern struct memory_block *find_memory_block(struct mem_section *); +extern struct memory_block *find_memory_block(unsigned long section_nr); typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); extern int walk_memory_blocks(unsigned long start, unsigned long size, void *arg, walk_memory_blocks_func_t func); -- cgit v1.2.3 From 11e02d3729da1a2d4a33db5ea61291770d411884 Mon Sep 17 00:00:00 2001 From: Ohhoon Kwon Date: Thu, 2 Sep 2021 14:57:04 -0700 Subject: mm: sparse: remove __section_nr() function As the last users of __section_nr() are gone, let's remove unused function __section_nr(). Link: https://lkml.kernel.org/r/20210707150212.855-4-ohoono.kwon@samsung.com Signed-off-by: Ohhoon Kwon Acked-by: Michal Hocko Acked-by: Mike Rapoport Reviewed-by: David Hildenbrand Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 - mm/sparse.c | 26 -------------------------- 2 files changed, 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fcb535560028..8827f4d081d4 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1342,7 +1342,6 @@ static inline struct mem_section *__nr_to_section(unsigned long nr) return NULL; return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; } -extern unsigned long __section_nr(struct mem_section *ms); extern size_t mem_section_usage_size(void); /* diff --git a/mm/sparse.c b/mm/sparse.c index 8018ee7fcda5..d85655242ed9 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -109,32 +109,6 @@ static inline int sparse_index_init(unsigned long section_nr, int nid) } #endif -#ifdef CONFIG_SPARSEMEM_EXTREME -unsigned long __section_nr(struct mem_section *ms) -{ - unsigned long root_nr; - struct mem_section *root = NULL; - - for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) { - root = __nr_to_section(root_nr * SECTIONS_PER_ROOT); - if (!root) - continue; - - if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT))) - break; - } - - VM_BUG_ON(!root); - - return (root_nr * SECTIONS_PER_ROOT) + (ms - root); -} -#else -unsigned long __section_nr(struct mem_section *ms) -{ - return (unsigned long)(ms - mem_section[0]); -} -#endif - /* * During early boot, before section_mem_map is used for an actual * mem_map, we use section_mem_map to store the section's NUMA -- cgit v1.2.3 From 01c8d337d195ed105cabab95bc4dcb9e145bf5ea Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 2 Sep 2021 14:57:07 -0700 Subject: mm/sparse: set SECTION_NID_SHIFT to 6 Currently SECTION_NID_SHIFT is set to 3, which is incorrect because bit 3 and 4 can be overlapped by sub-field for early NID, and can be unexpectedly set on NUMA systems. There are a few non-critical issues related to this: - Having SECTION_TAINT_ZONE_DEVICE set for wrong sections forces pfn_to_online_page() through the slow path, but doesn't actually break the kernel. - A kdump generation tool like makedumpfile uses this field to calculate the physical address to read. So wrong bits can make the tool access to wrong address and fail to create kdump. This can be avoided by the tool, so it's not critical. To fix it, set SECTION_NID_SHIFT to 6 which is the minimum number of available bits of section flag field. Link: https://lkml.kernel.org/r/20210707045548.810271-1-naoya.horiguchi@linux.dev Fixes: 1f90a3477df3 ("mm: teach pfn_to_online_page() about ZONE_DEVICE section collisions") Signed-off-by: Naoya Horiguchi Reported-by: Kazuhito Hagio Suggested-by: Dan Williams Acked-by: David Hildenbrand Cc: Oscar Salvador Cc: Wang Wensheng Cc: Rui Xiang Cc: Kazu Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 8827f4d081d4..59bad25ce78e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1364,7 +1364,7 @@ extern size_t mem_section_usage_size(void); #define SECTION_TAINT_ZONE_DEVICE (1UL<<4) #define SECTION_MAP_LAST_BIT (1UL<<5) #define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) -#define SECTION_NID_SHIFT 3 +#define SECTION_NID_SHIFT 6 static inline struct page *__section_mem_map_addr(struct mem_section *section) { -- cgit v1.2.3 From d0505e9f7dcec85da6634ec66da2b17656ee177b Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 2 Sep 2021 14:58:31 -0700 Subject: mm: hwpoison: don't drop slab caches for offlining non-LRU page In the current implementation of soft offline, if non-LRU page is met, all the slab caches will be dropped to free the page then offline. But if the page is not slab page all the effort is wasted in vain. Even though it is a slab page, it is not guaranteed the page could be freed at all. However the side effect and cost is quite high. It does not only drop the slab caches, but also may drop a significant amount of page caches which are associated with inode caches. It could make the most workingset gone in order to just offline a page. And the offline is not guaranteed to succeed at all, actually I really doubt the success rate for real life workload. Furthermore the worse consequence is the system may be locked up and unusable since the page cache release may incur huge amount of works queued for memcg release. Actually we ran into such unpleasant case in our production environment. Firstly, the workqueue of memory_failure_work_func is locked up as below: BUG: workqueue lockup - pool cpus=1 node=0 flags=0x0 nice=0 stuck for 53s! Showing busy workqueues and worker pools: workqueue events: flags=0x0 pwq 2: cpus=1 node=0 flags=0x0 nice=0 active=14/256 refcnt=15 in-flight: 409271:memory_failure_work_func pending: kfree_rcu_work, kfree_rcu_monitor, kfree_rcu_work, rht_deferred_worker, rht_deferred_worker, rht_deferred_worker, rht_deferred_worker, kfree_rcu_work, kfree_rcu_work, kfree_rcu_work, kfree_rcu_work, drain_local_stock, kfree_rcu_work workqueue mm_percpu_wq: flags=0x8 pwq 2: cpus=1 node=0 flags=0x0 nice=0 active=1/256 refcnt=2 pending: vmstat_update workqueue cgroup_destroy: flags=0x0 pwq 2: cpus=1 node=0 flags=0x0 nice=0 active=1/1 refcnt=12072 pending: css_release_work_fn There were over 12K css_release_work_fn queued, and this caused a few lockups due to the contention of worker pool lock with IRQ disabled, for example: NMI watchdog: Watchdog detected hard LOCKUP on cpu 1 Modules linked in: amd64_edac_mod edac_mce_amd crct10dif_pclmul crc32_pclmul ghash_clmulni_intel xt_DSCP iptable_mangle kvm_amd bpfilter vfat fat acpi_ipmi i2c_piix4 usb_storage ipmi_si k10temp i2c_core ipmi_devintf ipmi_msghandler acpi_cpufreq sch_fq_codel xfs libcrc32c crc32c_intel mlx5_core mlxfw nvme xhci_pci ptp nvme_core pps_core xhci_hcd CPU: 1 PID: 205500 Comm: kworker/1:0 Tainted: G L 5.10.32-t1.el7.twitter.x86_64 #1 Hardware name: TYAN F5AMT /z /S8026GM2NRE-CGN, BIOS V8.030 03/30/2021 Workqueue: events memory_failure_work_func RIP: 0010:queued_spin_lock_slowpath+0x41/0x1a0 Code: 41 f0 0f ba 2f 08 0f 92 c0 0f b6 c0 c1 e0 08 89 c2 8b 07 30 e4 09 d0 a9 00 01 ff ff 75 1b 85 c0 74 0e 8b 07 84 c0 74 08 f3 90 <8b> 07 84 c0 75 f8 b8 01 00 00 00 66 89 07 c3 f6 c4 01 75 04 c6 47 RSP: 0018:ffff9b2ac278f900 EFLAGS: 00000002 RAX: 0000000000480101 RBX: ffff8ce98ce71800 RCX: 0000000000000084 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8ce98ce6a140 RBP: 00000000000284c8 R08: ffffd7248dcb6808 R09: 0000000000000000 R10: 0000000000000003 R11: ffff9b2ac278f9b0 R12: 0000000000000001 R13: ffff8cb44dab9c00 R14: ffffffffbd1ce6a0 R15: ffff8cacaa37f068 FS: 0000000000000000(0000) GS:ffff8ce98ce40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fcf6e8cb000 CR3: 0000000a0c60a000 CR4: 0000000000350ee0 Call Trace: __queue_work+0xd6/0x3c0 queue_work_on+0x1c/0x30 uncharge_batch+0x10e/0x110 mem_cgroup_uncharge_list+0x6d/0x80 release_pages+0x37f/0x3f0 __pagevec_release+0x1c/0x50 __invalidate_mapping_pages+0x348/0x380 inode_lru_isolate+0x10a/0x160 __list_lru_walk_one+0x7b/0x170 list_lru_walk_one+0x4a/0x60 prune_icache_sb+0x37/0x50 super_cache_scan+0x123/0x1a0 do_shrink_slab+0x10c/0x2c0 shrink_slab+0x1f1/0x290 drop_slab_node+0x4d/0x70 soft_offline_page+0x1ac/0x5b0 memory_failure_work_func+0x6a/0x90 process_one_work+0x19e/0x340 worker_thread+0x30/0x360 kthread+0x116/0x130 The lockup made the machine is quite unusable. And it also made the most workingset gone, the reclaimabled slab caches were reduced from 12G to 300MB, the page caches were decreased from 17G to 4G. But the most disappointing thing is all the effort doesn't make the page offline, it just returns: soft_offline: 0x1469f2: unknown non LRU page type 5ffff0000000000 () It seems the aggressive behavior for non-LRU page didn't pay back, so it doesn't make too much sense to keep it considering the terrible side effect. Link: https://lkml.kernel.org/r/20210819054116.266126-1-shy828301@gmail.com Signed-off-by: Yang Shi Reported-by: David Mackey Acked-by: David Hildenbrand Acked-by: Naoya Horiguchi Cc: Oscar Salvador Cc: Matthew Wilcox (Oracle) Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- mm/hwpoison-inject.c | 2 +- mm/memory-failure.c | 18 ++++++++---------- 3 files changed, 10 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 35bbac32b6f6..11c38550627c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3110,7 +3110,7 @@ extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; -extern void shake_page(struct page *p, int access); +extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index 1ae1ebc2b9b1..aff4d27ec235 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -30,7 +30,7 @@ static int hwpoison_inject(void *data, u64 val) if (!hwpoison_filter_enable) goto inject; - shake_page(hpage, 0); + shake_page(hpage); /* * This implies unable to support non-LRU pages. */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f83a2af0af18..5decacb86b9f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -282,9 +282,9 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags) /* * Unknown page type encountered. Try to check whether it can turn PageLRU by - * lru_add_drain_all, or a free page by reclaiming slabs when possible. + * lru_add_drain_all. */ -void shake_page(struct page *p, int access) +void shake_page(struct page *p) { if (PageHuge(p)) return; @@ -296,11 +296,9 @@ void shake_page(struct page *p, int access) } /* - * Only call drop_slab_node here (which would also shrink - * other caches) if access is not potentially fatal. + * TODO: Could shrink slab caches here if a lightweight range-based + * shrinker will be available. */ - if (access) - drop_slab_node(page_to_nid(p)); } EXPORT_SYMBOL_GPL(shake_page); @@ -1205,7 +1203,7 @@ try_again: * page, retry. */ if (pass++ < 3) { - shake_page(p, 1); + shake_page(p); goto try_again; } ret = -EIO; @@ -1222,7 +1220,7 @@ try_again: */ if (pass++ < 3) { put_page(p); - shake_page(p, 1); + shake_page(p); count_increased = false; goto try_again; } @@ -1369,7 +1367,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * shake_page() again to ensure that it's flushed. */ if (mlocked) - shake_page(hpage, 0); + shake_page(hpage); /* * Now that the dirty bit has been propagated to the @@ -1723,7 +1721,7 @@ try_again: * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. */ - shake_page(p, 0); + shake_page(p); lock_page(p); -- cgit v1.2.3 From 09a26e832705fdb7a9484495b71a05e0bbc65207 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Thu, 2 Sep 2021 14:58:53 -0700 Subject: hugetlb: fix hugetlb cgroup refcounting during vma split Guillaume Morin reported hitting the following WARNING followed by GPF or NULL pointer deference either in cgroups_destroy or in the kill_css path.: percpu ref (css_release) <= 0 (-1) after switching to atomic WARNING: CPU: 23 PID: 130 at lib/percpu-refcount.c:196 percpu_ref_switch_to_atomic_rcu+0x127/0x130 CPU: 23 PID: 130 Comm: ksoftirqd/23 Kdump: loaded Tainted: G O 5.10.60 #1 RIP: 0010:percpu_ref_switch_to_atomic_rcu+0x127/0x130 Call Trace: rcu_core+0x30f/0x530 rcu_core_si+0xe/0x10 __do_softirq+0x103/0x2a2 run_ksoftirqd+0x2b/0x40 smpboot_thread_fn+0x11a/0x170 kthread+0x10a/0x140 ret_from_fork+0x22/0x30 Upon further examination, it was discovered that the css structure was associated with hugetlb reservations. For private hugetlb mappings the vma points to a reserve map that contains a pointer to the css. At mmap time, reservations are set up and a reference to the css is taken. This reference is dropped in the vma close operation; hugetlb_vm_op_close. However, if a vma is split no additional reference to the css is taken yet hugetlb_vm_op_close will be called twice for the split vma resulting in an underflow. Fix by taking another reference in hugetlb_vm_op_open. Note that the reference is only taken for the owner of the reserve map. In the more common fork case, the pointer to the reserve map is cleared for non-owning vmas. Link: https://lkml.kernel.org/r/20210830215015.155224-1-mike.kravetz@oracle.com Fixes: e9fe92ae0cd2 ("hugetlb_cgroup: add reservation accounting for private mappings") Signed-off-by: Mike Kravetz Reported-by: Guillaume Morin Suggested-by: Guillaume Morin Tested-by: Guillaume Morin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb_cgroup.h | 12 ++++++++++++ mm/hugetlb.c | 4 +++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 0b8d1fdda3a1..c137396129db 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -121,6 +121,13 @@ static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) css_put(&h_cg->css); } +static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( + struct resv_map *resv_map) +{ + if (resv_map->css) + css_get(resv_map->css); +} + extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, @@ -199,6 +206,11 @@ static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) { } +static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( + struct resv_map *resv_map) +{ +} + static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dd1c1e7d970b..41a1778d3f67 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4106,8 +4106,10 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma) * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ - if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); + } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) -- cgit v1.2.3 From a759a909d42d727e918bd5248d6cff7562fa8109 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Thu, 2 Sep 2021 14:58:56 -0700 Subject: userfaultfd: change mmap_changing to atomic Patch series "userfaultfd: minor bug fixes". Three unrelated bug fixes. The first two addresses possible issues (not too theoretical ones), but I did not encounter them in practice. The third patch addresses a test bug that causes the test to fail on my system. It has been sent before as part of a bigger RFC. This patch (of 3): mmap_changing is currently a boolean variable, which is set and cleared without any lock that protects against concurrent modifications. mmap_changing is supposed to mark whether userfaultfd page-faults handling should be retried since mappings are undergoing a change. However, concurrent calls, for instance to madvise(MADV_DONTNEED), might cause mmap_changing to be false, although the remove event was still not read (hence acknowledged) by the user. Change mmap_changing to atomic_t and increase/decrease appropriately. Add a debug assertion to see whether mmap_changing is negative. Link: https://lkml.kernel.org/r/20210808020724.1022515-1-namit@vmware.com Link: https://lkml.kernel.org/r/20210808020724.1022515-2-namit@vmware.com Fixes: df2cc96e77011 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races") Signed-off-by: Nadav Amit Cc: Mike Rapoport Cc: Peter Xu Cc: Axel Rasmussen Cc: Alexander Viro Cc: Andrea Arcangeli Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 25 +++++++++++++------------ include/linux/userfaultfd_k.h | 8 ++++---- mm/userfaultfd.c | 15 ++++++++------- 3 files changed, 25 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 5c2d806e6ae5..29a3016f16c9 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -74,7 +74,7 @@ struct userfaultfd_ctx { /* released */ bool released; /* memory mappings are changing because of non-cooperative event */ - bool mmap_changing; + atomic_t mmap_changing; /* mm with one ore more vmas attached to this userfaultfd_ctx */ struct mm_struct *mm; }; @@ -623,7 +623,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, * already released. */ out: - WRITE_ONCE(ctx->mmap_changing, false); + atomic_dec(&ctx->mmap_changing); + VM_BUG_ON(atomic_read(&ctx->mmap_changing) < 0); userfaultfd_ctx_put(ctx); } @@ -669,12 +670,12 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) ctx->state = UFFD_STATE_RUNNING; ctx->features = octx->features; ctx->released = false; - ctx->mmap_changing = false; + atomic_set(&ctx->mmap_changing, 0); ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); - WRITE_ONCE(octx->mmap_changing, true); + atomic_inc(&octx->mmap_changing); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); @@ -721,7 +722,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma, if (ctx->features & UFFD_FEATURE_EVENT_REMAP) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); - WRITE_ONCE(ctx->mmap_changing, true); + atomic_inc(&ctx->mmap_changing); } else { /* Drop uffd context if remap feature not enabled */ vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -766,7 +767,7 @@ bool userfaultfd_remove(struct vm_area_struct *vma, return true; userfaultfd_ctx_get(ctx); - WRITE_ONCE(ctx->mmap_changing, true); + atomic_inc(&ctx->mmap_changing); mmap_read_unlock(mm); msg_init(&ewq.msg); @@ -810,7 +811,7 @@ int userfaultfd_unmap_prep(struct vm_area_struct *vma, return -ENOMEM; userfaultfd_ctx_get(ctx); - WRITE_ONCE(ctx->mmap_changing, true); + atomic_inc(&ctx->mmap_changing); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; @@ -1700,7 +1701,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; - if (READ_ONCE(ctx->mmap_changing)) + if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; @@ -1757,7 +1758,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; - if (READ_ONCE(ctx->mmap_changing)) + if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; @@ -1807,7 +1808,7 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range range; bool mode_wp, mode_dontwake; - if (READ_ONCE(ctx->mmap_changing)) + if (atomic_read(&ctx->mmap_changing)) return -EAGAIN; user_uffdio_wp = (struct uffdio_writeprotect __user *) arg; @@ -1855,7 +1856,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; - if (READ_ONCE(ctx->mmap_changing)) + if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; @@ -2087,7 +2088,7 @@ SYSCALL_DEFINE1(userfaultfd, int, flags) ctx->features = 0; ctx->state = UFFD_STATE_WAIT_API; ctx->released = false; - ctx->mmap_changing = false; + atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; /* prevent the mm struct to be freed */ mmgrab(ctx->mm); diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 331d2ccf0bcc..33cea484d1ad 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -60,16 +60,16 @@ extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - bool *mmap_changing, __u64 mode); + atomic_t *mmap_changing, __u64 mode); extern ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long len, - bool *mmap_changing); + atomic_t *mmap_changing); extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long len, bool *mmap_changing); + unsigned long len, atomic_t *mmap_changing); extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, - bool enable_wp, bool *mmap_changing); + bool enable_wp, atomic_t *mmap_changing); /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 0e2132834bc7..7a9008415534 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -483,7 +483,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, unsigned long src_start, unsigned long len, enum mcopy_atomic_mode mcopy_mode, - bool *mmap_changing, + atomic_t *mmap_changing, __u64 mode) { struct vm_area_struct *dst_vma; @@ -517,7 +517,7 @@ retry: * request the user to retry later */ err = -EAGAIN; - if (mmap_changing && READ_ONCE(*mmap_changing)) + if (mmap_changing && atomic_read(mmap_changing)) goto out_unlock; /* @@ -650,28 +650,29 @@ out: ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - bool *mmap_changing, __u64 mode) + atomic_t *mmap_changing, __u64 mode) { return __mcopy_atomic(dst_mm, dst_start, src_start, len, MCOPY_ATOMIC_NORMAL, mmap_changing, mode); } ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start, - unsigned long len, bool *mmap_changing) + unsigned long len, atomic_t *mmap_changing) { return __mcopy_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_ZEROPAGE, mmap_changing, 0); } ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long start, - unsigned long len, bool *mmap_changing) + unsigned long len, atomic_t *mmap_changing) { return __mcopy_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_CONTINUE, mmap_changing, 0); } int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, - unsigned long len, bool enable_wp, bool *mmap_changing) + unsigned long len, bool enable_wp, + atomic_t *mmap_changing) { struct vm_area_struct *dst_vma; pgprot_t newprot; @@ -694,7 +695,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, * request the user to retry later */ err = -EAGAIN; - if (mmap_changing && READ_ONCE(*mmap_changing)) + if (mmap_changing && atomic_read(mmap_changing)) goto out_unlock; err = -ENOENT; -- cgit v1.2.3 From 5ac95884a784e822b8cbe3d4bd6e9f96b3b71e3f Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 2 Sep 2021 14:59:13 -0700 Subject: mm/migrate: enable returning precise migrate_pages() success count Under normal circumstances, migrate_pages() returns the number of pages migrated. In error conditions, it returns an error code. When returning an error code, there is no way to know how many pages were migrated or not migrated. Make migrate_pages() return how many pages are demoted successfully for all cases, including when encountering errors. Page reclaim behavior will depend on this in subsequent patches. Link: https://lkml.kernel.org/r/20210721063926.3024591-3-ying.huang@intel.com Link: https://lkml.kernel.org/r/20210715055145.195411-4-ying.huang@intel.com Signed-off-by: Yang Shi Signed-off-by: Dave Hansen Signed-off-by: "Huang, Ying" Suggested-by: Oscar Salvador [optional parameter] Reviewed-by: Yang Shi Reviewed-by: Zi Yan Cc: Michal Hocko Cc: Wei Xu Cc: Dan Williams Cc: David Hildenbrand Cc: David Rientjes Cc: Greg Thelen Cc: Keith Busch Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 5 +++-- mm/compaction.c | 2 +- mm/gup.c | 2 +- mm/memory-failure.c | 2 +- mm/memory_hotplug.c | 2 +- mm/mempolicy.c | 4 ++-- mm/migrate.c | 11 ++++++++--- mm/page_alloc.c | 2 +- 8 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 23dadf7aeba8..8ab88d46318e 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -41,7 +41,8 @@ extern int migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, - unsigned long private, enum migrate_mode mode, int reason); + unsigned long private, enum migrate_mode mode, int reason, + unsigned int *ret_succeeded); extern struct page *alloc_migration_target(struct page *page, unsigned long private); extern int isolate_movable_page(struct page *page, isolate_mode_t mode); @@ -56,7 +57,7 @@ extern int migrate_page_move_mapping(struct address_space *mapping, static inline void putback_movable_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, - int reason) + int reason, unsigned int *ret_succeeded) { return -ENOSYS; } static inline struct page *alloc_migration_target(struct page *page, unsigned long private) diff --git a/mm/compaction.c b/mm/compaction.c index 621508e0ecd5..61fb64f47a06 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2398,7 +2398,7 @@ compact_zone(struct compact_control *cc, struct capture_control *capc) err = migrate_pages(&cc->migratepages, compaction_alloc, compaction_free, (unsigned long)cc, cc->mode, - MR_COMPACTION); + MR_COMPACTION, NULL); trace_mm_compaction_migratepages(cc->nr_migratepages, err, &cc->migratepages); diff --git a/mm/gup.c b/mm/gup.c index 1c7f4ec6990b..9935a4480710 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1772,7 +1772,7 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, if (!list_empty(&movable_page_list)) { ret = migrate_pages(&movable_page_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, - MR_LONGTERM_PIN); + MR_LONGTERM_PIN, NULL); if (ret && !list_empty(&movable_page_list)) putback_movable_pages(&movable_page_list); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 2f925615e573..517789b03961 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2099,7 +2099,7 @@ static int __soft_offline_page(struct page *page) if (isolate_page(hpage, &pagelist)) { ret = migrate_pages(&pagelist, alloc_migration_target, NULL, - (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE); + (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL); if (!ret) { bool release = !huge; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 86c3af79e874..4c527a80b6c9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1469,7 +1469,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (nodes_empty(nmask)) node_set(mtc.nid, nmask); ret = migrate_pages(&source, alloc_migration_target, NULL, - (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); + (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG, NULL); if (ret) { list_for_each_entry(page, &source, lru) { if (__ratelimit(&migrate_rs)) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e32360e90274..939eabcaf488 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1084,7 +1084,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, - (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); + (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } @@ -1338,7 +1338,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); nr_failed = migrate_pages(&pagelist, new_page, NULL, - start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); + start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); if (nr_failed) putback_movable_pages(&pagelist); } diff --git a/mm/migrate.c b/mm/migrate.c index 0c12af203b68..ae923e9b8874 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1429,6 +1429,8 @@ static inline int try_split_thp(struct page *page, struct page **page2, * @mode: The migration mode that specifies the constraints for * page migration, if any. * @reason: The reason for page migration. + * @ret_succeeded: Set to the number of pages migrated successfully if + * the caller passes a non-NULL pointer. * * The function returns after 10 attempts or if no pages are movable any more * because the list has become empty or no retryable pages exist any more. @@ -1439,7 +1441,7 @@ static inline int try_split_thp(struct page *page, struct page **page2, */ int migrate_pages(struct list_head *from, new_page_t get_new_page, free_page_t put_new_page, unsigned long private, - enum migrate_mode mode, int reason) + enum migrate_mode mode, int reason, unsigned int *ret_succeeded) { int retry = 1; int thp_retry = 1; @@ -1594,6 +1596,9 @@ out: if (!swapwrite) current->flags &= ~PF_SWAPWRITE; + if (ret_succeeded) + *ret_succeeded = nr_succeeded; + return rc; } @@ -1663,7 +1668,7 @@ static int do_move_pages_to_node(struct mm_struct *mm, }; err = migrate_pages(pagelist, alloc_migration_target, NULL, - (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); + (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(pagelist); return err; @@ -2178,7 +2183,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, list_add(&page->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, *new, NULL, node, - MIGRATE_ASYNC, MR_NUMA_MISPLACED); + MIGRATE_ASYNC, MR_NUMA_MISPLACED, NULL); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cafdca874e0d..f95e1d2386a1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8990,7 +8990,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, cc->nr_migratepages -= nr_reclaimed; ret = migrate_pages(&cc->migratepages, alloc_migration_target, - NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE); + NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE, NULL); /* * On -ENOMEM, migrate_pages() bails out right away. It is pointless -- cgit v1.2.3 From 26aa2d199d6f2cfa6f2ef2a5dfe891f2250e71a0 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Thu, 2 Sep 2021 14:59:16 -0700 Subject: mm/migrate: demote pages during reclaim This is mostly derived from a patch from Yang Shi: https://lore.kernel.org/linux-mm/1560468577-101178-10-git-send-email-yang.shi@linux.alibaba.com/ Add code to the reclaim path (shrink_page_list()) to "demote" data to another NUMA node instead of discarding the data. This always avoids the cost of I/O needed to read the page back in and sometimes avoids the writeout cost when the page is dirty. A second pass through shrink_page_list() will be made if any demotions fail. This essentially falls back to normal reclaim behavior in the case that demotions fail. Previous versions of this patch may have simply failed to reclaim pages which were eligible for demotion but were unable to be demoted in practice. For some cases, for example, MADV_PAGEOUT, the pages are always discarded instead of demoted to follow the kernel API definition. Because MADV_PAGEOUT is defined as freeing specified pages regardless in which tier they are. Note: This just adds the start of infrastructure for migration. It is actually disabled next to the FIXME in migrate_demote_page_ok(). [dave.hansen@linux.intel.com: v11] Link: https://lkml.kernel.org/r/20210715055145.195411-5-ying.huang@intel.com Link: https://lkml.kernel.org/r/20210721063926.3024591-4-ying.huang@intel.com Link: https://lkml.kernel.org/r/20210715055145.195411-5-ying.huang@intel.com Signed-off-by: Dave Hansen Signed-off-by: "Huang, Ying" Reviewed-by: Yang Shi Reviewed-by: Wei Xu Reviewed-by: Oscar Salvador Reviewed-by: Zi Yan Cc: Michal Hocko Cc: David Rientjes Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Thelen Cc: Keith Busch Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 9 +++++ include/trace/events/migrate.h | 3 +- mm/vmscan.c | 85 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 96 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 8ab88d46318e..326250996b4e 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -28,6 +28,7 @@ enum migrate_reason { MR_NUMA_MISPLACED, MR_CONTIG_RANGE, MR_LONGTERM_PIN, + MR_DEMOTION, MR_TYPES }; @@ -167,6 +168,14 @@ struct migrate_vma { int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); +int next_demotion_node(int node); + +#else /* CONFIG_MIGRATION disabled: */ + +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} #endif /* CONFIG_MIGRATION */ diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 9fb2a3bbcdfb..779f3fad9ecd 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -21,7 +21,8 @@ EM( MR_MEMPOLICY_MBIND, "mempolicy_mbind") \ EM( MR_NUMA_MISPLACED, "numa_misplaced") \ EM( MR_CONTIG_RANGE, "contig_range") \ - EMe(MR_LONGTERM_PIN, "longterm_pin") + EM( MR_LONGTERM_PIN, "longterm_pin") \ + EMe(MR_DEMOTION, "demotion") /* * First define the enums in the above macros to be exported to userspace diff --git a/mm/vmscan.c b/mm/vmscan.c index 6c401b44a245..f26b247f5daf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include @@ -121,6 +122,9 @@ struct scan_control { /* The file pages on the current node are dangerously low */ unsigned int file_is_tiny:1; + /* Always discard instead of demoting to lower tier memory */ + unsigned int no_demotion:1; + /* Allocation order */ s8 order; @@ -518,6 +522,17 @@ static long add_nr_deferred(long nr, struct shrinker *shrinker, return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); } +static bool can_demote(int nid, struct scan_control *sc) +{ + if (sc->no_demotion) + return false; + if (next_demotion_node(nid) == NUMA_NO_NODE) + return false; + + // FIXME: actually enable this later in the series + return false; +} + /* * This misses isolated pages which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is @@ -1263,6 +1278,49 @@ static void page_check_dirty_writeback(struct page *page, mapping->a_ops->is_dirty_writeback(page, dirty, writeback); } +static struct page *alloc_demote_page(struct page *page, unsigned long node) +{ + struct migration_target_control mtc = { + /* + * Allocate from 'node', or fail quickly and quietly. + * When this happens, 'page' will likely just be discarded + * instead of migrated. + */ + .gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | + __GFP_THISNODE | __GFP_NOWARN | + __GFP_NOMEMALLOC | GFP_NOWAIT, + .nid = node + }; + + return alloc_migration_target(page, (unsigned long)&mtc); +} + +/* + * Take pages on @demote_list and attempt to demote them to + * another node. Pages which are not demoted are left on + * @demote_pages. + */ +static unsigned int demote_page_list(struct list_head *demote_pages, + struct pglist_data *pgdat) +{ + int target_nid = next_demotion_node(pgdat->node_id); + unsigned int nr_succeeded; + int err; + + if (list_empty(demote_pages)) + return 0; + + if (target_nid == NUMA_NO_NODE) + return 0; + + /* Demotion ignores all cpuset and mempolicy settings */ + err = migrate_pages(demote_pages, alloc_demote_page, NULL, + target_nid, MIGRATE_ASYNC, MR_DEMOTION, + &nr_succeeded); + + return nr_succeeded; +} + /* * shrink_page_list() returns the number of reclaimed pages */ @@ -1274,12 +1332,16 @@ static unsigned int shrink_page_list(struct list_head *page_list, { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); + LIST_HEAD(demote_pages); unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; + bool do_demote_pass; memset(stat, 0, sizeof(*stat)); cond_resched(); + do_demote_pass = can_demote(pgdat->node_id, sc); +retry: while (!list_empty(page_list)) { struct address_space *mapping; struct page *page; @@ -1428,6 +1490,17 @@ static unsigned int shrink_page_list(struct list_head *page_list, ; /* try to reclaim the page below */ } + /* + * Before reclaiming the page, try to relocate + * its contents to another node. + */ + if (do_demote_pass && + (thp_migration_supported() || !PageTransHuge(page))) { + list_add(&page->lru, &demote_pages); + unlock_page(page); + continue; + } + /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. @@ -1679,6 +1752,17 @@ keep: list_add(&page->lru, &ret_pages); VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } + /* 'page_list' is always empty here */ + + /* Migrate pages selected for demotion */ + nr_reclaimed += demote_page_list(&demote_pages, pgdat); + /* Pages that could not be demoted are still in @demote_pages */ + if (!list_empty(&demote_pages)) { + /* Pages which failed to demoted go back on @page_list for retry: */ + list_splice_init(&demote_pages, page_list); + do_demote_pass = false; + goto retry; + } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; @@ -2326,6 +2410,7 @@ unsigned long reclaim_pages(struct list_head *page_list) .may_writepage = 1, .may_unmap = 1, .may_swap = 1, + .no_demotion = 1, }; noreclaim_flag = memalloc_noreclaim_save(); -- cgit v1.2.3 From 668e4147d8850df32ca41e28f52c146025ca45c6 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 2 Sep 2021 14:59:19 -0700 Subject: mm/vmscan: add page demotion counter Account the number of demoted pages. Add pgdemote_kswapd and pgdemote_direct VM counters showed in /proc/vmstat. [ daveh: - __count_vm_events() a bit, and made them look at the THP size directly rather than getting data from migrate_pages() ] Link: https://lkml.kernel.org/r/20210721063926.3024591-5-ying.huang@intel.com Link: https://lkml.kernel.org/r/20210715055145.195411-6-ying.huang@intel.com Signed-off-by: Yang Shi Signed-off-by: Dave Hansen Signed-off-by: "Huang, Ying" Reviewed-by: Yang Shi Reviewed-by: Wei Xu Reviewed-by: Zi Yan Cc: Michal Hocko Cc: David Rientjes Cc: Dan Williams Cc: David Hildenbrand Cc: Oscar Salvador Cc: Greg Thelen Cc: Keith Busch Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 2 ++ mm/vmscan.c | 5 +++++ mm/vmstat.c | 2 ++ 3 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index ae0dd1948c2b..a185cc75ff52 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -33,6 +33,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGREUSE, PGSTEAL_KSWAPD, PGSTEAL_DIRECT, + PGDEMOTE_KSWAPD, + PGDEMOTE_DIRECT, PGSCAN_KSWAPD, PGSCAN_DIRECT, PGSCAN_DIRECT_THROTTLE, diff --git a/mm/vmscan.c b/mm/vmscan.c index f26b247f5daf..88593b82a8df 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1318,6 +1318,11 @@ static unsigned int demote_page_list(struct list_head *demote_pages, target_nid, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); + if (current_is_kswapd()) + __count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded); + else + __count_vm_events(PGDEMOTE_DIRECT, nr_succeeded); + return nr_succeeded; } diff --git a/mm/vmstat.c b/mm/vmstat.c index b0534e068166..ec5a2e789dd2 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1217,6 +1217,8 @@ const char * const vmstat_text[] = { "pgreuse", "pgsteal_kswapd", "pgsteal_direct", + "pgdemote_kswapd", + "pgdemote_direct", "pgscan_kswapd", "pgscan_direct", "pgscan_direct_throttle", -- cgit v1.2.3 From 20b51af15e014cac63b58a4f8b8b323ac35bccce Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 2 Sep 2021 14:59:33 -0700 Subject: mm/migrate: add sysfs interface to enable reclaim migration Some method is obviously needed to enable reclaim-based migration. Just like traditional autonuma, there will be some workloads that will benefit like workloads with more "static" configurations where hot pages stay hot and cold pages stay cold. If pages come and go from the hot and cold sets, the benefits of this approach will be more limited. The benefits are truly workload-based and *not* hardware-based. We do not believe that there is a viable threshold where certain hardware configurations should have this mechanism enabled while others do not. To be conservative, earlier work defaulted to disable reclaim- based migration and did not include a mechanism to enable it. This proposes add a new sysfs file /sys/kernel/mm/numa/demotion_enabled as a method to enable it. We are open to any alternative that allows end users to enable this mechanism or disable it if workload harm is detected (just like traditional autonuma). Once this is enabled page demotion may move data to a NUMA node that does not fall into the cpuset of the allocating process. This could be construed to violate the guarantees of cpusets. However, since this is an opt-in mechanism, the assumption is that anyone enabling it is content to relax the guarantees. Link: https://lkml.kernel.org/r/20210721063926.3024591-9-ying.huang@intel.com Link: https://lkml.kernel.org/r/20210715055145.195411-10-ying.huang@intel.com Signed-off-by: Huang Ying Originally-by: Dave Hansen Cc: Michal Hocko Cc: Wei Xu Cc: Yang Shi Cc: Zi Yan Cc: David Rientjes Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Thelen Cc: Keith Busch Cc: Oscar Salvador Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/ABI/testing/sysfs-kernel-mm-numa | 24 ++++++++++ include/linux/mempolicy.h | 4 ++ mm/mempolicy.c | 61 ++++++++++++++++++++++++++ mm/vmscan.c | 5 ++- 4 files changed, 92 insertions(+), 2 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-mm-numa (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-numa b/Documentation/ABI/testing/sysfs-kernel-mm-numa new file mode 100644 index 000000000000..77e559d4ed80 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm-numa @@ -0,0 +1,24 @@ +What: /sys/kernel/mm/numa/ +Date: June 2021 +Contact: Linux memory management mailing list +Description: Interface for NUMA + +What: /sys/kernel/mm/numa/demotion_enabled +Date: June 2021 +Contact: Linux memory management mailing list +Description: Enable/disable demoting pages during reclaim + + Page migration during reclaim is intended for systems + with tiered memory configurations. These systems have + multiple types of memory with varied performance + characteristics instead of plain NUMA systems where + the same kind of memory is found at varied distances. + Allowing page migration during reclaim enables these + systems to migrate pages from fast tiers to slow tiers + when the fast tier is under pressure. This migration + is performed before swap. It may move data to a NUMA + node that does not fall into the cpuset of the + allocating process which might be construed to violate + the guarantees of cpusets. This should not be enabled + on systems which need strict cpuset location + guarantees. diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 0aaf91b496e2..4ca025e2a77e 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -184,6 +184,8 @@ extern bool vma_migratable(struct vm_area_struct *vma); extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); +extern bool numa_demotion_enabled; + #else struct mempolicy {}; @@ -292,5 +294,7 @@ static inline nodemask_t *policy_nodemask_current(gfp_t gfp) { return NULL; } + +#define numa_demotion_enabled false #endif /* CONFIG_NUMA */ #endif diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 939eabcaf488..e675bfb856da 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -3021,3 +3021,64 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } + +bool numa_demotion_enabled = false; + +#ifdef CONFIG_SYSFS +static ssize_t numa_demotion_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", + numa_demotion_enabled? "true" : "false"); +} + +static ssize_t numa_demotion_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) + numa_demotion_enabled = true; + else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) + numa_demotion_enabled = false; + else + return -EINVAL; + + return count; +} + +static struct kobj_attribute numa_demotion_enabled_attr = + __ATTR(demotion_enabled, 0644, numa_demotion_enabled_show, + numa_demotion_enabled_store); + +static struct attribute *numa_attrs[] = { + &numa_demotion_enabled_attr.attr, + NULL, +}; + +static const struct attribute_group numa_attr_group = { + .attrs = numa_attrs, +}; + +static int __init numa_init_sysfs(void) +{ + int err; + struct kobject *numa_kobj; + + numa_kobj = kobject_create_and_add("numa", mm_kobj); + if (!numa_kobj) { + pr_err("failed to create numa kobject\n"); + return -ENOMEM; + } + err = sysfs_create_group(numa_kobj, &numa_attr_group); + if (err) { + pr_err("failed to register numa group\n"); + goto delete_obj; + } + return 0; + +delete_obj: + kobject_put(numa_kobj); + return err; +} +subsys_initcall(numa_init_sysfs); +#endif diff --git a/mm/vmscan.c b/mm/vmscan.c index 43289f5f8488..2255025f1891 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -524,6 +524,8 @@ static long add_nr_deferred(long nr, struct shrinker *shrinker, static bool can_demote(int nid, struct scan_control *sc) { + if (!numa_demotion_enabled) + return false; if (sc) { if (sc->no_demotion) return false; @@ -534,8 +536,7 @@ static bool can_demote(int nid, struct scan_control *sc) if (next_demotion_node(nid) == NUMA_NO_NODE) return false; - // FIXME: actually enable this later in the series - return false; + return true; } static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, -- cgit v1.2.3 From 9647875be52b33fe22cb034ec3074896c581543f Mon Sep 17 00:00:00 2001 From: Hui Su Date: Thu, 2 Sep 2021 14:59:36 -0700 Subject: mm/vmpressure: replace vmpressure_to_css() with vmpressure_to_memcg() We can get memcg directly form vmpr instead of vmpr->memcg->css->memcg, so add a new func helper vmpressure_to_memcg(). And no code will use vmpressure_to_css(), so delete it. Link: https://lkml.kernel.org/r/20210630112146.455103-1-suhui@zeku.com Signed-off-by: Hui Su Acked-by: Michal Hocko Acked-by: Chris Down Cc: Johannes Weiner Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmpressure.h | 2 +- mm/memcontrol.c | 4 ++-- mm/vmpressure.c | 3 +-- 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h index 6d28bc433c1c..6a2f51ebbfd3 100644 --- a/include/linux/vmpressure.h +++ b/include/linux/vmpressure.h @@ -37,7 +37,7 @@ extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio); extern void vmpressure_init(struct vmpressure *vmpr); extern void vmpressure_cleanup(struct vmpressure *vmpr); extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg); -extern struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr); +extern struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr); extern int vmpressure_register_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd, const char *args); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 06ae0075e864..896f0f403c52 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -256,9 +256,9 @@ struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg) return &memcg->vmpressure; } -struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) +struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr) { - return &container_of(vmpr, struct mem_cgroup, vmpressure)->css; + return container_of(vmpr, struct mem_cgroup, vmpressure); } #ifdef CONFIG_MEMCG_KMEM diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 9b172561fded..76518e4166dc 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -74,8 +74,7 @@ static struct vmpressure *work_to_vmpressure(struct work_struct *work) static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) { - struct cgroup_subsys_state *css = vmpressure_to_css(vmpr); - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *memcg = vmpressure_to_memcg(vmpr); memcg = parent_mem_cgroup(memcg); if (!memcg) -- cgit v1.2.3 From b87c517ac5de168aec6e8318ca0707b11b2ccfaf Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 2 Sep 2021 14:59:46 -0700 Subject: mm/vmscan: remove unneeded return value of kswapd_run() The return value of kswapd_run() is unused now. Clean it up. Link: https://lkml.kernel.org/r/20210717065911.61497-4-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Acked-by: Michal Hocko Cc: Alex Shi Cc: Alistair Popple Cc: David Hildenbrand Cc: Hillf Danton Cc: Jens Axboe Cc: Johannes Weiner Cc: John Hubbard Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Minchan Kim Cc: Shaohua Li Cc: Vlastimil Babka Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- mm/vmscan.c | 7 ++----- 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index f30d26b0f71d..ba52f3a3478e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -408,7 +408,7 @@ static inline bool node_reclaim_enabled(void) extern void check_move_unevictable_pages(struct pagevec *pvec); -extern int kswapd_run(int nid); +extern void kswapd_run(int nid); extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP diff --git a/mm/vmscan.c b/mm/vmscan.c index 8857e4dcbfd3..ab5019700dc3 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4434,23 +4434,20 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) * This kswapd start function will be called by init and node-hot-add. * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. */ -int kswapd_run(int nid) +void kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); - int ret = 0; if (pgdat->kswapd) - return 0; + return; pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ BUG_ON(system_state < SYSTEM_RUNNING); pr_err("Failed to start kswapd on node %d\n", nid); - ret = PTR_ERR(pgdat->kswapd); pgdat->kswapd = NULL; } - return ret; } /* -- cgit v1.2.3 From 65d759c8f9f57b96c199f3fe5cfb93ac7da095e9 Mon Sep 17 00:00:00 2001 From: Charan Teja Reddy Date: Thu, 2 Sep 2021 14:59:59 -0700 Subject: mm: compaction: support triggering of proactive compaction by user The proactive compaction[1] gets triggered for every 500msec and run compaction on the node for COMPACTION_HPAGE_ORDER (usually order-9) pages based on the value set to sysctl.compaction_proactiveness. Triggering the compaction for every 500msec in search of COMPACTION_HPAGE_ORDER pages is not needed for all applications, especially on the embedded system usecases which may have few MB's of RAM. Enabling the proactive compaction in its state will endup in running almost always on such systems. Other side, proactive compaction can still be very much useful for getting a set of higher order pages in some controllable manner(controlled by using the sysctl.compaction_proactiveness). So, on systems where enabling the proactive compaction always may proove not required, can trigger the same from user space on write to its sysctl interface. As an example, say app launcher decide to launch the memory heavy application which can be launched fast if it gets more higher order pages thus launcher can prepare the system in advance by triggering the proactive compaction from userspace. This triggering of proactive compaction is done on a write to sysctl.compaction_proactiveness by user. [1]https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?id=facdaa917c4d5a376d09d25865f5a863f906234a [akpm@linux-foundation.org: tweak vm.rst, per Mike] Link: https://lkml.kernel.org/r/1627653207-12317-1-git-send-email-charante@codeaurora.org Signed-off-by: Charan Teja Reddy Acked-by: Vlastimil Babka Acked-by: Rafael Aquini Cc: Mike Rapoport Cc: Luis Chamberlain Cc: Kees Cook Cc: Iurii Zaikin Cc: Dave Hansen Cc: Mel Gorman Cc: Nitin Gupta Cc: Jonathan Corbet Cc: Khalid Aziz Cc: David Rientjes Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/sysctl/vm.rst | 3 ++- include/linux/compaction.h | 2 ++ include/linux/mmzone.h | 1 + kernel/sysctl.c | 2 +- mm/compaction.c | 38 +++++++++++++++++++++++++++++++-- 5 files changed, 42 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 003d5cc3751b..5e795202111f 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -118,7 +118,8 @@ compaction_proactiveness This tunable takes a value in the range [0, 100] with a default value of 20. This tunable determines how aggressively compaction is done in the -background. Setting it to 0 disables proactive compaction. +background. Write of a non zero value to this tunable will immediately +trigger the proactive compaction. Setting it to 0 disables proactive compaction. Note that compaction has a non-trivial system-wide impact as pages belonging to different processes are moved around, which could also lead diff --git a/include/linux/compaction.h b/include/linux/compaction.h index c24098c7acca..34bce35c808d 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -84,6 +84,8 @@ static inline unsigned long compact_gap(unsigned int order) extern unsigned int sysctl_compaction_proactiveness; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); +extern int compaction_proactiveness_sysctl_handler(struct ctl_table *table, + int write, void *buffer, size_t *length, loff_t *ppos); extern int sysctl_extfrag_threshold; extern int sysctl_compact_unevictable_allowed; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 59bad25ce78e..1bd5f5955f9a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -846,6 +846,7 @@ typedef struct pglist_data { enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; + bool proactive_compact_trigger; #endif /* * This is a per-node reserve of pages that are not available diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 272f4a272f8c..297f0b3966bd 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2871,7 +2871,7 @@ static struct ctl_table vm_table[] = { .data = &sysctl_compaction_proactiveness, .maxlen = sizeof(sysctl_compaction_proactiveness), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = compaction_proactiveness_sysctl_handler, .extra1 = SYSCTL_ZERO, .extra2 = &one_hundred, }, diff --git a/mm/compaction.c b/mm/compaction.c index 4ee0d40d93f2..fa9b2b598eab 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2706,6 +2706,30 @@ static void compact_nodes(void) */ unsigned int __read_mostly sysctl_compaction_proactiveness = 20; +int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + int rc, nid; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + if (write && sysctl_compaction_proactiveness) { + for_each_online_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); + + if (pgdat->proactive_compact_trigger) + continue; + + pgdat->proactive_compact_trigger = true; + wake_up_interruptible(&pgdat->kcompactd_wait); + } + } + + return 0; +} + /* * This is the entry point for compacting all nodes via * /proc/sys/vm/compact_memory @@ -2750,7 +2774,8 @@ void compaction_unregister_node(struct node *node) static inline bool kcompactd_work_requested(pg_data_t *pgdat) { - return pgdat->kcompactd_max_order > 0 || kthread_should_stop(); + return pgdat->kcompactd_max_order > 0 || kthread_should_stop() || + pgdat->proactive_compact_trigger; } static bool kcompactd_node_suitable(pg_data_t *pgdat) @@ -2901,9 +2926,16 @@ static int kcompactd(void *p) while (!kthread_should_stop()) { unsigned long pflags; + /* + * Avoid the unnecessary wakeup for proactive compaction + * when it is disabled. + */ + if (!sysctl_compaction_proactiveness) + timeout = MAX_SCHEDULE_TIMEOUT; trace_mm_compaction_kcompactd_sleep(pgdat->node_id); if (wait_event_freezable_timeout(pgdat->kcompactd_wait, - kcompactd_work_requested(pgdat), timeout)) { + kcompactd_work_requested(pgdat), timeout) && + !pgdat->proactive_compact_trigger) { psi_memstall_enter(&pflags); kcompactd_do_work(pgdat); @@ -2938,6 +2970,8 @@ static int kcompactd(void *p) timeout = default_timeout << COMPACT_MAX_DEFER_SHIFT; } + if (unlikely(pgdat->proactive_compact_trigger)) + pgdat->proactive_compact_trigger = false; } return 0; -- cgit v1.2.3 From cfcaa66f803233c50e17239469f6c96136a673a1 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Thu, 2 Sep 2021 15:00:13 -0700 Subject: mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY Implement the missing huge page allocation functionality while obeying the preferred node semantics. This is similar to the implementation for general page allocation, as it uses a fallback mechanism to try multiple preferred nodes first, and then all other nodes. To avoid adding too many "#ifdef CONFIG_NUMA" check, add a helper function in mempolicy.h to check whether a mempolicy is MPOL_PREFERRED_MANY. [akpm@linux-foundation.org: fix compiling issue when merging with other hugetlb patch] [Thanks to 0day bot for catching the !CONFIG_NUMA compiling issue] [mhocko@suse.com: suggest to remove the #ifdef CONFIG_NUMA check] [ben.widawsky@intel.com: add helpers to avoid ifdefs] Link: https://lore.kernel.org/r/20200630212517.308045-12-ben.widawsky@intel.com Link: https://lkml.kernel.org/r/1627970362-61305-4-git-send-email-feng.tang@intel.com Link: https://lkml.kernel.org/r/20210809024430.GA46432@shbuild999.sh.intel.com [nathan@kernel.org: initialize page to NULL in alloc_buddy_huge_page_with_mpol()] Link: https://lkml.kernel.org/r/20210810200632.3812797-1-nathan@kernel.org Link: https://lore.kernel.org/r/20200630212517.308045-12-ben.widawsky@intel.com Link: https://lkml.kernel.org/r/1627970362-61305-4-git-send-email-feng.tang@intel.com Link: https://lkml.kernel.org/r/20210809024430.GA46432@shbuild999.sh.intel.com Signed-off-by: Ben Widawsky Signed-off-by: Feng Tang Signed-off-by: Nathan Chancellor Co-developed-by: Feng Tang Suggested-by: Michal Hocko Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 12 ++++++++++++ mm/hugetlb.c | 30 +++++++++++++++++++++++++----- 2 files changed, 37 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 4ca025e2a77e..4091692bed8c 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -186,6 +186,12 @@ extern void mpol_put_task_policy(struct task_struct *); extern bool numa_demotion_enabled; +static inline bool mpol_is_preferred_many(struct mempolicy *pol) +{ + return (pol->mode == MPOL_PREFERRED_MANY); +} + + #else struct mempolicy {}; @@ -296,5 +302,11 @@ static inline nodemask_t *policy_nodemask_current(gfp_t gfp) } #define numa_demotion_enabled false + +static inline bool mpol_is_preferred_many(struct mempolicy *pol) +{ + return false; +} + #endif /* CONFIG_NUMA */ #endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 41a1778d3f67..95dc7b83381f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1145,7 +1145,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, unsigned long address, int avoid_reserve, long chg) { - struct page *page; + struct page *page = NULL; struct mempolicy *mpol; gfp_t gfp_mask; nodemask_t *nodemask; @@ -1166,7 +1166,17 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); - page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask); + + if (mpol_is_preferred_many(mpol)) { + page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask); + + /* Fallback to all nodes if page==NULL */ + nodemask = NULL; + } + + if (!page) + page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask); + if (page && !avoid_reserve && vma_has_reserves(vma, chg)) { SetHPageRestoreReserve(page); h->resv_huge_pages--; @@ -2142,16 +2152,26 @@ static struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { - struct page *page; + struct page *page = NULL; struct mempolicy *mpol; gfp_t gfp_mask = htlb_alloc_mask(h); int nid; nodemask_t *nodemask; nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); - page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask, false); - mpol_cond_put(mpol); + if (mpol_is_preferred_many(mpol)) { + gfp_t gfp = gfp_mask | __GFP_NOWARN; + + gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); + page = alloc_surplus_huge_page(h, gfp, nid, nodemask, false); + /* Fallback to all nodes if page==NULL */ + nodemask = NULL; + } + + if (!page) + page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask, false); + mpol_cond_put(mpol); return page; } -- cgit v1.2.3 From a7259df7670240ee03b0cfce8a3e5d3773911e24 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 2 Sep 2021 15:00:26 -0700 Subject: memblock: make memblock_find_in_range method private There are a lot of uses of memblock_find_in_range() along with memblock_reserve() from the times memblock allocation APIs did not exist. memblock_find_in_range() is the very core of memblock allocations, so any future changes to its internal behaviour would mandate updates of all the users outside memblock. Replace the calls to memblock_find_in_range() with an equivalent calls to memblock_phys_alloc() and memblock_phys_alloc_range() and make memblock_find_in_range() private method of memblock. This simplifies the callers, ensures that (unlikely) errors in memblock_reserve() are handled and improves maintainability of memblock_find_in_range(). Link: https://lkml.kernel.org/r/20210816122622.30279-1-rppt@kernel.org Signed-off-by: Mike Rapoport Reviewed-by: Catalin Marinas [arm64] Acked-by: Kirill A. Shutemov Acked-by: Rafael J. Wysocki [ACPI] Acked-by: Russell King (Oracle) Acked-by: Nick Kossifidis [riscv] Tested-by: Guenter Roeck Acked-by: Rob Herring Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/kernel/setup.c | 20 +++++++----------- arch/arm64/kvm/hyp/reserved_mem.c | 9 +++----- arch/arm64/mm/init.c | 36 ++++++++++---------------------- arch/mips/kernel/setup.c | 14 ++++++------- arch/riscv/mm/init.c | 44 +++++++++++++-------------------------- arch/s390/kernel/setup.c | 9 +++++--- arch/x86/kernel/aperture_64.c | 5 ++--- arch/x86/mm/init.c | 23 +++++++++++++------- arch/x86/mm/numa.c | 5 ++--- arch/x86/mm/numa_emulation.c | 5 ++--- arch/x86/realmode/init.c | 2 +- drivers/acpi/tables.c | 5 ++--- drivers/base/arch_numa.c | 5 +---- drivers/of/of_reserved_mem.c | 12 +++++++---- include/linux/memblock.h | 2 -- mm/memblock.c | 2 +- 16 files changed, 81 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index f97eb2371672..284a80c0b6e1 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -1012,31 +1012,25 @@ static void __init reserve_crashkernel(void) unsigned long long lowmem_max = __pa(high_memory - 1) + 1; if (crash_max > lowmem_max) crash_max = lowmem_max; - crash_base = memblock_find_in_range(CRASH_ALIGN, crash_max, - crash_size, CRASH_ALIGN); + + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, + CRASH_ALIGN, crash_max); if (!crash_base) { pr_err("crashkernel reservation failed - No suitable area found.