From 223f5f79f2ce8facd9d77dd44e9f403343630bfc Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 23 Jun 2023 18:45:59 -0700 Subject: bpf, net: Check skb ownership against full socket. Check skb ownership of an skb against full sockets instead of request_sock. The filters were called only if an skb is owned by the sock that the skb is sent out through. In another words, skb->sk should point to the sock that it is sending through its egress. However, the filters would miss SYN/ACK skbs that they are owned by a request_sock but sent through the listener sock, that is the socket listening incoming connections. However, the listener socket is also the full socket of the request socket. We should use the full socket as the owner socket of an skb instead. What is the ownership check for? ================================ BPF_CGROUP_RUN_PROG_INET_EGRESS() checked sk == skb->sk to ensure the ownership of an skb. Alexei referred to a mailing list conversation [0] that took place a few years ago. In that conversation, Daniel Borkmann stated that: Wouldn't that mean however, when you go through stacked devices that you'd run the same eBPF cgroup program for skb->sk multiple times? According to what Daniel said, the ownership check mentioned earlier presumably prevents multiple calls of egress filters caused by an skb. A test that reproduce this scenario shows that the BPF cgroup egress programs can be called multiple times for one skb if this ownership check is not there. So, we can not just remove this check. Test Stacked Devices ==================== We use L2TP to build an environment of stacked devices. L2TP (Layer 2 Tunneling Protocol) is a tunneling protocol used to support virtual private networks (VPNs). It relays encapsulated packets; for example in UDP, to its peer by using a socket. Using L2TP, packets are first sent through the IP stack and should then arrive at an L2TP device. The device will expand its skb header to encapsulate the packet. The skb will be sent back to the IP stack using the socket that was made for the L2TP session. After that, the routing process will occur once more, but this time for a new destination. We changed tools/testing/selftests/net/l2tp.sh to set up a test environment using L2TP. The run_ping() function in l2tp.sh is where the main change occurred. run_ping() { local desc="$1" sleep 10 run_cmd host-1 ${ping6} -s 227 -c 4 -i 10 -I fc00:101::1 fc00:101::2 log_test $? 0 "IPv6 route through L2TP tunnel ${desc}" sleep 10 } The test will use L2TP devices to send PING messages. These messages will have a message size of 227 bytes as a special label to distinguish them. This is not an ideal solution, but works. During the execution of the test script, bpftrace was attached to ip6_finish_output() and l2tp_xmit_skb(): bpftrace -e ' kfunc:ip6_finish_output { time("%H:%M:%S: "); printf("ip6_finish_output skb=%p skb->len=%d cgroup=%p sk=%p skb->sk=%p\n", args->skb, args->skb->len, args->sk->sk_cgrp_data.cgroup, args->sk, args->skb->sk); } kfunc:l2tp_xmit_skb { time("%H:%M:%S: "); printf("l2tp_xmit_skb skb=%p sk=%p\n", args->skb, args->session->tunnel->sock); }' The following is part of the output messages printed by bpftrace: 16:35:20: ip6_finish_output skb=0xffff888103d8e600 skb->len=275 cgroup=0xffff88810741f800 sk=0xffff888105f3b900 skb->sk=0xffff888105f3b900 16:35:20: l2tp_xmit_skb skb=0xffff888103d8e600 sk=0xffff888103dd6300 16:35:20: ip6_finish_output skb=0xffff888103d8e600 skb->len=337 cgroup=0xffff88810741f800 sk=0xffff888103dd6300 skb->sk=0xffff888105f3b900 16:35:20: ip6_finish_output skb=0xffff888103d8e600 skb->len=337 cgroup=(nil) sk=(nil) skb->sk=(nil) 16:35:20: ip6_finish_output skb=0xffff888103d8e000 skb->len=275 cgroup=0xffffffff837741d0 sk=0xffff888101fe0000 skb->sk=0xffff888101fe0000 16:35:20: l2tp_xmit_skb skb=0xffff888103d8e000 sk=0xffff888103483180 16:35:20: ip6_finish_output skb=0xffff888103d8e000 skb->len=337 cgroup=0xffff88810741f800 sk=0xffff888103483180 skb->sk=0xffff888101fe0000 16:35:20: ip6_finish_output skb=0xffff888103d8e000 skb->len=337 cgroup=(nil) sk=(nil) skb->sk=(nil) The first four entries describe a PING message that was sent using the ping command, whereas the following four entries describe the response received. Multiple sockets are used to send one skb, including the socket used by the L2TP session. This can be observed. Based on this information, it seems that the ownership check is designed to avoid multiple calls of egress filters caused by a single skb. [0] https://lore.kernel.org/all/58193E9D.7040201@iogearbox.net/ Signed-off-by: Kui-Feng Lee Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230624014600.576756-2-kuifeng@meta.com --- include/linux/bpf-cgroup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 57e9e109257e..8506690dbb9c 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -199,9 +199,9 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ + if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ - if (sk_fullsock(__sk) && \ + if (sk_fullsock(__sk) && __sk == skb_to_full_sk(skb) && \ cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ CGROUP_INET_EGRESS); \ -- cgit v1.2.3 From 25954730461af01f66afa9e17036b051986b007e Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Thu, 6 Jul 2023 13:39:28 +0000 Subject: bpf: add percpu stats for bpf_map elements insertions/deletions Add a generic percpu stats for bpf_map elements insertions/deletions in order to keep track of both, the current (approximate) number of elements in a map and per-cpu statistics on update/delete operations. To expose these stats a particular map implementation should initialize the counter and adjust it as needed using the 'bpf_map_*_elem_count' helpers provided by this commit. Signed-off-by: Anton Protopopov Link: https://lore.kernel.org/r/20230706133932.45883-2-aspsk@isovalent.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f58895830ada..360433f14496 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -275,6 +275,7 @@ struct bpf_map { } owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ + s64 __percpu *elem_count; }; static inline const char *btf_field_type_name(enum btf_field_type type) @@ -2040,6 +2041,35 @@ bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, } #endif +static inline int +bpf_map_init_elem_count(struct bpf_map *map) +{ + size_t size = sizeof(*map->elem_count), align = size; + gfp_t flags = GFP_USER | __GFP_NOWARN; + + map->elem_count = bpf_map_alloc_percpu(map, size, align, flags); + if (!map->elem_count) + return -ENOMEM; + + return 0; +} + +static inline void +bpf_map_free_elem_count(struct bpf_map *map) +{ + free_percpu(map->elem_count); +} + +static inline void bpf_map_inc_elem_count(struct bpf_map *map) +{ + this_cpu_inc(*map->elem_count); +} + +static inline void bpf_map_dec_elem_count(struct bpf_map *map) +{ + this_cpu_dec(*map->elem_count); +} + extern int sysctl_unprivileged_bpf_disabled; static inline bool bpf_allow_ptr_leaks(void) -- cgit v1.2.3 From 7ac8d0d2619256cc13eaf4a889b3177a1607b02d Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 9 Jul 2023 02:56:21 +0000 Subject: bpf: Support ->fill_link_info for kprobe_multi With the addition of support for fill_link_info to the kprobe_multi link, users will gain the ability to inspect it conveniently using the `bpftool link show`. This enhancement provides valuable information to the user, including the count of probed functions and their respective addresses. It's important to note that if the kptr_restrict setting is not permitted, the probed address will not be exposed, ensuring security. Signed-off-by: Yafang Shao Acked-by: Jiri Olsa Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230709025630.3735-2-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 5 +++++ kernel/trace/bpf_trace.c | 37 +++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 5 +++++ 3 files changed, 47 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 60a9d59beeab..a4e881c64e0f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6439,6 +6439,11 @@ struct bpf_link_info { __s32 priority; __u32 flags; } netfilter; + struct { + __aligned_u64 addrs; + __u32 count; /* in/out: kprobe_multi function count */ + __u32 flags; + } kprobe_multi; }; } __attribute__((aligned(8))); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 03b7f6b8e4f0..acb3d6dd7a77 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2469,6 +2469,7 @@ struct bpf_kprobe_multi_link { u32 cnt; u32 mods_cnt; struct module **mods; + u32 flags; }; struct bpf_kprobe_multi_run_ctx { @@ -2558,9 +2559,44 @@ static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link) kfree(kmulti_link); } +static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + u64 __user *uaddrs = u64_to_user_ptr(info->kprobe_multi.addrs); + struct bpf_kprobe_multi_link *kmulti_link; + u32 ucount = info->kprobe_multi.count; + int err = 0, i; + + if (!uaddrs ^ !ucount) + return -EINVAL; + + kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); + info->kprobe_multi.count = kmulti_link->cnt; + info->kprobe_multi.flags = kmulti_link->flags; + + if (!uaddrs) + return 0; + if (ucount < kmulti_link->cnt) + err = -ENOSPC; + else + ucount = kmulti_link->cnt; + + if (kallsyms_show_value(current_cred())) { + if (copy_to_user(uaddrs, kmulti_link->addrs, ucount * sizeof(u64))) + return -EFAULT; + } else { + for (i = 0; i < ucount; i++) { + if (put_user(0, uaddrs + i)) + return -EFAULT; + } + } + return err; +} + static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { .release = bpf_kprobe_multi_link_release, .dealloc = bpf_kprobe_multi_link_dealloc, + .fill_link_info = bpf_kprobe_multi_link_fill_link_info, }; static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv) @@ -2872,6 +2908,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr link->addrs = addrs; link->cookies = cookies; link->cnt = cnt; + link->flags = flags; if (cookies) { /* diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 60a9d59beeab..a4e881c64e0f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6439,6 +6439,11 @@ struct bpf_link_info { __s32 priority; __u32 flags; } netfilter; + struct { + __aligned_u64 addrs; + __u32 count; /* in/out: kprobe_multi function count */ + __u32 flags; + } kprobe_multi; }; } __attribute__((aligned(8))); -- cgit v1.2.3 From 5125e757e62f6c1d5478db4c2b61a744060ddf3f Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 9 Jul 2023 02:56:25 +0000 Subject: bpf: Clear the probe_addr for uprobe To avoid returning uninitialized or random values when querying the file descriptor (fd) and accessing probe_addr, it is necessary to clear the variable prior to its use. Fixes: 41bdc4b40ed6 ("bpf: introduce bpf subcommand BPF_TASK_FD_QUERY") Signed-off-by: Yafang Shao Acked-by: Yonghong Song Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20230709025630.3735-6-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/trace_events.h | 3 ++- kernel/trace/bpf_trace.c | 2 +- kernel/trace/trace_uprobe.c | 3 ++- 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 7c4a0b72334e..36de9ebec440 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -864,7 +864,8 @@ extern int perf_uprobe_init(struct perf_event *event, extern void perf_uprobe_destroy(struct perf_event *event); extern int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, - u64 *probe_offset, bool perf_type_tracepoint); + u64 *probe_offset, u64 *probe_addr, + bool perf_type_tracepoint); #endif extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index acb3d6dd7a77..31ec0e2853ec 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2384,7 +2384,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, #ifdef CONFIG_UPROBE_EVENTS if (flags & TRACE_EVENT_FL_UPROBE) err = bpf_get_uprobe_info(event, fd_type, buf, - probe_offset, + probe_offset, probe_addr, event->attr.type == PERF_TYPE_TRACEPOINT); #endif } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 8b92e34ff0c8..fd6c71450ba7 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1415,7 +1415,7 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, u64 *probe_offset, - bool perf_type_tracepoint) + u64 *probe_addr, bool perf_type_tracepoint) { const char *pevent = trace_event_name(event->tp_event); const char *group = event->tp_event->class->system; @@ -1432,6 +1432,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, : BPF_FD_TYPE_UPROBE; *filename = tu->filename; *probe_offset = tu->offset; + *probe_addr = 0; return 0; } #endif /* CONFIG_PERF_EVENTS */ -- cgit v1.2.3 From 1b715e1b0ec531fae72cd6698fe1c98affa436f8 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 9 Jul 2023 02:56:28 +0000 Subject: bpf: Support ->fill_link_info for perf_event By introducing support for ->fill_link_info to the perf_event link, users gain the ability to inspect it using `bpftool link show`. While the current approach involves accessing this information via `bpftool perf show`, consolidating link information for all link types in one place offers greater convenience. Additionally, this patch extends support to the generic perf event, which is not currently accommodated by `bpftool perf show`. While only the perf type and config are exposed to userspace, other attributes such as sample_period and sample_freq are ignored. It's important to note that if kptr_restrict is not permitted, the probed address will not be exposed, maintaining security measures. A new enum bpf_perf_event_type is introduced to help the user understand which struct is relevant. Signed-off-by: Yafang Shao Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20230709025630.3735-9-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 35 ++++++++++ kernel/bpf/syscall.c | 146 +++++++++++++++++++++++++++++++++++++++++ kernel/trace/bpf_trace.c | 10 ++- tools/include/uapi/linux/bpf.h | 35 ++++++++++ 4 files changed, 223 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a4e881c64e0f..600d0caebbd8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1057,6 +1057,16 @@ enum bpf_link_type { MAX_BPF_LINK_TYPE, }; +enum bpf_perf_event_type { + BPF_PERF_EVENT_UNSPEC = 0, + BPF_PERF_EVENT_UPROBE = 1, + BPF_PERF_EVENT_URETPROBE = 2, + BPF_PERF_EVENT_KPROBE = 3, + BPF_PERF_EVENT_KRETPROBE = 4, + BPF_PERF_EVENT_TRACEPOINT = 5, + BPF_PERF_EVENT_EVENT = 6, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -6444,6 +6454,31 @@ struct bpf_link_info { __u32 count; /* in/out: kprobe_multi function count */ __u32 flags; } kprobe_multi; + struct { + __u32 type; /* enum bpf_perf_event_type */ + __u32 :32; + union { + struct { + __aligned_u64 file_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from file_name */ + } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ + struct { + __aligned_u64 func_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from func_name */ + __u64 addr; + } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ + struct { + __aligned_u64 tp_name; /* in/out */ + __u32 name_len; + } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ + struct { + __u64 config; + __u32 type; + } event; /* BPF_PERF_EVENT_EVENT */ + }; + } perf_event; }; } __attribute__((aligned(8))); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4aa6e5776a04..ee8cb1a174aa 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3364,9 +3364,155 @@ static void bpf_perf_link_dealloc(struct bpf_link *link) kfree(perf_link); } +static int bpf_perf_link_fill_common(const struct perf_event *event, + char __user *uname, u32 ulen, + u64 *probe_offset, u64 *probe_addr, + u32 *fd_type) +{ + const char *buf; + u32 prog_id; + size_t len; + int err; + + if (!ulen ^ !uname) + return -EINVAL; + if (!uname) + return 0; + + err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf, + probe_offset, probe_addr); + if (err) + return err; + + if (buf) { + len = strlen(buf); + err = bpf_copy_to_user(uname, buf, ulen, len); + if (err) + return err; + } else { + char zero = '\0'; + + if (put_user(zero, uname)) + return -EFAULT; + } + return 0; +} + +#ifdef CONFIG_KPROBE_EVENTS +static int bpf_perf_link_fill_kprobe(const struct perf_event *event, + struct bpf_link_info *info) +{ + char __user *uname; + u64 addr, offset; + u32 ulen, type; + int err; + + uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); + ulen = info->perf_event.kprobe.name_len; + err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, + &type); + if (err) + return err; + if (type == BPF_FD_TYPE_KRETPROBE) + info->perf_event.type = BPF_PERF_EVENT_KRETPROBE; + else + info->perf_event.type = BPF_PERF_EVENT_KPROBE; + + info->perf_event.kprobe.offset = offset; + if (!kallsyms_show_value(current_cred())) + addr = 0; + info->perf_event.kprobe.addr = addr; + return 0; +} +#endif + +#ifdef CONFIG_UPROBE_EVENTS +static int bpf_perf_link_fill_uprobe(const struct perf_event *event, + struct bpf_link_info *info) +{ + char __user *uname; + u64 addr, offset; + u32 ulen, type; + int err; + + uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); + ulen = info->perf_event.uprobe.name_len; + err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, + &type); + if (err) + return err; + + if (type == BPF_FD_TYPE_URETPROBE) + info->perf_event.type = BPF_PERF_EVENT_URETPROBE; + else + info->perf_event.type = BPF_PERF_EVENT_UPROBE; + info->perf_event.uprobe.offset = offset; + return 0; +} +#endif + +static int bpf_perf_link_fill_probe(const struct perf_event *event, + struct bpf_link_info *info) +{ +#ifdef CONFIG_KPROBE_EVENTS + if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE) + return bpf_perf_link_fill_kprobe(event, info); +#endif +#ifdef CONFIG_UPROBE_EVENTS + if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE) + return bpf_perf_link_fill_uprobe(event, info); +#endif + return -EOPNOTSUPP; +} + +static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, + struct bpf_link_info *info) +{ + char __user *uname; + u32 ulen; + + uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); + ulen = info->perf_event.tracepoint.name_len; + info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; + return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL); +} + +static int bpf_perf_link_fill_perf_event(const struct perf_event *event, + struct bpf_link_info *info) +{ + info->perf_event.event.type = event->attr.type; + info->perf_event.event.config = event->attr.config; + info->perf_event.type = BPF_PERF_EVENT_EVENT; + return 0; +} + +static int bpf_perf_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_perf_link *perf_link; + const struct perf_event *event; + + perf_link = container_of(link, struct bpf_perf_link, link); + event = perf_get_event(perf_link->perf_file); + if (IS_ERR(event)) + return PTR_ERR(event); + + switch (event->prog->type) { + case BPF_PROG_TYPE_PERF_EVENT: + return bpf_perf_link_fill_perf_event(event, info); + case BPF_PROG_TYPE_TRACEPOINT: + return bpf_perf_link_fill_tracepoint(event, info); + case BPF_PROG_TYPE_KPROBE: + return bpf_perf_link_fill_probe(event, info); + default: + return -EOPNOTSUPP; + } +} + static const struct bpf_link_ops bpf_perf_link_lops = { .release = bpf_perf_link_release, .dealloc = bpf_perf_link_dealloc, + .fill_link_info = bpf_perf_link_fill_link_info, }; static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 31ec0e2853ec..897edfc9ca12 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2369,9 +2369,13 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, if (is_tracepoint || is_syscall_tp) { *buf = is_tracepoint ? event->tp_event->tp->name : event->tp_event->name; - *fd_type = BPF_FD_TYPE_TRACEPOINT; - *probe_offset = 0x0; - *probe_addr = 0x0; + /* We allow NULL pointer for tracepoint */ + if (fd_type) + *fd_type = BPF_FD_TYPE_TRACEPOINT; + if (probe_offset) + *probe_offset = 0x0; + if (probe_addr) + *probe_addr = 0x0; } else { /* kprobe/uprobe */ err = -EOPNOTSUPP; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a4e881c64e0f..600d0caebbd8 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1057,6 +1057,16 @@ enum bpf_link_type { MAX_BPF_LINK_TYPE, }; +enum bpf_perf_event_type { + BPF_PERF_EVENT_UNSPEC = 0, + BPF_PERF_EVENT_UPROBE = 1, + BPF_PERF_EVENT_URETPROBE = 2, + BPF_PERF_EVENT_KPROBE = 3, + BPF_PERF_EVENT_KRETPROBE = 4, + BPF_PERF_EVENT_TRACEPOINT = 5, + BPF_PERF_EVENT_EVENT = 6, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -6444,6 +6454,31 @@ struct bpf_link_info { __u32 count; /* in/out: kprobe_multi function count */ __u32 flags; } kprobe_multi; + struct { + __u32 type; /* enum bpf_perf_event_type */ + __u32 :32; + union { + struct { + __aligned_u64 file_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from file_name */ + } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ + struct { + __aligned_u64 func_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from func_name */ + __u64 addr; + } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ + struct { + __aligned_u64 tp_name; /* in/out */ + __u32 name_len; + } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ + struct { + __u64 config; + __u32 type; + } event; /* BPF_PERF_EVENT_EVENT */ + }; + } perf_event; }; } __attribute__((aligned(8))); -- cgit v1.2.3 From 43a89baecfe200cb4530f42b9fcf904925d6d14a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 5 Jul 2023 20:34:43 -0700 Subject: rcu: Export rcu_request_urgent_qs_task() If a CPU is executing a long series of non-sleeping system calls, RCU grace periods can be delayed for on the order of a couple hundred milliseconds. This is normally not a problem, but if each system call does a call_rcu(), those callbacks can stack up. RCU will eventually notice this callback storm, but use of rcu_request_urgent_qs_task() allows the code invoking call_rcu() to give RCU a heads up. This function is not for general use, not yet, anyway. Reported-by: Alexei Starovoitov Signed-off-by: Paul E. McKenney Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230706033447.54696-11-alexei.starovoitov@gmail.com --- include/linux/rcutiny.h | 2 ++ include/linux/rcutree.h | 1 + kernel/rcu/rcu.h | 2 -- 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 7f17acf29dda..7b949292908a 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -138,6 +138,8 @@ static inline int rcu_needs_cpu(void) return 0; } +static inline void rcu_request_urgent_qs_task(struct task_struct *t) { } + /* * Take advantage of the fact that there is only one CPU, which * allows us to ignore virtualization-based context switches. diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 56bccb5a8fde..126f6b418f6a 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -21,6 +21,7 @@ void rcu_softirq_qs(void); void rcu_note_context_switch(bool preempt); int rcu_needs_cpu(void); void rcu_cpu_stall_reset(void); +void rcu_request_urgent_qs_task(struct task_struct *t); /* * Note a virtualization-based context switch. This is simply a diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 98c1544cf572..f95cfb5bf2ee 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -493,7 +493,6 @@ static inline void rcu_expedite_gp(void) { } static inline void rcu_unexpedite_gp(void) { } static inline void rcu_async_hurry(void) { } static inline void rcu_async_relax(void) { } -static inline void rcu_request_urgent_qs_task(struct task_struct *t) { } #else /* #ifdef CONFIG_TINY_RCU */ bool rcu_gp_is_normal(void); /* Internal RCU use. */ bool rcu_gp_is_expedited(void); /* Internal RCU use. */ @@ -508,7 +507,6 @@ void show_rcu_tasks_gp_kthreads(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ static inline void show_rcu_tasks_gp_kthreads(void) {} #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ -void rcu_request_urgent_qs_task(struct task_struct *t); #endif /* #else #ifdef CONFIG_TINY_RCU */ #define RCU_SCHEDULER_INACTIVE 0 -- cgit v1.2.3 From 5af6807bdb10d1af9d412d7d6c177ba8440adffb Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 5 Jul 2023 20:34:45 -0700 Subject: bpf: Introduce bpf_mem_free_rcu() similar to kfree_rcu(). Introduce bpf_mem_[cache_]free_rcu() similar to kfree_rcu(). Unlike bpf_mem_[cache_]free() that links objects for immediate reuse into per-cpu free list the _rcu() flavor waits for RCU grace period and then moves objects into free_by_rcu_ttrace list where they are waiting for RCU task trace grace period to be freed into slab. The life cycle of objects: alloc: dequeue free_llist free: enqeueu free_llist free_rcu: enqueue free_by_rcu -> waiting_for_gp free_llist above high watermark -> free_by_rcu_ttrace after RCU GP waiting_for_gp -> free_by_rcu_ttrace free_by_rcu_ttrace -> waiting_for_gp_ttrace -> slab Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Hou Tao Link: https://lore.kernel.org/bpf/20230706033447.54696-13-alexei.starovoitov@gmail.com --- include/linux/bpf_mem_alloc.h | 2 + kernel/bpf/memalloc.c | 129 +++++++++++++++++++++++++++++++++++++++++- 2 files changed, 128 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index 3929be5743f4..d644bbb298af 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -27,10 +27,12 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); /* kmalloc/kfree equivalent: */ void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); +void bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr); /* kmem_cache_alloc/free equivalent: */ void *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma); void bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr); +void bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr); void bpf_mem_cache_raw_free(void *ptr); void *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags); diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index e5a87f6cf2cc..17ef2e9b278a 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -101,6 +101,15 @@ struct bpf_mem_cache { bool draining; struct bpf_mem_cache *tgt; + /* list of objects to be freed after RCU GP */ + struct llist_head free_by_rcu; + struct llist_node *free_by_rcu_tail; + struct llist_head waiting_for_gp; + struct llist_node *waiting_for_gp_tail; + struct rcu_head rcu; + atomic_t call_rcu_in_progress; + struct llist_head free_llist_extra_rcu; + /* list of objects to be freed after RCU tasks trace GP */ struct llist_head free_by_rcu_ttrace; struct llist_head waiting_for_gp_ttrace; @@ -346,6 +355,69 @@ static void free_bulk(struct bpf_mem_cache *c) do_call_rcu_ttrace(tgt); } +static void __free_by_rcu(struct rcu_head *head) +{ + struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu); + struct bpf_mem_cache *tgt = c->tgt; + struct llist_node *llnode; + + llnode = llist_del_all(&c->waiting_for_gp); + if (!llnode) + goto out; + + llist_add_batch(llnode, c->waiting_for_gp_tail, &tgt->free_by_rcu_ttrace); + + /* Objects went through regular RCU GP. Send them to RCU tasks trace */ + do_call_rcu_ttrace(tgt); +out: + atomic_set(&c->call_rcu_in_progress, 0); +} + +static void check_free_by_rcu(struct bpf_mem_cache *c) +{ + struct llist_node *llnode, *t; + unsigned long flags; + + /* drain free_llist_extra_rcu */ + if (unlikely(!llist_empty(&c->free_llist_extra_rcu))) { + inc_active(c, &flags); + llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra_rcu)) + if (__llist_add(llnode, &c->free_by_rcu)) + c->free_by_rcu_tail = llnode; + dec_active(c, flags); + } + + if (llist_empty(&c->free_by_rcu)) + return; + + if (atomic_xchg(&c->call_rcu_in_progress, 1)) { + /* + * Instead of kmalloc-ing new rcu_head and triggering 10k + * call_rcu() to hit rcutree.qhimark and force RCU to notice + * the overload just ask RCU to hurry up. There could be many + * objects in free_by_rcu list. + * This hint reduces memory consumption for an artificial + * benchmark from 2 Gbyte to 150 Mbyte. + */ + rcu_request_urgent_qs_task(current); + return; + } + + WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp)); + + inc_active(c, &flags); + WRITE_ONCE(c->waiting_for_gp.first, __llist_del_all(&c->free_by_rcu)); + c->waiting_for_gp_tail = c->free_by_rcu_tail; + dec_active(c, flags); + + if (unlikely(READ_ONCE(c->draining))) { + free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size); + atomic_set(&c->call_rcu_in_progress, 0); + } else { + call_rcu_hurry(&c->rcu, __free_by_rcu); + } +} + static void bpf_mem_refill(struct irq_work *work) { struct bpf_mem_cache *c = container_of(work, struct bpf_mem_cache, refill_work); @@ -360,6 +432,8 @@ static void bpf_mem_refill(struct irq_work *work) alloc_bulk(c, c->batch, NUMA_NO_NODE); else if (cnt > c->high_watermark) free_bulk(c); + + check_free_by_rcu(c); } static void notrace irq_work_raise(struct bpf_mem_cache *c) @@ -488,6 +562,9 @@ static void drain_mem_cache(struct bpf_mem_cache *c) free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu); free_all(__llist_del_all(&c->free_llist), percpu); free_all(__llist_del_all(&c->free_llist_extra), percpu); + free_all(__llist_del_all(&c->free_by_rcu), percpu); + free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu); + free_all(llist_del_all(&c->waiting_for_gp), percpu); } static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma) @@ -500,8 +577,8 @@ static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma) static void free_mem_alloc(struct bpf_mem_alloc *ma) { - /* waiting_for_gp_ttrace lists was drained, but __free_rcu might - * still execute. Wait for it now before we freeing percpu caches. + /* waiting_for_gp[_ttrace] lists were drained, but RCU callbacks + * might still execute. Wait for them. * * rcu_barrier_tasks_trace() doesn't imply synchronize_rcu_tasks_trace(), * but rcu_barrier_tasks_trace() and rcu_barrier() below are only used @@ -510,7 +587,8 @@ static void free_mem_alloc(struct bpf_mem_alloc *ma) * rcu_trace_implies_rcu_gp(), it will be OK to skip rcu_barrier() by * using rcu_trace_implies_rcu_gp() as well. */ - rcu_barrier_tasks_trace(); + rcu_barrier(); /* wait for __free_by_rcu */ + rcu_barrier_tasks_trace(); /* wait for __free_rcu */ if (!rcu_trace_implies_rcu_gp()) rcu_barrier(); free_mem_alloc_no_barrier(ma); @@ -563,6 +641,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) irq_work_sync(&c->refill_work); drain_mem_cache(c); rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); + rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } /* objcg is the same across cpus */ if (c->objcg) @@ -579,6 +658,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) irq_work_sync(&c->refill_work); drain_mem_cache(c); rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); + rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } } if (c->objcg) @@ -663,6 +743,27 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr) irq_work_raise(c); } +static void notrace unit_free_rcu(struct bpf_mem_cache *c, void *ptr) +{ + struct llist_node *llnode = ptr - LLIST_NODE_SZ; + unsigned long flags; + + c->tgt = *(struct bpf_mem_cache **)llnode; + + local_irq_save(flags); + if (local_inc_return(&c->active) == 1) { + if (__llist_add(llnode, &c->free_by_rcu)) + c->free_by_rcu_tail = llnode; + } else { + llist_add(llnode, &c->free_llist_extra_rcu); + } + local_dec(&c->active); + local_irq_restore(flags); + + if (!atomic_read(&c->call_rcu_in_progress)) + irq_work_raise(c); +} + /* Called from BPF program or from sys_bpf syscall. * In both cases migration is disabled. */ @@ -696,6 +797,20 @@ void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr) unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr); } +void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr) +{ + int idx; + + if (!ptr) + return; + + idx = bpf_mem_cache_idx(ksize(ptr - LLIST_NODE_SZ)); + if (idx < 0) + return; + + unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr); +} + void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma) { void *ret; @@ -712,6 +827,14 @@ void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr) unit_free(this_cpu_ptr(ma->cache), ptr); } +void notrace bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr) +{ + if (!ptr) + return; + + unit_free_rcu(this_cpu_ptr(ma->cache), ptr); +} + /* Directly does a kfree() without putting 'ptr' back to the free_llist * for reuse and without waiting for a rcu_tasks_trace gp. * The caller must first go through the rcu_tasks_trace gp for 'ptr' -- cgit v1.2.3 From d26979f1cef71d6fa036f6cedfa0059715092503 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 10:59:50 +0200 Subject: net: stmmac: replace the has_integrated_pcs field with a flag struct plat_stmmacenet_data contains several boolean fields that could be easily replaced with a common integer 'flags' bitfield and bit defines. Start the process with the has_integrated_pcs field. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-2-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 3 ++- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++- include/linux/stmmac.h | 4 +++- 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 757504ebb676..3cfa4d2e1929 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -786,7 +786,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->tso_en = of_property_read_bool(np, "snps,tso"); if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) plat_dat->rx_clk_runs_in_lpi = 1; - plat_dat->has_integrated_pcs = data->has_integrated_pcs; + if (data->has_integrated_pcs) + plat_dat->flags |= STMMAC_FLAG_HAS_INTEGRATED_PCS; if (ethqos->serdes_phy) { plat_dat->serdes_powerup = qcom_ethqos_serdes_powerup; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4727f7be4f86..38b6cbd8a133 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5798,7 +5798,8 @@ static void stmmac_common_interrupt(struct stmmac_priv *priv) } /* PCS link status */ - if (priv->hw->pcs && !priv->plat->has_integrated_pcs) { + if (priv->hw->pcs && + !(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS)) { if (priv->xstats.pcs_link) netif_carrier_on(priv->dev); else diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 06090538fe2d..8e7511071ef1 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -204,6 +204,8 @@ struct dwmac4_addrs { u32 mtl_low_cred_offset; }; +#define STMMAC_FLAG_HAS_INTEGRATED_PCS BIT(0) + struct plat_stmmacenet_data { int bus_id; int phy_addr; @@ -293,6 +295,6 @@ struct plat_stmmacenet_data { bool sph_disable; bool serdes_up_after_phy_linkup; const struct dwmac4_addrs *dwmac4_addrs; - bool has_integrated_pcs; + unsigned int flags; }; #endif -- cgit v1.2.3 From 309efe6eb499d04b7c09e57298c453b602efe3fd Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 10:59:51 +0200 Subject: net: stmmac: replace the sph_disable field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-3-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++- include/linux/stmmac.h | 2 +- 4 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 9f88530c5e8c..0c12ab67c27b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -359,7 +359,7 @@ bypass_clk_reset_gpio: data->fix_mac_speed = tegra_eqos_fix_speed; data->init = tegra_eqos_init; data->bsp_priv = eqos; - data->sph_disable = 1; + data->flags |= STMMAC_FLAG_SPH_DISABLE; err = tegra_eqos_init(pdev, eqos); if (err < 0) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index ab9f876b6df7..ae5db39a3f1b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -459,7 +459,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->has_gmac4 = 1; plat->force_sf_dma_mode = 0; plat->tso_en = 1; - plat->sph_disable = 1; + plat->flags |= STMMAC_FLAG_SPH_DISABLE; /* Multiplying factor to the clk_eee_i clock time * period to make it closer to 100 ns. This value diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 38b6cbd8a133..18e56299363d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7258,7 +7258,8 @@ int stmmac_dvr_probe(struct device *device, dev_info(priv->device, "TSO feature enabled\n"); } - if (priv->dma_cap.sphen && !priv->plat->sph_disable) { + if (priv->dma_cap.sphen && + !(priv->plat->flags & STMMAC_FLAG_SPH_DISABLE)) { ndev->hw_features |= NETIF_F_GRO; priv->sph_cap = true; priv->sph = priv->sph_cap; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 8e7511071ef1..1b02f866316c 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -205,6 +205,7 @@ struct dwmac4_addrs { }; #define STMMAC_FLAG_HAS_INTEGRATED_PCS BIT(0) +#define STMMAC_FLAG_SPH_DISABLE BIT(1) struct plat_stmmacenet_data { int bus_id; @@ -292,7 +293,6 @@ struct plat_stmmacenet_data { int msi_rx_base_vec; int msi_tx_base_vec; bool use_phy_wol; - bool sph_disable; bool serdes_up_after_phy_linkup; const struct dwmac4_addrs *dwmac4_addrs; unsigned int flags; -- cgit v1.2.3 From fd1d62d80ebc1a68ba700e92c9da9d443c08f371 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 10:59:52 +0200 Subject: net: stmmac: replace the use_phy_wol field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-4-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c | 5 ++++- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- include/linux/stmmac.h | 2 +- 4 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index ae5db39a3f1b..c690ec1b9bab 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -628,7 +628,7 @@ static int ehl_common_data(struct pci_dev *pdev, { plat->rx_queues_to_use = 8; plat->tx_queues_to_use = 8; - plat->use_phy_wol = 1; + plat->flags |= STMMAC_FLAG_USE_PHY_WOL; plat->safety_feat_cfg->tsoee = 1; plat->safety_feat_cfg->mrxpee = 1; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index 73c1dfa7ecb1..4d877d75642d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -588,7 +588,10 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev, int i; plat->interface = priv_plat->phy_mode; - plat->use_phy_wol = priv_plat->mac_wol ? 0 : 1; + if (priv_plat->mac_wol) + plat->flags |= STMMAC_FLAG_USE_PHY_WOL; + else + plat->flags &= ~STMMAC_FLAG_USE_PHY_WOL; plat->riwt_off = 1; plat->maxmtu = ETH_DATA_LEN; plat->host_dma_width = priv_plat->variant->dma_bit_mask; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 18e56299363d..a1a59af3961d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -6877,7 +6877,7 @@ static int stmmac_hw_init(struct stmmac_priv *priv) */ priv->plat->enh_desc = priv->dma_cap.enh_desc; priv->plat->pmt = priv->dma_cap.pmt_remote_wake_up && - !priv->plat->use_phy_wol; + !(priv->plat->flags & STMMAC_FLAG_USE_PHY_WOL); priv->hw->pmt = priv->plat->pmt; if (priv->dma_cap.hash_tb_sz) { priv->hw->multicast_filter_bins = diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 1b02f866316c..15fb07cc89c8 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -206,6 +206,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_HAS_INTEGRATED_PCS BIT(0) #define STMMAC_FLAG_SPH_DISABLE BIT(1) +#define STMMAC_FLAG_USE_PHY_WOL BIT(2) struct plat_stmmacenet_data { int bus_id; @@ -292,7 +293,6 @@ struct plat_stmmacenet_data { int msi_sfty_ue_vec; int msi_rx_base_vec; int msi_tx_base_vec; - bool use_phy_wol; bool serdes_up_after_phy_linkup; const struct dwmac4_addrs *dwmac4_addrs; unsigned int flags; -- cgit v1.2.3 From d8daff284e305409fd640feda7345d0221d782ce Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 10:59:53 +0200 Subject: net: stmmac: replace the has_sun8i field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-5-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++-- include/linux/stmmac.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 1e714380d125..2b5ebb15bfda 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1227,7 +1227,7 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) plat_dat->interface = interface; plat_dat->rx_coe = STMMAC_RX_COE_TYPE2; plat_dat->tx_coe = 1; - plat_dat->has_sun8i = true; + plat_dat->flags |= STMMAC_FLAG_HAS_SUN8I; plat_dat->bsp_priv = gmac; plat_dat->init = sun8i_dwmac_init; plat_dat->exit = sun8i_dwmac_exit; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a1a59af3961d..3df32658b5bb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -325,7 +325,7 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv) priv->clk_csr = STMMAC_CSR_250_300M; } - if (priv->plat->has_sun8i) { + if (priv->plat->flags & STMMAC_FLAG_HAS_SUN8I) { if (clk_rate > 160000000) priv->clk_csr = 0x03; else if (clk_rate > 80000000) @@ -6856,7 +6856,7 @@ static int stmmac_hw_init(struct stmmac_priv *priv) int ret; /* dwmac-sun8i only work in chain mode */ - if (priv->plat->has_sun8i) + if (priv->plat->flags & STMMAC_FLAG_HAS_SUN8I) chain_mode = 1; priv->chain_mode = chain_mode; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 15fb07cc89c8..66dcf84d024a 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -207,6 +207,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_HAS_INTEGRATED_PCS BIT(0) #define STMMAC_FLAG_SPH_DISABLE BIT(1) #define STMMAC_FLAG_USE_PHY_WOL BIT(2) +#define STMMAC_FLAG_HAS_SUN8I BIT(3) struct plat_stmmacenet_data { int bus_id; @@ -270,7 +271,6 @@ struct plat_stmmacenet_data { struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; int has_gmac4; - bool has_sun8i; bool tso_en; int rss_en; int mac_port_sel_speed; -- cgit v1.2.3 From 68861a3bcc1caf5c15a56e02090310271fd085e1 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 10:59:54 +0200 Subject: net: stmmac: replace the tso_en field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-6-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 3 +-- drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 3 ++- drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 6 ++++-- include/linux/stmmac.h | 2 +- 8 files changed, 13 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 0c12ab67c27b..b5efd9c2eac7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -113,7 +113,7 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev, /* dwc-qos needs GMAC4, AAL, TSO and PMT */ plat_dat->has_gmac4 = 1; plat_dat->dma_cfg->aal = 1; - plat_dat->tso_en = 1; + plat_dat->flags |= STMMAC_FLAG_TSO_EN; plat_dat->pmt = 1; return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index c690ec1b9bab..faa6f4ec6838 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -458,8 +458,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->has_gmac = 0; plat->has_gmac4 = 1; plat->force_sf_dma_mode = 0; - plat->tso_en = 1; - plat->flags |= STMMAC_FLAG_SPH_DISABLE; + plat->flags |= (STMMAC_FLAG_TSO_EN | STMMAC_FLAG_SPH_DISABLE); /* Multiplying factor to the clk_eee_i clock time * period to make it closer to 100 ns. This value diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 3cfa4d2e1929..4b58904ee132 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -783,7 +783,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) if (ethqos->has_emac_ge_3) plat_dat->dwmac4_addrs = &data->dwmac4_addrs; plat_dat->pmt = 1; - plat_dat->tso_en = of_property_read_bool(np, "snps,tso"); + if (of_property_read_bool(np, "snps,tso")) + plat_dat->flags |= STMMAC_FLAG_TSO_EN; if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) plat_dat->rx_clk_runs_in_lpi = 1; if (data->has_integrated_pcs) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c index f8367c5b490b..5e8aa03cffae 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c @@ -290,7 +290,7 @@ static int tegra_mgbe_probe(struct platform_device *pdev) } plat->has_xgmac = 1; - plat->tso_en = 1; + plat->flags |= STMMAC_FLAG_TSO_EN; plat->pmt = 1; plat->bsp_priv = mgbe; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3df32658b5bb..73002ed923aa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5677,7 +5677,7 @@ static netdev_features_t stmmac_fix_features(struct net_device *dev, features &= ~NETIF_F_CSUM_MASK; /* Disable tso if asked by ethtool */ - if ((priv->plat->tso_en) && (priv->dma_cap.tsoen)) { + if ((priv->plat->flags & STMMAC_FLAG_TSO_EN) && (priv->dma_cap.tsoen)) { if (features & NETIF_F_TSO) priv->tso = true; else @@ -7250,7 +7250,7 @@ int stmmac_dvr_probe(struct device *device, ndev->hw_features |= NETIF_F_HW_TC; } - if ((priv->plat->tso_en) && (priv->dma_cap.tsoen)) { + if ((priv->plat->flags & STMMAC_FLAG_TSO_EN) && (priv->dma_cap.tsoen)) { ndev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; if (priv->plat->has_gmac4) ndev->hw_features |= NETIF_F_GSO_UDP_L4; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 644bb54f5f02..352b01678c22 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -77,7 +77,7 @@ static int snps_gmac5_default_data(struct pci_dev *pdev, plat->clk_csr = 5; plat->has_gmac4 = 1; plat->force_sf_dma_mode = 1; - plat->tso_en = 1; + plat->flags |= STMMAC_FLAG_TSO_EN; plat->pmt = 1; /* Set default value for multicast hash bins */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 231152ee5a32..f51522cb0061 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -525,7 +525,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->has_gmac4 = 1; plat->has_gmac = 0; plat->pmt = 1; - plat->tso_en = of_property_read_bool(np, "snps,tso"); + if (of_property_read_bool(np, "snps,tso")) + plat->flags |= STMMAC_FLAG_TSO_EN; } if (of_device_is_compatible(np, "snps,dwmac-3.610") || @@ -538,7 +539,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) if (of_device_is_compatible(np, "snps,dwxgmac")) { plat->has_xgmac = 1; plat->pmt = 1; - plat->tso_en = of_property_read_bool(np, "snps,tso"); + if (of_property_read_bool(np, "snps,tso")) + plat->flags |= STMMAC_FLAG_TSO_EN; } dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 66dcf84d024a..47ae29a98835 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -208,6 +208,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_SPH_DISABLE BIT(1) #define STMMAC_FLAG_USE_PHY_WOL BIT(2) #define STMMAC_FLAG_HAS_SUN8I BIT(3) +#define STMMAC_FLAG_TSO_EN BIT(4) struct plat_stmmacenet_data { int bus_id; @@ -271,7 +272,6 @@ struct plat_stmmacenet_data { struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; int has_gmac4; - bool tso_en; int rss_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; -- cgit v1.2.3 From efe92571bfc30f251f6f2fa7828aa5f239736abf Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 10:59:55 +0200 Subject: net: stmmac: replace the serdes_up_after_phy_linkup field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-7-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 9 ++++++--- include/linux/stmmac.h | 2 +- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c index 5e8aa03cffae..99e2e5a5cd60 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c @@ -337,7 +337,7 @@ static int tegra_mgbe_probe(struct platform_device *pdev) /* Program SID */ writel(MGBE_SID, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); - plat->serdes_up_after_phy_linkup = 1; + plat->flags |= STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP; err = stmmac_dvr_probe(&pdev->dev, plat, &res); if (err < 0) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 73002ed923aa..d444514db07e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -991,7 +991,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); u32 old_ctrl, ctrl; - if (priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) + if ((priv->plat->flags & STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP) && + priv->plat->serdes_powerup) priv->plat->serdes_powerup(priv->dev, priv->plat->bsp_priv); old_ctrl = readl(priv->ioaddr + MAC_CTRL_REG); @@ -3838,7 +3839,8 @@ static int __stmmac_open(struct net_device *dev, stmmac_reset_queues_param(priv); - if (!priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) { + if (!(priv->plat->flags & STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP) && + priv->plat->serdes_powerup) { ret = priv->plat->serdes_powerup(dev, priv->plat->bsp_priv); if (ret < 0) { netdev_err(priv->dev, "%s: Serdes powerup failed\n", @@ -7623,7 +7625,8 @@ int stmmac_resume(struct device *dev) stmmac_mdio_reset(priv->mii); } - if (!priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) { + if (!(priv->plat->flags & STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP) && + priv->plat->serdes_powerup) { ret = priv->plat->serdes_powerup(ndev, priv->plat->bsp_priv); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 47ae29a98835..aeb3e75dc748 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -209,6 +209,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_USE_PHY_WOL BIT(2) #define STMMAC_FLAG_HAS_SUN8I BIT(3) #define STMMAC_FLAG_TSO_EN BIT(4) +#define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP BIT(5) struct plat_stmmacenet_data { int bus_id; @@ -293,7 +294,6 @@ struct plat_stmmacenet_data { int msi_sfty_ue_vec; int msi_rx_base_vec; int msi_tx_base_vec; - bool serdes_up_after_phy_linkup; const struct dwmac4_addrs *dwmac4_addrs; unsigned int flags; }; -- cgit v1.2.3 From fc02152bdbb28bd46df66ddcf4f469760c1b8df8 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 10:59:56 +0200 Subject: net: stmmac: replace the vlan_fail_q_en field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-8-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++- include/linux/stmmac.h | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index faa6f4ec6838..1f1bc99571a5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -560,7 +560,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, /* Set the maxmtu to a default of JUMBO_LEN */ plat->maxmtu = JUMBO_LEN; - plat->vlan_fail_q_en = true; + plat->flags |= STMMAC_FLAG_VLAN_FAIL_Q_EN; /* Use the last Rx queue */ plat->vlan_fail_q = plat->rx_queues_to_use - 1; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d444514db07e..c5763f60c6ef 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -6923,7 +6923,8 @@ static int stmmac_hw_init(struct stmmac_priv *priv) if (priv->dma_cap.tsoen) dev_info(priv->device, "TSO supported\n"); - priv->hw->vlan_fail_q_en = priv->plat->vlan_fail_q_en; + priv->hw->vlan_fail_q_en = + (priv->plat->flags & STMMAC_FLAG_VLAN_FAIL_Q_EN); priv->hw->vlan_fail_q = priv->plat->vlan_fail_q; /* Run HW quirks, if any */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index aeb3e75dc748..155cb11b1c8a 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -210,6 +210,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_HAS_SUN8I BIT(3) #define STMMAC_FLAG_TSO_EN BIT(4) #define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP BIT(5) +#define STMMAC_FLAG_VLAN_FAIL_Q_EN BIT(6) struct plat_stmmacenet_data { int bus_id; @@ -278,7 +279,6 @@ struct plat_stmmacenet_data { bool en_tx_lpi_clockgating; bool rx_clk_runs_in_lpi; int has_xgmac; - bool vlan_fail_q_en; u8 vlan_fail_q; unsigned int eee_usecs_rate; struct pci_dev *pdev; -- cgit v1.2.3 From 956c3f09b9c4cc9567ca11c84007545b939e61aa Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 10:59:57 +0200 Subject: net: stmmac: replace the multi_msi_en field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-9-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 ++++--- include/linux/stmmac.h | 2 +- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 1f1bc99571a5..d8bcf9452197 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -953,7 +953,7 @@ static int stmmac_config_single_msi(struct pci_dev *pdev, res->irq = pci_irq_vector(pdev, 0); res->wol_irq = res->irq; - plat->multi_msi_en = 0; + plat->flags &= ~STMMAC_FLAG_MULTI_MSI_EN; dev_info(&pdev->dev, "%s: Single IRQ enablement successful\n", __func__); @@ -1005,7 +1005,7 @@ static int stmmac_config_multi_msi(struct pci_dev *pdev, if (plat->msi_sfty_ue_vec < STMMAC_MSI_VEC_MAX) res->sfty_ue_irq = pci_irq_vector(pdev, plat->msi_sfty_ue_vec); - plat->multi_msi_en = 1; + plat->flags |= STMMAC_FLAG_MULTI_MSI_EN; dev_info(&pdev->dev, "%s: multi MSI enablement successful\n", __func__); return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c5763f60c6ef..ebe82e7b50fc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3711,7 +3711,7 @@ static int stmmac_request_irq(struct net_device *dev) int ret; /* Request the IRQ lines */ - if (priv->plat->multi_msi_en) + if (priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN) ret = stmmac_request_irq_multi_msi(dev); else ret = stmmac_request_irq_single(dev); @@ -5954,7 +5954,7 @@ static void stmmac_poll_controller(struct net_device *dev) if (test_bit(STMMAC_DOWN, &priv->state)) return; - if (priv->plat->multi_msi_en) { + if (priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN) { for (i = 0; i < priv->plat->rx_queues_to_use; i++) stmmac_msi_intr_rx(0, &priv->dma_conf.rx_queue[i]); @@ -7169,7 +7169,8 @@ int stmmac_dvr_probe(struct device *device, priv->plat = plat_dat; priv->ioaddr = res->addr; priv->dev->base_addr = (unsigned long)res->addr; - priv->plat->dma_cfg->multi_msi_en = priv->plat->multi_msi_en; + priv->plat->dma_cfg->multi_msi_en = + (priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN); priv->dev->irq = res->irq; priv->wol_irq = res->wol_irq; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 155cb11b1c8a..3365b8071686 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -211,6 +211,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_TSO_EN BIT(4) #define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP BIT(5) #define STMMAC_FLAG_VLAN_FAIL_Q_EN BIT(6) +#define STMMAC_FLAG_MULTI_MSI_EN BIT(7) struct plat_stmmacenet_data { int bus_id; @@ -286,7 +287,6 @@ struct plat_stmmacenet_data { int ext_snapshot_num; bool int_snapshot_en; bool ext_snapshot_en; - bool multi_msi_en; int msi_mac_vec; int msi_wol_vec; int msi_lpi_vec; -- cgit v1.2.3 From aa5513f5d95f6b5311de859f8f466a09863bedf6 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 10:59:58 +0200 Subject: net: stmmac: replace the ext_snapshot_en field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-10-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 5 ++++- include/linux/stmmac.h | 2 +- 4 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index d8bcf9452197..a3d0da4e9e91 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -326,7 +326,7 @@ static int intel_crosststamp(ktime_t *device, /* Both internal crosstimestamping and external triggered event * timestamping cannot be run concurrently. */ - if (priv->plat->ext_snapshot_en) + if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN) return -EBUSY; priv->plat->int_snapshot_en = 1; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 8b50f03056b7..afd81aac6644 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -195,7 +195,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv) */ ts_status = readl(priv->ioaddr + GMAC_TIMESTAMP_STATUS); - if (!priv->plat->ext_snapshot_en) + if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN) return; num_snapshot = (ts_status & GMAC_TIMESTAMP_ATSNS_MASK) >> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index b4388ca8d211..3d7825cb30bb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -192,7 +192,10 @@ static int stmmac_enable(struct ptp_clock_info *ptp, write_unlock_irqrestore(&priv->ptp_lock, flags); break; case PTP_CLK_REQ_EXTTS: - priv->plat->ext_snapshot_en = on; + if (on) + priv->plat->flags |= STMMAC_FLAG_EXT_SNAPSHOT_EN; + else + priv->plat->flags &= ~STMMAC_FLAG_EXT_SNAPSHOT_EN; mutex_lock(&priv->aux_ts_lock); acr_value = readl(ptpaddr + PTP_ACR); acr_value &= ~PTP_ACR_MASK; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 3365b8071686..0a77e8b05d3a 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -212,6 +212,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP BIT(5) #define STMMAC_FLAG_VLAN_FAIL_Q_EN BIT(6) #define STMMAC_FLAG_MULTI_MSI_EN BIT(7) +#define STMMAC_FLAG_EXT_SNAPSHOT_EN BIT(8) struct plat_stmmacenet_data { int bus_id; @@ -286,7 +287,6 @@ struct plat_stmmacenet_data { int int_snapshot_num; int ext_snapshot_num; bool int_snapshot_en; - bool ext_snapshot_en; int msi_mac_vec; int msi_wol_vec; int msi_lpi_vec; -- cgit v1.2.3 From 621ba7ad7891b381baf9ebf3da4ec4e95c86ea4e Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 10:59:59 +0200 Subject: net: stmmac: replace the int_snapshot_en field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-11-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 10 +++++----- drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 2 +- include/linux/stmmac.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index a3d0da4e9e91..0ffae785d8bd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -329,7 +329,7 @@ static int intel_crosststamp(ktime_t *device, if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN) return -EBUSY; - priv->plat->int_snapshot_en = 1; + priv->plat->flags |= STMMAC_FLAG_INT_SNAPSHOT_EN; mutex_lock(&priv->aux_ts_lock); /* Enable Internal snapshot trigger */ @@ -350,7 +350,7 @@ static int intel_crosststamp(ktime_t *device, break; default: mutex_unlock(&priv->aux_ts_lock); - priv->plat->int_snapshot_en = 0; + priv->plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN; return -EINVAL; } writel(acr_value, ptpaddr + PTP_ACR); @@ -376,7 +376,7 @@ static int intel_crosststamp(ktime_t *device, if (!wait_event_interruptible_timeout(priv->tstamp_busy_wait, stmmac_cross_ts_isr(priv), HZ / 100)) { - priv->plat->int_snapshot_en = 0; + priv->plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN; return -ETIMEDOUT; } @@ -395,7 +395,7 @@ static int intel_crosststamp(ktime_t *device, } system->cycles *= intel_priv->crossts_adj; - priv->plat->int_snapshot_en = 0; + priv->plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN; return 0; } @@ -609,7 +609,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->ext_snapshot_num = AUX_SNAPSHOT0; plat->crosststamp = intel_crosststamp; - plat->int_snapshot_en = 0; + plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN; /* Setup MSI vector offset specific to Intel mGbE controller */ plat->msi_mac_vec = 29; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index afd81aac6644..fa2c3ba7e9fe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -180,7 +180,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv) u64 ptp_time; int i; - if (priv->plat->int_snapshot_en) { + if (priv->plat->flags & STMMAC_FLAG_INT_SNAPSHOT_EN) { wake_up(&priv->tstamp_busy_wait); return; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0a77e8b05d3a..47708ddd57fd 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -213,6 +213,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_VLAN_FAIL_Q_EN BIT(6) #define STMMAC_FLAG_MULTI_MSI_EN BIT(7) #define STMMAC_FLAG_EXT_SNAPSHOT_EN BIT(8) +#define STMMAC_FLAG_INT_SNAPSHOT_EN BIT(9) struct plat_stmmacenet_data { int bus_id; @@ -286,7 +287,6 @@ struct plat_stmmacenet_data { struct pci_dev *pdev; int int_snapshot_num; int ext_snapshot_num; - bool int_snapshot_en; int msi_mac_vec; int msi_wol_vec; int msi_lpi_vec; -- cgit v1.2.3 From 743dd1db85f40be1e2c7416c83f0289aaa260ceb Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 11:00:00 +0200 Subject: net: stmmac: replace the rx_clk_runs_in_lpi field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-12-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++- include/linux/stmmac.h | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 4b58904ee132..735525ba8b93 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -786,7 +786,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev) if (of_property_read_bool(np, "snps,tso")) plat_dat->flags |= STMMAC_FLAG_TSO_EN; if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) - plat_dat->rx_clk_runs_in_lpi = 1; + plat_dat->flags |= STMMAC_FLAG_RX_CLK_RUNS_IN_LPI; if (data->has_integrated_pcs) plat_dat->flags |= STMMAC_FLAG_HAS_INTEGRATED_PCS; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ebe82e7b50fc..2d68a6e84b0e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1085,7 +1085,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, stmmac_mac_set(priv, priv->ioaddr, true); if (phy && priv->dma_cap.eee) { priv->eee_active = - phy_init_eee(phy, !priv->plat->rx_clk_runs_in_lpi) >= 0; + phy_init_eee(phy, !(priv->plat->flags & + STMMAC_FLAG_RX_CLK_RUNS_IN_LPI)) >= 0; priv->eee_enabled = stmmac_eee_init(priv); priv->tx_lpi_enabled = priv->eee_enabled; stmmac_set_eee_pls(priv, priv->hw, true); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 47708ddd57fd..c3769dad8238 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -214,6 +214,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_MULTI_MSI_EN BIT(7) #define STMMAC_FLAG_EXT_SNAPSHOT_EN BIT(8) #define STMMAC_FLAG_INT_SNAPSHOT_EN BIT(9) +#define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI BIT(10) struct plat_stmmacenet_data { int bus_id; @@ -280,7 +281,6 @@ struct plat_stmmacenet_data { int rss_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; - bool rx_clk_runs_in_lpi; int has_xgmac; u8 vlan_fail_q; unsigned int eee_usecs_rate; -- cgit v1.2.3 From 9d0c0d5ebd635f914ab2ab691b68e8754fbe0a57 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 10 Jul 2023 11:00:01 +0200 Subject: net: stmmac: replace the en_tx_lpi_clockgating field with a flag Drop the boolean field of the plat_stmmacenet_data structure in favor of a simple bitfield flag. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Halaney Link: https://lore.kernel.org/r/20230710090001.303225-13-brgl@bgdev.pl Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 4 ++-- include/linux/stmmac.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 2d68a6e84b0e..efe85b086abe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -421,7 +421,7 @@ static int stmmac_enable_eee_mode(struct stmmac_priv *priv) /* Check and enter in LPI mode */ if (!priv->tx_path_in_lpi_mode) stmmac_set_eee_mode(priv, priv->hw, - priv->plat->en_tx_lpi_clockgating); + priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLOCKGATING); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index f51522cb0061..23d53ea04b24 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -466,8 +466,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->force_sf_dma_mode = of_property_read_bool(np, "snps,force_sf_dma_mode"); - plat->en_tx_lpi_clockgating = - of_property_read_bool(np, "snps,en-tx-lpi-clockgating"); + if (of_property_read_bool(np, "snps,en-tx-lpi-clockgating")) + plat->flags |= STMMAC_FLAG_EN_TX_LPI_CLOCKGATING; /* Set the maxmtu to a default of JUMBO_LEN in case the * parameter is not present in the device tree. diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c3769dad8238..ef67dba775d0 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -215,6 +215,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_EXT_SNAPSHOT_EN BIT(8) #define STMMAC_FLAG_INT_SNAPSHOT_EN BIT(9) #define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI BIT(10) +#define STMMAC_FLAG_EN_TX_LPI_CLOCKGATING BIT(11) struct plat_stmmacenet_data { int bus_id; @@ -280,7 +281,6 @@ struct plat_stmmacenet_data { int has_gmac4; int rss_en; int mac_port_sel_speed; - bool en_tx_lpi_clockgating; int has_xgmac; u8 vlan_fail_q; unsigned int eee_usecs_rate; -- cgit v1.2.3 From 5b52ad34f9487b2c2d1e60fe37e5bd5656b4dac8 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 11 Jul 2023 15:06:08 +0200 Subject: security: Constify sk in the sk_getsecid hook. The sk_getsecid hook shouldn't need to modify its socket argument. Make it const so that callers of security_sk_classify_flow() can use a const struct sock *. Signed-off-by: Guillaume Nault Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/lsm_hook_defs.h | 2 +- include/linux/security.h | 5 +++-- security/security.c | 2 +- security/selinux/hooks.c | 4 ++-- 4 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 7308a1a7599b..4f2621e87634 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -316,7 +316,7 @@ LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority) LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk) LSM_HOOK(void, LSM_RET_VOID, sk_clone_security, const struct sock *sk, struct sock *newsk) -LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, struct sock *sk, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, const struct sock *sk, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, sock_graft, struct sock *sk, struct socket *parent) LSM_HOOK(int, 0, inet_conn_request, const struct sock *sk, struct sk_buff *skb, struct request_sock *req) diff --git a/include/linux/security.h b/include/linux/security.h index 32828502f09e..994cf099d9ac 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1439,7 +1439,8 @@ int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u int security_sk_alloc(struct sock *sk, int family, gfp_t priority); void security_sk_free(struct sock *sk); void security_sk_clone(const struct sock *sk, struct sock *newsk); -void security_sk_classify_flow(struct sock *sk, struct flowi_common *flic); +void security_sk_classify_flow(const struct sock *sk, + struct flowi_common *flic); void security_req_classify_flow(const struct request_sock *req, struct flowi_common *flic); void security_sock_graft(struct sock*sk, struct socket *parent); @@ -1597,7 +1598,7 @@ static inline void security_sk_clone(const struct sock *sk, struct sock *newsk) { } -static inline void security_sk_classify_flow(struct sock *sk, +static inline void security_sk_classify_flow(const struct sock *sk, struct flowi_common *flic) { } diff --git a/security/security.c b/security/security.c index b720424ca37d..2dfc7b9f6ed9 100644 --- a/security/security.c +++ b/security/security.c @@ -4396,7 +4396,7 @@ void security_sk_clone(const struct sock *sk, struct sock *newsk) } EXPORT_SYMBOL(security_sk_clone); -void security_sk_classify_flow(struct sock *sk, struct flowi_common *flic) +void security_sk_classify_flow(const struct sock *sk, struct flowi_common *flic) { call_void_hook(sk_getsecid, sk, &flic->flowic_secid); } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index d06e350fedee..2bdc48dd8670 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5167,12 +5167,12 @@ static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk) selinux_netlbl_sk_security_reset(newsksec); } -static void selinux_sk_getsecid(struct sock *sk, u32 *secid) +static void selinux_sk_getsecid(const struct sock *sk, u32 *secid) { if (!sk) *secid = SECINITSID_ANY_SOCKET; else { - struct sk_security_struct *sksec = sk->sk_security; + const struct sk_security_struct *sksec = sk->sk_security; *secid = sksec->sid; } -- cgit v1.2.3 From 8d6eba33a2726e463eeab5c42b8eb373d7462127 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 11 Jul 2023 15:06:14 +0200 Subject: ipv4: Constify the sk parameter of ip_route_output_*(). These functions don't need to modify the socket, so let's allow the callers to pass a const struct sock *. Signed-off-by: Guillaume Nault Reviewed-by: Simon Horman Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/route.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 5a5c726472bd..d8d150155195 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -163,7 +163,7 @@ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr, } static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi4 *fl4, - struct sock *sk, + const struct sock *sk, __be32 daddr, __be32 saddr, __be16 dport, __be16 sport, __u8 proto, __u8 tos, int oif) @@ -309,7 +309,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst, __be32 src, int oif, u8 protocol, __be16 sport, __be16 dport, - struct sock *sk) + const struct sock *sk) { struct net *net = sock_net(sk); struct rtable *rt; @@ -330,7 +330,7 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst, static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable *rt, __be16 orig_sport, __be16 orig_dport, __be16 sport, __be16 dport, - struct sock *sk) + const struct sock *sk) { if (sport != orig_sport || dport != orig_dport) { fl4->fl4_dport = dport; -- cgit v1.2.3 From 5bc67a854cb4982aa7746e8d2206a00b46a9cc0f Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 11 Jul 2023 15:06:21 +0200 Subject: ipv6: Constify the sk parameter of several helper functions. icmpv6_flow_init(), ip6_datagram_flow_key_init() and ip6_mc_hdr() don't need to modify their sk argument. Make that explicit using const. Signed-off-by: Guillaume Nault Reviewed-by: Simon Horman Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 10 ++++------ net/ipv6/datagram.c | 7 ++++--- net/ipv6/icmp.c | 6 ++---- net/ipv6/mcast.c | 8 +++----- 4 files changed, 13 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index db0f4fcfdaf4..e3b3b0fa2a8f 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -85,12 +85,10 @@ extern void icmpv6_param_prob_reason(struct sk_buff *skb, struct flowi6; struct in6_addr; -extern void icmpv6_flow_init(struct sock *sk, - struct flowi6 *fl6, - u8 type, - const struct in6_addr *saddr, - const struct in6_addr *daddr, - int oif); + +void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type, + const struct in6_addr *saddr, + const struct in6_addr *daddr, int oif); static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 9b6818453afe..d80d6024cafa 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -38,10 +38,11 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a) return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0); } -static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk) +static void ip6_datagram_flow_key_init(struct flowi6 *fl6, + const struct sock *sk) { - struct inet_sock *inet = inet_sk(sk); - struct ipv6_pinfo *np = inet6_sk(sk); + const struct inet_sock *inet = inet_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); int oif = sk->sk_bound_dev_if; memset(fl6, 0, sizeof(*fl6)); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 65fa5014bc85..6d88f5248c1f 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -1034,11 +1034,9 @@ drop_no_count: return 0; } -void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6, - u8 type, +void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type, const struct in6_addr *saddr, - const struct in6_addr *daddr, - int oif) + const struct in6_addr *daddr, int oif) { memset(fl6, 0, sizeof(*fl6)); fl6->saddr = *saddr; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 714cdc9e2b8e..5ce25bcb9974 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1699,11 +1699,9 @@ mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) return scount; } -static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb, - struct net_device *dev, - const struct in6_addr *saddr, - const struct in6_addr *daddr, - int proto, int len) +static void ip6_mc_hdr(const struct sock *sk, struct sk_buff *skb, + struct net_device *dev, const struct in6_addr *saddr, + const struct in6_addr *daddr, int proto, int len) { struct ipv6hdr *hdr; -- cgit v1.2.3 From 90ef0a7b0622c62758b2638604927867775479ea Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 13 Jul 2023 09:42:07 +0100 Subject: net: phylink: add pcs_enable()/pcs_disable() methods Add phylink PCS enable/disable callbacks that will allow us to place IEEE 802.3 register compliant PCS in power-down mode while not being used. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 48 ++++++++++++++++++++++++++++++++++++++--------- include/linux/phylink.h | 16 ++++++++++++++++ 2 files changed, 55 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index d0aaa5cad853..748c62efceb8 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -34,6 +34,10 @@ enum { PHYLINK_DISABLE_STOPPED, PHYLINK_DISABLE_LINK, PHYLINK_DISABLE_MAC_WOL, + + PCS_STATE_DOWN = 0, + PCS_STATE_STARTING, + PCS_STATE_STARTED, }; /** @@ -72,6 +76,7 @@ struct phylink { struct phylink_link_state phy_state; struct work_struct resolve; unsigned int pcs_neg_mode; + unsigned int pcs_state; bool mac_link_dropped; bool using_mac_select_pcs; @@ -993,6 +998,22 @@ static void phylink_resolve_an_pause(struct phylink_link_state *state) } } +static void phylink_pcs_disable(struct phylink_pcs *pcs) +{ + if (pcs && pcs->ops->pcs_disable) + pcs->ops->pcs_disable(pcs); +} + +static int phylink_pcs_enable(struct phylink_pcs *pcs) +{ + int err = 0; + + if (pcs && pcs->ops->pcs_enable) + err = pcs->ops->pcs_enable(pcs); + + return err; +} + static int phylink_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, const struct phylink_link_state *state, bool permit_pause_to_mac) @@ -1095,11 +1116,17 @@ static void phylink_major_config(struct phylink *pl, bool restart, /* If we have a new PCS, switch to the new PCS after preparing the MAC * for the change. */ - if (pcs_changed) + if (pcs_changed) { + phylink_pcs_disable(pl->pcs); + pl->pcs = pcs; + } phylink_mac_config(pl, state); + if (pl->pcs_state == PCS_STATE_STARTING || pcs_changed) + phylink_pcs_enable(pl->pcs); + neg_mode = pl->cur_link_an_mode; if (pl->pcs && pl->pcs->neg_mode) neg_mode = pl->pcs_neg_mode; @@ -1586,6 +1613,7 @@ struct phylink *phylink_create(struct phylink_config *config, pl->link_config.pause = MLO_PAUSE_AN; pl->link_config.speed = SPEED_UNKNOWN; pl->link_config.duplex = DUPLEX_UNKNOWN; + pl->pcs_state = PCS_STATE_DOWN; pl->mac_ops = mac_ops; __set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); timer_setup(&pl->link_poll, phylink_fixed_poll, 0); @@ -1987,6 +2015,8 @@ void phylink_start(struct phylink *pl) if (pl->netdev) netif_carrier_off(pl->netdev); + pl->pcs_state = PCS_STATE_STARTING; + /* Apply the link configuration to the MAC when starting. This allows * a fixed-link to start with the correct parameters, and also * ensures that we set the appropriate advertisement for Serdes links. @@ -1997,6 +2027,8 @@ void phylink_start(struct phylink *pl) */ phylink_mac_initial_config(pl, true); + pl->pcs_state = PCS_STATE_STARTED; + phylink_enable_and_run_resolve(pl, PHYLINK_DISABLE_STOPPED); if (pl->cfg_link_an_mode == MLO_AN_FIXED && pl->link_gpio) { @@ -2015,15 +2047,9 @@ void phylink_start(struct phylink *pl) poll = true; } - switch (pl->cfg_link_an_mode) { - case MLO_AN_FIXED: + if (pl->cfg_link_an_mode == MLO_AN_FIXED) poll |= pl->config->poll_fixed_state; - break; - case MLO_AN_INBAND: - if (pl->pcs) - poll |= pl->pcs->poll; - break; - } + if (poll) mod_timer(&pl->link_poll, jiffies + HZ); if (pl->phydev) @@ -2060,6 +2086,10 @@ void phylink_stop(struct phylink *pl) } phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_STOPPED); + + pl->pcs_state = PCS_STATE_DOWN; + + phylink_pcs_disable(pl->pcs); } EXPORT_SYMBOL_GPL(phylink_stop); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 1817940a3418..8e2fdd48a935 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -535,6 +535,8 @@ struct phylink_pcs { /** * struct phylink_pcs_ops - MAC PCS operations structure. * @pcs_validate: validate the link configuration. + * @pcs_enable: enable the PCS. + * @pcs_disable: disable the PCS. * @pcs_get_state: read the current MAC PCS link state from the hardware. * @pcs_config: configure the MAC PCS for the selected mode and state. * @pcs_an_restart: restart 802.3z BaseX autonegotiation. @@ -544,6 +546,8 @@ struct phylink_pcs { struct phylink_pcs_ops { int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, const struct phylink_link_state *state); + int (*pcs_enable)(struct phylink_pcs *pcs); + void (*pcs_disable)(struct phylink_pcs *pcs); void (*pcs_get_state)(struct phylink_pcs *pcs, struct phylink_link_state *state); int (*pcs_config)(struct phylink_pcs *pcs, unsigned int neg_mode, @@ -573,6 +577,18 @@ struct phylink_pcs_ops { int pcs_validate(struct phylink_pcs *pcs, unsigned long *supported, const struct phylink_link_state *state); +/** + * pcs_enable() - enable the PCS. + * @pcs: a pointer to a &struct phylink_pcs. + */ +int pcs_enable(struct phylink_pcs *pcs); + +/** + * pcs_disable() - disable the PCS. + * @pcs: a pointer to a &struct phylink_pcs. + */ +void pcs_disable(struct phylink_pcs *pcs); + /** * pcs_get_state() - Read the current inband link state from the hardware * @pcs: a pointer to a &struct phylink_pcs. -- cgit v1.2.3 From aee6098822ed8a298ad817da8339ba4c7ea381fe Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 13 Jul 2023 09:42:12 +0100 Subject: net: phylink: add pcs_pre_config()/pcs_post_config() methods Add hooks that are called before and after the mac_config() call, which will be needed to deal with errata workarounds for the Marvell 88e639x DSA switches. Reviewed-by: Andrew Lunn Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 24 ++++++++++++++++++++++++ include/linux/phylink.h | 6 ++++++ 2 files changed, 30 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 748c62efceb8..9840a2952309 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -998,6 +998,24 @@ static void phylink_resolve_an_pause(struct phylink_link_state *state) } } +static void phylink_pcs_pre_config(struct phylink_pcs *pcs, + phy_interface_t interface) +{ + if (pcs && pcs->ops->pcs_pre_config) + pcs->ops->pcs_pre_config(pcs, interface); +} + +static int phylink_pcs_post_config(struct phylink_pcs *pcs, + phy_interface_t interface) +{ + int err = 0; + + if (pcs && pcs->ops->pcs_post_config) + err = pcs->ops->pcs_post_config(pcs, interface); + + return err; +} + static void phylink_pcs_disable(struct phylink_pcs *pcs) { if (pcs && pcs->ops->pcs_disable) @@ -1122,8 +1140,14 @@ static void phylink_major_config(struct phylink *pl, bool restart, pl->pcs = pcs; } + if (pl->pcs) + phylink_pcs_pre_config(pl->pcs, state->interface); + phylink_mac_config(pl, state); + if (pl->pcs) + phylink_pcs_post_config(pl->pcs, state->interface); + if (pl->pcs_state == PCS_STATE_STARTING || pcs_changed) phylink_pcs_enable(pl->pcs); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 8e2fdd48a935..99fc2fa60695 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -537,6 +537,8 @@ struct phylink_pcs { * @pcs_validate: validate the link configuration. * @pcs_enable: enable the PCS. * @pcs_disable: disable the PCS. + * @pcs_pre_config: pre-mac_config method (for errata) + * @pcs_post_config: post-mac_config method (for arrata) * @pcs_get_state: read the current MAC PCS link state from the hardware. * @pcs_config: configure the MAC PCS for the selected mode and state. * @pcs_an_restart: restart 802.3z BaseX autonegotiation. @@ -548,6 +550,10 @@ struct phylink_pcs_ops { const struct phylink_link_state *state); int (*pcs_enable)(struct phylink_pcs *pcs); void (*pcs_disable)(struct phylink_pcs *pcs); + void (*pcs_pre_config)(struct phylink_pcs *pcs, + phy_interface_t interface); + int (*pcs_post_config)(struct phylink_pcs *pcs, + phy_interface_t interface); void (*pcs_get_state)(struct phylink_pcs *pcs, struct phylink_link_state *state); int (*pcs_config)(struct phylink_pcs *pcs, unsigned int neg_mode, -- cgit v1.2.3 From 24699cc1ff3e633d7c3a0d3ef394243db11757ec Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 13 Jul 2023 09:42:17 +0100 Subject: net: phylink: add support for PCS link change notifications Add a function, phylink_pcs_change() which can be used by PCs drivers to notify phylink about changes to the PCS link state. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 38 ++++++++++++++++++++++++++++++++++---- include/linux/phylink.h | 7 +++++++ 2 files changed, 41 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 9840a2952309..71b1012ef3be 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1137,6 +1137,11 @@ static void phylink_major_config(struct phylink *pl, bool restart, if (pcs_changed) { phylink_pcs_disable(pl->pcs); + if (pl->pcs) + pl->pcs->phylink = NULL; + + pcs->phylink = pl; + pl->pcs = pcs; } @@ -1991,6 +1996,14 @@ void phylink_disconnect_phy(struct phylink *pl) } EXPORT_SYMBOL_GPL(phylink_disconnect_phy); +static void phylink_link_changed(struct phylink *pl, bool up, const char *what) +{ + if (!up) + pl->mac_link_dropped = true; + phylink_run_resolve(pl); + phylink_dbg(pl, "%s link %s\n", what, up ? "up" : "down"); +} + /** * phylink_mac_change() - notify phylink of a change in MAC state * @pl: a pointer to a &struct phylink returned from phylink_create() @@ -2001,13 +2014,30 @@ EXPORT_SYMBOL_GPL(phylink_disconnect_phy); */ void phylink_mac_change(struct phylink *pl, bool up) { - if (!up) - pl->mac_link_dropped = true; - phylink_run_resolve(pl); - phylink_dbg(pl, "mac link %s\n", up ? "up" : "down"); + phylink_link_changed(pl, up, "mac"); } EXPORT_SYMBOL_GPL(phylink_mac_change); +/** + * phylink_pcs_change() - notify phylink of a change to PCS link state + * @pcs: pointer to &struct phylink_pcs + * @up: indicates whether the link is currently up. + * + * The PCS driver should call this when the state of its link changes + * (e.g. link failure, new negotiation results, etc.) Note: it should + * not determine "up" by reading the BMSR. If in doubt about the link + * state at interrupt time, then pass true if pcs_get_state() returns + * the latched link-down state, otherwise pass false. + */ +void phylink_pcs_change(struct phylink_pcs *pcs, bool up) +{ + struct phylink *pl = pcs->phylink; + + if (pl) + phylink_link_changed(pl, up, "pcs"); +} +EXPORT_SYMBOL_GPL(phylink_pcs_change); + static irqreturn_t phylink_link_handler(int irq, void *data) { struct phylink *pl = data; diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 99fc2fa60695..b28aa3eef7d5 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -9,6 +9,7 @@ struct device_node; struct ethtool_cmd; struct fwnode_handle; struct net_device; +struct phylink; enum { MLO_PAUSE_NONE, @@ -520,14 +521,19 @@ struct phylink_pcs_ops; /** * struct phylink_pcs - PHYLINK PCS instance * @ops: a pointer to the &struct phylink_pcs_ops structure + * @phylink: pointer to &struct phylink_config * @neg_mode: provide PCS neg mode via "mode" argument * @poll: poll the PCS for link changes * * This structure is designed to be embedded within the PCS private data, * and will be passed between phylink and the PCS. + * + * The @phylink member is private to phylink and must not be touched by + * the PCS driver. */ struct phylink_pcs { const struct phylink_pcs_ops *ops; + struct phylink *phylink; bool neg_mode; bool poll; }; @@ -699,6 +705,7 @@ int phylink_fwnode_phy_connect(struct phylink *pl, void phylink_disconnect_phy(struct phylink *); void phylink_mac_change(struct phylink *, bool up); +void phylink_pcs_change(struct phylink_pcs *, bool up); void phylink_start(struct phylink *); void phylink_stop(struct phylink *); -- cgit v1.2.3 From e6a45700e7e19b1c945ee56feab429ff8489370b Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 13 Jul 2023 09:42:22 +0100 Subject: net: mdio: add unlocked mdiobus and mdiodev bus accessors Add the following unlocked accessors to complete the set: __mdiobus_modify() __mdiodev_read() __mdiodev_write() __mdiodev_modify() __mdiodev_modify_changed() which we will need for Marvell DSA PCS conversion. Reviewed-by: Andrew Lunn Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/mdio_bus.c | 24 ++++++++++++++++++++++-- include/linux/mdio.h | 26 ++++++++++++++++++++++++++ 2 files changed, 48 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 8b3618d3da4a..bc04048de2fa 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -1210,6 +1210,26 @@ int mdiobus_c45_write_nested(struct mii_bus *bus, int addr, int devad, } EXPORT_SYMBOL(mdiobus_c45_write_nested); +/* + * __mdiobus_modify - Convenience function for modifying a given mdio device + * register + * @bus: the mii_bus struct + * @addr: the phy address + * @regnum: register number to write + * @mask: bit mask of bits to clear + * @set: bit mask of bits to set + */ +int __mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, + u16 set) +{ + int err; + + err = __mdiobus_modify_changed(bus, addr, regnum, mask, set); + + return err < 0 ? err : 0; +} +EXPORT_SYMBOL_GPL(__mdiobus_modify); + /** * mdiobus_modify - Convenience function for modifying a given mdio device * register @@ -1224,10 +1244,10 @@ int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set) int err; mutex_lock(&bus->mdio_lock); - err = __mdiobus_modify_changed(bus, addr, regnum, mask, set); + err = __mdiobus_modify(bus, addr, regnum, mask, set); mutex_unlock(&bus->mdio_lock); - return err < 0 ? err : 0; + return err; } EXPORT_SYMBOL_GPL(mdiobus_modify); diff --git a/include/linux/mdio.h b/include/linux/mdio.h index c1b7008826e5..8fa23bdcedbf 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -537,6 +537,8 @@ static inline void mii_c73_mod_linkmode(unsigned long *adv, u16 *lpa) int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); +int __mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, + u16 set); int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set); @@ -564,6 +566,30 @@ int mdiobus_c45_modify(struct mii_bus *bus, int addr, int devad, u32 regnum, int mdiobus_c45_modify_changed(struct mii_bus *bus, int addr, int devad, u32 regnum, u16 mask, u16 set); +static inline int __mdiodev_read(struct mdio_device *mdiodev, u32 regnum) +{ + return __mdiobus_read(mdiodev->bus, mdiodev->addr, regnum); +} + +static inline int __mdiodev_write(struct mdio_device *mdiodev, u32 regnum, + u16 val) +{ + return __mdiobus_write(mdiodev->bus, mdiodev->addr, regnum, val); +} + +static inline int __mdiodev_modify(struct mdio_device *mdiodev, u32 regnum, + u16 mask, u16 set) +{ + return __mdiobus_modify(mdiodev->bus, mdiodev->addr, regnum, mask, set); +} + +static inline int __mdiodev_modify_changed(struct mdio_device *mdiodev, + u32 regnum, u16 mask, u16 set) +{ + return __mdiobus_modify_changed(mdiodev->bus, mdiodev->addr, regnum, + mask, set); +} + static inline int mdiodev_read(struct mdio_device *mdiodev, u32 regnum) { return mdiobus_read(mdiodev->bus, mdiodev->addr, regnum); -- cgit v1.2.3 From 9fa0bba012c2dd6d2b0db893314a4cc252a91b5f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 13 Jul 2023 15:19:05 -0700 Subject: net: phy: bcm7xxx: Add EPHY entry for 74165 74165 is a 16nm process SoC with a 10/100 integrated Ethernet PHY, utilize the recently defined 16nm EPHY macro to configure that PHY. Reviewed-by: Simon Horman Reviewed-by: Andrew Lunn Signed-off-by: Florian Fainelli Signed-off-by: Justin Chen Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 1 + include/linux/brcmphy.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index f8c17a253f8b..8478b081c058 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -913,6 +913,7 @@ static struct phy_driver bcm7xxx_driver[] = { BCM7XXX_28NM_GPHY(PHY_ID_BCM7278, "Broadcom BCM7278"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7364, "Broadcom BCM7364"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7366, "Broadcom BCM7366"), + BCM7XXX_16NM_EPHY(PHY_ID_BCM74165, "Broadcom BCM74165"), BCM7XXX_28NM_GPHY(PHY_ID_BCM74371, "Broadcom BCM74371"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7439, "Broadcom BCM7439"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7439_2, "Broadcom BCM7439 (2)"), diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 5d732f48f787..c55810a43541 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -44,6 +44,7 @@ #define PHY_ID_BCM7366 0x600d8490 #define PHY_ID_BCM7346 0x600d8650 #define PHY_ID_BCM7362 0x600d84b0 +#define PHY_ID_BCM74165 0x359052c0 #define PHY_ID_BCM7425 0x600d86b0 #define PHY_ID_BCM7429 0x600d8730 #define PHY_ID_BCM7435 0x600d8750 -- cgit v1.2.3 From a88dd7538461b2daf6883e5392957b21270638ed Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 14 Jul 2023 10:12:07 +0100 Subject: net: dsa: remove legacy_pre_march2020 detection All drivers are now updated for the March 2020 changes, and no longer make use of the mac_pcs_get_state() or mac_an_restart() operations, which are now NULL across all DSA drivers. All DSA drivers don't look at speed, duplex, pause or advertisement in their phylink_mac_config() method either. Remove support for these operations from DSA, and stop marking DSA as a legacy driver by default. Signed-off-by: Russell King (Oracle) Reviewed-by: Florian Fainelli Reviewed-by: Vladimir Oltean Signed-off-by: Paolo Abeni --- include/net/dsa.h | 3 --- net/dsa/port.c | 41 ----------------------------------------- 2 files changed, 44 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index d309ee7ed04b..0b9c6aa27047 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -873,8 +873,6 @@ struct dsa_switch_ops { struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds, int port, phy_interface_t iface); - int (*phylink_mac_link_state)(struct dsa_switch *ds, int port, - struct phylink_link_state *state); int (*phylink_mac_prepare)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); @@ -884,7 +882,6 @@ struct dsa_switch_ops { int (*phylink_mac_finish)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); - void (*phylink_mac_an_restart)(struct dsa_switch *ds, int port); void (*phylink_mac_link_down)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); diff --git a/net/dsa/port.c b/net/dsa/port.c index 0ce8fd311c78..c63cbfbe6489 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1568,27 +1568,6 @@ static void dsa_port_phylink_validate(struct phylink_config *config, phylink_generic_validate(config, supported, state); } -static void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) -{ - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); - struct dsa_switch *ds = dp->ds; - int err; - - /* Only called for inband modes */ - if (!ds->ops->phylink_mac_link_state) { - state->link = 0; - return; - } - - err = ds->ops->phylink_mac_link_state(ds, dp->index, state); - if (err < 0) { - dev_err(ds->dev, "p%d: phylink_mac_link_state() failed: %d\n", - dp->index, err); - state->link = 0; - } -} - static struct phylink_pcs * dsa_port_phylink_mac_select_pcs(struct phylink_config *config, phy_interface_t interface) @@ -1646,17 +1625,6 @@ static int dsa_port_phylink_mac_finish(struct phylink_config *config, return err; } -static void dsa_port_phylink_mac_an_restart(struct phylink_config *config) -{ - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->phylink_mac_an_restart) - return; - - ds->ops->phylink_mac_an_restart(ds, dp->index); -} - static void dsa_port_phylink_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) @@ -1700,11 +1668,9 @@ static void dsa_port_phylink_mac_link_up(struct phylink_config *config, static const struct phylink_mac_ops dsa_port_phylink_mac_ops = { .validate = dsa_port_phylink_validate, .mac_select_pcs = dsa_port_phylink_mac_select_pcs, - .mac_pcs_get_state = dsa_port_phylink_mac_pcs_get_state, .mac_prepare = dsa_port_phylink_mac_prepare, .mac_config = dsa_port_phylink_mac_config, .mac_finish = dsa_port_phylink_mac_finish, - .mac_an_restart = dsa_port_phylink_mac_an_restart, .mac_link_down = dsa_port_phylink_mac_link_down, .mac_link_up = dsa_port_phylink_mac_link_up, }; @@ -1720,13 +1686,6 @@ int dsa_port_phylink_create(struct dsa_port *dp) if (err) mode = PHY_INTERFACE_MODE_NA; - /* Presence of phylink_mac_link_state or phylink_mac_an_restart is - * an indicator of a legacy phylink driver. - */ - if (ds->ops->phylink_mac_link_state || - ds->ops->phylink_mac_an_restart) - dp->pl_config.legacy_pre_march2020 = true; - if (ds->ops->phylink_get_caps) ds->ops->phylink_get_caps(ds, dp->index, &dp->pl_config); -- cgit v1.2.3 From 76226787e137962750241bb29a9572dfc10d9eb1 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 14 Jul 2023 10:12:17 +0100 Subject: net: phylink: remove legacy mac_an_restart() method The mac_an_restart() method is now completely unused, and has been superseded by phylink_pcs support. Remove this method. Since phylink_pcs_mac_an_restart() now only deals with the PCS, rename the function to remove the _mac infix. Signed-off-by: Russell King (Oracle) Reviewed-by: Florian Fainelli Signed-off-by: Paolo Abeni --- drivers/net/phy/phylink.c | 22 +++++++++------------- include/linux/phylink.h | 12 ------------ 2 files changed, 9 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 71b1012ef3be..f07e496319b4 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1079,17 +1079,13 @@ static void phylink_mac_config(struct phylink *pl, pl->mac_ops->mac_config(pl->config, pl->cur_link_an_mode, state); } -static void phylink_mac_pcs_an_restart(struct phylink *pl) +static void phylink_pcs_an_restart(struct phylink *pl) { - if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - pl->link_config.advertising) && + if (pl->pcs && linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + pl->link_config.advertising) && phy_interface_mode_is_8023z(pl->link_config.interface) && - phylink_autoneg_inband(pl->cur_link_an_mode)) { - if (pl->pcs) - pl->pcs->ops->pcs_an_restart(pl->pcs); - else if (pl->config->legacy_pre_march2020) - pl->mac_ops->mac_an_restart(pl->config); - } + phylink_autoneg_inband(pl->cur_link_an_mode)) + pl->pcs->ops->pcs_an_restart(pl->pcs); } static void phylink_major_config(struct phylink *pl, bool restart, @@ -1169,7 +1165,7 @@ static void phylink_major_config(struct phylink *pl, bool restart, restart = true; if (restart) - phylink_mac_pcs_an_restart(pl); + phylink_pcs_an_restart(pl); if (pl->mac_ops->mac_finish) { err = pl->mac_ops->mac_finish(pl->config, pl->cur_link_an_mode, @@ -1205,7 +1201,7 @@ static int phylink_change_inband_advert(struct phylink *pl) if (!pl->pcs && pl->config->legacy_pre_march2020) { /* Legacy method */ phylink_mac_config(pl, &pl->link_config); - phylink_mac_pcs_an_restart(pl); + phylink_pcs_an_restart(pl); return 0; } @@ -1234,7 +1230,7 @@ static int phylink_change_inband_advert(struct phylink *pl) return ret; if (ret > 0) - phylink_mac_pcs_an_restart(pl); + phylink_pcs_an_restart(pl); return 0; } @@ -2533,7 +2529,7 @@ int phylink_ethtool_nway_reset(struct phylink *pl) if (pl->phydev) ret = phy_restart_aneg(pl->phydev); - phylink_mac_pcs_an_restart(pl); + phylink_pcs_an_restart(pl); return ret; } diff --git a/include/linux/phylink.h b/include/linux/phylink.h index b28aa3eef7d5..9e861c8316d0 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -234,7 +234,6 @@ struct phylink_config { * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. * @mac_finish: finish a major reconfiguration of the interface. - * @mac_an_restart: restart 802.3z BaseX autonegotiation. * @mac_link_down: take the link down. * @mac_link_up: allow the link to come up. * @@ -254,7 +253,6 @@ struct phylink_mac_ops { const struct phylink_link_state *state); int (*mac_finish)(struct phylink_config *config, unsigned int mode, phy_interface_t iface); - void (*mac_an_restart)(struct phylink_config *config); void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface); void (*mac_link_up)(struct phylink_config *config, @@ -459,16 +457,6 @@ void mac_config(struct phylink_config *config, unsigned int mode, int mac_finish(struct phylink_config *config, unsigned int mode, phy_interface_t iface); -/** - * mac_an_restart() - restart 802.3z BaseX autonegotiation - * @config: a pointer to a &struct phylink_config. - * - * Note: This is a legacy method. This function will not be called unless - * legacy_pre_march2020 is set in &struct phylink_config and there is no - * PCS attached. - */ -void mac_an_restart(struct phylink_config *config); - /** * mac_link_down() - take the link down * @config: a pointer to a &struct phylink_config. -- cgit v1.2.3 From 0a1f7bfe35a3e1302529fa900bf0574a5dfc8ea6 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Tue, 18 Jul 2023 01:38:09 -0700 Subject: bpf: Introduce internal definitions for UAPI-opaque bpf_{rb,list}_node Structs bpf_rb_node and bpf_list_node are opaquely defined in uapi/linux/bpf.h, as BPF program writers are not expected to touch their fields - nor does the verifier allow them to do so. Currently these structs are simple wrappers around structs rb_node and list_head and linked_list / rbtree implementation just casts and passes to library functions for those data structures. Later patches in this series, though, will add an "owner" field to bpf_{rb,list}_node, such that they're not just wrapping an underlying node type. Moreover, the bpf linked_list and rbtree implementations will deal with these owner pointers directly in a few different places. To avoid having to do void *owner = (void*)bpf_list_node + sizeof(struct list_head) with opaque UAPI node types, add bpf_{list,rb}_node_kern struct definitions to internal headers and modify linked_list and rbtree to use the internal types where appropriate. Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230718083813.3416104-3-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 10 ++++++++++ kernel/bpf/helpers.c | 23 +++++++++++++---------- 2 files changed, 23 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 360433f14496..511ed49c3fe9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -228,6 +228,16 @@ struct btf_record { struct btf_field fields[]; }; +/* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */ +struct bpf_rb_node_kern { + struct rb_node rb_node; +} __attribute__((aligned(8))); + +/* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */ +struct bpf_list_node_kern { + struct list_head list_head; +} __attribute__((aligned(8))); + struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9e80efa59a5d..d564ff97de0b 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1942,10 +1942,11 @@ __bpf_kfunc void *bpf_refcount_acquire_impl(void *p__refcounted_kptr, void *meta return (void *)p__refcounted_kptr; } -static int __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *head, +static int __bpf_list_add(struct bpf_list_node_kern *node, + struct bpf_list_head *head, bool tail, struct btf_record *rec, u64 off) { - struct list_head *n = (void *)node, *h = (void *)head; + struct list_head *n = &node->list_head, *h = (void *)head; /* If list_head was 0-initialized by map, bpf_obj_init_field wasn't * called on its fields, so init here @@ -1967,20 +1968,20 @@ __bpf_kfunc int bpf_list_push_front_impl(struct bpf_list_head *head, struct bpf_list_node *node, void *meta__ign, u64 off) { + struct bpf_list_node_kern *n = (void *)node; struct btf_struct_meta *meta = meta__ign; - return __bpf_list_add(node, head, false, - meta ? meta->record : NULL, off); + return __bpf_list_add(n, head, false, meta ? meta->record : NULL, off); } __bpf_kfunc int bpf_list_push_back_impl(struct bpf_list_head *head, struct bpf_list_node *node, void *meta__ign, u64 off) { + struct bpf_list_node_kern *n = (void *)node; struct btf_struct_meta *meta = meta__ign; - return __bpf_list_add(node, head, true, - meta ? meta->record : NULL, off); + return __bpf_list_add(n, head, true, meta ? meta->record : NULL, off); } static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tail) @@ -2013,7 +2014,7 @@ __bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root, struct bpf_rb_node *node) { struct rb_root_cached *r = (struct rb_root_cached *)root; - struct rb_node *n = (struct rb_node *)node; + struct rb_node *n = &((struct bpf_rb_node_kern *)node)->rb_node; if (RB_EMPTY_NODE(n)) return NULL; @@ -2026,11 +2027,12 @@ __bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root, /* Need to copy rbtree_add_cached's logic here because our 'less' is a BPF * program */ -static int __bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node, +static int __bpf_rbtree_add(struct bpf_rb_root *root, + struct bpf_rb_node_kern *node, void *less, struct btf_record *rec, u64 off) { struct rb_node **link = &((struct rb_root_cached *)root)->rb_root.rb_node; - struct rb_node *parent = NULL, *n = (struct rb_node *)node; + struct rb_node *parent = NULL, *n = &node->rb_node; bpf_callback_t cb = (bpf_callback_t)less; bool leftmost = true; @@ -2060,8 +2062,9 @@ __bpf_kfunc int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node void *meta__ign, u64 off) { struct btf_struct_meta *meta = meta__ign; + struct bpf_rb_node_kern *n = (void *)node; - return __bpf_rbtree_add(root, node, (void *)less, meta ? meta->record : NULL, off); + return __bpf_rbtree_add(root, n, (void *)less, meta ? meta->record : NULL, off); } __bpf_kfunc struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) -- cgit v1.2.3 From c3c510ce431cd99fa10dcd50d995c8e89330ee5b Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Tue, 18 Jul 2023 01:38:10 -0700 Subject: bpf: Add 'owner' field to bpf_{list,rb}_node As described by Kumar in [0], in shared ownership scenarios it is necessary to do runtime tracking of {rb,list} node ownership - and synchronize updates using this ownership information - in order to prevent races. This patch adds an 'owner' field to struct bpf_list_node and bpf_rb_node to implement such runtime tracking. The owner field is a void * that describes the ownership state of a node. It can have the following values: NULL - the node is not owned by any data structure BPF_PTR_POISON - the node is in the process of being added to a data structure ptr_to_root - the pointee is a data structure 'root' (bpf_rb_root / bpf_list_head) which owns this node The field is initially NULL (set by bpf_obj_init_field default behavior) and transitions states in the following sequence: Insertion: NULL -> BPF_PTR_POISON -> ptr_to_root Removal: ptr_to_root -> NULL Before a node has been successfully inserted, it is not protected by any root's lock, and therefore two programs can attempt to add the same node to different roots simultaneously. For this reason the intermediate BPF_PTR_POISON state is necessary. For removal, the node is protected by some root's lock so this intermediate hop isn't necessary. Note that bpf_list_pop_{front,back} helpers don't need to check owner before removing as the node-to-be-removed is not passed in as input and is instead taken directly from the list. Do the check anyways and WARN_ON_ONCE in this unexpected scenario. Selftest changes in this patch are entirely mechanical: some BTF tests have hardcoded struct sizes for structs that contain bpf_{list,rb}_node fields, those were adjusted to account for the new sizes. Selftest additions to validate the owner field are added in a further patch in the series. [0]: https://lore.kernel.org/bpf/d7hyspcow5wtjcmw4fugdgyp3fwhljwuscp3xyut5qnwivyeru@ysdq543otzv2 Signed-off-by: Dave Marchevsky Suggested-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20230718083813.3416104-4-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 + include/uapi/linux/bpf.h | 2 + kernel/bpf/helpers.c | 29 ++++++-- .../testing/selftests/bpf/prog_tests/linked_list.c | 78 +++++++++++----------- 4 files changed, 68 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 511ed49c3fe9..ceaa8c23287f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -231,11 +231,13 @@ struct btf_record { /* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */ struct bpf_rb_node_kern { struct rb_node rb_node; + void *owner; } __attribute__((aligned(8))); /* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */ struct bpf_list_node_kern { struct list_head list_head; + void *owner; } __attribute__((aligned(8))); struct bpf_map { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 600d0caebbd8..9ed59896ebc5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -7052,6 +7052,7 @@ struct bpf_list_head { struct bpf_list_node { __u64 :64; __u64 :64; + __u64 :64; } __attribute__((aligned(8))); struct bpf_rb_root { @@ -7063,6 +7064,7 @@ struct bpf_rb_node { __u64 :64; __u64 :64; __u64 :64; + __u64 :64; } __attribute__((aligned(8))); struct bpf_refcount { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index d564ff97de0b..bcff584985e7 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1953,13 +1953,18 @@ static int __bpf_list_add(struct bpf_list_node_kern *node, */ if (unlikely(!h->next)) INIT_LIST_HEAD(h); - if (!list_empty(n)) { + + /* node->owner != NULL implies !list_empty(n), no need to separately + * check the latter + */ + if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) { /* Only called from BPF prog, no need to migrate_disable */ __bpf_obj_drop_impl((void *)n - off, rec); return -EINVAL; } tail ? list_add_tail(n, h) : list_add(n, h); + WRITE_ONCE(node->owner, head); return 0; } @@ -1987,6 +1992,7 @@ __bpf_kfunc int bpf_list_push_back_impl(struct bpf_list_head *head, static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tail) { struct list_head *n, *h = (void *)head; + struct bpf_list_node_kern *node; /* If list_head was 0-initialized by map, bpf_obj_init_field wasn't * called on its fields, so init here @@ -1995,8 +2001,14 @@ static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tai INIT_LIST_HEAD(h); if (list_empty(h)) return NULL; + n = tail ? h->prev : h->next; + node = container_of(n, struct bpf_list_node_kern, list_head); + if (WARN_ON_ONCE(READ_ONCE(node->owner) != head)) + return NULL; + list_del_init(n); + WRITE_ONCE(node->owner, NULL); return (struct bpf_list_node *)n; } @@ -2013,14 +2025,19 @@ __bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) __bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root, struct bpf_rb_node *node) { + struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node; struct rb_root_cached *r = (struct rb_root_cached *)root; - struct rb_node *n = &((struct bpf_rb_node_kern *)node)->rb_node; + struct rb_node *n = &node_internal->rb_node; - if (RB_EMPTY_NODE(n)) + /* node_internal->owner != root implies either RB_EMPTY_NODE(n) or + * n is owned by some other tree. No need to check RB_EMPTY_NODE(n) + */ + if (READ_ONCE(node_internal->owner) != root) return NULL; rb_erase_cached(n, r); RB_CLEAR_NODE(n); + WRITE_ONCE(node_internal->owner, NULL); return (struct bpf_rb_node *)n; } @@ -2036,7 +2053,10 @@ static int __bpf_rbtree_add(struct bpf_rb_root *root, bpf_callback_t cb = (bpf_callback_t)less; bool leftmost = true; - if (!RB_EMPTY_NODE(n)) { + /* node->owner != NULL implies !RB_EMPTY_NODE(n), no need to separately + * check the latter + */ + if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) { /* Only called from BPF prog, no need to migrate_disable */ __bpf_obj_drop_impl((void *)n - off, rec); return -EINVAL; @@ -2054,6 +2074,7 @@ static int __bpf_rbtree_add(struct bpf_rb_root *root, rb_link_node(n, parent, link); rb_insert_color_cached(n, (struct rb_root_cached *)root, leftmost); + WRITE_ONCE(node->owner, root); return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c index f63309fd0e28..18cf7b17463d 100644 --- a/tools/testing/selftests/bpf/prog_tests/linked_list.c +++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c @@ -23,7 +23,7 @@ static struct { "bpf_spin_lock at off=" #off " must be held for bpf_list_head" }, \ { #test "_missing_lock_pop_back", \ "bpf_spin_lock at off=" #off " must be held for bpf_list_head" }, - TEST(kptr, 32) + TEST(kptr, 40) TEST(global, 16) TEST(map, 0) TEST(inner_map, 0) @@ -31,7 +31,7 @@ static struct { #define TEST(test, op) \ { #test "_kptr_incorrect_lock_" #op, \ "held lock and object are not in the same allocation\n" \ - "bpf_spin_lock at off=32 must be held for bpf_list_head" }, \ + "bpf_spin_lock at off=40 must be held for bpf_list_head" }, \ { #test "_global_incorrect_lock_" #op, \ "held lock and object are not in the same allocation\n" \ "bpf_spin_lock at off=16 must be held for bpf_list_head" }, \ @@ -84,23 +84,23 @@ static struct { { "double_push_back", "arg#1 expected pointer to allocated object" }, { "no_node_value_type", "bpf_list_node not found at offset=0" }, { "incorrect_value_type", - "operation on bpf_list_head expects arg#1 bpf_list_node at offset=40 in struct foo, " + "operation on bpf_list_head expects arg#1 bpf_list_node at offset=48 in struct foo, " "but arg is at offset=0 in struct bar" }, { "incorrect_node_var_off", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" }, - { "incorrect_node_off1", "bpf_list_node not found at offset=41" }, - { "incorrect_node_off2", "arg#1 offset=0, but expected bpf_list_node at offset=40 in struct foo" }, + { "incorrect_node_off1", "bpf_list_node not found at offset=49" }, + { "incorrect_node_off2", "arg#1 offset=0, but expected bpf_list_node at offset=48 in struct foo" }, { "no_head_type", "bpf_list_head not found at offset=0" }, { "incorrect_head_var_off1", "R1 doesn't have constant offset" }, { "incorrect_head_var_off2", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" }, - { "incorrect_head_off1", "bpf_list_head not found at offset=17" }, + { "incorrect_head_off1", "bpf_list_head not found at offset=25" }, { "incorrect_head_off2", "bpf_list_head not found at offset=1" }, { "pop_front_off", - "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) " - "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) refs=2,4\n" + "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) " + "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n" "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" }, { "pop_back_off", - "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) " - "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) refs=2,4\n" + "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) " + "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n" "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" }, }; @@ -257,7 +257,7 @@ static struct btf *init_btf(void) hid = btf__add_struct(btf, "bpf_list_head", 16); if (!ASSERT_EQ(hid, LIST_HEAD, "btf__add_struct bpf_list_head")) goto end; - nid = btf__add_struct(btf, "bpf_list_node", 16); + nid = btf__add_struct(btf, "bpf_list_node", 24); if (!ASSERT_EQ(nid, LIST_NODE, "btf__add_struct bpf_list_node")) goto end; return btf; @@ -276,7 +276,7 @@ static void list_and_rb_node_same_struct(bool refcount_field) if (!ASSERT_OK_PTR(btf, "init_btf")) return; - bpf_rb_node_btf_id = btf__add_struct(btf, "bpf_rb_node", 24); + bpf_rb_node_btf_id = btf__add_struct(btf, "bpf_rb_node", 32); if (!ASSERT_GT(bpf_rb_node_btf_id, 0, "btf__add_struct bpf_rb_node")) return; @@ -286,17 +286,17 @@ static void list_and_rb_node_same_struct(bool refcount_field) return; } - id = btf__add_struct(btf, "bar", refcount_field ? 44 : 40); + id = btf__add_struct(btf, "bar", refcount_field ? 60 : 56); if (!ASSERT_GT(id, 0, "btf__add_struct bar")) return; err = btf__add_field(btf, "a", LIST_NODE, 0, 0); if (!ASSERT_OK(err, "btf__add_field bar::a")) return; - err = btf__add_field(btf, "c", bpf_rb_node_btf_id, 128, 0); + err = btf__add_field(btf, "c", bpf_rb_node_btf_id, 192, 0); if (!ASSERT_OK(err, "btf__add_field bar::c")) return; if (refcount_field) { - err = btf__add_field(btf, "ref", bpf_refcount_btf_id, 320, 0); + err = btf__add_field(btf, "ref", bpf_refcount_btf_id, 448, 0); if (!ASSERT_OK(err, "btf__add_field bar::ref")) return; } @@ -527,7 +527,7 @@ static void test_btf(void) btf = init_btf(); if (!ASSERT_OK_PTR(btf, "init_btf")) break; - id = btf__add_struct(btf, "foo", 36); + id = btf__add_struct(btf, "foo", 44); if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -536,7 +536,7 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field foo::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field foo::c")) break; id = btf__add_decl_tag(btf, "contains:foo:b", 5, 0); @@ -553,7 +553,7 @@ static void test_btf(void) btf = init_btf(); if (!ASSERT_OK_PTR(btf, "init_btf")) break; - id = btf__add_struct(btf, "foo", 36); + id = btf__add_struct(btf, "foo", 44); if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -562,13 +562,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field foo::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field foo::c")) break; id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) break; - id = btf__add_struct(btf, "bar", 36); + id = btf__add_struct(btf, "bar", 44); if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -577,7 +577,7 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field bar::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field bar::c")) break; id = btf__add_decl_tag(btf, "contains:foo:b", 7, 0); @@ -594,19 +594,19 @@ static void test_btf(void) btf = init_btf(); if (!ASSERT_OK_PTR(btf, "init_btf")) break; - id = btf__add_struct(btf, "foo", 20); + id = btf__add_struct(btf, "foo", 28); if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); if (!ASSERT_OK(err, "btf__add_field foo::a")) break; - err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0); + err = btf__add_field(btf, "b", SPIN_LOCK, 192, 0); if (!ASSERT_OK(err, "btf__add_field foo::b")) break; id = btf__add_decl_tag(btf, "contains:bar:a", 5, 0); if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:a")) break; - id = btf__add_struct(btf, "bar", 16); + id = btf__add_struct(btf, "bar", 24); if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) break; err = btf__add_field(btf, "a", LIST_NODE, 0, 0); @@ -623,19 +623,19 @@ static void test_btf(void) btf = init_btf(); if (!ASSERT_OK_PTR(btf, "init_btf")) break; - id = btf__add_struct(btf, "foo", 20); + id = btf__add_struct(btf, "foo", 28); if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); if (!ASSERT_OK(err, "btf__add_field foo::a")) break; - err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0); + err = btf__add_field(btf, "b", SPIN_LOCK, 192, 0); if (!ASSERT_OK(err, "btf__add_field foo::b")) break; id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) break; - id = btf__add_struct(btf, "bar", 36); + id = btf__add_struct(btf, "bar", 44); if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -644,13 +644,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field bar::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field bar::c")) break; id = btf__add_decl_tag(btf, "contains:baz:a", 7, 0); if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:baz:a")) break; - id = btf__add_struct(btf, "baz", 16); + id = btf__add_struct(btf, "baz", 24); if (!ASSERT_EQ(id, 9, "btf__add_struct baz")) break; err = btf__add_field(btf, "a", LIST_NODE, 0, 0); @@ -667,7 +667,7 @@ static void test_btf(void) btf = init_btf(); if (!ASSERT_OK_PTR(btf, "init_btf")) break; - id = btf__add_struct(btf, "foo", 36); + id = btf__add_struct(btf, "foo", 44); if (!ASSERT_EQ(id, 5, "btf__add_struct foo")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -676,13 +676,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field foo::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field foo::c")) break; id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) break; - id = btf__add_struct(btf, "bar", 36); + id = btf__add_struct(btf, "bar", 44); if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -691,13 +691,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field bar:b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field bar:c")) break; id = btf__add_decl_tag(btf, "contains:baz:a", 7, 0); if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:baz:a")) break; - id = btf__add_struct(btf, "baz", 16); + id = btf__add_struct(btf, "baz", 24); if (!ASSERT_EQ(id, 9, "btf__add_struct baz")) break; err = btf__add_field(btf, "a", LIST_NODE, 0, 0); @@ -726,7 +726,7 @@ static void test_btf(void) id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0); if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b")) break; - id = btf__add_struct(btf, "bar", 36); + id = btf__add_struct(btf, "bar", 44); if (!ASSERT_EQ(id, 7, "btf__add_struct bar")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -735,13 +735,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field bar::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field bar::c")) break; id = btf__add_decl_tag(btf, "contains:baz:b", 7, 0); if (!ASSERT_EQ(id, 8, "btf__add_decl_tag")) break; - id = btf__add_struct(btf, "baz", 36); + id = btf__add_struct(btf, "baz", 44); if (!ASSERT_EQ(id, 9, "btf__add_struct baz")) break; err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); @@ -750,13 +750,13 @@ static void test_btf(void) err = btf__add_field(btf, "b", LIST_NODE, 128, 0); if (!ASSERT_OK(err, "btf__add_field bar::b")) break; - err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0); + err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0); if (!ASSERT_OK(err, "btf__add_field bar::c")) break; id = btf__add_decl_tag(btf, "contains:bam:a", 9, 0); if (!ASSERT_EQ(id, 10, "btf__add_decl_tag contains:bam:a")) break; - id = btf__add_struct(btf, "bam", 16); + id = btf__add_struct(btf, "bam", 24); if (!ASSERT_EQ(id, 11, "btf__add_struct bam")) break; err = btf__add_field(btf, "a", LIST_NODE, 0, 0); -- cgit v1.2.3 From dfa2f0483360d4d6f2324405464c9f281156bd87 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 Jul 2023 15:29:17 +0000 Subject: tcp: get rid of sysctl_tcp_adv_win_scale With modern NIC drivers shifting to full page allocations per received frame, we face the following issue: TCP has one per-netns sysctl used to tweak how to translate a memory use into an expected payload (RWIN), in RX path. tcp_win_from_space() implementation is limited to few cases. For hosts dealing with various MSS, we either under estimate or over estimate the RWIN we send to the remote peers. For instance with the default sysctl_tcp_adv_win_scale value, we expect to store 50% of payload per allocated chunk of memory. For the typical use of MTU=1500 traffic, and order-0 pages allocations by NIC drivers, we are sending too big RWIN, leading to potential tcp collapse operations, which are extremely expensive and source of latency spikes. This patch makes sysctl_tcp_adv_win_scale obsolete, and instead uses a per socket scaling factor, so that we can precisely adjust the RWIN based on effective skb->len/skb->truesize ratio. This patch alone can double TCP receive performance when receivers are too slow to drain their receive queue, or by allowing a bigger RWIN when MSS is close to PAGE_SIZE. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Link: https://lore.kernel.org/r/20230717152917.751987-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ip-sysctl.rst | 1 + include/linux/tcp.h | 4 +++- include/net/netns/ipv4.h | 2 +- include/net/tcp.h | 24 ++++++++++++++++++++---- net/ipv4/tcp.c | 11 ++++++----- net/ipv4/tcp_input.c | 19 ++++++++++++------- 6 files changed, 43 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 4a010a7cde7f..82f2117cf2b3 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -321,6 +321,7 @@ tcp_abort_on_overflow - BOOLEAN option can harm clients of your server. tcp_adv_win_scale - INTEGER + Obsolete since linux-6.6 Count buffering overhead as bytes/2^tcp_adv_win_scale (if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale), if it is <= 0. diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b4c08ac86983..fbcb0ce13171 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -172,6 +172,8 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) return (struct tcp_request_sock *)req; } +#define TCP_RMEM_TO_WIN_SCALE 8 + struct tcp_sock { /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; @@ -238,7 +240,7 @@ struct tcp_sock { u32 window_clamp; /* Maximal window to advertise */ u32 rcv_ssthresh; /* Current window clamp */ - + u8 scaling_ratio; /* see tcp_win_from_space() */ /* Information of the most recently (s)acked skb */ struct tcp_rack { u64 mstamp; /* (Re)sent time of the skb */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index f00374718159..7a41c4791536 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -152,7 +152,7 @@ struct netns_ipv4 { u8 sysctl_tcp_abort_on_overflow; u8 sysctl_tcp_fack; /* obsolete */ int sysctl_tcp_max_reordering; - int sysctl_tcp_adv_win_scale; + int sysctl_tcp_adv_win_scale; /* obsolete */ u8 sysctl_tcp_dsack; u8 sysctl_tcp_app_win; u8 sysctl_tcp_frto; diff --git a/include/net/tcp.h b/include/net/tcp.h index 226bce6d1e8c..2104a71c75ba 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1434,11 +1434,27 @@ void tcp_select_initial_window(const struct sock *sk, int __space, static inline int tcp_win_from_space(const struct sock *sk, int space) { - int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale); + s64 scaled_space = (s64)space * tcp_sk(sk)->scaling_ratio; - return tcp_adv_win_scale <= 0 ? - (space>>(-tcp_adv_win_scale)) : - space - (space>>tcp_adv_win_scale); + return scaled_space >> TCP_RMEM_TO_WIN_SCALE; +} + +/* inverse of tcp_win_from_space() */ +static inline int tcp_space_from_win(const struct sock *sk, int win) +{ + u64 val = (u64)win << TCP_RMEM_TO_WIN_SCALE; + + do_div(val, tcp_sk(sk)->scaling_ratio); + return val; +} + +static inline void tcp_scaling_ratio_init(struct sock *sk) +{ + /* Assume a conservative default of 1200 bytes of payload per 4K page. + * This may be adjusted later in tcp_measure_rcv_mss(). + */ + tcp_sk(sk)->scaling_ratio = (1200 << TCP_RMEM_TO_WIN_SCALE) / + SKB_TRUESIZE(4096); } /* Note: caller must be prepared to deal with negative returns */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e03e08745308..88f4ebab12ac 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -457,6 +457,7 @@ void tcp_init_sock(struct sock *sk) WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1])); WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1])); + tcp_scaling_ratio_init(sk); set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); @@ -1700,7 +1701,7 @@ EXPORT_SYMBOL(tcp_peek_len); /* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ int tcp_set_rcvlowat(struct sock *sk, int val) { - int cap; + int space, cap; if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) cap = sk->sk_rcvbuf >> 1; @@ -1715,10 +1716,10 @@ int tcp_set_rcvlowat(struct sock *sk, int val) if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) return 0; - val <<= 1; - if (val > sk->sk_rcvbuf) { - WRITE_ONCE(sk->sk_rcvbuf, val); - tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); + space = tcp_space_from_win(sk, val); + if (space > sk->sk_rcvbuf) { + WRITE_ONCE(sk->sk_rcvbuf, space); + tcp_sk(sk)->window_clamp = val; } return 0; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 57c8af1859c1..3cd92035e090 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -237,6 +237,16 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) */ len = skb_shinfo(skb)->gso_size ? : skb->len; if (len >= icsk->icsk_ack.rcv_mss) { + /* Note: divides are still a bit expensive. + * For the moment, only adjust scaling_ratio + * when we update icsk_ack.rcv_mss. + */ + if (unlikely(len != icsk->icsk_ack.rcv_mss)) { + u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE; + + do_div(val, skb->truesize); + tcp_sk(sk)->scaling_ratio = val ? val : 1; + } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); /* Account for possibly-removed options */ @@ -727,8 +737,8 @@ void tcp_rcv_space_adjust(struct sock *sk) if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - int rcvmem, rcvbuf; u64 rcvwin, grow; + int rcvbuf; /* minimal window to cope with packet losses, assuming * steady state. Add some cushion because of small variations. @@ -740,12 +750,7 @@ void tcp_rcv_space_adjust(struct sock *sk) do_div(grow, tp->rcvq_space.space); rcvwin += (grow << 1); - rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER); - while (tcp_win_from_space(sk, rcvmem) < tp->advmss) - rcvmem += 128; - - do_div(rcvwin, tp->advmss); - rcvbuf = min_t(u64, rcvwin * rcvmem, + rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); if (rcvbuf > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); -- cgit v1.2.3 From 8bb5e82589f0141a990d3fd21d5b79a73a8c6c7b Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 17 Jul 2023 11:12:26 +0300 Subject: ip_tunnels: Add nexthop ID field to ip_tunnel_key Extend the ip_tunnel_key structure with a field indicating the ID of the nexthop object via which the skb should be routed. The field is going to be populated in subsequent patches by the bridge driver in order to indicate to the VXLAN driver which FDB nexthop object to use in order to reach the target host. Signed-off-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index ed4b6ad3fcac..e8750b4ef7e1 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -52,6 +52,7 @@ struct ip_tunnel_key { u8 tos; /* TOS for IPv4, TC for IPv6 */ u8 ttl; /* TTL for IPv4, HL for IPv6 */ __be32 label; /* Flow Label for IPv6 */ + u32 nhid; __be16 tp_src; __be16 tp_dst; __u8 flow_flags; -- cgit v1.2.3 From 29cfb2aaa4425a608651a05b9b875bc445394443 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 17 Jul 2023 11:12:28 +0300 Subject: bridge: Add backup nexthop ID support Add a new bridge port attribute that allows attaching a nexthop object ID to an skb that is redirected to a backup bridge port with VLAN tunneling enabled. Specifically, when redirecting a known unicast packet, read the backup nexthop ID from the bridge port that lost its carrier and set it in the bridge control block of the skb before forwarding it via the backup port. Note that reading the ID from the bridge port should not result in a cache miss as the ID is added next to the 'backup_port' field that was already accessed. After this change, the 'state' field still stays on the first cache line, together with other data path related fields such as 'flags and 'vlgrp': struct net_bridge_port { struct net_bridge * br; /* 0 8 */ struct net_device * dev; /* 8 8 */ netdevice_tracker dev_tracker; /* 16 0 */ struct list_head list; /* 16 16 */ long unsigned int flags; /* 32 8 */ struct net_bridge_vlan_group * vlgrp; /* 40 8 */ struct net_bridge_port * backup_port; /* 48 8 */ u32 backup_nhid; /* 56 4 */ u8 priority; /* 60 1 */ u8 state; /* 61 1 */ u16 port_no; /* 62 2 */ /* --- cacheline 1 boundary (64 bytes) --- */ [...] } __attribute__((__aligned__(8))); When forwarding an skb via a bridge port that has VLAN tunneling enabled, check if the backup nexthop ID stored in the bridge control block is valid (i.e., not zero). If so, instead of attaching the pre-allocated metadata (that only has the tunnel key set), allocate a new metadata, set both the tunnel key and the nexthop object ID and attach it to the skb. By default, do not dump the new attribute to user space as a value of zero is an invalid nexthop object ID. The above is useful for EVPN multihoming. When one of the links composing an Ethernet Segment (ES) fails, traffic needs to be redirected towards the host via one of the other ES peers. For example, if a host is multihomed to three different VTEPs, the backup port of each ES link needs to be set to the VXLAN device and the backup nexthop ID needs to point to an FDB nexthop group that includes the IP addresses of the other two VTEPs. The VXLAN driver will extract the ID from the metadata of the redirected skb, calculate its flow hash and forward it towards one of the other VTEPs. If the ID does not exist, or represents an invalid nexthop object, the VXLAN driver will drop the skb. This relieves the bridge driver from the need to validate the ID. Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_forward.c | 1 + net/bridge/br_netlink.c | 12 ++++++++++++ net/bridge/br_private.h | 3 +++ net/bridge/br_vlan_tunnel.c | 15 +++++++++++++++ net/core/rtnetlink.c | 2 +- 6 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 0f6a0fe09bdb..ce3117df9cec 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -570,6 +570,7 @@ enum { IFLA_BRPORT_MCAST_N_GROUPS, IFLA_BRPORT_MCAST_MAX_GROUPS, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, + IFLA_BRPORT_BACKUP_NHID, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 6116eba1bd89..9d7bc8b96b53 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -154,6 +154,7 @@ void br_forward(const struct net_bridge_port *to, backup_port = rcu_dereference(to->backup_port); if (unlikely(!backup_port)) goto out; + BR_INPUT_SKB_CB(skb)->backup_nhid = READ_ONCE(to->backup_nhid); to = backup_port; } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 05c5863d2e20..10f0d33d8ccf 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -211,6 +211,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_IN_OPEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_CNT */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_BACKUP_NHID */ + 0; } @@ -319,6 +320,10 @@ static int br_port_fill_attrs(struct sk_buff *skb, backup_p->dev->ifindex); rcu_read_unlock(); + if (p->backup_nhid && + nla_put_u32(skb, IFLA_BRPORT_BACKUP_NHID, p->backup_nhid)) + return -EMSGSIZE; + return 0; } @@ -895,6 +900,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT }, [IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, [IFLA_BRPORT_NEIGH_VLAN_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1), + [IFLA_BRPORT_BACKUP_NHID] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ @@ -1065,6 +1071,12 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], return err; } + if (tb[IFLA_BRPORT_BACKUP_NHID]) { + u32 backup_nhid = nla_get_u32(tb[IFLA_BRPORT_BACKUP_NHID]); + + WRITE_ONCE(p->backup_nhid, backup_nhid); + } + return 0; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index a63b32c1638e..05a965ef76f1 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -387,6 +387,7 @@ struct net_bridge_port { struct net_bridge_vlan_group __rcu *vlgrp; #endif struct net_bridge_port __rcu *backup_port; + u32 backup_nhid; /* STP */ u8 priority; @@ -605,6 +606,8 @@ struct br_input_skb_cb { */ unsigned long fwd_hwdoms; #endif + + u32 backup_nhid; }; #define BR_INPUT_SKB_CB(__skb) ((struct br_input_skb_cb *)(__skb)->cb) diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 6399a8a69d07..81833ca7a2c7 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -201,6 +201,21 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, if (err) return err; + if (BR_INPUT_SKB_CB(skb)->backup_nhid) { + tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, + tunnel_id, 0); + if (!tunnel_dst) + return -ENOMEM; + + tunnel_dst->u.tun_info.mode |= IP_TUNNEL_INFO_TX | + IP_TUNNEL_INFO_BRIDGE; + tunnel_dst->u.tun_info.key.nhid = + BR_INPUT_SKB_CB(skb)->backup_nhid; + skb_dst_set(skb, &tunnel_dst->dst); + + return 0; + } + tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst); if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst)) skb_dst_set(skb, &tunnel_dst->dst); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 70838d7e5b32..1777a5e1830b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -61,7 +61,7 @@ #include "dev.h" #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 43 +#define RTNL_SLAVE_MAX_TYPE 44 struct rtnl_link { rtnl_doit_func doit; -- cgit v1.2.3 From 5ba190c29cf92f157bd63c9909c7050d6dc43df7 Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Wed, 19 Jul 2023 09:29:50 +0000 Subject: bpf: consider CONST_PTR_TO_MAP as trusted pointer to struct bpf_map Add the BTF id of struct bpf_map to the reg2btf_ids array. This makes the values of the CONST_PTR_TO_MAP type to be considered as trusted by kfuncs. This, in turn, allows users to execute trusted kfuncs which accept `struct bpf_map *` arguments from non-tracing programs. While exporting the btf_bpf_map_id variable, save some bytes by defining it as BTF_ID_LIST_GLOBAL_SINGLE (which is u32[1]) and not as BTF_ID_LIST (which is u32[64]). Signed-off-by: Anton Protopopov Link: https://lore.kernel.org/r/20230719092952.41202-3-aspsk@isovalent.com Signed-off-by: Alexei Starovoitov --- include/linux/btf_ids.h | 1 + kernel/bpf/map_iter.c | 3 +-- kernel/bpf/verifier.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 00950cc03bff..a3462a9b8e18 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -267,5 +267,6 @@ MAX_BTF_TRACING_TYPE, extern u32 btf_tracing_ids[]; extern u32 bpf_cgroup_btf_id[]; extern u32 bpf_local_storage_map_btf_id[]; +extern u32 btf_bpf_map_id[]; #endif diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index d06d3b7150e5..b67996147895 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -78,8 +78,7 @@ static const struct seq_operations bpf_map_seq_ops = { .show = bpf_map_seq_show, }; -BTF_ID_LIST(btf_bpf_map_id) -BTF_ID(struct, bpf_map) +BTF_ID_LIST_GLOBAL_SINGLE(btf_bpf_map_id, struct, bpf_map) static const struct bpf_iter_seq_info bpf_map_seq_info = { .seq_ops = &bpf_map_seq_ops, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 05123feab378..803b91135ca0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5419,6 +5419,7 @@ static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], #endif + [CONST_PTR_TO_MAP] = btf_bpf_map_id, }; static bool is_trusted_reg(const struct bpf_reg_state *reg) -- cgit v1.2.3 From 63a64a56bc3f77c74085047ee45356ac850da3e8 Mon Sep 17 00:00:00 2001 From: Tirthendu Sarkar Date: Wed, 19 Jul 2023 15:23:58 +0200 Subject: xsk: prepare 'options' in xdp_desc for multi-buffer use Use the 'options' field in xdp_desc as a packet continuity marker. Since 'options' field was unused till now and was expected to be set to 0, the 'eop' descriptor will have it set to 0, while the non-eop descriptors will have to set it to 1. This ensures legacy applications continue to work without needing any change for single-buffer packets. Add helper functions and extend xskq_prod_reserve_desc() to use the 'options' field. Signed-off-by: Tirthendu Sarkar Link: https://lore.kernel.org/r/20230719132421.584801-2-maciej.fijalkowski@intel.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/if_xdp.h | 7 +++++++ net/xdp/xsk.c | 8 ++++---- net/xdp/xsk_queue.h | 12 +++++++++--- 3 files changed, 20 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index a78a8096f4ce..434f313dc26c 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -108,4 +108,11 @@ struct xdp_desc { /* UMEM descriptor is __u64 */ +/* Flag indicating that the packet continues with the buffer pointed out by the + * next frame in the ring. The end of the packet is signalled by setting this + * bit to zero. For single buffer packets, every descriptor has 'options' set + * to 0 and this maintains backward compatibility. + */ +#define XDP_PKT_CONTD (1 << 0) + #endif /* _LINUX_IF_XDP_H */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 31dca4ecb2c5..914a80cd55d3 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -135,14 +135,14 @@ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, return 0; } -static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) +static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, u32 flags) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); u64 addr; int err; addr = xp_get_handle(xskb); - err = xskq_prod_reserve_desc(xs->rx, addr, len); + err = xskq_prod_reserve_desc(xs->rx, addr, len, flags); if (err) { xs->rx_queue_full++; return err; @@ -189,7 +189,7 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) } xsk_copy_xdp(xsk_xdp, xdp, len); - err = __xsk_rcv_zc(xs, xsk_xdp, len); + err = __xsk_rcv_zc(xs, xsk_xdp, len, 0); if (err) { xsk_buff_free(xsk_xdp); return err; @@ -259,7 +259,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) { len = xdp->data_end - xdp->data; - return __xsk_rcv_zc(xs, xdp, len); + return __xsk_rcv_zc(xs, xdp, len, 0); } err = __xsk_rcv(xs, xdp); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 6d40a77fccbe..2f1aacae81af 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -130,6 +130,11 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) return false; } +static inline bool xp_unused_options_set(u32 options) +{ + return options & ~XDP_PKT_CONTD; +} + static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { @@ -141,7 +146,7 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, if (desc->addr >= pool->addrs_cnt) return false; - if (desc->options) + if (xp_unused_options_set(desc->options)) return false; return true; } @@ -158,7 +163,7 @@ static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool, xp_desc_crosses_non_contig_pg(pool, addr, desc->len)) return false; - if (desc->options) + if (xp_unused_options_set(desc->options)) return false; return true; } @@ -360,7 +365,7 @@ static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_de } static inline int xskq_prod_reserve_desc(struct xsk_queue *q, - u64 addr, u32 len) + u64 addr, u32 len, u32 flags) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx; @@ -372,6 +377,7 @@ static inline int xskq_prod_reserve_desc(struct xsk_queue *q, idx = q->cached_prod++ & q->ring_mask; ring->desc[idx].addr = addr; ring->desc[idx].len = len; + ring->desc[idx].options = flags; return 0; } -- cgit v1.2.3 From 81470b5c3c6649eef8e5f282cd06793f788ae165 Mon Sep 17 00:00:00 2001 From: Tirthendu Sarkar Date: Wed, 19 Jul 2023 15:23:59 +0200 Subject: xsk: introduce XSK_USE_SG bind flag for xsk socket As of now xsk core drops any xdp_buff with data size greater than the xsk frame_size as set by the af_xdp application. With multi-buffer support introduced in the next patch xsk core can now split those buffers into multiple descriptors provided the af_xdp application can handle them. Such capability of the application needs to be independent of the xdp_prog's frag support capability since there are cases where even a single xdp_buffer may need to be split into multiple descriptors owing to a smaller xsk frame size. For e.g., with NIC rx_buffer size set to 4kB, a 3kB packet will constitute of a single buffer and so will be sent as such to AF_XDP layer irrespective of 'xdp.frags' capability of the XDP program. Now if the xsk frame size is set to 2kB by the AF_XDP application, then the packet will need to be split into 2 descriptors if AF_XDP application can handle multi-buffer, else it needs to be dropped. Applications can now advertise their frag handling capability to xsk core so that xsk core can decide if it should drop or split xdp_buffs that exceed xsk frame size. This is done using a new 'XSK_USE_SG' bind flag for the xdp socket. Signed-off-by: Tirthendu Sarkar Link: https://lore.kernel.org/r/20230719132421.584801-3-maciej.fijalkowski@intel.com Signed-off-by: Alexei Starovoitov --- include/net/xdp_sock.h | 1 + include/uapi/linux/if_xdp.h | 6 ++++++ net/xdp/xsk.c | 5 +++-- 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index e96a1151ec75..36b0411a0d1b 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -52,6 +52,7 @@ struct xdp_sock { struct xsk_buff_pool *pool; u16 queue_id; bool zc; + bool sg; enum { XSK_READY = 0, XSK_BOUND, diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index 434f313dc26c..8d48863472b9 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -25,6 +25,12 @@ * application. */ #define XDP_USE_NEED_WAKEUP (1 << 3) +/* By setting this option, userspace application indicates that it can + * handle multiple descriptors per packet thus enabling AF_XDP to split + * multi-buffer XDP frames into multiple Rx descriptors. Without this set + * such frames will be dropped. + */ +#define XDP_USE_SG (1 << 4) /* Flags for xsk_umem_config flags */ #define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 914a80cd55d3..7b709e4e7ec4 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -897,7 +897,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) flags = sxdp->sxdp_flags; if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY | - XDP_USE_NEED_WAKEUP)) + XDP_USE_NEED_WAKEUP | XDP_USE_SG)) return -EINVAL; bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); @@ -929,7 +929,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) struct socket *sock; if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY) || - (flags & XDP_USE_NEED_WAKEUP)) { + (flags & XDP_USE_NEED_WAKEUP) || (flags & XDP_USE_SG)) { /* Cannot specify flags for shared sockets. */ err = -EINVAL; goto out_unlock; @@ -1028,6 +1028,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xs->dev = dev; xs->zc = xs->umem->zc; + xs->sg = !!