\n"); return; } } else { + unsigned long long crash_max = crash_base + crash_size; unsigned long long start; - start = memblock_find_in_range(crash_base, - crash_base + crash_size, - crash_size, SECTION_SIZE); - if (start != crash_base) { + start = memblock_phys_alloc_range(crash_size, SECTION_SIZE, + crash_base, crash_max); + if (!start) { pr_err("crashkernel reservation failed - memory is in use.\n"); return; } } - ret = memblock_reserve(crash_base, crash_size); - if (ret < 0) { - pr_warn("crashkernel reservation failed - memory is in use (0x%lx)\n", - (unsigned long)crash_base); - return; - } - pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n", (unsigned long)(crash_size >> 20), (unsigned long)(crash_base >> 20), diff --git a/arch/arm64/kvm/hyp/reserved_mem.c b/arch/arm64/kvm/hyp/reserved_mem.c index d654921dd09b..578670e3f608 100644 --- a/arch/arm64/kvm/hyp/reserved_mem.c +++ b/arch/arm64/kvm/hyp/reserved_mem.c @@ -92,12 +92,10 @@ void __init kvm_hyp_reserve(void) * this is unmapped from the host stage-2, and fallback to PAGE_SIZE. */ hyp_mem_size = hyp_mem_pages << PAGE_SHIFT; - hyp_mem_base = memblock_find_in_range(0, memblock_end_of_DRAM(), - ALIGN(hyp_mem_size, PMD_SIZE), - PMD_SIZE); + hyp_mem_base = memblock_phys_alloc(ALIGN(hyp_mem_size, PMD_SIZE), + PMD_SIZE); if (!hyp_mem_base) - hyp_mem_base = memblock_find_in_range(0, memblock_end_of_DRAM(), - hyp_mem_size, PAGE_SIZE); + hyp_mem_base = memblock_phys_alloc(hyp_mem_size, PAGE_SIZE); else hyp_mem_size = ALIGN(hyp_mem_size, PMD_SIZE); @@ -105,7 +103,6 @@ void __init kvm_hyp_reserve(void) kvm_err("Failed to reserve hyp memory\n"); return; } - memblock_reserve(hyp_mem_base, hyp_mem_size); kvm_info("Reserved %lld MiB at 0x%llx\n", hyp_mem_size >> 20, hyp_mem_base); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 1fdb7bb7c198..bf5b8a5cd451 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -74,6 +74,7 @@ phys_addr_t arm64_dma_phys_limit __ro_after_init; static void __init reserve_crashkernel(void) { unsigned long long crash_base, crash_size; + unsigned long long crash_max = arm64_dma_phys_limit; int ret; ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), @@ -84,33 +85,18 @@ static void __init reserve_crashkernel(void) crash_size = PAGE_ALIGN(crash_size); - if (crash_base == 0) { - /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, arm64_dma_phys_limit, - crash_size, SZ_2M); - if (crash_base == 0) { - pr_warn("cannot allocate crashkernel (size:0x%llx)\n", - crash_size); - return; - } - } else { - /* User specifies base address explicitly. */ - if (!memblock_is_region_memory(crash_base, crash_size)) { - pr_warn("cannot reserve crashkernel: region is not memory\n"); - return; - } + /* User specifies base address explicitly. */ + if (crash_base) + crash_max = crash_base + crash_size; - if (memblock_is_region_reserved(crash_base, crash_size)) { - pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n"); - return; - } - - if (!IS_ALIGNED(crash_base, SZ_2M)) { - pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n"); - return; - } + /* Current arm64 boot protocol requires 2MB alignment */ + crash_base = memblock_phys_alloc_range(crash_size, SZ_2M, + crash_base, crash_max); + if (!crash_base) { + pr_warn("cannot allocate crashkernel (size:0x%llx)\n", + crash_size); + return; } - memblock_reserve(crash_base, crash_size); pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", crash_base, crash_base + crash_size, crash_size >> 20); diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 23a140327a0b..f979adfd4fc2 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -452,8 +452,9 @@ static void __init mips_parse_crashkernel(void) return; if (crash_base <= 0) { - crash_base = memblock_find_in_range(CRASH_ALIGN, CRASH_ADDR_MAX, - crash_size, CRASH_ALIGN); + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, + CRASH_ALIGN, + CRASH_ADDR_MAX); if (!crash_base) { pr_warn("crashkernel reservation failed - No suitable area found.\n"); return; @@ -461,8 +462,9 @@ static void __init mips_parse_crashkernel(void) } else { unsigned long long start; - start = memblock_find_in_range(crash_base, crash_base + crash_size, - crash_size, 1); + start = memblock_phys_alloc_range(crash_size, 1, + crash_base, + crash_base + crash_size); if (start != crash_base) { pr_warn("Invalid memory region reserved for crash kernel\n"); return; @@ -656,10 +658,6 @@ static void __init arch_mem_init(char **cmdline_p) mips_reserve_vmcore(); mips_parse_crashkernel(); -#ifdef CONFIG_KEXEC - if (crashk_res.start != crashk_res.end) - memblock_reserve(crashk_res.start, resource_size(&crashk_res)); -#endif device_tree_init(); /* diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 7cb4f391d106..e6cac495a9e8 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -819,38 +819,22 @@ static void __init reserve_crashkernel(void) crash_size = PAGE_ALIGN(crash_size); - if (crash_base == 0) { - /* - * Current riscv boot protocol requires 2MB alignment for - * RV64 and 4MB alignment for RV32 (hugepage size) - */ - crash_base = memblock_find_in_range(search_start, search_end, - crash_size, PMD_SIZE); - - if (crash_base == 0) { - pr_warn("crashkernel: couldn't allocate %lldKB\n", - crash_size >> 10); - return; - } - } else { - /* User specifies base address explicitly. */ - if (!memblock_is_region_memory(crash_base, crash_size)) { - pr_warn("crashkernel: requested region is not memory\n"); - return; - } - - if (memblock_is_region_reserved(crash_base, crash_size)) { - pr_warn("crashkernel: requested region is reserved\n"); - return; - } - + if (crash_base) { + search_start = crash_base; + search_end = crash_base + crash_size; + } - if (!IS_ALIGNED(crash_base, PMD_SIZE)) { - pr_warn("crashkernel: requested region is misaligned\n"); - return; - } + /* + * Current riscv boot protocol requires 2MB alignment for + * RV64 and 4MB alignment for RV32 (hugepage size) + */ + crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, + search_start, search_end); + if (crash_base == 0) { + pr_warn("crashkernel: couldn't allocate %lldKB\n", + crash_size >> 10); + return; } - memblock_reserve(crash_base, crash_size); pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n", crash_base, crash_base + crash_size, crash_size >> 20); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ff0f9e838916..0bab57d6413b 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -626,8 +626,9 @@ static void __init reserve_crashkernel(void) return; } low = crash_base ?: low; - crash_base = memblock_find_in_range(low, high, crash_size, - KEXEC_CRASH_MEM_ALIGN); + crash_base = memblock_phys_alloc_range(crash_size, + KEXEC_CRASH_MEM_ALIGN, + low, high); } if (!crash_base) { @@ -636,8 +637,10 @@ static void __init reserve_crashkernel(void) return; } - if (register_memory_notifier(&kdump_mem_nb)) + if (register_memory_notifier(&kdump_mem_nb)) { + memblock_free(crash_base, crash_size); return; + } if (!OLDMEM_BASE && MACHINE_IS_VM) diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size)); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 294ed4392a0e..10562885f5fc 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -109,14 +109,13 @@ static u32 __init allocate_aperture(void) * memory. Unfortunately we cannot move it up because that would * make the IOMMU useless. */ - addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR, - aper_size, aper_size); + addr = memblock_phys_alloc_range(aper_size, aper_size, + GART_MIN_ADDR, GART_MAX_ADDR); if (!addr) { pr_err("Cannot allocate aperture memory hole [mem %#010lx-%#010lx] (%uKB)\n", addr, addr + aper_size - 1, aper_size >> 10); return 0; } - memblock_reserve(addr, aper_size); pr_info("Mapping aperture over RAM [mem %#010lx-%#010lx] (%uKB)\n", addr, addr + aper_size - 1, aper_size >> 10); register_nosave_region(addr >> PAGE_SHIFT, diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 75ef19aa8903..23a14d82e783 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -127,14 +127,12 @@ __ref void *alloc_low_pages(unsigned int num) unsigned long ret = 0; if (min_pfn_mapped < max_pfn_mapped) { - ret = memblock_find_in_range( + ret = memblock_phys_alloc_range( + PAGE_SIZE * num, PAGE_SIZE, min_pfn_mapped << PAGE_SHIFT, - max_pfn_mapped << PAGE_SHIFT, - PAGE_SIZE * num , PAGE_SIZE); + max_pfn_mapped << PAGE_SHIFT); } - if (ret) - memblock_reserve(ret, PAGE_SIZE * num); - else if (can_use_brk_pgt) + if (!ret && can_use_brk_pgt) ret = __pa(extend_brk(PAGE_SIZE * num, PAGE_SIZE)); if (!ret) @@ -610,8 +608,17 @@ static void __init memory_map_top_down(unsigned long map_start, unsigned long addr; unsigned long mapped_ram_size = 0; - /* xen has big range in reserved near end of ram, skip it at first.*/ - addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE); + /* + * Systems that have many reserved areas near top of the memory, + * e.g. QEMU with less than 1G RAM and EFI enabled, or Xen, will + * require lots of 4K mappings which may exhaust pgt_buf. + * Start with top-most PMD_SIZE range aligned at PMD_SIZE to ensure + * there is enough mapped memory that can be allocated from + * memblock. + */ + addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start, + map_end); + memblock_free(addr, PMD_SIZE); real_end = addr + PMD_SIZE; /* step_size need to be small so pgt_buf from BRK could cover it */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index e94da744386f..a1b5c71099e6 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -376,15 +376,14 @@ static int __init numa_alloc_distance(void) cnt++; size = cnt * cnt * sizeof(numa_distance[0]); - phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), - size, PAGE_SIZE); + phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0, + PFN_PHYS(max_pfn_mapped)); if (!phys) { pr_warn("Warning: can't allocate distance table!\n"); /* don't retry until explicitly reset */ numa_distance = (void *)1LU; return -ENOMEM; } - memblock_reserve(phys, size); numa_distance = __va(phys); numa_distance_cnt = cnt; diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 87d77cc52f86..737491b13728 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -447,13 +447,12 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) if (numa_dist_cnt) { u64 phys; - phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), - phys_size, PAGE_SIZE); + phys = memblock_phys_alloc_range(phys_size, PAGE_SIZE, 0, + PFN_PHYS(max_pfn_mapped)); if (!phys) { pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); goto no_emu; } - memblock_reserve(phys, phys_size); phys_dist = __va(phys); for (i = 0; i < numa_dist_cnt; i++) diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 6534c92d0f83..31b5856010cb 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -28,7 +28,7 @@ void __init reserve_real_mode(void) WARN_ON(slab_is_available()); /* Has to be under 1M so we can execute real-mode AP code. */ - mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); + mem = memblock_phys_alloc_range(size, PAGE_SIZE, 0, 1<<20); if (!mem) pr_info("No sub-1M memory is available for the trampoline\n"); else diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index a37a1532a575..f9383736fa0f 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -583,8 +583,8 @@ void __init acpi_table_upgrade(void) } acpi_tables_addr = - memblock_find_in_range(0, ACPI_TABLE_UPGRADE_MAX_PHYS, - all_tables_size, PAGE_SIZE); + memblock_phys_alloc_range(all_tables_size, PAGE_SIZE, + 0, ACPI_TABLE_UPGRADE_MAX_PHYS); if (!acpi_tables_addr) { WARN_ON(1); return; @@ -599,7 +599,6 @@ void __init acpi_table_upgrade(void) * Both memblock_reserve and e820__range_add (via arch_reserve_mem_area) * works fine. */ - memblock_reserve(acpi_tables_addr, all_tables_size); arch_reserve_mem_area(acpi_tables_addr, all_tables_size); /* diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 4cc4e117727d..46c503486e96 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -279,13 +279,10 @@ static int __init numa_alloc_distance(void) int i, j; size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]); - phys = memblock_find_in_range(0, PFN_PHYS(max_pfn), - size, PAGE_SIZE); + phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0, PFN_PHYS(max_pfn)); if (WARN_ON(!phys)) return -ENOMEM; - memblock_reserve(phys, size); - numa_distance = __va(phys); numa_distance_cnt = nr_node_ids; diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index fd3964d24224..59c1390cdf42 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -33,18 +33,22 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, phys_addr_t *res_base) { phys_addr_t base; + int err = 0; end = !end ? MEMBLOCK_ALLOC_ANYWHERE : end; align = !align ? SMP_CACHE_BYTES : align; - base = memblock_find_in_range(start, end, size, align); + base = memblock_phys_alloc_range(size, align, start, end); if (!base) return -ENOMEM; *res_base = base; - if (nomap) - return memblock_mark_nomap(base, size); + if (nomap) { + err = memblock_mark_nomap(base, size); + if (err) + memblock_free(base, size); + } - return memblock_reserve(base, size); + return err; } /* diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 4a53c3ca86bd..b066024c62e3 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -99,8 +99,6 @@ void memblock_discard(void); static inline void memblock_discard(void) {} #endif -phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, - phys_addr_t size, phys_addr_t align); void memblock_allow_resize(void); int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); int memblock_add(phys_addr_t base, phys_addr_t size); diff --git a/mm/memblock.c b/mm/memblock.c index a69449bffc8d..e6b4654f9dfd 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -315,7 +315,7 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, * Return: * Found address on success, 0 on failure. */ -phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, +static phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align) { -- cgit v1.2.3 From dce49103962840dd61423d7627748d6c558d58c5 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 2 Sep 2021 15:00:33 -0700 Subject: mm: wire up syscall process_mrelease Split off from prev patch in the series that implements the syscall. Link: https://lkml.kernel.org/r/20210809185259.405936-2-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Geert Uytterhoeven Cc: Andy Lutomirski Cc: Christian Brauner Cc: Christoph Hellwig Cc: David Hildenbrand Cc: David Rientjes Cc: Florian Weimer Cc: Jan Engelhardt Cc: Jann Horn Cc: Johannes Weiner Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Minchan Kim Cc: Oleg Nesterov Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Tim Murray Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/syscalls/syscall.tbl | 2 ++ arch/arm/tools/syscall.tbl | 2 ++ arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 ++ arch/ia64/kernel/syscalls/syscall.tbl | 2 ++ arch/m68k/kernel/syscalls/syscall.tbl | 2 ++ arch/microblaze/kernel/syscalls/syscall.tbl | 2 ++ arch/mips/kernel/syscalls/syscall_n32.tbl | 2 ++ arch/mips/kernel/syscalls/syscall_n64.tbl | 2 ++ arch/mips/kernel/syscalls/syscall_o32.tbl | 2 ++ arch/parisc/kernel/syscalls/syscall.tbl | 2 ++ arch/powerpc/kernel/syscalls/syscall.tbl | 2 ++ arch/s390/kernel/syscalls/syscall.tbl | 2 ++ arch/sh/kernel/syscalls/syscall.tbl | 2 ++ arch/sparc/kernel/syscalls/syscall.tbl | 2 ++ arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 2 ++ include/linux/syscalls.h | 1 + include/uapi/asm-generic/unistd.h | 4 +++- kernel/sys_ni.c | 1 + 21 files changed, 38 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index a17687ed4b51..605645eae04c 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -486,3 +486,5 @@ 554 common landlock_create_ruleset sys_landlock_create_ruleset 555 common landlock_add_rule sys_landlock_add_rule 556 common landlock_restrict_self sys_landlock_restrict_self +# 557 reserved for memfd_secret +558 common process_mrelease sys_process_mrelease diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index c5df1179fc5d..2f32eb8beca8 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -460,3 +460,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 727bfc3be99b..3cb206aea3db 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 447 +#define __NR_compat_syscalls 449 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 99ffcafc736c..0f49cdb180dd 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -901,6 +901,8 @@ __SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule) #define __NR_landlock_restrict_self 446 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) +#define __NR_process_mrelease 448 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 6d07742c57b8..9bf45f2be966 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -367,3 +367,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 541bc1b3a8f9..f1f98ee6c82d 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -446,3 +446,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index a176faca2927..da49ddd4bb54 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -452,3 +452,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index c2d2e19abea8..56c8d3cf42ed 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -385,3 +385,5 @@ 444 n32 landlock_create_ruleset sys_landlock_create_ruleset 445 n32 landlock_add_rule sys_landlock_add_rule 446 n32 landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 n32 process_mrelease sys_process_mrelease diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index ac653d08b1ea..1ca7bc337932 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -361,3 +361,5 @@ 444 n64 landlock_create_ruleset sys_landlock_create_ruleset 445 n64 landlock_add_rule sys_landlock_add_rule 446 n64 landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 n64 process_mrelease sys_process_mrelease diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 253f2cd70b6b..fd3a9df60ec2 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -434,3 +434,5 @@ 444 o32 landlock_create_ruleset sys_landlock_create_ruleset 445 o32 landlock_add_rule sys_landlock_add_rule 446 o32 landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 o32 process_mrelease sys_process_mrelease diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index e26187b9ab87..040df1b7a589 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -444,3 +444,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index aef2a290e71a..d8ebd7d37c0f 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -526,3 +526,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 64d51ab5a8b4..57233ace30cb 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -449,3 +449,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease sys_process_mrelease diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index e0a70be77d84..2f6e95eb4690 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -449,3 +449,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 603f5a821502..42fc2906215d 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -492,3 +492,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ce763a12311c..661a03bcfbd1 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -452,3 +452,4 @@ 445 i386 landlock_add_rule sys_landlock_add_rule 446 i386 landlock_restrict_self sys_landlock_restrict_self 447 i386 memfd_secret sys_memfd_secret +448 i386 process_mrelease sys_process_mrelease diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index f6b57799c1ea..807b6a1de8e8 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -369,6 +369,7 @@ 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self 447 common memfd_secret sys_memfd_secret +448 common process_mrelease sys_process_mrelease # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 235d67d6ceb4..f4384951f393 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -417,3 +417,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 69c9a7010081..00bc170a50f0 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -915,6 +915,7 @@ asmlinkage long sys_mincore(unsigned long start, size_t len, asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior); asmlinkage long sys_process_madvise(int pidfd, const struct iovec __user *vec, size_t vlen, int behavior, unsigned int flags); +asmlinkage long sys_process_mrelease(int pidfd, unsigned int flags); asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, unsigned long flags); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index a9d6fcd95f42..14c8fe863c6d 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -877,9 +877,11 @@ __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) #define __NR_memfd_secret 447 __SYSCALL(__NR_memfd_secret, sys_memfd_secret) #endif +#define __NR_process_mrelease 448 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) #undef __NR_syscalls -#define __NR_syscalls 448 +#define __NR_syscalls 449 /* * 32 bit systems traditionally used different diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 30971b1dd4a9..18a9c2cde767 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -289,6 +289,7 @@ COND_SYSCALL(munlockall); COND_SYSCALL(mincore); COND_SYSCALL(madvise); COND_SYSCALL(process_madvise); +COND_SYSCALL(process_mrelease); COND_SYSCALL(remap_file_pages); COND_SYSCALL(mbind); COND_SYSCALL_COMPAT(mbind); -- cgit v1.2.3 From 0b303fb402862dcb7948eeeed2439bd8c99948b5 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Sat, 8 May 2021 02:28:02 +0200 Subject: mm, slub: do initial checks in ___slab_alloc() with irqs enabled As another step of shortening irq disabled sections in ___slab_alloc(), delay disabling irqs until we pass the initial checks if there is a cached percpu slab and it's suitable for our allocation. Now we have to recheck c->page after actually disabling irqs as an allocation in irq handler might have replaced it. Because we call pfmemalloc_match() as one of the checks, we might hit VM_BUG_ON_PAGE(!PageSlab(page)) in PageSlabPfmemalloc in case we get interrupted and the page is freed. Thus introduce a pfmemalloc_match_unsafe() variant that lacks the PageSlab check. Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman --- include/linux/page-flags.h | 9 ++++++++ mm/slub.c | 54 ++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 54 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5922031ffab6..7fda4fb85bdc 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -815,6 +815,15 @@ static inline int PageSlabPfmemalloc(struct page *page) return PageActive(page); } +/* + * A version of PageSlabPfmemalloc() for opportunistic checks where the page + * might have been freed under us and not be a PageSlab anymore. + */ +static inline int __PageSlabPfmemalloc(struct page *page) +{ + return PageActive(page); +} + static inline void SetPageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); diff --git a/mm/slub.c b/mm/slub.c index dda05cc83eef..6295695d8515 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2620,6 +2620,19 @@ static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags) return true; } +/* + * A variant of pfmemalloc_match() that tests page flags without asserting + * PageSlab. Intended for opportunistic checks before taking a lock and + * rechecking that nobody else freed the page under us. + */ +static inline bool pfmemalloc_match_unsafe(struct page *page, gfp_t gfpflags) +{ + if (unlikely(__PageSlabPfmemalloc(page))) + return gfp_pfmemalloc_allowed(gfpflags); + + return true; +} + /* * Check the page->freelist of a page and either transfer the freelist to the * per cpu freelist or deactivate the page. @@ -2682,8 +2695,9 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, stat(s, ALLOC_SLOWPATH); - local_irq_save(flags); - page = c->page; +reread_page: + + page = READ_ONCE(c->page); if (!page) { /* * if the node is not online or has no normal memory, just @@ -2692,6 +2706,11 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, if (unlikely(node != NUMA_NO_NODE && !node_isset(node, slab_nodes))) node = NUMA_NO_NODE; + local_irq_save(flags); + if (unlikely(c->page)) { + local_irq_restore(flags); + goto reread_page; + } goto new_slab; } redo: @@ -2706,8 +2725,7 @@ redo: goto redo; } else { stat(s, ALLOC_NODE_MISMATCH); - deactivate_slab(s, page, c->freelist, c); - goto new_slab; + goto deactivate_slab; } } @@ -2716,12 +2734,15 @@ redo: * PFMEMALLOC but right now, we are losing the pfmemalloc * information when the page leaves the per-cpu allocator */ - if (unlikely(!pfmemalloc_match(page, gfpflags))) { - deactivate_slab(s, page, c->freelist, c); - goto new_slab; - } + if (unlikely(!pfmemalloc_match_unsafe(page, gfpflags))) + goto deactivate_slab; - /* must check again c->freelist in case of cpu migration or IRQ */ + /* must check again c->page in case IRQ handler changed it */ + local_irq_save(flags); + if (unlikely(page != c->page)) { + local_irq_restore(flags); + goto reread_page; + } freelist = c->freelist; if (freelist) goto load_freelist; @@ -2737,6 +2758,9 @@ redo: stat(s, ALLOC_REFILL); load_freelist: + + lockdep_assert_irqs_disabled(); + /* * freelist is pointing to the list of objects to be used. * page is pointing to the page from which the objects are obtained. @@ -2748,11 +2772,23 @@ load_freelist: local_irq_restore(flags); return freelist; +deactivate_slab: + + local_irq_save(flags); + if (page != c->page) { + local_irq_restore(flags); + goto reread_page; + } + deactivate_slab(s, page, c->freelist, c); + new_slab: + lockdep_assert_irqs_disabled(); + if (slub_percpu_partial(c)) { page = c->page = slub_percpu_partial(c); slub_set_percpu_partial(c, page); + local_irq_restore(flags); stat(s, CPU_PARTIAL_ALLOC); goto redo; } -- cgit v1.2.3 From 2112ff5ce0c1128fe7b4d19cfe7f2b8ce5b595fa Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 23 Aug 2021 11:18:44 +0100 Subject: iov_iter: track truncated size Remember how many bytes were truncated and reverted back. Because not reexpanded iterators don't always work well with reverting, we may need to know that to reexpand ourselves when needed. Signed-off-by: Pavel Begunkov Signed-off-by: Al Viro --- include/linux/uio.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 82c3c3e819e0..5265024e8b90 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -47,6 +47,7 @@ struct iov_iter { }; loff_t xarray_start; }; + size_t truncated; }; static inline enum iter_type iov_iter_type(const struct iov_iter *i) @@ -254,8 +255,10 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ - if (i->count > count) + if (i->count > count) { + i->truncated += i->count - count; i->count = count; + } } /* @@ -264,6 +267,7 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { + i->truncated -= count - i->count; i->count = count; } -- cgit v1.2.3 From bd0e7491a931f5a2960555b10b9551464ff8cc8e Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Sat, 22 May 2021 01:59:38 +0200 Subject: mm, slub: convert kmem_cpu_slab protection to local_lock Embed local_lock into struct kmem_cpu_slab and use the irq-safe versions of local_lock instead of plain local_irq_save/restore. On !PREEMPT_RT that's equivalent, with better lockdep visibility. On PREEMPT_RT that means better preemption. However, the cost on PREEMPT_RT is the loss of lockless fast paths which only work with cpu freelist. Those are designed to detect and recover from being preempted by other conflicting operations (both fast or slow path), but the slow path operations assume they cannot be preempted by a fast path operation, which is guaranteed naturally with disabled irqs. With local locks on PREEMPT_RT, the fast paths now also need to take the local lock to avoid races. In the allocation fastpath slab_alloc_node() we can just defer to the slowpath __slab_alloc() which also works with cpu freelist, but under the local lock. In the free fastpath do_slab_free() we have to add a new local lock protected version of freeing to the cpu freelist, as the existing slowpath only works with the page freelist. Also update the comment about locking scheme in SLUB to reflect changes done by this series. [ Mike Galbraith : use local_lock() without irq in PREEMPT_RT scope; debugging of RT crashes resulting in put_cpu_partial() locking changes ] Signed-off-by: Vlastimil Babka --- include/linux/slub_def.h | 6 ++ mm/slub.c | 146 +++++++++++++++++++++++++++++++++++------------ 2 files changed, 117 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index dcde82a4434c..85499f0586b0 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -10,6 +10,7 @@ #include #include #include +#include enum stat_item { ALLOC_FASTPATH, /* Allocation from cpu slab */ @@ -40,6 +41,10 @@ enum stat_item { CPU_PARTIAL_DRAIN, /* Drain cpu partial to node partial */ NR_SLUB_STAT_ITEMS }; +/* + * When changing the layout, make sure freelist and tid are still compatible + * with this_cpu_cmpxchg_double() alignment requirements. + */ struct kmem_cache_cpu { void **freelist; /* Pointer to next available object */ unsigned long tid; /* Globally unique transaction id */ @@ -47,6 +52,7 @@ struct kmem_cache_cpu { #ifdef CONFIG_SLUB_CPU_PARTIAL struct page *partial; /* Partially allocated frozen slabs */ #endif + local_lock_t lock; /* Protects the fields above */ #ifdef CONFIG_SLUB_STATS unsigned stat[NR_SLUB_STAT_ITEMS]; #endif diff --git a/mm/slub.c b/mm/slub.c index 38d4cc51e880..3d2025f7163b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -46,13 +46,21 @@ /* * Lock order: * 1. slab_mutex (Global Mutex) - * 2. node->list_lock - * 3. slab_lock(page) (Only on some arches and for debugging) + * 2. node->list_lock (Spinlock) + * 3. kmem_cache->cpu_slab->lock (Local lock) + * 4. slab_lock(page) (Only on some arches or for debugging) + * 5. object_map_lock (Only for debugging) * * slab_mutex * * The role of the slab_mutex is to protect the list of all the slabs * and to synchronize major metadata changes to slab cache structures. + * Also synchronizes memory hotplug callbacks. + * + * slab_lock + * + * The slab_lock is a wrapper around the page lock, thus it is a bit + * spinlock. * * The slab_lock is only used for debugging and on arches that do not * have the ability to do a cmpxchg_double. It only protects: @@ -61,6 +69,8 @@ * C. page->objects -> Number of objects in page * D. page->frozen -> frozen state * + * Frozen slabs + * * If a slab is frozen then it is exempt from list management. It is not * on any list except per cpu partial list. The processor that froze the * slab is the one who can perform list operations on the page. Other @@ -68,6 +78,8 @@ * froze the slab is the only one that can retrieve the objects from the * page's freelist. * + * list_lock + * * The list_lock protects the partial and full list on each node and * the partial slab counter. If taken then no new slabs may be added or * removed from the lists nor make the number of partial slabs be modified. @@ -79,10 +91,36 @@ * slabs, operations can continue without any centralized lock. F.e. * allocating a long series of objects that fill up slabs does not require * the list lock. - * Interrupts are disabled during allocation and deallocation in order to - * make the slab allocator safe to use in the context of an irq. In addition - * interrupts are disabled to ensure that the processor does not change - * while handling per_cpu slabs, due to kernel preemption. + * + * cpu_slab->lock local lock + * + * This locks protect slowpath manipulation of all kmem_cache_cpu fields + * except the stat counters. This is a percpu structure manipulated only by + * the local cpu, so the lock protects against being preempted or interrupted + * by an irq. Fast path operations rely on lockless operations instead. + * On PREEMPT_RT, the local lock does not actually disable irqs (and thus + * prevent the lockless operations), so fastpath operations also need to take + * the lock and are no longer lockless. + * + * lockless fastpaths + * + * The fast path allocation (slab_alloc_node()) and freeing (do_slab_free()) + * are fully lockless when satisfied from the percpu slab (and when + * cmpxchg_double is possible to use, otherwise slab_lock is taken). + * They also don't disable preemption or migration or irqs. They rely on + * the transaction id (tid) field to detect being preempted or moved to + * another cpu. + * + * irq, preemption, migration considerations + * + * Interrupts are disabled as part of list_lock or local_lock operations, or + * around the slab_lock operation, in order to make the slab allocator safe + * to use in the context of an irq. + * + * In addition, preemption (or migration on PREEMPT_RT) is disabled in the + * allocation slowpath, bulk allocation, and put_cpu_partial(), so that the + * local cpu doesn't change in the process and e.g. the kmem_cache_cpu pointer + * doesn't have to be revalidated in each section protected by the local lock. * * SLUB assigns one slab for allocation to each processor. * Allocations only occur from these slabs called cpu slabs. @@ -2250,9 +2288,13 @@ static inline void note_cmpxchg_failure(const char *n, static void init_kmem_cache_cpus(struct kmem_cache *s) { int cpu; + struct kmem_cache_cpu *c; - for_each_possible_cpu(cpu) - per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu); + for_each_possible_cpu(cpu) { + c = per_cpu_ptr(s->cpu_slab, cpu); + local_lock_init(&c->lock); + c->tid = init_tid(cpu); + } } /* @@ -2463,10 +2505,10 @@ static void unfreeze_partials(struct kmem_cache *s) struct page *partial_page; unsigned long flags; - local_irq_save(flags); + local_lock_irqsave(&s->cpu_slab->lock, flags); partial_page = this_cpu_read(s->cpu_slab->partial); this_cpu_write(s->cpu_slab->partial, NULL); - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); if (partial_page) __unfreeze_partials(s, partial_page); @@ -2499,7 +2541,7 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) int pages = 0; int pobjects = 0; - local_irq_save(flags); + local_lock_irqsave(&s->cpu_slab->lock, flags); oldpage = this_cpu_read(s->cpu_slab->partial); @@ -2527,7 +2569,7 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) this_cpu_write(s->cpu_slab->partial, page); - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); if (page_to_unfreeze) { __unfreeze_partials(s, page_to_unfreeze); @@ -2549,7 +2591,7 @@ static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) struct page *page; void *freelist; - local_irq_save(flags); + local_lock_irqsave(&s->cpu_slab->lock, flags); page = c->page; freelist = c->freelist; @@ -2558,7 +2600,7 @@ static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) c->freelist = NULL; c->tid = next_tid(c->tid); - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); if (page) { deactivate_slab(s, page, freelist); @@ -2780,8 +2822,6 @@ static inline bool pfmemalloc_match_unsafe(struct page *page, gfp_t gfpflags) * The page is still frozen if the return value is not NULL. * * If this function returns NULL then the page has been unfrozen. - * - * This function must be called with interrupt disabled. */ static inline void *get_freelist(struct kmem_cache *s, struct page *page) { @@ -2789,6 +2829,8 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) unsigned long counters; void *freelist; + lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock)); + do { freelist = page->freelist; counters = page->counters; @@ -2873,9 +2915,9 @@ redo: goto deactivate_slab; /* must check again c->page in case we got preempted and it changed */ - local_irq_save(flags); + local_lock_irqsave(&s->cpu_slab->lock, flags); if (unlikely(page != c->page)) { - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); goto reread_page; } freelist = c->freelist; @@ -2886,7 +2928,7 @@ redo: if (!freelist) { c->page = NULL; - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); stat(s, DEACTIVATE_BYPASS); goto new_slab; } @@ -2895,7 +2937,7 @@ redo: load_freelist: - lockdep_assert_irqs_disabled(); + lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock)); /* * freelist is pointing to the list of objects to be used. @@ -2905,39 +2947,39 @@ load_freelist: VM_BUG_ON(!c->page->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); return freelist; deactivate_slab: - local_irq_save(flags); + local_lock_irqsave(&s->cpu_slab->lock, flags); if (page != c->page) { - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); goto reread_page; } freelist = c->freelist; c->page = NULL; c->freelist = NULL; - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); deactivate_slab(s, page, freelist); new_slab: if (slub_percpu_partial(c)) { - local_irq_save(flags); + local_lock_irqsave(&s->cpu_slab->lock, flags); if (unlikely(c->page)) { - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); goto reread_page; } if (unlikely(!slub_percpu_partial(c))) { - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); /* we were preempted and partial list got empty */ goto new_objects; } page = c->page = slub_percpu_partial(c); slub_set_percpu_partial(c, page); - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); stat(s, CPU_PARTIAL_ALLOC); goto redo; } @@ -2990,7 +3032,7 @@ check_new_page: retry_load_page: - local_irq_save(flags); + local_lock_irqsave(&s->cpu_slab->lock, flags); if (unlikely(c->page)) { void *flush_freelist = c->freelist; struct page *flush_page = c->page; @@ -2999,7 +3041,7 @@ retry_load_page: c->freelist = NULL; c->tid = next_tid(c->tid); - local_irq_restore(flags); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); deactivate_slab(s, flush_page, flush_freelist); @@ -3118,7 +3160,15 @@ redo: object = c->freelist; page = c->page; - if (unlikely(!object || !page || !node_match(page, node))) { + /* + * We cannot use the lockless fastpath on PREEMPT_RT because if a + * slowpath has taken the local_lock_irqsave(), it is not protected + * against a fast path operation in an irq handler. So we need to take + * the slow path which uses local_lock. It is still relatively fast if + * there is a suitable cpu freelist. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) || + unlikely(!object || !page || !node_match(page, node))) { object = __slab_alloc(s, gfpflags, node, addr, c); } else { void *next_object = get_freepointer_safe(s, object); @@ -3378,6 +3428,7 @@ redo: barrier(); if (likely(page == c->page)) { +#ifndef CONFIG_PREEMPT_RT void **freelist = READ_ONCE(c->freelist); set_freepointer(s, tail_obj, freelist); @@ -3390,6 +3441,31 @@ redo: note_cmpxchg_failure("slab_free", s, tid); goto redo; } +#else /* CONFIG_PREEMPT_RT */ + /* + * We cannot use the lockless fastpath on PREEMPT_RT because if + * a slowpath has taken the local_lock_irqsave(), it is not + * protected against a fast path operation in an irq handler. So + * we need to take the local_lock. We shouldn't simply defer to + * __slab_free() as that wouldn't use the cpu freelist at all. + */ + void **freelist; + + local_lock(&s->cpu_slab->lock); + c = this_cpu_ptr(s->cpu_slab); + if (unlikely(page != c->page)) { + local_unlock(&s->cpu_slab->lock); + goto redo; + } + tid = c->tid; + freelist = c->freelist; + + set_freepointer(s, tail_obj, freelist); + c->freelist = head; + c->tid = next_tid(tid); + + local_unlock(&s->cpu_slab->lock); +#endif stat(s, FREE_FASTPATH); } else __slab_free(s, page, head, tail_obj, cnt, addr); @@ -3568,7 +3644,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, * handlers invoking normal fastpath. */ c = slub_get_cpu_ptr(s->cpu_slab); - local_irq_disable(); + local_lock_irq(&s->cpu_slab->lock); for (i = 0; i < size; i++) { void *object = kfence_alloc(s, s->object_size, flags); @@ -3589,7 +3665,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, */ c->tid = next_tid(c->tid); - local_irq_enable(); + local_unlock_irq(&s->cpu_slab->lock); /* * Invoking slow path likely have side-effect @@ -3603,7 +3679,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, c = this_cpu_ptr(s->cpu_slab); maybe_wipe_obj_freeptr(s, p[i]); - local_irq_disable(); + local_lock_irq(&s->cpu_slab->lock); continue; /* goto for-loop */ } @@ -3612,7 +3688,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, maybe_wipe_obj_freeptr(s, p[i]); } c->tid = next_tid(c->tid); - local_irq_enable(); + local_unlock_irq(&s->cpu_slab->lock); slub_put_cpu_ptr(s->cpu_slab); /* -- cgit v1.2.3 From 48eab831ae8b9f7002a533fa4235eed63ea1f1a3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 2 Sep 2021 11:10:37 -0700 Subject: net: create netdev->dev_addr assignment helpers Recent work on converting address list to a tree made it obvious we need an abstraction around writing netdev->dev_addr. Without such abstraction updating the main device address is invisible to the core. Introduce a number of helpers which for now just wrap memcpy() but in the future can make necessary changes to the address tree. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 12 ++++++++++++ include/linux/netdevice.h | 18 ++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 330345b1be54..928c411bd509 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -299,6 +299,18 @@ static inline void ether_addr_copy(u8 *dst, const u8 *src) #endif } +/** + * eth_hw_addr_set - Assign Ethernet address to a net_device + * @dev: pointer to net_device structure + * @addr: address to assign + * + * Assign given address to the net_device, addr_assign_type is not changed. + */ +static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr) +{ + ether_addr_copy(dev->dev_addr, addr); +} + /** * eth_hw_addr_inherit - Copy dev_addr from another net_device * @dst: pointer to net_device to copy dev_addr to diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7c41593c1d6a..d79163208dfd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4641,6 +4641,24 @@ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ +static inline void +__dev_addr_set(struct net_device *dev, const u8 *addr, size_t len) +{ + memcpy(dev->dev_addr, addr, len); +} + +static inline void dev_addr_set(struct net_device *dev, const u8 *addr) +{ + __dev_addr_set(dev, addr, dev->addr_len); +} + +static inline void +dev_addr_mod(struct net_device *dev, unsigned int offset, + const u8 *addr, size_t len) +{ + memcpy(&dev->dev_addr[offset], addr, len); +} + int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, -- cgit v1.2.3 From 8486a32dd484a7d7ec25295c7439094608f54915 Mon Sep 17 00:00:00 2001 From: "Hector.Yuan" Date: Fri, 3 Sep 2021 16:39:23 +0800 Subject: cpufreq: Add of_perf_domain_get_sharing_cpumask Add of_perf_domain_get_sharing_cpumask function to group cpu to specific performance domain. Signed-off-by: Hector.Yuan [ Viresh: create separate routine parse_perf_domain() and always set the cpumask. ] Signed-off-by: Viresh Kumar --- include/linux/cpufreq.h | 58 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 57 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c65a1d7385f8..acd3ee5b8b0a 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -14,6 +14,8 @@ #include #include #include +#include +#include #include #include #include @@ -1003,6 +1005,55 @@ static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy return count; } + +static inline int parse_perf_domain(int cpu, const char *list_name, + const char *cell_name) +{ + struct device_node *cpu_np; + struct of_phandle_args args; + int ret; + + cpu_np = of_cpu_device_node_get(cpu); + if (!cpu_np) + return -ENODEV; + + ret = of_parse_phandle_with_args(cpu_np, list_name, cell_name, 0, + &args); + if (ret < 0) + return ret; + + of_node_put(cpu_np); + + return args.args[0]; +} + +static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_name, + const char *cell_name, struct cpumask *cpumask) +{ + int target_idx; + int cpu, ret; + + ret = parse_perf_domain(pcpu, list_name, cell_name); + if (ret < 0) + return ret; + + target_idx = ret; + cpumask_set_cpu(pcpu, cpumask); + + for_each_possible_cpu(cpu) { + if (cpu == pcpu) + continue; + + ret = parse_perf_domain(pcpu, list_name, cell_name); + if (ret < 0) + continue; + + if (target_idx == ret) + cpumask_set_cpu(cpu, cpumask); + } + + return target_idx; +} #else static inline int cpufreq_boost_trigger_state(int state) { @@ -1022,6 +1073,12 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) { return false; } + +static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_name, + const char *cell_name, struct cpumask *cpumask) +{ + return -EOPNOTSUPP; +} #endif #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) @@ -1043,7 +1100,6 @@ void arch_set_freq_scale(const struct cpumask *cpus, { } #endif - /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; -- cgit v1.2.3 From 3cc4e148b96263313e3dce926eae569c942bb74e Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Tue, 17 Aug 2021 00:26:39 +0000 Subject: KVM: stats: Add VM stat for remote tlb flush requests Add a new stat that counts the number of times a remote TLB flush is requested, regardless of whether it kicks vCPUs out of guest mode. This allows us to look at how often flushes are initiated. Unlike remote_tlb_flush, this one applies to ARM's instruction-set-based TLB flush implementation, so apply it there too. Original-by: David Matlack Signed-off-by: Jing Zhang Message-Id: <20210817002639.3856694-1-jingzhangos@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/mmu.c | 1 + include/linux/kvm_host.h | 3 ++- include/linux/kvm_types.h | 1 + virt/kvm/kvm_main.c | 1 + 4 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 0625bf2353c2..f5bb235bbb59 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -80,6 +80,7 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot) */ void kvm_flush_remote_tlbs(struct kvm *kvm) { + ++kvm->stat.generic.remote_tlb_flush_requests; kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e4d712e9f760..c177789a8542 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1444,7 +1444,8 @@ struct _kvm_stats_desc { KVM_STATS_BASE_POW10, -9, sz) #define KVM_GENERIC_VM_STATS() \ - STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush) + STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush), \ + STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush_requests) #define KVM_GENERIC_VCPU_STATS() \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll), \ diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index de7fb5f364d8..2237abb93ccd 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -80,6 +80,7 @@ struct kvm_mmu_memory_cache { struct kvm_vm_stat_generic { u64 remote_tlb_flush; + u64 remote_tlb_flush_requests; }; struct kvm_vcpu_stat_generic { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 140c7d311021..305956310174 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -318,6 +318,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) */ long dirty_count = smp_load_acquire(&kvm->tlbs_dirty); + ++kvm->stat.generic.remote_tlb_flush_requests; /* * We want to publish modifications to the page tables before reading * mode. Pairs with a memory barrier in arch-specific code. -- cgit v1.2.3 From 9c930054f2f5326d59ee4bf8d7d1cf6c82f5643b Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Tue, 31 Aug 2021 18:36:24 +0800 Subject: file: Export receive_fd() to modules Export receive_fd() so that some modules can use it to pass file descriptor between processes without missing any security stuffs. Signed-off-by: Xie Yongji Acked-by: Jason Wang Link: https://lore.kernel.org/r/20210831103634.33-4-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin --- fs/file.c | 6 ++++++ include/linux/file.h | 7 +++---- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/file.c b/fs/file.c index 86dc9956af32..210e540672aa 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1134,6 +1134,12 @@ int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) return new_fd; } +int receive_fd(struct file *file, unsigned int o_flags) +{ + return __receive_fd(file, NULL, o_flags); +} +EXPORT_SYMBOL_GPL(receive_fd); + static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; diff --git a/include/linux/file.h b/include/linux/file.h index 2de2e4613d7b..51e830b4fe3a 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -94,6 +94,9 @@ extern void fd_install(unsigned int fd, struct file *file); extern int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags); + +extern int receive_fd(struct file *file, unsigned int o_flags); + static inline int receive_fd_user(struct file *file, int __user *ufd, unsigned int o_flags) { @@ -101,10 +104,6 @@ static inline int receive_fd_user(struct file *file, int __user *ufd, return -EFAULT; return __receive_fd(file, ufd, o_flags); } -static inline int receive_fd(struct file *file, unsigned int o_flags) -{ - return __receive_fd(file, NULL, o_flags); -} int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags); extern void flush_delayed_fput(void); -- cgit v1.2.3 From 86e17a51c1a5a299009f8b1645e3e9da0d59faae Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Tue, 31 Aug 2021 18:36:25 +0800 Subject: vdpa: Fix some coding style issues Fix some code indent issues and following checkpatch warning: WARNING: Prefer 'unsigned int' to bare use of 'unsigned' 371: FILE: include/linux/vdpa.h:371: +static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, Signed-off-by: Xie Yongji Acked-by: Jason Wang Reviewed-by: Stefano Garzarella Link: https://lore.kernel.org/r/20210831103634.33-5-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 8cfe49d201dd..8ae1134070eb 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -43,17 +43,17 @@ struct vdpa_vq_state_split { * @last_used_idx: used index */ struct vdpa_vq_state_packed { - u16 last_avail_counter:1; - u16 last_avail_idx:15; - u16 last_used_counter:1; - u16 last_used_idx:15; + u16 last_avail_counter:1; + u16 last_avail_idx:15; + u16 last_used_counter:1; + u16 last_used_idx:15; }; struct vdpa_vq_state { - union { - struct vdpa_vq_state_split split; - struct vdpa_vq_state_packed packed; - }; + union { + struct vdpa_vq_state_split split; + struct vdpa_vq_state_packed packed; + }; }; struct vdpa_mgmt_dev; @@ -131,7 +131,7 @@ struct vdpa_iova_range { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) - * @get_vq_notification: Get the notification area for a virtqueue + * @get_vq_notification: Get the notification area for a virtqueue * @vdev: vdpa device * @idx: virtqueue index * Returns the notifcation area @@ -350,25 +350,25 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev) static inline void vdpa_reset(struct vdpa_device *vdev) { - const struct vdpa_config_ops *ops = vdev->config; + const struct vdpa_config_ops *ops = vdev->config; vdev->features_valid = false; - ops->set_status(vdev, 0); + ops->set_status(vdev, 0); } static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) { - const struct vdpa_config_ops *ops = vdev->config; + const struct vdpa_config_ops *ops = vdev->config; vdev->features_valid = true; - return ops->set_features(vdev, features); + return ops->set_features(vdev, features); } - -static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, - void *buf, unsigned int len) +static inline void vdpa_get_config(struct vdpa_device *vdev, + unsigned int offset, void *buf, + unsigned int len) { - const struct vdpa_config_ops *ops = vdev->config; + const struct vdpa_config_ops *ops = vdev->config; /* * Config accesses aren't supposed to trigger before features are set. -- cgit v1.2.3 From 0686082dbf7a204ca0fab326a820779e31666639 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Tue, 31 Aug 2021 18:36:26 +0800 Subject: vdpa: Add reset callback in vdpa_config_ops This adds a new callback to support device specific reset behavior. The vdpa bus driver will call the reset function instead of setting status to zero during resetting. Signed-off-by: Xie Yongji Link: https://lore.kernel.org/r/20210831103634.33-6-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/ifcvf/ifcvf_main.c | 35 +++++++++++++++++++++++----------- drivers/vdpa/mlx5/net/mlx5_vnet.c | 40 +++++++++++++++++++++++---------------- drivers/vdpa/vdpa_sim/vdpa_sim.c | 18 +++++++++++++++--- drivers/vdpa/virtio_pci/vp_vdpa.c | 15 +++++++++++++-- drivers/vhost/vdpa.c | 9 +++++++-- include/linux/vdpa.h | 8 ++++++-- 6 files changed, 89 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index bfc3d7d40c09..4293481ce910 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -222,17 +222,6 @@ static void ifcvf_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status) if (status_old == status) return; - if ((status_old & VIRTIO_CONFIG_S_DRIVER_OK) && - !