(flags & XDP_USE_SG); xs->queue_id = qid; xp_add_xsk(xs->pool, xs); -- cgit v1.2.3 From b7f72a30e9ac2555b05afc6cfddc9dbc98e1eb8d Mon Sep 17 00:00:00 2001 From: Tirthendu Sarkar Date: Wed, 19 Jul 2023 15:24:03 +0200 Subject: xsk: introduce wrappers and helpers for supporting multi-buffer in Tx path In Tx path, xsk core reserves space for each desc to be transmitted in the completion queue and it's address contained in it is stored in the skb destructor arg. After successful transmission the skb destructor submits the addr marking completion. To handle multiple descriptors per packet, now along with reserving space for each descriptor, the corresponding address is also stored in completion queue. The number of pending descriptors are stored in skb destructor arg and is used by the skb destructor to update completions. Introduce 'skb' in xdp_sock to store a partially built packet when __xsk_generic_xmit() must return before it sees the EOP descriptor for the current packet so that packet building can resume in next call of __xsk_generic_xmit(). Helper functions are introduced to set and get the pending descriptors in the skb destructor arg. Also, wrappers are introduced for storing descriptor addresses, submitting and cancelling (for unsuccessful transmissions) the number of completions. Signed-off-by: Tirthendu Sarkar Link: https://lore.kernel.org/r/20230719132421.584801-7-maciej.fijalkowski@intel.com Signed-off-by: Alexei Starovoitov --- include/net/xdp_sock.h | 6 ++++ net/xdp/xsk.c | 74 ++++++++++++++++++++++++++++++++++++-------------- net/xdp/xsk_queue.h | 19 +++++-------- 3 files changed, 67 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 36b0411a0d1b..1617af380162 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -68,6 +68,12 @@ struct xdp_sock { u64 rx_dropped; u64 rx_queue_full; + /* When __xsk_generic_xmit() must return before it sees the EOP descriptor for the current + * packet, the partially built skb is saved here so that packet building can resume in next + * call of __xsk_generic_xmit(). + */ + struct sk_buff *skb; + struct list_head map_list; /* Protects map_list */ spinlock_t map_list_lock; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 01c134b1186e..ed7f86300087 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -480,19 +480,65 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags) return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); } -static void xsk_destruct_skb(struct sk_buff *skb) +static int xsk_cq_reserve_addr_locked(struct xdp_sock *xs, u64 addr) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&xs->pool->cq_lock, flags); + ret = xskq_prod_reserve_addr(xs->pool->cq, addr); + spin_unlock_irqrestore(&xs->pool->cq_lock, flags); + + return ret; +} + +static void xsk_cq_submit_locked(struct xdp_sock *xs, u32 n) +{ + unsigned long flags; + + spin_lock_irqsave(&xs->pool->cq_lock, flags); + xskq_prod_submit_n(xs->pool->cq, n); + spin_unlock_irqrestore(&xs->pool->cq_lock, flags); +} + +static void xsk_cq_cancel_locked(struct xdp_sock *xs, u32 n) { - u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg; - struct xdp_sock *xs = xdp_sk(skb->sk); unsigned long flags; spin_lock_irqsave(&xs->pool->cq_lock, flags); - xskq_prod_submit_addr(xs->pool->cq, addr); + xskq_prod_cancel_n(xs->pool->cq, n); spin_unlock_irqrestore(&xs->pool->cq_lock, flags); +} + +static u32 xsk_get_num_desc(struct sk_buff *skb) +{ + return skb ? (long)skb_shinfo(skb)->destructor_arg : 0; +} +static void xsk_destruct_skb(struct sk_buff *skb) +{ + xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb)); sock_wfree(skb); } +static void xsk_set_destructor_arg(struct sk_buff *skb) +{ + long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1; + + skb_shinfo(skb)->destructor_arg = (void *)num; +} + +static void xsk_consume_skb(struct sk_buff *skb) +{ + struct xdp_sock *xs = xdp_sk(skb->sk); + + skb->destructor = sock_wfree; + xsk_cq_cancel_locked(xs, xsk_get_num_desc(skb)); + /* Free skb without triggering the perf drop trace */ + consume_skb(skb); + xs->skb = NULL; +} + static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, struct xdp_desc *desc) { @@ -578,8 +624,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb->dev = dev; skb->priority = xs->sk.sk_priority; skb->mark = xs->sk.sk_mark; - skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr; skb->destructor = xsk_destruct_skb; + xsk_set_destructor_arg(skb); return skb; } @@ -591,7 +637,6 @@ static int __xsk_generic_xmit(struct sock *sk) bool sent_frame = false; struct xdp_desc desc; struct sk_buff *skb; - unsigned long flags; int err = 0; mutex_lock(&xs->mutex); @@ -616,31 +661,20 @@ static int __xsk_generic_xmit(struct sock *sk) * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ - spin_lock_irqsave(&xs->pool->cq_lock, flags); - if (xskq_prod_reserve(xs->pool->cq)) { - spin_unlock_irqrestore(&xs->pool->cq_lock, flags); + if (xsk_cq_reserve_addr_locked(xs, desc.addr)) goto out; - } - spin_unlock_irqrestore(&xs->pool->cq_lock, flags); skb = xsk_build_skb(xs, &desc); if (IS_ERR(skb)) { err = PTR_ERR(skb); - spin_lock_irqsave(&xs->pool->cq_lock, flags); - xskq_prod_cancel(xs->pool->cq); - spin_unlock_irqrestore(&xs->pool->cq_lock, flags); + xsk_cq_cancel_locked(xs, 1); goto out; } err = __dev_direct_xmit(skb, xs->queue_id); if (err == NETDEV_TX_BUSY) { /* Tell user-space to retry the send */ - skb->destructor = sock_wfree; - spin_lock_irqsave(&xs->pool->cq_lock, flags); - xskq_prod_cancel(xs->pool->cq); - spin_unlock_irqrestore(&xs->pool->cq_lock, flags); - /* Free skb without triggering the perf drop trace */ - consume_skb(skb); + xsk_consume_skb(skb); err = -EAGAIN; goto out; } diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 2f1aacae81af..423ad7368fa2 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -297,6 +297,11 @@ static inline void xskq_cons_release(struct xsk_queue *q) q->cached_cons++; } +static inline void xskq_cons_cancel_n(struct xsk_queue *q, u32 cnt) +{ + q->cached_cons -= cnt; +} + static inline u32 xskq_cons_present_entries(struct xsk_queue *q) { /* No barriers needed since data is not accessed */ @@ -324,9 +329,9 @@ static inline bool xskq_prod_is_full(struct xsk_queue *q) return xskq_prod_nb_free(q, 1) ? false : true; } -static inline void xskq_prod_cancel(struct xsk_queue *q) +static inline void xskq_prod_cancel_n(struct xsk_queue *q, u32 cnt) { - q->cached_prod--; + q->cached_prod -= cnt; } static inline int xskq_prod_reserve(struct xsk_queue *q) @@ -392,16 +397,6 @@ static inline void xskq_prod_submit(struct xsk_queue *q) __xskq_prod_submit(q, q->cached_prod); } -static inline void xskq_prod_submit_addr(struct xsk_queue *q, u64 addr) -{ - struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; - u32 idx = q->ring->producer; - - ring->desc[idx++ & q->ring_mask] = addr; - - __xskq_prod_submit(q, idx); -} - static inline void xskq_prod_submit_n(struct xsk_queue *q, u32 nb_entries) { __xskq_prod_submit(q, q->ring->producer + nb_entries); -- cgit v1.2.3 From 1b725b0c8163cfd2d9ab22057df46b487981cfea Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 19 Jul 2023 15:24:04 +0200 Subject: xsk: allow core/drivers to test EOP bit Drivers are used to check for EOP bit whereas AF_XDP operates on inverted logic - user space indicates that current frag is not the last one and packet continues. For AF_XDP core needs, add xp_mb_desc() that will simply test XDP_PKT_CONTD from xdp_desc::options, but in order to preserve drivers default behavior, introduce an interface for ZC drivers that will negate xp_mb_desc() result and therefore make it easier to test EOP bit from during production of HW Tx descriptors. Signed-off-by: Maciej Fijalkowski Link: https://lore.kernel.org/r/20230719132421.584801-8-maciej.fijalkowski@intel.com Signed-off-by: Alexei Starovoitov --- include/net/xdp_sock_drv.h | 10 ++++++++++ include/net/xsk_buff_pool.h | 5 +++++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index c243f906ebed..0d34cdb5567d 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -89,6 +89,11 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) return xp_alloc(pool); } +static inline bool xsk_is_eop_desc(struct xdp_desc *desc) +{ + return !xp_mb_desc(desc); +} + /* Returns as many entries as possible up to max. 0 <= N <= max. */ static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) { @@ -241,6 +246,11 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) return NULL; } +static inline bool xsk_is_eop_desc(struct xdp_desc *desc) +{ + return false; +} + static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) { return 0; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index a8d7b8a3688a..4dcca163e076 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -184,6 +184,11 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK); } +static inline bool xp_mb_desc(struct xdp_desc *desc) +{ + return desc->options & XDP_PKT_CONTD; +} + static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr) { return addr & pool->chunk_mask; -- cgit v1.2.3 From 13ce2daa259a3bfbc9a5aeeee8b9a87058703731 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 19 Jul 2023 15:24:07 +0200 Subject: xsk: add new netlink attribute dedicated for ZC max frags Introduce new netlink attribute NETDEV_A_DEV_XDP_ZC_MAX_SEGS that will carry maximum fragments that underlying ZC driver is able to handle on TX side. It is going to be included in netlink response only when driver supports ZC. Any value higher than 1 implies multi-buffer ZC support on underlying device. Signed-off-by: Maciej Fijalkowski Link: https://lore.kernel.org/r/20230719132421.584801-11-maciej.fijalkowski@intel.com Signed-off-by: Alexei Starovoitov --- Documentation/netlink/specs/netdev.yaml | 6 ++++++ include/linux/netdevice.h | 1 + include/uapi/linux/netdev.h | 1 + net/core/dev.c | 1 + net/core/netdev-genl.c | 8 ++++++++ tools/include/uapi/linux/netdev.h | 1 + tools/lib/bpf/libbpf.h | 3 ++- tools/lib/bpf/netlink.c | 5 +++++ 8 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index b99e7ffef7a1..e41015310a6e 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -62,6 +62,12 @@ attribute-sets: type: u64 enum: xdp-act enum-as-flags: true + - + name: xdp_zc_max_segs + doc: max fragment count supported by ZC driver + type: u32 + checks: + min: 1 operations: list: diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b828c7a75be2..b12477ea4032 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2250,6 +2250,7 @@ struct net_device { #define GRO_MAX_SIZE (8 * 65535u) unsigned int gro_max_size; unsigned int gro_ipv4_max_size; + unsigned int xdp_zc_max_segs; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 639524b59930..bf71698a1e82 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -41,6 +41,7 @@ enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, NETDEV_A_DEV_XDP_FEATURES, + NETDEV_A_DEV_XDP_ZC_MAX_SEGS, __NETDEV_A_DEV_MAX, NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) diff --git a/net/core/dev.c b/net/core/dev.c index d6e1b786c5c5..dd4f114a7cbf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10613,6 +10613,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); dev->gso_max_size = GSO_LEGACY_MAX_SIZE; + dev->xdp_zc_max_segs = 1; dev->gso_max_segs = GSO_MAX_SEGS; dev->gro_max_size = GRO_LEGACY_MAX_SIZE; dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index a4270fafdf11..65ef4867fc49 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -25,6 +25,14 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, return -EINVAL; } + if (netdev->xdp_features & NETDEV_XDP_ACT_XSK_ZEROCOPY) { + if (nla_put_u32(rsp, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, + netdev->xdp_zc_max_segs)) { + genlmsg_cancel(rsp, hdr); + return -EINVAL; + } + } + genlmsg_end(rsp, hdr); return 0; diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 639524b59930..bf71698a1e82 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -41,6 +41,7 @@ enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, NETDEV_A_DEV_XDP_FEATURES, + NETDEV_A_DEV_XDP_ZC_MAX_SEGS, __NETDEV_A_DEV_MAX, NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 10642ad69d76..674e5788eb10 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -1105,9 +1105,10 @@ struct bpf_xdp_query_opts { __u32 skb_prog_id; /* output */ __u8 attach_mode; /* output */ __u64 feature_flags; /* output */ + __u32 xdp_zc_max_segs; /* output */ size_t :0; }; -#define bpf_xdp_query_opts__last_field feature_flags +#define bpf_xdp_query_opts__last_field xdp_zc_max_segs LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts); diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 84dd5fa14905..090bcf6e3b3d 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -45,6 +45,7 @@ struct xdp_id_md { struct xdp_features_md { int ifindex; + __u32 xdp_zc_max_segs; __u64 flags; }; @@ -421,6 +422,9 @@ static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, return NL_CONT; md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]); + if (tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS]) + md->xdp_zc_max_segs = + libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS]); return NL_DONE; } @@ -493,6 +497,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) return libbpf_err(err); opts->feature_flags = md.flags; + opts->xdp_zc_max_segs = md.xdp_zc_max_segs; skip_feature_flags: return 0; -- cgit v1.2.3 From 24ea50127ecf0efe819c1f6230add27abc6ca9d9 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 19 Jul 2023 15:24:08 +0200 Subject: xsk: support mbuf on ZC RX Given that skb_shared_info relies on skb_frag_t, in order to support xskb chaining, introduce xdp_buff_xsk::xskb_list_node and xsk_buff_pool::xskb_list. This is needed so ZC drivers can add frags as xskb nodes which will make it possible to handle it both when producing AF_XDP Rx descriptors as well as freeing/recycling all the frags that a single frame carries. Speaking of latter, update xsk_buff_free() to take care of list nodes. For the former (adding as frags), introduce xsk_buff_add_frag() for ZC drivers usage that is going to be used to add a frag to xskb list from pool. xsk_buff_get_frag() will be utilized by XDP_TX and, on contrary, will return xdp_buff. One of the previous patches added a wrapper for ZC Rx so implement xskb list walk and production of Rx descriptors there. On bind() path, bail out if socket wants to use ZC multi-buffer but underlying netdev does not support it. Signed-off-by: Maciej Fijalkowski Link: https://lore.kernel.org/r/20230719132421.584801-12-maciej.fijalkowski@intel.com Signed-off-by: Alexei Starovoitov --- include/net/xdp_sock_drv.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/net/xsk_buff_pool.h | 2 ++ net/xdp/xsk.c | 26 +++++++++++++++++++++++++- net/xdp/xsk_buff_pool.c | 7 +++++++ 4 files changed, 78 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 0d34cdb5567d..1f6fc8c7a84c 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -108,10 +108,45 @@ static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) static inline void xsk_buff_free(struct xdp_buff *xdp) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + struct list_head *xskb_list = &xskb->pool->xskb_list; + struct xdp_buff_xsk *pos, *tmp; + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) { + list_del(&pos->xskb_list_node); + xp_free(pos); + } + + xdp_get_shared_info_from_buff(xdp)->nr_frags = 0; +out: xp_free(xskb); } +static inline void xsk_buff_add_frag(struct xdp_buff *xdp) +{ + struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp); + + list_add_tail(&frag->xskb_list_node, &frag->pool->xskb_list); +} + +static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) +{ + struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp); + struct xdp_buff *ret = NULL; + struct xdp_buff_xsk *frag; + + frag = list_first_entry_or_null(&xskb->pool->xskb_list, + struct xdp_buff_xsk, xskb_list_node); + if (frag) { + list_del(&frag->xskb_list_node); + ret = &frag->xdp; + } + + return ret; +} + static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size) { xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM; @@ -265,6 +300,15 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) { } +static inline void xsk_buff_add_frag(struct xdp_buff *xdp) +{ +} + +static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) +{ + return NULL; +} + static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size) { } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 4dcca163e076..b0bdff26fc88 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -29,6 +29,7 @@ struct xdp_buff_xsk { struct xsk_buff_pool *pool; u64 orig_addr; struct list_head free_list_node; + struct list_head xskb_list_node; }; #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb)) @@ -54,6 +55,7 @@ struct xsk_buff_pool { struct xdp_umem *umem; struct work_struct work; struct list_head free_list; + struct list_head xskb_list; u32 heads_cnt; u16 queue_id; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index ba755fed3750..4f1e0599146e 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -155,8 +155,32 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff_xsk *xskb, u32 len, static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + u32 frags = xdp_buff_has_frags(xdp); + struct xdp_buff_xsk *pos, *tmp; + struct list_head *xskb_list; + u32 contd = 0; + int err; + + if (frags) + contd = XDP_PKT_CONTD; - return __xsk_rcv_zc(xs, xskb, len, 0); + err = __xsk_rcv_zc(xs, xskb, len, contd); + if (err || likely(!frags)) + goto out; + + xskb_list = &xskb->pool->xskb_list; + list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) { + if (list_is_singular(xskb_list)) + contd = 0; + len = pos->xdp.data_end - pos->xdp.data; + err = __xsk_rcv_zc(xs, pos, len, contd); + if (err) + return err; + list_del(&pos->xskb_list_node); + } + +out: + return err; } static void *xsk_copy_xdp_start(struct xdp_buff *from) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 26f6d304451e..b3f7b310811e 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -86,6 +86,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, pool->umem = umem; pool->addrs = umem->addrs; INIT_LIST_HEAD(&pool->free_list); + INIT_LIST_HEAD(&pool->xskb_list); INIT_LIST_HEAD(&pool->xsk_tx_list); spin_lock_init(&pool->xsk_tx_list_lock); spin_lock_init(&pool->cq_lock); @@ -99,6 +100,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, xskb->pool = pool; xskb->xdp.frame_sz = umem->chunk_size - umem->headroom; INIT_LIST_HEAD(&xskb->free_list_node); + INIT_LIST_HEAD(&xskb->xskb_list_node); if (pool->unaligned) pool->free_heads[i] = xskb; else @@ -187,6 +189,11 @@ int xp_assign_dev(struct xsk_buff_pool *pool, goto err_unreg_pool; } + if (netdev->xdp_zc_max_segs == 1 && (flags & XDP_USE_SG)) { + err = -EOPNOTSUPP; + goto err_unreg_pool; + } + bpf.command = XDP_SETUP_XSK_POOL; bpf.xsk.pool = pool; bpf.xsk.queue_id = queue_id; -- cgit v1.2.3 From 053c8e1f235dc3f69d13375b32f4209228e1cb96 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 19 Jul 2023 16:08:51 +0200 Subject: bpf: Add generic attach/detach/query API for multi-progs This adds a generic layer called bpf_mprog which can be reused by different attachment layers to enable multi-program attachment and dependency resolution. In-kernel users of the bpf_mprog don't need to care about the dependency resolution internals, they can just consume it with few API calls. The initial idea of having a generic API sparked out of discussion [0] from an earlier revision of this work where tc's priority was reused and exposed via BPF uapi as a way to coordinate dependencies among tc BPF programs, similar as-is for classic tc BPF. The feedback was that priority provides a bad user experience and is hard to use [1], e.g.: I cannot help but feel that priority logic copy-paste from old tc, netfilter and friends is done because "that's how things were done in the past". [...] Priority gets exposed everywhere in uapi all the way to bpftool when it's right there for users to understand. And that's the main problem with it. The user don't want to and don't need to be aware of it, but uapi forces them to pick the priority. [...] Your cover letter [0] example proves that in real life different service pick the same priority. They simply don't know any better. Priority is an unnecessary magic that apps _have_ to pick, so they just copy-paste and everyone ends up using the same. The course of the discussion showed more and more the need for a generic, reusable API where the "same look and feel" can be applied for various other program types beyond just tc BPF, for example XDP today does not have multi- program support in kernel, but also there was interest around this API for improving management of cgroup program types. Such common multi-program management concept is useful for BPF management daemons or user space BPF applications coordinating internally about their attachments. Both from Cilium and Meta side [2], we've collected the following requirements for a generic attach/detach/query API for multi-progs which has been implemented as part of this work: - Support prog-based attach/detach and link API - Dependency directives (can also be combined): - BPF_F_{BEFORE,AFTER} with relative_{fd,id} which can be {prog,link,none} - BPF_F_ID flag as {fd,id} toggle; the rationale for id is so that user space application does not need CAP_SYS_ADMIN to retrieve foreign fds via bpf_*_get_fd_by_id() - BPF_F_LINK flag as {prog,link} toggle - If relative_{fd,id} is none, then BPF_F_BEFORE will just prepend, and BPF_F_AFTER will just append for attaching - Enforced only at attach time - BPF_F_REPLACE with replace_bpf_fd which can be prog, links have their own infra for replacing their internal prog - If no flags are set, then it's default append behavior for attaching - Internal revision counter and optionally being able to pass expected_revision - User space application can query current state with revision, and pass it along for attachment to assert current state before doing updates - Query also gets extension for link_ids array and link_attach_flags: - prog_ids are always filled with program IDs - link_ids are filled with link IDs when link was used, otherwise 0 - {prog,link}_attach_flags for holding {prog,link}-specific flags - Must be easy to integrate/reuse for in-kernel users The uapi-side changes needed for supporting bpf_mprog are rather minimal, consisting of the additions of the attachment flags, revision counter, and expanding existing union with relative_{fd,id} member. The bpf_mprog framework consists of an bpf_mprog_entry object which holds an array of bpf_mprog_fp (fast-path structure). The bpf_mprog_cp (control-path structure) is part of bpf_mprog_bundle. Both have been separated, so that fast-path gets efficient packing of bpf_prog pointers for maximum cache efficiency. Also, array has been chosen instead of linked list or other structures to remove unnecessary indirections for a fast point-to-entry in tc for BPF. The bpf_mprog_entry comes as a pair via bpf_mprog_bundle so that in case of updates the peer bpf_mprog_entry is populated and then just swapped which avoids additional allocations that could otherwise fail, for example, in detach case. bpf_mprog_{fp,cp} arrays are currently static, but they could be converted to dynamic allocation if necessary at a point in future. Locking is deferred to the in-kernel user of bpf_mprog, for example, in case of tcx which uses this API in the next patch, it piggybacks on rtnl. An extensive test suite for checking all aspects of this API for prog-based attach/detach and link API comes as BPF selftests in this series. Thanks also to Andrii Nakryiko for early API discussions wrt Meta's BPF prog management. [0] https://lore.kernel.org/bpf/20221004231143.19190-1-daniel@iogearbox.net [1] https://lore.kernel.org/bpf/CAADnVQ+gEY3FjCR=+DmjDR4gp5bOYZUFJQXj4agKFHT9CQPZBw@mail.gmail.com [2] http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20230719140858.13224-2-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- MAINTAINERS | 1 + include/linux/bpf_mprog.h | 318 +++++++++++++++++++++++++++++ include/uapi/linux/bpf.h | 36 +++- kernel/bpf/Makefile | 2 +- kernel/bpf/mprog.c | 445 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 36 +++- 6 files changed, 821 insertions(+), 17 deletions(-) create mode 100644 include/linux/bpf_mprog.h create mode 100644 kernel/bpf/mprog.c (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 9a5863f1b016..678bef9f60b4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3684,6 +3684,7 @@ F: include/linux/filter.h F: include/linux/tnum.h F: kernel/bpf/core.c F: kernel/bpf/dispatcher.c +F: kernel/bpf/mprog.c F: kernel/bpf/syscall.c F: kernel/bpf/tnum.c F: kernel/bpf/trampoline.c diff --git a/include/linux/bpf_mprog.h b/include/linux/bpf_mprog.h new file mode 100644 index 000000000000..6feefec43422 --- /dev/null +++ b/include/linux/bpf_mprog.h @@ -0,0 +1,318 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Isovalent */ +#ifndef __BPF_MPROG_H +#define __BPF_MPROG_H + +#include + +/* bpf_mprog framework: + * + * bpf_mprog is a generic layer for multi-program attachment. In-kernel users + * of the bpf_mprog don't need to care about the dependency resolution + * internals, they can just consume it with few API calls. Currently available + * dependency directives are BPF_F_{BEFORE,AFTER} which enable insertion of + * a BPF program or BPF link relative to an existing BPF program or BPF link + * inside the multi-program array as well as prepend and append behavior if + * no relative object was specified, see corresponding selftests for concrete + * examples (e.g. tc_links and tc_opts test cases of test_progs). + * + * Usage of bpf_mprog_{attach,detach,query}() core APIs with pseudo code: + * + * Attach case: + * + * struct bpf_mprog_entry *entry, *entry_new; + * int ret; + * + * // bpf_mprog user-side lock + * // fetch active @entry from attach location + * [...] + * ret = bpf_mprog_attach(entry, &entry_new, [...]); + * if (!ret) { + * if (entry != entry_new) { + * // swap @entry to @entry_new at attach location + * // ensure there are no inflight users of @entry: + * synchronize_rcu(); + * } + * bpf_mprog_commit(entry); + * } else { + * // error path, bail out, propagate @ret + * } + * // bpf_mprog user-side unlock + * + * Detach case: + * + * struct bpf_mprog_entry *entry, *entry_new; + * int ret; + * + * // bpf_mprog user-side lock + * // fetch active @entry from attach location + * [...] + * ret = bpf_mprog_detach(entry, &entry_new, [...]); + * if (!ret) { + * // all (*) marked is optional and depends on the use-case + * // whether bpf_mprog_bundle should be freed or not + * if (!bpf_mprog_total(entry_new)) (*) + * entry_new = NULL (*) + * // swap @entry to @entry_new at attach location + * // ensure there are no inflight users of @entry: + * synchronize_rcu(); + * bpf_mprog_commit(entry); + * if (!entry_new) (*) + * // free bpf_mprog_bundle (*) + * } else { + * // error path, bail out, propagate @ret + * } + * // bpf_mprog user-side unlock + * + * Query case: + * + * struct bpf_mprog_entry *entry; + * int ret; + * + * // bpf_mprog user-side lock + * // fetch active @entry from attach location + * [...] + * ret = bpf_mprog_query(attr, uattr, entry); + * // bpf_mprog user-side unlock + * + * Data/fast path: + * + * struct bpf_mprog_entry *entry; + * struct bpf_mprog_fp *fp; + * struct bpf_prog *prog; + * int ret = [...]; + * + * rcu_read_lock(); + * // fetch active @entry from attach location + * [...] + * bpf_mprog_foreach_prog(entry, fp, prog) { + * ret = bpf_prog_run(prog, [...]); + * // process @ret from program + * } + * [...] + * rcu_read_unlock(); + * + * bpf_mprog locking considerations: + * + * bpf_mprog_{attach,detach,query}() must be protected by an external lock + * (like RTNL in case of tcx). + * + * bpf_mprog_entry pointer can be an __rcu annotated pointer (in case of tcx + * the netdevice has tcx_ingress and tcx_egress __rcu pointer) which gets + * updated via rcu_assign_pointer() pointing to the active bpf_mprog_entry of + * the bpf_mprog_bundle. + * + * Fast path accesses the active bpf_mprog_entry within RCU critical section + * (in case of tcx it runs in NAPI which provides RCU protection there, + * other users might need explicit rcu_read_lock()). The bpf_mprog_commit() + * assumes that for the old bpf_mprog_entry there are no inflight users + * anymore. + * + * The READ_ONCE()/WRITE_ONCE() pairing for bpf_mprog_fp's prog access is for + * the replacement case where we don't swap the bpf_mprog_entry. + */ + +#define bpf_mprog_foreach_tuple(entry, fp, cp, t) \ + for (fp = &entry->fp_items[0], cp = &entry->parent->cp_items[0];\ + ({ \ + t.prog = READ_ONCE(fp->prog); \ + t.link = cp->link; \ + t.prog; \ + }); \ + fp++, cp++) + +#define bpf_mprog_foreach_prog(entry, fp, p) \ + for (fp = &entry->fp_items[0]; \ + (p = READ_ONCE(fp->prog)); \ + fp++) + +#define BPF_MPROG_MAX 64 + +struct bpf_mprog_fp { + struct bpf_prog *prog; +}; + +struct bpf_mprog_cp { + struct bpf_link *link; +}; + +struct bpf_mprog_entry { + struct bpf_mprog_fp fp_items[BPF_MPROG_MAX]; + struct bpf_mprog_bundle *parent; +}; + +struct bpf_mprog_bundle { + struct bpf_mprog_entry a; + struct bpf_mprog_entry b; + struct bpf_mprog_cp cp_items[BPF_MPROG_MAX]; + struct bpf_prog *ref; + atomic64_t revision; + u32 count; +}; + +struct bpf_tuple { + struct bpf_prog *prog; + struct bpf_link *link; +}; + +static inline struct bpf_mprog_entry * +bpf_mprog_peer(const struct bpf_mprog_entry *entry) +{ + if (entry == &entry->parent->a) + return &entry->parent->b; + else + return &entry->parent->a; +} + +static inline void bpf_mprog_bundle_init(struct bpf_mprog_bundle *bundle) +{ + BUILD_BUG_ON(sizeof(bundle->a.fp_items[0]) > sizeof(u64)); + BUILD_BUG_ON(ARRAY_SIZE(bundle->a.fp_items) != + ARRAY_SIZE(bundle->cp_items)); + + memset(bundle, 0, sizeof(*bundle)); + atomic64_set(&bundle->revision, 1); + bundle->a.parent = bundle; + bundle->b.parent = bundle; +} + +static inline void bpf_mprog_inc(struct bpf_mprog_entry *entry) +{ + entry->parent->count++; +} + +static inline void bpf_mprog_dec(struct bpf_mprog_entry *entry) +{ + entry->parent->count--; +} + +static inline int bpf_mprog_max(void) +{ + return ARRAY_SIZE(((struct bpf_mprog_entry *)NULL)->fp_items) - 1; +} + +static inline int bpf_mprog_total(struct bpf_mprog_entry *entry) +{ + int total = entry->parent->count; + + WARN_ON_ONCE(total > bpf_mprog_max()); + return total; +} + +static inline bool bpf_mprog_exists(struct bpf_mprog_entry *entry, + struct bpf_prog *prog) +{ + const struct bpf_mprog_fp *fp; + const struct bpf_prog *tmp; + + bpf_mprog_foreach_prog(entry, fp, tmp) { + if (tmp == prog) + return true; + } + return false; +} + +static inline void bpf_mprog_mark_for_release(struct bpf_mprog_entry *entry, + struct bpf_tuple *tuple) +{ + WARN_ON_ONCE(entry->parent->ref); + if (!tuple->link) + entry->parent->ref = tuple->prog; +} + +static inline void bpf_mprog_complete_release(struct bpf_mprog_entry *entry) +{ + /* In the non-link case prog deletions can only drop the reference + * to the prog after the bpf_mprog_entry got swapped and the + * bpf_mprog ensured that there are no inflight users anymore. + * + * Paired with bpf_mprog_mark_for_release(). + */ + if (entry->parent->ref) { + bpf_prog_put(entry->parent->ref); + entry->parent->ref = NULL; + } +} + +static inline void bpf_mprog_revision_new(struct bpf_mprog_entry *entry) +{ + atomic64_inc(&entry->parent->revision); +} + +static inline void bpf_mprog_commit(struct bpf_mprog_entry *entry) +{ + bpf_mprog_complete_release(entry); + bpf_mprog_revision_new(entry); +} + +static inline u64 bpf_mprog_revision(struct bpf_mprog_entry *entry) +{ + return atomic64_read(&entry->parent->revision); +} + +static inline void bpf_mprog_entry_copy(struct bpf_mprog_entry *dst, + struct bpf_mprog_entry *src) +{ + memcpy(dst->fp_items, src->fp_items, sizeof(src->fp_items)); +} + +static inline void bpf_mprog_entry_grow(struct bpf_mprog_entry *entry, int idx) +{ + int total = bpf_mprog_total(entry); + + memmove(entry->fp_items + idx + 1, + entry->fp_items + idx, + (total - idx) * sizeof(struct bpf_mprog_fp)); + + memmove(entry->parent->cp_items + idx + 1, + entry->parent->cp_items + idx, + (total - idx) * sizeof(struct bpf_mprog_cp)); +} + +static inline void bpf_mprog_entry_shrink(struct bpf_mprog_entry *entry, int idx) +{ + /* Total array size is needed in this case to enure the NULL + * entry is copied at the end. + */ + int total = ARRAY_SIZE(entry->fp_items); + + memmove(entry->fp_items + idx, + entry->fp_items + idx + 1, + (total - idx - 1) * sizeof(struct bpf_mprog_fp)); + + memmove(entry->parent->cp_items + idx, + entry->parent->cp_items + idx + 1, + (total - idx - 1) * sizeof(struct bpf_mprog_cp)); +} + +static inline void bpf_mprog_read(struct bpf_mprog_entry *entry, u32 idx, + struct bpf_mprog_fp **fp, + struct bpf_mprog_cp **cp) +{ + *fp = &entry->fp_items[idx]; + *cp = &entry->parent->cp_items[idx]; +} + +static inline void bpf_mprog_write(struct bpf_mprog_fp *fp, + struct bpf_mprog_cp *cp, + struct bpf_tuple *tuple) +{ + WRITE_ONCE(fp->prog, tuple->prog); + cp->link = tuple->link; +} + +int bpf_mprog_attach(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_prog *prog_new, struct bpf_link *link, + struct bpf_prog *prog_old, + u32 flags, u32 id_or_fd, u64 revision); + +int bpf_mprog_detach(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_prog *prog, struct bpf_link *link, + u32 flags, u32 id_or_fd, u64 revision); + +int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, + struct bpf_mprog_entry *entry); + +#endif /* __BPF_MPROG_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9ed59896ebc5..d4c07e435336 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1113,7 +1113,12 @@ enum bpf_perf_event_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) #define BPF_F_ALLOW_MULTI (1U << 1) +/* Generic attachment flags. */ #define BPF_F_REPLACE (1U << 2) +#define BPF_F_BEFORE (1U << 3) +#define BPF_F_AFTER (1U << 4) +#define BPF_F_ID (1U << 5) +#define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -1444,14 +1449,19 @@ union bpf_attr { }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ - __u32 target_fd; /* container object to attach to */ - __u32 attach_bpf_fd; /* eBPF program to attach */ + union { + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ + }; + __u32 attach_bpf_fd; __u32 attach_type; __u32 attach_flags; - __u32 replace_bpf_fd; /* previously attached eBPF - * program to replace if - * BPF_F_REPLACE is used - */ + __u32 replace_bpf_fd; + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -1497,16 +1507,26 @@ union bpf_attr { } info; struct { /* anonymous struct used by BPF_PROG_QUERY command */ - __u32 target_fd; /* container object to query */ + union { + __u32 target_fd; /* target object to query or ... */ + __u32 target_ifindex; /* target ifindex */ + }; __u32 attach_type; __u32 query_flags; __u32 attach_flags; __aligned_u64 prog_ids; - __u32 prog_cnt; + union { + __u32 prog_cnt; + __u32 count; + }; + __u32 :32; /* output: per-program attach_flags. * not allowed to be set during effective query. */ __aligned_u64 prog_attach_flags; + __aligned_u64 link_ids; + __aligned_u64 link_attach_flags; + __u64 revision; } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 1d3892168d32..1bea2eb912cd 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -12,7 +12,7 @@ obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o -obj-$(CONFIG_BPF_SYSCALL) += disasm.o +obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o obj-$(CONFIG_BPF_JIT) += dispatcher.o diff --git a/kernel/bpf/mprog.c b/kernel/bpf/mprog.c new file mode 100644 index 000000000000..f7816d2bc3e4 --- /dev/null +++ b/kernel/bpf/mprog.c @@ -0,0 +1,445 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ + +#include +#include + +static int bpf_mprog_link(struct bpf_tuple *tuple, + u32 id_or_fd, u32 flags, + enum bpf_prog_type type) +{ + struct bpf_link *link = ERR_PTR(-EINVAL); + bool id = flags & BPF_F_ID; + + if (id) + link = bpf_link_by_id(id_or_fd); + else if (id_or_fd) + link = bpf_link_get_from_fd(id_or_fd); + if (IS_ERR(link)) + return PTR_ERR(link); + if (type && link->prog->type != type) { + bpf_link_put(link); + return -EINVAL; + } + + tuple->link = link; + tuple->prog = link->prog; + return 0; +} + +static int bpf_mprog_prog(struct bpf_tuple *tuple, + u32 id_or_fd, u32 flags, + enum bpf_prog_type type) +{ + struct bpf_prog *prog = ERR_PTR(-EINVAL); + bool id = flags & BPF_F_ID; + + if (id) + prog = bpf_prog_by_id(id_or_fd); + else if (id_or_fd) + prog = bpf_prog_get(id_or_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + if (type && prog->type != type) { + bpf_prog_put(prog); + return -EINVAL; + } + + tuple->link = NULL; + tuple->prog = prog; + return 0; +} + +static int bpf_mprog_tuple_relative(struct bpf_tuple *tuple, + u32 id_or_fd, u32 flags, + enum bpf_prog_type type) +{ + bool link = flags & BPF_F_LINK; + bool id = flags & BPF_F_ID; + + memset(tuple, 0, sizeof(*tuple)); + if (link) + return bpf_mprog_link(tuple, id_or_fd, flags, type); + /* If no relevant flag is set and no id_or_fd was passed, then + * tuple link/prog is just NULLed. This is the case when before/ + * after selects first/last position without passing fd. + */ + if (!id && !id_or_fd) + return 0; + return bpf_mprog_prog(tuple, id_or_fd, flags, type); +} + +static void bpf_mprog_tuple_put(struct bpf_tuple *tuple) +{ + if (tuple->link) + bpf_link_put(tuple->link); + else if (tuple->prog) + bpf_prog_put(tuple->prog); +} + +/* The bpf_mprog_{replace,delete}() operate on exact idx position with the + * one exception that for deletion we support delete from front/back. In + * case of front idx is -1, in case of back idx is bpf_mprog_total(entry). + * Adjustment to first and last entry is trivial. The bpf_mprog_insert() + * we have to deal with the following cases: + * + * idx + before: + * + * Insert P4 before P3: idx for old array is 1, idx for new array is 2, + * hence we adjust target idx for the new array, so that memmove copies + * P1 and P2 to the new entry, and we insert P4 into idx 2. Inserting + * before P1 would have old idx -1 and new idx 0. + * + * +--+--+--+ +--+--+--+--+ +--+--+--+--+ + * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3| + * +--+--+--+ +--+--+--+--+ +--+--+--+--+ + * + * idx + after: + * + * Insert P4 after P2: idx for old array is 2, idx for new array is 2. + * Again, memmove copies P1 and P2 to the new entry, and we insert P4 + * into idx 2. Inserting after P3 would have both old/new idx at 4 aka + * bpf_mprog_total(entry). + * + * +--+--+--+ +--+--+--+--+ +--+--+--+--+ + * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3| + * +--+--+--+ +--+--+--+--+ +--+--+--+--+ + */ +static int bpf_mprog_replace(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_tuple *ntuple, int idx) +{ + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + struct bpf_prog *oprog; + + bpf_mprog_read(entry, idx, &fp, &cp); + oprog = READ_ONCE(fp->prog); + bpf_mprog_write(fp, cp, ntuple); + if (!ntuple->link) { + WARN_ON_ONCE(cp->link); + bpf_prog_put(oprog); + } + *entry_new = entry; + return 0; +} + +static int bpf_mprog_insert(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_tuple *ntuple, int idx, u32 flags) +{ + int total = bpf_mprog_total(entry); + struct bpf_mprog_entry *peer; + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + + peer = bpf_mprog_peer(entry); + bpf_mprog_entry_copy(peer, entry); + if (idx == total) + goto insert; + else if (flags & BPF_F_BEFORE) + idx += 1; + bpf_mprog_entry_grow(peer, idx); +insert: + bpf_mprog_read(peer, idx, &fp, &cp); + bpf_mprog_write(fp, cp, ntuple); + bpf_mprog_inc(peer); + *entry_new = peer; + return 0; +} + +static int bpf_mprog_delete(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_tuple *dtuple, int idx) +{ + int total = bpf_mprog_total(entry); + struct bpf_mprog_entry *peer; + + peer = bpf_mprog_peer(entry); + bpf_mprog_entry_copy(peer, entry); + if (idx == -1) + idx = 0; + else if (idx == total) + idx = total - 1; + bpf_mprog_entry_shrink(peer, idx); + bpf_mprog_dec(peer); + bpf_mprog_mark_for_release(peer, dtuple); + *entry_new = peer; + return 0; +} + +/* In bpf_mprog_pos_*() we evaluate the target position for the BPF + * program/link that needs to be replaced, inserted or deleted for + * each "rule" independently. If all rules agree on that position + * or existing element, then enact replacement, addition or deletion. + * If this is not the case, then the request cannot be satisfied and + * we bail out with an error. + */ +static int bpf_mprog_pos_exact(struct bpf_mprog_entry *entry, + struct bpf_tuple *tuple) +{ + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + int i; + + for (i = 0; i < bpf_mprog_total(entry); i++) { + bpf_mprog_read(entry, i, &fp, &cp); + if (tuple->prog == READ_ONCE(fp->prog)) + return tuple->link == cp->link ? i : -EBUSY; + } + return -ENOENT; +} + +static int bpf_mprog_pos_before(struct bpf_mprog_entry *entry, + struct bpf_tuple *tuple) +{ + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + int i; + + for (i = 0; i < bpf_mprog_total(entry); i++) { + bpf_mprog_read(entry, i, &fp, &cp); + if (tuple->prog == READ_ONCE(fp->prog) && + (!tuple->link || tuple->link == cp->link)) + return i - 1; + } + return tuple->prog ? -ENOENT : -1; +} + +static int bpf_mprog_pos_after(struct bpf_mprog_entry *entry, + struct bpf_tuple *tuple) +{ + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + int i; + + for (i = 0; i < bpf_mprog_total(entry); i++) { + bpf_mprog_read(entry, i, &fp, &cp); + if (tuple->prog == READ_ONCE(fp->prog) && + (!tuple->link || tuple->link == cp->link)) + return i + 1; + } + return tuple->prog ? -ENOENT : bpf_mprog_total(entry); +} + +int bpf_mprog_attach(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_prog *prog_new, struct bpf_link *link, + struct bpf_prog *prog_old, + u32 flags, u32 id_or_fd, u64 revision) +{ + struct bpf_tuple rtuple, ntuple = { + .prog = prog_new, + .link = link, + }, otuple = { + .prog = prog_old, + .link = link, + }; + int ret, idx = -ERANGE, tidx; + + if (revision && revision != bpf_mprog_revision(entry)) + return -ESTALE; + if (bpf_mprog_exists(entry, prog_new)) + return -EEXIST; + ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, + flags & ~BPF_F_REPLACE, + prog_new->type); + if (ret) + return ret; + if (flags & BPF_F_REPLACE) { + tidx = bpf_mprog_pos_exact(entry, &otuple); + if (tidx < 0) { + ret = tidx; + goto out; + } + idx = tidx; + } + if (flags & BPF_F_BEFORE) { + tidx = bpf_mprog_pos_before(entry, &rtuple); + if (tidx < -1 || (idx >= -1 && tidx != idx)) { + ret = tidx < -1 ? tidx : -ERANGE; + goto out; + } + idx = tidx; + } + if (flags & BPF_F_AFTER) { + tidx = bpf_mprog_pos_after(entry, &rtuple); + if (tidx < -1 || (idx >= -1 && tidx != idx)) { + ret = tidx < 0 ? tidx : -ERANGE; + goto out; + } + idx = tidx; + } + if (idx < -1) { + if (rtuple.prog || flags) { + ret = -EINVAL; + goto out; + } + idx = bpf_mprog_total(entry); + flags = BPF_F_AFTER; + } + if (idx >= bpf_mprog_max()) { + ret = -ERANGE; + goto out; + } + if (flags & BPF_F_REPLACE) + ret = bpf_mprog_replace(entry, entry_new, &ntuple, idx); + else + ret = bpf_mprog_insert(entry, entry_new, &ntuple, idx, flags); +out: + bpf_mprog_tuple_put(&rtuple); + return ret; +} + +static int bpf_mprog_fetch(struct bpf_mprog_entry *entry, + struct bpf_tuple *tuple, int idx) +{ + int total = bpf_mprog_total(entry); + struct bpf_mprog_cp *cp; + struct bpf_mprog_fp *fp; + struct bpf_prog *prog; + struct bpf_link *link; + + if (idx == -1) + idx = 0; + else if (idx == total) + idx = total - 1; + bpf_mprog_read(entry, idx, &fp, &cp); + prog = READ_ONCE(fp->prog); + link = cp->link; + /* The deletion request can either be without filled tuple in which + * case it gets populated here based on idx, or with filled tuple + * where the only thing we end up doing is the WARN_ON_ONCE() assert. + * If we hit a BPF link at the given index, it must not be removed + * from opts path. + */ + if (link && !tuple->link) + return -EBUSY; + WARN_ON_ONCE(tuple->prog && tuple->prog != prog); + WARN_ON_ONCE(tuple->link && tuple->link != link); + tuple->prog = prog; + tuple->link = link; + return 0; +} + +int bpf_mprog_detach(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_prog *prog, struct bpf_link *link, + u32 flags, u32 id_or_fd, u64 revision) +{ + struct bpf_tuple rtuple, dtuple = { + .prog = prog, + .link = link, + }; + int ret, idx = -ERANGE, tidx; + + if (flags & BPF_F_REPLACE) + return -EINVAL; + if (revision && revision != bpf_mprog_revision(entry)) + return -ESTALE; + ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, flags, + prog ? prog->type : + BPF_PROG_TYPE_UNSPEC); + if (ret) + return ret; + if (dtuple.prog) { + tidx = bpf_mprog_pos_exact(entry, &dtuple); + if (tidx < 0) { + ret = tidx; + goto out; + } + idx = tidx; + } + if (flags & BPF_F_BEFORE) { + tidx = bpf_mprog_pos_before(entry, &rtuple); + if (tidx < -1 || (idx >= -1 && tidx != idx)) { + ret = tidx < -1 ? tidx : -ERANGE; + goto out; + } + idx = tidx; + } + if (flags & BPF_F_AFTER) { + tidx = bpf_mprog_pos_after(entry, &rtuple); + if (tidx < -1 || (idx >= -1 && tidx != idx)) { + ret = tidx < 0 ? tidx : -ERANGE; + goto out; + } + idx = tidx; + } + if (idx < -1) { + if (rtuple.prog || flags) { + ret = -EINVAL; + goto out; + } + idx = bpf_mprog_total(entry); + flags = BPF_F_AFTER; + } + if (idx >= bpf_mprog_max()) { + ret = -ERANGE; + goto out; + } + ret = bpf_mprog_fetch(entry, &dtuple, idx); + if (ret) + goto out; + ret = bpf_mprog_delete(entry, entry_new, &dtuple, idx); +out: + bpf_mprog_tuple_put(&rtuple); + return ret; +} + +int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, + struct bpf_mprog_entry *entry) +{ + u32 __user *uprog_flags, *ulink_flags; + u32 __user *uprog_id, *ulink_id; + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + struct bpf_prog *prog; + const u32 flags = 0; + int i, ret = 0; + u32 id, count; + u64 revision; + + if (attr->query.query_flags || attr->query.attach_flags) + return -EINVAL; + revision = bpf_mprog_revision(entry); + count = bpf_mprog_total(entry); + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision))) + return -EFAULT; + if (copy_to_user(&uattr->query.count, &count, sizeof(count))) + return -EFAULT; + uprog_id = u64_to_user_ptr(attr->query.prog_ids); + uprog_flags = u64_to_user_ptr(attr->query.prog_attach_flags); + ulink_id = u64_to_user_ptr(attr->query.link_ids); + ulink_flags = u64_to_user_ptr(attr->query.link_attach_flags); + if (attr->query.count == 0 || !uprog_id || !count) + return 0; + if (attr->query.count < count) { + count = attr->query.count; + ret = -ENOSPC; + } + for (i = 0; i < bpf_mprog_max(); i++) { + bpf_mprog_read(entry, i, &fp, &cp); + prog = READ_ONCE(fp->prog); + if (!prog) + break; + id = prog->aux->id; + if (copy_to_user(uprog_id + i, &id, sizeof(id))) + return -EFAULT; + if (uprog_flags && + copy_to_user(uprog_flags + i, &flags, sizeof(flags))) + return -EFAULT; + id = cp->link ? cp->link->id : 0; + if (ulink_id && + copy_to_user(ulink_id + i, &id, sizeof(id))) + return -EFAULT; + if (ulink_flags && + copy_to_user(ulink_flags + i, &flags, sizeof(flags))) + return -EFAULT; + if (i + 1 == count) + break; + } + return ret; +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 600d0caebbd8..1c166870cdf3 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1113,7 +1113,12 @@ enum bpf_perf_event_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) #define BPF_F_ALLOW_MULTI (1U << 1) +/* Generic attachment flags. */ #define BPF_F_REPLACE (1U << 2) +#define BPF_F_BEFORE (1U << 3) +#define BPF_F_AFTER (1U << 4) +#define BPF_F_ID (1U << 5) +#define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -1444,14 +1449,19 @@ union bpf_attr { }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ - __u32 target_fd; /* container object to attach to */ - __u32 attach_bpf_fd; /* eBPF program to attach */ + union { + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ + }; + __u32 attach_bpf_fd; __u32 attach_type; __u32 attach_flags; - __u32 replace_bpf_fd; /* previously attached eBPF - * program to replace if - * BPF_F_REPLACE is used - */ + __u32 replace_bpf_fd; + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -1497,16 +1507,26 @@ union bpf_attr { } info; struct { /* anonymous struct used by BPF_PROG_QUERY command */ - __u32 target_fd; /* container object to query */ + union { + __u32 target_fd; /* target object to query or ... */ + __u32 target_ifindex; /* target ifindex */ + }; __u32 attach_type; __u32 query_flags; __u32 attach_flags; __aligned_u64 prog_ids; - __u32 prog_cnt; + union { + __u32 prog_cnt; + __u32 count; + }; + __u32 :32; /* output: per-program attach_flags. * not allowed to be set during effective query. */ __aligned_u64 prog_attach_flags; + __aligned_u64 link_ids; + __aligned_u64 link_attach_flags; + __u64 revision; } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ -- cgit v1.2.3 From e420bed025071a623d2720a92bc2245c84757ecb Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 19 Jul 2023 16:08:52 +0200 Subject: bpf: Add fd-based tcx multi-prog infra with link support This work refactors and adds a lightweight extension ("tcx") to the tc BPF ingress and egress data path side for allowing BPF program management based on fds via bpf() syscall through the newly added generic multi-prog API. The main goal behind this work which we also presented at LPC [0] last year and a recent update at LSF/MM/BPF this year [3] is to support long-awaited BPF link functionality for tc BPF programs, which allows for a model of safe ownership and program detachment. Given the rise in tc BPF users in cloud native environments, this becomes necessary to avoid hard to debug incidents either through stale leftover programs or 3rd party applications accidentally stepping on each others toes. As a recap, a BPF link represents the attachment of a BPF program to a BPF hook point. The BPF link holds a single reference to keep BPF program alive. Moreover, hook points do not reference a BPF link, only the application's fd or pinning does. A BPF link holds meta-data specific to attachment and implements operations for link creation, (atomic) BPF program update, detachment and introspection. The motivation for BPF links for tc BPF programs is multi-fold, for example: - From Meta: "It's especially important for applications that are deployed fleet-wide and that don't "control" hosts they are deployed to. If such application crashes and no one notices and does anything about that, BPF program will keep running draining resources or even just, say, dropping packets. We at FB had outages due to such permanent BPF attachment semantics. With fd-based BPF link we are getting a framework, which allows safe, auto-detachable behavior by default, unless application explicitly opts in by pinning the BPF link." [1] - From Cilium-side the tc BPF programs we attach to host-facing veth devices and phys devices build the core datapath for Kubernetes Pods, and they implement forwarding, load-balancing, policy, EDT-management, etc, within BPF. Currently there is no concept of 'safe' ownership, e.g. we've recently experienced hard-to-debug issues in a user's staging environment where another Kubernetes application using tc BPF attached to the same prio/handle of cls_bpf, accidentally wiping all Cilium-based BPF programs from underneath it. The goal is to establish a clear/safe ownership model via links which cannot accidentally be overridden. [0,2] BPF links for tc can co-exist with non-link attachments, and the semantics are in line also with XDP links: BPF links cannot replace other BPF links, BPF links cannot replace non-BPF links, non-BPF links cannot replace BPF links and lastly only non-BPF links can replace non-BPF links. In case of Cilium, this would solve mentioned issue of safe ownership model as 3rd party applications would not be able to accidentally wipe Cilium programs, even if they are not BPF link aware. Earlier attempts [4] have tried to integrate BPF links into core tc machinery to solve cls_bpf, which has been intrusive to the generic tc kernel API with extensions only specific to cls_bpf and suboptimal/complex since cls_bpf could be wiped from the qdisc also. Locking a tc BPF program in place this way, is getting into layering hacks given the two object models are vastly different. We instead implemented the tcx (tc 'express') layer which is an fd-based tc BPF attach API, so that the BPF link implementation blends in naturally similar to other link types which are fd-based and without the need for changing core tc internal APIs. BPF programs for tc can then be successively migrated from classic cls_bpf to the new tc BPF link without needing to change the program's source code, just the BPF loader mechanics for attaching is sufficient. For the current tc framework, there is no change in behavior with this change and neither does this change touch on tc core kernel APIs. The gist of this patch is that the ingress and egress hook have a lightweight, qdisc-less extension for BPF to attach its tc BPF programs, in other words, a minimal entry point for tc BPF. The name tcx has been suggested from discussion of earlier revisions of this work as a good fit, and to more easily differ between the classic cls_bpf attachment and the fd-based one. For the ingress and egress tcx points, the device holds a cache-friendly array with program pointers which is separated from control plane (slow-path) data. Earlier versions of this work used priority to determine ordering and expression of dependencies similar as with classic tc, but it was challenged that for something more future-proof a better user experience is required. Hence this resulted in the design and development of the generic attach/detach/query API for multi-progs. See prior patch with its discussion on the API design. tcx is the first user and later we plan to integrate also others, for example, one candidate is multi-prog support for XDP which would benefit and have the same 'look and feel' from API perspective. The goal with tcx is to have maximum compatibility to existing tc BPF programs, so they don't need to be rewritten specifically. Compatibility to call into classic tcf_classify() is also provided in order to allow successive migration or both to cleanly co-exist where needed given its all one logical tc layer and the tcx plus classic tc cls/act build one logical overall processing pipeline. tcx supports the simplified return codes TCX_NEXT which is non-terminating (go to next program) and terminating ones with TCX_PASS, TCX_DROP, TCX_REDIRECT. The fd-based API is behind a static key, so that when unused the code is also not entered. The struct tcx_entry's program array is currently static, but could be made dynamic if necessary at a point in future. The a/b pair swap design has been chosen so that for detachment there are no allocations which otherwise could fail. The work has been tested with tc-testing selftest suite which all passes, as well as the tc BPF tests from the BPF CI, and also with Cilium's L4LB. Thanks also to Nikolay Aleksandrov and Martin Lau for in-depth early reviews of this work. [0] https://lpc.events/event/16/contributions/1353/ [1] https://lore.kernel.org/bpf/CAEf4BzbokCJN33Nw_kg82sO=xppXnKWEncGTWCTB9vGCmLB6pw@mail.gmail.com [2] https://colocatedeventseu2023.sched.com/event/1Jo6O/tales-from-an-ebpf-programs-murder-mystery-hemanth-malla-guillaume-fournier-datadog [3] http://vger.kernel.org/bpfconf2023_material/tcx_meta_netdev_borkmann.pdf [4] https://lore.kernel.org/bpf/20210604063116.234316-1-memxor@gmail.com Signed-off-by: Daniel Borkmann Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230719140858.13224-3-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- MAINTAINERS | 4 +- include/linux/bpf_mprog.h | 9 ++ include/linux/netdevice.h | 15 +- include/linux/skbuff.h | 4 +- include/net/sch_generic.h | 2 +- include/net/tcx.h | 206 ++++++++++++++++++++++++ include/uapi/linux/bpf.h | 34 +++- kernel/bpf/Kconfig | 1 + kernel/bpf/Makefile | 1 + kernel/bpf/syscall.c | 82 ++++++++-- kernel/bpf/tcx.c | 348 +++++++++++++++++++++++++++++++++++++++++ net/Kconfig | 5 + net/core/dev.c | 265 +++++++++++++++++++------------ net/core/filter.c | 4 +- net/sched/Kconfig | 4 +- net/sched/sch_ingress.c | 61 +++++++- tools/include/uapi/linux/bpf.h | 34 +++- 17 files changed, 935 insertions(+), 144 deletions(-) create mode 100644 include/net/tcx.h create mode 100644 kernel/bpf/tcx.c (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 678bef9f60b4..990e3fce753c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3778,13 +3778,15 @@ L: netdev@vger.kernel.org S: Maintained F: kernel/bpf/bpf_struct* -BPF [NETWORKING] (tc BPF, sock_addr) +BPF [NETWORKING] (tcx & tc BPF, sock_addr) M: Martin KaFai Lau M: Daniel Borkmann R: John Fastabend L: bpf@vger.kernel.org L: netdev@vger.kernel.org S: Maintained +F: include/net/tcx.h +F: kernel/bpf/tcx.c F: net/core/filter.c F: net/sched/act_bpf.c F: net/sched/cls_bpf.c diff --git a/include/linux/bpf_mprog.h b/include/linux/bpf_mprog.h index 6feefec43422..2b429488f840 100644 --- a/include/linux/bpf_mprog.h +++ b/include/linux/bpf_mprog.h @@ -315,4 +315,13 @@ int bpf_mprog_detach(struct bpf_mprog_entry *entry, int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, struct bpf_mprog_entry *entry); +static inline bool bpf_mprog_supported(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_SCHED_CLS: + return true; + default: + return false; + } +} #endif /* __BPF_MPROG_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b12477ea4032..3800d0479698 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1930,8 +1930,7 @@ enum netdev_ml_priv_type { * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one - * @miniq_ingress: ingress/clsact qdisc specific data for - * ingress processing + * @tcx_ingress: BPF & clsact qdisc specific data for ingress processing * @ingress_queue: XXX: need comments on this one * @nf_hooks_ingress: netfilter hooks executed for ingress packets * @broadcast: hw bcast address @@ -1952,8 +1951,7 @@ enum netdev_ml_priv_type { * @xps_maps: all CPUs/RXQs maps for XPS device * * @xps_maps: XXX: need comments on this one - * @miniq_egress: clsact qdisc specific data for - * egress processing + * @tcx_egress: BPF & clsact qdisc specific data for egress processing * @nf_hooks_egress: netfilter hooks executed for egress packets * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by @@ -2253,9 +2251,8 @@ struct net_device { unsigned int xdp_zc_max_segs; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; - -#ifdef CONFIG_NET_CLS_ACT - struct mini_Qdisc __rcu *miniq_ingress; +#ifdef CONFIG_NET_XGRESS + struct bpf_mprog_entry __rcu *tcx_ingress; #endif struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS @@ -2283,8 +2280,8 @@ struct net_device { #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX]; #endif -#ifdef CONFIG_NET_CLS_ACT - struct mini_Qdisc __rcu *miniq_egress; +#ifdef CONFIG_NET_XGRESS + struct bpf_mprog_entry __rcu *tcx_egress; #endif #ifdef CONFIG_NETFILTER_EGRESS struct nf_hook_entries __rcu *nf_hooks_egress; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 91ed66952580..ed83f1c5fc1f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -944,7 +944,7 @@ struct sk_buff { __u8 __mono_tc_offset[0]; /* public: */ __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; #endif @@ -993,7 +993,7 @@ struct sk_buff { __u8 csum_not_inet:1; #endif -#ifdef CONFIG_NET_SCHED +#if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e92f73bb3198..15be2d96b06d 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -703,7 +703,7 @@ int skb_do_redirect(struct sk_buff *); static inline bool skb_at_tc_ingress(const struct sk_buff *skb) { -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_XGRESS return skb->tc_at_ingress; #else return false; diff --git a/include/net/tcx.h b/include/net/tcx.h new file mode 100644 index 000000000000..264f147953ba --- /dev/null +++ b/include/net/tcx.h @@ -0,0 +1,206 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Isovalent */ +#ifndef __NET_TCX_H +#define __NET_TCX_H + +#include +#include + +#include + +struct mini_Qdisc; + +struct tcx_entry { + struct mini_Qdisc __rcu *miniq; + struct bpf_mprog_bundle bundle; + bool miniq_active; + struct rcu_head rcu; +}; + +struct tcx_link { + struct bpf_link link; + struct net_device *dev; + u32 location; +}; + +static inline void tcx_set_ingress(struct sk_buff *skb, bool ingress) +{ +#ifdef CONFIG_NET_XGRESS + skb->tc_at_ingress = ingress; +#endif +} + +#ifdef CONFIG_NET_XGRESS +static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry) +{ + struct bpf_mprog_bundle *bundle = entry->parent; + + return container_of(bundle, struct tcx_entry, bundle); +} + +static inline struct tcx_link *tcx_link(struct bpf_link *link) +{ + return container_of(link, struct tcx_link, link); +} + +static inline const struct tcx_link *tcx_link_const(const struct bpf_link *link) +{ + return tcx_link((struct bpf_link *)link); +} + +void tcx_inc(void); +void tcx_dec(void); + +static inline void tcx_entry_sync(void) +{ + /* bpf_mprog_entry got a/b swapped, therefore ensure that + * there are no inflight users on the old one anymore. + */ + synchronize_rcu(); +} + +static inline void +tcx_entry_update(struct net_device *dev, struct bpf_mprog_entry *entry, + bool ingress) +{ + ASSERT_RTNL(); + if (ingress) + rcu_assign_pointer(dev->tcx_ingress, entry); + else + rcu_assign_pointer(dev->tcx_egress, entry); +} + +static inline struct bpf_mprog_entry * +tcx_entry_fetch(struct net_device *dev, bool ingress) +{ + ASSERT_RTNL(); + if (ingress) + return rcu_dereference_rtnl(dev->tcx_ingress); + else + return rcu_dereference_rtnl(dev->tcx_egress); +} + +static inline struct bpf_mprog_entry *tcx_entry_create(void) +{ + struct tcx_entry *tcx = kzalloc(sizeof(*tcx), GFP_KERNEL); + + if (tcx) { + bpf_mprog_bundle_init(&tcx->bundle); + return &tcx->bundle.a; + } + return NULL; +} + +static inline void tcx_entry_free(struct bpf_mprog_entry *entry) +{ + kfree_rcu(tcx_entry(entry), rcu); +} + +static inline struct bpf_mprog_entry * +tcx_entry_fetch_or_create(struct net_device *dev, bool ingress, bool *created) +{ + struct bpf_mprog_entry *entry = tcx_entry_fetch(dev, ingress); + + *created = false; + if (!entry) { + entry = tcx_entry_create(); + if (!entry) + return NULL; + *created = true; + } + return entry; +} + +static inline void tcx_skeys_inc(bool ingress) +{ + tcx_inc(); + if (ingress) + net_inc_ingress_queue(); + else + net_inc_egress_queue(); +} + +static inline void tcx_skeys_dec(bool ingress) +{ + if (ingress) + net_dec_ingress_queue(); + else + net_dec_egress_queue(); + tcx_dec(); +} + +static inline void tcx_miniq_set_active(struct bpf_mprog_entry *entry, + const bool active) +{ + ASSERT_RTNL(); + tcx_entry(entry)->miniq_active = active; +} + +static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry) +{ + ASSERT_RTNL(); + return bpf_mprog_total(entry) || tcx_entry(entry)->miniq_active; +} + +static inline enum tcx_action_base tcx_action_code(struct sk_buff *skb, + int code) +{ + switch (code) { + case TCX_PASS: + skb->tc_index = qdisc_skb_cb(skb)->tc_classid; + fallthrough; + case TCX_DROP: + case TCX_REDIRECT: + return code; + case TCX_NEXT: + default: + return TCX_NEXT; + } +} +#endif /* CONFIG_NET_XGRESS */ + +#if defined(CONFIG_NET_XGRESS) && defined(CONFIG_BPF_SYSCALL) +int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); +void tcx_uninstall(struct net_device *dev, bool ingress); + +int tcx_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); + +static inline void dev_tcx_uninstall(struct net_device *dev) +{ + ASSERT_RTNL(); + tcx_uninstall(dev, true); + tcx_uninstall(dev, false); +} +#else +static inline int tcx_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int tcx_link_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int tcx_prog_detach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int tcx_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} + +static inline void dev_tcx_uninstall(struct net_device *dev) +{ +} +#endif /* CONFIG_NET_XGRESS && CONFIG_BPF_SYSCALL */ +#endif /* __NET_TCX_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d4c07e435336..739c15906a65 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1036,6 +1036,8 @@ enum bpf_attach_type { BPF_LSM_CGROUP, BPF_STRUCT_OPS, BPF_NETFILTER, + BPF_TCX_INGRESS, + BPF_TCX_EGRESS, __MAX_BPF_ATTACH_TYPE }; @@ -1053,7 +1055,7 @@ enum bpf_link_type { BPF_LINK_TYPE_KPROBE_MULTI = 8, BPF_LINK_TYPE_STRUCT_OPS = 9, BPF_LINK_TYPE_NETFILTER = 10, - + BPF_LINK_TYPE_TCX = 11, MAX_BPF_LINK_TYPE, }; @@ -1569,13 +1571,13 @@ union bpf_attr { __u32 map_fd; /* struct_ops to attach */ }; union { - __u32 target_fd; /* object to attach to */ - __u32 target_ifindex; /* target ifindex */ + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ union { - __u32 target_btf_id; /* btf_id of target to attach to */ + __u32 target_btf_id; /* btf_id of target to attach to */ struct { __aligned_u64 iter_info; /* extra bpf_iter_link_info */ __u32 iter_info_len; /* iter_info length */ @@ -1609,6 +1611,13 @@ union bpf_attr { __s32 priority; __u32 flags; } netfilter; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } tcx; }; } link_create; @@ -6217,6 +6226,19 @@ struct bpf_sock_tuple { }; }; +/* (Simplified) user return codes for tcx prog type. + * A valid tcx program must return one of these defined values. All other + * return codes are reserved for future use. Must remain compatible with + * their TC_ACT_* counter-parts. For compatibility in behavior, unknown + * return codes are mapped to TCX_NEXT. + */ +enum tcx_action_base { + TCX_NEXT = -1, + TCX_PASS = 0, + TCX_DROP = 2, + TCX_REDIRECT = 7, +}; + struct bpf_xdp_sock { __u32 queue_id; }; @@ -6499,6 +6521,10 @@ struct bpf_link_info { } event; /* BPF_PERF_EVENT_EVENT */ }; } perf_event; + struct { + __u32 ifindex; + __u32 attach_type; + } tcx; }; } __attribute__((aligned(8))); diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig index 2dfe1079f772..6a906ff93006 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -31,6 +31,7 @@ config BPF_SYSCALL select TASKS_TRACE_RCU select BINARY_PRINTF select NET_SOCK_MSG if NET + select NET_XGRESS if NET select PAGE_POOL if NET default n help diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 1bea2eb912cd..f526b7573e97 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -21,6 +21,7 @@ obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o obj-$(CONFIG_BPF_SYSCALL) += offload.o obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o +obj-$(CONFIG_BPF_SYSCALL) += tcx.o endif ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ee8cb1a174aa..7f4e8c357a6a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -37,6 +37,8 @@ #include #include +#include + #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) @@ -3740,31 +3742,45 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) return BPF_PROG_TYPE_XDP; case BPF_LSM_CGROUP: return BPF_PROG_TYPE_LSM; + case BPF_TCX_INGRESS: + case BPF_TCX_EGRESS: + return BPF_PROG_TYPE_SCHED_CLS; default: return BPF_PROG_TYPE_UNSPEC; } } -#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd +#define BPF_PROG_ATTACH_LAST_FIELD expected_revision + +#define BPF_F_ATTACH_MASK_BASE \ + (BPF_F_ALLOW_OVERRIDE | \ + BPF_F_ALLOW_MULTI | \ + BPF_F_REPLACE) -#define BPF_F_ATTACH_MASK \ - (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) +#define BPF_F_ATTACH_MASK_MPROG \ + (BPF_F_REPLACE | \ + BPF_F_BEFORE | \ + BPF_F_AFTER | \ + BPF_F_ID | \ + BPF_F_LINK) static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; struct bpf_prog *prog; + u32 mask; int ret; if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; - if (attr->attach_flags & ~BPF_F_ATTACH_MASK) - return -EINVAL; - ptype = attach_type_to_prog_type(attr->attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; + mask = bpf_mprog_supported(ptype) ? + BPF_F_ATTACH_MASK_MPROG : BPF_F_ATTACH_MASK_BASE; + if (attr->attach_flags & ~mask) + return -EINVAL; prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) @@ -3800,6 +3816,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) else ret = cgroup_bpf_prog_attach(attr, ptype, prog); break; + case BPF_PROG_TYPE_SCHED_CLS: + ret = tcx_prog_attach(attr, prog); + break; default: ret = -EINVAL; } @@ -3809,25 +3828,41 @@ static int bpf_prog_attach(const union bpf_attr *attr) return ret; } -#define BPF_PROG_DETACH_LAST_FIELD attach_type +#define BPF_PROG_DETACH_LAST_FIELD expected_revision static int bpf_prog_detach(const union bpf_attr *attr) { + struct bpf_prog *prog = NULL; enum bpf_prog_type ptype; + int ret; if (CHECK_ATTR(BPF_PROG_DETACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); + if (bpf_mprog_supported(ptype)) { + if (ptype == BPF_PROG_TYPE_UNSPEC) + return -EINVAL; + if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) + return -EINVAL; + if (attr->attach_bpf_fd) { + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + return PTR_ERR(prog); + } + } switch (ptype) { case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: - return sock_map_prog_detach(attr, ptype); + ret = sock_map_prog_detach(attr, ptype); + break; case BPF_PROG_TYPE_LIRC_MODE2: - return lirc_prog_detach(attr); + ret = lirc_prog_detach(attr); + break; case BPF_PROG_TYPE_FLOW_DISSECTOR: - return netns_bpf_prog_detach(attr, ptype); + ret = netns_bpf_prog_detach(attr, ptype); + break; case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: @@ -3836,13 +3871,21 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_LSM: - return cgroup_bpf_prog_detach(attr, ptype); + ret = cgroup_bpf_prog_detach(attr, ptype); + break; + case BPF_PROG_TYPE_SCHED_CLS: + ret = tcx_prog_detach(attr, prog); + break; default: - return -EINVAL; + ret = -EINVAL; } + + if (prog) + bpf_prog_put(prog); + return ret; } -#define BPF_PROG_QUERY_LAST_FIELD query.prog_attach_flags +#define BPF_PROG_QUERY_LAST_FIELD query.link_attach_flags static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -3890,6 +3933,9 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_SK_MSG_VERDICT: case BPF_SK_SKB_VERDICT: return sock_map_bpf_prog_query(attr, uattr); + case BPF_TCX_INGRESS: + case BPF_TCX_EGRESS: + return tcx_prog_query(attr, uattr); default: return -EINVAL; } @@ -4852,6 +4898,13 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) goto out; } break; + case BPF_PROG_TYPE_SCHED_CLS: + if (attr->link_create.attach_type != BPF_TCX_INGRESS && + attr->link_create.attach_type != BPF_TCX_EGRESS) { + ret = -EINVAL; + goto out; + } + break; default: ptype = attach_type_to_prog_type(attr->link_create.attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) { @@ -4903,6 +4956,9 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) case BPF_PROG_TYPE_XDP: ret = bpf_xdp_link_attach(attr, prog); break; + case BPF_PROG_TYPE_SCHED_CLS: + ret = tcx_link_attach(attr, prog); + break; case BPF_PROG_TYPE_NETFILTER: ret = bpf_nf_link_attach(attr, prog); break; diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c new file mode 100644 index 000000000000..69a272712b29 --- /dev/null +++ b/kernel/bpf/tcx.c @@ -0,0 +1,348 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ + +#include +#include +#include + +#include + +int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + bool created, ingress = attr->attach_type == BPF_TCX_INGRESS; + struct net *net = current->nsproxy->net_ns; + struct bpf_mprog_entry *entry, *entry_new; + struct bpf_prog *replace_prog = NULL; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = __dev_get_by_index(net, attr->target_ifindex); + if (!dev) { + ret = -ENODEV; + goto out; + } + if (attr->attach_flags & BPF_F_REPLACE) { + replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, + prog->type); + if (IS_ERR(replace_prog)) { + ret = PTR_ERR(replace_prog); + replace_prog = NULL; + goto out; + } + } + entry = tcx_entry_fetch_or_create(dev, ingress, &created); + if (!entry) { + ret = -ENOMEM; + goto out; + } + ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog, + attr->attach_flags, attr->relative_fd, + attr->expected_revision); + if (!ret) { + if (entry != entry_new) { + tcx_entry_update(dev, entry_new, ingress); + tcx_entry_sync(); + tcx_skeys_inc(ingress); + } + bpf_mprog_commit(entry); + } else if (created) { + tcx_entry_free(entry); + } +out: + if (replace_prog) + bpf_prog_put(replace_prog); + rtnl_unlock(); + return ret; +} + +int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + bool ingress = attr->attach_type == BPF_TCX_INGRESS; + struct net *net = current->nsproxy->net_ns; + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = __dev_get_by_index(net, attr->target_ifindex); + if (!dev) { + ret = -ENODEV; + goto out; + } + entry = tcx_entry_fetch(dev, ingress); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags, + attr->relative_fd, attr->expected_revision); + if (!ret) { + if (!tcx_entry_is_active(entry_new)) + entry_new = NULL; + tcx_entry_update(dev, entry_new, ingress); + tcx_entry_sync(); + tcx_skeys_dec(ingress); + bpf_mprog_commit(entry); + if (!entry_new) + tcx_entry_free(entry); + } +out: + rtnl_unlock(); + return ret; +} + +void tcx_uninstall(struct net_device *dev, bool ingress) +{ + struct bpf_tuple tuple = {}; + struct bpf_mprog_entry *entry; + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + + entry = tcx_entry_fetch(dev, ingress); + if (!entry) + return; + tcx_entry_update(dev, NULL, ingress); + tcx_entry_sync(); + bpf_mprog_foreach_tuple(entry, fp, cp, tuple) { + if (tuple.link) + tcx_link(tuple.link)->dev = NULL; + else + bpf_prog_put(tuple.prog); + tcx_skeys_dec(ingress); + } + WARN_ON_ONCE(tcx_entry(entry)->miniq_active); + tcx_entry_free(entry); +} + +int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) +{ + bool ingress = attr->query.attach_type == BPF_TCX_INGRESS; + struct net *net = current->nsproxy->net_ns; + struct bpf_mprog_entry *entry; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = __dev_get_by_index(net, attr->query.target_ifindex); + if (!dev) { + ret = -ENODEV; + goto out; + } + entry = tcx_entry_fetch(dev, ingress); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_query(attr, uattr, entry); +out: + rtnl_unlock(); + return ret; +} + +static int tcx_link_prog_attach(struct bpf_link *link, u32 flags, u32 id_or_fd, + u64 revision) +{ + struct tcx_link *tcx = tcx_link(link); + bool created, ingress = tcx->location == BPF_TCX_INGRESS; + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev = tcx->dev; + int ret; + + ASSERT_RTNL(); + entry = tcx_entry_fetch_or_create(dev, ingress, &created); + if (!entry) + return -ENOMEM; + ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags, + id_or_fd, revision); + if (!ret) { + if (entry != entry_new) { + tcx_entry_update(dev, entry_new, ingress); + tcx_entry_sync(); + tcx_skeys_inc(ingress); + } + bpf_mprog_commit(entry); + } else if (created) { + tcx_entry_free(entry); + } + return ret; +} + +static void tcx_link_release(struct bpf_link *link) +{ + struct tcx_link *tcx = tcx_link(link); + bool ingress = tcx->location == BPF_TCX_INGRESS; + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + dev = tcx->dev; + if (!dev) + goto out; + entry = tcx_entry_fetch(dev, ingress); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0); + if (!ret) { + if (!tcx_entry_is_active(entry_new)) + entry_new = NULL; + tcx_entry_update(dev, entry_new, ingress); + tcx_entry_sync(); + tcx_skeys_dec(ingress); + bpf_mprog_commit(entry); + if (!entry_new) + tcx_entry_free(entry); + tcx->dev = NULL; + } +out: + WARN_ON_ONCE(ret); + rtnl_unlock(); +} + +static int tcx_link_update(struct bpf_link *link, struct bpf_prog *nprog, + struct bpf_prog *oprog) +{ + struct tcx_link *tcx = tcx_link(link); + bool ingress = tcx->location == BPF_TCX_INGRESS; + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + dev = tcx->dev; + if (!dev) { + ret = -ENOLINK; + goto out; + } + if (oprog && link->prog != oprog) { + ret = -EPERM; + goto out; + } + oprog = link->prog; + if (oprog == nprog) { + bpf_prog_put(nprog); + goto out; + } + entry = tcx_entry_fetch(dev, ingress); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog, + BPF_F_REPLACE | BPF_F_ID, + link->prog->aux->id, 0); + if (!ret) { + WARN_ON_ONCE(entry != entry_new); + oprog = xchg(&link->prog, nprog); + bpf_prog_put(oprog); + bpf_mprog_commit(entry); + } +out: + rtnl_unlock(); + return ret; +} + +static void tcx_link_dealloc(struct bpf_link *link) +{ + kfree(tcx_link(link)); +} + +static void tcx_link_fdinfo(const struct bpf_link *link, struct seq_file *seq) +{ + const struct tcx_link *tcx = tcx_link_const(link); + u32 ifindex = 0; + + rtnl_lock(); + if (tcx->dev) + ifindex = tcx->dev->ifindex; + rtnl_unlock(); + + seq_printf(seq, "ifindex:\t%u\n", ifindex); + seq_printf(seq, "attach_type:\t%u (%s)\n", + tcx->location, + tcx->location == BPF_TCX_INGRESS ? "ingress" : "egress"); +} + +static int tcx_link_fill_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + const struct tcx_link *tcx = tcx_link_const(link); + u32 ifindex = 0; + + rtnl_lock(); + if (tcx->dev) + ifindex = tcx->dev->ifindex; + rtnl_unlock(); + + info->tcx.ifindex = ifindex; + info->tcx.attach_type = tcx->location; + return 0; +} + +static int tcx_link_detach(struct bpf_link *link) +{ + tcx_link_release(link); + return 0; +} + +static const struct bpf_link_ops tcx_link_lops = { + .release = tcx_link_release, + .detach = tcx_link_detach, + .dealloc = tcx_link_dealloc, + .update_prog = tcx_link_update, + .show_fdinfo = tcx_link_fdinfo, + .fill_link_info = tcx_link_fill_info, +}; + +static int tcx_link_init(struct tcx_link *tcx, + struct bpf_link_primer *link_primer, + const union bpf_attr *attr, + struct net_device *dev, + struct bpf_prog *prog) +{ + bpf_link_init(&tcx->link, BPF_LINK_TYPE_TCX, &tcx_link_lops, prog); + tcx->location = attr->link_create.attach_type; + tcx->dev = dev; + return bpf_link_prime(&tcx->link, link_primer); +} + +int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct net *net = current->nsproxy->net_ns; + struct bpf_link_primer link_primer; + struct net_device *dev; + struct tcx_link *tcx; + int ret; + + rtnl_lock(); + dev = __dev_get_by_index(net, attr->link_create.target_ifindex); + if (!dev) { + ret = -ENODEV; + goto out; + } + tcx = kzalloc(sizeof(*tcx), GFP_USER); + if (!tcx) { + ret = -ENOMEM; + goto out; + } + ret = tcx_link_init(tcx, &link_primer, attr, dev, prog); + if (ret) { + kfree(tcx); + goto out; + } + ret = tcx_link_prog_attach(&tcx->link, attr->link_create.flags, + attr->link_create.tcx.relative_fd, + attr->link_create.tcx.expected_revision); + if (ret) { + tcx->dev = NULL; + bpf_link_cleanup(&link_primer); + goto out; + } + ret = bpf_link_settle(&link_primer); +out: + rtnl_unlock(); + return ret; +} diff --git a/net/Kconfig b/net/Kconfig index 2fb25b534df5..d532ec33f1fe 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -52,6 +52,11 @@ config NET_INGRESS config NET_EGRESS bool +config NET_XGRESS + select NET_INGRESS + select NET_EGRESS + bool + config NET_REDIRECT bool diff --git a/net/core/dev.c b/net/core/dev.c index dd4f114a7cbf..8e7d0cb540cd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -107,6 +107,7 @@ #include #include #include +#include #include #include #include @@ -154,7 +155,6 @@ #include "dev.h" #include "net-sysfs.h" - static DEFINE_SPINLOCK(ptype_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; struct list_head ptype_all __read_mostly; /* Taps */ @@ -3882,69 +3882,198 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) EXPORT_SYMBOL(dev_loopback_xmit); #ifdef CONFIG_NET_EGRESS -static struct sk_buff * -sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) +static struct netdev_queue * +netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) +{ + int qm = skb_get_queue_mapping(skb); + + return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); +} + +static bool netdev_xmit_txqueue_skipped(void) { + return __this_cpu_read(softnet_data.xmit.skip_txqueue); +} + +void netdev_xmit_skip_txqueue(bool skip) +{ + __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); +} +EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); +#endif /* CONFIG_NET_EGRESS */ + +#ifdef CONFIG_NET_XGRESS +static int tc_run(struct tcx_entry *entry, struct sk_buff *skb) +{ + int ret = TC_ACT_UNSPEC; #ifdef CONFIG_NET_CLS_ACT - struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress); - struct tcf_result cl_res; + struct mini_Qdisc *miniq = rcu_dereference_bh(entry->miniq); + struct tcf_result res; if (!miniq) - return skb; + return ret; - /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ tc_skb_cb(skb)->mru = 0; tc_skb_cb(skb)->post_ct = false; - mini_qdisc_bstats_cpu_update(miniq, skb); - switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) { + mini_qdisc_bstats_cpu_update(miniq, skb); + ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false); + /* Only tcf related quirks below. */ + switch (ret) { + case TC_ACT_SHOT: + mini_qdisc_qstats_cpu_drop(miniq); + break; case TC_ACT_OK: case TC_ACT_RECLASSIFY: - skb->tc_index = TC_H_MIN(cl_res.classid); + skb->tc_index = TC_H_MIN(res.classid); break; + } +#endif /* CONFIG_NET_CLS_ACT */ + return ret; +} + +static DEFINE_STATIC_KEY_FALSE(tcx_needed_key); + +void tcx_inc(void) +{ + static_branch_inc(&tcx_needed_key); +} + +void tcx_dec(void) +{ + static_branch_dec(&tcx_needed_key); +} + +static __always_inline enum tcx_action_base +tcx_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb, + const bool needs_mac) +{ + const struct bpf_mprog_fp *fp; + const struct bpf_prog *prog; + int ret = TCX_NEXT; + + if (needs_mac) + __skb_push(skb, skb->mac_len); + bpf_mprog_foreach_prog(entry, fp, prog) { + bpf_compute_data_pointers(skb); + ret = bpf_prog_run(prog, skb); + if (ret != TCX_NEXT) + break; + } + if (needs_mac) + __skb_pull(skb, skb->mac_len); + return tcx_action_code(skb, ret); +} + +static __always_inline struct sk_buff * +sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, + struct net_device *orig_dev, bool *another) +{ + struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress); + int sch_ret; + + if (!entry) + return skb; + if (*pt_prev) { + *ret = deliver_skb(skb, *pt_prev, orig_dev); + *pt_prev = NULL; + } + + qdisc_skb_cb(skb)->pkt_len = skb->len; + tcx_set_ingress(skb, true); + + if (static_branch_unlikely(&tcx_needed_key)) { + sch_ret = tcx_run(entry, skb, true); + if (sch_ret != TC_ACT_UNSPEC) + goto ingress_verdict; + } + sch_ret = tc_run(tcx_entry(entry), skb); +ingress_verdict: + switch (sch_ret) { + case TC_ACT_REDIRECT: + /* skb_mac_header check was done by BPF, so we can safely + * push the L2 header back before redirecting to another + * netdev. + */ + __skb_push(skb, skb->mac_len); + if (skb_do_redirect(skb) == -EAGAIN) { + __skb_pull(skb, skb->mac_len); + *another = true; + break; + } + *ret = NET_RX_SUCCESS; + return NULL; case TC_ACT_SHOT: - mini_qdisc_qstats_cpu_drop(miniq); - *ret = NET_XMIT_DROP; - kfree_skb_reason(skb, SKB_DROP_REASON_TC_EGRESS); + kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS); + *ret = NET_RX_DROP; return NULL; + /* used by tc_run */ case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: - *ret = NET_XMIT_SUCCESS; consume_skb(skb); + fallthrough; + case TC_ACT_CONSUMED: + *ret = NET_RX_SUCCESS; return NULL; + } + + return skb; +} + +static __always_inline struct sk_buff * +sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) +{ + struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress); + int sch_ret; + + if (!entry) + return skb; + + /* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was + * already set by the caller. + */ + if (static_branch_unlikely(&tcx_needed_key)) { + sch_ret = tcx_run(entry, skb, false); + if (sch_ret != TC_ACT_UNSPEC) + goto egress_verdict; + } + sch_ret = tc_run(tcx_entry(entry), skb); +egress_verdict: + switch (sch_ret) { case TC_ACT_REDIRECT: /* No need to push/pop skb's mac_header here on egress! */ skb_do_redirect(skb); *ret = NET_XMIT_SUCCESS; return NULL; - default: - break; + case TC_ACT_SHOT: + kfree_skb_reason(skb, SKB_DROP_REASON_TC_EGRESS); + *ret = NET_XMIT_DROP; + return NULL; + /* used by tc_run */ + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + *ret = NET_XMIT_SUCCESS; + return NULL; } -#endif /* CONFIG_NET_CLS_ACT */ return skb; } - -static struct netdev_queue * -netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) -{ - int qm = skb_get_queue_mapping(skb); - - return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); -} - -static bool netdev_xmit_txqueue_skipped(void) +#else +static __always_inline struct sk_buff * +sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, + struct net_device *orig_dev, bool *another) { - return __this_cpu_read(softnet_data.xmit.skip_txqueue); + return skb; } -void netdev_xmit_skip_txqueue(bool skip) +static __always_inline struct sk_buff * +sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { - __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); + return skb; } -EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); -#endif /* CONFIG_NET_EGRESS */ +#endif /* CONFIG_NET_XGRESS */ #ifdef CONFIG_XPS static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, @@ -4128,9 +4257,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) skb_update_prio(skb); qdisc_pkt_len_init(skb); -#ifdef CONFIG_NET_CLS_ACT - skb->tc_at_ingress = 0; -#endif + tcx_set_ingress(skb, false); #ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { if (nf_hook_egress_active()) { @@ -5064,72 +5191,6 @@ int (*br_fdb_test_addr_hook)(struct net_device *dev, EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif -static inline struct sk_buff * -sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, - struct net_device *orig_dev, bool *another) -{ -#ifdef CONFIG_NET_CLS_ACT - struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress); - struct tcf_result cl_res; - - /* If there's at least one ingress present somewhere (so - * we get here via enabled static key), remaining devices - * that are not configured with an ingress qdisc will bail - * out here. - */ - if (!miniq) - return skb; - - if (*pt_prev) { - *ret = deliver_skb(skb, *pt_prev, orig_dev); - *pt_prev = NULL; - } - - qdisc_skb_cb(skb)->pkt_len = skb->len; - tc_skb_cb(skb)->mru = 0; - tc_skb_cb(skb)->post_ct = false; - skb->tc_at_ingress = 1; - mini_qdisc_bstats_cpu_update(miniq, skb); - - switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) { - case TC_ACT_OK: - case TC_ACT_RECLASSIFY: - skb->tc_index = TC_H_MIN(cl_res.classid); - break; - case TC_ACT_SHOT: - mini_qdisc_qstats_cpu_drop(miniq); - kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS); - *ret = NET_RX_DROP; - return NULL; - case TC_ACT_STOLEN: - case TC_ACT_QUEUED: - case TC_ACT_TRAP: - consume_skb(skb); - *ret = NET_RX_SUCCESS; - return NULL; - case TC_ACT_REDIRECT: - /* skb_mac_header check was done by cls/act_bpf, so - * we can safely push the L2 header back before - * redirecting to another netdev - */ - __skb_push(skb, skb->mac_len); - if (skb_do_redirect(skb) == -EAGAIN) { - __skb_pull(skb, skb->mac_len); - *another = true; - break; - } - *ret = NET_RX_SUCCESS; - return NULL; - case TC_ACT_CONSUMED: - *ret = NET_RX_SUCCESS; - return NULL; - default: - break; - } -#endif /* CONFIG_NET_CLS_ACT */ - return skb; -} - /** * netdev_is_rx_handler_busy - check if receive handler is registered * @dev: device to check @@ -10835,7 +10896,7 @@ void unregister_netdevice_many_notify(struct list_head *head, /* Shutdown queueing discipline. */ dev_shutdown(dev); - + dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); bpf_dev_bound_netdev_unregister(dev); diff --git a/net/core/filter.c b/net/core/filter.c index b4410dc841a0..797e8f039696 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -9307,7 +9307,7 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_XGRESS /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. * Thus, read skb->tstamp as is if tstamp_type_access is true. @@ -9341,7 +9341,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, __u8 value_reg = si->src_reg; __u8 skb_reg = si->dst_reg; -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_XGRESS /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. * Thus, write skb->tstamp as is if tstamp_type_access is true. diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 4b95cb1ac435..470c70deffe2 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -347,8 +347,7 @@ config NET_SCH_FQ_PIE config NET_SCH_INGRESS tristate "Ingress/classifier-action Qdisc" depends on NET_CLS_ACT - select NET_INGRESS - select NET_EGRESS + select NET_XGRESS help Say Y here if you want to use classifiers for incoming and/or outgoing packets. This qdisc doesn't do anything else besides running classifiers, @@ -679,6 +678,7 @@ config NET_EMATCH_IPT config NET_CLS_ACT bool "Actions" select NET_CLS + select NET_XGRESS help Say Y here if you want to use traffic control actions. Actions get attached to classifiers and are invoked after a successful diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index e43a45499372..04e886f6cee4 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -13,6 +13,7 @@ #include #include #include +#include struct ingress_sched_data { struct tcf_block *block; @@ -78,6 +79,8 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, { struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); + struct bpf_mprog_entry *entry; + bool created; int err; if (sch->parent != TC_H_INGRESS) @@ -85,7 +88,13 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, net_inc_ingress_queue(); - mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); + entry = tcx_entry_fetch_or_create(dev, true, &created); + if (!entry) + return -ENOMEM; + tcx_miniq_set_active(entry, true); + mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq); + if (created) + tcx_entry_update(dev, entry, true); q->block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; q->block_info.chain_head_change = clsact_chain_head_change; @@ -103,11 +112,22 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, static void ingress_destroy(struct Qdisc *sch) { struct ingress_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct bpf_mprog_entry *entry = rtnl_dereference(dev->tcx_ingress); if (sch->parent != TC_H_INGRESS) return; tcf_block_put_ext(q->block, sch, &q->block_info); + + if (entry) { + tcx_miniq_set_active(entry, false); + if (!tcx_entry_is_active(entry)) { + tcx_entry_update(dev, NULL, false); + tcx_entry_free(entry); + } + } + net_dec_ingress_queue(); } @@ -223,6 +243,8 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, { struct clsact_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); + struct bpf_mprog_entry *entry; + bool created; int err; if (sch->parent != TC_H_CLSACT) @@ -231,7 +253,13 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, net_inc_ingress_queue(); net_inc_egress_queue(); - mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress); + entry = tcx_entry_fetch_or_create(dev, true, &created); + if (!entry) + return -ENOMEM; + tcx_miniq_set_active(entry, true); + mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq); + if (created) + tcx_entry_update(dev, entry, true); q->ingress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; q->ingress_block_info.chain_head_change = clsact_chain_head_change; @@ -244,7 +272,13 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, mini_qdisc_pair_block_init(&q->miniqp_ingress, q->ingress_block); - mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress); + entry = tcx_entry_fetch_or_create(dev, false, &created); + if (!entry) + return -ENOMEM; + tcx_miniq_set_active(entry, true); + mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq); + if (created) + tcx_entry_update(dev, entry, false); q->egress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS; q->egress_block_info.chain_head_change = clsact_chain_head_change; @@ -256,12 +290,31 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, static void clsact_destroy(struct Qdisc *sch) { struct clsact_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct bpf_mprog_entry *ingress_entry = rtnl_dereference(dev->tcx_ingress); + struct bpf_mprog_entry *egress_entry = rtnl_dereference(dev->tcx_egress); if (sch->parent != TC_H_CLSACT) return; - tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); + tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); + + if (ingress_entry) { + tcx_miniq_set_active(ingress_entry, false); + if (!tcx_entry_is_active(ingress_entry)) { + tcx_entry_update(dev, NULL, true); + tcx_entry_free(ingress_entry); + } + } + + if (egress_entry) { + tcx_miniq_set_active(egress_entry, false); + if (!tcx_entry_is_active(egress_entry)) { + tcx_entry_update(dev, NULL, false); + tcx_entry_free(egress_entry); + } + } net_dec_ingress_queue(); net_dec_egress_queue(); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1c166870cdf3..47b76925189f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1036,6 +1036,8 @@ enum bpf_attach_type { BPF_LSM_CGROUP, BPF_STRUCT_OPS, BPF_NETFILTER, + BPF_TCX_INGRESS, + BPF_TCX_EGRESS, __MAX_BPF_ATTACH_TYPE }; @@ -1053,7 +1055,7 @@ enum bpf_link_type { BPF_LINK_TYPE_KPROBE_MULTI = 8, BPF_LINK_TYPE_STRUCT_OPS = 9, BPF_LINK_TYPE_NETFILTER = 10, - + BPF_LINK_TYPE_TCX = 11, MAX_BPF_LINK_TYPE, }; @@ -1569,13 +1571,13 @@ union bpf_attr { __u32 map_fd; /* struct_ops to attach */ }; union { - __u32 target_fd; /* object to attach to */ - __u32 target_ifindex; /* target ifindex */ + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ union { - __u32 target_btf_id; /* btf_id of target to attach to */ + __u32 target_btf_id; /* btf_id of target to attach to */ struct { __aligned_u64 iter_info; /* extra bpf_iter_link_info */ __u32 iter_info_len; /* iter_info length */ @@ -1609,6 +1611,13 @@ union bpf_attr { __s32 priority; __u32 flags; } netfilter; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } tcx; }; } link_create; @@ -6217,6 +6226,19 @@ struct bpf_sock_tuple { }; }; +/* (Simplified) user return codes for tcx prog type. + * A valid tcx program must return one of these defined values. All other + * return codes are reserved for future use. Must remain compatible with + * their TC_ACT_* counter-parts. For compatibility in behavior, unknown + * return codes are mapped to TCX_NEXT. + */ +enum tcx_action_base { + TCX_NEXT = -1, + TCX_PASS = 0, + TCX_DROP = 2, + TCX_REDIRECT = 7, +}; + struct bpf_xdp_sock { __u32 queue_id; }; @@ -6499,6 +6521,10 @@ struct bpf_link_info { } event; /* BPF_PERF_EVENT_EVENT */ }; } perf_event; + struct { + __u32 ifindex; + __u32 attach_type; + } tcx; }; } __attribute__((aligned(8))); -- cgit v1.2.3 From 6f5a630d7c57cd79b1f526a95e757311e32d41e5 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 18 Jul 2023 16:40:21 -0700 Subject: bpf, net: Introduce skb_pointer_if_linear(). Network drivers always call skb_header_pointer() with non-null buffer. Remove !buffer check to prevent accidental misuse of skb_header_pointer(). Introduce skb_pointer_if_linear() instead. Reported-by: Jakub Kicinski Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230718234021.43640-1-alexei.starovoitov@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/skbuff.h | 10 +++++++++- kernel/bpf/helpers.c | 5 ++++- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ed83f1c5fc1f..faaba050f843 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4023,7 +4023,7 @@ __skb_header_pointer(const struct sk_buff *skb, int offset, int len, if (likely(hlen - offset >= len)) return (void *)data + offset; - if (!skb || !buffer || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) + if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; @@ -4036,6 +4036,14 @@ skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) skb_headlen(skb), buffer); } +static inline void * __must_check +skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) +{ + if (likely(skb_headlen(skb) - offset >= len)) + return skb->data + offset; + return NULL; +} + /** * skb_needs_linearize - check if we need to linearize a given skb * depending on the given device features. diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index bcff584985e7..56ce5008aedd 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2263,7 +2263,10 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset case BPF_DYNPTR_TYPE_RINGBUF: return ptr->data + ptr->offset + offset; case BPF_DYNPTR_TYPE_SKB: - return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt); + if (buffer__opt) + return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt); + else + return skb_pointer_if_linear(ptr->data, ptr->offset + offset, len); case BPF_DYNPTR_TYPE_XDP: { void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len); -- cgit v1.2.3 From 730b9051b8bce5eabd1f5b67dfd090c37d5dabea Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 18 Jul 2023 16:16:20 +0000 Subject: tcp: remove tcp_send_partial() This function does not exist. Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230718161620.1391951-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 2104a71c75ba..8d1f1af5e02a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -606,7 +606,6 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, unsigned int mss_now, gfp_t gfp); void tcp_send_probe0(struct sock *); -void tcp_send_partial(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); -- cgit v1.2.3 From 03b123debcbc8db987bda17ed8412cc011064c22 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 18 Jul 2023 16:20:49 +0000 Subject: tcp: tcp_enter_quickack_mode() should be static After commit d2ccd7bc8acd ("tcp: avoid resetting ACK timer in DCTCP"), tcp_enter_quickack_mode() is only used from net/ipv4/tcp_input.c. Fixes: d2ccd7bc8acd ("tcp: avoid resetting ACK timer in DCTCP") Signed-off-by: Eric Dumazet Cc: Yuchung Cheng Cc: Neal Cardwell Link: https://lore.kernel.org/r/20230718162049.1444938-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 1 - net/ipv4/tcp_input.c | 3 +-- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 8d1f1af5e02a..c5fb90079920 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -350,7 +350,6 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule); -void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3cd92035e090..e2affdd147da 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -297,7 +297,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.quick = quickacks; } -void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) +static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -305,7 +305,6 @@ void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } -EXPORT_SYMBOL(tcp_enter_quickack_mode); /* Send ACKs quickly, if "quick" count is not exhausted * and the session is not interactive. -- cgit v1.2.3 From 4914109a8e1e494c6aa9852f9e84ec77a5fc643f Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 16 Jul 2023 17:09:17 -0400 Subject: netfilter: allow exp not to be removed in nf_ct_find_expectation Currently nf_conntrack_in() calling nf_ct_find_expectation() will remove the exp from the hash table. However, in some scenario, we expect the exp not to be removed when the created ct will not be confirmed, like in OVS and TC conntrack in the following patches. This patch allows exp not to be removed by setting IPS_CONFIRMED in the status of the tmpl. Signed-off-by: Xin Long Acked-by: Aaron Conole Acked-by: Florian Westphal Signed-off-by: Paolo Abeni --- include/net/netfilter/nf_conntrack_expect.h | 2 +- net/netfilter/nf_conntrack_core.c | 2 +- net/netfilter/nf_conntrack_expect.c | 4 ++-- net/netfilter/nft_ct.c | 2 ++ 4 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index cf0d81be5a96..165e7a03b8e9 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -100,7 +100,7 @@ nf_ct_expect_find_get(struct net *net, struct nf_conntrack_expect * nf_ct_find_expectation(struct net *net, const struct nf_conntrack_zone *zone, - const struct nf_conntrack_tuple *tuple); + const struct nf_conntrack_tuple *tuple, bool unlink); void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, u32 portid, int report); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 992393102d5f..9f6f2e643575 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1756,7 +1756,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, cnet = nf_ct_pernet(net); if (cnet->expect_count) { spin_lock_bh(&nf_conntrack_expect_lock); - exp = nf_ct_find_expectation(net, zone, tuple); + exp = nf_ct_find_expectation(net, zone, tuple, !tmpl || nf_ct_is_confirmed(tmpl)); if (exp) { /* Welcome, Mr. Bond. We've been expecting you... */ __set_bit(IPS_EXPECTED_BIT, &ct->status); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 96948e98ec53..81ca348915c9 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -171,7 +171,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_find_get); struct nf_conntrack_expect * nf_ct_find_expectation(struct net *net, const struct nf_conntrack_zone *zone, - const struct nf_conntrack_tuple *tuple) + const struct nf_conntrack_tuple *tuple, bool unlink) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_conntrack_expect *i, *exp = NULL; @@ -211,7 +211,7 @@ nf_ct_find_expectation(struct net *net, !refcount_inc_not_zero(&exp->master->ct_general.use))) return NULL; - if (exp->flags & NF_CT_EXPECT_PERMANENT) { + if (exp->flags & NF_CT_EXPECT_PERMANENT || !unlink) { refcount_inc(&exp->use); return exp; } else if (del_timer(&exp->timeout)) { diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 38958e067aa8..e87fd4314c68 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -262,6 +262,7 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr, regs->verdict.code = NF_DROP; return; } + __set_bit(IPS_CONFIRMED_BIT, &ct->status); } nf_ct_set(skb, ct, IP_CT_NEW); @@ -368,6 +369,7 @@ static bool nft_ct_tmpl_alloc_pcpu(void) return false; } + __set_bit(IPS_CONFIRMED_BIT, &tmp->status); per_cpu(nft_ct_pcpu_template, cpu) = tmp; } -- cgit v1.2.3 From 6f1c646d88c591a8139997c5591c1385cbc3d4e1 Mon Sep 17 00:00:00 2001 From: Stefan Eichenberger Date: Wed, 19 Jul 2023 08:42:54 +0200 Subject: net: phy: add registers to support 1000BASE-T1 Add registers and definitions to support 1000BASE-T1. This includes the PCS Control and Status registers (3.2304 and 3.2305) as well as some missing bits on the PMA/PMD extended ability register (1.18) and PMA/PMD CTRL (1.2100) register. Signed-off-by: Stefan Eichenberger Reviewed-by: Andrew Lunn Signed-off-by: Paolo Abeni --- include/uapi/linux/mdio.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index b826598d1e94..d03863da180e 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -82,6 +82,8 @@ #define MDIO_AN_10BT1_AN_CTRL 526 /* 10BASE-T1 AN control register */ #define MDIO_AN_10BT1_AN_STAT 527 /* 10BASE-T1 AN status register */ #define MDIO_PMA_PMD_BT1_CTRL 2100 /* BASE-T1 PMA/PMD control register */ +#define MDIO_PCS_1000BT1_CTRL 2304 /* 1000BASE-T1 PCS control register */ +#define MDIO_PCS_1000BT1_STAT 2305 /* 1000BASE-T1 PCS status register */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ #define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */ @@ -332,6 +334,8 @@ #define MDIO_PCS_10T1L_CTRL_RESET 0x8000 /* PCS reset */ /* BASE-T1 PMA/PMD extended ability register. */ +#define MDIO_PMA_PMD_BT1_B100_ABLE 0x0001 /* 100BASE-T1 Ability */ +#define MDIO_PMA_PMD_BT1_B1000_ABLE 0x0002 /* 1000BASE-T1 Ability */ #define MDIO_PMA_PMD_BT1_B10L_ABLE 0x0004 /* 10BASE-T1L Ability */ /* BASE-T1 auto-negotiation advertisement register [15:0] */ @@ -373,7 +377,19 @@ #define MDIO_AN_10BT1_AN_STAT_LPA_EEE_T1L 0x4000 /* 10BASE-T1L LP EEE ability advertisement */ /* BASE-T1 PMA/PMD control register */ -#define MDIO_PMA_PMD_BT1_CTRL_CFG_MST 0x4000 /* MASTER-SLAVE config value */ +#define MDIO_PMA_PMD_BT1_CTRL_STRAP 0x000F /* Type selection (Strap) */ +#define MDIO_PMA_PMD_BT1_CTRL_STRAP_B1000 0x0001 /* Select 1000BASE-T1 */ +#define MDIO_PMA_PMD_BT1_CTRL_CFG_MST 0x4000 /* MASTER-SLAVE config value */ + +/* 1000BASE-T1 PCS control register */ +#define MDIO_PCS_1000BT1_CTRL_LOW_POWER 0x0800 /* Low power mode */ +#define MDIO_PCS_1000BT1_CTRL_DISABLE_TX 0x4000 /* Global PMA transmit disable */ +#define MDIO_PCS_1000BT1_CTRL_RESET 0x8000 /* Software reset value */ + +/* 1000BASE-T1 PCS status register */ +#define MDIO_PCS_1000BT1_STAT_LINK 0x0004 /* PCS Link is up */ +#define MDIO_PCS_1000BT1_STAT_FAULT 0x0080 /* There is a fault condition */ + /* EEE Supported/Advertisement/LP Advertisement registers. * -- cgit v1.2.3 From eba2e4c2faef618b6e33dfdba918c76727f891b5 Mon Sep 17 00:00:00 2001 From: Stefan Eichenberger Date: Wed, 19 Jul 2023 08:42:56 +0200 Subject: net: phy: c45: add a separate function to read BASE-T1 abilities Add a separate function to read the BASE-T1 abilities. Some PHYs do not indicate the availability of the extended BASE-T1 ability register, so this function must be called separately. Signed-off-by: Stefan Eichenberger Reviewed-by: Andrew Lunn Signed-off-by: Paolo Abeni --- drivers/net/phy/phy-c45.c | 44 +++++++++++++++++++++++++++++++------------- include/linux/phy.h | 1 + 2 files changed, 32 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index b73c428a1566..58a6bbbe8a70 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -881,6 +881,36 @@ int genphy_c45_an_config_eee_aneg(struct phy_device *phydev) return genphy_c45_write_eee_adv(phydev, phydev->advertising_eee); } +/** + * genphy_c45_pma_baset1_read_abilities - read supported baset1 link modes from PMA + * @phydev: target phy_device struct + * + * Read the supported link modes from the extended BASE-T1 ability register + */ +int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev) +{ + int val; + + val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, + phydev->supported, + val & MDIO_PMA_PMD_BT1_B10L_ABLE); + + val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_STAT); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->supported, + val & MDIO_AN_STAT1_ABLE); + + return 0; +} +EXPORT_SYMBOL_GPL(genphy_c45_pma_baset1_read_abilities); + /** * genphy_c45_pma_read_abilities - read supported link modes from PMA * @phydev: target phy_device struct @@ -977,21 +1007,9 @@ int genphy_c45_pma_read_abilities(struct phy_device *phydev) } if (val & MDIO_PMA_EXTABLE_BT1) { - val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1); + val = genphy_c45_pma_baset1_read_abilities(phydev); if (val < 0) return val; - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, - phydev->supported, - val & MDIO_PMA_PMD_BT1_B10L_ABLE); - - val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_STAT); - if (val < 0) - return val; - - linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - phydev->supported, - val & MDIO_AN_STAT1_ABLE); } } diff --git a/include/linux/phy.h b/include/linux/phy.h index 11c1e91563d4..b254848a9c99 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1826,6 +1826,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); +int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev); int genphy_c45_read_eee_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); -- cgit v1.2.3 From 00f11ac71708d2e5e434aa2ef9249f95b5e7e313 Mon Sep 17 00:00:00 2001 From: Stefan Eichenberger Date: Wed, 19 Jul 2023 08:42:58 +0200 Subject: net: phy: marvell-88q2xxx: add driver for the Marvell 88Q2110 PHY Add a driver for the Marvell 88Q2110. This driver allows to detect the link, switch between 100BASE-T1 and 1000BASE-T1 and switch between master and slave mode. Autonegotiation supported by the PHY does not yet work. Signed-off-by: Stefan Eichenberger Reviewed-by: Andrew Lunn Signed-off-by: Paolo Abeni --- drivers/net/phy/Kconfig | 6 + drivers/net/phy/Makefile | 1 + drivers/net/phy/marvell-88q2xxx.c | 263 ++++++++++++++++++++++++++++++++++++++ include/linux/marvell_phy.h | 1 + 4 files changed, 271 insertions(+) create mode 100644 drivers/net/phy/marvell-88q2xxx.c (limited to 'include') diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 78e6981650d9..87b823858717 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -217,6 +217,12 @@ config MARVELL_10G_PHY help Support for the Marvell Alaska MV88X3310 and compatible PHYs. +config MARVELL_88Q2XXX_PHY + tristate "Marvell 88Q2XXX PHY" + help + Support for the Marvell 88Q2XXX 100/1000BASE-T1 Automotive Ethernet + PHYs. + config MARVELL_88X2222_PHY tristate "Marvell 88X2222 PHY" help diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 2fe51ea83bab..35142780fc9d 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -66,6 +66,7 @@ obj-$(CONFIG_LSI_ET1011C_PHY) += et1011c.o obj-$(CONFIG_LXT_PHY) += lxt.o obj-$(CONFIG_MARVELL_10G_PHY) += marvell10g.o obj-$(CONFIG_MARVELL_PHY) += marvell.o +obj-$(CONFIG_MARVELL_88Q2XXX_PHY) += marvell-88q2xxx.o obj-$(CONFIG_MARVELL_88X2222_PHY) += marvell-88x2222.o obj-$(CONFIG_MAXLINEAR_GPHY) += mxl-gpy.o obj-$(CONFIG_MEDIATEK_GE_PHY) += mediatek-ge.o diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c new file mode 100644 index 000000000000..1c3ff77de56b --- /dev/null +++ b/drivers/net/phy/marvell-88q2xxx.c @@ -0,0 +1,263 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Marvell 88Q2XXX automotive 100BASE-T1/1000BASE-T1 PHY driver + */ +#include +#include +#include + +#define MDIO_MMD_AN_MV_STAT 32769 +#define MDIO_MMD_AN_MV_STAT_ANEG 0x0100 +#define MDIO_MMD_AN_MV_STAT_LOCAL_RX 0x1000 +#define MDIO_MMD_AN_MV_STAT_REMOTE_RX 0x2000 +#define MDIO_MMD_AN_MV_STAT_LOCAL_MASTER 0x4000 +#define MDIO_MMD_AN_MV_STAT_MS_CONF_FAULT 0x8000 + +#define MDIO_MMD_PCS_MV_100BT1_STAT1 33032 +#define MDIO_MMD_PCS_MV_100BT1_STAT1_IDLE_ERROR 0x00FF +#define MDIO_MMD_PCS_MV_100BT1_STAT1_JABBER 0x0100 +#define MDIO_MMD_PCS_MV_100BT1_STAT1_LINK 0x0200 +#define MDIO_MMD_PCS_MV_100BT1_STAT1_LOCAL_RX 0x1000 +#define MDIO_MMD_PCS_MV_100BT1_STAT1_REMOTE_RX 0x2000 +#define MDIO_MMD_PCS_MV_100BT1_STAT1_LOCAL_MASTER 0x4000 + +#define MDIO_MMD_PCS_MV_100BT1_STAT2 33033 +#define MDIO_MMD_PCS_MV_100BT1_STAT2_JABBER 0x0001 +#define MDIO_MMD_PCS_MV_100BT1_STAT2_POL 0x0002 +#define MDIO_MMD_PCS_MV_100BT1_STAT2_LINK 0x0004 +#define MDIO_MMD_PCS_MV_100BT1_STAT2_ANGE 0x0008 + +static int mv88q2xxx_soft_reset(struct phy_device *phydev) +{ + int ret; + int val; + + ret = phy_write_mmd(phydev, MDIO_MMD_PCS, + MDIO_PCS_1000BT1_CTRL, MDIO_PCS_1000BT1_CTRL_RESET); + if (ret < 0) + return ret; + + return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_PCS, + MDIO_PCS_1000BT1_CTRL, val, + !(val & MDIO_PCS_1000BT1_CTRL_RESET), + 50000, 600000, true); +} + +static int mv88q2xxx_read_link_gbit(struct phy_device *phydev) +{ + int ret; + bool link = false; + + /* Read vendor specific Auto-Negotiation status register to get local + * and remote receiver status according to software initialization + * guide. + */ + ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_MMD_AN_MV_STAT); + if (ret < 0) { + return ret; + } else if ((ret & MDIO_MMD_AN_MV_STAT_LOCAL_RX) && + (ret & MDIO_MMD_AN_MV_STAT_REMOTE_RX)) { + /* The link state is latched low so that momentary link + * drops can be detected. Do not double-read the status + * in polling mode to detect such short link drops except + * the link was already down. + */ + if (!phy_polling_mode(phydev) || !phydev->link) { + ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_1000BT1_STAT); + if (ret < 0) + return ret; + else if (ret & MDIO_PCS_1000BT1_STAT_LINK) + link = true; + } + + if (!link) { + ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_1000BT1_STAT); + if (ret < 0) + return ret; + else if (ret & MDIO_PCS_1000BT1_STAT_LINK) + link = true; + } + } + + phydev->link = link; + + return 0; +} + +static int mv88q2xxx_read_link_100m(struct phy_device *phydev) +{ + int ret; + + /* The link state is latched low so that momentary link + * drops can be detected. Do not double-read the status + * in polling mode to detect such short link drops except + * the link was already down. In case we are not polling, + * we always read the realtime status. + */ + if (!phy_polling_mode(phydev) || !phydev->link) { + ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_MMD_PCS_MV_100BT1_STAT1); + if (ret < 0) + return ret; + else if (ret & MDIO_MMD_PCS_MV_100BT1_STAT1_LINK) + goto out; + } + + ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_MMD_PCS_MV_100BT1_STAT1); + if (ret < 0) + return ret; + +out: + /* Check if we have link and if the remote and local receiver are ok */ + if ((ret & MDIO_MMD_PCS_MV_100BT1_STAT1_LINK) && + (ret & MDIO_MMD_PCS_MV_100BT1_STAT1_LOCAL_RX) && + (ret & MDIO_MMD_PCS_MV_100BT1_STAT1_REMOTE_RX)) + phydev->link = true; + else + phydev->link = false; + + return 0; +} + +static int mv88q2xxx_read_link(struct phy_device *phydev) +{ + int ret; + + /* The 88Q2XXX PHYs do not have the PMA/PMD status register available, + * therefore we need to read the link status from the vendor specific + * registers depending on the speed. + */ + if (phydev->speed == SPEED_1000) + ret = mv88q2xxx_read_link_gbit(phydev); + else + ret = mv88q2xxx_read_link_100m(phydev); + + return ret; +} + +static int mv88q2xxx_read_status(struct phy_device *phydev) +{ + int ret; + + ret = mv88q2xxx_read_link(phydev); + if (ret < 0) + return ret; + + return genphy_c45_read_pma(phydev); +} + +static int mv88q2xxx_get_features(struct phy_device *phydev) +{ + int ret; + + ret = genphy_c45_pma_read_abilities(phydev); + if (ret) + return ret; + + /* We need to read the baset1 extended abilities manually because the + * PHY does not signalize it has the extended abilities register + * available. + */ + ret = genphy_c45_pma_baset1_read_abilities(phydev); + if (ret) + return ret; + + /* The PHY signalizes it supports autonegotiation. Unfortunately, so + * far it was not possible to get a link even when following the init + * sequence provided by Marvell. Disable it for now until a proper + * workaround is found or a new PHY revision is released. + */ + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported); + + return 0; +} + +static int mv88q2xxx_config_aneg(struct phy_device *phydev) +{ + int ret; + + ret = genphy_c45_config_aneg(phydev); + if (ret) + return ret; + + return mv88q2xxx_soft_reset(phydev); +} + +static int mv88q2xxx_config_init(struct phy_device *phydev) +{ + int ret; + + /* The 88Q2XXX PHYs do have the extended ability register available, but + * register MDIO_PMA_EXTABLE where they should signalize it does not + * work according to specification. Therefore, we force it here. + */ + phydev->pma_extable = MDIO_PMA_EXTABLE_BT1; + + /* Read the current PHY configuration */ + ret = genphy_c45_read_pma(phydev); + if (ret) + return ret; + + return mv88q2xxx_config_aneg(phydev); +} + +static int mv88q2xxxx_get_sqi(struct phy_device *phydev) +{ + int ret; + + if (phydev->speed == SPEED_100) { + /* Read the SQI from the vendor specific receiver status + * register + */ + ret = phy_read_mmd(phydev, MDIO_MMD_PCS, 0x8230); + if (ret < 0) + return ret; + + ret = ret >> 12; + } else { + /* Read from vendor specific registers, they are not documented + * but can be found in the Software Initialization Guide. Only + * revisions >= A0 are supported. + */ + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, 0xFC5D, 0x00FF, 0x00AC); + if (ret < 0) + return ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_PCS, 0xfc88); + if (ret < 0) + return ret; + } + + return ret & 0x0F; +} + +static int mv88q2xxxx_get_sqi_max(struct phy_device *phydev) +{ + return 15; +} + +static struct phy_driver mv88q2xxx_driver[] = { + { + .phy_id = MARVELL_PHY_ID_88Q2110, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .name = "mv88q2110", + .get_features = mv88q2xxx_get_features, + .config_aneg = mv88q2xxx_config_aneg, + .config_init = mv88q2xxx_config_init, + .read_status = mv88q2xxx_read_status, + .soft_reset = mv88q2xxx_soft_reset, + .set_loopback = genphy_c45_loopback, + .get_sqi = mv88q2xxxx_get_sqi, + .get_sqi_max = mv88q2xxxx_get_sqi_max, + }, +}; + +module_phy_driver(mv88q2xxx_driver); + +static struct mdio_device_id __maybe_unused mv88q2xxx_tbl[] = { + { MARVELL_PHY_ID_88Q2110, MARVELL_PHY_ID_MASK }, + { /*sentinel*/ } +}; +MODULE_DEVICE_TABLE(mdio, mv88q2xxx_tbl); + +MODULE_DESCRIPTION("Marvell 88Q2XXX 100/1000BASE-T1 Automotive Ethernet PHY driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 0f06c2287b52..9b54c4f0677f 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -25,6 +25,7 @@ #define MARVELL_PHY_ID_88X3310 0x002b09a0 #define MARVELL_PHY_ID_88E2110 0x002b09b0 #define MARVELL_PHY_ID_88X2222 0x01410f10 +#define MARVELL_PHY_ID_88Q2110 0x002b0980 /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 -- cgit v1.2.3 From b44693495af8f309b8ddec4b30833085d1c2d0c4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 06:47:54 +0000 Subject: tcp: add TCP_OLD_SEQUENCE drop reason tcp_sequence() uses two conditions to decide to drop a packet, and we currently report generic TCP_INVALID_SEQUENCE drop reason. Duplicates are common, we need to distinguish them from the other case. I chose to not reuse TCP_OLD_DATA, and instead added TCP_OLD_SEQUENCE drop reason. Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719064754.2794106-1-edumazet@google.com Signed-off-by: Paolo Abeni --- include/net/dropreason-core.h | 3 +++ net/ipv4/tcp_input.c | 16 +++++++++++----- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index a2b953b57689..f291a3b0f9e5 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -30,6 +30,7 @@ FN(TCP_OVERWINDOW) \ FN(TCP_OFOMERGE) \ FN(TCP_RFC7323_PAWS) \ + FN(TCP_OLD_SEQUENCE) \ FN(TCP_INVALID_SEQUENCE) \ FN(TCP_RESET) \ FN(TCP_INVALID_SYN) \ @@ -188,6 +189,8 @@ enum skb_drop_reason { * LINUX_MIB_PAWSESTABREJECTED */ SKB_DROP_REASON_TCP_RFC7323_PAWS, + /** @SKB_DROP_REASON_TCP_OLD_SEQUENCE: Old SEQ field (duplicate packet) */ + SKB_DROP_REASON_TCP_OLD_SEQUENCE, /** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */ SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /** @SKB_DROP_REASON_TCP_RESET: Invalid RST packet */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e2affdd147da..670c3dab24f2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4312,10 +4312,16 @@ static inline bool tcp_paws_discard(const struct sock *sk, * (borrowed from freebsd) */ -static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq) +static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp, + u32 seq, u32 end_seq) { - return !before(end_seq, tp->rcv_wup) && - !after(seq, tp->rcv_nxt + tcp_receive_window(tp)); + if (before(end_seq, tp->rcv_wup)) + return SKB_DROP_REASON_TCP_OLD_SEQUENCE; + + if (after(seq, tp->rcv_nxt + tcp_receive_window(tp))) + return SKB_DROP_REASON_TCP_INVALID_SEQUENCE; + + return SKB_NOT_DROPPED_YET; } /* When we get a reset we do this. */ @@ -5738,7 +5744,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, } /* Step 1: check sequence number */ - if (!tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq)) { + reason = tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); + if (reason) { /* RFC793, page 37: "In all states except SYN-SENT, all reset * (RST) segments are validated by checking their SEQ-fields." * And page 69: "If an incoming segment is not acceptable, @@ -5755,7 +5762,6 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, } else if (tcp_reset_check(sk, skb)) { goto reset; } - SKB_DR_SET(reason, TCP_INVALID_SEQUENCE); goto discard; } -- cgit v1.2.3 From f2e2857b352277a451e2f91409e461fa7ebf2d15 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 19 Jul 2023 13:01:17 +0200 Subject: net: switchdev: Add a helper to replay objects on a bridge port When a front panel joins a bridge via another netdevice (typically a LAG), the driver needs to learn about the objects configured on the bridge port. When the bridge port is offloaded by the driver for the first time, this can be achieved by passing a notifier to switchdev_bridge_port_offload(). The notifier is then invoked for the individual objects (such as VLANs) configured on the bridge, and can look for the interesting ones. Calling switchdev_bridge_port_offload() when the second port joins the bridge lower is unnecessary, but the replay is still needed. To that end, add a new function, switchdev_bridge_port_replay(), which does only the replay part of the _offload() function in exactly the same way as that function. Cc: Jiri Pirko Cc: Ivan Vecera Cc: Roopa Prabhu Cc: Nikolay Aleksandrov Cc: bridge@lists.linux-foundation.org Signed-off-by: Petr Machata Reviewed-by: Danielle Ratson Signed-off-by: David S. Miller --- include/net/switchdev.h | 6 ++++++ net/bridge/br.c | 8 ++++++++ net/bridge/br_private.h | 16 ++++++++++++++++ net/bridge/br_switchdev.c | 9 +++++++++ net/switchdev/switchdev.c | 25 +++++++++++++++++++++++++ 5 files changed, 64 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index ca0312b78294..4d324e2a2eef 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -231,6 +231,7 @@ enum switchdev_notifier_type { SWITCHDEV_BRPORT_OFFLOADED, SWITCHDEV_BRPORT_UNOFFLOADED, + SWITCHDEV_BRPORT_REPLAY, }; struct switchdev_notifier_info { @@ -299,6 +300,11 @@ void switchdev_bridge_port_unoffload(struct net_device *brport_dev, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb); +int switchdev_bridge_port_replay(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); void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, diff --git a/net/bridge/br.c b/net/bridge/br.c index 4f5098d33a46..a6e94ceb7c9a 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -234,6 +234,14 @@ static int br_switchdev_blocking_event(struct notifier_block *nb, br_switchdev_port_unoffload(p, b->ctx, b->atomic_nb, b->blocking_nb); break; + case SWITCHDEV_BRPORT_REPLAY: + brport_info = ptr; + b = &brport_info->brport; + + err = br_switchdev_port_replay(p, b->dev, b->ctx, b->atomic_nb, + b->blocking_nb, extack); + err = notifier_from_errno(err); + break; } out: diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 05a965ef76f1..51e4ca54b537 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -2118,6 +2118,12 @@ void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb); +int br_switchdev_port_replay(struct net_bridge_port *p, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + struct netlink_ext_ack *extack); + bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb); void br_switchdev_frame_set_offload_fwd_mark(struct sk_buff *skb); @@ -2168,6 +2174,16 @@ br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, { } +static inline int +br_switchdev_port_replay(struct net_bridge_port *p, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + 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 e92e0338afee..ee84e783e1df 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -829,3 +829,12 @@ void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, nbp_switchdev_del(p); } + +int br_switchdev_port_replay(struct net_bridge_port *p, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + struct netlink_ext_ack *extack) +{ + return nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack); +} diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8cc42aea19c7..5b045284849e 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -862,3 +862,28 @@ void switchdev_bridge_port_unoffload(struct net_device *brport_dev, NULL); } EXPORT_SYMBOL_GPL(switchdev_bridge_port_unoffload); + +int switchdev_bridge_port_replay(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) +{ + struct switchdev_notifier_brport_info brport_info = { + .brport = { + .dev = dev, + .ctx = ctx, + .atomic_nb = atomic_nb, + .blocking_nb = blocking_nb, + }, + }; + int err; + + ASSERT_RTNL(); + + err = call_switchdev_blocking_notifiers(SWITCHDEV_BRPORT_REPLAY, + brport_dev, &brport_info.info, + extack); + return notifier_to_errno(err); +} +EXPORT_SYMBOL_GPL(switchdev_bridge_port_replay); -- cgit v1.2.3 From 9fe63d5f1da939855bdfaebfd9e95c96938b6411 Mon Sep 17 00:00:00 2001 From: Naveen Mamindlapalli Date: Wed, 19 Jul 2023 16:34:41 +0530 Subject: sch_htb: Allow HTB quantum parameter in offload mode The current implementation of HTB offload returns the EINVAL error for quantum parameter. This patch removes the error returning checks for 'quantum' parameter and populates its value to tc_htb_qopt_offload structure such that driver can use the same. Add quantum parameter check in mlx5 driver, as mlx5 devices are not capable of supporting the quantum parameter when htb offload is used. Report error if quantum parameter is set to a non-default value. Signed-off-by: Naveen Mamindlapalli Signed-off-by: Hariprasad Kelam Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en/qos.c | 4 ++-- include/net/pkt_cls.h | 1 + net/sched/sch_htb.c | 7 +++---- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 1874c2f0587f..244bc15a42ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -379,9 +379,9 @@ int mlx5e_htb_setup_tc(struct mlx5e_priv *priv, struct tc_htb_qopt_offload *htb_ if (!htb && htb_qopt->command != TC_HTB_CREATE) return -EINVAL; - if (htb_qopt->prio) { + if (htb_qopt->prio || htb_qopt->quantum) { NL_SET_ERR_MSG_MOD(htb_qopt->extack, - "prio parameter is not supported by device with HTB offload enabled."); + "prio and quantum parameters are not supported by device with HTB offload enabled."); return -EOPNOTSUPP; } diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a2ea45c7b53e..139cd09828af 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -866,6 +866,7 @@ struct tc_htb_qopt_offload { u32 parent_classid; u16 classid; u16 qid; + u32 quantum; u64 rate; u64 ceil; u8 prio; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 325c29041c7d..333800a7d4eb 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1810,10 +1810,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, NL_SET_ERR_MSG(extack, "HTB offload doesn't support the mpu parameter"); goto failure; } - if (hopt->quantum) { - NL_SET_ERR_MSG(extack, "HTB offload doesn't support the quantum parameter"); - goto failure; - } } /* Keeping backward compatible with rate_table based iproute2 tc */ @@ -1910,6 +1906,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, .rate = max_t(u64, hopt->rate.rate, rate64), .ceil = max_t(u64, hopt->ceil.rate, ceil64), .prio = hopt->prio, + .quantum = hopt->quantum, .extack = extack, }; err = htb_offload(dev, &offload_opt); @@ -1931,6 +1928,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, .rate = max_t(u64, hopt->rate.rate, rate64), .ceil = max_t(u64, hopt->ceil.rate, ceil64), .prio = hopt->prio, + .quantum = hopt->quantum, .extack = extack, }; err = htb_offload(dev, &offload_opt); @@ -2017,6 +2015,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, .rate = max_t(u64, hopt->rate.rate, rate64), .ceil = max_t(u64, hopt->ceil.rate, ceil64), .prio = hopt->prio, + .quantum = hopt->quantum, .extack = extack, }; err = htb_offload(dev, &offload_opt); -- cgit v1.2.3 From 535b9c61bdef6017228c708128b7849a476f8da5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 19 Jul 2023 18:04:08 -0700 Subject: net: page_pool: hide page_pool_release_page() There seems to be no user calling page_pool_release_page() for legit reasons, all the users simply haven't been converted to skb-based recycling, yet. Previous changes converted them. Update the docs, and unexport the function. Link: https://lore.kernel.org/r/20230720010409.1967072-4-kuba@kernel.org Reviewed-by: Alexander Lobakin Signed-off-by: Jakub Kicinski --- Documentation/networking/page_pool.rst | 11 ++++------- include/net/page_pool.h | 10 ++-------- net/core/page_pool.c | 3 +-- 3 files changed, 7 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst index 873efd97f822..0aa850cf4447 100644 --- a/Documentation/networking/page_pool.rst +++ b/Documentation/networking/page_pool.rst @@ -13,9 +13,9 @@ replacing dev_alloc_pages(). API keeps track of in-flight pages, in order to let API user know when it is safe to free a page_pool object. Thus, API users -must run page_pool_release_page() when a page is leaving the page_pool or -call page_pool_put_page() where appropriate in order to maintain correct -accounting. +must call page_pool_put_page() to free the page, or attach +the page to a page_pool-aware objects like skbs marked with +skb_mark_for_recycle(). API user must call page_pool_put_page() once on a page, as it will either recycle the page, or in case of refcnt > 1, it will @@ -87,9 +87,6 @@ a page will cause no race conditions is enough. must guarantee safe context (e.g NAPI), since it will recycle the page directly into the pool fast cache. -* page_pool_release_page(): Unmap the page (if mapped) and account for it on - in-flight counters. - * page_pool_dev_alloc_pages(): Get a page from the page allocator or page_pool caches. @@ -194,7 +191,7 @@ NAPI poller if XDP_DROP: page_pool_recycle_direct(page_pool, page); } else (packet_is_skb) { - page_pool_release_page(page_pool, page); + skb_mark_for_recycle(skb); new_page = page_pool_dev_alloc_pages(page_pool); } } diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 126f9e294389..f1d5cc1fa13b 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -18,9 +18,8 @@ * * API keeps track of in-flight pages, in-order to let API user know * when it is safe to dealloactor page_pool object. Thus, API users - * must make sure to call page_pool_release_page() when a page is - * "leaving" the page_pool. Or call page_pool_put_page() where - * appropiate. For maintaining correct accounting. + * must call page_pool_put_page() where appropriate and only attach + * the page to a page_pool-aware objects, like skbs marked for recycling. * * API user must only call page_pool_put_page() once on a page, as it * will either recycle the page, or in case of elevated refcnt, it @@ -251,7 +250,6 @@ void page_pool_unlink_napi(struct page_pool *pool); void page_pool_destroy(struct page_pool *pool); void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), struct xdp_mem_info *mem); -void page_pool_release_page(struct page_pool *pool, struct page *page); void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count); #else @@ -268,10 +266,6 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool, struct xdp_mem_info *mem) { } -static inline void page_pool_release_page(struct page_pool *pool, - struct page *page) -{ -} static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index a3e12a61d456..2c7cf5f2bcb8 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -492,7 +492,7 @@ static s32 page_pool_inflight(struct page_pool *pool) * a regular page (that will eventually be returned to the normal * page-allocator via put_page). */ -void page_pool_release_page(struct page_pool *pool, struct page *page) +static void page_pool_release_page(struct page_pool *pool, struct page *page) { dma_addr_t dma; int count; @@ -519,7 +519,6 @@ skip_dma_unmap: count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt); trace_page_pool_state_release(pool, page, count); } -EXPORT_SYMBOL(page_pool_release_page); /* Return a page to the page allocator, cleaning up our state */ static void page_pool_return_page(struct page_pool *pool, struct page *page) -- cgit v1.2.3 From a3377386b56420d78a4c0a931a40f9a25c3ca2bd Mon Sep 17 00:00:00 2001 From: Anjali Kulkarni Date: Wed, 19 Jul 2023 13:18:16 -0700 Subject: netlink: Reverse the patch which removed filtering To use filtering at the connector & cn_proc layers, we need to enable filtering in the netlink layer. This reverses the patch which removed netlink filtering - commit ID for that patch: 549017aa1bb7 (netlink: remove netlink_broadcast_filtered). Signed-off-by: Anjali Kulkarni Reviewed-by: Liam R. Howlett Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netlink.h | 5 +++++ net/netlink/af_netlink.c | 27 +++++++++++++++++++++++++-- 2 files changed, 30 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 9eec3f4f5351..3a6563681b50 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -227,6 +227,11 @@ bool netlink_strict_get_check(struct sk_buff *skb); int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); +int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, + __u32 portid, __u32 group, gfp_t allocation, + int (*filter)(struct sock *dsk, + struct sk_buff *skb, void *data), + void *filter_data); int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code); int netlink_register_notifier(struct notifier_block *nb); int netlink_unregister_notifier(struct notifier_block *nb); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 9c9df143a2ec..6c0bcde620e8 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1432,6 +1432,8 @@ struct netlink_broadcast_data { int delivered; gfp_t allocation; struct sk_buff *skb, *skb2; + int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data); + void *tx_data; }; static void do_one_broadcast(struct sock *sk, @@ -1485,6 +1487,13 @@ static void do_one_broadcast(struct sock *sk, p->delivery_failure = 1; goto out; } + + if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { + kfree_skb(p->skb2); + p->skb2 = NULL; + goto out; + } + if (sk_filter(sk, p->skb2)) { kfree_skb(p->skb2); p->skb2 = NULL; @@ -1507,8 +1516,12 @@ out: sock_put(sk); } -int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, - u32 group, gfp_t allocation) +int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, + u32 portid, + u32 group, gfp_t allocation, + int (*filter)(struct sock *dsk, + struct sk_buff *skb, void *data), + void *filter_data) { struct net *net = sock_net(ssk); struct netlink_broadcast_data info; @@ -1527,6 +1540,8 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, info.allocation = allocation; info.skb = skb; info.skb2 = NULL; + info.tx_filter = filter; + info.tx_data = filter_data; /* While we sleep in clone, do not allow to change socket list */ @@ -1552,6 +1567,14 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, } return -ESRCH; } +EXPORT_SYMBOL(netlink_broadcast_filtered); + +int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, + u32 group, gfp_t allocation) +{ + return netlink_broadcast_filtered(ssk, skb, portid, group, allocation, + NULL, NULL); +} EXPORT_SYMBOL(netlink_broadcast); struct netlink_set_err_data { -- cgit v1.2.3 From a4c9a56e6a2cdeeab7caef1f496b7bfefd95b50e Mon Sep 17 00:00:00 2001 From: Anjali Kulkarni Date: Wed, 19 Jul 2023 13:18:17 -0700 Subject: netlink: Add new netlink_release function A new function netlink_release is added in netlink_sock to store the protocol's release function. This is called when the socket is deleted. This can be supplied by the protocol via the release function in netlink_kernel_cfg. This is being added for the NETLINK_CONNECTOR protocol, so it can free it's data when socket is deleted. Signed-off-by: Anjali Kulkarni Reviewed-by: Liam R. Howlett Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + net/netlink/af_netlink.c | 6 ++++++ net/netlink/af_netlink.h | 4 ++++ 3 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 3a6563681b50..75d7de34c908 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -50,6 +50,7 @@ struct netlink_kernel_cfg { struct mutex *cb_mutex; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); + void (*release) (struct sock *sk, unsigned long *groups); }; struct sock *__netlink_kernel_create(struct net *net, int unit, diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6c0bcde620e8..96c605e45235 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -677,6 +677,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, struct netlink_sock *nlk; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); + void (*release)(struct sock *sock, unsigned long *groups); int err = 0; sock->state = SS_UNCONNECTED; @@ -704,6 +705,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, cb_mutex = nl_table[protocol].cb_mutex; bind = nl_table[protocol].bind; unbind = nl_table[protocol].unbind; + release = nl_table[protocol].release; netlink_unlock_table(); if (err < 0) @@ -719,6 +721,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, nlk->module = module; nlk->netlink_bind = bind; nlk->netlink_unbind = unbind; + nlk->netlink_release = release; out: return err; @@ -763,6 +766,8 @@ static int netlink_release(struct socket *sock) * OK. Socket is unlinked, any packets that arrive now * will be purged. */ + if (nlk->netlink_release) + nlk->netlink_release(sk, nlk->groups); /* must not acquire netlink_table_lock in any way again before unbind * and notifying genetlink is done as otherwise it might deadlock @@ -2089,6 +2094,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module, if (cfg) { nl_table[unit].bind = cfg->bind; nl_table[unit].unbind = cfg->unbind; + nl_table[unit].release = cfg->release; nl_table[unit].flags = cfg->flags; } nl_table[unit].registered = 1; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 90a3198a9b7f..fd424cd63f31 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -42,6 +42,8 @@ struct netlink_sock { void (*netlink_rcv)(struct sk_buff *skb); int (*netlink_bind)(struct net *net, int group); void (*netlink_unbind)(struct net *net, int group); + void (*netlink_release)(struct sock *sk, + unsigned long *groups); struct module *module; struct rhash_head node; @@ -64,6 +66,8 @@ struct netlink_table { struct module *module; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); + void (*release)(struct sock *sk, + unsigned long *groups); int registered; }; -- cgit v1.2.3 From 2aa1f7a1f47ce8dac7593af605aaa859b3cf3bb1 Mon Sep 17 00:00:00 2001 From: Anjali Kulkarni Date: Wed, 19 Jul 2023 13:18:18 -0700 Subject: connector/cn_proc: Add filtering to fix some bugs The current proc connector code has the foll. bugs - if there are more than one listeners for the proc connector messages, and one of them deregisters for listening using PROC_CN_MCAST_IGNORE, they will still get all proc connector messages, as long as there is another listener. Another issue is if one client calls PROC_CN_MCAST_LISTEN, and another one calls PROC_CN_MCAST_IGNORE, then both will end up not getting any messages. This patch adds filtering and drops packet if client has sent PROC_CN_MCAST_IGNORE. This data is stored in the client socket's sk_user_data. In addition, we only increment or decrement proc_event_num_listeners once per client. This fixes the above issues. cn_release is the release function added for NETLINK_CONNECTOR. It uses the newly added netlink_release function added to netlink_sock. It will free sk_user_data. Signed-off-by: Anjali Kulkarni Reviewed-by: Liam R. Howlett Signed-off-by: David S. Miller --- drivers/connector/cn_proc.c | 57 +++++++++++++++++++++++++++++++++++-------- drivers/connector/connector.c | 21 +++++++++++++--- drivers/w1/w1_netlink.c | 6 +++-- include/linux/connector.h | 8 +++++- include/uapi/linux/cn_proc.h | 43 ++++++++++++++++++-------------- 5 files changed, 100 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index ccac1c453080..1ba288ed2bf7 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -48,6 +48,21 @@ static DEFINE_PER_CPU(struct local_event, local_event) = { .lock = INIT_LOCAL_LOCK(lock), }; +static int cn_filter(struct sock *dsk, struct sk_buff *skb, void *data) +{ + enum proc_cn_mcast_op mc_op; + + if (!dsk) + return 0; + + mc_op = ((struct proc_input *)(dsk->sk_user_data))->mcast_op; + + if (mc_op == PROC_CN_MCAST_IGNORE) + return 1; + + return 0; +} + static inline void send_msg(struct cn_msg *msg) { local_lock(&local_event.lock); @@ -61,7 +76,8 @@ static inline void send_msg(struct cn_msg *msg) * * If cn_netlink_send() fails, the data is not sent. */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT); + cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, + cn_filter, NULL); local_unlock(&local_event.lock); } @@ -346,11 +362,9 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) static void cn_proc_mcast_ctl(struct cn_msg *msg, struct netlink_skb_parms *nsp) { - enum proc_cn_mcast_op *mc_op = NULL; - int err = 0; - - if (msg->len != sizeof(*mc_op)) - return; + enum proc_cn_mcast_op mc_op = 0, prev_mc_op = 0; + int err = 0, initial = 0; + struct sock *sk = NULL; /* * Events are reported with respect to the initial pid @@ -367,13 +381,36 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg, goto out; } - mc_op = (enum proc_cn_mcast_op *)msg->data; - switch (*mc_op) { + if (msg->len == sizeof(mc_op)) + mc_op = *((enum proc_cn_mcast_op *)msg->data); + else + return; + + if (nsp->sk) { + sk = nsp->sk; + if (sk->sk_user_data == NULL) { + sk->sk_user_data = kzalloc(sizeof(struct proc_input), + GFP_KERNEL); + if (sk->sk_user_data == NULL) { + err = ENOMEM; + goto out; + } + initial = 1; + } else { + prev_mc_op = + ((struct proc_input *)(sk->sk_user_data))->mcast_op; + } + ((struct proc_input *)(sk->sk_user_data))->mcast_op = mc_op; + } + + switch (mc_op) { case PROC_CN_MCAST_LISTEN: - atomic_inc(&proc_event_num_listeners); + if (initial || (prev_mc_op != PROC_CN_MCAST_LISTEN)) + atomic_inc(&proc_event_num_listeners); break; case PROC_CN_MCAST_IGNORE: - atomic_dec(&proc_event_num_listeners); + if (!initial && (prev_mc_op != PROC_CN_MCAST_IGNORE)) + atomic_dec(&proc_event_num_listeners); break; default: err = EINVAL; diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 48ec7ce6ecac..d1179df2b0ba 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -59,7 +59,9 @@ static int cn_already_initialized; * both, or if both are zero then the group is looked up and sent there. */ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group, - gfp_t gfp_mask) + gfp_t gfp_mask, + int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), + void *filter_data) { struct cn_callback_entry *__cbq; unsigned int size; @@ -110,8 +112,9 @@ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group, NETLINK_CB(skb).dst_group = group; if (group) - return netlink_broadcast(dev->nls, skb, portid, group, - gfp_mask); + return netlink_broadcast_filtered(dev->nls, skb, portid, group, + gfp_mask, filter, + (void *)filter_data); return netlink_unicast(dev->nls, skb, portid, !gfpflags_allow_blocking(gfp_mask)); } @@ -121,7 +124,8 @@ EXPORT_SYMBOL_GPL(cn_netlink_send_mult); int cn_netlink_send(struct cn_msg *msg, u32 portid, u32 __group, gfp_t gfp_mask) { - return cn_netlink_send_mult(msg, msg->len, portid, __group, gfp_mask); + return cn_netlink_send_mult(msg, msg->len, portid, __group, gfp_mask, + NULL, NULL); } EXPORT_SYMBOL_GPL(cn_netlink_send); @@ -162,6 +166,14 @@ static int cn_call_callback(struct sk_buff *skb) return err; } +static void cn_release(struct sock *sk, unsigned long *groups) +{ + if (groups && test_bit(CN_IDX_PROC - 1, groups)) { + kfree(sk->sk_user_data); + sk->sk_user_data = NULL; + } +} + /* * Main netlink receiving function. * @@ -249,6 +261,7 @@ static int cn_init(void) struct netlink_kernel_cfg cfg = { .groups = CN_NETLINK_USERS + 0xf, .input = cn_rx_skb, + .release = cn_release, }; dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, &cfg); diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c index db110cc442b1..691978cddab7 100644 --- a/drivers/w1/w1_netlink.c +++ b/drivers/w1/w1_netlink.c @@ -65,7 +65,8 @@ static void w1_unref_block(struct w1_cb_block *block) u16 len = w1_reply_len(block); if (len) { cn_netlink_send_mult(block->first_cn, len, - block->portid, 0, GFP_KERNEL); + block->portid, 0, + GFP_KERNEL, NULL, NULL); } kfree(block); } @@ -83,7 +84,8 @@ static void w1_reply_make_space(struct w1_cb_block *block, u16 space) { u16 len = w1_reply_len(block); if (len + space >= block->maxlen) { - cn_netlink_send_mult(block->first_cn, len, block->portid, 0, GFP_KERNEL); + cn_netlink_send_mult(block->first_cn, len, block->portid, + 0, GFP_KERNEL, NULL, NULL); block->first_cn->len = 0; block->cn = NULL; block->msg = NULL; diff --git a/include/linux/connector.h b/include/linux/connector.h index 487350bb19c3..cec2d99ae902 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -90,13 +90,19 @@ void cn_del_callback(const struct cb_id *id); * If @group is not zero, then message will be delivered * to the specified group. * @gfp_mask: GFP mask. + * @filter: Filter function to be used at netlink layer. + * @filter_data:Filter data to be supplied to the filter function * * It can be safely called from softirq context, but may silently * fail under strong memory pressure. * * If there are no listeners for given group %-ESRCH can be returned. */ -int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 group, gfp_t gfp_mask); +int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, + u32 group, gfp_t gfp_mask, + int (*filter)(struct sock *dsk, struct sk_buff *skb, + void *data), + void *filter_data); /** * cn_netlink_send - Sends message to the specified groups. diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h index db210625cee8..6a06fb424313 100644 --- a/include/uapi/linux/cn_proc.h +++ b/include/uapi/linux/cn_proc.h @@ -30,6 +30,30 @@ enum proc_cn_mcast_op { PROC_CN_MCAST_IGNORE = 2 }; +enum proc_cn_event { + /* Use successive bits so the enums can be used to record + * sets of events as well + */ + PROC_EVENT_NONE = 0x00000000, + PROC_EVENT_FORK = 0x00000001, + PROC_EVENT_EXEC = 0x00000002, + PROC_EVENT_UID = 0x00000004, + PROC_EVENT_GID = 0x00000040, + PROC_EVENT_SID = 0x00000080, + PROC_EVENT_PTRACE = 0x00000100, + PROC_EVENT_COMM = 0x00000200, + /* "next" should be 0x00000400 */ + /* "last" is the last process event: exit, + * while "next to last" is coredumping event + */ + PROC_EVENT_COREDUMP = 0x40000000, + PROC_EVENT_EXIT = 0x80000000 +}; + +struct proc_input { + enum proc_cn_mcast_op mcast_op; +}; + /* * From the user's point of view, the process * ID is the thread group ID and thread ID is the internal @@ -44,24 +68,7 @@ enum proc_cn_mcast_op { */ struct proc_event { - enum what { - /* Use successive bits so the enums can be used to record - * sets of events as well - */ - PROC_EVENT_NONE = 0x00000000, - PROC_EVENT_FORK = 0x00000001, - PROC_EVENT_EXEC = 0x00000002, - PROC_EVENT_UID = 0x00000004, - PROC_EVENT_GID = 0x00000040, - PROC_EVENT_SID = 0x00000080, - PROC_EVENT_PTRACE = 0x00000100, - PROC_EVENT_COMM = 0x00000200, - /* "next" should be 0x00000400 */ - /* "last" is the last process event: exit, - * while "next to last" is coredumping event */ - PROC_EVENT_COREDUMP = 0x40000000, - PROC_EVENT_EXIT = 0x80000000 - } what; + enum proc_cn_event what; __u32 cpu; __u64 __attribute__((aligned(8))) timestamp_ns; /* Number of nano seconds since system boot */ -- cgit v1.2.3 From 743acf351bae1ff7ff4aaadd6a406d4d6091d90b Mon Sep 17 00:00:00 2001 From: Anjali Kulkarni Date: Wed, 19 Jul 2023 13:18:19 -0700 Subject: connector/cn_proc: Performance improvements This patch adds the capability to filter messages sent by the proc connector on the event type supplied in the message from the client to the connector. The client can register to listen for an event type given in struct proc_input. This event based filteting will greatly enhance performance - handling 8K exits takes about 70ms, whereas 8K-forks + 8K-exits takes about 150ms & handling 8K-forks + 8K-exits + 8K-execs takes 200ms. There are currently 9 different types of events, and we need to listen to all of them. Also, measuring the time using pidfds for monitoring 8K process exits took much longer - 200ms, as compared to 70ms using only exit notifications of proc connector. We also add a new event type - PROC_EVENT_NONZERO_EXIT, which is only sent by kernel to a listening application when any process exiting, has a non-zero exit status. This will help the clients like Oracle DB, where a monitoring process wants notfications for non-zero process exits so it can cleanup after them. This kind of a new event could also be useful to other applications like Google's lmkd daemon, which needs a killed process's exit notification. The patch takes care that existing clients using old mechanism of not sending the event type work without any changes. cn_filter function checks to see if the event type being notified via proc connector matches the event type requested by client, before sending(matches) or dropping(does not match) a packet. Signed-off-by: Anjali Kulkarni Reviewed-by: Liam R. Howlett Signed-off-by: David S. Miller --- drivers/connector/cn_proc.c | 62 +++++++++++++++++++++++++++++++++++++++----- include/uapi/linux/cn_proc.h | 19 ++++++++++++++ 2 files changed, 75 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 1ba288ed2bf7..dfc84d44f804 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -50,21 +50,45 @@ static DEFINE_PER_CPU(struct local_event, local_event) = { static int cn_filter(struct sock *dsk, struct sk_buff *skb, void *data) { + __u32 what, exit_code, *ptr; enum proc_cn_mcast_op mc_op; + uintptr_t val; - if (!dsk) + if (!dsk || !data) return 0; + ptr = (__u32 *)data; + what = *ptr++; + exit_code = *ptr; + val = ((struct proc_input *)(dsk->sk_user_data))->event_type; mc_op = ((struct proc_input *)(dsk->sk_user_data))->mcast_op; if (mc_op == PROC_CN_MCAST_IGNORE) return 1; - return 0; + if ((__u32)val == PROC_EVENT_ALL) + return 0; + + /* + * Drop packet if we have to report only non-zero exit status + * (PROC_EVENT_NONZERO_EXIT) and exit status is 0 + */ + if (((__u32)val & PROC_EVENT_NONZERO_EXIT) && + (what == PROC_EVENT_EXIT)) { + if (exit_code) + return 0; + } + + if ((__u32)val & what) + return 0; + + return 1; } static inline void send_msg(struct cn_msg *msg) { + __u32 filter_data[2]; + local_lock(&local_event.lock); msg->seq = __this_cpu_inc_return(local_event.count) - 1; @@ -76,8 +100,16 @@ static inline void send_msg(struct cn_msg *msg) * * If cn_netlink_send() fails, the data is not sent. */ + filter_data[0] = ((struct proc_event *)msg->data)->what; + if (filter_data[0] == PROC_EVENT_EXIT) { + filter_data[1] = + ((struct proc_event *)msg->data)->event_data.exit.exit_code; + } else { + filter_data[1] = 0; + } + cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, - cn_filter, NULL); + cn_filter, (void *)filter_data); local_unlock(&local_event.lock); } @@ -357,12 +389,15 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) /** * cn_proc_mcast_ctl - * @data: message sent from userspace via the connector + * @msg: message sent from userspace via the connector + * @nsp: NETLINK_CB of the client's socket buffer */ static void cn_proc_mcast_ctl(struct cn_msg *msg, struct netlink_skb_parms *nsp) { enum proc_cn_mcast_op mc_op = 0, prev_mc_op = 0; + struct proc_input *pinput = NULL; + enum proc_cn_event ev_type = 0; int err = 0, initial = 0; struct sock *sk = NULL; @@ -381,10 +416,21 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg, goto out; } - if (msg->len == sizeof(mc_op)) + if (msg->len == sizeof(*pinput)) { + pinput = (struct proc_input *)msg->data; + mc_op = pinput->mcast_op; + ev_type = pinput->event_type; + } else if (msg->len == sizeof(mc_op)) { mc_op = *((enum proc_cn_mcast_op *)msg->data); - else + ev_type = PROC_EVENT_ALL; + } else { return; + } + + ev_type = valid_event((enum proc_cn_event)ev_type); + + if (ev_type == PROC_EVENT_NONE) + ev_type = PROC_EVENT_ALL; if (nsp->sk) { sk = nsp->sk; @@ -400,6 +446,8 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg, prev_mc_op = ((struct proc_input *)(sk->sk_user_data))->mcast_op; } + ((struct proc_input *)(sk->sk_user_data))->event_type = + ev_type; ((struct proc_input *)(sk->sk_user_data))->mcast_op = mc_op; } @@ -411,6 +459,8 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg, case PROC_CN_MCAST_IGNORE: if (!initial && (prev_mc_op != PROC_CN_MCAST_IGNORE)) atomic_dec(&proc_event_num_listeners); + ((struct proc_input *)(sk->sk_user_data))->event_type = + PROC_EVENT_NONE; break; default: err = EINVAL; diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h index 6a06fb424313..f2afb7cc4926 100644 --- a/include/uapi/linux/cn_proc.h +++ b/include/uapi/linux/cn_proc.h @@ -30,6 +30,15 @@ enum proc_cn_mcast_op { PROC_CN_MCAST_IGNORE = 2 }; +#define PROC_EVENT_ALL (PROC_EVENT_FORK | PROC_EVENT_EXEC | PROC_EVENT_UID | \ + PROC_EVENT_GID | PROC_EVENT_SID | PROC_EVENT_PTRACE | \ + PROC_EVENT_COMM | PROC_EVENT_NONZERO_EXIT | \ + PROC_EVENT_COREDUMP | PROC_EVENT_EXIT) + +/* + * If you add an entry in proc_cn_event, make sure you add it in + * PROC_EVENT_ALL above as well. + */ enum proc_cn_event { /* Use successive bits so the enums can be used to record * sets of events as well @@ -45,15 +54,25 @@ enum proc_cn_event { /* "next" should be 0x00000400 */ /* "last" is the last process event: exit, * while "next to last" is coredumping event + * before that is report only if process dies + * with non-zero exit status */ + PROC_EVENT_NONZERO_EXIT = 0x20000000, PROC_EVENT_COREDUMP = 0x40000000, PROC_EVENT_EXIT = 0x80000000 }; struct proc_input { enum proc_cn_mcast_op mcast_op; + enum proc_cn_event event_type; }; +static inline enum proc_cn_event valid_event(enum proc_cn_event ev_type) +{ + ev_type &= PROC_EVENT_ALL; + return ev_type; +} + /* * From the user's point of view, the process * ID is the thread group ID and thread ID is the internal -- cgit v1.2.3 From 1671bcfd76fdc0b9e65153cf759153083755fe4c Mon Sep 17 00:00:00 2001 From: Patrick Rohr Date: Wed, 19 Jul 2023 07:52:13 -0700 Subject: net: add sysctl accept_ra_min_rtr_lft MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This change adds a new sysctl accept_ra_min_rtr_lft to specify the minimum acceptable router lifetime in an RA. If the received RA router lifetime is less than the configured value (and not 0), the RA is ignored. This is useful for mobile devices, whose battery life can be impacted by networks that configure RAs with a short lifetime. On such networks, the device should never gain IPv6 provisioning and should attempt to drop RAs via hardware offload, if available. Signed-off-by: Patrick Rohr Cc: Maciej Å»enczykowski Cc: Lorenzo Colitti Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.rst | 8 ++++++++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 10 ++++++++++ net/ipv6/ndisc.c | 18 ++++++++++++++++-- 5 files changed, 36 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 82f2117cf2b3..37603ad6126b 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2288,6 +2288,14 @@ accept_ra_min_hop_limit - INTEGER Default: 1 +accept_ra_min_rtr_lft - INTEGER + Minimum acceptable router lifetime in Router Advertisement. + + RAs with a router lifetime less than this value shall be + ignored. RAs with a router lifetime of 0 are unaffected. + + Default: 0 + accept_ra_pinfo - BOOLEAN Learn Prefix Information in Router Advertisement. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 839247a4f48e..ed3d110c2eb5 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -33,6 +33,7 @@ struct ipv6_devconf { __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; + __s32 accept_ra_min_rtr_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index ac56605fe9bc..8b6bcbf6ed4a 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -198,6 +198,7 @@ enum { DEVCONF_IOAM6_ID_WIDE, DEVCONF_NDISC_EVICT_NOCARRIER, DEVCONF_ACCEPT_UNTRACKED_NA, + DEVCONF_ACCEPT_RA_MIN_RTR_LFT, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e5213e598a04..19eb4b3d26ea 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -202,6 +202,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, + .accept_ra_min_rtr_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -262,6 +263,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, + .accept_ra_min_rtr_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -5596,6 +5598,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na; + array[DEVCONF_ACCEPT_RA_MIN_RTR_LFT] = cnf->accept_ra_min_rtr_lft; } static inline size_t inet6_ifla6_size(void) @@ -6789,6 +6792,13 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "accept_ra_min_rtr_lft", + .data = &ipv6_devconf.accept_ra_min_rtr_lft, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 18634ebd20a4..29ddad1c1a2f 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1280,6 +1280,8 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; + lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); + if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, did not accept ra for dev: %s\n", @@ -1287,6 +1289,13 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) goto skip_linkparms; } + if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { + ND_PRINTK(2, info, + "RA: router lifetime (%ds) is too short: %s\n", + lifetime, skb->dev->name); + goto skip_linkparms; + } + #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { @@ -1339,8 +1348,6 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) goto skip_defrtr; } - lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); - #ifdef CONFIG_IPV6_ROUTER_PREF pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ @@ -1492,6 +1499,13 @@ skip_linkparms: goto out; } + if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { + ND_PRINTK(2, info, + "RA: router lifetime (%ds) is too short: %s\n", + lifetime, skb->dev->name); + goto out; + } + #ifdef CONFIG_IPV6_ROUTE_INFO if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, -- cgit v1.2.3 From f5f80e32de12fad2813d37270e8364a03e6d3ef0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Jul 2023 11:09:01 +0000 Subject: ipv6: remove hard coded limitation on ipv6_pinfo IPv6 inet sockets are supposed to have a "struct ipv6_pinfo" field at the end of their definition, so that inet6_sk_generic() can derive from socket size the offset of the "struct ipv6_pinfo". This is very fragile, and prevents adding bigger alignment in sockets, because inet6_sk_generic() does not work if the compiler adds padding after the ipv6_pinfo component. We are currently working on a patch series to reorganize TCP structures for better data locality and found issues similar to the one fixed in commit f5d547676ca0 ("tcp: fix tcp_inet6_sk() for 32bit kernels") Alternative would be to force an alignment on "struct ipv6_pinfo", greater or equal to __alignof__(any ipv6 sock) to ensure there is no padding. This does not look great. v2: fix typo in mptcp_proto_v6_init() (Paolo) Signed-off-by: Eric Dumazet Cc: Chao Wu Cc: Wei Wang Cc: Coco Li Cc: YiFei Zhu Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/ipv6.h | 15 ++++----------- include/net/sock.h | 1 + net/dccp/ipv6.c | 1 + net/dccp/ipv6.h | 4 ---- net/ipv6/af_inet6.c | 4 ++-- net/ipv6/ping.c | 1 + net/ipv6/raw.c | 1 + net/ipv6/tcp_ipv6.c | 1 + net/ipv6/udp.c | 1 + net/ipv6/udplite.c | 1 + net/l2tp/l2tp_ip6.c | 4 +--- net/mptcp/protocol.c | 1 + net/sctp/socket.c | 1 + 13 files changed, 16 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ed3d110c2eb5..0295b47c10a3 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -200,14 +200,7 @@ struct inet6_cork { u8 tclass; }; -/** - * struct ipv6_pinfo - ipv6 private area - * - * In the struct sock hierarchy (tcp6_sock, upd6_sock, etc) - * this _must_ be the last member, so that inet6_sk_generic - * is able to calculate its offset from the base struct sock - * by using the struct proto->slab_obj_size member. -acme - */ +/* struct ipv6_pinfo - ipv6 private area */ struct ipv6_pinfo { struct in6_addr saddr; struct in6_pktinfo sticky_pktinfo; @@ -307,19 +300,19 @@ struct raw6_sock { __u32 offset; /* checksum offset */ struct icmp6_filter filter; __u32 ip6mr_table; - /* ipv6_pinfo has to be the last member of raw6_sock, see inet6_sk_generic */ + struct ipv6_pinfo inet6; }; struct udp6_sock { struct udp_sock udp; - /* ipv6_pinfo has to be the last member of udp6_sock, see inet6_sk_generic */ + struct ipv6_pinfo inet6; }; struct tcp6_sock { struct tcp_sock tcp; - /* ipv6_pinfo has to be the last member of tcp6_sock, see inet6_sk_generic */ + struct ipv6_pinfo inet6; }; diff --git a/include/net/sock.h b/include/net/sock.h index 2eb916d1ff64..7ae44bf866af 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1339,6 +1339,7 @@ struct proto { struct kmem_cache *slab; unsigned int obj_size; + unsigned int ipv6_pinfo_offset; slab_flags_t slab_flags; unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 7249ef218178..e03b5331df6d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1056,6 +1056,7 @@ static struct proto dccp_v6_prot = { .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp6_sock), + .ipv6_pinfo_offset = offsetof(struct dccp6_sock, inet6), .slab_flags = SLAB_TYPESAFE_BY_RCU, .rsk_prot = &dccp6_request_sock_ops, .twsk_prot = &dccp6_timewait_sock_ops, diff --git a/net/dccp/ipv6.h b/net/dccp/ipv6.h index 7e4c2a3b322b..c5d14c48def1 100644 --- a/net/dccp/ipv6.h +++ b/net/dccp/ipv6.h @@ -13,10 +13,6 @@ struct dccp6_sock { struct dccp_sock dccp; - /* - * ipv6_pinfo has to be the last member of dccp6_sock, - * see inet6_sk_generic. - */ struct ipv6_pinfo inet6; }; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 5d593ddc0347..9f9c4b838664 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -102,9 +102,9 @@ bool ipv6_mod_enabled(void) } EXPORT_SYMBOL_GPL(ipv6_mod_enabled); -static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) +static struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { - const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo); + const int offset = sk->sk_prot->ipv6_pinfo_offset; return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index f804c11e2146..2a0e8bc07398 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -215,6 +215,7 @@ struct proto pingv6_prot = { .get_port = ping_get_port, .put_port = ping_unhash, .obj_size = sizeof(struct raw6_sock), + .ipv6_pinfo_offset = offsetof(struct raw6_sock, inet6), }; EXPORT_SYMBOL_GPL(pingv6_prot); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ac1cef094c5f..0fcf1b890807 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1216,6 +1216,7 @@ struct proto rawv6_prot = { .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw6_sock), + .ipv6_pinfo_offset = offsetof(struct raw6_sock, inet6), .useroffset = offsetof(struct raw6_sock, filter), .usersize = sizeof_field(struct raw6_sock, filter), .h.raw_hash = &raw_v6_hashinfo, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4714eb695913..1b4529e833a1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2175,6 +2175,7 @@ struct proto tcpv6_prot = { .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), + .ipv6_pinfo_offset = offsetof(struct tcp6_sock, inet6), .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b7c972aa09a7..95c75d8f73d5 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1798,6 +1798,7 @@ struct proto udpv6_prot = { .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), + .ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6), .h.udp_table = NULL, .diag_destroy = udp_abort, }; diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 8e010d07917a..267d491e9707 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -67,6 +67,7 @@ struct proto udplitev6_prot = { .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), + .ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6), .h.udp_table = &udplite_table, }; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index b1623f9c4f92..2eee95a00c05 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -36,9 +36,6 @@ struct l2tp_ip6_sock { u32 conn_id; u32 peer_conn_id; - /* ipv6_pinfo has to be the last member of l2tp_ip6_sock, see - * inet6_sk_generic - */ struct ipv6_pinfo inet6; }; @@ -730,6 +727,7 @@ static struct proto l2tp_ip6_prot = { .hash = l2tp_ip6_hash, .unhash = l2tp_ip6_unhash, .obj_size = sizeof(struct l2tp_ip6_sock), + .ipv6_pinfo_offset = offsetof(struct l2tp_ip6_sock, inet6), }; static const struct proto_ops l2tp_ip6_ops = { diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3613489eb6e3..22323b1fa184 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3988,6 +3988,7 @@ int __init mptcp_proto_v6_init(void) strcpy(mptcp_v6_prot.name, "MPTCPv6"); mptcp_v6_prot.slab = NULL; mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock); + mptcp_v6_prot.ipv6_pinfo_offset = offsetof(struct mptcp6_sock, np); err = proto_register(&mptcp_v6_prot, 1); if (err) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9388d98aebc0..6e3d28aa587c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9732,6 +9732,7 @@ struct proto sctpv6_prot = { .unhash = sctp_unhash, .no_autobind = true, .obj_size = sizeof(struct sctp6_sock), + .ipv6_pinfo_offset = offsetof(struct sctp6_sock, inet6), .useroffset = offsetof(struct sctp6_sock, sctp.subscribe), .usersize = offsetof(struct sctp6_sock, sctp.initmsg) - offsetof(struct sctp6_sock, sctp.subscribe) + -- cgit v1.2.3 From a097627dcaddb90f55c1780da348bf9b56f6b4bd Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Fri, 21 Jul 2023 16:58:08 +0200 Subject: net: add missing net_device::xdp_zc_max_segs description Cited commit under 'Fixes' tag introduced new member to struct net_device without providing description of it - fix it. Reported-by: Stephen Rothwell Closes: https://lore.kernel.org/all/20230720141613.61488b9e@canb.auug.org.au/ Fixes: 13ce2daa259a ("xsk: add new netlink attribute dedicated for ZC max frags") Signed-off-by: Maciej Fijalkowski Reviewed-by: Simon Horman Tested-by: Simon Horman # build-tested Link: https://lore.kernel.org/r/20230721145808.596298-1-maciej.fijalkowski@intel.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3800d0479698..11652e464f5d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2043,6 +2043,8 @@ enum netdev_ml_priv_type { * receive offload (GRO) * @gro_ipv4_max_size: Maximum size of aggregated packet in generic * receive offload (GRO), for IPv4. + * @xdp_zc_max_segs: Maximum number of segments supported by AF_XDP + * zero copy driver * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. -- cgit v1.2.3 From b8dc6d6ce93142ccd4c976003bb6c25d63aac2ce Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 20 Jul 2023 20:47:50 +0200 Subject: mptcp: fix rcv buffer auto-tuning The MPTCP code uses the assumption that the tcp_win_from_space() helper does not use any TCP-specific field, and thus works correctly operating on an MPTCP socket. The commit dfa2f0483360 ("tcp: get rid of sysctl_tcp_adv_win_scale") broke such assumption, and as a consequence most MPTCP connections stall on zero-window event due to auto-tuning changing the rcv buffer size quite randomly. Address the issue syncing again the MPTCP auto-tuning code with the TCP one. To achieve that, factor out the windows size logic in socket independent helpers, and reuse them in mptcp_rcv_space_adjust(). The MPTCP level scaling_ratio is selected as the minimum one from the all the subflows, as a worst-case estimate. Fixes: dfa2f0483360 ("tcp: get rid of sysctl_tcp_adv_win_scale") Signed-off-by: Paolo Abeni Co-developed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Reviewed-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Link: https://lore.kernel.org/r/20230720-upstream-net-next-20230720-mptcp-fix-rcv-buffer-auto-tuning-v1-1-175ef12b8380@tessares.net Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 20 +++++++++++++++----- net/mptcp/protocol.c | 15 +++++++-------- net/mptcp/protocol.h | 8 +++++++- net/mptcp/subflow.c | 2 +- 4 files changed, 30 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index d17cb8ab4c48..6ebf54992ffe 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1430,22 +1430,32 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd); -static inline int tcp_win_from_space(const struct sock *sk, int space) +static inline int __tcp_win_from_space(u8 scaling_ratio, int space) { - s64 scaled_space = (s64)space * tcp_sk(sk)->scaling_ratio; + s64 scaled_space = (s64)space * scaling_ratio; return scaled_space >> TCP_RMEM_TO_WIN_SCALE; } -/* inverse of tcp_win_from_space() */ -static inline int tcp_space_from_win(const struct sock *sk, int win) +static inline int tcp_win_from_space(const struct sock *sk, int space) +{ + return __tcp_win_from_space(tcp_sk(sk)->scaling_ratio, space); +} + +/* inverse of __tcp_win_from_space() */ +static inline int __tcp_space_from_win(u8 scaling_ratio, int win) { u64 val = (u64)win << TCP_RMEM_TO_WIN_SCALE; - do_div(val, tcp_sk(sk)->scaling_ratio); + do_div(val, scaling_ratio); return val; } +static inline int tcp_space_from_win(const struct sock *sk, int win) +{ + return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win); +} + static inline void tcp_scaling_ratio_init(struct sock *sk) { /* Assume a conservative default of 1200 bytes of payload per 4K page. diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 22323b1fa184..68da26539970 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -90,6 +90,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) if (err) return err; + msk->scaling_ratio = tcp_sk(ssock->sk)->scaling_ratio; WRITE_ONCE(msk->first, ssock->sk); WRITE_ONCE(msk->subflow, ssock); subflow = mptcp_subflow_ctx(ssock->sk); @@ -1881,6 +1882,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; + u8 scaling_ratio = U8_MAX; u32 time, advmss = 1; u64 rtt_us, mstamp; @@ -1911,9 +1913,11 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) rtt_us = max(sf_rtt_us, rtt_us); advmss = max(sf_advmss, advmss); + scaling_ratio = min(tp->scaling_ratio, scaling_ratio); } msk->rcvq_space.rtt_us = rtt_us; + msk->scaling_ratio = scaling_ratio; if (time < (rtt_us >> 3) || rtt_us == 0) return; @@ -1922,8 +1926,8 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - int rcvmem, rcvbuf; u64 rcvwin, grow; + int rcvbuf; rcvwin = ((u64)msk->rcvq_space.copied << 1) + 16 * advmss; @@ -1932,18 +1936,13 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) do_div(grow, msk->rcvq_space.space); rcvwin += (grow << 1); - rcvmem = SKB_TRUESIZE(advmss + MAX_TCP_HEADER); - while (tcp_win_from_space(sk, rcvmem) < advmss) - rcvmem += 128; - - do_div(rcvwin, advmss); - rcvbuf = min_t(u64, rcvwin * rcvmem, + rcvbuf = min_t(u64, __tcp_space_from_win(scaling_ratio, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); if (rcvbuf > sk->sk_rcvbuf) { u32 window_clamp; - window_clamp = tcp_win_from_space(sk, rcvbuf); + window_clamp = __tcp_win_from_space(scaling_ratio, rcvbuf); WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make subflows follow along. If we do not do this, we diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 37fbe22e2433..795f422e8597 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -321,6 +321,7 @@ struct mptcp_sock { u64 time; /* start time of measurement window */ u64 rtt_us; /* last maximum rtt of subflows */ } rcvq_space; + u8 scaling_ratio; u32 subflow_id; u32 setsockopt_seq; @@ -351,9 +352,14 @@ static inline int __mptcp_rmem(const struct sock *sk) return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released); } +static inline int mptcp_win_from_space(const struct sock *sk, int space) +{ + return __tcp_win_from_space(mptcp_sk(sk)->scaling_ratio, space); +} + static inline int __mptcp_space(const struct sock *sk) { - return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk)); + return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk)); } static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9ee3b7abbaf6..ad7080fabb2f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1359,7 +1359,7 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) const struct sock *sk = subflow->conn; *space = __mptcp_space(sk); - *full_space = tcp_full_space(sk); + *full_space = mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } void __mptcp_error_report(struct sock *sk) -- cgit v1.2.3 From 4d72c3bb60dd9d5ea180f157bac72b4458112282 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Sat, 22 Jul 2023 21:32:59 +0100 Subject: net: phylink: strip out pre-March 2020 legacy code Strip out all the pre-March 2020 legacy code from phylink now that the last user of it is gone. Reviewed-by: Daniel Golle Tested-by: Daniel Golle Tested-by: Frank Wunderlich Signed-off-by: Russell King (Oracle) Signed-off-by: Paolo Abeni --- drivers/net/phy/phylink.c | 25 ++++--------------------- include/linux/phylink.h | 45 ++++++--------------------------------------- 2 files changed, 10 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index f07e496319b4..df413fb15088 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1198,13 +1198,6 @@ static int phylink_change_inband_advert(struct phylink *pl) if (test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) return 0; - if (!pl->pcs && pl->config->legacy_pre_march2020) { - /* Legacy method */ - phylink_mac_config(pl, &pl->link_config); - phylink_pcs_an_restart(pl); - return 0; - } - phylink_dbg(pl, "%s: mode=%s/%s adv=%*pb pause=%02x\n", __func__, phylink_an_mode_str(pl->cur_link_an_mode), phy_modes(pl->link_config.interface), @@ -1257,9 +1250,6 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, if (pl->pcs) pl->pcs->ops->pcs_get_state(pl->pcs, state); - else if (pl->mac_ops->mac_pcs_get_state && - pl->config->legacy_pre_march2020) - pl->mac_ops->mac_pcs_get_state(pl->config, state); else state->link = 0; } @@ -1492,13 +1482,6 @@ static void phylink_resolve(struct work_struct *w) } phylink_major_config(pl, false, &link_state); pl->link_config.interface = link_state.interface; - } else if (!pl->pcs && pl->config->legacy_pre_march2020) { - /* The interface remains unchanged, only the speed, - * duplex or pause settings have changed. Call the - * old mac_config() method to configure the MAC/PCS - * only if we do not have a legacy MAC driver. - */ - phylink_mac_config(pl, &link_state); } } @@ -3513,7 +3496,7 @@ static void phylink_decode_usgmii_word(struct phylink_link_state *state, * * Parse the Clause 37 or Cisco SGMII link partner negotiation word into * the phylink @state structure. This is suitable to be used for implementing - * the mac_pcs_get_state() member of the struct phylink_mac_ops structure if + * the pcs_get_state() member of the struct phylink_pcs_ops structure if * accessing @bmsr and @lpa cannot be done with MDIO directly. */ void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, @@ -3563,7 +3546,7 @@ EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_decode_state); * Read the MAC PCS state from the MII device configured in @config and * parse the Clause 37 or Cisco SGMII link partner negotiation word into * the phylink @state structure. This is suitable to be directly plugged - * into the mac_pcs_get_state() member of the struct phylink_mac_ops + * into the pcs_get_state() member of the struct phylink_pcs_ops * structure. */ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, @@ -3674,8 +3657,8 @@ EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_config); * clause 37 negotiation. * * Restart the clause 37 negotiation with the link partner. This is - * suitable to be directly plugged into the mac_pcs_get_state() member - * of the struct phylink_mac_ops structure. + * suitable to be directly plugged into the pcs_get_state() member + * of the struct phylink_pcs_ops structure. */ void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs) { diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 9e861c8316d0..789c516c6b4a 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -201,8 +201,6 @@ enum phylink_op_type { * struct phylink_config - PHYLINK configuration structure * @dev: a pointer to a struct device associated with the MAC * @type: operation type of PHYLINK instance - * @legacy_pre_march2020: driver has not been updated for March 2020 updates - * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. @@ -216,7 +214,6 @@ enum phylink_op_type { struct phylink_config { struct device *dev; enum phylink_op_type type; - bool legacy_pre_march2020; bool poll_fixed_state; bool mac_managed_pm; bool ovr_an_inband; @@ -230,7 +227,6 @@ struct phylink_config { * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. * @mac_select_pcs: Select a PCS for the interface mode. - * @mac_pcs_get_state: Read the current link state from the hardware. * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. * @mac_finish: finish a major reconfiguration of the interface. @@ -245,8 +241,6 @@ struct phylink_mac_ops { struct phylink_link_state *state); struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config, phy_interface_t interface); - void (*mac_pcs_get_state)(struct phylink_config *config, - struct phylink_link_state *state); int (*mac_prepare)(struct phylink_config *config, unsigned int mode, phy_interface_t iface); void (*mac_config)(struct phylink_config *config, unsigned int mode, @@ -312,25 +306,6 @@ void validate(struct phylink_config *config, unsigned long *supported, struct phylink_pcs *mac_select_pcs(struct phylink_config *config, phy_interface_t interface); -/** - * mac_pcs_get_state() - Read the current inband link state from the hardware - * @config: a pointer to a &struct phylink_config. - * @state: a pointer to a &struct phylink_link_state. - * - * Read the current inband link state from the MAC PCS, reporting the - * current speed in @state->speed, duplex mode in @state->duplex, pause - * mode in @state->pause using the %MLO_PAUSE_RX and %MLO_PAUSE_TX bits, - * negotiation completion state in @state->an_complete, and link up state - * in @state->link. If possible, @state->lp_advertising should also be - * populated. - * - * Note: This is a legacy method. This function will not be called unless - * legacy_pre_march2020 is set in &struct phylink_config and there is no - * PCS attached. - */ -void mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state); - /** * mac_prepare() - prepare to change the PHY interface mode * @config: a pointer to a &struct phylink_config. @@ -367,17 +342,9 @@ int mac_prepare(struct phylink_config *config, unsigned int mode, * guaranteed to be correct, and so any mac_config() implementation must * never reference these fields. * - * Note: For legacy March 2020 drivers (drivers with legacy_pre_march2020 set - * in their &phylnk_config and which don't have a PCS), this function will be - * called on each link up event, and to also change the in-band advert. For - * non-legacy drivers, it will only be called to reconfigure the MAC for a - * "major" change in e.g. interface mode. It will not be called for changes - * in speed, duplex or pause modes or to change the in-band advertisement. - * In any case, it is strongly preferred that speed, duplex and pause settings - * are handled in the mac_link_up() method and not in this method. - * - * (this requires a rewrite - please refer to mac_link_up() for situations - * where the PCS and MAC are not tightly integrated.) + * This will only be called to reconfigure the MAC for a "major" change in + * e.g. interface mode. It will not be called for changes in speed, duplex + * or pause modes or to change the in-band advertisement. * * In all negotiation modes, as defined by @mode, @state->pause indicates the * pause settings which should be applied as follows. If %MLO_PAUSE_AN is not @@ -409,7 +376,7 @@ int mac_prepare(struct phylink_config *config, unsigned int mode, * 1000base-X or Cisco SGMII mode depending on the @state->interface * mode). In both cases, link state management (whether the link * is up or not) is performed by the MAC, and reported via the - * mac_pcs_get_state() callback. Changes in link state must be made + * pcs_get_state() callback. Changes in link state must be made * by calling phylink_mac_change(). * * Interface mode specific details are mentioned below. @@ -601,8 +568,8 @@ void pcs_disable(struct phylink_pcs *pcs); * in @state->link. If possible, @state->lp_advertising should also be * populated. * - * When present, this overrides mac_pcs_get_state() in &struct - * phylink_mac_ops. + * When present, this overrides pcs_get_state() in &struct + * phylink_pcs_ops. */ void pcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state); -- cgit v1.2.3 From 57266281271add0132bea0b83ef0d6f32704c402 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 19 Jul 2023 12:26:53 +0300 Subject: net/mlx5: Add relevant capabilities bits to support NAT-T Provide an ability to check if flow steering supports UDP encapsulation and decapsulation of IPsec ESP packets. Signed-off-by: Leon Romanovsky Signed-off-by: Paolo Abeni --- include/linux/mlx5/mlx5_ifc.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 33344a71c3e3..b3ad6b9852ec 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -464,10 +464,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reformat_add_esp_trasport[0x1]; u8 reformat_l2_to_l3_esp_tunnel[0x1]; - u8 reserved_at_42[0x1]; + u8 reformat_add_esp_transport_over_udp[0x1]; u8 reformat_del_esp_trasport[0x1]; u8 reformat_l3_esp_tunnel_to_l2[0x1]; - u8 reserved_at_45[0x1]; + u8 reformat_del_esp_transport_over_udp[0x1]; u8 execute_aso[0x1]; u8 reserved_at_47[0x19]; @@ -6665,9 +6665,12 @@ enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4 = 0x5, MLX5_REFORMAT_TYPE_L2_TO_L3_ESP_TUNNEL = 0x6, + MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV4 = 0x7, MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT = 0x8, MLX5_REFORMAT_TYPE_L3_ESP_TUNNEL_TO_L2 = 0x9, + MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT_OVER_UDP = 0xa, MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6 = 0xb, + MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV6 = 0xc, MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, MLX5_REFORMAT_TYPE_ADD_MACSEC = 0x11, -- cgit v1.2.3 From ce796e60b3b196b61fcc565df195443cbb846ef0 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:07 +0200 Subject: net: export inet_lookup_reuseport and inet6_lookup_reuseport Rename the existing reuseport helpers for IPv4 and IPv6 so that they can be invoked in the follow up commit. Export them so that building DCCP and IPv6 as a module works. No change in functionality. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-3-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- include/net/inet6_hashtables.h | 7 +++++++ include/net/inet_hashtables.h | 5 +++++ net/ipv4/inet_hashtables.c | 15 ++++++++------- net/ipv6/inet6_hashtables.c | 19 ++++++++++--------- 4 files changed, 30 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 56f1286583d3..032ddab48f8f 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -48,6 +48,13 @@ struct sock *__inet6_lookup_established(struct net *net, const u16 hnum, const int dif, const int sdif); +struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, + struct sk_buff *skb, int doff, + const struct in6_addr *saddr, + __be16 sport, + const struct in6_addr *daddr, + unsigned short hnum); + struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 99bd823e97f6..8734f3488f5d 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -379,6 +379,11 @@ struct sock *__inet_lookup_established(struct net *net, const __be32 daddr, const u16 hnum, const int dif, const int sdif); +struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, + struct sk_buff *skb, int doff, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned short hnum); + static inline struct sock * inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0819d6001b9a..ecb838460629 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -332,10 +332,10 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } -static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk, - struct sk_buff *skb, int doff, - __be32 saddr, __be16 sport, - __be32 daddr, unsigned short hnum) +struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, + struct sk_buff *skb, int doff, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned short hnum) { struct sock *reuse_sk = NULL; u32 phash; @@ -346,6 +346,7 @@ static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk, } return reuse_sk; } +EXPORT_SYMBOL_GPL(inet_lookup_reuseport); /* * Here are some nice properties to exploit here. The BSD API @@ -369,8 +370,8 @@ static struct sock *inet_lhash2_lookup(struct net *net, sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) { score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { - result = lookup_reuseport(net, sk, skb, doff, - saddr, sport, daddr, hnum); + result = inet_lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, hnum); if (result) return result; @@ -399,7 +400,7 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); + reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); if (reuse_sk) sk = reuse_sk; return sk; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b64b49012655..b7c56867314e 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -111,12 +111,12 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } -static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk, - struct sk_buff *skb, int doff, - const struct in6_addr *saddr, - __be16 sport, - const struct in6_addr *daddr, - unsigned short hnum) +struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, + struct sk_buff *skb, int doff, + const struct in6_addr *saddr, + __be16 sport, + const struct in6_addr *daddr, + unsigned short hnum) { struct sock *reuse_sk = NULL; u32 phash; @@ -127,6 +127,7 @@ static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk, } return reuse_sk; } +EXPORT_SYMBOL_GPL(inet6_lookup_reuseport); /* called with rcu_read_lock() */ static struct sock *inet6_lhash2_lookup(struct net *net, @@ -143,8 +144,8 @@ static struct sock *inet6_lhash2_lookup(struct net *net, sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) { score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { - result = lookup_reuseport(net, sk, skb, doff, - saddr, sport, daddr, hnum); + result = inet6_lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, hnum); if (result) return result; @@ -175,7 +176,7 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); + reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); if (reuse_sk) sk = reuse_sk; return sk; -- cgit v1.2.3 From 0f495f7617229772403e683033abc473f0f0553c Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:08 +0200 Subject: net: remove duplicate reuseport_lookup functions There are currently four copies of reuseport_lookup: one each for (TCP, UDP)x(IPv4, IPv6). This forces us to duplicate all callers of those functions as well. This is already the case for sk_lookup helpers (inet,inet6,udp4,udp6)_lookup_run_bpf. There are two differences between the reuseport_lookup helpers: 1. They call different hash functions depending on protocol 2. UDP reuseport_lookup checks that sk_state != TCP_ESTABLISHED Move the check for sk_state into the caller and use the INDIRECT_CALL infrastructure to cut down the helpers to one per IP version. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-4-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- include/net/inet6_hashtables.h | 11 ++++++++++- include/net/inet_hashtables.h | 15 ++++++++++----- net/ipv4/inet_hashtables.c | 20 +++++++++++++------- net/ipv4/udp.c | 34 +++++++++++++--------------------- net/ipv6/inet6_hashtables.c | 14 ++++++++++---- net/ipv6/udp.c | 41 ++++++++++++++++------------------------- 6 files changed, 72 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 032ddab48f8f..f89320b6fee3 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -48,12 +48,21 @@ struct sock *__inet6_lookup_established(struct net *net, const u16 hnum, const int dif, const int sdif); +typedef u32 (inet6_ehashfn_t)(const struct net *net, + const struct in6_addr *laddr, const u16 lport, + const struct in6_addr *faddr, const __be16 fport); + +inet6_ehashfn_t inet6_ehashfn; + +INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); + struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, - unsigned short hnum); + unsigned short hnum, + inet6_ehashfn_t *ehashfn); struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 8734f3488f5d..ddfa2e67fdb5 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -379,10 +379,19 @@ struct sock *__inet_lookup_established(struct net *net, const __be32 daddr, const u16 hnum, const int dif, const int sdif); +typedef u32 (inet_ehashfn_t)(const struct net *net, + const __be32 laddr, const __u16 lport, + const __be32 faddr, const __be16 fport); + +inet_ehashfn_t inet_ehashfn; + +INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); + struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, - __be32 daddr, unsigned short hnum); + __be32 daddr, unsigned short hnum, + inet_ehashfn_t *ehashfn); static inline struct sock * inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, @@ -453,10 +462,6 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, refcounted); } -u32 inet6_ehashfn(const struct net *net, - const struct in6_addr *laddr, const u16 lport, - const struct in6_addr *faddr, const __be16 fport); - static inline void sk_daddr_set(struct sock *sk, __be32 addr) { sk->sk_daddr = addr; /* alias of inet_daddr */ diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index ecb838460629..0a7a726464d9 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -28,9 +28,9 @@ #include #include -static u32 inet_ehashfn(const struct net *net, const __be32 laddr, - const __u16 lport, const __be32 faddr, - const __be16 fport) +u32 inet_ehashfn(const struct net *net, const __be32 laddr, + const __u16 lport, const __be32 faddr, + const __be16 fport) { static u32 inet_ehash_secret __read_mostly; @@ -39,6 +39,7 @@ static u32 inet_ehashfn(const struct net *net, const __be32 laddr, return __inet_ehashfn(laddr, lport, faddr, fport, inet_ehash_secret + net_hash_mix(net)); } +EXPORT_SYMBOL_GPL(inet_ehashfn); /* This function handles inet_sock, but also timewait and request sockets * for IPv4/IPv6. @@ -332,16 +333,20 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } +INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); + struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, - __be32 daddr, unsigned short hnum) + __be32 daddr, unsigned short hnum, + inet_ehashfn_t *ehashfn) { struct sock *reuse_sk = NULL; u32 phash; if (sk->sk_reuseport) { - phash = inet_ehashfn(net, daddr, hnum, saddr, sport); + phash = INDIRECT_CALL_2(ehashfn, udp_ehashfn, inet_ehashfn, + net, daddr, hnum, saddr, sport); reuse_sk = reuseport_select_sock(sk, phash, skb, doff); } return reuse_sk; @@ -371,7 +376,7 @@ static struct sock *inet_lhash2_lookup(struct net *net, score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = inet_lookup_reuseport(net, sk, skb, doff, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, inet_ehashfn); if (result) return result; @@ -400,7 +405,8 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); + reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, + inet_ehashfn); if (reuse_sk) sk = reuse_sk; return sk; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0d81339bda2f..3abe8a1520da 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -406,9 +406,9 @@ static int compute_score(struct sock *sk, struct net *net, return score; } -static u32 udp_ehashfn(const struct net *net, const __be32 laddr, - const __u16 lport, const __be32 faddr, - const __be16 fport) +INDIRECT_CALLABLE_SCOPE +u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, + const __be32 faddr, const __be16 fport) { static u32 udp_ehash_secret __read_mostly; @@ -418,22 +418,6 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr, udp_ehash_secret + net_hash_mix(net)); } -static struct sock *lookup_reuseport(struct net *net, struct sock *sk, - struct sk_buff *skb, - __be32 saddr, __be16 sport, - __be32 daddr, unsigned short hnum) -{ - struct sock *reuse_sk = NULL; - u32 hash; - - if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { - hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - reuse_sk = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - } - return reuse_sk; -} - /* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, @@ -452,7 +436,14 @@ static struct sock *udp4_lib_lookup2(struct net *net, daddr, hnum, dif, sdif); if (score > badness) { badness = score; - result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + + if (sk->sk_state == TCP_ESTABLISHED) { + result = sk; + continue; + } + + result = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp_ehashfn); if (!result) { result = sk; continue; @@ -491,7 +482,8 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + reuse_sk = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp_ehashfn); if (reuse_sk) sk = reuse_sk; return sk; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b7c56867314e..3616225c89ef 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -39,6 +39,7 @@ u32 inet6_ehashfn(const struct net *net, return __inet6_ehashfn(lhash, lport, fhash, fport, inet6_ehash_secret + net_hash_mix(net)); } +EXPORT_SYMBOL_GPL(inet6_ehashfn); /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so @@ -111,18 +112,22 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } +INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); + struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, - unsigned short hnum) + unsigned short hnum, + inet6_ehashfn_t *ehashfn) { struct sock *reuse_sk = NULL; u32 phash; if (sk->sk_reuseport) { - phash = inet6_ehashfn(net, daddr, hnum, saddr, sport); + phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn, + net, daddr, hnum, saddr, sport); reuse_sk = reuseport_select_sock(sk, phash, skb, doff); } return reuse_sk; @@ -145,7 +150,7 @@ static struct sock *inet6_lhash2_lookup(struct net *net, score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = inet6_lookup_reuseport(net, sk, skb, doff, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, inet6_ehashfn); if (result) return result; @@ -176,7 +181,8 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); + reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, hnum, inet6_ehashfn); if (reuse_sk) sk = reuse_sk; return sk; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 556d74a7d7ab..918ca1771710 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -71,11 +71,12 @@ int udpv6_init_sock(struct sock *sk) return 0; } -static u32 udp6_ehashfn(const struct net *net, - const struct in6_addr *laddr, - const u16 lport, - const struct in6_addr *faddr, - const __be16 fport) +INDIRECT_CALLABLE_SCOPE +u32 udp6_ehashfn(const struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) { static u32 udp6_ehash_secret __read_mostly; static u32 udp_ipv6_hash_secret __read_mostly; @@ -160,24 +161,6 @@ static int compute_score(struct sock *sk, struct net *net, return score; } -static struct sock *lookup_reuseport(struct net *net, struct sock *sk, - struct sk_buff *skb, - const struct in6_addr *saddr, - __be16 sport, - const struct in6_addr *daddr, - unsigned int hnum) -{ - struct sock *reuse_sk = NULL; - u32 hash; - - if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { - hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - reuse_sk = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - } - return reuse_sk; -} - /* called with rcu_read_lock() */ static struct sock *udp6_lib_lookup2(struct net *net, const struct in6_addr *saddr, __be16 sport, @@ -195,7 +178,14 @@ static struct sock *udp6_lib_lookup2(struct net *net, daddr, hnum, dif, sdif); if (score > badness) { badness = score; - result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + + if (sk->sk_state == TCP_ESTABLISHED) { + result = sk; + continue; + } + + result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp6_ehashfn); if (!result) { result = sk; continue; @@ -235,7 +225,8 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + reuse_sk = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp6_ehashfn); if (reuse_sk) sk = reuse_sk; return sk; -- cgit v1.2.3 From 6c886db2e78ce1dee163d07240467770a235f33e Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:10 +0200 Subject: net: remove duplicate sk_lookup helpers Now that inet[6]_lookup_reuseport are parameterised on the ehashfn we can remove two sk_lookup helpers. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-6-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- include/net/inet6_hashtables.h | 9 +++++++++ include/net/inet_hashtables.h | 7 +++++++ net/ipv4/inet_hashtables.c | 26 +++++++++++++------------- net/ipv4/udp.c | 32 +++++--------------------------- net/ipv6/inet6_hashtables.c | 31 ++++++++++++++++--------------- net/ipv6/udp.c | 34 +++++----------------------------- 6 files changed, 55 insertions(+), 84 deletions(-) (limited to 'include') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index f89320b6fee3..a6722d6ef80f 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -73,6 +73,15 @@ struct sock *inet6_lookup_listener(struct net *net, const unsigned short hnum, const int dif, const int sdif); +struct sock *inet6_lookup_run_sk_lookup(struct net *net, + int protocol, + struct sk_buff *skb, int doff, + const struct in6_addr *saddr, + const __be16 sport, + const struct in6_addr *daddr, + const u16 hnum, const int dif, + inet6_ehashfn_t *ehashfn); + static inline struct sock *__inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ddfa2e67fdb5..c0532cc7587f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -393,6 +393,13 @@ struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, __be32 daddr, unsigned short hnum, inet_ehashfn_t *ehashfn); +struct sock *inet_lookup_run_sk_lookup(struct net *net, + int protocol, + struct sk_buff *skb, int doff, + __be32 saddr, __be16 sport, + __be32 daddr, u16 hnum, const int dif, + inet_ehashfn_t *ehashfn); + static inline struct sock * inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e9cec4807694..6a872b8fb0d3 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -403,25 +403,23 @@ static struct sock *inet_lhash2_lookup(struct net *net, return result; } -static inline struct sock *inet_lookup_run_bpf(struct net *net, - struct inet_hashinfo *hashinfo, - struct sk_buff *skb, int doff, - __be32 saddr, __be16 sport, - __be32 daddr, u16 hnum, const int dif) +struct sock *inet_lookup_run_sk_lookup(struct net *net, + int protocol, + struct sk_buff *skb, int doff, + __be32 saddr, __be16 sport, + __be32 daddr, u16 hnum, const int dif, + inet_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool no_reuseport; - if (hashinfo != net->ipv4.tcp_death_row.hashinfo) - return NULL; /* only TCP is supported */ - - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport, + no_reuseport = bpf_sk_lookup_run_v4(net, protocol, saddr, sport, daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, - inet_ehashfn); + ehashfn); if (reuse_sk) sk = reuse_sk; return sk; @@ -439,9 +437,11 @@ struct sock *__inet_lookup_listener(struct net *net, unsigned int hash2; /* Lookup redirect from BPF */ - if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { - result = inet_lookup_run_bpf(net, hashinfo, skb, doff, - saddr, sport, daddr, hnum, dif); + if (static_branch_unlikely(&bpf_sk_lookup_enabled) && + hashinfo == net->ipv4.tcp_death_row.hashinfo) { + result = inet_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff, + saddr, sport, daddr, hnum, dif, + inet_ehashfn); if (result) goto done; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 3abe8a1520da..456fb6ee6ee8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -465,30 +465,6 @@ static struct sock *udp4_lib_lookup2(struct net *net, return result; } -static struct sock *udp4_lookup_run_bpf(struct net *net, - struct udp_table *udptable, - struct sk_buff *skb, - __be32 saddr, __be16 sport, - __be32 daddr, u16 hnum, const int dif) -{ - struct sock *sk, *reuse_sk; - bool no_reuseport; - - if (udptable != net->ipv4.udp_table) - return NULL; /* only UDP is supported */ - - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport, - daddr, hnum, dif, &sk); - if (no_reuseport || IS_ERR_OR_NULL(sk)) - return sk; - - reuse_sk = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), - saddr, sport, daddr, hnum, udp_ehashfn); - if (reuse_sk) - sk = reuse_sk; - return sk; -} - /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ @@ -513,9 +489,11 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, goto done; /* Lookup redirect from BPF */ - if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { - sk = udp4_lookup_run_bpf(net, udptable, skb, - saddr, sport, daddr, hnum, dif); + if (static_branch_unlikely(&bpf_sk_lookup_enabled) && + udptable == net->ipv4.udp_table) { + sk = inet_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, dif, + udp_ehashfn); if (sk) { result = sk; goto done; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index f76dbbb29332..7c9700c7c9c8 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -177,31 +177,30 @@ static struct sock *inet6_lhash2_lookup(struct net *net, return result; } -static inline struct sock *inet6_lookup_run_bpf(struct net *net, - struct inet_hashinfo *hashinfo, - struct sk_buff *skb, int doff, - const struct in6_addr *saddr, - const __be16 sport, - const struct in6_addr *daddr, - const u16 hnum, const int dif) +struct sock *inet6_lookup_run_sk_lookup(struct net *net, + int protocol, + struct sk_buff *skb, int doff, + const struct in6_addr *saddr, + const __be16 sport, + const struct in6_addr *daddr, + const u16 hnum, const int dif, + inet6_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool no_reuseport; - if (hashinfo != net->ipv4.tcp_death_row.hashinfo) - return NULL; /* only TCP is supported */ - - no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, saddr, sport, + no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport, daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, - saddr, sport, daddr, hnum, inet6_ehashfn); + saddr, sport, daddr, hnum, ehashfn); if (reuse_sk) sk = reuse_sk; return sk; } +EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup); struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, @@ -215,9 +214,11 @@ struct sock *inet6_lookup_listener(struct net *net, unsigned int hash2; /* Lookup redirect from BPF */ - if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { - result = inet6_lookup_run_bpf(net, hashinfo, skb, doff, - saddr, sport, daddr, hnum, dif); + if (static_branch_unlikely(&bpf_sk_lookup_enabled) && + hashinfo == net->ipv4.tcp_death_row.hashinfo) { + result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff, + saddr, sport, daddr, hnum, dif, + inet6_ehashfn); if (result) goto done; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 918ca1771710..4b8974a8c7a3 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -206,32 +206,6 @@ static struct sock *udp6_lib_lookup2(struct net *net, return result; } -static inline struct sock *udp6_lookup_run_bpf(struct net *net, - struct udp_table *udptable, - struct sk_buff *skb, - const struct in6_addr *saddr, - __be16 sport, - const struct in6_addr *daddr, - u16 hnum, const int dif) -{ - struct sock *sk, *reuse_sk; - bool no_reuseport; - - if (udptable != net->ipv4.udp_table) - return NULL; /* only UDP is supported */ - - no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport, - daddr, hnum, dif, &sk); - if (no_reuseport || IS_ERR_OR_NULL(sk)) - return sk; - - reuse_sk = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), - saddr, sport, daddr, hnum, udp6_ehashfn); - if (reuse_sk) - sk = reuse_sk; - return sk; -} - /* rcu_read_lock() must be held */ struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, @@ -256,9 +230,11 @@ struct sock *__udp6_lib_lookup(struct net *net, goto done; /* Lookup redirect from BPF */ - if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { - sk = udp6_lookup_run_bpf(net, udptable, skb, - saddr, sport, daddr, hnum, dif); + if (static_branch_unlikely(&bpf_sk_lookup_enabled) && + udptable == net->ipv4.udp_table) { + sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, dif, + udp6_ehashfn); if (sk) { result = sk; goto done; -- cgit v1.2.3 From 9c02bec95954252c3c01bfbb3f7560e0b95ca955 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:11 +0200 Subject: bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign Currently the bpf_sk_assign helper in tc BPF context refuses SO_REUSEPORT sockets. This means we can't use the helper to steer traffic to Envoy, which configures SO_REUSEPORT on its sockets. In turn, we're blocked from removing TPROXY from our setup. The reason that bpf_sk_assign refuses such sockets is that the bpf_sk_lookup helpers don't execute SK_REUSEPORT programs. Instead, one of the reuseport sockets is selected by hash. This could cause dispatch to the "wrong" socket: sk = bpf_sk_lookup_tcp(...) // select SO_REUSEPORT by hash bpf_sk_assign(skb, sk) // SK_REUSEPORT wasn't executed Fixing this isn't as simple as invoking SK_REUSEPORT from the lookup helpers unfortunately. In the tc context, L2 headers are at the start of the skb, while SK_REUSEPORT expects L3 headers instead. Instead, we execute the SK_REUSEPORT program when the assigned socket is pulled out of the skb, further up the stack. This creates some trickiness with regards to refcounting as bpf_sk_assign will put both refcounted and RCU freed sockets in skb->sk. reuseport sockets are RCU freed. We can infer that the sk_assigned socket is RCU freed if the reuseport lookup succeeds, but convincing yourself of this fact isn't straight forward. Therefore we defensively check refcounting on the sk_assign sock even though it's probably not required in practice. Fixes: 8e368dc72e86 ("bpf: Fix use of sk->sk_reuseport from sk_assign") Fixes: cf7fbe660f2d ("bpf: Add socket assign support") Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Cc: Joe Stringer Link: https://lore.kernel.org/bpf/CACAyw98+qycmpQzKupquhkxbvWK4OFyDuuLMBNROnfWMZxUWeA@mail.gmail.com/ Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-7-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- include/net/inet6_hashtables.h | 56 ++++++++++++++++++++++++++++++++++++++---- include/net/inet_hashtables.h | 49 ++++++++++++++++++++++++++++++++++-- include/net/sock.h | 7 ++++-- include/uapi/linux/bpf.h | 3 --- net/core/filter.c | 2 -- net/ipv4/udp.c | 8 ++++-- net/ipv6/udp.c | 8 ++++-- tools/include/uapi/linux/bpf.h | 3 --- 8 files changed, 115 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index a6722d6ef80f..284b5ce7205d 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -103,6 +103,46 @@ static inline struct sock *__inet6_lookup(struct net *net, daddr, hnum, dif, sdif); } +static inline +struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff, + const struct in6_addr *saddr, const __be16 sport, + const struct in6_addr *daddr, const __be16 dport, + bool *refcounted, inet6_ehashfn_t *ehashfn) +{ + struct sock *sk, *reuse_sk; + bool prefetched; + + sk = skb_steal_sock(skb, refcounted, &prefetched); + if (!sk) + return NULL; + + if (!prefetched) + return sk; + + if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_state != TCP_LISTEN) + return sk; + } else if (sk->sk_protocol == IPPROTO_UDP) { + if (sk->sk_state != TCP_CLOSE) + return sk; + } else { + return sk; + } + + reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, ntohs(dport), + ehashfn); + if (!reuse_sk) + return sk; + + /* We've chosen a new reuseport sock which is never refcounted. This + * implies that sk also isn't refcounted. + */ + WARN_ON_ONCE(*refcounted); + + return reuse_sk; +} + static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be16 sport, @@ -110,14 +150,20 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, int iif, int sdif, bool *refcounted) { - struct sock *sk = skb_steal_sock(skb, refcounted); - + struct net *net = dev_net(skb_dst(skb)->dev); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct sock *sk; + + sk = inet6_steal_sock(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, dport, + refcounted, inet6_ehashfn); + if (IS_ERR(sk)) + return NULL; if (sk) return sk; - return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, - doff, &ipv6_hdr(skb)->saddr, sport, - &ipv6_hdr(skb)->daddr, ntohs(dport), + return __inet6_lookup(net, hashinfo, skb, + doff, &ip6h->saddr, sport, + &ip6h->daddr, ntohs(dport), iif, sdif, refcounted); } diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index c0532cc7587f..1177effabed3 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -449,6 +449,46 @@ static inline struct sock *inet_lookup(struct net *net, return sk; } +static inline +struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff, + const __be32 saddr, const __be16 sport, + const __be32 daddr, const __be16 dport, + bool *refcounted, inet_ehashfn_t *ehashfn) +{ + struct sock *sk, *reuse_sk; + bool prefetched; + + sk = skb_steal_sock(skb, refcounted, &prefetched); + if (!sk) + return NULL; + + if (!prefetched) + return sk; + + if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_state != TCP_LISTEN) + return sk; + } else if (sk->sk_protocol == IPPROTO_UDP) { + if (sk->sk_state != TCP_CLOSE) + return sk; + } else { + return sk; + } + + reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, ntohs(dport), + ehashfn); + if (!reuse_sk) + return sk; + + /* We've chosen a new reuseport sock which is never refcounted. This + * implies that sk also isn't refcounted. + */ + WARN_ON_ONCE(*refcounted); + + return reuse_sk; +} + static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, @@ -457,13 +497,18 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, const int sdif, bool *refcounted) { - struct sock *sk = skb_steal_sock(skb, refcounted); + struct net *net = dev_net(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); + struct sock *sk; + sk = inet_steal_sock(net, skb, doff, iph->saddr, sport, iph->daddr, dport, + refcounted, inet_ehashfn); + if (IS_ERR(sk)) + return NULL; if (sk) return sk; - return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, + return __inet_lookup(net, hashinfo, skb, doff, iph->saddr, sport, iph->daddr, dport, inet_iif(skb), sdif, refcounted); diff --git a/include/net/sock.h b/include/net/sock.h index 7ae44bf866af..74cbfb15d289 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2815,20 +2815,23 @@ sk_is_refcounted(struct sock *sk) * skb_steal_sock - steal a socket from an sk_buff * @skb: sk_buff to steal the socket from * @refcounted: is set to true if the socket is reference-counted + * @prefetched: is set to true if the socket was assigned from bpf */ static inline struct sock * -skb_steal_sock(struct sk_buff *skb, bool *refcounted) +skb_steal_sock(struct sk_buff *skb, bool *refcounted, bool *prefetched) { if (skb->sk) { struct sock *sk = skb->sk; *refcounted = true; - if (skb_sk_is_prefetched(skb)) + *prefetched = skb_sk_is_prefetched(skb); + if (*prefetched) *refcounted = sk_is_refcounted(sk); skb->destructor = NULL; skb->sk = NULL; return sk; } + *prefetched = false; *refcounted = false; return NULL; } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 739c15906a65..7fc98f4b63e9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4198,9 +4198,6 @@ union bpf_attr { * **-EOPNOTSUPP** if the operation is not supported, for example * a call from outside of TC ingress. * - * **-ESOCKTNOSUPPORT** if the socket type is not supported - * (reuseport). - * * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) * Description * Helper is overloaded depending on BPF program type. This diff --git a/net/core/filter.c b/net/core/filter.c index b5b51ef48c5f..7c37f4646c20 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7351,8 +7351,6 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) return -EOPNOTSUPP; if (unlikely(dev_net(skb->dev) != sock_net(sk))) return -ENETUNREACH; - if (unlikely(sk_fullsock(sk) && sk->sk_reuseport)) - return -ESOCKTNOSUPPORT; if (sk_unhashed(sk)) return -EOPNOTSUPP; if (sk_is_refcounted(sk) && diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 456fb6ee6ee8..d89c4a39cf27 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2388,7 +2388,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; - sk = skb_steal_sock(skb, &refcounted); + sk = inet_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest, + &refcounted, udp_ehashfn); + if (IS_ERR(sk)) + goto no_sk; + if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; @@ -2409,7 +2413,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) return udp_unicast_rcv_skb(sk, skb, uh); - +no_sk: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; nf_reset_ct(skb); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4b8974a8c7a3..00996f0f7cfe 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -964,7 +964,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, goto csum_error; /* Check if the socket is already available, e.g. due to early demux */ - sk = skb_steal_sock(skb, &refcounted); + sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest, + &refcounted, udp6_ehashfn); + if (IS_ERR(sk)) + goto no_sk; + if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; @@ -998,7 +1002,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, goto report_csum_error; return udp6_unicast_rcv_skb(sk, skb, uh); } - +no_sk: reason = SKB_DROP_REASON_NO_SOCKET; if (!uh->check) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 739c15906a65..7fc98f4b63e9 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4198,9 +4198,6 @@ union bpf_attr { * **-EOPNOTSUPP** if the operation is not supported, for example * a call from outside of TC ingress. * - * **-ESOCKTNOSUPPORT** if the socket type is not supported - * (reuseport). - * * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) * Description * Helper is overloaded depending on BPF program type. This -- cgit v1.2.3 From 2303fae130640874823ea1bc7ec65c3cd074a7eb Mon Sep 17 00:00:00 2001 From: Peter Seiderer Date: Mon, 24 Jul 2023 18:22:55 +0200 Subject: net: skbuff: remove unused HAVE_HW_TIME_STAMP feature define Remove unused HAVE_HW_TIME_STAMP feature define (introduced by commit ac45f602ee3d ("net: infrastructure for hardware time stamping"). Signed-off-by: Peter Seiderer Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index faaba050f843..16a49ba534e4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -441,8 +441,6 @@ static inline bool skb_frag_must_loop(struct page *p) copied += p_len, p++, p_off = 0, \ p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ -#define HAVE_HW_TIME_STAMP - /** * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration -- cgit v1.2.3 From 8b305ee2a91c3c4c89cb82ea940265b247eb0a13 Mon Sep 17 00:00:00 2001 From: Tristram Ha Date: Tue, 25 Jul 2023 16:54:30 -0700 Subject: net: phy: smsc: add WoL support to LAN8740/LAN8742 PHYs Microchip LAN8740/LAN8742 PHYs support basic unicast, broadcast, and Magic Packet WoL. They have one pattern filter matching up to 128 bytes of frame data, which can be used to implement ARP or multicast WoL. ARP WoL matches any ARP frame with broadcast address. Multicast WoL matches any multicast frame. Signed-off-by: Tristram Ha Reviewed-by: Florian Fainelli Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/1690329270-2873-1-git-send-email-Tristram.Ha@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/Kconfig | 1 + drivers/net/phy/smsc.c | 252 +++++++++++++++++++++++++++++++++++++++++++++++- include/linux/smscphy.h | 34 +++++++ 3 files changed, 285 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 87b823858717..67aaeb75301f 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -350,6 +350,7 @@ config ROCKCHIP_PHY config SMSC_PHY tristate "SMSC PHYs" + select CRC16 help Currently supports the LAN83C185, LAN8187 and LAN8700 PHYs diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 692930750215..c88edb19d2e7 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include /* Vendor-specific PHY Definitions */ @@ -51,6 +53,7 @@ struct smsc_phy_priv { unsigned int edpd_enable:1; unsigned int edpd_mode_set_by_user:1; unsigned int edpd_max_wait_ms; + bool wol_arp; }; static int smsc_phy_ack_interrupt(struct phy_device *phydev) @@ -258,6 +261,243 @@ int lan87xx_read_status(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(lan87xx_read_status); +static int lan874x_phy_config_init(struct phy_device *phydev) +{ + u16 val; + int rc; + + /* Setup LED2/nINT/nPME pin to function as nPME. May need user option + * to use LED1/nINT/nPME. + */ + val = MII_LAN874X_PHY_PME2_SET; + + /* The bits MII_LAN874X_PHY_WOL_PFDA_FR, MII_LAN874X_PHY_WOL_WUFR, + * MII_LAN874X_PHY_WOL_MPR, and MII_LAN874X_PHY_WOL_BCAST_FR need to + * be cleared to de-assert PME signal after a WoL event happens, but + * using PME auto clear gets around that. + */ + val |= MII_LAN874X_PHY_PME_SELF_CLEAR; + rc = phy_write_mmd(phydev, MDIO_MMD_PCS, MII_LAN874X_PHY_MMD_WOL_WUCSR, + val); + if (rc < 0) + return rc; + + /* set nPME self clear delay time */ + rc = phy_write_mmd(phydev, MDIO_MMD_PCS, MII_LAN874X_PHY_MMD_MCFGR, + MII_LAN874X_PHY_PME_SELF_CLEAR_DELAY); + if (rc < 0) + return rc; + + return smsc_phy_config_init(phydev); +} + +static void lan874x_get_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + struct smsc_phy_priv *priv = phydev->priv; + int rc; + + wol->supported = (WAKE_UCAST | WAKE_BCAST | WAKE_MAGIC | + WAKE_ARP | WAKE_MCAST); + wol->wolopts = 0; + + rc = phy_read_mmd(phydev, MDIO_MMD_PCS, MII_LAN874X_PHY_MMD_WOL_WUCSR); + if (rc < 0) + return; + + if (rc & MII_LAN874X_PHY_WOL_PFDAEN) + wol->wolopts |= WAKE_UCAST; + + if (rc & MII_LAN874X_PHY_WOL_BCSTEN) + wol->wolopts |= WAKE_BCAST; + + if (rc & MII_LAN874X_PHY_WOL_MPEN) + wol->wolopts |= WAKE_MAGIC; + + if (rc & MII_LAN874X_PHY_WOL_WUEN) { + if (priv->wol_arp) + wol->wolopts |= WAKE_ARP; + else + wol->wolopts |= WAKE_MCAST; + } +} + +static u16 smsc_crc16(const u8 *buffer, size_t len) +{ + return bitrev16(crc16(0xFFFF, buffer, len)); +} + +static int lan874x_chk_wol_pattern(const u8 pattern[], const u16 *mask, + u8 len, u8 *data, u8 *datalen) +{ + size_t i, j, k; + int ret = 0; + u16 bits; + + /* Pattern filtering can match up to 128 bytes of frame data. There + * are 8 registers to program the 16-bit masks, where each bit means + * the byte will be compared. The frame data will then go through a + * CRC16 calculation for hardware comparison. This helper function + * makes sure only relevant frame data are included in this + * calculation. It provides a warning when the masks and expected + * data size do not match. + */ + i = 0; + k = 0; + while (len > 0) { + bits = *mask; + for (j = 0; j < 16; j++, i++, len--) { + /* No more pattern. */ + if (!len) { + /* The rest of bitmap is not empty. */ + if (bits) + ret = i + 1; + break; + } + if (bits & 1) + data[k++] = pattern[i]; + bits >>= 1; + } + mask++; + } + *datalen = k; + return ret; +} + +static int lan874x_set_wol_pattern(struct phy_device *phydev, u16 val, + const u8 data[], u8 datalen, + const u16 *mask, u8 masklen) +{ + u16 crc, reg; + int rc; + + /* Starting pattern offset is set before calling this function. */ + val |= MII_LAN874X_PHY_WOL_FILTER_EN; + rc = phy_write_mmd(phydev, MDIO_MMD_PCS, + MII_LAN874X_PHY_MMD_WOL_WUF_CFGA, val); + if (rc < 0) + return rc; + + crc = smsc_crc16(data, datalen); + rc = phy_write_mmd(phydev, MDIO_MMD_PCS, + MII_LAN874X_PHY_MMD_WOL_WUF_CFGB, crc); + if (rc < 0) + return rc; + + masklen = (masklen + 15) & ~0xf; + reg = MII_LAN874X_PHY_MMD_WOL_WUF_MASK7; + while (masklen >= 16) { + rc = phy_write_mmd(phydev, MDIO_MMD_PCS, reg, *mask); + if (rc < 0) + return rc; + reg--; + mask++; + masklen -= 16; + } + + /* Clear out the rest of mask registers. */ + while (reg != MII_LAN874X_PHY_MMD_WOL_WUF_MASK0) { + phy_write_mmd(phydev, MDIO_MMD_PCS, reg, 0); + reg--; + } + return rc; +} + +static int lan874x_set_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + struct net_device *ndev = phydev->attached_dev; + struct smsc_phy_priv *priv = phydev->priv; + u16 val, val_wucsr; + u8 data[128]; + u8 datalen; + int rc; + + /* lan874x has only one WoL filter pattern */ + if ((wol->wolopts & (WAKE_ARP | WAKE_MCAST)) == + (WAKE_ARP | WAKE_MCAST)) { + phydev_info(phydev, + "lan874x WoL supports one of ARP|MCAST at a time\n"); + return -EOPNOTSUPP; + } + + rc = phy_read_mmd(phydev, MDIO_MMD_PCS, MII_LAN874X_PHY_MMD_WOL_WUCSR); + if (rc < 0) + return rc; + + val_wucsr = rc; + + if (wol->wolopts & WAKE_UCAST) + val_wucsr |= MII_LAN874X_PHY_WOL_PFDAEN; + else + val_wucsr &= ~MII_LAN874X_PHY_WOL_PFDAEN; + + if (wol->wolopts & WAKE_BCAST) + val_wucsr |= MII_LAN874X_PHY_WOL_BCSTEN; + else + val_wucsr &= ~MII_LAN874X_PHY_WOL_BCSTEN; + + if (wol->wolopts & WAKE_MAGIC) + val_wucsr |= MII_LAN874X_PHY_WOL_MPEN; + else + val_wucsr &= ~MII_LAN874X_PHY_WOL_MPEN; + + /* Need to use pattern matching */ + if (wol->wolopts & (WAKE_ARP | WAKE_MCAST)) + val_wucsr |= MII_LAN874X_PHY_WOL_WUEN; + else + val_wucsr &= ~MII_LAN874X_PHY_WOL_WUEN; + + if (wol->wolopts & WAKE_ARP) { + const u8 pattern[2] = { 0x08, 0x06 }; + const u16 mask[1] = { 0x0003 }; + + rc = lan874x_chk_wol_pattern(pattern, mask, 2, data, + &datalen); + if (rc) + phydev_dbg(phydev, "pattern not valid at %d\n", rc); + + /* Need to match broadcast destination address and provided + * data pattern at offset 12. + */ + val = 12 | MII_LAN874X_PHY_WOL_FILTER_BCSTEN; + rc = lan874x_set_wol_pattern(phydev, val, data, datalen, mask, + 2); + if (rc < 0) + return rc; + priv->wol_arp = true; + } + + if (wol->wolopts & WAKE_MCAST) { + /* Need to match multicast destination address. */ + val = MII_LAN874X_PHY_WOL_FILTER_MCASTTEN; + rc = lan874x_set_wol_pattern(phydev, val, data, 0, NULL, 0); + if (rc < 0) + return rc; + priv->wol_arp = false; + } + + if (wol->wolopts & (WAKE_MAGIC | WAKE_UCAST)) { + const u8 *mac = (const u8 *)ndev->dev_addr; + int i, reg; + + reg = MII_LAN874X_PHY_MMD_WOL_RX_ADDRC; + for (i = 0; i < 6; i += 2, reg--) { + rc = phy_write_mmd(phydev, MDIO_MMD_PCS, reg, + ((mac[i + 1] << 8) | mac[i])); + if (rc < 0) + return rc; + } + } + + rc = phy_write_mmd(phydev, MDIO_MMD_PCS, MII_LAN874X_PHY_MMD_WOL_WUCSR, + val_wucsr); + if (rc < 0) + return rc; + + return 0; +} + static int smsc_get_sset_count(struct phy_device *phydev) { return ARRAY_SIZE(smsc_hw_stats); @@ -533,7 +773,7 @@ static struct phy_driver smsc_phy_driver[] = { /* basic functions */ .read_status = lan87xx_read_status, - .config_init = smsc_phy_config_init, + .config_init = lan874x_phy_config_init, .soft_reset = smsc_phy_reset, /* IRQ related */ @@ -548,6 +788,10 @@ static struct phy_driver smsc_phy_driver[] = { .get_tunable = smsc_phy_get_tunable, .set_tunable = smsc_phy_set_tunable, + /* WoL */ + .set_wol = lan874x_set_wol, + .get_wol = lan874x_get_wol, + .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -566,7 +810,7 @@ static struct phy_driver smsc_phy_driver[] = { /* basic functions */ .read_status = lan87xx_read_status, - .config_init = smsc_phy_config_init, + .config_init = lan874x_phy_config_init, .soft_reset = smsc_phy_reset, /* IRQ related */ @@ -581,6 +825,10 @@ static struct phy_driver smsc_phy_driver[] = { .get_tunable = smsc_phy_get_tunable, .set_tunable = smsc_phy_set_tunable, + /* WoL */ + .set_wol = lan874x_set_wol, + .get_wol = lan874x_get_wol, + .suspend = genphy_suspend, .resume = genphy_resume, } }; diff --git a/include/linux/smscphy.h b/include/linux/smscphy.h index e1c88627755a..1a6a851d2cf8 100644 --- a/include/linux/smscphy.h +++ b/include/linux/smscphy.h @@ -38,4 +38,38 @@ int smsc_phy_set_tunable(struct phy_device *phydev, struct ethtool_tunable *tuna, const void *data); int smsc_phy_probe(struct phy_device *phydev); +#define MII_LAN874X_PHY_MMD_WOL_WUCSR 0x8010 +#define MII_LAN874X_PHY_MMD_WOL_WUF_CFGA 0x8011 +#define MII_LAN874X_PHY_MMD_WOL_WUF_CFGB 0x8012 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK0 0x8021 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK1 0x8022 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK2 0x8023 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK3 0x8024 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK4 0x8025 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK5 0x8026 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK6 0x8027 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK7 0x8028 +#define MII_LAN874X_PHY_MMD_WOL_RX_ADDRA 0x8061 +#define MII_LAN874X_PHY_MMD_WOL_RX_ADDRB 0x8062 +#define MII_LAN874X_PHY_MMD_WOL_RX_ADDRC 0x8063 +#define MII_LAN874X_PHY_MMD_MCFGR 0x8064 + +#define MII_LAN874X_PHY_PME1_SET (2 << 13) +#define MII_LAN874X_PHY_PME2_SET (2 << 11) +#define MII_LAN874X_PHY_PME_SELF_CLEAR BIT(9) +#define MII_LAN874X_PHY_WOL_PFDA_FR BIT(7) +#define MII_LAN874X_PHY_WOL_WUFR BIT(6) +#define MII_LAN874X_PHY_WOL_MPR BIT(5) +#define MII_LAN874X_PHY_WOL_BCAST_FR BIT(4) +#define MII_LAN874X_PHY_WOL_PFDAEN BIT(3) +#define MII_LAN874X_PHY_WOL_WUEN BIT(2) +#define MII_LAN874X_PHY_WOL_MPEN BIT(1) +#define MII_LAN874X_PHY_WOL_BCSTEN BIT(0) + +#define MII_LAN874X_PHY_WOL_FILTER_EN BIT(15) +#define MII_LAN874X_PHY_WOL_FILTER_MCASTTEN BIT(9) +#define MII_LAN874X_PHY_WOL_FILTER_BCSTEN BIT(8) + +#define MII_LAN874X_PHY_PME_SELF_CLEAR_DELAY 0x1000 /* 81 milliseconds */ + #endif /* __LINUX_SMSCPHY_H__ */ -- cgit v1.2.3 From 5fac9b7c16c50c6c7699517f582b56e3743f453a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 18 Jul 2023 09:52:29 +0200 Subject: netlink: allow be16 and be32 types in all uint policy checks __NLA_IS_BEINT_TYPE(tp) isn't useful. NLA_BE16/32 are identical to NLA_U16/32, the only difference is that it tells the netlink validation functions that byteorder conversion might be needed before comparing the value to the policy min/max ones. After this change all policy macros that can be used with UINT types, such as NLA_POLICY_MASK() can also be used with NLA_BE16/32. This will be used to validate nf_tables flag attributes which are in bigendian byte order. Signed-off-by: Florian Westphal --- include/net/netlink.h | 10 +++------- lib/nlattr.c | 6 ++++++ 2 files changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index b12cd957abb4..8a7cd1170e1f 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -375,12 +375,11 @@ struct nla_policy { #define NLA_POLICY_BITFIELD32(valid) \ { .type = NLA_BITFIELD32, .bitfield32_valid = valid } -#define __NLA_IS_UINT_TYPE(tp) \ - (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || tp == NLA_U64) +#define __NLA_IS_UINT_TYPE(tp) \ + (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || \ + tp == NLA_U64 || tp == NLA_BE16 || tp == NLA_BE32) #define __NLA_IS_SINT_TYPE(tp) \ (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64) -#define __NLA_IS_BEINT_TYPE(tp) \ - (tp == NLA_BE16 || tp == NLA_BE32) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_UINT_TYPE(tp) \ @@ -394,7 +393,6 @@ struct nla_policy { #define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ __NLA_IS_SINT_TYPE(tp) || \ - __NLA_IS_BEINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ @@ -402,8 +400,6 @@ struct nla_policy { tp != NLA_REJECT && \ tp != NLA_NESTED && \ tp != NLA_NESTED_ARRAY) + tp) -#define NLA_ENSURE_BEINT_TYPE(tp) \ - (__NLA_ENSURE(__NLA_IS_BEINT_TYPE(tp)) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ diff --git a/lib/nlattr.c b/lib/nlattr.c index 489e15bde5c1..7a2b6c38fd59 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -355,6 +355,12 @@ static int nla_validate_mask(const struct nla_policy *pt, case NLA_U64: value = nla_get_u64(nla); break; + case NLA_BE16: + value = ntohs(nla_get_be16(nla)); + break; + case NLA_BE32: + value = ntohl(nla_get_be32(nla)); + break; default: return -EINVAL; } -- cgit v1.2.3 From 88d162b479815f5d6b6a4ff5fdb07aec9dc6280c Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Thu, 4 May 2023 12:14:00 +0300 Subject: net/mlx5: Devcom, Infrastructure changes Update devcom infrastructure to be more generic, without depending on max supported ports definition or a device guid, and also more encapsulated so callers don't need to pass the register devcom component id per event call. Signed-off-by: Eli Cohen Signed-off-by: Roi Dayan Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 21 +- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 36 +- .../net/ethernet/mellanox/mlx5/core/esw/bridge.c | 22 +- .../ethernet/mellanox/mlx5/core/esw/bridge_mcast.c | 17 +- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 3 + .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 47 ++- drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 2 +- .../net/ethernet/mellanox/mlx5/core/lib/devcom.c | 448 +++++++++++---------- .../net/ethernet/mellanox/mlx5/core/lib/devcom.h | 74 ++-- drivers/net/ethernet/mellanox/mlx5/core/main.c | 12 +- include/linux/mlx5/driver.h | 4 +- 11 files changed, 359 insertions(+), 327 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 152b62138450..ca4f57f5064f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -399,15 +399,13 @@ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw, } static int mlx5e_sqs2vport_add_peers_rules(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, - struct mlx5_devcom *devcom, struct mlx5e_rep_sq *rep_sq, int i) { - struct mlx5_eswitch *peer_esw = NULL; struct mlx5_flow_handle *flow_rule; - int tmp; + struct mlx5_devcom_comp_dev *tmp; + struct mlx5_eswitch *peer_esw; - mlx5_devcom_for_each_peer_entry(devcom, MLX5_DEVCOM_ESW_OFFLOADS, - peer_esw, tmp) { + mlx5_devcom_for_each_peer_entry(esw->devcom, peer_esw, tmp) { u16 peer_rule_idx = MLX5_CAP_GEN(peer_esw->dev, vhca_id); struct mlx5e_rep_sq_peer *sq_peer; int err; @@ -443,7 +441,6 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, struct mlx5_flow_handle *flow_rule; struct mlx5e_rep_priv *rpriv; struct mlx5e_rep_sq *rep_sq; - struct mlx5_devcom *devcom; bool devcom_locked = false; int err; int i; @@ -451,10 +448,10 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, if (esw->mode != MLX5_ESWITCH_OFFLOADS) return 0; - devcom = esw->dev->priv.devcom; rpriv = mlx5e_rep_to_rep_priv(rep); - if (mlx5_devcom_comp_is_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS) && - mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) + + if (mlx5_devcom_comp_is_ready(esw->devcom) && + mlx5_devcom_for_each_peer_begin(esw->devcom)) devcom_locked = true; for (i = 0; i < sqns_num; i++) { @@ -477,7 +474,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, xa_init(&rep_sq->sq_peer); if (devcom_locked) { - err = mlx5e_sqs2vport_add_peers_rules(esw, rep, devcom, rep_sq, i); + err = mlx5e_sqs2vport_add_peers_rules(esw, rep, rep_sq, i); if (err) { mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule); xa_destroy(&rep_sq->sq_peer); @@ -490,7 +487,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, } if (devcom_locked) - mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(esw->devcom); return 0; @@ -498,7 +495,7 @@ out_err: mlx5e_sqs2vport_stop(esw, rep); if (devcom_locked) - mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(esw->devcom); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 8d0a3f69693e..22bc88620653 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1668,11 +1668,10 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro { struct mlx5e_priv *out_priv, *route_priv; struct mlx5_core_dev *route_mdev; - struct mlx5_devcom *devcom; + struct mlx5_devcom_comp_dev *pos; struct mlx5_eswitch *esw; u16 vhca_id; int err; - int i; out_priv = netdev_priv(out_dev); esw = out_priv->mdev->priv.eswitch; @@ -1688,10 +1687,8 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro return err; rcu_read_lock(); - devcom = out_priv->mdev->priv.devcom; err = -ENODEV; - mlx5_devcom_for_each_peer_entry_rcu(devcom, MLX5_DEVCOM_ESW_OFFLOADS, - esw, i) { + mlx5_devcom_for_each_peer_entry_rcu(esw->devcom, esw, pos) { err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); if (!err) break; @@ -2031,15 +2028,15 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { if (mlx5e_is_eswitch_flow(flow)) { - struct mlx5_devcom *devcom = flow->priv->mdev->priv.devcom; + struct mlx5_devcom_comp_dev *devcom = flow->priv->mdev->priv.eswitch->devcom; - if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) { + if (!mlx5_devcom_for_each_peer_begin(devcom)) { mlx5e_tc_del_fdb_flow(priv, flow); return; } mlx5e_tc_del_fdb_peers_flow(flow); - mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(devcom); mlx5e_tc_del_fdb_flow(priv, flow); } else { mlx5e_tc_del_nic_flow(priv, flow); @@ -4216,8 +4213,7 @@ static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow) flow_flag_test(flow, INGRESS); bool act_is_encap = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT); - bool esw_paired = mlx5_devcom_comp_is_ready(esw_attr->in_mdev->priv.devcom, - MLX5_DEVCOM_ESW_OFFLOADS); + bool esw_paired = mlx5_devcom_comp_is_ready(esw_attr->in_mdev->priv.eswitch->devcom); if (!esw_paired) return false; @@ -4471,14 +4467,13 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct net_device *filter_dev, struct mlx5e_tc_flow **__flow) { - struct mlx5_devcom *devcom = priv->mdev->priv.devcom; + struct mlx5_devcom_comp_dev *devcom = priv->mdev->priv.eswitch->devcom, *pos; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *in_rep = rpriv->rep; struct mlx5_core_dev *in_mdev = priv->mdev; struct mlx5_eswitch *peer_esw; struct mlx5e_tc_flow *flow; int err; - int i; flow = __mlx5e_add_fdb_flow(priv, f, flow_flags, filter_dev, in_rep, in_mdev); @@ -4490,27 +4485,25 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv, return 0; } - if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) { + if (!mlx5_devcom_for_each_peer_begin(devcom)) { err = -ENODEV; goto clean_flow; } - mlx5_devcom_for_each_peer_entry(devcom, - MLX5_DEVCOM_ESW_OFFLOADS, - peer_esw, i) { + mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) { err = mlx5e_tc_add_fdb_peer_flow(f, flow, flow_flags, peer_esw); if (err) goto peer_clean; } - mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(devcom); *__flow = flow; return 0; peer_clean: mlx5e_tc_del_fdb_peers_flow(flow); - mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(devcom); clean_flow: mlx5e_tc_del_fdb_flow(priv, flow); return err; @@ -4728,7 +4721,7 @@ int mlx5e_tc_fill_action_stats(struct mlx5e_priv *priv, int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, struct flow_cls_offload *f, unsigned long flags) { - struct mlx5_devcom *devcom = priv->mdev->priv.devcom; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct rhashtable *tc_ht = get_tc_ht(priv, flags); struct mlx5e_tc_flow *flow; struct mlx5_fc *counter; @@ -4764,7 +4757,7 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, /* Under multipath it's possible for one rule to be currently * un-offloaded while the other rule is offloaded. */ - if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) + if (esw && !mlx5_devcom_for_each_peer_begin(esw->devcom)) goto out; if (flow_flag_test(flow, DUP)) { @@ -4795,7 +4788,8 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, } no_peer_counter: - mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + if (esw) + mlx5_devcom_for_each_peer_end(esw->devcom); out: flow_stats_update(&f->stats, bytes, packets, 0, lastuse, FLOW_ACTION_HW_STATS_DELAYED); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index f4fe1daa4afd..e36294b7ade2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -652,30 +652,30 @@ mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, u16 esw_owner_vhca_id, struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, struct mlx5_esw_bridge *bridge) { - struct mlx5_devcom *devcom = bridge->br_offloads->esw->dev->priv.devcom; + struct mlx5_devcom_comp_dev *devcom = bridge->br_offloads->esw->devcom, *pos; struct mlx5_eswitch *tmp, *peer_esw = NULL; static struct mlx5_flow_handle *handle; - int i; - if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) + if (!mlx5_devcom_for_each_peer_begin(devcom)) return ERR_PTR(-ENODEV); - mlx5_devcom_for_each_peer_entry(devcom, - MLX5_DEVCOM_ESW_OFFLOADS, - tmp, i) { + mlx5_devcom_for_each_peer_entry(devcom, tmp, pos) { if (mlx5_esw_is_owner(tmp, vport_num, esw_owner_vhca_id)) { peer_esw = tmp; break; } } + if (!peer_esw) { - mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - return ERR_PTR(-ENODEV); + handle = ERR_PTR(-ENODEV); + goto out; } handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id, bridge, peer_esw); - mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + +out: + mlx5_devcom_for_each_peer_end(devcom); return handle; } @@ -1391,8 +1391,8 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_ow mlx5_fc_id(counter), bridge); if (IS_ERR(handle)) { err = PTR_ERR(handle); - esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d)\n", - vport_num, err); + esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d,peer=%d)\n", + vport_num, err, peer); goto err_ingress_flow_create; } entry->ingress_handle = handle; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c index 2455f8b93c1e..7a01714b3780 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c @@ -539,30 +539,29 @@ mlx5_esw_bridge_mcast_filter_flow_create(struct mlx5_esw_bridge_port *port) static struct mlx5_flow_handle * mlx5_esw_bridge_mcast_filter_flow_peer_create(struct mlx5_esw_bridge_port *port) { - struct mlx5_devcom *devcom = port->bridge->br_offloads->esw->dev->priv.devcom; + struct mlx5_devcom_comp_dev *devcom = port->bridge->br_offloads->esw->devcom, *pos; struct mlx5_eswitch *tmp, *peer_esw = NULL; static struct mlx5_flow_handle *handle; - int i; - if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) + if (!mlx5_devcom_for_each_peer_begin(devcom)) return ERR_PTR(-ENODEV); - mlx5_devcom_for_each_peer_entry(devcom, - MLX5_DEVCOM_ESW_OFFLOADS, - tmp, i) { + mlx5_devcom_for_each_peer_entry(devcom, tmp, pos) { if (mlx5_esw_is_owner(tmp, port->vport_num, port->esw_owner_vhca_id)) { peer_esw = tmp; break; } } + if (!peer_esw) { - mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - return ERR_PTR(-ENODEV); + handle = ERR_PTR(-ENODEV); + goto out; } handle = mlx5_esw_bridge_mcast_flow_with_esw_create(port, peer_esw); - mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); +out: + mlx5_devcom_for_each_peer_end(devcom); return handle; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index ae0dc8a3060d..6d9378b0bce5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -354,6 +354,7 @@ struct mlx5_eswitch { } params; struct blocking_notifier_head n_head; struct xarray paired; + struct mlx5_devcom_comp_dev *devcom; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -383,6 +384,7 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw); void mlx5_eswitch_disable(struct mlx5_eswitch *esw); void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw); void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw); +bool mlx5_esw_offloads_devcom_is_ready(struct mlx5_eswitch *esw); int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, u16 vport, const u8 *mac); int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, @@ -818,6 +820,7 @@ static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool cle static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw) {} static inline void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw) {} static inline void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) {} +static inline bool mlx5_esw_offloads_devcom_is_ready(struct mlx5_eswitch *esw) { return false; } static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; } static inline int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index bdfe609cc9ec..11cce630c1b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2811,7 +2811,6 @@ static int mlx5_esw_offloads_devcom_event(int event, void *event_data) { struct mlx5_eswitch *esw = my_data; - struct mlx5_devcom *devcom = esw->dev->priv.devcom; struct mlx5_eswitch *peer_esw = event_data; u16 esw_i, peer_esw_i; bool esw_paired; @@ -2833,6 +2832,7 @@ static int mlx5_esw_offloads_devcom_event(int event, err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true); if (err) goto err_out; + err = mlx5_esw_offloads_pair(esw, peer_esw); if (err) goto err_peer; @@ -2851,7 +2851,7 @@ static int mlx5_esw_offloads_devcom_event(int event, esw->num_peers++; peer_esw->num_peers++; - mlx5_devcom_comp_set_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true); + mlx5_devcom_comp_set_ready(esw->devcom, true); break; case ESW_OFFLOADS_DEVCOM_UNPAIR: @@ -2861,7 +2861,7 @@ static int mlx5_esw_offloads_devcom_event(int event, peer_esw->num_peers--; esw->num_peers--; if (!esw->num_peers && !peer_esw->num_peers) - mlx5_devcom_comp_set_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false); + mlx5_devcom_comp_set_ready(esw->devcom, false); xa_erase(&peer_esw->paired, esw_i); xa_erase(&esw->paired, peer_esw_i); mlx5_esw_offloads_unpair(peer_esw, esw); @@ -2888,7 +2888,7 @@ err_out: void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw) { - struct mlx5_devcom *devcom = esw->dev->priv.devcom; + u64 guid; int i; for (i = 0; i < MLX5_MAX_PORTS; i++) @@ -2902,34 +2902,41 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw) return; xa_init(&esw->paired); - mlx5_devcom_register_component(devcom, - MLX5_DEVCOM_ESW_OFFLOADS, - mlx5_esw_offloads_devcom_event, - esw); + guid = mlx5_query_nic_system_image_guid(esw->dev); esw->num_peers = 0; - mlx5_devcom_send_event(devcom, - MLX5_DEVCOM_ESW_OFFLOADS, + esw->devcom = mlx5_devcom_register_component(esw->dev->priv.devc, + MLX5_DEVCOM_ESW_OFFLOADS, + guid, + mlx5_esw_offloads_devcom_event, + esw); + if (IS_ERR_OR_NULL(esw->devcom)) + return; + + mlx5_devcom_send_event(esw->devcom, ESW_OFFLOADS_DEVCOM_PAIR, - ESW_OFFLOADS_DEVCOM_UNPAIR, esw); + ESW_OFFLOADS_DEVCOM_UNPAIR, + esw); } void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) { - struct mlx5_devcom *devcom = esw->dev->priv.devcom; - - if (!MLX5_CAP_ESW(esw->dev, merged_eswitch)) + if (IS_ERR_OR_NULL(esw->devcom)) return; - if (!mlx5_lag_is_supported(esw->dev)) - return; - - mlx5_devcom_send_event(devcom, MLX5_DEVCOM_ESW_OFFLOADS, + mlx5_devcom_send_event(esw->devcom, + ESW_OFFLOADS_DEVCOM_UNPAIR, ESW_OFFLOADS_DEVCOM_UNPAIR, - ESW_OFFLOADS_DEVCOM_UNPAIR, esw); + esw); - mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_unregister_component(esw->devcom); xa_destroy(&esw->paired); + esw->devcom = NULL; +} + +bool mlx5_esw_offloads_devcom_is_ready(struct mlx5_eswitch *esw) +{ + return mlx5_devcom_comp_is_ready(esw->devcom); } bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 900a18883f28..af3fac090b82 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -835,7 +835,7 @@ static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) dev = ldev->pf[MLX5_LAG_P1].dev; if (is_mdev_switchdev_mode(dev) && mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) && - mlx5_devcom_comp_is_ready(dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS) && + mlx5_esw_offloads_devcom_is_ready(dev->priv.eswitch) && MLX5_CAP_ESW(dev, esw_shared_ingress_acl) && mlx5_eswitch_get_npeers(dev->priv.eswitch) == MLX5_CAP_GEN(dev, num_lag_ports) - 1) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index 78c94b22bdc0..feb62d952643 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -2,214 +2,273 @@ /* Copyright (c) 2018 Mellanox Technologies */ #include +#include #include "lib/devcom.h" #include "mlx5_core.h" -static LIST_HEAD(devcom_list); +static LIST_HEAD(devcom_dev_list); +static LIST_HEAD(devcom_comp_list); +/* protect device list */ +static DEFINE_MUTEX(dev_list_lock); +/* protect component list */ +static DEFINE_MUTEX(comp_list_lock); -#define devcom_for_each_component(priv, comp, iter) \ - for (iter = 0; \ - comp = &(priv)->components[iter], iter < MLX5_DEVCOM_NUM_COMPONENTS; \ - iter++) +#define devcom_for_each_component(iter) \ + list_for_each_entry(iter, &devcom_comp_list, comp_list) -struct mlx5_devcom_component { - struct { - void __rcu *data; - } device[MLX5_DEVCOM_PORTS_SUPPORTED]; +struct mlx5_devcom_dev { + struct list_head list; + struct mlx5_core_dev *dev; + struct kref ref; +}; +struct mlx5_devcom_comp { + struct list_head comp_list; + enum mlx5_devcom_component id; + u64 key; + struct list_head comp_dev_list_head; mlx5_devcom_event_handler_t handler; - struct rw_semaphore sem; + struct kref ref; bool ready; + struct rw_semaphore sem; }; -struct mlx5_devcom_list { +struct mlx5_devcom_comp_dev { struct list_head list; - - struct mlx5_devcom_component components[MLX5_DEVCOM_NUM_COMPONENTS]; - struct mlx5_core_dev *devs[MLX5_DEVCOM_PORTS_SUPPORTED]; + struct mlx5_devcom_comp *comp; + struct mlx5_devcom_dev *devc; + void __rcu *data; }; -struct mlx5_devcom { - struct mlx5_devcom_list *priv; - int idx; -}; - -static struct mlx5_devcom_list *mlx5_devcom_list_alloc(void) +static bool devcom_dev_exists(struct mlx5_core_dev *dev) { - struct mlx5_devcom_component *comp; - struct mlx5_devcom_list *priv; - int i; - - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - return NULL; + struct mlx5_devcom_dev *iter; - devcom_for_each_component(priv, comp, i) - init_rwsem(&comp->sem); + list_for_each_entry(iter, &devcom_dev_list, list) + if (iter->dev == dev) + return true; - return priv; + return false; } -static struct mlx5_devcom *mlx5_devcom_alloc(struct mlx5_devcom_list *priv, - u8 idx) +static struct mlx5_devcom_dev * +mlx5_devcom_dev_alloc(struct mlx5_core_dev *dev) { - struct mlx5_devcom *devcom; + struct mlx5_devcom_dev *devc; - devcom = kzalloc(sizeof(*devcom), GFP_KERNEL); - if (!devcom) + devc = kzalloc(sizeof(*devc), GFP_KERNEL); + if (!devc) return NULL; - devcom->priv = priv; - devcom->idx = idx; - return devcom; + devc->dev = dev; + kref_init(&devc->ref); + return devc; } -/* Must be called with intf_mutex held */ -struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) +struct mlx5_devcom_dev * +mlx5_devcom_register_device(struct mlx5_core_dev *dev) { - struct mlx5_devcom_list *priv = NULL, *iter; - struct mlx5_devcom *devcom = NULL; - bool new_priv = false; - u64 sguid0, sguid1; - int idx, i; - - if (!mlx5_core_is_pf(dev)) - return NULL; - if (MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_DEVCOM_PORTS_SUPPORTED) - return NULL; - - mlx5_dev_list_lock(); - sguid0 = mlx5_query_nic_system_image_guid(dev); - list_for_each_entry(iter, &devcom_list, list) { - /* There is at least one device in iter */ - struct mlx5_core_dev *tmp_dev; - - idx = -1; - for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) { - if (iter->devs[i]) - tmp_dev = iter->devs[i]; - else - idx = i; - } - - if (idx == -1) - continue; - - sguid1 = mlx5_query_nic_system_image_guid(tmp_dev); - if (sguid0 != sguid1) - continue; - - priv = iter; - break; - } + struct mlx5_devcom_dev *devc; - if (!priv) { - priv = mlx5_devcom_list_alloc(); - if (!priv) { - devcom = ERR_PTR(-ENOMEM); - goto out; - } + mutex_lock(&dev_list_lock); - idx = 0; - new_priv = true; + if (devcom_dev_exists(dev)) { + devc = ERR_PTR(-EEXIST); + goto out; } - priv->devs[idx] = dev; - devcom = mlx5_devcom_alloc(priv, idx); - if (!devcom) { - if (new_priv) - kfree(priv); - devcom = ERR_PTR(-ENOMEM); + devc = mlx5_devcom_dev_alloc(dev); + if (!devc) { + devc = ERR_PTR(-ENOMEM); goto out; } - if (new_priv) - list_add(&priv->list, &devcom_list); + list_add_tail(&devc->list, &devcom_dev_list); out: - mlx5_dev_list_unlock(); - return devcom; + mutex_unlock(&dev_list_lock); + return devc; } -/* Must be called with intf_mutex held */ -void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom) +static void +mlx5_devcom_dev_release(struct kref *ref) { - struct mlx5_devcom_list *priv; - int i; + struct mlx5_devcom_dev *devc = container_of(ref, struct mlx5_devcom_dev, ref); - if (IS_ERR_OR_NULL(devcom)) - return; + mutex_lock(&dev_list_lock); + list_del(&devc->list); + mutex_unlock(&dev_list_lock); + kfree(devc); +} - mlx5_dev_list_lock(); - priv = devcom->priv; - priv->devs[devcom->idx] = NULL; +void mlx5_devcom_unregister_device(struct mlx5_devcom_dev *devc) +{ + if (!IS_ERR_OR_NULL(devc)) + kref_put(&devc->ref, mlx5_devcom_dev_release); +} - kfree(devcom); +static struct mlx5_devcom_comp * +mlx5_devcom_comp_alloc(u64 id, u64 key, mlx5_devcom_event_handler_t handler) +{ + struct mlx5_devcom_comp *comp; - for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) - if (priv->devs[i]) - break; + comp = kzalloc(sizeof(*comp), GFP_KERNEL); + if (!comp) + return ERR_PTR(-ENOMEM); - if (i != MLX5_DEVCOM_PORTS_SUPPORTED) - goto out; + comp->id = id; + comp->key = key; + comp->handler = handler; + init_rwsem(&comp->sem); + kref_init(&comp->ref); + INIT_LIST_HEAD(&comp->comp_dev_list_head); - list_del(&priv->list); - kfree(priv); -out: - mlx5_dev_list_unlock(); + return comp; } -void mlx5_devcom_register_component(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, - mlx5_devcom_event_handler_t handler, - void *data) +static void +mlx5_devcom_comp_release(struct kref *ref) { - struct mlx5_devcom_component *comp; + struct mlx5_devcom_comp *comp = container_of(ref, struct mlx5_devcom_comp, ref); - if (IS_ERR_OR_NULL(devcom)) - return; + mutex_lock(&comp_list_lock); + list_del(&comp->comp_list); + mutex_unlock(&comp_list_lock); + kfree(comp); +} + +static struct mlx5_devcom_comp_dev * +devcom_alloc_comp_dev(struct mlx5_devcom_dev *devc, + struct mlx5_devcom_comp *comp, + void *data) +{ + struct mlx5_devcom_comp_dev *devcom; - WARN_ON(!data); + devcom = kzalloc(sizeof(*devcom), GFP_KERNEL); + if (!devcom) + return ERR_PTR(-ENOMEM); + + kref_get(&devc->ref); + devcom->devc = devc; + devcom->comp = comp; + rcu_assign_pointer(devcom->data, data); - comp = &devcom->priv->components[id]; down_write(&comp->sem); - comp->handler = handler; - rcu_assign_pointer(comp->device[devcom->idx].data, data); + list_add_tail(&devcom->list, &comp->comp_dev_list_head); up_write(&comp->sem); + + return devcom; } -void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id) +static void +devcom_free_comp_dev(struct mlx5_devcom_comp_dev *devcom) { - struct mlx5_devcom_component *comp; - - if (IS_ERR_OR_NULL(devcom)) - return; + struct mlx5_devcom_comp *comp = devcom->comp; - comp = &devcom->priv->components[id]; down_write(&comp->sem); - RCU_INIT_POINTER(comp->device[devcom->idx].data, NULL); + list_del(&devcom->list); up_write(&comp->sem); - synchronize_rcu(); + + kref_put(&devcom->devc->ref, mlx5_devcom_dev_release); + kfree(devcom); + kref_put(&comp->ref, mlx5_devcom_comp_release); } -int mlx5_devcom_send_event(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, +static bool +devcom_component_equal(struct mlx5_devcom_comp *devcom, + enum mlx5_devcom_component id, + u64 key) +{ + return devcom->id == id && devcom->key == key; +} + +static struct mlx5_devcom_comp * +devcom_component_get(struct mlx5_devcom_dev *devc, + enum mlx5_devcom_component id, + u64 key, + mlx5_devcom_event_handler_t handler) +{ + struct mlx5_devcom_comp *comp; + + devcom_for_each_component(comp) { + if (devcom_component_equal(comp, id, key)) { + if (handler == comp->handler) { + kref_get(&comp->ref); + return comp; + } + + mlx5_core_err(devc->dev, + "Cannot register existing devcom component with different handler\n"); + return ERR_PTR(-EINVAL); + } + } + + return NULL; +} + +struct mlx5_devcom_comp_dev * +mlx5_devcom_register_component(struct mlx5_devcom_dev *devc, + enum mlx5_devcom_component id, + u64 key, + mlx5_devcom_event_handler_t handler, + void *data) +{ + struct mlx5_devcom_comp_dev *devcom; + struct mlx5_devcom_comp *comp; + + if (IS_ERR_OR_NULL(devc)) + return NULL; + + mutex_lock(&comp_list_lock); + comp = devcom_component_get(devc, id, key, handler); + if (IS_ERR(comp)) { + devcom = ERR_PTR(-EINVAL); + goto out_unlock; + } + + if (!comp) { + comp = mlx5_devcom_comp_alloc(id, key, handler); + if (IS_ERR(comp)) { + devcom = ERR_CAST(comp); + goto out_unlock; + } + list_add_tail(&comp->comp_list, &devcom_comp_list); + } + mutex_unlock(&comp_list_lock); + + devcom = devcom_alloc_comp_dev(devc, comp, data); + if (IS_ERR(devcom)) + kref_put(&comp->ref, mlx5_devcom_comp_release); + + return devcom; + +out_unlock: + mutex_unlock(&comp_list_lock); + return devcom; +} + +void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom) +{ + if (!IS_ERR_OR_NULL(devcom)) + devcom_free_comp_dev(devcom); +} + +int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom, int event, int rollback_event, void *event_data) { - struct mlx5_devcom_component *comp; - int err = -ENODEV, i; + struct mlx5_devcom_comp *comp = devcom->comp; + struct mlx5_devcom_comp_dev *pos; + int err = 0; + void *data; if (IS_ERR_OR_NULL(devcom)) - return err; + return -ENODEV; - comp = &devcom->priv->components[id]; down_write(&comp->sem); - for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) { - void *data = rcu_dereference_protected(comp->device[i].data, - lockdep_is_held(&comp->sem)); + list_for_each_entry(pos, &comp->comp_dev_list_head, list) { + data = rcu_dereference_protected(pos->data, lockdep_is_held(&comp->sem)); - if (i != devcom->idx && data) { + if (pos != devcom && data) { err = comp->handler(event, data, event_data); if (err) goto rollback; @@ -220,48 +279,43 @@ int mlx5_devcom_send_event(struct mlx5_devcom *devcom, return 0; rollback: - while (i--) { - void *data = rcu_dereference_protected(comp->device[i].data, - lockdep_is_held(&comp->sem)); + if (list_entry_is_head(pos, &comp->comp_dev_list_head, list)) + goto out; + pos = list_prev_entry(pos, list); + list_for_each_entry_from_reverse(pos, &comp->comp_dev_list_head, list) { + data = rcu_dereference_protected(pos->data, lockdep_is_held(&comp->sem)); - if (i != devcom->idx && data) + if (pos != devcom && data) comp->handler(rollback_event, data, event_data); } - +out: up_write(&comp->sem); return err; } -void mlx5_devcom_comp_set_ready(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, - bool ready) +void mlx5_devcom_comp_set_ready(struct mlx5_devcom_comp_dev *devcom, bool ready) { - struct mlx5_devcom_component *comp; - - comp = &devcom->priv->components[id]; - WARN_ON(!rwsem_is_locked(&comp->sem)); + WARN_ON(!rwsem_is_locked(&devcom->comp->sem)); - WRITE_ONCE(comp->ready, ready); + WRITE_ONCE(devcom->comp->ready, ready); } -bool mlx5_devcom_comp_is_ready(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id) +bool mlx5_devcom_comp_is_ready(struct mlx5_devcom_comp_dev *devcom) { if (IS_ERR_OR_NULL(devcom)) return false; - return READ_ONCE(devcom->priv->components[id].ready); + return READ_ONCE(devcom->comp->ready); } -bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id) +bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom_comp_dev *devcom) { - struct mlx5_devcom_component *comp; + struct mlx5_devcom_comp *comp; if (IS_ERR_OR_NULL(devcom)) return false; - comp = &devcom->priv->components[id]; + comp = devcom->comp; down_read(&comp->sem); if (!READ_ONCE(comp->ready)) { up_read(&comp->sem); @@ -271,74 +325,60 @@ bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom *devcom, return true; } -void mlx5_devcom_for_each_peer_end(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id) +void mlx5_devcom_for_each_peer_end(struct mlx5_devcom_comp_dev *devcom) { - struct mlx5_devcom_component *comp = &devcom->priv->components[id]; - - up_read(&comp->sem); + up_read(&devcom->comp->sem); } -void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, - int *i) +void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom_comp_dev *devcom, + struct mlx5_devcom_comp_dev **pos) { - struct mlx5_devcom_component *comp; - void *ret; - int idx; + struct mlx5_devcom_comp *comp = devcom->comp; + struct mlx5_devcom_comp_dev *tmp; + void *data; - comp = &devcom->priv->components[id]; + tmp = list_prepare_entry(*pos, &comp->comp_dev_list_head, list); - if (*i == MLX5_DEVCOM_PORTS_SUPPORTED) - return NULL; - for (idx = *i; idx < MLX5_DEVCOM_PORTS_SUPPORTED; idx++) { - if (idx != devcom->idx) { - ret = rcu_dereference_protected(comp->device[idx].data, - lockdep_is_held(&comp->sem)); - if (ret) + list_for_each_entry_continue(tmp, &comp->comp_dev_list_head, list) { + if (tmp != devcom) { + data = rcu_dereference_protected(tmp->data, lockdep_is_held(&comp->sem)); + if (data) break; } } - if (idx == MLX5_DEVCOM_PORTS_SUPPORTED) { - *i = idx; + if (list_entry_is_head(tmp, &comp->comp_dev_list_head, list)) return NULL; - } - *i = idx + 1; - return ret; + *pos = tmp; + return data; } -void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, - int *i) +void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom_comp_dev *devcom, + struct mlx5_devcom_comp_dev **pos) { - struct mlx5_devcom_component *comp; - void *ret; - int idx; + struct mlx5_devcom_comp *comp = devcom->comp; + struct mlx5_devcom_comp_dev *tmp; + void *data; - comp = &devcom->priv->components[id]; + tmp = list_prepare_entry(*pos, &comp->comp_dev_list_head, list); - if (*i == MLX5_DEVCOM_PORTS_SUPPORTED) - return NULL; - for (idx = *i; idx < MLX5_DEVCOM_PORTS_SUPPORTED; idx++) { - if (idx != devcom->idx) { + list_for_each_entry_continue(tmp, &comp->comp_dev_list_head, list) { + if (tmp != devcom) { /* This can change concurrently, however 'data' pointer will remain * valid for the duration of RCU read section. */ if (!READ_ONCE(comp->ready)) return NULL; - ret = rcu_dereference(comp->device[idx].data); - if (ret) + data = rcu_dereference(tmp->data); + if (data) break; } } - if (idx == MLX5_DEVCOM_PORTS_SUPPORTED) { - *i = idx; + if (list_entry_is_head(tmp, &comp->comp_dev_list_head, list)) return NULL; - } - *i = idx + 1; - return ret; + *pos = tmp; + return data; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index d953a01b8eaa..8389ac0af708 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -6,11 +6,8 @@ #include -#define MLX5_DEVCOM_PORTS_SUPPORTED 4 - -enum mlx5_devcom_components { +enum mlx5_devcom_component { MLX5_DEVCOM_ESW_OFFLOADS, - MLX5_DEVCOM_NUM_COMPONENTS, }; @@ -18,45 +15,40 @@ typedef int (*mlx5_devcom_event_handler_t)(int event, void *my_data, void *event_data); -struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev); -void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom); +struct mlx5_devcom_dev *mlx5_devcom_register_device(struct mlx5_core_dev *dev); +void mlx5_devcom_unregister_device(struct mlx5_devcom_dev *devc); -void mlx5_devcom_register_component(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, - mlx5_devcom_event_handler_t handler, - void *data); -void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id); +struct mlx5_devcom_comp_dev * +mlx5_devcom_register_component(struct mlx5_devcom_dev *devc, + enum mlx5_devcom_component id, + u64 key, + mlx5_devcom_event_handler_t handler, + void *data); +void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom); -int mlx5_devcom_send_event(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, +int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom, int event, int rollback_event, void *event_data); -void mlx5_devcom_comp_set_ready(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, - bool ready); -bool mlx5_devcom_comp_is_ready(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id); - -bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id); -void mlx5_devcom_for_each_peer_end(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id); -void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, int *i); - -#define mlx5_devcom_for_each_peer_entry(devcom, id, data, i) \ - for (i = 0, data = mlx5_devcom_get_next_peer_data(devcom, id, &i); \ - data; \ - data = mlx5_devcom_get_next_peer_data(devcom, id, &i)) - -void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, int *i); - -#define mlx5_devcom_for_each_peer_entry_rcu(devcom, id, data, i) \ - for (i = 0, data = mlx5_devcom_get_next_peer_data_rcu(devcom, id, &i); \ - data; \ - data = mlx5_devcom_get_next_peer_data_rcu(devcom, id, &i)) - -#endif +void mlx5_devcom_comp_set_ready(struct mlx5_devcom_comp_dev *devcom, bool ready); +bool mlx5_devcom_comp_is_ready(struct mlx5_devcom_comp_dev *devcom); + +bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom_comp_dev *devcom); +void mlx5_devcom_for_each_peer_end(struct mlx5_devcom_comp_dev *devcom); +void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom_comp_dev *devcom, + struct mlx5_devcom_comp_dev **pos); + +#define mlx5_devcom_for_each_peer_entry(devcom, data, pos) \ + for (pos = NULL, data = mlx5_devcom_get_next_peer_data(devcom, &pos); \ + data; \ + data = mlx5_devcom_get_next_peer_data(devcom, &pos)) + +void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom_comp_dev *devcom, + struct mlx5_devcom_comp_dev **pos); + +#define mlx5_devcom_for_each_peer_entry_rcu(devcom, data, pos) \ + for (pos = NULL, data = mlx5_devcom_get_next_peer_data_rcu(devcom, &pos); \ + data; \ + data = mlx5_devcom_get_next_peer_data_rcu(devcom, &pos)) + +#endif /* __LIB_MLX5_DEVCOM_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 88dbea6631d5..a79c9b8286a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -951,10 +951,10 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) { int err; - dev->priv.devcom = mlx5_devcom_register_device(dev); - if (IS_ERR(dev->priv.devcom)) - mlx5_core_err(dev, "failed to register with devcom (0x%p)\n", - dev->priv.devcom); + dev->priv.devc = mlx5_devcom_register_device(dev); + if (IS_ERR(dev->priv.devc)) + mlx5_core_warn(dev, "failed to register devcom device %ld\n", + PTR_ERR(dev->priv.devc)); err = mlx5_query_board_id(dev); if (err) { @@ -1089,7 +1089,7 @@ err_eq_cleanup: err_irq_cleanup: mlx5_irq_table_cleanup(dev); err_devcom: - mlx5_devcom_unregister_device(dev->priv.devcom); + mlx5_devcom_unregister_device(dev->priv.devc); return err; } @@ -1118,7 +1118,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_events_cleanup(dev); mlx5_eq_table_cleanup(dev); mlx5_irq_table_cleanup(dev); - mlx5_devcom_unregister_device(dev->priv.devcom); + mlx5_devcom_unregister_device(dev->priv.devc); } static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeout) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 25d0528f9219..56dd3dfe2304 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -501,7 +501,7 @@ struct mlx5_events; struct mlx5_mpfs; struct mlx5_eswitch; struct mlx5_lag; -struct mlx5_devcom; +struct mlx5_devcom_dev; struct mlx5_fw_reset; struct mlx5_eq_table; struct mlx5_irq_table; @@ -618,7 +618,7 @@ struct mlx5_priv { struct mlx5_core_sriov sriov; struct mlx5_lag *lag; u32 flags; - struct mlx5_devcom *devcom; + struct mlx5_devcom_dev *devc; struct mlx5_fw_reset *fw_reset; struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; -- cgit v1.2.3 From 58db72869a9f8e01910844ca145efc2ea91bbbf9 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 18 Jan 2023 16:52:17 +0200 Subject: net/mlx5: Re-organize mlx5_cmd struct Downstream patch will split mlx5_cmd_init() to probe and reload routines. As a preparation, organize mlx5_cmd struct so that any field that will be used in the reload routine are grouped at new nested struct. Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 94 +++++++++++------------ drivers/net/ethernet/mellanox/mlx5/core/debugfs.c | 4 +- include/linux/mlx5/driver.h | 21 ++--- 3 files changed, 60 insertions(+), 59 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index d532883b42d7..f175af528fe0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -162,18 +162,18 @@ static int cmd_alloc_index(struct mlx5_cmd *cmd) int ret; spin_lock_irqsave(&cmd->alloc_lock, flags); - ret = find_first_bit(&cmd->bitmask, cmd->max_reg_cmds); - if (ret < cmd->max_reg_cmds) - clear_bit(ret, &cmd->bitmask); + ret = find_first_bit(&cmd->vars.bitmask, cmd->vars.max_reg_cmds); + if (ret < cmd->vars.max_reg_cmds) + clear_bit(ret, &cmd->vars.bitmask); spin_unlock_irqrestore(&cmd->alloc_lock, flags); - return ret < cmd->max_reg_cmds ? ret : -ENOMEM; + return ret < cmd->vars.max_reg_cmds ? ret : -ENOMEM; } static void cmd_free_index(struct mlx5_cmd *cmd, int idx) { lockdep_assert_held(&cmd->alloc_lock); - set_bit(idx, &cmd->bitmask); + set_bit(idx, &cmd->vars.bitmask); } static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) @@ -192,7 +192,7 @@ static void cmd_ent_put(struct mlx5_cmd_work_ent *ent) if (ent->idx >= 0) { cmd_free_index(cmd, ent->idx); - up(ent->page_queue ? &cmd->pages_sem : &cmd->sem); + up(ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem); } cmd_free_ent(ent); @@ -202,7 +202,7 @@ out: static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) { - return cmd->cmd_buf + (idx << cmd->log_stride); + return cmd->cmd_buf + (idx << cmd->vars.log_stride); } static int mlx5_calc_cmd_blocks(struct mlx5_cmd_msg *msg) @@ -974,7 +974,7 @@ static void cmd_work_handler(struct work_struct *work) cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); complete(&ent->handling); - sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; + sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem; down(sem); if (!ent->page_queue) { alloc_ret = cmd_alloc_index(cmd); @@ -994,9 +994,9 @@ static void cmd_work_handler(struct work_struct *work) } ent->idx = alloc_ret; } else { - ent->idx = cmd->max_reg_cmds; + ent->idx = cmd->vars.max_reg_cmds; spin_lock_irqsave(&cmd->alloc_lock, flags); - clear_bit(ent->idx, &cmd->bitmask); + clear_bit(ent->idx, &cmd->vars.bitmask); spin_unlock_irqrestore(&cmd->alloc_lock, flags); } @@ -1572,15 +1572,15 @@ void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode) struct mlx5_cmd *cmd = &dev->cmd; int i; - for (i = 0; i < cmd->max_reg_cmds; i++) - down(&cmd->sem); - down(&cmd->pages_sem); + for (i = 0; i < cmd->vars.max_reg_cmds; i++) + down(&cmd->vars.sem); + down(&cmd->vars.pages_sem); cmd->allowed_opcode = opcode; - up(&cmd->pages_sem); - for (i = 0; i < cmd->max_reg_cmds; i++) - up(&cmd->sem); + up(&cmd->vars.pages_sem); + for (i = 0; i < cmd->vars.max_reg_cmds; i++) + up(&cmd->vars.sem); } static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode) @@ -1588,15 +1588,15 @@ static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode) struct mlx5_cmd *cmd = &dev->cmd; int i; - for (i = 0; i < cmd->max_reg_cmds; i++) - down(&cmd->sem); - down(&cmd->pages_sem); + for (i = 0; i < cmd->vars.max_reg_cmds; i++) + down(&cmd->vars.sem); + down(&cmd->vars.pages_sem); cmd->mode = mode; - up(&cmd->pages_sem); - for (i = 0; i < cmd->max_reg_cmds; i++) - up(&cmd->sem); + up(&cmd->vars.pages_sem); + for (i = 0; i < cmd->vars.max_reg_cmds; i++) + up(&cmd->vars.sem); } static int cmd_comp_notifier(struct notifier_block *nb, @@ -1655,7 +1655,7 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force /* there can be at most 32 command queues */ vector = vec & 0xffffffff; - for (i = 0; i < (1 << cmd->log_sz); i++) { + for (i = 0; i < (1 << cmd->vars.log_sz); i++) { if (test_bit(i, &vector)) { ent = cmd->ent_arr[i]; @@ -1744,7 +1744,7 @@ static void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) /* wait for pending handlers to complete */ mlx5_eq_synchronize_cmd_irq(dev); spin_lock_irqsave(&dev->cmd.alloc_lock, flags); - vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1); + vector = ~dev->cmd.vars.bitmask & ((1ul << (1 << dev->cmd.vars.log_sz)) - 1); if (!vector) goto no_trig; @@ -1753,14 +1753,14 @@ static void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) * to guarantee pending commands will not get freed in the meanwhile. * For that reason, it also has to be done inside the alloc_lock. */ - for_each_set_bit(i, &bitmask, (1 << cmd->log_sz)) + for_each_set_bit(i, &bitmask, (1 << cmd->vars.log_sz)) cmd_ent_get(cmd->ent_arr[i]); vector |= MLX5_TRIGGERED_CMD_COMP; spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); mlx5_core_dbg(dev, "vector 0x%llx\n", vector); mlx5_cmd_comp_handler(dev, vector, true); - for_each_set_bit(i, &bitmask, (1 << cmd->log_sz)) + for_each_set_bit(i, &bitmask, (1 << cmd->vars.log_sz)) cmd_ent_put(cmd->ent_arr[i]); return; @@ -1773,22 +1773,22 @@ void mlx5_cmd_flush(struct mlx5_core_dev *dev) struct mlx5_cmd *cmd = &dev->cmd; int i; - for (i = 0; i < cmd->max_reg_cmds; i++) { - while (down_trylock(&cmd->sem)) { + for (i = 0; i < cmd->vars.max_reg_cmds; i++) { + while (down_trylock(&cmd->vars.sem)) { mlx5_cmd_trigger_completions(dev); cond_resched(); } } - while (down_trylock(&cmd->pages_sem)) { + while (down_trylock(&cmd->vars.pages_sem)) { mlx5_cmd_trigger_completions(dev); cond_resched(); } /* Unlock cmdif */ - up(&cmd->pages_sem); - for (i = 0; i < cmd->max_reg_cmds; i++) - up(&cmd->sem); + up(&cmd->vars.pages_sem); + for (i = 0; i < cmd->vars.max_reg_cmds; i++) + up(&cmd->vars.sem); } static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size, @@ -1858,7 +1858,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, /* atomic context may not sleep */ if (callback) return -EINVAL; - down(&dev->cmd.throttle_sem); + down(&dev->cmd.vars.throttle_sem); } pages_queue = is_manage_pages(in); @@ -1903,7 +1903,7 @@ out_in: free_msg(dev, inb); out_up: if (throttle_op) - up(&dev->cmd.throttle_sem); + up(&dev->cmd.vars.throttle_sem); return err; } @@ -2213,16 +2213,16 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) goto err_free_pool; cmd_l = ioread32be(&dev->iseg->cmdq_addr_l_sz) & 0xff; - cmd->log_sz = cmd_l >> 4 & 0xf; - cmd->log_stride = cmd_l & 0xf; - if (1 << cmd->log_sz > MLX5_MAX_COMMANDS) { + cmd->vars.log_sz = cmd_l >> 4 & 0xf; + cmd->vars.log_stride = cmd_l & 0xf; + if (1 << cmd->vars.log_sz > MLX5_MAX_COMMANDS) { mlx5_core_err(dev, "firmware reports too many outstanding commands %d\n", - 1 << cmd->log_sz); + 1 << cmd->vars.log_sz); err = -EINVAL; goto err_free_page; } - if (cmd->log_sz + cmd->log_stride > MLX5_ADAPTER_PAGE_SHIFT) { + if (cmd->vars.log_sz + cmd->vars.log_stride > MLX5_ADAPTER_PAGE_SHIFT) { mlx5_core_err(dev, "command queue size overflow\n"); err = -EINVAL; goto err_free_page; @@ -2230,13 +2230,13 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) cmd->state = MLX5_CMDIF_STATE_DOWN; cmd->checksum_disabled = 1; - cmd->max_reg_cmds = (1 << cmd->log_sz) - 1; - cmd->bitmask = (1UL << cmd->max_reg_cmds) - 1; + cmd->vars.max_reg_cmds = (1 << cmd->vars.log_sz) - 1; + cmd->vars.bitmask = (1UL << cmd->vars.max_reg_cmds) - 1; - cmd->cmdif_rev = ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16; - if (cmd->cmdif_rev > CMD_IF_REV) { + cmd->vars.cmdif_rev = ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16; + if (cmd->vars.cmdif_rev > CMD_IF_REV) { mlx5_core_err(dev, "driver does not support command interface version. driver %d, firmware %d\n", - CMD_IF_REV, cmd->cmdif_rev); + CMD_IF_REV, cmd->vars.cmdif_rev); err = -EOPNOTSUPP; goto err_free_page; } @@ -2246,9 +2246,9 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) for (i = 0; i < MLX5_CMD_OP_MAX; i++) spin_lock_init(&cmd->stats[i].lock); - sema_init(&cmd->sem, cmd->max_reg_cmds); - sema_init(&cmd->pages_sem, 1); - sema_init(&cmd->throttle_sem, DIV_ROUND_UP(cmd->max_reg_cmds, 2)); + sema_init(&cmd->vars.sem, cmd->vars.max_reg_cmds); + sema_init(&cmd->vars.pages_sem, 1); + sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2)); cmd_h = (u32)((u64)(cmd->dma) >> 32); cmd_l = (u32)(cmd->dma); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 2138f28a2931..9a826fb3ca38 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -176,8 +176,8 @@ static ssize_t slots_read(struct file *filp, char __user *buf, size_t count, int ret; cmd = filp->private_data; - weight = bitmap_weight(&cmd->bitmask, cmd->max_reg_cmds); - field = cmd->max_reg_cmds - weight; + weight = bitmap_weight(&cmd->vars.bitmask, cmd->vars.max_reg_cmds); + field = cmd->vars.max_reg_cmds - weight; ret = snprintf(tbuf, sizeof(tbuf), "%d\n", field); return simple_read_from_buffer(buf, count, pos, tbuf, ret); } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 56dd3dfe2304..39c5f4087c39 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -287,18 +287,23 @@ struct mlx5_cmd_stats { struct mlx5_cmd { struct mlx5_nb nb; + /* members which needs to be queried or reinitialized each reload */ + struct { + u16 cmdif_rev; + u8 log_sz; + u8 log_stride; + int max_reg_cmds; + unsigned long bitmask; + struct semaphore sem; + struct semaphore pages_sem; + struct semaphore throttle_sem; + } vars; enum mlx5_cmdif_state state; void *cmd_alloc_buf; dma_addr_t alloc_dma; int alloc_size; void *cmd_buf; dma_addr_t dma; - u16 cmdif_rev; - u8 log_sz; - u8 log_stride; - int max_reg_cmds; - int events; - u32 __iomem *vector; /* protect command queue allocations */ @@ -308,12 +313,8 @@ struct mlx5_cmd { */ spinlock_t token_lock; u8 token; - unsigned long bitmask; char wq_name[MLX5_CMD_WQ_MAX_NAME]; struct workqueue_struct *wq; - struct semaphore sem; - struct semaphore pages_sem; - struct semaphore throttle_sem; int mode; u16 allowed_opcode; struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS]; -- cgit v1.2.3 From b90ebfc018b087ba1e4981b298b58733236ff296 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 19 Jan 2023 09:10:50 +0200 Subject: net/mlx5: Allocate command stats with xarray Command stats is an array with more than 2K entries, which amounts to ~180KB. This is way more than actually needed, as only ~190 entries are being used. Therefore, replace the array with xarray. Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 15 ++++++------ drivers/net/ethernet/mellanox/mlx5/core/debugfs.c | 30 ++++++++++++++++++++++- include/linux/mlx5/driver.h | 2 +- 3 files changed, 37 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 45edd5a110c8..afb348579577 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1225,8 +1225,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, goto out_free; ds = ent->ts2 - ent->ts1; - if (ent->op < MLX5_CMD_OP_MAX) { - stats = &cmd->stats[ent->op]; + stats = xa_load(&cmd->stats, ent->op); + if (stats) { spin_lock_irq(&stats->lock); stats->sum += ds; ++stats->n; @@ -1695,8 +1695,8 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force if (ent->callback) { ds = ent->ts2 - ent->ts1; - if (ent->op < MLX5_CMD_OP_MAX) { - stats = &cmd->stats[ent->op]; + stats = xa_load(&cmd->stats, ent->op); + if (stats) { spin_lock_irqsave(&stats->lock, flags); stats->sum += ds; ++stats->n; @@ -1923,7 +1923,9 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, if (!err || !(strcmp(namep, "unknown command opcode"))) return; - stats = &dev->cmd.stats[opcode]; + stats = xa_load(&dev->cmd.stats, opcode); + if (!stats) + return; spin_lock_irq(&stats->lock); stats->failed++; if (err < 0) @@ -2189,7 +2191,6 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) struct mlx5_cmd *cmd = &dev->cmd; u32 cmd_l; int err; - int i; cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0); if (!cmd->pool) @@ -2209,8 +2210,6 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) spin_lock_init(&cmd->alloc_lock); spin_lock_init(&cmd->token_lock); - for (i = 0; i < MLX5_CMD_OP_MAX; i++) - spin_lock_init(&cmd->stats[i].lock); create_msg_cache(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 9a826fb3ca38..09652dc89115 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -188,6 +188,24 @@ static const struct file_operations slots_fops = { .read = slots_read, }; +static struct mlx5_cmd_stats * +mlx5_cmdif_alloc_stats(struct xarray *stats_xa, int opcode) +{ + struct mlx5_cmd_stats *stats = kzalloc(sizeof(*stats), GFP_KERNEL); + int err; + + if (!stats) + return NULL; + + err = xa_insert(stats_xa, opcode, stats, GFP_KERNEL); + if (err) { + kfree(stats); + return NULL; + } + spin_lock_init(&stats->lock); + return stats; +} + void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) { struct mlx5_cmd_stats *stats; @@ -200,10 +218,14 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) debugfs_create_file("slots_inuse", 0400, *cmd, &dev->cmd, &slots_fops); + xa_init(&dev->cmd.stats); + for (i = 0; i < MLX5_CMD_OP_MAX; i++) { - stats = &dev->cmd.stats[i]; namep = mlx5_command_str(i); if (strcmp(namep, "unknown command opcode")) { + stats = mlx5_cmdif_alloc_stats(&dev->cmd.stats, i); + if (!stats) + continue; stats->root = debugfs_create_dir(namep, *cmd); debugfs_create_file("average", 0400, stats->root, stats, @@ -224,7 +246,13 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev) { + struct mlx5_cmd_stats *stats; + unsigned long i; + debugfs_remove_recursive(dev->priv.dbg.cmdif_debugfs); + xa_for_each(&dev->cmd.stats, i, stats) + kfree(stats); + xa_destroy(&dev->cmd.stats); } void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 39c5f4087c39..f21703fb75fd 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -322,7 +322,7 @@ struct mlx5_cmd { struct mlx5_cmd_debug dbg; struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES]; int checksum_disabled; - struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX]; + struct xarray stats; }; struct mlx5_cmd_mailbox { -- cgit v1.2.3 From d0358c1a37db4c46b9a1cd6c1b36e5a24ff970f9 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 26 Jul 2023 22:37:15 +0800 Subject: net: Remove unused declaration dev_restart() This is not used, so can remove it. Signed-off-by: YueHaibing Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230726143715.24700-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 11652e464f5d..32a4cdf37dd4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3130,8 +3130,6 @@ struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); -int dev_restart(struct net_device *dev); - static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, -- cgit v1.2.3 From 994650353cae9e10cca7fd61de79c911aa8ed287 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 26 Jul 2023 22:40:54 +0800 Subject: net: datalink: Remove unused declarations These declarations is not used after ipx protocol removed. Signed-off-by: YueHaibing Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230726144054.28780-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/datalink.