(status & VIRTIO_CONFIG_S_DRIVER_OK)) { - ifcvf_stop_datapath(adapter); - ifcvf_free_irq(adapter, vf->nr_vring); - } - - if (status == 0) { - ifcvf_reset_vring(adapter); - return; - } - if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) { ret = ifcvf_request_irq(adapter); @@ -252,6 +241,29 @@ static void ifcvf_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status) ifcvf_set_status(vf, status); } +static int ifcvf_vdpa_reset(struct vdpa_device *vdpa_dev) +{ + struct ifcvf_adapter *adapter; + struct ifcvf_hw *vf; + u8 status_old; + + vf = vdpa_to_vf(vdpa_dev); + adapter = vdpa_to_adapter(vdpa_dev); + status_old = ifcvf_get_status(vf); + + if (status_old == 0) + return 0; + + if (status_old & VIRTIO_CONFIG_S_DRIVER_OK) { + ifcvf_stop_datapath(adapter); + ifcvf_free_irq(adapter, vf->nr_vring); + } + + ifcvf_reset_vring(adapter); + + return 0; +} + static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev) { return IFCVF_QUEUE_MAX; @@ -435,6 +447,7 @@ static const struct vdpa_config_ops ifc_vdpa_ops = { .set_features = ifcvf_vdpa_set_features, .get_status = ifcvf_vdpa_get_status, .set_status = ifcvf_vdpa_set_status, + .reset = ifcvf_vdpa_reset, .get_vq_num_max = ifcvf_vdpa_get_vq_num_max, .get_vq_state = ifcvf_vdpa_get_vq_state, .set_vq_state = ifcvf_vdpa_set_vq_state, diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 4ba3ac48ee83..608f6b900cd9 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2154,22 +2154,6 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) int err; print_status(mvdev, status, true); - if (!status) { - mlx5_vdpa_info(mvdev, "performing device reset\n"); - teardown_driver(ndev); - clear_vqs_ready(ndev); - mlx5_vdpa_destroy_mr(&ndev->mvdev); - ndev->mvdev.status = 0; - ndev->mvdev.mlx_features = 0; - memset(ndev->event_cbs, 0, sizeof(ndev->event_cbs)); - ndev->mvdev.actual_features = 0; - ++mvdev->generation; - if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) { - if (mlx5_vdpa_create_mr(mvdev, NULL)) - mlx5_vdpa_warn(mvdev, "create MR failed\n"); - } - return; - } if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) { if (status & VIRTIO_CONFIG_S_DRIVER_OK) { @@ -2192,6 +2176,29 @@ err_setup: ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED; } +static int mlx5_vdpa_reset(struct vdpa_device *vdev) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + + print_status(mvdev, 0, true); + mlx5_vdpa_info(mvdev, "performing device reset\n"); + teardown_driver(ndev); + clear_vqs_ready(ndev); + mlx5_vdpa_destroy_mr(&ndev->mvdev); + ndev->mvdev.status = 0; + ndev->mvdev.mlx_features = 0; + memset(ndev->event_cbs, 0, sizeof(ndev->event_cbs)); + ndev->mvdev.actual_features = 0; + ++mvdev->generation; + if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) { + if (mlx5_vdpa_create_mr(mvdev, NULL)) + mlx5_vdpa_warn(mvdev, "create MR failed\n"); + } + + return 0; +} + static size_t mlx5_vdpa_get_config_size(struct vdpa_device *vdev) { return sizeof(struct virtio_net_config); @@ -2305,6 +2312,7 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = { .get_vendor_id = mlx5_vdpa_get_vendor_id, .get_status = mlx5_vdpa_get_status, .set_status = mlx5_vdpa_set_status, + .reset = mlx5_vdpa_reset, .get_config_size = mlx5_vdpa_get_config_size, .get_config = mlx5_vdpa_get_config, .set_config = mlx5_vdpa_set_config, diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 5b51d0ac8bae..f292bb05d6c9 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -92,7 +92,7 @@ static void vdpasim_vq_reset(struct vdpasim *vdpasim, vq->vring.notify = NULL; } -static void vdpasim_reset(struct vdpasim *vdpasim) +static void vdpasim_do_reset(struct vdpasim *vdpasim) { int i; @@ -460,11 +460,21 @@ static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status) spin_lock(&vdpasim->lock); vdpasim->status = status; - if (status == 0) - vdpasim_reset(vdpasim); spin_unlock(&vdpasim->lock); } +static int vdpasim_reset(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + spin_lock(&vdpasim->lock); + vdpasim->status = 0; + vdpasim_do_reset(vdpasim); + spin_unlock(&vdpasim->lock); + + return 0; +} + static size_t vdpasim_get_config_size(struct vdpa_device *vdpa) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); @@ -608,6 +618,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .get_vendor_id = vdpasim_get_vendor_id, .get_status = vdpasim_get_status, .set_status = vdpasim_set_status, + .reset = vdpasim_reset, .get_config_size = vdpasim_get_config_size, .get_config = vdpasim_get_config, .set_config = vdpasim_set_config, @@ -636,6 +647,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = { .get_vendor_id = vdpasim_get_vendor_id, .get_status = vdpasim_get_status, .set_status = vdpasim_set_status, + .reset = vdpasim_reset, .get_config_size = vdpasim_get_config_size, .get_config = vdpasim_get_config, .set_config = vdpasim_set_config, diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index fe0527329857..cd7718b43a6e 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -189,10 +189,20 @@ static void vp_vdpa_set_status(struct vdpa_device *vdpa, u8 status) } vp_modern_set_status(mdev, status); +} - if (!(status & VIRTIO_CONFIG_S_DRIVER_OK) && - (s & VIRTIO_CONFIG_S_DRIVER_OK)) +static int vp_vdpa_reset(struct vdpa_device *vdpa) +{ + struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa); + struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev; + u8 s = vp_vdpa_get_status(vdpa); + + vp_modern_set_status(mdev, 0); + + if (s & VIRTIO_CONFIG_S_DRIVER_OK) vp_vdpa_free_irq(vp_vdpa); + + return 0; } static u16 vp_vdpa_get_vq_num_max(struct vdpa_device *vdpa) @@ -398,6 +408,7 @@ static const struct vdpa_config_ops vp_vdpa_ops = { .set_features = vp_vdpa_set_features, .get_status = vp_vdpa_get_status, .set_status = vp_vdpa_set_status, + .reset = vp_vdpa_reset, .get_vq_num_max = vp_vdpa_get_vq_num_max, .get_vq_state = vp_vdpa_get_vq_state, .get_vq_notification = vp_vdpa_get_vq_notification, diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 42c998c82102..5562258f6238 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -157,7 +157,7 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; u8 status, status_old; - int nvqs = v->nvqs; + int ret, nvqs = v->nvqs; u16 i; if (copy_from_user(&status, statusp, sizeof(status))) @@ -172,7 +172,12 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) if (status != 0 && (ops->get_status(vdpa) & ~status) != 0) return -EINVAL; - ops->set_status(vdpa, status); + if (status == 0) { + ret = ops->reset(vdpa); + if (ret) + return ret; + } else + ops->set_status(vdpa, status); if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) for (i = 0; i < nvqs; i++) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 8ae1134070eb..e1eae8c7483d 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -171,6 +171,9 @@ struct vdpa_iova_range { * @set_status: Set the device status * @vdev: vdpa device * @status: virtio device status + * @reset: Reset device + * @vdev: vdpa device + * Returns integer: success (0) or error (< 0) * @get_config_size: Get the size of the configuration space * @vdev: vdpa device * Returns size_t: configuration size @@ -255,6 +258,7 @@ struct vdpa_config_ops { u32 (*get_vendor_id)(struct vdpa_device *vdev); u8 (*get_status)(struct vdpa_device *vdev); void (*set_status)(struct vdpa_device *vdev, u8 status); + int (*reset)(struct vdpa_device *vdev); size_t (*get_config_size)(struct vdpa_device *vdev); void (*get_config)(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); @@ -348,12 +352,12 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev) return vdev->dma_dev; } -static inline void vdpa_reset(struct vdpa_device *vdev) +static inline int vdpa_reset(struct vdpa_device *vdev) { const struct vdpa_config_ops *ops = vdev->config; vdev->features_valid = false; - ops->set_status(vdev, 0); + return ops->reset(vdev); } static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) -- cgit v1.2.3 From 59dfe4f1e810b5820443c84f9863b04b033143e8 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Tue, 31 Aug 2021 18:36:28 +0800 Subject: vhost-iotlb: Add an opaque pointer for vhost IOTLB Add an opaque pointer for vhost IOTLB. And introduce vhost_iotlb_add_range_ctx() to accept it. Suggested-by: Jason Wang Signed-off-by: Xie Yongji Acked-by: Jason Wang Link: https://lore.kernel.org/r/20210831103634.33-8-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin --- drivers/vhost/iotlb.c | 20 ++++++++++++++++---- include/linux/vhost_iotlb.h | 3 +++ 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c index 0582079e4bcc..670d56c879e5 100644 --- a/drivers/vhost/iotlb.c +++ b/drivers/vhost/iotlb.c @@ -36,19 +36,21 @@ void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, EXPORT_SYMBOL_GPL(vhost_iotlb_map_free); /** - * vhost_iotlb_add_range - add a new range to vhost IOTLB + * vhost_iotlb_add_range_ctx - add a new range to vhost IOTLB * @iotlb: the IOTLB * @start: start of the IOVA range * @last: last of IOVA range * @addr: the address that is mapped to @start * @perm: access permission of this range + * @opaque: the opaque pointer for the new mapping * * Returns an error last is smaller than start or memory allocation * fails */ -int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, - u64 start, u64 last, - u64 addr, unsigned int perm) +int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, + u64 start, u64 last, + u64 addr, unsigned int perm, + void *opaque) { struct vhost_iotlb_map *map; @@ -71,6 +73,7 @@ int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, map->last = last; map->addr = addr; map->perm = perm; + map->opaque = opaque; iotlb->nmaps++; vhost_iotlb_itree_insert(map, &iotlb->root); @@ -80,6 +83,15 @@ int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, return 0; } +EXPORT_SYMBOL_GPL(vhost_iotlb_add_range_ctx); + +int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, + u64 start, u64 last, + u64 addr, unsigned int perm) +{ + return vhost_iotlb_add_range_ctx(iotlb, start, last, + addr, perm, NULL); +} EXPORT_SYMBOL_GPL(vhost_iotlb_add_range); /** diff --git a/include/linux/vhost_iotlb.h b/include/linux/vhost_iotlb.h index 6b09b786a762..2d0e2f52f938 100644 --- a/include/linux/vhost_iotlb.h +++ b/include/linux/vhost_iotlb.h @@ -17,6 +17,7 @@ struct vhost_iotlb_map { u32 perm; u32 flags_padding; u64 __subtree_last; + void *opaque; }; #define VHOST_IOTLB_FLAG_RETIRE 0x1 @@ -29,6 +30,8 @@ struct vhost_iotlb { unsigned int flags; }; +int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, u64 start, u64 last, + u64 addr, unsigned int perm, void *opaque); int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last, u64 addr, unsigned int perm); void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last); -- cgit v1.2.3 From c10fb9454adc80c062151c6a436047e1fa59e99f Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Tue, 31 Aug 2021 18:36:29 +0800 Subject: vdpa: Add an opaque pointer for vdpa_config_ops.dma_map() Add an opaque pointer for DMA mapping. Suggested-by: Jason Wang Signed-off-by: Xie Yongji Acked-by: Jason Wang Link: https://lore.kernel.org/r/20210831103634.33-9-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 6 +++--- drivers/vhost/vdpa.c | 2 +- include/linux/vdpa.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index f292bb05d6c9..a70fd2a08ff1 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -555,14 +555,14 @@ err: } static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size, - u64 pa, u32 perm) + u64 pa, u32 perm, void *opaque) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); int ret; spin_lock(&vdpasim->iommu_lock); - ret = vhost_iotlb_add_range(vdpasim->iommu, iova, iova + size - 1, pa, - perm); + ret = vhost_iotlb_add_range_ctx(vdpasim->iommu, iova, iova + size - 1, + pa, perm, opaque); spin_unlock(&vdpasim->iommu_lock); return ret; diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 86fb8d9ce409..5eb2fcc59532 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -571,7 +571,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, return r; if (ops->dma_map) { - r = ops->dma_map(vdpa, iova, size, pa, perm); + r = ops->dma_map(vdpa, iova, size, pa, perm, NULL); } else if (ops->set_map) { if (!v->in_batch) r = ops->set_map(vdpa, dev->iotlb); diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index e1eae8c7483d..f3014aaca47e 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -270,7 +270,7 @@ struct vdpa_config_ops { /* DMA ops */ int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb); int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size, - u64 pa, u32 perm); + u64 pa, u32 perm, void *opaque); int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size); /* Free device resources */ -- cgit v1.2.3 From d8945ec411209272bcd4ae9e75ea1b078257e492 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Tue, 31 Aug 2021 18:36:31 +0800 Subject: vdpa: Support transferring virtual addressing during DMA mapping This patch introduces an attribute for vDPA device to indicate whether virtual address can be used. If vDPA device driver set it, vhost-vdpa bus driver will not pin user page and transfer userspace virtual address instead of physical address during DMA mapping. And corresponding vma->vm_file and offset will be also passed as an opaque pointer. Suggested-by: Jason Wang Signed-off-by: Xie Yongji Acked-by: Jason Wang Link: https://lore.kernel.org/r/20210831103634.33-11-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/ifcvf/ifcvf_main.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 +- drivers/vdpa/vdpa.c | 9 +++- drivers/vdpa/vdpa_sim/vdpa_sim.c | 2 +- drivers/vdpa/virtio_pci/vp_vdpa.c | 2 +- drivers/vhost/vdpa.c | 99 ++++++++++++++++++++++++++++++++++----- include/linux/vdpa.h | 20 ++++++-- 7 files changed, 117 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index 4293481ce910..dcd648e1f7e7 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -515,7 +515,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name) pdev = ifcvf_mgmt_dev->pdev; dev = &pdev->dev; adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, - dev, &ifc_vdpa_ops, name); + dev, &ifc_vdpa_ops, name, false); if (IS_ERR(adapter)) { IFCVF_ERR(pdev, "Failed to allocate vDPA structure"); return PTR_ERR(adapter); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 608f6b900cd9..08f39952fa6a 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2425,7 +2425,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS); ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, - name); + name, false); if (IS_ERR(ndev)) return PTR_ERR(ndev); diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index bb3f1d1f0422..8f01d6a7ecc5 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -71,6 +71,7 @@ static void vdpa_release_dev(struct device *d) * @config: the bus operations that is supported by this device * @size: size of the parent structure that contains private data * @name: name of the vdpa device; optional. + * @use_va: indicate whether virtual address must be used by this device * * Driver should use vdpa_alloc_device() wrapper macro instead of * using this directly. @@ -80,7 +81,8 @@ static void vdpa_release_dev(struct device *d) */ struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - size_t size, const char *name) + size_t size, const char *name, + bool use_va) { struct vdpa_device *vdev; int err = -EINVAL; @@ -91,6 +93,10 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, if (!!config->dma_map != !!config->dma_unmap) goto err; + /* It should only work for the device that use on-chip IOMMU */ + if (use_va && !(config->dma_map || config->set_map)) + goto err; + err = -ENOMEM; vdev = kzalloc(size, GFP_KERNEL); if (!vdev) @@ -106,6 +112,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->index = err; vdev->config = config; vdev->features_valid = false; + vdev->use_va = use_va; if (name) err = dev_set_name(&vdev->dev, "%s", name); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index a70fd2a08ff1..5f484fff8dbe 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -251,7 +251,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) ops = &vdpasim_config_ops; vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, - dev_attr->name); + dev_attr->name, false); if (IS_ERR(vdpasim)) { ret = PTR_ERR(vdpasim); goto err_alloc; diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index cd7718b43a6e..5bcd00246d2e 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -446,7 +446,7 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) return ret; vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa, - dev, &vp_vdpa_ops, NULL); + dev, &vp_vdpa_ops, NULL, false); if (IS_ERR(vp_vdpa)) { dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n"); return PTR_ERR(vp_vdpa); diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index ad50d52d6655..f41d081777f5 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -526,8 +526,28 @@ static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, u64 start, u64 last) } } +static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, u64 start, u64 last) +{ + struct vhost_dev *dev = &v->vdev; + struct vhost_iotlb *iotlb = dev->iotlb; + struct vhost_iotlb_map *map; + struct vdpa_map_file *map_file; + + while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) { + map_file = (struct vdpa_map_file *)map->opaque; + fput(map_file->file); + kfree(map_file); + vhost_iotlb_map_free(iotlb, map); + } +} + static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last) { + struct vdpa_device *vdpa = v->vdpa; + + if (vdpa->use_va) + return vhost_vdpa_va_unmap(v, start, last); + return vhost_vdpa_pa_unmap(v, start, last); } @@ -562,21 +582,21 @@ static int perm_to_iommu_flags(u32 perm) return flags | IOMMU_CACHE; } -static int vhost_vdpa_map(struct vhost_vdpa *v, - u64 iova, u64 size, u64 pa, u32 perm) +static int vhost_vdpa_map(struct vhost_vdpa *v, u64 iova, + u64 size, u64 pa, u32 perm, void *opaque) { struct vhost_dev *dev = &v->vdev; struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; int r = 0; - r = vhost_iotlb_add_range(dev->iotlb, iova, iova + size - 1, - pa, perm); + r = vhost_iotlb_add_range_ctx(dev->iotlb, iova, iova + size - 1, + pa, perm, opaque); if (r) return r; if (ops->dma_map) { - r = ops->dma_map(vdpa, iova, size, pa, perm, NULL); + r = ops->dma_map(vdpa, iova, size, pa, perm, opaque); } else if (ops->set_map) { if (!v->in_batch) r = ops->set_map(vdpa, dev->iotlb); @@ -584,13 +604,15 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, r = iommu_map(v->domain, iova, pa, size, perm_to_iommu_flags(perm)); } - - if (r) + if (r) { vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1); - else + return r; + } + + if (!vdpa->use_va) atomic64_add(PFN_DOWN(size), &dev->mm->pinned_vm); - return r; + return 0; } static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size) @@ -611,6 +633,56 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size) } } +static int vhost_vdpa_va_map(struct vhost_vdpa *v, + u64 iova, u64 size, u64 uaddr, u32 perm) +{ + struct vhost_dev *dev = &v->vdev; + u64 offset, map_size, map_iova = iova; + struct vdpa_map_file *map_file; + struct vm_area_struct *vma; + int ret; + + mmap_read_lock(dev->mm); + + while (size) { + vma = find_vma(dev->mm, uaddr); + if (!vma) { + ret = -EINVAL; + break; + } + map_size = min(size, vma->vm_end - uaddr); + if (!(vma->vm_file && (vma->vm_flags & VM_SHARED) && + !(vma->vm_flags & (VM_IO | VM_PFNMAP)))) + goto next; + + map_file = kzalloc(sizeof(*map_file), GFP_KERNEL); + if (!map_file) { + ret = -ENOMEM; + break; + } + offset = (vma->vm_pgoff << PAGE_SHIFT) + uaddr - vma->vm_start; + map_file->offset = offset; + map_file->file = get_file(vma->vm_file); + ret = vhost_vdpa_map(v, map_iova, map_size, uaddr, + perm, map_file); + if (ret) { + fput(map_file->file); + kfree(map_file); + break; + } +next: + size -= map_size; + uaddr += map_size; + map_iova += map_size; + } + if (ret) + vhost_vdpa_unmap(v, iova, map_iova - iova); + + mmap_read_unlock(dev->mm); + + return ret; +} + static int vhost_vdpa_pa_map(struct vhost_vdpa *v, u64 iova, u64 size, u64 uaddr, u32 perm) { @@ -677,7 +749,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v, csize = PFN_PHYS(last_pfn - map_pfn + 1); ret = vhost_vdpa_map(v, iova, csize, PFN_PHYS(map_pfn), - perm); + perm, NULL); if (ret) { /* * Unpin the pages that are left unmapped @@ -706,7 +778,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v, /* Pin the rest chunk */ ret = vhost_vdpa_map(v, iova, PFN_PHYS(last_pfn - map_pfn + 1), - PFN_PHYS(map_pfn), perm); + PFN_PHYS(map_pfn), perm, NULL); out: if (ret) { if (nchunks) { @@ -739,6 +811,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, struct vhost_iotlb_msg *msg) { struct vhost_dev *dev = &v->vdev; + struct vdpa_device *vdpa = v->vdpa; struct vhost_iotlb *iotlb = dev->iotlb; if (msg->iova < v->range.first || !msg->size || @@ -750,6 +823,10 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, msg->iova + msg->size - 1)) return -EEXIST; + if (vdpa->use_va) + return vhost_vdpa_va_map(v, msg->iova, msg->size, + msg->uaddr, msg->perm); + return vhost_vdpa_pa_map(v, msg->iova, msg->size, msg->uaddr, msg->perm); } diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index f3014aaca47e..3972ab765de1 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -65,6 +65,7 @@ struct vdpa_mgmt_dev; * @config: the configuration ops for this device. * @index: device index * @features_valid: were features initialized? for legacy guests + * @use_va: indicate whether virtual address must be used by this device * @nvqs: maximum number of supported virtqueues * @mdev: management device pointer; caller must setup when registering device as part * of dev_add() mgmtdev ops callback before invoking _vdpa_register_device(). @@ -75,6 +76,7 @@ struct vdpa_device { const struct vdpa_config_ops *config; unsigned int index; bool features_valid; + bool use_va; int nvqs; struct vdpa_mgmt_dev *mdev; }; @@ -89,6 +91,16 @@ struct vdpa_iova_range { u64 last; }; +/** + * Corresponding file area for device memory mapping + * @file: vma->vm_file for the mapping + * @offset: mapping offset in the vm_file + */ +struct vdpa_map_file { + struct file *file; + u64 offset; +}; + /** * struct vdpa_config_ops - operations for configuring a vDPA device. * Note: vDPA device drivers are required to implement all of the @@ -279,7 +291,8 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - size_t size, const char *name); + size_t size, const char *name, + bool use_va); /** * vdpa_alloc_device - allocate and initilaize a vDPA device @@ -289,15 +302,16 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, * @parent: the parent device * @config: the bus operations that is supported by this device * @name: name of the vdpa device + * @use_va: indicate whether virtual address must be used by this device * * Return allocated data structure or ERR_PTR upon error */ -#define vdpa_alloc_device(dev_struct, member, parent, config, name) \ +#define vdpa_alloc_device(dev_struct, member, parent, config, name, use_va) \ container_of(__vdpa_alloc_device( \ parent, config, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name), \ + dev_struct, member)), name, use_va), \ dev_struct, member) int vdpa_register_device(struct vdpa_device *vdev, int nvqs); -- cgit v1.2.3 From f97493657c6372eeefe70faadd214bf31488c44e Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 7 Sep 2021 18:56:46 +0800 Subject: net: phylink: add suspend/resume support Joakim Zhang reports that Wake-on-Lan with the stmmac ethernet driver broke when moving the incorrect handling of mac link state out of mac_config(). This reason this breaks is because the stmmac's WoL is handled by the MAC rather than the PHY, and phylink doesn't cater for that scenario. This patch adds the necessary phylink code to handle suspend/resume events according to whether the MAC still needs a valid link or not. This is the barest minimum for this support. Reported-by: Joakim Zhang Tested-by: Joakim Zhang Signed-off-by: Russell King (Oracle) Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/phylink.h | 3 ++ 2 files changed, 85 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 2cdf9f989dec..a1464b764d4d 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -33,6 +33,7 @@ enum { PHYLINK_DISABLE_STOPPED, PHYLINK_DISABLE_LINK, + PHYLINK_DISABLE_MAC_WOL, }; /** @@ -1282,6 +1283,9 @@ EXPORT_SYMBOL_GPL(phylink_start); * network device driver's &struct net_device_ops ndo_stop() method. The * network device's carrier state should not be changed prior to calling this * function. + * + * This will synchronously bring down the link if the link is not already + * down (in other words, it will trigger a mac_link_down() method call.) */ void phylink_stop(struct phylink *pl) { @@ -1301,6 +1305,84 @@ void phylink_stop(struct phylink *pl) } EXPORT_SYMBOL_GPL(phylink_stop); +/** + * phylink_suspend() - handle a network device suspend event + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @mac_wol: true if the MAC needs to receive packets for Wake-on-Lan + * + * Handle a network device suspend event. There are several cases: + * - If Wake-on-Lan is not active, we can bring down the link between + * the MAC and PHY by calling phylink_stop(). + * - If Wake-on-Lan is active, and being handled only by the PHY, we + * can also bring down the link between the MAC and PHY. + * - If Wake-on-Lan is active, but being handled by the MAC, the MAC + * still needs to receive packets, so we can not bring the link down. + */ +void phylink_suspend(struct phylink *pl, bool mac_wol) +{ + ASSERT_RTNL(); + + if (mac_wol && (!pl->netdev || pl->netdev->wol_enabled)) { + /* Wake-on-Lan enabled, MAC handling */ + mutex_lock(&pl->state_mutex); + + /* Stop the resolver bringing the link up */ + __set_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state); + + /* Disable the carrier, to prevent transmit timeouts, + * but one would hope all packets have been sent. This + * also means phylink_resolve() will do nothing. + */ + netif_carrier_off(pl->netdev); + + /* We do not call mac_link_down() here as we want the + * link to remain up to receive the WoL packets. + */ + mutex_unlock(&pl->state_mutex); + } else { + phylink_stop(pl); + } +} +EXPORT_SYMBOL_GPL(phylink_suspend); + +/** + * phylink_resume() - handle a network device resume event + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * Undo the effects of phylink_suspend(), returning the link to an + * operational state. + */ +void phylink_resume(struct phylink *pl) +{ + ASSERT_RTNL(); + + if (test_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state)) { + /* Wake-on-Lan enabled, MAC handling */ + + /* Call mac_link_down() so we keep the overall state balanced. + * Do this under the state_mutex lock for consistency. This + * will cause a "Link Down" message to be printed during + * resume, which is harmless - the true link state will be + * printed when we run a resolve. + */ + mutex_lock(&pl->state_mutex); + phylink_link_down(pl); + mutex_unlock(&pl->state_mutex); + + /* Re-apply the link parameters so that all the settings get + * restored to the MAC. + */ + phylink_mac_initial_config(pl, true); + + /* Re-enable and re-resolve the link parameters */ + clear_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state); + phylink_run_resolve(pl); + } else { + phylink_start(pl); + } +} +EXPORT_SYMBOL_GPL(phylink_resume); + /** * phylink_ethtool_get_wol() - get the wake on lan parameters for the PHY * @pl: a pointer to a &struct phylink returned from phylink_create() diff --git a/include/linux/phylink.h b/include/linux/phylink.h index afb3ded0b691..237291196ce2 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -451,6 +451,9 @@ void phylink_mac_change(struct phylink *, bool up); void phylink_start(struct phylink *); void phylink_stop(struct phylink *); +void phylink_suspend(struct phylink *pl, bool mac_wol); +void phylink_resume(struct phylink *pl); + void phylink_ethtool_get_wol(struct phylink *, struct ethtool_wolinfo *); int phylink_ethtool_set_wol(struct phylink *, struct ethtool_wolinfo *); -- cgit v1.2.3 From cd1adf1b63a112d762832e9c64b0a886fbb840d6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 7 Sep 2021 11:03:45 -0700 Subject: Revert "mm/gup: remove try_get_page(), call try_get_compound_head() directly" This reverts commit 9857a17f206ff374aea78bccfb687f145368be2e. That commit was completely broken, and I should have caught on to it earlier. But happily, the kernel test robot noticed the breakage fairly quickly. The breakage is because "try_get_page()" is about avoiding the page reference count overflow case, but is otherwise the exact same as a plain "get_page()". In contrast, "try_get_compound_head()" is an entirely different beast, and uses __page_cache_add_speculative() because it's not just about the page reference count, but also about possibly racing with the underlying page going away. So all the commentary about how "try_get_page() has fallen a little behind in terms of maintenance, try_get_compound_head() handles speculative page references more thoroughly" was just completely wrong: yes, try_get_compound_head() handles speculative page references, but the point is that try_get_page() does not, and must not. So there's no lack of maintainance - there are fundamentally different semantics. A speculative page reference would be entirely wrong in "get_page()", and it's entirely wrong in "try_get_page()". It's not about speculation, it's purely about "uhhuh, you can't get this page because you've tried to increment the reference count too much already". The reason the kernel test robot noticed this bug was that it hit the VM_BUG_ON() in __page_cache_add_speculative(), which is all about verifying that the context of any speculative page access is correct. But since that isn't what try_get_page() is all about, the VM_BUG_ON() tests things that are not correct to test for try_get_page(). Reported-by: kernel test robot Cc: John Hubbard Cc: Christoph Hellwig Cc: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/mm/fault.c | 2 +- fs/pipe.c | 2 +- include/linux/mm.h | 10 +++++++++- mm/gup.c | 21 ++++----------------- 4 files changed, 15 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index a834e4672f72..212632d57db9 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -822,7 +822,7 @@ void do_secure_storage_access(struct pt_regs *regs) break; case KERNEL_FAULT: page = phys_to_page(addr); - if (unlikely(!try_get_compound_head(page, 1))) + if (unlikely(!try_get_page(page))) break; rc = arch_make_page_accessible(page); put_page(page); diff --git a/fs/pipe.c b/fs/pipe.c index 1fa1f52763f0..6d4342bad9f1 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -191,7 +191,7 @@ EXPORT_SYMBOL(generic_pipe_buf_try_steal); */ bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - return try_get_compound_head(buf->page, 1); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); diff --git a/include/linux/mm.h b/include/linux/mm.h index 50e2c2914ac2..73a52aba448f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1218,7 +1218,15 @@ bool __must_check try_grab_page(struct page *page, unsigned int flags); struct page *try_grab_compound_head(struct page *page, int refs, unsigned int flags); -struct page *try_get_compound_head(struct page *page, int refs); + +static inline __must_check bool try_get_page(struct page *page) +{ + page = compound_head(page); + if (WARN_ON_ONCE(page_ref_count(page) <= 0)) + return false; + page_ref_inc(page); + return true; +} static inline void put_page(struct page *page) { diff --git a/mm/gup.c b/mm/gup.c index 9935a4480710..886d6148d3d0 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -62,24 +62,11 @@ static void put_page_refs(struct page *page, int refs) put_page(page); } -/** - * try_get_compound_head() - return the compound head page with refcount - * appropriately incremented, or NULL if that failed. - * - * This handles potential refcount overflow correctly. It also works correctly - * for various lockless get_user_pages()-related callers, due to the use of - * page_cache_add_speculative(). - * - * Even though the name includes "compound_head", this function is still - * appropriate for callers that have a non-compound @page to get. - * - * @page: pointer to page to be gotten - * @refs: the value to add to the page's refcount - * - * Return: head page (with refcount appropriately incremented) for success, or - * NULL upon failure. +/* + * Return the compound head page with ref appropriately incremented, + * or NULL if that failed. */ -struct page *try_get_compound_head(struct page *page, int refs) +static inline struct page *try_get_compound_head(struct page *page, int refs) { struct page *head = compound_head(page); -- cgit v1.2.3 From ca67408ad57a5a67ad6801d792c40c010451bdef Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Mon, 6 Sep 2021 09:44:52 +0100 Subject: PM: EM: fix kernel-doc comments Fix the kernel-doc comments for the improved Energy Model documentation. Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 1834752c5617..39dcadd492b5 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -11,7 +11,7 @@ #include /** - * em_perf_state - Performance state of a performance domain + * struct em_perf_state - Performance state of a performance domain * @frequency: The frequency in KHz, for consistency with CPUFreq * @power: The power consumed at this level (by 1 CPU or by a registered * device). It can be a total power: static and dynamic. @@ -25,7 +25,7 @@ struct em_perf_state { }; /** - * em_perf_domain - Performance domain + * struct em_perf_domain - Performance domain * @table: List of performance states, in ascending order * @nr_perf_states: Number of performance states * @milliwatts: Flag indicating the power values are in milli-Watts @@ -103,12 +103,12 @@ void em_dev_unregister_perf_domain(struct device *dev); /** * em_cpu_energy() - Estimates the energy consumed by the CPUs of a - performance domain + * performance domain * @pd : performance domain for which energy has to be estimated * @max_util : highest utilization among CPUs of the domain * @sum_util : sum of the utilization of all CPUs in the domain * @allowed_cpu_cap : maximum allowed CPU capacity for the @pd, which - might reflect reduced frequency (due to thermal) + * might reflect reduced frequency (due to thermal) * * This function must be used only for CPU devices. There is no validation, * i.e. if the EM is a CPU type and has cpumask allocated. It is called from -- cgit v1.2.3 From 39ff83f2f6cc5cc1458dfcea9697f96338210beb Mon Sep 17 00:00:00 2001 From: Lukas Hannen Date: Wed, 25 Aug 2021 10:12:43 +0000 Subject: time: Handle negative seconds correctly in timespec64_to_ns() timespec64_ns() prevents multiplication overflows by comparing the seconds value of the timespec to KTIME_SEC_MAX. If the value is greater or equal it returns KTIME_MAX. But that check casts the signed seconds value to unsigned which makes the comparision true for all negative values and therefore return wrongly KTIME_MAX. Negative second values are perfectly valid and required in some places, e.g. ptp_clock_adjtime(). Remove the cast and add a check for the negative boundary which is required to prevent undefined behaviour due to multiplication underflow. Fixes: cb47755725da ("time: Prevent undefined behaviour in timespec64_to_ns()")' Signed-off-by: Lukas Hannen Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/AM6PR01MB541637BD6F336B8FFB72AF80EEC69@AM6PR01MB5416.eurprd01.prod.exchangelabs.com --- include/linux/time64.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time64.h b/include/linux/time64.h index 5117cb5b5656..81b9686a2079 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -25,7 +25,9 @@ struct itimerspec64 { #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) +#define KTIME_MIN (-KTIME_MAX - 1) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) +#define KTIME_SEC_MIN (KTIME_MIN / NSEC_PER_SEC) /* * Limits for settimeofday(): @@ -124,10 +126,13 @@ static inline bool timespec64_valid_settod(const struct timespec64 *ts) */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { - /* Prevent multiplication overflow */ - if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) + /* Prevent multiplication overflow / underflow */ + if (ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; + if (ts->tv_sec <= KTIME_SEC_MIN) + return KTIME_MIN; + return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } -- cgit v1.2.3 From 859a85ddf90e714092dea71a0e54c7b9896621be Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 7 Sep 2021 19:54:52 -0700 Subject: mm: remove pfn_valid_within() and CONFIG_HOLES_IN_ZONE Patch series "mm: remove pfn_valid_within() and CONFIG_HOLES_IN_ZONE". After recent updates to freeing unused parts of the memory map, no architecture can have holes in the memory map within a pageblock. This makes pfn_valid_within() check and CONFIG_HOLES_IN_ZONE configuration option redundant. The first patch removes them both in a mechanical way and the second patch simplifies memory_hotplug::test_pages_in_a_zone() that had pfn_valid_within() surrounded by more logic than simple if. This patch (of 2): After recent changes in freeing of the unused parts of the memory map and rework of pfn_valid() in arm and arm64 there are no architectures that can have holes in the memory map within a pageblock and so nothing can enable CONFIG_HOLES_IN_ZONE which guards non trivial implementation of pfn_valid_within(). With that, pfn_valid_within() is always hardwired to 1 and can be completely removed. Remove calls to pfn_valid_within() and CONFIG_HOLES_IN_ZONE. Link: https://lkml.kernel.org/r/20210713080035.7464-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20210713080035.7464-2-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 2 -- include/linux/mmzone.h | 12 ------------ mm/Kconfig | 3 --- mm/compaction.c | 20 +++++++------------- mm/memory_hotplug.c | 4 ---- mm/page_alloc.c | 24 ++---------------------- mm/page_isolation.c | 7 +------ mm/page_owner.c | 14 +------------- 8 files changed, 11 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/node.c b/drivers/base/node.c index 4a4ae868ad9f..8ec6b7dfbb0f 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -768,8 +768,6 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static int __ref get_nid_for_pfn(unsigned long pfn) { - if (!pfn_valid_within(pfn)) - return -1; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT if (system_state < SYSTEM_RUNNING) return early_pfn_to_nid(pfn); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fcb535560028..ee3a86830519 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1525,18 +1525,6 @@ void sparse_init(void); #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ -/* - * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we - * need to check pfn validity within that MAX_ORDER_NR_PAGES block. - * pfn_valid_within() should be used in this case; we optimise this away - * when we have no holes within a MAX_ORDER_NR_PAGES block. - */ -#ifdef CONFIG_HOLES_IN_ZONE -#define pfn_valid_within(pfn) pfn_valid(pfn) -#else -#define pfn_valid_within(pfn) (1) -#endif - #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ diff --git a/mm/Kconfig b/mm/Kconfig index 40a9bfcd5062..14d5d2837737 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -96,9 +96,6 @@ config HAVE_FAST_GUP depends on MMU bool -config HOLES_IN_ZONE - bool - # Don't discard allocated memory used to track "memory" and "reserved" memblocks # after early boot, so it can still be used to test for validity of memory. # Also, memblocks are updated with memory hot(un)plug. diff --git a/mm/compaction.c b/mm/compaction.c index 621508e0ecd5..ed37e1cb4369 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -306,16 +306,14 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, * is necessary for the block to be a migration source/target. */ do { - if (pfn_valid_within(pfn)) { - if (check_source && PageLRU(page)) { - clear_pageblock_skip(page); - return true; - } + if (check_source && PageLRU(page)) { + clear_pageblock_skip(page); + return true; + } - if (check_target && PageBuddy(page)) { - clear_pageblock_skip(page); - return true; - } + if (check_target && PageBuddy(page)) { + clear_pageblock_skip(page); + return true; } page += (1 << PAGE_ALLOC_COSTLY_ORDER); @@ -585,8 +583,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, break; nr_scanned++; - if (!pfn_valid_within(blockpfn)) - goto isolate_fail; /* * For compound pages such as THP and hugetlbfs, we can save @@ -885,8 +881,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, cond_resched(); } - if (!pfn_valid_within(low_pfn)) - goto isolate_fail; nr_scanned++; page = pfn_to_page(low_pfn); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 86c3af79e874..8d3376f66f01 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1308,10 +1308,6 @@ struct zone *test_pages_in_a_zone(unsigned long start_pfn, for (; pfn < sec_end_pfn && pfn < end_pfn; pfn += MAX_ORDER_NR_PAGES) { i = 0; - /* This is just a CONFIG_HOLES_IN_ZONE check.*/ - while ((i < MAX_ORDER_NR_PAGES) && - !pfn_valid_within(pfn + i)) - i++; if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) continue; /* Check if we got outside of the zone */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index eeb3a9cb36bb..79a2fc5b6c6f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -594,8 +594,6 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page) static int page_is_consistent(struct zone *zone, struct page *page) { - if (!pfn_valid_within(page_to_pfn(page))) - return 0; if (zone != page_zone(page)) return 0; @@ -1025,16 +1023,12 @@ buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, if (order >= MAX_ORDER - 2) return false; - if (!pfn_valid_within(buddy_pfn)) - return false; - combined_pfn = buddy_pfn & pfn; higher_page = page + (combined_pfn - pfn); buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1); higher_buddy = higher_page + (buddy_pfn - combined_pfn); - return pfn_valid_within(buddy_pfn) && - page_is_buddy(higher_page, higher_buddy, order + 1); + return page_is_buddy(higher_page, higher_buddy, order + 1); } /* @@ -1095,8 +1089,6 @@ continue_merging: buddy_pfn = __find_buddy_pfn(pfn, order); buddy = page + (buddy_pfn - pfn); - if (!pfn_valid_within(buddy_pfn)) - goto done_merging; if (!page_is_buddy(page, buddy, order)) goto done_merging; /* @@ -1754,9 +1746,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, /* * Check that the whole (or subset of) a pageblock given by the interval of * [start_pfn, end_pfn) is valid and within the same zone, before scanning it - * with the migration of free compaction scanner. The scanners then need to - * use only pfn_valid_within() check for arches that allow holes within - * pageblocks. + * with the migration of free compaction scanner. * * Return struct page pointer of start_pfn, or NULL if checks were not passed. * @@ -1872,8 +1862,6 @@ static inline void __init pgdat_init_report_one_done(void) */ static inline bool __init deferred_pfn_valid(unsigned long pfn) { - if (!pfn_valid_within(pfn)) - return false; if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn)) return false; return true; @@ -2520,11 +2508,6 @@ static int move_freepages(struct zone *zone, int pages_moved = 0; for (pfn = start_pfn; pfn <= end_pfn;) { - if (!pfn_valid_within(pfn)) { - pfn++; - continue; - } - page = pfn_to_page(pfn); if (!PageBuddy(page)) { /* @@ -8814,9 +8797,6 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page, } for (; iter < pageblock_nr_pages - offset; iter++) { - if (!pfn_valid_within(pfn + iter)) - continue; - page = pfn_to_page(pfn + iter); /* diff --git a/mm/page_isolation.c b/mm/page_isolation.c index bddf788f45bf..471e3a13b541 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -93,8 +93,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) buddy_pfn = __find_buddy_pfn(pfn, order); buddy = page + (buddy_pfn - pfn); - if (pfn_valid_within(buddy_pfn) && - !is_migrate_isolate_page(buddy)) { + if (!is_migrate_isolate_page(buddy)) { __isolate_free_page(page, order); isolated_page = true; } @@ -250,10 +249,6 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, struct page *page; while (pfn < end_pfn) { - if (!pfn_valid_within(pfn)) { - pfn++; - continue; - } page = pfn_to_page(pfn); if (PageBuddy(page)) /* diff --git a/mm/page_owner.c b/mm/page_owner.c index f51a57e92aa3..62402d22539b 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -276,9 +276,6 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, pageblock_mt = get_pageblock_migratetype(page); for (; pfn < block_end_pfn; pfn++) { - if (!pfn_valid_within(pfn)) - continue; - /* The pageblock is online, no need to recheck. */ page = pfn_to_page(pfn); @@ -479,10 +476,6 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) continue; } - /* Check for holes within a MAX_ORDER area */ - if (!pfn_valid_within(pfn)) - continue; - page = pfn_to_page(pfn); if (PageBuddy(page)) { unsigned long freepage_order = buddy_order_unsafe(page); @@ -560,14 +553,9 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) block_end_pfn = min(block_end_pfn, end_pfn); for (; pfn < block_end_pfn; pfn++) { - struct page *page; + struct page *page = pfn_to_page(pfn); struct page_ext *page_ext; - if (!pfn_valid_within(pfn)) - continue; - - page = pfn_to_page(pfn); - if (page_zone(page) != zone) continue; -- cgit v1.2.3 From 7cf209ba8a86410939a24cb1aeb279479a7e0ca6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:54:59 -0700 Subject: mm/memory_hotplug: use "unsigned long" for PFN in zone_for_pfn_range() Patch series "mm/memory_hotplug: preparatory patches for new online policy and memory" These are all cleanups and one fix previously sent as part of [1]: [PATCH v1 00/12] mm/memory_hotplug: "auto-movable" online policy and memory groups. These patches make sense even without the other series, therefore I pulled them out to make the other series easier to digest. [1] https://lkml.kernel.org/r/20210607195430.48228-1-david@redhat.com This patch (of 4): Checkpatch complained on a follow-up patch that we are using "unsigned" here, which defaults to "unsigned int" and checkpatch is correct. As we will search for a fitting zone using the wrong pfn, we might end up onlining memory to one of the special kernel zones, such as ZONE_DMA, which can end badly as the onlined memory does not satisfy properties of these zones. Use "unsigned long" instead, just as we do in other places when handling PFNs. This can bite us once we have physical addresses in the range of multiple TB. Link: https://lkml.kernel.org/r/20210712124052.26491-2-david@redhat.com Fixes: e5e689302633 ("mm, memory_hotplug: display allowed zones in the preferred ordering") Signed-off-by: David Hildenbrand Reviewed-by: Pankaj Gupta Reviewed-by: Muchun Song Reviewed-by: Oscar Salvador Cc: David Hildenbrand Cc: Vitaly Kuznetsov Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Pankaj Gupta Cc: Wei Yang Cc: Michal Hocko Cc: Dan Williams Cc: Anshuman Khandual Cc: Dave Hansen Cc: Vlastimil Babka Cc: Mike Rapoport Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Pavel Tatashin Cc: Heiko Carstens Cc: Michael Ellerman Cc: Catalin Marinas Cc: virtualization@lists.linux-foundation.org Cc: Andy Lutomirski Cc: "Aneesh Kumar K.V" Cc: Anton Blanchard Cc: Ard Biesheuvel Cc: Baoquan He Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Dave Jiang Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jia He Cc: Joe Perches Cc: Kefeng Wang Cc: Laurent Dufour Cc: Michel Lespinasse Cc: Nathan Lynch Cc: Nicholas Piggin Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Pierre Morel Cc: "Rafael J. Wysocki" Cc: Rich Felker Cc: Scott Cheloha Cc: Sergei Trofimovich Cc: Thiago Jung Bauermann Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vishal Verma Cc: Will Deacon Cc: Yoshinori Sato Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 4 ++-- mm/memory_hotplug.