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/datalink.h b/include/net/datalink.h index c837ffc7ebf8..6c529a40e00d 100644 --- a/include/net/datalink.h +++ b/include/net/datalink.h @@ -23,6 +23,4 @@ struct datalink_proto { struct list_head node; }; -struct datalink_proto *make_EII_client(void); -void destroy_EII_client(struct datalink_proto *dl); #endif -- cgit v1.2.3 From 1f9a1ea821ff25353a0e80d971e7958cd55b47a3 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 27 Jul 2023 18:11:56 -0700 Subject: bpf: Support new sign-extension load insns Add interpreter/jit support for new sign-extension load insns which adds a new mode (BPF_MEMSX). Also add verifier support to recognize these insns and to do proper verification with new insns. In verifier, besides to deduce proper bounds for the dst_reg, probed memory access is also properly handled. Acked-by: Eduard Zingerman Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20230728011156.3711870-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- arch/x86/net/bpf_jit_comp.c | 42 ++++++++++++- include/linux/filter.h | 3 + include/uapi/linux/bpf.h | 1 + kernel/bpf/core.c | 21 +++++++ kernel/bpf/verifier.c | 140 ++++++++++++++++++++++++++++++++++------- tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 181 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 83c4b45dc65f..54478a9c93e1 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -779,6 +779,29 @@ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) *pprog = prog; } +/* LDSX: dst_reg = *(s8*)(src_reg + off) */ +static void emit_ldsx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) +{ + u8 *prog = *pprog; + + switch (size) { + case BPF_B: + /* Emit 'movsx rax, byte ptr [rax + off]' */ + EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xBE); + break; + case BPF_H: + /* Emit 'movsx rax, word ptr [rax + off]' */ + EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xBF); + break; + case BPF_W: + /* Emit 'movsx rax, dword ptr [rax+0x14]' */ + EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x63); + break; + } + emit_insn_suffix(&prog, src_reg, dst_reg, off); + *pprog = prog; +} + /* STX: *(u8*)(dst_reg + off) = src_reg */ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { @@ -1370,9 +1393,17 @@ st: if (is_imm8(insn->off)) case BPF_LDX | BPF_PROBE_MEM | BPF_W: case BPF_LDX | BPF_MEM | BPF_DW: case BPF_LDX | BPF_PROBE_MEM | BPF_DW: + /* LDXS: dst_reg = *(s8*)(src_reg + off) */ + case BPF_LDX | BPF_MEMSX | BPF_B: + case BPF_LDX | BPF_MEMSX | BPF_H: + case BPF_LDX | BPF_MEMSX | BPF_W: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_B: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_H: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_W: insn_off = insn->off; - if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { + if (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX) { /* Conservatively check that src_reg + insn->off is a kernel address: * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE * src_reg is used as scratch for src_reg += insn->off and restored @@ -1415,8 +1446,13 @@ st: if (is_imm8(insn->off)) start_of_ldx = prog; end_of_jmp[-1] = start_of_ldx - end_of_jmp; } - emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off); - if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { + if (BPF_MODE(insn->code) == BPF_PROBE_MEMSX || + BPF_MODE(insn->code) == BPF_MEMSX) + emit_ldsx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off); + else + emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off); + if (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX) { struct exception_table_entry *ex; u8 *_insn = image + proglen + (start_of_ldx - temp); s64 delta; diff --git a/include/linux/filter.h b/include/linux/filter.h index f69114083ec7..a93242b5516b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -69,6 +69,9 @@ struct ctl_table_header; /* unused opcode to mark special load instruction. Same as BPF_ABS */ #define BPF_PROBE_MEM 0x20 +/* unused opcode to mark special ldsx instruction. Same as BPF_IND */ +#define BPF_PROBE_MEMSX 0x40 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7fc98f4b63e9..14fd26b09e4b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -19,6 +19,7 @@ /* ld/ldx fields */ #define BPF_DW 0x18 /* double word (64-bit) */ +#define BPF_MEMSX 0x80 /* load with sign extension */ #define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */ #define BPF_XADD 0xc0 /* exclusive add - legacy name */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index dc85240a0134..01b72fc001f6 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1610,6 +1610,9 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(LDX, MEM, H), \ INSN_3(LDX, MEM, W), \ INSN_3(LDX, MEM, DW), \ + INSN_3(LDX, MEMSX, B), \ + INSN_3(LDX, MEMSX, H), \ + INSN_3(LDX, MEMSX, W), \ /* Immediate based. */ \ INSN_3(LD, IMM, DW) @@ -1666,6 +1669,9 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW, + [BPF_LDX | BPF_PROBE_MEMSX | BPF_B] = &&LDX_PROBE_MEMSX_B, + [BPF_LDX | BPF_PROBE_MEMSX | BPF_H] = &&LDX_PROBE_MEMSX_H, + [BPF_LDX | BPF_PROBE_MEMSX | BPF_W] = &&LDX_PROBE_MEMSX_W, }; #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL @@ -1942,6 +1948,21 @@ out: LDST(DW, u64) #undef LDST +#define LDSX(SIZEOP, SIZE) \ + LDX_MEMSX_##SIZEOP: \ + DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ + CONT; \ + LDX_PROBE_MEMSX_##SIZEOP: \ + bpf_probe_read_kernel(&DST, sizeof(SIZE), \ + (const void *)(long) (SRC + insn->off)); \ + DST = *((SIZE *)&DST); \ + CONT; + + LDSX(B, s8) + LDSX(H, s16) + LDSX(W, s32) +#undef LDSX + #define ATOMIC_ALU_OP(BOP, KOP) \ case BOP: \ if (BPF_SIZE(insn->code) == BPF_W) \ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 71473c19093d..b154854034e0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5827,6 +5827,84 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) __reg_combine_64_into_32(reg); } +static void set_sext64_default_val(struct bpf_reg_state *reg, int size) +{ + if (size == 1) { + reg->smin_value = reg->s32_min_value = S8_MIN; + reg->smax_value = reg->s32_max_value = S8_MAX; + } else if (size == 2) { + reg->smin_value = reg->s32_min_value = S16_MIN; + reg->smax_value = reg->s32_max_value = S16_MAX; + } else { + /* size == 4 */ + reg->smin_value = reg->s32_min_value = S32_MIN; + reg->smax_value = reg->s32_max_value = S32_MAX; + } + reg->umin_value = reg->u32_min_value = 0; + reg->umax_value = U64_MAX; + reg->u32_max_value = U32_MAX; + reg->var_off = tnum_unknown; +} + +static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size) +{ + s64 init_s64_max, init_s64_min, s64_max, s64_min, u64_cval; + u64 top_smax_value, top_smin_value; + u64 num_bits = size * 8; + + if (tnum_is_const(reg->var_off)) { + u64_cval = reg->var_off.value; + if (size == 1) + reg->var_off = tnum_const((s8)u64_cval); + else if (size == 2) + reg->var_off = tnum_const((s16)u64_cval); + else + /* size == 4 */ + reg->var_off = tnum_const((s32)u64_cval); + + u64_cval = reg->var_off.value; + reg->smax_value = reg->smin_value = u64_cval; + reg->umax_value = reg->umin_value = u64_cval; + reg->s32_max_value = reg->s32_min_value = u64_cval; + reg->u32_max_value = reg->u32_min_value = u64_cval; + return; + } + + top_smax_value = ((u64)reg->smax_value >> num_bits) << num_bits; + top_smin_value = ((u64)reg->smin_value >> num_bits) << num_bits; + + if (top_smax_value != top_smin_value) + goto out; + + /* find the s64_min and s64_min after sign extension */ + if (size == 1) { + init_s64_max = (s8)reg->smax_value; + init_s64_min = (s8)reg->smin_value; + } else if (size == 2) { + init_s64_max = (s16)reg->smax_value; + init_s64_min = (s16)reg->smin_value; + } else { + init_s64_max = (s32)reg->smax_value; + init_s64_min = (s32)reg->smin_value; + } + + s64_max = max(init_s64_max, init_s64_min); + s64_min = min(init_s64_max, init_s64_min); + + /* both of s64_max/s64_min positive or negative */ + if (s64_max >= 0 == s64_min >= 0) { + reg->smin_value = reg->s32_min_value = s64_min; + reg->smax_value = reg->s32_max_value = s64_max; + reg->umin_value = reg->u32_min_value = s64_min; + reg->umax_value = reg->u32_max_value = s64_max; + reg->var_off = tnum_range(s64_min, s64_max); + return; + } + +out: + set_sext64_default_val(reg, size); +} + static bool bpf_map_is_rdonly(const struct bpf_map *map) { /* A map is considered read-only if the following condition are true: @@ -5847,7 +5925,8 @@ static bool bpf_map_is_rdonly(const struct bpf_map *map) !bpf_map_write_active(map); } -static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) +static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val, + bool is_ldsx) { void *ptr; u64 addr; @@ -5860,13 +5939,13 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) switch (size) { case sizeof(u8): - *val = (u64)*(u8 *)ptr; + *val = is_ldsx ? (s64)*(s8 *)ptr : (u64)*(u8 *)ptr; break; case sizeof(u16): - *val = (u64)*(u16 *)ptr; + *val = is_ldsx ? (s64)*(s16 *)ptr : (u64)*(u16 *)ptr; break; case sizeof(u32): - *val = (u64)*(u32 *)ptr; + *val = is_ldsx ? (s64)*(s32 *)ptr : (u64)*(u32 *)ptr; break; case sizeof(u64): *val = *(u64 *)ptr; @@ -6285,7 +6364,7 @@ static int check_stack_access_within_bounds( */ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int bpf_size, enum bpf_access_type t, - int value_regno, bool strict_alignment_once) + int value_regno, bool strict_alignment_once, bool is_ldsx) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; @@ -6346,7 +6425,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn u64 val = 0; err = bpf_map_direct_read(map, map_off, size, - &val); + &val, is_ldsx); if (err) return err; @@ -6516,8 +6595,11 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ && regs[value_regno].type == SCALAR_VALUE) { - /* b/h/w load zero-extends, mark upper bits as known 0 */ - coerce_reg_to_size(®s[value_regno], size); + if (!is_ldsx) + /* b/h/w load zero-extends, mark upper bits as known 0 */ + coerce_reg_to_size(®s[value_regno], size); + else + coerce_reg_to_size_sx(®s[value_regno], size); } return err; } @@ -6609,17 +6691,17 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i * case to simulate the register fill. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, -1, true); + BPF_SIZE(insn->code), BPF_READ, -1, true, false); if (!err && load_reg >= 0) err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, load_reg, - true); + true, false); if (err) return err; /* Check whether we can write into the same memory. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_WRITE, -1, true); + BPF_SIZE(insn->code), BPF_WRITE, -1, true, false); if (err) return err; @@ -6865,7 +6947,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return zero_size_allowed ? 0 : -EACCES; return check_mem_access(env, env->insn_idx, regno, offset, BPF_B, - atype, -1, false); + atype, -1, false, false); } fallthrough; @@ -7237,7 +7319,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn /* we write BPF_DW bits (8 bytes) at a time */ for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { err = check_mem_access(env, insn_idx, regno, - i, BPF_DW, BPF_WRITE, -1, false); + i, BPF_DW, BPF_WRITE, -1, false, false); if (err) return err; } @@ -7330,7 +7412,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) { err = check_mem_access(env, insn_idx, regno, - i, BPF_DW, BPF_WRITE, -1, false); + i, BPF_DW, BPF_WRITE, -1, false, false); if (err) return err; } @@ -9474,7 +9556,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn */ for (i = 0; i < meta.access_size; i++) { err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, - BPF_WRITE, -1, false); + BPF_WRITE, -1, false, false); if (err) return err; } @@ -16202,7 +16284,7 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ * Have to support a use case when one path through * the program yields TRUSTED pointer while another * is UNTRUSTED. Fallback to UNTRUSTED to generate - * BPF_PROBE_MEM. + * BPF_PROBE_MEM/BPF_PROBE_MEMSX. */ *prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED; } else { @@ -16343,7 +16425,8 @@ static int do_check(struct bpf_verifier_env *env) */ err = check_mem_access(env, env->insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), - BPF_READ, insn->dst_reg, false); + BPF_READ, insn->dst_reg, false, + BPF_MODE(insn->code) == BPF_MEMSX); if (err) return err; @@ -16380,7 +16463,7 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), - BPF_WRITE, insn->src_reg, false); + BPF_WRITE, insn->src_reg, false, false); if (err) return err; @@ -16405,7 +16488,7 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), - BPF_WRITE, -1, false); + BPF_WRITE, -1, false, false); if (err) return err; @@ -16833,7 +16916,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && - (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) { + ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) || + insn->imm != 0)) { verbose(env, "BPF_LDX uses reserved fields\n"); return -EINVAL; } @@ -17531,7 +17615,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) 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) || + insn->code == (BPF_LDX | BPF_MEMSX | BPF_B) || + insn->code == (BPF_LDX | BPF_MEMSX | BPF_H) || + insn->code == (BPF_LDX | BPF_MEMSX | BPF_W)) { type = BPF_READ; } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || insn->code == (BPF_STX | BPF_MEM | BPF_H) || @@ -17590,8 +17677,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) */ case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: if (type == BPF_READ) { - insn->code = BPF_LDX | BPF_PROBE_MEM | - BPF_SIZE((insn)->code); + if (BPF_MODE(insn->code) == BPF_MEM) + insn->code = BPF_LDX | BPF_PROBE_MEM | + BPF_SIZE((insn)->code); + else + insn->code = BPF_LDX | BPF_PROBE_MEMSX | + BPF_SIZE((insn)->code); env->prog->aux->num_exentries++; } continue; @@ -17779,7 +17870,8 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && - BPF_MODE(insn->code) == BPF_PROBE_MEM) + (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) num_exentries++; } func[i]->aux->num_exentries = num_exentries; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7fc98f4b63e9..14fd26b09e4b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -19,6 +19,7 @@ /* ld/ldx fields */ #define BPF_DW 0x18 /* double word (64-bit) */ +#define BPF_MEMSX 0x80 /* load with sign extension */ #define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */ #define BPF_XADD 0xc0 /* exclusive add - legacy name */ -- cgit v1.2.3 From 7058e3a31ee4b9240cccab5bc13c1afbfa3d16a0 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 27 Jul 2023 18:12:25 -0700 Subject: bpf: Fix jit blinding with new sdiv/smov insns Handle new insns properly in bpf_jit_blind_insn() function. Acked-by: Eduard Zingerman Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20230728011225.3715812-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 14 ++++++++++---- kernel/bpf/core.c | 4 ++-- 2 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index a93242b5516b..f5eabe3fa5e8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -93,22 +93,28 @@ struct ctl_table_header; /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ -#define BPF_ALU64_REG(OP, DST, SRC) \ +#define BPF_ALU64_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ - .off = 0, \ + .off = OFF, \ .imm = 0 }) -#define BPF_ALU32_REG(OP, DST, SRC) \ +#define BPF_ALU64_REG(OP, DST, SRC) \ + BPF_ALU64_REG_OFF(OP, DST, SRC, 0) + +#define BPF_ALU32_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ - .off = 0, \ + .off = OFF, \ .imm = 0 }) +#define BPF_ALU32_REG(OP, DST, SRC) \ + BPF_ALU32_REG_OFF(OP, DST, SRC, 0) + /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ #define BPF_ALU64_IMM(OP, DST, IMM) \ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 3fe895199f6e..646d2fe537be 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1272,7 +1272,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case BPF_ALU | BPF_MOD | BPF_K: *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX); + *to++ = BPF_ALU32_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_ALU64 | BPF_ADD | BPF_K: @@ -1286,7 +1286,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case BPF_ALU64 | BPF_MOD | BPF_K: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX); + *to++ = BPF_ALU64_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_JMP | BPF_JEQ | BPF_K: -- cgit v1.2.3 From d928d14be6514af9da37009c2091270c5c714366 Mon Sep 17 00:00:00 2001 From: Andrew Halaney Date: Tue, 25 Jul 2023 16:04:25 -0500 Subject: net: stmmac: Make ptp_clk_freq_config variable type explicit The priv variable is _always_ of type (struct stmmac_priv *), so let's stop using (void *) since it isn't abstracting anything. Reviewed-by: Simon Horman Signed-off-by: Andrew Halaney Link: https://lore.kernel.org/r/20230725211853.895832-3-ahalaney@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 3 +-- include/linux/stmmac.h | 4 +++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 0ffae785d8bd..979c755964b1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -257,9 +257,8 @@ static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data) /* Program PTP Clock Frequency for different variant of * Intel mGBE that has slightly different GPO mapping */ -static void intel_mgbe_ptp_clk_freq_config(void *npriv) +static void intel_mgbe_ptp_clk_freq_config(struct stmmac_priv *priv) { - struct stmmac_priv *priv = (struct stmmac_priv *)npriv; struct intel_priv_data *intel_priv; u32 gpio_value; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index ef67dba775d0..3d0702510224 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -76,6 +76,8 @@ | DMA_AXI_BLEN_32 | DMA_AXI_BLEN_64 \ | DMA_AXI_BLEN_128 | DMA_AXI_BLEN_256) +struct stmmac_priv; + /* Platfrom data for platform device structure's platform_data field */ struct stmmac_mdio_bus_data { @@ -258,7 +260,7 @@ struct plat_stmmacenet_data { int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); void (*speed_mode_2500)(struct net_device *ndev, void *priv); - void (*ptp_clk_freq_config)(void *priv); + void (*ptp_clk_freq_config)(struct stmmac_priv *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); struct mac_device_info *(*setup)(void *priv); -- cgit v1.2.3 From 2e3df4a3b3178006d530f4c4d0e91f3d96cddb3c Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Fri, 2 Jun 2023 09:36:38 +0200 Subject: can: rx-offload: rename rx_offload_get_echo_skb() -> can_rx_offload_get_echo_skb_queue_timestamp() Rename the rx_offload_get_echo_skb() function to can_rx_offload_get_echo_skb_queue_timestamp(), since it inserts the echo skb into the rx-offload queue sorted by timestamp. This is a preparation for adding can_rx_offload_get_echo_skb_queue_tail(), which adds the echo skb to the end of the queue. This is intended for devices that do not support timestamps. Link: https://lore.kernel.org/all/20230718-gs_usb-rx-offload-v2-1-716e542d14d5@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/rx-offload.c | 9 +++++---- drivers/net/can/flexcan/flexcan-core.c | 4 ++-- drivers/net/can/m_can/m_can.c | 8 ++++---- drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c | 6 +++--- drivers/net/can/ti_hecc.c | 4 ++-- include/linux/can/rx-offload.h | 6 +++--- 6 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/drivers/net/can/dev/rx-offload.c b/drivers/net/can/dev/rx-offload.c index 161e45a7e8c1..6e87ad908346 100644 --- a/drivers/net/can/dev/rx-offload.c +++ b/drivers/net/can/dev/rx-offload.c @@ -240,9 +240,10 @@ int can_rx_offload_queue_timestamp(struct can_rx_offload *offload, } EXPORT_SYMBOL_GPL(can_rx_offload_queue_timestamp); -unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, - unsigned int idx, u32 timestamp, - unsigned int *frame_len_ptr) +unsigned int +can_rx_offload_get_echo_skb_queue_timestamp(struct can_rx_offload *offload, + unsigned int idx, u32 timestamp, + unsigned int *frame_len_ptr) { struct net_device *dev = offload->dev; struct net_device_stats *stats = &dev->stats; @@ -262,7 +263,7 @@ unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, return len; } -EXPORT_SYMBOL_GPL(can_rx_offload_get_echo_skb); +EXPORT_SYMBOL_GPL(can_rx_offload_get_echo_skb_queue_timestamp); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb) diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index ff0fc18baf13..48273d51f271 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -1097,8 +1097,8 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id) handled = IRQ_HANDLED; stats->tx_bytes += - can_rx_offload_get_echo_skb(&priv->offload, 0, - reg_ctrl << 16, NULL); + can_rx_offload_get_echo_skb_queue_timestamp(&priv->offload, 0, + reg_ctrl << 16, NULL); stats->tx_packets++; /* after sending a RTR frame MB is in RX mode */ diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index a6263a617ac9..d204703521d2 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1016,10 +1016,10 @@ static void m_can_tx_update_stats(struct m_can_classdev *cdev, if (cdev->is_peripheral) stats->tx_bytes += - can_rx_offload_get_echo_skb(&cdev->offload, - msg_mark, - timestamp, - NULL); + can_rx_offload_get_echo_skb_queue_timestamp(&cdev->offload, + msg_mark, + timestamp, + NULL); else stats->tx_bytes += can_get_echo_skb(dev, msg_mark, NULL); diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c index 237617b0c125..e5bd57b65aaf 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c @@ -111,9 +111,9 @@ mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv, if (skb) mcp251xfd_skb_set_timestamp(priv, skb, hw_tef_obj->ts); stats->tx_bytes += - can_rx_offload_get_echo_skb(&priv->offload, - tef_tail, hw_tef_obj->ts, - frame_len_ptr); + can_rx_offload_get_echo_skb_queue_timestamp(&priv->offload, + tef_tail, hw_tef_obj->ts, + frame_len_ptr); stats->tx_packets++; priv->tef->tail++; diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index a8243acde92d..5aab440074c6 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -747,8 +747,8 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) spin_unlock_irqrestore(&priv->mbx_lock, flags); stamp = hecc_read_stamp(priv, mbxno); stats->tx_bytes += - can_rx_offload_get_echo_skb(&priv->offload, - mbxno, stamp, NULL); + can_rx_offload_get_echo_skb_queue_timestamp(&priv->offload, + mbxno, stamp, NULL); stats->tx_packets++; --priv->tx_tail; } diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index c205c51d79c9..e3b4199732c6 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -44,9 +44,9 @@ int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); int can_rx_offload_queue_timestamp(struct can_rx_offload *offload, struct sk_buff *skb, u32 timestamp); -unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, - unsigned int idx, u32 timestamp, - unsigned int *frame_len_ptr); +unsigned int can_rx_offload_get_echo_skb_queue_timestamp(struct can_rx_offload *offload, + unsigned int idx, u32 timestamp, + 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); -- cgit v1.2.3 From 8e0e2950c9ef48f7f40a7175048744ec2390b16e Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 3 Jul 2023 18:18:19 +0200 Subject: can: rx-offload: add can_rx_offload_get_echo_skb_queue_tail() Add can_rx_offload_get_echo_skb_queue_tail(). This function addds the echo skb at the end of rx-offload the queue. This is intended for devices without timestamp support. Link: https://lore.kernel.org/all/20230718-gs_usb-rx-offload-v2-2-716e542d14d5@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/rx-offload.c | 27 ++++++++++++++++++++++++++- include/linux/can/rx-offload.h | 5 ++++- 2 files changed, 30 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/can/dev/rx-offload.c b/drivers/net/can/dev/rx-offload.c index 6e87ad908346..77091f7d1fa7 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) 2014-2021 Pengutronix, + * Copyright (C) 2014-2021, 2023 Pengutronix, * Marc Kleine-Budde */ @@ -280,6 +280,31 @@ int can_rx_offload_queue_tail(struct can_rx_offload *offload, } EXPORT_SYMBOL_GPL(can_rx_offload_queue_tail); +unsigned int +can_rx_offload_get_echo_skb_queue_tail(struct can_rx_offload *offload, + unsigned int idx, + unsigned int *frame_len_ptr) +{ + struct net_device *dev = offload->dev; + struct net_device_stats *stats = &dev->stats; + struct sk_buff *skb; + unsigned int len; + int err; + + skb = __can_get_echo_skb(dev, idx, &len, frame_len_ptr); + if (!skb) + return 0; + + err = can_rx_offload_queue_tail(offload, skb); + if (err) { + stats->rx_errors++; + stats->tx_fifo_errors++; + } + + return len; +} +EXPORT_SYMBOL_GPL(can_rx_offload_get_echo_skb_queue_tail); + void can_rx_offload_irq_finish(struct can_rx_offload *offload) { unsigned long flags; diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index e3b4199732c6..d29bb4521947 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -3,7 +3,7 @@ * linux/can/rx-offload.h * * Copyright (c) 2014 David Jander, Protonic Holland - * Copyright (c) 2014-2017 Pengutronix, Marc Kleine-Budde + * Copyright (c) 2014-2017, 2023 Pengutronix, Marc Kleine-Budde */ #ifndef _CAN_RX_OFFLOAD_H @@ -49,6 +49,9 @@ unsigned int can_rx_offload_get_echo_skb_queue_timestamp(struct can_rx_offload * unsigned int *frame_len_ptr); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb); +unsigned int can_rx_offload_get_echo_skb_queue_tail(struct can_rx_offload *offload, + unsigned int idx, + unsigned int *frame_len_ptr); 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); -- cgit v1.2.3 From 7f6c40391a048c5d0f593f285bee45f7f98a3ca4 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 26 Jul 2023 10:39:05 +0800 Subject: IPv6: add extack info for IPv6 address add/delete Add extack info for IPv6 address add/delete, which would be useful for users to understand the problem without having to read kernel code. Suggested-by: Beniamino Galvani Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Hangbin Liu Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/ip6_route.h | 2 +- net/ipv6/addrconf.c | 77 ++++++++++++++++++++++++++++++++++--------------- net/ipv6/anycast.c | 2 +- net/ipv6/route.c | 5 ++-- 4 files changed, 59 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 3556595ce59a..b32539bb0fb0 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -156,7 +156,7 @@ void fib6_force_start_gc(struct net *net); struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, bool anycast, - gfp_t gfp_flags); + gfp_t gfp_flags, struct netlink_ext_ack *extack); struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 94d1fdb0393f..5daf6a4986f8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1063,20 +1063,28 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, struct fib6_info *f6i = NULL; int err = 0; - if (addr_type == IPV6_ADDR_ANY || - (addr_type & IPV6_ADDR_MULTICAST && - !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) || - (!(idev->dev->flags & IFF_LOOPBACK) && - !netif_is_l3_master(idev->dev) && - addr_type & IPV6_ADDR_LOOPBACK)) + if (addr_type == IPV6_ADDR_ANY) { + NL_SET_ERR_MSG_MOD(extack, "Invalid address"); return ERR_PTR(-EADDRNOTAVAIL); + } else if (addr_type & IPV6_ADDR_MULTICAST && + !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) { + NL_SET_ERR_MSG_MOD(extack, "Cannot assign multicast address without \"IFA_F_MCAUTOJOIN\" flag"); + return ERR_PTR(-EADDRNOTAVAIL); + } else if (!(idev->dev->flags & IFF_LOOPBACK) && + !netif_is_l3_master(idev->dev) && + addr_type & IPV6_ADDR_LOOPBACK) { + NL_SET_ERR_MSG_MOD(extack, "Cannot assign loopback address on this device"); + return ERR_PTR(-EADDRNOTAVAIL); + } if (idev->dead) { - err = -ENODEV; /*XXX*/ + NL_SET_ERR_MSG_MOD(extack, "device is going away"); + err = -ENODEV; goto out; } if (idev->cnf.disable_ipv6) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device"); err = -EACCES; goto out; } @@ -1103,7 +1111,7 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, goto out; } - f6i = addrconf_f6i_alloc(net, idev, cfg->pfx, false, gfp_flags); + f6i = addrconf_f6i_alloc(net, idev, cfg->pfx, false, gfp_flags, extack); if (IS_ERR(f6i)) { err = PTR_ERR(f6i); f6i = NULL; @@ -2927,30 +2935,40 @@ static int inet6_addr_add(struct net *net, int ifindex, ASSERT_RTNL(); - if (cfg->plen > 128) + if (cfg->plen > 128) { + NL_SET_ERR_MSG_MOD(extack, "Invalid prefix length"); return -EINVAL; + } /* check the lifetime */ - if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft) + if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft) { + NL_SET_ERR_MSG_MOD(extack, "address lifetime invalid"); return -EINVAL; + } - if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64) + if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64) { + NL_SET_ERR_MSG_MOD(extack, "address with \"mngtmpaddr\" flag must have a prefix length of 64"); return -EINVAL; + } dev = __dev_get_by_index(net, ifindex); if (!dev) return -ENODEV; idev = addrconf_add_dev(dev); - if (IS_ERR(idev)) + if (IS_ERR(idev)) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device"); return PTR_ERR(idev); + } if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk, true, cfg->pfx, ifindex); - if (ret < 0) + if (ret < 0) { + NL_SET_ERR_MSG_MOD(extack, "Multicast auto join failed"); return ret; + } } cfg->scope = ipv6_addr_scope(cfg->pfx); @@ -3007,22 +3025,29 @@ static int inet6_addr_add(struct net *net, int ifindex, } static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, - const struct in6_addr *pfx, unsigned int plen) + const struct in6_addr *pfx, unsigned int plen, + struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; - if (plen > 128) + if (plen > 128) { + NL_SET_ERR_MSG_MOD(extack, "Invalid prefix length"); return -EINVAL; + } dev = __dev_get_by_index(net, ifindex); - if (!dev) + if (!dev) { + NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface"); return -ENODEV; + } idev = __in6_dev_get(dev); - if (!idev) + if (!idev) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device"); return -ENXIO; + } read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { @@ -3045,6 +3070,8 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, } } read_unlock_bh(&idev->lock); + + NL_SET_ERR_MSG_MOD(extack, "address not found"); return -EADDRNOTAVAIL; } @@ -3087,7 +3114,7 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg) rtnl_lock(); err = inet6_addr_del(net, ireq.ifr6_ifindex, 0, &ireq.ifr6_addr, - ireq.ifr6_prefixlen); + ireq.ifr6_prefixlen, NULL); rtnl_unlock(); return err; } @@ -3490,7 +3517,7 @@ static int fixup_permanent_addr(struct net *net, struct fib6_info *f6i, *prev; f6i = addrconf_f6i_alloc(net, idev, &ifp->addr, false, - GFP_ATOMIC); + GFP_ATOMIC, NULL); if (IS_ERR(f6i)) return PTR_ERR(f6i); @@ -4700,7 +4727,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, ifa_flags &= IFA_F_MANAGETEMPADDR; return inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx, - ifm->ifa_prefixlen); + ifm->ifa_prefixlen, extack); } static int modify_prefix_route(struct inet6_ifaddr *ifp, @@ -4905,8 +4932,10 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, } dev = __dev_get_by_index(net, ifm->ifa_index); - if (!dev) + if (!dev) { + NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface"); return -ENODEV; + } if (tb[IFA_FLAGS]) cfg.ifa_flags = nla_get_u32(tb[IFA_FLAGS]); @@ -4941,10 +4970,12 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, } if (nlh->nlmsg_flags & NLM_F_EXCL || - !(nlh->nlmsg_flags & NLM_F_REPLACE)) + !(nlh->nlmsg_flags & NLM_F_REPLACE)) { + NL_SET_ERR_MSG_MOD(extack, "address already assigned"); err = -EEXIST; - else + } else { err = inet6_addr_modify(net, ifa, &cfg); + } in6_ifa_put(ifa); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index dacdea7fcb62..bb17f484ee2c 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -305,7 +305,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) } net = dev_net(idev->dev); - f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC); + f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC, NULL); if (IS_ERR(f6i)) { err = PTR_ERR(f6i); goto out; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 64e873f5895f..c90700aed3a1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4543,7 +4543,8 @@ static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, - bool anycast, gfp_t gfp_flags) + bool anycast, gfp_t gfp_flags, + struct netlink_ext_ack *extack) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL, @@ -4565,7 +4566,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net, cfg.fc_flags |= RTF_LOCAL; } - f6i = ip6_route_info_create(&cfg, gfp_flags, NULL); + f6i = ip6_route_info_create(&cfg, gfp_flags, extack); if (!IS_ERR(f6i)) { f6i->dst_nocount = true; -- cgit v1.2.3 From 25b5a2a1905fd8631c73596f98793f7494f29f2a Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 27 Jul 2023 09:30:00 -0700 Subject: ynl: regenerate all headers Also add support to pass topdir to ynl-regen.sh (Jakub) and call it from the makefile to update the UAPI headers. Signed-off-by: Stanislav Fomichev Co-developed-by: Jakub Kicinski Reviewed-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230727163001.3952878-4-sdf@google.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/netdev.h | 3 ++- tools/include/uapi/linux/netdev.h | 3 ++- tools/net/ynl/Makefile | 1 + tools/net/ynl/generated/netdev-user.c | 6 ++++++ tools/net/ynl/generated/netdev-user.h | 2 ++ tools/net/ynl/ynl-regen.sh | 5 +++++ 6 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index bf71698a1e82..c1634b95c223 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -11,7 +11,7 @@ /** * enum netdev_xdp_act - * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers + * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements @@ -34,6 +34,7 @@ enum netdev_xdp_act { NETDEV_XDP_ACT_RX_SG = 32, NETDEV_XDP_ACT_NDO_XMIT_SG = 64, + /* private: */ NETDEV_XDP_ACT_MASK = 127, }; diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index bf71698a1e82..c1634b95c223 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -11,7 +11,7 @@ /** * enum netdev_xdp_act - * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers + * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements @@ -34,6 +34,7 @@ enum netdev_xdp_act { NETDEV_XDP_ACT_RX_SG = 32, NETDEV_XDP_ACT_NDO_XMIT_SG = 64, + /* private: */ NETDEV_XDP_ACT_MASK = 127, }; diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index d664b36deb5b..8156f03e23ac 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -3,6 +3,7 @@ SUBDIRS = lib generated samples all: $(SUBDIRS) + ./ynl-regen.sh -f -p $(PWD)/../../../ $(SUBDIRS): @if [ -f "$@/Makefile" ] ; then \ diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c index 4eb8aefef0cd..68b408ca0f7f 100644 --- a/tools/net/ynl/generated/netdev-user.c +++ b/tools/net/ynl/generated/netdev-user.c @@ -50,6 +50,7 @@ struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = { [NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, [NETDEV_A_DEV_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, }, [NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, }, + [NETDEV_A_DEV_XDP_ZC_MAX_SEGS] = { .name = "xdp-zc-max-segs", .type = YNL_PT_U32, }, }; struct ynl_policy_nest netdev_dev_nest = { @@ -91,6 +92,11 @@ int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data) return MNL_CB_ERROR; dst->_present.xdp_features = 1; dst->xdp_features = mnl_attr_get_u64(attr); + } else if (type == NETDEV_A_DEV_XDP_ZC_MAX_SEGS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.xdp_zc_max_segs = 1; + dst->xdp_zc_max_segs = mnl_attr_get_u32(attr); } } diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h index 5554dc69bb9c..0952d3261f4d 100644 --- a/tools/net/ynl/generated/netdev-user.h +++ b/tools/net/ynl/generated/netdev-user.h @@ -47,10 +47,12 @@ struct netdev_dev_get_rsp { struct { __u32 ifindex:1; __u32 xdp_features:1; + __u32 xdp_zc_max_segs:1; } _present; __u32 ifindex; __u64 xdp_features; + __u32 xdp_zc_max_segs; }; void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp); diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 8d4ca6a50582..bdba24066cf1 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -4,15 +4,18 @@ TOOL=$(dirname $(realpath $0))/ynl-gen-c.py force= +search= while [ ! -z "$1" ]; do case "$1" in -f ) force=yes; shift ;; + -p ) search=$2; shift 2 ;; * ) echo "Unrecognized option '$1'"; exit 1 ;; esac done KDIR=$(dirname $(dirname $(dirname $(dirname $(realpath $0))))) +pushd ${search:-$KDIR} >>/dev/null files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\|user\)') for f in $files; do @@ -30,3 +33,5 @@ for f in $files; do $TOOL --mode ${params[2]} --${params[3]} --spec $KDIR/${params[0]} \ $args -o $f done + +popd >>/dev/null -- cgit v1.2.3 From 759ab1edb56c88906830fd6b2e7b12514dd32758 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jul 2023 11:55:29 -0700 Subject: net: store netdevs in an xarray Iterating over the netdev hash table for netlink dumps is hard. Dumps are done in "chunks" so we need to save the position after each chunk, so we know where to restart from. Because netdevs are stored in a hash table we remember which bucket we were in and how many devices we dumped. Since we don't hold any locks across the "chunks" - devices may come and go while we're dumping. If that happens we may miss a device (if device is deleted from the bucket we were in). We indicate to user space that this may have happened by setting NLM_F_DUMP_INTR. User space is supposed to dump again (I think) if it sees that. Somehow I doubt most user space gets this right.. To illustrate let's look at an example: System state: start: # [A, B, C] del: B # [A, C] with the hash table we may dump [A, B], missing C completely even tho it existed both before and after the "del B". Add an xarray and use it to allocate ifindexes. This way we can iterate ifindexes in order, without the worry that we'll skip one. We may still generate a dump of a state which "never existed", for example for a set of values and sequence of ops: System state: start: # [A, B] add: C # [A, C, B] del: B # [A, C] we may generate a dump of [A], if C got an index between A and B. System has never been in such state. But I'm 90% sure that's perfectly fine, important part is that we can't _miss_ devices which exist before and after. User space which wants to mirror kernel's state subscribes to notifications and does periodic dumps so it will know that C exists from the notification about its creation or from the next dump (next dump is _guaranteed_ to include C, if it doesn't get removed). To avoid any perf regressions keep the hash table for now. Most net namespaces have very few devices and microbenchmarking 1M lookups on Skylake I get the following results (not counting loopback to number of devs): #devs | hash | xa | delta 2 | 18.3 | 20.1 | + 9.8% 16 | 18.3 | 20.1 | + 9.5% 64 | 18.3 | 26.3 | +43.8% 128 | 20.4 | 26.3 | +28.6% 256 | 20.0 | 26.4 | +32.1% 1024 | 26.6 | 26.7 | + 0.2% 8192 |541.3 | 33.5 | -93.8% No surprises since the hash table has 256 entries. The microbenchmark scans indexes in order, if the pattern is more random xa starts to win at 512 devices already. But that's a lot of devices, in practice. Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230726185530.2247698-2-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/net_namespace.h | 4 ++- net/core/dev.c | 82 +++++++++++++++++++++++++++++---------------- 2 files changed, 57 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 78beaa765c73..9f6add96de2d 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -42,6 +42,7 @@ #include #include #include +#include struct user_namespace; struct proc_dir_entry; @@ -69,7 +70,7 @@ struct net { atomic_t dev_unreg_count; unsigned int dev_base_seq; /* protected by rtnl_mutex */ - int ifindex; + u32 ifindex; spinlock_t nsid_lock; atomic_t fnhe_genid; @@ -110,6 +111,7 @@ struct net { struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; + struct xarray dev_by_index; struct raw_notifier_head netdev_chain; /* Note that @hash_mix can be read millions times per second, diff --git a/net/core/dev.c b/net/core/dev.c index e7ffcfa037f7..b58674774a57 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -388,6 +388,8 @@ static void list_netdevice(struct net_device *dev) hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock(&dev_base_lock); + /* We reserved the ifindex, this can't fail */ + WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL)); dev_base_seq_inc(net); } @@ -397,8 +399,12 @@ static void list_netdevice(struct net_device *dev) */ static void unlist_netdevice(struct net_device *dev, bool lock) { + struct net *net = dev_net(dev); + ASSERT_RTNL(); + xa_erase(&net->dev_by_index, dev->ifindex); + /* Unlink dev from the device chain */ if (lock) write_lock(&dev_base_lock); @@ -9565,23 +9571,35 @@ err_out: } /** - * dev_new_index - allocate an ifindex - * @net: the applicable net namespace + * dev_index_reserve() - allocate an ifindex in a namespace + * @net: the applicable net namespace + * @ifindex: requested ifindex, pass %0 to get one allocated + * + * Allocate a ifindex for a new device. Caller must either use the ifindex + * to store the device (via list_netdevice()) or call dev_index_release() + * to give the index up. * - * Returns a suitable unique value for a new device interface - * number. The caller must hold the rtnl semaphore or the - * dev_base_lock to be sure it remains unique. + * Return: a suitable unique value for a new device interface number or -errno. */ -static int dev_new_index(struct net *net) +static int dev_index_reserve(struct net *net, u32 ifindex) { - int ifindex = net->ifindex; + int err; - for (;;) { - if (++ifindex <= 0) - ifindex = 1; - if (!__dev_get_by_index(net, ifindex)) - return net->ifindex = ifindex; - } + if (!ifindex) + err = xa_alloc_cyclic(&net->dev_by_index, &ifindex, NULL, + xa_limit_31b, &net->ifindex, GFP_KERNEL); + else + err = xa_insert(&net->dev_by_index, ifindex, NULL, GFP_KERNEL); + if (err < 0) + return err; + + return ifindex; +} + +static void dev_index_release(struct net *net, int ifindex) +{ + /* Expect only unused indexes, unlist_netdevice() removes the used */ + WARN_ON(xa_erase(&net->dev_by_index, ifindex)); } /* Delayed registration/unregisteration */ @@ -10051,11 +10069,10 @@ int register_netdevice(struct net_device *dev) goto err_uninit; } - ret = -EBUSY; - if (!dev->ifindex) - dev->ifindex = dev_new_index(net); - else if (__dev_get_by_index(net, dev->ifindex)) + ret = dev_index_reserve(net, dev->ifindex); + if (ret < 0) goto err_uninit; + dev->ifindex = ret; /* Transfer changeable features to wanted_features and enable * software offloads (GSO and GRO). @@ -10102,7 +10119,7 @@ int register_netdevice(struct net_device *dev) ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) - goto err_uninit; + goto err_ifindex_release; ret = netdev_register_kobject(dev); write_lock(&dev_base_lock); @@ -10158,6 +10175,8 @@ out: err_uninit_notify: call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); +err_ifindex_release: + dev_index_release(net, dev->ifindex); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -11035,9 +11054,19 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, } /* Check that new_ifindex isn't used yet. */ - err = -EBUSY; - if (new_ifindex && __dev_get_by_index(net, new_ifindex)) - goto out; + if (new_ifindex) { + err = dev_index_reserve(net, new_ifindex); + if (err < 0) + goto out; + } else { + /* If there is an ifindex conflict assign a new one */ + err = dev_index_reserve(net, dev->ifindex); + if (err == -EBUSY) + err = dev_index_reserve(net, 0); + if (err < 0) + goto out; + new_ifindex = err; + } /* * And now a mini version of register_netdevice unregister_netdevice. @@ -11065,13 +11094,6 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, rcu_barrier(); new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); - /* If there is an ifindex conflict assign a new one */ - if (!new_ifindex) { - if (__dev_get_by_index(net, dev->ifindex)) - new_ifindex = dev_new_index(net); - else - new_ifindex = dev->ifindex; - } rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid, new_ifindex); @@ -11249,6 +11271,9 @@ static int __net_init netdev_init(struct net *net) if (net->dev_index_head == NULL) goto err_idx; + net->ifindex = 1; + xa_init_flags(&net->dev_by_index, XA_FLAGS_ALLOC); + RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain); return 0; @@ -11346,6 +11371,7 @@ static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); kfree(net->dev_index_head); + xa_destroy(&net->dev_by_index); if (net != &init_net) WARN_ON_ONCE(!list_empty(&net->dev_base_head)); } -- cgit v1.2.3 From 84e00d9bd4e472bd9b145ed40dbd132dd7a15462 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jul 2023 11:55:30 -0700 Subject: net: convert some netlink netdev iterators to depend on the xarray Reap the benefits of easier iteration thanks to the xarray. Convert just the genetlink ones, those are easier to test. Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230726185530.2247698-3-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 3 ++ net/core/netdev-genl.c | 37 ++++++------------------ net/ethtool/netlink.c | 65 ++++++++++++------------------------------- net/ethtool/tunnels.c | 71 +++++++++++++++++------------------------------ 4 files changed, 54 insertions(+), 122 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 32a4cdf37dd4..84c36a7f873f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3016,6 +3016,9 @@ extern rwlock_t dev_base_lock; /* Device list lock */ if (netdev_master_upper_dev_get_rcu(slave) == (bond)) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) +#define for_each_netdev_dump(net, d, ifindex) \ + xa_for_each_start(&(net)->dev_by_index, (ifindex), (d), (ifindex)) + static inline struct net_device *next_net_device(struct net_device *dev) { struct list_head *lh; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 65ef4867fc49..797c813c7c77 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -101,43 +101,22 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct net_device *netdev; - int idx = 0, s_idx; - int h, s_h; - int err; - - s_h = cb->args[0]; - s_idx = cb->args[1]; + int err = 0; rtnl_lock(); - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - struct hlist_head *head; - - idx = 0; - head = &net->dev_index_head[h]; - hlist_for_each_entry(netdev, head, index_hlist) { - if (idx < s_idx) - goto cont; - err = netdev_nl_dev_fill(netdev, skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - NETDEV_CMD_DEV_GET); - if (err < 0) - break; -cont: - idx++; - } + for_each_netdev_dump(net, netdev, cb->args[0]) { + err = netdev_nl_dev_fill(netdev, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NETDEV_CMD_DEV_GET); + if (err < 0) + break; } - rtnl_unlock(); if (err != -EMSGSIZE) return err; - cb->args[1] = idx; - cb->args[0] = h; - cb->seq = net->dev_base_seq; - return skb->len; } diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 39a459b0111b..ae344f1b0bbd 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -252,8 +252,7 @@ int ethnl_multicast(struct sk_buff *skb, struct net_device *dev) * @ops: request ops of currently processed message type * @req_info: parsed request header of processed request * @reply_data: data needed to compose the reply - * @pos_hash: saved iteration position - hashbucket - * @pos_idx: saved iteration position - index + * @pos_ifindex: saved iteration position - ifindex * * These parameters are kept in struct netlink_callback as context preserved * between iterations. They are initialized by ethnl_default_start() and used @@ -263,8 +262,7 @@ struct ethnl_dump_ctx { const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct ethnl_reply_data *reply_data; - int pos_hash; - int pos_idx; + unsigned long pos_ifindex; }; static const struct ethnl_request_ops * @@ -490,55 +488,27 @@ static int ethnl_default_dumpit(struct sk_buff *skb, { struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); struct net *net = sock_net(skb->sk); - int s_idx = ctx->pos_idx; - int h, idx = 0; + struct net_device *dev; int ret = 0; rtnl_lock(); - for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - struct hlist_head *head; - struct net_device *dev; - unsigned int seq; - - head = &net->dev_index_head[h]; - -restart_chain: - seq = net->dev_base_seq; - cb->seq = seq; - idx = 0; - hlist_for_each_entry(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - dev_hold(dev); - rtnl_unlock(); - - ret = ethnl_default_dump_one(skb, dev, ctx, cb); - dev_put(dev); - if (ret < 0) { - if (ret == -EOPNOTSUPP) - goto lock_and_cont; - if (likely(skb->len)) - ret = skb->len; - goto out; - } -lock_and_cont: - rtnl_lock(); - if (net->dev_base_seq != seq) { - s_idx = idx + 1; - goto restart_chain; - } -cont: - idx++; - } + for_each_netdev_dump(net, dev, ctx->pos_ifindex) { + dev_hold(dev); + rtnl_unlock(); + + ret = ethnl_default_dump_one(skb, dev, ctx, cb); + + rtnl_lock(); + dev_put(dev); + if (ret < 0 && ret != -EOPNOTSUPP) { + if (likely(skb->len)) + ret = skb->len; + break; + } } rtnl_unlock(); -out: - ctx->pos_hash = h; - ctx->pos_idx = idx; - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); - return ret; } @@ -584,8 +554,7 @@ static int ethnl_default_start(struct netlink_callback *cb) ctx->ops = ops; ctx->req_info = req_info; ctx->reply_data = reply_data; - ctx->pos_hash = 0; - ctx->pos_idx = 0; + ctx->pos_ifindex = 0; return 0; diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c index 67fb414ca859..05f752557b5e 100644 --- a/net/ethtool/tunnels.c +++ b/net/ethtool/tunnels.c @@ -212,8 +212,7 @@ err_unlock_rtnl: struct ethnl_tunnel_info_dump_ctx { struct ethnl_req_info req_info; - int pos_hash; - int pos_idx; + unsigned long ifindex; }; int ethnl_tunnel_info_start(struct netlink_callback *cb) @@ -243,57 +242,39 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx; struct net *net = sock_net(skb->sk); - int s_idx = ctx->pos_idx; - int h, idx = 0; + struct net_device *dev; int ret = 0; void *ehdr; rtnl_lock(); - cb->seq = net->dev_base_seq; - for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - struct hlist_head *head; - struct net_device *dev; - - head = &net->dev_index_head[h]; - idx = 0; - hlist_for_each_entry(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - - ehdr = ethnl_dump_put(skb, cb, - ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY); - if (!ehdr) { - ret = -EMSGSIZE; - goto out; - } - - ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_TUNNEL_INFO_HEADER); - if (ret < 0) { - genlmsg_cancel(skb, ehdr); - goto out; - } - - ctx->req_info.dev = dev; - ret = ethnl_tunnel_info_fill_reply(&ctx->req_info, skb); - ctx->req_info.dev = NULL; - if (ret < 0) { - genlmsg_cancel(skb, ehdr); - if (ret == -EOPNOTSUPP) - goto cont; - goto out; - } - genlmsg_end(skb, ehdr); -cont: - idx++; + for_each_netdev_dump(net, dev, ctx->ifindex) { + ehdr = ethnl_dump_put(skb, cb, + ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY); + if (!ehdr) { + ret = -EMSGSIZE; + break; } + + ret = ethnl_fill_reply_header(skb, dev, + ETHTOOL_A_TUNNEL_INFO_HEADER); + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + break; + } + + ctx->req_info.dev = dev; + ret = ethnl_tunnel_info_fill_reply(&ctx->req_info, skb); + ctx->req_info.dev = NULL; + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + if (ret == -EOPNOTSUPP) + continue; + break; + } + genlmsg_end(skb, ehdr); } -out: rtnl_unlock(); - ctx->pos_hash = h; - ctx->pos_idx = idx; - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); - if (ret == -EMSGSIZE && skb->len) return skb->len; return ret; -- cgit v1.2.3 From 5027d54a9c30bc7ec808360378e2b4753f053f25 Mon Sep 17 00:00:00 2001 From: Patrick Rohr Date: Wed, 26 Jul 2023 16:07:01 -0700 Subject: net: change accept_ra_min_rtr_lft to affect all RA lifetimes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit accept_ra_min_rtr_lft only considered the lifetime of the default route and discarded entire RAs accordingly. This change renames accept_ra_min_rtr_lft to accept_ra_min_lft, and applies the value to individual RA sections; in particular, router lifetime, PIO preferred lifetime, and RIO lifetime. If any of those lifetimes are lower than the configured value, the specific RA section is ignored. In order for the sysctl to be useful to Android, it should really apply to all lifetimes in the RA, since that is what determines the minimum frequency at which RAs must be processed by the kernel. Android uses hardware offloads to drop RAs for a fraction of the minimum of all lifetimes present in the RA (some networks have very frequent RAs (5s) with high lifetimes (2h)). Despite this, we have encountered networks that set the router lifetime to 30s which results in very frequent CPU wakeups. Instead of disabling IPv6 (and dropping IPv6 ethertype in the WiFi firmware) entirely on such networks, it seems better to ignore the misconfigured routers while still processing RAs from other IPv6 routers on the same network (i.e. to support IoT applications). The previous implementation dropped the entire RA based on router lifetime. This turned out to be hard to expand to the other lifetimes present in the RA in a consistent manner; dropping the entire RA based on RIO/PIO lifetimes would essentially require parsing the whole thing twice. Fixes: 1671bcfd76fd ("net: add sysctl accept_ra_min_rtr_lft") Cc: Lorenzo Colitti Signed-off-by: Patrick Rohr Reviewed-by: Maciej Å»enczykowski Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230726230701.919212-1-prohr@google.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ip-sysctl.rst | 8 ++++---- include/linux/ipv6.h | 2 +- include/uapi/linux/ipv6.h | 2 +- net/ipv6/addrconf.c | 13 ++++++++----- net/ipv6/ndisc.c | 27 +++++++++++---------------- 5 files changed, 25 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 37603ad6126b..a66054d0763a 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2288,11 +2288,11 @@ accept_ra_min_hop_limit - INTEGER Default: 1 -accept_ra_min_rtr_lft - INTEGER - Minimum acceptable router lifetime in Router Advertisement. +accept_ra_min_lft - INTEGER + Minimum acceptable lifetime value in Router Advertisement. - RAs with a router lifetime less than this value shall be - ignored. RAs with a router lifetime of 0 are unaffected. + RA sections with a lifetime less than this value shall be + ignored. Zero lifetimes stay unaffected. Default: 0 diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 0295b47c10a3..5883551b1ee8 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -33,7 +33,7 @@ struct ipv6_devconf { __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; - __s32 accept_ra_min_rtr_lft; + __s32 accept_ra_min_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 8b6bcbf6ed4a..cf592d7b630f 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -198,7 +198,7 @@ enum { DEVCONF_IOAM6_ID_WIDE, DEVCONF_NDISC_EVICT_NOCARRIER, DEVCONF_ACCEPT_UNTRACKED_NA, - DEVCONF_ACCEPT_RA_MIN_RTR_LFT, + DEVCONF_ACCEPT_RA_MIN_LFT, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5daf6a4986f8..5184bd0ceb12 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -202,7 +202,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, - .accept_ra_min_rtr_lft = 0, + .accept_ra_min_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -263,7 +263,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, - .accept_ra_min_rtr_lft = 0, + .accept_ra_min_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -2741,6 +2741,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) return; } + if (valid_lft != 0 && valid_lft < in6_dev->cnf.accept_ra_min_lft) + return; + /* * Two things going on here: * 1) Add routes for on-link prefixes @@ -5635,7 +5638,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na; - array[DEVCONF_ACCEPT_RA_MIN_RTR_LFT] = cnf->accept_ra_min_rtr_lft; + array[DEVCONF_ACCEPT_RA_MIN_LFT] = cnf->accept_ra_min_lft; } static inline size_t inet6_ifla6_size(void) @@ -6830,8 +6833,8 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, { - .procname = "accept_ra_min_rtr_lft", - .data = &ipv6_devconf.accept_ra_min_rtr_lft, + .procname = "accept_ra_min_lft", + .data = &ipv6_devconf.accept_ra_min_lft, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 95750fbf6782..c394799be38f 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1276,8 +1276,6 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; - lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); - if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, did not accept ra for dev: %s\n", @@ -1285,13 +1283,6 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) goto skip_linkparms; } - if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { - ND_PRINTK(2, info, - "RA: router lifetime (%ds) is too short: %s\n", - lifetime, skb->dev->name); - goto skip_linkparms; - } - #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { @@ -1332,6 +1323,14 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) goto skip_defrtr; } + lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); + if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_lft) { + ND_PRINTK(2, info, + "RA: router lifetime (%ds) is too short: %s\n", + lifetime, skb->dev->name); + goto skip_defrtr; + } + /* Do not accept RA with source-addr found on local machine unless * accept_ra_from_local is set to true. */ @@ -1495,13 +1494,6 @@ skip_linkparms: goto out; } - if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { - ND_PRINTK(2, info, - "RA: router lifetime (%ds) is too short: %s\n", - lifetime, skb->dev->name); - goto out; - } - #ifdef CONFIG_IPV6_ROUTE_INFO if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, @@ -1526,6 +1518,9 @@ skip_linkparms: if (ri->prefix_len == 0 && !in6_dev->cnf.accept_ra_defrtr) continue; + if (ri->lifetime != 0 && + ntohl(ri->lifetime) < in6_dev->cnf.accept_ra_min_lft) + continue; if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen) continue; if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) -- cgit v1.2.3 From 6a7eccef47b205ae66371a26d36dfb2529835075 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 27 Jul 2023 13:35:23 -0400 Subject: net/tls: Move TLS protocol elements to a separate header Kernel TLS consumers will need definitions of various parts of the TLS protocol, but often do not need the function declarations and other infrastructure provided in . Break out existing standardized protocol elements into a separate header, and make room for a few more elements in subsequent patches. Signed-off-by: Chuck Lever Link: https://lore.kernel.org/r/169047931374.5241.7713175865185969309.stgit@oracle-102.nfsv4bat.org Signed-off-by: Jakub Kicinski --- .../ethernet/chelsio/inline_crypto/chtls/chtls.h | 1 + include/net/tls.h | 4 ---- include/net/tls_prot.h | 26 ++++++++++++++++++++++ net/sunrpc/svcsock.c | 1 + net/sunrpc/xprtsock.c | 1 + net/tls/tls.h | 1 + 6 files changed, 30 insertions(+), 4 deletions(-) create mode 100644 include/net/tls_prot.h (limited to 'include') diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h index 68562a82d036..62f62bff74a5 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h @@ -22,6 +22,7 @@ #include #include #include +#include #include #include "t4fw_api.h" diff --git a/include/net/tls.h b/include/net/tls.h index 5e71dd3df8ca..06fca9160346 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -69,10 +69,6 @@ extern const struct tls_cipher_size_desc tls_cipher_size_desc[]; #define TLS_CRYPTO_INFO_READY(info) ((info)->cipher_type) -#define TLS_RECORD_TYPE_ALERT 0x15 -#define TLS_RECORD_TYPE_HANDSHAKE 0x16 -#define TLS_RECORD_TYPE_DATA 0x17 - #define TLS_AAD_SPACE_SIZE 13 #define MAX_IV_SIZE 16 diff --git a/include/net/tls_prot.h b/include/net/tls_prot.h new file mode 100644 index 000000000000..47d6cfd1619e --- /dev/null +++ b/include/net/tls_prot.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* + * Copyright (c) 2023, Oracle and/or its affiliates. + * + * TLS Protocol definitions + * + * From https://www.iana.org/assignments/tls-parameters/tls-parameters.xhtml + */ + +#ifndef _TLS_PROT_H +#define _TLS_PROT_H + +/* + * TLS Record protocol: ContentType + */ +enum { + TLS_RECORD_TYPE_CHANGE_CIPHER_SPEC = 20, + TLS_RECORD_TYPE_ALERT = 21, + TLS_RECORD_TYPE_HANDSHAKE = 22, + TLS_RECORD_TYPE_DATA = 23, + TLS_RECORD_TYPE_HEARTBEAT = 24, + TLS_RECORD_TYPE_TLS12_CID = 25, + TLS_RECORD_TYPE_ACK = 26, +}; + +#endif /* _TLS_PROT_H */ diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index e43f26382411..449df8cabfcb 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include #include diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9f010369100a..9457ebf22fb1 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include diff --git a/net/tls/tls.h b/net/tls/tls.h index 86cef1c68e03..26a0358f6f49 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -39,6 +39,7 @@ #include #include #include +#include #define TLS_PAGE_ORDER (min_t(unsigned int, PAGE_ALLOC_COSTLY_ORDER, \ TLS_MAX_PAYLOAD_SIZE >> PAGE_SHIFT)) -- cgit v1.2.3 From 0257427146e84af365612508ace9d0d87dfb7d7a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 27 Jul 2023 13:35:50 -0400 Subject: net/tls: Add TLS Alert definitions I'm about to add support for kernel handshake API consumers to send TLS Alerts, so introduce the needed protocol definitions in the new header tls_prot.h. This presages support for Closure alerts. Also, support for alerts is a pre-requite for handling session re-keying, where one peer will signal the need for a re-key by sending a TLS Alert. Reviewed-by: Hannes Reinecke Signed-off-by: Chuck Lever Link: https://lore.kernel.org/r/169047934064.5241.8377890858495063518.stgit@oracle-102.nfsv4bat.org Signed-off-by: Jakub Kicinski --- include/net/tls_prot.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'include') diff --git a/include/net/tls_prot.h b/include/net/tls_prot.h index 47d6cfd1619e..68a40756440b 100644 --- a/include/net/tls_prot.h +++ b/include/net/tls_prot.h @@ -23,4 +23,46 @@ enum { TLS_RECORD_TYPE_ACK = 26, }; +/* + * TLS Alert protocol: AlertLevel + */ +enum { + TLS_ALERT_LEVEL_WARNING = 1, + TLS_ALERT_LEVEL_FATAL = 2, +}; + +/* + * TLS Alert protocol: AlertDescription + */ +enum { + TLS_ALERT_DESC_CLOSE_NOTIFY = 0, + TLS_ALERT_DESC_UNEXPECTED_MESSAGE = 10, + TLS_ALERT_DESC_BAD_RECORD_MAC = 20, + TLS_ALERT_DESC_RECORD_OVERFLOW = 22, + TLS_ALERT_DESC_HANDSHAKE_FAILURE = 40, + TLS_ALERT_DESC_BAD_CERTIFICATE = 42, + TLS_ALERT_DESC_UNSUPPORTED_CERTIFICATE = 43, + TLS_ALERT_DESC_CERTIFICATE_REVOKED = 44, + TLS_ALERT_DESC_CERTIFICATE_EXPIRED = 45, + TLS_ALERT_DESC_CERTIFICATE_UNKNOWN = 46, + TLS_ALERT_DESC_ILLEGAL_PARAMETER = 47, + TLS_ALERT_DESC_UNKNOWN_CA = 48, + TLS_ALERT_DESC_ACCESS_DENIED = 49, + TLS_ALERT_DESC_DECODE_ERROR = 50, + TLS_ALERT_DESC_DECRYPT_ERROR = 51, + TLS_ALERT_DESC_TOO_MANY_CIDS_REQUESTED = 52, + TLS_ALERT_DESC_PROTOCOL_VERSION = 70, + TLS_ALERT_DESC_INSUFFICIENT_SECURITY = 71, + TLS_ALERT_DESC_INTERNAL_ERROR = 80, + TLS_ALERT_DESC_INAPPROPRIATE_FALLBACK = 86, + TLS_ALERT_DESC_USER_CANCELED = 90, + TLS_ALERT_DESC_MISSING_EXTENSION = 109, + TLS_ALERT_DESC_UNSUPPORTED_EXTENSION = 110, + TLS_ALERT_DESC_UNRECOGNIZED_NAME = 112, + TLS_ALERT_DESC_BAD_CERTIFICATE_STATUS_RESPONSE = 113, + TLS_ALERT_DESC_UNKNOWN_PSK_IDENTITY = 115, + TLS_ALERT_DESC_CERTIFICATE_REQUIRED = 116, + TLS_ALERT_DESC_NO_APPLICATION_PROTOCOL = 120, +}; + #endif /* _TLS_PROT_H */ -- cgit v1.2.3 From 35b1b538d422fd765d88fbdaaa6e06ee466d9f93 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 27 Jul 2023 13:36:17 -0400 Subject: net/handshake: Add API for sending TLS Closure alerts This helper sends an alert only if a TLS session was established. Signed-off-by: Chuck Lever Link: https://lore.kernel.org/r/169047936730.5241.618595693821012638.stgit@oracle-102.nfsv4bat.org Signed-off-by: Jakub Kicinski --- include/net/handshake.h | 1 + net/handshake/Makefile | 2 +- net/handshake/alert.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++ net/handshake/handshake.h | 6 +++++ net/handshake/tlshd.c | 23 ++++++++++++++++++ 5 files changed, 92 insertions(+), 1 deletion(-) create mode 100644 net/handshake/alert.c (limited to 'include') diff --git a/include/net/handshake.h b/include/net/handshake.h index 2e26e436e85f..bb88dfa6e3c9 100644 --- a/include/net/handshake.h +++ b/include/net/handshake.h @@ -40,5 +40,6 @@ int tls_server_hello_x509(const struct tls_handshake_args *args, gfp_t flags); int tls_server_hello_psk(const struct tls_handshake_args *args, gfp_t flags); bool tls_handshake_cancel(struct sock *sk); +void tls_handshake_close(struct socket *sock); #endif /* _NET_HANDSHAKE_H */ diff --git a/net/handshake/Makefile b/net/handshake/Makefile index 247d73c6ff6e..ef4d9a2112bd 100644 --- a/net/handshake/Makefile +++ b/net/handshake/Makefile @@ -8,6 +8,6 @@ # obj-y += handshake.o -handshake-y := genl.o netlink.o request.o tlshd.o trace.o +handshake-y := alert.o genl.o netlink.o request.o tlshd.o trace.o obj-$(CONFIG_NET_HANDSHAKE_KUNIT_TEST) += handshake-test.o diff --git a/net/handshake/alert.c b/net/handshake/alert.c new file mode 100644 index 000000000000..2f1a16868ff6 --- /dev/null +++ b/net/handshake/alert.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Handle the TLS Alert protocol + * + * Author: Chuck Lever + * + * Copyright (c) 2023, Oracle and/or its affiliates. + */ + +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#include "handshake.h" + +/** + * tls_alert_send - send a TLS Alert on a kTLS socket + * @sock: open kTLS socket to send on + * @level: TLS Alert level + * @description: TLS Alert description + * + * Returns zero on success or a negative errno. + */ +int tls_alert_send(struct socket *sock, u8 level, u8 description) +{ + u8 record_type = TLS_RECORD_TYPE_ALERT; + u8 buf[CMSG_SPACE(sizeof(record_type))]; + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct kvec iov; + u8 alert[2]; + int ret; + + alert[0] = level; + alert[1] = description; + iov.iov_base = alert; + iov.iov_len = sizeof(alert); + + memset(buf, 0, sizeof(buf)); + msg.msg_control = buf; + msg.msg_controllen = sizeof(buf); + msg.msg_flags = MSG_DONTWAIT; + + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_TLS; + cmsg->cmsg_type = TLS_SET_RECORD_TYPE; + cmsg->cmsg_len = CMSG_LEN(sizeof(record_type)); + memcpy(CMSG_DATA(cmsg), &record_type, sizeof(record_type)); + + iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, iov.iov_len); + ret = sock_sendmsg(sock, &msg); + return ret < 0 ? ret : 0; +} diff --git a/net/handshake/handshake.h b/net/handshake/handshake.h index 4dac965c99df..a48163765a7a 100644 --- a/net/handshake/handshake.h +++ b/net/handshake/handshake.h @@ -41,8 +41,11 @@ struct handshake_req { enum hr_flags_bits { HANDSHAKE_F_REQ_COMPLETED, + HANDSHAKE_F_REQ_SESSION, }; +struct genl_info; + /* Invariants for all handshake requests for one transport layer * security protocol */ @@ -63,6 +66,9 @@ enum hp_flags_bits { HANDSHAKE_F_PROTO_NOTIFY, }; +/* alert.c */ +int tls_alert_send(struct socket *sock, u8 level, u8 description); + /* netlink.c */ int handshake_genl_notify(struct net *net, const struct handshake_proto *proto, gfp_t flags); diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c index b735f5cced2f..bbfb4095ddd6 100644 --- a/net/handshake/tlshd.c +++ b/net/handshake/tlshd.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -100,6 +101,9 @@ static void tls_handshake_done(struct handshake_req *req, if (info) tls_handshake_remote_peerids(treq, info); + if (!status) + set_bit(HANDSHAKE_F_REQ_SESSION, &req->hr_flags); + treq->th_consumer_done(treq->th_consumer_data, -status, treq->th_peerid[0]); } @@ -424,3 +428,22 @@ bool tls_handshake_cancel(struct sock *sk) return handshake_req_cancel(sk); } EXPORT_SYMBOL(tls_handshake_cancel); + +/** + * tls_handshake_close - send a Closure alert + * @sock: an open socket + * + */ +void tls_handshake_close(struct socket *sock) +{ + struct handshake_req *req; + + req = handshake_req_hash_lookup(sock->sk); + if (!req) + return; + if (!test_and_clear_bit(HANDSHAKE_F_REQ_SESSION, &req->hr_flags)) + return; + tls_alert_send(sock, TLS_ALERT_LEVEL_WARNING, + TLS_ALERT_DESC_CLOSE_NOTIFY); +} +EXPORT_SYMBOL(tls_handshake_close); -- cgit v1.2.3 From 39d0e38dcced8d4da92cd11f3ff618bacc42d8a9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 27 Jul 2023 13:37:10 -0400 Subject: net/handshake: Add helpers for parsing incoming TLS Alerts Kernel TLS consumers can replace common TLS Alert parsing code with these helpers. Signed-off-by: Chuck Lever Link: https://lore.kernel.org/r/169047942074.5241.13791647439480672048.stgit@oracle-102.nfsv4bat.org Signed-off-by: Jakub Kicinski --- include/net/handshake.h | 4 ++++ net/handshake/alert.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+) (limited to 'include') diff --git a/include/net/handshake.h b/include/net/handshake.h index bb88dfa6e3c9..8ebd4f9ed26e 100644 --- a/include/net/handshake.h +++ b/include/net/handshake.h @@ -42,4 +42,8 @@ int tls_server_hello_psk(const struct tls_handshake_args *args, gfp_t flags); bool tls_handshake_cancel(struct sock *sk); void tls_handshake_close(struct socket *sock); +u8 tls_get_record_type(const struct sock *sk, const struct cmsghdr *msg); +void tls_alert_recv(const struct sock *sk, const struct msghdr *msg, + u8 *level, u8 *description); + #endif /* _NET_HANDSHAKE_H */ diff --git a/net/handshake/alert.c b/net/handshake/alert.c index 2f1a16868ff6..286bf94d93a3 100644 --- a/net/handshake/alert.c +++ b/net/handshake/alert.c @@ -59,3 +59,45 @@ int tls_alert_send(struct socket *sock, u8 level, u8 description) ret = sock_sendmsg(sock, &msg); return ret < 0 ? ret : 0; } + +/** + * tls_get_record_type - Look for TLS RECORD_TYPE information + * @sk: socket (for IP address information) + * @cmsg: incoming message to be parsed + * + * Returns zero or a TLS_RECORD_TYPE value. + */ +u8 tls_get_record_type(const struct sock *sk, const struct cmsghdr *cmsg) +{ + u8 record_type; + + if (cmsg->cmsg_level != SOL_TLS) + return 0; + if (cmsg->cmsg_type != TLS_GET_RECORD_TYPE) + return 0; + + record_type = *((u8 *)CMSG_DATA(cmsg)); + return record_type; +} +EXPORT_SYMBOL(tls_get_record_type); + +/** + * tls_alert_recv - Parse TLS Alert messages + * @sk: socket (for IP address information) + * @msg: incoming message to be parsed + * @level: OUT - TLS AlertLevel value + * @description: OUT - TLS AlertDescription value + * + */ +void tls_alert_recv(const struct sock *sk, const struct msghdr *msg, + u8 *level, u8 *description) +{ + const struct kvec *iov; + u8 *data; + + iov = msg->msg_iter.kvec; + data = iov->iov_base; + *level = data[0]; + *description = data[1]; +} +EXPORT_SYMBOL(tls_alert_recv); -- cgit v1.2.3 From b470985c76df6d53a9454670fb7551e1197f55e2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 27 Jul 2023 13:38:04 -0400 Subject: net/handshake: Trace events for TLS Alert helpers Add observability for the new TLS Alert infrastructure. Reviewed-by: Hannes Reinecke Signed-off-by: Chuck Lever Link: https://lore.kernel.org/r/169047947409.5241.14548832149596892717.stgit@oracle-102.nfsv4bat.org Signed-off-by: Jakub Kicinski --- include/trace/events/handshake.h | 160 +++++++++++++++++++++++++++++++++++++++ net/handshake/alert.c | 7 ++ net/handshake/trace.c | 2 + 3 files changed, 169 insertions(+) (limited to 'include') diff --git a/include/trace/events/handshake.h b/include/trace/events/handshake.h index 8dadcab5f12a..bdd8a03cf5ba 100644 --- a/include/trace/events/handshake.h +++ b/include/trace/events/handshake.h @@ -6,7 +6,86 @@ #define _TRACE_HANDSHAKE_H #include +#include #include +#include + +#define TLS_RECORD_TYPE_LIST \ + record_type(CHANGE_CIPHER_SPEC) \ + record_type(ALERT) \ + record_type(HANDSHAKE) \ + record_type(DATA) \ + record_type(HEARTBEAT) \ + record_type(TLS12_CID) \ + record_type_end(ACK) + +#undef record_type +#undef record_type_end +#define record_type(x) TRACE_DEFINE_ENUM(TLS_RECORD_TYPE_##x); +#define record_type_end(x) TRACE_DEFINE_ENUM(TLS_RECORD_TYPE_##x); + +TLS_RECORD_TYPE_LIST + +#undef record_type +#undef record_type_end +#define record_type(x) { TLS_RECORD_TYPE_##x, #x }, +#define record_type_end(x) { TLS_RECORD_TYPE_##x, #x } + +#define show_tls_content_type(type) \ + __print_symbolic(type, TLS_RECORD_TYPE_LIST) + +TRACE_DEFINE_ENUM(TLS_ALERT_LEVEL_WARNING); +TRACE_DEFINE_ENUM(TLS_ALERT_LEVEL_FATAL); + +#define show_tls_alert_level(level) \ + __print_symbolic(level, \ + { TLS_ALERT_LEVEL_WARNING, "Warning" }, \ + { TLS_ALERT_LEVEL_FATAL, "Fatal" }) + +#define TLS_ALERT_DESCRIPTION_LIST \ + alert_description(CLOSE_NOTIFY) \ + alert_description(UNEXPECTED_MESSAGE) \ + alert_description(BAD_RECORD_MAC) \ + alert_description(RECORD_OVERFLOW) \ + alert_description(HANDSHAKE_FAILURE) \ + alert_description(BAD_CERTIFICATE) \ + alert_description(UNSUPPORTED_CERTIFICATE) \ + alert_description(CERTIFICATE_REVOKED) \ + alert_description(CERTIFICATE_EXPIRED) \ + alert_description(CERTIFICATE_UNKNOWN) \ + alert_description(ILLEGAL_PARAMETER) \ + alert_description(UNKNOWN_CA) \ + alert_description(ACCESS_DENIED) \ + alert_description(DECODE_ERROR) \ + alert_description(DECRYPT_ERROR) \ + alert_description(TOO_MANY_CIDS_REQUESTED) \ + alert_description(PROTOCOL_VERSION) \ + alert_description(INSUFFICIENT_SECURITY) \ + alert_description(INTERNAL_ERROR) \ + alert_description(INAPPROPRIATE_FALLBACK) \ + alert_description(USER_CANCELED) \ + alert_description(MISSING_EXTENSION) \ + alert_description(UNSUPPORTED_EXTENSION) \ + alert_description(UNRECOGNIZED_NAME) \ + alert_description(BAD_CERTIFICATE_STATUS_RESPONSE) \ + alert_description(UNKNOWN_PSK_IDENTITY) \ + alert_description(CERTIFICATE_REQUIRED) \ + alert_description_end(NO_APPLICATION_PROTOCOL) + +#undef alert_description +#undef alert_description_end +#define alert_description(x) TRACE_DEFINE_ENUM(TLS_ALERT_DESC_##x); +#define alert_description_end(x) TRACE_DEFINE_ENUM(TLS_ALERT_DESC_##x); + +TLS_ALERT_DESCRIPTION_LIST + +#undef alert_description +#undef alert_description_end +#define alert_description(x) { TLS_ALERT_DESC_##x, #x }, +#define alert_description_end(x) { TLS_ALERT_DESC_##x, #x } + +#define show_tls_alert_description(desc) \ + __print_symbolic(desc, TLS_ALERT_DESCRIPTION_LIST) DECLARE_EVENT_CLASS(handshake_event_class, TP_PROTO( @@ -106,6 +185,47 @@ DECLARE_EVENT_CLASS(handshake_error_class, ), \ TP_ARGS(net, req, sk, err)) +DECLARE_EVENT_CLASS(handshake_alert_class, + TP_PROTO( + const struct sock *sk, + unsigned char level, + unsigned char description + ), + TP_ARGS(sk, level, description), + TP_STRUCT__entry( + /* sockaddr_in6 is always bigger than sockaddr_in */ + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) + __field(unsigned int, netns_ino) + __field(unsigned long, level) + __field(unsigned long, description) + ), + TP_fast_assign( + const struct inet_sock *inet = inet_sk(sk); + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + TP_STORE_ADDR_PORTS(__entry, inet, sk); + + __entry->netns_ino = sock_net(sk)->ns.inum; + __entry->level = level; + __entry->description = description; + ), + TP_printk("src=%pISpc dest=%pISpc %s: %s", + __entry->saddr, __entry->daddr, + show_tls_alert_level(__entry->level), + show_tls_alert_description(__entry->description) + ) +); +#define DEFINE_HANDSHAKE_ALERT(name) \ + DEFINE_EVENT(handshake_alert_class, name, \ + TP_PROTO( \ + const struct sock *sk, \ + unsigned char level, \ + unsigned char description \ + ), \ + TP_ARGS(sk, level, description)) + /* * Request lifetime events @@ -154,6 +274,46 @@ DEFINE_HANDSHAKE_ERROR(handshake_cmd_accept_err); DEFINE_HANDSHAKE_FD_EVENT(handshake_cmd_done); DEFINE_HANDSHAKE_ERROR(handshake_cmd_done_err); +/* + * TLS Record events + */ + +TRACE_EVENT(tls_contenttype, + TP_PROTO( + const struct sock *sk, + unsigned char type + ), + TP_ARGS(sk, type), + TP_STRUCT__entry( + /* sockaddr_in6 is always bigger than sockaddr_in */ + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) + __field(unsigned int, netns_ino) + __field(unsigned long, type) + ), + TP_fast_assign( + const struct inet_sock *inet = inet_sk(sk); + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + TP_STORE_ADDR_PORTS(__entry, inet, sk); + + __entry->netns_ino = sock_net(sk)->ns.inum; + __entry->type = type; + ), + TP_printk("src=%pISpc dest=%pISpc %s", + __entry->saddr, __entry->daddr, + show_tls_content_type(__entry->type) + ) +); + +/* + * TLS Alert events + */ + +DEFINE_HANDSHAKE_ALERT(tls_alert_send); +DEFINE_HANDSHAKE_ALERT(tls_alert_recv); + #endif /* _TRACE_HANDSHAKE_H */ #include diff --git a/net/handshake/alert.c b/net/handshake/alert.c index 286bf94d93a3..329d91984683 100644 --- a/net/handshake/alert.c +++ b/net/handshake/alert.c @@ -21,6 +21,8 @@ #include "handshake.h" +#include + /** * tls_alert_send - send a TLS Alert on a kTLS socket * @sock: open kTLS socket to send on @@ -39,6 +41,8 @@ int tls_alert_send(struct socket *sock, u8 level, u8 description) u8 alert[2]; int ret; + trace_tls_alert_send(sock->sk, level, description); + alert[0] = level; alert[1] = description; iov.iov_base = alert; @@ -77,6 +81,7 @@ u8 tls_get_record_type(const struct sock *sk, const struct cmsghdr *cmsg) return 0; record_type = *((u8 *)CMSG_DATA(cmsg)); + trace_tls_contenttype(sk, record_type); return record_type; } EXPORT_SYMBOL(tls_get_record_type); @@ -99,5 +104,7 @@ void tls_alert_recv(const struct sock *sk, const struct msghdr *msg, data = iov->iov_base; *level = data[0]; *description = data[1]; + + trace_tls_alert_recv(sk, *level, *description); } EXPORT_SYMBOL(tls_alert_recv); diff --git a/net/handshake/trace.c b/net/handshake/trace.c index 1c4d8e27e17a..44432d0857b9 100644 --- a/net/handshake/trace.c +++ b/net/handshake/trace.c @@ -8,8 +8,10 @@ */ #include +#include #include +#include #include #include -- cgit v1.2.3 From 9abddac583d68e16258d5e0b95dc1b3ca1886173 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Fri, 21 Jul 2023 14:22:45 -0600 Subject: netfilter: defrag: Add glue hooks for enabling/disabling defrag We want to be able to enable/disable IP packet defrag from core bpf/netfilter code. In other words, execute code from core that could possibly be built as a module. To help avoid symbol resolution errors, use glue hooks that the modules will register callbacks with during module init. Signed-off-by: Daniel Xu Reviewed-by: Florian Westphal Link: https://lore.kernel.org/r/f6a8824052441b72afe5285acedbd634bd3384c1.1689970773.git.dxu@dxuuu.xyz Signed-off-by: Alexei Starovoitov --- include/linux/netfilter.h | 10 ++++++++++ net/ipv4/netfilter/nf_defrag_ipv4.c | 17 ++++++++++++++++- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 11 +++++++++++ net/netfilter/core.c | 6 ++++++ 4 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d4fed4c508ca..d68644b7c299 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -481,6 +482,15 @@ struct nfnl_ct_hook { }; extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; +struct nf_defrag_hook { + struct module *owner; + int (*enable)(struct net *net); + void (*disable)(struct net *net); +}; + +extern const struct nf_defrag_hook __rcu *nf_defrag_v4_hook; +extern const struct nf_defrag_hook __rcu *nf_defrag_v6_hook; + /* * nf_skb_duplicated - TEE target has sent a packet * diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index e61ea428ea18..a9ba7de092c4 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -113,17 +114,31 @@ static void __net_exit defrag4_net_exit(struct net *net) } } +static const struct nf_defrag_hook defrag_hook = { + .owner = THIS_MODULE, + .enable = nf_defrag_ipv4_enable, + .disable = nf_defrag_ipv4_disable, +}; + static struct pernet_operations defrag4_net_ops = { .exit = defrag4_net_exit, }; static int __init nf_defrag_init(void) { - return register_pernet_subsys(&defrag4_net_ops); + int err; + + err = register_pernet_subsys(&defrag4_net_ops); + if (err) + return err; + + rcu_assign_pointer(nf_defrag_v4_hook, &defrag_hook); + return err; } static void __exit nf_defrag_fini(void) { + rcu_assign_pointer(nf_defrag_v4_hook, NULL); unregister_pernet_subsys(&defrag4_net_ops); } diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index cb4eb1d2c620..d59b296b4f51 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -96,6 +97,12 @@ static void __net_exit defrag6_net_exit(struct net *net) } } +static const struct nf_defrag_hook defrag_hook = { + .owner = THIS_MODULE, + .enable = nf_defrag_ipv6_enable, + .disable = nf_defrag_ipv6_disable, +}; + static struct pernet_operations defrag6_net_ops = { .exit = defrag6_net_exit, }; @@ -114,6 +121,9 @@ static int __init nf_defrag_init(void) pr_err("nf_defrag_ipv6: can't register pernet ops\n"); goto cleanup_frag6; } + + rcu_assign_pointer(nf_defrag_v6_hook, &defrag_hook); + return ret; cleanup_frag6: @@ -124,6 +134,7 @@ cleanup_frag6: static void __exit nf_defrag_fini(void) { + rcu_assign_pointer(nf_defrag_v6_hook, NULL); unregister_pernet_subsys(&defrag6_net_ops); nf_ct_frag6_cleanup(); } diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 5f76ae86a656..ef4e76e5aef9 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -680,6 +680,12 @@ EXPORT_SYMBOL_GPL(nfnl_ct_hook); const struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_hook); +const struct nf_defrag_hook __rcu *nf_defrag_v4_hook __read_mostly; +EXPORT_SYMBOL_GPL(nf_defrag_v4_hook); + +const struct nf_defrag_hook __rcu *nf_defrag_v6_hook __read_mostly; +EXPORT_SYMBOL_GPL(nf_defrag_v6_hook); + #if IS_ENABLED(CONFIG_NF_CONNTRACK) u8 nf_ctnetlink_has_listener; EXPORT_SYMBOL_GPL(nf_ctnetlink_has_listener); -- cgit v1.2.3 From 91721c2d02d3a0141df8a4787c7079b89b0d0607 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Fri, 21 Jul 2023 14:22:46 -0600 Subject: netfilter: bpf: Support BPF_F_NETFILTER_IP_DEFRAG in netfilter link This commit adds support for enabling IP defrag using pre-existing netfilter defrag support. Basically all the flag does is bump a refcnt while the link the active. Checks are also added to ensure the prog requesting defrag support is run _after_ netfilter defrag hooks. We also take care to avoid any issues w.r.t. module unloading -- while defrag is active on a link, the module is prevented from unloading. Signed-off-by: Daniel Xu Reviewed-by: Florian Westphal Link: https://lore.kernel.org/r/5cff26f97e55161b7d56b09ddcf5f8888a5add1d.1689970773.git.dxu@dxuuu.xyz Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 5 ++ net/netfilter/nf_bpf_link.c | 123 ++++++++++++++++++++++++++++++++++++----- tools/include/uapi/linux/bpf.h | 5 ++ 3 files changed, 118 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 14fd26b09e4b..70da85200695 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1188,6 +1188,11 @@ enum bpf_perf_event_type { */ #define BPF_F_KPROBE_MULTI_RETURN (1U << 0) +/* link_create.netfilter.flags used in LINK_CREATE command for + * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation. + */ +#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index c36da56d756f..8fe594bbc7e2 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include +#include #include #include @@ -23,8 +25,88 @@ struct bpf_nf_link { struct nf_hook_ops hook_ops; struct net *net; u32 dead; + const struct nf_defrag_hook *defrag_hook; }; +static const struct nf_defrag_hook * +get_proto_defrag_hook(struct bpf_nf_link *link, + const struct nf_defrag_hook __rcu *global_hook, + const char *mod) +{ + const struct nf_defrag_hook *hook; + int err; + + /* RCU protects us from races against module unloading */ + rcu_read_lock(); + hook = rcu_dereference(global_hook); + if (!hook) { + rcu_read_unlock(); + err = request_module(mod); + if (err) + return ERR_PTR(err < 0 ? err : -EINVAL); + + rcu_read_lock(); + hook = rcu_dereference(global_hook); + } + + if (hook && try_module_get(hook->owner)) { + /* Once we have a refcnt on the module, we no longer need RCU */ + hook = rcu_pointer_handoff(hook); + } else { + WARN_ONCE(!hook, "%s has bad registration", mod); + hook = ERR_PTR(-ENOENT); + } + rcu_read_unlock(); + + if (!IS_ERR(hook)) { + err = hook->enable(link->net); + if (err) { + module_put(hook->owner); + hook = ERR_PTR(err); + } + } + + return hook; +} + +static int bpf_nf_enable_defrag(struct bpf_nf_link *link) +{ + const struct nf_defrag_hook __maybe_unused *hook; + + switch (link->hook_ops.pf) { +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) + case NFPROTO_IPV4: + hook = get_proto_defrag_hook(link, nf_defrag_v4_hook, "nf_defrag_ipv4"); + if (IS_ERR(hook)) + return PTR_ERR(hook); + + link->defrag_hook = hook; + return 0; +#endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + case NFPROTO_IPV6: + hook = get_proto_defrag_hook(link, nf_defrag_v6_hook, "nf_defrag_ipv6"); + if (IS_ERR(hook)) + return PTR_ERR(hook); + + link->defrag_hook = hook; + return 0; +#endif + default: + return -EAFNOSUPPORT; + } +} + +static void bpf_nf_disable_defrag(struct bpf_nf_link *link) +{ + const struct nf_defrag_hook *hook = link->defrag_hook; + + if (!hook) + return; + hook->disable(link->net); + module_put(hook->owner); +} + static void bpf_nf_link_release(struct bpf_link *link) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); @@ -32,11 +114,11 @@ static void bpf_nf_link_release(struct bpf_link *link) if (nf_link->dead) return; - /* prevent hook-not-found warning splat from netfilter core when - * .detach was already called - */ - if (!cmpxchg(&nf_link->dead, 0, 1)) + /* do not double release in case .detach was already called */ + if (!cmpxchg(&nf_link->dead, 0, 1)) { nf_unregister_net_hook(nf_link->net, &nf_link->hook_ops); + bpf_nf_disable_defrag(nf_link); + } } static void bpf_nf_link_dealloc(struct bpf_link *link) @@ -92,6 +174,8 @@ static const struct bpf_link_ops bpf_nf_link_lops = { static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr) { + int prio; + switch (attr->link_create.netfilter.pf) { case NFPROTO_IPV4: case NFPROTO_IPV6: @@ -102,19 +186,18 @@ static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr) return -EAFNOSUPPORT; } - if (attr->link_create.netfilter.flags) + if (attr->link_create.netfilter.flags & ~BPF_F_NETFILTER_IP_DEFRAG) return -EOPNOTSUPP; - /* make sure conntrack confirm is always last. - * - * In the future, if userspace can e.g. request defrag, then - * "defrag_requested && prio before NF_IP_PRI_CONNTRACK_DEFRAG" - * should fail. - */ - switch (attr->link_create.netfilter.priority) { - case NF_IP_PRI_FIRST: return -ERANGE; /* sabotage_in and other warts */ - case NF_IP_PRI_LAST: return -ERANGE; /* e.g. conntrack confirm */ - } + /* make sure conntrack confirm is always last */ + prio = attr->link_create.netfilter.priority; + if (prio == NF_IP_PRI_FIRST) + return -ERANGE; /* sabotage_in and other warts */ + else if (prio == NF_IP_PRI_LAST) + return -ERANGE; /* e.g. conntrack confirm */ + else if ((attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) && + prio <= NF_IP_PRI_CONNTRACK_DEFRAG) + return -ERANGE; /* cannot use defrag if prog runs before nf_defrag */ return 0; } @@ -149,6 +232,7 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) link->net = net; link->dead = false; + link->defrag_hook = NULL; err = bpf_link_prime(&link->link, &link_primer); if (err) { @@ -156,8 +240,17 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) return err; } + if (attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) { + err = bpf_nf_enable_defrag(link); + if (err) { + bpf_link_cleanup(&link_primer); + return err; + } + } + err = nf_register_net_hook(net, &link->hook_ops); if (err) { + bpf_nf_disable_defrag(link); bpf_link_cleanup(&link_primer); return err; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 14fd26b09e4b..70da85200695 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1188,6 +1188,11 @@ enum bpf_perf_event_type { */ #define BPF_F_KPROBE_MULTI_RETURN (1U << 0) +/* link_create.netfilter.flags used in LINK_CREATE command for + * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation. + */ +#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * -- cgit v1.2.3 From 61c5145317a23b3ee03d3aa01d46df57d75e4dee Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 26 Jul 2023 22:38:16 +0800 Subject: bonding: 3ad: Remove unused declaration bond_3ad_update_lacp_active() This is not used since commit 3a755cd8b7c6 ("bonding: add new option lacp_active") Signed-off-by: YueHaibing Acked-by: Hangbin Liu Link: https://lore.kernel.org/r/20230726143816.15280-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/bond_3ad.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index a016f275cb01..c5e57c6bd873 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -301,7 +301,6 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond, int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); int bond_3ad_set_carrier(struct bonding *bond); -void bond_3ad_update_lacp_active(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); void bond_3ad_update_ad_actor_settings(struct bonding *bond); int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats); -- cgit v1.2.3 From 2b3082c6ef3b0104d822f6f18d2afbe5fc9a5c2c Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Sat, 29 Jul 2023 04:52:15 +0530 Subject: net: flow_dissector: Use 64bits for used_keys As 32bits of dissector->used_keys are exhausted, increase the size to 64bits. This is base change for ESP/AH flow dissector patch. Please find patch and discussions at https://lore.kernel.org/netdev/ZMDNjD46BvZ5zp5I@corigine.com/T/#t Signed-off-by: Ratheesh Kannoth Reviewed-by: Petr Machata # for mlxsw Tested-by: Petr Machata Reviewed-by: Martin Habets Reviewed-by: Simon Horman Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix_vsc9959.c | 8 +-- drivers/net/dsa/sja1105/sja1105_flower.c | 8 +-- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 6 +- .../net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 18 +++--- .../ethernet/freescale/dpaa2/dpaa2-switch-flower.c | 22 +++---- drivers/net/ethernet/freescale/enetc/enetc_qos.c | 8 +-- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 16 +++--- drivers/net/ethernet/intel/i40e/i40e_main.c | 18 +++--- drivers/net/ethernet/intel/iavf/iavf_main.c | 18 +++--- drivers/net/ethernet/intel/ice/ice_tc_lib.c | 44 +++++++------- drivers/net/ethernet/intel/igb/igb_main.c | 8 +-- .../net/ethernet/marvell/octeontx2/nic/otx2_tc.c | 18 +++--- .../ethernet/marvell/prestera/prestera_flower.c | 20 +++---- .../ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c | 25 ++++---- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 44 +++++++------- .../net/ethernet/mellanox/mlxsw/spectrum_flower.c | 22 +++---- .../ethernet/microchip/lan966x/lan966x_tc_flower.c | 4 +- .../ethernet/microchip/sparx5/sparx5_tc_flower.c | 4 +- drivers/net/ethernet/microchip/vcap/vcap_tc.c | 18 +++--- drivers/net/ethernet/microchip/vcap/vcap_tc.h | 2 +- drivers/net/ethernet/mscc/ocelot_flower.c | 28 ++++----- .../net/ethernet/netronome/nfp/flower/conntrack.c | 43 +++++++------- .../net/ethernet/netronome/nfp/flower/offload.c | 64 ++++++++++----------- drivers/net/ethernet/qlogic/qede/qede_filter.c | 12 ++-- drivers/net/ethernet/sfc/tc.c | 67 +++++++++++----------- .../net/ethernet/stmicro/stmmac/stmmac_selftests.c | 6 +- drivers/net/ethernet/ti/am65-cpsw-qos.c | 6 +- drivers/net/ethernet/ti/cpsw_priv.c | 6 +- include/net/flow_dissector.h | 5 +- net/core/flow_dissector.c | 2 +- net/ethtool/ioctl.c | 16 +++--- net/netfilter/nf_flow_table_offload.c | 22 +++---- net/netfilter/nf_tables_offload.c | 13 +++-- net/netfilter/nft_cmp.c | 2 +- 34 files changed, 317 insertions(+), 306 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index dce3548dcd05..4a6e52929d25 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1746,10 +1746,10 @@ static int vsc9959_stream_identify(struct flow_cls_offload *f, struct flow_dissector *dissector = rule->match.dissector; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS))) + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS))) return -EOPNOTSUPP; if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { diff --git a/drivers/net/dsa/sja1105/sja1105_flower.c b/drivers/net/dsa/sja1105/sja1105_flower.c index fad5afe3819c..9e8ca182c722 100644 --- a/drivers/net/dsa/sja1105/sja1105_flower.c +++ b/drivers/net/dsa/sja1105/sja1105_flower.c @@ -205,10 +205,10 @@ static int sja1105_flower_parse_key(struct sja1105_private *priv, u16 pcp = U16_MAX; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported keys used"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index d8afcf8d6b30..38d89d80b4a9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -373,9 +373,9 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, struct flow_dissector *dissector = rule->match.dissector; /* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */ - if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 || - (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) == 0) { - netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x\n", + if ((dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) == 0 || + (dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC)) == 0) { + netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%llx\n", dissector->used_keys); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index d3541159487d..72ac4a34424b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -313,15 +313,15 @@ static int cxgb4_validate_flow_match(struct net_device *dev, u16 ethtype_key = 0; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_IP))) { - netdev_warn(dev, "Unsupported key used: 0x%x\n", + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP))) { + netdev_warn(dev, "Unsupported key used: 0x%llx\n", dissector->used_keys); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c index c39b866e2582..4798fb7fe35d 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c @@ -17,14 +17,14 @@ static int dpaa2_switch_flower_parse_key(struct flow_cls_offload *cls, struct dpsw_acl_fields *acl_h, *acl_m; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_IP) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported keys used"); return -EOPNOTSUPP; @@ -539,9 +539,9 @@ static int dpaa2_switch_flower_parse_mirror_key(struct flow_cls_offload *cls, int ret = -EOPNOTSUPP; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_VLAN))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN))) { NL_SET_ERR_MSG_MOD(extack, "Mirroring is supported only per VLAN"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 270cbd5e8684..2513b44056c1 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -483,13 +483,13 @@ struct enetc_psfp { static struct actions_fwd enetc_act_fwd[] = { { BIT(FLOW_ACTION_GATE), - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS), + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS), FILTER_ACTION_TYPE_PSFP }, { BIT(FLOW_ACTION_POLICE) | BIT(FLOW_ACTION_GATE), - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS), + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS), FILTER_ACTION_TYPE_PSFP }, /* example for ACL actions */ @@ -1069,8 +1069,8 @@ revert_sid: return err; } -static struct actions_fwd *enetc_check_flow_actions(u64 acts, - unsigned int inputkeys) +static struct actions_fwd * +enetc_check_flow_actions(u64 acts, unsigned long long inputkeys) { int i; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index bf675c15fbb9..83ab89f44250 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -7315,14 +7315,14 @@ static int hclge_parse_cls_flower(struct hclge_dev *hdev, struct flow_dissector *dissector = flow->match.dissector; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS))) { - dev_err(&hdev->pdev->dev, "unsupported key set: %#x\n", + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS))) { + dev_err(&hdev->pdev->dev, "unsupported key set: %#llx\n", dissector->used_keys); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 982ae70c51e8..3d0d6974c2a7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -8525,15 +8525,15 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, u8 field_flags = 0; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { - dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n", + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID))) { + dev_err(&pf->pdev->dev, "Unsupported key used: 0x%llx\n", dissector->used_keys); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 9610ca770349..7b300c86ceda 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3744,15 +3744,15 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, struct virtchnl_filter *vf = &filter->f; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { - dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n", + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID))) { + dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%llx\n", dissector->used_keys); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index 4a34ef5f58d3..38547db1ec4e 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -1343,24 +1343,24 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, dissector = rule->match.dissector; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_CVLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | - BIT(FLOW_DISSECTOR_KEY_IP) | - BIT(FLOW_DISSECTOR_KEY_ENC_IP) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_PPPOE) | - BIT(FLOW_DISSECTOR_KEY_L2TPV3))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PPPOE) | + BIT_ULL(FLOW_DISSECTOR_KEY_L2TPV3))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported key used"); return -EOPNOTSUPP; } @@ -1382,10 +1382,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, */ headers = &fltr->inner_headers; } else if (dissector->used_keys & - (BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))) { + (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel"); return -EOPNOTSUPP; } else { diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 9a2561409b06..9f63a10c6f80 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2615,10 +2615,10 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, struct netlink_ext_ack *extack = f->common.extack; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported key used, only BASIC, CONTROL, ETH_ADDRS and VLAN are supported"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 0915a0121316..5a44e9b96fc0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -454,15 +454,15 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, dissector = rule->match.dissector; if ((dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_IP)))) { - netdev_info(nic->netdev, "unsupported flow used key 0x%x", + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP)))) { + netdev_info(nic->netdev, "unsupported flow used key 0x%llx", dissector->used_keys); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.c b/drivers/net/ethernet/marvell/prestera/prestera_flower.c index 3e20e71b0f81..8b9455d8a4f7 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flower.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.c @@ -202,16 +202,16 @@ static int prestera_flower_parse(struct prestera_flow_block *block, int err; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_META) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ICMP) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_PORTS_RANGE) | - BIT(FLOW_DISSECTOR_KEY_VLAN))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_META) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ICMP) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS_RANGE) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN))) { NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported key"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c index 2b80fe73549d..8c531f4ec912 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c @@ -221,16 +221,21 @@ mlx5_ct_fs_smfs_destroy(struct mlx5_ct_fs *fs) } static inline bool -mlx5_tc_ct_valid_used_dissector_keys(const u32 used_keys) +mlx5_tc_ct_valid_used_dissector_keys(const u64 used_keys) { -#define DISS_BIT(name) BIT(FLOW_DISSECTOR_KEY_ ## name) - const u32 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) | DISS_BIT(META); - const u32 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) | DISS_BIT(PORTS) | DISS_BIT(TCP); - const u32 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) | DISS_BIT(PORTS) | DISS_BIT(TCP); - const u32 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) | DISS_BIT(PORTS); - const u32 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) | DISS_BIT(PORTS); - const u32 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS); - const u32 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS); +#define DISS_BIT(name) BIT_ULL(FLOW_DISSECTOR_KEY_ ## name) + const u64 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) | + DISS_BIT(META); + const u64 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) | + DISS_BIT(PORTS) | DISS_BIT(TCP); + const u64 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) | + DISS_BIT(PORTS) | DISS_BIT(TCP); + const u64 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) | + DISS_BIT(PORTS); + const u64 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) | + DISS_BIT(PORTS); + const u64 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS); + const u64 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS); return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp || used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre); @@ -247,7 +252,7 @@ mlx5_ct_fs_smfs_ct_validate_flow_rule(struct mlx5_ct_fs *fs, struct flow_rule *f struct flow_match_tcp tcp; if (!mlx5_tc_ct_valid_used_dissector_keys(flow_rule->match.dissector->used_keys)) { - ct_dbg("rule uses unexpected dissectors (0x%08x)", + ct_dbg("rule uses unexpected dissectors (0x%016llx)", flow_rule->match.dissector->used_keys); return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 507825a1abc8..dfd282319753 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2590,29 +2590,29 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, match_level = outer_match_level; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_META) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_CVLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_TCP) | - BIT(FLOW_DISSECTOR_KEY_IP) | - BIT(FLOW_DISSECTOR_KEY_CT) | - BIT(FLOW_DISSECTOR_KEY_ENC_IP) | - BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | - BIT(FLOW_DISSECTOR_KEY_ICMP) | - BIT(FLOW_DISSECTOR_KEY_MPLS))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_META) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_TCP) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_CT) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ICMP) | + BIT_ULL(FLOW_DISSECTOR_KEY_MPLS))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported key"); - netdev_dbg(priv->netdev, "Unsupported key used: 0x%x\n", + netdev_dbg(priv->netdev, "Unsupported key used: 0x%llx\n", dissector->used_keys); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 8329100479b3..af3f57d017ec 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -558,17 +558,17 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, int err; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_META) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_PORTS_RANGE) | - BIT(FLOW_DISSECTOR_KEY_TCP) | - BIT(FLOW_DISSECTOR_KEY_IP) | - BIT(FLOW_DISSECTOR_KEY_VLAN))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_META) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS_RANGE) | + BIT_ULL(FLOW_DISSECTOR_KEY_TCP) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN))) { dev_err(mlxsw_sp->bus_info->dev, "Unsupported key\n"); NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported key"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c index 96b3def6c474..d696cf9dbd19 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c @@ -75,7 +75,7 @@ lan966x_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL); return err; @@ -172,7 +172,7 @@ lan966x_tc_flower_handler_basic_usage(struct vcap_tc_flower_parse_usage *st) } } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_BASIC); return err; out: NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_proto parse error"); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c index 3f87a5285a6d..906299ad8425 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -126,7 +126,7 @@ sparx5_tc_flower_handler_basic_usage(struct vcap_tc_flower_parse_usage *st) } } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_BASIC); return err; @@ -175,7 +175,7 @@ sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL); return err; diff --git a/drivers/net/ethernet/microchip/vcap/vcap_tc.c b/drivers/net/ethernet/microchip/vcap/vcap_tc.c index 09abe7944af6..27e2dffb65e6 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_tc.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_tc.c @@ -50,7 +50,7 @@ int vcap_tc_flower_handler_ethaddr_usage(struct vcap_tc_flower_parse_usage *st) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS); return err; @@ -86,7 +86,7 @@ int vcap_tc_flower_handler_ipv4_usage(struct vcap_tc_flower_parse_usage *st) } } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS); return err; @@ -124,7 +124,7 @@ int vcap_tc_flower_handler_ipv6_usage(struct vcap_tc_flower_parse_usage *st) goto out; } } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS); return err; out: NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv6_addr parse error"); @@ -158,7 +158,7 @@ int vcap_tc_flower_handler_portnum_usage(struct vcap_tc_flower_parse_usage *st) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_PORTS); return err; @@ -201,7 +201,7 @@ int vcap_tc_flower_handler_cvlan_usage(struct vcap_tc_flower_parse_usage *st) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN); return 0; out: @@ -238,7 +238,7 @@ int vcap_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st, if (mt.mask->vlan_tpid) st->tpid = be16_to_cpu(mt.key->vlan_tpid); - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN); return 0; out: @@ -313,7 +313,7 @@ int vcap_tc_flower_handler_tcp_usage(struct vcap_tc_flower_parse_usage *st) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_TCP); return err; @@ -376,7 +376,7 @@ int vcap_tc_flower_handler_arp_usage(struct vcap_tc_flower_parse_usage *st) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ARP); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_ARP); return 0; @@ -401,7 +401,7 @@ int vcap_tc_flower_handler_ip_usage(struct vcap_tc_flower_parse_usage *st) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IP); + st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_IP); return err; diff --git a/drivers/net/ethernet/microchip/vcap/vcap_tc.h b/drivers/net/ethernet/microchip/vcap/vcap_tc.h index 071f892f9aa4..49b02d032906 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_tc.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_tc.h @@ -14,7 +14,7 @@ struct vcap_tc_flower_parse_usage { u16 l3_proto; u8 l4_proto; u16 tpid; - unsigned int used_keys; + unsigned long long used_keys; }; int vcap_tc_flower_handler_ethaddr_usage(struct vcap_tc_flower_parse_usage *st); diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index e0916afcddfb..33b438c6aec5 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -581,14 +581,14 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, int ret; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_META) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_META) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS))) { return -EOPNOTSUPP; } @@ -641,12 +641,12 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, * then just bail out */ if ((dissector->used_keys & - (BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_CONTROL))) != - (BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_CONTROL))) + (BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL))) != + (BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL))) return -EOPNOTSUPP; flow_rule_match_eth_addrs(rule, &match); diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c index 73032173ac4e..2643c4b3ff1f 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -61,7 +61,7 @@ bool is_pre_ct_flow(struct flow_cls_offload *flow) struct flow_match_ct ct; int i; - if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) { + if (dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CT)) { flow_rule_match_ct(rule, &ct); if (ct.key->ct_state) return false; @@ -94,7 +94,7 @@ bool is_post_ct_flow(struct flow_cls_offload *flow) struct flow_match_ct ct; int i; - if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) { + if (dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CT)) { flow_rule_match_ct(rule, &ct); if (ct.key->ct_state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED) return true; @@ -236,10 +236,11 @@ static bool nfp_ct_merge_check_cannot_skip(struct nfp_fl_ct_flow_entry *entry1, static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, struct nfp_fl_ct_flow_entry *entry2) { - unsigned int ovlp_keys = entry1->rule->match.dissector->used_keys & - entry2->rule->match.dissector->used_keys; + unsigned long long ovlp_keys; bool out, is_v6 = false; u8 ip_proto = 0; + ovlp_keys = entry1->rule->match.dissector->used_keys & + entry2->rule->match.dissector->used_keys; /* Temporary buffer for mangling keys, 64 is enough to cover max * struct size of key in various fields that may be mangled. * Supported fields to mangle: @@ -257,7 +258,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, /* Check the overlapped fields one by one, the unmasked part * should not conflict with each other. */ - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_match_control match1, match2; flow_rule_match_control(entry1->rule, &match1); @@ -267,7 +268,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC)) { struct flow_match_basic match1, match2; flow_rule_match_basic(entry1->rule, &match1); @@ -289,7 +290,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, * will be do merge check when do nft and post ct merge, * so skip this ip merge check here. */ - if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS)) && + if ((ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS)) && nfp_ct_merge_check_cannot_skip(entry1, entry2)) { struct flow_match_ipv4_addrs match1, match2; @@ -311,7 +312,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, * will be do merge check when do nft and post ct merge, * so skip this ip merge check here. */ - if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS)) && + if ((ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS)) && nfp_ct_merge_check_cannot_skip(entry1, entry2)) { struct flow_match_ipv6_addrs match1, match2; @@ -333,7 +334,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, * will be do merge check when do nft and post ct merge, * so skip this tport merge check here. */ - if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_PORTS)) && + if ((ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_PORTS)) && nfp_ct_merge_check_cannot_skip(entry1, entry2)) { enum flow_action_mangle_base htype = FLOW_ACT_MANGLE_UNSPEC; struct flow_match_ports match1, match2; @@ -355,7 +356,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_match_eth_addrs match1, match2; flow_rule_match_eth_addrs(entry1->rule, &match1); @@ -371,7 +372,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_VLAN)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN)) { struct flow_match_vlan match1, match2; flow_rule_match_vlan(entry1->rule, &match1); @@ -381,7 +382,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_MPLS)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_MPLS)) { struct flow_match_mpls match1, match2; flow_rule_match_mpls(entry1->rule, &match1); @@ -391,7 +392,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_TCP)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_TCP)) { struct flow_match_tcp match1, match2; flow_rule_match_tcp(entry1->rule, &match1); @@ -401,7 +402,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IP)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_IP)) { struct flow_match_ip match1, match2; flow_rule_match_ip(entry1->rule, &match1); @@ -413,7 +414,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_KEYID)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID)) { struct flow_match_enc_keyid match1, match2; flow_rule_match_enc_keyid(entry1->rule, &match1); @@ -423,7 +424,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { struct flow_match_ipv4_addrs match1, match2; flow_rule_match_enc_ipv4_addrs(entry1->rule, &match1); @@ -433,7 +434,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { struct flow_match_ipv6_addrs match1, match2; flow_rule_match_enc_ipv6_addrs(entry1->rule, &match1); @@ -443,7 +444,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL)) { struct flow_match_control match1, match2; flow_rule_match_enc_control(entry1->rule, &match1); @@ -453,7 +454,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IP)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP)) { struct flow_match_ip match1, match2; flow_rule_match_enc_ip(entry1->rule, &match1); @@ -463,7 +464,7 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, goto check_failed; } - if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_OPTS)) { + if (ovlp_keys & BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS)) { struct flow_match_enc_opts match1, match2; flow_rule_match_enc_opts(entry1->rule, &match1); @@ -589,7 +590,7 @@ static int nfp_ct_check_meta(struct nfp_fl_ct_flow_entry *post_ct_entry, int i; ct_met = get_flow_act(nft_entry->rule, FLOW_ACTION_CT_METADATA); - if (ct_met && (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT))) { + if (ct_met && (dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CT))) { u32 *act_lbl; act_lbl = ct_met->ct_metadata.labels; diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 18328eb7f5c3..c153f0575b92 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -24,43 +24,43 @@ FLOW_DIS_FIRST_FRAG) #define NFP_FLOWER_WHITELIST_DISSECTOR \ - (BIT(FLOW_DISSECTOR_KEY_CONTROL) | \ - BIT(FLOW_DISSECTOR_KEY_BASIC) | \ - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | \ - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | \ - BIT(FLOW_DISSECTOR_KEY_TCP) | \ - BIT(FLOW_DISSECTOR_KEY_PORTS) | \ - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \ - BIT(FLOW_DISSECTOR_KEY_VLAN) | \ - BIT(FLOW_DISSECTOR_KEY_CVLAN) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_IP) | \ - BIT(FLOW_DISSECTOR_KEY_MPLS) | \ - BIT(FLOW_DISSECTOR_KEY_CT) | \ - BIT(FLOW_DISSECTOR_KEY_META) | \ - BIT(FLOW_DISSECTOR_KEY_IP)) + (BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_TCP) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_MPLS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_CT) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_META) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_IP)) #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR \ - (BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_IP)) + (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP)) #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R \ - (BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) + (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR_V6_R \ - (BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) + (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) #define NFP_FLOWER_MERGE_FIELDS \ (NFP_FLOWER_LAYER_PORT | \ @@ -1303,7 +1303,7 @@ static bool offload_pre_check(struct flow_cls_offload *flow) struct flow_dissector *dissector = rule->match.dissector; struct flow_match_ct ct; - if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) { + if (dissector->used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CT)) { flow_rule_match_ct(rule, &ct); /* Allow special case where CT match is all 0 */ if (memchr_inv(ct.key, 0, sizeof(*ct.key))) diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 3010833ddde3..a5ac21a0ee33 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1827,12 +1827,12 @@ qede_parse_flow_attr(struct qede_dev *edev, __be16 proto, memset(tuple, 0, sizeof(*tuple)); if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS))) { - DP_NOTICE(edev, "Unsupported key set:0x%x\n", + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS))) { + DP_NOTICE(edev, "Unsupported key set:0x%llx\n", dissector->used_keys); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index 15ebd3973922..4dc881159246 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -201,23 +201,23 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx, } } if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_CVLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IP) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_TCP) | - BIT(FLOW_DISSECTOR_KEY_IP))) { - NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported flower keys %#x", + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_TCP) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP))) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported flower keys %#llx", dissector->used_keys); return -EOPNOTSUPP; } @@ -228,12 +228,13 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx, !(match->value.eth_proto == htons(ETH_P_IP) || match->value.eth_proto == htons(ETH_P_IPV6))) if (dissector->used_keys & - (BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_IP) | - BIT(FLOW_DISSECTOR_KEY_TCP))) { - NL_SET_ERR_MSG_FMT_MOD(extack, "L3/L4 flower keys %#x require protocol ipv[46]", + (BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_TCP))) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "L3/L4 flower keys %#llx require protocol ipv[46]", dissector->used_keys); return -EINVAL; } @@ -281,9 +282,10 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx, if ((match->value.ip_proto != IPPROTO_UDP && match->value.ip_proto != IPPROTO_TCP) || !IS_ALL_ONES(match->mask.ip_proto)) if (dissector->used_keys & - (BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_TCP))) { - NL_SET_ERR_MSG_FMT_MOD(extack, "L4 flower keys %#x require ipproto udp or tcp", + (BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_TCP))) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "L4 flower keys %#llx require ipproto udp or tcp", dissector->used_keys); return -EINVAL; } @@ -344,12 +346,13 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx, MAP_ENC_KEY_AND_MASK(PORTS, ports, enc_ports, dst, enc_dport); MAP_ENC_KEY_AND_MASK(KEYID, enc_keyid, enc_keyid, keyid, enc_keyid); } else if (dissector->used_keys & - (BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IP) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))) { - NL_SET_ERR_MSG_FMT_MOD(extack, "Flower enc keys require enc_control (keys: %#x)", + (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Flower enc keys require enc_control (keys: %#llx)", dissector->used_keys); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index 687f43cd466c..f9e43fc32ee8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -1355,7 +1355,7 @@ static int __stmmac_test_l3filt(struct stmmac_priv *priv, u32 dst, u32 src, goto cleanup_rss; } - dissector->used_keys |= (1 << FLOW_DISSECTOR_KEY_IPV4_ADDRS); + dissector->used_keys |= (1ULL << FLOW_DISSECTOR_KEY_IPV4_ADDRS); dissector->offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] = 0; cls = kzalloc(sizeof(*cls), GFP_KERNEL); @@ -1481,8 +1481,8 @@ static int __stmmac_test_l4filt(struct stmmac_priv *priv, u32 dst, u32 src, goto cleanup_rss; } - dissector->used_keys |= (1 << FLOW_DISSECTOR_KEY_BASIC); - dissector->used_keys |= (1 << FLOW_DISSECTOR_KEY_PORTS); + dissector->used_keys |= (1ULL << FLOW_DISSECTOR_KEY_BASIC); + dissector->used_keys |= (1ULL << FLOW_DISSECTOR_KEY_PORTS); dissector->offset[FLOW_DISSECTOR_KEY_BASIC] = 0; dissector->offset[FLOW_DISSECTOR_KEY_PORTS] = offsetof(typeof(keys), key); diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c index eced87fa261c..9ac2ff05d501 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-qos.c +++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c @@ -624,9 +624,9 @@ static int am65_cpsw_qos_clsflower_add_policer(struct am65_cpsw_port *port, int ret; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported keys used"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index e966dd47e2db..ae52cdbcf8cc 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -1396,9 +1396,9 @@ static int cpsw_qos_clsflower_add_policer(struct cpsw_priv *priv, int ret; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported keys used"); return -EOPNOTSUPP; diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 8664ed4fbbdf..830f06b2f36d 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -370,7 +370,8 @@ struct flow_dissector_key { }; struct flow_dissector { - unsigned int used_keys; /* each bit repesents presence of one key id */ + unsigned long long used_keys; + /* each bit represents presence of one key id */ unsigned short int offset[FLOW_DISSECTOR_KEY_MAX]; }; @@ -430,7 +431,7 @@ void skb_flow_get_icmp_tci(const struct sk_buff *skb, static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { - return flow_dissector->used_keys & (1 << key_id); + return flow_dissector->used_keys & (1ULL << key_id); } static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 85a2d0d9bd39..ed5dfa376024 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -40,7 +40,7 @@ static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { - flow_dissector->used_keys |= (1 << key_id); + flow_dissector->used_keys |= (1ULL << key_id); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7d40e7913e76..0b0ce4f81c01 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -3208,7 +3208,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) if (v4_m_spec->ip4src || v4_m_spec->ip4dst) { match->dissector.used_keys |= - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS); match->dissector.offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] = offsetof(struct ethtool_rx_flow_key, ipv4); } @@ -3223,7 +3223,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) if (v4_m_spec->psrc || v4_m_spec->pdst) { match->dissector.used_keys |= - BIT(FLOW_DISSECTOR_KEY_PORTS); + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS); match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] = offsetof(struct ethtool_rx_flow_key, tp); } @@ -3260,7 +3260,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) if (!ipv6_addr_any((struct in6_addr *)v6_m_spec->ip6src) || !ipv6_addr_any((struct in6_addr *)v6_m_spec->ip6dst)) { match->dissector.used_keys |= - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS); match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] = offsetof(struct ethtool_rx_flow_key, ipv6); } @@ -3275,7 +3275,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) if (v6_m_spec->psrc || v6_m_spec->pdst) { match->dissector.used_keys |= - BIT(FLOW_DISSECTOR_KEY_PORTS); + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS); match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] = offsetof(struct ethtool_rx_flow_key, tp); } @@ -3283,7 +3283,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) match->key.ip.tos = v6_spec->tclass; match->mask.ip.tos = v6_m_spec->tclass; match->dissector.used_keys |= - BIT(FLOW_DISSECTOR_KEY_IP); + BIT_ULL(FLOW_DISSECTOR_KEY_IP); match->dissector.offset[FLOW_DISSECTOR_KEY_IP] = offsetof(struct ethtool_rx_flow_key, ip); } @@ -3307,7 +3307,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) break; } - match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); + match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_BASIC); match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] = offsetof(struct ethtool_rx_flow_key, basic); @@ -3340,7 +3340,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) if (ext_m_spec->vlan_etype || ext_m_spec->vlan_tci) { match->dissector.used_keys |= - BIT(FLOW_DISSECTOR_KEY_VLAN); + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN); match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = offsetof(struct ethtool_rx_flow_key, vlan); } @@ -3355,7 +3355,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) ETH_ALEN); match->dissector.used_keys |= - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS); match->dissector.offset[FLOW_DISSECTOR_KEY_ETH_ADDRS] = offsetof(struct ethtool_rx_flow_key, eth_addrs); } diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 1c26f03fc661..a010b25076ca 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -34,7 +34,7 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match, { struct nf_flow_key *mask = &match->mask; struct nf_flow_key *key = &match->key; - unsigned int enc_keys; + unsigned long long enc_keys; if (!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX)) return; @@ -43,8 +43,8 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match, NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id); key->enc_key_id.keyid = tunnel_id_to_key32(tun_info->key.tun_id); mask->enc_key_id.keyid = 0xffffffff; - enc_keys = BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL); + enc_keys = BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL); if (ip_tunnel_info_af(tun_info) == AF_INET) { NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, @@ -55,7 +55,7 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match, mask->enc_ipv4.src = 0xffffffff; if (key->enc_ipv4.dst) mask->enc_ipv4.dst = 0xffffffff; - enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS); + enc_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS); key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } else { memcpy(&key->enc_ipv6.src, &tun_info->key.u.ipv6.dst, @@ -70,7 +70,7 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match, sizeof(struct in6_addr))) memset(&mask->enc_ipv6.dst, 0xff, sizeof(struct in6_addr)); - enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS); + enc_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS); key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } @@ -163,14 +163,14 @@ static int nf_flow_rule_match(struct nf_flow_match *match, return -EOPNOTSUPP; } mask->control.addr_type = 0xffff; - match->dissector.used_keys |= BIT(key->control.addr_type); + match->dissector.used_keys |= BIT_ULL(key->control.addr_type); mask->basic.n_proto = 0xffff; switch (tuple->l4proto) { case IPPROTO_TCP: key->tcp.flags = 0; mask->tcp.flags = cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16); - match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); + match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_TCP); break; case IPPROTO_UDP: case IPPROTO_GRE: @@ -182,9 +182,9 @@ static int nf_flow_rule_match(struct nf_flow_match *match, key->basic.ip_proto = tuple->l4proto; mask->basic.ip_proto = 0xff; - match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_META) | - BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC); + match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_META) | + BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC); switch (tuple->l4proto) { case IPPROTO_TCP: @@ -194,7 +194,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, key->tp.dst = tuple->dst_port; mask->tp.dst = 0xffff; - match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS); + match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_PORTS); break; } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 910ef881c3b8..12ab78fa5d84 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -35,12 +35,12 @@ void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, struct nft_flow_key *mask = &match->mask; struct nft_flow_key *key = &match->key; - if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) + if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) return; key->control.addr_type = addr_type; mask->control.addr_type = 0xffff; - match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); + match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL); match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = offsetof(struct nft_flow_key, control); } @@ -59,7 +59,7 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, .mask = match->mask.basic.n_proto, }; - if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_VLAN) && + if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || match->key.vlan.vlan_tpid == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.cvlan.vlan_tpid; @@ -70,8 +70,9 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); - match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN); - } else if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC) && + match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN); + } else if (match->dissector.used_keys & + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) && (match->key.basic.n_proto == htons(ETH_P_8021Q) || match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; @@ -80,7 +81,7 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = offsetof(struct nft_flow_key, vlan); - match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN); + match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN); } } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 6eb21a4f5698..cd4652259095 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -162,7 +162,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, memcpy(key + reg->offset, data, reg->len); memcpy(mask + reg->offset, datamask, reg->len); - flow->match.dissector.used_keys |= BIT(reg->key); + flow->match.dissector.used_keys |= BIT_ULL(reg->key); flow->match.dissector.offset[reg->key] = reg->base_offset; if (reg->key == FLOW_DISSECTOR_KEY_META && -- cgit v1.2.3 From 2628d40899d1acb5120993bef651595787ddaa8e Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Fri, 28 Jul 2023 21:21:13 +0800 Subject: devlink: Remove unused extern declaration devlink_port_region_destroy() devlink_port_region_destroy() is never implemented since commit 544e7c33ec2f ("net: devlink: Add support for port regions"). Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230728132113.32888-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 0cdb4b16e5b5..a1a8e1b6e7df 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1790,8 +1790,6 @@ devlink_port_region_create(struct devlink_port *port, u32 region_max_snapshots, u64 region_size); void devl_region_destroy(struct devlink_region *region); void devlink_region_destroy(struct devlink_region *region); -void devlink_port_region_destroy(struct devlink_region *region); - int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id); void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id); int devlink_region_snapshot_create(struct devlink_region *region, -- cgit v1.2.3 From 68223f96997e8ac2bb1751a72a211d1551a0dbcd Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Sat, 29 Jul 2023 20:26:44 +0800 Subject: tcp: Remove unused function declarations commit 8a59f9d1e3d4 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()") left behind tcp_bpf_get_proto() declaration. And tcp_v4_tw_remember_stamp() function is remove in ccb7c410ddc0 ("timewait_sock: Create and use getpeer op."). Since commit 686989700cab ("tcp: simplify tcp_mark_skb_lost") tcp_skb_mark_lost_uncond_verify() declaration is not used anymore. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230729122644.10648-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 6ebf54992ffe..6d77c08d83b7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -323,7 +323,6 @@ int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); void tcp_remove_empty_skb(struct sock *sk); -int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, @@ -622,7 +621,6 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb, void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk, struct sk_buff *skb); -void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); void tcp_sack_compress_send_ack(struct sock *sk); @@ -2360,7 +2358,6 @@ struct sk_msg; struct sk_psock; #ifdef CONFIG_BPF_SYSCALL -struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #endif /* CONFIG_BPF_SYSCALL */ -- cgit v1.2.3 From 079082c60affefeb9d2bd4176a4f2b390a9ccfda Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 28 Jul 2023 23:47:17 +0200 Subject: tcx: Fix splat during dev unregister During unregister_netdevice_many_notify(), the ordering of our concerned function calls is like this: unregister_netdevice_many_notify dev_shutdown qdisc_put clsact_destroy tcx_uninstall The syzbot reproducer triggered a case that the qdisc refcnt is not zero during dev_shutdown(). tcx_uninstall() will then WARN_ON_ONCE(tcx_entry(entry)->miniq_active) because the miniq is still active and the entry should not be freed. The latter assumed that qdisc destruction happens before tcx teardown. This fix is to avoid tcx_uninstall() doing tcx_entry_free() when the miniq is still alive and let the clsact_destroy() do the free later, so that we do not assume any specific ordering for either of them. If still active, tcx_uninstall() does clear the entry when flushing out the prog/link. clsact_destroy() will then notice the "!tcx_entry_is_active()" and then does the tcx_entry_free() eventually. Fixes: e420bed02507 ("bpf: Add fd-based tcx multi-prog infra with link support") Reported-by: syzbot+376a289e86a0fd02b9ba@syzkaller.appspotmail.com Reported-by: Leon Romanovsky Signed-off-by: Martin KaFai Lau Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Tested-by: syzbot+376a289e86a0fd02b9ba@syzkaller.appspotmail.com Tested-by: Leon Romanovsky Link: https://lore.kernel.org/r/222255fe07cb58f15ee662e7ee78328af5b438e4.1690549248.git.daniel@iogearbox.net Signed-off-by: Jakub Kicinski --- include/linux/bpf_mprog.h | 16 ++++++++++++++++ kernel/bpf/tcx.c | 12 ++++++++---- 2 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_mprog.h b/include/linux/bpf_mprog.h index 2b429488f840..929225f7b095 100644 --- a/include/linux/bpf_mprog.h +++ b/include/linux/bpf_mprog.h @@ -256,6 +256,22 @@ static inline void bpf_mprog_entry_copy(struct bpf_mprog_entry *dst, memcpy(dst->fp_items, src->fp_items, sizeof(src->fp_items)); } +static inline void bpf_mprog_entry_clear(struct bpf_mprog_entry *dst) +{ + memset(dst->fp_items, 0, sizeof(dst->fp_items)); +} + +static inline void bpf_mprog_clear_all(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new) +{ + struct bpf_mprog_entry *peer; + + peer = bpf_mprog_peer(entry); + bpf_mprog_entry_clear(peer); + peer->parent->count = 0; + *entry_new = peer; +} + static inline void bpf_mprog_entry_grow(struct bpf_mprog_entry *entry, int idx) { int total = bpf_mprog_total(entry); diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c index 69a272712b29..13f0b5dc8262 100644 --- a/kernel/bpf/tcx.c +++ b/kernel/bpf/tcx.c @@ -94,15 +94,19 @@ out: void tcx_uninstall(struct net_device *dev, bool ingress) { + struct bpf_mprog_entry *entry, *entry_new = NULL; struct bpf_tuple tuple = {}; - struct bpf_mprog_entry *entry; struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; + bool active; entry = tcx_entry_fetch(dev, ingress); if (!entry) return; - tcx_entry_update(dev, NULL, ingress); + active = tcx_entry(entry)->miniq_active; + if (active) + bpf_mprog_clear_all(entry, &entry_new); + tcx_entry_update(dev, entry_new, ingress); tcx_entry_sync(); bpf_mprog_foreach_tuple(entry, fp, cp, tuple) { if (tuple.link) @@ -111,8 +115,8 @@ void tcx_uninstall(struct net_device *dev, bool ingress) bpf_prog_put(tuple.prog); tcx_skeys_dec(ingress); } - WARN_ON_ONCE(tcx_entry(entry)->miniq_active); - tcx_entry_free(entry); + if (!active) + tcx_entry_free(entry); } int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) -- cgit v1.2.3 From 8798481b667fa7c9bbd5aa843bf1557ada699964 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Fri, 28 Jul 2023 12:35:33 -0300 Subject: net/sched: wrap open coded Qdics class filter counter The 'filter_cnt' counter is used to control a Qdisc class lifetime. Each filter referecing this class by its id will eventually increment/decrement this counter in their respective 'add/update/delete' routines. As these operations are always serialized under rtnl lock, we don't need an atomic type like 'refcount_t'. It also means that we lose the overflow/underflow checks already present in refcount_t, which are valuable to hunt down bugs where the unsigned counter wraps around as it aids automated tools like syzkaller to scream in such situations. Wrap the open coded increment/decrement into helper functions and add overflow checks to the operations. Acked-by: Jamal Hadi Salim Signed-off-by: Pedro Tammela Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni --- include/net/sch_generic.h | 26 ++++++++++++++++++++++++++ net/sched/sch_drr.c | 9 ++++----- net/sched/sch_hfsc.c | 8 ++++---- net/sched/sch_htb.c | 8 +++----- net/sched/sch_qfq.c | 10 ++++------ 5 files changed, 41 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 15be2d96b06d..f232512505f8 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -599,6 +599,7 @@ get_default_qdisc_ops(const struct net_device *dev, int ntx) struct Qdisc_class_common { u32 classid; + unsigned int filter_cnt; struct hlist_node hnode; }; @@ -633,6 +634,31 @@ qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id) return NULL; } +static inline bool qdisc_class_in_use(const struct Qdisc_class_common *cl) +{ + return cl->filter_cnt > 0; +} + +static inline void qdisc_class_get(struct Qdisc_class_common *cl) +{ + unsigned int res; + + if (check_add_overflow(cl->filter_cnt, 1, &res)) + WARN(1, "Qdisc class overflow"); + + cl->filter_cnt = res; +} + +static inline void qdisc_class_put(struct Qdisc_class_common *cl) +{ + unsigned int res; + + if (check_sub_overflow(cl->filter_cnt, 1, &res)) + WARN(1, "Qdisc class underflow"); + + cl->filter_cnt = res; +} + static inline int tc_classid_to_hwtc(struct net_device *dev, u32 classid) { u32 hwtc = TC_H_MIN(classid) - TC_H_MIN_PRIORITY; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index e35a4e90f4e6..1b22b3b741c9 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -17,7 +17,6 @@ struct drr_class { struct Qdisc_class_common common; - unsigned int filter_cnt; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; @@ -150,7 +149,7 @@ static int drr_delete_class(struct Qdisc *sch, unsigned long arg, struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl = (struct drr_class *)arg; - if (cl->filter_cnt > 0) + if (qdisc_class_in_use(&cl->common)) return -EBUSY; sch_tree_lock(sch); @@ -187,8 +186,8 @@ static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent, { struct drr_class *cl = drr_find_class(sch, classid); - if (cl != NULL) - cl->filter_cnt++; + if (cl) + qdisc_class_get(&cl->common); return (unsigned long)cl; } @@ -197,7 +196,7 @@ static void drr_unbind_tcf(struct Qdisc *sch, unsigned long arg) { struct drr_class *cl = (struct drr_class *)arg; - cl->filter_cnt--; + qdisc_class_put(&cl->common); } static int drr_graft_class(struct Qdisc *sch, unsigned long arg, diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 70b0c5873d32..896cb401fdb9 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -116,7 +116,6 @@ struct hfsc_class { struct net_rate_estimator __rcu *rate_est; struct tcf_proto __rcu *filter_list; /* filter list */ struct tcf_block *block; - unsigned int filter_cnt; /* filter count */ unsigned int level; /* class level in hierarchy */ struct hfsc_sched *sched; /* scheduler data */ @@ -1094,7 +1093,8 @@ hfsc_delete_class(struct Qdisc *sch, unsigned long arg, struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; - if (cl->level > 0 || cl->filter_cnt > 0 || cl == &q->root) + if (cl->level > 0 || qdisc_class_in_use(&cl->cl_common) || + cl == &q->root) return -EBUSY; sch_tree_lock(sch); @@ -1223,7 +1223,7 @@ hfsc_bind_tcf(struct Qdisc *sch, unsigned long parent, u32 classid) if (cl != NULL) { if (p != NULL && p->level <= cl->level) return 0; - cl->filter_cnt++; + qdisc_class_get(&cl->cl_common); } return (unsigned long)cl; @@ -1234,7 +1234,7 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; - cl->filter_cnt--; + qdisc_class_put(&cl->cl_common); } static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg, diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 333800a7d4eb..05c8291865ae 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -102,7 +102,6 @@ struct htb_class { struct tcf_proto __rcu *filter_list; /* class attached filters */ struct tcf_block *block; - int filter_cnt; int level; /* our level (see above) */ unsigned int children; @@ -1710,7 +1709,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, * tc subsys guarantee us that in htb_destroy it holds no class * refs so that we can remove children safely there ? */ - if (cl->children || cl->filter_cnt) + if (cl->children || qdisc_class_in_use(&cl->common)) return -EBUSY; if (!cl->level && htb_parent_last_child(cl)) @@ -2107,7 +2106,7 @@ static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent, * be broken by class during destroy IIUC. */ if (cl) - cl->filter_cnt++; + qdisc_class_get(&cl->common); return (unsigned long)cl; } @@ -2115,8 +2114,7 @@ static void htb_unbind_filter(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - if (cl) - cl->filter_cnt--; + qdisc_class_put(&cl->common); } static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index befaf74b33ca..7addc15f01b5 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -130,8 +130,6 @@ struct qfq_aggregate; struct qfq_class { struct Qdisc_class_common common; - unsigned int filter_cnt; - struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; @@ -545,7 +543,7 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg, struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)arg; - if (cl->filter_cnt > 0) + if (qdisc_class_in_use(&cl->common)) return -EBUSY; sch_tree_lock(sch); @@ -580,8 +578,8 @@ static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent, { struct qfq_class *cl = qfq_find_class(sch, classid); - if (cl != NULL) - cl->filter_cnt++; + if (cl) + qdisc_class_get(&cl->common); return (unsigned long)cl; } @@ -590,7 +588,7 @@ static void qfq_unbind_tcf(struct Qdisc *sch, unsigned long arg) { struct qfq_class *cl = (struct qfq_class *)arg; - cl->filter_cnt--; + qdisc_class_put(&cl->common); } static int qfq_graft_class(struct Qdisc *sch, unsigned long arg, -- cgit v1.2.3 From 999d0863ff6416dd33c904f496bf363c8afb6540 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 31 Jul 2023 22:04:37 +0800 Subject: inet6: Remove unused function declaration udpv6_connect() This is never implemented since the beginning of git history. Signed-off-by: Yue Haibing Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230731140437.37056-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/transp_v6.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index d27b1caf3753..1a97e3f32029 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -33,8 +33,6 @@ void udplitev6_exit(void); int tcpv6_init(void); void tcpv6_exit(void); -int udpv6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); - /* this does all the common and the specific ctl work */ void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb); -- cgit v1.2.3 From 394bd87764b615b0fc17d34127a1cc7da76ff49f Mon Sep 17 00:00:00 2001 From: Gavin Li Date: Mon, 31 Jul 2023 10:06:55 +0300 Subject: virtio_net: support per queue interrupt coalesce command Add interrupt_coalesce config in send_queue and receive_queue to cache user config. Send per virtqueue interrupt moderation config to underlying device in order to have more efficient interrupt moderation and cpu utilization of guest VM. Additionally, address all the VQs when updating the global configuration, as now the individual VQs configuration can diverge from the global configuration. Signed-off-by: Gavin Li Reviewed-by: Dragos Tatulea Reviewed-by: Jiri Pirko Acked-by: Michael S. Tsirkin Reviewed-by: Heng Qi Acked-by: Jason Wang Link: https://lore.kernel.org/r/20230731070656.96411-3-gavinl@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 149 +++++++++++++++++++++++++++++++++++++--- include/uapi/linux/virtio_net.h | 14 ++++ 2 files changed, 155 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b1e2e63edd35..77805796fddd 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -144,6 +144,8 @@ struct send_queue { struct virtnet_sq_stats stats; + struct virtnet_interrupt_coalesce intr_coal; + struct napi_struct napi; /* Record whether sq is in reset state. */ @@ -161,6 +163,8 @@ struct receive_queue { struct virtnet_rq_stats stats; + struct virtnet_interrupt_coalesce intr_coal; + /* Chain pages by the private ptr. */ struct page *pages; @@ -212,6 +216,7 @@ struct control_buf { struct virtio_net_ctrl_rss rss; struct virtio_net_ctrl_coal_tx coal_tx; struct virtio_net_ctrl_coal_rx coal_rx; + struct virtio_net_ctrl_coal_vq coal_vq; }; struct virtnet_info { @@ -3078,6 +3083,55 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, return 0; } +static int virtnet_send_ctrl_coal_vq_cmd(struct virtnet_info *vi, + u16 vqn, u32 max_usecs, u32 max_packets) +{ + struct scatterlist sgs; + + vi->ctrl->coal_vq.vqn = cpu_to_le16(vqn); + vi->ctrl->coal_vq.coal.max_usecs = cpu_to_le32(max_usecs); + vi->ctrl->coal_vq.coal.max_packets = cpu_to_le32(max_packets); + sg_init_one(&sgs, &vi->ctrl->coal_vq, sizeof(vi->ctrl->coal_vq)); + + if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, + VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET, + &sgs)) + return -EINVAL; + + return 0; +} + +static int virtnet_send_notf_coal_vq_cmds(struct virtnet_info *vi, + struct ethtool_coalesce *ec, + u16 queue) +{ + int err; + + if (ec->rx_coalesce_usecs || ec->rx_max_coalesced_frames) { + err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue), + ec->rx_coalesce_usecs, + ec->rx_max_coalesced_frames); + if (err) + return err; + /* Save parameters */ + vi->rq[queue].intr_coal.max_usecs = ec->rx_coalesce_usecs; + vi->rq[queue].intr_coal.max_packets = ec->rx_max_coalesced_frames; + } + + if (ec->tx_coalesce_usecs || ec->tx_max_coalesced_frames) { + err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue), + ec->tx_coalesce_usecs, + ec->tx_max_coalesced_frames); + if (err) + return err; + /* Save parameters */ + vi->sq[queue].intr_coal.max_usecs = ec->tx_coalesce_usecs; + vi->sq[queue].intr_coal.max_packets = ec->tx_max_coalesced_frames; + } + + return 0; +} + static int virtnet_coal_params_supported(struct ethtool_coalesce *ec) { /* usecs coalescing is supported only if VIRTIO_NET_F_NOTF_COAL @@ -3093,22 +3147,42 @@ static int virtnet_coal_params_supported(struct ethtool_coalesce *ec) return 0; } +static int virtnet_should_update_vq_weight(int dev_flags, int weight, + int vq_weight, bool *should_update) +{ + if (weight ^ vq_weight) { + if (dev_flags & IFF_UP) + return -EBUSY; + *should_update = true; + } + + return 0; +} + static int virtnet_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); - int ret, i, napi_weight; + int ret, queue_number, napi_weight; bool update_napi = false; /* Can't change NAPI weight if the link is up */ napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0; - if (napi_weight ^ vi->sq[0].napi.weight) { - if (dev->flags & IFF_UP) - return -EBUSY; - else - update_napi = true; + for (queue_number = 0; queue_number < vi->max_queue_pairs; queue_number++) { + ret = virtnet_should_update_vq_weight(dev->flags, napi_weight, + vi->sq[queue_number].napi.weight, + &update_napi); + if (ret) + return ret; + + if (update_napi) { + /* All queues that belong to [queue_number, vi->max_queue_pairs] will be + * updated for the sake of simplicity, which might not be necessary + */ + break; + } } if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) @@ -3120,8 +3194,8 @@ static int virtnet_set_coalesce(struct net_device *dev, return ret; if (update_napi) { - for (i = 0; i < vi->max_queue_pairs; i++) - vi->sq[i].napi.weight = napi_weight; + for (; queue_number < vi->max_queue_pairs; queue_number++) + vi->sq[queue_number].napi.weight = napi_weight; } return ret; @@ -3149,6 +3223,63 @@ static int virtnet_get_coalesce(struct net_device *dev, return 0; } +static int virtnet_set_per_queue_coalesce(struct net_device *dev, + u32 queue, + struct ethtool_coalesce *ec) +{ + struct virtnet_info *vi = netdev_priv(dev); + int ret, napi_weight; + bool update_napi = false; + + if (queue >= vi->max_queue_pairs) + return -EINVAL; + + /* Can't change NAPI weight if the link is up */ + napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0; + ret = virtnet_should_update_vq_weight(dev->flags, napi_weight, + vi->sq[queue].napi.weight, + &update_napi); + if (ret) + return ret; + + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) + ret = virtnet_send_notf_coal_vq_cmds(vi, ec, queue); + else + ret = virtnet_coal_params_supported(ec); + + if (ret) + return ret; + + if (update_napi) + vi->sq[queue].napi.weight = napi_weight; + + return 0; +} + +static int virtnet_get_per_queue_coalesce(struct net_device *dev, + u32 queue, + struct ethtool_coalesce *ec) +{ + struct virtnet_info *vi = netdev_priv(dev); + + if (queue >= vi->max_queue_pairs) + return -EINVAL; + + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) { + ec->rx_coalesce_usecs = vi->rq[queue].intr_coal.max_usecs; + ec->tx_coalesce_usecs = vi->sq[queue].intr_coal.max_usecs; + ec->tx_max_coalesced_frames = vi->sq[queue].intr_coal.max_packets; + ec->rx_max_coalesced_frames = vi->rq[queue].intr_coal.max_packets; + } else { + ec->rx_max_coalesced_frames = 1; + + if (vi->sq[0].napi.weight) + ec->tx_max_coalesced_frames = 1; + } + + return 0; +} + static void virtnet_init_settings(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -3279,6 +3410,8 @@ static const struct ethtool_ops virtnet_ethtool_ops = { .set_link_ksettings = virtnet_set_link_ksettings, .set_coalesce = virtnet_set_coalesce, .get_coalesce = virtnet_get_coalesce, + .set_per_queue_coalesce = virtnet_set_per_queue_coalesce, + .get_per_queue_coalesce = virtnet_get_per_queue_coalesce, .get_rxfh_key_size = virtnet_get_rxfh_key_size, .get_rxfh_indir_size = virtnet_get_rxfh_indir_size, .get_rxfh = virtnet_get_rxfh, diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 12c1c9699935..cc65ef0f3c3e 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -56,6 +56,7 @@ #define VIRTIO_NET_F_MQ 22 /* Device supports Receive Flow * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ +#define VIRTIO_NET_F_VQ_NOTF_COAL 52 /* Device supports virtqueue notification coalescing */ #define VIRTIO_NET_F_NOTF_COAL 53 /* Device supports notifications coalescing */ #define VIRTIO_NET_F_GUEST_USO4 54 /* Guest can handle USOv4 in. */ #define VIRTIO_NET_F_GUEST_USO6 55 /* Guest can handle USOv6 in. */ @@ -391,5 +392,18 @@ struct virtio_net_ctrl_coal_rx { }; #define VIRTIO_NET_CTRL_NOTF_COAL_RX_SET 1 +#define VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET 2 +#define VIRTIO_NET_CTRL_NOTF_COAL_VQ_GET 3 + +struct virtio_net_ctrl_coal { + __le32 max_packets; + __le32 max_usecs; +}; + +struct virtio_net_ctrl_coal_vq { + __le16 vqn; + __le16 reserved; + struct virtio_net_ctrl_coal coal; +}; #endif /* _UAPI_LINUX_VIRTIO_NET_H */ -- cgit v1.2.3 From a57c34a80cbe15e36e12d42a4ddc5160a5bbb1a4 Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Tue, 1 Aug 2023 07:10:58 +0530 Subject: net: flow_dissector: Add IPSEC dissector Support for dissecting IPSEC field SPI (which is 32bits in size) for ESP and AH packets. Signed-off-by: Ratheesh Kannoth Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 9 ++++++++ net/core/flow_dissector.c | 53 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 61 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 830f06b2f36d..1a7131d6cb0e 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -301,6 +301,14 @@ struct flow_dissector_key_l2tpv3 { __be32 session_id; }; +/** + * struct flow_dissector_key_ipsec: + * @spi: identifier for a ipsec connection + */ +struct flow_dissector_key_ipsec { + __be32 spi; +}; + /** * struct flow_dissector_key_cfm * @mdl_ver: maintenance domain level (mdl) and cfm protocol version @@ -354,6 +362,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_PPPOE, /* struct flow_dissector_key_pppoe */ FLOW_DISSECTOR_KEY_L2TPV3, /* struct flow_dissector_key_l2tpv3 */ FLOW_DISSECTOR_KEY_CFM, /* struct flow_dissector_key_cfm */ + FLOW_DISSECTOR_KEY_IPSEC, /* struct flow_dissector_key_ipsec */ FLOW_DISSECTOR_KEY_MAX, }; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ed5dfa376024..89d15ceaf9af 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -205,6 +205,50 @@ static void __skb_flow_dissect_icmp(const struct sk_buff *skb, skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen); } +static void __skb_flow_dissect_ah(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, const void *data, + int nhoff, int hlen) +{ + struct flow_dissector_key_ipsec *key_ah; + struct ip_auth_hdr _hdr, *hdr; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC)) + return; + + hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); + if (!hdr) + return; + + key_ah = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPSEC, + target_container); + + key_ah->spi = hdr->spi; +} + +static void __skb_flow_dissect_esp(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, const void *data, + int nhoff, int hlen) +{ + struct flow_dissector_key_ipsec *key_esp; + struct ip_esp_hdr _hdr, *hdr; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC)) + return; + + hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); + if (!hdr) + return; + + key_esp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPSEC, + target_container); + + key_esp->spi = hdr->spi; +} + static void __skb_flow_dissect_l2tpv3(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, @@ -1571,7 +1615,14 @@ ip_proto_again: __skb_flow_dissect_l2tpv3(skb, flow_dissector, target_container, data, nhoff, hlen); break; - + case IPPROTO_ESP: + __skb_flow_dissect_esp(skb, flow_dissector, target_container, + data, nhoff, hlen); + break; + case IPPROTO_AH: + __skb_flow_dissect_ah(skb, flow_dissector, target_container, + data, nhoff, hlen); + break; default: break; } -- cgit v1.2.3 From 4c13eda757e3ca72f523d07ed9e5f3e72b374299 Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Tue, 1 Aug 2023 07:10:59 +0530 Subject: tc: flower: support for SPI tc flower rules support to classify ESP/AH packets matching SPI field. Signed-off-by: Ratheesh Kannoth Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 3 +++ net/sched/cls_flower.c | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 7865f5a9885b..75506f157340 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -598,6 +598,9 @@ enum { TCA_FLOWER_KEY_CFM, /* nested */ + TCA_FLOWER_KEY_SPI, /* be32 */ + TCA_FLOWER_KEY_SPI_MASK, /* be32 */ + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 8da9d039d964..eca260272845 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -72,6 +72,7 @@ struct fl_flow_key { struct flow_dissector_key_num_of_vlans num_of_vlans; struct flow_dissector_key_pppoe pppoe; struct flow_dissector_key_l2tpv3 l2tpv3; + struct flow_dissector_key_ipsec ipsec; struct flow_dissector_key_cfm cfm; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ @@ -726,6 +727,8 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_PPPOE_SID] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_PPP_PROTO] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_L2TPV3_SID] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_SPI] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_SPI_MASK] = { .type = NLA_U32 }, [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1), [TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED }, }; @@ -795,6 +798,24 @@ static void fl_set_key_val(struct nlattr **tb, nla_memcpy(mask, tb[mask_type], len); } +static int fl_set_key_spi(struct nlattr **tb, struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + if (key->basic.ip_proto != IPPROTO_ESP && + key->basic.ip_proto != IPPROTO_AH) { + NL_SET_ERR_MSG(extack, + "Protocol must be either ESP or AH"); + return -EINVAL; + } + + fl_set_key_val(tb, &key->ipsec.spi, + TCA_FLOWER_KEY_SPI, + &mask->ipsec.spi, TCA_FLOWER_KEY_SPI_MASK, + sizeof(key->ipsec.spi)); + return 0; +} + static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -1894,6 +1915,12 @@ static int fl_set_key(struct net *net, struct nlattr **tb, return ret; } + if (tb[TCA_FLOWER_KEY_SPI]) { + ret = fl_set_key_spi(tb, key, mask, extack); + if (ret) + return ret; + } + if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] || tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) { key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; @@ -2066,6 +2093,8 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_PPPOE, pppoe); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_L2TPV3, l2tpv3); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_IPSEC, ipsec); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_CFM, cfm); @@ -3364,6 +3393,12 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, sizeof(key->l2tpv3.session_id))) goto nla_put_failure; + if (key->ipsec.spi && + fl_dump_key_val(skb, &key->ipsec.spi, TCA_FLOWER_KEY_SPI, + &mask->ipsec.spi, TCA_FLOWER_KEY_SPI_MASK, + sizeof(key->ipsec.spi))) + goto nla_put_failure; + if ((key->basic.ip_proto == IPPROTO_TCP || key->basic.ip_proto == IPPROTO_UDP || key->basic.ip_proto == IPPROTO_SCTP) && -- cgit v1.2.3 From c8915d7329d6e9164c5c847dc1c56a2c0437053f Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Tue, 1 Aug 2023 07:11:00 +0530 Subject: tc: flower: Enable offload support IPSEC SPI field. This patch enables offload for TC classifier flower rules which matches against SPI field. Signed-off-by: Ratheesh Kannoth Signed-off-by: David S. Miller --- include/net/flow_offload.h | 6 ++++++ net/core/flow_offload.c | 7 +++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 118082eae48c..9efa9a59e81f 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -64,6 +64,10 @@ struct flow_match_tcp { struct flow_dissector_key_tcp *key, *mask; }; +struct flow_match_ipsec { + struct flow_dissector_key_ipsec *key, *mask; +}; + struct flow_match_mpls { struct flow_dissector_key_mpls *key, *mask; }; @@ -116,6 +120,8 @@ void flow_rule_match_ports_range(const struct flow_rule *rule, struct flow_match_ports_range *out); void flow_rule_match_tcp(const struct flow_rule *rule, struct flow_match_tcp *out); +void flow_rule_match_ipsec(const struct flow_rule *rule, + struct flow_match_ipsec *out); void flow_rule_match_icmp(const struct flow_rule *rule, struct flow_match_icmp *out); void flow_rule_match_mpls(const struct flow_rule *rule, diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index acfc1f88ea79..bc5169482710 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -146,6 +146,13 @@ void flow_rule_match_tcp(const struct flow_rule *rule, } EXPORT_SYMBOL(flow_rule_match_tcp); +void flow_rule_match_ipsec(const struct flow_rule *rule, + struct flow_match_ipsec *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPSEC, out); +} +EXPORT_SYMBOL(flow_rule_match_ipsec); + void flow_rule_match_icmp(const struct flow_rule *rule, struct flow_match_icmp *out) { -- cgit v1.2.3 From 9e63a99c566faf2a4b8f6257ea7fea82106612cc Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Tue, 1 Aug 2023 21:39:02 +0800 Subject: udp: Remove unused function declaration udp_bpf_get_proto() commit 8a59f9d1e3d4 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()") left behind this. Signed-off-by: Yue Haibing Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20230801133902.3660-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/udp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/udp.h b/include/net/udp.h index 4d13424f8f72..5a8421cd9083 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -529,7 +529,6 @@ static inline void udp_post_segment_fix_csum(struct sk_buff *skb) #ifdef CONFIG_BPF_SYSCALL struct sk_psock; -struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); #endif -- cgit v1.2.3 From 2fca1b5ef898b131c430eed6f07b8972fb6c9673 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Tue, 1 Aug 2023 22:31:29 +0800 Subject: ila: Remove unnecessary file net/ila.h Commit 642c2c95585d ("ila: xlat changes") removed ila_xlat_outgoing() and ila_xlat_incoming() functions, then this file became unnecessary. Signed-off-by: Yue Haibing Reviewed-by: Larysa Zaremba Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230801143129.40652-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/ila.h | 16 ---------------- net/ipv6/ila/ila_main.c | 1 - net/ipv6/ila/ila_xlat.c | 1 - 3 files changed, 18 deletions(-) delete mode 100644 include/net/ila.h (limited to 'include') diff --git a/include/net/ila.h b/include/net/ila.h deleted file mode 100644 index 73ebe5eab272..000000000000 --- a/include/net/ila.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * ILA kernel interface - * - * Copyright (c) 2015 Tom Herbert - */ - -#ifndef _NET_ILA_H -#define _NET_ILA_H - -struct sk_buff; - -int ila_xlat_outgoing(struct sk_buff *skb); -int ila_xlat_incoming(struct sk_buff *skb); - -#endif /* _NET_ILA_H */ diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c index 3faf62530d6a..69caed07315f 100644 --- a/net/ipv6/ila/ila_main.c +++ b/net/ipv6/ila/ila_main.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include #include #include #include "ila.h" diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index bee45dfeb187..67e8c9440977 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -5,7 +5,6 @@ #include #include #include -#include #include #include #include "ila.h" -- cgit v1.2.3 From f85b1c7da776d0cb2b4509bdd7f406fe5607930b Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Tue, 1 Aug 2023 22:42:09 +0800 Subject: net: switchdev: Remove unused typedef switchdev_obj_dump_cb_t() Commit 29ab586c3d83 ("net: switchdev: Remove bridge bypass support from switchdev") leave this unused. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230801144209.27512-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/switchdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 4d324e2a2eef..0294cfec9c37 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -201,8 +201,6 @@ struct switchdev_obj_in_state_mrp { #define SWITCHDEV_OBJ_IN_STATE_MRP(OBJ) \ container_of((OBJ), struct switchdev_obj_in_state_mrp, obj) -typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); - struct switchdev_brport { struct net_device *dev; const void *ctx; -- cgit v1.2.3 From 6a5a148aaf14747570cc634f9cdfcb0393f5617f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 1 Aug 2023 13:13:58 +0200 Subject: bpf: fix bpf_probe_read_kernel prototype mismatch bpf_probe_read_kernel() has a __weak definition in core.c and another definition with an incompatible prototype in kernel/trace/bpf_trace.c, when CONFIG_BPF_EVENTS is enabled. Since the two are incompatible, there cannot be a shared declaration in a header file, but the lack of a prototype causes a W=1 warning: kernel/bpf/core.c:1638:12: error: no previous prototype for 'bpf_probe_read_kernel' [-Werror=missing-prototypes] On 32-bit architectures, the local prototype u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) passes arguments in other registers as the one in bpf_trace.c BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size, const void *, unsafe_ptr) which uses 64-bit arguments in pairs of registers. As both versions of the function are fairly simple and only really differ in one line, just move them into a header file as an inline function that does not add any overhead for the bpf_trace.c callers and actually avoids a function call for the other one. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/ac25cb0f-b804-1649-3afb-1dc6138c2716@iogearbox.net/ Signed-off-by: Arnd Bergmann Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230801111449.185301-1-arnd@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 12 ++++++++++++ kernel/bpf/core.c | 12 +++--------- kernel/trace/bpf_trace.c | 11 ----------- 3 files changed, 15 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ceaa8c23287f..abe75063630b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2661,6 +2661,18 @@ static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) } #endif /* CONFIG_BPF_SYSCALL */ +static __always_inline int +bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) +{ + int ret = -EFAULT; + + if (IS_ENABLED(CONFIG_BPF_EVENTS)) + ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); + if (unlikely(ret < 0)) + memset(dst, 0, size); + return ret; +} + void __bpf_free_used_btfs(struct bpf_prog_aux *aux, struct btf_mod_pair *used_btfs, u32 len); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index baccdec22f19..0f8f036d8bd1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1650,12 +1650,6 @@ bool bpf_opcode_in_insntable(u8 code) } #ifndef CONFIG_BPF_JIT_ALWAYS_ON -u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) -{ - memset(dst, 0, size); - return -EFAULT; -} - /** * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers @@ -2066,8 +2060,8 @@ out: DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ CONT; \ LDX_PROBE_MEM_##SIZEOP: \ - bpf_probe_read_kernel(&DST, sizeof(SIZE), \ - (const void *)(long) (SRC + insn->off)); \ + bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ + (const void *)(long) (SRC + insn->off)); \ DST = *((SIZE *)&DST); \ CONT; @@ -2082,7 +2076,7 @@ out: DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ CONT; \ LDX_PROBE_MEMSX_##SIZEOP: \ - bpf_probe_read_kernel(&DST, sizeof(SIZE), \ + bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ (const void *)(long) (SRC + insn->off)); \ DST = *((SIZE *)&DST); \ CONT; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c92eb8c6ff08..83bde2475ae5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -223,17 +223,6 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = { .arg3_type = ARG_ANYTHING, }; -static __always_inline int -bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) -{ - int ret; - - ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); - if (unlikely(ret < 0)) - memset(dst, 0, size); - return ret; -} - BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size, const void *, unsafe_ptr) { -- cgit v1.2.3 From bf4ea1d0b2cb2251f9e5619c81daa98591087c33 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Tue, 1 Aug 2023 22:26:20 +0800 Subject: bpf, xdp: Add tracepoint to xdp attaching failure When error happens in dev_xdp_attach(), it should have a way to tell users the error message like the netlink approach. To avoid breaking uapi, adding a tracepoint in bpf_xdp_link_attach() is an appropriate way to notify users the error message. Hence, bpf libraries are able to retrieve the error message by this tracepoint, and then report the error message to users. Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20230801142621.7925-2-hffilwlqm@gmail.com Signed-off-by: Alexei Starovoitov --- include/trace/events/xdp.h | 17 +++++++++++++++++ net/core/dev.c | 5 ++++- 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index c40fc97f9417..cd89f1d5ce7b 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -404,6 +404,23 @@ TRACE_EVENT(mem_return_failed, ) ); +TRACE_EVENT(bpf_xdp_link_attach_failed, + + TP_PROTO(const char *msg), + + TP_ARGS(msg), + + TP_STRUCT__entry( + __string(msg, msg) + ), + + TP_fast_assign( + __assign_str(msg, msg); + ), + + TP_printk("errmsg=%s", __get_str(msg)) +); + #endif /* _TRACE_XDP_H */ #include diff --git a/net/core/dev.c b/net/core/dev.c index 8e7d0cb540cd..002fec07de73 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -133,6 +133,7 @@ #include #include #include +#include #include #include #include @@ -9470,6 +9471,7 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct net *net = current->nsproxy->net_ns; struct bpf_link_primer link_primer; + struct netlink_ext_ack extack = {}; struct bpf_xdp_link *link; struct net_device *dev; int err, fd; @@ -9497,12 +9499,13 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) goto unlock; } - err = dev_xdp_attach_link(dev, NULL, link); + err = dev_xdp_attach_link(dev, &extack, link); rtnl_unlock(); if (err) { link->dev = NULL; bpf_link_cleanup(&link_primer); + trace_bpf_xdp_link_attach_failed(extack._msg); goto out_put_dev; } -- cgit v1.2.3 From 1762f132d54200ffa008e86f9f6c96ab4ee3fb71 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Mon, 31 Jul 2023 14:28:16 +0300 Subject: net/mlx5e: Support IPsec packet offload for RX in switchdev mode As decryption must be done first, add new prio for IPsec offload in FDB, and put it just lower than BYPASS prio and higher than TC prio. Three levels are added for RX. The first one is for ip xfrm policy. SA table is created in the second level for ip xfrm state. The status table is created in the last to check the decryption result. If success, packets continue with the next process, or dropped otherwise. For now, the set of reg c1 is removed for swtichdev mode, and the datapath process will be added in the next patch. Signed-off-by: Jianbo Liu Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/c91063554cf643fb50b99cf093e8a9bf11729de5.1690802064.git.leon@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 4 + .../ethernet/mellanox/mlx5/core/en_accel/ipsec.h | 41 ++++- .../mellanox/mlx5/core/en_accel/ipsec_fs.c | 80 ++++----- .../mellanox/mlx5/core/en_accel/ipsec_offload.c | 5 +- .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c | 184 +++++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h | 39 +++++ drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 6 + include/linux/mlx5/fs.h | 1 + 8 files changed, 313 insertions(+), 47 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 35f00700a4d6..63a2f2bb80a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -75,6 +75,10 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += esw/acl/helper.o \ esw/acl/egress_lgcy.o esw/acl/egress_ofld.o \ esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o +ifneq ($(CONFIG_MLX5_EN_IPSEC),) + mlx5_core-$(CONFIG_MLX5_ESWITCH) += esw/ipsec_fs.o +endif + mlx5_core-$(CONFIG_MLX5_BRIDGE) += esw/bridge.o esw/bridge_mcast.o esw/bridge_debugfs.o \ en/rep/bridge.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 03d83cdf1e20..578af9d7aef3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -143,7 +143,7 @@ struct mlx5e_ipsec_sw_stats { atomic64_t ipsec_tx_drop_trailer; }; -struct mlx5e_ipsec_rx; +struct mlx5e_ipsec_fc; struct mlx5e_ipsec_tx; struct mlx5e_ipsec_work { @@ -180,6 +180,38 @@ struct mlx5e_ipsec_rx_create_attr { enum mlx5_flow_namespace_type chains_ns; }; +struct mlx5e_ipsec_ft { + struct mutex mutex; /* Protect changes to this struct */ + struct mlx5_flow_table *pol; + struct mlx5_flow_table *sa; + struct mlx5_flow_table *status; + u32 refcnt; +}; + +struct mlx5e_ipsec_rule { + struct mlx5_flow_handle *rule; + struct mlx5_modify_hdr *modify_hdr; + struct mlx5_pkt_reformat *pkt_reformat; + struct mlx5_fc *fc; +}; + +struct mlx5e_ipsec_miss { + struct mlx5_flow_group *group; + struct mlx5_flow_handle *rule; +}; + +struct mlx5e_ipsec_rx { + struct mlx5e_ipsec_ft ft; + struct mlx5e_ipsec_miss pol; + struct mlx5e_ipsec_miss sa; + struct mlx5e_ipsec_rule status; + struct mlx5e_ipsec_miss status_drop; + struct mlx5_fc *status_drop_cnt; + struct mlx5e_ipsec_fc *fc; + struct mlx5_fs_chains *chains; + u8 allow_tunnel_mode : 1; +}; + struct mlx5e_ipsec { struct mlx5_core_dev *mdev; struct xarray sadb; @@ -205,13 +237,6 @@ struct mlx5e_ipsec_esn_state { u8 overlap: 1; }; -struct mlx5e_ipsec_rule { - struct mlx5_flow_handle *rule; - struct mlx5_modify_hdr *modify_hdr; - struct mlx5_pkt_reformat *pkt_reformat; - struct mlx5_fc *fc; -}; - struct mlx5e_ipsec_limits { u64 round; u8 soft_limit_hit : 1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 52e382948c13..2db16e49abc1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -9,6 +9,7 @@ #include "fs_core.h" #include "lib/ipsec_fs_roce.h" #include "lib/fs_chains.h" +#include "esw/ipsec_fs.h" #define NUM_IPSEC_FTE BIT(15) #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16 @@ -19,29 +20,6 @@ struct mlx5e_ipsec_fc { struct mlx5_fc *drop; }; -struct mlx5e_ipsec_ft { - struct mutex mutex; /* Protect changes to this struct */ - struct mlx5_flow_table *pol; - struct mlx5_flow_table *sa; - struct mlx5_flow_table *status; - u32 refcnt; -}; - -struct mlx5e_ipsec_miss { - struct mlx5_flow_group *group; - struct mlx5_flow_handle *rule; -}; - -struct mlx5e_ipsec_rx { - struct mlx5e_ipsec_ft ft; - struct mlx5e_ipsec_miss pol; - struct mlx5e_ipsec_miss sa; - struct mlx5e_ipsec_rule status; - struct mlx5e_ipsec_fc *fc; - struct mlx5_fs_chains *chains; - u8 allow_tunnel_mode : 1; -}; - struct mlx5e_ipsec_tx { struct mlx5e_ipsec_ft ft; struct mlx5e_ipsec_miss pol; @@ -259,9 +237,9 @@ static void ipsec_rx_ft_disconnect(struct mlx5e_ipsec *ipsec, u32 family) static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx, u32 family) { - /* disconnect */ - ipsec_rx_ft_disconnect(ipsec, family); + if (rx != ipsec->rx_esw) + ipsec_rx_ft_disconnect(ipsec, family); if (rx->chains) { ipsec_chains_destroy(rx->chains); @@ -276,8 +254,12 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, mlx5_destroy_flow_table(rx->ft.sa); if (rx->allow_tunnel_mode) mlx5_eswitch_unblock_encap(mdev); - mlx5_del_flow_rules(rx->status.rule); - mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); + if (rx == ipsec->rx_esw) { + mlx5_esw_ipsec_rx_status_destroy(ipsec, rx); + } else { + mlx5_del_flow_rules(rx->status.rule); + mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); + } mlx5_destroy_flow_table(rx->ft.status); mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family); @@ -288,6 +270,13 @@ static void ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, u32 family, struct mlx5e_ipsec_rx_create_attr *attr) { + if (rx == ipsec->rx_esw) { + /* For packet offload in switchdev mode, RX & TX use FDB namespace */ + attr->ns = ipsec->tx_esw->ns; + mlx5_esw_ipsec_rx_create_attr_set(ipsec, attr); + return; + } + attr->ns = mlx5e_fs_get_ns(ipsec->fs, false); attr->ttc = mlx5e_fs_get_ttc(ipsec->fs, false); attr->family = family; @@ -306,6 +295,9 @@ static int ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec, struct mlx5_flow_table *ft; int err; + if (rx == ipsec->rx_esw) + return mlx5_esw_ipsec_rx_status_pass_dest_get(ipsec, dest); + *dest = mlx5_ttc_get_default_dest(attr->ttc, family2tt(attr->family)); err = mlx5_ipsec_fs_roce_rx_create(ipsec->mdev, ipsec->roce, attr->ns, dest, attr->family, MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL, @@ -357,7 +349,10 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; dest[1].counter_id = mlx5_fc_id(rx->fc->cnt); - err = ipsec_status_rule(mdev, rx, dest); + if (rx == ipsec->rx_esw) + err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest); + else + err = ipsec_status_rule(mdev, rx, dest); if (err) goto err_add; @@ -406,7 +401,8 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, connect: /* connect */ - ipsec_rx_ft_connect(ipsec, rx, &attr); + if (rx != ipsec->rx_esw) + ipsec_rx_ft_connect(ipsec, rx, &attr); return 0; err_pol_miss: @@ -864,18 +860,22 @@ static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upsp } } -static enum mlx5_flow_namespace_type ipsec_fs_get_ns(struct mlx5e_ipsec *ipsec, u8 dir) +static enum mlx5_flow_namespace_type ipsec_fs_get_ns(struct mlx5e_ipsec *ipsec, + int type, u8 dir) { + if (ipsec->is_uplink_rep && type == XFRM_DEV_OFFLOAD_PACKET) + return MLX5_FLOW_NAMESPACE_FDB; + if (dir == XFRM_DEV_OFFLOAD_IN) return MLX5_FLOW_NAMESPACE_KERNEL; return MLX5_FLOW_NAMESPACE_EGRESS; } -static int setup_modify_header(struct mlx5e_ipsec *ipsec, u32 val, u8 dir, +static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8 dir, struct mlx5_flow_act *flow_act) { - enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, dir); + enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, type, dir); u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; struct mlx5_core_dev *mdev = ipsec->mdev; struct mlx5_modify_hdr *modify_hdr; @@ -1085,7 +1085,8 @@ static int setup_pkt_reformat(struct mlx5e_ipsec *ipsec, struct mlx5_accel_esp_xfrm_attrs *attrs, struct mlx5_flow_act *flow_act) { - enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, attrs->dir); + enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, attrs->type, + attrs->dir); struct mlx5_pkt_reformat_params reformat_params = {}; struct mlx5_core_dev *mdev = ipsec->mdev; struct mlx5_pkt_reformat *pkt_reformat; @@ -1127,7 +1128,7 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) struct mlx5_flow_spec *spec; struct mlx5e_ipsec_rx *rx; struct mlx5_fc *counter; - int err; + int err = 0; rx = rx_ft_get(mdev, ipsec, attrs->family, attrs->type); if (IS_ERR(rx)) @@ -1148,8 +1149,10 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) setup_fte_esp(spec); setup_fte_no_frags(spec); - err = setup_modify_header(ipsec, sa_entry->ipsec_obj_id | BIT(31), - XFRM_DEV_OFFLOAD_IN, &flow_act); + if (rx != ipsec->rx_esw) + err = setup_modify_header(ipsec, attrs->type, + sa_entry->ipsec_obj_id | BIT(31), + XFRM_DEV_OFFLOAD_IN, &flow_act); if (err) goto err_mod_header; @@ -1340,7 +1343,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry) if (!attrs->reqid) break; - err = setup_modify_header(ipsec, attrs->reqid, + err = setup_modify_header(ipsec, attrs->type, attrs->reqid, XFRM_DEV_OFFLOAD_OUT, &flow_act); if (err) goto err_mod_header; @@ -1388,6 +1391,7 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry) { struct mlx5_accel_pol_xfrm_attrs *attrs = &pol_entry->attrs; struct mlx5_core_dev *mdev = mlx5e_ipsec_pol2dev(pol_entry); + struct mlx5e_ipsec *ipsec = pol_entry->ipsec; struct mlx5_flow_destination dest[2]; struct mlx5_flow_act flow_act = {}; struct mlx5_flow_handle *rule; @@ -1433,6 +1437,8 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry) } flow_act.flags |= FLOW_ACT_NO_APPEND; + if (rx == ipsec->rx_esw && rx->chains) + flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest[dstn].ft = rx->ft.sa; dstn++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 5ff06263c5bd..3245d1c9d539 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -45,8 +45,9 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap)) caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD; - if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) && - MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) + if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) || + MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level)) caps |= MLX5_IPSEC_CAP_PRIO; if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c new file mode 100644 index 000000000000..7df7a8b0a6a0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "fs_core.h" +#include "eswitch.h" +#include "en_accel/ipsec.h" +#include "esw/ipsec_fs.h" + +enum { + MLX5_ESW_IPSEC_RX_POL_FT_LEVEL, + MLX5_ESW_IPSEC_RX_ESP_FT_LEVEL, + MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL, +}; + +static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + mlx5_del_flow_rules(rx->status_drop.rule); + mlx5_destroy_flow_group(rx->status_drop.group); + mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt); +} + +static void esw_ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + mlx5_del_flow_rules(rx->status.rule); + mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0); +} + +static int esw_ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; + struct mlx5_flow_spec *spec; + struct mlx5_flow_group *g; + u32 *flow_group_in; + int err = 0; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!flow_group_in || !spec) { + err = -ENOMEM; + goto err_out; + } + + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1); + g = mlx5_create_flow_group(ft, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop flow group, err=%d\n", err); + goto err_out; + } + + flow_counter = mlx5_fc_create(mdev, false); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; + } + + rx->status_drop.group = g; + rx->status_drop.rule = rule; + rx->status_drop_cnt = flow_counter; + + kvfree(flow_group_in); + kvfree(spec); + return 0; + +err_rule: + mlx5_fc_destroy(mdev, flow_counter); +err_cnt: + mlx5_destroy_flow_group(g); +err_out: + kvfree(flow_group_in); + kvfree(spec); + return err; +} + +static int esw_ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + int err; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters_2.ipsec_syndrome); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.ipsec_syndrome, 0); + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + flow_act.flags = FLOW_ACT_NO_APPEND; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_warn(ipsec->mdev, + "Failed to add ipsec rx status pass rule, err=%d\n", err); + goto err_rule; + } + + rx->status.rule = rule; + kvfree(spec); + return 0; + +err_rule: + kvfree(spec); + return err; +} + +void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + esw_ipsec_rx_status_pass_destroy(ipsec, rx); + esw_ipsec_rx_status_drop_destroy(ipsec, rx); +} + +int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + int err; + + err = esw_ipsec_rx_status_drop_create(ipsec, rx); + if (err) + return err; + + err = esw_ipsec_rx_status_pass_create(ipsec, rx, dest); + if (err) + goto err_pass_create; + + return 0; + +err_pass_create: + esw_ipsec_rx_status_drop_destroy(ipsec, rx); + return err; +} + +void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx_create_attr *attr) +{ + attr->prio = FDB_CRYPTO_INGRESS; + attr->pol_level = MLX5_ESW_IPSEC_RX_POL_FT_LEVEL; + attr->sa_level = MLX5_ESW_IPSEC_RX_ESP_FT_LEVEL; + attr->status_level = MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL; + attr->chains_ns = MLX5_FLOW_NAMESPACE_FDB; +} + +int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec, + struct mlx5_flow_destination *dest) +{ + dest->type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest->ft = mlx5_chains_get_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h new file mode 100644 index 000000000000..1d6104648d32 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_ESW_IPSEC_FS_H__ +#define __MLX5_ESW_IPSEC_FS_H__ + +struct mlx5e_ipsec; + +#ifdef CONFIG_MLX5_ESWITCH +void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx); +int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest); +void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx_create_attr *attr); +int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec, + struct mlx5_flow_destination *dest); +#else +static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) {} + +static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + return -EINVAL; +} + +static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx_create_attr *attr) {} + +static inline int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec, + struct mlx5_flow_destination *dest) +{ + return -EINVAL; +} +#endif /* CONFIG_MLX5_ESWITCH */ +#endif /* __MLX5_ESW_IPSEC_FS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 4ef04aa28771..8ae1854d6b73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2987,6 +2987,12 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) if (err) goto out_err; + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_CRYPTO_INGRESS, 3); + if (IS_ERR(maj_prio)) { + err = PTR_ERR(maj_prio); + goto out_err; + } + err = create_fdb_fast_path(steering); if (err) goto out_err; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 2cb404c7ea13..6b1fa94f69c8 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -109,6 +109,7 @@ enum mlx5_flow_namespace_type { enum { FDB_BYPASS_PATH, + FDB_CRYPTO_INGRESS, FDB_TC_OFFLOAD, FDB_FT_OFFLOAD, FDB_TC_MISS, -- cgit v1.2.3 From 91bafc638ed4128eaca074fe7e88a5444db14325 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Mon, 31 Jul 2023 14:28:17 +0300 Subject: net/mlx5e: Handle IPsec offload for RX datapath in switchdev mode Reuse tun opts bits in reg c1, to pass IPsec obj id to datapath. As this is only for RX SA and there are only 11 bits, xarray is used to map IPsec obj id to an index, which is between 1 and 0x7ff, and replace obj id to write to reg c1. Signed-off-by: Jianbo Liu Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/43d60fbcc9cd672a97d7e2a2f7fe6a3d9e9a776d.1690802064.git.leon@kernel.org Signed-off-by: Jakub Kicinski --- .../net/ethernet/mellanox/mlx5/core/en/rep/tc.c | 17 +++++- .../ethernet/mellanox/mlx5/core/en_accel/ipsec.h | 2 + .../mellanox/mlx5/core/en_accel/ipsec_fs.c | 7 +++ .../mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 22 +++++++ .../mellanox/mlx5/core/en_accel/ipsec_rxtx.h | 2 + .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c | 69 ++++++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h | 20 +++++++ include/linux/mlx5/eswitch.h | 3 + 8 files changed, 139 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index b5c773ffc763..b12fe3c5a258 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -715,9 +715,20 @@ void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, uplink_priv = &uplink_rpriv->uplink_priv; ct_priv = uplink_priv->ct_priv; - if (!mlx5_ipsec_is_rx_flow(cqe) && - !mlx5e_tc_update_skb(cqe, skb, mapping_ctx, reg_c0, ct_priv, zone_restore_id, tunnel_id, - &tc_priv)) +#ifdef CONFIG_MLX5_EN_IPSEC + if (!(tunnel_id >> ESW_TUN_OPTS_BITS)) { + u32 mapped_id; + u32 metadata; + + mapped_id = tunnel_id & ESW_IPSEC_RX_MAPPED_ID_MASK; + if (mapped_id && + !mlx5_esw_ipsec_rx_make_metadata(priv, mapped_id, &metadata)) + mlx5e_ipsec_offload_handle_rx_skb(priv->netdev, skb, metadata); + } +#endif + + if (!mlx5e_tc_update_skb(cqe, skb, mapping_ctx, reg_c0, ct_priv, + zone_restore_id, tunnel_id, &tc_priv)) goto free_skb; forward: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 578af9d7aef3..168b9600bde3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -210,6 +210,7 @@ struct mlx5e_ipsec_rx { struct mlx5e_ipsec_fc *fc; struct mlx5_fs_chains *chains; u8 allow_tunnel_mode : 1; + struct xarray ipsec_obj_id_map; }; struct mlx5e_ipsec { @@ -256,6 +257,7 @@ struct mlx5e_ipsec_sa_entry { struct mlx5e_ipsec_work *work; struct mlx5e_ipsec_dwork *dwork; struct mlx5e_ipsec_limits limits; + u32 rx_mapped_id; }; struct mlx5_accel_pol_xfrm_attrs { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 2db16e49abc1..84322e85cd23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -1153,6 +1153,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) err = setup_modify_header(ipsec, attrs->type, sa_entry->ipsec_obj_id | BIT(31), XFRM_DEV_OFFLOAD_IN, &flow_act); + else + err = mlx5_esw_ipsec_rx_setup_modify_header(sa_entry, &flow_act); + if (err) goto err_mod_header; @@ -1641,6 +1644,7 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry) } mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr); + mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry); rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type); } @@ -1693,6 +1697,8 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec) kfree(ipsec->rx_ipv6); if (ipsec->is_uplink_rep) { + xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map); + mutex_destroy(&ipsec->tx_esw->ft.mutex); WARN_ON(ipsec->tx_esw->ft.refcnt); kfree(ipsec->tx_esw); @@ -1753,6 +1759,7 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec) mutex_init(&ipsec->tx_esw->ft.mutex); mutex_init(&ipsec->rx_esw->ft.mutex); ipsec->tx_esw->ns = ns_esw; + xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1); } else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) { ipsec->roce = mlx5_ipsec_fs_roce_init(mdev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 8d6379ac4574..c00fe0d5ea11 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -37,6 +37,7 @@ #include "ipsec.h" #include "ipsec_rxtx.h" #include "en.h" +#include "esw/ipsec_fs.h" enum { MLX5E_IPSEC_TX_SYNDROME_OFFLOAD = 0x8, @@ -355,3 +356,24 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_syndrome); } } + +int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metadata) +{ + struct mlx5e_ipsec *ipsec = priv->ipsec; + u32 ipsec_obj_id; + int err; + + if (!ipsec || !ipsec->is_uplink_rep) + return -EINVAL; + + err = mlx5_esw_ipsec_rx_ipsec_obj_id_search(priv, id, &ipsec_obj_id); + if (err) { + atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_sadb_miss); + return err; + } + + *metadata = MLX5_IPSEC_METADATA_CREATE(ipsec_obj_id, + MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 436e9a8a32d3..9ee014a8ad24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -43,6 +43,7 @@ #define MLX5_IPSEC_METADATA_MARKER(metadata) (((metadata) >> 31) & 0x1) #define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(5, 0)) #define MLX5_IPSEC_METADATA_HANDLE(metadata) ((metadata) & GENMASK(23, 0)) +#define MLX5_IPSEC_METADATA_CREATE(id, syndrome) ((id) | ((syndrome) << 24)) struct mlx5e_accel_tx_ipsec_state { struct xfrm_offload *xo; @@ -67,6 +68,7 @@ void mlx5e_ipsec_handle_tx_wqe(struct mlx5e_tx_wqe *wqe, void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb, u32 ipsec_meta_data); +int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metadata); static inline unsigned int mlx5e_ipsec_tx_ids_len(struct mlx5e_accel_tx_ipsec_state *ipsec_st) { return ipsec_st->tailen; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 7df7a8b0a6a0..0675587c1a79 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -182,3 +182,72 @@ int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec, return 0; } + +int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5_flow_act *flow_act) +{ + u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_modify_hdr *modify_hdr; + u32 mapped_id; + int err; + + err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id, + xa_mk_value(sa_entry->ipsec_obj_id), + XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0); + if (err) + return err; + + /* reuse tunnel bits for ipsec, + * tun_id is always 0 and tun_opts is mapped to ipsec_obj_id. + */ + MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action, field, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_1); + MLX5_SET(set_action_in, action, offset, ESW_ZONE_ID_BITS); + MLX5_SET(set_action_in, action, length, + ESW_TUN_ID_BITS + ESW_TUN_OPTS_BITS); + MLX5_SET(set_action_in, action, data, mapped_id); + + modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_FDB, + 1, action); + if (IS_ERR(modify_hdr)) { + err = PTR_ERR(modify_hdr); + goto err_header_alloc; + } + + sa_entry->rx_mapped_id = mapped_id; + flow_act->modify_hdr = modify_hdr; + flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + + return 0; + +err_header_alloc: + xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id); + return err; +} + +void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry) +{ + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + + if (sa_entry->rx_mapped_id) + xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, + sa_entry->rx_mapped_id); +} + +int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id, + u32 *ipsec_obj_id) +{ + struct mlx5e_ipsec *ipsec = priv->ipsec; + void *val; + + val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id); + if (!val) + return -ENOENT; + + *ipsec_obj_id = xa_to_value(val); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h index 1d6104648d32..44df34032d1e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h @@ -5,6 +5,7 @@ #define __MLX5_ESW_IPSEC_FS_H__ struct mlx5e_ipsec; +struct mlx5e_ipsec_sa_entry; #ifdef CONFIG_MLX5_ESWITCH void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, @@ -16,6 +17,11 @@ void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr); int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec, struct mlx5_flow_destination *dest); +int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5_flow_act *flow_act); +void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry); +int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id, + u32 *ipsec_obj_id); #else static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx) {} @@ -35,5 +41,19 @@ static inline int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ips { return -EINVAL; } + +static inline int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5_flow_act *flow_act) +{ + return -EINVAL; +} + +static inline void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry) {} + +static inline int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id, + u32 *ipsec_obj_id) +{ + return -EINVAL; +} #endif /* CONFIG_MLX5_ESWITCH */ #endif /* __MLX5_ESW_IPSEC_FS_H__ */ diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index e2701ed0200e..950d2431a53c 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -144,6 +144,9 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \ ESW_TUN_OPTS_OFFSET + 1) +/* reuse tun_opts for the mapped ipsec obj id when tun_id is 0 (invalid) */ +#define ESW_IPSEC_RX_MAPPED_ID_MASK GENMASK(ESW_TUN_OPTS_BITS - 1, 0) + u8 mlx5_eswitch_mode(const 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); -- cgit v1.2.3 From c6c2bf5db4ea14b316af1fd03cc6c5c61f751f79 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Mon, 31 Jul 2023 14:28:19 +0300 Subject: net/mlx5e: Support IPsec packet offload for TX in switchdev mode The IPsec encryption is done at the last, so add new prio for IPsec offload in FDB, and put it just lower than the slow path prio and higher than the per-vport prio. Three levels are added for TX. The first one is for ip xfrm policy. The sa table is created in the second level for ip xfrm state. The status table is created at the last to count the number of packets encrypted. The rules, which forward packets to uplink, are changed to forward them to IPsec TX tables first. These rules are restored after those tables are destroyed, which is done immediately when there is no reference to them, just as what does in legacy mode. The support for slow path is added here, by refreshing uplink's channels. But, the handling for TC fast path, which is more complicated, will be added later. Besides, reg c4 is used instead to match reqid. Signed-off-by: Jianbo Liu Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/cfd0e6ffaf0b8c55ebaa9fb0649b7c504b6b8ec6.1690802064.git.leon@kernel.org Signed-off-by: Jakub Kicinski --- .../mellanox/mlx5/core/en_accel/ipsec_fs.c | 70 +++++++++++++++++++--- .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c | 16 +++++ .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h | 5 ++ drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 1 + .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 11 ++++ drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 6 ++ include/linux/mlx5/fs.h | 1 + 7 files changed, 101 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 6d4d2b824b75..36704c9fce33 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -10,6 +10,7 @@ #include "lib/ipsec_fs_roce.h" #include "lib/fs_chains.h" #include "esw/ipsec_fs.h" +#include "en_rep.h" #define NUM_IPSEC_FTE BIT(15) #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16 @@ -23,6 +24,7 @@ struct mlx5e_ipsec_fc { struct mlx5e_ipsec_tx { struct mlx5e_ipsec_ft ft; struct mlx5e_ipsec_miss pol; + struct mlx5e_ipsec_miss sa; struct mlx5e_ipsec_rule status; struct mlx5_flow_namespace *ns; struct mlx5e_ipsec_fc *fc; @@ -550,7 +552,7 @@ err_rule: } /* IPsec TX flow steering */ -static void tx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx, +static void tx_destroy(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx, struct mlx5_ipsec_fs *roce) { mlx5_ipsec_fs_roce_tx_destroy(roce); @@ -562,9 +564,13 @@ static void tx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx, mlx5_destroy_flow_table(tx->ft.pol); } + if (tx == ipsec->tx_esw) { + mlx5_del_flow_rules(tx->sa.rule); + mlx5_destroy_flow_group(tx->sa.group); + } mlx5_destroy_flow_table(tx->ft.sa); if (tx->allow_tunnel_mode) - mlx5_eswitch_unblock_encap(mdev); + mlx5_eswitch_unblock_encap(ipsec->mdev); mlx5_del_flow_rules(tx->status.rule); mlx5_destroy_flow_table(tx->ft.status); } @@ -573,6 +579,11 @@ static void ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx, struct mlx5e_ipsec_tx_create_attr *attr) { + if (tx == ipsec->tx_esw) { + mlx5_esw_ipsec_tx_create_attr_set(ipsec, attr); + return; + } + attr->prio = 0; attr->pol_level = 0; attr->sa_level = 1; @@ -611,6 +622,15 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx, } tx->ft.sa = ft; + if (tx == ipsec->tx_esw) { + dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + dest.vport.num = MLX5_VPORT_UPLINK; + err = ipsec_miss_create(mdev, tx->ft.sa, &tx->sa, &dest); + if (err) + goto err_sa_miss; + memset(&dest, 0, sizeof(dest)); + } + if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) { tx->chains = ipsec_chains_create( mdev, tx->ft.sa, attr.chains_ns, attr.prio, attr.pol_level, @@ -652,6 +672,11 @@ err_roce: mlx5_destroy_flow_table(tx->ft.pol); } err_pol_ft: + if (tx == ipsec->tx_esw) { + mlx5_del_flow_rules(tx->sa.rule); + mlx5_destroy_flow_group(tx->sa.group); + } +err_sa_miss: mlx5_destroy_flow_table(tx->ft.sa); err_sa_ft: if (tx->allow_tunnel_mode) @@ -662,6 +687,25 @@ err_status_rule: return err; } +static void ipsec_esw_tx_ft_policy_set(struct mlx5_core_dev *mdev, + struct mlx5_flow_table *ft) +{ +#ifdef CONFIG_MLX5_ESWITCH + struct mlx5_eswitch *esw = mdev->priv.eswitch; + struct mlx5e_rep_priv *uplink_rpriv; + struct mlx5e_priv *priv; + + esw->offloads.ft_ipsec_tx_pol = ft; + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + priv = netdev_priv(uplink_rpriv->netdev); + if (!priv->channels.num) + return; + + mlx5e_rep_deactivate_channels(priv); + mlx5e_rep_activate_channels(priv); +#endif +} + static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx) { @@ -674,6 +718,9 @@ static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, if (err) return err; + if (tx == ipsec->tx_esw) + ipsec_esw_tx_ft_policy_set(mdev, tx->ft.pol); + skip: tx->ft.refcnt++; return 0; @@ -684,7 +731,10 @@ static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx) if (--tx->ft.refcnt) return; - tx_destroy(ipsec->mdev, tx, ipsec->roce); + if (tx == ipsec->tx_esw) + ipsec_esw_tx_ft_policy_set(ipsec->mdev, NULL); + + tx_destroy(ipsec, tx, ipsec->roce); } static struct mlx5_flow_table *tx_ft_get_policy(struct mlx5_core_dev *mdev, @@ -842,15 +892,15 @@ static void setup_fte_reg_a(struct mlx5_flow_spec *spec) misc_parameters_2.metadata_reg_a, MLX5_ETH_WQE_FT_META_IPSEC); } -static void setup_fte_reg_c0(struct mlx5_flow_spec *spec, u32 reqid) +static void setup_fte_reg_c4(struct mlx5_flow_spec *spec, u32 reqid) { /* Pass policy check before choosing this SA */ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; - MLX5_SET(fte_match_param, spec->match_criteria, - misc_parameters_2.metadata_reg_c_0, reqid); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters_2.metadata_reg_c_4); MLX5_SET(fte_match_param, spec->match_value, - misc_parameters_2.metadata_reg_c_0, reqid); + misc_parameters_2.metadata_reg_c_4, reqid); } static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upspec *upspec) @@ -902,7 +952,7 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8 break; case XFRM_DEV_OFFLOAD_OUT: MLX5_SET(set_action_in, action, field, - MLX5_ACTION_IN_FIELD_METADATA_REG_C_0); + MLX5_ACTION_IN_FIELD_METADATA_REG_C_4); break; default: return -EINVAL; @@ -1268,7 +1318,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) break; case XFRM_DEV_OFFLOAD_PACKET: if (attrs->reqid) - setup_fte_reg_c0(spec, attrs->reqid); + setup_fte_reg_c4(spec, attrs->reqid); err = setup_pkt_reformat(ipsec, attrs, &flow_act); if (err) goto err_pkt_reformat; @@ -1379,6 +1429,8 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry) } flow_act.flags |= FLOW_ACT_NO_APPEND; + if (tx == ipsec->tx_esw && tx->chains) + flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; dest[dstn].ft = tx->ft.sa; dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dstn++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 0675587c1a79..e60cd3dc1b13 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -12,6 +12,12 @@ enum { MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL, }; +enum { + MLX5_ESW_IPSEC_TX_POL_FT_LEVEL, + MLX5_ESW_IPSEC_TX_ESP_FT_LEVEL, + MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL, +}; + static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx) { @@ -251,3 +257,13 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id, return 0; } + +void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_tx_create_attr *attr) +{ + attr->prio = FDB_CRYPTO_EGRESS; + attr->pol_level = MLX5_ESW_IPSEC_TX_POL_FT_LEVEL; + attr->sa_level = MLX5_ESW_IPSEC_TX_ESP_FT_LEVEL; + attr->cnt_level = MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL; + attr->chains_ns = MLX5_FLOW_NAMESPACE_FDB; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h index 44df34032d1e..275684f99ed3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h @@ -22,6 +22,8 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry, void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry); int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id, u32 *ipsec_obj_id); +void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_tx_create_attr *attr); #else static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx *rx) {} @@ -55,5 +57,8 @@ static inline int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, { return -EINVAL; } + +static inline void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_tx_create_attr *attr) {} #endif /* CONFIG_MLX5_ESWITCH */ #endif /* __MLX5_ESW_IPSEC_FS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 2944c9207487..c7b5faae20a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -254,6 +254,7 @@ struct mlx5_esw_offload { struct mlx5_flow_group *vport_rx_group; struct mlx5_flow_group *vport_rx_drop_group; struct mlx5_flow_handle *vport_rx_drop_rule; + struct mlx5_flow_table *ft_ipsec_tx_pol; struct xarray vport_reps; struct list_head peer_flows[MLX5_MAX_PORTS]; struct mutex peer_mutex; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f83667b4339e..dc22a7f959e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -884,6 +884,17 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + if (rep->vport == MLX5_VPORT_UPLINK && on_esw->offloads.ft_ipsec_tx_pol) { + dest.ft = on_esw->offloads.ft_ipsec_tx_pol; + flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL; + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + } else { + dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + dest.vport.num = rep->vport; + dest.vport.vhca_id = MLX5_CAP_GEN(rep->esw->dev, vhca_id); + dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; + } + if (MLX5_CAP_ESW_FLOWTABLE(on_esw->dev, flow_source) && rep->vport == MLX5_VPORT_UPLINK) spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 8ae1854d6b73..830ff8480fe1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -3015,6 +3015,12 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) goto out_err; } + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_CRYPTO_EGRESS, 3); + if (IS_ERR(maj_prio)) { + err = PTR_ERR(maj_prio); + goto out_err; + } + /* We put this priority last, knowing that nothing will get here * unless explicitly forwarded to. This is possible because the * slow path tables have catch all rules and nothing gets passed diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 6b1fa94f69c8..c302ec34255b 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -115,6 +115,7 @@ enum { FDB_TC_MISS, FDB_BR_OFFLOAD, FDB_SLOW_PATH, + FDB_CRYPTO_EGRESS, FDB_PER_VPORT, }; -- cgit v1.2.3 From c8e350e62fc51f3fda28f166fc402f4fb539f528 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Mon, 31 Jul 2023 14:28:24 +0300 Subject: net/mlx5e: Make TC and IPsec offloads mutually exclusive on a netdev For IPsec packet offload mode, the order of TC offload and IPsec offload on the same netdevice is not aligned with the order in the non-offload software. For example, for RX, the software performs TC first and then IPsec transformation, but the implementation for offload does that in the opposite way. To resolve the difference for now, either IPsec offload or TC offload, not both, is allowed for a specific interface. Signed-off-by: Jianbo Liu Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/8e2e5e3b0984d785066e8663aaf97b3ba1bb873f.1690802064.git.leon@kernel.org Signed-off-by: Jakub Kicinski --- .../mellanox/mlx5/core/en_accel/ipsec_fs.c | 84 ++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 47 ++++++++++++ include/linux/mlx5/driver.h | 2 + 3 files changed, 129 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index f635b5f6e886..9a5b67344277 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -1717,12 +1717,68 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats) } } +#ifdef CONFIG_MLX5_ESWITCH +static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int err = 0; + + if (esw) + down_write(&esw->mode_lock); + + if (mdev->num_block_ipsec) { + err = -EBUSY; + goto unlock; + } + + mdev->num_block_tc++; + +unlock: + if (esw) + up_write(&esw->mode_lock); + + return err; +} +#else +static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) +{ + if (mdev->num_block_ipsec) + return -EBUSY; + + mdev->num_block_tc++; + return 0; +} +#endif + +static void mlx5e_ipsec_unblock_tc_offload(struct mlx5_core_dev *mdev) +{ + mdev->num_block_tc++; +} + int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) { + int err; + + if (sa_entry->attrs.type == XFRM_DEV_OFFLOAD_PACKET) { + err = mlx5e_ipsec_block_tc_offload(sa_entry->ipsec->mdev); + if (err) + return err; + } + if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT) - return tx_add_rule(sa_entry); + err = tx_add_rule(sa_entry); + else + err = rx_add_rule(sa_entry); + + if (err) + goto err_out; + + return 0; - return rx_add_rule(sa_entry); +err_out: + if (sa_entry->attrs.type == XFRM_DEV_OFFLOAD_PACKET) + mlx5e_ipsec_unblock_tc_offload(sa_entry->ipsec->mdev); + return err; } void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry) @@ -1735,6 +1791,9 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry) if (ipsec_rule->pkt_reformat) mlx5_packet_reformat_dealloc(mdev, ipsec_rule->pkt_reformat); + if (sa_entry->attrs.type == XFRM_DEV_OFFLOAD_PACKET) + mlx5e_ipsec_unblock_tc_offload(mdev); + if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT) { tx_ft_put(sa_entry->ipsec, sa_entry->attrs.type); return; @@ -1747,10 +1806,25 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry) int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry) { + int err; + + err = mlx5e_ipsec_block_tc_offload(pol_entry->ipsec->mdev); + if (err) + return err; + if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT) - return tx_add_policy(pol_entry); + err = tx_add_policy(pol_entry); + else + err = rx_add_policy(pol_entry); + + if (err) + goto err_out; + + return 0; - return rx_add_policy(pol_entry); +err_out: + mlx5e_ipsec_unblock_tc_offload(pol_entry->ipsec->mdev); + return err; } void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry) @@ -1760,6 +1834,8 @@ void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry) mlx5_del_flow_rules(ipsec_rule->rule); + mlx5e_ipsec_unblock_tc_offload(pol_entry->ipsec->mdev); + if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) { rx_ft_put_policy(pol_entry->ipsec, pol_entry->attrs.family, pol_entry->attrs.prio, pol_entry->attrs.type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index dfd282319753..7d2a029e0932 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4606,6 +4606,46 @@ static bool is_flow_rule_duplicate_allowed(struct net_device *dev, return netif_is_lag_port(dev) && rpriv && rpriv->rep->vport != MLX5_VPORT_UPLINK; } +/* As IPsec and TC order is not aligned between software and hardware-offload, + * either IPsec offload or TC offload, not both, is allowed for a specific interface. + */ +static bool is_tc_ipsec_order_check_needed(struct net_device *filter, struct mlx5e_priv *priv) +{ + if (!IS_ENABLED(CONFIG_MLX5_EN_IPSEC)) + return false; + + if (filter != priv->netdev) + return false; + + if (mlx5e_eswitch_vf_rep(priv->netdev)) + return false; + + return true; +} + +static int mlx5e_tc_block_ipsec_offload(struct net_device *filter, struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + + if (!is_tc_ipsec_order_check_needed(filter, priv)) + return 0; + + if (mdev->num_block_tc) + return -EBUSY; + + mdev->num_block_ipsec++; + + return 0; +} + +static void mlx5e_tc_unblock_ipsec_offload(struct net_device *filter, struct mlx5e_priv *priv) +{ + if (!is_tc_ipsec_order_check_needed(filter, priv)) + return; + + priv->mdev->num_block_ipsec--; +} + int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, struct flow_cls_offload *f, unsigned long flags) { @@ -4618,6 +4658,10 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, if (!mlx5_esw_hold(priv->mdev)) return -EBUSY; + err = mlx5e_tc_block_ipsec_offload(dev, priv); + if (err) + goto esw_release; + mlx5_esw_get(priv->mdev); rcu_read_lock(); @@ -4663,7 +4707,9 @@ rcu_unlock: err_free: mlx5e_flow_put(priv, flow); out: + mlx5e_tc_unblock_ipsec_offload(dev, priv); mlx5_esw_put(priv->mdev); +esw_release: mlx5_esw_release(priv->mdev); return err; } @@ -4704,6 +4750,7 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv, trace_mlx5e_delete_flower(f); mlx5e_flow_put(priv, flow); + mlx5e_tc_unblock_ipsec_offload(dev, priv); mlx5_esw_put(priv->mdev); return 0; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f21703fb75fd..fa70c25423b2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -806,6 +806,8 @@ struct mlx5_core_dev { u32 vsc_addr; struct mlx5_hv_vhca *hv_vhca; struct mlx5_thermal *thermal; + u64 num_block_tc; + u64 num_block_ipsec; }; struct mlx5_db { -- cgit v1.2.3 From 49c467dca39df9a3674854969cc5a8eb7170682d Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 31 Jul 2023 22:10:30 +0800 Subject: sctp: Remove unused function declarations These declarations are never implemented since beginning of git history. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Acked-by: Xin Long Link: https://lore.kernel.org/r/20230731141030.32772-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/sctp/sm.h | 3 --- include/net/sctp/structs.h | 2 -- 2 files changed, 5 deletions(-) (limited to 'include') diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index f37c7a558d6d..64c42bd56bb2 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -156,7 +156,6 @@ sctp_state_fn_t sctp_sf_do_6_2_sack; sctp_state_fn_t sctp_sf_autoclose_timer_expire; /* Prototypes for utility support functions. */ -__u8 sctp_get_chunk_type(struct sctp_chunk *chunk); const struct sctp_sm_table_entry *sctp_sm_lookup_event( struct net *net, enum sctp_event_type event_type, @@ -166,8 +165,6 @@ int sctp_chunk_iif(const struct sctp_chunk *); struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *, struct sctp_chunk *, gfp_t gfp); -__u32 sctp_generate_verification_tag(void); -void sctp_populate_tie_tags(__u8 *cookie, __u32 curTag, __u32 hisTag); /* Prototypes for chunk-building functions. */ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 5c72d1864dd6..5a24d6d8522a 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1122,8 +1122,6 @@ void sctp_outq_free(struct sctp_outq*); void sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk, gfp_t); int sctp_outq_sack(struct sctp_outq *, struct sctp_chunk *); int sctp_outq_is_empty(const struct sctp_outq *); -void sctp_outq_restart(struct sctp_outq *); - void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, enum sctp_retransmit_reason reason); void sctp_retransmit_mark(struct sctp_outq *, struct sctp_transport *, __u8); -- cgit v1.2.3 From 66f7223039c0cef81221e9779520479895995815 Mon Sep 17 00:00:00 2001 From: Maxim Georgiev Date: Tue, 1 Aug 2023 17:28:13 +0300 Subject: net: add NDOs for configuring hardware timestamping Current hardware timestamping API for NICs requires implementing .ndo_eth_ioctl() for SIOCGHWTSTAMP and SIOCSHWTSTAMP. That API has some boilerplate such as request parameter translation between user and kernel address spaces, handling possible translation failures correctly, etc. Since it is the same all across the board, it would be desirable to handle it through generic code. Here we introduce .ndo_hwtstamp_get() and .ndo_hwtstamp_set(), which implement that boilerplate and allow drivers to just act upon requests. Suggested-by: Jakub Kicinski Signed-off-by: Maxim Georgiev Signed-off-by: Vladimir Oltean Reviewed-by: Jacob Keller Tested-by: Horatiu Vultur Link: https://lore.kernel.org/r/20230801142824.1772134-2-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- include/linux/net_tstamp.h | 8 ++++++++ include/linux/netdevice.h | 16 ++++++++++++++++ net/core/dev_ioctl.c | 46 ++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 68 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h index fd67f3cc0c4b..7c59824f43f5 100644 --- a/include/linux/net_tstamp.h +++ b/include/linux/net_tstamp.h @@ -30,4 +30,12 @@ static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kern kernel_cfg->rx_filter = cfg->rx_filter; } +static inline void hwtstamp_config_from_kernel(struct hwtstamp_config *cfg, + const struct kernel_hwtstamp_config *kernel_cfg) +{ + cfg->flags = kernel_cfg->flags; + cfg->tx_type = kernel_cfg->tx_type; + cfg->rx_filter = kernel_cfg->rx_filter; +} + #endif /* _LINUX_NET_TIMESTAMPING_H_ */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 84c36a7f873f..08a0b8d45dc9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -57,6 +57,7 @@ struct netpoll_info; struct device; struct ethtool_ops; +struct kernel_hwtstamp_config; struct phy_device; struct dsa_port; struct ip_tunnel_parm; @@ -1418,6 +1419,16 @@ struct netdev_net_notifier { * Get hardware timestamp based on normal/adjustable time or free running * cycle counter. This function is required if physical clock supports a * free running cycle counter. + * + * int (*ndo_hwtstamp_get)(struct net_device *dev, + * struct kernel_hwtstamp_config *kernel_config); + * Get the currently configured hardware timestamping parameters for the + * NIC device. + * + * int (*ndo_hwtstamp_set)(struct net_device *dev, + * struct kernel_hwtstamp_config *kernel_config, + * struct netlink_ext_ack *extack); + * Change the hardware timestamping parameters for NIC device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1652,6 +1663,11 @@ struct net_device_ops { ktime_t (*ndo_get_tstamp)(struct net_device *dev, const struct skb_shared_hwtstamps *hwtstamps, bool cycles); + int (*ndo_hwtstamp_get)(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_config); + int (*ndo_hwtstamp_set)(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_config, + struct netlink_ext_ack *extack); }; struct xdp_metadata_ops { diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 3730945ee294..10c0e173b38b 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -254,11 +254,32 @@ static int dev_eth_ioctl(struct net_device *dev, static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) { - return dev_eth_ioctl(dev, ifr, SIOCGHWTSTAMP); + const struct net_device_ops *ops = dev->netdev_ops; + struct kernel_hwtstamp_config kernel_cfg = {}; + struct hwtstamp_config cfg; + int err; + + if (!ops->ndo_hwtstamp_get) + return dev_eth_ioctl(dev, ifr, SIOCGHWTSTAMP); /* legacy */ + + if (!netif_device_present(dev)) + return -ENODEV; + + err = ops->ndo_hwtstamp_get(dev, &kernel_cfg); + if (err) + return err; + + hwtstamp_config_from_kernel(&cfg, &kernel_cfg); + + if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) + return -EFAULT; + + return 0; } static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) { + const struct net_device_ops *ops = dev->netdev_ops; struct kernel_hwtstamp_config kernel_cfg; struct netlink_ext_ack extack = {}; struct hwtstamp_config cfg; @@ -280,7 +301,28 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) return err; } - return dev_eth_ioctl(dev, ifr, SIOCSHWTSTAMP); + if (!ops->ndo_hwtstamp_set) + return dev_eth_ioctl(dev, ifr, SIOCSHWTSTAMP); /* legacy */ + + if (!netif_device_present(dev)) + return -ENODEV; + + err = ops->ndo_hwtstamp_set(dev, &kernel_cfg, &extack); + if (err) { + if (extack._msg) + netdev_err(dev, "%s\n", extack._msg); + return err; + } + + /* The driver may have modified the configuration, so copy the + * updated version of it back to user space + */ + hwtstamp_config_from_kernel(&cfg, &kernel_cfg); + + if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) + return -EFAULT; + + return 0; } static int dev_siocbond(struct net_device *dev, -- cgit v1.2.3 From e47d01fea663b1fe58d0a493efc9ed667f70242e Mon Sep 17 00:00:00 2001 From: Maxim Georgiev Date: Tue, 1 Aug 2023 17:28:14 +0300 Subject: net: add hwtstamping helpers for stackable net devices The stackable net devices with hwtstamping support (vlan, macvlan, bonding) only pass the hwtstamping ops to the lower (real) device. These drivers are the first that need to be converted to the new timestamping API, because if they aren't prepared to handle that, then no real device driver cannot be converted to the new API either. After studying what vlan_dev_ioctl(), macvlan_eth_ioctl() and bond_eth_ioctl() have in common, here we propose two generic implementations of ndo_hwtstamp_get() and ndo_hwtstamp_set() which can be called by those 3 drivers, with "dev" being their lower device. These helpers cover both cases, when the lower driver is converted to the new API or unconverted. We need some hacks in case of an unconverted driver, namely to stuff some pointers in struct kernel_hwtstamp_config which shouldn't have been there (since the new API isn't supposed to need it). These will be removed when all drivers will have been converted to the new API. Signed-off-by: Maxim Georgiev Signed-off-by: Vladimir Oltean Reviewed-by: Jacob Keller Link: https://lore.kernel.org/r/20230801142824.1772134-3-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- include/linux/net_tstamp.h | 6 ++++ include/linux/netdevice.h | 5 ++++ net/core/dev_ioctl.c | 75 +++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 79 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h index 7c59824f43f5..03e922814851 100644 --- a/include/linux/net_tstamp.h +++ b/include/linux/net_tstamp.h @@ -11,6 +11,10 @@ * @flags: see struct hwtstamp_config * @tx_type: see struct hwtstamp_config * @rx_filter: see struct hwtstamp_config + * @ifr: pointer to ifreq structure from the original ioctl request, to pass to + * a legacy implementation of a lower driver + * @copied_to_user: request was passed to a legacy implementation which already + * copied the ioctl request back to user space * * Prefer using this structure for in-kernel processing of hardware * timestamping configuration, over the inextensible struct hwtstamp_config @@ -20,6 +24,8 @@ struct kernel_hwtstamp_config { int flags; int tx_type; int rx_filter; + struct ifreq *ifr; + bool copied_to_user; }; static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 08a0b8d45dc9..23e335f245cf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3950,6 +3950,11 @@ int put_user_ifreq(struct ifreq *ifr, void __user *arg); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, void __user *data, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf __user *ifc); +int generic_hwtstamp_get_lower(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_cfg); +int generic_hwtstamp_set_lower(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_cfg, + struct netlink_ext_ack *extack); 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, diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 10c0e173b38b..d0223ecd6f6f 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -265,14 +265,20 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) if (!netif_device_present(dev)) return -ENODEV; + kernel_cfg.ifr = ifr; err = ops->ndo_hwtstamp_get(dev, &kernel_cfg); if (err) return err; - hwtstamp_config_from_kernel(&cfg, &kernel_cfg); + /* If the request was resolved through an unconverted driver, omit + * the copy_to_user(), since the implementation has already done that + */ + if (!kernel_cfg.copied_to_user) { + hwtstamp_config_from_kernel(&cfg, &kernel_cfg); - if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) - return -EFAULT; + if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) + return -EFAULT; + } return 0; } @@ -280,7 +286,7 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) { const struct net_device_ops *ops = dev->netdev_ops; - struct kernel_hwtstamp_config kernel_cfg; + struct kernel_hwtstamp_config kernel_cfg = {}; struct netlink_ext_ack extack = {}; struct hwtstamp_config cfg; int err; @@ -289,6 +295,7 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) return -EFAULT; hwtstamp_config_to_kernel(&kernel_cfg, &cfg); + kernel_cfg.ifr = ifr; err = net_hwtstamp_validate(&kernel_cfg); if (err) @@ -317,14 +324,68 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) /* The driver may have modified the configuration, so copy the * updated version of it back to user space */ - hwtstamp_config_from_kernel(&cfg, &kernel_cfg); + if (!kernel_cfg.copied_to_user) { + hwtstamp_config_from_kernel(&cfg, &kernel_cfg); - if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) - return -EFAULT; + if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) + return -EFAULT; + } + + return 0; +} + +static int generic_hwtstamp_ioctl_lower(struct net_device *dev, int cmd, + struct kernel_hwtstamp_config *kernel_cfg) +{ + struct ifreq ifrr; + int err; + + strscpy_pad(ifrr.ifr_name, dev->name, IFNAMSIZ); + ifrr.ifr_ifru = kernel_cfg->ifr->ifr_ifru; + + err = dev_eth_ioctl(dev, &ifrr, cmd); + if (err) + return err; + + kernel_cfg->ifr->ifr_ifru = ifrr.ifr_ifru; + kernel_cfg->copied_to_user = true; return 0; } +int generic_hwtstamp_get_lower(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_cfg) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!netif_device_present(dev)) + return -ENODEV; + + if (ops->ndo_hwtstamp_get) + return ops->ndo_hwtstamp_get(dev, kernel_cfg); + + /* Legacy path: unconverted lower driver */ + return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg); +} +EXPORT_SYMBOL(generic_hwtstamp_get_lower); + +int generic_hwtstamp_set_lower(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_cfg, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!netif_device_present(dev)) + return -ENODEV; + + if (ops->ndo_hwtstamp_set) + return ops->ndo_hwtstamp_set(dev, kernel_cfg, extack); + + /* Legacy path: unconverted lower driver */ + return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg); +} +EXPORT_SYMBOL(generic_hwtstamp_set_lower); + static int dev_siocbond(struct net_device *dev, struct ifreq *ifr, unsigned int cmd) { -- cgit v1.2.3 From 60495b6622ca67f5180343b89bd932d28d23f63a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 1 Aug 2023 17:28:23 +0300 Subject: net: phy: provide phylib stubs for hardware timestamping operations net/core/dev_ioctl.c (built-in code) will want to call phy_mii_ioctl() for hardware timestamping purposes. This is not directly possible, because phy_mii_ioctl() is a symbol provided under CONFIG_PHYLIB. Do something similar to what was done in DSA in commit 5a17818682cf ("net: dsa: replace NETDEV_PRE_CHANGE_HWTSTAMP notifier with a stub"), and arrange some indirect calls to phy_mii_ioctl() through a stub structure containing function pointers, that's provided by phylib as built-in even when CONFIG_PHYLIB=m, and which phy_init() populates at runtime (module insertion). Note: maybe the ownership of the ethtool_phy_ops singleton is backwards, and the methods exposed by that should be later merged into phylib_stubs. Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230801142824.1772134-12-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + drivers/net/phy/Makefile | 2 ++ drivers/net/phy/phy.c | 34 ++++++++++++++++++++++ drivers/net/phy/phy_device.c | 19 +++++++++++++ drivers/net/phy/stubs.c | 10 +++++++ include/linux/phy.h | 7 +++++ include/linux/phylib_stubs.h | 68 ++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 141 insertions(+) create mode 100644 drivers/net/phy/stubs.c create mode 100644 include/linux/phylib_stubs.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index c4f95a9d03b9..069e176d607a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7752,6 +7752,7 @@ F: include/linux/mii.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h +F: include/linux/phylib_stubs.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/linux/platform_data/mdio-gpio.h F: include/trace/events/mdio.h diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 35142780fc9d..c945ed9bd14b 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -14,6 +14,8 @@ endif # dedicated loadable module, so we bundle them all together into libphy.ko ifdef CONFIG_PHYLIB libphy-y += $(mdio-bus-y) +# the stubs are built-in whenever PHYLIB is built-in or module +obj-y += stubs.o else obj-$(CONFIG_MDIO_DEVICE) += mdio-bus.o endif diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index bdf00b2b2c1d..8aec8e83038c 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -455,6 +455,40 @@ int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd) } EXPORT_SYMBOL(phy_do_ioctl_running); +/** + * __phy_hwtstamp_get - Get hardware timestamping configuration from PHY + * + * @phydev: the PHY device structure + * @config: structure holding the timestamping configuration + * + * Query the PHY device for its current hardware timestamping configuration. + */ +int __phy_hwtstamp_get(struct phy_device *phydev, + struct kernel_hwtstamp_config *config) +{ + if (!phydev) + return -ENODEV; + + return phy_mii_ioctl(phydev, config->ifr, SIOCGHWTSTAMP); +} + +/** + * __phy_hwtstamp_set - Modify PHY hardware timestamping configuration + * + * @phydev: the PHY device structure + * @config: structure holding the timestamping configuration + * @extack: netlink extended ack structure, for error reporting + */ +int __phy_hwtstamp_set(struct phy_device *phydev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + if (!phydev) + return -ENODEV; + + return phy_mii_ioctl(phydev, config->ifr, SIOCSHWTSTAMP); +} + /** * phy_queue_state_machine - Trigger the state machine to run soon * diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 98b8ac28e5a1..e19c4fee8d22 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -3448,12 +3449,28 @@ static const struct ethtool_phy_ops phy_ethtool_phy_ops = { .start_cable_test_tdr = phy_start_cable_test_tdr, }; +static const struct phylib_stubs __phylib_stubs = { + .hwtstamp_get = __phy_hwtstamp_get, + .hwtstamp_set = __phy_hwtstamp_set, +}; + +static void phylib_register_stubs(void) +{ + phylib_stubs = &__phylib_stubs; +} + +static void phylib_unregister_stubs(void) +{ + phylib_stubs = NULL; +} + static int __init phy_init(void) { int rc; rtnl_lock(); ethtool_set_ethtool_phy_ops(&phy_ethtool_phy_ops); + phylib_register_stubs(); rtnl_unlock(); rc = mdio_bus_init(); @@ -3478,6 +3495,7 @@ err_mdio_bus: mdio_bus_exit(); err_ethtool_phy_ops: rtnl_lock(); + phylib_unregister_stubs(); ethtool_set_ethtool_phy_ops(NULL); rtnl_unlock(); @@ -3490,6 +3508,7 @@ static void __exit phy_exit(void) phy_driver_unregister(&genphy_driver); mdio_bus_exit(); rtnl_lock(); + phylib_unregister_stubs(); ethtool_set_ethtool_phy_ops(NULL); rtnl_unlock(); } diff --git a/drivers/net/phy/stubs.c b/drivers/net/phy/stubs.c new file mode 100644 index 000000000000..cfb9f275eb18 --- /dev/null +++ b/drivers/net/phy/stubs.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Stubs for PHY library functionality called by the core network stack. + * These are necessary because CONFIG_PHYLIB can be a module, and built-in + * code cannot directly call symbols exported by modules. + */ +#include + +const struct phylib_stubs *phylib_stubs; +EXPORT_SYMBOL_GPL(phylib_stubs); diff --git a/include/linux/phy.h b/include/linux/phy.h index b254848a9c99..ba08b0e60279 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -298,6 +298,7 @@ static inline const char *phy_modes(phy_interface_t interface) #define MII_BUS_ID_SIZE 61 struct device; +struct kernel_hwtstamp_config; struct phylink; struct sfp_bus; struct sfp_upstream_ops; @@ -1955,6 +1956,12 @@ int phy_ethtool_set_plca_cfg(struct phy_device *phydev, int phy_ethtool_get_plca_status(struct phy_device *phydev, struct phy_plca_status *plca_st); +int __phy_hwtstamp_get(struct phy_device *phydev, + struct kernel_hwtstamp_config *config); +int __phy_hwtstamp_set(struct phy_device *phydev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); + static inline int phy_package_read(struct phy_device *phydev, u32 regnum) { struct phy_package_shared *shared = phydev->shared; diff --git a/include/linux/phylib_stubs.h b/include/linux/phylib_stubs.h new file mode 100644 index 000000000000..1279f48c8a70 --- /dev/null +++ b/include/linux/phylib_stubs.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Stubs for the Network PHY library + */ + +#include + +struct kernel_hwtstamp_config; +struct netlink_ext_ack; +struct phy_device; + +#if IS_ENABLED(CONFIG_PHYLIB) + +extern const struct phylib_stubs *phylib_stubs; + +struct phylib_stubs { + int (*hwtstamp_get)(struct phy_device *phydev, + struct kernel_hwtstamp_config *config); + int (*hwtstamp_set)(struct phy_device *phydev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); +}; + +static inline int phy_hwtstamp_get(struct phy_device *phydev, + struct kernel_hwtstamp_config *config) +{ + /* phylib_register_stubs() and phylib_unregister_stubs() + * also run under rtnl_lock(). + */ + ASSERT_RTNL(); + + if (!phylib_stubs) + return -EOPNOTSUPP; + + return phylib_stubs->hwtstamp_get(phydev, config); +} + +static inline int phy_hwtstamp_set(struct phy_device *phydev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + /* phylib_register_stubs() and phylib_unregister_stubs() + * also run under rtnl_lock(). + */ + ASSERT_RTNL(); + + if (!phylib_stubs) + return -EOPNOTSUPP; + + return phylib_stubs->hwtstamp_set(phydev, config, extack); +} + +#else + +static inline int phy_hwtstamp_get(struct phy_device *phydev, + struct kernel_hwtstamp_config *config) +{ + return -EOPNOTSUPP; +} + +static inline int phy_hwtstamp_set(struct phy_device *phydev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +#endif -- cgit v1.2.3 From fd770e856e226f80fe6e1dc9d1861bcb135cdf0b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 1 Aug 2023 17:28:24 +0300 Subject: net: remove phy_has_hwtstamp() -> phy_mii_ioctl() decision from converted drivers It is desirable that the new .ndo_hwtstamp_set() API gives more uniformity, less overhead and future flexibility w.r.t. the PHY timestamping behavior. Currently there are some drivers which allow PHY timestamping through the procedure mentioned in Documentation/networking/timestamping.rst. They don't do anything locally if phy_has_hwtstamp() is set, except for lan966x which installs PTP packet traps. Centralize that behavior in a new dev_set_hwtstamp_phylib() code function, which calls either phy_mii_ioctl() for the phylib PHY, or .ndo_hwtstamp_set() of the netdev, based on a single policy (currently simplistic: phy_has_hwtstamp()). Any driver converted to .ndo_hwtstamp_set() will automatically opt into the centralized phylib timestamping policy. Unconverted drivers still get to choose whether they let the PHY handle timestamping or not. Netdev drivers with integrated PHY drivers that don't use phylib presumably don't set dev->phydev, and those will always see HWTSTAMP_SOURCE_NETDEV requests even when converted. The timestamping policy will remain 100% up to them. Signed-off-by: Vladimir Oltean Reviewed-by: Jacob Keller Tested-by: Horatiu Vultur Link: https://lore.kernel.org/r/20230801142824.1772134-13-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fec_main.c | 8 -- .../net/ethernet/microchip/lan966x/lan966x_main.c | 25 +++--- .../net/ethernet/microchip/sparx5/sparx5_netdev.c | 6 -- include/linux/net_tstamp.h | 16 ++++ include/linux/netdevice.h | 4 + net/core/dev_ioctl.c | 91 ++++++++++++++++++++-- 6 files changed, 117 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 6d81fff0227e..43f14cec91e9 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3872,10 +3872,6 @@ static int fec_hwtstamp_get(struct net_device *ndev, struct kernel_hwtstamp_config *config) { struct fec_enet_private *fep = netdev_priv(ndev); - struct phy_device *phydev = ndev->phydev; - - if (phy_has_hwtstamp(phydev)) - return phy_mii_ioctl(phydev, config->ifr, SIOCGHWTSTAMP); if (!netif_running(ndev)) return -EINVAL; @@ -3893,10 +3889,6 @@ static int fec_hwtstamp_set(struct net_device *ndev, struct netlink_ext_ack *extack) { struct fec_enet_private *fep = netdev_priv(ndev); - struct phy_device *phydev = ndev->phydev; - - if (phy_has_hwtstamp(phydev)) - return phy_mii_ioctl(phydev, config->ifr, SIOCSHWTSTAMP); if (!netif_running(ndev)) return -EINVAL; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 1baa94a98fe3..4a1acc7234f6 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -455,9 +455,6 @@ static int lan966x_port_hwtstamp_get(struct net_device *dev, { struct lan966x_port *port = netdev_priv(dev); - if (phy_has_hwtstamp(dev->phydev)) - return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCGHWTSTAMP); - if (!port->lan966x->ptp) return -EOPNOTSUPP; @@ -473,21 +470,26 @@ static int lan966x_port_hwtstamp_set(struct net_device *dev, struct lan966x_port *port = netdev_priv(dev); int err; + if (cfg->source != HWTSTAMP_SOURCE_NETDEV && + cfg->source != HWTSTAMP_SOURCE_PHYLIB) + return -EOPNOTSUPP; + err = lan966x_ptp_setup_traps(port, cfg); if (err) return err; - if (phy_has_hwtstamp(dev->phydev)) { - err = phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCSHWTSTAMP); - if (err) + if (cfg->source == HWTSTAMP_SOURCE_NETDEV) { + if (!port->lan966x->ptp) + return -EOPNOTSUPP; + + err = lan966x_ptp_hwtstamp_set(port, cfg, extack); + if (err) { lan966x_ptp_del_traps(port); - return err; + return err; + } } - if (!port->lan966x->ptp) - return -EOPNOTSUPP; - - return lan966x_ptp_hwtstamp_set(port, cfg, extack); + return 0; } static const struct net_device_ops lan966x_port_netdev_ops = { @@ -815,6 +817,7 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p, NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_TC; dev->hw_features |= NETIF_F_HW_TC; + dev->priv_flags |= IFF_SEE_ALL_HWTSTAMP_REQUESTS; dev->needed_headroom = IFH_LEN_BYTES; eth_hw_addr_gen(dev, lan966x->base_mac, p + 1); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c index e01d3b1e17e0..705a004b324f 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -216,9 +216,6 @@ static int sparx5_port_hwtstamp_get(struct net_device *dev, struct sparx5_port *sparx5_port = netdev_priv(dev); struct sparx5 *sparx5 = sparx5_port->sparx5; - if (phy_has_hwtstamp(dev->phydev)) - return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCGHWTSTAMP); - if (!sparx5->ptp) return -EOPNOTSUPP; @@ -234,9 +231,6 @@ static int sparx5_port_hwtstamp_set(struct net_device *dev, struct sparx5_port *sparx5_port = netdev_priv(dev); struct sparx5 *sparx5 = sparx5_port->sparx5; - if (phy_has_hwtstamp(dev->phydev)) - return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCSHWTSTAMP); - if (!sparx5->ptp) return -EOPNOTSUPP; diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h index 03e922814851..eb01c37e71e0 100644 --- a/include/linux/net_tstamp.h +++ b/include/linux/net_tstamp.h @@ -5,6 +5,11 @@ #include +enum hwtstamp_source { + HWTSTAMP_SOURCE_NETDEV, + HWTSTAMP_SOURCE_PHYLIB, +}; + /** * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config * @@ -15,6 +20,8 @@ * a legacy implementation of a lower driver * @copied_to_user: request was passed to a legacy implementation which already * copied the ioctl request back to user space + * @source: indication whether timestamps should come from the netdev or from + * an attached phylib PHY * * Prefer using this structure for in-kernel processing of hardware * timestamping configuration, over the inextensible struct hwtstamp_config @@ -26,6 +33,7 @@ struct kernel_hwtstamp_config { int rx_filter; struct ifreq *ifr; bool copied_to_user; + enum hwtstamp_source source; }; static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg, @@ -44,4 +52,12 @@ static inline void hwtstamp_config_from_kernel(struct hwtstamp_config *cfg, cfg->rx_filter = kernel_cfg->rx_filter; } +static inline bool kernel_hwtstamp_config_changed(const struct kernel_hwtstamp_config *a, + const struct kernel_hwtstamp_config *b) +{ + return a->flags != b->flags || + a->tx_type != b->tx_type || + a->rx_filter != b->rx_filter; +} + #endif /* _LINUX_NET_TIMESTAMPING_H_ */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 23e335f245cf..85d594460c66 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1724,6 +1724,9 @@ struct xdp_metadata_ops { * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN + * @IFF_SEE_ALL_HWTSTAMP_REQUESTS: device wants to see calls to + * ndo_hwtstamp_set() for all timestamp requests regardless of source, + * even if those aren't HWTSTAMP_SOURCE_NETDEV. */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1759,6 +1762,7 @@ enum netdev_priv_flags { IFF_NO_ADDRCONF = BIT_ULL(30), IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), + IFF_SEE_ALL_HWTSTAMP_REQUESTS = BIT_ULL(33), }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index d0223ecd6f6f..72e077022348 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -252,6 +253,30 @@ static int dev_eth_ioctl(struct net_device *dev, return ops->ndo_eth_ioctl(dev, ifr, cmd); } +/** + * dev_get_hwtstamp_phylib() - Get hardware timestamping settings of NIC + * or of attached phylib PHY + * @dev: Network device + * @cfg: Timestamping configuration structure + * + * Helper for enforcing a common policy that phylib timestamping, if available, + * should take precedence in front of hardware timestamping provided by the + * netdev. + * + * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), and + * there only exists a phydev->mii_ts->hwtstamp() method. So this will return + * -EOPNOTSUPP for phylib for now, which is still more accurate than letting + * the netdev handle the GET request. + */ +static int dev_get_hwtstamp_phylib(struct net_device *dev, + struct kernel_hwtstamp_config *cfg) +{ + if (phy_has_hwtstamp(dev->phydev)) + return phy_hwtstamp_get(dev->phydev, cfg); + + return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg); +} + static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) { const struct net_device_ops *ops = dev->netdev_ops; @@ -266,7 +291,7 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) return -ENODEV; kernel_cfg.ifr = ifr; - err = ops->ndo_hwtstamp_get(dev, &kernel_cfg); + err = dev_get_hwtstamp_phylib(dev, &kernel_cfg); if (err) return err; @@ -283,6 +308,59 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) return 0; } +/** + * dev_set_hwtstamp_phylib() - Change hardware timestamping of NIC + * or of attached phylib PHY + * @dev: Network device + * @cfg: Timestamping configuration structure + * @extack: Netlink extended ack message structure, for error reporting + * + * Helper for enforcing a common policy that phylib timestamping, if available, + * should take precedence in front of hardware timestamping provided by the + * netdev. If the netdev driver needs to perform specific actions even for PHY + * timestamping to work properly (a switch port must trap the timestamped + * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in + * dev->priv_flags. + */ +static int dev_set_hwtstamp_phylib(struct net_device *dev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + bool phy_ts = phy_has_hwtstamp(dev->phydev); + struct kernel_hwtstamp_config old_cfg = {}; + bool changed = false; + int err; + + cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV; + + if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) { + err = ops->ndo_hwtstamp_get(dev, &old_cfg); + if (err) + return err; + + err = ops->ndo_hwtstamp_set(dev, cfg, extack); + if (err) { + if (extack->_msg) + netdev_err(dev, "%s\n", extack->_msg); + return err; + } + + changed = kernel_hwtstamp_config_changed(&old_cfg, cfg); + } + + if (phy_ts) { + err = phy_hwtstamp_set(dev->phydev, cfg, extack); + if (err) { + if (changed) + ops->ndo_hwtstamp_set(dev, &old_cfg, NULL); + return err; + } + } + + return 0; +} + static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) { const struct net_device_ops *ops = dev->netdev_ops; @@ -314,12 +392,9 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) if (!netif_device_present(dev)) return -ENODEV; - err = ops->ndo_hwtstamp_set(dev, &kernel_cfg, &extack); - if (err) { - if (extack._msg) - netdev_err(dev, "%s\n", extack._msg); + err = dev_set_hwtstamp_phylib(dev, &kernel_cfg, &extack); + if (err) return err; - } /* The driver may have modified the configuration, so copy the * updated version of it back to user space @@ -362,7 +437,7 @@ int generic_hwtstamp_get_lower(struct net_device *dev, return -ENODEV; if (ops->ndo_hwtstamp_get) - return ops->ndo_hwtstamp_get(dev, kernel_cfg); + return dev_get_hwtstamp_phylib(dev, kernel_cfg); /* Legacy path: unconverted lower driver */ return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg); @@ -379,7 +454,7 @@ int generic_hwtstamp_set_lower(struct net_device *dev, return -ENODEV; if (ops->ndo_hwtstamp_set) - return ops->ndo_hwtstamp_set(dev, kernel_cfg, extack); + return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack); /* Legacy path: unconverted lower driver */ return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg); -- cgit v1.2.3 From f11e5bd159b08976db9e7a9eabbf0318dfe5429d Mon Sep 17 00:00:00 2001 From: Mateusz Kowalski Date: Tue, 1 Aug 2023 14:37:50 +0200 Subject: bonding: support balance-alb with openvswitch Commit d5410ac7b0ba ("net:bonding:support balance-alb interface with vlan to bridge") introduced a support for balance-alb mode for interfaces connected to the linux bridge by fixing missing matching of MAC entry in FDB. In our testing we discovered that it still does not work when the bond is connected to the OVS bridge as show in diagram below: eth1(mac:eth1_mac)--bond0(balance-alb,mac:eth0_mac)--eth0(mac:eth0_mac) | bond0.150(mac:eth0_mac) | ovs_bridge(ip:bridge_ip,mac:eth0_mac) This patch fixes it by checking not only if the device is a bridge but also if it is an openvswitch. Signed-off-by: Mateusz Kowalski Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/9fe7297c-609e-208b-c77b-3ceef6eb51a4@redhat.com Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_alb.c | 2 +- include/linux/netdevice.h | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index b9dbad3a8af8..cc5049eb25f8 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -668,7 +668,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) dev = ip_dev_find(dev_net(bond->dev), arp->ip_src); if (dev) { - if (netif_is_bridge_master(dev)) { + if (netif_is_any_bridge_master(dev)) { dev_put(dev); return NULL; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 85d594460c66..4176a738177b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5128,6 +5128,11 @@ static inline bool netif_is_ovs_port(const struct net_device *dev) return dev->priv_flags & IFF_OVS_DATAPATH; } +static inline bool netif_is_any_bridge_master(const struct net_device *dev) +{ + return netif_is_bridge_master(dev) || netif_is_ovs_master(dev); +} + static inline bool netif_is_any_bridge_port(const struct net_device *dev) { return netif_is_bridge_port(dev) || netif_is_ovs_port(dev); -- cgit v1.2.3 From 92272ec4107ef4f826b694a1338562c007e09821 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 2 Aug 2023 18:02:28 -0700 Subject: eth: add missing xdp.h includes in drivers Handful of drivers currently expect to get xdp.h by virtue of including netdevice.h. This will soon no longer be the case so add explicit includes. Reviewed-by: Wei Fang Reviewed-by: Gerhard Engleder Signed-off-by: Jakub Kicinski Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230803010230.1755386-2-kuba@kernel.org Signed-off-by: Martin KaFai Lau --- drivers/net/bonding/bond_main.c | 1 + drivers/net/ethernet/amazon/ena/ena_netdev.h | 1 + drivers/net/ethernet/engleder/tsnep.h | 1 + drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h | 1 + drivers/net/ethernet/freescale/enetc/enetc.h | 1 + drivers/net/ethernet/freescale/fec.h | 1 + drivers/net/ethernet/fungible/funeth/funeth_txrx.h | 1 + drivers/net/ethernet/google/gve/gve.h | 1 + drivers/net/ethernet/intel/igc/igc.h | 1 + drivers/net/ethernet/microchip/lan966x/lan966x_main.h | 1 + drivers/net/ethernet/microsoft/mana/mana_en.c | 1 + drivers/net/ethernet/stmicro/stmmac/stmmac.h | 1 + drivers/net/ethernet/ti/cpsw_priv.h | 1 + drivers/net/hyperv/hyperv_net.h | 1 + drivers/net/tap.c | 1 + include/net/mana/mana.h | 2 ++ 16 files changed, 17 insertions(+) (limited to 'include') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 7a0f25301f7e..2f21cca4fdaf 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -90,6 +90,7 @@ #include #endif #include +#include #include "bonding_priv.h" diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 248b715b4d68..33c923e1261a 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include "ena_com.h" diff --git a/drivers/net/ethernet/engleder/tsnep.h b/drivers/net/ethernet/engleder/tsnep.h index 11b29f56aaf9..6e14c918e3fb 100644 --- a/drivers/net/ethernet/engleder/tsnep.h +++ b/drivers/net/ethernet/engleder/tsnep.h @@ -14,6 +14,7 @@ #include #include #include +#include #define TSNEP "tsnep" diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index d56d7a13262e..bfb6c96c3b2f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #include diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 8577cf7699a0..7439739cd81a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -11,6 +11,7 @@ #include #include #include +#include #include "enetc_hw.h" diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 8f1edcca96c4..5a0974e62f99 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -22,6 +22,7 @@ #include #include #include +#include #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ diff --git a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h index 53b7e95213a8..5eec552a1f24 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h +++ b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h @@ -5,6 +5,7 @@ #include #include +#include /* Tx descriptor size */ #define FUNETH_SQE_SIZE 64U diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 4b425bf71ede..a31256f70348 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -11,6 +11,7 @@ #include #include #include +#include #include "gve_desc.h" #include "gve_desc_dqo.h" diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 9db384f66a8e..4bffc3cb502f 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -15,6 +15,7 @@ #include #include #include +#include #include "igc_hw.h" diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 27f272831ea5..eb7d81b5e9f8 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index ac2acc9aca9d..21665f114fe9 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -11,6 +11,7 @@ #include #include +#include #include #include diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 4ce5eaaae513..a6d034968654 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -22,6 +22,7 @@ #include #include #include +#include #include struct stmmac_resources { diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index 34230145ca0b..0e27c433098d 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -6,6 +6,7 @@ #ifndef DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_ #define DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_ +#include #include #include "davinci_cpdma.h" diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index c9dd69dbe1b8..810977952f95 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -16,6 +16,7 @@ #include #include #include +#include /* RSS related */ #define OID_GEN_RECEIVE_SCALE_CAPABILITIES 0x00010203 /* query only */ diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 9137fb8c1c42..b196a2a54355 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 024ad8ddb27e..1ccdca03e166 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -4,6 +4,8 @@ #ifndef _MANA_H #define _MANA_H +#include + #include "gdma.h" #include "hw_channel.h" -- cgit v1.2.3 From 49e47a5b6145d86c30022fe0e949bbb24bae28ba Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 2 Aug 2023 18:02:29 -0700 Subject: net: move struct netdev_rx_queue out of netdevice.h struct netdev_rx_queue is touched in only a few places and having it defined in netdevice.h brings in the dependency on xdp.h, because struct xdp_rxq_info gets embedded in struct netdev_rx_queue. In prep for removal of xdp.h from netdevice.h move all the netdev_rx_queue stuff to a new header. We could technically break the new header up to avoid the sysfs.h include but it's so rarely included it doesn't seem to be worth it at this point. Reviewed-by: Amritha Nambiar Signed-off-by: Jakub Kicinski Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230803010230.1755386-3-kuba@kernel.org Signed-off-by: Martin KaFai Lau --- drivers/net/virtio_net.c | 1 + include/linux/netdevice.h | 44 ----------------------------------- include/net/netdev_rx_queue.h | 53 +++++++++++++++++++++++++++++++++++++++++++ net/bpf/test_run.c | 1 + net/core/dev.c | 1 + net/core/net-sysfs.c | 1 + net/xdp/xsk.c | 1 + 7 files changed, 58 insertions(+), 44 deletions(-) create mode 100644 include/net/netdev_rx_queue.h (limited to 'include') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0db14f6b87d3..5bcfd69333ea 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -22,6 +22,7 @@ #include #include #include +#include static int napi_weight = NAPI_POLL_WEIGHT; module_param(napi_weight, int, 0444); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3800d0479698..5563c8a210b5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -782,32 +782,6 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, #endif #endif /* CONFIG_RPS */ -/* 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; - netdevice_tracker dev_tracker; - -#ifdef CONFIG_XDP_SOCKETS - struct xsk_buff_pool *pool; -#endif -} ____cacheline_aligned_in_smp; - -/* - * RX queue sysfs structures and functions. - */ -struct rx_queue_attribute { - struct attribute attr; - ssize_t (*show)(struct netdev_rx_queue *queue, char *buf); - ssize_t (*store)(struct netdev_rx_queue *queue, - const char *buf, size_t len); -}; - /* XPS map type and offset of the xps map within net_device->xps_maps[]. */ enum xps_map_type { XPS_CPUS = 0, @@ -3828,24 +3802,6 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev, 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) -{ - return dev->_rx + rxq; -} - -#ifdef CONFIG_SYSFS -static inline unsigned int get_netdev_rx_queue_index( - struct netdev_rx_queue *queue) -{ - struct net_device *dev = queue->dev; - int index = queue - dev->_rx; - - BUG_ON(index >= dev->num_rx_queues); - return index; -} -#endif - int netif_get_num_default_rss_queues(void); void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason); diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h new file mode 100644 index 000000000000..cdcafb30d437 --- /dev/null +++ b/include/net/netdev_rx_queue.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_NETDEV_RX_QUEUE_H +#define _LINUX_NETDEV_RX_QUEUE_H + +#include +#include +#include +#include + +/* 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; + netdevice_tracker dev_tracker; + +#ifdef CONFIG_XDP_SOCKETS + struct xsk_buff_pool *pool; +#endif +} ____cacheline_aligned_in_smp; + +/* + * RX queue sysfs structures and functions. + */ +struct rx_queue_attribute { + struct attribute attr; + ssize_t (*show)(struct netdev_rx_queue *queue, char *buf); + ssize_t (*store)(struct netdev_rx_queue *queue, + const char *buf, size_t len); +}; + +static inline struct netdev_rx_queue * +__netif_get_rx_queue(struct net_device *dev, unsigned int rxq) +{ + return dev->_rx + rxq; +} + +#ifdef CONFIG_SYSFS +static inline unsigned int +get_netdev_rx_queue_index(struct netdev_rx_queue *queue) +{ + struct net_device *dev = queue->dev; + int index = queue - dev->_rx; + + BUG_ON(index >= dev->num_rx_queues); + return index; +} +#endif +#endif diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 7d47f53f20c1..0aac76c13fd4 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include diff --git a/net/core/dev.c b/net/core/dev.c index 002fec07de73..1916ec990f58 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -152,6 +152,7 @@ #include #include #include +#include #include "dev.h" #include "net-sysfs.h" diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 15e3f4606b5f..fccaa5bac0ed 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "dev.h" #include "net-sysfs.h" diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 4f1e0599146e..82aaec1b079f 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include "xsk_queue.h" -- cgit v1.2.3 From 680ee0456a5712309db9ec2692e908ea1d6b1644 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 2 Aug 2023 18:02:30 -0700 Subject: net: invert the netdevice.h vs xdp.h dependency xdp.h is far more specific and is included in only 67 other files vs netdevice.h's 1538 include sites. Make xdp.h include netdevice.h, instead of the other way around. This decreases the incremental allmodconfig builds size when xdp.h is touched from 5947 to 662 objects. Move bpf_prog_run_xdp() to xdp.h, seems appropriate and filter.h is a mega-header in its own right so it's nice to avoid xdp.h getting included there as well. The only unfortunate part is that the typedef for xdp_features_t has to move to netdevice.h, since its embedded in struct netdevice. Signed-off-by: Jakub Kicinski Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230803010230.1755386-4-kuba@kernel.org Signed-off-by: Martin KaFai Lau --- include/linux/filter.h | 17 ----------------- include/linux/netdevice.h | 11 ++++------- include/net/busy_poll.h | 1 + include/net/xdp.h | 29 +++++++++++++++++++++++++---- include/trace/events/xdp.h | 1 + kernel/bpf/btf.c | 1 + kernel/bpf/offload.c | 1 + kernel/bpf/verifier.c | 1 + net/netfilter/nf_conntrack_bpf.c | 1 + 9 files changed, 35 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index f5eabe3fa5e8..2d6fe30bad5f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -774,23 +774,6 @@ 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) -{ - /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus - * 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)); - - 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); static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5563c8a210b5..d8ed85183fe4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -40,7 +40,6 @@ #include #endif #include -#include #include #include @@ -76,8 +75,12 @@ struct udp_tunnel_nic_info; struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; +struct xdp_frame; +struct xdp_metadata_ops; struct xdp_md; +typedef u32 xdp_features_t; + void synchronize_net(void); void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -1628,12 +1631,6 @@ struct net_device_ops { bool cycles); }; -struct xdp_metadata_ops { - int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); - int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, - enum xdp_rss_hash_type *rss_type); -}; - /** * enum netdev_priv_flags - &struct net_device priv_flags * diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index f90f0021f5f2..4dabeb6c76d3 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -16,6 +16,7 @@ #include #include #include +#include /* 0 - Reserved to indicate value not set * 1..NR_CPUS - Reserved for sender_cpu diff --git a/include/net/xdp.h b/include/net/xdp.h index d1c5381fc95f..de08c8e0d134 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -6,9 +6,10 @@ #ifndef __LINUX_NET_XDP_H__ #define __LINUX_NET_XDP_H__ -#include /* skb_shared_info */ -#include #include +#include +#include +#include /* skb_shared_info */ /** * DOC: XDP RX-queue information @@ -45,8 +46,6 @@ enum xdp_mem_type { MEM_TYPE_MAX, }; -typedef u32 xdp_features_t; - /* XDP flags for ndo_xdp_xmit */ #define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ #define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH @@ -443,6 +442,12 @@ enum xdp_rss_hash_type { XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR, }; +struct xdp_metadata_ops { + int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); + int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type); +}; + #ifdef CONFIG_NET u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); @@ -474,4 +479,20 @@ static inline void xdp_clear_features_flag(struct net_device *dev) xdp_set_features_flag(dev, 0); } +static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, + struct xdp_buff *xdp) +{ + /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus + * 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)); + + 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; +} #endif /* __LINUX_NET_XDP_H__ */ diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index cd89f1d5ce7b..9adc2bdf2f94 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -9,6 +9,7 @@ #include #include #include +#include #define __XDP_ACT_MAP(FN) \ FN(ABORTED) \ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index ef9581a580e2..249657c466dd 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -29,6 +29,7 @@ #include #include +#include #include "../tools/lib/bpf/relo_core.h" /* BTF (BPF Type Format) is the meta data format which describes diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 8a26cd8814c1..3e4f2ec1af06 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -25,6 +25,7 @@ #include #include #include +#include /* Protects offdevs, members of bpf_offload_netdev and offload members * of all progs. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e7b1af016841..132f25dab931 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "disasm.h" diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index 0d36d7285e3f..c7a6114091ae 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3 From 82e896d992fa631cda1f63239fd47b3ab781ffa6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 2 Aug 2023 09:18:21 -0700 Subject: docs: net: page_pool: use kdoc to avoid duplicating the information All struct members of the driver-facing APIs are documented twice, in the code and under Documentation. This is a bit tedious. I also get the feeling that a lot of developers will read the header when coding, rather than the doc. Bring the two a little closer together by using kdoc for structs and functions. Using kdoc also gives us links (mentioning a function or struct in the text gets replaced by a link to its doc). Reviewed-by: Randy Dunlap Tested-by: Randy Dunlap Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230802161821.3621985-3-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/networking/page_pool.rst | 92 ++++++---------------- include/net/page_pool.h | 134 +++++++++++++++++++++++++-------- net/core/page_pool.c | 31 +++++++- 3 files changed, 155 insertions(+), 102 deletions(-) (limited to 'include') diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst index eb96a592ec6b..53b5448cc0f1 100644 --- a/Documentation/networking/page_pool.rst +++ b/Documentation/networking/page_pool.rst @@ -64,50 +64,19 @@ This lockless guarantee naturally comes from running under a NAPI softirq. The protection doesn't strictly have to be NAPI, any guarantee that allocating a page will cause no race conditions is enough. -* page_pool_create(): Create a pool. - * flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV - * order: 2^order pages on allocation - * pool_size: size of the ptr_ring - * nid: preferred NUMA node for allocation - * dev: struct device. Used on DMA operations - * dma_dir: DMA direction - * max_len: max DMA sync memory size - * offset: DMA address offset - -* page_pool_put_page(): The outcome of this depends on the page refcnt. If the - driver bumps the refcnt > 1 this will unmap the page. If the page refcnt is 1 - the allocator owns the page and will try to recycle it in one of the pool - caches. If PP_FLAG_DMA_SYNC_DEV is set, the page will be synced for_device - using dma_sync_single_range_for_device(). - -* page_pool_put_full_page(): Similar to page_pool_put_page(), but will DMA sync - for the entire memory area configured in area pool->max_len. - -* page_pool_recycle_direct(): Similar to page_pool_put_full_page() but caller - must guarantee safe context (e.g NAPI), since it will recycle the page - directly into the pool fast cache. - -* page_pool_dev_alloc_pages(): Get a page from the page allocator or page_pool - caches. - -* page_pool_get_dma_addr(): Retrieve the stored DMA address. - -* page_pool_get_dma_dir(): Retrieve the stored DMA direction. - -* page_pool_put_page_bulk(): Tries to refill a number of pages into the - ptr_ring cache holding ptr_ring producer lock. If the ptr_ring is full, - page_pool_put_page_bulk() will release leftover pages to the page allocator. - page_pool_put_page_bulk() is suitable to be run inside the driver NAPI tx - completion loop for the XDP_REDIRECT use case. - Please note the caller must not use data area after running - page_pool_put_page_bulk(), as this function overwrites it. - -* page_pool_get_stats(): Retrieve statistics about the page_pool. This API - is only available if the kernel has been configured with - ``CONFIG_PAGE_POOL_STATS=y``. A pointer to a caller allocated ``struct - page_pool_stats`` structure is passed to this API which is filled in. The - caller can then report those stats to the user (perhaps via ethtool, - debugfs, etc.). See below for an example usage of this API. +.. kernel-doc:: net/core/page_pool.c + :identifiers: page_pool_create + +.. kernel-doc:: include/net/page_pool.h + :identifiers: struct page_pool_params + +.. kernel-doc:: include/net/page_pool.h + :identifiers: page_pool_put_page page_pool_put_full_page + page_pool_recycle_direct page_pool_dev_alloc_pages + page_pool_get_dma_addr page_pool_get_dma_dir + +.. kernel-doc:: net/core/page_pool.c + :identifiers: page_pool_put_page_bulk page_pool_get_stats DMA sync -------- @@ -146,36 +115,17 @@ with fragmented page pools. Stats API and structures ------------------------ If the kernel is configured with ``CONFIG_PAGE_POOL_STATS=y``, the API -``page_pool_get_stats()`` and structures described below are available. It -takes a pointer to a ``struct page_pool`` and a pointer to a ``struct -page_pool_stats`` allocated by the caller. +page_pool_get_stats() and structures described below are available. +It takes a pointer to a ``struct page_pool`` and a pointer to a struct +page_pool_stats allocated by the caller. -The API will fill in the provided ``struct page_pool_stats`` with +The API will fill in the provided struct page_pool_stats with statistics about the page_pool. -The stats structure has the following fields:: - - struct page_pool_stats { - struct page_pool_alloc_stats alloc_stats; - struct page_pool_recycle_stats recycle_stats; - }; - - -The ``struct page_pool_alloc_stats`` has the following fields: - * ``fast``: successful fast path allocations - * ``slow``: slow path order-0 allocations - * ``slow_high_order``: slow path high order allocations - * ``empty``: ptr ring is empty, so a slow path allocation was forced. - * ``refill``: an allocation which triggered a refill of the cache - * ``waive``: pages obtained from the ptr ring that cannot be added to - the cache due to a NUMA mismatch. - -The ``struct page_pool_recycle_stats`` has the following fields: - * ``cached``: recycling placed page in the page pool cache - * ``cache_full``: page pool cache was full - * ``ring``: page placed into the ptr ring - * ``ring_full``: page released from page pool because the ptr ring was full - * ``released_refcnt``: page released (and not recycled) because refcnt > 1 +.. kernel-doc:: include/net/page_pool.h + :identifiers: struct page_pool_recycle_stats + struct page_pool_alloc_stats + struct page_pool_stats Coding examples =============== diff --git a/include/net/page_pool.h b/include/net/page_pool.h index f1d5cc1fa13b..73d4f786418d 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -70,47 +70,76 @@ struct pp_alloc_cache { struct page *cache[PP_ALLOC_CACHE_SIZE]; }; +/** + * struct page_pool_params - page pool parameters + * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_PAGE_FRAG + * @order: 2^order pages on allocation + * @pool_size: size of the ptr_ring + * @nid: NUMA node id to allocate from pages from + * @dev: device, for DMA pre-mapping purposes + * @napi: NAPI which is the sole consumer of pages, otherwise NULL + * @dma_dir: DMA mapping direction + * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV + * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV + */ struct page_pool_params { unsigned int flags; unsigned int order; unsigned int pool_size; - int nid; /* Numa node id to allocate from pages from */ - struct device *dev; /* device, for DMA pre-mapping purposes */ - struct napi_struct *napi; /* Sole consumer of pages, otherwise NULL */ - enum dma_data_direction dma_dir; /* DMA mapping direction */ - unsigned int max_len; /* max DMA sync memory size */ - unsigned int offset; /* DMA addr offset */ + int nid; + struct device *dev; + struct napi_struct *napi; + enum dma_data_direction dma_dir; + unsigned int max_len; + unsigned int offset; +/* private: used by test code only */ void (*init_callback)(struct page *page, void *arg); void *init_arg; }; #ifdef CONFIG_PAGE_POOL_STATS +/** + * struct page_pool_alloc_stats - allocation statistics + * @fast: successful fast path allocations + * @slow: slow path order-0 allocations + * @slow_high_order: slow path high order allocations + * @empty: ptr ring is empty, so a slow path allocation was forced + * @refill: an allocation which triggered a refill of the cache + * @waive: pages obtained from the ptr ring that cannot be added to + * the cache due to a NUMA mismatch + */ struct page_pool_alloc_stats { - u64 fast; /* fast path allocations */ - u64 slow; /* slow-path order 0 allocations */ - u64 slow_high_order; /* slow-path high order allocations */ - u64 empty; /* failed refills due to empty ptr ring, forcing - * slow path allocation - */ - u64 refill; /* allocations via successful refill */ - u64 waive; /* failed refills due to numa zone mismatch */ + u64 fast; + u64 slow; + u64 slow_high_order; + u64 empty; + u64 refill; + u64 waive; }; +/** + * struct page_pool_recycle_stats - recycling (freeing) statistics + * @cached: recycling placed page in the page pool cache + * @cache_full: page pool cache was full + * @ring: page placed into the ptr ring + * @ring_full: page released from page pool because the ptr ring was full + * @released_refcnt: page released (and not recycled) because refcnt > 1 + */ struct page_pool_recycle_stats { - u64 cached; /* recycling placed page in the cache. */ - u64 cache_full; /* cache was full */ - u64 ring; /* recycling placed page back into ptr ring */ - u64 ring_full; /* page was released from page-pool because - * PTR ring was full. - */ - u64 released_refcnt; /* page released because of elevated - * refcnt - */ + u64 cached; + u64 cache_full; + u64 ring; + u64 ring_full; + u64 released_refcnt; }; -/* This struct wraps the above stats structs so users of the - * page_pool_get_stats API can pass a single argument when requesting the - * stats for the page pool. +/** + * struct page_pool_stats - combined page pool use statistics + * @alloc_stats: see struct page_pool_alloc_stats + * @recycle_stats: see struct page_pool_recycle_stats + * + * Wrapper struct for combining page pool stats with different storage + * requirements. */ struct page_pool_stats { struct page_pool_alloc_stats alloc_stats; @@ -211,6 +240,12 @@ struct page_pool { struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); +/** + * page_pool_dev_alloc_pages() - allocate a page. + * @pool: pool from which to allocate + * + * Get a page from the page allocator or page_pool caches. + */ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) { gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); @@ -230,8 +265,12 @@ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, return page_pool_alloc_frag(pool, offset, size, gfp); } -/* get the stored dma direction. A driver might decide to treat this locally and - * avoid the extra cache line from page_pool to determine the direction +/** + * page_pool_get_dma_dir() - Retrieve the stored DMA direction. + * @pool: pool from which page was allocated + * + * Get the stored dma direction. A driver might decide to store this locally + * and avoid the extra cache line from page_pool to determine the direction. */ static inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) @@ -321,6 +360,19 @@ static inline bool page_pool_is_last_frag(struct page_pool *pool, (page_pool_defrag_page(page, 1) == 0); } +/** + * page_pool_put_page() - release a reference to a page pool page + * @pool: pool from which page was allocated + * @page: page to release a reference on + * @dma_sync_size: how much of the page may have been touched by the device + * @allow_direct: released by the consumer, allow lockless caching + * + * The outcome of this depends on the page refcnt. If the driver bumps + * the refcnt > 1 this will unmap the page. If the page refcnt is 1 + * the allocator owns the page and will try to recycle it in one of the pool + * caches. If PP_FLAG_DMA_SYNC_DEV is set, the page will be synced for_device + * using dma_sync_single_range_for_device(). + */ static inline void page_pool_put_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, @@ -337,14 +389,29 @@ static inline void page_pool_put_page(struct page_pool *pool, #endif } -/* Same as above but will try to sync the entire area pool->max_len */ +/** + * page_pool_put_full_page() - release a reference on a page pool page + * @pool: pool from which page was allocated + * @page: page to release a reference on + * @allow_direct: released by the consumer, allow lockless caching + * + * Similar to page_pool_put_page(), but will DMA sync the entire memory area + * as configured in &page_pool_params.max_len. + */ static inline void page_pool_put_full_page(struct page_pool *pool, struct page *page, bool allow_direct) { page_pool_put_page(pool, page, -1, allow_direct); } -/* Same as above but the caller must guarantee safe context. e.g NAPI */ +/** + * page_pool_recycle_direct() - release a reference on a page pool page + * @pool: pool from which page was allocated + * @page: page to release a reference on + * + * Similar to page_pool_put_full_page() but caller must guarantee safe context + * (e.g NAPI), since it will recycle the page directly into the pool fast cache. + */ static inline void page_pool_recycle_direct(struct page_pool *pool, struct page *page) { @@ -354,6 +421,13 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, #define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ (sizeof(dma_addr_t) > sizeof(unsigned long)) +/** + * page_pool_get_dma_addr() - Retrieve the stored DMA address. + * @page: page allocated from a page pool + * + * Fetch the DMA address of the page. The page pool to which the page belongs + * must had been created with PP_FLAG_DMA_MAP. + */ static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { dma_addr_t ret = page->dma_addr; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 7ca456bfab71..5d615a169718 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -58,6 +58,17 @@ static const char pp_stats[][ETH_GSTRING_LEN] = { "rx_pp_recycle_released_ref", }; +/** + * page_pool_get_stats() - fetch page pool stats + * @pool: pool from which page was allocated + * @stats: struct page_pool_stats to fill in + * + * Retrieve statistics about the page_pool. This API is only available + * if the kernel has been configured with ``CONFIG_PAGE_POOL_STATS=y``. + * A pointer to a caller allocated struct page_pool_stats structure + * is passed to this API which is filled in. The caller can then report + * those stats to the user (perhaps via ethtool, debugfs, etc.). + */ bool page_pool_get_stats(struct page_pool *pool, struct page_pool_stats *stats) { @@ -224,6 +235,10 @@ static int page_pool_init(struct page_pool *pool, return 0; } +/** + * page_pool_create() - create a page pool. + * @params: parameters, see struct page_pool_params + */ struct page_pool *page_pool_create(const struct page_pool_params *params) { struct page_pool *pool; @@ -626,7 +641,21 @@ void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, } EXPORT_SYMBOL(page_pool_put_defragged_page); -/* Caller must not use data area after call, as this function overwrites it */ +/** + * page_pool_put_page_bulk() - release references on multiple pages + * @pool: pool from which pages were allocated + * @data: array holding page pointers + * @count: number of pages in @data + * + * Tries to refill a number of pages into the ptr_ring cache holding ptr_ring + * producer lock. If the ptr_ring is full, page_pool_put_page_bulk() + * will release leftover pages to the page allocator. + * page_pool_put_page_bulk() is suitable to be run inside the driver NAPI tx + * completion loop for the XDP_REDIRECT use case. + * + * Please note the caller must not use data area after running + * page_pool_put_page_bulk(), as this function overwrites it. + */ void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count) { -- cgit v1.2.3 From 992725ff32f534eaa13adfa37f933d4fbf1aa040 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Wed, 2 Aug 2023 21:07:16 +0800 Subject: net: Space.h: Remove unused function declarations Commit 5aa83a4c0a15 (" [PATCH] remove two obsolete net drivers") remove fmv18x_probe(). And commmit 01f4685797a5 ("eth: amd: remove NI6510 support (ni65)") leave ni65_probe(). Commit a10079c66290 ("staging: remove hp100 driver") remove hp100 driver and hp100_probe() declaration is not used anymore. sonic_probe() and iph5526_probe() are never implemented since the beginning of git history. Signed-off-by: Yue Haibing Link: https://lore.kernel.org/r/20230802130716.37308-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/Space.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/net/Space.h b/include/net/Space.h index 08ca9cef0213..c29f3d51c078 100644 --- a/include/net/Space.h +++ b/include/net/Space.h @@ -3,18 +3,11 @@ * ethernet adaptor have the name "eth[0123...]". */ -struct net_device *hp100_probe(int unit); struct net_device *ultra_probe(int unit); struct net_device *wd_probe(int unit); struct net_device *ne_probe(int unit); -struct net_device *fmv18x_probe(int unit); -struct net_device *ni65_probe(int unit); -struct net_device *sonic_probe(int unit); struct net_device *smc_init(int unit); struct net_device *cs89x0_probe(int unit); struct net_device *tc515_probe(int unit); struct net_device *lance_probe(int unit); struct net_device *cops_probe(int unit); - -/* Fibre Channel adapters */ -int iph5526_probe(struct net_device *dev); -- cgit v1.2.3 From 62c1bff593b7e30041d0273b835af9fd6f5ee737 Mon Sep 17 00:00:00 2001 From: Souradeep Chakrabarti Date: Wed, 2 Aug 2023 04:07:40 -0700 Subject: net: mana: Configure hwc timeout from hardware At present hwc timeout value is a fixed value. This patch sets the hwc timeout from the hardware. It now uses a new hardware capability GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG to query and set the value in hwc_timeout. Signed-off-by: Souradeep Chakrabarti Reviewed-by: Jesse Brandeburg Signed-off-by: David S. Miller --- drivers/net/ethernet/microsoft/mana/gdma_main.c | 30 +++++++++++++++++++++++- drivers/net/ethernet/microsoft/mana/hw_channel.c | 24 ++++++++++++++++++- include/net/mana/gdma.h | 20 +++++++++++++++- include/net/mana/hw_channel.h | 5 ++++ 4 files changed, 76 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 3765d3389a9a..6367de0c2c2e 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -106,6 +106,25 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev) return 0; } +static int mana_gd_query_hwc_timeout(struct pci_dev *pdev, u32 *timeout_val) +{ + struct gdma_context *gc = pci_get_drvdata(pdev); + struct gdma_query_hwc_timeout_resp resp = {}; + struct gdma_query_hwc_timeout_req req = {}; + int err; + + mana_gd_init_req_hdr(&req.hdr, GDMA_QUERY_HWC_TIMEOUT, + sizeof(req), sizeof(resp)); + req.timeout_ms = *timeout_val; + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); + if (err || resp.hdr.status) + return err ? err : -EPROTO; + + *timeout_val = resp.timeout_ms; + + return 0; +} + static int mana_gd_detect_devices(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); @@ -882,8 +901,10 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev) struct gdma_context *gc = pci_get_drvdata(pdev); struct gdma_verify_ver_resp resp = {}; struct gdma_verify_ver_req req = {}; + struct hw_channel_context *hwc; int err; + hwc = gc->hwc.driver_data; mana_gd_init_req_hdr(&req.hdr, GDMA_VERIFY_VF_DRIVER_VERSION, sizeof(req), sizeof(resp)); @@ -910,7 +931,14 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev) err, resp.hdr.status); return err ? err : -EPROTO; } - + if (resp.pf_cap_flags1 & GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) { + err = mana_gd_query_hwc_timeout(pdev, &hwc->hwc_timeout); + if (err) { + dev_err(gc->dev, "Failed to set the hwc timeout %d\n", err); + return err; + } + dev_dbg(gc->dev, "set the hwc timeout to %u\n", hwc->hwc_timeout); + } return 0; } diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 2bd1d74021f7..9d1cd3bfcf66 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -174,7 +174,25 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self, complete(&hwc->hwc_init_eqe_comp); break; + case GDMA_EQE_HWC_SOC_RECONFIG_DATA: + type_data.as_uint32 = event->details[0]; + type = type_data.type; + val = type_data.value; + + switch (type) { + case HWC_DATA_CFG_HWC_TIMEOUT: + hwc->hwc_timeout = val; + break; + + default: + dev_warn(hwc->dev, "Received unknown reconfig type %u\n", type); + break; + } + + break; + default: + dev_warn(hwc->dev, "Received unknown gdma event %u\n", event->type); /* Ignore unknown events, which should never happen. */ break; } @@ -696,6 +714,7 @@ int mana_hwc_create_channel(struct gdma_context *gc) gd->driver_data = hwc; hwc->gdma_dev = gd; hwc->dev = gc->dev; + hwc->hwc_timeout = HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS; /* HWC's instance number is always 0. */ gd->dev_id.as_uint32 = 0; @@ -770,6 +789,8 @@ void mana_hwc_destroy_channel(struct gdma_context *gc) hwc->gdma_dev->doorbell = INVALID_DOORBELL; hwc->gdma_dev->pdid = INVALID_PDID; + hwc->hwc_timeout = 0; + kfree(hwc); gc->hwc.driver_data = NULL; gc->hwc.gdma_context = NULL; @@ -825,7 +846,8 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, goto out; } - if (!wait_for_completion_timeout(&ctx->comp_event, 30 * HZ)) { + if (!wait_for_completion_timeout(&ctx->comp_event, + (msecs_to_jiffies(hwc->hwc_timeout) * HZ))) { dev_err(hwc->dev, "HWC: Request timed out!