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index a7fd2c3ccb77..d01b504ce06f 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -339,8 +339,8 @@ extern void sparse_remove_section(struct mem_section *ms, unsigned long map_offset, struct vmem_altmap *altmap); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); -extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, - unsigned long nr_pages); +extern struct zone *zone_for_pfn_range(int online_type, int nid, + unsigned long start_pfn, unsigned long nr_pages); extern int arch_create_linear_mapping(int nid, u64 start, u64 size, struct mhp_params *params); void arch_remove_linear_mapping(u64 start, u64 size); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index f829805fe1ca..fa349acb8810 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -708,8 +708,8 @@ static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn return movable_node_enabled ? movable_zone : kernel_zone; } -struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, - unsigned long nr_pages) +struct zone *zone_for_pfn_range(int online_type, int nid, + unsigned long start_pfn, unsigned long nr_pages) { if (online_type == MMOP_ONLINE_KERNEL) return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages); -- cgit v1.2.3 From 65a2aa5f482ed0c1b5afb9e6b0b9e0b16bb8b616 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:04 -0700 Subject: mm/memory_hotplug: remove nid parameter from arch_remove_memory() The parameter is unused, let's remove it. Link: https://lkml.kernel.org/r/20210712124052.26491-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Catalin Marinas Acked-by: Michael Ellerman [powerpc] Acked-by: Heiko Carstens [s390] Reviewed-by: Pankaj Gupta Reviewed-by: Oscar Salvador Cc: Catalin Marinas Cc: Will Deacon Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Yoshinori Sato Cc: Rich Felker Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Pavel Tatashin Cc: Baoquan He Cc: Laurent Dufour Cc: Sergei Trofimovich Cc: Kefeng Wang Cc: Michel Lespinasse Cc: Christophe Leroy Cc: "Aneesh Kumar K.V" Cc: Thiago Jung Bauermann Cc: Joe Perches Cc: Pierre Morel Cc: Jia He Cc: Anton Blanchard Cc: Dan Williams Cc: Dave Jiang Cc: Jason Wang Cc: Len Brown Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Nathan Lynch Cc: Pankaj Gupta Cc: "Rafael J. Wysocki" Cc: "Rafael J. Wysocki" Cc: Scott Cheloha Cc: Vishal Verma Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/mm/mmu.c | 3 +-- arch/ia64/mm/init.c | 3 +-- arch/powerpc/mm/mem.c | 3 +-- arch/s390/mm/init.c | 3 +-- arch/sh/mm/init.c | 3 +-- arch/x86/mm/init_32.c | 3 +-- arch/x86/mm/init_64.c | 3 +-- include/linux/memory_hotplug.h | 3 +-- mm/memory_hotplug.c | 4 ++-- mm/memremap.c | 5 +---- 10 files changed, 11 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9ff0de1b2b93..cfd9deb347c3 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1502,8 +1502,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return ret; } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 064a967a7b6e..5c6da8d83c1a 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -484,8 +484,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return ret; } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index ad198b439222..c3c4e31462ec 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -119,8 +119,7 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, return rc; } -void __ref arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 8ac710de1ab1..d85bd7f5d8dc 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -306,8 +306,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return rc; } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index ce26c7f8950a..506784702430 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -414,8 +414,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return ret; } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = PFN_DOWN(start); unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 74b78840182d..bd90b8fe81e4 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -801,8 +801,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return __add_pages(nid, start_pfn, nr_pages, params); } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ddeaba947eb3..a6e11763763f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1255,8 +1255,7 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end) remove_pagetable(start, end, true, NULL); } -void __ref arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index d01b504ce06f..010a192298b5 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -130,8 +130,7 @@ static inline bool movable_node_is_enabled(void) return movable_node_enabled; } -extern void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap); +extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap); extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fa349acb8810..14c4f6051c13 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1106,7 +1106,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) /* create memory block devices after memory was added */ ret = create_memory_block_devices(start, size, mhp_altmap.alloc); if (ret) { - arch_remove_memory(nid, start, size, NULL); + arch_remove_memory(start, size, NULL); goto error; } @@ -1886,7 +1886,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) mem_hotplug_begin(); - arch_remove_memory(nid, start, size, altmap); + arch_remove_memory(start, size, altmap); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { memblock_free(start, size); diff --git a/mm/memremap.c b/mm/memremap.c index 15a074ffb8d7..ed593bf87109 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -140,14 +140,11 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) { struct range *range = &pgmap->ranges[range_id]; struct page *first_page; - int nid; /* make sure to access a memmap that was actually initialized */ first_page = pfn_to_page(pfn_first(pgmap, range_id)); /* pages are dead and unused, undo the arch mapping */ - nid = page_to_nid(first_page); - mem_hotplug_begin(); remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(range->start), PHYS_PFN(range_len(range))); @@ -155,7 +152,7 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) __remove_pages(PHYS_PFN(range->start), PHYS_PFN(range_len(range)), NULL); } else { - arch_remove_memory(nid, range->start, range_len(range), + arch_remove_memory(range->start, range_len(range), pgmap_altmap(pgmap)); kasan_remove_zero_shadow(__va(range->start), range_len(range)); } -- cgit v1.2.3 From e1c158e4956612e7bada4c03dfb99210af4d6cde Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:09 -0700 Subject: mm/memory_hotplug: remove nid parameter from remove_memory() and friends There is only a single user remaining. We can simply lookup the nid only used for node offlining purposes when walking our memory blocks. We don't expect to remove multi-nid ranges; and if we'd ever do, we most probably don't care about removing multi-nid ranges that actually result in empty nodes. If ever required, we can detect the "multi-nid" scenario and simply try offlining all online nodes. Link: https://lkml.kernel.org/r/20210712124052.26491-4-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michael Ellerman (powerpc) Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Dan Williams Cc: Vishal Verma Cc: Dave Jiang Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Nathan Lynch Cc: Laurent Dufour Cc: "Aneesh Kumar K.V" Cc: Scott Cheloha Cc: Anton Blanchard Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Baoquan He Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Dave Hansen Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jia He Cc: Joe Perches Cc: Kefeng Wang Cc: Michal Hocko Cc: Michel Lespinasse Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Pierre Morel Cc: "Rafael J. Wysocki" Cc: Rich Felker Cc: Sergei Trofimovich Cc: Thiago Jung Bauermann Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/pseries/hotplug-memory.c | 9 ++++---- drivers/acpi/acpi_memhotplug.c | 7 +------ drivers/dax/kmem.c | 3 +-- drivers/virtio/virtio_mem.c | 4 ++-- include/linux/memory_hotplug.h | 10 ++++----- mm/memory_hotplug.c | 28 +++++++++++++++---------- 6 files changed, 30 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 377d852f5a9a..ef5c24b42cf1 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -286,7 +286,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si { unsigned long block_sz, start_pfn; int sections_per_block; - int i, nid; + int i; start_pfn = base >> PAGE_SHIFT; @@ -297,10 +297,9 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si block_sz = pseries_memory_block_size(); sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; - nid = memory_add_physaddr_to_nid(base); for (i = 0; i < sections_per_block; i++) { - __remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE); + __remove_memory(base, MIN_MEMORY_BLOCK_SIZE); base += MIN_MEMORY_BLOCK_SIZE; } @@ -387,7 +386,7 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb) block_sz = pseries_memory_block_size(); - __remove_memory(mem_block->nid, lmb->base_addr, block_sz); + __remove_memory(lmb->base_addr, block_sz); put_device(&mem_block->dev); /* Update memory regions for memory remove */ @@ -660,7 +659,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) rc = dlpar_online_lmb(lmb); if (rc) { - __remove_memory(nid, lmb->base_addr, block_sz); + __remove_memory(lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); } else { lmb->flags |= DRCONF_MEM_ASSIGNED; diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 8cc195c4c861..1d01d9414c40 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -239,19 +239,14 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) static void acpi_memory_remove_memory(struct acpi_memory_device *mem_device) { - acpi_handle handle = mem_device->device->handle; struct acpi_memory_info *info, *n; - int nid = acpi_get_node(handle); list_for_each_entry_safe(info, n, &mem_device->res_list, list) { if (!info->enabled) continue; - if (nid == NUMA_NO_NODE) - nid = memory_add_physaddr_to_nid(info->start_addr); - acpi_unbind_memory_blocks(info); - __remove_memory(nid, info->start_addr, info->length); + __remove_memory(info->start_addr, info->length); list_del(&info->list); kfree(info); } diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c index ac231cc36359..99e0f60c4c26 100644 --- a/drivers/dax/kmem.c +++ b/drivers/dax/kmem.c @@ -156,8 +156,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax) if (rc) continue; - rc = remove_memory(dev_dax->target_node, range.start, - range_len(&range)); + rc = remove_memory(range.start, range_len(&range)); if (rc == 0) { release_resource(data->res[i]); kfree(data->res[i]); diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index b91bc810a87e..7e83ed373e00 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -677,7 +677,7 @@ static int virtio_mem_remove_memory(struct virtio_mem *vm, uint64_t addr, dev_dbg(&vm->vdev->dev, "removing memory: 0x%llx - 0x%llx\n", addr, addr + size - 1); - rc = remove_memory(vm->nid, addr, size); + rc = remove_memory(addr, size); if (!rc) { atomic64_sub(size, &vm->offline_size); /* @@ -720,7 +720,7 @@ static int virtio_mem_offline_and_remove_memory(struct virtio_mem *vm, "offlining and removing memory: 0x%llx - 0x%llx\n", addr, addr + size - 1); - rc = offline_and_remove_memory(vm->nid, addr, size); + rc = offline_and_remove_memory(addr, size); if (!rc) { atomic64_sub(size, &vm->offline_size); /* diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 010a192298b5..068e3dcf4690 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -292,9 +292,9 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); -extern int remove_memory(int nid, u64 start, u64 size); -extern void __remove_memory(int nid, u64 start, u64 size); -extern int offline_and_remove_memory(int nid, u64 start, u64 size); +extern int remove_memory(u64 start, u64 size); +extern void __remove_memory(u64 start, u64 size); +extern int offline_and_remove_memory(u64 start, u64 size); #else static inline void try_offline_node(int nid) {} @@ -304,12 +304,12 @@ static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) return -EINVAL; } -static inline int remove_memory(int nid, u64 start, u64 size) +static inline int remove_memory(u64 start, u64 size) { return -EBUSY; } -static inline void __remove_memory(int nid, u64 start, u64 size) {} +static inline void __remove_memory(u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern void set_zone_contiguous(struct zone *zone); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 14c4f6051c13..6ea62efe2a8f 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1739,7 +1739,9 @@ failed_removal: static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) { int ret = !is_memblock_offlined(mem); + int *nid = arg; + *nid = mem->nid; if (unlikely(ret)) { phys_addr_t beginpa, endpa; @@ -1832,12 +1834,12 @@ void try_offline_node(int nid) } EXPORT_SYMBOL(try_offline_node); -static int __ref try_remove_memory(int nid, u64 start, u64 size) +static int __ref try_remove_memory(u64 start, u64 size) { - int rc = 0; struct vmem_altmap mhp_altmap = {}; struct vmem_altmap *altmap = NULL; unsigned long nr_vmemmap_pages; + int rc = 0, nid = NUMA_NO_NODE; BUG_ON(check_hotplug_memory_range(start, size)); @@ -1845,8 +1847,12 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) * All memory blocks must be offlined before removing memory. Check * whether all memory blocks in question are offline and return error * if this is not the case. + * + * While at it, determine the nid. Note that if we'd have mixed nodes, + * we'd only try to offline the last determined one -- which is good + * enough for the cases we care about. */ - rc = walk_memory_blocks(start, size, NULL, check_memblock_offlined_cb); + rc = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb); if (rc) return rc; @@ -1895,7 +1901,8 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) release_mem_region_adjustable(start, size); - try_offline_node(nid); + if (nid != NUMA_NO_NODE) + try_offline_node(nid); mem_hotplug_done(); return 0; @@ -1903,7 +1910,6 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) /** * __remove_memory - Remove memory if every memory block is offline - * @nid: the node ID * @start: physical address of the region to remove * @size: size of the region to remove * @@ -1911,14 +1917,14 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) * and online/offline operations before this call, as required by * try_offline_node(). */ -void __remove_memory(int nid, u64 start, u64 size) +void __remove_memory(u64 start, u64 size) { /* * trigger BUG() if some memory is not offlined prior to calling this * function */ - if (try_remove_memory(nid, start, size)) + if (try_remove_memory(start, size)) BUG(); } @@ -1926,12 +1932,12 @@ void __remove_memory(int nid, u64 start, u64 size) * Remove memory if every memory block is offline, otherwise return -EBUSY is * some memory is not offline */ -int remove_memory(int nid, u64 start, u64 size) +int remove_memory(u64 start, u64 size) { int rc; lock_device_hotplug(); - rc = try_remove_memory(nid, start, size); + rc = try_remove_memory(start, size); unlock_device_hotplug(); return rc; @@ -1991,7 +1997,7 @@ static int try_reonline_memory_block(struct memory_block *mem, void *arg) * unplugged all memory (so it's no longer in use) and want to offline + remove * that memory. */ -int offline_and_remove_memory(int nid, u64 start, u64 size) +int offline_and_remove_memory(u64 start, u64 size) { const unsigned long mb_count = size / memory_block_size_bytes(); uint8_t *online_types, *tmp; @@ -2027,7 +2033,7 @@ int offline_and_remove_memory(int nid, u64 start, u64 size) * This cannot fail as it cannot get onlined in the meantime. */ if (!rc) { - rc = try_remove_memory(nid, start, size); + rc = try_remove_memory(start, size); if (rc) pr_err("%s: Failed to remove memory: %d", __func__, rc); } -- cgit v1.2.3 From 4b0970024408afb17886e0c76e9761c4264db2a8 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:19 -0700 Subject: mm: track present early pages per zone Patch series "mm/memory_hotplug: "auto-movable" online policy and memory groups", v3. I. Goal The goal of this series is improving in-kernel auto-online support. It tackles the fundamental problems that: 1) We can create zone imbalances when onlining all memory blindly to ZONE_MOVABLE, in the worst case crashing the system. We have to know upfront how much memory we are going to hotplug such that we can safely enable auto-onlining of all hotplugged memory to ZONE_MOVABLE via "online_movable". This is far from practical and only applicable in limited setups -- like inside VMs under the RHV/oVirt hypervisor which will never hotplug more than 3 times the boot memory (and the limitation is only in place due to the Linux limitation). 2) We see more setups that implement dynamic VM resizing, hot(un)plugging memory to resize VM memory. In these setups, we might hotplug a lot of memory, but it might happen in various small steps in both directions (e.g., 2 GiB -> 8 GiB -> 4 GiB -> 16 GiB ...). virtio-mem is the primary driver of this upstream right now, performing such dynamic resizing NUMA-aware via multiple virtio-mem devices. Onlining all hotplugged memory to ZONE_NORMAL means we basically have no hotunplug guarantees. Onlining all to ZONE_MOVABLE means we can easily run into zone imbalances when growing a VM. We want a mixture, and we want as much memory as reasonable/configured in ZONE_MOVABLE. Details regarding zone imbalances can be found at [1]. 3) Memory devices consist of 1..X memory block devices, however, the kernel doesn't really track the relationship. Consequently, also user space has no idea. We want to make per-device decisions. As one example, for memory hotunplug it doesn't make sense to use a mixture of zones within a single DIMM: we want all MOVABLE if possible, otherwise all !MOVABLE, because any !MOVABLE part will easily block the whole DIMM from getting hotunplugged. As another example, virtio-mem operates on individual units that span 1..X memory blocks. Similar to a DIMM, we want a unit to either be all MOVABLE or !MOVABLE. A "unit" can be thought of like a DIMM, however, all units of a virtio-mem device logically belong together and are managed (added/removed) by a single driver. We want as much memory of a virtio-mem device to be MOVABLE as possible. 4) We want memory onlining to be done right from the kernel while adding memory, not triggered by user space via udev rules; for example, this is reqired for fast memory hotplug for drivers that add individual memory blocks, like virito-mem. We want a way to configure a policy in the kernel and avoid implementing advanced policies in user space. The auto-onlining support we have in the kernel is not sufficient. All we have is a) online everything MOVABLE (online_movable) b) online everything !MOVABLE (online_kernel) c) keep zones contiguous (online). This series allows configuring c) to mean instead "online movable if possible according to the coniguration, driven by a maximum MOVABLE:KERNEL ratio" -- a new onlining policy. II. Approach This series does 3 things: 1) Introduces the "auto-movable" online policy that initially operates on individual memory blocks only. It uses a maximum MOVABLE:KERNEL ratio to make a decision whether a memory block will be onlined to ZONE_MOVABLE or not. However, in the basic form, hotplugged KERNEL memory does not allow for more MOVABLE memory (details in the patches). CMA memory is treated like MOVABLE memory. 2) Introduces static (e.g., DIMM) and dynamic (e.g., virtio-mem) memory groups and uses group information to make decisions in the "auto-movable" online policy across memory blocks of a single memory device (modeled as memory group). More details can be found in patch #3 or in the DIMM example below. 3) Maximizes ZONE_MOVABLE memory within dynamic memory groups, by allowing ZONE_NORMAL memory within a dynamic memory group to allow for more ZONE_MOVABLE memory within the same memory group. The target use case is dynamic VM resizing using virtio-mem. See the virtio-mem example below. I remember that the basic idea of using a ratio to implement a policy in the kernel was once mentioned by Vitaly Kuznetsov, but I might be wrong (I lost the pointer to that discussion). For me, the main use case is using it along with virtio-mem (and DIMMs / ppc64 dlpar where necessary) for dynamic resizing of VMs, increasing the amount of memory we can hotunplug reliably again if we might eventually hotplug a lot of memory to a VM. III. Target Usage The target usage will be: 1) Linux boots with "mhp_default_online_type=offline" 2) User space (e.g., systemd unit) configures memory onlining (according to a config file and system properties), for example: * Setting memory_hotplug.online_policy=auto-movable * Setting memory_hotplug.auto_movable_ratio=301 * Setting memory_hotplug.auto_movable_numa_aware=true 3) User space enabled auto onlining via "echo online > /sys/devices/system/memory/auto_online_blocks" 4) User space triggers manual onlining of all already-offline memory blocks (go over offline memory blocks and set them to "online") IV. Example For DIMMs, hotplugging 4 GiB DIMMs to a 4 GiB VM with a configured ratio of 301% results in the following layout: Memory block 0-15: DMA32 (early) Memory block 32-47: Normal (early) Memory block 48-79: Movable (DIMM 0) Memory block 80-111: Movable (DIMM 1) Memory block 112-143: Movable (DIMM 2) Memory block 144-275: Normal (DIMM 3) Memory block 176-207: Normal (DIMM 4) ... all Normal (-> hotplugged Normal memory does not allow for more Movable memory) For virtio-mem, using a simple, single virtio-mem device with a 4 GiB VM will result in the following layout: Memory block 0-15: DMA32 (early) Memory block 32-47: Normal (early) Memory block 48-143: Movable (virtio-mem, first 12 GiB) Memory block 144: Normal (virtio-mem, next 128 MiB) Memory block 145-147: Movable (virtio-mem, next 384 MiB) Memory block 148: Normal (virtio-mem, next 128 MiB) Memory block 149-151: Movable (virtio-mem, next 384 MiB) ... Normal/Movable mixture as above (-> hotplugged Normal memory allows for more Movable memory within the same device) Which gives us maximum flexibility when dynamically growing/shrinking a VM in smaller steps. V. Doc Update I'll update the memory-hotplug.rst documentation, once the overhaul [1] is usptream. Until then, details can be found in patch #2. VI. Future Work 1) Use memory groups for ppc64 dlpar 2) Being able to specify a portion of (early) kernel memory that will be excluded from the ratio. Like "128 MiB globally/per node" are excluded. This might be helpful when starting VMs with extremely small memory footprint (e.g., 128 MiB) and hotplugging memory later -- not wanting the first hotplugged units getting onlined to ZONE_MOVABLE. One alternative would be a trigger to not consider ZONE_DMA memory in the ratio. We'll have to see if this is really rrequired. 3) Indicate to user space that MOVABLE might be a bad idea -- especially relevant when memory ballooning without support for balloon compaction is active. This patch (of 9): For implementing a new memory onlining policy, which determines when to online memory blocks to ZONE_MOVABLE semi-automatically, we need the number of present early (boot) pages -- present pages excluding hotplugged pages. Let's track these pages per zone. Pass a page instead of the zone to adjust_present_page_count(), similar as adjust_managed_page_count() and derive the zone from the page. It's worth noting that a memory block to be offlined/onlined is either completely "early" or "not early". add_memory() and friends can only add complete memory blocks and we only online/offline complete (individual) memory blocks. Link: https://lkml.kernel.org/r/20210806124715.17090-1-david@redhat.com Link: https://lkml.kernel.org/r/20210806124715.17090-2-david@redhat.com Signed-off-by: David Hildenbrand Cc: Vitaly Kuznetsov Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Marek Kedzierski Cc: Hui Zhu Cc: Pankaj Gupta Cc: Wei Yang Cc: Oscar Salvador Cc: Michal Hocko Cc: Dan Williams Cc: Anshuman Khandual Cc: Dave Hansen Cc: Vlastimil Babka Cc: Mike Rapoport Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Pavel Tatashin Cc: Greg Kroah-Hartman Cc: Rafael J. Wysocki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 14 +++++++------- include/linux/memory_hotplug.h | 2 +- include/linux/mmzone.h | 7 +++++++ mm/memory_hotplug.c | 14 +++++++++++--- mm/page_alloc.c | 3 +++ 5 files changed, 29 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index aa31a21f33d7..86ec2dc82fc2 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -205,7 +205,8 @@ static int memory_block_online(struct memory_block *mem) * now already properly populated. */ if (nr_vmemmap_pages) - adjust_present_page_count(zone, nr_vmemmap_pages); + adjust_present_page_count(pfn_to_page(start_pfn), + nr_vmemmap_pages); return ret; } @@ -215,24 +216,23 @@ static int memory_block_offline(struct memory_block *mem) unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages; - struct zone *zone; int ret; /* * Unaccount before offlining, such that unpopulated zone and kthreads * can properly be torn down in offline_pages(). */ - if (nr_vmemmap_pages) { - zone = page_zone(pfn_to_page(start_pfn)); - adjust_present_page_count(zone, -nr_vmemmap_pages); - } + if (nr_vmemmap_pages) + adjust_present_page_count(pfn_to_page(start_pfn), + -nr_vmemmap_pages); ret = offline_pages(start_pfn + nr_vmemmap_pages, nr_pages - nr_vmemmap_pages); if (ret) { /* offline_pages() failed. Account back. */ if (nr_vmemmap_pages) - adjust_present_page_count(zone, nr_vmemmap_pages); + adjust_present_page_count(pfn_to_page(start_pfn), + nr_vmemmap_pages); return ret; } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 068e3dcf4690..39b04e99a30e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -95,7 +95,7 @@ static inline void zone_seqlock_init(struct zone *zone) extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); -extern void adjust_present_page_count(struct zone *zone, long nr_pages); +extern void adjust_present_page_count(struct page *page, long nr_pages); /* VM interface that may be used by firmware interface */ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, struct zone *zone); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ee3a86830519..1c0e3bf42521 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -540,6 +540,10 @@ struct zone { * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * + * present_early_pages is present pages existing within the zone + * located on memory available since early boot, excluding hotplugged + * memory. + * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): @@ -572,6 +576,9 @@ struct zone { atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; +#if defined(CONFIG_MEMORY_HOTPLUG) + unsigned long present_early_pages; +#endif #ifdef CONFIG_CMA unsigned long cma_pages; #endif diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 6ea62efe2a8f..8a99fa6d096c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -724,8 +724,16 @@ struct zone *zone_for_pfn_range(int online_type, int nid, * This function should only be called by memory_block_{online,offline}, * and {online,offline}_pages. */ -void adjust_present_page_count(struct zone *zone, long nr_pages) +void adjust_present_page_count(struct page *page, long nr_pages) { + struct zone *zone = page_zone(page); + + /* + * We only support onlining/offlining/adding/removing of complete + * memory blocks; therefore, either all is either early or hotplugged. + */ + if (early_section(__pfn_to_section(page_to_pfn(page)))) + zone->present_early_pages += nr_pages; zone->present_pages += nr_pages; zone->zone_pgdat->node_present_pages += nr_pages; } @@ -826,7 +834,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z } online_pages_range(pfn, nr_pages); - adjust_present_page_count(zone, nr_pages); + adjust_present_page_count(pfn_to_page(pfn), nr_pages); node_states_set_node(nid, &arg); if (need_zonelists_rebuild) @@ -1697,7 +1705,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) /* removal success */ adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages); - adjust_present_page_count(zone, -nr_pages); + adjust_present_page_count(pfn_to_page(start_pfn), -nr_pages); /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 79a2fc5b6c6f..9353418892a7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7240,6 +7240,9 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat, zone->zone_start_pfn = 0; zone->spanned_pages = size; zone->present_pages = real_size; +#if defined(CONFIG_MEMORY_HOTPLUG) + zone->present_early_pages = real_size; +#endif totalpages += size; realtotalpages += real_size; -- cgit v1.2.3 From 028fc57a1c361116e3bcebfeba4ca87878baaf4f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:26 -0700 Subject: drivers/base/memory: introduce "memory groups" to logically group memory blocks In our "auto-movable" memory onlining policy, we want to make decisions across memory blocks of a single memory device. Examples of memory devices include ACPI memory devices (in the simplest case a single DIMM) and virtio-mem. For now, we don't have a connection between a single memory block device and the real memory device. Each memory device consists of 1..X memory block devices. Let's logically group memory blocks belonging to the same memory device in "memory groups". Memory groups can span multiple physical ranges and a memory group itself does not contain any information regarding physical ranges, only properties (e.g., "max_pages") necessary for improved memory onlining. Introduce two memory group types: 1) Static memory group: E.g., a single ACPI memory device, consisting of 1..X memory resources. A memory group consists of 1..Y memory blocks. The whole group is added/removed in one go. If any part cannot get offlined, the whole group cannot be removed. 2) Dynamic memory group: E.g., a single virtio-mem device. Memory is dynamically added/removed in a fixed granularity, called a "unit", consisting of 1..X memory blocks. A unit is added/removed in one go. If any part of a unit cannot get offlined, the whole unit cannot be removed. In case of 1) we usually want either all memory managed by ZONE_MOVABLE or none. In case of 2) we usually want to have as many units as possible managed by ZONE_MOVABLE. We want a single unit to be of the same type. For now, memory groups are an internal concept that is not exposed to user space; we might want to change that in the future, though. add_memory() users can specify a mgid instead of a nid when passing the MHP_NID_IS_MGID flag. Link: https://lkml.kernel.org/r/20210806124715.17090-4-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: Dan Williams Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Hui Zhu Cc: Jason Wang Cc: Len Brown Cc: Marek Kedzierski Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 159 +++++++++++++++++++++++++++++++++++++++-- include/linux/memory.h | 46 +++++++++++- include/linux/memory_hotplug.h | 5 ++ mm/memory_hotplug.c | 11 ++- 4 files changed, 215 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 86ec2dc82fc2..16f5a3610229 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -82,6 +82,11 @@ static struct bus_type memory_subsys = { */ static DEFINE_XARRAY(memory_blocks); +/* + * Memory groups, indexed by memory group id (mgid). + */ +static DEFINE_XARRAY_FLAGS(memory_groups, XA_FLAGS_ALLOC); + static BLOCKING_NOTIFIER_HEAD(memory_chain); int register_memory_notifier(struct notifier_block *nb) @@ -634,7 +639,8 @@ int register_memory(struct memory_block *memory) } static int init_memory_block(unsigned long block_id, unsigned long state, - unsigned long nr_vmemmap_pages) + unsigned long nr_vmemmap_pages, + struct memory_group *group) { struct memory_block *mem; int ret = 0; @@ -652,6 +658,12 @@ static int init_memory_block(unsigned long block_id, unsigned long state, mem->state = state; mem->nid = NUMA_NO_NODE; mem->nr_vmemmap_pages = nr_vmemmap_pages; + INIT_LIST_HEAD(&mem->group_next); + + if (group) { + mem->group = group; + list_add(&mem->group_next, &group->memory_blocks); + } ret = register_memory(mem); @@ -671,7 +683,7 @@ static int add_memory_block(unsigned long base_section_nr) if (section_count == 0) return 0; return init_memory_block(memory_block_id(base_section_nr), - MEM_ONLINE, 0); + MEM_ONLINE, 0, NULL); } static void unregister_memory(struct memory_block *memory) @@ -681,6 +693,11 @@ static void unregister_memory(struct memory_block *memory) WARN_ON(xa_erase(&memory_blocks, memory->dev.id) == NULL); + if (memory->group) { + list_del(&memory->group_next); + memory->group = NULL; + } + /* drop the ref. we got via find_memory_block() */ put_device(&memory->dev); device_unregister(&memory->dev); @@ -694,7 +711,8 @@ static void unregister_memory(struct memory_block *memory) * Called under device_hotplug_lock. */ int create_memory_block_devices(unsigned long start, unsigned long size, - unsigned long vmemmap_pages) + unsigned long vmemmap_pages, + struct memory_group *group) { const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start)); unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size)); @@ -707,7 +725,8 @@ int create_memory_block_devices(unsigned long start, unsigned long size, return -EINVAL; for (block_id = start_block_id; block_id != end_block_id; block_id++) { - ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages); + ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages, + group); if (ret) break; } @@ -891,3 +910,135 @@ int for_each_memory_block(void *arg, walk_memory_blocks_func_t func) return bus_for_each_dev(&memory_subsys, NULL, &cb_data, for_each_memory_block_cb); } + +/* + * This is an internal helper to unify allocation and initialization of + * memory groups. Note that the passed memory group will be copied to a + * dynamically allocated memory group. After this call, the passed + * memory group should no longer be used. + */ +static int memory_group_register(struct memory_group group) +{ + struct memory_group *new_group; + uint32_t mgid; + int ret; + + if (!node_possible(group.nid)) + return -EINVAL; + + new_group = kzalloc(sizeof(group), GFP_KERNEL); + if (!new_group) + return -ENOMEM; + *new_group = group; + INIT_LIST_HEAD(&new_group->memory_blocks); + + ret = xa_alloc(&memory_groups, &mgid, new_group, xa_limit_31b, + GFP_KERNEL); + if (ret) { + kfree(new_group); + return ret; + } + return mgid; +} + +/** + * memory_group_register_static() - Register a static memory group. + * @nid: The node id. + * @max_pages: The maximum number of pages we'll have in this static memory + * group. + * + * Register a new static memory group and return the memory group id. + * All memory in the group belongs to a single unit, such as a DIMM. All + * memory belonging to a static memory group is added in one go to be removed + * in one go -- it's static. + * + * Returns an error if out of memory, if the node id is invalid, if no new + * memory groups can be registered, or if max_pages is invalid (0). Otherwise, + * returns the new memory group id. + */ +int memory_group_register_static(int nid, unsigned long max_pages) +{ + struct memory_group group = { + .nid = nid, + .s = { + .max_pages = max_pages, + }, + }; + + if (!max_pages) + return -EINVAL; + return memory_group_register(group); +} +EXPORT_SYMBOL_GPL(memory_group_register_static); + +/** + * memory_group_register_dynamic() - Register a dynamic memory group. + * @nid: The node id. + * @unit_pages: Unit in pages in which is memory added/removed in this dynamic + * memory group. + * + * Register a new dynamic memory group and return the memory group id. + * Memory within a dynamic memory group is added/removed dynamically + * in unit_pages. + * + * Returns an error if out of memory, if the node id is invalid, if no new + * memory groups can be registered, or if unit_pages is invalid (0, not a + * power of two, smaller than a single memory block). Otherwise, returns the + * new memory group id. + */ +int memory_group_register_dynamic(int nid, unsigned long unit_pages) +{ + struct memory_group group = { + .nid = nid, + .is_dynamic = true, + .d = { + .unit_pages = unit_pages, + }, + }; + + if (!unit_pages || !is_power_of_2(unit_pages) || + unit_pages < PHYS_PFN(memory_block_size_bytes())) + return -EINVAL; + return memory_group_register(group); +} +EXPORT_SYMBOL_GPL(memory_group_register_dynamic); + +/** + * memory_group_unregister() - Unregister a memory group. + * @mgid: the memory group id + * + * Unregister a memory group. If any memory block still belongs to this + * memory group, unregistering will fail. + * + * Returns -EINVAL if the memory group id is invalid, returns -EBUSY if some + * memory blocks still belong to this memory group and returns 0 if + * unregistering succeeded. + */ +int memory_group_unregister(int mgid) +{ + struct memory_group *group; + + if (mgid < 0) + return -EINVAL; + + group = xa_load(&memory_groups, mgid); + if (!group) + return -EINVAL; + if (!list_empty(&group->memory_blocks)) + return -EBUSY; + xa_erase(&memory_groups, mgid); + kfree(group); + return 0; +} +EXPORT_SYMBOL_GPL(memory_group_unregister); + +/* + * This is an internal helper only to be used in core memory hotplug code to + * lookup a memory group. We don't care about locking, as we don't expect a + * memory group to get unregistered while adding memory to it -- because + * the group and the memory is managed by the same driver. + */ +struct memory_group *memory_group_find_by_id(int mgid) +{ + return xa_load(&memory_groups, mgid); +} diff --git a/include/linux/memory.h b/include/linux/memory.h index 97e92e8b556a..d505c12c5c77 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -23,6 +23,42 @@ #define MIN_MEMORY_BLOCK_SIZE (1UL << SECTION_SIZE_BITS) +/** + * struct memory_group - a logical group of memory blocks + * @nid: The node id for all memory blocks inside the memory group. + * @blocks: List of all memory blocks belonging to this memory group. + * @is_dynamic: The memory group type: static vs. dynamic + * @s.max_pages: Valid with &memory_group.is_dynamic == false. The maximum + * number of pages we'll have in this static memory group. + * @d.unit_pages: Valid with &memory_group.is_dynamic == true. Unit in pages + * in which memory is added/removed in this dynamic memory group. + * This granularity defines the alignment of a unit in physical + * address space; it has to be at least as big as a single + * memory block. + * + * A memory group logically groups memory blocks; each memory block + * belongs to at most one memory group. A memory group corresponds to + * a memory device, such as a DIMM or a NUMA node, which spans multiple + * memory blocks and might even span multiple non-contiguous physical memory + * ranges. + * + * Modification of members after registration is serialized by memory + * hot(un)plug code. + */ +struct memory_group { + int nid; + struct list_head memory_blocks; + bool is_dynamic; + union { + struct { + unsigned long max_pages; + } s; + struct { + unsigned long unit_pages; + } d; + }; +}; + struct memory_block { unsigned long start_section_nr; unsigned long state; /* serialized by the dev->lock */ @@ -34,6 +70,8 @@ struct memory_block { * lay at the beginning of the memory block. */ unsigned long nr_vmemmap_pages; + struct memory_group *group; /* group (if any) for this block */ + struct list_head group_next; /* next block inside memory group */ }; int arch_get_memory_phys_device(unsigned long start_pfn); @@ -86,7 +124,8 @@ static inline int memory_notify(unsigned long val, void *v) extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); int create_memory_block_devices(unsigned long start, unsigned long size, - unsigned long vmemmap_pages); + unsigned long vmemmap_pages, + struct memory_group *group); void remove_memory_block_devices(unsigned long start, unsigned long size); extern void memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); @@ -96,6 +135,11 @@ extern int walk_memory_blocks(unsigned long start, unsigned long size, void *arg, walk_memory_blocks_func_t func); extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<nid; + } + if (!node_possible(nid)) { WARN(1, "node %d was absent from the node_possible_map\n", nid); return -EINVAL; @@ -1303,7 +1311,8 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) goto error; /* create memory block devices after memory was added */ - ret = create_memory_block_devices(start, size, mhp_altmap.alloc); + ret = create_memory_block_devices(start, size, mhp_altmap.alloc, + group); if (ret) { arch_remove_memory(start, size, NULL); goto error; -- cgit v1.2.3 From 836809ec75cc07c6d07c43036e3844affbe0d46f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:30 -0700 Subject: mm/memory_hotplug: track present pages in memory groups Let's track all present pages in each memory group. Especially, track memory present in ZONE_MOVABLE and memory present in one of the kernel zones (which really only is ZONE_NORMAL right now as memory groups only apply to hotplugged memory) separately within a memory group, to prepare for making smart auto-online decision for individual memory blocks within a memory group based on group statistics. Link: https://lkml.kernel.org/r/20210806124715.17090-5-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: Dan Williams Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Hui Zhu Cc: Jason Wang Cc: Len Brown Cc: Marek Kedzierski Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 10 +++++----- include/linux/memory.h | 6 ++++++ include/linux/memory_hotplug.h | 13 +++++++++---- mm/memory_hotplug.c | 19 ++++++++++++++----- 4 files changed, 34 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 16f5a3610229..a1082013e10c 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -198,7 +198,7 @@ static int memory_block_online(struct memory_block *mem) } ret = online_pages(start_pfn + nr_vmemmap_pages, - nr_pages - nr_vmemmap_pages, zone); + nr_pages - nr_vmemmap_pages, zone, mem->group); if (ret) { if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); @@ -210,7 +210,7 @@ static int memory_block_online(struct memory_block *mem) * now already properly populated. */ if (nr_vmemmap_pages) - adjust_present_page_count(pfn_to_page(start_pfn), + adjust_present_page_count(pfn_to_page(start_pfn), mem->group, nr_vmemmap_pages); return ret; @@ -228,16 +228,16 @@ static int memory_block_offline(struct memory_block *mem) * can properly be torn down in offline_pages(). */ if (nr_vmemmap_pages) - adjust_present_page_count(pfn_to_page(start_pfn), + adjust_present_page_count(pfn_to_page(start_pfn), mem->group, -nr_vmemmap_pages); ret = offline_pages(start_pfn + nr_vmemmap_pages, - nr_pages - nr_vmemmap_pages); + nr_pages - nr_vmemmap_pages, mem->group); if (ret) { /* offline_pages() failed. Account back. */ if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), - nr_vmemmap_pages); + mem->group, nr_vmemmap_pages); return ret; } diff --git a/include/linux/memory.h b/include/linux/memory.h index d505c12c5c77..6ffdc1db385f 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -27,6 +27,10 @@ * struct memory_group - a logical group of memory blocks * @nid: The node id for all memory blocks inside the memory group. * @blocks: List of all memory blocks belonging to this memory group. + * @present_kernel_pages: Present (online) memory outside ZONE_MOVABLE of this + * memory group. + * @present_movable_pages: Present (online) memory in ZONE_MOVABLE of this + * memory group. * @is_dynamic: The memory group type: static vs. dynamic * @s.max_pages: Valid with &memory_group.is_dynamic == false. The maximum * number of pages we'll have in this static memory group. @@ -48,6 +52,8 @@ struct memory_group { int nid; struct list_head memory_blocks; + unsigned long present_kernel_pages; + unsigned long present_movable_pages; bool is_dynamic; union { struct { diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 5d341978b4bc..cf3f423c8a74 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -12,6 +12,7 @@ struct zone; struct pglist_data; struct mem_section; struct memory_block; +struct memory_group; struct resource; struct vmem_altmap; @@ -100,13 +101,15 @@ static inline void zone_seqlock_init(struct zone *zone) extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); -extern void adjust_present_page_count(struct page *page, long nr_pages); +extern void adjust_present_page_count(struct page *page, + struct memory_group *group, + long nr_pages); /* VM interface that may be used by firmware interface */ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, struct zone *zone); extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, - struct zone *zone); + struct zone *zone, struct memory_group *group); extern struct zone *test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn); extern void __offline_isolated_pages(unsigned long start_pfn, @@ -296,7 +299,8 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} #ifdef CONFIG_MEMORY_HOTREMOVE extern void try_offline_node(int nid); -extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); +extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages, + struct memory_group *group); extern int remove_memory(u64 start, u64 size); extern void __remove_memory(u64 start, u64 size); extern int offline_and_remove_memory(u64 start, u64 size); @@ -304,7 +308,8 @@ extern int offline_and_remove_memory(u64 start, u64 size); #else static inline void try_offline_node(int nid) {} -static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) +static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages, + struct memory_group *group) { return -EINVAL; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fd57a296dd27..8199a4f98b2b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -915,9 +915,11 @@ struct zone *zone_for_pfn_range(int online_type, int nid, * This function should only be called by memory_block_{online,offline}, * and {online,offline}_pages. */ -void adjust_present_page_count(struct page *page, long nr_pages) +void adjust_present_page_count(struct page *page, struct memory_group *group, + long nr_pages) { struct zone *zone = page_zone(page); + const bool movable = zone_idx(zone) == ZONE_MOVABLE; /* * We only support onlining/offlining/adding/removing of complete @@ -927,6 +929,11 @@ void adjust_present_page_count(struct page *page, long nr_pages) zone->present_early_pages += nr_pages; zone->present_pages += nr_pages; zone->zone_pgdat->node_present_pages += nr_pages; + + if (group && movable) + group->present_movable_pages += nr_pages; + else if (group && !movable) + group->present_kernel_pages += nr_pages; } int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, @@ -972,7 +979,8 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); } -int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone) +int __ref online_pages(unsigned long pfn, unsigned long nr_pages, + struct zone *zone, struct memory_group *group) { unsigned long flags; int need_zonelists_rebuild = 0; @@ -1025,7 +1033,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z } online_pages_range(pfn, nr_pages); - adjust_present_page_count(pfn_to_page(pfn), nr_pages); + adjust_present_page_count(pfn_to_page(pfn), group, nr_pages); node_states_set_node(nid, &arg); if (need_zonelists_rebuild) @@ -1769,7 +1777,8 @@ static int count_system_ram_pages_cb(unsigned long start_pfn, return 0; } -int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) +int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, + struct memory_group *group) { const unsigned long end_pfn = start_pfn + nr_pages; unsigned long pfn, system_ram_pages = 0; @@ -1905,7 +1914,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) /* removal success */ adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages); - adjust_present_page_count(pfn_to_page(start_pfn), -nr_pages); + adjust_present_page_count(pfn_to_page(start_pfn), group, -nr_pages); /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); -- cgit v1.2.3 From 445fcf7c721450dd1d4ec6c217b3c6a932602a44 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:45 -0700 Subject: mm/memory_hotplug: memory group aware "auto-movable" online policy Use memory groups to improve our "auto-movable" onlining policy: 1. For static memory groups (e.g., a DIMM), online a memory block MOVABLE only if all other memory blocks in the group are either MOVABLE or could be onlined MOVABLE. A DIMM will either be MOVABLE or not, not a mixture. 2. For dynamic memory groups (e.g., a virtio-mem device), online a memory block MOVABLE only if all other memory blocks inside the current unit are either MOVABLE or could be onlined MOVABLE. For a virtio-mem device with a device block size with 512 MiB, all 128 MiB memory blocks wihin a 512 MiB unit will either be MOVABLE or not, not a mixture. We have to pass the memory group to zone_for_pfn_range() to take the memory group into account. Note: for now, there seems to be no compelling reason to make this behavior configurable. Link: https://lkml.kernel.org/r/20210806124715.17090-9-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: Dan Williams Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Hui Zhu Cc: Jason Wang Cc: Len Brown Cc: Marek Kedzierski Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 18 +++++++++------- include/linux/memory_hotplug.h | 3 ++- mm/memory_hotplug.c | 48 +++++++++++++++++++++++++++++++++++++++--- 3 files changed, 57 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index a1082013e10c..b699ddc42693 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -182,7 +182,8 @@ static int memory_block_online(struct memory_block *mem) struct zone *zone; int ret; - zone = zone_for_pfn_range(mem->online_type, mem->nid, start_pfn, nr_pages); + zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group, + start_pfn, nr_pages); /* * Although vmemmap pages have a different lifecycle than the pages @@ -379,12 +380,13 @@ static ssize_t phys_device_show(struct device *dev, #ifdef CONFIG_MEMORY_HOTREMOVE static int print_allowed_zone(char *buf, int len, int nid, + struct memory_group *group, unsigned long start_pfn, unsigned long nr_pages, int online_type, struct zone *default_zone) { struct zone *zone; - zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages); + zone = zone_for_pfn_range(online_type, nid, group, start_pfn, nr_pages); if (zone == default_zone) return 0; @@ -397,9 +399,10 @@ static ssize_t valid_zones_show(struct device *dev, struct memory_block *mem = to_memory_block(dev); unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; + struct memory_group *group = mem->group; struct zone *default_zone; + int nid = mem->nid; int len = 0; - int nid; /* * Check the existing zone. Make sure that we do that only on the @@ -418,14 +421,13 @@ static ssize_t valid_zones_show(struct device *dev, goto out; } - nid = mem->nid; - default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, start_pfn, - nr_pages); + default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, group, + start_pfn, nr_pages); len += sysfs_emit_at(buf, len, "%s", default_zone->name); - len += print_allowed_zone(buf, len, nid, start_pfn, nr_pages, + len += print_allowed_zone(buf, len, nid, group, start_pfn, nr_pages, MMOP_ONLINE_KERNEL, default_zone); - len += print_allowed_zone(buf, len, nid, start_pfn, nr_pages, + len += print_allowed_zone(buf, len, nid, group, start_pfn, nr_pages, MMOP_ONLINE_MOVABLE, default_zone); out: len += sysfs_emit_at(buf, len, "\n"); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index cf3f423c8a74..e5a867c950b2 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -349,7 +349,8 @@ extern void sparse_remove_section(struct mem_section *ms, extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); extern struct zone *zone_for_pfn_range(int online_type, int nid, - unsigned long start_pfn, unsigned long nr_pages); + struct memory_group *group, unsigned long start_pfn, + unsigned long nr_pages); extern int arch_create_linear_mapping(int nid, u64 start, u64 size, struct mhp_params *params); void arch_remove_linear_mapping(u64 start, u64 size); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 8199a4f98b2b..248e2ba4ac59 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -852,12 +852,53 @@ static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn * "present pages" is an upper limit that can get reached at runtime. As * we base our calculations on KERNEL_EARLY, this is not an issue. */ -static struct zone *auto_movable_zone_for_pfn(int nid, unsigned long pfn, +static struct zone *auto_movable_zone_for_pfn(int nid, + struct memory_group *group, + unsigned long pfn, unsigned long nr_pages) { + unsigned long online_pages = 0, max_pages, end_pfn; + struct page *page; + if (!auto_movable_ratio) goto kernel_zone; + if (group && !group->is_dynamic) { + max_pages = group->s.max_pages; + online_pages = group->present_movable_pages; + + /* If anything is !MOVABLE online the rest !MOVABLE. */ + if (group->present_kernel_pages) + goto kernel_zone; + } else if (!group || group->d.unit_pages == nr_pages) { + max_pages = nr_pages; + } else { + max_pages = group->d.unit_pages; + /* + * Take a look at all online sections in the current unit. + * We can safely assume that all pages within a section belong + * to the same zone, because dynamic memory groups only deal + * with hotplugged memory. + */ + pfn = ALIGN_DOWN(pfn, group->d.unit_pages); + end_pfn = pfn + group->d.unit_pages; + for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + page = pfn_to_online_page(pfn); + if (!page) + continue; + /* If anything is !MOVABLE online the rest !MOVABLE. */ + if (page_zonenum(page) != ZONE_MOVABLE) + goto kernel_zone; + online_pages += PAGES_PER_SECTION; + } + } + + /* + * Online MOVABLE if we could *currently* online all remaining parts + * MOVABLE. We expect to (add+) online them immediately next, so if + * nobody interferes, all will be MOVABLE if possible. + */ + nr_pages = max_pages - online_pages; if (!auto_movable_can_online_movable(NUMA_NO_NODE, nr_pages)) goto kernel_zone; @@ -897,7 +938,8 @@ static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn } struct zone *zone_for_pfn_range(int online_type, int nid, - unsigned long start_pfn, unsigned long nr_pages) + struct memory_group *group, unsigned long start_pfn, + unsigned long nr_pages) { if (online_type == MMOP_ONLINE_KERNEL) return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages); @@ -906,7 +948,7 @@ struct zone *zone_for_pfn_range(int online_type, int nid, return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; if (online_policy == ONLINE_POLICY_AUTO_MOVABLE) - return auto_movable_zone_for_pfn(nid, start_pfn, nr_pages); + return auto_movable_zone_for_pfn(nid, group, start_pfn, nr_pages); return default_zone_for_pfn(nid, start_pfn, nr_pages); } -- cgit v1.2.3 From 3fcebf90209a7f52d384ad7701425aa91be309ab Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:48 -0700 Subject: mm/memory_hotplug: improved dynamic memory group aware "auto-movable" online policy Currently, the "auto-movable" online policy does not allow for hotplugged KERNEL (ZONE_NORMAL) memory to increase the amount of MOVABLE memory we can have, primarily, because there is no coordiantion across memory devices and we don't want to create zone-imbalances accidentially when unplugging memory. However, within a single memory device it's different. Let's allow for KERNEL memory within a dynamic memory group to allow for more MOVABLE within the same memory group. The only thing we have to take care of is that the managing driver avoids zone imbalances by unplugging MOVABLE memory first, otherwise there can be corner cases where unplug of memory could result in (accidential) zone imbalances. virtio-mem is the only user of dynamic memory groups and recently added support for prioritizing unplug of ZONE_MOVABLE over ZONE_NORMAL, so we don't need a new toggle to enable it for dynamic memory groups. We limit this handling to dynamic memory groups, because: * We want to keep the runtime overhead for collecting stats when onlining a single memory block small. We tend to have only a handful of dynamic memory groups, but we can have quite some static memory groups (e.g., 256 DIMMs). * It doesn't make too much sense for static memory groups, as we try onlining all applicable memory blocks either completely to ZONE_MOVABLE or not. In ordinary operation, we won't have a mixture of zones within a static memory group. When adding memory to a dynamic memory group, we'll first online memory to ZONE_MOVABLE as long as early KERNEL memory allows for it. Then, we'll online the next unit(s) to ZONE_NORMAL, until we can online the next unit(s) to ZONE_MOVABLE. For a simple virtio-mem device with a MOVABLE:KERNEL ratio of 3:1, it will result in a layout like: [M][M][M][M][M][M][M][M][N][M][M][M][N][M][M][M]... ^ movable memory due to early kernel memory ^ allows for more movable memory ... ^-----^ ... here ^ allows for more movable memory ... ^-----^ ... here While the created layout is sub-optimal when it comes to contiguous zones, it gives us the maximum flexibility when dynamically growing/shrinking a device; we can grow small VMs really big in small steps, and still shrink reliably to e.g., 1/4 of the maximum VM size in this example, removing full memory blocks along with meta data more reliably. Mark dynamic memory groups in the xarray such that we can efficiently iterate over them when collecting stats. In usual setups, we have one virtio-mem device per NUMA node, and usually only a small number of NUMA nodes. Note: for now, there seems to be no compelling reason to make this behavior configurable. Link: https://lkml.kernel.org/r/20210806124715.17090-10-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: Dan Williams Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Hui Zhu Cc: Jason Wang Cc: Len Brown Cc: Marek Kedzierski Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 30 +++++++++++++++++++++++++ include/linux/memory.h | 3 +++ mm/memory_hotplug.