\n"); err = -ETIMEDOUT; goto out; diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 96c120160f15..88b6ef7ce1a6 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -33,6 +33,7 @@ enum gdma_request_type { GDMA_DESTROY_PD = 30, GDMA_CREATE_MR = 31, GDMA_DESTROY_MR = 32, + GDMA_QUERY_HWC_TIMEOUT = 84, /* 0x54 */ }; #define GDMA_RESOURCE_DOORBELL_PAGE 27 @@ -57,6 +58,8 @@ enum gdma_eqe_type { GDMA_EQE_HWC_INIT_EQ_ID_DB = 129, GDMA_EQE_HWC_INIT_DATA = 130, GDMA_EQE_HWC_INIT_DONE = 131, + GDMA_EQE_HWC_SOC_RECONFIG = 132, + GDMA_EQE_HWC_SOC_RECONFIG_DATA = 133, }; enum { @@ -531,10 +534,12 @@ enum { * so the driver is able to reliably support features like busy_poll. */ #define GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX BIT(2) +#define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3) #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ - GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX) + GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ + GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) #define GDMA_DRV_CAP_FLAGS2 0 @@ -664,6 +669,19 @@ struct gdma_disable_queue_req { u32 alloc_res_id_on_creation; }; /* HW DATA */ +/* GDMA_QUERY_HWC_TIMEOUT */ +struct gdma_query_hwc_timeout_req { + struct gdma_req_hdr hdr; + u32 timeout_ms; + u32 reserved; +}; + +struct gdma_query_hwc_timeout_resp { + struct gdma_resp_hdr hdr; + u32 timeout_ms; + u32 reserved; +}; + enum atb_page_size { ATB_PAGE_SIZE_4K, ATB_PAGE_SIZE_8K, diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h index 6a757a6e2732..3d3b5c881bc1 100644 --- a/include/net/mana/hw_channel.h +++ b/include/net/mana/hw_channel.h @@ -23,6 +23,10 @@ #define HWC_INIT_DATA_PF_DEST_RQ_ID 10 #define HWC_INIT_DATA_PF_DEST_CQ_ID 11 +#define HWC_DATA_CFG_HWC_TIMEOUT 1 + +#define HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS 30000 + /* Structures labeled with "HW DATA" are exchanged with the hardware. All of * them are naturally aligned and hence don't need __packed. */ @@ -182,6 +186,7 @@ struct hw_channel_context { u32 pf_dest_vrq_id; u32 pf_dest_vrcq_id; + u32 hwc_timeout; struct hwc_caller_ctx *caller_ctx; }; -- cgit v1.2.3 From 6f5ca184cbef6d2b78772a350a3ed8be696b54a2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Aug 2023 07:53:34 +0000 Subject: tcp/dccp: cache line align inet_hashinfo I have seen tcp_hashinfo starting at a non optimal location, forcing input handlers to pull two cache lines instead of one, and sharing a cache line that was dirtied more than necessary: ffffffff83680600 b tcp_orphan_timer ffffffff83680628 b tcp_orphan_cache ffffffff8368062c b tcp_enable_tx_delay.__tcp_tx_delay_enabled ffffffff83680630 B tcp_hashinfo ffffffff83680680 b tcp_cong_list_lock After this patch, ehash, ehash_locks, ehash_mask and ehash_locks_mask are located in a read-only cache line. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 1177effabed3..843557223414 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -177,7 +177,7 @@ struct inet_hashinfo { struct inet_listen_hashbucket *lhash2; bool pernet; -}; +} ____cacheline_aligned_in_smp; static inline struct inet_hashinfo *tcp_or_dccp_get_hashinfo(const struct sock *sk) { -- cgit v1.2.3 From 7740bb882fdea16b2f3a4d3804827b910f44206c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Aug 2023 07:14:26 +0000 Subject: net: vlan: update wrong comments vlan_insert_tag() and friends do not allocate a new skb. However they might allocate a new skb->head. Update their comments to better describe their behavior. Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 6ba71957851e..3028af87716e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -408,7 +408,7 @@ static inline int __vlan_insert_tag(struct sk_buff *skb, * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len - * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. @@ -437,7 +437,7 @@ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload - * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. @@ -457,7 +457,7 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload - * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. -- cgit v1.2.3 From 8a60a041eada0fbfdc7b6b7a10fdf68ae6a840ce Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Thu, 3 Aug 2023 17:51:01 -0700 Subject: bpf: fix inconsistent return types of bpf_xdp_copy_buf(). Fix inconsistent return types in two implementations of bpf_xdp_copy_buf(). There are two implementations: one is an empty implementation whose return type does not match the actual implementation. Suggested-by: Alexei Starovoitov Signed-off-by: Kui-Feng Lee Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230804005101.1534505-1-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/filter.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 2d6fe30bad5f..761af6b3cf2b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1572,10 +1572,9 @@ static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) return NULL; } -static inline void *bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, - unsigned long len, bool flush) +static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, + unsigned long len, bool flush) { - return NULL; } #endif /* CONFIG_NET */ -- cgit v1.2.3 From 57ecc157b68eac54ee7cdc039e0df8f7f7bd5bc7 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Thu, 3 Aug 2023 21:47:47 +0800 Subject: net: llc: Remove unused function declarations llc_conn_ac_send_i_rsp_as_ack() and llc_conn_ev_sendack_tmr_exp() are never implemented since beginning of git history. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230803134747.41512-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/llc_c_ac.h | 1 - include/net/llc_c_ev.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/llc_c_ac.h b/include/net/llc_c_ac.h index 3e1f76786d7b..7620a9196922 100644 --- a/include/net/llc_c_ac.h +++ b/include/net/llc_c_ac.h @@ -175,7 +175,6 @@ int llc_conn_ac_send_ack_if_needed(struct sock *sk, struct sk_buff *skb); int llc_conn_ac_adjust_npta_by_rr(struct sock *sk, struct sk_buff *skb); int llc_conn_ac_adjust_npta_by_rnr(struct sock *sk, struct sk_buff *skb); int llc_conn_ac_rst_sendack_flag(struct sock *sk, struct sk_buff *skb); -int llc_conn_ac_send_i_rsp_as_ack(struct sock *sk, struct sk_buff *skb); int llc_conn_ac_send_i_as_ack(struct sock *sk, struct sk_buff *skb); void llc_conn_busy_tmr_cb(struct timer_list *t); diff --git a/include/net/llc_c_ev.h b/include/net/llc_c_ev.h index 3948cf111dd0..241889955157 100644 --- a/include/net/llc_c_ev.h +++ b/include/net/llc_c_ev.h @@ -158,7 +158,6 @@ int llc_conn_ev_p_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_ack_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rej_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_busy_tmr_exp(struct sock *sk, struct sk_buff *skb); -int llc_conn_ev_sendack_tmr_exp(struct sock *sk, struct sk_buff *skb); /* NOT_USED functions and their variations */ int llc_conn_ev_rx_xxx_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From 2f0e807bc2f105435be902997a385ebab86d1a7c Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Thu, 3 Aug 2023 21:54:24 +0800 Subject: net: 802: Remove unused function declarations Commit d8d9ba8dc9c7 ("net: 802: remove dead leftover after ipx driver removal") remove these implementations but leave the declarations. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230803135424.41664-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/p8022.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/p8022.h b/include/net/p8022.h index b690ffcad66b..a29e224ac498 100644 --- a/include/net/p8022.h +++ b/include/net/p8022.h @@ -13,7 +13,4 @@ register_8022_client(unsigned char type, struct packet_type *pt, struct net_device *orig_dev)); void unregister_8022_client(struct datalink_proto *proto); - -struct datalink_proto *make_8023_client(void); -void destroy_8023_client(struct datalink_proto *dl); #endif -- cgit v1.2.3 From 781486e415dc701466a25e49fb8bcc28362d80bf Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Thu, 3 Aug 2023 21:45:07 +0800 Subject: af_vsock: Remove unused declaration vsock_release_pending()/vsock_init_tap() Commit d021c344051a ("VSOCK: Introduce VM Sockets") declared but never implemented vsock_release_pending(). Also vsock_init_tap() never implemented since introduction in commit 531b374834c8 ("VSOCK: Add vsockmon tap functions"). Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Reviewed-by: Stefano Garzarella Link: https://lore.kernel.org/r/20230803134507.22660-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/af_vsock.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 0e7504a42925..b01cf9ac2437 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -201,7 +201,6 @@ static inline bool __vsock_in_connected_table(struct vsock_sock *vsk) return !list_empty(&vsk->connected_table); } -void vsock_release_pending(struct sock *pending); void vsock_add_pending(struct sock *listener, struct sock *pending); void vsock_remove_pending(struct sock *listener, struct sock *pending); void vsock_enqueue_accept(struct sock *listener, struct sock *connected); @@ -225,7 +224,6 @@ struct vsock_tap { struct list_head list; }; -int vsock_init_tap(void); int vsock_add_tap(struct vsock_tap *vt); int vsock_remove_tap(struct vsock_tap *vt); void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); -- cgit v1.2.3 From d58f2e15aa0c07f6f03ec71f64d7697ca43d04a1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Aug 2023 14:46:12 +0000 Subject: tcp: set TCP_USER_TIMEOUT locklessly icsk->icsk_user_timeout can be set locklessly, if all read sides use READ_ONCE(). Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- net/ipv4/tcp.c | 23 ++++++++++------------- net/ipv4/tcp_timer.c | 37 ++++++++++++++++++++++--------------- 3 files changed, 33 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d16abdb3541a..3c5efeeb024f 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -564,6 +564,6 @@ void __tcp_sock_set_nodelay(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); -void tcp_sock_set_user_timeout(struct sock *sk, u32 val); +int tcp_sock_set_user_timeout(struct sock *sk, int val); #endif /* _LINUX_TCP_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bcbb33a8c152..34c2a40b0247 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3296,11 +3296,16 @@ int tcp_sock_set_syncnt(struct sock *sk, int val) } EXPORT_SYMBOL(tcp_sock_set_syncnt); -void tcp_sock_set_user_timeout(struct sock *sk, u32 val) +int tcp_sock_set_user_timeout(struct sock *sk, int val) { - lock_sock(sk); + /* Cap the max time in ms TCP will retry or probe the window + * before giving up and aborting (ETIMEDOUT) a connection. + */ + if (val < 0) + return -EINVAL; + WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); - release_sock(sk); + return 0; } EXPORT_SYMBOL(tcp_sock_set_user_timeout); @@ -3464,6 +3469,8 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case TCP_SYNCNT: return tcp_sock_set_syncnt(sk, val); + case TCP_USER_TIMEOUT: + return tcp_sock_set_user_timeout(sk, val); } sockopt_lock_sock(sk); @@ -3611,16 +3618,6 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif - case TCP_USER_TIMEOUT: - /* Cap the max time in ms TCP will retry or probe the window - * before giving up and aborting (ETIMEDOUT) a connection. - */ - if (val < 0) - err = -EINVAL; - else - WRITE_ONCE(icsk->icsk_user_timeout, val); - break; - case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 66040ab457d4..f99e2d06ae7c 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -26,14 +26,15 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - u32 elapsed, start_ts; + u32 elapsed, start_ts, user_timeout; s32 remaining; start_ts = tcp_sk(sk)->retrans_stamp; - if (!icsk->icsk_user_timeout) + user_timeout = READ_ONCE(icsk->icsk_user_timeout); + if (!user_timeout) return icsk->icsk_rto; elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; - remaining = icsk->icsk_user_timeout - elapsed; + remaining = user_timeout - elapsed; if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ @@ -43,16 +44,17 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) { struct inet_connection_sock *icsk = inet_csk(sk); - u32 remaining; + u32 remaining, user_timeout; s32 elapsed; - if (!icsk->icsk_user_timeout || !icsk->icsk_probes_tstamp) + user_timeout = READ_ONCE(icsk->icsk_user_timeout); + if (!user_timeout || !icsk->icsk_probes_tstamp) return when; elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp; if (unlikely(elapsed < 0)) elapsed = 0; - remaining = msecs_to_jiffies(icsk->icsk_user_timeout) - elapsed; + remaining = msecs_to_jiffies(user_timeout) - elapsed; remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN); return min_t(u32, remaining, when); @@ -270,7 +272,7 @@ static int tcp_write_timeout(struct sock *sk) } if (!expired) expired = retransmits_timed_out(sk, retry_until, - icsk->icsk_user_timeout); + READ_ONCE(icsk->icsk_user_timeout)); tcp_fastopen_active_detect_blackhole(sk, expired); if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG)) @@ -384,13 +386,16 @@ static void tcp_probe_timer(struct sock *sk) * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ - if (!icsk->icsk_probes_tstamp) + if (!icsk->icsk_probes_tstamp) { icsk->icsk_probes_tstamp = tcp_jiffies32; - else if (icsk->icsk_user_timeout && - (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >= - msecs_to_jiffies(icsk->icsk_user_timeout)) - goto abort; + } else { + u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); + if (user_timeout && + (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >= + msecs_to_jiffies(user_timeout)) + goto abort; + } max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; @@ -734,13 +739,15 @@ static void tcp_keepalive_timer (struct timer_list *t) elapsed = keepalive_time_elapsed(tp); if (elapsed >= keepalive_time_when(tp)) { + u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); + /* If the TCP_USER_TIMEOUT option is enabled, use that * to determine when to timeout instead. */ - if ((icsk->icsk_user_timeout != 0 && - elapsed >= msecs_to_jiffies(icsk->icsk_user_timeout) && + if ((user_timeout != 0 && + elapsed >= msecs_to_jiffies(user_timeout) && icsk->icsk_probes_out > 0) || - (icsk->icsk_user_timeout == 0 && + (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { tcp_send_active_reset(sk, GFP_ATOMIC); tcp_write_err(sk); -- cgit v1.2.3 From b1d13f7a3b5396503e6869ed627bb4eeab9b524f Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 4 Aug 2023 13:33:53 -0700 Subject: net: mana: Add page pool for RX buffers Add page pool for RX buffers for faster buffer cycle and reduce CPU usage. The standard page pool API is used. With iperf and 128 threads test, this patch improved the throughput by 12-15%, and decreased the IRQ associated CPU's usage from 99-100% to 10-50%. Signed-off-by: Haiyang Zhang Reviewed-by: Jesse Brandeburg Signed-off-by: David S. Miller --- drivers/net/ethernet/microsoft/mana/mana_en.c | 90 ++++++++++++++++++++++----- include/net/mana/mana.h | 3 + 2 files changed, 77 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 21665f114fe9..a08023c57e25 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1415,8 +1415,8 @@ static struct sk_buff *mana_build_skb(struct mana_rxq *rxq, void *buf_va, return skb; } -static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, - struct mana_rxq *rxq) +static void mana_rx_skb(void *buf_va, bool from_pool, + struct mana_rxcomp_oob *cqe, struct mana_rxq *rxq) { struct mana_stats_rx *rx_stats = &rxq->stats; struct net_device *ndev = rxq->ndev; @@ -1449,6 +1449,9 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, if (!skb) goto drop; + if (from_pool) + skb_mark_for_recycle(skb); + skb->dev = napi->dev; skb->protocol = eth_type_trans(skb, ndev); @@ -1499,9 +1502,14 @@ drop_xdp: u64_stats_update_end(&rx_stats->syncp); drop: - WARN_ON_ONCE(rxq->xdp_save_va); - /* Save for reuse */ - rxq->xdp_save_va = buf_va; + if (from_pool) { + page_pool_recycle_direct(rxq->page_pool, + virt_to_head_page(buf_va)); + } else { + WARN_ON_ONCE(rxq->xdp_save_va); + /* Save for reuse */ + rxq->xdp_save_va = buf_va; + } ++ndev->stats.rx_dropped; @@ -1509,11 +1517,13 @@ drop: } static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, - dma_addr_t *da, bool is_napi) + dma_addr_t *da, bool *from_pool, bool is_napi) { struct page *page; void *va; + *from_pool = false; + /* Reuse XDP dropped page if available */ if (rxq->xdp_save_va) { va = rxq->xdp_save_va; @@ -1534,17 +1544,22 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, return NULL; } } else { - page = dev_alloc_page(); + page = page_pool_dev_alloc_pages(rxq->page_pool); if (!page) return NULL; + *from_pool = true; va = page_to_virt(page); } *da = dma_map_single(dev, va + rxq->headroom, rxq->datasize, DMA_FROM_DEVICE); if (dma_mapping_error(dev, *da)) { - put_page(virt_to_head_page(va)); + if (*from_pool) + page_pool_put_full_page(rxq->page_pool, page, false); + else + put_page(virt_to_head_page(va)); + return NULL; } @@ -1553,21 +1568,25 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, /* Allocate frag for rx buffer, and save the old buf */ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq, - struct mana_recv_buf_oob *rxoob, void **old_buf) + struct mana_recv_buf_oob *rxoob, void **old_buf, + bool *old_fp) { + bool from_pool; dma_addr_t da; void *va; - va = mana_get_rxfrag(rxq, dev, &da, true); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool, true); if (!va) return; dma_unmap_single(dev, rxoob->sgl[0].address, rxq->datasize, DMA_FROM_DEVICE); *old_buf = rxoob->buf_va; + *old_fp = rxoob->from_pool; rxoob->buf_va = va; rxoob->sgl[0].address = da; + rxoob->from_pool = from_pool; } static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, @@ -1581,6 +1600,7 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, struct device *dev = gc->dev; void *old_buf = NULL; u32 curr, pktlen; + bool old_fp; apc = netdev_priv(ndev); @@ -1623,12 +1643,12 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, rxbuf_oob = &rxq->rx_oobs[curr]; WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1); - mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf); + mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp); /* Unsuccessful refill will have old_buf == NULL. * In this case, mana_rx_skb() will drop the packet. */ - mana_rx_skb(old_buf, oob, rxq); + mana_rx_skb(old_buf, old_fp, oob, rxq); drop: mana_move_wq_tail(rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu); @@ -1888,6 +1908,7 @@ static void mana_destroy_rxq(struct mana_port_context *apc, struct mana_recv_buf_oob *rx_oob; struct device *dev = gc->dev; struct napi_struct *napi; + struct page *page; int i; if (!rxq) @@ -1920,10 +1941,18 @@ static void mana_destroy_rxq(struct mana_port_context *apc, dma_unmap_single(dev, rx_oob->sgl[0].address, rx_oob->sgl[0].size, DMA_FROM_DEVICE); - put_page(virt_to_head_page(rx_oob->buf_va)); + page = virt_to_head_page(rx_oob->buf_va); + + if (rx_oob->from_pool) + page_pool_put_full_page(rxq->page_pool, page, false); + else + put_page(page); + rx_oob->buf_va = NULL; } + page_pool_destroy(rxq->page_pool); + if (rxq->gdma_rq) mana_gd_destroy_queue(gc, rxq->gdma_rq); @@ -1934,18 +1963,20 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, struct mana_rxq *rxq, struct device *dev) { struct mana_port_context *mpc = netdev_priv(rxq->ndev); + bool from_pool = false; dma_addr_t da; void *va; if (mpc->rxbufs_pre) va = mana_get_rxbuf_pre(rxq, &da); else - va = mana_get_rxfrag(rxq, dev, &da, false); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool, false); if (!va) return -ENOMEM; rx_oob->buf_va = va; + rx_oob->from_pool = from_pool; rx_oob->sgl[0].address = da; rx_oob->sgl[0].size = rxq->datasize; @@ -2015,6 +2046,26 @@ static int mana_push_wqe(struct mana_rxq *rxq) return 0; } +static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc) +{ + struct page_pool_params pprm = {}; + int ret; + + pprm.pool_size = RX_BUFFERS_PER_QUEUE; + pprm.nid = gc->numa_node; + pprm.napi = &rxq->rx_cq.napi; + + rxq->page_pool = page_pool_create(&pprm); + + if (IS_ERR(rxq->page_pool)) { + ret = PTR_ERR(rxq->page_pool); + rxq->page_pool = NULL; + return ret; + } + + return 0; +} + static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, u32 rxq_idx, struct mana_eq *eq, struct net_device *ndev) @@ -2044,6 +2095,13 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, mana_get_rxbuf_cfg(ndev->mtu, &rxq->datasize, &rxq->alloc_size, &rxq->headroom); + /* Create page pool for RX queue */ + err = mana_create_page_pool(rxq, gc); + if (err) { + netdev_err(ndev, "Create page pool err:%d\n", err); + goto out; + } + err = mana_alloc_rx_wqe(apc, rxq, &rq_size, &cq_size); if (err) goto out; @@ -2115,8 +2173,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx, cq->napi.napi_id)); - WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL)); + WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, MEM_TYPE_PAGE_POOL, + rxq->page_pool)); napi_enable(&cq->napi); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 1ccdca03e166..879990101c9f 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -282,6 +282,7 @@ struct mana_recv_buf_oob { struct gdma_wqe_request wqe_req; void *buf_va; + bool from_pool; /* allocated from a page pool */ /* SGL of the buffer going to be sent has part of the work request. */ u32 num_sge; @@ -332,6 +333,8 @@ struct mana_rxq { bool xdp_flush; int xdp_rc; /* XDP redirect return code */ + struct page_pool *page_pool; + /* MUST BE THE LAST MEMBER: * Each receive buffer has an associated mana_recv_buf_oob. */ -- cgit v1.2.3 From 047551cd305ce2f51f8cf16ed5638f1e120f90af Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Sat, 5 Aug 2023 18:50:33 +0800 Subject: neighbour: Remove unused function declaration pneigh_for_each() pneigh_for_each() is never implemented since the beginning of git history. Signed-off-by: Yue Haibing Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/neighbour.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index f6a8ecc6b1fa..6da68886fabb 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -394,8 +394,6 @@ void neigh_for_each(struct neigh_table *tbl, void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)); int neigh_xmit(int fam, struct net_device *, const void *, struct sk_buff *); -void pneigh_for_each(struct neigh_table *tbl, - void (*cb)(struct pneigh_entry *)); struct neigh_seq_state { struct seq_net_private p; -- cgit v1.2.3 From 992b47851be9125c1de480c8f34cc0ea7eb58daf Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Sat, 5 Aug 2023 18:52:08 +0800 Subject: net: pkt_cls: Remove unused inline helpers Commit acb674428c3d ("net: sched: introduce per-block callbacks") implemented these but never used it. Signed-off-by: Yue Haibing Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 139cd09828af..f308e8268651 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -138,19 +138,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return NULL; } -static inline -int tc_setup_cb_block_register(struct tcf_block *block, flow_setup_cb_t *cb, - void *cb_priv) -{ - return 0; -} - -static inline -void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb, - void *cb_priv) -{ -} - static inline int tcf_classify(struct sk_buff *skb, const struct tcf_block *block, const struct tcf_proto *tp, -- cgit v1.2.3 From 2c6af36beb2e7e0066a74bc930e562f66ad88bb6 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Sat, 5 Aug 2023 18:53:54 +0800 Subject: ndisc: Remove unused ndisc_ifinfo_sysctl_strategy() declaration Commit f8572d8f2a2b ("sysctl net: Remove unused binary sysctl code") left behind this declaration. Signed-off-by: Yue Haibing Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/ndisc.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 52eae0943433..9bbdf6eaa942 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -488,9 +488,6 @@ void igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen); #endif void inet6_ifinfo_notify(int event, struct inet6_dev *idev); -- cgit v1.2.3 From cc97777c80fdfabe12997581131872a03fdcf683 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Sat, 5 Aug 2023 19:00:09 +0800 Subject: udp/udplite: Remove unused function declarations udp{,lite}_get_port() Commit 6ba5a3c52da0 ("[UDP]: Make full use of proto.h.udp_hash innovation.") removed these implementations but leave declarations. Signed-off-by: Yue Haibing Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/udp.h | 3 --- include/net/udplite.h | 2 -- 2 files changed, 5 deletions(-) (limited to 'include') diff --git a/include/net/udp.h b/include/net/udp.h index 5a8421cd9083..488a6d2babcc 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -273,9 +273,6 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, int udp_v4_early_demux(struct sk_buff *skb); bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); -int udp_get_port(struct sock *sk, unsigned short snum, - int (*saddr_cmp)(const struct sock *, - const struct sock *)); int udp_err(struct sk_buff *, u32); int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); diff --git a/include/net/udplite.h b/include/net/udplite.h index 299c14ce2bb9..bd33ff2b8f42 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -81,6 +81,4 @@ static inline __wsum udplite_csum(struct sk_buff *skb) } void udplite4_register(void); -int udplite_get_port(struct sock *sk, unsigned short snum, - int (*scmp)(const struct sock *, const struct sock *)); #endif /* _UDPLITE_H */ -- cgit v1.2.3 From f3147015fa0769cf1dcbfdb9040ad380cc4daeb5 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Mon, 12 Jun 2023 11:58:14 +0300 Subject: net/mlx5: Add IRQ vector to CPU lookup function Currently, once driver load completes, IRQ requests were performed for all vectors. However, as we move to support dynamic creation of EQs, this will not be the case as some IRQs will not exist at this stage. Thus, in such case, use the default CPU to IRQ mapping which is the serial mapping based on IRQ vector index. Meaning, the n'th vector gets mapped to the n'th CPU. Introduce an API function mlx5_comp_vector_cpu() that takes an IRQ index and provides the corresponding CPU mapping. It utilizes the existing IRQ affinity if defined, or resorts to the default serialized CPU mapping otherwise. Signed-off-by: Maher Sanalla Reviewed-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/trap.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 19 ++++++++++++++++--- include/linux/mlx5/driver.h | 3 +-- 4 files changed, 20 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index 201ac7dd338f..bcf9807a5556 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -128,7 +128,7 @@ static void mlx5e_build_trap_params(struct mlx5_core_dev *mdev, static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv) { - int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, 0)); + int cpu = mlx5_comp_vector_get_cpu(priv->mdev, 0); struct net_device *netdev = priv->netdev; struct mlx5e_trap *t; 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 1c820119e438..9ec7b975c549 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2445,7 +2445,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct xsk_buff_pool *xsk_pool, struct mlx5e_channel **cp) { - int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix)); + int cpu = mlx5_comp_vector_get_cpu(priv->mdev, ix); struct net_device *netdev = priv->netdev; struct mlx5e_xsk_param xsk; struct mlx5e_channel *c; @@ -2862,7 +2862,7 @@ static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, cpumask_clear(priv->scratchpad.cpumask); for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) { - int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(mdev, irq)); + int cpu = mlx5_comp_vector_get_cpu(mdev, irq); cpumask_set_cpu(cpu, priv->scratchpad.cpumask); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index ad654d460d0c..2f5c0d00285f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -1058,7 +1058,7 @@ unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_comp_vectors_count); -struct cpumask * +static struct cpumask * mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector) { struct mlx5_eq_table *table = dev->priv.eq_table; @@ -1068,10 +1068,23 @@ mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector) if (eq) return mlx5_irq_get_affinity_mask(eq->core.irq); - WARN_ON_ONCE(1); return NULL; } -EXPORT_SYMBOL(mlx5_comp_irq_get_affinity_mask); + +int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector) +{ + struct cpumask *mask; + int cpu; + + mask = mlx5_comp_irq_get_affinity_mask(dev, vector); + if (mask) + cpu = cpumask_first(mask); + else + cpu = mlx5_cpumask_default_spread(dev->priv.numa_node, vector); + + return cpu; +} +EXPORT_SYMBOL(mlx5_comp_vector_get_cpu); #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fa70c25423b2..e686722fa4ca 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1109,8 +1109,7 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg, void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg); unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev); -struct cpumask * -mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector); +int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector); unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev); int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index, u8 roce_version, u8 roce_l3_type, const u8 *gid, -- cgit v1.2.3 From 674dd4e2e04e7a62bfacf28129e0808f33395bdf Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Thu, 22 Jun 2023 18:52:44 +0300 Subject: net/mlx5: Rename mlx5_comp_vectors_count() to mlx5_comp_vectors_max() To accurately represent its purpose, rename the function that retrieves the value of maximum vectors from mlx5_comp_vectors_count() to mlx5_comp_vectors_max(). Signed-off-by: Maher Sanalla Reviewed-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/main.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c | 2 +- drivers/vfio/pci/mlx5/cmd.c | 2 +- include/linux/mlx5/driver.h | 2 +- 7 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index f0b394ed7452..3c25b9045f9d 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3685,7 +3685,7 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) if (mlx5_use_mad_ifc(dev)) get_ext_port_caps(dev); - dev->ib_dev.num_comp_vectors = mlx5_comp_vectors_count(mdev); + dev->ib_dev.num_comp_vectors = mlx5_comp_vectors_max(mdev); mutex_init(&dev->cap_mask_mutex); INIT_LIST_HEAD(&dev->qp_list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0f8f70b91485..c1deb04ba7e8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -193,7 +193,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) { return is_kdump_kernel() ? MLX5E_MIN_NUM_CHANNELS : - min_t(int, mlx5_comp_vectors_count(mdev), MLX5E_MAX_NUM_CHANNELS); + min_t(int, mlx5_comp_vectors_max(mdev), MLX5E_MAX_NUM_CHANNELS); } /* The maximum WQE size can be retrieved by max_wqe_sz_sq in diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 9ec7b975c549..5710d755c2c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2856,7 +2856,7 @@ static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, struct mlx5_core_dev *mdev = priv->mdev; int num_comp_vectors, ix, irq; - num_comp_vectors = mlx5_comp_vectors_count(mdev); + num_comp_vectors = mlx5_comp_vectors_max(mdev); for (ix = 0; ix < params->num_channels; ix++) { cpumask_clear(priv->scratchpad.cpumask); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 2f5c0d00285f..6272962ea077 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -1052,11 +1052,11 @@ 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) +unsigned int mlx5_comp_vectors_max(struct mlx5_core_dev *dev) { return dev->priv.eq_table->max_comp_eqs; } -EXPORT_SYMBOL(mlx5_comp_vectors_count); +EXPORT_SYMBOL(mlx5_comp_vectors_max); static struct cpumask * mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector) 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 4a5ae86e2b62..24bb30b5008c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -1096,7 +1096,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, if (!in) goto err_cqwq; - vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev); + vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev); err = mlx5_vector2eqn(mdev, vector, &eqn); if (err) { kvfree(in); diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c index deed156e6165..eee20f04a469 100644 --- a/drivers/vfio/pci/mlx5/cmd.c +++ b/drivers/vfio/pci/mlx5/cmd.c @@ -1025,7 +1025,7 @@ static int mlx5vf_create_cq(struct mlx5_core_dev *mdev, goto err_buff; } - vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev); + vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev); err = mlx5_vector2eqn(mdev, vector, &eqn); if (err) goto err_vec; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e686722fa4ca..43c4fd26c69a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1108,7 +1108,7 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg, bool map_wc, bool fast_path); void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg); -unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev); +unsigned int mlx5_comp_vectors_max(struct mlx5_core_dev *dev); int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector); unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev); int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index, -- cgit v1.2.3 From f14c1a14e63227a65faa68237687784a6dd2e922 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Mon, 12 Jun 2023 10:13:50 +0300 Subject: net/mlx5: Allocate completion EQs dynamically This commit enables the dynamic allocation of EQs at runtime, allowing for more flexibility in managing completion EQs and reducing the memory overhead of driver load. Whenever a CQ is created for a given vector index, the driver will lookup to see if there is an already mapped completion EQ for that vector, if so, utilize it. Otherwise, allocate a new EQ on demand and then utilize it for the CQ completion events. Add a protection lock to the EQ table to protect from concurrent EQ creation attempts. While at it, replace mlx5_vector2irqn()/mlx5_vector2eqn() with mlx5_comp_eqn_get() and mlx5_comp_irqn_get() which will allocate an EQ on demand if no EQ is found for the given vector. Signed-off-by: Maher Sanalla Reviewed-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/cq.c | 2 +- drivers/infiniband/hw/mlx5/devx.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 +- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 80 ++++++++++++---------- .../net/ethernet/mellanox/mlx5/core/fpga/conn.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h | 2 +- .../ethernet/mellanox/mlx5/core/steering/dr_send.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 +- drivers/vfio/pci/mlx5/cmd.c | 2 +- include/linux/mlx5/driver.h | 2 +- 11 files changed, 54 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index efc9e4a6df04..9773d2a3d97f 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -993,7 +993,7 @@ 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); + err = mlx5_comp_eqn_get(dev->mdev, vector, &eqn); if (err) goto err_cqb; diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index db5fb196c728..8ba53edf2311 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1002,7 +1002,7 @@ 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); + err = mlx5_comp_eqn_get(dev->mdev, user_vector, &dev_eqn); if (err < 0) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5710d755c2c4..5919b889479f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1989,7 +1989,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) int eqn; int err; - err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn); + err = mlx5_comp_eqn_get(mdev, param->eq_ix, &eqn); if (err) return err; @@ -2452,7 +2452,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, unsigned int irq; int err; - err = mlx5_vector2irqn(priv->mdev, ix, &irq); + err = mlx5_comp_irqn_get(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 6e6e0a1c12b5..ea0405e0a43f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -58,6 +58,7 @@ struct mlx5_eq_table { struct mlx5_nb cq_err_nb; struct mutex lock; /* sync async eqs creations */ + struct mutex comp_lock; /* sync comp eqs creations */ int curr_comp_eqs; int max_comp_eqs; struct mlx5_irq_table *irq_table; @@ -457,6 +458,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev) cpumask_clear(&eq_table->used_cpus); xa_init(&eq_table->comp_eqs); xa_init(&eq_table->comp_irqs); + mutex_init(&eq_table->comp_lock); eq_table->curr_comp_eqs = 0; return 0; } @@ -985,6 +987,7 @@ static u16 comp_eq_depth_devlink_param_get(struct mlx5_core_dev *dev) return MLX5_COMP_EQ_SIZE; } +/* Must be called with EQ table comp_lock held */ static int create_comp_eq(struct mlx5_core_dev *dev, u16 vecidx) { struct mlx5_eq_table *table = dev->priv.eq_table; @@ -994,6 +997,13 @@ static int create_comp_eq(struct mlx5_core_dev *dev, u16 vecidx) int nent; int err; + lockdep_assert_held(&table->comp_lock); + if (table->curr_comp_eqs == table->max_comp_eqs) { + mlx5_core_err(dev, "maximum number of vectors is allocated, %d\n", + table->max_comp_eqs); + return -ENOMEM; + } + err = comp_irq_request(dev, vecidx); if (err) return err; @@ -1033,7 +1043,7 @@ static int create_comp_eq(struct mlx5_core_dev *dev, u16 vecidx) goto disable_eq; table->curr_comp_eqs++; - return 0; + return eq->core.eqn; disable_eq: mlx5_eq_disable(dev, &eq->core, &eq->irq_nb); @@ -1044,32 +1054,47 @@ clean_irq: return err; } -static int vector2eqnirqn(struct mlx5_core_dev *dev, int vector, int *eqn, - unsigned int *irqn) +int mlx5_comp_eqn_get(struct mlx5_core_dev *dev, u16 vecidx, int *eqn) { struct mlx5_eq_table *table = dev->priv.eq_table; struct mlx5_eq_comp *eq; + int ret = 0; - eq = xa_load(&table->comp_eqs, vector); - if (!eq) - return -ENOENT; - - if (irqn) - *irqn = eq->core.irqn; - if (eqn) + mutex_lock(&table->comp_lock); + eq = xa_load(&table->comp_eqs, vecidx); + if (eq) { *eqn = eq->core.eqn; + goto out; + } + + ret = create_comp_eq(dev, vecidx); + if (ret < 0) { + mutex_unlock(&table->comp_lock); + return ret; + } + + *eqn = ret; +out: + mutex_unlock(&table->comp_lock); return 0; } +EXPORT_SYMBOL(mlx5_comp_eqn_get); -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn) +int mlx5_comp_irqn_get(struct mlx5_core_dev *dev, int vector, unsigned int *irqn) { - return vector2eqnirqn(dev, vector, eqn, NULL); -} -EXPORT_SYMBOL(mlx5_vector2eqn); + struct mlx5_eq_table *table = dev->priv.eq_table; + struct mlx5_eq_comp *eq; + int eqn; + int err; -int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn) -{ - return vector2eqnirqn(dev, vector, NULL, irqn); + /* Allocate the EQ if not allocated yet */ + err = mlx5_comp_eqn_get(dev, vector, &eqn); + if (err) + return err; + + eq = xa_load(&table->comp_eqs, vector); + *irqn = eq->core.irqn; + return 0; } unsigned int mlx5_comp_vectors_max(struct mlx5_core_dev *dev) @@ -1119,10 +1144,9 @@ struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn) struct mlx5_eq_comp *eq; unsigned long index; - xa_for_each(&table->comp_eqs, index, eq) { + xa_for_each(&table->comp_eqs, index, eq) if (eq->core.eqn == eqn) return eq; - } return ERR_PTR(-ENOENT); } @@ -1130,11 +1154,7 @@ struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn) /* This function should only be called after mlx5_cmd_force_teardown_hca */ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev) { - struct mlx5_eq_table *table = dev->priv.eq_table; - - mutex_lock(&table->lock); /* sync with create/destroy_async_eq */ mlx5_irq_table_free_irqs(dev); - mutex_unlock(&table->lock); } #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING @@ -1176,7 +1196,6 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev) { struct mlx5_eq_table *eq_table = dev->priv.eq_table; int err; - int i; eq_table->max_comp_eqs = get_num_eqs(dev); err = create_async_eqs(dev); @@ -1191,21 +1210,8 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev) goto err_rmap; } - for (i = 0; i < eq_table->max_comp_eqs; i++) { - err = create_comp_eq(dev, i); - if (err < 0) - break; - } - - if (!i) { - mlx5_core_err(dev, "Failed to create completion EQs\n"); - goto err_comp_eqs; - } - return 0; -err_comp_eqs: - free_rmap(dev); err_rmap: destroy_async_eqs(dev); err_async_eqs: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index 12abe991583a..c4de6bf8d1b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -445,7 +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); + err = mlx5_comp_eqn_get(mdev, smp_processor_id(), &eqn); if (err) { kvfree(in); goto err_cqwq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c index 5a80fb7dbbca..40c7be124041 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c @@ -81,7 +81,7 @@ static int create_aso_cq(struct mlx5_aso_cq *cq, void *cqc_data) int inlen, eqn; int err; - err = mlx5_vector2eqn(mdev, 0, &eqn); + err = mlx5_comp_eqn_get(mdev, 0, &eqn); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index d3d628b862f3..69a75459775d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -104,6 +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); +int mlx5_comp_irqn_get(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 24bb30b5008c..6fa06ba2d346 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -1097,7 +1097,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, goto err_cqwq; vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev); - err = mlx5_vector2eqn(mdev, vector, &eqn); + err = mlx5_comp_eqn_get(mdev, vector, &eqn); if (err) { kvfree(in); goto err_cqwq; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 9138ef2fb2c8..bece4df7b8dd 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -580,7 +580,7 @@ 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); + err = mlx5_comp_eqn_get(mdev, 0, &eqn); if (err) goto err_vec; diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c index eee20f04a469..c82c1f4fc588 100644 --- a/drivers/vfio/pci/mlx5/cmd.c +++ b/drivers/vfio/pci/mlx5/cmd.c @@ -1026,7 +1026,7 @@ static int mlx5vf_create_cq(struct mlx5_core_dev *mdev, } vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev); - err = mlx5_vector2eqn(mdev, vector, &eqn); + err = mlx5_comp_eqn_get(mdev, vector, &eqn); if (err) goto err_vec; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 43c4fd26c69a..3e1017d764b7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1058,7 +1058,7 @@ void mlx5_unregister_debugfs(void); 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); +int mlx5_comp_eqn_get(struct mlx5_core_dev *dev, u16 vecidx, 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 26cfb838aa002a5c03319f7fce87e9313e794351 Mon Sep 17 00:00:00 2001 From: Johannes Zink Date: Tue, 1 Aug 2023 17:44:29 +0200 Subject: net: stmmac: correct MAC propagation delay The IEEE1588 Standard specifies that the timestamps of Packets must be captured when the PTP message timestamp point (leading edge of first octet after the start of frame delimiter) crosses the boundary between the node and the network. As the MAC latches the timestamp at an internal point, the captured timestamp must be corrected for the additional data transmission latency, as described in the publicly available datasheet [1]. This patch only corrects for the MAC-Internal delay, which can be read out from the MAC_Ingress_Timestamp_Latency register on DWMAC version 5, since the Phy framework currently does not support querying the Phy ingress and egress latency. The Closs Domain Crossing Circuits errors as indicated in [1] are already being accounted in the stmmac_get_tx_hwtstamp() function and are not corrected here. As the Latency varies for different link speeds and MII modes of operation, the correction value needs to be updated on each link state change. As the delay also causes a phase shift in the timestamp counter compared to the rest of the network, this correction will also reduce phase error when generating PPS outputs from the timestamp counter. Since the correction registers may be unavailable on some hardware and no feature bits are documented for dynamically detection of the MAC propagation delay readout, introduce a feature bit to explicitely enable MAC delay Correction in the gluecode driver. [1] i.MX8MP Reference Manual, rev.1 Section 11.7.2.5.3 "Timestamp correction" Signed-off-by: Johannes Zink Link: https://lore.kernel.org/r/20230719-stmmac_correct_mac_delay-v2-1-3366f38ee9a6@pengutronix.de Link: https://lore.kernel.org/r/20230719-stmmac_correct_mac_delay-v3-1-61e63427735e@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/hwif.h | 3 ++ .../net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 43 ++++++++++++++++++++++ drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +++ drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h | 6 +++ include/linux/stmmac.h | 1 + 5 files changed, 59 insertions(+) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 652af8f6e75f..238f17c50a1e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -532,6 +532,7 @@ struct stmmac_hwtimestamp { void (*get_systime) (void __iomem *ioaddr, u64 *systime); void (*get_ptptime)(void __iomem *ioaddr, u64 *ptp_time); void (*timestamp_interrupt)(struct stmmac_priv *priv); + void (*hwtstamp_correct_latency)(struct stmmac_priv *priv); }; #define stmmac_config_hw_tstamping(__priv, __args...) \ @@ -550,6 +551,8 @@ struct stmmac_hwtimestamp { stmmac_do_void_callback(__priv, ptp, get_ptptime, __args) #define stmmac_timestamp_interrupt(__priv, __args...) \ stmmac_do_void_callback(__priv, ptp, timestamp_interrupt, __args) +#define stmmac_hwtstamp_correct_latency(__priv, __args...) \ + stmmac_do_void_callback(__priv, ptp, hwtstamp_correct_latency, __args) struct stmmac_tx_queue; struct stmmac_rx_queue; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index fa2c3ba7e9fe..540f6a4ec0b8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -60,6 +60,48 @@ static void config_sub_second_increment(void __iomem *ioaddr, *ssinc = data; } +static void hwtstamp_correct_latency(struct stmmac_priv *priv) +{ + void __iomem *ioaddr = priv->ptpaddr; + u32 reg_tsic, reg_tsicsns; + u32 reg_tsec, reg_tsecsns; + u64 scaled_ns; + u32 val; + + /* MAC-internal ingress latency */ + scaled_ns = readl(ioaddr + PTP_TS_INGR_LAT); + + /* See section 11.7.2.5.3.1 "Ingress Correction" on page 4001 of + * i.MX8MP Applications Processor Reference Manual Rev. 1, 06/2021 + */ + val = readl(ioaddr + PTP_TCR); + if (val & PTP_TCR_TSCTRLSSR) + /* nanoseconds field is in decimal format with granularity of 1ns/bit */ + scaled_ns = ((u64)NSEC_PER_SEC << 16) - scaled_ns; + else + /* nanoseconds field is in binary format with granularity of ~0.466ns/bit */ + scaled_ns = ((1ULL << 31) << 16) - + DIV_U64_ROUND_CLOSEST(scaled_ns * PSEC_PER_NSEC, 466U); + + reg_tsic = scaled_ns >> 16; + reg_tsicsns = scaled_ns & 0xff00; + + /* set bit 31 for 2's compliment */ + reg_tsic |= BIT(31); + + writel(reg_tsic, ioaddr + PTP_TS_INGR_CORR_NS); + writel(reg_tsicsns, ioaddr + PTP_TS_INGR_CORR_SNS); + + /* MAC-internal egress latency */ + scaled_ns = readl(ioaddr + PTP_TS_EGR_LAT); + + reg_tsec = scaled_ns >> 16; + reg_tsecsns = scaled_ns & 0xff00; + + writel(reg_tsec, ioaddr + PTP_TS_EGR_CORR_NS); + writel(reg_tsecsns, ioaddr + PTP_TS_EGR_CORR_SNS); +} + static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec) { u32 value; @@ -221,4 +263,5 @@ const struct stmmac_hwtimestamp stmmac_ptp = { .get_systime = get_systime, .get_ptptime = get_ptptime, .timestamp_interrupt = timestamp_interrupt, + .hwtstamp_correct_latency = hwtstamp_correct_latency, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e1f1c034d325..99aa5360b3ff 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -909,6 +909,9 @@ static int stmmac_init_ptp(struct stmmac_priv *priv) priv->hwts_tx_en = 0; priv->hwts_rx_en = 0; + if (priv->plat->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY) + stmmac_hwtstamp_correct_latency(priv, priv); + return 0; } @@ -1094,6 +1097,9 @@ static void stmmac_mac_link_up(struct phylink_config *config, if (priv->dma_cap.fpesel) stmmac_fpe_link_state_handle(priv, true); + + if (priv->plat->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY) + stmmac_hwtstamp_correct_latency(priv, priv); } static const struct phylink_mac_ops stmmac_phylink_mac_ops = { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h index bf619295d079..d1fe4b46f162 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h @@ -26,6 +26,12 @@ #define PTP_ACR 0x40 /* Auxiliary Control Reg */ #define PTP_ATNR 0x48 /* Auxiliary Timestamp - Nanoseconds Reg */ #define PTP_ATSR 0x4c /* Auxiliary Timestamp - Seconds Reg */ +#define PTP_TS_INGR_CORR_NS 0x58 /* Ingress timestamp correction nanoseconds */ +#define PTP_TS_EGR_CORR_NS 0x5C /* Egress timestamp correction nanoseconds*/ +#define PTP_TS_INGR_CORR_SNS 0x60 /* Ingress timestamp correction subnanoseconds */ +#define PTP_TS_EGR_CORR_SNS 0x64 /* Egress timestamp correction subnanoseconds */ +#define PTP_TS_INGR_LAT 0x68 /* MAC internal Ingress Latency */ +#define PTP_TS_EGR_LAT 0x6c /* MAC internal Egress Latency */ #define PTP_STNSUR_ADDSUB_SHIFT 31 #define PTP_DIGITAL_ROLLOVER_MODE 0x3B9ACA00 /* 10e9-1 ns */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 3d0702510224..652404c03944 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -218,6 +218,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_INT_SNAPSHOT_EN BIT(9) #define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI BIT(10) #define STMMAC_FLAG_EN_TX_LPI_CLOCKGATING BIT(11) +#define STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY BIT(12) struct plat_stmmacenet_data { int bus_id; -- cgit v1.2.3 From a9ca9f9ceff382b58b488248f0c0da9e157f5d06 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Fri, 4 Aug 2023 20:05:24 +0200 Subject: page_pool: split types and declarations from page_pool.h Split types and pure function declarations from page_pool.h and add them in page_page/types.h, so that C sources can include page_pool.h and headers should generally only include page_pool/types.h as suggested by jakub. Rename page_pool.h to page_pool/helpers.h to have both in one place. Signed-off-by: Yunsheng Lin Suggested-by: Jakub Kicinski Signed-off-by: Alexander Lobakin Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/20230804180529.2483231-2-aleksander.lobakin@intel.com [Jakub: change microsoft/mana, fix kdoc paths in Documentation] Signed-off-by: Jakub Kicinski --- Documentation/networking/page_pool.rst | 6 +- MAINTAINERS | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 2 +- drivers/net/ethernet/engleder/tsnep_main.c | 1 + drivers/net/ethernet/freescale/fec_main.c | 1 + drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 1 + drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 2 +- drivers/net/ethernet/marvell/mvneta.c | 2 +- drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 2 +- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 1 + .../ethernet/marvell/octeontx2/nic/otx2_common.c | 1 + .../net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 1 + drivers/net/ethernet/mediatek/mtk_eth_soc.c | 1 + drivers/net/ethernet/mediatek/mtk_eth_soc.h | 2 +- .../net/ethernet/mellanox/mlx5/core/en/params.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en/trap.c | 1 - drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 2 +- .../net/ethernet/microchip/lan966x/lan966x_fdma.c | 1 + .../net/ethernet/microchip/lan966x/lan966x_main.h | 2 +- drivers/net/ethernet/microsoft/mana/mana_en.c | 1 + drivers/net/ethernet/socionext/netsec.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 + drivers/net/ethernet/ti/cpsw.c | 2 +- drivers/net/ethernet/ti/cpsw_new.c | 2 +- drivers/net/ethernet/ti/cpsw_priv.c | 2 +- drivers/net/ethernet/wangxun/libwx/wx_lib.c | 2 +- drivers/net/veth.c | 2 +- drivers/net/wireless/mediatek/mt76/mac80211.c | 1 - drivers/net/wireless/mediatek/mt76/mt76.h | 1 + drivers/net/xen-netfront.c | 2 +- include/linux/skbuff.h | 2 +- include/net/page_pool.h | 470 --------------------- include/net/page_pool/helpers.h | 238 +++++++++++ include/net/page_pool/types.h | 238 +++++++++++ include/trace/events/page_pool.h | 2 +- net/bpf/test_run.c | 2 +- net/core/page_pool.c | 2 +- net/core/skbuff.c | 2 +- net/core/xdp.c | 2 +- 44 files changed, 517 insertions(+), 500 deletions(-) delete mode 100644 include/net/page_pool.h create mode 100644 include/net/page_pool/helpers.h create mode 100644 include/net/page_pool/types.h (limited to 'include') diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst index 53b5448cc0f1..68b82cea13e4 100644 --- a/Documentation/networking/page_pool.rst +++ b/Documentation/networking/page_pool.rst @@ -67,10 +67,10 @@ a page will cause no race conditions is enough. .. kernel-doc:: net/core/page_pool.c :identifiers: page_pool_create -.. kernel-doc:: include/net/page_pool.h +.. kernel-doc:: include/net/page_pool/types.h :identifiers: struct page_pool_params -.. kernel-doc:: include/net/page_pool.h +.. kernel-doc:: include/net/page_pool/helpers.h :identifiers: page_pool_put_page page_pool_put_full_page page_pool_recycle_direct page_pool_dev_alloc_pages page_pool_get_dma_addr page_pool_get_dma_dir @@ -122,7 +122,7 @@ page_pool_stats allocated by the caller. The API will fill in the provided struct page_pool_stats with statistics about the page_pool. -.. kernel-doc:: include/net/page_pool.h +.. kernel-doc:: include/net/page_pool/types.h :identifiers: struct page_pool_recycle_stats struct page_pool_alloc_stats struct page_pool_stats diff --git a/MAINTAINERS b/MAINTAINERS index 5e2bb1059ab6..08bcf3a7c482 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16020,7 +16020,7 @@ M: Ilias Apalodimas L: netdev@vger.kernel.org S: Supported F: Documentation/networking/page_pool.rst -F: include/net/page_pool.h +F: include/net/page_pool/ F: include/trace/events/page_pool.h F: net/core/page_pool.c diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6a643aae7802..eb168ca983b7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -54,7 +54,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 2ce46d7affe4..96f5ca778c67 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include "bnxt_hsi.h" #include "bnxt.h" #include "bnxt_xdp.h" diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 079f9f6ae21a..f61bd89734c5 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #define TSNEP_RX_OFFSET (max(NET_SKB_PAD, XDP_PACKET_HEADROOM) + NET_IP_ALIGN) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 43f14cec91e9..3bd0bf03aedb 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 9f6890059666..e5e37a33fd81 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 88af34bbee34..acd756b0c7c9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -6,7 +6,7 @@ #include #include -#include +#include #include #include "hnae3.h" diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index acf4f6ba73a6..d483b8c00ec0 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -37,7 +37,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 11e603686a27..e809f91c08fb 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 9e1b596c8f08..eb74ccddb440 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 8cdd92dd9762..8336cea16aff 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -7,6 +7,7 @@ #include #include +#include #include #include diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 61f62a6ec662..70b9065f7d10 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "otx2_reg.h" #include "otx2_common.h" diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 1b89f800f6df..fe05c9020269 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "mtk_eth_soc.h" #include "mtk_wed.h" diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 80d17729e557..4a2470fbad2c 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include "mtk_ppe.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 5ce28ff7685f..e097f336e1c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -6,6 +6,7 @@ #include "en/port.h" #include "en_accel/en_accel.h" #include "en_accel/ipsec.h" +#include #include static u8 mlx5e_mpwrq_min_page_shift(struct mlx5_core_dev *mdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index 201ac7dd338f..698647cc8c0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2020 Mellanox Technologies */ -#include #include "en/txrx.h" #include "en/params.h" #include "en/trap.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 40589cebb773..12f56d0db0af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -35,6 +35,7 @@ #include "en/xdp.h" #include "en/params.h" #include +#include int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 1c820119e438..c8ec6467d4d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -38,7 +38,7 @@ #include #include #include -#include +#include #include #include #include "eswitch.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index f7bb5f4aaaca..3fd11b0761e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -36,7 +36,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 4d77055abd4b..07b84d668fcc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -38,7 +38,7 @@ #include "en/port.h" #ifdef CONFIG_PAGE_POOL_STATS -#include +#include #endif static unsigned int stats_grps_num(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c index bd72fbc2220f..3960534ac2ad 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c @@ -2,6 +2,7 @@ #include #include +#include #include "lan966x_main.h" diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index aebc9154693a..caa9e0533c96 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index a08023c57e25..31e2f2c74e15 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -11,6 +11,7 @@ #include #include +#include #include #include diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 0dcd6a568b06..f358ea003193 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -15,7 +15,7 @@ #include #include -#include +#include #include #define NETSEC_REG_SOFT_RST 0x104 diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index a6d034968654..3401e888a9f6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 99aa5360b3ff..fcab363d8dfa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include #include "stmmac_ptp.h" diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index f9cd566d1c9b..ca4d4548f85e 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -31,7 +31,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index c61e4e44a78f..0e4f526b1753 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -30,7 +30,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index ae52cdbcf8cc..0ec85635dfd6 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 2c3f08be8c37..e04d4a5eed7b 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -3,7 +3,7 @@ #include #include -#include +#include #include #include #include diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 614f3e3efab0..953f6d8f8db0 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #define DRV_NAME "veth" #define DRV_VERSION "1.0" diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index c0ff36a98bed..d158320bc15d 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -4,7 +4,6 @@ */ #include #include -#include #include "mt76.h" #define CHAN2G(_idx, _freq) { \ diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 878087257ea7..e8757865a3d0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -15,6 +15,7 @@ #include #include #include +#include #include "util.h" #include "testmode.h" diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 47d54d8ea59d..ad29f370034e 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -45,7 +45,7 @@ #include #include #include -#include +#include #include #include diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 16a49ba534e4..888e3d7e74c1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -32,7 +32,7 @@ #include #include #include -#include +#include #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif diff --git a/include/net/page_pool.h b/include/net/page_pool.h deleted file mode 100644 index 73d4f786418d..000000000000 --- a/include/net/page_pool.h +++ /dev/null @@ -1,470 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 - * - * page_pool.h - * Author: Jesper Dangaard Brouer - * Copyright (C) 2016 Red Hat, Inc. - */ - -/** - * DOC: page_pool allocator - * - * This page_pool allocator is optimized for the XDP mode that - * uses one-frame-per-page, but have fallbacks that act like the - * regular page allocator APIs. - * - * Basic use involve replacing alloc_pages() calls with the - * page_pool_alloc_pages() call. Drivers should likely use - * page_pool_dev_alloc_pages() replacing dev_alloc_pages(). - * - * API keeps track of in-flight pages, in-order to let API user know - * when it is safe to dealloactor page_pool object. Thus, API users - * must call page_pool_put_page() where appropriate and only attach - * the page to a page_pool-aware objects, like skbs marked for recycling. - * - * API user must only call page_pool_put_page() once on a page, as it - * will either recycle the page, or in case of elevated refcnt, it - * will release the DMA mapping and in-flight state accounting. We - * hope to lift this requirement in the future. - */ -#ifndef _NET_PAGE_POOL_H -#define _NET_PAGE_POOL_H - -#include /* Needed by ptr_ring */ -#include -#include - -#define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA - * map/unmap - */ -#define PP_FLAG_DMA_SYNC_DEV BIT(1) /* If set all pages that the driver gets - * from page_pool will be - * DMA-synced-for-device according to - * the length provided by the device - * driver. - * Please note DMA-sync-for-CPU is still - * device driver responsibility - */ -#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 - * - * The cache size and refill watermark is related to the network - * use-case. The NAPI budget is 64 packets. After a NAPI poll the RX - * ring is usually refilled and the max consumed elements will be 64, - * thus a natural max size of objects needed in the cache. - * - * Keeping room for more objects, is due to XDP_DROP use-case. As - * XDP_DROP allows the opportunity to recycle objects directly into - * this array, as it shares the same softirq/NAPI protection. If - * cache is already full (or partly full) then the XDP_DROP recycles - * would have to take a slower code path. - */ -#define PP_ALLOC_CACHE_SIZE 128 -#define PP_ALLOC_CACHE_REFILL 64 -struct pp_alloc_cache { - u32 count; - struct page *cache[PP_ALLOC_CACHE_SIZE]; -}; - -/** - * struct page_pool_params - page pool parameters - * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_PAGE_FRAG - * @order: 2^order pages on allocation - * @pool_size: size of the ptr_ring - * @nid: NUMA node id to allocate from pages from - * @dev: device, for DMA pre-mapping purposes - * @napi: NAPI which is the sole consumer of pages, otherwise NULL - * @dma_dir: DMA mapping direction - * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV - * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV - */ -struct page_pool_params { - unsigned int flags; - unsigned int order; - unsigned int pool_size; - int nid; - struct device *dev; - struct napi_struct *napi; - enum dma_data_direction dma_dir; - unsigned int max_len; - unsigned int offset; -/* private: used by test code only */ - void (*init_callback)(struct page *page, void *arg); - void *init_arg; -}; - -#ifdef CONFIG_PAGE_POOL_STATS -/** - * struct page_pool_alloc_stats - allocation statistics - * @fast: successful fast path allocations - * @slow: slow path order-0 allocations - * @slow_high_order: slow path high order allocations - * @empty: ptr ring is empty, so a slow path allocation was forced - * @refill: an allocation which triggered a refill of the cache - * @waive: pages obtained from the ptr ring that cannot be added to - * the cache due to a NUMA mismatch - */ -struct page_pool_alloc_stats { - u64 fast; - u64 slow; - u64 slow_high_order; - u64 empty; - u64 refill; - u64 waive; -}; - -/** - * struct page_pool_recycle_stats - recycling (freeing) statistics - * @cached: recycling placed page in the page pool cache - * @cache_full: page pool cache was full - * @ring: page placed into the ptr ring - * @ring_full: page released from page pool because the ptr ring was full - * @released_refcnt: page released (and not recycled) because refcnt > 1 - */ -struct page_pool_recycle_stats { - u64 cached; - u64 cache_full; - u64 ring; - u64 ring_full; - u64 released_refcnt; -}; - -/** - * struct page_pool_stats - combined page pool use statistics - * @alloc_stats: see struct page_pool_alloc_stats - * @recycle_stats: see struct page_pool_recycle_stats - * - * Wrapper struct for combining page pool stats with different storage - * requirements. - */ -struct page_pool_stats { - struct page_pool_alloc_stats alloc_stats; - struct page_pool_recycle_stats recycle_stats; -}; - -int page_pool_ethtool_stats_get_count(void); -u8 *page_pool_ethtool_stats_get_strings(u8 *data); -u64 *page_pool_ethtool_stats_get(u64 *data, void *stats); - -/* - * Drivers that wish to harvest page pool stats and report them to users - * (perhaps via ethtool, debugfs, or another mechanism) can allocate a - * struct page_pool_stats call page_pool_get_stats to get stats for the specified pool. - */ -bool page_pool_get_stats(struct page_pool *pool, - struct page_pool_stats *stats); -#else - -static inline int page_pool_ethtool_stats_get_count(void) -{ - return 0; -} - -static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data) -{ - return data; -} - -static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats) -{ - return data; -} - -#endif - -struct page_pool { - struct page_pool_params p; - - struct delayed_work release_dw; - void (*disconnect)(void *); - unsigned long defer_start; - unsigned long defer_warn; - - u32 pages_state_hold_cnt; - unsigned int frag_offset; - struct page *frag_page; - long frag_users; - -#ifdef CONFIG_PAGE_POOL_STATS - /* these stats are incremented while in softirq context */ - struct page_pool_alloc_stats alloc_stats; -#endif - u32 xdp_mem_id; - - /* - * Data structure for allocation side - * - * Drivers allocation side usually already perform some kind - * of resource protection. Piggyback on this protection, and - * require driver to protect allocation side. - * - * For NIC drivers this means, allocate a page_pool per - * RX-queue. As the RX-queue is already protected by - * Softirq/BH scheduling and napi_schedule. NAPI schedule - * guarantee that a single napi_struct will only be scheduled - * on a single CPU (see napi_schedule). - */ - struct pp_alloc_cache alloc ____cacheline_aligned_in_smp; - - /* Data structure for storing recycled pages. - * - * Returning/freeing pages is more complicated synchronization - * wise, because free's can happen on remote CPUs, with no - * association with allocation resource. - * - * Use ptr_ring, as it separates consumer and producer - * effeciently, it a way that doesn't bounce cache-lines. - * - * TODO: Implement bulk return pages into this structure. - */ - struct ptr_ring ring; - -#ifdef CONFIG_PAGE_POOL_STATS - /* recycle stats are per-cpu to avoid locking */ - struct page_pool_recycle_stats __percpu *recycle_stats; -#endif - atomic_t pages_state_release_cnt; - - /* A page_pool is strictly tied to a single RX-queue being - * protected by NAPI, due to above pp_alloc_cache. This - * refcnt serves purpose is to simplify drivers error handling. - */ - refcount_t user_cnt; - - u64 destroy_cnt; -}; - -struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); - -/** - * page_pool_dev_alloc_pages() - allocate a page. - * @pool: pool from which to allocate - * - * Get a page from the page allocator or page_pool caches. - */ -static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) -{ - gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); - - return page_pool_alloc_pages(pool, gfp); -} - -struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset, - unsigned int size, gfp_t gfp); - -static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, - unsigned int *offset, - unsigned int size) -{ - gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); - - return page_pool_alloc_frag(pool, offset, size, gfp); -} - -/** - * page_pool_get_dma_dir() - Retrieve the stored DMA direction. - * @pool: pool from which page was allocated - * - * Get the stored dma direction. A driver might decide to store this locally - * and avoid the extra cache line from page_pool to determine the direction. - */ -static -inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) -{ - return pool->p.dma_dir; -} - -bool page_pool_return_skb_page(struct page *page, bool napi_safe); - -struct page_pool *page_pool_create(const struct page_pool_params *params); - -struct xdp_mem_info; - -#ifdef CONFIG_PAGE_POOL -void page_pool_unlink_napi(struct page_pool *pool); -void page_pool_destroy(struct page_pool *pool); -void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), - struct xdp_mem_info *mem); -void page_pool_put_page_bulk(struct page_pool *pool, void **data, - int count); -#else -static inline void page_pool_unlink_napi(struct page_pool *pool) -{ -} - -static inline void page_pool_destroy(struct page_pool *pool) -{ -} - -static inline void page_pool_use_xdp_mem(struct page_pool *pool, - void (*disconnect)(void *), - struct xdp_mem_info *mem) -{ -} - -static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, - int count) -{ -} -#endif - -void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, - bool allow_direct); - -/* pp_frag_count represents the number of writers who can update the page - * either by updating skb->data or via DMA mappings for the device. - * We can't rely on the page refcnt for that as we don't know who might be - * holding page references and we can't reliably destroy or sync DMA mappings - * of the fragments. - * - * When pp_frag_count reaches 0 we can either recycle the page if the page - * refcnt is 1 or return it back to the memory allocator and destroy any - * mappings we have. - */ -static inline void page_pool_fragment_page(struct page *page, long nr) -{ - atomic_long_set(&page->pp_frag_count, nr); -} - -static inline long page_pool_defrag_page(struct page *page, long nr) -{ - long ret; - - /* If nr == pp_frag_count then we have cleared all remaining - * references to the page. No need to actually overwrite it, instead - * we can leave this to be overwritten by the calling function. - * - * The main advantage to doing this is that an atomic_read is - * generally a much cheaper operation than an atomic update, - * especially when dealing with a page that may be partitioned - * into only 2 or 3 pieces. - */ - if (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 page_pool_is_last_frag(struct page_pool *pool, - struct page *page) -{ - /* If fragments aren't enabled or count is 0 we were the last user */ - return !(pool->p.flags & PP_FLAG_PAGE_FRAG) || - (page_pool_defrag_page(page, 1) == 0); -} - -/** - * page_pool_put_page() - release a reference to a page pool page - * @pool: pool from which page was allocated - * @page: page to release a reference on - * @dma_sync_size: how much of the page may have been touched by the device - * @allow_direct: released by the consumer, allow lockless caching - * - * The outcome of this depends on the page refcnt. If the driver bumps - * the refcnt > 1 this will unmap the page. If the page refcnt is 1 - * the allocator owns the page and will try to recycle it in one of the pool - * caches. If PP_FLAG_DMA_SYNC_DEV is set, the page will be synced for_device - * using dma_sync_single_range_for_device(). - */ -static inline void page_pool_put_page(struct page_pool *pool, - struct page *page, - unsigned int dma_sync_size, - bool allow_direct) -{ - /* When page_pool isn't compiled-in, net/core/xdp.c doesn't - * allow registering MEM_TYPE_PAGE_POOL, but shield linker. - */ -#ifdef CONFIG_PAGE_POOL - if (!page_pool_is_last_frag(pool, page)) - return; - - page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct); -#endif -} - -/** - * page_pool_put_full_page() - release a reference on a page pool page - * @pool: pool from which page was allocated - * @page: page to release a reference on - * @allow_direct: released by the consumer, allow lockless caching - * - * Similar to page_pool_put_page(), but will DMA sync the entire memory area - * as configured in &page_pool_params.max_len. - */ -static inline void page_pool_put_full_page(struct page_pool *pool, - struct page *page, bool allow_direct) -{ - page_pool_put_page(pool, page, -1, allow_direct); -} - -/** - * page_pool_recycle_direct() - release a reference on a page pool page - * @pool: pool from which page was allocated - * @page: page to release a reference on - * - * Similar to page_pool_put_full_page() but caller must guarantee safe context - * (e.g NAPI), since it will recycle the page directly into the pool fast cache. - */ -static inline void page_pool_recycle_direct(struct page_pool *pool, - struct page *page) -{ - page_pool_put_full_page(pool, page, true); -} - -#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ - (sizeof(dma_addr_t) > sizeof(unsigned long)) - -/** - * page_pool_get_dma_addr() - Retrieve the stored DMA address. - * @page: page allocated from a page pool - * - * Fetch the DMA address of the page. The page pool to which the page belongs - * must had been created with PP_FLAG_DMA_MAP. - */ -static inline dma_addr_t page_pool_get_dma_addr(struct page *page) -{ - 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 = addr; - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) - page->dma_addr_upper = upper_32_bits(addr); -} - -static inline bool is_page_pool_compiled_in(void) -{ -#ifdef CONFIG_PAGE_POOL - return true; -#else - return false; -#endif -} - -static inline bool page_pool_put(struct page_pool *pool) -{ - return refcount_dec_and_test(&pool->user_cnt); -} - -/* Caller must provide appropriate safe context, e.g. NAPI. */ -void page_pool_update_nid(struct page_pool *pool, int new_nid); -static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) -{ - if (unlikely(pool->p.nid != new_nid)) - page_pool_update_nid(pool, new_nid); -} - -#endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h new file mode 100644 index 000000000000..78df91804c87 --- /dev/null +++ b/include/net/page_pool/helpers.h @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * page_pool/helpers.h + * Author: Jesper Dangaard Brouer + * Copyright (C) 2016 Red Hat, Inc. + */ + +/** + * DOC: page_pool allocator + * + * This page_pool allocator is optimized for the XDP mode that + * uses one-frame-per-page, but have fallbacks that act like the + * regular page allocator APIs. + * + * Basic use involve replacing alloc_pages() calls with the + * page_pool_alloc_pages() call. Drivers should likely use + * page_pool_dev_alloc_pages() replacing dev_alloc_pages(). + * + * API keeps track of in-flight pages, in-order to let API user know + * when it is safe to dealloactor page_pool object. Thus, API users + * must call page_pool_put_page() where appropriate and only attach + * the page to a page_pool-aware objects, like skbs marked for recycling. + * + * API user must only call page_pool_put_page() once on a page, as it + * will either recycle the page, or in case of elevated refcnt, it + * will release the DMA mapping and in-flight state accounting. We + * hope to lift this requirement in the future. + */ +#ifndef _NET_PAGE_POOL_HELPERS_H +#define _NET_PAGE_POOL_HELPERS_H + +#include + +#ifdef CONFIG_PAGE_POOL_STATS +int page_pool_ethtool_stats_get_count(void); +u8 *page_pool_ethtool_stats_get_strings(u8 *data); +u64 *page_pool_ethtool_stats_get(u64 *data, void *stats); + +/* + * Drivers that wish to harvest page pool stats and report them to users + * (perhaps via ethtool, debugfs, or another mechanism) can allocate a + * struct page_pool_stats call page_pool_get_stats to get stats for the specified pool. + */ +bool page_pool_get_stats(struct page_pool *pool, + struct page_pool_stats *stats); +#else +static inline int page_pool_ethtool_stats_get_count(void) +{ + return 0; +} + +static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data) +{ + return data; +} + +static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats) +{ + return data; +} +#endif + +/** + * page_pool_dev_alloc_pages() - allocate a page. + * @pool: pool from which to allocate + * + * Get a page from the page allocator or page_pool caches. + */ +static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) +{ + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + return page_pool_alloc_pages(pool, gfp); +} + +static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, + unsigned int *offset, + unsigned int size) +{ + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + return page_pool_alloc_frag(pool, offset, size, gfp); +} + +/** + * page_pool_get_dma_dir() - Retrieve the stored DMA direction. + * @pool: pool from which page was allocated + * + * Get the stored dma direction. A driver might decide to store this locally + * and avoid the extra cache line from page_pool to determine the direction. + */ +static +inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) +{ + return pool->p.dma_dir; +} + +/* pp_frag_count represents the number of writers who can update the page + * either by updating skb->data or via DMA mappings for the device. + * We can't rely on the page refcnt for that as we don't know who might be + * holding page references and we can't reliably destroy or sync DMA mappings + * of the fragments. + * + * When pp_frag_count reaches 0 we can either recycle the page if the page + * refcnt is 1 or return it back to the memory allocator and destroy any + * mappings we have. + */ +static inline void page_pool_fragment_page(struct page *page, long nr) +{ + atomic_long_set(&page->pp_frag_count, nr); +} + +static inline long page_pool_defrag_page(struct page *page, long nr) +{ + long ret; + + /* If nr == pp_frag_count then we have cleared all remaining + * references to the page. No need to actually overwrite it, instead + * we can leave this to be overwritten by the calling function. + * + * The main advantage to doing this is that an atomic_read is + * generally a much cheaper operation than an atomic update, + * especially when dealing with a page that may be partitioned + * into only 2 or 3 pieces. + */ + if (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 page_pool_is_last_frag(struct page_pool *pool, + struct page *page) +{ + /* If fragments aren't enabled or count is 0 we were the last user */ + return !(pool->p.flags & PP_FLAG_PAGE_FRAG) || + (page_pool_defrag_page(page, 1) == 0); +} + +/** + * page_pool_put_page() - release a reference to a page pool page + * @pool: pool from which page was allocated + * @page: page to release a reference on + * @dma_sync_size: how much of the page may have been touched by the device + * @allow_direct: released by the consumer, allow lockless caching + * + * The outcome of this depends on the page refcnt. If the driver bumps + * the refcnt > 1 this will unmap the page. If the page refcnt is 1 + * the allocator owns the page and will try to recycle it in one of the pool + * caches. If PP_FLAG_DMA_SYNC_DEV is set, the page will be synced for_device + * using dma_sync_single_range_for_device(). + */ +static inline void page_pool_put_page(struct page_pool *pool, + struct page *page, + unsigned int dma_sync_size, + bool allow_direct) +{ + /* When page_pool isn't compiled-in, net/core/xdp.c doesn't + * allow registering MEM_TYPE_PAGE_POOL, but shield linker. + */ +#ifdef CONFIG_PAGE_POOL + if (!page_pool_is_last_frag(pool, page)) + return; + + page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct); +#endif +} + +/** + * page_pool_put_full_page() - release a reference on a page pool page + * @pool: pool from which page was allocated + * @page: page to release a reference on + * @allow_direct: released by the consumer, allow lockless caching + * + * Similar to page_pool_put_page(), but will DMA sync the entire memory area + * as configured in &page_pool_params.max_len. + */ +static inline void page_pool_put_full_page(struct page_pool *pool, + struct page *page, bool allow_direct) +{ + page_pool_put_page(pool, page, -1, allow_direct); +} + +/** + * page_pool_recycle_direct() - release a reference on a page pool page + * @pool: pool from which page was allocated + * @page: page to release a reference on + * + * Similar to page_pool_put_full_page() but caller must guarantee safe context + * (e.g NAPI), since it will recycle the page directly into the pool fast cache. + */ +static inline void page_pool_recycle_direct(struct page_pool *pool, + struct page *page) +{ + page_pool_put_full_page(pool, page, true); +} + +#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ + (sizeof(dma_addr_t) > sizeof(unsigned long)) + +/** + * page_pool_get_dma_addr() - Retrieve the stored DMA address. + * @page: page allocated from a page pool + * + * Fetch the DMA address of the page. The page pool to which the page belongs + * must had been created with PP_FLAG_DMA_MAP. + */ +static inline dma_addr_t page_pool_get_dma_addr(struct page *page) +{ + 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 = addr; + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + page->dma_addr_upper = upper_32_bits(addr); +} + +static inline bool page_pool_put(struct page_pool *pool) +{ + return refcount_dec_and_test(&pool->user_cnt); +} + +static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) +{ + if (unlikely(pool->p.nid != new_nid)) + page_pool_update_nid(pool, new_nid); +} + +#endif /* _NET_PAGE_POOL_HELPERS_H */ diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h new file mode 100644 index 000000000000..9ac39191bed7 --- /dev/null +++ b/include/net/page_pool/types.h @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _NET_PAGE_POOL_TYPES_H +#define _NET_PAGE_POOL_TYPES_H + +#include +#include + +#define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA + * map/unmap + */ +#define PP_FLAG_DMA_SYNC_DEV BIT(1) /* If set all pages that the driver gets + * from page_pool will be + * DMA-synced-for-device according to + * the length provided by the device + * driver. + * Please note DMA-sync-for-CPU is still + * device driver responsibility + */ +#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 + * + * The cache size and refill watermark is related to the network + * use-case. The NAPI budget is 64 packets. After a NAPI poll the RX + * ring is usually refilled and the max consumed elements will be 64, + * thus a natural max size of objects needed in the cache. + * + * Keeping room for more objects, is due to XDP_DROP use-case. As + * XDP_DROP allows the opportunity to recycle objects directly into + * this array, as it shares the same softirq/NAPI protection. If + * cache is already full (or partly full) then the XDP_DROP recycles + * would have to take a slower code path. + */ +#define PP_ALLOC_CACHE_SIZE 128 +#define PP_ALLOC_CACHE_REFILL 64 +struct pp_alloc_cache { + u32 count; + struct page *cache[PP_ALLOC_CACHE_SIZE]; +}; + +/** + * struct page_pool_params - page pool parameters + * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_PAGE_FRAG + * @order: 2^order pages on allocation + * @pool_size: size of the ptr_ring + * @nid: NUMA node id to allocate from pages from + * @dev: device, for DMA pre-mapping purposes + * @napi: NAPI which is the sole consumer of pages, otherwise NULL + * @dma_dir: DMA mapping direction + * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV + * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV + */ +struct page_pool_params { + unsigned int flags; + unsigned int order; + unsigned int pool_size; + int nid; + struct device *dev; + struct napi_struct *napi; + enum dma_data_direction dma_dir; + unsigned int max_len; + unsigned int offset; +/* private: used by test code only */ + void (*init_callback)(struct page *page, void *arg); + void *init_arg; +}; + +#ifdef CONFIG_PAGE_POOL_STATS +/** + * struct page_pool_alloc_stats - allocation statistics + * @fast: successful fast path allocations + * @slow: slow path order-0 allocations + * @slow_high_order: slow path high order allocations + * @empty: ptr ring is empty, so a slow path allocation was forced + * @refill: an allocation which triggered a refill of the cache + * @waive: pages obtained from the ptr ring that cannot be added to + * the cache due to a NUMA mismatch + */ +struct page_pool_alloc_stats { + u64 fast; + u64 slow; + u64 slow_high_order; + u64 empty; + u64 refill; + u64 waive; +}; + +/** + * struct page_pool_recycle_stats - recycling (freeing) statistics + * @cached: recycling placed page in the page pool cache + * @cache_full: page pool cache was full + * @ring: page placed into the ptr ring + * @ring_full: page released from page pool because the ptr ring was full + * @released_refcnt: page released (and not recycled) because refcnt > 1 + */ +struct page_pool_recycle_stats { + u64 cached; + u64 cache_full; + u64 ring; + u64 ring_full; + u64 released_refcnt; +}; + +/** + * struct page_pool_stats - combined page pool use statistics + * @alloc_stats: see struct page_pool_alloc_stats + * @recycle_stats: see struct page_pool_recycle_stats + * + * Wrapper struct for combining page pool stats with different storage + * requirements. + */ +struct page_pool_stats { + struct page_pool_alloc_stats alloc_stats; + struct page_pool_recycle_stats recycle_stats; +}; +#endif + +struct page_pool { + struct page_pool_params p; + + struct delayed_work release_dw; + void (*disconnect)(void *pool); + unsigned long defer_start; + unsigned long defer_warn; + + u32 pages_state_hold_cnt; + unsigned int frag_offset; + struct page *frag_page; + long frag_users; + +#ifdef CONFIG_PAGE_POOL_STATS + /* these stats are incremented while in softirq context */ + struct page_pool_alloc_stats alloc_stats; +#endif + u32 xdp_mem_id; + + /* + * Data structure for allocation side + * + * Drivers allocation side usually already perform some kind + * of resource protection. Piggyback on this protection, and + * require driver to protect allocation side. + * + * For NIC drivers this means, allocate a page_pool per + * RX-queue. As the RX-queue is already protected by + * Softirq/BH scheduling and napi_schedule. NAPI schedule + * guarantee that a single napi_struct will only be scheduled + * on a single CPU (see napi_schedule). + */ + struct pp_alloc_cache alloc ____cacheline_aligned_in_smp; + + /* Data structure for storing recycled pages. + * + * Returning/freeing pages is more complicated synchronization + * wise, because free's can happen on remote CPUs, with no + * association with allocation resource. + * + * Use ptr_ring, as it separates consumer and producer + * efficiently, it a way that doesn't bounce cache-lines. + * + * TODO: Implement bulk return pages into this structure. + */ + struct ptr_ring ring; + +#ifdef CONFIG_PAGE_POOL_STATS + /* recycle stats are per-cpu to avoid locking */ + struct page_pool_recycle_stats __percpu *recycle_stats; +#endif + atomic_t pages_state_release_cnt; + + /* A page_pool is strictly tied to a single RX-queue being + * protected by NAPI, due to above pp_alloc_cache. This + * refcnt serves purpose is to simplify drivers error handling. + */ + refcount_t user_cnt; + + u64 destroy_cnt; +}; + +struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); +struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset, + unsigned int size, gfp_t gfp); +bool page_pool_return_skb_page(struct page *page, bool napi_safe); + +struct page_pool *page_pool_create(const struct page_pool_params *params); + +struct xdp_mem_info; + +#ifdef CONFIG_PAGE_POOL +void page_pool_unlink_napi(struct page_pool *pool); +void page_pool_destroy(struct page_pool *pool); +void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), + struct xdp_mem_info *mem); +void page_pool_put_page_bulk(struct page_pool *pool, void **data, + int count); +#else +static inline void page_pool_unlink_napi(struct page_pool *pool) +{ +} + +static inline void page_pool_destroy(struct page_pool *pool) +{ +} + +static inline void page_pool_use_xdp_mem(struct page_pool *pool, + void (*disconnect)(void *), + struct xdp_mem_info *mem) +{ +} + +static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, + int count) +{ +} +#endif + +void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, + bool allow_direct); + +static inline bool is_page_pool_compiled_in(void) +{ +#ifdef CONFIG_PAGE_POOL + return true; +#else + return false; +#endif +} + +/* Caller must provide appropriate safe context, e.g. NAPI. */ +void page_pool_update_nid(struct page_pool *pool, int new_nid); + +#endif /* _NET_PAGE_POOL_H */ diff --git a/include/trace/events/page_pool.h b/include/trace/events/page_pool.h index ca534501158b..6834356b2d2a 100644 --- a/include/trace/events/page_pool.h +++ b/include/trace/events/page_pool.h @@ -9,7 +9,7 @@ #include #include -#include +#include TRACE_EVENT(page_pool_release, diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 0aac76c13fd4..57a7a64b84ed 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 5d615a169718..cd28c1f14002 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -10,7 +10,7 @@ #include #include -#include +#include #include #include diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c6f98245582c..d3bed964123c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -73,7 +73,7 @@ #include #include #include -#include +#include #include #include diff --git a/net/core/xdp.c b/net/core/xdp.c index 8362130bf085..a70670fe9a2d 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include /* struct xdp_mem_allocator */ -- cgit v1.2.3 From 75eaf63ea7afeafd026ffef03bdc69e31f10829b Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 4 Aug 2023 20:05:25 +0200 Subject: net: skbuff: don't include to Currently, touching triggers a rebuild of more than half of the kernel. That's because it's included in . And each new include to page_pool/types.h adds more [useless] data for the toolchain to process per each source file from that pile. In commit 6a5bcd84e886 ("page_pool: Allow drivers to hint on SKB recycling"), Matteo included it to be able to call a couple of functions defined there. Then, in commit 57f05bc2ab24 ("page_pool: keep pp info as long as page pool owns the page") one of the calls was removed, so only one was left. It's the call to page_pool_return_skb_page() in napi_frag_unref(). The function is external and doesn't have any dependencies. Having very niche page_pool_types.h included only for that looks like an overkill. As %PP_SIGNATURE is not local to page_pool.c (was only in the early submissions), nothing holds this function there. Teleport page_pool_return_skb_page() to skbuff.c, just next to the main consumer, skb_pp_recycle(), and rename it to napi_pp_put_page(), as it doesn't work with skbs at all and the former name tells nothing. The #if guards here are only to not compile and have it in the vmlinux when not needed -- both call sites are already guarded. Now, touching page_pool_types.h only triggers rebuilding of the drivers using it and a couple of core networking files. Suggested-by: Jakub Kicinski # make skbuff.h less heavy Suggested-by: Alexander Duyck # move to skbuff.c Signed-off-by: Alexander Lobakin Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/20230804180529.2483231-3-aleksander.lobakin@intel.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 5 +++-- include/net/page_pool/types.h | 2 -- net/core/page_pool.c | 39 ------------------------------------- net/core/skbuff.c | 45 +++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 46 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 888e3d7e74c1..aa57e2eca33b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -32,7 +32,6 @@ #include #include #include -#include #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif @@ -3421,13 +3420,15 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } +bool napi_pp_put_page(struct page *page, bool napi_safe); + static inline void napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) { struct page *page = skb_frag_page(frag); #ifdef CONFIG_PAGE_POOL - if (recycle && page_pool_return_skb_page(page, napi_safe)) + if (recycle && napi_pp_put_page(page, napi_safe)) return; #endif put_page(page); diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 9ac39191bed7..fcb846523398 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -185,8 +185,6 @@ struct page_pool { struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset, unsigned int size, gfp_t gfp); -bool page_pool_return_skb_page(struct page *page, bool napi_safe); - struct page_pool *page_pool_create(const struct page_pool_params *params); struct xdp_mem_info; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index cd28c1f14002..03ad74d25959 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -935,42 +935,3 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) } } EXPORT_SYMBOL(page_pool_update_nid); - -bool page_pool_return_skb_page(struct page *page, bool napi_safe) -{ - struct napi_struct *napi; - struct page_pool *pp; - bool allow_direct; - - page = compound_head(page); - - /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation - * in order to preserve any existing bits, such as bit 0 for the - * head page of compound page and bit 1 for pfmemalloc page, so - * mask those bits for freeing side when doing below checking, - * and page_is_pfmemalloc() is checked in __page_pool_put_page() - * to avoid recycling the pfmemalloc page. - */ - if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE)) - return false; - - pp = page->pp; - - /* Allow direct recycle if we have reasons to believe that we are - * in the same context as the consumer would run, so there's - * no possible race. - */ - napi = READ_ONCE(pp->p.napi); - allow_direct = napi_safe && napi && - READ_ONCE(napi->list_owner) == smp_processor_id(); - - /* Driver set this to memory recycling info. Reset it on recycle. - * This will *not* work for NIC using a split-page memory model. - * The page will be returned to the pool here regardless of the - * 'flipped' fragment being in use or not. - */ - page_pool_put_full_page(pp, page, allow_direct); - - return true; -} -EXPORT_SYMBOL(page_pool_return_skb_page); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d3bed964123c..acc5844a0de1 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -73,7 +73,7 @@ #include #include #include -#include +#include #include #include @@ -879,11 +879,52 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } +#if IS_ENABLED(CONFIG_PAGE_POOL) +bool napi_pp_put_page(struct page *page, bool napi_safe) +{ + struct napi_struct *napi; + struct page_pool *pp; + bool allow_direct; + + page = compound_head(page); + + /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation + * in order to preserve any existing bits, such as bit 0 for the + * head page of compound page and bit 1 for pfmemalloc page, so + * mask those bits for freeing side when doing below checking, + * and page_is_pfmemalloc() is checked in __page_pool_put_page() + * to avoid recycling the pfmemalloc page. + */ + if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE)) + return false; + + pp = page->pp; + + /* Allow direct recycle if we have reasons to believe that we are + * in the same context as the consumer would run, so there's + * no possible race. + */ + napi = READ_ONCE(pp->p.napi); + allow_direct = napi_safe && napi && + READ_ONCE(napi->list_owner) == smp_processor_id(); + + /* Driver set this to memory recycling info. Reset it on recycle. + * This will *not* work for NIC using a split-page memory model. + * The page will be returned to the pool here regardless of the + * 'flipped' fragment being in use or not. + */ + page_pool_put_full_page(pp, page, allow_direct); + + return true; +} +EXPORT_SYMBOL(napi_pp_put_page); +#endif + static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe) { if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) return false; - return page_pool_return_skb_page(virt_to_page(data), napi_safe); + return napi_pp_put_page(virt_to_page(data), napi_safe); } static void skb_kfree_head(void *head, unsigned int end_offset) -- cgit v1.2.3 From 06d0fbdad612cb8def19065cf1fa14fc34dba9f8 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 4 Aug 2023 20:05:26 +0200 Subject: page_pool: place frag_* fields in one cacheline On x86_64, frag_* fields of struct page_pool are scattered across two cachelines despite the summary size of 24 bytes. All three fields are used in pretty much the same places, but the last field, ::frag_users, is pushed out to the next CL, provoking unwanted false-sharing on hotpath (frags allocation code). There are some holes and cold members to move around. Move frag_* one block up, placing them right after &page_pool_params perfectly at the beginning of CL2. This doesn't do any meaningful to the second block, as those are some destroy-path cold structures, and doesn't do anything to ::alloc_stats, which still starts at 200-byte offset, 8 bytes after CL3 (still fitting into 1 cacheline). On my setup, this yields 1-2% of Mpps when using PP frags actively. When it comes to 32-bit architectures with 32-byte CL: &page_pool_params plus ::pad is 44 bytes, the block taken care of is 16 bytes within one CL, so there should be at least no regressions from the actual change. ::pages_state_hold_cnt is not related directly to that triple, but is paired currently with ::frags_offset and decoupling them would mean either two 4-byte holes or more invasive layout changes. Signed-off-by: Alexander Lobakin Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/20230804180529.2483231-4-aleksander.lobakin@intel.com Signed-off-by: Jakub Kicinski --- include/net/page_pool/types.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index fcb846523398..887e7946a597 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -123,16 +123,16 @@ struct page_pool_stats { struct page_pool { struct page_pool_params p; + long frag_users; + struct page *frag_page; + unsigned int frag_offset; + u32 pages_state_hold_cnt; + struct delayed_work release_dw; void (*disconnect)(void *pool); unsigned long defer_start; unsigned long defer_warn; - u32 pages_state_hold_cnt; - unsigned int frag_offset; - struct page *frag_page; - long frag_users; - #ifdef CONFIG_PAGE_POOL_STATS /* these stats are incremented while in softirq context */ struct page_pool_alloc_stats alloc_stats; -- cgit v1.2.3 From ff4e538c8c3e675a15e1e49509c55951832e0451 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 4 Aug 2023 20:05:28 +0200 Subject: page_pool: add a lockdep check for recycling in hardirq Page pool use in hardirq is prohibited, add debug checks to catch misuses. IIRC we previously discussed using DEBUG_NET_WARN_ON_ONCE() for this, but there were concerns that people will have DEBUG_NET enabled in perf testing. I don't think anyone enables lockdep in perf testing, so use lockdep to avoid pushback and arguing :) Acked-by: Jesper Dangaard Brouer Signed-off-by: Alexander Lobakin Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/20230804180529.2483231-6-aleksander.lobakin@intel.com Signed-off-by: Jakub Kicinski --- include/linux/lockdep.h | 7 +++++++ net/core/page_pool.c | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 310f85903c91..dc2844b071c2 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -625,6 +625,12 @@ do { \ WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirq_context)); \ } while (0) +#define lockdep_assert_no_hardirq() \ +do { \ + WARN_ON_ONCE(__lockdep_enabled && (this_cpu_read(hardirq_context) || \ + !this_cpu_read(hardirqs_enabled))); \ +} while (0) + #define lockdep_assert_preemption_enabled() \ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ @@ -659,6 +665,7 @@ do { \ # define lockdep_assert_irqs_enabled() do { } while (0) # define lockdep_assert_irqs_disabled() do { } while (0) # define lockdep_assert_in_irq() do { } while (0) +# define lockdep_assert_no_hardirq() do { } while (0) # define lockdep_assert_preemption_enabled() do { } while (0) # define lockdep_assert_preemption_disabled() do { } while (0) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 03ad74d25959..77cb75e63aca 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -587,6 +587,8 @@ static __always_inline struct page * __page_pool_put_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, bool allow_direct) { + lockdep_assert_no_hardirq(); + /* This allocator is optimized for the XDP mode that uses * one-frame-per-page, but have fallbacks that act like the * regular page allocator APIs. -- cgit v1.2.3 From a3c485a5d8d47af5d2d1a0e5c3b7a1ed223669f9 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 7 Aug 2023 10:59:54 +0200 Subject: bpf: Add support for bpf_get_func_ip helper for uprobe program Adding support for bpf_get_func_ip helper for uprobe program to return probed address for both uprobe and return uprobe. We discussed this in [1] and agreed that uprobe can have special use of bpf_get_func_ip helper that differs from kprobe. The kprobe bpf_get_func_ip returns: - address of the function if probe is attach on function entry for both kprobe and return kprobe - 0 if the probe is not attach on function entry The uprobe bpf_get_func_ip returns: - address of the probe for both uprobe and return uprobe The reason for this semantic change is that kernel can't really tell if the probe user space address is function entry. The uprobe program is actually kprobe type program attached as uprobe. One of the consequences of this design is that uprobes do not have its own set of helpers, but share them with kprobes. As we need different functionality for bpf_get_func_ip helper for uprobe, I'm adding the bool value to the bpf_trace_run_ctx, so the helper can detect that it's executed in uprobe context and call specific code. The is_uprobe bool is set as true in bpf_prog_run_array_sleepable, which is currently used only for executing bpf programs in uprobe. Renaming bpf_prog_run_array_sleepable to bpf_prog_run_array_uprobe to address that it's only used for uprobes and that it sets the run_ctx.is_uprobe as suggested by Yafang Shao. Suggested-by: Andrii Nakryiko Tested-by: Alan Maguire [1] https://lore.kernel.org/bpf/CAEf4BzZ=xLVkG5eurEuvLU79wAMtwho7ReR+XJAgwhFF4M-7Cg@mail.gmail.com/ Signed-off-by: Jiri Olsa Tested-by: Viktor Malik Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230807085956.2344866-2-jolsa@kernel.org Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 9 +++++++-- include/uapi/linux/bpf.h | 7 ++++++- kernel/trace/bpf_trace.c | 11 ++++++++++- kernel/trace/trace_probe.h | 5 +++++ kernel/trace/trace_uprobe.c | 7 +------ tools/include/uapi/linux/bpf.h | 7 ++++++- 6 files changed, 35 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index abe75063630b..db3fe5a61b05 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1819,6 +1819,7 @@ struct bpf_cg_run_ctx { struct bpf_trace_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; + bool is_uprobe; }; struct bpf_tramp_run_ctx { @@ -1867,6 +1868,8 @@ bpf_prog_run_array(const struct bpf_prog_array *array, if (unlikely(!array)) return ret; + run_ctx.is_uprobe = false; + migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; @@ -1891,8 +1894,8 @@ bpf_prog_run_array(const struct bpf_prog_array *array, * rcu-protected dynamically sized maps. */ static __always_inline u32 -bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog) +bpf_prog_run_array_uprobe(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; @@ -1906,6 +1909,8 @@ bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu, rcu_read_lock_trace(); migrate_disable(); + run_ctx.is_uprobe = true; + array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); if (unlikely(!array)) goto out; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 70da85200695..d21deb46f49f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5086,9 +5086,14 @@ union bpf_attr { * u64 bpf_get_func_ip(void *ctx) * Description * Get address of the traced function (for tracing and kprobe programs). + * + * When called for kprobe program attached as uprobe it returns + * probe address for both entry and return uprobe. + * * Return - * Address of the traced function. + * Address of the traced function for kprobe. * 0 for kprobes placed within the function (not at the entry). + * Address of the probe for uprobe and return uprobe. * * u64 bpf_get_attach_cookie(void *ctx) * Description diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d6296d51a826..792445e1f3f0 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1055,7 +1055,16 @@ static unsigned long get_entry_ip(unsigned long fentry_ip) BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs) { - struct kprobe *kp = kprobe_running(); + struct bpf_trace_run_ctx *run_ctx __maybe_unused; + struct kprobe *kp; + +#ifdef CONFIG_UPROBES + run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); + if (run_ctx->is_uprobe) + return ((struct uprobe_dispatch_data *)current->utask->vaddr)->bp_addr; +#endif + + kp = kprobe_running(); if (!kp || !(kp->flags & KPROBE_FLAG_ON_FUNC_ENTRY)) return 0; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 01ea148723de..7dde806be91e 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -519,3 +519,8 @@ void __trace_probe_log_err(int offset, int err); #define trace_probe_log_err(offs, err) \ __trace_probe_log_err(offs, TP_ERR_##err) + +struct uprobe_dispatch_data { + struct trace_uprobe *tu; + unsigned long bp_addr; +}; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 555c223c3232..576b3bcb8ebd 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -88,11 +88,6 @@ static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev) static int register_uprobe_event(struct trace_uprobe *tu); static int unregister_uprobe_event(struct trace_uprobe *tu); -struct uprobe_dispatch_data { - struct trace_uprobe *tu; - unsigned long bp_addr; -}; - static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); static int uretprobe_dispatcher(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs); @@ -1352,7 +1347,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, if (bpf_prog_array_valid(call)) { u32 ret; - ret = bpf_prog_run_array_sleepable(call->prog_array, regs, bpf_prog_run); + ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run); if (!ret) return; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 70da85200695..d21deb46f49f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5086,9 +5086,14 @@ union bpf_attr { * u64 bpf_get_func_ip(void *ctx) * Description * Get address of the traced function (for tracing and kprobe programs). + * + * When called for kprobe program attached as uprobe it returns + * probe address for both entry and return uprobe. + * * Return - * Address of the traced function. + * Address of the traced function for kprobe. * 0 for kprobes placed within the function (not at the entry). + * Address of the probe for uprobe and return uprobe. * * u64 bpf_get_attach_cookie(void *ctx) * Description -- cgit v1.2.3 From 29cfda963f899da403d6bc5a3abe19d2e0be0cf4 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Wed, 2 Aug 2023 21:09:57 +0800 Subject: netfilter: gre: Remove unused function declaration nf_ct_gre_keymap_flush() Commit a23f89a99906 ("netfilter: conntrack: nf_ct_gre_keymap_flush() removal") leave this unused, remove it. Signed-off-by: Yue Haibing Signed-off-by: Florian Westphal --- include/linux/netfilter/nf_conntrack_proto_gre.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index f33aa6021364..34ce5d2f37a2 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -25,7 +25,6 @@ struct nf_ct_gre_keymap { int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t); -void nf_ct_gre_keymap_flush(struct net *net); /* delete keymap entries */ void nf_ct_gre_keymap_destroy(struct nf_conn *ct); -- cgit v1.2.3 From 529f63fa11eba5fbe448fbe537b3576edd9fd277 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Wed, 2 Aug 2023 21:15:49 +0800 Subject: netfilter: helper: Remove unused function declarations Commit b118509076b3 ("netfilter: remove nf_conntrack_helper sysctl and modparam toggles") leave these unused declarations. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Signed-off-by: Florian Westphal --- include/net/netfilter/nf_conntrack_helper.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index f30b1694b690..de2f956abf34 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -136,8 +136,6 @@ static inline void *nfct_help_data(const struct nf_conn *ct) return (void *)help->data; } -void nf_conntrack_helper_pernet_init(struct net *net); - int nf_conntrack_helper_init(void); void nf_conntrack_helper_fini(void); @@ -182,5 +180,4 @@ void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat); int nf_nat_helper_try_module_get(const char *name, u16 l3num, u8 protonum); void nf_nat_helper_put(struct nf_conntrack_helper *helper); -void nf_ct_set_auto_assign_helper_warned(struct net *net); #endif /*_NF_CONNTRACK_HELPER_H*/ -- cgit v1.2.3 From 172af3eab05f096122d7c239ab9a11b38b5e5c90 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Fri, 4 Aug 2023 21:41:49 +0800 Subject: netfilter: conntrack: Remove unused function declarations Commit 1015c3de23ee ("netfilter: conntrack: remove extension register api") leave nf_conntrack_acct_fini() and nf_conntrack_labels_init() unused, remove it. And commit a0ae2562c6c4 ("netfilter: conntrack: remove l3proto abstraction") leave behind nf_ct_l3proto_try_module_get() and nf_ct_l3proto_module_put(). Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Signed-off-by: Florian Westphal --- include/net/netfilter/nf_conntrack.h | 4 ---- include/net/netfilter/nf_conntrack_acct.h | 2 -- include/net/netfilter/nf_conntrack_labels.h | 1 - 3 files changed, 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index a72028dbef0c..4085765c3370 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -190,10 +190,6 @@ static inline void nf_ct_put(struct nf_conn *ct) nf_ct_destroy(&ct->ct_general); } -/* Protocol module loading */ -int nf_ct_l3proto_try_module_get(unsigned short l3proto); -void nf_ct_l3proto_module_put(unsigned short l3proto); - /* load module; enable/disable conntrack in this namespace */ int nf_ct_netns_get(struct net *net, u8 nfproto); void nf_ct_netns_put(struct net *net, u8 nfproto); diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h index 4b2b7f8914ea..a120685cac93 100644 --- a/include/net/netfilter/nf_conntrack_acct.h +++ b/include/net/netfilter/nf_conntrack_acct.h @@ -78,6 +78,4 @@ static inline void nf_ct_acct_update(struct nf_conn *ct, u32 dir, void nf_conntrack_acct_pernet_init(struct net *net); -void nf_conntrack_acct_fini(void); - #endif /* _NF_CONNTRACK_ACCT_H */ diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index 66bab6c60d12..fcb19a4e8f2b 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -52,7 +52,6 @@ int nf_connlabels_replace(struct nf_conn *ct, const u32 *data, const u32 *mask, unsigned int words); #ifdef CONFIG_NF_CONNTRACK_LABELS -int nf_conntrack_labels_init(void); int nf_connlabels_get(struct net *net, unsigned int bit); void nf_connlabels_put(struct net *net); #else -- cgit v1.2.3 From 61e9ab294b39e5e7c040884b65d06f52e06ac40f Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 7 Aug 2023 22:25:26 +0800 Subject: netfilter: h323: Remove unused function declarations Commit f587de0e2feb ("[NETFILTER]: nf_conntrack/nf_nat: add H.323 helper port") declared but never implemented these. Signed-off-by: Yue Haibing Signed-off-by: Florian Westphal --- include/linux/netfilter/nf_conntrack_h323.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h index 9e937f64a1ad..81286c499325 100644 --- a/include/linux/netfilter/nf_conntrack_h323.h +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -34,10 +34,6 @@ struct nf_ct_h323_master { int get_h225_addr(struct nf_conn *ct, unsigned char *data, TransportAddress *taddr, union nf_inet_addr *addr, __be16 *port); -void nf_conntrack_h245_expect(struct nf_conn *new, - struct nf_conntrack_expect *this); -void nf_conntrack_q931_expect(struct nf_conn *new, - struct nf_conntrack_expect *this); struct nfct_h323_nat_hooks { int (*set_h245_addr)(struct sk_buff *skb, unsigned int protoff, -- cgit v1.2.3 From 26bbbef8ff4047f857ac2d7353eb19e46100ce18 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 4 Aug 2023 15:30:13 +0200 Subject: net: fs_enet: Remove fs_get_id() fs_get_id() hasn't been used since commit b219108cbace ("fs_enet: Remove !CONFIG_PPC_CPM_NEW_BINDING code") Remove it. Signed-off-by: Christophe Leroy Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/7a53b88cc40302fcbea59554f5e7067e3594ad53.1691155346.git.christophe.leroy@csgroup.eu Signed-off-by: Jakub Kicinski --- include/linux/fs_enet_pd.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h index 77d783f71527..2351c3d9404d 100644 --- a/include/linux/fs_enet_pd.h +++ b/include/linux/fs_enet_pd.h @@ -151,15 +151,4 @@ struct fs_mii_fec_platform_info { u32 mii_speed; }; -static inline int fs_get_id(struct fs_platform_info *fpi) -{ - if(strstr(fpi->fs_type, "SCC")) - return fs_scc_index2id(fpi->fs_no); - if(strstr(fpi->fs_type, "FCC")) - return fs_fcc_index2id(fpi->fs_no); - if(strstr(fpi->fs_type, "FEC")) - return fs_fec_index2id(fpi->fs_no); - return fpi->fs_no; -} - #endif -- cgit v1.2.3 From caaf482e265415778de74e262a6f153dd2f18fa4 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 4 Aug 2023 15:30:14 +0200 Subject: net: fs_enet: Remove unused fields in fs_platform_info struct Since commit 3dd82a1ea724 ("[POWERPC] CPM: Always use new binding.") many fields of fs_platform_info structure are not used anymore. Remove them. Signed-off-by: Christophe Leroy Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/2e584fcd75e21a0f7e7d5f942eebdc067b2f82f9.1691155346.git.christophe.leroy@csgroup.eu Signed-off-by: Jakub Kicinski --- include/linux/fs_enet_pd.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include') diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h index 2351c3d9404d..a1905e41c167 100644 --- a/include/linux/fs_enet_pd.h +++ b/include/linux/fs_enet_pd.h @@ -111,33 +111,14 @@ struct fs_mii_bb_platform_info { }; struct fs_platform_info { - - void(*init_ioports)(struct fs_platform_info *); /* device specific information */ - int fs_no; /* controller index */ - char fs_type[4]; /* controller type */ - - u32 cp_page; /* CPM page */ - u32 cp_block; /* CPM sblock */ u32 cp_command; /* CPM page/sblock/mcn */ - u32 clk_trx; /* some stuff for pins & mux configuration*/ - u32 clk_rx; - u32 clk_tx; - u32 clk_route; - u32 clk_mask; - - u32 mem_offset; u32 dpram_offset; - u32 fcc_regs_c; - u32 device_flags; - struct device_node *phy_node; - const struct fs_mii_bus_info *bus_info; int rx_ring, tx_ring; /* number of buffers on rx */ - __u8 macaddr[ETH_ALEN]; /* mac address */ int rx_copybreak; /* limit we copy small frames */ int napi_weight; /* NAPI weight */ -- cgit v1.2.3 From 9359a48c65a3c2723d469ba11889c56387e4395a Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 4 Aug 2023 15:30:15 +0200 Subject: net: fs_enet: Remove has_phy field in fs_platform_info struct Since commit 3dd82a1ea724 ("[POWERPC] CPM: Always use new binding.") has_phy field is never set. Remove dead code and remove the field. Signed-off-by: Christophe Leroy Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/bb5264e09e18f0ce8a0dbee399926a59f33cb248.1691155346.git.christophe.leroy@csgroup.eu Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fs_enet/mac-fec.c | 14 -------------- include/linux/fs_enet_pd.h | 1 - 2 files changed, 15 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c index f609dc112458..cdc89d83cf07 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c @@ -339,11 +339,7 @@ static void restart(struct net_device *dev) static void stop(struct net_device *dev) { struct fs_enet_private *fep = netdev_priv(dev); - const struct fs_platform_info *fpi = fep->fpi; struct fec __iomem *fecp = fep->fec.fecp; - - struct fec_info *feci = dev->phydev->mdio.bus->priv; - int i; if ((FR(fecp, ecntrl) & FEC_ECNTRL_ETHER_EN) == 0) @@ -363,16 +359,6 @@ static void stop(struct net_device *dev) FC(fecp, ecntrl, FEC_ECNTRL_ETHER_EN); fs_cleanup_bds(dev); - - /* shut down FEC1? that's where the mii bus is */ - if (fpi->has_phy) { - FS(fecp, r_cntrl, fpi->use_rmii ? - FEC_RCNTRL_RMII_MODE : - FEC_RCNTRL_MII_MODE); /* MII/RMII enable */ - FS(fecp, ecntrl, FEC_ECNTRL_PINMUX | FEC_ECNTRL_ETHER_EN); - FW(fecp, ievent, FEC_ENET_MII); - FW(fecp, mii_speed, feci->mii_speed); - } } static void napi_clear_event_fs(struct net_device *dev) diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h index a1905e41c167..2b351b676467 100644 --- a/include/linux/fs_enet_pd.h +++ b/include/linux/fs_enet_pd.h @@ -123,7 +123,6 @@ struct fs_platform_info { int napi_weight; /* NAPI weight */ int use_rmii; /* use RMII mode */ - int has_phy; /* if the network is phy container as well...*/ struct clk *clk_per; /* 'per' clock for register access */ }; -- cgit v1.2.3 From 7a76918371fe04667528142554a3f26a8879e8ab Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 4 Aug 2023 15:30:17 +0200 Subject: net: fs_enet: Move struct fs_platform_info into fs_enet.h struct fs_platform_info is only used in fs_enet ethernet driver since commit 3dd82a1ea724 ("[POWERPC] CPM: Always use new binding."). Stale prototypes using fs_platform_info were left over in arch/powerpc/sysdev/fsl_soc.c but they are now removed by previous patch. Move struct fs_platform_info into fs_enet.h Signed-off-by: Christophe Leroy Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/f882d6b0b7075d0d8435310634ceaa2cc8e9938f.1691155347.git.christophe.leroy@csgroup.eu Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fs_enet/fs_enet.h | 19 ++++++++++++++++++- drivers/net/ethernet/freescale/fs_enet/mii-fec.c | 1 + include/linux/fs_enet_pd.h | 16 ---------------- 3 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h index cb419aef8d1b..d371072fff60 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h @@ -2,6 +2,7 @@ #ifndef FS_ENET_H #define FS_ENET_H +#include #include #include #include @@ -9,7 +10,6 @@ #include #include -#include #include #ifdef CONFIG_CPM1 @@ -118,6 +118,23 @@ struct phy_info { #define ENET_RX_ALIGN 16 #define ENET_RX_FRSIZE L1_CACHE_ALIGN(PKT_MAXBUF_SIZE + ENET_RX_ALIGN - 1) +struct fs_platform_info { + /* device specific information */ + u32 cp_command; /* CPM page/sblock/mcn */ + + u32 dpram_offset; + + struct device_node *phy_node; + + int rx_ring, tx_ring; /* number of buffers on rx */ + int rx_copybreak; /* limit we copy small frames */ + int napi_weight; /* NAPI weight */ + + int use_rmii; /* use RMII mode */ + + struct clk *clk_per; /* 'per' clock for register access */ +}; + struct fs_enet_private { struct napi_struct napi; struct device *dev; /* pointer back to the device (must be initialized first) */ diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c index 1910df250c33..a1e777a4b75f 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c +++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h index 2b351b676467..7c9897dab558 100644 --- a/include/linux/fs_enet_pd.h +++ b/include/linux/fs_enet_pd.h @@ -110,22 +110,6 @@ struct fs_mii_bb_platform_info { int irq[32]; /* irqs per phy's */ }; -struct fs_platform_info { - /* device specific information */ - u32 cp_command; /* CPM page/sblock/mcn */ - - u32 dpram_offset; - - struct device_node *phy_node; - - int rx_ring, tx_ring; /* number of buffers on rx */ - int rx_copybreak; /* limit we copy small frames */ - int napi_weight; /* NAPI weight */ - - int use_rmii; /* use RMII mode */ - - struct clk *clk_per; /* 'per' clock for register access */ -}; struct fs_mii_fec_platform_info { u32 irq[32]; u32 mii_speed; -- cgit v1.2.3 From 7149b38dc7cbc77548afd65e4bb4d4b11dca8670 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 4 Aug 2023 15:30:19 +0200 Subject: net: fs_enet: Remove linux/fs_enet_pd.h linux/fs_enet_pd.h is not used anymore. Remove it. Signed-off-by: Christophe Leroy Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/5be102791c987792ad127b15543ee6715394cf67.1691155347.git.christophe.leroy@csgroup.eu Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 - include/linux/fs_enet_pd.h | 118 --------------------------------------------- 2 files changed, 119 deletions(-) delete mode 100644 include/linux/fs_enet_pd.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 08bcf3a7c482..6efcd8713682 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8371,7 +8371,6 @@ L: linuxppc-dev@lists.ozlabs.org L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/freescale/fs_enet/ -F: include/linux/fs_enet_pd.h FREESCALE SOC SOUND DRIVERS M: Shengjiu Wang diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h deleted file mode 100644 index 7c9897dab558..000000000000 --- a/include/linux/fs_enet_pd.h +++ /dev/null @@ -1,118 +0,0 @@ -/* - * Platform information definitions for the - * universal Freescale Ethernet driver. - * - * Copyright (c) 2003 Intracom S.A. - * by Pantelis Antoniou - * - * 2005 (c) MontaVista Software, Inc. - * Vitaly Bordug - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef FS_ENET_PD_H -#define FS_ENET_PD_H - -#include -#include -#include -#include -#include - -#define FS_ENET_NAME "fs_enet" - -enum fs_id { - fsid_fec1, - fsid_fec2, - fsid_fcc1, - fsid_fcc2, - fsid_fcc3, - fsid_scc1, - fsid_scc2, - fsid_scc3, - fsid_scc4, -}; - -#define FS_MAX_INDEX 9 - -static inline int fs_get_fec_index(enum fs_id id) -{ - if (id >= fsid_fec1 && id <= fsid_fec2) - return id - fsid_fec1; - return -1; -} - -static inline int fs_get_fcc_index(enum fs_id id) -{ - if (id >= fsid_fcc1 && id <= fsid_fcc3) - return id - fsid_fcc1; - return -1; -} - -static inline int fs_get_scc_index(enum fs_id id) -{ - if (id >= fsid_scc1 && id <= fsid_scc4) - return id - fsid_scc1; - return -1; -} - -static inline int fs_fec_index2id(int index) -{ - int id = fsid_fec1 + index - 1; - if (id >= fsid_fec1 && id <= fsid_fec2) - return id; - return FS_MAX_INDEX; - } - -static inline int fs_fcc_index2id(int index) -{ - int id = fsid_fcc1 + index - 1; - if (id >= fsid_fcc1 && id <= fsid_fcc3) - return id; - return FS_MAX_INDEX; -} - -static inline int fs_scc_index2id(int index) -{ - int id = fsid_scc1 + index - 1; - if (id >= fsid_scc1 && id <= fsid_scc4) - return id; - return FS_MAX_INDEX; -} - -enum fs_mii_method { - fsmii_fixed, - fsmii_fec, - fsmii_bitbang, -}; - -enum fs_ioport { - fsiop_porta, - fsiop_portb, - fsiop_portc, - fsiop_portd, - fsiop_porte, -}; - -struct fs_mii_bit { - u32 offset; - u8 bit; - u8 polarity; -}; -struct fs_mii_bb_platform_info { - struct fs_mii_bit mdio_dir; - struct fs_mii_bit mdio_dat; - struct fs_mii_bit mdc_dat; - int delay; /* delay in us */ - int irq[32]; /* irqs per phy's */ -}; - -struct fs_mii_fec_platform_info { - u32 irq[32]; - u32 mii_speed; -}; - -#endif -- cgit v1.2.3 From de3ecc4fd8bf201c5cd02dc49687fb1506cebb45 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Mon, 7 Aug 2023 09:25:54 +0800 Subject: team: change the init function in the team_option structure to void Because the init function in the team_option structure always returns 0, so change the init function to void and remove redundant code. Signed-off-by: Zhengchao Shao Reviewed-by: Hangbin Liu Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230807012556.3146071-4-shaozhengchao@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/team/team.c | 8 ++------ drivers/net/team/team_mode_activebackup.c | 5 ++--- drivers/net/team/team_mode_loadbalance.c | 15 ++++++--------- include/linux/if_team.h | 2 +- 4 files changed, 11 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index e4fe70a71b40..b88e1c451e07 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -149,7 +149,6 @@ static int __team_option_inst_add(struct team *team, struct team_option *option, struct team_option_inst *opt_inst; unsigned int array_size; unsigned int i; - int err; array_size = option->array_size; if (!array_size) @@ -165,11 +164,8 @@ static int __team_option_inst_add(struct team *team, struct team_option *option, opt_inst->changed = true; opt_inst->removed = false; list_add_tail(&opt_inst->list, &team->option_inst_list); - if (option->init) { - err = option->init(team, &opt_inst->info); - if (err) - return err; - } + if (option->init) + option->init(team, &opt_inst->info); } return 0; diff --git a/drivers/net/team/team_mode_activebackup.c b/drivers/net/team/team_mode_activebackup.c index 3147a4fdf8d9..44d604f1c512 100644 --- a/drivers/net/team/team_mode_activebackup.c +++ b/drivers/net/team/team_mode_activebackup.c @@ -57,11 +57,10 @@ static void ab_port_leave(struct team *team, struct team_port *port) } } -static int ab_active_port_init(struct team *team, - struct team_option_inst_info *info) +static void ab_active_port_init(struct team *team, + struct team_option_inst_info *info) { ab_priv(team)->ap_opt_inst_info = info; - return 0; } static int ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx) diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c index 18d99fda997c..50c015cd0682 100644 --- a/drivers/net/team/team_mode_loadbalance.c +++ b/drivers/net/team/team_mode_loadbalance.c @@ -361,14 +361,13 @@ static int lb_tx_method_set(struct team *team, struct team_gsetter_ctx *ctx) return 0; } -static int lb_tx_hash_to_port_mapping_init(struct team *team, - struct team_option_inst_info *info) +static void lb_tx_hash_to_port_mapping_init(struct team *team, + struct team_option_inst_info *info) { struct lb_priv *lb_priv = get_lb_priv(team); unsigned char hash = info->array_index; LB_HTPM_OPT_INST_INFO_BY_HASH(lb_priv, hash) = info; - return 0; } static int lb_tx_hash_to_port_mapping_get(struct team *team, @@ -401,14 +400,13 @@ static int lb_tx_hash_to_port_mapping_set(struct team *team, return -ENODEV; } -static int lb_hash_stats_init(struct team *team, - struct team_option_inst_info *info) +static void lb_hash_stats_init(struct team *team, + struct team_option_inst_info *info) { struct lb_priv *lb_priv = get_lb_priv(team); unsigned char hash = info->array_index; lb_priv->ex->stats.info[hash].opt_inst_info = info; - return 0; } static int lb_hash_stats_get(struct team *team, struct team_gsetter_ctx *ctx) @@ -421,14 +419,13 @@ static int lb_hash_stats_get(struct team *team, struct team_gsetter_ctx *ctx) return 0; } -static int lb_port_stats_init(struct team *team, - struct team_option_inst_info *info) +static void lb_port_stats_init(struct team *team, + struct team_option_inst_info *info) { struct team_port *port = info->port; struct lb_port_priv *lb_port_priv = get_lb_port_priv(port); lb_port_priv->stats_info.opt_inst_info = info; - return 0; } static int lb_port_stats_get(struct team *team, struct team_gsetter_ctx *ctx) diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 8de6b6e67829..fc01c3cfe86d 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -162,7 +162,7 @@ struct team_option { bool per_port; unsigned int array_size; /* != 0 means the option is array */ enum team_option_type type; - int (*init)(struct team *team, struct team_option_inst_info *info); + void (*init)(struct team *team, struct team_option_inst_info *info); int (*getter)(struct team *team, struct team_gsetter_ctx *ctx); int (*setter)(struct team *team, struct team_gsetter_ctx *ctx); }; -- cgit v1.2.3 From c3b41f4c7b7ce573f379c0053e3c86e722562659 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Mon, 7 Aug 2023 09:25:55 +0800 Subject: team: change the getter function in the team_option structure to void Because the getter function in the team_option structure always returns 0, so change the getter function to void and remove redundant code. Signed-off-by: Zhengchao Shao Reviewed-by: Hangbin Liu Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230807012556.3146071-5-shaozhengchao@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/team/team.c | 52 +++++++++++++------------------ drivers/net/team/team_mode_activebackup.c | 3 +- drivers/net/team/team_mode_loadbalance.c | 24 ++++++-------- include/linux/if_team.h | 2 +- 4 files changed, 33 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index b88e1c451e07..8243563a40f0 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -358,7 +358,9 @@ static int team_option_get(struct team *team, { if (!opt_inst->option->getter) return -EOPNOTSUPP; - return opt_inst->option->getter(team, ctx); + + opt_inst->option->getter(team, ctx); + return 0; } static int team_option_set(struct team *team, @@ -1373,10 +1375,9 @@ static int team_port_del(struct team *team, struct net_device *port_dev) * Net device ops *****************/ -static int team_mode_option_get(struct team *team, struct team_gsetter_ctx *ctx) +static void team_mode_option_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.str_val = team->mode->kind; - return 0; } static int team_mode_option_set(struct team *team, struct team_gsetter_ctx *ctx) @@ -1384,11 +1385,10 @@ static int team_mode_option_set(struct team *team, struct team_gsetter_ctx *ctx) return team_change_mode(team, ctx->data.str_val); } -static int team_notify_peers_count_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void team_notify_peers_count_get(struct team *team, + struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->notify_peers.count; - return 0; } static int team_notify_peers_count_set(struct team *team, @@ -1398,11 +1398,10 @@ static int team_notify_peers_count_set(struct team *team, return 0; } -static int team_notify_peers_interval_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void team_notify_peers_interval_get(struct team *team, + struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->notify_peers.interval; - return 0; } static int team_notify_peers_interval_set(struct team *team, @@ -1412,11 +1411,10 @@ static int team_notify_peers_interval_set(struct team *team, return 0; } -static int team_mcast_rejoin_count_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void team_mcast_rejoin_count_get(struct team *team, + struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->mcast_rejoin.count; - return 0; } static int team_mcast_rejoin_count_set(struct team *team, @@ -1426,11 +1424,10 @@ static int team_mcast_rejoin_count_set(struct team *team, return 0; } -static int team_mcast_rejoin_interval_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void team_mcast_rejoin_interval_get(struct team *team, + struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->mcast_rejoin.interval; - return 0; } static int team_mcast_rejoin_interval_set(struct team *team, @@ -1440,13 +1437,12 @@ static int team_mcast_rejoin_interval_set(struct team *team, return 0; } -static int team_port_en_option_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void team_port_en_option_get(struct team *team, + struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = team_port_enabled(port); - return 0; } static int team_port_en_option_set(struct team *team, @@ -1461,13 +1457,12 @@ static int team_port_en_option_set(struct team *team, return 0; } -static int team_user_linkup_option_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void team_user_linkup_option_get(struct team *team, + struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = port->user.linkup; - return 0; } static void __team_carrier_check(struct team *team); @@ -1483,13 +1478,12 @@ static int team_user_linkup_option_set(struct team *team, return 0; } -static int team_user_linkup_en_option_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void team_user_linkup_en_option_get(struct team *team, + struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = port->user.linkup_enabled; - return 0; } static int team_user_linkup_en_option_set(struct team *team, @@ -1503,13 +1497,12 @@ static int team_user_linkup_en_option_set(struct team *team, return 0; } -static int team_priority_option_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void team_priority_option_get(struct team *team, + struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.s32_val = port->priority; - return 0; } static int team_priority_option_set(struct team *team, @@ -1525,13 +1518,12 @@ static int team_priority_option_set(struct team *team, return 0; } -static int team_queue_id_option_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void team_queue_id_option_get(struct team *team, + struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.u32_val = port->queue_id; - return 0; } static int team_queue_id_option_set(struct team *team, diff --git a/drivers/net/team/team_mode_activebackup.c b/drivers/net/team/team_mode_activebackup.c index 44d604f1c512..e0f599e2a51d 100644 --- a/drivers/net/team/team_mode_activebackup.c +++ b/drivers/net/team/team_mode_activebackup.c @@ -63,7 +63,7 @@ static void ab_active_port_init(struct team *team, ab_priv(team)->ap_opt_inst_info = info; } -static int ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx) +static void ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *active_port; @@ -73,7 +73,6 @@ static int ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx) ctx->data.u32_val = active_port->dev->ifindex; else ctx->data.u32_val = 0; - return 0; } static int ab_active_port_set(struct team *team, struct team_gsetter_ctx *ctx) diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c index 50c015cd0682..2f1573f253ec 100644 --- a/drivers/net/team/team_mode_loadbalance.c +++ b/drivers/net/team/team_mode_loadbalance.c @@ -242,19 +242,18 @@ drop: return false; } -static int lb_bpf_func_get(struct team *team, struct team_gsetter_ctx *ctx) +static void lb_bpf_func_get(struct team *team, struct team_gsetter_ctx *ctx) { struct lb_priv *lb_priv = get_lb_priv(team); if (!lb_priv->ex->orig_fprog) { ctx->data.bin_val.len = 0; ctx->data.bin_val.ptr = NULL; - return 0; + return; } ctx->data.bin_val.len = lb_priv->ex->orig_fprog->len * sizeof(struct sock_filter); ctx->data.bin_val.ptr = lb_priv->ex->orig_fprog->filter; - return 0; } static int __fprog_create(struct sock_fprog_kern **pfprog, u32 data_len, @@ -335,7 +334,7 @@ static void lb_bpf_func_free(struct team *team) bpf_prog_destroy(fp); } -static int lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx) +static void lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx) { struct lb_priv *lb_priv = get_lb_priv(team); lb_select_tx_port_func_t *func; @@ -346,7 +345,6 @@ static int lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx) name = lb_select_tx_port_get_name(func); BUG_ON(!name); ctx->data.str_val = name; - return 0; } static int lb_tx_method_set(struct team *team, struct team_gsetter_ctx *ctx) @@ -370,8 +368,8 @@ static void lb_tx_hash_to_port_mapping_init(struct team *team, LB_HTPM_OPT_INST_INFO_BY_HASH(lb_priv, hash) = info; } -static int lb_tx_hash_to_port_mapping_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void lb_tx_hash_to_port_mapping_get(struct team *team, + struct team_gsetter_ctx *ctx) { struct lb_priv *lb_priv = get_lb_priv(team); struct team_port *port; @@ -379,7 +377,6 @@ static int lb_tx_hash_to_port_mapping_get(struct team *team, port = LB_HTPM_PORT_BY_HASH(lb_priv, hash); ctx->data.u32_val = port ? port->dev->ifindex : 0; - return 0; } static int lb_tx_hash_to_port_mapping_set(struct team *team, @@ -409,14 +406,13 @@ static void lb_hash_stats_init(struct team *team, lb_priv->ex->stats.info[hash].opt_inst_info = info; } -static int lb_hash_stats_get(struct team *team, struct team_gsetter_ctx *ctx) +static void lb_hash_stats_get(struct team *team, struct team_gsetter_ctx *ctx) { struct lb_priv *lb_priv = get_lb_priv(team); unsigned char hash = ctx->info->array_index; ctx->data.bin_val.ptr = &lb_priv->ex->stats.info[hash].stats; ctx->data.bin_val.len = sizeof(struct lb_stats); - return 0; } static void lb_port_stats_init(struct team *team, @@ -428,14 +424,13 @@ static void lb_port_stats_init(struct team *team, lb_port_priv->stats_info.opt_inst_info = info; } -static int lb_port_stats_get(struct team *team, struct team_gsetter_ctx *ctx) +static void lb_port_stats_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; struct lb_port_priv *lb_port_priv = get_lb_port_priv(port); ctx->data.bin_val.ptr = &lb_port_priv->stats_info.stats; ctx->data.bin_val.len = sizeof(struct lb_stats); - return 0; } static void __lb_stats_info_refresh_prepare(struct lb_stats_info *s_info) @@ -528,13 +523,12 @@ static void lb_stats_refresh(struct work_struct *work) mutex_unlock(&team->lock); } -static int lb_stats_refresh_interval_get(struct team *team, - struct team_gsetter_ctx *ctx) +static void lb_stats_refresh_interval_get(struct team *team, + struct team_gsetter_ctx *ctx) { struct lb_priv *lb_priv = get_lb_priv(team); ctx->data.u32_val = lb_priv->ex->stats.refresh_interval; - return 0; } static int lb_stats_refresh_interval_set(struct team *team, diff --git a/include/linux/if_team.h b/include/linux/if_team.h index fc01c3cfe86d..1b9b15a492fa 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -163,7 +163,7 @@ struct team_option { unsigned int array_size; /* != 0 means the option is array */ enum team_option_type type; void (*init)(struct team *team, struct team_option_inst_info *info); - int (*getter)(struct team *team, struct team_gsetter_ctx *ctx); + void (*getter)(struct team *team, struct team_gsetter_ctx *ctx); int (*setter)(struct team *team, struct team_gsetter_ctx *ctx); }; -- cgit v1.2.3 From 209bccbac9e6baa68308e1e236992ae3873e49dc Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 7 Aug 2023 22:21:11 +0800 Subject: net: fq: Remove unused typedef fq_flow_get_default_t Commitbf9009bf21b5 ("net/fq_impl: drop get_default_func, move default flow to fq_tin") remove its last user, so can remove it. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230807142111.33524-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/fq.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/net/fq.h b/include/net/fq.h index 07b5aff6ec58..99fbe4127b95 100644 --- a/include/net/fq.h +++ b/include/net/fq.h @@ -98,9 +98,4 @@ typedef bool fq_skb_filter_t(struct fq *, struct sk_buff *, void *); -typedef struct fq_flow *fq_flow_get_default_t(struct fq *, - struct fq_tin *, - int idx, - struct sk_buff *); - #endif -- cgit v1.2.3 From b876b71a6ac24265848cff4f208e96bf82c32b29 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 7 Aug 2023 22:32:14 +0800 Subject: devlink: Remove unused devlink_dpipe_table_resource_set() declaration Commit f655dacb59ac ("net: devlink: remove unused locked functions") removed this but leave the declaration. Signed-off-by: Yue Haibing Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230807143214.46648-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index a1a8e1b6e7df..f7fec0791acc 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1743,9 +1743,6 @@ int devl_resource_size_get(struct devlink *devlink, int devl_dpipe_table_resource_set(struct devlink *devlink, const char *table_name, u64 resource_id, u64 resource_units); -int devlink_dpipe_table_resource_set(struct devlink *devlink, - const char *table_name, u64 resource_id, - u64 resource_units); void devl_resource_occ_get_register(struct devlink *devlink, u64 resource_id, devlink_resource_occ_get_t *occ_get, -- cgit v1.2.3 From 2c2b88748fd5028a7771a864d46b1b78fb436a07 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 7 Aug 2023 14:00:51 -0700 Subject: docs: net: page_pool: de-duplicate the intro comment In commit 82e896d992fa ("docs: net: page_pool: use kdoc to avoid duplicating the information") I shied away from using the DOC: comments when moving to kdoc for documenting page_pool API, because I wasn't sure how familiar people are with it. Turns out there is already a DOC: comment for the intro, which is the same in both places, modulo what looks like minor rewording. Use the version from Documentation/ but keep the contents with the code. Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230807210051.1014580-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/networking/page_pool.rst | 18 ++---------------- include/net/page_pool/helpers.h | 24 ++++++++++++------------ 2 files changed, 14 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst index 68b82cea13e4..215ebc92752c 100644 --- a/Documentation/networking/page_pool.rst +++ b/Documentation/networking/page_pool.rst @@ -4,22 +4,8 @@ Page Pool API ============= -The page_pool allocator is optimized for the XDP mode that uses one frame -per-page, but it can fallback on the regular page allocator APIs. - -Basic use involves replacing alloc_pages() calls with the -page_pool_alloc_pages() call. Drivers should use page_pool_dev_alloc_pages() -replacing dev_alloc_pages(). - -API keeps track of in-flight pages, in order to let API user know -when it is safe to free a page_pool object. Thus, API users -must call page_pool_put_page() to free the page, or attach -the page to a page_pool-aware objects like skbs marked with -skb_mark_for_recycle(). - -API user must call page_pool_put_page() once on a page, as it -will either recycle the page, or in case of refcnt > 1, it will -release the DMA mapping and in-flight state accounting. +.. kernel-doc:: include/net/page_pool/helpers.h + :doc: page_pool allocator Architecture overview ===================== diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 78df91804c87..94231533a369 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -8,23 +8,23 @@ /** * DOC: page_pool allocator * - * This page_pool allocator is optimized for the XDP mode that - * uses one-frame-per-page, but have fallbacks that act like the + * The page_pool allocator is optimized for the XDP mode that + * uses one frame per-page, but it can fallback on the * regular page allocator APIs. * - * Basic use involve replacing alloc_pages() calls with the - * page_pool_alloc_pages() call. Drivers should likely use + * Basic use involves replacing alloc_pages() calls with the + * page_pool_alloc_pages() call. Drivers should use * page_pool_dev_alloc_pages() replacing dev_alloc_pages(). * - * API keeps track of in-flight pages, in-order to let API user know - * when it is safe to dealloactor page_pool object. Thus, API users - * must call page_pool_put_page() where appropriate and only attach - * the page to a page_pool-aware objects, like skbs marked for recycling. + * API keeps track of in-flight pages, in order to let API user know + * when it is safe to free a page_pool object. Thus, API users + * must call page_pool_put_page() to free the page, or attach + * the page to a page_pool-aware objects like skbs marked with + * skb_mark_for_recycle(). * - * API user must only call page_pool_put_page() once on a page, as it - * will either recycle the page, or in case of elevated refcnt, it - * will release the DMA mapping and in-flight state accounting. We - * hope to lift this requirement in the future. + * API user must call page_pool_put_page() once on a page, as it + * will either recycle the page, or in case of refcnt > 1, it will + * release the DMA mapping and in-flight state accounting. */ #ifndef _NET_PAGE_POOL_HELPERS_H #define _NET_PAGE_POOL_HELPERS_H -- cgit v1.2.3 From 2adbb7637fd1fcec93f4680ddb5ddbbd1a91aefb Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Tue, 8 Aug 2023 22:57:41 +0800 Subject: bpf: btf: Remove two unused function declarations Commit db559117828d ("bpf: Consolidate spin_lock, timer management into btf_record") removed the implementations but leave declarations. Signed-off-by: Yue Haibing Link: https://lore.kernel.org/r/20230808145741.33292-1-yuehaibing@huawei.com Signed-off-by: Martin KaFai Lau --- include/linux/btf.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index cac9f304e27a..df64cc642074 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -204,8 +204,6 @@ u32 btf_nr_types(const struct btf *btf); 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); struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size); int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec); -- cgit v1.2.3 From 90ed8d3dc34bb36b5fb59671924d1ac35f01e75d Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Tue, 8 Aug 2023 22:46:10 +0800 Subject: net: phy: Remove two unused function declarations Commit 1e2dc14509fd ("net: ethtool: Add helpers for reporting test results") declared but never implemented these function. Signed-off-by: Yue Haibing Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230808144610.19096-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index ba08b0e60279..b963ce22e7c7 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1732,10 +1732,6 @@ int phy_start_cable_test_tdr(struct phy_device *phydev, } #endif -int phy_cable_test_result(struct phy_device *phydev, u8 pair, u16 result); -int phy_cable_test_fault_length(struct phy_device *phydev, u8 pair, - u16 cm); - static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); -- cgit v1.2.3 From a76728719c85eaa8440c353490c639655d60d28f Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Tue, 8 Aug 2023 22:59:55 +0800 Subject: net: switchdev: Remove unused declaration switchdev_port_fwd_mark_set() Commit 6bc506b4fb06 ("bridge: switchdev: Add forward mark support for stacked devices") removed the implementation but leave declaration. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Reviewed-by: Petr Machata Link: https://lore.kernel.org/r/20230808145955.2176-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/switchdev.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 0294cfec9c37..a43062d4c734 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -326,10 +326,6 @@ int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info, struct netlink_ext_ack *extack); -void switchdev_port_fwd_mark_set(struct net_device *dev, - struct net_device *group_dev, - bool joining); - int switchdev_handle_fdb_event_to_device(struct net_device *dev, unsigned long event, const struct switchdev_notifier_fdb_info *fdb_info, bool (*check_cb)(const struct net_device *dev), -- cgit v1.2.3 From 1ded5e5a5931bb8b31e15b63b655fe232e3416b2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Aug 2023 13:58:09 +0000 Subject: net: annotate data-races around sock->ops IPV6_ADDRFORM socket option is evil, because it can change sock->ops while other threads might read it. Same issue for sk->sk_family being set to AF_INET. Adding READ_ONCE() over sock->ops reads is needed for sockets that might be impacted by IPV6_ADDRFORM. Note that mptcp_is_tcpsk() can also overwrite sock->ops. Adding annotations for all sk->sk_family reads will require more patches :/ BUG: KCSAN: data-race in ____sys_sendmsg / do_ipv6_setsockopt write to 0xffff888109f24ca0 of 8 bytes by task 4470 on cpu 0: do_ipv6_setsockopt+0x2c5e/0x2ce0 net/ipv6/ipv6_sockglue.c:491 ipv6_setsockopt+0x57/0x130 net/ipv6/ipv6_sockglue.c:1012 udpv6_setsockopt+0x95/0xa0 net/ipv6/udp.c:1690 sock_common_setsockopt+0x61/0x70 net/core/sock.c:3663 __sys_setsockopt+0x1c3/0x230 net/socket.c:2273 __do_sys_setsockopt net/socket.c:2284 [inline] __se_sys_setsockopt net/socket.c:2281 [inline] __x64_sys_setsockopt+0x66/0x80 net/socket.c:2281 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff888109f24ca0 of 8 bytes by task 4469 on cpu 1: sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x349/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmmsg+0x263/0x500 net/socket.c:2643 __do_sys_sendmmsg net/socket.c:2672 [inline] __se_sys_sendmmsg net/socket.c:2669 [inline] __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2669 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0xffffffff850e32b8 -> 0xffffffff850da890 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 4469 Comm: syz-executor.1 Not tainted 6.4.0-rc5-syzkaller-00313-g4c605260bc60 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023 Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230808135809.2300241-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/net.h | 2 +- net/9p/trans_fd.c | 4 +- net/core/scm.c | 3 +- net/core/skmsg.c | 8 ++- net/core/sock.c | 24 ++++++--- net/ipv6/ipv6_sockglue.c | 8 +-- net/mptcp/protocol.c | 8 +-- net/socket.c | 136 ++++++++++++++++++++++++++++------------------- net/unix/scm.c | 3 +- 9 files changed, 118 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 41c608c1b02c..c9b4a63791a4 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -123,7 +123,7 @@ struct socket { struct file *file; struct sock *sk; - const struct proto_ops *ops; + const struct proto_ops *ops; /* Might change with IPV6_ADDRFORM or MPTCP. */ struct socket_wq wq; }; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 00b684616e8d..c4015f30f9fa 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -1019,7 +1019,7 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) } } - err = csocket->ops->connect(csocket, + err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr *)&sin_server, sizeof(struct sockaddr_in), 0); if (err < 0) { @@ -1060,7 +1060,7 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) return err; } - err = csocket->ops->connect(csocket, (struct sockaddr *)&sun_server, + err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr *)&sun_server, sizeof(struct sockaddr_un) - 1, 0); if (err < 0) { pr_err("%s (%d): problem connecting socket: %s: %d\n", diff --git a/net/core/scm.c b/net/core/scm.c index 3cd7dd377e53..880027ecf516 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -130,6 +130,7 @@ EXPORT_SYMBOL(__scm_destroy); int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) { + const struct proto_ops *ops = READ_ONCE(sock->ops); struct cmsghdr *cmsg; int err; @@ -153,7 +154,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) switch (cmsg->cmsg_type) { case SCM_RIGHTS: - if (!sock->ops || sock->ops->family != PF_UNIX) + if (!ops || ops->family != PF_UNIX) goto error; err=scm_fp_copy(cmsg, &p->fp); if (err<0) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a29508e1ff35..e6dfc846018f 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1198,13 +1198,17 @@ out: static void sk_psock_verdict_data_ready(struct sock *sk) { struct socket *sock = sk->sk_socket; + const struct proto_ops *ops; int copied; trace_sk_data_ready(sk); - if (unlikely(!sock || !sock->ops || !sock->ops->read_skb)) + if (unlikely(!sock)) return; - copied = sock->ops->read_skb(sk, sk_psock_verdict_recv); + ops = READ_ONCE(sock->ops); + if (!ops || !ops->read_skb) + return; + copied = ops->read_skb(sk, sk_psock_verdict_recv); if (copied >= 0) { struct sk_psock *psock; diff --git a/net/core/sock.c b/net/core/sock.c index 49915801d53a..51f7d94eccf7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1277,14 +1277,19 @@ set_sndbuf: break; case SO_RCVLOWAT: + { + int (*set_rcvlowat)(struct sock *sk, int val) = NULL; + if (val < 0) val = INT_MAX; - if (sock && sock->ops->set_rcvlowat) - ret = sock->ops->set_rcvlowat(sk, val); + if (sock) + set_rcvlowat = READ_ONCE(sock->ops)->set_rcvlowat; + if (set_rcvlowat) + ret = set_rcvlowat(sk, val); else WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; - + } case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, @@ -1379,11 +1384,16 @@ set_sndbuf: break; case SO_PEEK_OFF: - if (sock->ops->set_peek_off) - ret = sock->ops->set_peek_off(sk, val); + { + int (*set_peek_off)(struct sock *sk, int val); + + set_peek_off = READ_ONCE(sock->ops)->set_peek_off; + if (set_peek_off) + ret = set_peek_off(sk, val); else ret = -EOPNOTSUPP; break; + } case SO_NOFCS: sock_valbool_flag(sk, SOCK_NOFCS, valbool); @@ -1816,7 +1826,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, { struct sockaddr_storage address; - lv = sock->ops->getname(sock, (struct sockaddr *)&address, 2); + lv = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 2); if (lv < 0) return -ENOTCONN; if (lv < len) @@ -1858,7 +1868,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_PEEK_OFF: - if (!sock->ops->set_peek_off) + if (!READ_ONCE(sock->ops)->set_peek_off) return -EOPNOTSUPP; v.val = READ_ONCE(sk->sk_peek_off); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ae818ff46224..ca377159967c 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -474,8 +474,8 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, WRITE_ONCE(sk->sk_prot, &tcp_prot); /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv4_specific); - sk->sk_socket->ops = &inet_stream_ops; - sk->sk_family = PF_INET; + WRITE_ONCE(sk->sk_socket->ops, &inet_stream_ops); + WRITE_ONCE(sk->sk_family, PF_INET); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } else { struct proto *prot = &udp_prot; @@ -488,8 +488,8 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, /* Paired with READ_ONCE(sk->sk_prot) in inet6_dgram_ops */ WRITE_ONCE(sk->sk_prot, prot); - sk->sk_socket->ops = &inet_dgram_ops; - sk->sk_family = PF_INET; + WRITE_ONCE(sk->sk_socket->ops, &inet_dgram_ops); + WRITE_ONCE(sk->sk_family, PF_INET); } /* Disable all options not to allocate memory anymore, diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 65ee949a8a44..1c079e83481e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -67,11 +67,11 @@ static bool mptcp_is_tcpsk(struct sock *sk) * Hand the socket over to tcp so all further socket ops * bypass mptcp. */ - sock->ops = &inet_stream_ops; + WRITE_ONCE(sock->ops, &inet_stream_ops); return true; #if IS_ENABLED(CONFIG_MPTCP_IPV6) } else if (unlikely(sk->sk_prot == &tcpv6_prot)) { - sock->ops = &inet6_stream_ops; + WRITE_ONCE(sock->ops, &inet6_stream_ops); return true; #endif } @@ -3683,7 +3683,7 @@ static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto unlock; } - err = ssock->ops->bind(ssock, uaddr, addr_len); + err = READ_ONCE(ssock->ops)->bind(ssock, uaddr, addr_len); if (!err) mptcp_copy_inaddrs(sock->sk, ssock->sk); @@ -3717,7 +3717,7 @@ static int mptcp_listen(struct socket *sock, int backlog) inet_sk_state_store(sk, TCP_LISTEN); sock_set_flag(sk, SOCK_RCU_FREE); - err = ssock->ops->listen(ssock, backlog); + err = READ_ONCE(ssock->ops)->listen(ssock, backlog); inet_sk_state_store(sk, inet_sk_state_load(ssock->sk)); if (!err) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); diff --git a/net/socket.c b/net/socket.c index 2b0e54b2405c..5d4e37595e9a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -136,9 +136,10 @@ static void sock_splice_eof(struct file *file); static void sock_show_fdinfo(struct seq_file *m, struct file *f) { struct socket *sock = f->private_data; + const struct proto_ops *ops = READ_ONCE(sock->ops); - if (sock->ops->show_fdinfo) - sock->ops->show_fdinfo(m, sock); + if (ops->show_fdinfo) + ops->show_fdinfo(m, sock); } #else #define sock_show_fdinfo NULL @@ -646,12 +647,14 @@ EXPORT_SYMBOL(sock_alloc); static void __sock_release(struct socket *sock, struct inode *inode) { - if (sock->ops) { - struct module *owner = sock->ops->owner; + const struct proto_ops *ops = READ_ONCE(sock->ops); + + if (ops) { + struct module *owner = ops->owner; if (inode) inode_lock(inode); - sock->ops->release(sock); + ops->release(sock); sock->sk = NULL; if (inode) inode_unlock(inode); @@ -722,7 +725,7 @@ static noinline void call_trace_sock_send_length(struct sock *sk, int ret, static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { - int ret = INDIRECT_CALL_INET(sock->ops->sendmsg, inet6_sendmsg, + int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->sendmsg, inet6_sendmsg, inet_sendmsg, sock, msg, msg_data_left(msg)); BUG_ON(ret == -EIOCBQUEUED); @@ -786,13 +789,14 @@ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { struct socket *sock = sk->sk_socket; + const struct proto_ops *ops = READ_ONCE(sock->ops); - if (!sock->ops->sendmsg_locked) + if (!ops->sendmsg_locked) return sock_no_sendmsg_locked(sk, msg, size); iov_iter_kvec(&msg->msg_iter, ITER_SOURCE, vec, num, size); - return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg)); + return ops->sendmsg_locked(sk, msg, msg_data_left(msg)); } EXPORT_SYMBOL(kernel_sendmsg_locked); @@ -1017,7 +1021,8 @@ static noinline void call_trace_sock_recv_length(struct sock *sk, int ret, int f static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, int flags) { - int ret = INDIRECT_CALL_INET(sock->ops->recvmsg, inet6_recvmsg, + int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->recvmsg, + inet6_recvmsg, inet_recvmsg, sock, msg, msg_data_left(msg), flags); if (trace_sock_recv_length_enabled()) @@ -1072,19 +1077,23 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, unsigned int flags) { struct socket *sock = file->private_data; + const struct proto_ops *ops; - if (unlikely(!sock->ops->splice_read)) + ops = READ_ONCE(sock->ops); + if (unlikely(!ops->splice_read)) return copy_splice_read(file, ppos, pipe, len, flags); - return sock->ops->splice_read(sock, ppos, pipe, len, flags); + return ops->splice_read(sock, ppos, pipe, len, flags); } static void sock_splice_eof(struct file *file) { struct socket *sock = file->private_data; + const struct proto_ops *ops; - if (sock->ops->splice_eof) - sock->ops->splice_eof(sock); + ops = READ_ONCE(sock->ops); + if (ops->splice_eof) + ops->splice_eof(sock); } static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -1181,13 +1190,14 @@ EXPORT_SYMBOL(vlan_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, unsigned int cmd, unsigned long arg) { + const struct proto_ops *ops = READ_ONCE(sock->ops); struct ifreq ifr; bool need_copyout; int err; void __user *argp = (void __user *)arg; void __user *data; - err = sock->ops->ioctl(sock, cmd, arg); + err = ops->ioctl(sock, cmd, arg); /* * If this ioctl is unknown try to hand it down @@ -1216,6 +1226,7 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { + const struct proto_ops *ops; struct socket *sock; struct sock *sk; void __user *argp = (void __user *)arg; @@ -1223,6 +1234,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) struct net *net; sock = file->private_data; + ops = READ_ONCE(sock->ops); sk = sock->sk; net = sock_net(sk); if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) { @@ -1280,23 +1292,23 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) break; case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: - if (!sock->ops->gettstamp) { + if (!ops->gettstamp) { err = -ENOIOCTLCMD; break; } - err = sock->ops->gettstamp(sock, argp, - cmd == SIOCGSTAMP_OLD, - !IS_ENABLED(CONFIG_64BIT)); + err = ops->gettstamp(sock, argp, + cmd == SIOCGSTAMP_OLD, + !IS_ENABLED(CONFIG_64BIT)); break; case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: - if (!sock->ops->gettstamp) { + if (!ops->gettstamp) { err = -ENOIOCTLCMD; break; } - err = sock->ops->gettstamp(sock, argp, - cmd == SIOCGSTAMP_NEW, - false); + err = ops->gettstamp(sock, argp, + cmd == SIOCGSTAMP_NEW, + false); break; case SIOCGIFCONF: @@ -1357,9 +1369,10 @@ EXPORT_SYMBOL(sock_create_lite); static __poll_t sock_poll(struct file *file, poll_table *wait) { struct socket *sock = file->private_data; + const struct proto_ops *ops = READ_ONCE(sock->ops); __poll_t events = poll_requested_events(wait), flag = 0; - if (!sock->ops->poll) + if (!ops->poll) return 0; if (sk_can_busy_loop(sock->sk)) { @@ -1371,14 +1384,14 @@ static __poll_t sock_poll(struct file *file, poll_table *wait) flag = POLL_BUSY_LOOP; } - return sock->ops->poll(file, sock, wait) | flag; + return ops->poll(file, sock, wait) | flag; } static int sock_mmap(struct file *file, struct vm_area_struct *vma) { struct socket *sock = file->private_data; - return sock->ops->mmap(file, sock, vma); + return READ_ONCE(sock->ops)->mmap(file, sock, vma); } static int sock_close(struct inode *inode, struct file *filp) @@ -1728,7 +1741,7 @@ int __sys_socketpair(int family, int type, int protocol, int __user *usockvec) goto out; } - err = sock1->ops->socketpair(sock1, sock2); + err = READ_ONCE(sock1->ops)->socketpair(sock1, sock2); if (unlikely(err < 0)) { sock_release(sock2); sock_release(sock1); @@ -1789,7 +1802,7 @@ int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) (struct sockaddr *)&address, addrlen); if (!err) - err = sock->ops->bind(sock, + err = READ_ONCE(sock->ops)->bind(sock, (struct sockaddr *) &address, addrlen); } @@ -1823,7 +1836,7 @@ int __sys_listen(int fd, int backlog) err = security_socket_listen(sock, backlog); if (!err) - err = sock->ops->listen(sock, backlog); + err = READ_ONCE(sock->ops)->listen(sock, backlog); fput_light(sock->file, fput_needed); } @@ -1843,6 +1856,7 @@ struct file *do_accept(struct file *file, unsigned file_flags, struct file *newfile; int err, len; struct sockaddr_storage address; + const struct proto_ops *ops; sock = sock_from_file(file); if (!sock) @@ -1851,15 +1865,16 @@ struct file *do_accept(struct file *file, unsigned file_flags, newsock = sock_alloc(); if (!newsock) return ERR_PTR(-ENFILE); + ops = READ_ONCE(sock->ops); newsock->type = sock->type; - newsock->ops = sock->ops; + newsock->ops = ops; /* * We don't need try_module_get here, as the listening socket (sock) * has the protocol module (sock->ops->owner) held. */ - __module_get(newsock->ops->owner); + __module_get(ops->owner); newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); if (IS_ERR(newfile)) @@ -1869,14 +1884,13 @@ struct file *do_accept(struct file *file, unsigned file_flags, if (err) goto out_fd; - err = sock->ops->accept(sock, newsock, sock->file->f_flags | file_flags, + err = ops->accept(sock, newsock, sock->file->f_flags | file_flags, false); if (err < 0) goto out_fd; if (upeer_sockaddr) { - len = newsock->ops->getname(newsock, - (struct sockaddr *)&address, 2); + len = ops->getname(newsock, (struct sockaddr *)&address, 2); if (len < 0) { err = -ECONNABORTED; goto out_fd; @@ -1989,8 +2003,8 @@ int __sys_connect_file(struct file *file, struct sockaddr_storage *address, if (err) goto out; - err = sock->ops->connect(sock, (struct sockaddr *)address, addrlen, - sock->file->f_flags | file_flags); + err = READ_ONCE(sock->ops)->connect(sock, (struct sockaddr *)address, + addrlen, sock->file->f_flags | file_flags); out: return err; } @@ -2039,7 +2053,7 @@ int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, if (err) goto out_put; - err = sock->ops->getname(sock, (struct sockaddr *)&address, 0); + err = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 0); if (err < 0) goto out_put; /* "err" is actually length in this case */ @@ -2071,13 +2085,15 @@ int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { + const struct proto_ops *ops = READ_ONCE(sock->ops); + err = security_socket_getpeername(sock); if (err) { fput_light(sock->file, fput_needed); return err; } - err = sock->ops->getname(sock, (struct sockaddr *)&address, 1); + err = ops->getname(sock, (struct sockaddr *)&address, 1); if (err >= 0) /* "err" is actually length in this case */ err = move_addr_to_user(&address, err, usockaddr, @@ -2227,6 +2243,7 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, int optlen) { sockptr_t optval = USER_SOCKPTR(user_optval); + const struct proto_ops *ops; char *kernel_optval = NULL; int err, fput_needed; struct socket *sock; @@ -2255,12 +2272,13 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, if (kernel_optval) optval = KERNEL_SOCKPTR(kernel_optval); + ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET && !sock_use_custom_sol_socket(sock)) err = sock_setsockopt(sock, level, optname, optval, optlen); - else if (unlikely(!sock->ops->setsockopt)) + else if (unlikely(!ops->setsockopt)) err = -EOPNOTSUPP; else - err = sock->ops->setsockopt(sock, level, optname, optval, + err = ops->setsockopt(sock, level, optname, optval, optlen); kfree(kernel_optval); out_put: @@ -2285,6 +2303,7 @@ int __sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) { int max_optlen __maybe_unused; + const struct proto_ops *ops; int err, fput_needed; struct socket *sock; @@ -2299,12 +2318,13 @@ int __sys_getsockopt(int fd, int level, int optname, char __user *optval, if (!in_compat_syscall()) max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); + ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET) err = sock_getsockopt(sock, level, optname, optval, optlen); - else if (unlikely(!sock->ops->getsockopt)) + else if (unlikely(!ops->getsockopt)) err = -EOPNOTSUPP; else - err = sock->ops->getsockopt(sock, level, optname, optval, + err = ops->getsockopt(sock, level, optname, optval, optlen); if (!in_compat_syscall()) @@ -2332,7 +2352,7 @@ int __sys_shutdown_sock(struct socket *sock, int how) err = security_socket_shutdown(sock, how); if (!err) - err = sock->ops->shutdown(sock, how); + err = READ_ONCE(sock->ops)->shutdown(sock, how); return err; } @@ -3324,6 +3344,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; struct net *net = sock_net(sk); + const struct proto_ops *ops; if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) return sock_ioctl(file, cmd, (unsigned long)argp); @@ -3333,10 +3354,11 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, return compat_siocwandev(net, argp); case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: - if (!sock->ops->gettstamp) + ops = READ_ONCE(sock->ops); + if (!ops->gettstamp) return -ENOIOCTLCMD; - return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, - !COMPAT_USE_64BIT_TIME); + return ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, + !COMPAT_USE_64BIT_TIME); case SIOCETHTOOL: case SIOCBONDSLAVEINFOQUERY: @@ -3417,6 +3439,7 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct socket *sock = file->private_data; + const struct proto_ops *ops = READ_ONCE(sock->ops); int ret = -ENOIOCTLCMD; struct sock *sk; struct net *net; @@ -3424,8 +3447,8 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, sk = sock->sk; net = sock_net(sk); - if (sock->ops->compat_ioctl) - ret = sock->ops->compat_ioctl(sock, cmd, arg); + if (ops->compat_ioctl) + ret = ops->compat_ioctl(sock, cmd, arg); if (ret == -ENOIOCTLCMD && (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)) @@ -3449,7 +3472,7 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { - return sock->ops->bind(sock, addr, addrlen); + return READ_ONCE(sock->ops)->bind(sock, addr, addrlen); } EXPORT_SYMBOL(kernel_bind); @@ -3463,7 +3486,7 @@ EXPORT_SYMBOL(kernel_bind); int kernel_listen(struct socket *sock, int backlog) { - return sock->ops->listen(sock, backlog); + return READ_ONCE(sock->ops)->listen(sock, backlog); } EXPORT_SYMBOL(kernel_listen); @@ -3481,6 +3504,7 @@ EXPORT_SYMBOL(kernel_listen); int kernel_accept(struct socket *sock, struct socket **newsock, int flags) { struct sock *sk = sock->sk; + const struct proto_ops *ops = READ_ONCE(sock->ops); int err; err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol, @@ -3488,15 +3512,15 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) if (err < 0) goto done; - err = sock->ops->accept(sock, *newsock, flags, true); + err = ops->accept(sock, *newsock, flags, true); if (err < 0) { sock_release(*newsock); *newsock = NULL; goto done; } - (*newsock)->ops = sock->ops; - __module_get((*newsock)->ops->owner); + (*newsock)->ops = ops; + __module_get(ops->owner); done: return err; @@ -3519,7 +3543,7 @@ EXPORT_SYMBOL(kernel_accept); int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags) { - return sock->ops->connect(sock, addr, addrlen, flags); + return READ_ONCE(sock->ops)->connect(sock, addr, addrlen, flags); } EXPORT_SYMBOL(kernel_connect); @@ -3534,7 +3558,7 @@ EXPORT_SYMBOL(kernel_connect); int kernel_getsockname(struct socket *sock, struct sockaddr *addr) { - return sock->ops->getname(sock, addr, 0); + return READ_ONCE(sock->ops)->getname(sock, addr, 0); } EXPORT_SYMBOL(kernel_getsockname); @@ -3549,7 +3573,7 @@ EXPORT_SYMBOL(kernel_getsockname); int kernel_getpeername(struct socket *sock, struct sockaddr *addr) { - return sock->ops->getname(sock, addr, 1); + return READ_ONCE(sock->ops)->getname(sock, addr, 1); } EXPORT_SYMBOL(kernel_getpeername); @@ -3563,7 +3587,7 @@ EXPORT_SYMBOL(kernel_getpeername); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) { - return sock->ops->shutdown(sock, how); + return READ_ONCE(sock->ops)->shutdown(sock, how); } EXPORT_SYMBOL(kernel_sock_shutdown); diff --git a/net/unix/scm.c b/net/unix/scm.c index f9152881d77f..e9dde7176c8a 100644 --- a/net/unix/scm.c +++ b/net/unix/scm.c @@ -29,10 +29,11 @@ struct sock *unix_get_socket(struct file *filp) /* Socket ? */ if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { struct socket *sock = SOCKET_I(inode); + const struct proto_ops *ops = READ_ONCE(sock->ops); struct sock *s = sock->sk; /* PF_UNIX ? */ - if (s && sock->ops && sock->ops->family == PF_UNIX) + if (s && ops && ops->family == PF_UNIX) u_sock = s; } else { /* Could be an io_uring instance */ -- cgit v1.2.3 From 1f507e80c700e31e358bf4213dc7e4dd614c7c72 Mon Sep 17 00:00:00 2001 From: Adham Faris Date: Mon, 7 Aug 2023 11:05:07 -0700 Subject: net/mlx5: Expose NIC temperature via hardware monitoring kernel API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Expose NIC temperature by implementing hwmon kernel API, which turns current thermal zone kernel API to redundant. For each one of the supported and exposed thermal diode sensors, expose the following attributes: 1) Input temperature. 2) Highest temperature. 3) Temperature label: Depends on the firmware capability, if firmware doesn't support sensors naming, the fallback naming convention would be: "sensorX", where X is the HW spec (MTMP register) sensor index. 4) Temperature critical max value: refers to the high threshold of Warning Event. Will be exposed as `tempY_crit` hwmon attribute (RO attribute). For example for ConnectX5 HCA's this temperature value will be 105 Celsius, 10 degrees lower than the HW shutdown temperature). 5) Temperature reset history: resets highest temperature. For example, for dualport ConnectX5 NIC with a single IC thermal diode sensor will have 2 hwmon directories (one for each PCI function) under "/sys/class/hwmon/hwmon[X,Y]". Listing one of the directories above (hwmonX/Y) generates the corresponding output below: $ grep -H -d skip . /sys/class/hwmon/hwmon0/* Output ======================================================================= /sys/class/hwmon/hwmon0/name:mlx5 /sys/class/hwmon/hwmon0/temp1_crit:105000 /sys/class/hwmon/hwmon0/temp1_highest:48000 /sys/class/hwmon/hwmon0/temp1_input:46000 /sys/class/hwmon/hwmon0/temp1_label:asic grep: /sys/class/hwmon/hwmon0/temp1_reset_history: Permission denied In addition, displaying the sensors data via lm_sensors generates the corresponding output below: $ sensors Output ======================================================================= mlx5-pci-0800 Adapter: PCI adapter asic: +46.0°C (crit = +105.0°C, highest = +48.0°C) mlx5-pci-0801 Adapter: PCI adapter asic: +46.0°C (crit = +105.0°C, highest = +48.0°C) CC: Jean Delvare Signed-off-by: Adham Faris Reviewed-by: Tariq Toukan Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed Acked-by: Guenter Roeck Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230807180507.22984-3-saeed@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 1 + drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx5/core/hwmon.c | 418 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/hwmon.h | 24 ++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 8 +- drivers/net/ethernet/mellanox/mlx5/core/thermal.c | 114 ------ drivers/net/ethernet/mellanox/mlx5/core/thermal.h | 20 -- include/linux/mlx5/driver.h | 3 +- include/linux/mlx5/mlx5_ifc.h | 14 +- 9 files changed, 463 insertions(+), 141 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/hwmon.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/hwmon.h delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/thermal.c delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/thermal.h (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index bb1d7b039a7e..d537d517cabe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -12,6 +12,7 @@ config MLX5_CORE depends on MLXFW || !MLXFW depends on PTP_1588_CLOCK_OPTIONAL depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE + depends on HWMON || !HWMON help Core driver for low level functionality of the ConnectX-4 and Connect-IB cards by Mellanox Technologies. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 63a2f2bb80a6..946310390659 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -82,7 +82,7 @@ endif mlx5_core-$(CONFIG_MLX5_BRIDGE) += esw/bridge.o esw/bridge_mcast.o esw/bridge_debugfs.o \ en/rep/bridge.o -mlx5_core-$(CONFIG_THERMAL) += thermal.o +mlx5_core-$(CONFIG_HWMON) += hwmon.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c new file mode 100644 index 000000000000..353f81dccd1c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c @@ -0,0 +1,418 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved + +#include +#include +#include +#include +#include +#include "mlx5_core.h" +#include "hwmon.h" + +#define CHANNELS_TYPE_NUM 2 /* chip channel and temp channel */ +#define CHIP_CONFIG_NUM 1 + +/* module 0 is mapped to sensor_index 64 in MTMP register */ +#define to_mtmp_module_sensor_idx(idx) (64 + (idx)) + +/* All temperatures retrieved in units of 0.125C. hwmon framework expect + * it in units of millidegrees C. Hence multiply values by 125. + */ +#define mtmp_temp_to_mdeg(temp) ((temp) * 125) + +struct temp_channel_desc { + u32 sensor_index; + char sensor_name[32]; +}; + +/* chip_channel_config and channel_info arrays must be 0-terminated, hence + 1 */ +struct mlx5_hwmon { + struct mlx5_core_dev *mdev; + struct device *hwmon_dev; + struct hwmon_channel_info chip_info; + u32 chip_channel_config[CHIP_CONFIG_NUM + 1]; + struct hwmon_channel_info temp_info; + u32 *temp_channel_config; + const struct hwmon_channel_info *channel_info[CHANNELS_TYPE_NUM + 1]; + struct hwmon_chip_info chip; + struct temp_channel_desc *temp_channel_desc; + u32 asic_platform_scount; + u32 module_scount; +}; + +static int mlx5_hwmon_query_mtmp(struct mlx5_core_dev *mdev, u32 sensor_index, u32 *mtmp_out) +{ + u32 mtmp_in[MLX5_ST_SZ_DW(mtmp_reg)] = {}; + + MLX5_SET(mtmp_reg, mtmp_in, sensor_index, sensor_index); + + return mlx5_core_access_reg(mdev, mtmp_in, sizeof(mtmp_in), + mtmp_out, MLX5_ST_SZ_BYTES(mtmp_reg), + MLX5_REG_MTMP, 0, 0); +} + +static int mlx5_hwmon_reset_max_temp(struct mlx5_core_dev *mdev, int sensor_index) +{ + u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)] = {}; + u32 mtmp_in[MLX5_ST_SZ_DW(mtmp_reg)] = {}; + + MLX5_SET(mtmp_reg, mtmp_in, sensor_index, sensor_index); + MLX5_SET(mtmp_reg, mtmp_in, mtr, 1); + + return mlx5_core_access_reg(mdev, mtmp_in, sizeof(mtmp_in), + mtmp_out, sizeof(mtmp_out), + MLX5_REG_MTMP, 0, 0); +} + +static int mlx5_hwmon_enable_max_temp(struct mlx5_core_dev *mdev, int sensor_index) +{ + u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)] = {}; + u32 mtmp_in[MLX5_ST_SZ_DW(mtmp_reg)] = {}; + int err; + + err = mlx5_hwmon_query_mtmp(mdev, sensor_index, mtmp_in); + if (err) + return err; + + MLX5_SET(mtmp_reg, mtmp_in, mte, 1); + return mlx5_core_access_reg(mdev, mtmp_in, sizeof(mtmp_in), + mtmp_out, sizeof(mtmp_out), + MLX5_REG_MTMP, 0, 1); +} + +static int mlx5_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, + int channel, long *val) +{ + struct mlx5_hwmon *hwmon = dev_get_drvdata(dev); + u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)] = {}; + int err; + + if (type != hwmon_temp) + return -EOPNOTSUPP; + + err = mlx5_hwmon_query_mtmp(hwmon->mdev, hwmon->temp_channel_desc[channel].sensor_index, + mtmp_out); + if (err) + return err; + + switch (attr) { + case hwmon_temp_input: + *val = mtmp_temp_to_mdeg(MLX5_GET(mtmp_reg, mtmp_out, temperature)); + return 0; + case hwmon_temp_highest: + *val = mtmp_temp_to_mdeg(MLX5_GET(mtmp_reg, mtmp_out, max_temperature)); + return 0; + case hwmon_temp_crit: + *val = mtmp_temp_to_mdeg(MLX5_GET(mtmp_reg, mtmp_out, temp_threshold_hi)); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int mlx5_hwmon_write(struct device *dev, enum hwmon_sensor_types type, u32 attr, + int channel, long val) +{ + struct mlx5_hwmon *hwmon = dev_get_drvdata(dev); + + if (type != hwmon_temp || attr != hwmon_temp_reset_history) + return -EOPNOTSUPP; + + return mlx5_hwmon_reset_max_temp(hwmon->mdev, + hwmon->temp_channel_desc[channel].sensor_index); +} + +static umode_t mlx5_hwmon_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr, + int channel) +{ + if (type != hwmon_temp) + return 0; + + switch (attr) { + case hwmon_temp_input: + case hwmon_temp_highest: + case hwmon_temp_crit: + case hwmon_temp_label: + return 0444; + case hwmon_temp_reset_history: + return 0200; + default: + return 0; + } +} + +static int mlx5_hwmon_read_string(struct device *dev, enum hwmon_sensor_types type, u32 attr, + int channel, const char **str) +{ + struct mlx5_hwmon *hwmon = dev_get_drvdata(dev); + + if (type != hwmon_temp || attr != hwmon_temp_label) + return -EOPNOTSUPP; + + *str = (const char *)hwmon->temp_channel_desc[channel].sensor_name; + return 0; +} + +static const struct hwmon_ops mlx5_hwmon_ops = { + .read = mlx5_hwmon_read, + .read_string = mlx5_hwmon_read_string, + .is_visible = mlx5_hwmon_is_visible, + .write = mlx5_hwmon_write, +}; + +static int mlx5_hwmon_init_channels_names(struct mlx5_hwmon *hwmon) +{ + u32 i; + + for (i = 0; i < hwmon->asic_platform_scount + hwmon->module_scount; i++) { + u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)] = {}; + char *sensor_name; + int err; + + err = mlx5_hwmon_query_mtmp(hwmon->mdev, hwmon->temp_channel_desc[i].sensor_index, + mtmp_out); + if (err) + return err; + + sensor_name = MLX5_ADDR_OF(mtmp_reg, mtmp_out, sensor_name_hi); + if (!*sensor_name) { + snprintf(hwmon->temp_channel_desc[i].sensor_name, + sizeof(hwmon->temp_channel_desc[i].sensor_name), "sensor%u", + hwmon->temp_channel_desc[i].sensor_index); + continue; + } + + memcpy(&hwmon->temp_channel_desc[i].sensor_name, sensor_name, + MLX5_FLD_SZ_BYTES(mtmp_reg, sensor_name_hi) + + MLX5_FLD_SZ_BYTES(mtmp_reg, sensor_name_lo)); + } + + return 0; +} + +static int mlx5_hwmon_get_module_sensor_index(struct mlx5_core_dev *mdev, u32 *module_index) +{ + int module_num; + int err; + + err = mlx5_query_module_num(mdev, &module_num); + if (err) + return err; + + *module_index = to_mtmp_module_sensor_idx(module_num); + + return 0; +} + +static int mlx5_hwmon_init_sensors_indexes(struct mlx5_hwmon *hwmon, u64 sensor_map) +{ + DECLARE_BITMAP(smap, BITS_PER_TYPE(sensor_map)); + unsigned long bit_pos; + int err = 0; + int i = 0; + + bitmap_from_u64(smap, sensor_map); + + for_each_set_bit(bit_pos, smap, BITS_PER_TYPE(sensor_map)) { + hwmon->temp_channel_desc[i].sensor_index = bit_pos; + i++; + } + + if (hwmon->module_scount) + err = mlx5_hwmon_get_module_sensor_index(hwmon->mdev, + &hwmon->temp_channel_desc[i].sensor_index); + + return err; +} + +static void mlx5_hwmon_channel_info_init(struct mlx5_hwmon *hwmon) +{ + int i; + + hwmon->channel_info[0] = &hwmon->chip_info; + hwmon->channel_info[1] = &hwmon->temp_info; + + hwmon->chip_channel_config[0] = HWMON_C_REGISTER_TZ; + hwmon->chip_info.config = (const u32 *)hwmon->chip_channel_config; + hwmon->chip_info.type = hwmon_chip; + + for (i = 0; i < hwmon->asic_platform_scount + hwmon->module_scount; i++) + hwmon->temp_channel_config[i] = HWMON_T_INPUT | HWMON_T_HIGHEST | HWMON_T_CRIT | + HWMON_T_RESET_HISTORY | HWMON_T_LABEL; + + hwmon->temp_info.config = (const u32 *)hwmon->temp_channel_config; + hwmon->temp_info.type = hwmon_temp; +} + +static int mlx5_hwmon_is_module_mon_cap(struct mlx5_core_dev *mdev, bool *mon_cap) +{ + u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)]; + u32 module_index; + int err; + + err = mlx5_hwmon_get_module_sensor_index(mdev, &module_index); + if (err) + return err; + + err = mlx5_hwmon_query_mtmp(mdev, module_index, mtmp_out); + if (err) + return err; + + if (MLX5_GET(mtmp_reg, mtmp_out, temperature)) + *mon_cap = true; + + return 0; +} + +static int mlx5_hwmon_get_sensors_count(struct mlx5_core_dev *mdev, u32 *asic_platform_scount) +{ + u32 mtcap_out[MLX5_ST_SZ_DW(mtcap_reg)] = {}; + u32 mtcap_in[MLX5_ST_SZ_DW(mtcap_reg)] = {}; + int err; + + err = mlx5_core_access_reg(mdev, mtcap_in, sizeof(mtcap_in), + mtcap_out, sizeof(mtcap_out), + MLX5_REG_MTCAP, 0, 0); + if (err) + return err; + + *asic_platform_scount = MLX5_GET(mtcap_reg, mtcap_out, sensor_count); + + return 0; +} + +static void mlx5_hwmon_free(struct mlx5_hwmon *hwmon) +{ + if (!hwmon) + return; + + kfree(hwmon->temp_channel_config); + kfree(hwmon->temp_channel_desc); + kfree(hwmon); +} + +static struct mlx5_hwmon *mlx5_hwmon_alloc(struct mlx5_core_dev *mdev) +{ + struct mlx5_hwmon *hwmon; + bool mon_cap = false; + u32 sensors_count; + int err; + + hwmon = kzalloc(sizeof(*mdev->hwmon), GFP_KERNEL); + if (!hwmon) + return ERR_PTR(-ENOMEM); + + err = mlx5_hwmon_get_sensors_count(mdev, &hwmon->asic_platform_scount); + if (err) + goto err_free_hwmon; + + /* check if module sensor has thermal mon cap. if yes, allocate channel desc for it */ + err = mlx5_hwmon_is_module_mon_cap(mdev, &mon_cap); + if (err) + goto err_free_hwmon; + + hwmon->module_scount = mon_cap ? 1 : 0; + sensors_count = hwmon->asic_platform_scount + hwmon->module_scount; + hwmon->temp_channel_desc = kcalloc(sensors_count, sizeof(*hwmon->temp_channel_desc), + GFP_KERNEL); + if (!hwmon->temp_channel_desc) { + err = -ENOMEM; + goto err_free_hwmon; + } + + /* sensors configuration values array, must be 0-terminated hence, + 1 */ + hwmon->temp_channel_config = kcalloc(sensors_count + 1, sizeof(*hwmon->temp_channel_config), + GFP_KERNEL); + if (!hwmon->temp_channel_config) { + err = -ENOMEM; + goto err_free_temp_channel_desc; + } + + hwmon->mdev = mdev; + + return hwmon; + +err_free_temp_channel_desc: + kfree(hwmon->temp_channel_desc); +err_free_hwmon: + kfree(hwmon); + return ERR_PTR(err); +} + +static int mlx5_hwmon_dev_init(struct mlx5_hwmon *hwmon) +{ + u32 mtcap_out[MLX5_ST_SZ_DW(mtcap_reg)] = {}; + u32 mtcap_in[MLX5_ST_SZ_DW(mtcap_reg)] = {}; + int err; + int i; + + err = mlx5_core_access_reg(hwmon->mdev, mtcap_in, sizeof(mtcap_in), + mtcap_out, sizeof(mtcap_out), + MLX5_REG_MTCAP, 0, 0); + if (err) + return err; + + mlx5_hwmon_channel_info_init(hwmon); + mlx5_hwmon_init_sensors_indexes(hwmon, MLX5_GET64(mtcap_reg, mtcap_out, sensor_map)); + err = mlx5_hwmon_init_channels_names(hwmon); + if (err) + return err; + + for (i = 0; i < hwmon->asic_platform_scount + hwmon->module_scount; i++) { + err = mlx5_hwmon_enable_max_temp(hwmon->mdev, + hwmon->temp_channel_desc[i].sensor_index); + if (err) + return err; + } + + hwmon->chip.ops = &mlx5_hwmon_ops; + hwmon->chip.info = (const struct hwmon_channel_info **)hwmon->channel_info; + + return 0; +} + +int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev) +{ + struct device *dev = mdev->device; + struct mlx5_hwmon *hwmon; + int err; + + if (!MLX5_CAP_MCAM_REG(mdev, mtmp)) + return 0; + + hwmon = mlx5_hwmon_alloc(mdev); + if (IS_ERR(hwmon)) + return PTR_ERR(hwmon); + + err = mlx5_hwmon_dev_init(hwmon); + if (err) + goto err_free_hwmon; + + hwmon->hwmon_dev = hwmon_device_register_with_info(dev, "mlx5", + hwmon, + &hwmon->chip, + NULL); + if (IS_ERR(hwmon->hwmon_dev)) { + err = PTR_ERR(hwmon->hwmon_dev); + goto err_free_hwmon; + } + + mdev->hwmon = hwmon; + return 0; + +err_free_hwmon: + mlx5_hwmon_free(hwmon); + return err; +} + +void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev) +{ + struct mlx5_hwmon *hwmon = mdev->hwmon; + + if (!hwmon) + return; + + hwmon_device_unregister(hwmon->hwmon_dev); + mlx5_hwmon_free(hwmon); + mdev->hwmon = NULL; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h new file mode 100644 index 000000000000..999654a9b9da --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB + * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved + */ +#ifndef __MLX5_HWMON_H__ +#define __MLX5_HWMON_H__ + +#include + +#if IS_ENABLED(CONFIG_HWMON) + +int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev); +void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev); + +#else +static inline int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev) +{ + return 0; +} + +static inline void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev) {} + +#endif + +#endif /* __MLX5_HWMON_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index db2e8e4f848d..0389e84f9815 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -49,7 +49,6 @@ #include #include #include "mlx5_core.h" -#include "thermal.h" #include "lib/eq.h" #include "fs_core.h" #include "lib/mpfs.h" @@ -73,6 +72,7 @@ #include "sf/dev/dev.h" #include "sf/sf.h" #include "mlx5_irq.h" +#include "hwmon.h" MODULE_AUTHOR("Eli Cohen "); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); @@ -1930,9 +1930,9 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) if (err) dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err); - err = mlx5_thermal_init(dev); + err = mlx5_hwmon_dev_register(dev); if (err) - dev_err(&pdev->dev, "mlx5_thermal_init failed with error code %d\n", err); + mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err); pci_save_state(pdev); devlink_register(devlink); @@ -1964,7 +1964,7 @@ static void remove_one(struct pci_dev *pdev) mlx5_drain_health_wq(dev); devlink_unregister(devlink); mlx5_sriov_disable(pdev, false); - mlx5_thermal_uninit(dev); + mlx5_hwmon_dev_unregister(dev); mlx5_crdump_disable(dev); mlx5_uninit_one(dev); mlx5_pci_close(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c b/drivers/net/ethernet/mellanox/mlx5/core/thermal.c deleted file mode 100644 index 52199d39657e..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c +++ /dev/null @@ -1,114 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB -// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. - -#include -#include -#include -#include -#include -#include -#include "mlx5_core.h" -#include "thermal.h" - -#define MLX5_THERMAL_POLL_INT_MSEC 1000 -#define MLX5_THERMAL_NUM_TRIPS 0 -#define MLX5_THERMAL_ASIC_SENSOR_INDEX 0 - -/* Bit string indicating the writeablility of trip points if any */ -#define MLX5_THERMAL_TRIP_MASK (BIT(MLX5_THERMAL_NUM_TRIPS) - 1) - -struct mlx5_thermal { - struct mlx5_core_dev *mdev; - struct thermal_zone_device *tzdev; -}; - -static int mlx5_thermal_get_mtmp_temp(struct mlx5_core_dev *mdev, u32 id, int *p_temp) -{ - u32 mtmp_out[MLX5_ST_SZ_DW(mtmp_reg)] = {}; - u32 mtmp_in[MLX5_ST_SZ_DW(mtmp_reg)] = {}; - int err; - - MLX5_SET(mtmp_reg, mtmp_in, sensor_index, id); - - err = mlx5_core_access_reg(mdev, mtmp_in, sizeof(mtmp_in), - mtmp_out, sizeof(mtmp_out), - MLX5_REG_MTMP, 0, 0); - - if (err) - return err; - - *p_temp = MLX5_GET(mtmp_reg, mtmp_out, temperature); - - return 0; -} - -static int mlx5_thermal_get_temp(struct thermal_zone_device *tzdev, - int *p_temp) -{ - struct mlx5_thermal *thermal = thermal_zone_device_priv(tzdev); - struct mlx5_core_dev *mdev = thermal->mdev; - int err; - - err = mlx5_thermal_get_mtmp_temp(mdev, MLX5_THERMAL_ASIC_SENSOR_INDEX, p_temp); - - if (err) - return err; - - /* The unit of temp returned is in 0.125 C. The thermal - * framework expects the value in 0.001 C. - */ - *p_temp *= 125; - - return 0; -} - -static struct thermal_zone_device_ops mlx5_thermal_ops = { - .get_temp = mlx5_thermal_get_temp, -}; - -int mlx5_thermal_init(struct mlx5_core_dev *mdev) -{ - char data[THERMAL_NAME_LENGTH]; - struct mlx5_thermal *thermal; - int err; - - if (!mlx5_core_is_pf(mdev) && !mlx5_core_is_ecpf(mdev)) - return 0; - - err = snprintf(data, sizeof(data), "mlx5_%s", dev_name(mdev->device)); - if (err < 0 || err >= sizeof(data)) { - mlx5_core_err(mdev, "Failed to setup thermal zone name, %d\n", err); - return -EINVAL; - } - - thermal = kzalloc(sizeof(*thermal), GFP_KERNEL); - if (!thermal) - return -ENOMEM; - - thermal->mdev = mdev; - thermal->tzdev = thermal_zone_device_register_with_trips(data, - NULL, - MLX5_THERMAL_NUM_TRIPS, - MLX5_THERMAL_TRIP_MASK, - thermal, - &mlx5_thermal_ops, - NULL, 0, MLX5_THERMAL_POLL_INT_MSEC); - if (IS_ERR(thermal->tzdev)) { - err = PTR_ERR(thermal->tzdev); - mlx5_core_err(mdev, "Failed to register thermal zone device (%s) %d\n", data, err); - kfree(thermal); - return err; - } - - mdev->thermal = thermal; - return 0; -} - -void mlx5_thermal_uninit(struct mlx5_core_dev *mdev) -{ - if (!mdev->thermal) - return; - - thermal_zone_device_unregister(mdev->thermal->tzdev); - kfree(mdev->thermal); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/thermal.h b/drivers/net/ethernet/mellanox/mlx5/core/thermal.h deleted file mode 100644 index 7d752c122192..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/thermal.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB - * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. - */ -#ifndef __MLX5_THERMAL_DRIVER_H -#define __MLX5_THERMAL_DRIVER_H - -#if IS_ENABLED(CONFIG_THERMAL) -int mlx5_thermal_init(struct mlx5_core_dev *mdev); -void mlx5_thermal_uninit(struct mlx5_core_dev *mdev); -#else -static inline int mlx5_thermal_init(struct mlx5_core_dev *mdev) -{ - mdev->thermal = NULL; - return 0; -} - -static inline void mlx5_thermal_uninit(struct mlx5_core_dev *mdev) { } -#endif - -#endif /* __MLX5_THERMAL_DRIVER_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3e1017d764b7..e1c7e502a4fc 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -134,6 +134,7 @@ enum { MLX5_REG_PCAM = 0x507f, MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, + MLX5_REG_MTCAP = 0x9009, MLX5_REG_MTMP = 0x900A, MLX5_REG_MCIA = 0x9014, MLX5_REG_MFRL = 0x9028, @@ -805,7 +806,7 @@ struct mlx5_core_dev { struct mlx5_rsc_dump *rsc_dump; u32 vsc_addr; struct mlx5_hv_vhca *hv_vhca; - struct mlx5_thermal *thermal; + struct mlx5_hwmon *hwmon; u64 num_block_tc; u64 num_block_ipsec; }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b3ad6b9852ec..87fd6f9ed82c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10196,7 +10196,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mrtc[0x1]; u8 regs_44_to_32[0xd]; - u8 regs_31_to_0[0x20]; + u8 regs_31_to_10[0x16]; + u8 mtmp[0x1]; + u8 regs_8_to_0[0x9]; }; struct mlx5_ifc_mcam_access_reg_bits1 { @@ -10949,6 +10951,15 @@ struct mlx5_ifc_mrtc_reg_bits { u8 time_l[0x20]; }; +struct mlx5_ifc_mtcap_reg_bits { + u8 reserved_at_0[0x19]; + u8 sensor_count[0x7]; + + u8 reserved_at_20[0x20]; + + u8 sensor_map[0x40]; +}; + struct mlx5_ifc_mtmp_reg_bits { u8 reserved_at_0[0x14]; u8 sensor_index[0xc]; @@ -11036,6 +11047,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mfrl_reg_bits mfrl_reg; struct mlx5_ifc_mtutc_reg_bits mtutc_reg; struct mlx5_ifc_mrtc_reg_bits mrtc_reg; + struct mlx5_ifc_mtcap_reg_bits mtcap_reg; struct mlx5_ifc_mtmp_reg_bits mtmp_reg; u8 reserved_at_0[0x60e0]; }; -- cgit v1.2.3 From 40b0425f8ba17c32cf7182975032a3999c364dfc Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 7 Aug 2023 22:33:19 +0300 Subject: net: ptp: create a mock-up PTP Hardware Clock driver There are several cases where virtual net devices may benefit from having a PTP clock, and these have to do with testing. I can see at least netdevsim and veth as potential users of a common mock-up PTP hardware clock driver. The proposed idea is to create an object which emulates PTP clock operations on top of the unadjustable CLOCK_MONOTONIC_RAW plus a software-controlled time domain via a timecounter/cyclecounter and then link that PHC to the netdevsim device. The driver is fully functional for its intended purpose, and it successfully passes the PTP selftests. $ cd tools/testing/selftests/ptp/ $ ./phc.sh /dev/ptp2 TEST: settime [ OK ] TEST: adjtime [ OK ] TEST: adjfreq [ OK ] Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230807193324.4128292-7-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 7 ++ drivers/ptp/Kconfig | 11 +++ drivers/ptp/Makefile | 1 + drivers/ptp/ptp_mock.c | 175 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/ptp_mock.h | 38 ++++++++++ 5 files changed, 232 insertions(+) create mode 100644 drivers/ptp/ptp_mock.c create mode 100644 include/linux/ptp_mock.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 6efcd8713682..49f032556cf1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17170,6 +17170,13 @@ F: drivers/ptp/* F: include/linux/ptp_cl* K: (?:\b|_)ptp(?:\b|_) +PTP MOCKUP CLOCK SUPPORT +M: Vladimir Oltean +L: netdev@vger.kernel.org +S: Maintained +F: drivers/ptp/ptp_mock.c +F: include/linux/ptp_mock.h + PTP VIRTUAL CLOCK SUPPORT M: Yangbo Lu L: netdev@vger.kernel.org diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index 32dff1b4f891..ed9d97a032f1 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -155,6 +155,17 @@ config PTP_1588_CLOCK_IDTCM To compile this driver as a module, choose M here: the module will be called ptp_clockmatrix. +config PTP_1588_CLOCK_MOCK + tristate "Mock-up PTP clock" + depends on PTP_1588_CLOCK + help + This driver offers a set of PTP clock manipulation operations over + the system monotonic time. It can be used by virtual network device + drivers to emulate PTP capabilities. + + To compile this driver as a module, choose M here: the module + will be called ptp_mock. + config PTP_1588_CLOCK_VMW tristate "VMware virtual PTP clock" depends on ACPI && HYPERVISOR_GUEST && X86 diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile index 553f18bf3c83..dea0cebd2303 100644 --- a/drivers/ptp/Makefile +++ b/drivers/ptp/Makefile @@ -16,6 +16,7 @@ ptp-qoriq-y += ptp_qoriq.o ptp-qoriq-$(CONFIG_DEBUG_FS) += ptp_qoriq_debugfs.o obj-$(CONFIG_PTP_1588_CLOCK_IDTCM) += ptp_clockmatrix.o obj-$(CONFIG_PTP_1588_CLOCK_IDT82P33) += ptp_idt82p33.o +obj-$(CONFIG_PTP_1588_CLOCK_MOCK) += ptp_mock.o obj-$(CONFIG_PTP_1588_CLOCK_VMW) += ptp_vmw.o obj-$(CONFIG_PTP_1588_CLOCK_OCP) += ptp_ocp.o obj-$(CONFIG_PTP_DFL_TOD) += ptp_dfl_tod.o diff --git a/drivers/ptp/ptp_mock.c b/drivers/ptp/ptp_mock.c new file mode 100644 index 000000000000..e7b459c846a2 --- /dev/null +++ b/drivers/ptp/ptp_mock.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright 2023 NXP + * + * Mock-up PTP Hardware Clock driver for virtual network devices + * + * Create a PTP clock which offers PTP time manipulation operations + * using a timecounter/cyclecounter on top of CLOCK_MONOTONIC_RAW. + */ + +#include +#include +#include + +/* Clamp scaled_ppm between -2,097,152,000 and 2,097,152,000, + * and thus "adj" between -68,719,476 and 68,719,476 + */ +#define MOCK_PHC_MAX_ADJ_PPB 32000000 +/* Timestamps from ktime_get_raw() have 1 ns resolution, so the scale factor + * (MULT >> SHIFT) needs to be 1. Pick SHIFT as 31 bits, which translates + * MULT(freq 0) into 0x80000000. + */ +#define MOCK_PHC_CC_SHIFT 31 +#define MOCK_PHC_CC_MULT (1 << MOCK_PHC_CC_SHIFT) +#define MOCK_PHC_FADJ_SHIFT 9 +#define MOCK_PHC_FADJ_DENOMINATOR 15625ULL + +/* The largest cycle_delta that timecounter_read_delta() can handle without a + * 64-bit overflow during the multiplication with cc->mult, given the max "adj" + * we permit, is ~8.3 seconds. Make sure readouts are more frequent than that. + */ +#define MOCK_PHC_REFRESH_INTERVAL (HZ * 5) + +#define info_to_phc(d) container_of((d), struct mock_phc, info) + +struct mock_phc { + struct ptp_clock_info info; + struct ptp_clock *clock; + struct timecounter tc; + struct cyclecounter cc; + spinlock_t lock; +}; + +static u64 mock_phc_cc_read(const struct cyclecounter *cc) +{ + return ktime_get_raw_ns(); +} + +static int mock_phc_adjfine(struct ptp_clock_info *info, long scaled_ppm) +{ + struct mock_phc *phc = info_to_phc(info); + s64 adj; + + adj = (s64)scaled_ppm << MOCK_PHC_FADJ_SHIFT; + adj = div_s64(adj, MOCK_PHC_FADJ_DENOMINATOR); + + spin_lock(&phc->lock); + timecounter_read(&phc->tc); + phc->cc.mult = MOCK_PHC_CC_MULT + adj; + spin_unlock(&phc->lock); + + return 0; +} + +static int mock_phc_adjtime(struct ptp_clock_info *info, s64 delta) +{ + struct mock_phc *phc = info_to_phc(info); + + spin_lock(&phc->lock); + timecounter_adjtime(&phc->tc, delta); + spin_unlock(&phc->lock); + + return 0; +} + +static int mock_phc_settime64(struct ptp_clock_info *info, + const struct timespec64 *ts) +{ + struct mock_phc *phc = info_to_phc(info); + u64 ns = timespec64_to_ns(ts); + + spin_lock(&phc->lock); + timecounter_init(&phc->tc, &phc->cc, ns); + spin_unlock(&phc->lock); + + return 0; +} + +static int mock_phc_gettime64(struct ptp_clock_info *info, struct timespec64 *ts) +{ + struct mock_phc *phc = info_to_phc(info); + u64 ns; + + spin_lock(&phc->lock); + ns = timecounter_read(&phc->tc); + spin_unlock(&phc->lock); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +static long mock_phc_refresh(struct ptp_clock_info *info) +{ + struct timespec64 ts; + + mock_phc_gettime64(info, &ts); + + return MOCK_PHC_REFRESH_INTERVAL; +} + +int mock_phc_index(struct mock_phc *phc) +{ + return ptp_clock_index(phc->clock); +} +EXPORT_SYMBOL_GPL(mock_phc_index); + +struct mock_phc *mock_phc_create(struct device *dev) +{ + struct mock_phc *phc; + int err; + + phc = kzalloc(sizeof(*phc), GFP_KERNEL); + if (!phc) { + err = -ENOMEM; + goto out; + } + + phc->info = (struct ptp_clock_info) { + .owner = THIS_MODULE, + .name = "Mock-up PTP clock", + .max_adj = MOCK_PHC_MAX_ADJ_PPB, + .adjfine = mock_phc_adjfine, + .adjtime = mock_phc_adjtime, + .gettime64 = mock_phc_gettime64, + .settime64 = mock_phc_settime64, + .do_aux_work = mock_phc_refresh, + }; + + phc->cc = (struct cyclecounter) { + .read = mock_phc_cc_read, + .mask = CYCLECOUNTER_MASK(64), + .mult = MOCK_PHC_CC_MULT, + .shift = MOCK_PHC_CC_SHIFT, + }; + + spin_lock_init(&phc->lock); + timecounter_init(&phc->tc, &phc->cc, 0); + + phc->clock = ptp_clock_register(&phc->info, dev); + if (IS_ERR(phc->clock)) { + err = PTR_ERR(phc->clock); + goto out_free_phc; + } + + ptp_schedule_worker(phc->clock, MOCK_PHC_REFRESH_INTERVAL); + + return phc; + +out_free_phc: + kfree(phc); +out: + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(mock_phc_create); + +void mock_phc_destroy(struct mock_phc *phc) +{ + ptp_clock_unregister(phc->clock); + kfree(phc); +} +EXPORT_SYMBOL_GPL(mock_phc_destroy); + +MODULE_DESCRIPTION("Mock-up PTP Hardware Clock driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/ptp_mock.h b/include/linux/ptp_mock.h new file mode 100644 index 000000000000..72eb401034d9 --- /dev/null +++ b/include/linux/ptp_mock.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Mock-up PTP Hardware Clock driver for virtual network devices + * + * Copyright 2023 NXP + */ + +#ifndef _PTP_MOCK_H_ +#define _PTP_MOCK_H_ + +struct device; +struct mock_phc; + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK_MOCK) + +struct mock_phc *mock_phc_create(struct device *dev); +void mock_phc_destroy(struct mock_phc *phc); +int mock_phc_index(struct mock_phc *phc); + +#else + +static inline struct mock_phc *mock_phc_create(struct device *dev) +{ + return NULL; +} + +static inline void mock_phc_destroy(struct mock_phc *phc) +{ +} + +static inline int mock_phc_index(struct mock_phc *phc) +{ + return -1; +} + +#endif + +#endif /* _PTP_MOCK_H_ */ -- cgit v1.2.3 From 1fc04a0b973392df5975901f56addc913d2c8f4d Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Mon, 7 Aug 2023 11:07:15 -0500 Subject: net: stmmac: add new mode parameter for fix_mac_speed A mode parameter has been added to the callback function of fix_mac_speed to indicate the physical layer type. The mode can be one the following: MLO_AN_PHY - Conventional PHY MLO_AN_FIXED - Fixed-link mode MLO_AN_INBAND - In-band protocol Signed-off-by: Shenwei Wang Link: https://lore.kernel.org/r/20230807160716.259072-2-shenwei.wang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c | 8 ++++---- drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- include/linux/stmmac.h | 2 +- 14 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 74c10373cc39..61ebf36da13d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -178,7 +178,7 @@ static void dwc_qos_remove(struct platform_device *pdev) #define AUTO_CAL_STATUS 0x880c #define AUTO_CAL_STATUS_ACTIVE BIT(31) -static void tegra_eqos_fix_speed(void *priv, unsigned int speed) +static void tegra_eqos_fix_speed(void *priv, unsigned int speed, unsigned int mode) { struct tegra_eqos *eqos = priv; unsigned long rate = 125000000; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index 645a9454a490..7c4f3ad88bdc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -178,7 +178,7 @@ static void imx_dwmac_exit(struct platform_device *pdev, void *priv) /* nothing to do now */ } -static void imx_dwmac_fix_speed(void *priv, unsigned int speed) +static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode) { struct plat_stmmacenet_data *plat_dat; struct imx_priv_data *dwmac = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c index a5e639ab0b9e..d352a14f9d48 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -22,13 +22,13 @@ struct intel_dwmac { }; struct intel_dwmac_data { - void (*fix_mac_speed)(void *priv, unsigned int speed); + void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode); unsigned long ptp_ref_clk_rate; unsigned long tx_clk_rate; bool tx_clk_en; }; -static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed) +static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) { struct intel_dwmac *dwmac = priv; unsigned long rate; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index e39406df8516..9b0200749109 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -257,7 +257,7 @@ static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac) return PTR_ERR_OR_ZERO(gmac->qsgmii_csr); } -static void ipq806x_gmac_fix_mac_speed(void *priv, unsigned int speed) +static void ipq806x_gmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) { struct ipq806x_gmac *gmac = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c index 7aa5e6bc04eb..959f88c6da16 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c @@ -22,7 +22,7 @@ struct meson_dwmac { void __iomem *reg; }; -static void meson6_dwmac_fix_mac_speed(void *priv, unsigned int speed) +static void meson6_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) { struct meson_dwmac *dwmac = priv; unsigned int val; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 5b3df27035ec..d3bf42d0fceb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -630,7 +630,7 @@ static int ethqos_configure(struct qcom_ethqos *ethqos) return ethqos->configure_func(ethqos); } -static void ethqos_fix_mac_speed(void *priv, unsigned int speed) +static void ethqos_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) { struct qcom_ethqos *ethqos = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 35789cb549f7..d920a50dd16c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1785,7 +1785,7 @@ static void rk_gmac_powerdown(struct rk_priv_data *gmac) gmac_clk_enable(gmac, false); } -static void rk_fix_speed(void *priv, unsigned int speed) +static void rk_fix_speed(void *priv, unsigned int speed, unsigned int mode) { struct rk_priv_data *bsp_priv = priv; struct device *dev = &bsp_priv->pdev->dev; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 6267bcb60206..7db176e8691f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -61,7 +61,7 @@ struct socfpga_dwmac { struct mdio_device *pcs_mdiodev; }; -static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) +static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) { struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)priv; void __iomem *splitter_base = dwmac->splitter_base; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c index b1c5f2527c0d..892612564694 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c @@ -24,7 +24,7 @@ struct starfive_dwmac { struct clk *clk_tx; }; -static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed) +static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) { struct starfive_dwmac *dwmac = priv; unsigned long rate; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index ef03e4669491..0d653bbb931b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -103,11 +103,11 @@ struct sti_dwmac { struct regmap *regmap; bool gmac_en; u32 speed; - void (*fix_retime_src)(void *priv, unsigned int speed); + void (*fix_retime_src)(void *priv, unsigned int speed, unsigned int mode); }; struct sti_dwmac_of_data { - void (*fix_retime_src)(void *priv, unsigned int speed); + void (*fix_retime_src)(void *priv, unsigned int speed, unsigned int mode); }; static u32 phy_intf_sels[] = { @@ -135,7 +135,7 @@ static u32 stih4xx_tx_retime_val[] = { | STIH4XX_ETH_SEL_INTERNAL_NOTEXT_PHYCLK, }; -static void stih4xx_fix_retime_src(void *priv, u32 spd) +static void stih4xx_fix_retime_src(void *priv, u32 spd, unsigned int mode) { struct sti_dwmac *dwmac = priv; u32 src = dwmac->tx_retime_src; @@ -187,7 +187,7 @@ static int sti_dwmac_set_mode(struct sti_dwmac *dwmac) val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII; regmap_update_bits(regmap, reg, ENMII_MASK, val); - dwmac->fix_retime_src(dwmac, dwmac->speed); + dwmac->fix_retime_src(dwmac, dwmac->speed, 0); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index 50963e91c347..beceeae579bf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -72,7 +72,7 @@ static void sun7i_gmac_exit(struct platform_device *pdev, void *priv) regulator_disable(gmac->regulator); } -static void sun7i_fix_speed(void *priv, unsigned int speed) +static void sun7i_fix_speed(void *priv, unsigned int speed, unsigned int mode) { struct sunxi_priv_data *gmac = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c index a8731ce0fff0..22d113fb8e09 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c @@ -54,7 +54,7 @@ struct visconti_eth { spinlock_t lock; /* lock to protect register update */ }; -static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed) +static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) { struct visconti_eth *dwmac = priv; struct net_device *netdev = dev_get_drvdata(dwmac->dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index fcab363d8dfa..351eca6109e0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1064,7 +1064,7 @@ static void stmmac_mac_link_up(struct phylink_config *config, priv->speed = speed; if (priv->plat->fix_mac_speed) - priv->plat->fix_mac_speed(priv->plat->bsp_priv, speed); + priv->plat->fix_mac_speed(priv->plat->bsp_priv, speed, mode); if (!duplex) ctrl &= ~priv->hw->link.duplex; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 652404c03944..784277d666eb 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -256,7 +256,7 @@ struct plat_stmmacenet_data { u8 tx_sched_algorithm; struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; - void (*fix_mac_speed)(void *priv, unsigned int speed); + void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode); int (*fix_soc_reset)(void *priv, void __iomem *ioaddr); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); -- cgit v1.2.3 From 1dcc03c9a7a824a31eaaecdfaa03542fb25feb6c Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 8 Aug 2023 23:04:34 +0200 Subject: net: phy: phy_device: Call into the PHY driver to set LED offload Linux LEDs can be requested to perform hardware accelerated blinking to indicate link, RX, TX etc. Pass the rules for blinking to the PHY driver, if it implements the ops needed to determine if a given pattern can be offloaded, to offload it, and what the current offload is. Additionally implement the op needed to get what device the LED is for. Reviewed-by: Simon Horman Signed-off-by: Andrew Lunn Tested-by: Daniel Golle Link: https://lore.kernel.org/r/20230808210436.838995-3-andrew@lunn.ch Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy_device.c | 68 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 33 +++++++++++++++++++++ 2 files changed, 101 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 3e9909b30938..17cb3e07216a 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3020,6 +3020,61 @@ static int phy_led_blink_set(struct led_classdev *led_cdev, return err; } +static __maybe_unused struct device * +phy_led_hw_control_get_device(struct led_classdev *led_cdev) +{ + struct phy_led *phyled = to_phy_led(led_cdev); + struct phy_device *phydev = phyled->phydev; + + if (phydev->attached_dev) + return &phydev->attached_dev->dev; + return NULL; +} + +static int __maybe_unused +phy_led_hw_control_get(struct led_classdev *led_cdev, + unsigned long *rules) +{ + struct phy_led *phyled = to_phy_led(led_cdev); + struct phy_device *phydev = phyled->phydev; + int err; + + mutex_lock(&phydev->lock); + err = phydev->drv->led_hw_control_get(phydev, phyled->index, rules); + mutex_unlock(&phydev->lock); + + return err; +} + +static int __maybe_unused +phy_led_hw_control_set(struct led_classdev *led_cdev, + unsigned long rules) +{ + struct phy_led *phyled = to_phy_led(led_cdev); + struct phy_device *phydev = phyled->phydev; + int err; + + mutex_lock(&phydev->lock); + err = phydev->drv->led_hw_control_set(phydev, phyled->index, rules); + mutex_unlock(&phydev->lock); + + return err; +} + +static __maybe_unused int phy_led_hw_is_supported(struct led_classdev *led_cdev, + unsigned long rules) +{ + struct phy_led *phyled = to_phy_led(led_cdev); + struct phy_device *phydev = phyled->phydev; + int err; + + mutex_lock(&phydev->lock); + err = phydev->drv->led_hw_is_supported(phydev, phyled->index, rules); + mutex_unlock(&phydev->lock); + + return err; +} + static void phy_leds_unregister(struct phy_device *phydev) { struct phy_led *phyled; @@ -3057,6 +3112,19 @@ static int of_phy_led(struct phy_device *phydev, cdev->brightness_set_blocking = phy_led_set_brightness; if (phydev->drv->led_blink_set) cdev->blink_set = phy_led_blink_set; + +#ifdef CONFIG_LEDS_TRIGGERS + if (phydev->drv->led_hw_is_supported && + phydev->drv->led_hw_control_set && + phydev->drv->led_hw_control_get) { + cdev->hw_control_is_supported = phy_led_hw_is_supported; + cdev->hw_control_set = phy_led_hw_control_set; + cdev->hw_control_get = phy_led_hw_control_get; + cdev->hw_control_trigger = "netdev"; + } + + cdev->hw_control_get_device = phy_led_hw_control_get_device; +#endif cdev->max_brightness = 1; init_data.devicename = dev_name(&phydev->mdio.dev); init_data.fwnode = of_fwnode_handle(led); diff --git a/include/linux/phy.h b/include/linux/phy.h index b963ce22e7c7..3c1ceedd1b77 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1105,6 +1105,39 @@ struct phy_driver { int (*led_blink_set)(struct phy_device *dev, u8 index, unsigned long *delay_on, unsigned long *delay_off); + /** + * @led_hw_is_supported: Can the HW support the given rules. + * @dev: PHY device which has the LED + * @index: Which LED of the PHY device + * @rules The core is interested in these rules + * + * Return 0 if yes, -EOPNOTSUPP if not, or an error code. + */ + int (*led_hw_is_supported)(struct phy_device *dev, u8 index, + unsigned long rules); + /** + * @led_hw_control_set: Set the HW to control the LED + * @dev: PHY device which has the LED + * @index: Which LED of the PHY device + * @rules The rules used to control the LED + * + * Returns 0, or a an error code. + */ + int (*led_hw_control_set)(struct phy_device *dev, u8 index, + unsigned long rules); + /** + * @led_hw_control_get: Get how the HW is controlling the LED + * @dev: PHY device which has the LED + * @index: Which LED of the PHY device + * @rules Pointer to the rules used to control the LED + * + * Set *@rules to how the HW is currently blinking. Returns 0 + * on success, or a error code if the current blinking cannot + * be represented in rules, or some other error happens. + */ + int (*led_hw_control_get)(struct phy_device *dev, u8 index, + unsigned long *rules); + }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) -- cgit v1.2.3 From 4a8d287909c905107d88a9835141ad592aedae75 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Wed, 9 Aug 2023 21:49:43 +0800 Subject: net: caif: Remove unused declaration cfsrvl_ctrlcmd() Commit 43e369210108 ("caif: Move refcount from service layer to sock and dev.") declared but never implemented this. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230809134943.37844-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/caif/cfsrvl.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/caif/cfsrvl.h b/include/net/caif/cfsrvl.h index bd5440977f7f..5ee7b322e18b 100644 --- a/include/net/caif/cfsrvl.h +++ b/include/net/caif/cfsrvl.h @@ -33,9 +33,6 @@ struct cflayer *cfrfml_create(u8 linkid, struct dev_info *dev_info, int mtu_size); struct cflayer *cfdbgl_create(u8 linkid, struct dev_info *dev_info); -void cfsrvl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, - int phyid); - bool cfsrvl_phyid_match(struct cflayer *layer, int phyid); void cfsrvl_init(struct cfsrvl *service, -- cgit v1.2.3 From afa2420cff5448eb225e88543e01b0b34b9a43cd Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Wed, 9 Aug 2023 22:23:23 +0800 Subject: sctp: Remove unused declaration sctp_backlog_migrate() Commit 61c9fed41638 ("[SCTP]: A better solution to fix the race between sctp_peeloff() and sctp_rcv().") removed the implementation but left declaration in place. Remove it. Signed-off-by: Yue Haibing Acked-by: Xin Long Link: https://lore.kernel.org/r/20230809142323.9428-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- include/net/sctp/sctp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 2a67100b2a17..a2310fa995f6 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -148,8 +148,6 @@ void sctp_icmp_redirect(struct sock *, struct sctp_transport *, void sctp_icmp_proto_unreachable(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t); -void sctp_backlog_migrate(struct sctp_association *assoc, - struct sock *oldsk, struct sock *newsk); int sctp_transport_hashtable_init(void); void sctp_transport_hashtable_destroy(void); int sctp_hash_transport(struct sctp_transport *t); -- cgit v1.2.3 From ac3899c6229649737b9d5cb86e417c98243883dc Mon Sep 17 00:00:00 2001 From: Shradha Gupta Date: Wed, 9 Aug 2023 21:15:22 -0700 Subject: net: mana: Add gdma stats to ethtool output for mana Extended performance counter stats in 'ethtool -S ' for MANA VF to include GDMA tx LSO packets and bytes count. Tested-on: Ubuntu22 Testcases: 1. LISA testcase: PERF-NETWORK-TCP-THROUGHPUT-MULTICONNECTION-NTTTCP-Synthetic 2. LISA testcase: PERF-NETWORK-TCP-THROUGHPUT-MULTICONNECTION-NTTTCP-SRIOV 3. Validated the GDMA stat packets and byte counters Signed-off-by: Shradha Gupta Reviewed-by: Pavan Chebbi Signed-off-by: David S. Miller --- drivers/net/ethernet/microsoft/mana/mana_en.c | 40 ++++++++++ drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 15 ++++ include/net/mana/mana.h | 87 ++++++++++++++++++++++ 3 files changed, 142 insertions(+) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 48f330d59284..4a16ebff3d1d 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -2295,6 +2295,46 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, return 0; } +void mana_query_gf_stats(struct mana_port_context *apc) +{ + struct mana_query_gf_stat_resp resp = {}; + struct mana_query_gf_stat_req req = {}; + struct net_device *ndev = apc->ndev; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT, + sizeof(req), sizeof(resp)); + req.req_stats = STATISTICS_FLAGS_HC_TX_BYTES | + STATISTICS_FLAGS_HC_TX_UCAST_PACKETS | + STATISTICS_FLAGS_HC_TX_UCAST_BYTES | + STATISTICS_FLAGS_HC_TX_MCAST_PACKETS | + STATISTICS_FLAGS_HC_TX_MCAST_BYTES | + STATISTICS_FLAGS_HC_TX_BCAST_PACKETS | + STATISTICS_FLAGS_HC_TX_BCAST_BYTES; + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + if (err) { + netdev_err(ndev, "Failed to query GF stats: %d\n", err); + return; + } + err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT, + sizeof(resp)); + if (err || resp.hdr.status) { + netdev_err(ndev, "Failed to query GF stats: %d, 0x%x\n", err, + resp.hdr.status); + return; + } + + apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes; + apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; + apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; + apc->eth_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; + apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; + apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; + apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; +} + static int mana_init_port(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index 0dc78679f620..607150165ab4 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -13,6 +13,19 @@ static const struct { } mana_eth_stats[] = { {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, + {"hc_tx_bytes", offsetof(struct mana_ethtool_stats, hc_tx_bytes)}, + {"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_stats, + hc_tx_ucast_pkts)}, + {"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_stats, + hc_tx_ucast_bytes)}, + {"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_stats, + hc_tx_bcast_pkts)}, + {"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_stats, + hc_tx_bcast_bytes)}, + {"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_stats, + hc_tx_mcast_pkts)}, + {"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_stats, + hc_tx_mcast_bytes)}, {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, tx_cqe_unknown_type)}, @@ -114,6 +127,8 @@ static void mana_get_ethtool_stats(struct net_device *ndev, if (!apc->port_is_up) return; + /* we call mana function to update stats from GDMA */ + mana_query_gf_stats(apc); for (q = 0; q < ARRAY_SIZE(mana_eth_stats); q++) data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 879990101c9f..9f70b4332238 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -352,6 +352,13 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; + u64 hc_tx_bytes; + u64 hc_tx_ucast_pkts; + u64 hc_tx_ucast_bytes; + u64 hc_tx_bcast_pkts; + u64 hc_tx_bcast_bytes; + u64 hc_tx_mcast_pkts; + u64 hc_tx_mcast_bytes; u64 tx_cqe_err; u64 tx_cqe_unknown_type; u64 rx_coalesced_err; @@ -442,6 +449,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); +void mana_query_gf_stats(struct mana_port_context *apc); extern const struct ethtool_ops mana_ethtool_ops; @@ -583,6 +591,49 @@ struct mana_fence_rq_resp { struct gdma_resp_hdr hdr; }; /* HW DATA */ +/* Query stats RQ */ +struct mana_query_gf_stat_req { + struct gdma_req_hdr hdr; + u64 req_stats; +}; /* HW DATA */ + +struct mana_query_gf_stat_resp { + struct gdma_resp_hdr hdr; + u64 reported_stats; + /* rx errors/discards */ + u64 discard_rx_nowqe; + u64 err_rx_vport_disabled; + /* rx bytes/packets */ + u64 hc_rx_bytes; + u64 hc_rx_ucast_pkts; + u64 hc_rx_ucast_bytes; + u64 hc_rx_bcast_pkts; + u64 hc_rx_bcast_bytes; + u64 hc_rx_mcast_pkts; + u64 hc_rx_mcast_bytes; + /* tx errors */ + u64 err_tx_gf_disabled; + u64 err_tx_vport_disabled; + u64 err_tx_inval_vport_offset_pkt; + u64 err_tx_vlan_enforcement; + u64 err_tx_ethtype_enforcement; + u64 err_tx_SA_enforecement; + u64 err_tx_SQPDID_enforcement; + u64 err_tx_CQPDID_enforcement; + u64 err_tx_mtu_violation; + u64 err_tx_inval_oob; + /* tx bytes/packets */ + u64 hc_tx_bytes; + u64 hc_tx_ucast_pkts; + u64 hc_tx_ucast_bytes; + u64 hc_tx_bcast_pkts; + u64 hc_tx_bcast_bytes; + u64 hc_tx_mcast_pkts; + u64 hc_tx_mcast_bytes; + /* tx error */ + u64 err_tx_gdma; +}; /* HW DATA */ + /* Configure vPort Rx Steering */ struct mana_cfg_rx_steer_req_v2 { struct gdma_req_hdr hdr; @@ -662,6 +713,42 @@ struct mana_deregister_filter_resp { struct gdma_resp_hdr hdr; }; /* HW DATA */ +/* Requested GF stats Flags */ +/* Rx discards/Errors */ +#define STATISTICS_FLAGS_RX_DISCARDS_NO_WQE 0x0000000000000001 +#define STATISTICS_FLAGS_RX_ERRORS_VPORT_DISABLED 0x0000000000000002 +/* Rx bytes/pkts */ +#define STATISTICS_FLAGS_HC_RX_BYTES 0x0000000000000004 +#define STATISTICS_FLAGS_HC_RX_UCAST_PACKETS 0x0000000000000008 +#define STATISTICS_FLAGS_HC_RX_UCAST_BYTES 0x0000000000000010 +#define STATISTICS_FLAGS_HC_RX_MCAST_PACKETS 0x0000000000000020 +#define STATISTICS_FLAGS_HC_RX_MCAST_BYTES 0x0000000000000040 +#define STATISTICS_FLAGS_HC_RX_BCAST_PACKETS 0x0000000000000080 +#define STATISTICS_FLAGS_HC_RX_BCAST_BYTES 0x0000000000000100 +/* Tx errors */ +#define STATISTICS_FLAGS_TX_ERRORS_GF_DISABLED 0x0000000000000200 +#define STATISTICS_FLAGS_TX_ERRORS_VPORT_DISABLED 0x0000000000000400 +#define STATISTICS_FLAGS_TX_ERRORS_INVAL_VPORT_OFFSET_PACKETS \ + 0x0000000000000800 +#define STATISTICS_FLAGS_TX_ERRORS_VLAN_ENFORCEMENT 0x0000000000001000 +#define STATISTICS_FLAGS_TX_ERRORS_ETH_TYPE_ENFORCEMENT \ + 0x0000000000002000 +#define STATISTICS_FLAGS_TX_ERRORS_SA_ENFORCEMENT 0x0000000000004000 +#define STATISTICS_FLAGS_TX_ERRORS_SQPDID_ENFORCEMENT 0x0000000000008000 +#define STATISTICS_FLAGS_TX_ERRORS_CQPDID_ENFORCEMENT 0x0000000000010000 +#define STATISTICS_FLAGS_TX_ERRORS_MTU_VIOLATION 0x0000000000020000 +#define STATISTICS_FLAGS_TX_ERRORS_INVALID_OOB 0x0000000000040000 +/* Tx bytes/pkts */ +#define STATISTICS_FLAGS_HC_TX_BYTES 0x0000000000080000 +#define STATISTICS_FLAGS_HC_TX_UCAST_PACKETS 0x0000000000100000 +#define STATISTICS_FLAGS_HC_TX_UCAST_BYTES 0x0000000000200000 +#define STATISTICS_FLAGS_HC_TX_MCAST_PACKETS 0x0000000000400000 +#define STATISTICS_FLAGS_HC_TX_MCAST_BYTES 0x0000000000800000 +#define STATISTICS_FLAGS_HC_TX_BCAST_PACKETS 0x0000000001000000 +#define STATISTICS_FLAGS_HC_TX_BCAST_BYTES 0x0000000002000000 +/* Tx error */ +#define STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR 0x0000000004000000 + #define MANA_MAX_NUM_QUEUES 64 #define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1) -- cgit v1.2.3 From ae75336131337f926d61b7fd86a0cca3146a7620 Mon Sep 17 00:00:00 2001 From: Claudia Draghicescu Date: Wed, 10 May 2023 16:45:57 +0300 Subject: Bluetooth: Check for ISO support in controller This patch checks for ISO_BROADCASTER and ISO_SYNC_RECEIVER in controller. Signed-off-by: Claudia Draghicescu Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci.h | 1 + include/net/bluetooth/hci_core.h | 1 + include/net/bluetooth/mgmt.h | 2 ++ net/bluetooth/mgmt.c | 6 ++++++ 4 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 872dcb91a540..ab2f8f1817cf 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -577,6 +577,7 @@ enum { #define HCI_LE_CIS_CENTRAL 0x10 #define HCI_LE_CIS_PERIPHERAL 0x20 #define HCI_LE_ISO_BROADCASTER 0x40 +#define HCI_LE_ISO_SYNC_RECEIVER 0x80 /* Connection modes */ #define HCI_CM_ACTIVE 0x0000 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index e01d52cb668c..da871581ef87 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1765,6 +1765,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define cis_peripheral_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL) #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER) +#define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ (!test_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &(dev)->quirks))) diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 5e68b3dd4422..d382679efd2b 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -111,6 +111,8 @@ struct mgmt_rp_read_index_list { #define MGMT_SETTING_WIDEBAND_SPEECH BIT(17) #define MGMT_SETTING_CIS_CENTRAL BIT(18) #define MGMT_SETTING_CIS_PERIPHERAL BIT(19) +#define MGMT_SETTING_ISO_BROADCASTER BIT(20) +#define MGMT_SETTING_ISO_SYNC_RECEIVER BIT(21) #define MGMT_OP_READ_INFO 0x0004 #define MGMT_READ_INFO_SIZE 0 diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d4498037fadc..4c352abe063b 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -944,6 +944,12 @@ static u32 get_current_settings(struct hci_dev *hdev) if (cis_peripheral_capable(hdev)) settings |= MGMT_SETTING_CIS_PERIPHERAL; + if (bis_capable(hdev)) + settings |= MGMT_SETTING_ISO_BROADCASTER; + + if (sync_recv_capable(hdev)) + settings |= MGMT_SETTING_ISO_SYNC_RECEIVER; + return settings; } -- cgit v1.2.3 From a0bfde167b506423111ddb8cd71930497a40fc54 Mon Sep 17 00:00:00 2001 From: Iulia Tanasescu Date: Tue, 30 May 2023 17:21:59 +0300 Subject: Bluetooth: ISO: Add support for connecting multiple BISes It is required for some configurations to have multiple BISes as part of the same BIG. Similar to the flow implemented for unicast, DEFER_SETUP will also be used to bind multiple BISes for the same BIG, before starting Periodic Advertising and creating the BIG. The user will have to open a new socket for each BIS. By setting the BT_DEFER_SETUP socket option and calling connect, a new connection will be added for the BIG and advertising handle set by the socket QoS parameters. Since all BISes will be bound for the same BIG and advertising handle, the socket QoS options and base parameters should match for all connections. By calling connect on a socket that does not have the BT_DEFER_SETUP option set, periodic advertising will be started and the BIG will be created, with a BIS for each previously bound connection. Since a BIG cannot be reconfigured with additional BISes after creation, no more connections can be bound for the BIG after the start periodic advertising and create BIG commands have been queued. The bis_cleanup function has also been updated, so that the advertising set and the BIG will not be terminated unless there are no more bound or connected BISes. The HCI_CONN_BIG_CREATED connection flag has been added to indicate that the BIG has been successfully created. This flag is checked at bis_cleanup, so that the BIG is only terminated if the HCI_LE_Create_BIG_Complete has been received. This implementation has been tested on hardware, using the "isotest" tool with an additional command line option, to specify the number of BISes to create as part of the desired BIG: tools/isotest -i hci0 -s 00:00:00:00:00:00 -N 2 -G 1 -T 1 The btmon log shows that a BIG containing 2 BISes has been created: < HCI Command: LE Create Broadcast Isochronous Group (0x08|0x0068) plen 31 Handle: 0x01 Advertising Handle: 0x01 Number of BIS: 2 SDU Interval: 10000 us (0x002710) Maximum SDU size: 40 Maximum Latency: 10 ms (0x000a) RTN: 0x02 PHY: LE 2M (0x02) Packing: Sequential (0x00) Framing: Unframed (0x00) Encryption: 0x00 Broadcast Code: 00000000000000000000000000000000 > HCI Event: Command Status (0x0f) plen 4 LE Create Broadcast Isochronous Group (0x08|0x0068) ncmd 1 Status: Success (0x00) > HCI Event: LE Meta Event (0x3e) plen 23 LE Broadcast Isochronous Group Complete (0x1b) Status: Success (0x00) Handle: 0x01 BIG Synchronization Delay: 1974 us (0x0007b6) Transport Latency: 1974 us (0x0007b6) PHY: LE 2M (0x02) NSE: 3 BN: 1 PTO: 1 IRC: 3 Maximum PDU: 40 ISO Interval: 10.00 msec (0x0008) Connection Handle #0: 10 Connection Handle #1: 11 < HCI Command: LE Setup Isochronous Data Path (0x08|0x006e) plen 13 Handle: 10 Data Path Direction: Input (Host to Controller) (0x00) Data Path: HCI (0x00) Coding Format: Transparent (0x03) Company Codec ID: Ericsson Technology Licensing (0) Vendor Codec ID: 0 Controller Delay: 0 us (0x000000) Codec Configuration Length: 0 Codec Configuration: > HCI Event: Command Complete (0x0e) plen 6 LE Setup Isochronous Data Path (0x08|0x006e) ncmd 1 Status: Success (0x00) Handle: 10 < HCI Command: LE Setup Isochronous Data Path (0x08|0x006e) plen 13 Handle: 11 Data Path Direction: Input (Host to Controller) (0x00) Data Path: HCI (0x00) Coding Format: Transparent (0x03) Company Codec ID: Ericsson Technology Licensing (0) Vendor Codec ID: 0 Controller Delay: 0 us (0x000000) Codec Configuration Length: 0 Codec Configuration: > HCI Event: Command Complete (0x0e) plen 6 LE Setup Isochronous Data Path (0x08|0x006e) ncmd 1 Status: Success (0x00) Handle: 11 < ISO Data TX: Handle 10 flags 0x02 dlen 44 < ISO Data TX: Handle 11 flags 0x02 dlen 44 > HCI Event: Number of Completed Packets (0x13) plen 5 Num handles: 1 Handle: 10 Count: 1 > HCI Event: Number of Completed Packets (0x13) plen 5 Num handles: 1 Handle: 11 Count: 1 Signed-off-by: Iulia Tanasescu Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 30 ++++++++ net/bluetooth/hci_conn.c | 152 +++++++++++++++++++++++++++------------ net/bluetooth/hci_event.c | 52 ++++++++------ net/bluetooth/iso.c | 28 ++++++-- 4 files changed, 189 insertions(+), 73 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index da871581ef87..c0bb58f1e86f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -974,6 +974,7 @@ enum { HCI_CONN_SCANNING, HCI_CONN_AUTH_FAILURE, HCI_CONN_PER_ADV, + HCI_CONN_BIG_CREATED, }; static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) @@ -1115,6 +1116,32 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, return NULL; } +static inline struct hci_conn * +hci_conn_hash_lookup_per_adv_bis(struct hci_dev *hdev, + bdaddr_t *ba, + __u8 big, __u8 bis) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (bacmp(&c->dst, ba) || c->type != ISO_LINK || + !test_bit(HCI_CONN_PER_ADV, &c->flags)) + continue; + + if (c->iso_qos.bcast.big == big && + c->iso_qos.bcast.bis == bis) { + rcu_read_unlock(); + return c; + } + } + rcu_read_unlock(); + + return NULL; +} + static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev, __u16 handle) { @@ -1351,6 +1378,9 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, __u16 setting, struct bt_codec *codec); struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos); +struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, + struct bt_iso_qos *qos, + __u8 base_len, __u8 *base); struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos); struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 76222565e2df..13c266dbee67 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -792,6 +792,7 @@ struct iso_list_data { }; int count; struct iso_cig_params pdu; + bool big_term; }; static void bis_list(struct hci_conn *conn, void *data) @@ -828,11 +829,8 @@ static int terminate_big_sync(struct hci_dev *hdev, void *data) hci_remove_ext_adv_instance_sync(hdev, d->bis, NULL); - /* Check if ISO connection is a BIS and terminate BIG if there are - * no other connections using it. - */ - hci_conn_hash_list_state(hdev, find_bis, ISO_LINK, BT_CONNECTED, d); - if (d->count) + /* Only terminate BIG if it has been created */ + if (!d->big_term) return 0; return hci_le_terminate_big_sync(hdev, d->big, @@ -844,19 +842,21 @@ static void terminate_big_destroy(struct hci_dev *hdev, void *data, int err) kfree(data); } -static int hci_le_terminate_big(struct hci_dev *hdev, u8 big, u8 bis) +static int hci_le_terminate_big(struct hci_dev *hdev, struct hci_conn *conn) { struct iso_list_data *d; int ret; - bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", big, bis); + bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", conn->iso_qos.bcast.big, + conn->iso_qos.bcast.bis); d = kzalloc(sizeof(*d), GFP_KERNEL); if (!d) return -ENOMEM; - d->big = big; - d->bis = bis; + d->big = conn->iso_qos.bcast.big; + d->bis = conn->iso_qos.bcast.bis; + d->big_term = test_and_clear_bit(HCI_CONN_BIG_CREATED, &conn->flags); ret = hci_cmd_sync_queue(hdev, terminate_big_sync, d, terminate_big_destroy); @@ -916,6 +916,7 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle) static void bis_cleanup(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; + struct hci_conn *bis; bt_dev_dbg(hdev, "conn %p", conn); @@ -923,8 +924,16 @@ static void bis_cleanup(struct hci_conn *conn) if (!test_and_clear_bit(HCI_CONN_PER_ADV, &conn->flags)) return; - hci_le_terminate_big(hdev, conn->iso_qos.bcast.big, - conn->iso_qos.bcast.bis); + /* Check if ISO connection is a BIS and terminate advertising + * set and BIG if there are no other connections using it. + */ + bis = hci_conn_hash_lookup_bis(hdev, BDADDR_ANY, + conn->iso_qos.bcast.big, + conn->iso_qos.bcast.bis); + if (bis) + return; + + hci_le_terminate_big(hdev, conn); } else { hci_le_big_terminate(hdev, conn->iso_qos.bcast.big, conn->sync_handle); @@ -1495,10 +1504,10 @@ static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos) /* This function requires the caller holds hdev->lock */ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst, - struct bt_iso_qos *qos) + struct bt_iso_qos *qos, __u8 base_len, + __u8 *base) { struct hci_conn *conn; - struct iso_list_data data; int err; /* Let's make sure that le is enabled.*/ @@ -1516,24 +1525,27 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst, if (err) return ERR_PTR(err); - data.big = qos->bcast.big; - data.bis = qos->bcast.bis; - data.count = 0; - - /* Check if there is already a matching BIG/BIS */ - hci_conn_hash_list_state(hdev, bis_list, ISO_LINK, BT_BOUND, &data); - if (data.count) + /* Check if the LE Create BIG command has already been sent */ + conn = hci_conn_hash_lookup_per_adv_bis(hdev, dst, qos->bcast.big, + qos->bcast.big); + if (conn) return ERR_PTR(-EADDRINUSE); - conn = hci_conn_hash_lookup_bis(hdev, dst, qos->bcast.big, qos->bcast.bis); - if (conn) + /* Check BIS settings against other bound BISes, since all + * BISes in a BIG must have the same value for all parameters + */ + conn = hci_conn_hash_lookup_bis(hdev, dst, qos->bcast.big, + qos->bcast.bis); + + if (conn && (memcmp(qos, &conn->iso_qos, sizeof(*qos)) || + base_len != conn->le_per_adv_data_len || + memcmp(conn->le_per_adv_data, base, base_len))) return ERR_PTR(-EADDRINUSE); conn = hci_conn_add(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); if (!conn) return ERR_PTR(-ENOMEM); - set_bit(HCI_CONN_PER_ADV, &conn->flags); conn->state = BT_CONNECT; hci_conn_hold(conn); @@ -1747,12 +1759,21 @@ static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos) { struct hci_dev *hdev = conn->hdev; struct hci_cp_le_create_big cp; + struct iso_list_data data; memset(&cp, 0, sizeof(cp)); + data.big = qos->bcast.big; + data.bis = qos->bcast.bis; + data.count = 0; + + /* Create a BIS for each bound connection */ + hci_conn_hash_list_state(hdev, bis_list, ISO_LINK, + BT_BOUND, &data); + cp.handle = qos->bcast.big; cp.adv_handle = qos->bcast.bis; - cp.num_bis = 0x01; + cp.num_bis = data.count; hci_cpu_to_le24(qos->bcast.out.interval, cp.bis.sdu_interval); cp.bis.sdu = cpu_to_le16(qos->bcast.out.sdu); cp.bis.latency = cpu_to_le16(qos->bcast.out.latency); @@ -2051,16 +2072,6 @@ static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn, qos->latency = conn->le_conn_latency; } -static void hci_bind_bis(struct hci_conn *conn, - struct bt_iso_qos *qos) -{ - /* Update LINK PHYs according to QoS preference */ - conn->le_tx_phy = qos->bcast.out.phy; - conn->le_tx_phy = qos->bcast.out.phy; - conn->iso_qos = *qos; - conn->state = BT_BOUND; -} - static int create_big_sync(struct hci_dev *hdev, void *data) { struct hci_conn *conn = data; @@ -2183,27 +2194,80 @@ static void create_big_complete(struct hci_dev *hdev, void *data, int err) } } -struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, - __u8 dst_type, struct bt_iso_qos *qos, - __u8 base_len, __u8 *base) +struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, + struct bt_iso_qos *qos, + __u8 base_len, __u8 *base) { struct hci_conn *conn; - int err; + __u8 eir[HCI_MAX_PER_AD_LENGTH]; + + if (base_len && base) + base_len = eir_append_service_data(eir, 0, 0x1851, + base, base_len); /* We need hci_conn object using the BDADDR_ANY as dst */ - conn = hci_add_bis(hdev, dst, qos); + conn = hci_add_bis(hdev, dst, qos, base_len, eir); if (IS_ERR(conn)) return conn; - hci_bind_bis(conn, qos); + /* Update LINK PHYs according to QoS preference */ + conn->le_tx_phy = qos->bcast.out.phy; + conn->le_tx_phy = qos->bcast.out.phy; /* Add Basic Announcement into Peridic Adv Data if BASE is set */ if (base_len && base) { - base_len = eir_append_service_data(conn->le_per_adv_data, 0, - 0x1851, base, base_len); + memcpy(conn->le_per_adv_data, eir, sizeof(eir)); conn->le_per_adv_data_len = base_len; } + hci_iso_qos_setup(hdev, conn, &qos->bcast.out, + conn->le_tx_phy ? conn->le_tx_phy : + hdev->le_tx_def_phys); + + conn->iso_qos = *qos; + conn->state = BT_BOUND; + + return conn; +} + +static void bis_mark_per_adv(struct hci_conn *conn, void *data) +{ + struct iso_list_data *d = data; + + /* Skip if not broadcast/ANY address */ + if (bacmp(&conn->dst, BDADDR_ANY)) + return; + + if (d->big != conn->iso_qos.bcast.big || + d->bis == BT_ISO_QOS_BIS_UNSET || + d->bis != conn->iso_qos.bcast.bis) + return; + + set_bit(HCI_CONN_PER_ADV, &conn->flags); +} + +struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, + __u8 dst_type, struct bt_iso_qos *qos, + __u8 base_len, __u8 *base) +{ + struct hci_conn *conn; + int err; + struct iso_list_data data; + + conn = hci_bind_bis(hdev, dst, qos, base_len, base); + if (IS_ERR(conn)) + return conn; + + data.big = qos->bcast.big; + data.bis = qos->bcast.bis; + + /* Set HCI_CONN_PER_ADV for all bound connections, to mark that + * the start periodic advertising and create BIG commands have + * been queued + */ + hci_conn_hash_list_state(hdev, bis_mark_per_adv, ISO_LINK, + BT_BOUND, &data); + /* Queue start periodic advertising and create BIG */ err = hci_cmd_sync_queue(hdev, create_big_sync, conn, create_big_complete); @@ -2212,10 +2276,6 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(err); } - hci_iso_qos_setup(hdev, conn, &qos->bcast.out, - conn->le_tx_phy ? conn->le_tx_phy : - hdev->le_tx_def_phys); - return conn; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 31ca320ce38d..86a7e4b3b98d 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6936,6 +6936,7 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, { struct hci_evt_le_create_big_complete *ev = data; struct hci_conn *conn; + __u8 bis_idx = 0; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); @@ -6944,33 +6945,44 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, return; hci_dev_lock(hdev); + rcu_read_lock(); - conn = hci_conn_hash_lookup_big(hdev, ev->handle); - if (!conn) - goto unlock; + /* Connect all BISes that are bound to the BIG */ + list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { + if (bacmp(&conn->dst, BDADDR_ANY) || + conn->type != ISO_LINK || + conn->iso_qos.bcast.big != ev->handle) + continue; - if (conn->type != ISO_LINK) { - bt_dev_err(hdev, - "Invalid connection link type handle 0x%2.2x", - ev->handle); - goto unlock; - } + conn->handle = __le16_to_cpu(ev->bis_handle[bis_idx++]); - if (ev->num_bis) - conn->handle = __le16_to_cpu(ev->bis_handle[0]); + if (!ev->status) { + conn->state = BT_CONNECTED; + set_bit(HCI_CONN_BIG_CREATED, &conn->flags); + rcu_read_unlock(); + hci_debugfs_create_conn(conn); + hci_conn_add_sysfs(conn); + hci_iso_setup_path(conn); + rcu_read_lock(); + continue; + } - if (!ev->status) { - conn->state = BT_CONNECTED; - hci_debugfs_create_conn(conn); - hci_conn_add_sysfs(conn); - hci_iso_setup_path(conn); - goto unlock; + hci_connect_cfm(conn, ev->status); + rcu_read_unlock(); + hci_conn_del(conn); + rcu_read_lock(); } - hci_connect_cfm(conn, ev->status); - hci_conn_del(conn); + if (!ev->status && !bis_idx) + /* If no BISes have been connected for the BIG, + * terminate. This is in case all bound connections + * have been closed before the BIG creation + * has completed. + */ + hci_le_terminate_big_sync(hdev, ev->handle, + HCI_ERROR_LOCAL_HOST_TERM); -unlock: + rcu_read_unlock(); hci_dev_unlock(hdev); } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 505d62247268..5808d57c1d7b 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -287,13 +287,24 @@ static int iso_connect_bis(struct sock *sk) goto unlock; } - hcon = hci_connect_bis(hdev, &iso_pi(sk)->dst, - le_addr_type(iso_pi(sk)->dst_type), - &iso_pi(sk)->qos, iso_pi(sk)->base_len, - iso_pi(sk)->base); - if (IS_ERR(hcon)) { - err = PTR_ERR(hcon); - goto unlock; + /* Just bind if DEFER_SETUP has been set */ + if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + hcon = hci_bind_bis(hdev, &iso_pi(sk)->dst, + &iso_pi(sk)->qos, iso_pi(sk)->base_len, + iso_pi(sk)->base); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; + } + } else { + hcon = hci_connect_bis(hdev, &iso_pi(sk)->dst, + le_addr_type(iso_pi(sk)->dst_type), + &iso_pi(sk)->qos, iso_pi(sk)->base_len, + iso_pi(sk)->base); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; + } } conn = iso_conn_add(hcon); @@ -317,6 +328,9 @@ static int iso_connect_bis(struct sock *sk) if (hcon->state == BT_CONNECTED) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; + } else if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + iso_sock_clear_timer(sk); + sk->sk_state = BT_CONNECT; } else { sk->sk_state = BT_CONNECT; iso_sock_set_timer(sk, sk->sk_sndtimeo); -- cgit v1.2.3 From 7f74563e6140e42b4ffae62adbef7a65967a3f98 Mon Sep 17 00:00:00 2001 From: Pauli Virtanen Date: Thu, 1 Jun 2023 09:34:46 +0300 Subject: Bluetooth: ISO: do not emit new LE Create CIS if previous is pending LE Create CIS command shall not be sent before all CIS Established events from its previous invocation have been processed. Currently it is sent via hci_sync but that only waits for the first event, but there can be multiple. Make it wait for all events, and simplify the CIS creation as follows: Add new flag HCI_CONN_CREATE_CIS, which is set if Create CIS has been sent for the connection but it is not yet completed. Make BT_CONNECT state to mean the connection wants Create CIS. On events after which new Create CIS may need to be sent, send it if possible and some connections need it. These events are: hci_connect_cis, iso_connect_cfm, hci_cs_le_create_cis, hci_le_cis_estabilished_evt. The Create CIS status/completion events shall queue new Create CIS only if at least one of the connections transitions away from BT_CONNECT, so that we don't loop if controller is sending bogus events. This fixes sending multiple CIS Create for the same CIS in the "ISO AC 6(i) - Success" BlueZ test case: < HCI Command: LE Create Co.. (0x08|0x0064) plen 9 #129 [hci0] Number of CIS: 2 CIS Handle: 257 ACL Handle: 42 CIS Handle: 258 ACL Handle: 42 > HCI Event: Command Status (0x0f) plen 4 #130 [hci0] LE Create Connected Isochronous Stream (0x08|0x0064) ncmd 1 Status: Success (0x00) > HCI Event: LE Meta Event (0x3e) plen 29 #131 [hci0] LE Connected Isochronous Stream Established (0x19) Status: Success (0x00) Connection Handle: 257 ... < HCI Command: LE Setup Is.. (0x08|0x006e) plen 13 #132 [hci0] ... > HCI Event: Command Complete (0x0e) plen 6 #133 [hci0] LE Setup Isochronous Data Path (0x08|0x006e) ncmd 1 ... < HCI Command: LE Create Co.. (0x08|0x0064) plen 5 #134 [hci0] Number of CIS: 1 CIS Handle: 258 ACL Handle: 42 > HCI Event: Command Status (0x0f) plen 4 #135 [hci0] LE Create Connected Isochronous Stream (0x08|0x0064) ncmd 1 Status: ACL Connection Already Exists (0x0b) > HCI Event: LE Meta Event (0x3e) plen 29 #136 [hci0] LE Connected Isochronous Stream Established (0x19) Status: Success (0x00) Connection Handle: 258 ... Fixes: c09b80be6ffc ("Bluetooth: hci_conn: Fix not waiting for HCI_EVT_LE_CIS_ESTABLISHED") Signed-off-by: Pauli Virtanen Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 4 +- include/net/bluetooth/hci_sync.h | 2 +- net/bluetooth/hci_conn.c | 74 ++++++++++++++------------------- net/bluetooth/hci_event.c | 25 +++++++++-- net/bluetooth/hci_sync.c | 90 ++++++++++++++++++++++++++++------------ net/bluetooth/iso.c | 2 +- 6 files changed, 119 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index c0bb58f1e86f..ad39d09e9bd6 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -975,6 +975,7 @@ enum { HCI_CONN_AUTH_FAILURE, HCI_CONN_PER_ADV, HCI_CONN_BIG_CREATED, + HCI_CONN_CREATE_CIS, }; static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) @@ -1351,7 +1352,8 @@ int hci_disconnect(struct hci_conn *conn, __u8 reason); bool hci_setup_sync(struct hci_conn *conn, __u16 handle); void hci_sco_setup(struct hci_conn *conn, __u8 status); bool hci_iso_setup_path(struct hci_conn *conn); -int hci_le_create_cis(struct hci_conn *conn); +int hci_le_create_cis_pending(struct hci_dev *hdev); +int hci_conn_check_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role); diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 2495be4d8b82..b516a0f4a55b 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -124,7 +124,7 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason); int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn); -int hci_le_create_cis_sync(struct hci_dev *hdev, struct hci_conn *conn); +int hci_le_create_cis_sync(struct hci_dev *hdev); int hci_le_remove_cig_sync(struct hci_dev *hdev, u8 handle); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 13c266dbee67..4b5223e62141 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1990,59 +1990,47 @@ bool hci_iso_setup_path(struct hci_conn *conn) return true; } -static int hci_create_cis_sync(struct hci_dev *hdev, void *data) +int hci_conn_check_create_cis(struct hci_conn *conn) { - return hci_le_create_cis_sync(hdev, data); -} + if (conn->type != ISO_LINK || !bacmp(&conn->dst, BDADDR_ANY)) + return -EINVAL; -int hci_le_create_cis(struct hci_conn *conn) -{ - struct hci_conn *cis; - struct hci_link *link, *t; - struct hci_dev *hdev = conn->hdev; - int err; + if (!conn->parent || conn->parent->state != BT_CONNECTED || + conn->state != BT_CONNECT || conn->handle == HCI_CONN_HANDLE_UNSET) + return 1; - bt_dev_dbg(hdev, "hcon %p", conn); + return 0; +} - switch (conn->type) { - case LE_LINK: - if (conn->state != BT_CONNECTED || list_empty(&conn->link_list)) - return -EINVAL; +static int hci_create_cis_sync(struct hci_dev *hdev, void *data) +{ + return hci_le_create_cis_sync(hdev); +} - cis = NULL; +int hci_le_create_cis_pending(struct hci_dev *hdev) +{ + struct hci_conn *conn; + bool pending = false; - /* hci_conn_link uses list_add_tail_rcu so the list is in - * the same order as the connections are requested. - */ - list_for_each_entry_safe(link, t, &conn->link_list, list) { - if (link->conn->state == BT_BOUND) { - err = hci_le_create_cis(link->conn); - if (err) - return err; + rcu_read_lock(); - cis = link->conn; - } + list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { + if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) { + rcu_read_unlock(); + return -EBUSY; } - return cis ? 0 : -EINVAL; - case ISO_LINK: - cis = conn; - break; - default: - return -EINVAL; + if (!hci_conn_check_create_cis(conn)) + pending = true; } - if (cis->state == BT_CONNECT) + rcu_read_unlock(); + + if (!pending) return 0; /* Queue Create CIS */ - err = hci_cmd_sync_queue(hdev, hci_create_cis_sync, cis, NULL); - if (err) - return err; - - cis->state = BT_CONNECT; - - return 0; + return hci_cmd_sync_queue(hdev, hci_create_cis_sync, NULL, NULL); } static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn, @@ -2317,11 +2305,9 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(-ENOLINK); } - /* If LE is already connected and CIS handle is already set proceed to - * Create CIS immediately. - */ - if (le->state == BT_CONNECTED && cis->handle != HCI_CONN_HANDLE_UNSET) - hci_le_create_cis(cis); + cis->state = BT_CONNECT; + + hci_le_create_cis_pending(hdev); return cis; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 86a7e4b3b98d..e7249ed3f5f2 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3810,6 +3810,7 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, struct hci_cp_le_set_cig_params *cp; struct hci_conn *conn; u8 status = rp->status; + bool pending = false; int i; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); @@ -3852,13 +3853,15 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "%p handle 0x%4.4x parent %p", conn, conn->handle, conn->parent); - - /* Create CIS if LE is already connected */ - if (conn->parent && conn->parent->state == BT_CONNECTED) - hci_le_create_cis(conn); + + if (conn->state == BT_CONNECT) + pending = true; } unlock: + if (pending) + hci_le_create_cis_pending(hdev); + hci_dev_unlock(hdev); return rp->status; @@ -4224,6 +4227,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, void *data, static void hci_cs_le_create_cis(struct hci_dev *hdev, u8 status) { struct hci_cp_le_create_cis *cp; + bool pending = false; int i; bt_dev_dbg(hdev, "status 0x%2.2x", status); @@ -4246,12 +4250,18 @@ static void hci_cs_le_create_cis(struct hci_dev *hdev, u8 status) conn = hci_conn_hash_lookup_handle(hdev, handle); if (conn) { + if (test_and_clear_bit(HCI_CONN_CREATE_CIS, + &conn->flags)) + pending = true; conn->state = BT_CLOSED; hci_connect_cfm(conn, status); hci_conn_del(conn); } } + if (pending) + hci_le_create_cis_pending(hdev); + hci_dev_unlock(hdev); } @@ -6790,6 +6800,7 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, struct hci_evt_le_cis_established *ev = data; struct hci_conn *conn; struct bt_iso_qos *qos; + bool pending = false; u16 handle = __le16_to_cpu(ev->handle); bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -6813,6 +6824,8 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, qos = &conn->iso_qos; + pending = test_and_clear_bit(HCI_CONN_CREATE_CIS, &conn->flags); + /* Convert ISO Interval (1.25 ms slots) to SDU Interval (us) */ qos->ucast.in.interval = le16_to_cpu(ev->interval) * 1250; qos->ucast.out.interval = qos->ucast.in.interval; @@ -6854,10 +6867,14 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, goto unlock; } + conn->state = BT_CLOSED; hci_connect_cfm(conn, ev->status); hci_conn_del(conn); unlock: + if (pending) + hci_le_create_cis_pending(hdev); + hci_dev_unlock(hdev); } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 4d1e32bb6a9c..b617d1dd247a 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6260,56 +6260,92 @@ done: return err; } -int hci_le_create_cis_sync(struct hci_dev *hdev, struct hci_conn *conn) +int hci_le_create_cis_sync(struct hci_dev *hdev) { struct { struct hci_cp_le_create_cis cp; struct hci_cis cis[0x1f]; } cmd; - u8 cig; - struct hci_conn *hcon = conn; + struct hci_conn *conn; + u8 cig = BT_ISO_QOS_CIG_UNSET; + + /* The spec allows only one pending LE Create CIS command at a time. If + * the command is pending now, don't do anything. We check for pending + * connections after each CIS Established event. + * + * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E + * page 2566: + * + * If the Host issues this command before all the + * HCI_LE_CIS_Established events from the previous use of the + * command have been generated, the Controller shall return the + * error code Command Disallowed (0x0C). + * + * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E + * page 2567: + * + * When the Controller receives the HCI_LE_Create_CIS command, the + * Controller sends the HCI_Command_Status event to the Host. An + * HCI_LE_CIS_Established event will be generated for each CIS when it + * is established or if it is disconnected or considered lost before + * being established; until all the events are generated, the command + * remains pending. + */ memset(&cmd, 0, sizeof(cmd)); - cmd.cis[0].acl_handle = cpu_to_le16(conn->parent->handle); - cmd.cis[0].cis_handle = cpu_to_le16(conn->handle); - cmd.cp.num_cis++; - cig = conn->iso_qos.ucast.cig; hci_dev_lock(hdev); rcu_read_lock(); + /* Wait until previous Create CIS has completed */ list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { - struct hci_cis *cis = &cmd.cis[cmd.cp.num_cis]; + if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) + goto done; + } - if (conn == hcon || conn->type != ISO_LINK || - conn->state == BT_CONNECTED || - conn->iso_qos.ucast.cig != cig) + /* Find CIG with all CIS ready */ + list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { + struct hci_conn *link; + + if (hci_conn_check_create_cis(conn)) continue; - /* Check if all CIS(s) belonging to a CIG are ready */ - if (!conn->parent || conn->parent->state != BT_CONNECTED || - conn->state != BT_CONNECT) { - cmd.cp.num_cis = 0; - break; + cig = conn->iso_qos.ucast.cig; + + list_for_each_entry_rcu(link, &hdev->conn_hash.list, list) { + if (hci_conn_check_create_cis(link) > 0 && + link->iso_qos.ucast.cig == cig && + link->state != BT_CONNECTED) { + cig = BT_ISO_QOS_CIG_UNSET; + break; + } } - /* Group all CIS with state BT_CONNECT since the spec don't - * allow to send them individually: - * - * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E - * page 2566: - * - * If the Host issues this command before all the - * HCI_LE_CIS_Established events from the previous use of the - * command have been generated, the Controller shall return the - * error code Command Disallowed (0x0C). - */ + if (cig != BT_ISO_QOS_CIG_UNSET) + break; + } + + if (cig == BT_ISO_QOS_CIG_UNSET) + goto done; + + list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { + struct hci_cis *cis = &cmd.cis[cmd.cp.num_cis]; + + if (hci_conn_check_create_cis(conn) || + conn->iso_qos.ucast.cig != cig) + continue; + + set_bit(HCI_CONN_CREATE_CIS, &conn->flags); cis->acl_handle = cpu_to_le16(conn->parent->handle); cis->cis_handle = cpu_to_le16(conn->handle); cmd.cp.num_cis++; + + if (cmd.cp.num_cis >= ARRAY_SIZE(cmd.cis)) + break; } +done: rcu_read_unlock(); hci_dev_unlock(hdev); diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 5808d57c1d7b..5db4d68c96d5 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1690,7 +1690,7 @@ static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) } /* Create CIS if pending */ - hci_le_create_cis(hcon); + hci_le_create_cis_pending(hcon->hdev); return; } -- cgit v1.2.3 From 6bfa273e533d7b25eee3d74e28a7fe8e6a8e7a93 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 25 May 2023 16:46:41 -0700 Subject: Bluetooth: Consolidate code around sk_alloc into a helper function This consolidates code around sk_alloc into bt_sock_alloc which does take care of common initialization. Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/bluetooth.h | 2 ++ net/bluetooth/af_bluetooth.c | 21 +++++++++++++++++++++ net/bluetooth/bnep/sock.c | 10 +--------- net/bluetooth/hci_sock.c | 10 ++-------- net/bluetooth/iso.c | 10 +--------- net/bluetooth/l2cap_sock.c | 10 +--------- net/bluetooth/rfcomm/sock.c | 13 +++---------- net/bluetooth/sco.c | 10 +--------- 8 files changed, 32 insertions(+), 54 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index af729859385e..60689a07b82c 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -400,6 +400,8 @@ int bt_sock_register(int proto, const struct net_proto_family *ops); void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); +struct sock *bt_sock_alloc(struct net *net, struct socket *sock, + struct proto *prot, int proto, gfp_t prio, int kern); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 1c3c7ff5c3c6..6035422e13da 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -140,6 +140,27 @@ static int bt_sock_create(struct net *net, struct socket *sock, int proto, return err; } +struct sock *bt_sock_alloc(struct net *net, struct socket *sock, + struct proto *prot, int proto, gfp_t prio, int kern) +{ + struct sock *sk; + + sk = sk_alloc(net, PF_BLUETOOTH, prio, prot, kern); + if (!sk) + return NULL; + + sock_init_data(sock, sk); + INIT_LIST_HEAD(&bt_sk(sk)->accept_q); + + sock_reset_flag(sk, SOCK_ZAPPED); + + sk->sk_protocol = proto; + sk->sk_state = BT_OPEN; + + return sk; +} +EXPORT_SYMBOL(bt_sock_alloc); + void bt_sock_link(struct bt_sock_list *l, struct sock *sk) { write_lock(&l->lock); diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index 57d509d77cb4..00d47bcf4d7d 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -205,21 +205,13 @@ static int bnep_sock_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &bnep_proto, kern); + sk = bt_sock_alloc(net, sock, &bnep_proto, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; - sock_init_data(sock, sk); - sock->ops = &bnep_sock_ops; - sock->state = SS_UNCONNECTED; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = protocol; - sk->sk_state = BT_OPEN; - bt_sock_link(&bnep_sk_list, sk); return 0; } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 1d249d839819..9c45586f5818 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -2143,18 +2143,12 @@ static int hci_sock_create(struct net *net, struct socket *sock, int protocol, sock->ops = &hci_sock_ops; - sk = sk_alloc(net, PF_BLUETOOTH, GFP_ATOMIC, &hci_sk_proto, kern); + sk = bt_sock_alloc(net, sock, &hci_sk_proto, protocol, GFP_ATOMIC, + kern); if (!sk) return -ENOMEM; - sock_init_data(sock, sk); - - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = protocol; - sock->state = SS_UNCONNECTED; - sk->sk_state = BT_OPEN; sk->sk_destruct = hci_sock_destruct; bt_sock_link(&hci_sk_list, sk); diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 5db4d68c96d5..84d238d0639a 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -738,21 +738,13 @@ static struct sock *iso_sock_alloc(struct net *net, struct socket *sock, { struct sock *sk; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &iso_proto, kern); + sk = bt_sock_alloc(net, sock, &iso_proto, proto, prio, kern); if (!sk) return NULL; - sock_init_data(sock, sk); - INIT_LIST_HEAD(&bt_sk(sk)->accept_q); - sk->sk_destruct = iso_sock_destruct; sk->sk_sndtimeo = ISO_CONN_TIMEOUT; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = proto; - sk->sk_state = BT_OPEN; - /* Set address type as public as default src address is BDADDR_ANY */ iso_pi(sk)->src_type = BDADDR_LE_PUBLIC; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 947ca580bb9a..9ef936f27a6a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1858,21 +1858,13 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, struct sock *sk; struct l2cap_chan *chan; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto, kern); + sk = bt_sock_alloc(net, sock, &l2cap_proto, proto, prio, kern); if (!sk) return NULL; - sock_init_data(sock, sk); - INIT_LIST_HEAD(&bt_sk(sk)->accept_q); - sk->sk_destruct = l2cap_sock_destruct; sk->sk_sndtimeo = L2CAP_CONN_TIMEOUT; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = proto; - sk->sk_state = BT_OPEN; - chan = l2cap_chan_create(); if (!chan) { sk_free(sk); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 4397e14ff560..b54e8a530f55 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -268,18 +268,16 @@ static struct proto rfcomm_proto = { .obj_size = sizeof(struct rfcomm_pinfo) }; -static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern) +static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, + int proto, gfp_t prio, int kern) { struct rfcomm_dlc *d; struct sock *sk; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &rfcomm_proto, kern); + sk = bt_sock_alloc(net, sock, &rfcomm_proto, proto, prio, kern); if (!sk) return NULL; - sock_init_data(sock, sk); - INIT_LIST_HEAD(&bt_sk(sk)->accept_q); - d = rfcomm_dlc_alloc(prio); if (!d) { sk_free(sk); @@ -298,11 +296,6 @@ static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int sk->sk_sndbuf = RFCOMM_MAX_CREDITS * RFCOMM_DEFAULT_MTU * 10; sk->sk_rcvbuf = RFCOMM_MAX_CREDITS * RFCOMM_DEFAULT_MTU * 10; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = proto; - sk->sk_state = BT_OPEN; - bt_sock_link(&rfcomm_sk_list, sk); BT_DBG("sk %p", sk); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 7762604ddfc0..ec6dce488a40 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -504,21 +504,13 @@ static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, { struct sock *sk; - sk = sk_alloc(net, PF_BLUETOOTH, prio, &sco_proto, kern); + sk = bt_sock_alloc(net, sock, &sco_proto, proto, prio, kern); if (!sk) return NULL; - sock_init_data(sock, sk); - INIT_LIST_HEAD(&bt_sk(sk)->accept_q); - sk->sk_destruct = sco_sock_destruct; sk->sk_sndtimeo = SCO_CONN_TIMEOUT; - sock_reset_flag(sk, SOCK_ZAPPED); - - sk->sk_protocol = proto; - sk->sk_state = BT_OPEN; - sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT; sco_pi(sk)->codec.id = BT_CODEC_CVSD; sco_pi(sk)->codec.cid = 0xffff; -- cgit v1.2.3 From 69ae5065061c53ded4f49e821646b9bc60ab302a Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 25 May 2023 16:46:43 -0700 Subject: Bluetooth: hci_sock: Forward credentials to monitor This stores scm_creds into hci_skb_cb so they can be properly forwarded to the likes of btmon which is then able to print information about the process who is originating the traffic: bluetoothd[35]: @ MGMT Command: Rea.. (0x0001) plen 0 {0x0001} @ MGMT Event: Command Complete (0x0001) plen 6 {0x0001} Read Management Version Information (0x0001) plen 3 bluetoothd[35]: < ACL Data T.. flags 0x00 dlen 41 ATT: Write Command (0x52) len 36 Handle: 0x0043 Type: ASE Control Point (0x2bc6) Data: 020203000110270000022800020a00409c0001000110270000022800020a00409c00 Opcode: QoS Configuration (0x02) Number of ASE(s): 2 ASE: #0 ASE ID: 0x03 CIG ID: 0x00 CIS ID: 0x01 SDU Interval: 10000 usec Framing: Unframed (0x00) PHY: 0x02 LE 2M PHY (0x02) Max SDU: 40 RTN: 2 Max Transport Latency: 10 Presentation Delay: 40000 us ASE: #1 ASE ID: 0x01 CIG ID: 0x00 CIS ID: 0x01 SDU Interval: 10000 usec Framing: Unframed (0x00) PHY: 0x02 LE 2M PHY (0x02) Max SDU: 40 RTN: 2 Max Transport Latency: 10 Presentation Delay: 40000 us Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/bluetooth.h | 1 + net/bluetooth/hci_sock.c | 67 +++++++++++++++++++++++++++++++++++++-- 2 files changed, 66 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 60689a07b82c..34998ae8ed78 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -471,6 +471,7 @@ struct bt_skb_cb { struct sco_ctrl sco; struct hci_ctrl hci; struct mgmt_ctrl mgmt; + struct scm_creds creds; }; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 9c45586f5818..5e4f718073b7 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -264,6 +264,53 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) kfree_skb(skb_copy); } +static void hci_sock_copy_creds(struct sock *sk, struct sk_buff *skb) +{ + struct scm_creds *creds; + + if (!sk || WARN_ON(!skb)) + return; + + creds = &bt_cb(skb)->creds; + + /* Check if peer credentials is set */ + if (!sk->sk_peer_pid) { + /* Check if parent peer credentials is set */ + if (bt_sk(sk)->parent && bt_sk(sk)->parent->sk_peer_pid) + sk = bt_sk(sk)->parent; + else + return; + } + + /* Check if scm_creds already set */ + if (creds->pid == pid_vnr(sk->sk_peer_pid)) + return; + + memset(creds, 0, sizeof(*creds)); + + creds->pid = pid_vnr(sk->sk_peer_pid); + if (sk->sk_peer_cred) { + creds->uid = sk->sk_peer_cred->uid; + creds->gid = sk->sk_peer_cred->gid; + } +} + +static struct sk_buff *hci_skb_clone(struct sk_buff *skb) +{ + struct sk_buff *nskb; + + if (!skb) + return NULL; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return NULL; + + hci_sock_copy_creds(skb->sk, nskb); + + return nskb; +} + /* Send frame to sockets with specific channel */ static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb, int flag, struct sock *skip_sk) @@ -289,7 +336,7 @@ static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb, if (hci_pi(sk)->channel != channel) continue; - nskb = skb_clone(skb, GFP_ATOMIC); + nskb = hci_skb_clone(skb); if (!nskb) continue; @@ -356,6 +403,8 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) if (!skb_copy) return; + hci_sock_copy_creds(skb->sk, skb_copy); + /* Put header before the data */ hdr = skb_push(skb_copy, HCI_MON_HDR_SIZE); hdr->opcode = opcode; @@ -531,10 +580,12 @@ static struct sk_buff *create_monitor_ctrl_open(struct sock *sk) return NULL; } - skb = bt_skb_alloc(14 + TASK_COMM_LEN , GFP_ATOMIC); + skb = bt_skb_alloc(14 + TASK_COMM_LEN, GFP_ATOMIC); if (!skb) return NULL; + hci_sock_copy_creds(sk, skb); + flags = hci_sock_test_flag(sk, HCI_SOCK_TRUSTED) ? 0x1 : 0x0; put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); @@ -580,6 +631,8 @@ static struct sk_buff *create_monitor_ctrl_close(struct sock *sk) if (!skb) return NULL; + hci_sock_copy_creds(sk, skb); + put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); __net_timestamp(skb); @@ -606,6 +659,8 @@ static struct sk_buff *create_monitor_ctrl_command(struct sock *sk, u16 index, if (!skb) return NULL; + hci_sock_copy_creds(sk, skb); + put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); put_unaligned_le16(opcode, skb_put(skb, 2)); @@ -638,6 +693,8 @@ send_monitor_note(struct sock *sk, const char *fmt, ...) if (!skb) return; + hci_sock_copy_creds(sk, skb); + va_start(args, fmt); vsprintf(skb_put(skb, len), fmt, args); *(u8 *)skb_put(skb, 1) = 0; @@ -1494,6 +1551,7 @@ static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { + struct scm_cookie scm; struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; @@ -1538,11 +1596,16 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, break; } + memset(&scm, 0, sizeof(scm)); + scm.creds = bt_cb(skb)->creds; + skb_free_datagram(sk, skb); if (flags & MSG_TRUNC) copied = skblen; + scm_recv(sock, msg, &scm, flags); + return err ? : copied; } -- cgit v1.2.3 From 6a42e9bfd17f7135d59701f93942a3392da482f4 Mon Sep 17 00:00:00 2001 From: Iulia Tanasescu Date: Mon, 19 Jun 2023 17:53:16 +0300 Subject: Bluetooth: ISO: Support multiple BIGs This adds support for creating multiple BIGs. According to spec, each BIG shall have an unique handle, and each BIG should be associated with a different advertising handle. Otherwise, the LE Create BIG command will fail, with error code Command Disallowed (for reusing a BIG handle), or Unknown Advertising Identifier (for reusing an advertising handle). The btmon snippet below shows an exercise for creating two BIGs for the same controller, by opening two isotest instances with the following command: tools/isotest -i hci0 -s 00:00:00:00:00:00 < HCI Command: LE Create Broadcast Isochronous Group (0x08|0x0068) plen 31 Handle: 0x00 Advertising Handle: 0x01 Number of BIS: 1 SDU Interval: 10000 us (0x002710) Maximum SDU size: 40 Maximum Latency: 10 ms (0x000a) RTN: 0x02 PHY: LE 2M (0x02) Packing: Sequential (0x00) Framing: Unframed (0x00) Encryption: 0x00 Broadcast Code: 00000000000000000000000000000000 > HCI Event: Command Status (0x0f) plen 4 LE Create Broadcast Isochronous Group (0x08|0x0068) ncmd 1 Status: Success (0x00) > HCI Event: LE Meta Event (0x3e) plen 21 LE Broadcast Isochronous Group Complete (0x1b) Status: Success (0x00) Handle: 0x00 BIG Synchronization Delay: 912 us (0x000390) Transport Latency: 912 us (0x000390) PHY: LE 2M (0x02) NSE: 3 BN: 1 PTO: 1 IRC: 3 Maximum PDU: 40 ISO Interval: 10.00 msec (0x0008) Connection Handle #0: 10 < HCI Command: LE Create Broadcast Isochronous Group (0x08|0x0068) Handle: 0x01 Advertising Handle: 0x02 Number of BIS: 1 SDU Interval: 10000 us (0x002710) Maximum SDU size: 40 Maximum Latency: 10 ms (0x000a) RTN: 0x02 PHY: LE 2M (0x02) Packing: Sequential (0x00) Framing: Unframed (0x00) Encryption: 0x00 Broadcast Code: 00000000000000000000000000000000 > HCI Event: Command Status (0x0f) plen 4 LE Create Broadcast Isochronous Group (0x08|0x0068) ncmd 1 Status: Success (0x00) Signed-off-by: Iulia Tanasescu Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 5 ++--- net/bluetooth/hci_conn.c | 40 +++++++++++++++++----------------------- net/bluetooth/hci_event.c | 35 +++++++++++++++++++++++++++++------ net/bluetooth/hci_sync.c | 28 +++++++++++++++------------- 4 files changed, 63 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index ad39d09e9bd6..9140d4a80e38 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1095,8 +1095,7 @@ static inline __u8 hci_conn_lookup_type(struct hci_dev *hdev, __u16 handle) } static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, - bdaddr_t *ba, - __u8 big, __u8 bis) + bdaddr_t *ba, __u8 bis) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; @@ -1107,7 +1106,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, if (bacmp(&c->dst, ba) || c->type != ISO_LINK) continue; - if (c->iso_qos.bcast.big == big && c->iso_qos.bcast.bis == bis) { + if (c->iso_qos.bcast.bis == bis) { rcu_read_unlock(); return c; } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 4b5223e62141..0f89daafe194 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -927,9 +927,7 @@ static void bis_cleanup(struct hci_conn *conn) /* Check if ISO connection is a BIS and terminate advertising * set and BIG if there are no other connections using it. */ - bis = hci_conn_hash_lookup_bis(hdev, BDADDR_ANY, - conn->iso_qos.bcast.big, - conn->iso_qos.bcast.bis); + bis = hci_conn_hash_lookup_big(hdev, conn->iso_qos.bcast.big); if (bis) return; @@ -1449,25 +1447,23 @@ static int hci_explicit_conn_params_set(struct hci_dev *hdev, static int qos_set_big(struct hci_dev *hdev, struct bt_iso_qos *qos) { - struct iso_list_data data; + struct hci_conn *conn; + u8 big; /* Allocate a BIG if not set */ if (qos->bcast.big == BT_ISO_QOS_BIG_UNSET) { - for (data.big = 0x00; data.big < 0xef; data.big++) { - data.count = 0; - data.bis = 0xff; + for (big = 0x00; big < 0xef; big++) { - hci_conn_hash_list_state(hdev, bis_list, ISO_LINK, - BT_BOUND, &data); - if (!data.count) + conn = hci_conn_hash_lookup_big(hdev, big); + if (!conn) break; } - if (data.big == 0xef) + if (big == 0xef) return -EADDRNOTAVAIL; /* Update BIG */ - qos->bcast.big = data.big; + qos->bcast.big = big; } return 0; @@ -1475,28 +1471,27 @@ static int qos_set_big(struct hci_dev *hdev, struct bt_iso_qos *qos) static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos) { - struct iso_list_data data; + struct hci_conn *conn; + u8 bis; /* Allocate BIS if not set */ if (qos->bcast.bis == BT_ISO_QOS_BIS_UNSET) { /* Find an unused adv set to advertise BIS, skip instance 0x00 * since it is reserved as general purpose set. */ - for (data.bis = 0x01; data.bis < hdev->le_num_of_adv_sets; - data.bis++) { - data.count = 0; + for (bis = 0x01; bis < hdev->le_num_of_adv_sets; + bis++) { - hci_conn_hash_list_state(hdev, bis_list, ISO_LINK, - BT_BOUND, &data); - if (!data.count) + conn = hci_conn_hash_lookup_bis(hdev, BDADDR_ANY, bis); + if (!conn) break; } - if (data.bis == hdev->le_num_of_adv_sets) + if (bis == hdev->le_num_of_adv_sets) return -EADDRNOTAVAIL; /* Update BIS */ - qos->bcast.bis = data.bis; + qos->bcast.bis = bis; } return 0; @@ -1534,8 +1529,7 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst, /* Check BIS settings against other bound BISes, since all * BISes in a BIG must have the same value for all parameters */ - conn = hci_conn_hash_lookup_bis(hdev, dst, qos->bcast.big, - qos->bcast.bis); + conn = hci_conn_hash_lookup_big(hdev, qos->bcast.big); if (conn && (memcmp(qos, &conn->iso_qos, sizeof(*qos)) || base_len != conn->le_per_adv_data_len || diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index e7249ed3f5f2..c67612c99f89 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1639,7 +1639,7 @@ static u8 hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, void *data, hci_dev_set_flag(hdev, HCI_LE_ADV); - if (adv) + if (adv && !adv->periodic) adv->enabled = true; conn = hci_lookup_le_connect(hdev); @@ -3941,24 +3941,47 @@ static u8 hci_cc_le_set_per_adv_enable(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; - __u8 *sent; + struct hci_cp_le_set_per_adv_enable *cp; + struct adv_info *adv = NULL, *n; + u8 per_adv_cnt = 0; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; - sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_PER_ADV_ENABLE); - if (!sent) + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_PER_ADV_ENABLE); + if (!cp) return rp->status; hci_dev_lock(hdev); - if (*sent) + adv = hci_find_adv_instance(hdev, cp->handle); + + if (cp->enable) { hci_dev_set_flag(hdev, HCI_LE_PER_ADV); - else + + if (adv) + adv->enabled = true; + } else { + /* If just one instance was disabled check if there are + * any other instance enabled before clearing HCI_LE_PER_ADV. + * The current periodic adv instance will be marked as + * disabled once extended advertising is also disabled. + */ + list_for_each_entry_safe(adv, n, &hdev->adv_instances, + list) { + if (adv->periodic && adv->enabled) + per_adv_cnt++; + } + + if (per_adv_cnt > 1) + goto unlock; + hci_dev_clear_flag(hdev, HCI_LE_PER_ADV); + } +unlock: hci_dev_unlock(hdev); return rp->status; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index b617d1dd247a..afb8e970e62c 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -3,6 +3,7 @@ * BlueZ - Bluetooth protocol stack for Linux * * Copyright (C) 2021 Intel Corporation + * Copyright 2023 NXP */ #include @@ -1319,9 +1320,11 @@ int hci_start_ext_adv_sync(struct hci_dev *hdev, u8 instance) static int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance) { struct hci_cp_le_set_per_adv_enable cp; + struct adv_info *adv = NULL; /* If periodic advertising already disabled there is nothing to do. */ - if (!hci_dev_test_flag(hdev, HCI_LE_PER_ADV)) + adv = hci_find_adv_instance(hdev, instance); + if (!adv || !adv->periodic || !adv->enabled) return 0; memset(&cp, 0, sizeof(cp)); @@ -1386,9 +1389,11 @@ static int hci_set_per_adv_data_sync(struct hci_dev *hdev, u8 instance) static int hci_enable_per_advertising_sync(struct hci_dev *hdev, u8 instance) { struct hci_cp_le_set_per_adv_enable cp; + struct adv_info *adv = NULL; /* If periodic advertising already enabled there is nothing to do. */ - if (hci_dev_test_flag(hdev, HCI_LE_PER_ADV)) + adv = hci_find_adv_instance(hdev, instance); + if (adv && adv->periodic && adv->enabled) return 0; memset(&cp, 0, sizeof(cp)); @@ -1458,22 +1463,19 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len, sync_interval); if (IS_ERR(adv)) return PTR_ERR(adv); + adv->pending = false; added = true; } } - /* Only start advertising if instance 0 or if a dedicated instance has - * been added. - */ - if (!adv || added) { - err = hci_start_ext_adv_sync(hdev, instance); - if (err < 0) - goto fail; + /* Start advertising */ + err = hci_start_ext_adv_sync(hdev, instance); + if (err < 0) + goto fail; - err = hci_adv_bcast_annoucement(hdev, adv); - if (err < 0) - goto fail; - } + err = hci_adv_bcast_annoucement(hdev, adv); + if (err < 0) + goto fail; err = hci_set_per_adv_params_sync(hdev, instance, min_interval, max_interval); -- cgit v1.2.3 From 9e14606d8f38ea52a38c27692a9c1513c987a5da Mon Sep 17 00:00:00 2001 From: Hilda Wu Date: Wed, 21 Jun 2023 18:00:31 +0800 Subject: Bluetooth: msft: Extended monitor tracking by address filter Since limited tracking device per condition, this feature is to support tracking multiple devices concurrently. When a pattern monitor detects the device, this feature issues an address monitor for tracking that device. Let pattern monitor can keep monitor new devices. This feature adds an address filter when receiving a LE monitor device event which monitor handle is for a pattern, and the controller started monitoring the device. And this feature also has cancelled the monitor advertisement from address filters when receiving a LE monitor device event when the controller stopped monitoring the device specified by an address and monitor handle. Below is an example to know the feature adds the address filter. //Add MSFT pattern monitor < HCI Command: Vendor (0x3f|0x00f0) plen 14 #142 [hci0] 55.552420 03 b8 a4 03 ff 01 01 06 09 05 5f 52 45 46 .........._REF > HCI Event: Command Complete (0x0e) plen 6 #143 [hci0] 55.653960 Vendor (0x3f|0x00f0) ncmd 2 Status: Success (0x00) 03 00 //Got event from the pattern monitor > HCI Event: Vendor (0xff) plen 18 #148 [hci0] 58.384953 23 79 54 33 77 88 97 68 02 00 fb c1 29 eb 27 b8 #yT3w..h....).'. 00 01 .. //Add MSFT address monitor (Sample address: B8:27:EB:29:C1:FB) < HCI Command: Vendor (0x3f|0x00f0) plen 13 #149 [hci0] 58.385067 03 b8 a4 03 ff 04 00 fb c1 29 eb 27 b8 .........).'. //Report to userspace about found device (ADV Monitor Device Found) @ MGMT Event: Unknown (0x002f) plen 38 {0x0003} [hci0] 58.680042 01 00 fb c1 29 eb 27 b8 01 ce 00 00 00 00 16 00 ....).'......... 0a 09 4b 45 59 42 44 5f 52 45 46 02 01 06 03 19 ..KEYBD_REF..... c1 03 03 03 12 18 ...... //Got event from address monitor > HCI Event: Vendor (0xff) plen 18 #152 [hci0] 58.672956 23 79 54 33 77 88 97 68 02 00 fb c1 29 eb 27 b8 #yT3w..h....).'. 01 01 Signed-off-by: Alex Lu Signed-off-by: Hilda Wu Reviewed-by: Simon Horman Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btrtl.c | 4 + include/net/bluetooth/hci.h | 10 ++ net/bluetooth/msft.c | 412 ++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 411 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 04399b3c39a0..ddae6524106d 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -1269,6 +1269,10 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) if (btrtl_dev->project_id == CHIP_ID_8852C) btrealtek_set_flag(hdev, REALTEK_ALT6_CONTINUOUS_TX_CHIP); + if (btrtl_dev->project_id == CHIP_ID_8852A || + btrtl_dev->project_id == CHIP_ID_8852C) + set_bit(HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, &hdev->quirks); + hci_set_aosp_capable(hdev); break; default: diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index ab2f8f1817cf..5723405b833e 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -309,6 +309,16 @@ enum { * to support it. */ HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT, + + /* When this quirk is set, MSFT extension monitor tracking by + * address filter is supported. Since tracking quantity of each + * pattern is limited, this feature supports tracking multiple + * devices concurrently if controller supports multiple + * address filters. + * + * This quirk must be set before hci_register_dev is called. + */ + HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, }; /* HCI device flags */ diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index bf5cee48916c..b80a2162a5c3 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -91,6 +91,33 @@ struct msft_ev_le_monitor_device { struct msft_monitor_advertisement_handle_data { __u8 msft_handle; __u16 mgmt_handle; + __s8 rssi_high; + __s8 rssi_low; + __u8 rssi_low_interval; + __u8 rssi_sampling_period; + __u8 cond_type; + struct list_head list; +}; + +enum monitor_addr_filter_state { + AF_STATE_IDLE, + AF_STATE_ADDING, + AF_STATE_ADDED, + AF_STATE_REMOVING, +}; + +#define MSFT_MONITOR_ADVERTISEMENT_TYPE_ADDR 0x04 +struct msft_monitor_addr_filter_data { + __u8 msft_handle; + __u8 pattern_handle; /* address filters pertain to */ + __u16 mgmt_handle; + int state; + __s8 rssi_high; + __s8 rssi_low; + __u8 rssi_low_interval; + __u8 rssi_sampling_period; + __u8 addr_type; + bdaddr_t bdaddr; struct list_head list; }; @@ -99,9 +126,12 @@ struct msft_data { __u8 evt_prefix_len; __u8 *evt_prefix; struct list_head handle_map; + struct list_head address_filters; __u8 resuming; __u8 suspending; __u8 filter_enabled; + /* To synchronize add/remove address filter and monitor device event.