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 89 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index b699ddc42693..440fd656c002 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -86,6 +86,7 @@ static DEFINE_XARRAY(memory_blocks); * Memory groups, indexed by memory group id (mgid). */ static DEFINE_XARRAY_FLAGS(memory_groups, XA_FLAGS_ALLOC); +#define MEMORY_GROUP_MARK_DYNAMIC XA_MARK_1 static BLOCKING_NOTIFIER_HEAD(memory_chain); @@ -939,6 +940,8 @@ static int memory_group_register(struct memory_group group) if (ret) { kfree(new_group); return ret; + } else if (group.is_dynamic) { + xa_set_mark(&memory_groups, mgid, MEMORY_GROUP_MARK_DYNAMIC); } return mgid; } @@ -1044,3 +1047,30 @@ struct memory_group *memory_group_find_by_id(int mgid) { return xa_load(&memory_groups, mgid); } + +/* + * This is an internal helper only to be used in core memory hotplug code to + * walk all dynamic memory groups excluding a given memory group, either + * belonging to a specific node, or belonging to any node. + */ +int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, + struct memory_group *excluded, void *arg) +{ + struct memory_group *group; + unsigned long index; + int ret = 0; + + xa_for_each_marked(&memory_groups, index, group, + MEMORY_GROUP_MARK_DYNAMIC) { + if (group == excluded) + continue; +#ifdef CONFIG_NUMA + if (nid != NUMA_NO_NODE && group->nid != nid) + continue; +#endif /* CONFIG_NUMA */ + ret = func(group, arg); + if (ret) + break; + } + return ret; +} diff --git a/include/linux/memory.h b/include/linux/memory.h index 6ffdc1db385f..cbcc43ad2b97 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -146,6 +146,9 @@ extern int memory_group_register_static(int nid, unsigned long max_pages); extern int memory_group_register_dynamic(int nid, unsigned long unit_pages); extern int memory_group_unregister(int mgid); struct memory_group *memory_group_find_by_id(int mgid); +typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *); +int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, + struct memory_group *excluded, void *arg); #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 248e2ba4ac59..b80fb8164fb8 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -752,11 +752,44 @@ static void auto_movable_stats_account_zone(struct auto_movable_stats *stats, #endif /* CONFIG_CMA */ } } +struct auto_movable_group_stats { + unsigned long movable_pages; + unsigned long req_kernel_early_pages; +}; -static bool auto_movable_can_online_movable(int nid, unsigned long nr_pages) +static int auto_movable_stats_account_group(struct memory_group *group, + void *arg) +{ + const int ratio = READ_ONCE(auto_movable_ratio); + struct auto_movable_group_stats *stats = arg; + long pages; + + /* + * We don't support modifying the config while the auto-movable online + * policy is already enabled. Just avoid the division by zero below. + */ + if (!ratio) + return 0; + + /* + * Calculate how many early kernel pages this group requires to + * satisfy the configured zone ratio. + */ + pages = group->present_movable_pages * 100 / ratio; + pages -= group->present_kernel_pages; + + if (pages > 0) + stats->req_kernel_early_pages += pages; + stats->movable_pages += group->present_movable_pages; + return 0; +} + +static bool auto_movable_can_online_movable(int nid, struct memory_group *group, + unsigned long nr_pages) { - struct auto_movable_stats stats = {}; unsigned long kernel_early_pages, movable_pages; + struct auto_movable_group_stats group_stats = {}; + struct auto_movable_stats stats = {}; pg_data_t *pgdat = NODE_DATA(nid); struct zone *zone; int i; @@ -777,6 +810,21 @@ static bool auto_movable_can_online_movable(int nid, unsigned long nr_pages) kernel_early_pages = stats.kernel_early_pages; movable_pages = stats.movable_pages; + /* + * Kernel memory inside dynamic memory group allows for more MOVABLE + * memory within the same group. Remove the effect of all but the + * current group from the stats. + */ + walk_dynamic_memory_groups(nid, auto_movable_stats_account_group, + group, &group_stats); + if (kernel_early_pages <= group_stats.req_kernel_early_pages) + return false; + kernel_early_pages -= group_stats.req_kernel_early_pages; + movable_pages -= group_stats.movable_pages; + + if (group && group->is_dynamic) + kernel_early_pages += group->present_kernel_pages; + /* * Test if we could online the given number of pages to ZONE_MOVABLE * and still stay in the configured ratio. @@ -834,6 +882,10 @@ static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn * with unmovable allocations). While there are corner cases where it might * still work, it is barely relevant in practice. * + * Exceptions are dynamic memory groups, which allow for more MOVABLE + * memory within the same memory group -- because in that case, there is + * coordination within the single memory device managed by a single driver. + * * We rely on "present pages" instead of "managed pages", as the latter is * highly unreliable and dynamic in virtualized environments, and does not * consider boot time allocations. For example, memory ballooning adjusts the @@ -899,12 +951,12 @@ static struct zone *auto_movable_zone_for_pfn(int nid, * nobody interferes, all will be MOVABLE if possible. */ nr_pages = max_pages - online_pages; - if (!auto_movable_can_online_movable(NUMA_NO_NODE, nr_pages)) + if (!auto_movable_can_online_movable(NUMA_NO_NODE, group, nr_pages)) goto kernel_zone; #ifdef CONFIG_NUMA if (auto_movable_numa_aware && - !auto_movable_can_online_movable(nid, nr_pages)) + !auto_movable_can_online_movable(nid, group, nr_pages)) goto kernel_zone; #endif /* CONFIG_NUMA */ -- cgit v1.2.3 From fe3df441ef885a75a3eff5e151ead1a92266d222 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 7 Sep 2021 19:55:55 -0700 Subject: mm: remove redundant compound_head() calling There is a READ_ONCE() in the macro of compound_head(), which will prevent compiler from optimizing the code when there are more than once calling of it in a function. Remove the redundant calling of compound_head() from page_to_index() and page_add_file_rmap() for better code generation. Link: https://lkml.kernel.org/r/20210811101431.83940-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: David Howells Cc: Matthew Wilcox (Oracle) Cc: William Kucharski Cc: Kirill A. Shutemov Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 7 +++---- mm/rmap.c | 6 ++++-- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ed02aa522263..904e57db3a7d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -521,18 +521,17 @@ static inline struct page *read_mapping_page(struct address_space *mapping, */ static inline pgoff_t page_to_index(struct page *page) { - pgoff_t pgoff; + struct page *head; if (likely(!PageTransTail(page))) return page->index; + head = compound_head(page); /* * We don't initialize ->index for tail pages: calculate based on * head page */ - pgoff = compound_head(page)->index; - pgoff += page - compound_head(page); - return pgoff; + return head->index + page - head; } extern pgoff_t hugetlb_basepage_index(struct page *page); diff --git a/mm/rmap.c b/mm/rmap.c index b9eb5c12f3fe..b2cebf35ffe7 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1230,11 +1230,13 @@ void page_add_file_rmap(struct page *page, bool compound) nr_pages); } else { if (PageTransCompound(page) && page_mapping(page)) { + struct page *head = compound_head(page); + VM_WARN_ON_ONCE(!PageLocked(page)); - SetPageDoubleMap(compound_head(page)); + SetPageDoubleMap(head); if (PageMlocked(page)) - clear_page_mlock(compound_head(page)); + clear_page_mlock(head); } if (!atomic_inc_and_test(&page->_mapcount)) goto out; -- cgit v1.2.3 From 82a70ce0426dd7c4099516175019dccbd18cebf9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Sep 2021 19:56:01 -0700 Subject: mm: move ioremap_page_range to vmalloc.c Patch series "small ioremap cleanups". The first patch moves a little code around the vmalloc/ioremap boundary following a bigger move by Nick earlier. The second enforces non-executable mapping on ioremap just like we do for vmap. No driver currently uses executable mappings anyway, as they should. This patch (of 2): This keeps it together with the implementation, and to remove the vmap_range wrapper. Link: https://lkml.kernel.org/r/20210824091259.1324527-1-hch@lst.de Link: https://lkml.kernel.org/r/20210824091259.1324527-2-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Nicholas Piggin Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 3 --- mm/Makefile | 3 ++- mm/ioremap.c | 25 ------------------------- mm/vmalloc.c | 22 +++++++++++++++++----- 4 files changed, 19 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 2644425b6dce..671d402c3778 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -225,9 +225,6 @@ static inline bool is_vm_area_hugepages(const void *addr) } #ifdef CONFIG_MMU -int vmap_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int max_page_shift); void vunmap_range(unsigned long addr, unsigned long end); static inline void set_vm_flush_reset_perms(void *addr) { diff --git a/mm/Makefile b/mm/Makefile index e3436741d539..0e0a5a6fe127 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -38,7 +38,7 @@ mmu-y := nommu.o mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \ mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \ msync.o page_vma_mapped.o pagewalk.o \ - pgtable-generic.o rmap.o vmalloc.o ioremap.o + pgtable-generic.o rmap.o vmalloc.o ifdef CONFIG_CROSS_MEMORY_ATTACH @@ -128,3 +128,4 @@ obj-$(CONFIG_PTDUMP_CORE) += ptdump.o obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o obj-$(CONFIG_IO_MAPPING) += io-mapping.o obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o +obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o diff --git a/mm/ioremap.c b/mm/ioremap.c index 8ee0136f8cb0..5fe598ecd9b7 100644 --- a/mm/ioremap.c +++ b/mm/ioremap.c @@ -8,33 +8,9 @@ */ #include #include -#include #include #include -#include -#include "pgalloc-track.h" - -#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -static unsigned int __ro_after_init iomap_max_page_shift = BITS_PER_LONG - 1; - -static int __init set_nohugeiomap(char *str) -{ - iomap_max_page_shift = PAGE_SHIFT; - return 0; -} -early_param("nohugeiomap", set_nohugeiomap); -#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ -static const unsigned int iomap_max_page_shift = PAGE_SHIFT; -#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ - -int ioremap_page_range(unsigned long addr, - unsigned long end, phys_addr_t phys_addr, pgprot_t prot) -{ - return vmap_range(addr, end, phys_addr, prot, iomap_max_page_shift); -} - -#ifdef CONFIG_GENERIC_IOREMAP void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot) { unsigned long offset, vaddr; @@ -71,4 +47,3 @@ void iounmap(volatile void __iomem *addr) vunmap((void *)((unsigned long)addr & PAGE_MASK)); } EXPORT_SYMBOL(iounmap); -#endif /* CONFIG_GENERIC_IOREMAP */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d5cd52805149..e44983fb2d15 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -44,6 +44,19 @@ #include "internal.h" #include "pgalloc-track.h" +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1; + +static int __init set_nohugeiomap(char *str) +{ + ioremap_max_page_shift = PAGE_SHIFT; + return 0; +} +early_param("nohugeiomap", set_nohugeiomap); +#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ +static const unsigned int ioremap_max_page_shift = PAGE_SHIFT; +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ + #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC static bool __ro_after_init vmap_allow_huge = true; @@ -298,15 +311,14 @@ static int vmap_range_noflush(unsigned long addr, unsigned long end, return err; } -int vmap_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int max_page_shift) +int ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot) { int err; - err = vmap_range_noflush(addr, end, phys_addr, prot, max_page_shift); + err = vmap_range_noflush(addr, end, phys_addr, prot, + ioremap_max_page_shift); flush_cache_vmap(addr, end); - return err; } -- cgit v1.2.3 From 513861202d1259e35934e206b79cd54f523d79b5 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 7 Sep 2021 19:56:09 -0700 Subject: highmem: don't disable preemption on RT in kmap_atomic() kmap_atomic() disables preemption and pagefaults for historical reasons. The conversion to kmap_local(), which only disables migration, cannot be done wholesale because quite some call sites need to be updated to accommodate with the changed semantics. On PREEMPT_RT enabled kernels the kmap_atomic() semantics are problematic due to the implicit disabling of preemption which makes it impossible to acquire 'sleeping' spinlocks within the kmap atomic sections. PREEMPT_RT replaces the preempt_disable() with a migrate_disable() for more than a decade. It could be argued that this is a justification to do this unconditionally, but PREEMPT_RT covers only a limited number of architectures and it disables some functionality which limits the coverage further. Limit the replacement to PREEMPT_RT for now. Link: https://lkml.kernel.org/r/20210810091116.pocdmaatdcogvdso@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Acked-by: Vlastimil Babka Cc: Thomas Gleixner Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem-internal.h | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 7902c7d8b55f..4aa1031d3e4c 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -90,7 +90,11 @@ static inline void __kunmap_local(void *vaddr) static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { - preempt_disable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + migrate_disable(); + else + preempt_disable(); + pagefault_disable(); return __kmap_local_page_prot(page, prot); } @@ -102,7 +106,11 @@ static inline void *kmap_atomic(struct page *page) static inline void *kmap_atomic_pfn(unsigned long pfn) { - preempt_disable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + migrate_disable(); + else + preempt_disable(); + pagefault_disable(); return __kmap_local_pfn_prot(pfn, kmap_prot); } @@ -111,7 +119,10 @@ static inline void __kunmap_atomic(void *addr) { kunmap_local_indexed(addr); pagefault_enable(); - preempt_enable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + migrate_enable(); + else + preempt_enable(); } unsigned int __nr_free_highpages(void); @@ -179,7 +190,10 @@ static inline void __kunmap_local(void *addr) static inline void *kmap_atomic(struct page *page) { - preempt_disable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + migrate_disable(); + else + preempt_disable(); pagefault_disable(); return page_address(page); } @@ -200,7 +214,10 @@ static inline void __kunmap_atomic(void *addr) kunmap_flush_on_unmap(addr); #endif pagefault_enable(); - preempt_enable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + migrate_enable(); + else + preempt_enable(); } static inline unsigned int nr_free_highpages(void) { return 0; } -- cgit v1.2.3 From 41c961b9013ee9b6d0491f6926df546e37964b1f Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 7 Sep 2021 19:56:15 -0700 Subject: mm: introduce PAGEFLAGS_MASK to replace ((1UL << NR_PAGEFLAGS) - 1) Instead of hard-coding ((1UL << NR_PAGEFLAGS) - 1) everywhere, introducing PAGEFLAGS_MASK to make the code clear to get the page flags. Link: https://lkml.kernel.org/r/20210819150712.59948-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Roman Gushchin Acked-by: Johannes Weiner Reviewed-by: Shakeel Butt Cc: Michal Hocko Cc: Vladimir Davydov Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 4 +++- include/trace/events/page_ref.h | 4 ++-- lib/test_printf.c | 2 +- lib/vsprintf.c | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5922031ffab6..6b8d66965145 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -178,6 +178,8 @@ enum pageflags { PG_reported = PG_uptodate, }; +#define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) + #ifndef __GENERATING_BOUNDS_H static inline unsigned long _compound_head(const struct page *page) @@ -859,7 +861,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ - (((1UL << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON) + (PAGEFLAGS_MASK & ~__PG_HWPOISON) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/include/trace/events/page_ref.h b/include/trace/events/page_ref.h index 5d2ea93956ce..8a99c1cd417b 100644 --- a/include/trace/events/page_ref.h +++ b/include/trace/events/page_ref.h @@ -38,7 +38,7 @@ DECLARE_EVENT_CLASS(page_ref_mod_template, TP_printk("pfn=0x%lx flags=%s count=%d mapcount=%d mapping=%p mt=%d val=%d", __entry->pfn, - show_page_flags(__entry->flags & ((1UL << NR_PAGEFLAGS) - 1)), + show_page_flags(__entry->flags & PAGEFLAGS_MASK), __entry->count, __entry->mapcount, __entry->mapping, __entry->mt, __entry->val) @@ -88,7 +88,7 @@ DECLARE_EVENT_CLASS(page_ref_mod_and_test_template, TP_printk("pfn=0x%lx flags=%s count=%d mapcount=%d mapping=%p mt=%d val=%d ret=%d", __entry->pfn, - show_page_flags(__entry->flags & ((1UL << NR_PAGEFLAGS) - 1)), + show_page_flags(__entry->flags & PAGEFLAGS_MASK), __entry->count, __entry->mapcount, __entry->mapping, __entry->mt, __entry->val, __entry->ret) diff --git a/lib/test_printf.c b/lib/test_printf.c index 8ac71aee46af..ec69953cf80c 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -614,7 +614,7 @@ page_flags_test(int section, int node, int zone, int last_cpupid, bool append = false; int i; - flags &= BIT(NR_PAGEFLAGS) - 1; + flags &= PAGEFLAGS_MASK; if (flags) { page_flags |= flags; snprintf(cmp_buf + size, BUF_SIZE - size, "%s", name); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 26c83943748a..cc7bdd3ac2ee 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2019,7 +2019,7 @@ static const struct page_flags_fields pff[] = { static char *format_page_flags(char *buf, char *end, unsigned long flags) { - unsigned long main_flags = flags & (BIT(NR_PAGEFLAGS) - 1); + unsigned long main_flags = flags & PAGEFLAGS_MASK; bool append = false; int i; -- cgit v1.2.3 From 2224d8485492e499ca2e5d25407f8502cc06f149 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:28 -0700 Subject: mm: introduce Data Access MONitor (DAMON) Patch series "Introduce Data Access MONitor (DAMON)", v34. Introduction ============ DAMON is a data access monitoring framework for the Linux kernel. The core mechanisms of DAMON called 'region based sampling' and 'adaptive regions adjustment' (refer to 'mechanisms.rst' in the 11th patch of this patchset for the detail) make it - accurate (The monitored information is useful for DRAM level memory management. It might not appropriate for Cache-level accuracy, though.), - light-weight (The monitoring overhead is low enough to be applied online while making no impact on the performance of the target workloads.), and - scalable (the upper-bound of the instrumentation overhead is controllable regardless of the size of target workloads.). Using this framework, therefore, several memory management mechanisms such as reclamation and THP can be optimized to aware real data access patterns. Experimental access pattern aware memory management optimization works that incurring high instrumentation overhead will be able to have another try. Though DAMON is for kernel subsystems, it can be easily exposed to the user space by writing a DAMON-wrapper kernel subsystem. Then, user space users who have some special workloads will be able to write personalized tools or applications for deeper understanding and specialized optimizations of their systems. DAMON is also merged in two public Amazon Linux kernel trees that based on v5.4.y[1] and v5.10.y[2]. [1] https://github.com/amazonlinux/linux/tree/amazon-5.4.y/master/mm/damon [2] https://github.com/amazonlinux/linux/tree/amazon-5.10.y/master/mm/damon The userspace tool[1] is available, released under GPLv2, and actively being maintained. I am also planning to implement another basic user interface in perf[2]. Also, the basic test suite for DAMON is available under GPLv2[3]. [1] https://github.com/awslabs/damo [2] https://lore.kernel.org/linux-mm/20210107120729.22328-1-sjpark@amazon.com/ [3] https://github.com/awslabs/damon-tests Long-term Plan -------------- DAMON is a part of a project called Data Access-aware Operating System (DAOS). As the name implies, I want to improve the performance and efficiency of systems using fine-grained data access patterns. The optimizations are for both kernel and user spaces. I will therefore modify or create kernel subsystems, export some of those to user space and implement user space library / tools. Below shows the layers and components for the project. --------------------------------------------------------------------------- Primitives: PTE Accessed bit, PG_idle, rmap, (Intel CMT), ... Framework: DAMON Features: DAMOS, virtual addr, physical addr, ... Applications: DAMON-debugfs, (DARC), ... ^^^^^^^^^^^^^^^^^^^^^^^ KERNEL SPACE ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Raw Interface: debugfs, (sysfs), (damonfs), tracepoints, (sys_damon), ... vvvvvvvvvvvvvvvvvvvvvvv USER SPACE vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv Library: (libdamon), ... Tools: DAMO, (perf), ... --------------------------------------------------------------------------- The components in parentheses or marked as '...' are not implemented yet but in the future plan. IOW, those are the TODO tasks of DAOS project. For more detail, please refer to the plans: https://lore.kernel.org/linux-mm/20201202082731.24828-1-sjpark@amazon.com/ Evaluations =========== We evaluated DAMON's overhead, monitoring quality and usefulness using 24 realistic workloads on my QEMU/KVM based virtual machine running a kernel that v24 DAMON patchset is applied. DAMON is lightweight. It increases system memory usage by 0.39% and slows target workloads down by 1.16%. DAMON is accurate and useful for memory management optimizations. An experimental DAMON-based operation scheme for THP, namely 'ethp', removes 76.15% of THP memory overheads while preserving 51.25% of THP speedup. Another experimental DAMON-based 'proactive reclamation' implementation, 'prcl', reduces 93.38% of residential sets and 23.63% of system memory footprint while incurring only 1.22% runtime overhead in the best case (parsec3/freqmine). NOTE that the experimental THP optimization and proactive reclamation are not for production but only for proof of concepts. Please refer to the official document[1] or "Documentation/admin-guide/mm: Add a document for DAMON" patch in this patchset for detailed evaluation setup and results. [1] https://damonitor.github.io/doc/html/latest-damon/admin-guide/mm/damon/eval.html Real-world User Story ===================== In summary, DAMON has used on production systems and proved its usefulness. DAMON as a profiler ------------------- We analyzed characteristics of a large scale production systems of our customers using DAMON. The systems utilize 70GB DRAM and 36 CPUs. From this, we were able to find interesting things below. There were obviously different access pattern under idle workload and active workload. Under the idle workload, it accessed large memory regions with low frequency, while the active workload accessed small memory regions with high freuqnecy. DAMON found a 7GB memory region that showing obviously high access frequency under the active workload. We believe this is the performance-effective working set and need to be protected. There was a 4KB memory region that showing highest access frequency under not only active but also idle workloads. We think this must be a hottest code section like thing that should never be paged out. For this analysis, DAMON used only 0.3-1% of single CPU time. Because we used recording-based analysis, it consumed about 3-12 MB of disk space per 20 minutes. This is only small amount of disk space, but we can further reduce the disk usage by using non-recording-based DAMON features. I'd like to argue that only DAMON can do such detailed analysis (finding 4KB highest region in 70GB memory) with the light overhead. DAMON as a system optimization tool ----------------------------------- We also found below potential performance problems on the systems and made DAMON-based solutions. The system doesn't want to make the workload suffer from the page reclamation and thus it utilizes enough DRAM but no swap device. However, we found the system is actively reclaiming file-backed pages, because the system has intensive file IO. The file IO turned out to be not performance critical for the workload, but the customer wanted to ensure performance critical file-backed pages like code section to not mistakenly be evicted. Using direct IO should or `mlock()` would be a straightforward solution, but modifying the user space code is not easy for the customer. Alternatively, we could use DAMON-based operation scheme[1]. By using it, we can ask DAMON to track access frequency of each region and make 'process_madvise(MADV_WILLNEED)[2]' call for regions having specific size and access frequency for a time interval. We also found the system is having high number of TLB misses. We tried 'always' THP enabled policy and it greatly reduced TLB misses, but the page reclamation also been more frequent due to the THP internal fragmentation caused memory bloat. We could try another DAMON-based operation scheme that applies 'MADV_HUGEPAGE' to memory regions having >=2MB size and high access frequency, while applying 'MADV_NOHUGEPAGE' to regions having <2MB size and low access frequency. We do not own the systems so we only reported the analysis results and possible optimization solutions to the customers. The customers satisfied about the analysis results and promised to try the optimization guides. [1] https://lore.kernel.org/linux-mm/20201006123931.5847-1-sjpark@amazon.com/ [2] https://lore.kernel.org/linux-api/20200622192900.22757-4-minchan@kernel.org/ Comparison with Idle Page Tracking ================================== Idle Page Tracking allows users to set and read idleness of pages using a bitmap file which represents each page with each bit of the file. One recommended usage of it is working set size detection. Users can do that by 1. find PFN of each page for workloads in interest, 2. set all the pages as idle by doing writes to the bitmap file, 3. wait until the workload accesses its working set, and 4. read the idleness of the pages again and count pages became not idle. NOTE: While Idle Page Tracking is for user space users, DAMON is primarily designed for kernel subsystems though it can easily exposed to the user space. Hence, this section only assumes such user space use of DAMON. For what use cases Idle Page Tracking would be better? ------------------------------------------------------ 1. Flexible usecases other than hotness monitoring. Because Idle Page Tracking allows users to control the primitive (Page idleness) by themselves, Idle Page Tracking users can do anything they want. Meanwhile, DAMON is primarily designed to monitor the hotness of each memory region. For this, DAMON asks users to provide sampling interval and aggregation interval. For the reason, there could be some use case that using Idle Page Tracking is simpler. 2. Physical memory monitoring. Idle Page Tracking receives PFN range as input, so natively supports physical memory monitoring. DAMON is designed to be extensible for multiple address spaces and use cases by implementing and using primitives for the given use case. Therefore, by theory, DAMON has no limitation in the type of target address space as long as primitives for the given address space exists. However, the default primitives introduced by this patchset supports only virtual address spaces. Therefore, for physical memory monitoring, you should implement your own primitives and use it, or simply use Idle Page Tracking. Nonetheless, RFC patchsets[1] for the physical memory address space primitives is already available. It also supports user memory same to Idle Page Tracking. [1] https://lore.kernel.org/linux-mm/20200831104730.28970-1-sjpark@amazon.com/ For what use cases DAMON is better? ----------------------------------- 1. Hotness Monitoring. Idle Page Tracking let users know only if a page frame is accessed or not. For hotness check, the user should write more code and use more memory. DAMON do that by itself. 2. Low Monitoring Overhead DAMON receives user's monitoring request with one step and then provide the results. So, roughly speaking, DAMON require only O(1) user/kernel context switches. In case of Idle Page Tracking, however, because the interface receives contiguous page frames, the number of user/kernel context switches increases as the monitoring target becomes complex and huge. As a result, the context switch overhead could be not negligible. Moreover, DAMON is born to handle with the monitoring overhead. Because the core mechanism is pure logical, Idle Page Tracking users might be able to implement the mechanism on their own, but it would be time consuming and the user/kernel context switching will still more frequent than that of DAMON. Also, the kernel subsystems cannot use the logic in this case. 3. Page granularity working set size detection. Until v22 of this patchset, this was categorized as the thing Idle Page Tracking could do better, because DAMON basically maintains additional metadata for each of the monitoring target regions. So, in the page granularity working set size detection use case, DAMON would incur (number of monitoring target pages * size of metadata) memory overhead. Size of the single metadata item is about 54 bytes, so assuming 4KB pages, about 1.3% of monitoring target pages will be additionally used. All essential metadata for Idle Page Tracking are embedded in 'struct page' and page table entries. Therefore, in this use case, only one counter variable for working set size accounting is required if Idle Page Tracking is used. There are more details to consider, but roughly speaking, this is true in most cases. However, the situation changed from v23. Now DAMON supports arbitrary types of monitoring targets, which don't use the metadata. Using that, DAMON can do the working set size detection with no additional space overhead but less user-kernel context switch. A first draft for the implementation of monitoring primitives for this usage is available in a DAMON development tree[1]. An RFC patchset for it based on this patchset will also be available soon. Since v24, the arbitrary type support is dropped from this patchset because this patchset doesn't introduce real use of the type. You can still get it from the DAMON development tree[2], though. [1] https://github.com/sjp38/linux/tree/damon/pgidle_hack [2] https://github.com/sjp38/linux/tree/damon/master 4. More future usecases While Idle Page Tracking has tight coupling with base primitives (PG_Idle and page table Accessed bits), DAMON is designed to be extensible for many use cases and address spaces. If you need some special address type or want to use special h/w access check primitives, you can write your own primitives for that and configure DAMON to use those. Therefore, if your use case could be changed a lot in future, using DAMON could be better. Can I use both Idle Page Tracking and DAMON? -------------------------------------------- Yes, though using them concurrently for overlapping memory regions could result in interference to each other. Nevertheless, such use case would be rare or makes no sense at all. Even in the case, the noise would bot be really significant. So, you can choose whatever you want depending on the characteristics of your use cases. More Information ================ We prepared a showcase web site[1] that you can get more information. There are - the official documentations[2], - the heatmap format dynamic access pattern of various realistic workloads for heap area[3], mmap()-ed area[4], and stack[5] area, - the dynamic working set size distribution[6] and chronological working set size changes[7], and - the latest performance test results[8]. [1] https://damonitor.github.io/_index [2] https://damonitor.github.io/doc/html/latest-damon [3] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.0.png.html [4] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.1.png.html [5] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.2.png.html [6] https://damonitor.github.io/test/result/visual/latest/rec.wss_sz.png.html [7] https://damonitor.github.io/test/result/visual/latest/rec.wss_time.png.html [8] https://damonitor.github.io/test/result/perf/latest/html/index.html Baseline and Complete Git Trees =============================== The patches are based on the latest -mm tree, specifically v5.14-rc1-mmots-2021-07-15-18-47 of https://github.com/hnaz/linux-mm. You can also clone the complete git tree: $ git clone git://github.com/sjp38/linux -b damon/patches/v34 The web is also available: https://github.com/sjp38/linux/releases/tag/damon/patches/v34 Development Trees ----------------- There are a couple of trees for entire DAMON patchset series and features for future release. - For latest release: https://github.com/sjp38/linux/tree/damon/master - For next release: https://github.com/sjp38/linux/tree/damon/next Long-term Support Trees ----------------------- For people who want to test DAMON but using LTS kernels, there are another couple of trees based on two latest LTS kernels respectively and containing the 'damon/master' backports. - For v5.4.y: https://github.com/sjp38/linux/tree/damon/for-v5.4.y - For v5.10.y: https://github.com/sjp38/linux/tree/damon/for-v5.10.y Amazon Linux Kernel Trees ------------------------- DAMON is also merged in two public Amazon Linux kernel trees that based on v5.4.y[1] and v5.10.y[2]. [1] https://github.com/amazonlinux/linux/tree/amazon-5.4.y/master/mm/damon [2] https://github.com/amazonlinux/linux/tree/amazon-5.10.y/master/mm/damon Git Tree for Diff of Patches ============================ For easy review of diff between different versions of each patch, I prepared a git tree containing all versions of the DAMON patchset series: https://github.com/sjp38/damon-patches You can clone it and use 'diff' for easy review of changes between different versions of the patchset. For example: $ git clone https://github.com/sjp38/damon-patches && cd damon-patches $ diff -u damon/v33 damon/v34 Sequence Of Patches =================== First three patches implement the core logics of DAMON. The 1st patch introduces basic sampling based hotness monitoring for arbitrary types of targets. Following two patches implement the core mechanisms for control of overhead and accuracy, namely regions based sampling (patch 2) and adaptive regions adjustment (patch 3). Now the essential parts of DAMON is complete, but it cannot work unless someone provides monitoring primitives for a specific use case. The following two patches make it just work for virtual address spaces monitoring. The 4th patch makes 'PG_idle' can be used by DAMON and the 5th patch implements the virtual memory address space specific monitoring primitives using page table Accessed bits and the 'PG_idle' page flag. Now DAMON just works for virtual address space monitoring via the kernel space api. To let the user space users can use DAMON, following four patches add interfaces for them. The 6th patch adds a tracepoint for monitoring results. The 7th patch implements a DAMON application kernel module, namely damon-dbgfs, that simply wraps DAMON and exposes DAMON interface to the user space via the debugfs interface. The 8th patch further exports pid of monitoring thread (kdamond) to user space for easier cpu usage accounting, and the 9th patch makes the debugfs interface to support multiple contexts. Three patches for maintainability follows. The 10th patch adds documentations for both the user space and the kernel space. The 11th patch provides unit tests (based on the kunit) while the 12th patch adds user space tests (based on the kselftest). Finally, the last patch (13th) updates the MAINTAINERS file. This patch (of 13): DAMON is a data access monitoring framework for the Linux kernel. The core mechanisms of DAMON make it - accurate (the monitoring output is useful enough for DRAM level performance-centric memory management; It might be inappropriate for CPU cache levels, though), - light-weight (the monitoring overhead is normally low enough to be applied online), and - scalable (the upper-bound of the overhead is in constant range regardless of the size of target workloads). Using this framework, hence, we can easily write efficient kernel space data access monitoring applications. For example, the kernel's memory management mechanisms can make advanced decisions using this. Experimental data access aware optimization works that incurring high access monitoring overhead could again be implemented on top of this. Due to its simple and flexible interface, providing user space interface would be also easy. Then, user space users who have some special workloads can write personalized applications for better understanding and optimizations of their workloads and systems. === Nevertheless, this commit is defining and implementing only basic access check part without the overhead-accuracy handling core logic. The basic access check is as below. The output of DAMON says what memory regions are how frequently accessed for a given duration. The resolution of the access frequency is controlled by setting ``sampling interval`` and ``aggregation interval``. In detail, DAMON checks access to each page per ``sampling interval`` and aggregates the results. In other words, counts the number of the accesses to each region. After each ``aggregation interval`` passes, DAMON calls callback functions that previously registered by users so that users can read the aggregated results and then clears the results. This can be described in below simple pseudo-code:: init() while monitoring_on: for page in monitoring_target: if accessed(page): nr_accesses[page] += 1 if time() % aggregation_interval == 0: for callback in user_registered_callbacks: callback(monitoring_target, nr_accesses) for page in monitoring_target: nr_accesses[page] = 0 if time() % update_interval == 0: update() sleep(sampling interval) The target regions constructed at the beginning of the monitoring and updated after each ``regions_update_interval``, because the target regions could be dynamically changed (e.g., mmap() or memory hotplug). The monitoring overhead of this mechanism will arbitrarily increase as the size of the target workload grows. The basic monitoring primitives for actual access check and dynamic target regions construction aren't in the core part of DAMON. Instead, it allows users to implement their own primitives that are optimized for their use case and configure DAMON to use those. In other words, users cannot use current version of DAMON without some additional works. Following commits will implement the core mechanisms for the overhead-accuracy control and default primitives implementations. Link: https://lkml.kernel.org/r/20210716081449.22187-1-sj38.park@gmail.com Link: https://lkml.kernel.org/r/20210716081449.22187-2-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Fernand Sieber Acked-by: Shakeel Butt Cc: Jonathan Cameron Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Joe Perches Cc: Mel Gorman Cc: Maximilian Heyne Cc: Minchan Kim Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: David Rientjes Cc: Steven Rostedt (VMware) Cc: Shuah Khan Cc: Vlastimil Babka Cc: Vladimir Davydov Cc: Brendan Higgins Cc: Markus Boehme Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 167 ++++++++++++++++++++++++++ mm/Kconfig | 2 + mm/Makefile | 1 + mm/damon/Kconfig | 15 +++ mm/damon/Makefile | 3 + mm/damon/core.c | 320 ++++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 508 insertions(+) create mode 100644 include/linux/damon.h create mode 100644 mm/damon/Kconfig create mode 100644 mm/damon/Makefile create mode 100644 mm/damon/core.c (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h new file mode 100644 index 000000000000..2f652602b1ea --- /dev/null +++ b/include/linux/damon.h @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * DAMON api + * + * Author: SeongJae Park + */ + +#ifndef _DAMON_H_ +#define _DAMON_H_ + +#include +#include +#include + +struct damon_ctx; + +/** + * struct damon_primitive Monitoring primitives for given use cases. + * + * @init: Initialize primitive-internal data structures. + * @update: Update primitive-internal data structures. + * @prepare_access_checks: Prepare next access check of target regions. + * @check_accesses: Check the accesses to target regions. + * @reset_aggregated: Reset aggregated accesses monitoring results. + * @target_valid: Determine if the target is valid. + * @cleanup: Clean up the context. + * + * DAMON can be extended for various address spaces and usages. For this, + * users should register the low level primitives for their target address + * space and usecase via the &damon_ctx.primitive. Then, the monitoring thread + * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting + * the monitoring, @update after each &damon_ctx.primitive_update_interval, and + * @check_accesses, @target_valid and @prepare_access_checks after each + * &damon_ctx.sample_interval. Finally, @reset_aggregated is called after each + * &damon_ctx.aggr_interval. + * + * @init should initialize primitive-internal data structures. For example, + * this could be used to construct proper monitoring target regions and link + * those to @damon_ctx.target. + * @update should update the primitive-internal data structures. For example, + * this could be used to update monitoring target regions for current status. + * @prepare_access_checks should manipulate the monitoring regions to be + * prepared for the next access check. + * @check_accesses should check the accesses to each region that made after the + * last preparation and update the number of observed accesses of each region. + * @reset_aggregated should reset the access monitoring results that aggregated + * by @check_accesses. + * @target_valid should check whether the target is still valid for the + * monitoring. + * @cleanup is called from @kdamond just before its termination. + */ +struct damon_primitive { + void (*init)(struct damon_ctx *context); + void (*update)(struct damon_ctx *context); + void (*prepare_access_checks)(struct damon_ctx *context); + void (*check_accesses)(struct damon_ctx *context); + void (*reset_aggregated)(struct damon_ctx *context); + bool (*target_valid)(void *target); + void (*cleanup)(struct damon_ctx *context); +}; + +/* + * struct damon_callback Monitoring events notification callbacks. + * + * @before_start: Called before starting the monitoring. + * @after_sampling: Called after each sampling. + * @after_aggregation: Called after each aggregation. + * @before_terminate: Called before terminating the monitoring. + * @private: User private data. + * + * The monitoring thread (&damon_ctx.kdamond) calls @before_start and + * @before_terminate just before starting and finishing the monitoring, + * respectively. Therefore, those are good places for installing and cleaning + * @private. + * + * The monitoring thread calls @after_sampling and @after_aggregation for each + * of the sampling intervals and aggregation intervals, respectively. + * Therefore, users can safely access the monitoring results without additional + * protection. For the reason, users are recommended to use these callback for + * the accesses to the results. + * + * If any callback returns non-zero, monitoring stops. + */ +struct damon_callback { + void *private; + + int (*before_start)(struct damon_ctx *context); + int (*after_sampling)(struct damon_ctx *context); + int (*after_aggregation)(struct damon_ctx *context); + int (*before_terminate)(struct damon_ctx *context); +}; + +/** + * struct damon_ctx - Represents a context for each monitoring. This is the + * main interface that allows users to set the attributes and get the results + * of the monitoring. + * + * @sample_interval: The time between access samplings. + * @aggr_interval: The time between monitor results aggregations. + * @primitive_update_interval: The time between monitoring primitive updates. + * + * For each @sample_interval, DAMON checks whether each region is accessed or + * not. It aggregates and keeps the access information (number of accesses to + * each region) for @aggr_interval time. DAMON also checks whether the target + * memory regions need update (e.g., by ``mmap()`` calls from the application, + * in case of virtual memory monitoring) and applies the changes for each + * @primitive_update_interval. All time intervals are in micro-seconds. + * Please refer to &struct damon_primitive and &struct damon_callback for more + * detail. + * + * @kdamond: Kernel thread who does the monitoring. + * @kdamond_stop: Notifies whether kdamond should stop. + * @kdamond_lock: Mutex for the synchronizations with @kdamond. + * + * For each monitoring context, one kernel thread for the monitoring is + * created. The pointer to the thread is stored in @kdamond. + * + * Once started, the monitoring thread runs until explicitly required to be + * terminated or every monitoring target is invalid. The validity of the + * targets is checked via the &damon_primitive.target_valid of @primitive. The + * termination can also be explicitly requested by writing non-zero to + * @kdamond_stop. The thread sets @kdamond to NULL when it terminates. + * Therefore, users can know whether the monitoring is ongoing or terminated by + * reading @kdamond. Reads and writes to @kdamond and @kdamond_stop from + * outside of the monitoring thread must be protected by @kdamond_lock. + * + * Note that the monitoring thread protects only @kdamond and @kdamond_stop via + * @kdamond_lock. Accesses to other fields must be protected by themselves. + * + * @primitive: Set of monitoring primitives for given use cases. + * @callback: Set of callbacks for monitoring events notifications. + * + * @target: Pointer to the user-defined monitoring target. + */ +struct damon_ctx { + unsigned long sample_interval; + unsigned long aggr_interval; + unsigned long primitive_update_interval; + +/* private: internal use only */ + struct timespec64 last_aggregation; + struct timespec64 last_primitive_update; + +/* public: */ + struct task_struct *kdamond; + bool kdamond_stop; + struct mutex kdamond_lock; + + struct damon_primitive primitive; + struct damon_callback callback; + + void *target; +}; + +#ifdef CONFIG_DAMON + +struct damon_ctx *damon_new_ctx(void); +void damon_destroy_ctx(struct damon_ctx *ctx); +int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, + unsigned long aggr_int, unsigned long primitive_upd_int); + +int damon_start(struct damon_ctx **ctxs, int nr_ctxs); +int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); + +#endif /* CONFIG_DAMON */ + +#endif /* _DAMON_H */ diff --git a/mm/Kconfig b/mm/Kconfig index 14d5d2837737..8459167b0294 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -886,4 +886,6 @@ config IO_MAPPING config SECRETMEM def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED +source "mm/damon/Kconfig" + endmenu diff --git a/mm/Makefile b/mm/Makefile index 0e0a5a6fe127..fc60a40ce954 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -118,6 +118,7 @@ obj-$(CONFIG_CMA_SYSFS) += cma_sysfs.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o +obj-$(CONFIG_DAMON) += damon/ obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o obj-$(CONFIG_ZONE_DEVICE) += memremap.o diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig new file mode 100644 index 000000000000..d00e99ac1a15 --- /dev/null +++ b/mm/damon/Kconfig @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0-only + +menu "Data Access Monitoring" + +config DAMON + bool "DAMON: Data Access Monitoring Framework" + help + This builds a framework that allows kernel subsystems to monitor + access frequency of each memory region. The information can be useful + for performance-centric DRAM level memory management. + + See https://damonitor.github.io/doc/html/latest-damon/index.html for + more information. + +endmenu diff --git a/mm/damon/Makefile b/mm/damon/Makefile new file mode 100644 index 000000000000..4fd2edb4becf --- /dev/null +++ b/mm/damon/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_DAMON) := core.o diff --git a/mm/damon/core.c b/mm/damon/core.c new file mode 100644 index 000000000000..651590bf49b1 --- /dev/null +++ b/mm/damon/core.c @@ -0,0 +1,320 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Data Access Monitor + * + * Author: SeongJae Park + */ + +#define pr_fmt(fmt) "damon: " fmt + +#include +#include +#include +#include + +static DEFINE_MUTEX(damon_lock); +static int nr_running_ctxs; + +struct damon_ctx *damon_new_ctx(void) +{ + struct damon_ctx *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; + + ctx->sample_interval = 5 * 1000; + ctx->aggr_interval = 100 * 1000; + ctx->primitive_update_interval = 60 * 1000 * 1000; + + ktime_get_coarse_ts64(&ctx->last_aggregation); + ctx->last_primitive_update = ctx->last_aggregation; + + mutex_init(&ctx->kdamond_lock); + + ctx->target = NULL; + + return ctx; +} + +void damon_destroy_ctx(struct damon_ctx *ctx) +{ + if (ctx->primitive.cleanup) + ctx->primitive.cleanup(ctx); + kfree(ctx); +} + +/** + * damon_set_attrs() - Set attributes for the monitoring. + * @ctx: monitoring context + * @sample_int: time interval between samplings + * @aggr_int: time interval between aggregations + * @primitive_upd_int: time interval between monitoring primitive updates + * + * This function should not be called while the kdamond is running. + * Every time interval is in micro-seconds. + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, + unsigned long aggr_int, unsigned long primitive_upd_int) +{ + ctx->sample_interval = sample_int; + ctx->aggr_interval = aggr_int; + ctx->primitive_update_interval = primitive_upd_int; + + return 0; +} + +static bool damon_kdamond_running(struct damon_ctx *ctx) +{ + bool running; + + mutex_lock(&ctx->kdamond_lock); + running = ctx->kdamond != NULL; + mutex_unlock(&ctx->kdamond_lock); + + return running; +} + +static int kdamond_fn(void *data); + +/* + * __damon_start() - Starts monitoring with given context. + * @ctx: monitoring context + * + * This function should be called while damon_lock is hold. + * + * Return: 0 on success, negative error code otherwise. + */ +static int __damon_start(struct damon_ctx *ctx) +{ + int err = -EBUSY; + + mutex_lock(&ctx->kdamond_lock); + if (!ctx->kdamond) { + err = 0; + ctx->kdamond_stop = false; + ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", + nr_running_ctxs); + if (IS_ERR(ctx->kdamond)) { + err = PTR_ERR(ctx->kdamond); + ctx->kdamond = 0; + } + } + mutex_unlock(&ctx->kdamond_lock); + + return err; +} + +/** + * damon_start() - Starts the monitorings for a given group of contexts. + * @ctxs: an array of the pointers for contexts to start monitoring + * @nr_ctxs: size of @ctxs + * + * This function starts a group of monitoring threads for a group of monitoring + * contexts. One thread per each context is created and run in parallel. The + * caller should handle synchronization between the threads by itself. If a + * group of threads that created by other 'damon_start()' call is currently + * running, this function does nothing but returns -EBUSY. + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_start(struct damon_ctx **ctxs, int nr_ctxs) +{ + int i; + int err = 0; + + mutex_lock(&damon_lock); + if (nr_running_ctxs) { + mutex_unlock(&damon_lock); + return -EBUSY; + } + + for (i = 0; i < nr_ctxs; i++) { + err = __damon_start(ctxs[i]); + if (err) + break; + nr_running_ctxs++; + } + mutex_unlock(&damon_lock); + + return err; +} + +/* + * __damon_stop() - Stops monitoring of given context. + * @ctx: monitoring context + * + * Return: 0 on success, negative error code otherwise. + */ +static int __damon_stop(struct damon_ctx *ctx) +{ + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + ctx->kdamond_stop = true; + mutex_unlock(&ctx->kdamond_lock); + while (damon_kdamond_running(ctx)) + usleep_range(ctx->sample_interval, + ctx->sample_interval * 2); + return 0; + } + mutex_unlock(&ctx->kdamond_lock); + + return -EPERM; +} + +/** + * damon_stop() - Stops the monitorings for a given group of contexts. + * @ctxs: an array of the pointers for contexts to stop monitoring + * @nr_ctxs: size of @ctxs + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_stop(struct damon_ctx **ctxs, int nr_ctxs) +{ + int i, err = 0; + + for (i = 0; i < nr_ctxs; i++) { + /* nr_running_ctxs is decremented in kdamond_fn */ + err = __damon_stop(ctxs[i]); + if (err) + return err; + } + + return err; +} + +/* + * damon_check_reset_time_interval() - Check if a time interval is elapsed. + * @baseline: the time to check whether the interval has elapsed since + * @interval: the time interval (microseconds) + * + * See whether the given time interval has passed since the given baseline + * time. If so, it also updates the baseline to current time for next check. + * + * Return: true if the time interval has passed, or false otherwise. + */ +static bool damon_check_reset_time_interval(struct timespec64 *baseline, + unsigned long interval) +{ + struct timespec64 now; + + ktime_get_coarse_ts64(&now); + if ((timespec64_to_ns(&now) - timespec64_to_ns(baseline)) < + interval * 1000) + return false; + *baseline = now; + return true; +} + +/* + * Check whether it is time to flush the aggregated information + */ +static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx) +{ + return damon_check_reset_time_interval(&ctx->last_aggregation, + ctx->aggr_interval); +} + +/* + * Check whether it is time to check and apply the target monitoring regions + * + * Returns true if it is. + */ +static bool kdamond_need_update_primitive(struct damon_ctx *ctx) +{ + return damon_check_reset_time_interval(&ctx->last_primitive_update, + ctx->primitive_update_interval); +} + +/* + * Check whether current monitoring should be stopped + * + * The monitoring is stopped when either the user requested to stop, or all + * monitoring targets are invalid. + * + * Returns true if need to stop current monitoring. + */ +static bool kdamond_need_stop(struct damon_ctx *ctx) +{ + bool stop; + + mutex_lock(&ctx->kdamond_lock); + stop = ctx->kdamond_stop; + mutex_unlock(&ctx->kdamond_lock); + if (stop) + return true; + + if (!ctx->primitive.target_valid) + return false; + + return !ctx->primitive.target_valid(ctx->target); +} + +static void set_kdamond_stop(struct damon_ctx *ctx) +{ + mutex_lock(&ctx->kdamond_lock); + ctx->kdamond_stop = true; + mutex_unlock(&ctx->kdamond_lock); +} + +/* + * The monitoring daemon that runs as a kernel thread + */ +static int kdamond_fn(void *data) +{ + struct damon_ctx *ctx = (struct damon_ctx *)data; + + mutex_lock(&ctx->kdamond_lock); + pr_info("kdamond (%d) starts\n", ctx->kdamond->pid); + mutex_unlock(&ctx->kdamond_lock); + + if (ctx->primitive.init) + ctx->primitive.init(ctx); + if (ctx->callback.before_start && ctx->callback.before_start(ctx)) + set_kdamond_stop(ctx); + + while (!kdamond_need_stop(ctx)) { + if (ctx->primitive.prepare_access_checks) + ctx->primitive.prepare_access_checks(ctx); + if (ctx->callback.after_sampling && + ctx->callback.after_sampling(ctx)) + set_kdamond_stop(ctx); + + usleep_range(ctx->sample_interval, ctx->sample_interval + 1); + + if (ctx->primitive.check_accesses) + ctx->primitive.check_accesses(ctx); + + if (kdamond_aggregate_interval_passed(ctx)) { + if (ctx->callback.after_aggregation && + ctx->callback.after_aggregation(ctx)) + set_kdamond_stop(ctx); + if (ctx->primitive.reset_aggregated) + ctx->primitive.reset_aggregated(ctx); + } + + if (kdamond_need_update_primitive(ctx)) { + if (ctx->primitive.update) + ctx->primitive.update(ctx); + } + } + + if (ctx->callback.before_terminate && + ctx->callback.before_terminate(ctx)) + set_kdamond_stop(ctx); + if (ctx->primitive.cleanup) + ctx->primitive.cleanup(ctx); + + pr_debug("kdamond (%d) finishes\n", ctx->kdamond->pid); + mutex_lock(&ctx->kdamond_lock); + ctx->kdamond = NULL; + mutex_unlock(&ctx->kdamond_lock); + + mutex_lock(&damon_lock); + nr_running_ctxs--; + mutex_unlock(&damon_lock); + + do_exit(0); +} -- cgit v1.2.3 From f23b8eee1871a6db5c37f90831147de5426c40b7 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:32 -0700 Subject: mm/damon/core: implement region-based sampling To avoid the unbounded increase of the overhead, DAMON groups adjacent pages that are assumed to have the same access frequencies into a region. As long as the assumption (pages in a region have the same access frequencies) is kept, only one page in the region is required to be checked. Thus, for each ``sampling interval``, 1. the 'prepare_access_checks' primitive picks one page in each region, 2. waits for one ``sampling interval``, 3. checks whether the page is accessed meanwhile, and 4. increases the access count of the region if so. Therefore, the monitoring overhead is controllable by adjusting the number of regions. DAMON allows both the underlying primitives and user callbacks to adjust regions for the trade-off. In other words, this commit makes DAMON to use not only time-based sampling but also space-based sampling. This scheme, however, cannot preserve the quality of the output if the assumption is not guaranteed. Next commit will address this problem. Link: https://lkml.kernel.org/r/20210716081449.22187-3-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Fernand Sieber Acked-by: Shakeel Butt Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 77 +++++++++++++++++++++++++-- mm/damon/core.c | 143 ++++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 213 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 2f652602b1ea..67db309ad61b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -12,6 +12,48 @@ #include #include +/** + * struct damon_addr_range - Represents an address region of [@start, @end). + * @start: Start address of the region (inclusive). + * @end: End address of the region (exclusive). + */ +struct damon_addr_range { + unsigned long start; + unsigned long end; +}; + +/** + * struct damon_region - Represents a monitoring target region. + * @ar: The address range of the region. + * @sampling_addr: Address of the sample for the next access check. + * @nr_accesses: Access frequency of this region. + * @list: List head for siblings. + */ +struct damon_region { + struct damon_addr_range ar; + unsigned long sampling_addr; + unsigned int nr_accesses; + struct list_head list; +}; + +/** + * struct damon_target - Represents a monitoring target. + * @id: Unique identifier for this target. + * @regions_list: Head of the monitoring target regions of this target. + * @list: List head for siblings. + * + * Each monitoring context could have multiple targets. For example, a context + * for virtual memory address spaces could have multiple target processes. The + * @id of each target should be unique among the targets of the context. For + * example, in the virtual address monitoring context, it could be a pidfd or + * an address of an mm_struct. + */ +struct damon_target { + unsigned long id; + struct list_head regions_list; + struct list_head list; +}; + struct damon_ctx; /** @@ -36,7 +78,7 @@ struct damon_ctx; * * @init should initialize primitive-internal data structures. For example, * this could be used to construct proper monitoring target regions and link - * those to @damon_ctx.target. + * those to @damon_ctx.adaptive_targets. * @update should update the primitive-internal data structures. For example, * this could be used to update monitoring target regions for current status. * @prepare_access_checks should manipulate the monitoring regions to be @@ -130,7 +172,7 @@ struct damon_callback { * @primitive: Set of monitoring primitives for given use cases. * @callback: Set of callbacks for monitoring events notifications. * - * @target: Pointer to the user-defined monitoring target. + * @region_targets: Head of monitoring targets (&damon_target) list. */ struct damon_ctx { unsigned long sample_interval; @@ -149,11 +191,40 @@ struct damon_ctx { struct damon_primitive primitive; struct damon_callback callback; - void *target; + struct list_head region_targets; }; +#define damon_next_region(r) \ + (container_of(r->list.next, struct damon_region, list)) + +#define damon_prev_region(r) \ + (container_of(r->list.prev, struct damon_region, list)) + +#define damon_for_each_region(r, t) \ + list_for_each_entry(r, &t->regions_list, list) + +#define damon_for_each_region_safe(r, next, t) \ + list_for_each_entry_safe(r, next, &t->regions_list, list) + +#define damon_for_each_target(t, ctx) \ + list_for_each_entry(t, &(ctx)->region_targets, list) + +#define damon_for_each_target_safe(t, next, ctx) \ + list_for_each_entry_safe(t, next, &(ctx)->region_targets, list) + #ifdef CONFIG_DAMON +struct damon_region *damon_new_region(unsigned long start, unsigned long end); +inline void damon_insert_region(struct damon_region *r, + struct damon_region *prev, struct damon_region *next); +void damon_add_region(struct damon_region *r, struct damon_target *t); +void damon_destroy_region(struct damon_region *r); + +struct damon_target *damon_new_target(unsigned long id); +void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); +void damon_free_target(struct damon_target *t); +void damon_destroy_target(struct damon_target *t); + struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, diff --git a/mm/damon/core.c b/mm/damon/core.c index 651590bf49b1..947486a150ce 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -15,6 +15,101 @@ static DEFINE_MUTEX(damon_lock); static int nr_running_ctxs; +/* + * Construct a damon_region struct + * + * Returns the pointer to the new struct if success, or NULL otherwise + */ +struct damon_region *damon_new_region(unsigned long start, unsigned long end) +{ + struct damon_region *region; + + region = kmalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return NULL; + + region->ar.start = start; + region->ar.end = end; + region->nr_accesses = 0; + INIT_LIST_HEAD(®ion->list); + + return region; +} + +/* + * Add a region between two other regions + */ +inline void damon_insert_region(struct damon_region *r, + struct damon_region *prev, struct damon_region *next) +{ + __list_add(&r->list, &prev->list, &next->list); +} + +void damon_add_region(struct damon_region *r, struct damon_target *t) +{ + list_add_tail(&r->list, &t->regions_list); +} + +static void damon_del_region(struct damon_region *r) +{ + list_del(&r->list); +} + +static void damon_free_region(struct damon_region *r) +{ + kfree(r); +} + +void damon_destroy_region(struct damon_region *r) +{ + damon_del_region(r); + damon_free_region(r); +} + +/* + * Construct a damon_target struct + * + * Returns the pointer to the new struct if success, or NULL otherwise + */ +struct damon_target *damon_new_target(unsigned long id) +{ + struct damon_target *t; + + t = kmalloc(sizeof(*t), GFP_KERNEL); + if (!t) + return NULL; + + t->id = id; + INIT_LIST_HEAD(&t->regions_list); + + return t; +} + +void damon_add_target(struct damon_ctx *ctx, struct damon_target *t) +{ + list_add_tail(&t->list, &ctx->region_targets); +} + +static void damon_del_target(struct damon_target *t) +{ + list_del(&t->list); +} + +void damon_free_target(struct damon_target *t) +{ + struct damon_region *r, *next; + + damon_for_each_region_safe(r, next, t) + damon_free_region(r); + kfree(t); +} + +void damon_destroy_target(struct damon_target *t) +{ + damon_del_target(t); + damon_free_target(t); +} + struct damon_ctx *damon_new_ctx(void) { struct damon_ctx *ctx; @@ -32,15 +127,27 @@ struct damon_ctx *damon_new_ctx(void) mutex_init(&ctx->kdamond_lock); - ctx->target = NULL; + INIT_LIST_HEAD(&ctx->region_targets); return ctx; } -void damon_destroy_ctx(struct damon_ctx *ctx) +static void damon_destroy_targets(struct damon_ctx *ctx) { - if (ctx->primitive.cleanup) + struct damon_target *t, *next_t; + + if (ctx->primitive.cleanup) { ctx->primitive.cleanup(ctx); + return; + } + + damon_for_each_target_safe(t, next_t, ctx) + damon_destroy_target(t); +} + +void damon_destroy_ctx(struct damon_ctx *ctx) +{ + damon_destroy_targets(ctx); kfree(ctx); } @@ -217,6 +324,21 @@ static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx) ctx->aggr_interval); } +/* + * Reset the aggregated monitoring results ('nr_accesses' of each region). + */ +static void kdamond_reset_aggregated(struct damon_ctx *c) +{ + struct damon_target *t; + + damon_for_each_target(t, c) { + struct damon_region *r; + + damon_for_each_region(r, t) + r->nr_accesses = 0; + } +} + /* * Check whether it is time to check and apply the target monitoring regions * @@ -238,6 +360,7 @@ static bool kdamond_need_update_primitive(struct damon_ctx *ctx) */ static bool kdamond_need_stop(struct damon_ctx *ctx) { + struct damon_target *t; bool stop; mutex_lock(&ctx->kdamond_lock); @@ -249,7 +372,12 @@ static bool kdamond_need_stop(struct damon_ctx *ctx) if (!ctx->primitive.target_valid) return false; - return !ctx->primitive.target_valid(ctx->target); + damon_for_each_target(t, ctx) { + if (ctx->primitive.target_valid(t)) + return false; + } + + return true; } static void set_kdamond_stop(struct damon_ctx *ctx) @@ -265,6 +393,8 @@ static void set_kdamond_stop(struct damon_ctx *ctx) static int kdamond_fn(void *data) { struct damon_ctx *ctx = (struct damon_ctx *)data; + struct damon_target *t; + struct damon_region *r, *next; mutex_lock(&ctx->kdamond_lock); pr_info("kdamond (%d) starts\n", ctx->kdamond->pid); @@ -291,6 +421,7 @@ static int kdamond_fn(void *data) if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) set_kdamond_stop(ctx); + kdamond_reset_aggregated(ctx); if (ctx->primitive.reset_aggregated) ctx->primitive.reset_aggregated(ctx); } @@ -300,6 +431,10 @@ static int kdamond_fn(void *data) ctx->primitive.update(ctx); } } + damon_for_each_target(t, ctx) { + damon_for_each_region_safe(r, next, t) + damon_destroy_region(r); + } if (ctx->callback.before_terminate && ctx->callback.before_terminate(ctx)) -- cgit v1.2.3 From b9a6ac4e4ede4172d165c133398b93e3233b0ba7 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:36 -0700 Subject: mm/damon: adaptively adjust regions Even somehow the initial monitoring target regions are well constructed to fulfill the assumption (pages in same region have similar access frequencies), the data access pattern can be dynamically changed. This will result in low monitoring quality. To keep the assumption as much as possible, DAMON adaptively merges and splits each region based on their access frequency. For each ``aggregation interval``, it compares the access frequencies of adjacent regions and merges those if the frequency difference is small. Then, after it reports and clears the aggregated access frequency of each region, it splits each region into two or three regions if the total number of regions will not exceed the user-specified maximum number of regions after the split. In this way, DAMON provides its best-effort quality and minimal overhead while keeping the upper-bound overhead that users set. Link: https://lkml.kernel.org/r/20210716081449.22187-4-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Fernand Sieber Acked-by: Shakeel Butt Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 30 +++++-- mm/damon/core.c | 224 ++++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 237 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 67db309ad61b..ce2a84b26cd7 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -12,6 +12,9 @@ #include #include +/* Minimal region size. Every damon_region is aligned by this. */ +#define DAMON_MIN_REGION PAGE_SIZE + /** * struct damon_addr_range - Represents an address region of [@start, @end). * @start: Start address of the region (inclusive). @@ -39,6 +42,7 @@ struct damon_region { /** * struct damon_target - Represents a monitoring target. * @id: Unique identifier for this target. + * @nr_regions: Number of monitoring target regions of this target. * @regions_list: Head of the monitoring target regions of this target. * @list: List head for siblings. * @@ -50,6 +54,7 @@ struct damon_region { */ struct damon_target { unsigned long id; + unsigned int nr_regions; struct list_head regions_list; struct list_head list; }; @@ -85,6 +90,8 @@ struct damon_ctx; * prepared for the next access check. * @check_accesses should check the accesses to each region that made after the * last preparation and update the number of observed accesses of each region. + * It should also return max number of observed accesses that made as a result + * of its update. The value will be used for regions adjustment threshold. * @reset_aggregated should reset the access monitoring results that aggregated * by @check_accesses. * @target_valid should check whether the target is still valid for the @@ -95,7 +102,7 @@ struct damon_primitive { void (*init)(struct damon_ctx *context); void (*update)(struct damon_ctx *context); void (*prepare_access_checks)(struct damon_ctx *context); - void (*check_accesses)(struct damon_ctx *context); + unsigned int (*check_accesses)(struct damon_ctx *context); void (*reset_aggregated)(struct damon_ctx *context); bool (*target_valid)(void *target); void (*cleanup)(struct damon_ctx *context); @@ -172,7 +179,9 @@ struct damon_callback { * @primitive: Set of monitoring primitives for given use cases. * @callback: Set of callbacks for monitoring events notifications. * - * @region_targets: Head of monitoring targets (&damon_target) list. + * @min_nr_regions: The minimum number of adaptive monitoring regions. + * @max_nr_regions: The maximum number of adaptive monitoring regions. + * @adaptive_targets: Head of monitoring targets (&damon_target) list. */ struct damon_ctx { unsigned long sample_interval; @@ -191,7 +200,9 @@ struct damon_ctx { struct damon_primitive primitive; struct damon_callback callback; - struct list_head region_targets; + unsigned long min_nr_regions; + unsigned long max_nr_regions; + struct list_head adaptive_targets; }; #define damon_next_region(r) \ @@ -207,28 +218,31 @@ struct damon_ctx { list_for_each_entry_safe(r, next, &t->regions_list, list) #define damon_for_each_target(t, ctx) \ - list_for_each_entry(t, &(ctx)->region_targets, list) + list_for_each_entry(t, &(ctx)->adaptive_targets, list) #define damon_for_each_target_safe(t, next, ctx) \ - list_for_each_entry_safe(t, next, &(ctx)->region_targets, list) + list_for_each_entry_safe(t, next, &(ctx)->adaptive_targets, list) #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); inline void damon_insert_region(struct damon_region *r, - struct damon_region *prev, struct damon_region *next); + struct damon_region *prev, struct damon_region *next, + struct damon_target *t); void damon_add_region(struct damon_region *r, struct damon_target *t); -void damon_destroy_region(struct damon_region *r); +void damon_destroy_region(struct damon_region *r, struct damon_target *t); struct damon_target *damon_new_target(unsigned long id); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); void damon_free_target(struct damon_target *t); void damon_destroy_target(struct damon_target *t); +unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long primitive_upd_int); + unsigned long aggr_int, unsigned long primitive_upd_int, + unsigned long min_nr_reg, unsigned long max_nr_reg); int damon_start(struct damon_ctx **ctxs, int nr_ctxs); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); diff --git a/mm/damon/core.c b/mm/damon/core.c index 947486a150ce..28a2c78914fa 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -10,8 +10,12 @@ #include #include #include +#include #include +/* Get a random number in [l, r) */ +#define damon_rand(l, r) (l + prandom_u32_max(r - l)) + static DEFINE_MUTEX(damon_lock); static int nr_running_ctxs; @@ -40,19 +44,23 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end) * Add a region between two other regions */ inline void damon_insert_region(struct damon_region *r, - struct damon_region *prev, struct damon_region *next) + struct damon_region *prev, struct damon_region *next, + struct damon_target *t) { __list_add(&r->list, &prev->list, &next->list); + t->nr_regions++; } void damon_add_region(struct damon_region *r, struct damon_target *t) { list_add_tail(&r->list, &t->regions_list); + t->nr_regions++; } -static void damon_del_region(struct damon_region *r) +static void damon_del_region(struct damon_region *r, struct damon_target *t) { list_del(&r->list); + t->nr_regions--; } static void damon_free_region(struct damon_region *r) @@ -60,9 +68,9 @@ static void damon_free_region(struct damon_region *r) kfree(r); } -void damon_destroy_region(struct damon_region *r) +void damon_destroy_region(struct damon_region *r, struct damon_target *t) { - damon_del_region(r); + damon_del_region(r, t); damon_free_region(r); } @@ -80,6 +88,7 @@ struct damon_target *damon_new_target(unsigned long id) return NULL; t->id = id; + t->nr_regions = 0; INIT_LIST_HEAD(&t->regions_list); return t; @@ -87,7 +96,7 @@ struct damon_target *damon_new_target(unsigned long id) void damon_add_target(struct damon_ctx *ctx, struct damon_target *t) { - list_add_tail(&t->list, &ctx->region_targets); + list_add_tail(&t->list, &ctx->adaptive_targets); } static void damon_del_target(struct damon_target *t) @@ -110,6 +119,11 @@ void damon_destroy_target(struct damon_target *t) damon_free_target(t); } +unsigned int damon_nr_regions(struct damon_target *t) +{ + return t->nr_regions; +} + struct damon_ctx *damon_new_ctx(void) { struct damon_ctx *ctx; @@ -127,7 +141,10 @@ struct damon_ctx *damon_new_ctx(void) mutex_init(&ctx->kdamond_lock); - INIT_LIST_HEAD(&ctx->region_targets); + ctx->min_nr_regions = 10; + ctx->max_nr_regions = 1000; + + INIT_LIST_HEAD(&ctx->adaptive_targets); return ctx; } @@ -157,6 +174,8 @@ void damon_destroy_ctx(struct damon_ctx *ctx) * @sample_int: time interval between samplings * @aggr_int: time interval between aggregations * @primitive_upd_int: time interval between monitoring primitive updates + * @min_nr_reg: minimal number of regions + * @max_nr_reg: maximum number of regions * * This function should not be called while the kdamond is running. * Every time interval is in micro-seconds. @@ -164,15 +183,49 @@ void damon_destroy_ctx(struct damon_ctx *ctx) * Return: 0 on success, negative error code otherwise. */ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long primitive_upd_int) + unsigned long aggr_int, unsigned long primitive_upd_int, + unsigned long min_nr_reg, unsigned long max_nr_reg) { + if (min_nr_reg < 3) { + pr_err("min_nr_regions (%lu) must be at least 3\n", + min_nr_reg); + return -EINVAL; + } + if (min_nr_reg > max_nr_reg) { + pr_err("invalid nr_regions. min (%lu) > max (%lu)\n", + min_nr_reg, max_nr_reg); + return -EINVAL; + } + ctx->sample_interval = sample_int; ctx->aggr_interval = aggr_int; ctx->primitive_update_interval = primitive_upd_int; + ctx->min_nr_regions = min_nr_reg; + ctx->max_nr_regions = max_nr_reg; return 0; } +/* Returns the size upper limit for each monitoring region */ +static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct damon_region *r; + unsigned long sz = 0; + + damon_for_each_target(t, ctx) { + damon_for_each_region(r, t) + sz += r->ar.end - r->ar.start; + } + + if (ctx->min_nr_regions) + sz /= ctx->min_nr_regions; + if (sz < DAMON_MIN_REGION) + sz = DAMON_MIN_REGION; + + return sz; +} + static bool damon_kdamond_running(struct damon_ctx *ctx) { bool running; @@ -339,6 +392,150 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) } } +#define sz_damon_region(r) (r->ar.end - r->ar.start) + +/* + * Merge two adjacent regions into one region + */ +static void damon_merge_two_regions(struct damon_target *t, + struct damon_region *l, struct damon_region *r) +{ + unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r); + + l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) / + (sz_l + sz_r); + l->ar.end = r->ar.end; + damon_destroy_region(r, t); +} + +#define diff_of(a, b) (a > b ? a - b : b - a) + +/* + * Merge adjacent regions having similar access frequencies + * + * t target affected by this merge operation + * thres '->nr_accesses' diff threshold for the merge + * sz_limit size upper limit of each region + */ +static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, + unsigned long sz_limit) +{ + struct damon_region *r, *prev = NULL, *next; + + damon_for_each_region_safe(r, next, t) { + if (prev && prev->ar.end == r->ar.start && + diff_of(prev->nr_accesses, r->nr_accesses) <= thres && + sz_damon_region(prev) + sz_damon_region(r) <= sz_limit) + damon_merge_two_regions(t, prev, r); + else + prev = r; + } +} + +/* + * Merge adjacent regions having similar access frequencies + * + * threshold '->nr_accesses' diff threshold for the merge + * sz_limit size upper limit of each region + * + * This function merges monitoring target regions which are adjacent and their + * access frequencies are similar. This is for minimizing the monitoring + * overhead under the dynamically changeable access pattern. If a merge was + * unnecessarily made, later 'kdamond_split_regions()' will revert it. + */ +static void kdamond_merge_regions(struct damon_ctx *c, unsigned int threshold, + unsigned long sz_limit) +{ + struct damon_target *t; + + damon_for_each_target(t, c) + damon_merge_regions_of(t, threshold, sz_limit); +} + +/* + * Split a region in two + * + * r the region to be split + * sz_r size of the first sub-region that will be made + */ +static void damon_split_region_at(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + unsigned long sz_r) +{ + struct damon_region *new; + + new = damon_new_region(r->ar.start + sz_r, r->ar.end); + if (!new) + return; + + r->ar.end = new->ar.start; + + damon_insert_region(new, r, damon_next_region(r), t); +} + +/* Split every region in the given target into 'nr_subs' regions */ +static void damon_split_regions_of(struct damon_ctx *ctx, + struct damon_target *t, int nr_subs) +{ + struct damon_region *r, *next; + unsigned long sz_region, sz_sub = 0; + int i; + + damon_for_each_region_safe(r, next, t) { + sz_region = r->ar.end - r->ar.start; + + for (i = 0; i < nr_subs - 1 && + sz_region > 2 * DAMON_MIN_REGION; i++) { + /* + * Randomly select size of left sub-region to be at + * least 10 percent and at most 90% of original region + */ + sz_sub = ALIGN_DOWN(damon_rand(1, 10) * + sz_region / 10, DAMON_MIN_REGION); + /* Do not allow blank region */ + if (sz_sub == 0 || sz_sub >= sz_region) + continue; + + damon_split_region_at(ctx, t, r, sz_sub); + sz_region = sz_sub; + } + } +} + +/* + * Split every target region into randomly-sized small regions + * + * This function splits every target region into random-sized small regions if + * current total number of the regions is equal or smaller than half of the + * user-specified maximum number of regions. This is for maximizing the + * monitoring accuracy under the dynamically changeable access patterns. If a + * split was unnecessarily made, later 'kdamond_merge_regions()' will revert + * it. + */ +static void kdamond_split_regions(struct damon_ctx *ctx) +{ + struct damon_target *t; + unsigned int nr_regions = 0; + static unsigned int last_nr_regions; + int nr_subregions = 2; + + damon_for_each_target(t, ctx) + nr_regions += damon_nr_regions(t); + + if (nr_regions > ctx->max_nr_regions / 2) + return; + + /* Maybe the middle of the region has different access frequency */ + if (last_nr_regions == nr_regions && + nr_regions < ctx->max_nr_regions / 3) + nr_subregions = 3; + + damon_for_each_target(t, ctx) + damon_split_regions_of(ctx, t, nr_subregions); + + last_nr_regions = nr_regions; +} + /* * Check whether it is time to check and apply the target monitoring regions * @@ -395,6 +592,8 @@ static int kdamond_fn(void *data) struct damon_ctx *ctx = (struct damon_ctx *)data; struct damon_target *t; struct damon_region *r, *next; + unsigned int max_nr_accesses = 0; + unsigned long sz_limit = 0; mutex_lock(&ctx->kdamond_lock); pr_info("kdamond (%d) starts\n", ctx->kdamond->pid); @@ -405,6 +604,8 @@ static int kdamond_fn(void *data) if (ctx->callback.before_start && ctx->callback.before_start(ctx)) set_kdamond_stop(ctx); + sz_limit = damon_region_sz_limit(ctx); + while (!kdamond_need_stop(ctx)) { if (ctx->primitive.prepare_access_checks) ctx->primitive.prepare_access_checks(ctx); @@ -415,13 +616,17 @@ static int kdamond_fn(void *data) usleep_range(ctx->sample_interval, ctx->sample_interval + 1); if (ctx->primitive.check_accesses) - ctx->primitive.check_accesses(ctx); + max_nr_accesses = ctx->primitive.check_accesses(ctx); if (kdamond_aggregate_interval_passed(ctx)) { + kdamond_merge_regions(ctx, + max_nr_accesses / 10, + sz_limit); if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) set_kdamond_stop(ctx); kdamond_reset_aggregated(ctx); + kdamond_split_regions(ctx); if (ctx->primitive.reset_aggregated) ctx->primitive.reset_aggregated(ctx); } @@ -429,11 +634,12 @@ static int kdamond_fn(void *data) if (kdamond_need_update_primitive(ctx)) { if (ctx->primitive.update) ctx->primitive.update(ctx); + sz_limit = damon_region_sz_limit(ctx); } } damon_for_each_target(t, ctx) { damon_for_each_region_safe(r, next, t) - damon_destroy_region(r); + damon_destroy_region(r, t); } if (ctx->callback.before_terminate && -- cgit v1.2.3 From 1c676e0d9b1a59b98885b24a0e16a81fe4cc8301 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:40 -0700 Subject: mm/idle_page_tracking: make PG_idle reusable PG_idle and PG_young allow the two PTE Accessed bit users, Idle Page Tracking and the reclaim logic concurrently work while not interfering with each other. That is, when they need to clear the Accessed bit, they set PG_young to represent the previous state of the bit, respectively. And when they need to read the bit, if the bit is cleared, they further read the PG_young to know whether the other has cleared the bit meanwhile or not. For yet another user of the PTE Accessed bit, we could add another page flag, or extend the mechanism to use the flags. For the DAMON usecase, however, we don't need to do that just yet. IDLE_PAGE_TRACKING and DAMON are mutually exclusive, so there's only ever going to be one user of the current set of flags. In this commit, we split out the CONFIG options to allow for the use of PG_young and PG_idle outside of idle page tracking. In the next commit, DAMON's reference implementation of the virtual memory address space monitoring primitives will use it. [sjpark@amazon.de: set PAGE_EXTENSION for non-64BIT] Link: https://lkml.kernel.org/r/20210806095153.6444-1-sj38.park@gmail.com [akpm@linux-foundation.org: tweak Kconfig text] [sjpark@amazon.de: hide PAGE_IDLE_FLAG from users] Link: https://lkml.kernel.org/r/20210813081238.34705-1-sj38.park@gmail.com Link: https://lkml.kernel.org/r/20210716081449.22187-5-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Shakeel Butt Reviewed-by: Fernand Sieber Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 4 ++-- include/linux/page_ext.h | 2 +- include/linux/page_idle.h | 6 +++--- include/trace/events/mmflags.h | 2 +- mm/Kconfig | 10 +++++++++- mm/page_ext.c | 12 +++++++++++- mm/page_idle.c | 10 ---------- 7 files changed, 27 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 6b8d66965145..0a51dd1bb6b1 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -131,7 +131,7 @@ enum pageflags { #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif @@ -441,7 +441,7 @@ PAGEFLAG_FALSE(HWPoison) #define __PG_HWPOISON 0 #endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) TESTPAGEFLAG(Young, young, PF_ANY) SETPAGEFLAG(Young, young, PF_ANY) TESTCLEARFLAG(Young, young, PF_ANY) diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index aff81ba31bd8..fabb2e1e087f 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -19,7 +19,7 @@ struct page_ext_operations { enum page_ext_flags { PAGE_EXT_OWNER, PAGE_EXT_OWNER_ALLOCATED, -#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, PAGE_EXT_IDLE, #endif diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index 1e894d34bdce..d8a6aecf99cb 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -6,7 +6,7 @@ #include #include -#ifdef CONFIG_IDLE_PAGE_TRACKING +#ifdef CONFIG_PAGE_IDLE_FLAG #ifdef CONFIG_64BIT static inline bool page_is_young(struct page *page) @@ -106,7 +106,7 @@ static inline void clear_page_idle(struct page *page) } #endif /* CONFIG_64BIT */ -#else /* !CONFIG_IDLE_PAGE_TRACKING */ +#else /* !CONFIG_PAGE_IDLE_FLAG */ static inline bool page_is_young(struct page *page) { @@ -135,6 +135,6 @@ static inline void clear_page_idle(struct page *page) { } -#endif /* CONFIG_IDLE_PAGE_TRACKING */ +#endif /* CONFIG_PAGE_IDLE_FLAG */ #endif /* _LINUX_MM_PAGE_IDLE_H */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index f160484afc5c..a26dbefdf294 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -75,7 +75,7 @@ #define IF_HAVE_PG_HWPOISON(flag,string) #endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) #define IF_HAVE_PG_IDLE(flag,string) ,{1UL << flag, string} #else #define IF_HAVE_PG_IDLE(flag,string) diff --git a/mm/Kconfig b/mm/Kconfig index 8459167b0294..d16ba9249bc5 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -739,10 +739,18 @@ config DEFERRED_STRUCT_PAGE_INIT lifetime of the system until these kthreads finish the initialisation. +config PAGE_IDLE_FLAG + bool + select PAGE_EXTENSION if !64BIT + help + This adds PG_idle and PG_young flags to 'struct page'. PTE Accessed + bit writers can set the state of the bit in the flags so that PTE + Accessed bit readers may avoid disturbance. + config IDLE_PAGE_TRACKING bool "Enable idle page tracking" depends on SYSFS && MMU - select PAGE_EXTENSION if !64BIT + select PAGE_IDLE_FLAG help This feature allows to estimate the amount of user pages that have not been touched during a given period of time. This information can diff --git a/mm/page_ext.c b/mm/page_ext.c index 293b2685fc48..dfb91653d359 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -58,11 +58,21 @@ * can utilize this callback to initialize the state of it correctly. */ +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) +static bool need_page_idle(void) +{ + return true; +} +struct page_ext_operations page_idle_ops = { + .need = need_page_idle, +}; +#endif + static struct page_ext_operations *page_ext_ops[] = { #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif }; diff --git a/mm/page_idle.c b/mm/page_idle.c index 64e5344a992c..edead6a8a5f9 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -207,16 +207,6 @@ static const struct attribute_group page_idle_attr_group = { .name = "page_idle", }; -#ifndef CONFIG_64BIT -static bool need_page_idle(void) -{ - return true; -} -struct page_ext_operations page_idle_ops = { - .need = need_page_idle, -}; -#endif - static int __init page_idle_init(void) { int err; -- cgit v1.2.3 From 3f49584b262cf8f42b25f4c1ad9f5bfd3bdc1bca Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:44 -0700 Subject: mm/damon: implement primitives for the virtual memory address spaces This commit introduces a reference implementation of the address space specific low level primitives for the virtual address space, so that users of DAMON can easily monitor the data accesses on virtual address spaces of specific processes by simply configuring the implementation to be used by DAMON. The low level primitives for the fundamental access monitoring are defined in two parts: 1. Identification of the monitoring target address range for the address space. 2. Access check of specific address range in the target space. The reference implementation for the virtual address space does the works as below. PTE Accessed-bit Based Access Check ----------------------------------- The implementation uses PTE Accessed-bit for basic access checks. That is, it clears the bit for the next sampling target page and checks whether it is set again after one sampling period. This could disturb the reclaim logic. DAMON uses ``PG_idle`` and ``PG_young`` page flags to solve the conflict, as Idle page tracking does. VMA-based Target Address Range Construction ------------------------------------------- Only small parts in the super-huge virtual address space of the processes are mapped to physical memory and accessed. Thus, tracking the unmapped address regions is just wasteful. However, because DAMON can deal with some level of noise using the adaptive regions adjustment mechanism, tracking every mapping is not strictly required but could even incur a high overhead in some cases. That said, too huge unmapped areas inside the monitoring target should be removed to not take the time for the adaptive mechanism. For the reason, this implementation converts the complex mappings to three distinct regions that cover every mapped area of the address space. Also, the two gaps between the three regions are the two biggest unmapped areas in the given address space. The two biggest unmapped areas would be the gap between the heap and the uppermost mmap()-ed region, and the gap between the lowermost mmap()-ed region and the stack in most of the cases. Because these gaps are exceptionally huge in usual address spaces, excluding these will be sufficient to make a reasonable trade-off. Below shows this in detail:: (small mmap()-ed regions and munmap()-ed regions) [akpm@linux-foundation.org: mm/damon/vaddr.c needs highmem.h for kunmap_atomic()] [sjpark@amazon.de: remove unnecessary PAGE_EXTENSION setup] Link: https://lkml.kernel.org/r/20210806095153.6444-2-sj38.park@gmail.com [sjpark@amazon.de: safely walk page table] Link: https://lkml.kernel.org/r/20210831161800.29419-1-sj38.park@gmail.com Link: https://lkml.kernel.org/r/20210716081449.22187-6-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Fernand Sieber Acked-by: Shakeel Butt Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 13 + mm/damon/Kconfig | 8 + mm/damon/Makefile | 1 + mm/damon/vaddr.c | 665 ++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 687 insertions(+) create mode 100644 mm/damon/vaddr.c (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index ce2a84b26cd7..edb350e52b93 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -249,4 +249,17 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); #endif /* CONFIG_DAMON */ +#ifdef CONFIG_DAMON_VADDR + +/* Monitoring primitives for virtual memory address spaces */ +void damon_va_init(struct damon_ctx *ctx); +void damon_va_update(struct damon_ctx *ctx); +void damon_va_prepare_access_checks(struct damon_ctx *ctx); +unsigned int damon_va_check_accesses(struct damon_ctx *ctx); +bool damon_va_target_valid(void *t); +void damon_va_cleanup(struct damon_ctx *ctx); +void damon_va_set_primitives(struct damon_ctx *ctx); + +#endif /* CONFIG_DAMON_VADDR */ + #endif /* _DAMON_H */ diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index d00e99ac1a15..5cbb5db54158 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -12,4 +12,12 @@ config DAMON See https://damonitor.github.io/doc/html/latest-damon/index.html for more information. +config DAMON_VADDR + bool "Data access monitoring primitives for virtual address spaces" + depends on DAMON && MMU + select PAGE_IDLE_FLAG + help + This builds the default data access monitoring primitives for DAMON + that works for virtual address spaces. + endmenu diff --git a/mm/damon/Makefile b/mm/damon/Makefile index 4fd2edb4becf..6ebbd08aed67 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_DAMON) := core.o +obj-$(CONFIG_DAMON_VADDR) += vaddr.o diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c new file mode 100644 index 000000000000..897aa8cf96c8 --- /dev/null +++ b/mm/damon/vaddr.c @@ -0,0 +1,665 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON Primitives for Virtual Address Spaces + * + * Author: SeongJae Park + */ + +#define pr_fmt(fmt) "damon-va: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Get a random number in [l, r) */ +#define damon_rand(l, r) (l + prandom_u32_max(r - l)) + +/* + * 't->id' should be the pointer to the relevant 'struct pid' having reference + * count. Caller must put the returned task, unless it is NULL. + */ +#define damon_get_task_struct(t) \ + (get_pid_task((struct pid *)t->id, PIDTYPE_PID)) + +/* + * Get the mm_struct of the given target + * + * Caller _must_ put the mm_struct after use, unless it is NULL. + * + * Returns the mm_struct of the target on success, NULL on failure + */ +static struct mm_struct *damon_get_mm(struct damon_target *t) +{ + struct task_struct *task; + struct mm_struct *mm; + + task = damon_get_task_struct(t); + if (!task) + return NULL; + + mm = get_task_mm(task); + put_task_struct(task); + return mm; +} + +/* + * Functions for the initial monitoring target regions construction + */ + +/* + * Size-evenly split a region into 'nr_pieces' small regions + * + * Returns 0 on success, or negative error code otherwise. + */ +static int damon_va_evenly_split_region(struct damon_target *t, + struct damon_region *r, unsigned int nr_pieces) +{ + unsigned long sz_orig, sz_piece, orig_end; + struct damon_region *n = NULL, *next; + unsigned long start; + + if (!r || !nr_pieces) + return -EINVAL; + + orig_end = r->ar.end; + sz_orig = r->ar.end - r->ar.start; + sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, DAMON_MIN_REGION); + + if (!sz_piece) + return -EINVAL; + + r->ar.end = r->ar.start + sz_piece; + next = damon_next_region(r); + for (start = r->ar.end; start + sz_piece <= orig_end; + start += sz_piece) { + n = damon_new_region(start, start + sz_piece); + if (!n) + return -ENOMEM; + damon_insert_region(n, r, next, t); + r = n; + } + /* complement last region for possible rounding error */ + if (n) + n->ar.end = orig_end; + + return 0; +} + +static unsigned long sz_range(struct damon_addr_range *r) +{ + return r->end - r->start; +} + +static void swap_ranges(struct damon_addr_range *r1, + struct damon_addr_range *r2) +{ + struct damon_addr_range tmp; + + tmp = *r1; + *r1 = *r2; + *r2 = tmp; +} + +/* + * Find three regions separated by two biggest unmapped regions + * + * vma the head vma of the target address space + * regions an array of three address ranges that results will be saved + * + * This function receives an address space and finds three regions in it which + * separated by the two biggest unmapped regions in the space. Please refer to + * below comments of '__damon_va_init_regions()' function to know why this is + * necessary. + * + * Returns 0 if success, or negative error code otherwise. + */ +static int __damon_va_three_regions(struct vm_area_struct *vma, + struct damon_addr_range regions[3]) +{ + struct damon_addr_range gap = {0}, first_gap = {0}, second_gap = {0}; + struct vm_area_struct *last_vma = NULL; + unsigned long start = 0; + struct rb_root rbroot; + + /* Find two biggest gaps so that first_gap > second_gap > others */ + for (; vma; vma = vma->vm_next) { + if (!last_vma) { + start = vma->vm_start; + goto next; + } + + if (vma->rb_subtree_gap <= sz_range(&second_gap)) { + rbroot.rb_node = &vma->vm_rb; + vma = rb_entry(rb_last(&rbroot), + struct vm_area_struct, vm_rb); + goto next; + } + + gap.start = last_vma->vm_end; + gap.end = vma->vm_start; + if (sz_range(&gap) > sz_range(&second_gap)) { + swap_ranges(&gap, &second_gap); + if (sz_range(&second_gap) > sz_range(&first_gap)) + swap_ranges(&second_gap, &first_gap); + } +next: + last_vma = vma; + } + + if (!sz_range(&second_gap) || !sz_range(&first_gap)) + return -EINVAL; + + /* Sort the two biggest gaps by address */ + if (first_gap.start > second_gap.start) + swap_ranges(&first_gap, &second_gap); + + /* Store the result */ + regions[0].start = ALIGN(start, DAMON_MIN_REGION); + regions[0].end = ALIGN(first_gap.start, DAMON_MIN_REGION); + regions[1].start = ALIGN(first_gap.end, DAMON_MIN_REGION); + regions[1].end = ALIGN(second_gap.start, DAMON_MIN_REGION); + regions[2].start = ALIGN(second_gap.end, DAMON_MIN_REGION); + regions[2].end = ALIGN(last_vma->vm_end, DAMON_MIN_REGION); + + return 0; +} + +/* + * Get the three regions in the given target (task) + * + * Returns 0 on success, negative error code otherwise. + */ +static int damon_va_three_regions(struct damon_target *t, + struct damon_addr_range regions[3]) +{ + struct mm_struct *mm; + int rc; + + mm = damon_get_mm(t); + if (!mm) + return -EINVAL; + + mmap_read_lock(mm); + rc = __damon_va_three_regions(mm->mmap, regions); + mmap_read_unlock(mm); + + mmput(mm); + return rc; +} + +/* + * Initialize the monitoring target regions for the given target (task) + * + * t the given target + * + * Because only a number of small portions of the entire address space + * is actually mapped to the memory and accessed, monitoring the unmapped + * regions is wasteful. That said, because we can deal with small noises, + * tracking every mapping is not strictly required but could even incur a high + * overhead if the mapping frequently changes or the number of mappings is + * high. The adaptive regions adjustment mechanism will further help to deal + * with the noise by simply identifying the unmapped areas as a region that + * has no access. Moreover, applying the real mappings that would have many + * unmapped areas inside will make the adaptive mechanism quite complex. That + * said, too huge unmapped areas inside the monitoring target should be removed + * to not take the time for the adaptive mechanism. + * + * For the reason, we convert the complex mappings to three distinct regions + * that cover every mapped area of the address space. Also the two gaps + * between the three regions are the two biggest unmapped areas in the given + * address space. In detail, this function first identifies the start and the + * end of the mappings and the two biggest unmapped areas of the address space. + * Then, it constructs the three regions as below: + * + * [mappings[0]->start, big_two_unmapped_areas[0]->start) + * [big_two_unmapped_areas[0]->end, big_two_unmapped_areas[1]->start) + * [big_two_unmapped_areas[1]->end, mappings[nr_mappings - 1]->end) + * + * As usual memory map of processes is as below, the gap between the heap and + * the uppermost mmap()-ed region, and the gap between the lowermost mmap()-ed + * region and the stack will be two biggest unmapped regions. Because these + * gaps are exceptionally huge areas in usual address space, excluding these + * two biggest unmapped regions will be sufficient to make a trade-off. + * + * + * + * + * (other mmap()-ed regions and small unmapped regions) + * + * + * + */ +static void __damon_va_init_regions(struct damon_ctx *ctx, + struct damon_target *t) +{ + struct damon_region *r; + struct damon_addr_range regions[3]; + unsigned long sz = 0, nr_pieces; + int i; + + if (damon_va_three_regions(t, regions)) { + pr_err("Failed to get three regions of target %lu\n", t->id); + return; + } + + for (i = 0; i < 3; i++) + sz += regions[i].end - regions[i].start; + if (ctx->min_nr_regions) + sz /= ctx->min_nr_regions; + if (sz < DAMON_MIN_REGION) + sz = DAMON_MIN_REGION; + + /* Set the initial three regions of the target */ + for (i = 0; i < 3; i++) { + r = damon_new_region(regions[i].start, regions[i].end); + if (!r) { + pr_err("%d'th init region creation failed\n", i); + return; + } + damon_add_region(r, t); + + nr_pieces = (regions[i].end - regions[i].start) / sz; + damon_va_evenly_split_region(t, r, nr_pieces); + } +} + +/* Initialize '->regions_list' of every target (task) */ +void damon_va_init(struct damon_ctx *ctx) +{ + struct damon_target *t; + + damon_for_each_target(t, ctx) { + /* the user may set the target regions as they want */ + if (!damon_nr_regions(t)) + __damon_va_init_regions(ctx, t); + } +} + +/* + * Functions for the dynamic monitoring target regions update + */ + +/* + * Check whether a region is intersecting an address range + * + * Returns true if it is. + */ +static bool damon_intersect(struct damon_region *r, struct damon_addr_range *re) +{ + return !(r->ar.end <= re->start || re->end <= r->ar.start); +} + +/* + * Update damon regions for the three big regions of the given target + * + * t the given target + * bregions the three big regions of the target + */ +static void damon_va_apply_three_regions(struct damon_target *t, + struct damon_addr_range bregions[3]) +{ + struct damon_region *r, *next; + unsigned int i = 0; + + /* Remove regions which are not in the three big regions now */ + damon_for_each_region_safe(r, next, t) { + for (i = 0; i < 3; i++) { + if (damon_intersect(r, &bregions[i])) + break; + } + if (i == 3) + damon_destroy_region(r, t); + } + + /* Adjust intersecting regions to fit with the three big regions */ + for (i = 0; i < 3; i++) { + struct damon_region *first = NULL, *last; + struct damon_region *newr; + struct damon_addr_range *br; + + br = &bregions[i]; + /* Get the first and last regions which intersects with br */ + damon_for_each_region(r, t) { + if (damon_intersect(r, br)) { + if (!first) + first = r; + last = r; + } + if (r->ar.start >= br->end) + break; + } + if (!first) { + /* no damon_region intersects with this big region */ + newr = damon_new_region( + ALIGN_DOWN(br->start, + DAMON_MIN_REGION), + ALIGN(br->end, DAMON_MIN_REGION)); + if (!newr) + continue; + damon_insert_region(newr, damon_prev_region(r), r, t); + } else { + first->ar.start = ALIGN_DOWN(br->start, + DAMON_MIN_REGION); + last->ar.end = ALIGN(br->end, DAMON_MIN_REGION); + } + } +} + +/* + * Update regions for current memory mappings + */ +void damon_va_update(struct damon_ctx *ctx) +{ + struct damon_addr_range three_regions[3]; + struct damon_target *t; + + damon_for_each_target(t, ctx) { + if (damon_va_three_regions(t, three_regions)) + continue; + damon_va_apply_three_regions(t, three_regions); + } +} + +/* + * Get an online page for a pfn if it's in the LRU list. Otherwise, returns + * NULL. + * + * The body of this function is stolen from the 'page_idle_get_page()'. We + * steal rather than reuse it because the code is quite simple. + */ +static struct page *damon_get_page(unsigned long pfn) +{ + struct page *page = pfn_to_online_page(pfn); + + if (!page || !PageLRU(page) || !get_page_unless_zero(page)) + return NULL; + + if (unlikely(!PageLRU(page))) { + put_page(page); + page = NULL; + } + return page; +} + +static void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, + unsigned long addr) +{ + bool referenced = false; + struct page *page = damon_get_page(pte_pfn(*pte)); + + if (!page) + return; + + if (pte_young(*pte)) { + referenced = true; + *pte = pte_mkold(*pte); + } + +#ifdef CONFIG_MMU_NOTIFIER + if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE)) + referenced = true; +#endif /* CONFIG_MMU_NOTIFIER */ + + if (referenced) + set_page_young(page); + + set_page_idle(page); + put_page(page); +} + +static void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, + unsigned long addr) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bool referenced = false; + struct page *page = damon_get_page(pmd_pfn(*pmd)); + + if (!page) + return; + + if (pmd_young(*pmd)) { + referenced = true; + *pmd = pmd_mkold(*pmd); + } + +#ifdef CONFIG_MMU_NOTIFIER + if (mmu_notifier_clear_young(mm, addr, + addr + ((1UL) << HPAGE_PMD_SHIFT))) + referenced = true; +#endif /* CONFIG_MMU_NOTIFIER */ + + if (referenced) + set_page_young(page); + + set_page_idle(page); + put_page(page); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +} + +static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t *pte; + spinlock_t *ptl; + + if (pmd_huge(*pmd)) { + ptl = pmd_lock(walk->mm, pmd); + if (pmd_huge(*pmd)) { + damon_pmdp_mkold(pmd, walk->mm, addr); + spin_unlock(ptl); + return 0; + } + spin_unlock(ptl); + } + + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + return 0; + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + if (!pte_present(*pte)) + goto out; + damon_ptep_mkold(pte, walk->mm, addr); +out: + pte_unmap_unlock(pte, ptl); + return 0; +} + +static struct mm_walk_ops damon_mkold_ops = { + .pmd_entry = damon_mkold_pmd_entry, +}; + +static void damon_va_mkold(struct mm_struct *mm, unsigned long addr) +{ + mmap_read_lock(mm); + walk_page_range(mm, addr, addr + 1, &damon_mkold_ops, NULL); + mmap_read_unlock(mm); +} + +/* + * Functions for the access checking of the regions + */ + +static void damon_va_prepare_access_check(struct damon_ctx *ctx, + struct mm_struct *mm, struct damon_region *r) +{ + r->sampling_addr = damon_rand(r->ar.start, r->ar.end); + + damon_va_mkold(mm, r->sampling_addr); +} + +void damon_va_prepare_access_checks(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct mm_struct *mm; + struct damon_region *r; + + damon_for_each_target(t, ctx) { + mm = damon_get_mm(t); + if (!mm) + continue; + damon_for_each_region(r, t) + damon_va_prepare_access_check(ctx, mm, r); + mmput(mm); + } +} + +struct damon_young_walk_private { + unsigned long *page_sz; + bool young; +}; + +static int damon_young_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t *pte; + spinlock_t *ptl; + struct page *page; + struct damon_young_walk_private *priv = walk->private; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_huge(*pmd)) { + ptl = pmd_lock(walk->mm, pmd); + if (!pmd_huge(*pmd)) { + spin_unlock(ptl); + goto regular_page; + } + page = damon_get_page(pmd_pfn(*pmd)); + if (!page) + goto huge_out; + if (pmd_young(*pmd) || !page_is_idle(page) || + mmu_notifier_test_young(walk->mm, + addr)) { + *priv->page_sz = ((1UL) << HPAGE_PMD_SHIFT); + priv->young = true; + } + put_page(page); +huge_out: + spin_unlock(ptl); + return 0; + } + +regular_page: +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + return -EINVAL; + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + if (!pte_present(*pte)) + goto out; + page = damon_get_page(pte_pfn(*pte)); + if (!page) + goto out; + if (pte_young(*pte) || !page_is_idle(page) || + mmu_notifier_test_young(walk->mm, addr)) { + *priv->page_sz = PAGE_SIZE; + priv->young = true; + } + put_page(page); +out: + pte_unmap_unlock(pte, ptl); + return 0; +} + +static struct mm_walk_ops damon_young_ops = { + .pmd_entry = damon_young_pmd_entry, +}; + +static bool damon_va_young(struct mm_struct *mm, unsigned long addr, + unsigned long *page_sz) +{ + struct damon_young_walk_private arg = { + .page_sz = page_sz, + .young = false, + }; + + mmap_read_lock(mm); + walk_page_range(mm, addr, addr + 1, &damon_young_ops, &arg); + mmap_read_unlock(mm); + return arg.young; +} + +/* + * Check whether the region was accessed after the last preparation + * + * mm 'mm_struct' for the given virtual address space + * r the region to be checked + */ +static void damon_va_check_access(struct damon_ctx *ctx, + struct mm_struct *mm, struct damon_region *r) +{ + static struct mm_struct *last_mm; + static unsigned long last_addr; + static unsigned long last_page_sz = PAGE_SIZE; + static bool last_accessed; + + /* If the region is in the last checked page, reuse the result */ + if (mm == last_mm && (ALIGN_DOWN(last_addr, last_page_sz) == + ALIGN_DOWN(r->sampling_addr, last_page_sz))) { + if (last_accessed) + r->nr_accesses++; + return; + } + + last_accessed = damon_va_young(mm, r->sampling_addr, &last_page_sz); + if (last_accessed) + r->nr_accesses++; + + last_mm = mm; + last_addr = r->sampling_addr; +} + +unsigned int damon_va_check_accesses(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct mm_struct *mm; + struct damon_region *r; + unsigned int max_nr_accesses = 0; + + damon_for_each_target(t, ctx) { + mm = damon_get_mm(t); + if (!mm) + continue; + damon_for_each_region(r, t) { + damon_va_check_access(ctx, mm, r); + max_nr_accesses = max(r->nr_accesses, max_nr_accesses); + } + mmput(mm); + } + + return max_nr_accesses; +} + +/* + * Functions for the target validity check and cleanup + */ + +bool damon_va_target_valid(void *target) +{ + struct damon_target *t = target; + struct task_struct *task; + + task = damon_get_task_struct(t); + if (task) { + put_task_struct(task); + return true; + } + + return false; +} + +void damon_va_set_primitives(struct damon_ctx *ctx) +{ + ctx->primitive.init = damon_va_init; + ctx->primitive.update = damon_va_update; + ctx->primitive.prepare_access_checks = damon_va_prepare_access_checks; + ctx->primitive.check_accesses = damon_va_check_accesses; + ctx->primitive.reset_aggregated = NULL; + ctx->primitive.target_valid = damon_va_target_valid; + ctx->primitive.cleanup = NULL; +} -- cgit v1.2.3 From 4bc05954d0076655cfaf6f0135585bdc20cd6b11 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:53 -0700 Subject: mm/damon: implement a debugfs-based user space interface DAMON is designed to be used by kernel space code such as the memory management subsystems, and therefore it provides only kernel space API. That said, letting the user space control DAMON could provide some benefits to them. For example, it will allow user space to analyze their specific workloads and make their own special optimizations. For such cases, this commit implements a simple DAMON application kernel module, namely 'damon-dbgfs', which merely wraps the DAMON api and exports those to the user space via the debugfs. 'damon-dbgfs' exports three files, ``attrs``, ``target_ids``, and ``monitor_on`` under its debugfs directory, ``/damon/``. Attributes ---------- Users can read and write the ``sampling interval``, ``aggregation interval``, ``regions update interval``, and min/max number of monitoring target regions by reading from and writing to the ``attrs`` file. For example, below commands set those values to 5 ms, 100 ms, 1,000 ms, 10, 1000 and check it again:: # cd /damon # echo 5000 100000 1000000 10 1000 > attrs # cat attrs 5000 100000 1000000 10 1000 Target IDs ---------- Some types of address spaces supports multiple monitoring target. For example, the virtual memory address spaces monitoring can have multiple processes as the monitoring targets. Users can set the targets by writing relevant id values of the targets to, and get the ids of the current targets by reading from the ``target_ids`` file. In case of the virtual address spaces monitoring, the values should be pids of the monitoring target processes. For example, below commands set processes having pids 42 and 4242 as the monitoring targets and check it again:: # cd /damon # echo 42 4242 > target_ids # cat target_ids 42 4242 Note that setting the target ids doesn't start the monitoring. Turning On/Off -------------- Setting the files as described above doesn't incur effect unless you explicitly start the monitoring. You can start, stop, and check the current status of the monitoring by writing to and reading from the ``monitor_on`` file. Writing ``on`` to the file starts the monitoring of the targets with the attributes. Writing ``off`` to the file stops those. DAMON also stops if every targets are invalidated (in case of the virtual memory monitoring, target processes are invalidated when terminated). Below example commands turn on, off, and check the status of DAMON:: # cd /damon # echo on > monitor_on # echo off > monitor_on # cat monitor_on off Please note that you cannot write to the above-mentioned debugfs files while the monitoring is turned on. If you write to the files while DAMON is running, an error code such as ``-EBUSY`` will be returned. [akpm@linux-foundation.org: remove unneeded "alloc failed" printks] [akpm@linux-foundation.org: replace macro with static inline] Link: https://lkml.kernel.org/r/20210716081449.22187-8-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Fernand Sieber Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shakeel Butt Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 3 + mm/damon/Kconfig | 9 ++ mm/damon/Makefile | 1 + mm/damon/core.c | 47 ++++++ mm/damon/dbgfs.c | 397 ++++++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 457 insertions(+) create mode 100644 mm/damon/dbgfs.c (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index edb350e52b93..d68b67b8d458 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -240,9 +240,12 @@ unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); +int damon_set_targets(struct damon_ctx *ctx, + unsigned long *ids, ssize_t nr_ids); int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, unsigned long aggr_int, unsigned long primitive_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg); +int damon_nr_running_ctxs(void); int damon_start(struct damon_ctx **ctxs, int nr_ctxs); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index 5cbb5db54158..c8e3dba6fb4c 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -20,4 +20,13 @@ config DAMON_VADDR This builds the default data access monitoring primitives for DAMON that works for virtual address spaces. +config DAMON_DBGFS + bool "DAMON debugfs interface" + depends on DAMON_VADDR && DEBUG_FS + help + This builds the debugfs interface for DAMON. The user space admins + can use the interface for arbitrary data access monitoring. + + If unsure, say N. + endmenu diff --git a/mm/damon/Makefile b/mm/damon/Makefile index 6ebbd08aed67..fed4be3bace3 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -2,3 +2,4 @@ obj-$(CONFIG_DAMON) := core.o obj-$(CONFIG_DAMON_VADDR) += vaddr.o +obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o diff --git a/mm/damon/core.c b/mm/damon/core.c index ee24d64e8019..59033488402e 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -171,6 +171,39 @@ void damon_destroy_ctx(struct damon_ctx *ctx) kfree(ctx); } +/** + * damon_set_targets() - Set monitoring targets. + * @ctx: monitoring context + * @ids: array of target ids + * @nr_ids: number of entries in @ids + * + * This function should not be called while the kdamond is running. + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_set_targets(struct damon_ctx *ctx, + unsigned long *ids, ssize_t nr_ids) +{ + ssize_t i; + struct damon_target *t, *next; + + damon_destroy_targets(ctx); + + for (i = 0; i < nr_ids; i++) { + t = damon_new_target(ids[i]); + if (!t) { + pr_err("Failed to alloc damon_target\n"); + /* The caller should do cleanup of the ids itself */ + damon_for_each_target_safe(t, next, ctx) + damon_destroy_target(t); + return -ENOMEM; + } + damon_add_target(ctx, t); + } + + return 0; +} + /** * damon_set_attrs() - Set attributes for the monitoring. * @ctx: monitoring context @@ -209,6 +242,20 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, return 0; } +/** + * damon_nr_running_ctxs() - Return number of currently running contexts. + */ +int damon_nr_running_ctxs(void) +{ + int nr_ctxs; + + mutex_lock(&damon_lock); + nr_ctxs = nr_running_ctxs; + mutex_unlock(&damon_lock); + + return nr_ctxs; +} + /* Returns the size upper limit for each monitoring region */ static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) { diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c new file mode 100644 index 000000000000..d2e0a547eb3f --- /dev/null +++ b/mm/damon/dbgfs.c @@ -0,0 +1,397 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON Debugfs Interface + * + * Author: SeongJae Park + */ + +#define pr_fmt(fmt) "damon-dbgfs: " fmt + +#include +#include +#include +#include +#include +#include +#include + +static struct damon_ctx **dbgfs_ctxs; +static int dbgfs_nr_ctxs; +static struct dentry **dbgfs_dirs; + +/* + * Returns non-empty string on success, negative error code otherwise. + */ +static char *user_input_str(const char __user *buf, size_t count, loff_t *ppos) +{ + char *kbuf; + ssize_t ret; + + /* We do not accept continuous write */ + if (*ppos) + return ERR_PTR(-EINVAL); + + kbuf = kmalloc(count + 1, GFP_KERNEL); + if (!kbuf) + return ERR_PTR(-ENOMEM); + + ret = simple_write_to_buffer(kbuf, count + 1, ppos, buf, count); + if (ret != count) { + kfree(kbuf); + return ERR_PTR(-EIO); + } + kbuf[ret] = '\0'; + + return kbuf; +} + +static ssize_t dbgfs_attrs_read(struct file *file, + char __user *buf, size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char kbuf[128]; + int ret; + + mutex_lock(&ctx->kdamond_lock); + ret = scnprintf(kbuf, ARRAY_SIZE(kbuf), "%lu %lu %lu %lu %lu\n", + ctx->sample_interval, ctx->aggr_interval, + ctx->primitive_update_interval, ctx->min_nr_regions, + ctx->max_nr_regions); + mutex_unlock(&ctx->kdamond_lock); + + return simple_read_from_buffer(buf, count, ppos, kbuf, ret); +} + +static ssize_t dbgfs_attrs_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + unsigned long s, a, r, minr, maxr; + char *kbuf; + ssize_t ret = count; + int err; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + if (sscanf(kbuf, "%lu %lu %lu %lu %lu", + &s, &a, &r, &minr, &maxr) != 5) { + ret = -EINVAL; + goto out; + } + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + ret = -EBUSY; + goto unlock_out; + } + + err = damon_set_attrs(ctx, s, a, r, minr, maxr); + if (err) + ret = err; +unlock_out: + mutex_unlock(&ctx->kdamond_lock); +out: + kfree(kbuf); + return ret; +} + +static inline bool targetid_is_pid(const struct damon_ctx *ctx) +{ + return ctx->primitive.target_valid == damon_va_target_valid; +} + +static ssize_t sprint_target_ids(struct damon_ctx *ctx, char *buf, ssize_t len) +{ + struct damon_target *t; + unsigned long id; + int written = 0; + int rc; + + damon_for_each_target(t, ctx) { + id = t->id; + if (targetid_is_pid(ctx)) + /* Show pid numbers to debugfs users */ + id = (unsigned long)pid_vnr((struct pid *)id); + + rc = scnprintf(&buf[written], len - written, "%lu ", id); + if (!rc) + return -ENOMEM; + written += rc; + } + if (written) + written -= 1; + written += scnprintf(&buf[written], len - written, "\n"); + return written; +} + +static ssize_t dbgfs_target_ids_read(struct file *file, + char __user *buf, size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + ssize_t len; + char ids_buf[320]; + + mutex_lock(&ctx->kdamond_lock); + len = sprint_target_ids(ctx, ids_buf, 320); + mutex_unlock(&ctx->kdamond_lock); + if (len < 0) + return len; + + return simple_read_from_buffer(buf, count, ppos, ids_buf, len); +} + +/* + * Converts a string into an array of unsigned long integers + * + * Returns an array of unsigned long integers if the conversion success, or + * NULL otherwise. + */ +static unsigned long *str_to_target_ids(const char *str, ssize_t len, + ssize_t *nr_ids) +{ + unsigned long *ids; + const int max_nr_ids = 32; + unsigned long id; + int pos = 0, parsed, ret; + + *nr_ids = 0; + ids = kmalloc_array(max_nr_ids, sizeof(id), GFP_KERNEL); + if (!ids) + return NULL; + while (*nr_ids < max_nr_ids && pos < len) { + ret = sscanf(&str[pos], "%lu%n", &id, &parsed); + pos += parsed; + if (ret != 1) + break; + ids[*nr_ids] = id; + *nr_ids += 1; + } + + return ids; +} + +static void dbgfs_put_pids(unsigned long *ids, int nr_ids) +{ + int i; + + for (i = 0; i < nr_ids; i++) + put_pid((struct pid *)ids[i]); +} + +static ssize_t dbgfs_target_ids_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf, *nrs; + unsigned long *targets; + ssize_t nr_targets; + ssize_t ret = count; + int i; + int err; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + nrs = kbuf; + + targets = str_to_target_ids(nrs, ret, &nr_targets); + if (!targets) { + ret = -ENOMEM; + goto out; + } + + if (targetid_is_pid(ctx)) { + for (i = 0; i < nr_targets; i++) { + targets[i] = (unsigned long)find_get_pid( + (int)targets[i]); + if (!targets[i]) { + dbgfs_put_pids(targets, i); + ret = -EINVAL; + goto free_targets_out; + } + } + } + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + if (targetid_is_pid(ctx)) + dbgfs_put_pids(targets, nr_targets); + ret = -EBUSY; + goto unlock_out; + } + + err = damon_set_targets(ctx, targets, nr_targets); + if (err) { + if (targetid_is_pid(ctx)) + dbgfs_put_pids(targets, nr_targets); + ret = err; + } + +unlock_out: + mutex_unlock(&ctx->kdamond_lock); +free_targets_out: + kfree(targets); +out: + kfree(kbuf); + return ret; +} + +static int damon_dbgfs_open(struct inode *inode, struct file *file) +{ + file->private_data = inode->i_private; + + return nonseekable_open(inode, file); +} + +static const struct file_operations attrs_fops = { + .open = damon_dbgfs_open, + .read = dbgfs_attrs_read, + .write = dbgfs_attrs_write, +}; + +static const struct file_operations target_ids_fops = { + .open = damon_dbgfs_open, + .read = dbgfs_target_ids_read, + .write = dbgfs_target_ids_write, +}; + +static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx) +{ + const char * const file_names[] = {"attrs", "target_ids"}; + const struct file_operations *fops[] = {&attrs_fops, &target_ids_fops}; + int i; + + for (i = 0; i < ARRAY_SIZE(file_names); i++) + debugfs_create_file(file_names[i], 0600, dir, ctx, fops[i]); +} + +static int dbgfs_before_terminate(struct damon_ctx *ctx) +{ + struct damon_target *t, *next; + + if (!targetid_is_pid(ctx)) + return 0; + + damon_for_each_target_safe(t, next, ctx) { + put_pid((struct pid *)t->id); + damon_destroy_target(t); + } + return 0; +} + +static struct damon_ctx *dbgfs_new_ctx(void) +{ + struct damon_ctx *ctx; + + ctx = damon_new_ctx(); + if (!ctx) + return NULL; + + damon_va_set_primitives(ctx); + ctx->callback.before_terminate = dbgfs_before_terminate; + return ctx; +} + +static ssize_t dbgfs_monitor_on_read(struct file *file, + char __user *buf, size_t count, loff_t *ppos) +{ + char monitor_on_buf[5]; + bool monitor_on = damon_nr_running_ctxs() != 0; + int len; + + len = scnprintf(monitor_on_buf, 5, monitor_on ? "on\n" : "off\n"); + + return simple_read_from_buffer(buf, count, ppos, monitor_on_buf, len); +} + +static ssize_t dbgfs_monitor_on_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppos) +{ + ssize_t ret = count; + char *kbuf; + int err; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + /* Remove white space */ + if (sscanf(kbuf, "%s", kbuf) != 1) { + kfree(kbuf); + return -EINVAL; + } + + if (!strncmp(kbuf, "on", count)) + err = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs); + else if (!strncmp(kbuf, "off", count)) + err = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs); + else + err = -EINVAL; + + if (err) + ret = err; + kfree(kbuf); + return ret; +} + +static const struct file_operations monitor_on_fops = { + .read = dbgfs_monitor_on_read, + .write = dbgfs_monitor_on_write, +}; + +static int __init __damon_dbgfs_init(void) +{ + struct dentry *dbgfs_root; + const char * const file_names[] = {"monitor_on"}; + const struct file_operations *fops[] = {&monitor_on_fops}; + int i; + + dbgfs_root = debugfs_create_dir("damon", NULL); + + for (i = 0; i < ARRAY_SIZE(file_names); i++) + debugfs_create_file(file_names[i], 0600, dbgfs_root, NULL, + fops[i]); + dbgfs_fill_ctx_dir(dbgfs_root, dbgfs_ctxs[0]); + + dbgfs_dirs = kmalloc_array(1, sizeof(dbgfs_root), GFP_KERNEL); + if (!dbgfs_dirs) { + debugfs_remove(dbgfs_root); + return -ENOMEM; + } + dbgfs_dirs[0] = dbgfs_root; + + return 0; +} + +/* + * Functions for the initialization + */ + +static int __init damon_dbgfs_init(void) +{ + int rc; + + dbgfs_ctxs = kmalloc(sizeof(*dbgfs_ctxs), GFP_KERNEL); + if (!dbgfs_ctxs) + return -ENOMEM; + dbgfs_ctxs[0] = dbgfs_new_ctx(); + if (!dbgfs_ctxs[0]) { + kfree(dbgfs_ctxs); + return -ENOMEM; + } + dbgfs_nr_ctxs = 1; + + rc = __damon_dbgfs_init(); + if (rc) { + kfree(dbgfs_ctxs[0]); + kfree(dbgfs_ctxs); + pr_err("%s: dbgfs init failed\n", __func__); + } + + return rc; +} + +module_init(damon_dbgfs_init); -- cgit v1.2.3 From a8a47cf5ce4bbc70a54fa4eca71d35f43dc8218a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 Sep 2021 19:57:41 -0700 Subject: include/linux/once.h: fix trivia typo Not -> Note Fix trivia typo Not -> Note in the comment to DO_ONCE(). Link: https://lkml.kernel.org/r/20210722184349.76290-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/once.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/once.h b/include/linux/once.h index ae6f4eb41cbe..d361fb14ac3a 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -16,7 +16,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key, * out the condition into a nop. DO_ONCE() guarantees type safety of * arguments! * - * Not that the following is not equivalent ... + * Note that the following is not equivalent ... * * DO_ONCE(func, arg); * DO_ONCE(func, arg); -- cgit v1.2.3 From c9221919a2d2df5741ab074dfec5bdfc6f1e043b Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 7 Sep 2021 19:57:44 -0700 Subject: units: change from 'L' to 'UL' Patch series "Add Hz macros", v3. There are multiple definitions of the HZ_PER_MHZ or HZ_PER_KHZ in the different drivers. Instead of duplicating this definition again and again, add one in the units.h header to be reused in all the place the redefiniton occurs. At the same time, change the type of the Watts, as they can not be negative. This patch (of 10): The users of the macros are safe to be assigned with an unsigned instead of signed as the variables using them are themselves unsigned. Link: https://lkml.kernel.org/r/20210816114732.1834145-1-daniel.lezcano@linaro.org Link: https://lkml.kernel.org/r/20210816114732.1834145-2-daniel.lezcano@linaro.org Signed-off-by: Daniel Lezcano Cc: Andy Shevchenko Cc: Jonathan Cameron Cc: Christian Eggers Cc: Lukasz Luba Cc: MyungJoo Ham Cc: Kyungmin Park Cc: Lars-Peter Clausen Cc: Peter Meerwald Cc: Zhang Rui Cc: Guenter Roeck Cc: Miquel Raynal Cc: Maxime Coquelin Cc: "Rafael J. Wysocki" Cc: Daniel Lezcano Cc: Chanwoo Choi Cc: Jonathan Cameron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/units.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/units.h b/include/linux/units.h index dcc30a53fa93..ff51d3cfc6a0 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -4,9 +4,9 @@ #include -#define MILLIWATT_PER_WATT 1000L -#define MICROWATT_PER_MILLIWATT 1000L -#define MICROWATT_PER_WATT 1000000L +#define MILLIWATT_PER_WATT 1000UL +#define MICROWATT_PER_MILLIWATT 1000UL +#define MICROWATT_PER_WATT 1000000UL #define ABSOLUTE_ZERO_MILLICELSIUS -273150 -- cgit v1.2.3 From e2c77032fcbe515194107994d12cd72ddb77b022 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 7 Sep 2021 19:57:48 -0700 Subject: units: add the HZ macros The macros for the unit conversion for frequency are duplicated in different places. Provide these macros in the 'units' header, so they can be reused. Link: https://lkml.kernel.org/r/20210816114732.1834145-3-daniel.lezcano@linaro.org Signed-off-by: Daniel Lezcano Reviewed-by: Christian Eggers Reviewed-by: Andy Shevchenko Cc: Chanwoo Choi Cc: Guenter Roeck Cc: Jonathan Cameron Cc: Jonathan Cameron Cc: Kyungmin Park Cc: Lars-Peter Clausen Cc: Lukasz Luba Cc: Maxime Coquelin Cc: Miquel Raynal Cc: MyungJoo Ham Cc: Peter Meerwald Cc: "Rafael J. Wysocki" Cc: Zhang Rui Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/units.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/units.h b/include/linux/units.h index ff51d3cfc6a0..8b8dc8a84d93 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -4,6 +4,10 @@ #include +#define HZ_PER_KHZ 1000UL +#define KHZ_PER_MHZ 1000UL +#define HZ_PER_MHZ 1000000UL + #define MILLIWATT_PER_WATT 1000UL #define MICROWATT_PER_MILLIWATT 1000UL #define MICROWATT_PER_WATT 1000000UL -- cgit v1.2.3 From 1e1c15839df084f4011825fee922aa976c9159dc Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 7 Sep 2021 20:00:00 -0700 Subject: fs/epoll: use a per-cpu counter for user's watches count This counter tracks the number of watches a user has, to compare against the 'max_user_watches' limit. This causes a scalability bottleneck on SPECjbb2015 on large systems as there is only one user. Changing to a per-cpu counter increases throughput of the benchmark by about 30% on a 16-socket, > 1000 thread system. [rdunlap@infradead.org: fix build errors in kernel/user.c when CONFIG_EPOLL=n] [npiggin@gmail.com: move ifdefs into wrapper functions, slightly improve panic message] Link: https://lkml.kernel.org/r/1628051945.fens3r99ox.astroid@bobo.none [akpm@linux-foundation.org: tweak user_epoll_alloc(), per Guenter] Link: https://lkml.kernel.org/r/20210804191421.GA1900577@roeck-us.net Link: https://lkml.kernel.org/r/20210802032013.2751916-1-npiggin@gmail.com Signed-off-by: Nicholas Piggin Reported-by: Anton Blanchard Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventpoll.c | 18 ++++++++++-------- include/linux/sched/user.h | 3 ++- kernel/user.c | 25 +++++++++++++++++++++++++ 3 files changed, 37 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 1e596e1d0bba..648ed77f4164 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -723,7 +723,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) */ call_rcu(&epi->rcu, epi_rcu_free); - atomic_long_dec(&ep->user->epoll_watches); + percpu_counter_dec(&ep->user->epoll_watches); return 0; } @@ -1439,7 +1439,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, { int error, pwake = 0; __poll_t revents; - long user_watches; struct epitem *epi; struct ep_pqueue epq; struct eventpoll *tep = NULL; @@ -1449,11 +1448,15 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, lockdep_assert_irqs_enabled(); - user_watches = atomic_long_read(&ep->user->epoll_watches); - if (unlikely(user_watches >= max_user_watches)) + if (unlikely(percpu_counter_compare(&ep->user->epoll_watches, + max_user_watches) >= 0)) return -ENOSPC; - if (!(epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL))) + percpu_counter_inc(&ep->user->epoll_watches); + + if (!(epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL))) { + percpu_counter_dec(&ep->user->epoll_watches); return -ENOMEM; + } /* Item initialization follow here ... */ INIT_LIST_HEAD(&epi->rdllink); @@ -1466,17 +1469,16 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, mutex_lock_nested(&tep->mtx, 1); /* Add the current item to the list of active epoll hook for this file */ if (unlikely(attach_epitem(tfile, epi) < 0)) { - kmem_cache_free(epi_cache, epi); if (tep) mutex_unlock(&tep->mtx); + kmem_cache_free(epi_cache, epi); + percpu_counter_dec(&ep->user->epoll_watches); return -ENOMEM; } if (full_check && !tep) list_file(tfile); - atomic_long_inc(&ep->user->epoll_watches); - /* * Add the current item to the RB tree. All RB tree operations are * protected by "mtx", and ep_insert() is called with "mtx" held. diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 2462f7d07695..00ed419dd464 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -4,6 +4,7 @@ #include #include +#include #include #include @@ -13,7 +14,7 @@ struct user_struct { refcount_t __count; /* reference count */ #ifdef CONFIG_EPOLL - atomic_long_t epoll_watches; /* The number of file descriptors currently watched */ + struct percpu_counter epoll_watches; /* The number of file descriptors currently watched */ #endif unsigned long unix_inflight; /* How many files in flight in unix sockets */ atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */ diff --git a/kernel/user.c b/kernel/user.c index c82399c1618a..e2cf8c22b539 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -129,6 +129,22 @@ static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent) return NULL; } +static int user_epoll_alloc(struct user_struct *up) +{ +#ifdef CONFIG_EPOLL + return percpu_counter_init(&up->epoll_watches, 0, GFP_KERNEL); +#else + return 0; +#endif +} + +static void user_epoll_free(struct user_struct *up) +{ +#ifdef CONFIG_EPOLL + percpu_counter_destroy(&up->epoll_watches); +#endif +} + /* IRQs are disabled and uidhash_lock is held upon function entry. * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. @@ -138,6 +154,7 @@ static void free_user(struct user_struct *up, unsigned long flags) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); + user_epoll_free(up); kmem_cache_free(uid_cachep, up); } @@ -185,6 +202,10 @@ struct user_struct *alloc_uid(kuid_t uid) new->uid = uid; refcount_set(&new->__count, 1); + if (user_epoll_alloc(new)) { + kmem_cache_free(uid_cachep, new); + return NULL; + } ratelimit_state_init(&new->ratelimit, HZ, 100); ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE); @@ -195,6 +216,7 @@ struct user_struct *alloc_uid(kuid_t uid) spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { + user_epoll_free(new); kmem_cache_free(uid_cachep, new); } else { uid_hash_insert(new, hashent); @@ -216,6 +238,9 @@ static int __init uid_cache_init(void) for(n = 0; n < UIDHASH_SZ; ++n) INIT_HLIST_HEAD(uidhash_table + n); + if (user_epoll_alloc(&root_user)) + panic("root_user epoll percpu counter alloc failed"); + /* Insert the root user immediately (init already runs as root) */ spin_lock_irq(&uidhash_lock); uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID)); -- cgit v1.2.3 From 5b91a75b3312c03798f555e10569fd85211a490c Mon Sep 17 00:00:00 2001 From: Takahiro Itazuri Date: Tue, 7 Sep 2021 20:00:38 -0700 Subject: pid: cleanup the stale comment mentioning pidmap_init(). pidmap_init() has already been replaced with pid_idr_init() in the commit 95846ecf9dac ("pid: replace pid bitmap implementation with IDR API"). Cleanup the stale comment which still mentions it. Link: https://lkml.kernel.org/r/20210714120713.19825-1-itazur@amazon.com Signed-off-by: Takahiro Itazuri Cc: Kuniyuki Iwashima Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/threads.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/threads.h b/include/linux/threads.h index 18d5a74bcc3d..c34173e6c5f1 100644 --- a/include/linux/threads.h +++ b/include/linux/threads.h @@ -38,7 +38,7 @@ * Define a minimum number of pids per cpu. Heuristically based * on original pid max of 32k for 32 cpus. Also, increase the * minimum settable value for pid_max on the running system based - * on similar defaults. See kernel/pid.c:pidmap_init() for details. + * on similar defaults. See kernel/pid.c:pid_idr_init() for details. */ #define PIDS_PER_CPU_DEFAULT 1024 #define PIDS_PER_CPU_MIN 8 -- cgit v1.2.3 From e130242dc351f1cfa2bbeb6766a1486ce936ef88 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Sep 2021 15:18:21 -0700 Subject: mm: simplify compat numa syscalls The compat implementations for mbind, get_mempolicy, set_mempolicy and migrate_pages are just there to handle the subtly different layout of bitmaps on 32-bit hosts. The compat implementation however lacks some of the checks that are present in the native one, in particular for checking that the extra bits are all zero when user space has a larger mask size than the kernel. Worse, those extra bits do not get cleared when copying in or out of the kernel, which can lead to incorrect data as well. Unify the implementation to handle the compat bitmap layout directly in the get_nodes() and copy_nodes_to_user() helpers. Splitting out the get_bitmap() helper from get_nodes() also helps readability of the native case. On x86, two additional problems are addressed by this: compat tasks can pass a bitmap at the end of a mapping, causing a fault when reading across the page boundary for a 64-bit word. x32 tasks might also run into problems with get_mempolicy corrupting data when an odd number of 32-bit words gets passed. On parisc the migrate_pages() system call apparently had the wrong calling convention, as big-endian architectures expect the words inside of a bitmap to be swapped. This is not a problem though since parisc has no NUMA support. [arnd@arndb.de: fix mempolicy crash] Link: https://lkml.kernel.org/r/20210730143417.3700653-1-arnd@kernel.org Link: https://lore.kernel.org/lkml/YQPLG20V3dmOfq3a@osiris/ Link: https://lkml.kernel.org/r/20210727144859.4150043-5-arnd@kernel.org Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christoph Hellwig Cc: "David S. Miller" Cc: Eric Biederman Cc: Feng Tang Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Paul Mackerras Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 17 ++--- mm/mempolicy.c | 176 ++++++++++++++++--------------------------------- 2 files changed, 64 insertions(+), 129 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 8e0598c7d1d1..3a2ac5afee30 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -395,14 +395,6 @@ struct compat_kexec_segment; struct compat_mq_attr; struct compat_msgbuf; -#define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) - -#define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) - -long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, - unsigned long bitmap_size); -long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, - unsigned long bitmap_size); void copy_siginfo_to_external32(struct compat_siginfo *to, const struct kernel_siginfo *from); int copy_siginfo_from_user32(kernel_siginfo_t *to, @@ -976,6 +968,15 @@ static inline bool in_compat_syscall(void) { return false; } #endif /* CONFIG_COMPAT */ +#define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) + +#define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) + +long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, + unsigned long bitmap_size); +long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, + unsigned long bitmap_size); + /* * Some legacy ABIs like the i386 one use less than natural alignment for 64-bit * types, and will need special compat treatment for that. Most architectures diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 5e90b3fb7794..eb95578f5997 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1362,16 +1362,33 @@ mpol_out: /* * User space interface with variable sized bitmaps for nodelists. */ +static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask, + unsigned long maxnode) +{ + unsigned long nlongs = BITS_TO_LONGS(maxnode); + int ret; + + if (in_compat_syscall()) + ret = compat_get_bitmap(mask, + (const compat_ulong_t __user *)nmask, + maxnode); + else + ret = copy_from_user(mask, nmask, + nlongs * sizeof(unsigned long)); + + if (ret) + return -EFAULT; + + if (maxnode % BITS_PER_LONG) + mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1; + + return 0; +} /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { - unsigned long k; - unsigned long t; - unsigned long nlongs; - unsigned long endmask; - --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) @@ -1379,49 +1396,29 @@ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; - nlongs = BITS_TO_LONGS(maxnode); - if ((maxnode % BITS_PER_LONG) == 0) - endmask = ~0UL; - else - endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1; - /* * When the user specified more nodes than supported just check - * if the non supported part is all zero. - * - * If maxnode have more longs than MAX_NUMNODES, check - * the bits in that area first. And then go through to - * check the rest bits which equal or bigger than MAX_NUMNODES. - * Otherwise, just check bits [MAX_NUMNODES, maxnode). + * if the non supported part is all zero, one word at a time, + * starting at the end. */ - if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) { - for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) { - if (get_user(t, nmask + k)) - return -EFAULT; - if (k == nlongs - 1) { - if (t & endmask) - return -EINVAL; - } else if (t) - return -EINVAL; - } - nlongs = BITS_TO_LONGS(MAX_NUMNODES); - endmask = ~0UL; - } + while (maxnode > MAX_NUMNODES) { + unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); + unsigned long t; - if (maxnode > MAX_NUMNODES && MAX_NUMNODES % BITS_PER_LONG != 0) { - unsigned long valid_mask = endmask; - - valid_mask &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); - if (get_user(t, nmask + nlongs - 1)) + if (get_bitmap(&t, &nmask[maxnode / BITS_PER_LONG], bits)) return -EFAULT; - if (t & valid_mask) + + if (maxnode - bits >= MAX_NUMNODES) { + maxnode -= bits; + } else { + maxnode = MAX_NUMNODES; + t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); + } + if (t) return -EINVAL; } - if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long))) - return -EFAULT; - nodes_addr(*nodes)[nlongs-1] &= endmask; - return 0; + return get_bitmap(nodes_addr(*nodes), nmask, maxnode); } /* Copy a kernel node mask to user space */ @@ -1430,6 +1427,10 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); + bool compat = in_compat_syscall(); + + if (compat) + nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t); if (copy > nbytes) { if (copy > PAGE_SIZE) @@ -1437,7 +1438,13 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; + maxnode = nr_node_ids; } + + if (compat) + return compat_put_bitmap((compat_ulong_t __user *)mask, + nodes_addr(*nodes), maxnode); + return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } @@ -1649,72 +1656,22 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, compat_ulong_t, maxnode, compat_ulong_t, addr, compat_ulong_t, flags) { - long err; - unsigned long __user *nm = NULL; - unsigned long nr_bits, alloc_size; - DECLARE_BITMAP(bm, MAX_NUMNODES); - - nr_bits = min_t(unsigned long, maxnode-1, nr_node_ids); - alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; - - if (nmask) - nm = compat_alloc_user_space(alloc_size); - - err = kernel_get_mempolicy(policy, nm, nr_bits+1, addr, flags); - - if (!err && nmask) { - unsigned long copy_size; - copy_size = min_t(unsigned long, sizeof(bm), alloc_size); - err = copy_from_user(bm, nm, copy_size); - /* ensure entire bitmap is zeroed */ - err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8); - err |= compat_put_bitmap(nmask, bm, nr_bits); - } - - return err; + return kernel_get_mempolicy(policy, (unsigned long __user *)nmask, + maxnode, addr, flags); } COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode) { - unsigned long __user *nm = NULL; - unsigned long nr_bits, alloc_size; - DECLARE_BITMAP(bm, MAX_NUMNODES); - - nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); - alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; - - if (nmask) { - if (compat_get_bitmap(bm, nmask, nr_bits)) - return -EFAULT; - nm = compat_alloc_user_space(alloc_size); - if (copy_to_user(nm, bm, alloc_size)) - return -EFAULT; - } - - return kernel_set_mempolicy(mode, nm, nr_bits+1); + return kernel_set_mempolicy(mode, (unsigned long __user *)nmask, maxnode); } COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, compat_ulong_t, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, flags) { - unsigned long __user *nm = NULL; - unsigned long nr_bits, alloc_size; - nodemask_t bm; - - nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); - alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; - - if (nmask) { - if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits)) - return -EFAULT; - nm = compat_alloc_user_space(alloc_size); - if (copy_to_user(nm, nodes_addr(bm), alloc_size)) - return -EFAULT; - } - - return kernel_mbind(start, len, mode, nm, nr_bits+1, flags); + return kernel_mbind(start, len, mode, (unsigned long __user *)nmask, + maxnode, flags); } COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, @@ -1722,32 +1679,9 @@ COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, const compat_ulong_t __user *, old_nodes, const compat_ulong_t __user *, new_nodes) { - unsigned long __user *old = NULL; - unsigned long __user *new = NULL; - nodemask_t tmp_mask; - unsigned long nr_bits; - unsigned long size; - - nr_bits = min_t(unsigned long, maxnode - 1, MAX_NUMNODES); - size = ALIGN(nr_bits, BITS_PER_LONG) / 8; - if (old_nodes) { - if (compat_get_bitmap(nodes_addr(tmp_mask), old_nodes, nr_bits)) - return -EFAULT; - old = compat_alloc_user_space(new_nodes ? size * 2 : size); - if (new_nodes) - new = old + size / sizeof(unsigned long); - if (copy_to_user(old, nodes_addr(tmp_mask), size)) - return -EFAULT; - } - if (new_nodes) { - if (compat_get_bitmap(nodes_addr(tmp_mask), new_nodes, nr_bits)) - return -EFAULT; - if (new == NULL) - new = compat_alloc_user_space(size); - if (copy_to_user(new, nodes_addr(tmp_mask), size)) - return -EFAULT; - } - return kernel_migrate_pages(pid, nr_bits + 1, old, new); + return kernel_migrate_pages(pid, maxnode, + (const unsigned long __user *)old_nodes, + (const unsigned long __user *)new_nodes); } #endif /* CONFIG_COMPAT */ -- cgit v1.2.3 From 59ab844eed9c6b01d32dcb27b57accc23771b324 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Sep 2021 15:18:25 -0700 Subject: compat: remove some compat entry points These are all handled correctly when calling the native system call entry point, so remove the special cases. Link: https://lkml.kernel.org/r/20210727144859.4150043-6-arnd@kernel.org Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christoph Hellwig Cc: "David S. Miller" Cc: Eric Biederman Cc: Feng Tang Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Paul Mackerras Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/include/asm/unistd32.h | 10 ++++----- arch/mips/kernel/syscalls/syscall_n32.tbl | 10 ++++----- arch/mips/kernel/syscalls/syscall_o32.tbl | 10 ++++----- arch/parisc/kernel/syscalls/syscall.tbl | 8 +++---- arch/powerpc/kernel/syscalls/syscall.tbl | 10 ++++----- arch/s390/kernel/syscalls/syscall.tbl | 10 ++++----- arch/sparc/kernel/syscalls/syscall.tbl | 10 ++++----- arch/x86/entry/syscalls/syscall_32.tbl | 4 ++-- arch/x86/entry/syscalls/syscall_64.tbl | 2 +- include/linux/compat.h | 20 ----------------- include/uapi/asm-generic/unistd.h | 10 ++++----- kernel/sys_ni.c | 5 ----- mm/mempolicy.c | 37 ------------------------------- mm/migrate.c | 13 ----------- 14 files changed, 42 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 4e99e4b912ef..844f6ae58662 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -649,11 +649,11 @@ __SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch) #define __NR_inotify_rm_watch 318 __SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch) #define __NR_mbind 319 -__SYSCALL(__NR_mbind, compat_sys_mbind) +__SYSCALL(__NR_mbind, sys_mbind) #define __NR_get_mempolicy 320 -__SYSCALL(__NR_get_mempolicy, compat_sys_get_mempolicy) +__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy) #define __NR_set_mempolicy 321 -__SYSCALL(__NR_set_mempolicy, compat_sys_set_mempolicy) +__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy) #define __NR_openat 322 __SYSCALL(__NR_openat, compat_sys_openat) #define __NR_mkdirat 323 @@ -699,7 +699,7 @@ __SYSCALL(__NR_tee, sys_tee) #define __NR_vmsplice 343 __SYSCALL(__NR_vmsplice, sys_vmsplice) #define __NR_move_pages 344 -__SYSCALL(__NR_move_pages, compat_sys_move_pages) +__SYSCALL(__NR_move_pages, sys_move_pages) #define __NR_getcpu 345 __SYSCALL(__NR_getcpu, sys_getcpu) #define __NR_epoll_pwait 346 @@ -811,7 +811,7 @@ __SYSCALL(__NR_rseq, sys_rseq) #define __NR_io_pgetevents 399 __SYSCALL(__NR_io_pgetevents, compat_sys_io_pgetevents) #define __NR_migrate_pages 400 -__SYSCALL(__NR_migrate_pages, compat_sys_migrate_pages) +__SYSCALL(__NR_migrate_pages, sys_migrate_pages) #define __NR_kexec_file_load 401 __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) /* 402 is unused */ diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 56c8d3cf42ed..70e32de2bcaa 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -239,9 +239,9 @@ 228 n32 clock_nanosleep sys_clock_nanosleep_time32 229 n32 tgkill sys_tgkill 230 n32 utimes sys_utimes_time32 -231 n32 mbind compat_sys_mbind -232 n32 get_mempolicy compat_sys_get_mempolicy -233 n32 set_mempolicy compat_sys_set_mempolicy +231 n32 mbind sys_mbind +232 n32 get_mempolicy sys_get_mempolicy +233 n32 set_mempolicy sys_set_mempolicy 234 n32 mq_open compat_sys_mq_open 235 n32 mq_unlink sys_mq_unlink 236 n32 mq_timedsend sys_mq_timedsend_time32 @@ -258,7 +258,7 @@ 247 n32 inotify_init sys_inotify_init 248 n32 inotify_add_watch sys_inotify_add_watch 249 n32 inotify_rm_watch sys_inotify_rm_watch -250 n32 migrate_pages compat_sys_migrate_pages +250 n32 migrate_pages sys_migrate_pages 251 n32 openat sys_openat 252 n32 mkdirat sys_mkdirat 253 n32 mknodat sys_mknodat @@ -279,7 +279,7 @@ 268 n32 sync_file_range sys_sync_file_range 269 n32 tee sys_tee 270 n32 vmsplice sys_vmsplice -271 n32 move_pages compat_sys_move_pages +271 n32 move_pages sys_move_pages 272 n32 set_robust_list compat_sys_set_robust_list 273 n32 get_robust_list compat_sys_get_robust_list 274 n32 kexec_load compat_sys_kexec_load diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 201237fd0f43..a61c35edaa74 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -279,9 +279,9 @@ 265 o32 clock_nanosleep sys_clock_nanosleep_time32 266 o32 tgkill sys_tgkill 267 o32 utimes sys_utimes_time32 -268 o32 mbind sys_mbind compat_sys_mbind -269 o32 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy -270 o32 set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy +268 o32 mbind sys_mbind +269 o32 get_mempolicy sys_get_mempolicy +270 o32 set_mempolicy sys_set_mempolicy 271 o32 mq_open sys_mq_open compat_sys_mq_open 272 o32 mq_unlink sys_mq_unlink 273 o32 mq_timedsend sys_mq_timedsend_time32 @@ -298,7 +298,7 @@ 284 o32 inotify_init sys_inotify_init 285 o32 inotify_add_watch sys_inotify_add_watch 286 o32 inotify_rm_watch sys_inotify_rm_watch -287 o32 migrate_pages sys_migrate_pages compat_sys_migrate_pages +287 o32 migrate_pages sys_migrate_pages 288 o32 openat sys_openat compat_sys_openat 289 o32 mkdirat sys_mkdirat 290 o32 mknodat sys_mknodat @@ -319,7 +319,7 @@ 305 o32 sync_file_range sys_sync_file_range sys32_sync_file_range 306 o32 tee sys_tee 307 o32 vmsplice sys_vmsplice -308 o32 move_pages sys_move_pages compat_sys_move_pages +308 o32 move_pages sys_move_pages 309 o32 set_robust_list sys_set_robust_list compat_sys_set_robust_list 310 o32 get_robust_list sys_get_robust_list compat_sys_get_robust_list 311 o32 kexec_load sys_kexec_load compat_sys_kexec_load diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 0bf854b70612..bf751e0732b7 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -292,9 +292,9 @@ 258 32 clock_nanosleep sys_clock_nanosleep_time32 258 64 clock_nanosleep sys_clock_nanosleep 259 common tgkill sys_tgkill -260 common mbind sys_mbind compat_sys_mbind -261 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy -262 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy +260 common mbind sys_mbind +261 common get_mempolicy sys_get_mempolicy +262 common set_mempolicy sys_set_mempolicy # 263 was vserver 264 common add_key sys_add_key 265 common request_key sys_request_key @@ -331,7 +331,7 @@ 292 64 sync_file_range sys_sync_file_range 293 common tee sys_tee 294 common vmsplice sys_vmsplice -295 common move_pages sys_move_pages compat_sys_move_pages +295 common move_pages sys_move_pages 296 common getcpu sys_getcpu 297 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait 298 common statfs64 sys_statfs64 compat_sys_statfs64 diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 29b55e2e035c..7bef917cc84e 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -330,10 +330,10 @@ 256 64 sys_debug_setcontext sys_ni_syscall 256 spu sys_debug_setcontext sys_ni_syscall # 257 reserved for vserver -258 nospu migrate_pages sys_migrate_pages compat_sys_migrate_pages -259 nospu mbind sys_mbind compat_sys_mbind -260 nospu get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy -261 nospu set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy +258 nospu migrate_pages sys_migrate_pages +259 nospu mbind sys_mbind +260 nospu get_mempolicy sys_get_mempolicy +261 nospu set_mempolicy sys_set_mempolicy 262 nospu mq_open sys_mq_open compat_sys_mq_open 263 nospu mq_unlink sys_mq_unlink 264 32 mq_timedsend sys_mq_timedsend_time32 @@ -381,7 +381,7 @@ 298 common faccessat sys_faccessat 299 common get_robust_list sys_get_robust_list compat_sys_get_robust_list 300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list -301 common move_pages sys_move_pages compat_sys_move_pages +301 common move_pages sys_move_pages 302 common getcpu sys_getcpu 303 nospu epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait 304 32 utimensat sys_utimensat_time32 diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index aa9d68b8ee14..df5261e5cfe1 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -274,9 +274,9 @@ 265 common statfs64 sys_statfs64 compat_sys_statfs64 266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 267 common remap_file_pages sys_remap_file_pages sys_remap_file_pages -268 common mbind sys_mbind compat_sys_mbind -269 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy -270 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy +268 common mbind sys_mbind sys_mbind +269 common get_mempolicy sys_get_mempolicy sys_get_mempolicy +270 common set_mempolicy sys_set_mempolicy sys_set_mempolicy 271 common mq_open sys_mq_open compat_sys_mq_open 272 common mq_unlink sys_mq_unlink sys_mq_unlink 273 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 @@ -293,7 +293,7 @@ 284 common inotify_init sys_inotify_init sys_inotify_init 285 common inotify_add_watch sys_inotify_add_watch sys_inotify_add_watch 286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch -287 common migrate_pages sys_migrate_pages compat_sys_migrate_pages +287 common migrate_pages sys_migrate_pages sys_migrate_pages 288 common openat sys_openat compat_sys_openat 289 common mkdirat sys_mkdirat sys_mkdirat 290 common mknodat sys_mknodat sys_mknodat @@ -317,7 +317,7 @@ 307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range 308 common tee sys_tee sys_tee 309 common vmsplice sys_vmsplice sys_vmsplice -310 common move_pages sys_move_pages compat_sys_move_pages +310 common move_pages sys_move_pages sys_move_pages 311 common getcpu sys_getcpu sys_getcpu 312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait 313 common utimes sys_utimes sys_utimes_time32 diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 7893104718c2..c37764dc764d 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -365,12 +365,12 @@ 299 common unshare sys_unshare 300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list 301 common get_robust_list sys_get_robust_list compat_sys_get_robust_list -302 common migrate_pages sys_migrate_pages compat_sys_migrate_pages -303 common mbind sys_mbind compat_sys_mbind -304 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy -305 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy +302 common migrate_pages sys_migrate_pages +303 common mbind sys_mbind +304 common get_mempolicy sys_get_mempolicy +305 common set_mempolicy sys_set_mempolicy 306 common kexec_load sys_kexec_load compat_sys_kexec_load -307 common move_pages sys_move_pages compat_sys_move_pages +307 common move_pages sys_move_pages 308 common getcpu sys_getcpu 309 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait 310 32 utimensat sys_utimensat_time32 diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 61f18b72552b..960a021d543e 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -286,7 +286,7 @@ 272 i386 fadvise64_64 sys_ia32_fadvise64_64 273 i386 vserver 274 i386 mbind sys_mbind -275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy +275 i386 get_mempolicy sys_get_mempolicy 276 i386 set_mempolicy sys_set_mempolicy 277 i386 mq_open sys_mq_open compat_sys_mq_open 278 i386 mq_unlink sys_mq_unlink @@ -328,7 +328,7 @@ 314 i386 sync_file_range sys_ia32_sync_file_range 315 i386 tee sys_tee 316 i386 vmsplice sys_vmsplice -317 i386 move_pages sys_move_pages compat_sys_move_pages +317 i386 move_pages sys_move_pages 318 i386 getcpu sys_getcpu 319 i386 epoll_pwait sys_epoll_pwait 320 i386 utimensat sys_utimensat_time32 diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 807b6a1de8e8..18b5500ea8bf 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -398,7 +398,7 @@ 530 x32 set_robust_list compat_sys_set_robust_list 531 x32 get_robust_list compat_sys_get_robust_list 532 x32 vmsplice sys_vmsplice -533 x32 move_pages compat_sys_move_pages +533 x32 move_pages sys_move_pages 534 x32 preadv compat_sys_preadv64 535 x32 pwritev compat_sys_pwritev64 536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo diff --git a/include/linux/compat.h b/include/linux/compat.h index 3a2ac5afee30..2d42cebd1fb8 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -799,26 +799,6 @@ asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr /* mm/fadvise.c: No generic prototype for fadvise64_64 */ /* mm/, CONFIG_MMU only */ -asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len, - compat_ulong_t mode, - compat_ulong_t __user *nmask, - compat_ulong_t maxnode, compat_ulong_t flags); -asmlinkage long compat_sys_get_mempolicy(int __user *policy, - compat_ulong_t __user *nmask, - compat_ulong_t maxnode, - compat_ulong_t addr, - compat_ulong_t flags); -asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask, - compat_ulong_t maxnode); -asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, - compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, - const compat_ulong_t __user *new_nodes); -asmlinkage long compat_sys_move_pages(pid_t pid, compat_ulong_t nr_pages, - __u32 __user *pages, - const int __user *nodes, - int __user *status, - int flags); - asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 14c8fe863c6d..1c5fb86d455a 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -673,15 +673,15 @@ __SYSCALL(__NR_madvise, sys_madvise) #define __NR_remap_file_pages 234 __SYSCALL(__NR_remap_file_pages, sys_remap_file_pages) #define __NR_mbind 235 -__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind) +__SYSCALL(__NR_mbind, sys_mbind) #define __NR_get_mempolicy 236 -__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy) +__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy) #define __NR_set_mempolicy 237 -__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy) +__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy) #define __NR_migrate_pages 238 -__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages) +__SYSCALL(__NR_migrate_pages, sys_migrate_pages) #define __NR_move_pages 239 -__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages) +__SYSCALL(__NR_move_pages, sys_move_pages) #endif #define __NR_rt_tgsigqueueinfo 240 diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 64578adfe115..f43d89d92860 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -292,15 +292,10 @@ COND_SYSCALL(process_madvise); COND_SYSCALL(process_mrelease); COND_SYSCALL(remap_file_pages); COND_SYSCALL(mbind); -COND_SYSCALL_COMPAT(mbind); COND_SYSCALL(get_mempolicy); -COND_SYSCALL_COMPAT(get_mempolicy); COND_SYSCALL(set_mempolicy); -COND_SYSCALL_COMPAT(set_mempolicy); COND_SYSCALL(migrate_pages); -COND_SYSCALL_COMPAT(migrate_pages); COND_SYSCALL(move_pages); -COND_SYSCALL_COMPAT(move_pages); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index eb95578f5997..8d14240896a8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1649,43 +1649,6 @@ SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } -#ifdef CONFIG_COMPAT - -COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, - compat_ulong_t __user *, nmask, - compat_ulong_t, maxnode, - compat_ulong_t, addr, compat_ulong_t, flags) -{ - return kernel_get_mempolicy(policy, (unsigned long __user *)nmask, - maxnode, addr, flags); -} - -COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, - compat_ulong_t, maxnode) -{ - return kernel_set_mempolicy(mode, (unsigned long __user *)nmask, maxnode); -} - -COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, - compat_ulong_t, mode, compat_ulong_t __user *, nmask, - compat_ulong_t, maxnode, compat_ulong_t, flags) -{ - return kernel_mbind(start, len, mode, (unsigned long __user *)nmask, - maxnode, flags); -} - -COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, - compat_ulong_t, maxnode, - const compat_ulong_t __user *, old_nodes, - const compat_ulong_t __user *, new_nodes) -{ - return kernel_migrate_pages(pid, maxnode, - (const unsigned long __user *)old_nodes, - (const unsigned long __user *)new_nodes); -} - -#endif /* CONFIG_COMPAT */ - bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) diff --git a/mm/migrate.c b/mm/migrate.c index 2bc494875cea..a6a7743ee98f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2047,19 +2047,6 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags); } -#ifdef CONFIG_COMPAT -COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages, - compat_uptr_t __user *, pages, - const int __user *, nodes, - int __user *, status, - int, flags) -{ - return kernel_move_pages(pid, nr_pages, - (const void __user *__user *)pages, - nodes, status, flags); -} -#endif /* CONFIG_COMPAT */ - #ifdef CONFIG_NUMA_BALANCING /* * Returns true if this is a safe migration target node for misplaced NUMA -- cgit v1.2.3 From a7a08b275a8bbade798c4bdaad07ade68fe7003c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Sep 2021 15:18:29 -0700 Subject: arch: remove compat_alloc_user_space All users of compat_alloc_user_space() and copy_in_user() have been removed from the kernel, only a few functions in sparc remain that can be changed to calling arch_copy_in_user() instead. Link: https://lkml.kernel.org/r/20210727144859.4150043-7-arnd@kernel.org Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christoph Hellwig Cc: "David S. Miller" Cc: Eric Biederman Cc: Feng Tang Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Paul Mackerras Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/include/asm/compat.h | 5 --- arch/arm64/include/asm/uaccess.h | 11 ----- arch/arm64/lib/Makefile | 2 +- arch/arm64/lib/copy_in_user.S | 77 --------------------------------- arch/mips/cavium-octeon/octeon-memcpy.S | 2 - arch/mips/include/asm/compat.h | 8 ---- arch/mips/include/asm/uaccess.h | 26 ----------- arch/mips/lib/memcpy.S | 11 ----- arch/parisc/include/asm/compat.h | 6 --- arch/parisc/include/asm/uaccess.h | 2 - arch/parisc/lib/memcpy.c | 9 ---- arch/powerpc/include/asm/compat.h | 16 ------- arch/s390/include/asm/compat.h | 10 ----- arch/s390/include/asm/uaccess.h | 3 -- arch/s390/lib/uaccess.c | 63 --------------------------- arch/sparc/include/asm/compat.h | 19 -------- arch/sparc/kernel/process_64.c | 2 +- arch/sparc/kernel/signal32.c | 12 ++--- arch/sparc/kernel/signal_64.c | 8 ++-- arch/x86/include/asm/compat.h | 13 ------ arch/x86/include/asm/uaccess_64.h | 7 --- include/linux/compat.h | 2 - include/linux/uaccess.h | 10 ----- kernel/compat.c | 21 --------- 24 files changed, 12 insertions(+), 333 deletions(-) delete mode 100644 arch/arm64/lib/copy_in_user.S (limited to 'include/linux') diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 79c1a750e357..eaa6ca062d89 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -107,11 +107,6 @@ struct compat_statfs { #define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current))) #define COMPAT_MINSIGSTKSZ 2048 -static inline void __user *arch_compat_alloc_user_space(long len) -{ - return (void __user *)compat_user_stack_pointer() - len; -} - struct compat_ipc64_perm { compat_key_t key; __compat_uid32_t uid; diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index b5f08621fa29..190b494e22ab 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -430,17 +430,6 @@ extern unsigned long __must_check __arch_copy_to_user(void __user *to, const voi __actu_ret; \ }) -extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n); -#define raw_copy_in_user(to, from, n) \ -({ \ - unsigned long __aciu_ret; \ - uaccess_ttbr0_enable(); \ - __aciu_ret = __arch_copy_in_user(__uaccess_mask_ptr(to), \ - __uaccess_mask_ptr(from), (n)); \ - uaccess_ttbr0_disable(); \ - __aciu_ret; \ -}) - #define INLINE_COPY_TO_USER #define INLINE_COPY_FROM_USER diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 6dd56a49790a..0941180a86d3 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 lib-y := clear_user.o delay.o copy_from_user.o \ - copy_to_user.o copy_in_user.o copy_page.o \ + copy_to_user.o copy_page.o \ clear_page.o csum.o insn.o memchr.o memcpy.o \ memset.o memcmp.o strcmp.o strncmp.o strlen.o \ strnlen.o strchr.o strrchr.o tishift.o diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S deleted file mode 100644 index dbea3799c3ef..000000000000 --- a/arch/arm64/lib/copy_in_user.S +++ /dev/null @@ -1,77 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copy from user space to user space - * - * Copyright (C) 2012 ARM Ltd. - */ - -#include - -#include -#include -#include - -/* - * Copy from user space to user space (alignment handled by the hardware) - * - * Parameters: - * x0 - to - * x1 - from - * x2 - n - * Returns: - * x0 - bytes not copied - */ - .macro ldrb1 reg, ptr, val - user_ldst 9998f, ldtrb, \reg, \ptr, \val - .endm - - .macro strb1 reg, ptr, val - user_ldst 9998f, sttrb, \reg, \ptr, \val - .endm - - .macro ldrh1 reg, ptr, val - user_ldst 9997f, ldtrh, \reg, \ptr, \val - .endm - - .macro strh1 reg, ptr, val - user_ldst 9997f, sttrh, \reg, \ptr, \val - .endm - - .macro ldr1 reg, ptr, val - user_ldst 9997f, ldtr, \reg, \ptr, \val - .endm - - .macro str1 reg, ptr, val - user_ldst 9997f, sttr, \reg, \ptr, \val - .endm - - .macro ldp1 reg1, reg2, ptr, val - user_ldp 9997f, \reg1, \reg2, \ptr, \val - .endm - - .macro stp1 reg1, reg2, ptr, val - user_stp 9997f, \reg1, \reg2, \ptr, \val - .endm - -end .req x5 -srcin .req x15 -SYM_FUNC_START(__arch_copy_in_user) - add end, x0, x2 - mov srcin, x1 -#include "copy_template.S" - mov x0, #0 - ret -SYM_FUNC_END(__arch_copy_in_user) -EXPORT_SYMBOL(__arch_copy_in_user) - - .section .fixup,"ax" - .align 2 -9997: cmp dst, dstin - b.ne 9998f - // Before being absolutely sure we couldn't copy anything, try harder -USER(9998f, ldtrb tmp1w, [srcin]) -USER(9998f, sttrb tmp1w, [dst]) - add dst, dst, #1 -9998: sub x0, end, dst // bytes not copied - ret - .previous diff --git a/arch/mips/cavium-octeon/octeon-memcpy.S b/arch/mips/cavium-octeon/octeon-memcpy.S index 600d018cf354..0a515cde1c18 100644 --- a/arch/mips/cavium-octeon/octeon-memcpy.S +++ b/arch/mips/cavium-octeon/octeon-memcpy.S @@ -154,8 +154,6 @@ FEXPORT(__raw_copy_from_user) EXPORT_SYMBOL(__raw_copy_from_user) FEXPORT(__raw_copy_to_user) EXPORT_SYMBOL(__raw_copy_to_user) -FEXPORT(__raw_copy_in_user) -EXPORT_SYMBOL(__raw_copy_in_user) /* * Note: dst & src may be unaligned, len may be 0 * Temps diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 53f015a1b0a7..bbb3bc5a42fd 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -96,14 +96,6 @@ struct compat_statfs { #define COMPAT_OFF_T_MAX 0x7fffffff -static inline void __user *arch_compat_alloc_user_space(long len) -{ - struct pt_regs *regs = (struct pt_regs *) - ((unsigned long) current_thread_info() + THREAD_SIZE - 32) - 1; - - return (void __user *) (regs->regs[29] - len); -} - struct compat_ipc64_perm { compat_key_t key; __compat_uid32_t uid; diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index 783fecce65c8..f8f74f9f5883 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -428,7 +428,6 @@ do { \ extern size_t __raw_copy_from_user(void *__to, const void *__from, size_t __n); extern size_t __raw_copy_to_user(void *__to, const void *__from, size_t __n); -extern size_t __raw_copy_in_user(void *__to, const void *__from, size_t __n); static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) @@ -480,31 +479,6 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) #define INLINE_COPY_FROM_USER #define INLINE_COPY_TO_USER -static inline unsigned long -raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) -{ - register void __user *__cu_to_r __asm__("$4"); - register const void __user *__cu_from_r __asm__("$5"); - register long __cu_len_r __asm__("$6"); - - __cu_to_r = to; - __cu_from_r = from; - __cu_len_r = n; - - __asm__ __volatile__( - ".set\tnoreorder\n\t" - __MODULE_JAL(__raw_copy_in_user) - ".set\tnoat\n\t" - __UA_ADDU "\t$1, %1, %2\n\t" - ".set\tat\n\t" - ".set\treorder" - : "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r) - : - : "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31", - DADDI_SCRATCH, "memory"); - return __cu_len_r; -} - extern __kernel_size_t __bzero(void __user *addr, __kernel_size_t size); /* diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S index e19fb98b5d38..277c32296636 100644 --- a/arch/mips/lib/memcpy.S +++ b/arch/mips/lib/memcpy.S @@ -666,8 +666,6 @@ FEXPORT(__raw_copy_from_user) EXPORT_SYMBOL(__raw_copy_from_user) FEXPORT(__raw_copy_to_user) EXPORT_SYMBOL(__raw_copy_to_user) -FEXPORT(__raw_copy_in_user) -EXPORT_SYMBOL(__raw_copy_in_user) #endif /* Legacy Mode, user <-> user */ __BUILD_COPY_USER LEGACY_MODE USEROP USEROP @@ -703,13 +701,4 @@ EXPORT_SYMBOL(__raw_copy_to_user) __BUILD_COPY_USER EVA_MODE KERNELOP USEROP END(__raw_copy_to_user) -/* - * __copy_in_user (EVA) - */ - -LEAF(__raw_copy_in_user) -EXPORT_SYMBOL(__raw_copy_in_user) -__BUILD_COPY_USER EVA_MODE USEROP USEROP -END(__raw_copy_in_user) - #endif diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index b5d90e82b65d..c04f5a637c39 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -163,12 +163,6 @@ struct compat_shmid64_ds { #define COMPAT_ELF_NGREG 80 typedef compat_ulong_t compat_elf_gregset_t[COMPAT_ELF_NGREG]; -static __inline__ void __user *arch_compat_alloc_user_space(long len) -{ - struct pt_regs *regs = ¤t->thread.regs; - return (void __user *)regs->gr[30]; -} - static inline int __is_compat_task(struct task_struct *t) { return test_tsk_thread_flag(t, TIF_32BIT); diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index ed2cd4fb479b..7c13314aae4a 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -215,8 +215,6 @@ unsigned long __must_check raw_copy_to_user(void __user *dst, const void *src, unsigned long len); unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src, unsigned long len); -unsigned long __must_check raw_copy_in_user(void __user *dst, const void __user *src, - unsigned long len); #define INLINE_COPY_TO_USER #define INLINE_COPY_FROM_USER diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c index 4b75388190b4..ea70a0e08321 100644 --- a/arch/parisc/lib/memcpy.c +++ b/arch/parisc/lib/memcpy.c @@ -38,14 +38,6 @@ unsigned long raw_copy_from_user(void *dst, const void __user *src, } EXPORT_SYMBOL(raw_copy_from_user); -unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long len) -{ - mtsp(get_user_space(), 1); - mtsp(get_user_space(), 2); - return pa_memcpy((void __force *)dst, (void __force *)src, len); -} - - void * memcpy(void * dst,const void *src, size_t count) { mtsp(get_kernel_space(), 1); @@ -54,7 +46,6 @@ void * memcpy(void * dst,const void *src, size_t count) return dst; } -EXPORT_SYMBOL(raw_copy_in_user); EXPORT_SYMBOL(memcpy); bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index e33dcf134cdd..7afc96fb6524 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -83,22 +83,6 @@ struct compat_statfs { #define COMPAT_OFF_T_MAX 0x7fffffff -static inline void __user *arch_compat_alloc_user_space(long len) -{ - struct pt_regs *regs = current->thread.regs; - unsigned long usp = regs->gpr[1]; - - /* - * We can't access below the stack pointer in the 32bit ABI and - * can access 288 bytes in the 64bit big-endian ABI, - * or 512 bytes with the new ELFv2 little-endian ABI. - */ - if (!is_32bit_task()) - usp -= USER_REDZONE_SIZE; - - return (void __user *) (usp - len); -} - /* * ipc64_perm is actually 32/64bit clean but since the compat layer refers to * it we may as well define it. diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 8d49505b4a43..cdc7ae72529d 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -176,16 +176,6 @@ static inline int is_compat_task(void) return test_thread_flag(TIF_31BIT); } -static inline void __user *arch_compat_alloc_user_space(long len) -{ - unsigned long stack; - - stack = KSTK_ESP(current); - if (is_compat_task()) - stack &= 0x7fffffffUL; - return (void __user *) (stack - len); -} - #endif struct compat_ipc64_perm { diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 9ed9aa37e836..ce550d06abc3 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -227,9 +227,6 @@ static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long s __get_user(x, ptr); \ }) -unsigned long __must_check -raw_copy_in_user(void __user *to, const void __user *from, unsigned long n); - /* * Copy a null terminated string from userspace. */ diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index 94ca99bde59d..a596e69d3c47 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -204,69 +204,6 @@ unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long } EXPORT_SYMBOL(raw_copy_to_user); -static inline unsigned long copy_in_user_mvcos(void __user *to, const void __user *from, - unsigned long size) -{ - unsigned long tmp1, tmp2; - - tmp1 = -4096UL; - /* FIXME: copy with reduced length. */ - asm volatile( - " lgr 0,%[spec]\n" - "0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n" - " jz 2f\n" - "1: algr %0,%3\n" - " slgr %1,%3\n" - " slgr %2,%3\n" - " j 0b\n" - "2:slgr %0,%0\n" - "3: \n" - EX_TABLE(0b,3b) - : "+a" (size), "+a" (to), "+a" (from), "+a" (tmp1), "=a" (tmp2) - : [spec] "d" (0x810081UL) - : "cc", "memory", "0"); - return size; -} - -static inline unsigned long copy_in_user_mvc(void __user *to, const void __user *from, - unsigned long size) -{ - unsigned long tmp1; - - asm volatile( - " sacf 256\n" - " aghi %0,-1\n" - " jo 5f\n" - " bras %3,3f\n" - "0: aghi %0,257\n" - "1: mvc 0(1,%1),0(%2)\n" - " la %1,1(%1)\n" - " la %2,1(%2)\n" - " aghi %0,-1\n" - " jnz 1b\n" - " j 5f\n" - "2: mvc 0(256,%1),0(%2)\n" - " la %1,256(%1)\n" - " la %2,256(%2)\n" - "3: aghi %0,-256\n" - " jnm 2b\n" - "4: ex %0,1b-0b(%3)\n" - "5: slgr %0,%0\n" - "6: sacf 768\n" - EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b) - : "+a" (size), "+a" (to), "+a" (from), "=a" (tmp1) - : : "cc", "memory"); - return size; -} - -unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) -{ - if (copy_with_mvcos()) - return copy_in_user_mvcos(to, from, n); - return copy_in_user_mvc(to, from, n); -} -EXPORT_SYMBOL(raw_copy_in_user); - static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size) { unsigned long tmp1, tmp2; diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 8b63410e830f..bd949fcf9d63 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -116,25 +116,6 @@ struct compat_statfs { #define COMPAT_OFF_T_MAX 0x7fffffff -#ifdef CONFIG_COMPAT -static inline void __user *arch_compat_alloc_user_space(long len) -{ - struct pt_regs *regs = current_thread_info()->kregs; - unsigned long usp = regs->u_regs[UREG_I6]; - - if (test_thread_64bit_stack(usp)) - usp += STACK_BIAS; - - if (test_thread_flag(TIF_32BIT)) - usp &= 0xffffffffUL; - - usp -= len; - usp &= ~0x7UL; - - return (void __user *) usp; -} -#endif - struct compat_ipc64_perm { compat_key_t key; __compat_uid32_t uid; diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 093849bfda50..d1cc410d2f64 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -455,7 +455,7 @@ static unsigned long clone_stackframe(unsigned long csp, unsigned long psp) distance = fp - psp; rval = (csp - distance); - if (copy_in_user((void __user *) rval, (void __user *) psp, distance)) + if (raw_copy_in_user((void __user *)rval, (void __user *)psp, distance)) rval = 0; else if (!stack_64bit) { if (put_user(((u32)csp), diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 4276b9e003ca..6cc124a3bb98 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -435,9 +435,9 @@ static int setup_frame32(struct ksignal *ksig, struct pt_regs *regs, (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int)); if (!wsaved) { - err |= copy_in_user((u32 __user *)sf, - (u32 __user *)(regs->u_regs[UREG_FP]), - sizeof(struct reg_window32)); + err |= raw_copy_in_user((u32 __user *)sf, + (u32 __user *)(regs->u_regs[UREG_FP]), + sizeof(struct reg_window32)); } else { struct reg_window *rp; @@ -567,9 +567,9 @@ static int setup_rt_frame32(struct ksignal *ksig, struct pt_regs *regs, err |= put_compat_sigset(&sf->mask, oldset, sizeof(compat_sigset_t)); if (!wsaved) { - err |= copy_in_user((u32 __user *)sf, - (u32 __user *)(regs->u_regs[UREG_FP]), - sizeof(struct reg_window32)); + err |= raw_copy_in_user((u32 __user *)sf, + (u32 __user *)(regs->u_regs[UREG_FP]), + sizeof(struct reg_window32)); } else { struct reg_window *rp; diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index cea23cf95600..2a78d2af1265 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -406,10 +406,10 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) err |= copy_to_user(&sf->mask, sigmask_to_save(), sizeof(sigset_t)); if (!wsaved) { - err |= copy_in_user((u64 __user *)sf, - (u64 __user *)(regs->u_regs[UREG_FP] + - STACK_BIAS), - sizeof(struct reg_window)); + err |= raw_copy_in_user((u64 __user *)sf, + (u64 __user *)(regs->u_regs[UREG_FP] + + STACK_BIAS), + sizeof(struct reg_window)); } else { struct reg_window *rp; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 4ae01cdb99de..7516e4199b3c 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -156,19 +156,6 @@ struct compat_shmid64_ds { (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) #endif -static inline void __user *arch_compat_alloc_user_space(long len) -{ - compat_uptr_t sp = task_pt_regs(current)->sp; - - /* - * -128 for the x32 ABI redzone. For IA32, it is not strictly - * necessary, but not harmful. - */ - sp -= 128; - - return (void __user *)round_down(sp - len, 16); -} - static inline bool in_x32_syscall(void) { #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index e7265a552f4f..45697e04d771 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -58,13 +58,6 @@ raw_copy_to_user(void __user *dst, const void *src, unsigned long size) return copy_user_generic((__force void *)dst, src, size); } -static __always_inline __must_check -unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size) -{ - return copy_user_generic((__force void *)dst, - (__force void *)src, size); -} - extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); diff --git a/include/linux/compat.h b/include/linux/compat.h index 2d42cebd1fb8..1c758b0e0359 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -511,8 +511,6 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request, struct epoll_event; /* fortunately, this one is fixed-layout */ -extern void __user *compat_alloc_user_space(unsigned long len); - int compat_restore_altstack(const compat_stack_t __user *uss); int __compat_save_altstack(compat_stack_t __user *, unsigned long); #define unsafe_compat_save_altstack(uss, sp, label) do { \ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index c05e903cef02..ac0394087f7d 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -200,16 +200,6 @@ copy_to_user(void __user *to, const void *from, unsigned long n) n = _copy_to_user(to, from, n); return n; } -#ifdef CONFIG_COMPAT -static __always_inline unsigned long __must_check -copy_in_user(void __user *to, const void __user *from, unsigned long n) -{ - might_fault(); - if (access_ok(to, n) && access_ok(from, n)) - n = raw_copy_in_user(to, from, n); - return n; -} -#endif #ifndef copy_mc_to_kernel /* diff --git a/kernel/compat.c b/kernel/compat.c index 05adfd6fa8bf..55551989d9da 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -269,24 +269,3 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat) return 0; } EXPORT_SYMBOL_GPL(get_compat_sigset); - -/* - * Allocate user-space memory for the duration of a single system call, - * in order to marshall parameters inside a compat thunk. - */ -void __user *compat_alloc_user_space(unsigned long len) -{ - void __user *ptr; - - /* If len would occupy more than half of the entire compat space... */ - if (unlikely(len > (((compat_uptr_t)~0) >> 1))) - return NULL; - - ptr = arch_compat_alloc_user_space(len); - - if (unlikely(!access_ok(ptr, len))) - return NULL; - - return ptr; -} -EXPORT_SYMBOL_GPL(compat_alloc_user_space); -- cgit v1.2.3 From b83a908498d68fafca931e1276e145b339cac5fb Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Mon, 2 Aug 2021 13:23:20 -0700 Subject: compiler_attributes.h: move __compiletime_{error|warning} Clang 14 will add support for __attribute__((__error__(""))) and __attribute__((__warning__(""))). To make use of these in __compiletime_error and __compiletime_warning (as used by BUILD_BUG and friends) for newer clang and detect/fallback for older versions of clang, move these to compiler_attributes.h and guard them with __has_attribute preprocessor guards. Link: https://reviews.llvm.org/D106030 Link: https://bugs.llvm.org/show_bug.cgi?id=16428 Link: https://github.com/ClangBuiltLinux/linux/issues/1173 Signed-off-by: Nick Desaulniers Reviewed-by: Nathan Chancellor Reviewed-by: Kees Cook [Reworded, landed in Clang 14] Signed-off-by: Miguel Ojeda --- include/linux/compiler-gcc.h | 3 --- include/linux/compiler_attributes.h | 24 ++++++++++++++++++++++++ include/linux/compiler_types.h | 6 ------ 3 files changed, 24 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 5d97ef738a57..61c1479688db 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -43,9 +43,6 @@ #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) -#define __compiletime_warning(message) __attribute__((__warning__(message))) -#define __compiletime_error(message) __attribute__((__error__(message))) - #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) #define __latent_entropy __attribute__((latent_entropy)) #endif diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 7b1fa5c30169..f4df9e5a8c76 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -30,6 +30,7 @@ # define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) # define __GCC4_has_attribute___copy__ 0 # define __GCC4_has_attribute___designated_init__ 0 +# define __GCC4_has_attribute___error__ 1 # define __GCC4_has_attribute___externally_visible__ 1 # define __GCC4_has_attribute___no_caller_saved_registers__ 0 # define __GCC4_has_attribute___noclone__ 1 @@ -38,6 +39,7 @@ # define __GCC4_has_attribute___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9) # define __GCC4_has_attribute___no_sanitize_coverage__ 0 # define __GCC4_has_attribute___fallthrough__ 0 +# define __GCC4_has_attribute___warning__ 1 #endif /* @@ -137,6 +139,17 @@ # define __designated_init #endif +/* + * Optional: only supported since clang >= 14.0 + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-error-function-attribute + */ +#if __has_attribute(__error__) +# define __compiletime_error(msg) __attribute__((__error__(msg))) +#else +# define __compiletime_error(msg) +#endif + /* * Optional: not supported by clang * @@ -286,6 +299,17 @@ */ #define __must_check __attribute__((__warn_unused_result__)) +/* + * Optional: only supported since clang >= 14.0 + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-warning-function-attribute + */ +#if __has_attribute(__warning__) +# define __compiletime_warning(msg) __attribute__((__warning__(msg))) +#else +# define __compiletime_warning(msg) +#endif + /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index d29bda7f6ebd..8246d0caffa6 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -294,12 +294,6 @@ struct ftrace_likely_data { #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 #endif -#ifndef __compiletime_warning -# define __compiletime_warning(message) -#endif -#ifndef __compiletime_error -# define __compiletime_error(message) -#endif #ifdef __OPTIMIZE__ # define __compiletime_assert(condition, msg, prefix, suffix) \ -- cgit v1.2.3 From 13db8c50477d83ad3e3b9b0ae247e5cd833a7ae4 Mon Sep 17 00:00:00 2001 From: Liu Zixian Date: Wed, 8 Sep 2021 18:10:05 -0700 Subject: mm/hugetlb: initialize hugetlb_usage in mm_init After fork, the child process will get incorrect (2x) hugetlb_usage. If a process uses 5 2MB hugetlb pages in an anonymous mapping, HugetlbPages: 10240 kB and then forks, the child will show, HugetlbPages: 20480 kB The reason for double the amount is because hugetlb_usage will be copied from the parent and then increased when we copy page tables from parent to child. Child will have 2x actual usage. Fix this by adding hugetlb_count_init in mm_init. Link: https://lkml.kernel.org/r/20210826071742.877-1-liuzixian4@huawei.com Fixes: 5d317b2b6536 ("mm: hugetlb: proc: add HugetlbPages field to /proc/PID/status") Signed-off-by: Liu Zixian Reviewed-by: Naoya Horiguchi Reviewed-by: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 9 +++++++++ kernel/fork.c | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index f7ca1a3870ea..1faebe1cd0ed 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -858,6 +858,11 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); +static inline void hugetlb_count_init(struct mm_struct *mm) +{ + atomic_long_set(&mm->hugetlb_usage, 0); +} + static inline void hugetlb_count_add(long l, struct mm_struct *mm) { atomic_long_add(l, &mm->hugetlb_usage); @@ -1042,6 +1047,10 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, return &mm->page_table_lock; } +static inline void hugetlb_count_init(struct mm_struct *mm) +{ +} + static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) { } diff --git a/kernel/fork.c b/kernel/fork.c index ff5be23800af..38681ad44c76 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1063,6 +1063,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); + hugetlb_count_init(mm); if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; -- cgit v1.2.3 From 10994316089c9682f2fbe0be0b1e82bcaf5f4e8c Mon Sep 17 00:00:00 2001 From: Liam Howlett Date: Wed, 8 Sep 2021 18:10:14 -0700 Subject: mmap_lock: change trace and locking order Print to the trace log before releasing the lock to avoid racing with other trace log printers of the same lock type. Link: https://lkml.kernel.org/r/20210903022041.1843024-1-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Suggested-by: Steven Rostedt (VMware) Reviewed-by: Matthew Wilcox (Oracle) Cc: Michel Lespinasse Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmap_lock.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 0540f0156f58..b179f1e3541a 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -101,14 +101,14 @@ static inline bool mmap_write_trylock(struct mm_struct *mm) static inline void mmap_write_unlock(struct mm_struct *mm) { - up_write(&mm->mmap_lock); __mmap_lock_trace_released(mm, true); + up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { - downgrade_write(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, false, true); + downgrade_write(&mm->mmap_lock); } static inline void mmap_read_lock(struct mm_struct *mm) @@ -140,8 +140,8 @@ static inline bool mmap_read_trylock(struct mm_struct *mm) static inline void mmap_read_unlock(struct mm_struct *mm) { - up_read(&mm->mmap_lock); __mmap_lock_trace_released(mm, false); + up_read(&mm->mmap_lock); } static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) @@ -155,8 +155,8 @@ static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { - up_read_non_owner(&mm->mmap_lock); __mmap_lock_trace_released(mm, false); + up_read_non_owner(&mm->mmap_lock); } static inline void mmap_assert_locked(struct mm_struct *mm) -- cgit v1.2.3 From 5dfe50b05588010f347cb2f436434bf22b7a84ed Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 9 Sep 2021 22:36:38 +0900 Subject: bootconfig: Rename xbc_node_find_child() to xbc_node_find_subkey() Rename xbc_node_find_child() to xbc_node_find_subkey() for clarifying that function returns a key node (no value node). Since there are xbc_node_for_each_child() (loop on all child nodes) and xbc_node_for_each_subkey() (loop on only subkey nodes), this name distinction is necessary to avoid confusing users. Link: https://lkml.kernel.org/r/163119459826.161018.11200274779483115300.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 4 ++-- kernel/trace/trace_boot.c | 24 ++++++++++++------------ lib/bootconfig.c | 8 ++++---- 3 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index abe089c27529..537e1b991f11 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -110,7 +110,7 @@ static inline __init bool xbc_node_is_leaf(struct xbc_node *node) } /* Tree-based key-value access APIs */ -struct xbc_node * __init xbc_node_find_child(struct xbc_node *parent, +struct xbc_node * __init xbc_node_find_subkey(struct xbc_node *parent, const char *key); const char * __init xbc_node_find_value(struct xbc_node *parent, @@ -148,7 +148,7 @@ xbc_find_value(const char *key, struct xbc_node **vnode) */ static inline struct xbc_node * __init xbc_find_node(const char *key) { - return xbc_node_find_child(NULL, key); + return xbc_node_find_subkey(NULL, key); } /** diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index db6ee372dc6d..8d252f63cd78 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -262,9 +262,9 @@ trace_boot_hist_add_one_handler(struct xbc_node *hnode, char **bufp, append_printf(bufp, end, ":%s(%s)", handler, p); /* Compose 'action' parameter */ - knode = xbc_node_find_child(hnode, "trace"); + knode = xbc_node_find_subkey(hnode, "trace"); if (!knode) - knode = xbc_node_find_child(hnode, "save"); + knode = xbc_node_find_subkey(hnode, "save"); if (knode) { anode = xbc_node_get_child(knode); @@ -283,7 +283,7 @@ trace_boot_hist_add_one_handler(struct xbc_node *hnode, char **bufp, sep = ','; } append_printf(bufp, end, ")"); - } else if (xbc_node_find_child(hnode, "snapshot")) { + } else if (xbc_node_find_subkey(hnode, "snapshot")) { append_printf(bufp, end, ".snapshot()"); } else { pr_err("hist.%s requires an action.\n", @@ -314,7 +314,7 @@ trace_boot_hist_add_handlers(struct xbc_node *hnode, char **bufp, break; } - if (xbc_node_find_child(hnode, param)) + if (xbc_node_find_subkey(hnode, param)) ret = trace_boot_hist_add_one_handler(hnode, bufp, end, handler, param); return ret; @@ -374,7 +374,7 @@ trace_boot_compose_hist_cmd(struct xbc_node *hnode, char *buf, size_t size) if (p) append_printf(&buf, end, ":name=%s", p); - node = xbc_node_find_child(hnode, "var"); + node = xbc_node_find_subkey(hnode, "var"); if (node) { xbc_node_for_each_key_value(node, knode, p) { /* Expression must not include spaces. */ @@ -393,13 +393,13 @@ trace_boot_compose_hist_cmd(struct xbc_node *hnode, char *buf, size_t size) append_printf(&buf, end, ":clear"); /* Histogram handler and actions */ - node = xbc_node_find_child(hnode, "onmax"); + node = xbc_node_find_subkey(hnode, "onmax"); if (node && trace_boot_hist_add_handlers(node, &buf, end, "var") < 0) return -EINVAL; - node = xbc_node_find_child(hnode, "onchange"); + node = xbc_node_find_subkey(hnode, "onchange"); if (node && trace_boot_hist_add_handlers(node, &buf, end, "var") < 0) return -EINVAL; - node = xbc_node_find_child(hnode, "onmatch"); + node = xbc_node_find_subkey(hnode, "onmatch"); if (node && trace_boot_hist_add_handlers(node, &buf, end, "event") < 0) return -EINVAL; @@ -436,7 +436,7 @@ trace_boot_init_histograms(struct trace_event_file *file, } } - if (xbc_node_find_child(hnode, "keys")) { + if (xbc_node_find_subkey(hnode, "keys")) { if (trace_boot_compose_hist_cmd(hnode, buf, size) == 0) { tmp = kstrdup(buf, GFP_KERNEL); if (trigger_process_regex(file, buf) < 0) @@ -495,7 +495,7 @@ trace_boot_init_one_event(struct trace_array *tr, struct xbc_node *gnode, else if (trigger_process_regex(file, buf) < 0) pr_err("Failed to apply an action: %s\n", p); } - anode = xbc_node_find_child(enode, "hist"); + anode = xbc_node_find_subkey(enode, "hist"); if (anode) trace_boot_init_histograms(file, anode, buf, ARRAY_SIZE(buf)); } else if (xbc_node_find_value(enode, "actions", NULL)) @@ -517,7 +517,7 @@ trace_boot_init_events(struct trace_array *tr, struct xbc_node *node) bool enable, enable_all = false; const char *data; - node = xbc_node_find_child(node, "event"); + node = xbc_node_find_subkey(node, "event"); if (!node) return; /* per-event key starts with "event.GROUP.EVENT" */ @@ -620,7 +620,7 @@ trace_boot_init_instances(struct xbc_node *node) struct trace_array *tr; const char *p; - node = xbc_node_find_child(node, "instance"); + node = xbc_node_find_subkey(node, "instance"); if (!node) return; diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 927017431fb6..f8419cff1147 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -142,16 +142,16 @@ xbc_node_match_prefix(struct xbc_node *node, const char **prefix) } /** - * xbc_node_find_child() - Find a child node which matches given key + * xbc_node_find_subkey() - Find a subkey node which matches given key * @parent: An XBC node. * @key: A key string. * - * Search a node under @parent which matches @key. The @key can contain + * Search a key node under @parent which matches @key. The @key can contain * several words jointed with '.'. If @parent is NULL, this searches the * node from whole tree. Return NULL if no node is matched. */ struct xbc_node * __init -xbc_node_find_child(struct xbc_node *parent, const char *key) +xbc_node_find_subkey(struct xbc_node *parent, const char *key) { struct xbc_node *node; @@ -191,7 +191,7 @@ const char * __init xbc_node_find_value(struct xbc_node *parent, const char *key, struct xbc_node **vnode) { - struct xbc_node *node = xbc_node_find_child(parent, key); + struct xbc_node *node = xbc_node_find_subkey(parent, key); if (!node || !xbc_node_is_key(node)) return NULL; -- cgit v1.2.3 From 8c854303ce0e38e5bbedd725ff39da7e235865d8 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 3 Aug 2021 16:16:21 +0200 Subject: cpu/hotplug: Remove deprecated CPU-hotplug functions. No users in tree use the deprecated CPU-hotplug functions anymore. Remove them. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210803141621.780504-39-bigeasy@linutronix.de --- include/linux/cpu.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 94a578a96202..9cf51e41e697 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -143,12 +143,6 @@ static inline int remove_cpu(unsigned int cpu) { return -EPERM; } static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { } #endif /* !CONFIG_HOTPLUG_CPU */ -/* Wrappers which go away once all code is converted */ -static inline void cpu_hotplug_begin(void) { cpus_write_lock(); } -static inline void cpu_hotplug_done(void) { cpus_write_unlock(); } -static inline void get_online_cpus(void) { cpus_read_lock(); } -static inline void put_online_cpus(void) { cpus_read_unlock(); } - #ifdef CONFIG_PM_SLEEP_SMP extern int freeze_secondary_cpus(int primary); extern void thaw_secondary_cpus(void); -- cgit v1.2.3 From c9871c800f65fffed40f3df3e1eb38984f95cfcf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 9 Sep 2021 14:34:59 +0200 Subject: Documentation: core-api/cpuhotplug: Rewrite the API section Dave stumbled over the incomplete and confusing documentation of the CPU hotplug API. Rewrite it, add the missing function documentations and correct the existing ones. Reported-by: Dave Chinner Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210909123212.489059409@linutronix.de --- Documentation/core-api/cpu_hotplug.rst | 579 +++++++++++++++++++++++++++------ include/linux/cpuhotplug.h | 132 ++++++-- 2 files changed, 590 insertions(+), 121 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/cpu_hotplug.rst b/Documentation/core-api/cpu_hotplug.rst index b66e3cae1472..c6f4ba2fb32d 100644 --- a/Documentation/core-api/cpu_hotplug.rst +++ b/Documentation/core-api/cpu_hotplug.rst @@ -2,12 +2,13 @@ CPU hotplug in the Kernel ========================= -:Date: December, 2016 +:Date: September, 2021 :Author: Sebastian Andrzej Siewior , - Rusty Russell , - Srivatsa Vaddagiri , - Ashok Raj , - Joel Schopp + Rusty Russell , + Srivatsa Vaddagiri , + Ashok Raj , + Joel Schopp , + Thomas Gleixner Introduction ============ @@ -158,100 +159,480 @@ at state ``CPUHP_OFFLINE``. This includes: * Once all services are migrated, kernel calls an arch specific routine ``__cpu_disable()`` to perform arch specific cleanup. -Using the hotplug API ---------------------- - -It is possible to receive notifications once a CPU is offline or onlined. This -might be important to certain drivers which need to perform some kind of setup -or clean up functions based on the number of available CPUs:: - - #include - - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "X/Y:online", - Y_online, Y_prepare_down); - -*X* is the subsystem and *Y* the particular driver. The *Y_online* callback -will be invoked during registration on all online CPUs. If an error -occurs during the online callback the *Y_prepare_down* callback will be -invoked on all CPUs on which the online callback was previously invoked. -After registration completed, the *Y_online* callback will be invoked -once a CPU is brought online and *Y_prepare_down* will be invoked when a -CPU is shutdown. All resources which were previously allocated in -*Y_online* should be released in *Y_prepare_down*. -The return value *ret* is negative if an error occurred during the -registration process. Otherwise a positive value is returned which -contains the allocated hotplug for dynamically allocated states -(*CPUHP_AP_ONLINE_DYN*). It will return zero for predefined states. - -The callback can be remove by invoking ``cpuhp_remove_state()``. In case of a -dynamically allocated state (*CPUHP_AP_ONLINE_DYN*) use the returned state. -During the removal of a hotplug state the teardown callback will be invoked. - -Multiple instances -~~~~~~~~~~~~~~~~~~ - -If a driver has multiple instances and each instance needs to perform the -callback independently then it is likely that a ''multi-state'' should be used. -First a multi-state state needs to be registered:: - - ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "X/Y:online, - Y_online, Y_prepare_down); - Y_hp_online = ret; - -The ``cpuhp_setup_state_multi()`` behaves similar to ``cpuhp_setup_state()`` -except it prepares the callbacks for a multi state and does not invoke -the callbacks. This is a one time setup. -Once a new instance is allocated, you need to register this new instance:: - - ret = cpuhp_state_add_instance(Y_hp_online, &d->node); - -This function will add this instance to your previously allocated -*Y_hp_online* state and invoke the previously registered callback -(*Y_online*) on all online CPUs. The *node* element is a ``struct -hlist_node`` member of your per-instance data structure. - -On removal of the instance:: - - cpuhp_state_remove_instance(Y_hp_online, &d->node) - -should be invoked which will invoke the teardown callback on all online -CPUs. - -Manual setup -~~~~~~~~~~~~ - -Usually it is handy to invoke setup and teardown callbacks on registration or -removal of a state because usually the operation needs to performed once a CPU -goes online (offline) and during initial setup (shutdown) of the driver. However -each registration and removal function is also available with a ``_nocalls`` -suffix which does not invoke the provided callbacks if the invocation of the -callbacks is not desired. During the manual setup (or teardown) the functions -``cpus_read_lock()`` and ``cpus_read_unlock()`` should be used to inhibit CPU -hotplug operations. - - -The ordering of the events --------------------------- - -The hotplug states are defined in ``include/linux/cpuhotplug.h``: - -* The states *CPUHP_OFFLINE* … *CPUHP_AP_OFFLINE* are invoked before the - CPU is up. -* The states *CPUHP_AP_OFFLINE* … *CPUHP_AP_ONLINE* are invoked - just the after the CPU has been brought up. The interrupts are off and - the scheduler is not yet active on this CPU. Starting with *CPUHP_AP_OFFLINE* - the callbacks are invoked on the target CPU. -* The states between *CPUHP_AP_ONLINE_DYN* and *CPUHP_AP_ONLINE_DYN_END* are - reserved for the dynamic allocation. -* The states are invoked in the reverse order on CPU shutdown starting with - *CPUHP_ONLINE* and stopping at *CPUHP_OFFLINE*. Here the callbacks are - invoked on the CPU that will be shutdown until *CPUHP_AP_OFFLINE*. - -A dynamically allocated state via *CPUHP_AP_ONLINE_DYN* is often enough. -However if an earlier invocation during the bring up or shutdown is required -then an explicit state should be acquired. An explicit state might also be -required if the hotplug event requires specific ordering in respect to -another hotplug event. + +The CPU hotplug API +=================== + +CPU hotplug state machine +------------------------- + +CPU hotplug uses a trivial state machine with a linear state space from +CPUHP_OFFLINE to CPUHP_ONLINE. Each state has a startup and a teardown +callback. + +When a CPU is onlined, the startup callbacks are invoked sequentially until +the state CPUHP_ONLINE is reached. They can also be invoked when the +callbacks of a state are set up or an instance is added to a multi-instance +state. + +When a CPU is offlined the teardown callbacks are invoked in the reverse +order sequentially until the state CPUHP_OFFLINE is reached. They can also +be invoked when the callbacks of a state are removed or an instance is +removed from a multi-instance state. + +If a usage site requires only a callback in one direction of the hotplug +operations (CPU online or CPU offline) then the other not-required callback +can be set to NULL when the state is set up. + +The state space is divided into three sections: + +* The PREPARE section + + The PREPARE section covers the state space from CPUHP_OFFLINE to + CPUHP_BRINGUP_CPU. + + The startup callbacks in this section are invoked before the CPU is + started during a CPU online operation. The teardown callbacks are invoked + after the CPU has become dysfunctional during a CPU offline operation. + + The callbacks are invoked on a control CPU as they can't obviously run on + the hotplugged CPU which is either not yet started or has become + dysfunctional already. + + The startup callbacks are used to setup resources which are required to + bring a CPU successfully online. The teardown callbacks are used to free + resources or to move pending work to an online CPU after the hotplugged + CPU became dysfunctional. + + The startup callbacks are allowed to fail. If a callback fails, the CPU + online operation is aborted and the CPU is brought down to the previous + state (usually CPUHP_OFFLINE) again. + + The teardown callbacks in this section are not allowed to fail. + +* The STARTING section + + The STARTING section covers the state space between CPUHP_BRINGUP_CPU + 1 + and CPUHP_AP_ONLINE. + + The startup callbacks in this section are invoked on the hotplugged CPU + with interrupts disabled during a CPU online operation in the early CPU + setup code. The teardown callbacks are invoked with interrupts disabled + on the hotplugged CPU during a CPU offline operation shortly before the + CPU is completely shut down. + + The callbacks in this section are not allowed to fail. + + The callbacks are used for low level hardware initialization/shutdown and + for core subsystems. + +* The ONLINE section + + The ONLINE section covers the state space between CPUHP_AP_ONLINE + 1 and + CPUHP_ONLINE. + + The startup callbacks in this section are invoked on the hotplugged CPU + during a CPU online operation. The teardown callbacks are invoked on the + hotplugged CPU during a CPU offline operation. + + The callbacks are invoked in the context of the per CPU hotplug thread, + which is pinned on the hotplugged CPU. The callbacks are invoked with + interrupts and preemption enabled. + + The callbacks are allowed to fail. When a callback fails the hotplug + operation is aborted and the CPU is brought back to the previous state. + +CPU online/offline operations +----------------------------- + +A successful online operation looks like this:: + + [CPUHP_OFFLINE] + [CPUHP_OFFLINE + 1]->startup() -> success + [CPUHP_OFFLINE + 2]->startup() -> success + [CPUHP_OFFLINE + 3] -> skipped because startup == NULL + ... + [CPUHP_BRINGUP_CPU]->startup() -> success + === End of PREPARE section + [CPUHP_BRINGUP_CPU + 1]->startup() -> success + ... + [CPUHP_AP_ONLINE]->startup() -> success + === End of STARTUP section + [CPUHP_AP_ONLINE + 1]->startup() -> success + ... + [CPUHP_ONLINE - 1]->startup() -> success + [CPUHP_ONLINE] + +A successful offline operation looks like this:: + + [CPUHP_ONLINE] + [CPUHP_ONLINE - 1]->teardown() -> success + ... + [CPUHP_AP_ONLINE + 1]->teardown() -> success + === Start of STARTUP section + [CPUHP_AP_ONLINE]->teardown() -> success + ... + [CPUHP_BRINGUP_ONLINE - 1]->teardown() + ... + === Start of PREPARE section + [CPUHP_BRINGUP_CPU]->teardown() + [CPUHP_OFFLINE + 3]->teardown() + [CPUHP_OFFLINE + 2] -> skipped because teardown == NULL + [CPUHP_OFFLINE + 1]->teardown() + [CPUHP_OFFLINE] + +A failed online operation looks like this:: + + [CPUHP_OFFLINE] + [CPUHP_OFFLINE + 1]->startup() -> success + [CPUHP_OFFLINE + 2]->startup() -> success + [CPUHP_OFFLINE + 3] -> skipped because startup == NULL + ... + [CPUHP_BRINGUP_CPU]->startup() -> success + === End of PREPARE section + [CPUHP_BRINGUP_CPU + 1]->startup() -> success + ... + [CPUHP_AP_ONLINE]->startup() -> success + === End of STARTUP section + [CPUHP_AP_ONLINE + 1]->startup() -> success + --- + [CPUHP_AP_ONLINE + N]->startup() -> fail + [CPUHP_AP_ONLINE + (N - 1)]->teardown() + ... + [CPUHP_AP_ONLINE + 1]->teardown() + === Start of STARTUP section + [CPUHP_AP_ONLINE]->teardown() + ... + [CPUHP_BRINGUP_ONLINE - 1]->teardown() + ... + === Start of PREPARE section + [CPUHP_BRINGUP_CPU]->teardown() + [CPUHP_OFFLINE + 3]->teardown() + [CPUHP_OFFLINE + 2] -> skipped because teardown == NULL + [CPUHP_OFFLINE + 1]->teardown() + [CPUHP_OFFLINE] + +A failed offline operation looks like this:: + + [CPUHP_ONLINE] + [CPUHP_ONLINE - 1]->teardown() -> success + ... + [CPUHP_ONLINE - N]->teardown() -> fail + [CPUHP_ONLINE - (N - 1)]->startup() + ... + [CPUHP_ONLINE - 1]->startup() + [CPUHP_ONLINE] + +Recursive failures cannot be handled sensibly. Look at the following +example of a recursive fail due to a failed offline operation: :: + + [CPUHP_ONLINE] + [CPUHP_ONLINE - 1]->teardown() -> success + ... + [CPUHP_ONLINE - N]->teardown() -> fail + [CPUHP_ONLINE - (N - 1)]->startup() -> success + [CPUHP_ONLINE - (N - 2)]->startup() -> fail + +The CPU hotplug state machine stops right here and does not try to go back +down again because that would likely result in an endless loop:: + + [CPUHP_ONLINE - (N - 1)]->teardown() -> success + [CPUHP_ONLINE - N]->teardown() -> fail + [CPUHP_ONLINE - (N - 1)]->startup() -> success + [CPUHP_ONLINE - (N - 2)]->startup() -> fail + [CPUHP_ONLINE - (N - 1)]->teardown() -> success + [CPUHP_ONLINE - N]->teardown() -> fail + +Lather, rinse and repeat. In this case the CPU left in state:: + + [CPUHP_ONLINE - (N - 1)] + +which at least lets the system make progress and gives the user a chance to +debug or even resolve the situation. + +Allocating a state +------------------ + +There are two ways to allocate a CPU hotplug state: + +* Static allocation + + Static allocation has to be used when the subsystem or driver has + ordering requirements versus other CPU hotplug states. E.g. the PERF core + startup callback has to be invoked before the PERF driver startup + callbacks during a CPU online operation. During a CPU offline operation + the driver teardown callbacks have to be invoked before the core teardown + callback. The statically allocated states are described by constants in + the cpuhp_state enum which can be found in include/linux/cpuhotplug.h. + + Insert the state into the enum at the proper place so the ordering + requirements are fulfilled. The state constant has to be used for state + setup and removal. + + Static allocation is also required when the state callbacks are not set + up at runtime and are part of the initializer of the CPU hotplug state + array in kernel/cpu.c. + +* Dynamic allocation + + When there are no ordering requirements for the state callbacks then + dynamic allocation is the preferred method. The state number is allocated + by the setup function and returned to the caller on success. + + Only the PREPARE and ONLINE sections provide a dynamic allocation + range. The STARTING section does not as most of the callbacks in that + section have explicit ordering requirements. + +Setup of a CPU hotplug state +---------------------------- + +The core code provides the following functions to setup a state: + +* cpuhp_setup_state(state, name, startup, teardown) +* cpuhp_setup_state_nocalls(state, name, startup, teardown) +* cpuhp_setup_state_cpuslocked(state, name, startup, teardown) +* cpuhp_setup_state_nocalls_cpuslocked(state, name, startup, teardown) + +For cases where a driver or a subsystem has multiple instances and the same +CPU hotplug state callbacks need to be invoked for each instance, the CPU +hotplug core provides multi-instance support. The advantage over driver +specific instance lists is that the instance related functions are fully +serialized against CPU hotplug operations and provide the automatic +invocations of the state callbacks on add and removal. To set up such a +multi-instance state the following function is available: + +* cpuhp_setup_state_multi(state, name, startup, teardown) + +The @state argument is either a statically allocated state or one of the +constants for dynamically allocated states - CPUHP_PREPARE_DYN, +CPUHP_ONLINE_DYN - depending on the state section (PREPARE, ONLINE) for +which a dynamic state should be allocated. + +The @name argument is used for sysfs output and for instrumentation. The +naming convention is "subsys:mode" or "subsys/driver:mode", +e.g. "perf:mode" or "perf/x86:mode". The common mode names are: + +======== ======================================================= +prepare For states in the PREPARE section + +dead For states in the PREPARE section which do not provide + a startup callback + +starting For states in the STARTING section + +dying For states in the STARTING section which do not provide + a startup callback + +online For states in the ONLINE section + +offline For states in the ONLINE section which do not provide + a startup callback +======== ======================================================= + +As the @name argument is only used for sysfs and instrumentation other mode +descriptors can be used as well if they describe the nature of the state +better than the common ones. + +Examples for @name arguments: "perf/online", "perf/x86:prepare", +"RCU/tree:dying", "sched/waitempty" + +The @startup argument is a function pointer to the callback which should be +invoked during a CPU online operation. If the usage site does not require a +startup callback set the pointer to NULL. + +The @teardown argument is a function pointer to the callback which should +be invoked during a CPU offline operation. If the usage site does not +require a teardown callback set the pointer to NULL. + +The functions differ in the way how the installed callbacks are treated: + + * cpuhp_setup_state_nocalls(), cpuhp_setup_state_nocalls_cpuslocked() + and cpuhp_setup_state_multi() only install the callbacks + + * cpuhp_setup_state() and cpuhp_setup_state_cpuslocked() install the + callbacks and invoke the @startup callback (if not NULL) for all online + CPUs which have currently a state greater than the newly installed + state. Depending on the state section the callback is either invoked on + the current CPU (PREPARE section) or on each online CPU (ONLINE + section) in the context of the CPU's hotplug thread. + + If a callback fails for CPU N then the teardown callback for CPU + 0 .. N-1 is invoked to rollback the operation. The state setup fails, + the callbacks for the state are not installed and in case of dynamic + allocation the allocated state is freed. + +The state setup and the callback invocations are serialized against CPU +hotplug operations. If the setup function has to be called from a CPU +hotplug read locked region, then the _cpuslocked() variants have to be +used. These functions cannot be used from within CPU hotplug callbacks. + +The function return values: + ======== =================================================================== + 0 Statically allocated state was successfully set up + + >0 Dynamically allocated state was successfully set up. + + The returned number is the state number which was allocated. If + the state callbacks have to be removed later, e.g. module + removal, then this number has to be saved by the caller and used + as @state argument for the state remove function. For + multi-instance states the dynamically allocated state number is + also required as @state argument for the instance add/remove + operations. + + <0 Operation failed + ======== =================================================================== + +Removal of a CPU hotplug state +------------------------------ + +To remove a previously set up state, the following functions are provided: + +* cpuhp_remove_state(state) +* cpuhp_remove_state_nocalls(state) +* cpuhp_remove_state_nocalls_cpuslocked(state) +* cpuhp_remove_multi_state(state) + +The @state argument is either a statically allocated state or the state +number which was allocated in the dynamic range by cpuhp_setup_state*(). If +the state is in the dynamic range, then the state number is freed and +available for dynamic allocation again. + +The functions differ in the way how the installed callbacks are treated: + + * cpuhp_remove_state_nocalls(), cpuhp_remove_state_nocalls_cpuslocked() + and cpuhp_remove_multi_state() only remove the callbacks. + + * cpuhp_remove_state() removes the callbacks and invokes the teardown + callback (if not NULL) for all online CPUs which have currently a state + greater than the removed state. Depending on the state section the + callback is either invoked on the current CPU (PREPARE section) or on + each online CPU (ONLINE section) in the context of the CPU's hotplug + thread. + + In order to complete the removal, the teardown callback should not fail. + +The state removal and the callback invocations are serialized against CPU +hotplug operations. If the remove function has to be called from a CPU +hotplug read locked region, then the _cpuslocked() variants have to be +used. These functions cannot be used from within CPU hotplug callbacks. + +If a multi-instance state is removed then the caller has to remove all +instances first. + +Multi-Instance state instance management +---------------------------------------- + +Once the multi-instance state is set up, instances can be added to the +state: + + * cpuhp_state_add_instance(state, node) + * cpuhp_state_add_instance_nocalls(state, node) + +The @state argument is either a statically allocated state or the state +number which was allocated in the dynamic range by cpuhp_setup_state_multi(). + +The @node argument is a pointer to an hlist_node which is embedded in the +instance's data structure. The pointer is handed to the multi-instance +state callbacks and can be used by the callback to retrieve the instance +via container_of(). + +The functions differ in the way how the installed callbacks are treated: + + * cpuhp_state_add_instance_nocalls() and only adds the instance to the + multi-instance state's node list. + + * cpuhp_state_add_instance() adds the instance and invokes the startup + callback (if not NULL) associated with @state for all online CPUs which + have currently a state greater than @state. The callback is only + invoked for the to be added instance. Depending on the state section + the callback is either invoked on the current CPU (PREPARE section) or + on each online CPU (ONLINE section) in the context of the CPU's hotplug + thread. + + If a callback fails for CPU N then the teardown callback for CPU + 0 .. N-1 is invoked to rollback the operation, the function fails and + the instance is not added to the node list of the multi-instance state. + +To remove an instance from the state's node list these functions are +available: + + * cpuhp_state_remove_instance(state, node) + * cpuhp_state_remove_instance_nocalls(state, node) + +The arguments are the same as for the the cpuhp_state_add_instance*() +variants above. + +The functions differ in the way how the installed callbacks are treated: + + * cpuhp_state_remove_instance_nocalls() only removes the instance from the + state's node list. + + * cpuhp_state_remove_instance() removes the instance and invokes the + teardown callback (if not NULL) associated with @state for all online + CPUs which have currently a state greater than @state. The callback is + only invoked for the to be removed instance. Depending on the state + section the callback is either invoked on the current CPU (PREPARE + section) or on each online CPU (ONLINE section) in the context of the + CPU's hotplug thread. + + In order to complete the removal, the teardown callback should not fail. + +The node list add/remove operations and the callback invocations are +serialized against CPU hotplug operations. These functions cannot be used +from within CPU hotplug callbacks and CPU hotplug read locked regions. + +Examples +-------- + +Setup and teardown a statically allocated state in the STARTING section for +notifications on online and offline operations:: + + ret = cpuhp_setup_state(CPUHP_SUBSYS_STARTING, "subsys:starting", subsys_cpu_starting, subsys_cpu_dying); + if (ret < 0) + return ret; + .... + cpuhp_remove_state(CPUHP_SUBSYS_STARTING); + +Setup and teardown a dynamically allocated state in the ONLINE section +for notifications on offline operations:: + + state = cpuhp_setup_state(CPUHP_ONLINE_DYN, "subsys:offline", NULL, subsys_cpu_offline); + if (state < 0) + return state; + .... + cpuhp_remove_state(state); + +Setup and teardown a dynamically allocated state in the ONLINE section +for notifications on online operations without invoking the callbacks:: + + state = cpuhp_setup_state_nocalls(CPUHP_ONLINE_DYN, "subsys:online", subsys_cpu_online, NULL); + if (state < 0) + return state; + .... + cpuhp_remove_state_nocalls(state); + +Setup, use and teardown a dynamically allocated multi-instance state in the +ONLINE section for notifications on online and offline operation:: + + state = cpuhp_setup_state_multi(CPUHP_ONLINE_DYN, "subsys:online", subsys_cpu_online, subsys_cpu_offline); + if (state < 0) + return state; + .... + ret = cpuhp_state_add_instance(state, &inst1->node); + if (ret) + return ret; + .... + ret = cpuhp_state_add_instance(state, &inst2->node); + if (ret) + return ret; + .... + cpuhp_remove_instance(state, &inst1->node); + .... + cpuhp_remove_instance(state, &inst2->node); + .... + remove_multi_state(state); + Testing of hotplug states ========================= diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 39cf84a30b9f..832d8a74fa59 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -22,8 +22,42 @@ * AP_ACTIVE AP_ACTIVE */ +/* + * CPU hotplug states. The state machine invokes the installed state + * startup callbacks sequentially from CPUHP_OFFLINE + 1 to CPUHP_ONLINE + * during a CPU online operation. During a CPU offline operation the + * installed teardown callbacks are invoked in the reverse order from + * CPU_ONLINE - 1 down to CPUHP_OFFLINE. + * + * The state space has three sections: PREPARE, STARTING and ONLINE. + * + * PREPARE: The callbacks are invoked on a control CPU before the + * hotplugged CPU is started up or after the hotplugged CPU has died. + * + * STARTING: The callbacks are invoked on the hotplugged CPU from the low level + * hotplug startup/teardown code with interrupts disabled. + * + * ONLINE: The callbacks are invoked on the hotplugged CPU from the per CPU + * hotplug thread with interrupts and preemption enabled. + * + * Adding explicit states to this enum is only necessary when: + * + * 1) The state is within the STARTING section + * + * 2) The state has ordering constraints vs. other states in the + * same section. + * + * If neither #1 nor #2 apply, please use the dynamic state space when + * setting up a state by using CPUHP_PREPARE_DYN or CPUHP_PREPARE_ONLINE + * for the @state argument of the setup function. + * + * See Documentation/core-api/cpu_hotplug.rst for further information and + * examples. + */ enum cpuhp_state { CPUHP_INVALID = -1, + + /* PREPARE section invoked on a control CPU */ CPUHP_OFFLINE = 0, CPUHP_CREATE_THREADS, CPUHP_PERF_PREPARE, @@ -95,6 +129,11 @@ enum cpuhp_state { CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, CPUHP_BRINGUP_CPU, + + /* + * STARTING section invoked on the hotplugged CPU in low level + * bringup and teardown code. + */ CPUHP_AP_IDLE_DEAD, CPUHP_AP_OFFLINE, CPUHP_AP_SCHED_STARTING, @@ -155,6 +194,8 @@ enum cpuhp_state { CPUHP_AP_ARM_CACHE_B15_RAC_DYING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, + + /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, @@ -216,14 +257,15 @@ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, int (*teardown)(unsigned int cpu), bool multi_instance); /** - * cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks + * cpuhp_setup_state - Setup hotplug state callbacks with calling the @startup + * callback * @state: The state for which the calls are installed * @name: Name of the callback (will be used in debug output) - * @startup: startup callback function - * @teardown: teardown callback function + * @startup: startup callback function or NULL if not required + * @teardown: teardown callback function or NULL if not required * - * Installs the callback functions and invokes the startup callback on - * the present cpus which have already reached the @state. + * Installs the callback functions and invokes the @startup callback on + * the online cpus which have already reached the @state. */ static inline int cpuhp_setup_state(enum cpuhp_state state, const char *name, @@ -233,6 +275,18 @@ static inline int cpuhp_setup_state(enum cpuhp_state state, return __cpuhp_setup_state(state, name, true, startup, teardown, false); } +/** + * cpuhp_setup_state_cpuslocked - Setup hotplug state callbacks with calling + * @startup callback from a cpus_read_lock() + * held region + * @state: The state for which the calls are installed + * @name: Name of the callback (will be used in debug output) + * @startup: startup callback function or NULL if not required + * @teardown: teardown callback function or NULL if not required + * + * Same as cpuhp_setup_state() except that it must be invoked from within a + * cpus_read_lock() held region. + */ static inline int cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, int (*startup)(unsigned int cpu), @@ -244,14 +298,14 @@ static inline int cpuhp_setup_state_cpuslocked(enum cpuhp_state state, /** * cpuhp_setup_state_nocalls - Setup hotplug state callbacks without calling the - * callbacks + * @startup callback * @state: The state for which the calls are installed * @name: Name of the callback. - * @startup: startup callback function - * @teardown: teardown callback function + * @startup: startup callback function or NULL if not required + * @teardown: teardown callback function or NULL if not required * - * Same as @cpuhp_setup_state except that no calls are executed are invoked - * during installation of this callback. NOP if SMP=n or HOTPLUG_CPU=n. + * Same as cpuhp_setup_state() except that the @startup callback is not + * invoked during installation. NOP if SMP=n or HOTPLUG_CPU=n. */ static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state, const char *name, @@ -262,6 +316,19 @@ static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state, false); } +/** + * cpuhp_setup_state_nocalls_cpuslocked - Setup hotplug state callbacks without + * invoking the @startup callback from + * a cpus_read_lock() held region + * callbacks + * @state: The state for which the calls are installed + * @name: Name of the callback. + * @startup: startup callback function or NULL if not required + * @teardown: teardown callback function or NULL if not required + * + * Same as cpuhp_setup_state_nocalls() except that it must be invoked from + * within a cpus_read_lock() held region. + */ static inline int cpuhp_setup_state_nocalls_cpuslocked(enum cpuhp_state state, const char *name, int (*startup)(unsigned int cpu), @@ -275,13 +342,13 @@ static inline int cpuhp_setup_state_nocalls_cpuslocked(enum cpuhp_state state, * cpuhp_setup_state_multi - Add callbacks for multi state * @state: The state for which the calls are installed * @name: Name of the callback. - * @startup: startup callback function - * @teardown: teardown callback function + * @startup: startup callback function or NULL if not required + * @teardown: teardown callback function or NULL if not required * * Sets the internal multi_instance flag and prepares a state to work as a multi * instance callback. No callbacks are invoked at this point. The callbacks are * invoked once an instance for this state are registered via - * @cpuhp_state_add_instance or @cpuhp_state_add_instance_nocalls. + * cpuhp_state_add_instance() or cpuhp_state_add_instance_nocalls() */ static inline int cpuhp_setup_state_multi(enum cpuhp_state state, const char *name, @@ -306,9 +373,10 @@ int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, * @state: The state for which the instance is installed * @node: The node for this individual state. * - * Installs the instance for the @state and invokes the startup callback on - * the present cpus which have already reached the @state. The @state must have - * been earlier marked as multi-instance by @cpuhp_setup_state_multi. + * Installs the instance for the @state and invokes the registered startup + * callback on the online cpus which have already reached the @state. The + * @state must have been earlier marked as multi-instance by + * cpuhp_setup_state_multi(). */ static inline int cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node) @@ -322,8 +390,9 @@ static inline int cpuhp_state_add_instance(enum cpuhp_state state, * @state: The state for which the instance is installed * @node: The node for this individual state. * - * Installs the instance for the @state The @state must have been earlier - * marked as multi-instance by @cpuhp_setup_state_multi. + * Installs the instance for the @state. The @state must have been earlier + * marked as multi-instance by cpuhp_setup_state_multi. NOP if SMP=n or + * HOTPLUG_CPU=n. */ static inline int cpuhp_state_add_instance_nocalls(enum cpuhp_state state, struct hlist_node *node) @@ -331,6 +400,17 @@ static inline int cpuhp_state_add_instance_nocalls(enum cpuhp_state state, return __cpuhp_state_add_instance(state, node, false); } +/** + * cpuhp_state_add_instance_nocalls_cpuslocked - Add an instance for a state + * without invoking the startup + * callback from a cpus_read_lock() + * held region. + * @state: The state for which the instance is installed + * @node: The node for this individual state. + * + * Same as cpuhp_state_add_instance_nocalls() except that it must be + * invoked from within a cpus_read_lock() held region. + */ static inline int cpuhp_state_add_instance_nocalls_cpuslocked(enum cpuhp_state state, struct hlist_node *node) @@ -346,7 +426,7 @@ void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke); * @state: The state for which the calls are removed * * Removes the callback functions and invokes the teardown callback on - * the present cpus which have already reached the @state. + * the online cpus which have already reached the @state. */ static inline void cpuhp_remove_state(enum cpuhp_state state) { @@ -355,7 +435,7 @@ static inline void cpuhp_remove_state(enum cpuhp_state state) /** * cpuhp_remove_state_nocalls - Remove hotplug state callbacks without invoking - * teardown + * the teardown callback * @state: The state for which the calls are removed */ static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state) @@ -363,6 +443,14 @@ static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state) __cpuhp_remove_state(state, false); } +/** + * cpuhp_remove_state_nocalls_cpuslocked - Remove hotplug state callbacks without invoking + * teardown from a cpus_read_lock() held region. + * @state: The state for which the calls are removed + * + * Same as cpuhp_remove_state nocalls() except that it must be invoked + * from within a cpus_read_lock() held region. + */ static inline void cpuhp_remove_state_nocalls_cpuslocked(enum cpuhp_state state) { __cpuhp_remove_state_cpuslocked(state, false); @@ -390,8 +478,8 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state, * @state: The state from which the instance is removed * @node: The node for this individual state. * - * Removes the instance and invokes the teardown callback on the present cpus - * which have already reached the @state. + * Removes the instance and invokes the teardown callback on the online cpus + * which have already reached @state. */ static inline int cpuhp_state_remove_instance(enum cpuhp_state state, struct hlist_node *node) -- cgit v1.2.3