*/ + struct mutex filter_lock; }; bool msft_monitor_supported(struct hci_dev *hdev) @@ -180,6 +210,24 @@ static struct msft_monitor_advertisement_handle_data *msft_find_handle_data return NULL; } +/* This function requires the caller holds msft->filter_lock */ +static struct msft_monitor_addr_filter_data *msft_find_address_data + (struct hci_dev *hdev, u8 addr_type, bdaddr_t *addr, + u8 pattern_handle) +{ + struct msft_monitor_addr_filter_data *entry; + struct msft_data *msft = hdev->msft_data; + + list_for_each_entry(entry, &msft->address_filters, list) { + if (entry->pattern_handle == pattern_handle && + addr_type == entry->addr_type && + !bacmp(addr, &entry->bdaddr)) + return entry; + } + + return NULL; +} + /* This function requires the caller holds hdev->lock */ static int msft_monitor_device_del(struct hci_dev *hdev, __u16 mgmt_handle, bdaddr_t *bdaddr, __u8 addr_type, @@ -240,6 +288,7 @@ static int msft_le_monitor_advertisement_cb(struct hci_dev *hdev, u16 opcode, handle_data->mgmt_handle = monitor->handle; handle_data->msft_handle = rp->handle; + handle_data->cond_type = MSFT_MONITOR_ADVERTISEMENT_TYPE_PATTERN; INIT_LIST_HEAD(&handle_data->list); list_add(&handle_data->list, &msft->handle_map); @@ -254,6 +303,70 @@ unlock: return status; } +/* This function requires the caller holds hci_req_sync_lock */ +static void msft_remove_addr_filters_sync(struct hci_dev *hdev, u8 handle) +{ + struct msft_monitor_addr_filter_data *address_filter, *n; + struct msft_cp_le_cancel_monitor_advertisement cp; + struct msft_data *msft = hdev->msft_data; + struct list_head head; + struct sk_buff *skb; + + INIT_LIST_HEAD(&head); + + /* Cancel all corresponding address monitors */ + mutex_lock(&msft->filter_lock); + + list_for_each_entry_safe(address_filter, n, &msft->address_filters, + list) { + if (address_filter->pattern_handle != handle) + continue; + + list_del(&address_filter->list); + + /* Keep the address filter and let + * msft_add_address_filter_sync() remove and free the address + * filter. + */ + if (address_filter->state == AF_STATE_ADDING) { + address_filter->state = AF_STATE_REMOVING; + continue; + } + + /* Keep the address filter and let + * msft_cancel_address_filter_sync() remove and free the address + * filter + */ + if (address_filter->state == AF_STATE_REMOVING) + continue; + + list_add_tail(&address_filter->list, &head); + } + + mutex_unlock(&msft->filter_lock); + + list_for_each_entry_safe(address_filter, n, &head, list) { + list_del(&address_filter->list); + + cp.sub_opcode = MSFT_OP_LE_CANCEL_MONITOR_ADVERTISEMENT; + cp.handle = address_filter->msft_handle; + + skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, + HCI_CMD_TIMEOUT); + if (IS_ERR_OR_NULL(skb)) { + kfree(address_filter); + continue; + } + + kfree_skb(skb); + + bt_dev_dbg(hdev, "MSFT: Canceled device %pMR address filter", + &address_filter->bdaddr); + + kfree(address_filter); + } +} + static int msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev, u16 opcode, struct adv_monitor *monitor, @@ -263,6 +376,7 @@ static int msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev, struct msft_monitor_advertisement_handle_data *handle_data; struct msft_data *msft = hdev->msft_data; int status = 0; + u8 msft_handle; rp = (struct msft_rp_le_cancel_monitor_advertisement *)skb->data; if (skb->len < sizeof(*rp)) { @@ -293,11 +407,17 @@ static int msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev, NULL, 0, false); } + msft_handle = handle_data->msft_handle; + list_del(&handle_data->list); kfree(handle_data); - } - hci_dev_unlock(hdev); + hci_dev_unlock(hdev); + + msft_remove_addr_filters_sync(hdev, msft_handle); + } else { + hci_dev_unlock(hdev); + } done: return status; @@ -394,12 +514,14 @@ static int msft_add_monitor_sync(struct hci_dev *hdev, { struct msft_cp_le_monitor_advertisement *cp; struct msft_le_monitor_advertisement_pattern_data *pattern_data; + struct msft_monitor_advertisement_handle_data *handle_data; struct msft_le_monitor_advertisement_pattern *pattern; struct adv_pattern *entry; size_t total_size = sizeof(*cp) + sizeof(*pattern_data); ptrdiff_t offset = 0; u8 pattern_count = 0; struct sk_buff *skb; + int err; if (!msft_monitor_pattern_valid(monitor)) return -EINVAL; @@ -436,16 +558,31 @@ static int msft_add_monitor_sync(struct hci_dev *hdev, skb = __hci_cmd_sync(hdev, hdev->msft_opcode, total_size, cp, HCI_CMD_TIMEOUT); - kfree(cp); if (IS_ERR_OR_NULL(skb)) { - if (!skb) - return -EIO; - return PTR_ERR(skb); + err = PTR_ERR(skb); + goto out_free; } - return msft_le_monitor_advertisement_cb(hdev, hdev->msft_opcode, - monitor, skb); + err = msft_le_monitor_advertisement_cb(hdev, hdev->msft_opcode, + monitor, skb); + if (err) + goto out_free; + + handle_data = msft_find_handle_data(hdev, monitor->handle, true); + if (!handle_data) { + err = -ENODATA; + goto out_free; + } + + handle_data->rssi_high = cp->rssi_high; + handle_data->rssi_low = cp->rssi_low; + handle_data->rssi_low_interval = cp->rssi_low_interval; + handle_data->rssi_sampling_period = cp->rssi_sampling_period; + +out_free: + kfree(cp); + return err; } /* This function requires the caller holds hci_req_sync_lock */ @@ -538,6 +675,7 @@ void msft_do_close(struct hci_dev *hdev) { struct msft_data *msft = hdev->msft_data; struct msft_monitor_advertisement_handle_data *handle_data, *tmp; + struct msft_monitor_addr_filter_data *address_filter, *n; struct adv_monitor *monitor; if (!msft) @@ -559,6 +697,14 @@ void msft_do_close(struct hci_dev *hdev) kfree(handle_data); } + mutex_lock(&msft->filter_lock); + list_for_each_entry_safe(address_filter, n, &msft->address_filters, + list) { + list_del(&address_filter->list); + kfree(address_filter); + } + mutex_unlock(&msft->filter_lock); + hci_dev_lock(hdev); /* Clear any devices that are being monitored and notify device lost */ @@ -568,6 +714,49 @@ void msft_do_close(struct hci_dev *hdev) hci_dev_unlock(hdev); } +static int msft_cancel_address_filter_sync(struct hci_dev *hdev, void *data) +{ + struct msft_monitor_addr_filter_data *address_filter = data; + struct msft_cp_le_cancel_monitor_advertisement cp; + struct msft_data *msft = hdev->msft_data; + struct sk_buff *skb; + int err = 0; + + if (!msft) { + bt_dev_err(hdev, "MSFT: msft data is freed"); + return -EINVAL; + } + + /* The address filter has been removed by hci dev close */ + if (!test_bit(HCI_UP, &hdev->flags)) + return 0; + + mutex_lock(&msft->filter_lock); + list_del(&address_filter->list); + mutex_unlock(&msft->filter_lock); + + cp.sub_opcode = MSFT_OP_LE_CANCEL_MONITOR_ADVERTISEMENT; + cp.handle = address_filter->msft_handle; + + skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, + HCI_CMD_TIMEOUT); + if (IS_ERR_OR_NULL(skb)) { + bt_dev_err(hdev, "MSFT: Failed to cancel address (%pMR) filter", + &address_filter->bdaddr); + err = EIO; + goto done; + } + kfree_skb(skb); + + bt_dev_dbg(hdev, "MSFT: Canceled device %pMR address filter", + &address_filter->bdaddr); + +done: + kfree(address_filter); + + return err; +} + void msft_register(struct hci_dev *hdev) { struct msft_data *msft = NULL; @@ -581,7 +770,9 @@ void msft_register(struct hci_dev *hdev) } INIT_LIST_HEAD(&msft->handle_map); + INIT_LIST_HEAD(&msft->address_filters); hdev->msft_data = msft; + mutex_init(&msft->filter_lock); } void msft_unregister(struct hci_dev *hdev) @@ -596,6 +787,7 @@ void msft_unregister(struct hci_dev *hdev) hdev->msft_data = NULL; kfree(msft->evt_prefix); + mutex_destroy(&msft->filter_lock); kfree(msft); } @@ -645,11 +837,149 @@ static void *msft_skb_pull(struct hci_dev *hdev, struct sk_buff *skb, return data; } +static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data) +{ + struct msft_monitor_addr_filter_data *address_filter = data; + struct msft_rp_le_monitor_advertisement *rp; + struct msft_cp_le_monitor_advertisement *cp; + struct msft_data *msft = hdev->msft_data; + struct sk_buff *skb = NULL; + bool remove = false; + size_t size; + + if (!msft) { + bt_dev_err(hdev, "MSFT: msft data is freed"); + return -EINVAL; + } + + /* The address filter has been removed by hci dev close */ + if (!test_bit(HCI_UP, &hdev->flags)) + return -ENODEV; + + /* We are safe to use the address filter from now on. + * msft_monitor_device_evt() wouldn't delete this filter because it's + * not been added by now. + * And all other functions that requiring hci_req_sync_lock wouldn't + * touch this filter before this func completes because it's protected + * by hci_req_sync_lock. + */ + + if (address_filter->state == AF_STATE_REMOVING) { + mutex_lock(&msft->filter_lock); + list_del(&address_filter->list); + mutex_unlock(&msft->filter_lock); + kfree(address_filter); + return 0; + } + + size = sizeof(*cp) + + sizeof(address_filter->addr_type) + + sizeof(address_filter->bdaddr); + cp = kzalloc(size, GFP_KERNEL); + if (!cp) { + bt_dev_err(hdev, "MSFT: Alloc cmd param err"); + remove = true; + goto done; + } + cp->sub_opcode = MSFT_OP_LE_MONITOR_ADVERTISEMENT; + cp->rssi_high = address_filter->rssi_high; + cp->rssi_low = address_filter->rssi_low; + cp->rssi_low_interval = address_filter->rssi_low_interval; + cp->rssi_sampling_period = address_filter->rssi_sampling_period; + cp->cond_type = MSFT_MONITOR_ADVERTISEMENT_TYPE_ADDR; + cp->data[0] = address_filter->addr_type; + memcpy(&cp->data[1], &address_filter->bdaddr, + sizeof(address_filter->bdaddr)); + + skb = __hci_cmd_sync(hdev, hdev->msft_opcode, size, cp, + HCI_CMD_TIMEOUT); + if (IS_ERR_OR_NULL(skb)) { + bt_dev_err(hdev, "Failed to enable address %pMR filter", + &address_filter->bdaddr); + skb = NULL; + remove = true; + goto done; + } + + rp = skb_pull_data(skb, sizeof(*rp)); + if (!rp || rp->sub_opcode != MSFT_OP_LE_MONITOR_ADVERTISEMENT || + rp->status) + remove = true; + +done: + mutex_lock(&msft->filter_lock); + + if (remove) { + bt_dev_warn(hdev, "MSFT: Remove address (%pMR) filter", + &address_filter->bdaddr); + list_del(&address_filter->list); + kfree(address_filter); + } else { + address_filter->state = AF_STATE_ADDED; + address_filter->msft_handle = rp->handle; + bt_dev_dbg(hdev, "MSFT: Address %pMR filter enabled", + &address_filter->bdaddr); + } + mutex_unlock(&msft->filter_lock); + + kfree_skb(skb); + + return 0; +} + +/* This function requires the caller holds msft->filter_lock */ +static struct msft_monitor_addr_filter_data *msft_add_address_filter + (struct hci_dev *hdev, u8 addr_type, bdaddr_t *bdaddr, + struct msft_monitor_advertisement_handle_data *handle_data) +{ + struct msft_monitor_addr_filter_data *address_filter = NULL; + struct msft_data *msft = hdev->msft_data; + int err; + + address_filter = kzalloc(sizeof(*address_filter), GFP_KERNEL); + if (!address_filter) + return NULL; + + address_filter->state = AF_STATE_ADDING; + address_filter->msft_handle = 0xff; + address_filter->pattern_handle = handle_data->msft_handle; + address_filter->mgmt_handle = handle_data->mgmt_handle; + address_filter->rssi_high = handle_data->rssi_high; + address_filter->rssi_low = handle_data->rssi_low; + address_filter->rssi_low_interval = handle_data->rssi_low_interval; + address_filter->rssi_sampling_period = handle_data->rssi_sampling_period; + address_filter->addr_type = addr_type; + bacpy(&address_filter->bdaddr, bdaddr); + + /* With the above AF_STATE_ADDING, duplicated address filter can be + * avoided when receiving monitor device event (found/lost) frequently + * for the same device. + */ + list_add_tail(&address_filter->list, &msft->address_filters); + + err = hci_cmd_sync_queue(hdev, msft_add_address_filter_sync, + address_filter, NULL); + if (err < 0) { + bt_dev_err(hdev, "MSFT: Add address %pMR filter err", bdaddr); + list_del(&address_filter->list); + kfree(address_filter); + return NULL; + } + + bt_dev_dbg(hdev, "MSFT: Add device %pMR address filter", + &address_filter->bdaddr); + + return address_filter; +} + /* This function requires the caller holds hdev->lock */ static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb) { + struct msft_monitor_addr_filter_data *n, *address_filter = NULL; struct msft_ev_le_monitor_device *ev; struct msft_monitor_advertisement_handle_data *handle_data; + struct msft_data *msft = hdev->msft_data; + u16 mgmt_handle = 0xffff; u8 addr_type; ev = msft_skb_pull(hdev, skb, MSFT_EV_LE_MONITOR_DEVICE, sizeof(*ev)); @@ -662,9 +992,53 @@ static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb) ev->monitor_state, &ev->bdaddr); handle_data = msft_find_handle_data(hdev, ev->monitor_handle, false); - if (!handle_data) + + if (!test_bit(HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, &hdev->quirks)) { + if (!handle_data) + return; + mgmt_handle = handle_data->mgmt_handle; + goto report_state; + } + + if (handle_data) { + /* Don't report any device found/lost event from pattern + * monitors. Pattern monitor always has its address filters for + * tracking devices. + */ + + address_filter = msft_find_address_data(hdev, ev->addr_type, + &ev->bdaddr, + handle_data->msft_handle); + if (address_filter) + return; + + if (ev->monitor_state && handle_data->cond_type == + MSFT_MONITOR_ADVERTISEMENT_TYPE_PATTERN) + msft_add_address_filter(hdev, ev->addr_type, + &ev->bdaddr, handle_data); + return; + } + /* This device event is not from pattern monitor. + * Report it if there is a corresponding address_filter for it. + */ + list_for_each_entry(n, &msft->address_filters, list) { + if (n->state == AF_STATE_ADDED && + n->msft_handle == ev->monitor_handle) { + mgmt_handle = n->mgmt_handle; + address_filter = n; + break; + } + } + + if (!address_filter) { + bt_dev_warn(hdev, "MSFT: Unexpected device event %pMR, %u, %u", + &ev->bdaddr, ev->monitor_handle, ev->monitor_state); + return; + } + +report_state: switch (ev->addr_type) { case ADDR_LE_DEV_PUBLIC: addr_type = BDADDR_LE_PUBLIC; @@ -681,12 +1055,18 @@ static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb) return; } - if (ev->monitor_state) - msft_device_found(hdev, &ev->bdaddr, addr_type, - handle_data->mgmt_handle); - else - msft_device_lost(hdev, &ev->bdaddr, addr_type, - handle_data->mgmt_handle); + if (ev->monitor_state) { + msft_device_found(hdev, &ev->bdaddr, addr_type, mgmt_handle); + } else { + if (address_filter && address_filter->state == AF_STATE_ADDED) { + address_filter->state = AF_STATE_REMOVING; + hci_cmd_sync_queue(hdev, + msft_cancel_address_filter_sync, + address_filter, + NULL); + } + msft_device_lost(hdev, &ev->bdaddr, addr_type, mgmt_handle); + } } void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) @@ -724,7 +1104,9 @@ void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) switch (*evt) { case MSFT_EV_LE_MONITOR_DEVICE: + mutex_lock(&msft->filter_lock); msft_monitor_device_evt(hdev, skb); + mutex_unlock(&msft->filter_lock); break; default: -- cgit v1.2.3 From a13f316e90fdb1fb6df6582e845aa9b3270f3581 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 26 Jun 2023 17:25:06 -0700 Subject: Bluetooth: hci_conn: Consolidate code for aborting connections This consolidates code for aborting connections using hci_cmd_sync_queue so it is synchronized with other threads, but because of the fact that some commands may block the cmd_sync_queue while waiting specific events this attempt to cancel those requests by using hci_cmd_sync_cancel. Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 2 +- net/bluetooth/hci_conn.c | 154 ++++++++------------------------------- net/bluetooth/hci_sync.c | 23 ++++-- net/bluetooth/mgmt.c | 15 +--- 4 files changed, 47 insertions(+), 147 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9140d4a80e38..2dd59e3a51b3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -739,6 +739,7 @@ struct hci_conn { unsigned long flags; enum conn_reasons conn_reason; + __u8 abort_reason; __u32 clock; __u16 clock_accuracy; @@ -758,7 +759,6 @@ struct hci_conn { struct delayed_work auto_accept_work; struct delayed_work idle_work; struct delayed_work le_conn_timeout; - struct work_struct le_scan_cleanup; struct device dev; struct dentry *debugfs; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 0f89daafe194..fa9236dfba3e 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -178,57 +178,6 @@ static void hci_conn_cleanup(struct hci_conn *conn) hci_conn_put(conn); } -static void le_scan_cleanup(struct work_struct *work) -{ - struct hci_conn *conn = container_of(work, struct hci_conn, - le_scan_cleanup); - struct hci_dev *hdev = conn->hdev; - struct hci_conn *c = NULL; - - BT_DBG("%s hcon %p", hdev->name, conn); - - hci_dev_lock(hdev); - - /* Check that the hci_conn is still around */ - rcu_read_lock(); - list_for_each_entry_rcu(c, &hdev->conn_hash.list, list) { - if (c == conn) - break; - } - rcu_read_unlock(); - - if (c == conn) { - hci_connect_le_scan_cleanup(conn, 0x00); - hci_conn_cleanup(conn); - } - - hci_dev_unlock(hdev); - hci_dev_put(hdev); - hci_conn_put(conn); -} - -static void hci_connect_le_scan_remove(struct hci_conn *conn) -{ - BT_DBG("%s hcon %p", conn->hdev->name, conn); - - /* We can't call hci_conn_del/hci_conn_cleanup here since that - * could deadlock with another hci_conn_del() call that's holding - * hci_dev_lock and doing cancel_delayed_work_sync(&conn->disc_work). - * Instead, grab temporary extra references to the hci_dev and - * hci_conn and perform the necessary cleanup in a separate work - * callback. - */ - - hci_dev_hold(conn->hdev); - hci_conn_get(conn); - - /* Even though we hold a reference to the hdev, many other - * things might get cleaned up meanwhile, including the hdev's - * own workqueue, so we can't use that for scheduling. - */ - schedule_work(&conn->le_scan_cleanup); -} - static void hci_acl_create_connection(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -679,13 +628,6 @@ static void hci_conn_timeout(struct work_struct *work) if (refcnt > 0) return; - /* LE connections in scanning state need special handling */ - if (conn->state == BT_CONNECT && conn->type == LE_LINK && - test_bit(HCI_CONN_SCANNING, &conn->flags)) { - hci_connect_le_scan_remove(conn); - return; - } - hci_abort_conn(conn, hci_proto_disconn_ind(conn)); } @@ -1066,7 +1008,6 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept); INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle); INIT_DELAYED_WORK(&conn->le_conn_timeout, le_conn_timeout); - INIT_WORK(&conn->le_scan_cleanup, le_scan_cleanup); atomic_set(&conn->refcnt, 0); @@ -2888,81 +2829,46 @@ u32 hci_conn_get_phy(struct hci_conn *conn) return phys; } -int hci_abort_conn(struct hci_conn *conn, u8 reason) +static int abort_conn_sync(struct hci_dev *hdev, void *data) { - int r = 0; + struct hci_conn *conn; + u16 handle = PTR_ERR(data); - if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + conn = hci_conn_hash_lookup_handle(hdev, handle); + if (!conn) return 0; - switch (conn->state) { - case BT_CONNECTED: - case BT_CONFIG: - if (conn->type == AMP_LINK) { - struct hci_cp_disconn_phy_link cp; + return hci_abort_conn_sync(hdev, conn, conn->abort_reason); +} - cp.phy_handle = HCI_PHY_HANDLE(conn->handle); - cp.reason = reason; - r = hci_send_cmd(conn->hdev, HCI_OP_DISCONN_PHY_LINK, - sizeof(cp), &cp); - } else { - struct hci_cp_disconnect dc; +int hci_abort_conn(struct hci_conn *conn, u8 reason) +{ + struct hci_dev *hdev = conn->hdev; - dc.handle = cpu_to_le16(conn->handle); - dc.reason = reason; - r = hci_send_cmd(conn->hdev, HCI_OP_DISCONNECT, - sizeof(dc), &dc); - } + /* If abort_reason has already been set it means the connection is + * already being aborted so don't attempt to overwrite it. + */ + if (conn->abort_reason) + return 0; - conn->state = BT_DISCONN; + bt_dev_dbg(hdev, "handle 0x%2.2x reason 0x%2.2x", conn->handle, reason); - break; - case BT_CONNECT: - if (conn->type == LE_LINK) { - if (test_bit(HCI_CONN_SCANNING, &conn->flags)) - break; - r = hci_send_cmd(conn->hdev, - HCI_OP_LE_CREATE_CONN_CANCEL, 0, NULL); - } else if (conn->type == ACL_LINK) { - if (conn->hdev->hci_ver < BLUETOOTH_VER_1_2) - break; - r = hci_send_cmd(conn->hdev, - HCI_OP_CREATE_CONN_CANCEL, - 6, &conn->dst); - } - break; - case BT_CONNECT2: - if (conn->type == ACL_LINK) { - struct hci_cp_reject_conn_req rej; - - bacpy(&rej.bdaddr, &conn->dst); - rej.reason = reason; - - r = hci_send_cmd(conn->hdev, - HCI_OP_REJECT_CONN_REQ, - sizeof(rej), &rej); - } else if (conn->type == SCO_LINK || conn->type == ESCO_LINK) { - struct hci_cp_reject_sync_conn_req rej; - - bacpy(&rej.bdaddr, &conn->dst); - - /* SCO rejection has its own limited set of - * allowed error values (0x0D-0x0F) which isn't - * compatible with most values passed to this - * function. To be safe hard-code one of the - * values that's suitable for SCO. - */ - rej.reason = HCI_ERROR_REJ_LIMITED_RESOURCES; + conn->abort_reason = reason; - r = hci_send_cmd(conn->hdev, - HCI_OP_REJECT_SYNC_CONN_REQ, - sizeof(rej), &rej); + /* If the connection is pending check the command opcode since that + * might be blocking on hci_cmd_sync_work while waiting its respective + * event so we need to hci_cmd_sync_cancel to cancel it. + */ + if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) { + switch (hci_skb_event(hdev->sent_cmd)) { + case HCI_EV_LE_CONN_COMPLETE: + case HCI_EV_LE_ENHANCED_CONN_COMPLETE: + case HCI_EVT_LE_CIS_ESTABLISHED: + hci_cmd_sync_cancel(hdev, -ECANCELED); + break; } - break; - default: - conn->state = BT_CLOSED; - break; } - return r; + return hci_cmd_sync_queue(hdev, abort_conn_sync, ERR_PTR(conn->handle), + NULL); } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 73b49d0c1e11..5f7a901709b5 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -5274,22 +5274,27 @@ static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn, } static int hci_le_connect_cancel_sync(struct hci_dev *hdev, - struct hci_conn *conn) + struct hci_conn *conn, u8 reason) { + /* Return reason if scanning since the connection shall probably be + * cleanup directly. + */ if (test_bit(HCI_CONN_SCANNING, &conn->flags)) - return 0; + return reason; - if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + if (conn->role == HCI_ROLE_SLAVE || + test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_LE_CREATE_CONN_CANCEL, 0, NULL, HCI_CMD_TIMEOUT); } -static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn) +static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn, + u8 reason) { if (conn->type == LE_LINK) - return hci_le_connect_cancel_sync(hdev, conn); + return hci_le_connect_cancel_sync(hdev, conn, reason); if (hdev->hci_ver < BLUETOOTH_VER_1_2) return 0; @@ -5342,9 +5347,11 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) case BT_CONFIG: return hci_disconnect_sync(hdev, conn, reason); case BT_CONNECT: - err = hci_connect_cancel_sync(hdev, conn); + err = hci_connect_cancel_sync(hdev, conn, reason); /* Cleanup hci_conn object if it cannot be cancelled as it - * likelly means the controller and host stack are out of sync. + * likelly means the controller and host stack are out of sync + * or in case of LE it was still scanning so it can be cleanup + * safely. */ if (err) { hci_dev_lock(hdev); @@ -6258,7 +6265,7 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) done: if (err == -ETIMEDOUT) - hci_le_connect_cancel_sync(hdev, conn); + hci_le_connect_cancel_sync(hdev, conn, 0x00); /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 4c352abe063b..5707ff468842 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3586,18 +3586,6 @@ unlock: return err; } -static int abort_conn_sync(struct hci_dev *hdev, void *data) -{ - struct hci_conn *conn; - u16 handle = PTR_ERR(data); - - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return 0; - - return hci_abort_conn_sync(hdev, conn, HCI_ERROR_REMOTE_USER_TERM); -} - static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { @@ -3648,8 +3636,7 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, le_addr_type(addr->type)); if (conn->conn_reason == CONN_REASON_PAIR_DEVICE) - hci_cmd_sync_queue(hdev, abort_conn_sync, ERR_PTR(conn->handle), - NULL); + hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); unlock: hci_dev_unlock(hdev); -- cgit v1.2.3 From 9f78191cc9f1b34c2e2afd7b554a83bf034092dd Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Wed, 28 Jun 2023 12:15:53 -0700 Subject: Bluetooth: hci_conn: Always allocate unique handles This attempts to always allocate a unique handle for connections so they can be properly aborted by the likes of hci_abort_conn, so this uses the invalid range as a pool of unset handles that way if userspace is trying to create multiple connections at once each will be given a unique handle which will be considered unset. Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 2 +- net/bluetooth/hci_conn.c | 25 ++++++++++++++++++++++--- net/bluetooth/hci_event.c | 6 +++--- 3 files changed, 26 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 2dd59e3a51b3..491ab83ccafc 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -321,8 +321,8 @@ struct adv_monitor { #define HCI_MAX_SHORT_NAME_LENGTH 10 -#define HCI_CONN_HANDLE_UNSET 0xffff #define HCI_CONN_HANDLE_MAX 0x0eff +#define HCI_CONN_HANDLE_UNSET(_handle) (_handle > HCI_CONN_HANDLE_MAX) /* Min encryption key size to match with SMP */ #define HCI_MIN_ENC_KEY_SIZE 7 diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index a0ffe7db412b..af7dc8131a8c 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -932,6 +932,25 @@ static void cis_cleanup(struct hci_conn *conn) hci_le_remove_cig(hdev, conn->iso_qos.ucast.cig); } +static u16 hci_conn_hash_alloc_unset(struct hci_dev *hdev) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + u16 handle = HCI_CONN_HANDLE_MAX + 1; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + /* Find the first unused handle */ + if (handle == 0xffff || c->handle != handle) + break; + handle++; + } + rcu_read_unlock(); + + return handle; +} + struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role) { @@ -945,7 +964,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, bacpy(&conn->dst, dst); bacpy(&conn->src, &hdev->bdaddr); - conn->handle = HCI_CONN_HANDLE_UNSET; + conn->handle = hci_conn_hash_alloc_unset(hdev); conn->hdev = hdev; conn->type = type; conn->role = role; @@ -1057,7 +1076,7 @@ static void hci_conn_unlink(struct hci_conn *conn) */ if ((child->type == SCO_LINK || child->type == ESCO_LINK) && - child->handle == HCI_CONN_HANDLE_UNSET) + HCI_CONN_HANDLE_UNSET(child->handle)) hci_conn_del(child); } @@ -1943,7 +1962,7 @@ int hci_conn_check_create_cis(struct hci_conn *conn) return -EINVAL; if (!conn->parent || conn->parent->state != BT_CONNECTED || - conn->state != BT_CONNECT || conn->handle == HCI_CONN_HANDLE_UNSET) + conn->state != BT_CONNECT || HCI_CONN_HANDLE_UNSET(conn->handle)) return 1; return 0; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index c67612c99f89..90cfd30616f5 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3173,7 +3173,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, * As the connection handle is set here for the first time, it indicates * whether the connection is already set up. */ - if (conn->handle != HCI_CONN_HANDLE_UNSET) { + if (!HCI_CONN_HANDLE_UNSET(conn->handle)) { bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection"); goto unlock; } @@ -5032,7 +5032,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, * As the connection handle is set here for the first time, it indicates * whether the connection is already set up. */ - if (conn->handle != HCI_CONN_HANDLE_UNSET) { + if (!HCI_CONN_HANDLE_UNSET(conn->handle)) { bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete event for existing connection"); goto unlock; } @@ -5896,7 +5896,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, * As the connection handle is set here for the first time, it indicates * whether the connection is already set up. */ - if (conn->handle != HCI_CONN_HANDLE_UNSET) { + if (!HCI_CONN_HANDLE_UNSET(conn->handle)) { bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection"); goto unlock; } -- cgit v1.2.3 From f777d88278170410b06a1f6633f3b9375a4ddd6b Mon Sep 17 00:00:00 2001 From: Iulia Tanasescu Date: Mon, 3 Jul 2023 10:02:38 +0300 Subject: Bluetooth: ISO: Notify user space about failed bis connections Some use cases require the user to be informed if BIG synchronization fails. This commit makes it so that even if the BIG sync established event arrives with error status, a new hconn is added for each BIS, and the iso layer is notified about the failed connections. Unsuccesful bis connections will be marked using the HCI_CONN_BIG_SYNC_FAILED flag. From the iso layer, the POLLERR event is triggered on the newly allocated bis sockets, before adding them to the accept list of the parent socket. From user space, a new fd for each failed bis connection will be obtained by calling accept. The user should check for the POLLERR event on the new socket, to determine if the connection was successful or not. The HCI_CONN_BIG_SYNC flag has been added to mark whether the BIG sync has been successfully established. This flag is checked at bis cleanup, so the HCI LE BIG Terminate Sync command is only issued if needed. The BT_SK_BIG_SYNC flag indicates if BIG create sync has been called for a listening socket, to avoid issuing the command everytime a BIGInfo advertising report is received. Signed-off-by: Iulia Tanasescu Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 25 +++++++++++++++++++++++++ net/bluetooth/hci_conn.c | 37 ++++++++++++++----------------------- net/bluetooth/hci_event.c | 21 +++++++++++++++++---- net/bluetooth/hci_sync.c | 8 ++++++++ net/bluetooth/iso.c | 40 +++++++++++++++++++++++++++++----------- 5 files changed, 93 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 491ab83ccafc..105c1c394f82 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -976,6 +976,8 @@ enum { HCI_CONN_PER_ADV, HCI_CONN_BIG_CREATED, HCI_CONN_CREATE_CIS, + HCI_CONN_BIG_SYNC, + HCI_CONN_BIG_SYNC_FAILED, }; static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) @@ -1286,6 +1288,29 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, return NULL; } +static inline struct hci_conn *hci_conn_hash_lookup_big_any_dst(struct hci_dev *hdev, + __u8 handle) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type != ISO_LINK) + continue; + + if (handle == c->iso_qos.bcast.big) { + rcu_read_unlock(); + return c; + } + } + + rcu_read_unlock(); + + return NULL; +} + static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev, __u8 type, __u16 state) { diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index af7dc8131a8c..cccc2b8b60a8 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -735,6 +735,7 @@ struct iso_list_data { int count; struct iso_cig_params pdu; bool big_term; + bool big_sync_term; }; static void bis_list(struct hci_conn *conn, void *data) @@ -752,17 +753,6 @@ static void bis_list(struct hci_conn *conn, void *data) d->count++; } -static void find_bis(struct hci_conn *conn, void *data) -{ - struct iso_list_data *d = data; - - /* Ignore unicast */ - if (bacmp(&conn->dst, BDADDR_ANY)) - return; - - d->count++; -} - static int terminate_big_sync(struct hci_dev *hdev, void *data) { struct iso_list_data *d = data; @@ -815,31 +805,26 @@ static int big_terminate_sync(struct hci_dev *hdev, void *data) bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", d->big, d->sync_handle); - /* Check if ISO connection is a BIS and terminate BIG if there are - * no other connections using it. - */ - hci_conn_hash_list_state(hdev, find_bis, ISO_LINK, BT_CONNECTED, d); - if (d->count) - return 0; - - hci_le_big_terminate_sync(hdev, d->big); + if (d->big_sync_term) + hci_le_big_terminate_sync(hdev, d->big); return hci_le_pa_terminate_sync(hdev, d->sync_handle); } -static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle) +static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn) { struct iso_list_data *d; int ret; - bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, sync_handle); + bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, conn->sync_handle); d = kzalloc(sizeof(*d), GFP_KERNEL); if (!d) return -ENOMEM; d->big = big; - d->sync_handle = sync_handle; + d->sync_handle = conn->sync_handle; + d->big_sync_term = test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags); ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, terminate_big_destroy); @@ -875,8 +860,14 @@ static void bis_cleanup(struct hci_conn *conn) hci_le_terminate_big(hdev, conn); } else { + bis = hci_conn_hash_lookup_big_any_dst(hdev, + conn->iso_qos.bcast.big); + + if (bis) + return; + hci_le_big_terminate(hdev, conn->iso_qos.bcast.big, - conn->sync_handle); + conn); } } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 90cfd30616f5..c29eece88d2c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -7039,9 +7039,6 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, flex_array_size(ev, bis, ev->num_bis))) return; - if (ev->status) - return; - hci_dev_lock(hdev); for (i = 0; i < ev->num_bis; i++) { @@ -7065,9 +7062,25 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis->iso_qos.bcast.in.latency = le16_to_cpu(ev->interval) * 125 / 100; bis->iso_qos.bcast.in.sdu = le16_to_cpu(ev->max_pdu); - hci_iso_setup_path(bis); + if (!ev->status) { + set_bit(HCI_CONN_BIG_SYNC, &bis->flags); + hci_iso_setup_path(bis); + } } + /* In case BIG sync failed, notify each failed connection to + * the user after all hci connections have been added + */ + if (ev->status) + for (i = 0; i < ev->num_bis; i++) { + u16 handle = le16_to_cpu(ev->bis[i]); + + bis = hci_conn_hash_lookup_handle(hdev, handle); + + set_bit(HCI_CONN_BIG_SYNC_FAILED, &bis->flags); + hci_connect_cfm(bis, ev->status); + } + hci_dev_unlock(hdev); } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index c085b54d158b..3348a1b0e3f7 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -5395,6 +5395,14 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) return err; case BT_CONNECT2: return hci_reject_conn_sync(hdev, conn, reason); + case BT_OPEN: + /* Cleanup bises that failed to be established */ + if (test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags)) { + hci_dev_lock(hdev); + hci_conn_failed(conn, reason); + hci_dev_unlock(hdev); + } + break; default: conn->state = BT_CLOSED; break; diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 9c41af55f2c7..efac284badbc 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -48,6 +48,11 @@ static void iso_sock_kill(struct sock *sk); #define EIR_SERVICE_DATA_LENGTH 4 #define BASE_MAX_LENGTH (HCI_MAX_PER_AD_LENGTH - EIR_SERVICE_DATA_LENGTH) +/* iso_pinfo flags values */ +enum { + BT_SK_BIG_SYNC, +}; + struct iso_pinfo { struct bt_sock bt; bdaddr_t src; @@ -58,7 +63,7 @@ struct iso_pinfo { __u8 bc_num_bis; __u8 bc_bis[ISO_MAX_NUM_BIS]; __u16 sync_handle; - __u32 flags; + unsigned long flags; struct bt_iso_qos qos; bool qos_user_set; __u8 base_len; @@ -1555,6 +1560,12 @@ static void iso_conn_ready(struct iso_conn *conn) hci_conn_hold(hcon); iso_chan_add(conn, sk, parent); + if (ev && ((struct hci_evt_le_big_sync_estabilished *)ev)->status) { + /* Trigger error signal on child socket */ + sk->sk_err = ECONNREFUSED; + sk->sk_error_report(sk); + } + if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) sk->sk_state = BT_CONNECT2; else @@ -1623,15 +1634,17 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) if (ev2->num_bis < iso_pi(sk)->bc_num_bis) iso_pi(sk)->bc_num_bis = ev2->num_bis; - err = hci_le_big_create_sync(hdev, - &iso_pi(sk)->qos, - iso_pi(sk)->sync_handle, - iso_pi(sk)->bc_num_bis, - iso_pi(sk)->bc_bis); - if (err) { - bt_dev_err(hdev, "hci_le_big_create_sync: %d", - err); - sk = NULL; + if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { + err = hci_le_big_create_sync(hdev, + &iso_pi(sk)->qos, + iso_pi(sk)->sync_handle, + iso_pi(sk)->bc_num_bis, + iso_pi(sk)->bc_bis); + if (err) { + bt_dev_err(hdev, "hci_le_big_create_sync: %d", + err); + sk = NULL; + } } } } else { @@ -1674,7 +1687,12 @@ static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); - if (!status) { + /* Similar to the success case, if HCI_CONN_BIG_SYNC_FAILED is set, + * queue the failed bis connection into the accept queue of the + * listening socket and wake up userspace, to inform the user about + * the BIG sync failed event. + */ + if (!status || test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) { struct iso_conn *conn; conn = iso_conn_add(hcon); -- cgit v1.2.3 From 112b5090c21905531314fee41f691f0317bbf4f6 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 6 Jul 2023 12:06:32 -0700 Subject: Bluetooth: MGMT: Fix always using HCI_MAX_AD_LENGTH HCI_MAX_AD_LENGTH shall only be used if the controller doesn't support extended advertising, otherwise HCI_MAX_EXT_AD_LENGTH shall be used instead. Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 4 ++++ net/bluetooth/hci_event.c | 12 +++++++----- net/bluetooth/mgmt.c | 6 +++--- 3 files changed, 14 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 105c1c394f82..8200a6689b39 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1801,6 +1801,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) +/* Maximum advertising length */ +#define max_adv_len(dev) \ + (ext_adv_capable(dev) ? HCI_MAX_EXT_AD_LENGTH : HCI_MAX_AD_LENGTH) + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 1789: * * C24: Mandatory if the LE Controller supports Connection State and either diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index c29eece88d2c..f1fcece29e7d 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1747,7 +1747,7 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, { struct discovery_state *d = &hdev->discovery; - if (len > HCI_MAX_AD_LENGTH) + if (len > max_adv_len(hdev)) return; bacpy(&d->last_adv_addr, bdaddr); @@ -6249,8 +6249,9 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, return; } - if (!ext_adv && len > HCI_MAX_AD_LENGTH) { - bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes"); + if (len > max_adv_len(hdev)) { + bt_dev_err_ratelimited(hdev, + "adv larger than maximum supported"); return; } @@ -6315,7 +6316,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, bdaddr_resolved, type); - if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) { + if (!ext_adv && conn && type == LE_ADV_IND && + len <= max_adv_len(hdev)) { /* Store report for later inclusion by * mgmt_device_connected */ @@ -6456,7 +6458,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data, info->length + 1)) break; - if (info->length <= HCI_MAX_AD_LENGTH) { + if (info->length <= max_adv_len(hdev)) { rssi = info->data[info->length]; process_adv_report(hdev, info->type, &info->bdaddr, info->bdaddr_type, NULL, 0, rssi, diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 5707ff468842..d6c9b7bc8592 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -8428,8 +8428,8 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, supported_flags = get_supported_adv_flags(hdev); rp->supported_flags = cpu_to_le32(supported_flags); - rp->max_adv_data_len = HCI_MAX_AD_LENGTH; - rp->max_scan_rsp_len = HCI_MAX_AD_LENGTH; + rp->max_adv_data_len = max_adv_len(hdev); + rp->max_scan_rsp_len = max_adv_len(hdev); rp->max_instances = hdev->le_num_of_adv_sets; rp->num_instances = hdev->adv_instance_cnt; @@ -8465,7 +8465,7 @@ static u8 calculate_name_len(struct hci_dev *hdev) static u8 tlv_data_max_len(struct hci_dev *hdev, u32 adv_flags, bool is_adv_data) { - u8 max_len = HCI_MAX_AD_LENGTH; + u8 max_len = max_adv_len(hdev); if (is_adv_data) { if (adv_flags & (MGMT_ADV_FLAG_DISCOV | -- cgit v1.2.3 From 3f19ffb2f924db5b0925c77818d18ac1f6f08a44 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 13 Jul 2023 13:41:31 -0700 Subject: Bluetooth: af_bluetooth: Make BT_PKT_STATUS generic This makes the handling of BT_PKT_STATUS more generic so it can be reused by sockets other than SCO like BT_DEFER_SETUP, etc. Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/bluetooth.h | 8 +++----- include/net/bluetooth/sco.h | 2 -- net/bluetooth/af_bluetooth.c | 8 ++++++-- net/bluetooth/hci_core.c | 2 +- net/bluetooth/sco.c | 22 ++++------------------ 5 files changed, 14 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 34998ae8ed78..aa90adc3b2a4 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -386,6 +386,7 @@ struct bt_sock { enum { BT_SK_DEFER_SETUP, BT_SK_SUSPEND, + BT_SK_PKT_STATUS }; struct bt_sock_list { @@ -432,10 +433,6 @@ struct l2cap_ctrl { struct l2cap_chan *chan; }; -struct sco_ctrl { - u8 pkt_status; -}; - struct hci_dev; typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); @@ -466,9 +463,9 @@ struct bt_skb_cb { u8 force_active; u16 expect; u8 incoming:1; + u8 pkt_status:2; union { struct l2cap_ctrl l2cap; - struct sco_ctrl sco; struct hci_ctrl hci; struct mgmt_ctrl mgmt; struct scm_creds creds; @@ -477,6 +474,7 @@ struct bt_skb_cb { #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) #define hci_skb_pkt_type(skb) bt_cb((skb))->pkt_type +#define hci_skb_pkt_status(skb) bt_cb((skb))->pkt_status #define hci_skb_expect(skb) bt_cb((skb))->expect #define hci_skb_opcode(skb) bt_cb((skb))->hci.opcode #define hci_skb_event(skb) bt_cb((skb))->hci.req_event diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h index 1aa2e14b6c94..f40ddb4264fc 100644 --- a/include/net/bluetooth/sco.h +++ b/include/net/bluetooth/sco.h @@ -46,6 +46,4 @@ struct sco_conninfo { __u8 dev_class[3]; }; -#define SCO_CMSG_PKT_STATUS 0x01 - #endif /* __SCO_H */ diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 647afb187147..336a76165454 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -333,8 +333,12 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, bt_sk(sk)->skb_msg_name(skb, msg->msg_name, &msg->msg_namelen); - if (bt_sk(sk)->skb_put_cmsg) - bt_sk(sk)->skb_put_cmsg(skb, msg, sk); + if (test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags)) { + u8 pkt_status = hci_skb_pkt_status(skb); + + put_cmsg(msg, SOL_BLUETOOTH, BT_SCM_PKT_STATUS, + sizeof(pkt_status), &pkt_status); + } } skb_free_datagram(sk, skb); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index bd90caad4804..0fefa6788911 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3895,7 +3895,7 @@ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) if (conn) { /* Send to upper protocol */ - bt_cb(skb)->sco.pkt_status = flags & 0x03; + hci_skb_pkt_status(skb) = flags & 0x03; sco_recv_scodata(conn, skb); return; } else { diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index ec6dce488a40..50ad5935ae47 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -68,7 +68,6 @@ struct sco_pinfo { bdaddr_t dst; __u32 flags; __u16 setting; - __u8 cmsg_mask; struct bt_codec codec; struct sco_conn *conn; }; @@ -471,15 +470,6 @@ static void sco_sock_close(struct sock *sk) release_sock(sk); } -static void sco_skb_put_cmsg(struct sk_buff *skb, struct msghdr *msg, - struct sock *sk) -{ - if (sco_pi(sk)->cmsg_mask & SCO_CMSG_PKT_STATUS) - put_cmsg(msg, SOL_BLUETOOTH, BT_SCM_PKT_STATUS, - sizeof(bt_cb(skb)->sco.pkt_status), - &bt_cb(skb)->sco.pkt_status); -} - static void sco_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); @@ -488,8 +478,6 @@ static void sco_sock_init(struct sock *sk, struct sock *parent) sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; security_sk_clone(parent, sk); - } else { - bt_sk(sk)->skb_put_cmsg = sco_skb_put_cmsg; } } @@ -907,9 +895,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, } if (opt) - sco_pi(sk)->cmsg_mask |= SCO_CMSG_PKT_STATUS; + set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); else - sco_pi(sk)->cmsg_mask &= SCO_CMSG_PKT_STATUS; + clear_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); break; case BT_CODEC: @@ -1040,7 +1028,6 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, int len, err = 0; struct bt_voice voice; u32 phys; - int pkt_status; int buf_len; struct codec_list *c; u8 num_codecs, i, __user *ptr; @@ -1094,9 +1081,8 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - pkt_status = (sco_pi(sk)->cmsg_mask & SCO_CMSG_PKT_STATUS); - - if (put_user(pkt_status, (int __user *)optval)) + if (put_user(test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags), + (int __user *)optval)) err = -EFAULT; break; -- cgit v1.2.3 From 16e3b6429159795a87add7584eb100b19aa1d70b Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 3 Aug 2023 14:49:14 -0700 Subject: Bluetooth: hci_conn: Fix modifying handle while aborting This introduces hci_conn_set_handle which takes care of verifying the conditions where the hci_conn handle can be modified, including when hci_conn_abort has been called and also checks that the handles is valid as well. Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 1 + net/bluetooth/hci_conn.c | 27 +++++++++++++++++++++++++++ net/bluetooth/hci_event.c | 29 +++++++++++------------------ 3 files changed, 39 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8200a6689b39..d2a3a2a9fd7d 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1425,6 +1425,7 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); void hci_conn_failed(struct hci_conn *conn, u8 status); +u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle); /* * hci_conn_get() and hci_conn_put() are used to control the life-time of an diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 923bb7e7be2b..6132eed7e8dc 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1231,6 +1231,33 @@ void hci_conn_failed(struct hci_conn *conn, u8 status) hci_conn_del(conn); } +/* This function requires the caller holds hdev->lock */ +u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) +{ + struct hci_dev *hdev = conn->hdev; + + bt_dev_dbg(hdev, "hcon %p handle 0x%4.4x", conn, handle); + + if (conn->handle == handle) + return 0; + + if (handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", + handle, HCI_CONN_HANDLE_MAX); + return HCI_ERROR_INVALID_PARAMETERS; + } + + /* If abort_reason has been sent it means the connection is being + * aborted and the handle shall not be changed. + */ + if (conn->abort_reason) + return conn->abort_reason; + + conn->handle = handle; + + return 0; +} + static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index f1fcece29e7d..218da9b0fe8f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3179,13 +3179,9 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, } if (!status) { - conn->handle = __le16_to_cpu(ev->handle); - if (conn->handle > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", - conn->handle, HCI_CONN_HANDLE_MAX); - status = HCI_ERROR_INVALID_PARAMETERS; + status = hci_conn_set_handle(conn, __le16_to_cpu(ev->handle)); + if (status) goto done; - } if (conn->type == ACL_LINK) { conn->state = BT_CONFIG; @@ -3849,11 +3845,9 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, if (conn->state != BT_BOUND && conn->state != BT_CONNECT) continue; - conn->handle = __le16_to_cpu(rp->handle[i]); + if (hci_conn_set_handle(conn, __le16_to_cpu(rp->handle[i]))) + continue; - bt_dev_dbg(hdev, "%p handle 0x%4.4x parent %p", conn, - conn->handle, conn->parent); - if (conn->state == BT_CONNECT) pending = true; } @@ -5039,11 +5033,8 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, switch (status) { case 0x00: - conn->handle = __le16_to_cpu(ev->handle); - if (conn->handle > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", - conn->handle, HCI_CONN_HANDLE_MAX); - status = HCI_ERROR_INVALID_PARAMETERS; + status = hci_conn_set_handle(conn, __le16_to_cpu(ev->handle)); + if (status) { conn->state = BT_CLOSED; break; } @@ -6978,7 +6969,7 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, { struct hci_evt_le_create_big_complete *ev = data; struct hci_conn *conn; - __u8 bis_idx = 0; + __u8 i = 0; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); @@ -6996,7 +6987,9 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, conn->iso_qos.bcast.big != ev->handle) continue; - conn->handle = __le16_to_cpu(ev->bis_handle[bis_idx++]); + if (hci_conn_set_handle(conn, + __le16_to_cpu(ev->bis_handle[i++]))) + continue; if (!ev->status) { conn->state = BT_CONNECTED; @@ -7015,7 +7008,7 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, rcu_read_lock(); } - if (!ev->status && !bis_idx) + if (!ev->status && !i) /* If no BISes have been connected for the BIG, * terminate. This is in case all bound connections * have been closed before the BIG creation -- cgit v1.2.3 From f88670161eb205f842989df555d0dd2f9fe2d4b5 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 4 Aug 2023 11:03:43 -0700 Subject: Bluetooth: hci_core: Make hci_is_le_conn_scanning public This moves hci_is_le_conn_scanning to hci_core.h so it can be used by different files without having to duplicate its code. Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 21 +++++++++++++++++++++ net/bluetooth/hci_request.c | 21 --------------------- net/bluetooth/hci_sync.c | 21 --------------------- 3 files changed, 21 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d2a3a2a9fd7d..f4462c325e2a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1372,6 +1372,27 @@ static inline struct hci_conn *hci_lookup_le_connect(struct hci_dev *hdev) return NULL; } +/* Returns true if an le connection is in the scanning state */ +static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type == LE_LINK && c->state == BT_CONNECT && + test_bit(HCI_CONN_SCANNING, &c->flags)) { + rcu_read_unlock(); + return true; + } + } + + rcu_read_unlock(); + + return false; +} + int hci_disconnect(struct hci_conn *conn, __u8 reason); bool hci_setup_sync(struct hci_conn *conn, __u16 handle); void hci_sco_setup(struct hci_conn *conn, __u8 status); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index f7e006a36382..6e023b0104b0 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -629,27 +629,6 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, } } -/* Returns true if an le connection is in the scanning state */ -static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev) -{ - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c; - - rcu_read_lock(); - - list_for_each_entry_rcu(c, &h->list, list) { - if (c->type == LE_LINK && c->state == BT_CONNECT && - test_bit(HCI_CONN_SCANNING, &c->flags)) { - rcu_read_unlock(); - return true; - } - } - - rcu_read_unlock(); - - return false; -} - static void set_random_addr(struct hci_request *req, bdaddr_t *rpa); static int hci_update_random_address(struct hci_request *req, bool require_privacy, bool use_rpa, diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index ec8929e79502..41a8e57d8267 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2672,27 +2672,6 @@ done: return filter_policy; } -/* Returns true if an le connection is in the scanning state */ -static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev) -{ - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c; - - rcu_read_lock(); - - list_for_each_entry_rcu(c, &h->list, list) { - if (c->type == LE_LINK && c->state == BT_CONNECT && - test_bit(HCI_CONN_SCANNING, &c->flags)) { - rcu_read_unlock(); - return true; - } - } - - rcu_read_unlock(); - - return false; -} - static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, u16 interval, u16 window, u8 own_addr_type, u8 filter_policy) -- cgit v1.2.3 From a1f6c3aef13c9e7f8d459bd464e9e34da1342c0c Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 4 Aug 2023 16:23:41 -0700 Subject: Bluetooth: hci_sync: Introduce PTR_UINT/UINT_PTR macros This introduces PTR_UINT/UINT_PTR macros and replace the use of PTR_ERR/ERR_PTR. Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_sync.h | 3 +++ net/bluetooth/hci_conn.c | 19 ++++++++++--------- net/bluetooth/hci_sync.c | 4 ++-- 3 files changed, 15 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index b516a0f4a55b..57eeb07aeb25 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -5,6 +5,9 @@ * Copyright (C) 2021 Intel Corporation */ +#define UINT_PTR(_handle) ((void *)((uintptr_t)_handle)) +#define PTR_UINT(_ptr) ((uintptr_t)((void *)_ptr)) + typedef int (*hci_cmd_sync_work_func_t)(struct hci_dev *hdev, void *data); typedef void (*hci_cmd_sync_work_destroy_t)(struct hci_dev *hdev, void *data, int err); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index ae206eb551f7..4ad6af4e3145 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -872,7 +872,7 @@ static void bis_cleanup(struct hci_conn *conn) static int remove_cig_sync(struct hci_dev *hdev, void *data) { - u8 handle = PTR_ERR(data); + u8 handle = PTR_UINT(data); return hci_le_remove_cig_sync(hdev, handle); } @@ -881,7 +881,8 @@ static int hci_le_remove_cig(struct hci_dev *hdev, u8 handle) { bt_dev_dbg(hdev, "handle 0x%2.2x", handle); - return hci_cmd_sync_queue(hdev, remove_cig_sync, ERR_PTR(handle), NULL); + return hci_cmd_sync_queue(hdev, remove_cig_sync, UINT_PTR(handle), + NULL); } static void find_cis(struct hci_conn *conn, void *data) @@ -1260,7 +1261,7 @@ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn; - u16 handle = PTR_ERR(data); + u16 handle = PTR_UINT(data); conn = hci_conn_hash_lookup_handle(hdev, handle); if (!conn) @@ -1290,7 +1291,7 @@ done: static int hci_connect_le_sync(struct hci_dev *hdev, void *data) { struct hci_conn *conn; - u16 handle = PTR_ERR(data); + u16 handle = PTR_UINT(data); conn = hci_conn_hash_lookup_handle(hdev, handle); if (!conn) @@ -1372,7 +1373,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, clear_bit(HCI_CONN_SCANNING, &conn->flags); err = hci_cmd_sync_queue(hdev, hci_connect_le_sync, - ERR_PTR(conn->handle), + UINT_PTR(conn->handle), create_le_conn_complete); if (err) { hci_conn_del(conn); @@ -1736,7 +1737,7 @@ static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos) static int set_cig_params_sync(struct hci_dev *hdev, void *data) { - u8 cig_id = PTR_ERR(data); + u8 cig_id = PTR_UINT(data); struct hci_conn *conn; struct bt_iso_qos *qos; struct iso_cig_params pdu; @@ -1846,7 +1847,7 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) done: if (hci_cmd_sync_queue(hdev, set_cig_params_sync, - ERR_PTR(qos->ucast.cig), NULL) < 0) + UINT_PTR(qos->ucast.cig), NULL) < 0) return false; return true; @@ -2858,7 +2859,7 @@ u32 hci_conn_get_phy(struct hci_conn *conn) static int abort_conn_sync(struct hci_dev *hdev, void *data) { struct hci_conn *conn; - u16 handle = PTR_ERR(data); + u16 handle = PTR_UINT(data); conn = hci_conn_hash_lookup_handle(hdev, handle); if (!conn) @@ -2898,6 +2899,6 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) } } - return hci_cmd_sync_queue(hdev, abort_conn_sync, ERR_PTR(conn->handle), + return hci_cmd_sync_queue(hdev, abort_conn_sync, UINT_PTR(conn->handle), NULL); } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 41a8e57d8267..5eb30ba21370 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6528,7 +6528,7 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, static int _update_adv_data_sync(struct hci_dev *hdev, void *data) { - u8 instance = PTR_ERR(data); + u8 instance = PTR_UINT(data); return hci_update_adv_data_sync(hdev, instance); } @@ -6536,5 +6536,5 @@ static int _update_adv_data_sync(struct hci_dev *hdev, void *data) int hci_update_adv_data(struct hci_dev *hdev, u8 instance) { return hci_cmd_sync_queue(hdev, _update_adv_data_sync, - ERR_PTR(instance), NULL); + UINT_PTR(instance), NULL); } -- cgit v1.2.3 From b5793de3cfaefef34a1fc9305c9fe3dbcd0ac792 Mon Sep 17 00:00:00 2001 From: Pauli Virtanen Date: Sat, 5 Aug 2023 19:08:42 +0300 Subject: Bluetooth: hci_conn: avoid checking uninitialized CIG/CIS ids The CIS/CIG ids of ISO connections are defined only when the connection is unicast. Fix the lookup functions to check for unicast first. Ensure CIG/CIS IDs have valid value also in state BT_OPEN. Signed-off-by: Pauli Virtanen Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 4 ++-- net/bluetooth/hci_conn.c | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index f4462c325e2a..c53d74236e3a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1219,7 +1219,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK) + if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY)) continue; /* Match CIG ID if set */ @@ -1251,7 +1251,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_cig(struct hci_dev *hdev, rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK) + if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY)) continue; if (handle == c->iso_qos.ucast.cig) { diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 4ad6af4e3145..234746721047 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1866,6 +1866,8 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(-ENOMEM); cis->cleanup = cis_cleanup; cis->dst_type = dst_type; + cis->iso_qos.ucast.cig = BT_ISO_QOS_CIG_UNSET; + cis->iso_qos.ucast.cis = BT_ISO_QOS_CIS_UNSET; } if (cis->state == BT_CONNECTED) -- cgit v1.2.3 From 01b8539655635288dcd46366806abfacbb9b1f6c Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Wed, 9 Aug 2023 22:05:56 +0800 Subject: bpf: Remove unused declaration bpf_link_new_file() Commit a3b80e107894 ("bpf: Allocate ID for bpf_link") removed the implementation but not the declaration. Signed-off-by: Yue Haibing Link: https://lore.kernel.org/r/20230809140556.45836-1-yuehaibing@huawei.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index db3fe5a61b05..cfabbcf47bdb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2120,7 +2120,6 @@ void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); -struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); -- cgit v1.2.3 From e2142825c120d4317abf7160a0fc34b3de532586 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 11 Aug 2023 10:55:27 +0800 Subject: net: tcp: send zero-window ACK when no memory For now, skb will be dropped when no memory, which makes client keep retrans util timeout and it's not friendly to the users. In this patch, we reply an ACK with zero-window in this case to update the snd_wnd of the sender to 0. Therefore, the sender won't timeout the connection and will probe the zero-window with the retransmits. Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 ++- net/ipv4/tcp_input.c | 18 ++++++++++++------ net/ipv4/tcp_output.c | 14 +++++++++++--- 3 files changed, 25 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c2b15f7e5516..be3c858a2ebb 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -164,7 +164,8 @@ enum inet_csk_ack_state_t { ICSK_ACK_TIMER = 2, ICSK_ACK_PUSHED = 4, ICSK_ACK_PUSHED2 = 8, - ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */ + ICSK_ACK_NOW = 16, /* Send the next ACK immediately (once) */ + ICSK_ACK_NOMEM = 32, }; void inet_csk_init_xmit_timers(struct sock *sk, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8e96ebe373d7..2ac059483410 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5059,13 +5059,19 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) /* Ok. In sequence. In window. */ queue_and_out: - if (skb_queue_len(&sk->sk_receive_queue) == 0) - sk_forced_mem_schedule(sk, skb->truesize); - else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { - reason = SKB_DROP_REASON_PROTO_MEM; - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); + if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { + /* TODO: maybe ratelimit these WIN 0 ACK ? */ + inet_csk(sk)->icsk_ack.pending |= + (ICSK_ACK_NOMEM | ICSK_ACK_NOW); + inet_csk_schedule_ack(sk); sk->sk_data_ready(sk); - goto drop; + + if (skb_queue_len(&sk->sk_receive_queue)) { + reason = SKB_DROP_REASON_PROTO_MEM; + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); + goto drop; + } + sk_forced_mem_schedule(sk, skb->truesize); } eaten = tcp_queue_rcv(sk, skb, &fragstolen); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c5412ee77fc8..769a558159ee 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -257,11 +257,19 @@ EXPORT_SYMBOL(tcp_select_initial_window); static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - u32 old_win = tp->rcv_wnd; - u32 cur_win = tcp_receive_window(tp); - u32 new_win = __tcp_select_window(sk); struct net *net = sock_net(sk); + u32 old_win = tp->rcv_wnd; + u32 cur_win, new_win; + + /* Make the window 0 if we failed to queue the data because we + * are out of memory. The window is temporary, so we don't store + * it on the socket. + */ + if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) + return 0; + cur_win = tcp_receive_window(tp); + new_win = __tcp_select_window(sk); if (new_win < cur_win) { /* Danger Will Robinson! * Don't update rcv_wup/rcv_wnd here or else -- cgit v1.2.3 From f614a29d6ca6962139b0eb36b985e3dda80258a6 Mon Sep 17 00:00:00 2001 From: Jörn-Thorben Hinz Date: Fri, 11 Aug 2023 19:33:57 +0200 Subject: net: Remove leftover include from nftables.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit db3685b4046f ("net: remove obsolete members from struct net") removed the uses of struct list_head from this header, without removing the corresponding included header. Signed-off-by: Jörn-Thorben Hinz Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/netns/nftables.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index 8c77832d0240..cc8060c017d5 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -2,8 +2,6 @@ #ifndef _NETNS_NFTABLES_H_ #define _NETNS_NFTABLES_H_ -#include - struct netns_nftables { u8 gencursor; }; -- cgit v1.2.3 From e6d360ff87f005e5b28edc26cb43718244ae7e73 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 11 Aug 2023 17:57:17 +0200 Subject: net: factor out inet{,6}_bind_sk helpers The mptcp protocol maintains an additional socket just to easily invoke a few stream operations on the first subflow. One of them is bind(). Factor out the helpers operating directly on the struct sock, to allow get rid of the above dependency in the next patch without duplicating the existing code. No functional changes intended. Signed-off-by: Paolo Abeni Acked-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- include/net/inet_common.h | 1 + include/net/ipv6.h | 1 + net/ipv4/af_inet.c | 8 ++++++-- net/ipv6/af_inet6.c | 10 +++++++--- 4 files changed, 15 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/inet_common.h b/include/net/inet_common.h index b86b8e21de7f..8e97de700991 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -42,6 +42,7 @@ int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); void inet_sock_destruct(struct sock *sk); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); +int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); /* Don't allocate port at this moment, defer to connect. */ #define BIND_FORCE_ADDRESS_NO_PORT (1 << 0) /* Grab and release socket lock. */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 2acc4c808d45..22643ffc2df8 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1216,6 +1216,7 @@ void inet6_cleanup_sock(struct sock *sk); void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); +int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9b2ca2fcc5a1..2fd23437c1d2 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -431,9 +431,8 @@ int inet_release(struct socket *sock) } EXPORT_SYMBOL(inet_release); -int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct sock *sk = sock->sk; u32 flags = BIND_WITH_LOCK; int err; @@ -454,6 +453,11 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return __inet_bind(sk, uaddr, addr_len, flags); } + +int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +{ + return inet_bind_sk(sock->sk, uaddr, addr_len); +} EXPORT_SYMBOL(inet_bind); int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 9f9c4b838664..3ec0359d5c1f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -435,10 +435,8 @@ out_unlock: goto out; } -/* bind for INET6 API */ -int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct sock *sk = sock->sk; u32 flags = BIND_WITH_LOCK; const struct proto *prot; int err = 0; @@ -462,6 +460,12 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return __inet6_bind(sk, uaddr, addr_len, flags); } + +/* bind for INET6 API */ +int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +{ + return inet6_bind_sk(sock->sk, uaddr, addr_len); +} EXPORT_SYMBOL(inet6_bind); int inet6_release(struct socket *sock) -- cgit v1.2.3 From 71a9a874cd6beb074896519f762741fbc448f5be Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 11 Aug 2023 17:57:19 +0200 Subject: net: factor out __inet_listen_sk() helper The mptcp protocol maintains an additional socket just to easily invoke a few stream operations on the first subflow. One of them is inet_listen(). Factor out an helper operating directly on the (locked) struct sock, to allow get rid of the above dependency in the next patch without duplicating the existing code. No functional changes intended. Signed-off-by: Paolo Abeni Acked-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- include/net/inet_common.h | 1 + net/ipv4/af_inet.c | 38 ++++++++++++++++++++++---------------- 2 files changed, 23 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 8e97de700991..f50a644d87a9 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -40,6 +40,7 @@ int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); +int __inet_listen_sk(struct sock *sk, int backlog); void inet_sock_destruct(struct sock *sk); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 2fd23437c1d2..c59da65f19d2 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -187,24 +187,13 @@ static int inet_autobind(struct sock *sk) return 0; } -/* - * Move a socket into listening state. - */ -int inet_listen(struct socket *sock, int backlog) +int __inet_listen_sk(struct sock *sk, int backlog) { - struct sock *sk = sock->sk; - unsigned char old_state; + unsigned char old_state = sk->sk_state; int err, tcp_fastopen; - lock_sock(sk); - - err = -EINVAL; - if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) - goto out; - - old_state = sk->sk_state; if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN))) - goto out; + return -EINVAL; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state @@ -227,10 +216,27 @@ int inet_listen(struct socket *sock, int backlog) err = inet_csk_listen_start(sk); if (err) - goto out; + return err; + tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); } - err = 0; + return 0; +} + +/* + * Move a socket into listening state. + */ +int inet_listen(struct socket *sock, int backlog) +{ + struct sock *sk = sock->sk; + int err = -EINVAL; + + lock_sock(sk); + + if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) + goto out; + + err = __inet_listen_sk(sk, backlog); out: release_sock(sk); -- cgit v1.2.3 From 9d802da40b7c820deb9c60fc394457ea565cafc8 Mon Sep 17 00:00:00 2001 From: Adrian Moreno Date: Fri, 11 Aug 2023 16:12:48 +0200 Subject: net: openvswitch: add last-action drop reason Create a new drop reason subsystem for openvswitch and add the first drop reason to represent last-action drops. Last-action drops happen when a flow has an empty action list or there is no action that consumes the packet (output, userspace, recirc, etc). It is the most common way in which OVS drops packets. Implementation-wise, most of these skb-consuming actions already call "consume_skb" internally and return directly from within the do_execute_actions() loop so with minimal changes we can assume that any skb that exits the loop normally is a packet drop. Signed-off-by: Adrian Moreno Signed-off-by: David S. Miller --- include/net/dropreason.h | 6 ++++++ net/openvswitch/actions.c | 12 ++++++++++-- net/openvswitch/datapath.c | 16 ++++++++++++++++ net/openvswitch/drop.h | 31 +++++++++++++++++++++++++++++++ 4 files changed, 63 insertions(+), 2 deletions(-) create mode 100644 net/openvswitch/drop.h (limited to 'include') diff --git a/include/net/dropreason.h b/include/net/dropreason.h index 685fb37df8e8..56cb7be92244 100644 --- a/include/net/dropreason.h +++ b/include/net/dropreason.h @@ -23,6 +23,12 @@ enum skb_drop_reason_subsys { */ SKB_DROP_REASON_SUBSYS_MAC80211_MONITOR, + /** + * @SKB_DROP_REASON_SUBSYS_OPENVSWITCH: openvswitch drop reasons, + * see net/openvswitch/drop.h + */ + SKB_DROP_REASON_SUBSYS_OPENVSWITCH, + /** @SKB_DROP_REASON_SUBSYS_NUM: number of subsystems defined */ SKB_DROP_REASON_SUBSYS_NUM }; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index cab1e02b63e0..8c8a7a82f76f 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -27,6 +27,7 @@ #include #include "datapath.h" +#include "drop.h" #include "flow.h" #include "conntrack.h" #include "vport.h" @@ -1036,7 +1037,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, if ((arg->probability != U32_MAX) && (!arg->probability || get_random_u32() > arg->probability)) { if (last) - consume_skb(skb); + ovs_kfree_skb_reason(skb, OVS_DROP_LAST_ACTION); return 0; } @@ -1297,6 +1298,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, if (trace_ovs_do_execute_action_enabled()) trace_ovs_do_execute_action(dp, skb, key, a, rem); + /* Actions that rightfully have to consume the skb should do it + * and return directly. + */ switch (nla_type(a)) { case OVS_ACTION_ATTR_OUTPUT: { int port = nla_get_u32(a); @@ -1332,6 +1336,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, output_userspace(dp, skb, key, a, attr, len, OVS_CB(skb)->cutlen); OVS_CB(skb)->cutlen = 0; + if (nla_is_last(a, rem)) { + consume_skb(skb); + return 0; + } break; case OVS_ACTION_ATTR_HASH: @@ -1485,7 +1493,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, } } - consume_skb(skb); + ovs_kfree_skb_reason(skb, OVS_DROP_LAST_ACTION); return 0; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index a6d2a0b1aa21..d33cb739883f 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -41,6 +41,7 @@ #include #include "datapath.h" +#include "drop.h" #include "flow.h" #include "flow_table.h" #include "flow_netlink.h" @@ -2702,6 +2703,17 @@ static struct pernet_operations ovs_net_ops = { .size = sizeof(struct ovs_net), }; +static const char * const ovs_drop_reasons[] = { +#define S(x) (#x), + OVS_DROP_REASONS(S) +#undef S +}; + +static struct drop_reason_list drop_reason_list_ovs = { + .reasons = ovs_drop_reasons, + .n_reasons = ARRAY_SIZE(ovs_drop_reasons), +}; + static int __init dp_init(void) { int err; @@ -2743,6 +2755,9 @@ static int __init dp_init(void) if (err < 0) goto error_unreg_netdev; + drop_reasons_register_subsys(SKB_DROP_REASON_SUBSYS_OPENVSWITCH, + &drop_reason_list_ovs); + return 0; error_unreg_netdev: @@ -2769,6 +2784,7 @@ static void dp_cleanup(void) ovs_netdev_exit(); unregister_netdevice_notifier(&ovs_dp_device_notifier); unregister_pernet_device(&ovs_net_ops); + drop_reasons_unregister_subsys(SKB_DROP_REASON_SUBSYS_OPENVSWITCH); rcu_barrier(); ovs_vport_exit(); ovs_flow_exit(); diff --git a/net/openvswitch/drop.h b/net/openvswitch/drop.h new file mode 100644 index 000000000000..a5b2b901249b --- /dev/null +++ b/net/openvswitch/drop.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * OpenvSwitch drop reason list. + */ + +#ifndef OPENVSWITCH_DROP_H +#define OPENVSWITCH_DROP_H +#include +#include + +#define OVS_DROP_REASONS(R) \ + R(OVS_DROP_LAST_ACTION) \ + /* deliberate comment for trailing \ */ + +enum ovs_drop_reason { + __OVS_DROP_REASON = SKB_DROP_REASON_SUBSYS_OPENVSWITCH << + SKB_DROP_REASON_SUBSYS_SHIFT, +#define ENUM(x) x, + OVS_DROP_REASONS(ENUM) +#undef ENUM + + OVS_DROP_MAX, +}; + +static inline void +ovs_kfree_skb_reason(struct sk_buff *skb, enum ovs_drop_reason reason) +{ + kfree_skb_reason(skb, (u32)reason); +} + +#endif /* OPENVSWITCH_DROP_H */ -- cgit v1.2.3 From e7bc7db9ba463e763ac6113279cade19da9cb939 Mon Sep 17 00:00:00 2001 From: Eric Garver Date: Fri, 11 Aug 2023 16:12:50 +0200 Subject: net: openvswitch: add explicit drop action From: Eric Garver This adds an explicit drop action. This is used by OVS to drop packets for which it cannot determine what to do. An explicit action in the kernel allows passing the reason _why_ the packet is being dropped or zero to indicate no particular error happened (i.e: OVS intentionally dropped the packet). Since the error codes coming from userspace mean nothing for the kernel, we squash all of them into only two drop reasons: - OVS_DROP_EXPLICIT_WITH_ERROR to indicate a non-zero value was passed - OVS_DROP_EXPLICIT to indicate a zero value was passed (no error) e.g. trace all OVS dropped skbs # perf trace -e skb:kfree_skb --filter="reason >= 0x30000" [..] 106.023 ping/2465 skb:kfree_skb(skbaddr: 0xffffa0e8765f2000, \ location:0xffffffffc0d9b462, protocol: 2048, reason: 196611) reason: 196611 --> 0x30003 (OVS_DROP_EXPLICIT) Also, this patch allows ovs-dpctl.py to add explicit drop actions as: "drop" -> implicit empty-action drop "drop(0)" -> explicit non-error action drop "drop(42)" -> explicit error action drop Signed-off-by: Eric Garver Co-developed-by: Adrian Moreno Signed-off-by: Adrian Moreno Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 ++ net/openvswitch/actions.c | 9 +++++++++ net/openvswitch/drop.h | 2 ++ net/openvswitch/flow_netlink.c | 10 +++++++++- .../testing/selftests/net/openvswitch/ovs-dpctl.py | 22 ++++++++++++++++++---- 5 files changed, 40 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index e94870e77ee9..efc82c318fa2 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -965,6 +965,7 @@ struct check_pkt_len_arg { * start of the packet or at the start of the l3 header depending on the value * of l3 tunnel flag in the tun_flags field of OVS_ACTION_ATTR_ADD_MPLS * argument. + * @OVS_ACTION_ATTR_DROP: Explicit drop action. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -1002,6 +1003,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_CHECK_PKT_LEN, /* Nested OVS_CHECK_PKT_LEN_ATTR_*. */ OVS_ACTION_ATTR_ADD_MPLS, /* struct ovs_action_add_mpls. */ OVS_ACTION_ATTR_DEC_TTL, /* Nested OVS_DEC_TTL_ATTR_*. */ + OVS_ACTION_ATTR_DROP, /* u32 error code. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index bb7aa181da30..e188f32ea96f 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1485,6 +1485,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, return dec_ttl_exception_handler(dp, skb, key, a); break; + + case OVS_ACTION_ATTR_DROP: { + enum ovs_drop_reason reason = nla_get_u32(a) + ? OVS_DROP_EXPLICIT_WITH_ERROR + : OVS_DROP_EXPLICIT; + + ovs_kfree_skb_reason(skb, reason); + return 0; + } } if (unlikely(err)) { diff --git a/net/openvswitch/drop.h b/net/openvswitch/drop.h index b87613ced713..22e66d28c0ca 100644 --- a/net/openvswitch/drop.h +++ b/net/openvswitch/drop.h @@ -11,6 +11,8 @@ #define OVS_DROP_REASONS(R) \ R(OVS_DROP_LAST_ACTION) \ R(OVS_DROP_ACTION_ERROR) \ + R(OVS_DROP_EXPLICIT) \ + R(OVS_DROP_EXPLICIT_WITH_ERROR) \ /* deliberate comment for trailing \ */ enum ovs_drop_reason { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 41116361433d..88965e2068ac 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -38,6 +38,7 @@ #include #include +#include "drop.h" #include "flow_netlink.h" struct ovs_len_tbl { @@ -61,6 +62,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_RECIRC: case OVS_ACTION_ATTR_TRUNC: case OVS_ACTION_ATTR_USERSPACE: + case OVS_ACTION_ATTR_DROP: break; case OVS_ACTION_ATTR_CT: @@ -2394,7 +2396,7 @@ static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) /* Whenever new actions are added, the need to update this * function should be considered. */ - BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23); + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 24); if (!actions) return; @@ -3182,6 +3184,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1, [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), [OVS_ACTION_ATTR_DEC_TTL] = (u32)-1, + [OVS_ACTION_ATTR_DROP] = sizeof(u32), }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3453,6 +3456,11 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, skip_copy = true; break; + case OVS_ACTION_ATTR_DROP: + if (!nla_is_last(a, rem)) + return -EINVAL; + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index fbdac15e3134..912dc8c49085 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -301,6 +301,7 @@ class ovsactions(nla): ("OVS_ACTION_ATTR_CHECK_PKT_LEN", "none"), ("OVS_ACTION_ATTR_ADD_MPLS", "none"), ("OVS_ACTION_ATTR_DEC_TTL", "none"), + ("OVS_ACTION_ATTR_DROP", "uint32"), ) class ctact(nla): @@ -447,6 +448,8 @@ class ovsactions(nla): print_str += "recirc(0x%x)" % int(self.get_attr(field[0])) elif field[0] == "OVS_ACTION_ATTR_TRUNC": print_str += "trunc(%d)" % int(self.get_attr(field[0])) + elif field[0] == "OVS_ACTION_ATTR_DROP": + print_str += "drop(%d)" % int(self.get_attr(field[0])) elif field[1] == "flag": if field[0] == "OVS_ACTION_ATTR_CT_CLEAR": print_str += "ct_clear" @@ -468,10 +471,21 @@ class ovsactions(nla): while len(actstr) != 0: parsed = False if actstr.startswith("drop"): - # for now, drops have no explicit action, so we - # don't need to set any attributes. The final - # act of the processing chain will just drop the packet - return + # If no reason is provided, the implicit drop is used (i.e no + # action). If some reason is given, an explicit action is used. + actstr, reason = parse_extract_field( + actstr, + "drop(", + "([0-9]+)", + lambda x: int(x, 0), + False, + None, + ) + if reason is not None: + self["attrs"].append(["OVS_ACTION_ATTR_DROP", reason]) + parsed = True + else: + return elif parse_starts_block(actstr, "^(\d+)", False, True): actstr, output = parse_extract_field( -- cgit v1.2.3 From 83b5f0253b1ef352f4333c4fb2d24eff23045f6b Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Fri, 11 Aug 2023 13:10:07 +0200 Subject: net: phy: Introduce PSGMII PHY interface mode The PSGMII interface is similar to QSGMII. The main difference is that the PSGMII interface combines five SGMII lines into a single link while in QSGMII only four lines are combined. Similarly to the QSGMII, this interface mode might also needs special handling within the MAC driver. It is commonly used by Qualcomm with their QCA807x PHY series and modern WiSoC-s. Add definitions for the PHY layer to allow to express this type of connection between the MAC and PHY. Signed-off-by: Gabor Juhos Signed-off-by: Robert Marko Signed-off-by: David S. Miller --- Documentation/networking/phy.rst | 4 ++++ drivers/net/phy/phy-core.c | 2 ++ drivers/net/phy/phylink.c | 3 +++ include/linux/phy.h | 4 ++++ 4 files changed, 13 insertions(+) (limited to 'include') diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index b7ac4c64cf67..1283240d7620 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -323,6 +323,10 @@ Some of the interface modes are described below: contrast with the 1000BASE-X phy mode used for Clause 38 and 39 PMDs, this interface mode has different autonegotiation and only supports full duplex. +``PHY_INTERFACE_MODE_PSGMII`` + This is the Penta SGMII mode, it is similar to QSGMII but it combines 5 + SGMII lines into a single link compared to 4 on QSGMII. + Pause frames / flow control =========================== diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index a64186dc53f8..966c93cbe616 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -142,6 +142,8 @@ int phy_interface_num_ports(phy_interface_t interface) case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_QUSGMII: return 4; + case PHY_INTERFACE_MODE_PSGMII: + return 5; case PHY_INTERFACE_MODE_MAX: WARN_ONCE(1, "PHY_INTERFACE_MODE_MAX isn't a valid interface mode"); return 0; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 4f1c8bb199e9..160bce608c34 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -210,6 +210,7 @@ static int phylink_interface_max_speed(phy_interface_t interface) case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_PSGMII: case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_QUSGMII: case PHY_INTERFACE_MODE_SGMII: @@ -475,6 +476,7 @@ unsigned long phylink_get_capabilities(phy_interface_t interface, case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_PSGMII: case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_QUSGMII: case PHY_INTERFACE_MODE_SGMII: @@ -868,6 +870,7 @@ static int phylink_parse_mode(struct phylink *pl, switch (pl->link_config.interface) { case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_PSGMII: case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_QUSGMII: case PHY_INTERFACE_MODE_RGMII: diff --git a/include/linux/phy.h b/include/linux/phy.h index 3c1ceedd1b77..1351b802ffcf 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -110,6 +110,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax + * @PHY_INTERFACE_MODE_PSGMII: Penta SGMII * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX @@ -147,6 +148,7 @@ typedef enum { PHY_INTERFACE_MODE_XGMII, PHY_INTERFACE_MODE_XLGMII, PHY_INTERFACE_MODE_MOCA, + PHY_INTERFACE_MODE_PSGMII, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, PHY_INTERFACE_MODE_100BASEX, @@ -254,6 +256,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "xlgmii"; case PHY_INTERFACE_MODE_MOCA: return "moca"; + case PHY_INTERFACE_MODE_PSGMII: + return "psgmii"; case PHY_INTERFACE_MODE_QSGMII: return "qsgmii"; case PHY_INTERFACE_MODE_TRGMII: -- cgit v1.2.3 From a9f168e4c6e1f623dcf2640b9d76a4f61b9731e5 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 31 May 2023 13:50:21 +0300 Subject: net/mlx5: Check with FW that sync reset completed successfully Even if the PF driver had no error on his part of the sync reset flow, the firmware can see wider picture as it syncs all the PFs in the flow. So add at end of sync reset flow check with firmware by reading MFRL register and initialization segment that the flow had no issue from firmware point of view too. Signed-off-by: Moshe Shemesh Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 3 ++ drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 39 ++++++++++++++++++---- drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h | 2 ++ include/linux/mlx5/mlx5_ifc.h | 3 +- 4 files changed, 40 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 3d82ec890666..af8460bb257b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -212,6 +212,9 @@ static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_a /* On fw_activate action, also driver is reloaded and reinit performed */ *actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT); ret = mlx5_load_one_devl_locked(dev, true); + if (ret) + return ret; + ret = mlx5_fw_reset_verify_fw_complete(dev, extack); break; default: /* Unsupported action should not get to this function */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 4804990b7f22..e87766f91150 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -127,17 +127,23 @@ static int mlx5_fw_reset_get_reset_state_err(struct mlx5_core_dev *dev, if (mlx5_reg_mfrl_query(dev, NULL, NULL, &reset_state)) goto out; + if (!reset_state) + return 0; + switch (reset_state) { case MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION: case MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS: - NL_SET_ERR_MSG_MOD(extack, "Sync reset was already triggered"); + NL_SET_ERR_MSG_MOD(extack, "Sync reset still in progress"); return -EBUSY; - case MLX5_MFRL_REG_RESET_STATE_TIMEOUT: - NL_SET_ERR_MSG_MOD(extack, "Sync reset got timeout"); + case MLX5_MFRL_REG_RESET_STATE_NEG_TIMEOUT: + NL_SET_ERR_MSG_MOD(extack, "Sync reset negotiation timeout"); return -ETIMEDOUT; case MLX5_MFRL_REG_RESET_STATE_NACK: NL_SET_ERR_MSG_MOD(extack, "One of the hosts disabled reset"); return -EPERM; + case MLX5_MFRL_REG_RESET_STATE_UNLOAD_TIMEOUT: + NL_SET_ERR_MSG_MOD(extack, "Sync reset unload timeout"); + return -ETIMEDOUT; } out: @@ -151,7 +157,7 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel, struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; u32 out[MLX5_ST_SZ_DW(mfrl_reg)] = {}; u32 in[MLX5_ST_SZ_DW(mfrl_reg)] = {}; - int err; + int err, rst_res; set_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags); @@ -164,13 +170,34 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel, return 0; clear_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags); - if (err == -EREMOTEIO && MLX5_CAP_MCAM_FEATURE(dev, reset_state)) - return mlx5_fw_reset_get_reset_state_err(dev, extack); + if (err == -EREMOTEIO && MLX5_CAP_MCAM_FEATURE(dev, reset_state)) { + rst_res = mlx5_fw_reset_get_reset_state_err(dev, extack); + return rst_res ? rst_res : err; + } NL_SET_ERR_MSG_MOD(extack, "Sync reset command failed"); return mlx5_cmd_check(dev, err, in, out); } +int mlx5_fw_reset_verify_fw_complete(struct mlx5_core_dev *dev, + struct netlink_ext_ack *extack) +{ + u8 rst_state; + int err; + + err = mlx5_fw_reset_get_reset_state_err(dev, extack); + if (err) + return err; + + rst_state = mlx5_get_fw_rst_state(dev); + if (!rst_state) + return 0; + + mlx5_core_err(dev, "Sync reset did not complete, state=%d\n", rst_state); + NL_SET_ERR_MSG_MOD(extack, "Sync reset did not complete successfully"); + return rst_state; +} + int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev) { return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h index c57465595f7c..ea527d06a85f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h @@ -12,6 +12,8 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel, int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev); int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev); +int mlx5_fw_reset_verify_fw_complete(struct mlx5_core_dev *dev, + struct netlink_ext_ack *extack); void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev); void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev); void mlx5_drain_fw_reset(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 87fd6f9ed82c..9aed7e9b9f29 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10858,8 +10858,9 @@ enum { MLX5_MFRL_REG_RESET_STATE_IDLE = 0, MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1, MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS = 2, - MLX5_MFRL_REG_RESET_STATE_TIMEOUT = 3, + MLX5_MFRL_REG_RESET_STATE_NEG_TIMEOUT = 3, MLX5_MFRL_REG_RESET_STATE_NACK = 4, + MLX5_MFRL_REG_RESET_STATE_UNLOAD_TIMEOUT = 5, }; enum { -- cgit v1.2.3 From 0b4eb603d635ca47c1c372f69b4b96672e4c2c05 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Sun, 2 Jan 2022 14:57:39 +0200 Subject: net/mlx5: Remove unused CAPs mlx5 driver queries the device for VECTOR_CALC and SHAMPO caps, but there isn't any user who requires them. As well as, MLX5_MCAM_REGS_0x9080_0x90FF is queried but not used. Thus, drop all usages and definitions of the mentioned caps above. Signed-off-by: Shay Drory Reviewed-by: Maher Sanalla Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 13 -------- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 -- include/linux/mlx5/device.h | 17 +--------- include/linux/mlx5/mlx5_ifc.h | 43 -------------------------- 4 files changed, 1 insertion(+), 74 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index fb2035a5ec99..c982ce06d7a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -206,12 +206,6 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } - if (MLX5_CAP_GEN(dev, vector_calc)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_VECTOR_CALC); - if (err) - return err; - } - if (MLX5_CAP_GEN(dev, qos)) { err = mlx5_core_get_caps(dev, MLX5_CAP_QOS); if (err) @@ -226,7 +220,6 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, mcam_reg)) { mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_FIRST_128); - mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9080_0x90FF); mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9100_0x917F); } @@ -270,12 +263,6 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } - if (MLX5_CAP_GEN(dev, shampo)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_SHAMPO); - if (err) - return err; - } - if (MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD) { err = mlx5_core_get_caps(dev, MLX5_CAP_MACSEC); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index f4fe06a5042e..cb77b5774aad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1714,7 +1714,6 @@ static const int types[] = { 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, @@ -1723,7 +1722,6 @@ static const int types[] = { MLX5_CAP_VDPA_EMULATION, MLX5_CAP_IPSEC, MLX5_CAP_PORT_SELECTION, - MLX5_CAP_DEV_SHAMPO, MLX5_CAP_MACSEC, MLX5_CAP_ADV_VIRTUALIZATION, MLX5_CAP_CRYPTO, diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 80cc12a9a531..5041965250f6 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1208,9 +1208,7 @@ enum mlx5_cap_type { MLX5_CAP_FLOW_TABLE, MLX5_CAP_ESWITCH_FLOW_TABLE, MLX5_CAP_ESWITCH, - MLX5_CAP_RESERVED, - MLX5_CAP_VECTOR_CALC, - MLX5_CAP_QOS, + MLX5_CAP_QOS = 0xc, MLX5_CAP_DEBUG, MLX5_CAP_RESERVED_14, MLX5_CAP_DEV_MEM, @@ -1220,7 +1218,6 @@ enum mlx5_cap_type { MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, MLX5_CAP_CRYPTO = 0x1a, - MLX5_CAP_DEV_SHAMPO = 0x1d, MLX5_CAP_MACSEC = 0x1f, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, @@ -1239,7 +1236,6 @@ enum mlx5_pcam_feature_groups { enum mlx5_mcam_reg_groups { MLX5_MCAM_REGS_FIRST_128 = 0x0, - MLX5_MCAM_REGS_0x9080_0x90FF = 0x1, MLX5_MCAM_REGS_0x9100_0x917F = 0x2, MLX5_MCAM_REGS_NUM = 0x3, }; @@ -1416,10 +1412,6 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ODP_MAX(mdev, 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) - #define MLX5_CAP_QOS(mdev, cap)\ MLX5_GET(qos_cap, mdev->caps.hca[MLX5_CAP_QOS]->cur, cap) @@ -1436,10 +1428,6 @@ enum mlx5_qcam_feature_groups { MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_FIRST_128], \ mng_access_reg_cap_mask.access_regs.reg) -#define MLX5_CAP_MCAM_REG1(mdev, reg) \ - MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9080_0x90FF], \ - mng_access_reg_cap_mask.access_regs1.reg) - #define MLX5_CAP_MCAM_REG2(mdev, reg) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \ mng_access_reg_cap_mask.access_regs2.reg) @@ -1485,9 +1473,6 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_CRYPTO(mdev, cap)\ MLX5_GET(crypto_cap, (mdev)->caps.hca[MLX5_CAP_CRYPTO]->cur, cap) -#define MLX5_CAP_DEV_SHAMPO(mdev, cap)\ - MLX5_GET(shampo_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_SHAMPO], cap) - #define MLX5_CAP_MACSEC(mdev, cap)\ MLX5_GET(macsec_cap, (mdev)->caps.hca[MLX5_CAP_MACSEC]->cur, cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9aed7e9b9f29..08dcb1f43be7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1314,33 +1314,6 @@ struct mlx5_ifc_odp_cap_bits { u8 reserved_at_120[0x6E0]; }; -struct mlx5_ifc_calc_op { - u8 reserved_at_0[0x10]; - u8 reserved_at_10[0x9]; - u8 op_swap_endianness[0x1]; - u8 op_min[0x1]; - u8 op_xor[0x1]; - u8 op_or[0x1]; - u8 op_and[0x1]; - u8 op_max[0x1]; - u8 op_add[0x1]; -}; - -struct mlx5_ifc_vector_calc_cap_bits { - u8 calc_matrix[0x1]; - u8 reserved_at_1[0x1f]; - u8 reserved_at_20[0x8]; - u8 max_vec_count[0x8]; - u8 reserved_at_30[0xd]; - u8 max_chunk_size[0x3]; - struct mlx5_ifc_calc_op calc0; - struct mlx5_ifc_calc_op calc1; - struct mlx5_ifc_calc_op calc2; - struct mlx5_ifc_calc_op calc3; - - u8 reserved_at_c0[0x720]; -}; - struct mlx5_ifc_tls_cap_bits { u8 tls_1_2_aes_gcm_128[0x1]; u8 tls_1_3_aes_gcm_128[0x1]; @@ -3435,20 +3408,6 @@ struct mlx5_ifc_roce_addr_layout_bits { u8 reserved_at_e0[0x20]; }; -struct mlx5_ifc_shampo_cap_bits { - u8 reserved_at_0[0x3]; - u8 shampo_log_max_reservation_size[0x5]; - u8 reserved_at_8[0x3]; - u8 shampo_log_min_reservation_size[0x5]; - u8 shampo_min_mss_size[0x10]; - - u8 reserved_at_20[0x3]; - u8 shampo_max_log_headers_entry_size[0x5]; - u8 reserved_at_28[0x18]; - - u8 reserved_at_40[0x7c0]; -}; - struct mlx5_ifc_crypto_cap_bits { u8 reserved_at_0[0x3]; u8 synchronize_dek[0x1]; @@ -3484,14 +3443,12 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; struct mlx5_ifc_port_selection_cap_bits port_selection_cap; - struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; struct mlx5_ifc_qos_cap_bits qos_cap; struct mlx5_ifc_debug_cap_bits debug_cap; struct mlx5_ifc_fpga_cap_bits fpga_cap; struct mlx5_ifc_tls_cap_bits tls_cap; struct mlx5_ifc_device_mem_cap_bits device_mem_cap; struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap; - struct mlx5_ifc_shampo_cap_bits shampo_cap; struct mlx5_ifc_macsec_cap_bits macsec_cap; struct mlx5_ifc_crypto_cap_bits crypto_cap; u8 reserved_at_0[0x8000]; -- cgit v1.2.3 From a41cb59117fa12ee17cda5e5c781eecfcb15dc0f Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 11 Jul 2023 15:56:08 +0300 Subject: net/mlx5: Remove unused MAX HCA capabilities Each device cap has two modes: MAX and CUR. The driver maintains a cache of both modes of the capabilities. For most device caps, the MAX cap mode is never used. Hence, remove all driver queries of the MAX mode of the said caps as well as their helper MACROs. Signed-off-by: Shay Drory Reviewed-by: Maher Sanalla Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 34 +++++++------- drivers/net/ethernet/mellanox/mlx5/core/main.c | 14 +++--- .../net/ethernet/mellanox/mlx5/core/mlx5_core.h | 3 ++ include/linux/mlx5/device.h | 52 ---------------------- include/linux/mlx5/driver.h | 1 - 5 files changed, 30 insertions(+), 74 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index c982ce06d7a3..0e394408af75 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -160,13 +160,15 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) } if (MLX5_CAP_GEN(dev, eth_net_offloads)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ETHERNET_OFFLOADS, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_IPOIB_ENHANCED_OFFLOADS); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_IPOIB_ENHANCED_OFFLOADS, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } @@ -191,29 +193,30 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, nic_flow_table) || MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_FLOW_TABLE, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_ESWITCH_MANAGER(dev)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ESWITCH_FLOW_TABLE, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; - err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ESWITCH, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, qos)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_QOS); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_QOS, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, debug)) - mlx5_core_get_caps(dev, MLX5_CAP_DEBUG); + mlx5_core_get_caps_mode(dev, MLX5_CAP_DEBUG, HCA_CAP_OPMOD_GET_CUR); if (MLX5_CAP_GEN(dev, pcam_reg)) mlx5_get_pcam_reg(dev); @@ -227,51 +230,52 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) mlx5_get_qcam_reg(dev); if (MLX5_CAP_GEN(dev, device_memory)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_MEM); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_DEV_MEM, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, event_cap)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_EVENT); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_DEV_EVENT, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, tls_tx) || MLX5_CAP_GEN(dev, tls_rx)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_TLS); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_TLS, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q) { - err = mlx5_core_get_caps(dev, MLX5_CAP_VDPA_EMULATION); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_VDPA_EMULATION, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, ipsec_offload)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_IPSEC); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_IPSEC, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, crypto)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_CRYPTO); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_CRYPTO, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD) { - err = mlx5_core_get_caps(dev, MLX5_CAP_MACSEC); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_MACSEC, HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, adv_virtualization)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ADV_VIRTUALIZATION); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ADV_VIRTUALIZATION, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index cb77b5774aad..15561965d2af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -361,9 +361,8 @@ void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_core_uplink_netdev_event_replay); -static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, - enum mlx5_cap_type cap_type, - enum mlx5_cap_mode cap_mode) +int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, + enum mlx5_cap_mode cap_mode) { u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)]; int out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out); @@ -1620,21 +1619,24 @@ static int mlx5_query_hca_caps_light(struct mlx5_core_dev *dev) return err; if (MLX5_CAP_GEN(dev, eth_net_offloads)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ETHERNET_OFFLOADS, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN(dev, nic_flow_table) || MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) { - err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_FLOW_TABLE, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } if (MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q) { - err = mlx5_core_get_caps(dev, MLX5_CAP_VDPA_EMULATION); + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_VDPA_EMULATION, + HCA_CAP_OPMOD_GET_CUR); if (err) return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 8e2028d20a9e..124352459c23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -174,6 +174,9 @@ static inline int mlx5_flexible_inlen(struct mlx5_core_dev *dev, size_t fixed, #define MLX5_FLEXIBLE_INLEN(dev, fixed, item_size, num_items) \ mlx5_flexible_inlen(dev, fixed, item_size, num_items, __func__, __LINE__) +int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); +int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, + enum mlx5_cap_mode cap_mode); int mlx5_query_hca_caps(struct mlx5_core_dev *dev); int mlx5_query_board_id(struct mlx5_core_dev *dev); int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 5041965250f6..93399802ba77 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1275,10 +1275,6 @@ enum mlx5_qcam_feature_groups { MLX5_GET(per_protocol_networking_offload_caps,\ 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) - #define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS]->cur, cap) @@ -1301,77 +1297,40 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP64_FLOWTABLE(mdev, 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) - #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap) -#define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap) - #define MLX5_CAP_FLOWTABLE_NIC_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit.cap) -#define MLX5_CAP_FLOWTABLE_NIC_TX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit.cap) - #define MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_sniffer.cap) -#define MLX5_CAP_FLOWTABLE_SNIFFER_RX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_sniffer.cap) - #define MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_sniffer.cap) -#define MLX5_CAP_FLOWTABLE_SNIFFER_TX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_sniffer.cap) - #define MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_rdma.cap) -#define MLX5_CAP_FLOWTABLE_RDMA_RX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_rdma.cap) - #define MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_rdma.cap) -#define MLX5_CAP_FLOWTABLE_RDMA_TX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_rdma.cap) - #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_eswitch_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) - #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap) -#define MLX5_CAP_ESW_FLOWTABLE_FDB_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_nic_esw_fdb.cap) - #define MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_egress.cap) -#define MLX5_CAP_ESW_EGRESS_ACL_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_egress.cap) - #define MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_ingress.cap) -#define MLX5_CAP_ESW_INGRESS_ACL_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_ingress.cap) - #define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap) -#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, ft_field_support_2_esw_fdb.cap) - #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) @@ -1380,10 +1339,6 @@ enum mlx5_qcam_feature_groups { MLX5_GET64(flow_table_eswitch_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) - #define MLX5_CAP_PORT_SELECTION(mdev, cap) \ MLX5_GET(port_selection_cap, \ mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->cur, cap) @@ -1396,16 +1351,9 @@ enum mlx5_qcam_feature_groups { MLX5_GET(adv_virtualization_cap, \ mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->cur, cap) -#define MLX5_CAP_ADV_VIRTUALIZATION_MAX(mdev, cap) \ - MLX5_GET(adv_virtualization_cap, \ - mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->max, cap) - #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) -#define MLX5_CAP_FLOWTABLE_PORT_SELECTION_MAX(mdev, cap) \ - MLX5_CAP_PORT_SELECTION_MAX(mdev, flow_table_properties_port_selection.cap) - #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e1c7e502a4fc..c9d82e74daaa 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1022,7 +1022,6 @@ bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev); void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev); -int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); -- cgit v1.2.3 From bb48cf1679d294d4fd3bfaa88289ed9004cbb025 Mon Sep 17 00:00:00 2001 From: David Vernet Date: Mon, 14 Aug 2023 13:59:08 -0500 Subject: bpf: Document struct bpf_struct_ops fields Subsystems that want to implement a struct bpf_struct_ops structure to enable struct_ops maps must currently reverse engineer how the structure works. Given that this is meant to be a way for subsystem maintainers to extend their subsystems using BPF, let's document it to make it a bit easier on them. Signed-off-by: David Vernet Link: https://lore.kernel.org/r/20230814185908.700553-3-void@manifault.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cfabbcf47bdb..eced6400f778 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1550,6 +1550,53 @@ struct bpf_struct_ops_value; struct btf_member; #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 +/** + * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to + * define a BPF_MAP_TYPE_STRUCT_OPS map type composed + * of BPF_PROG_TYPE_STRUCT_OPS progs. + * @verifier_ops: A structure of callbacks that are invoked by the verifier + * when determining whether the struct_ops progs in the + * struct_ops map are valid. + * @init: A callback that is invoked a single time, and before any other + * callback, to initialize the structure. A nonzero return value means + * the subsystem could not be initialized. + * @check_member: When defined, a callback invoked by the verifier to allow + * the subsystem to determine if an entry in the struct_ops map + * is valid. A nonzero return value means that the map is + * invalid and should be rejected by the verifier. + * @init_member: A callback that is invoked for each member of the struct_ops + * map to allow the subsystem to initialize the member. A nonzero + * value means the member could not be initialized. This callback + * is exclusive with the @type, @type_id, @value_type, and + * @value_id fields. + * @reg: A callback that is invoked when the struct_ops map has been + * initialized and is being attached to. Zero means the struct_ops map + * has been successfully registered and is live. A nonzero return value + * means the struct_ops map could not be registered. + * @unreg: A callback that is invoked when the struct_ops map should be + * unregistered. + * @update: A callback that is invoked when the live struct_ops map is being + * updated to contain new values. This callback is only invoked when + * the struct_ops map is loaded with BPF_F_LINK. If not defined, the + * it is assumed that the struct_ops map cannot be updated. + * @validate: A callback that is invoked after all of the members have been + * initialized. This callback should perform static checks on the + * map, meaning that it should either fail or succeed + * deterministically. A struct_ops map that has been validated may + * not necessarily succeed in being registered if the call to @reg + * fails. For example, a valid struct_ops map may be loaded, but + * then fail to be registered due to there being another active + * struct_ops map on the system in the subsystem already. For this + * reason, if this callback is not defined, the check is skipped as + * the struct_ops map will have final verification performed in + * @reg. + * @type: BTF type. + * @value_type: Value type. + * @name: The name of the struct bpf_struct_ops object. + * @func_models: Func models + * @type_id: BTF type id. + * @value_id: BTF value id. + */ struct bpf_struct_ops { const struct bpf_verifier_ops *verifier_ops; int (*init)(struct btf *btf); -- cgit v1.2.3 From 8897562f67b3e61ad736cd5c9f307447d33280e4 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Tue, 15 Aug 2023 09:53:41 +0100 Subject: net: Fix slab-out-of-bounds in inet[6]_steal_sock Kumar reported a KASAN splat in tcp_v6_rcv: bash-5.2# ./test_progs -t btf_skc_cls_ingress ... [ 51.810085] BUG: KASAN: slab-out-of-bounds in tcp_v6_rcv+0x2d7d/0x3440 [ 51.810458] Read of size 2 at addr ffff8881053f038c by task test_progs/226 The problem is that inet[6]_steal_sock accesses sk->sk_protocol without accounting for request or timewait sockets. To fix this we can't just check sock_common->skc_reuseport since that flag is present on timewait sockets. Instead, add a fullsock check to avoid the out of bands access of sk_protocol. Fixes: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign") Reported-by: Kumar Kartikeya Dwivedi Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230815-bpf-next-v2-1-95126eaa4c1b@isovalent.com Signed-off-by: Martin KaFai Lau --- include/net/inet6_hashtables.h | 2 +- include/net/inet_hashtables.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 284b5ce7205d..533a7337865a 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -116,7 +116,7 @@ struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff, if (!sk) return NULL; - if (!prefetched) + if (!prefetched || !sk_fullsock(sk)) return sk; if (sk->sk_protocol == IPPROTO_TCP) { diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 843557223414..3ecfeadbfa06 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -462,7 +462,7 @@ struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff, if (!sk) return NULL; - if (!prefetched) + if (!prefetched || !sk_fullsock(sk)) return sk; if (sk->sk_protocol == IPPROTO_TCP) { -- cgit v1.2.3 From fde9bd4a4d41b65a936d65eb416c1de27cb562f1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Aug 2023 14:47:15 -0700 Subject: genetlink: make genl_info->nlhdr const struct netlink_callback has a const nlh pointer, make the pointer in struct genl_info const as well, to make copying between the two easier. Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230814214723.2924989-3-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/genetlink.h | 2 +- net/ncsi/ncsi-netlink.c | 2 +- net/ncsi/ncsi-netlink.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index ed4622dd4828..0366d0925596 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -104,7 +104,7 @@ struct genl_family { struct genl_info { u32 snd_seq; u32 snd_portid; - struct nlmsghdr * nlhdr; + const struct nlmsghdr * nlhdr; struct genlmsghdr * genlhdr; void * userhdr; struct nlattr ** attrs; diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index d27f4eccce6d..a3a6753a1db7 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -563,7 +563,7 @@ int ncsi_send_netlink_timeout(struct ncsi_request *nr, int ncsi_send_netlink_err(struct net_device *dev, u32 snd_seq, u32 snd_portid, - struct nlmsghdr *nlhdr, + const struct nlmsghdr *nlhdr, int err) { struct nlmsghdr *nlh; diff --git a/net/ncsi/ncsi-netlink.h b/net/ncsi/ncsi-netlink.h index 39a1a9d7bf77..747767ea0aae 100644 --- a/net/ncsi/ncsi-netlink.h +++ b/net/ncsi/ncsi-netlink.h @@ -19,7 +19,7 @@ int ncsi_send_netlink_timeout(struct ncsi_request *nr, int ncsi_send_netlink_err(struct net_device *dev, u32 snd_seq, u32 snd_portid, - struct nlmsghdr *nlhdr, + const struct nlmsghdr *nlhdr, int err); #endif /* __NCSI_NETLINK_H__ */ -- cgit v1.2.3 From bffcc6882a1bb2be8c9420184966f4c2c822078e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Aug 2023 14:47:16 -0700 Subject: genetlink: remove userhdr from struct genl_info Only three families use info->userhdr today and going forward we discourage using fixed headers in new families. So having the pointer to user header in struct genl_info is an overkill. Compute the header pointer at runtime. Reviewed-by: Johannes Berg Reviewed-by: Jiri Pirko Reviewed-by: Aaron Conole Link: https://lore.kernel.org/r/20230814214723.2924989-4-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/block/drbd/drbd_nl.c | 9 +++++---- include/net/genetlink.h | 7 +++++-- net/netlink/genetlink.c | 1 - net/openvswitch/conntrack.c | 2 +- net/openvswitch/datapath.c | 29 ++++++++++++++++------------- net/openvswitch/meter.c | 10 +++++----- net/tipc/netlink_compat.c | 2 +- 7 files changed, 33 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index cddae6f4b00f..d3538bd83fb3 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -159,7 +159,7 @@ static int drbd_msg_sprintf_info(struct sk_buff *skb, const char *fmt, ...) static int drbd_adm_prepare(struct drbd_config_context *adm_ctx, struct sk_buff *skb, struct genl_info *info, unsigned flags) { - struct drbd_genlmsghdr *d_in = info->userhdr; + struct drbd_genlmsghdr *d_in = genl_info_userhdr(info); const u8 cmd = info->genlhdr->cmd; int err; @@ -1396,8 +1396,9 @@ static void drbd_suspend_al(struct drbd_device *device) static bool should_set_defaults(struct genl_info *info) { - unsigned flags = ((struct drbd_genlmsghdr*)info->userhdr)->flags; - return 0 != (flags & DRBD_GENL_F_SET_DEFAULTS); + struct drbd_genlmsghdr *dh = genl_info_userhdr(info); + + return 0 != (dh->flags & DRBD_GENL_F_SET_DEFAULTS); } static unsigned int drbd_al_extents_max(struct drbd_backing_dev *bdev) @@ -4276,7 +4277,7 @@ static void device_to_info(struct device_info *info, int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context adm_ctx; - struct drbd_genlmsghdr *dh = info->userhdr; + struct drbd_genlmsghdr *dh = genl_info_userhdr(info); enum drbd_ret_code retcode; retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE); diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 0366d0925596..9dc21ec15734 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -95,7 +95,6 @@ struct genl_family { * @snd_portid: netlink portid of sender * @nlhdr: netlink message header * @genlhdr: generic netlink message header - * @userhdr: user specific header * @attrs: netlink attributes * @_net: network namespace * @user_ptr: user pointers @@ -106,7 +105,6 @@ struct genl_info { u32 snd_portid; const struct nlmsghdr * nlhdr; struct genlmsghdr * genlhdr; - void * userhdr; struct nlattr ** attrs; possible_net_t _net; void * user_ptr[2]; @@ -123,6 +121,11 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) write_pnet(&info->_net, net); } +static inline void *genl_info_userhdr(const struct genl_info *info) +{ + return (u8 *)info->genlhdr + GENL_HDRLEN; +} + #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) #define GENL_SET_ERR_MSG_FMT(info, msg, args...) \ diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 0d4285688ab9..f98f730bb245 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -943,7 +943,6 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, info.snd_portid = NETLINK_CB(skb).portid; info.nlhdr = nlh; info.genlhdr = nlmsg_data(nlh); - info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN; info.attrs = attrbuf; info.extack = extack; genl_info_net_set(&info, net); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 0cfa1e9482e6..0b9a785dea45 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1605,7 +1605,7 @@ static struct sk_buff * ovs_ct_limit_cmd_reply_start(struct genl_info *info, u8 cmd, struct ovs_header **ovs_reply_header) { - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct sk_buff *skb; skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index d33cb739883f..0a974eeef76e 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -590,7 +590,7 @@ out: static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) { - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; struct sw_flow_actions *acts; @@ -967,7 +967,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct sw_flow *flow = NULL, *new_flow; struct sw_flow_mask mask; struct sk_buff *reply; @@ -1214,7 +1214,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct sw_flow_key key; struct sw_flow *flow; struct sk_buff *reply = NULL; @@ -1315,7 +1315,7 @@ error: static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct net *net = sock_net(skb->sk); struct sw_flow_key key; struct sk_buff *reply; @@ -1374,7 +1374,7 @@ unlock: static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct net *net = sock_net(skb->sk); struct sw_flow_key key; struct sk_buff *reply; @@ -1642,7 +1642,7 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, { struct datapath *dp; - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, + dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), info->attrs); if (IS_ERR(dp)) return; @@ -1935,7 +1935,8 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; ovs_lock(); - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), + info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) goto err_unlock_free; @@ -1968,7 +1969,8 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; ovs_lock(); - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), + info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) goto err_unlock_free; @@ -2003,7 +2005,8 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; ovs_lock(); - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), genl_info_userhdr(info), + info->attrs); if (IS_ERR(dp)) { err = PTR_ERR(dp); goto err_unlock_free; @@ -2246,7 +2249,7 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom) static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct vport_parms parms; struct sk_buff *reply; struct vport *vport; @@ -2348,7 +2351,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; ovs_lock(); - vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); + vport = lookup_vport(sock_net(skb->sk), genl_info_userhdr(info), a); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock_free; @@ -2404,7 +2407,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; ovs_lock(); - vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); + vport = lookup_vport(sock_net(skb->sk), genl_info_userhdr(info), a); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock_free; @@ -2447,7 +2450,7 @@ exit_unlock_free: static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct sk_buff *reply; struct vport *vport; int err; diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index c4ebf810e4b1..cc08e0403909 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -211,7 +211,7 @@ ovs_meter_cmd_reply_start(struct genl_info *info, u8 cmd, struct ovs_header **ovs_reply_header) { struct sk_buff *skb; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) @@ -272,7 +272,7 @@ error: static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info) { - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct ovs_header *ovs_reply_header; struct nlattr *nla, *band_nla; struct sk_buff *reply; @@ -409,7 +409,7 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) struct dp_meter *meter, *old_meter; struct sk_buff *reply; struct ovs_header *ovs_reply_header; - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct dp_meter_table *meter_tbl; struct datapath *dp; int err; @@ -482,7 +482,7 @@ exit_free_meter: static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info) { - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct ovs_header *ovs_reply_header; struct nlattr **a = info->attrs; struct dp_meter *meter; @@ -535,7 +535,7 @@ exit_unlock: static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info) { - struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_header = genl_info_userhdr(info); struct ovs_header *ovs_reply_header; struct nlattr **a = info->attrs; struct dp_meter *old_meter; diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 9b47c8409231..299cd6754f14 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -1294,7 +1294,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) struct tipc_nl_compat_msg msg; struct nlmsghdr *req_nlh; struct nlmsghdr *rep_nlh; - struct tipc_genlmsghdr *req_userhdr = info->userhdr; + struct tipc_genlmsghdr *req_userhdr = genl_info_userhdr(info); memset(&msg, 0, sizeof(msg)); -- cgit v1.2.3 From 9272af109fe65d1a13f28c5c13777b62d3e97e8c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Aug 2023 14:47:17 -0700 Subject: genetlink: add struct genl_info to struct genl_dumpit_info Netlink GET implementations must currently juggle struct genl_info and struct netlink_callback, depending on whether they were called from doit or dumpit. Add genl_info to the dump state and populate the fields. This way implementations can simply pass struct genl_info around. Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230814214723.2924989-5-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/genetlink.h | 8 ++++++++ net/netlink/genetlink.c | 16 ++++++++++++++-- 2 files changed, 22 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 9dc21ec15734..86c8eaaa3a43 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -250,11 +250,13 @@ struct genl_split_ops { * @family: generic netlink family - for internal genl code usage * @op: generic netlink ops - for internal genl code usage * @attrs: netlink attributes + * @info: struct genl_info describing the request */ struct genl_dumpit_info { const struct genl_family *family; struct genl_split_ops op; struct nlattr **attrs; + struct genl_info info; }; static inline const struct genl_dumpit_info * @@ -263,6 +265,12 @@ genl_dumpit_info(struct netlink_callback *cb) return cb->data; } +static inline const struct genl_info * +genl_info_dump(struct netlink_callback *cb) +{ + return &genl_dumpit_info(cb)->info; +} + int genl_register_family(struct genl_family *family); int genl_unregister_family(const struct genl_family *family); void genl_notify(const struct genl_family *family, struct sk_buff *skb, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index f98f730bb245..82ad26970b9b 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -847,6 +847,14 @@ static int genl_start(struct netlink_callback *cb) info->family = ctx->family; info->op = *ops; info->attrs = attrs; + info->info.snd_seq = cb->nlh->nlmsg_seq; + info->info.snd_portid = NETLINK_CB(cb->skb).portid; + info->info.nlhdr = cb->nlh; + info->info.genlhdr = nlmsg_data(cb->nlh); + info->info.attrs = attrs; + genl_info_net_set(&info->info, sock_net(cb->skb->sk)); + info->info.extack = cb->extack; + memset(&info->info.user_ptr, 0, sizeof(info->info.user_ptr)); cb->data = info; if (ops->start) { @@ -865,10 +873,12 @@ static int genl_start(struct netlink_callback *cb) static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { - const struct genl_dumpit_info *info = genl_dumpit_info(cb); + struct genl_dumpit_info *info = cb->data; const struct genl_split_ops *ops = &info->op; int rc; + info->info.extack = cb->extack; + genl_op_lock(info->family); rc = ops->dumpit(skb, cb); genl_op_unlock(info->family); @@ -877,10 +887,12 @@ static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb) static int genl_done(struct netlink_callback *cb) { - const struct genl_dumpit_info *info = genl_dumpit_info(cb); + struct genl_dumpit_info *info = cb->data; const struct genl_split_ops *ops = &info->op; int rc = 0; + info->info.extack = cb->extack; + if (ops->done) { genl_op_lock(info->family); rc = ops->done(cb); -- cgit v1.2.3 From 7288dd2fd4888c85c687f8ded69c280938d1a7b6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Aug 2023 14:47:18 -0700 Subject: genetlink: use attrs from struct genl_info Since dumps carry struct genl_info now, use the attrs pointer from genl_info and remove the one in struct genl_dumpit_info. Reviewed-by: Johannes Berg Reviewed-by: Miquel Raynal Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230814214723.2924989-6-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/wireguard/netlink.c | 2 +- include/net/genetlink.h | 1 - net/devlink/health.c | 4 ++-- net/devlink/leftover.c | 6 +++--- net/devlink/netlink.c | 2 +- net/ethtool/netlink.c | 3 ++- net/ethtool/tunnels.c | 2 +- net/ieee802154/nl802154.c | 4 ++-- net/netlink/genetlink.c | 7 +++---- net/nfc/netlink.c | 4 ++-- net/tipc/netlink_compat.c | 2 +- net/tipc/node.c | 4 ++-- net/tipc/socket.c | 2 +- net/tipc/udp_media.c | 2 +- 14 files changed, 22 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index 6d1bd9f52d02..dc09b75a3248 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -200,7 +200,7 @@ static int wg_get_device_start(struct netlink_callback *cb) { struct wg_device *wg; - wg = lookup_interface(genl_dumpit_info(cb)->attrs, cb->skb); + wg = lookup_interface(genl_info_dump(cb)->attrs, cb->skb); if (IS_ERR(wg)) return PTR_ERR(wg); DUMP_CTX(cb)->wg = wg; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 86c8eaaa3a43..a8a15b9c22c8 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -255,7 +255,6 @@ struct genl_split_ops { struct genl_dumpit_info { const struct genl_family *family; struct genl_split_ops op; - struct nlattr **attrs; struct genl_info info; }; diff --git a/net/devlink/health.c b/net/devlink/health.c index a85bdec34801..638cad8d5c65 100644 --- a/net/devlink/health.c +++ b/net/devlink/health.c @@ -390,7 +390,7 @@ static int devlink_nl_health_reporter_get_dump_one(struct sk_buff *msg, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); - const struct genl_dumpit_info *info = genl_dumpit_info(cb); + const struct genl_info *info = genl_info_dump(cb); struct devlink_health_reporter *reporter; unsigned long port_index_end = ULONG_MAX; struct nlattr **attrs = info->attrs; @@ -1264,7 +1264,7 @@ out: static struct devlink_health_reporter * devlink_health_reporter_get_from_cb(struct netlink_callback *cb) { - const struct genl_dumpit_info *info = genl_dumpit_info(cb); + const struct genl_info *info = genl_info_dump(cb); struct devlink_health_reporter *reporter; struct nlattr **attrs = info->attrs; struct devlink *devlink; diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index 3883a90d32bb..72ba8a716525 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -5201,7 +5201,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct nlattr *chunks_attr, *region_attr, *snapshot_attr; u64 ret_offset, start_offset, end_offset = U64_MAX; - struct nlattr **attrs = info->attrs; + struct nlattr **attrs = info->info.attrs; struct devlink_port *port = NULL; devlink_chunk_fill_t *region_cb; struct devlink_region *region; @@ -5224,8 +5224,8 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto out_unlock; } - if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { - index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + if (attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) { diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index a9b43b0c5959..72a5005a64cd 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -228,7 +228,7 @@ static int devlink_nl_inst_iter_dumpit(struct sk_buff *msg, int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb, devlink_nl_dump_one_func_t *dump_one) { - const struct genl_dumpit_info *info = genl_dumpit_info(cb); + const struct genl_info *info = genl_info_dump(cb); struct nlattr **attrs = info->attrs; int flags = NLM_F_MULTI; diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index ae344f1b0bbd..9fc7c41f4786 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -538,7 +538,8 @@ static int ethnl_default_start(struct netlink_callback *cb) goto free_req_info; } - ret = ethnl_default_parse(req_info, info->attrs, sock_net(cb->skb->sk), + ret = ethnl_default_parse(req_info, info->info.attrs, + sock_net(cb->skb->sk), ops, cb->extack, false); if (req_info->dev) { /* We ignore device specification in dump requests but as the diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c index 05f752557b5e..b4ce47dd2aa6 100644 --- a/net/ethtool/tunnels.c +++ b/net/ethtool/tunnels.c @@ -219,7 +219,7 @@ int ethnl_tunnel_info_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx; - struct nlattr **tb = info->attrs; + struct nlattr **tb = info->info.attrs; int ret; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index d610c1886160..1a265a421308 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -262,7 +262,7 @@ nl802154_prepare_wpan_dev_dump(struct sk_buff *skb, if (!cb->args[0]) { *wpan_dev = __cfg802154_wpan_dev_from_attrs(sock_net(skb->sk), - info->attrs); + info->info.attrs); if (IS_ERR(*wpan_dev)) { err = PTR_ERR(*wpan_dev); goto out_unlock; @@ -570,7 +570,7 @@ static int nl802154_dump_wpan_phy_parse(struct sk_buff *skb, struct nl802154_dump_wpan_phy_state *state) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); - struct nlattr **tb = info->attrs; + struct nlattr **tb = info->info.attrs; if (tb[NL802154_ATTR_WPAN_PHY]) state->filter_wpan_phy = nla_get_u32(tb[NL802154_ATTR_WPAN_PHY]); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 82ad26970b9b..d47879d5a74c 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -846,7 +846,6 @@ static int genl_start(struct netlink_callback *cb) } info->family = ctx->family; info->op = *ops; - info->attrs = attrs; info->info.snd_seq = cb->nlh->nlmsg_seq; info->info.snd_portid = NETLINK_CB(cb->skb).portid; info->info.nlhdr = cb->nlh; @@ -864,7 +863,7 @@ static int genl_start(struct netlink_callback *cb) } if (rc) { - genl_family_rcv_msg_attrs_free(info->attrs); + genl_family_rcv_msg_attrs_free(info->info.attrs); genl_dumpit_info_free(info); cb->data = NULL; } @@ -898,7 +897,7 @@ static int genl_done(struct netlink_callback *cb) rc = ops->done(cb); genl_op_unlock(info->family); } - genl_family_rcv_msg_attrs_free(info->attrs); + genl_family_rcv_msg_attrs_free(info->info.attrs); genl_dumpit_info_free(info); return rc; } @@ -1387,7 +1386,7 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; - struct nlattr **tb = info->attrs; + struct nlattr **tb = info->info.attrs; const struct genl_family *rt; struct genl_op_iter i; int err; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index e9ac6a6f934e..aa1dbf654c3e 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -110,10 +110,10 @@ static struct nfc_dev *__get_device_from_cb(struct netlink_callback *cb) struct nfc_dev *dev; u32 idx; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->info.attrs[NFC_ATTR_DEVICE_INDEX]) return ERR_PTR(-EINVAL); - idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + idx = nla_get_u32(info->info.attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 299cd6754f14..5bc076f2fa74 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -208,7 +208,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, goto err_out; } - info.attrs = attrbuf; + info.info.attrs = attrbuf; if (nlmsg_len(cb.nlh) > 0) { err = nlmsg_parse_deprecated(cb.nlh, GENL_HDRLEN, attrbuf, diff --git a/net/tipc/node.c b/net/tipc/node.c index a9c5b6594889..3105abe97bb9 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2662,7 +2662,7 @@ static int __tipc_nl_add_node_links(struct net *net, struct tipc_nl_msg *msg, int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - struct nlattr **attrs = genl_dumpit_info(cb)->attrs; + struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs; struct nlattr *link[TIPC_NLA_LINK_MAX + 1]; struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *node; @@ -2870,7 +2870,7 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb, int err; if (!prev_node) { - struct nlattr **attrs = genl_dumpit_info(cb)->attrs; + struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs; struct nlattr *mon[TIPC_NLA_MON_MAX + 1]; if (!attrs[TIPC_NLA_MON]) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ef8e5139a873..bb1118d02f95 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3791,7 +3791,7 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb) struct tipc_sock *tsk; if (!tsk_portid) { - struct nlattr **attrs = genl_dumpit_info(cb)->attrs; + struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs; struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1]; if (!attrs[TIPC_NLA_SOCK]) diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 926232557e77..f892b0903dba 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -465,7 +465,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) int i; if (!bid && !skip_cnt) { - struct nlattr **attrs = genl_dumpit_info(cb)->attrs; + struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs; struct net *net = sock_net(skb->sk); struct nlattr *battrs[TIPC_NLA_BEARER_MAX + 1]; char *bname; -- cgit v1.2.3 From 5c670a010de46687ed27553602d8131ce4d7a9fb Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Aug 2023 14:47:19 -0700 Subject: genetlink: add a family pointer to struct genl_info Having family in struct genl_info is quite useful. It cuts down the number of arguments which need to be passed to helpers which already take struct genl_info. Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230814214723.2924989-7-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/genetlink.h | 4 ++-- net/netlink/genetlink.c | 21 ++++++++++++--------- 2 files changed, 14 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index a8a15b9c22c8..6b858c4cba5b 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -93,6 +93,7 @@ struct genl_family { * struct genl_info - receiving information * @snd_seq: sending sequence number * @snd_portid: netlink portid of sender + * @family: generic netlink family * @nlhdr: netlink message header * @genlhdr: generic netlink message header * @attrs: netlink attributes @@ -103,6 +104,7 @@ struct genl_family { struct genl_info { u32 snd_seq; u32 snd_portid; + const struct genl_family *family; const struct nlmsghdr * nlhdr; struct genlmsghdr * genlhdr; struct nlattr ** attrs; @@ -247,13 +249,11 @@ struct genl_split_ops { /** * struct genl_dumpit_info - info that is available during dumpit op call - * @family: generic netlink family - for internal genl code usage * @op: generic netlink ops - for internal genl code usage * @attrs: netlink attributes * @info: struct genl_info describing the request */ struct genl_dumpit_info { - const struct genl_family *family; struct genl_split_ops op; struct genl_info info; }; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d47879d5a74c..8315d31b53db 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -844,8 +844,8 @@ static int genl_start(struct netlink_callback *cb) genl_family_rcv_msg_attrs_free(attrs); return -ENOMEM; } - info->family = ctx->family; info->op = *ops; + info->info.family = ctx->family; info->info.snd_seq = cb->nlh->nlmsg_seq; info->info.snd_portid = NETLINK_CB(cb->skb).portid; info->info.nlhdr = cb->nlh; @@ -872,11 +872,12 @@ static int genl_start(struct netlink_callback *cb) static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { - struct genl_dumpit_info *info = cb->data; - const struct genl_split_ops *ops = &info->op; + struct genl_dumpit_info *dump_info = cb->data; + const struct genl_split_ops *ops = &dump_info->op; + struct genl_info *info = &dump_info->info; int rc; - info->info.extack = cb->extack; + info->extack = cb->extack; genl_op_lock(info->family); rc = ops->dumpit(skb, cb); @@ -886,19 +887,20 @@ static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb) static int genl_done(struct netlink_callback *cb) { - struct genl_dumpit_info *info = cb->data; - const struct genl_split_ops *ops = &info->op; + struct genl_dumpit_info *dump_info = cb->data; + const struct genl_split_ops *ops = &dump_info->op; + struct genl_info *info = &dump_info->info; int rc = 0; - info->info.extack = cb->extack; + info->extack = cb->extack; if (ops->done) { genl_op_lock(info->family); rc = ops->done(cb); genl_op_unlock(info->family); } - genl_family_rcv_msg_attrs_free(info->info.attrs); - genl_dumpit_info_free(info); + genl_family_rcv_msg_attrs_free(info->attrs); + genl_dumpit_info_free(dump_info); return rc; } @@ -952,6 +954,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, info.snd_seq = nlh->nlmsg_seq; info.snd_portid = NETLINK_CB(skb).portid; + info.family = family; info.nlhdr = nlh; info.genlhdr = nlmsg_data(nlh); info.attrs = attrbuf; -- cgit v1.2.3 From 5aa51d9f889ca61201044b28677eb60236b0d746 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Aug 2023 14:47:20 -0700 Subject: genetlink: add genlmsg_iput() API Add some APIs and helpers required for convenient construction of replies and notifications based on struct genl_info. Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230814214723.2924989-8-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/genetlink.h | 54 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 53 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 6b858c4cba5b..e18a4c0d69ee 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -113,7 +113,7 @@ struct genl_info { struct netlink_ext_ack *extack; }; -static inline struct net *genl_info_net(struct genl_info *info) +static inline struct net *genl_info_net(const struct genl_info *info) { return read_pnet(&info->_net); } @@ -270,6 +270,32 @@ genl_info_dump(struct netlink_callback *cb) return &genl_dumpit_info(cb)->info; } +/** + * genl_info_init_ntf() - initialize genl_info for notifications + * @info: genl_info struct to set up + * @family: pointer to the genetlink family + * @cmd: command to be used in the notification + * + * Initialize a locally declared struct genl_info to pass to various APIs. + * Intended to be used when creating notifications. + */ +static inline void +genl_info_init_ntf(struct genl_info *info, const struct genl_family *family, + u8 cmd) +{ + struct genlmsghdr *hdr = (void *) &info->user_ptr[0]; + + memset(info, 0, sizeof(*info)); + info->family = family; + info->genlhdr = hdr; + hdr->cmd = cmd; +} + +static inline bool genl_info_is_ntf(const struct genl_info *info) +{ + return !info->nlhdr; +} + int genl_register_family(struct genl_family *family); int genl_unregister_family(const struct genl_family *family); void genl_notify(const struct genl_family *family, struct sk_buff *skb, @@ -278,6 +304,32 @@ void genl_notify(const struct genl_family *family, struct sk_buff *skb, void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, const struct genl_family *family, int flags, u8 cmd); +static inline void * +__genlmsg_iput(struct sk_buff *skb, const struct genl_info *info, int flags) +{ + return genlmsg_put(skb, info->snd_portid, info->snd_seq, info->family, + flags, info->genlhdr->cmd); +} + +/** + * genlmsg_iput - start genetlink message based on genl_info + * @skb: skb in which message header will be placed + * @info: genl_info as provided to do/dump handlers + * + * Convenience wrapper which starts a genetlink message based on + * information in user request. @info should be either the struct passed + * by genetlink core to do/dump handlers (when constructing replies to + * such requests) or a struct initialized by genl_info_init_ntf() + * when constructing notifications. + * + * Returns pointer to new genetlink header. + */ +static inline void * +genlmsg_iput(struct sk_buff *skb, const struct genl_info *info) +{ + return __genlmsg_iput(skb, info, 0); +} + /** * genlmsg_nlhdr - Obtain netlink header from user specified header * @user_hdr: user header as returned from genlmsg_put() -- cgit v1.2.3 From c274af2242693f59f00851b3660a21b10bcd76cc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:33 +0000 Subject: inet: introduce inet->inet_flags Various inet fields are currently racy. do_ip_setsockopt() and do_ip_getsockopt() are mostly holding the socket lock, but some (fast) paths do not. Use a new inet->inet_flags to hold atomic bits in the series. Remove inet->cmsg_flags, and use instead 9 bits from inet_flags. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/inet_sock.h | 55 +++++++++++++++++++++++++------- net/ipv4/ip_sockglue.c | 84 ++++++++++++++++++------------------------------- net/ipv4/ping.c | 5 +-- net/ipv4/raw.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/udp.c | 2 +- net/l2tp/l2tp_ip.c | 2 +- 8 files changed, 83 insertions(+), 71 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 0bb32bfc6183..e3b35b0015f3 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -194,6 +194,7 @@ struct rtable; * @inet_rcv_saddr - Bound local IPv4 addr * @inet_dport - Destination port * @inet_num - Local port + * @inet_flags - various atomic flags * @inet_saddr - Sending source * @uc_ttl - Unicast TTL * @inet_sport - Source port @@ -218,11 +219,11 @@ struct inet_sock { #define inet_dport sk.__sk_common.skc_dport #define inet_num sk.__sk_common.skc_num + unsigned long inet_flags; __be32 inet_saddr; __s16 uc_ttl; - __u16 cmsg_flags; - struct ip_options_rcu __rcu *inet_opt; __be16 inet_sport; + struct ip_options_rcu __rcu *inet_opt; __u16 inet_id; __u8 tos; @@ -259,16 +260,48 @@ struct inet_sock { #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ #define IPCORK_ALLFRAG 2 /* always fragment (for ipv6 for now) */ +enum { + INET_FLAGS_PKTINFO = 0, + INET_FLAGS_TTL = 1, + INET_FLAGS_TOS = 2, + INET_FLAGS_RECVOPTS = 3, + INET_FLAGS_RETOPTS = 4, + INET_FLAGS_PASSSEC = 5, + INET_FLAGS_ORIGDSTADDR = 6, + INET_FLAGS_CHECKSUM = 7, + INET_FLAGS_RECVFRAGSIZE = 8, +}; + /* cmsg flags for inet */ -#define IP_CMSG_PKTINFO BIT(0) -#define IP_CMSG_TTL BIT(1) -#define IP_CMSG_TOS BIT(2) -#define IP_CMSG_RECVOPTS BIT(3) -#define IP_CMSG_RETOPTS BIT(4) -#define IP_CMSG_PASSSEC BIT(5) -#define IP_CMSG_ORIGDSTADDR BIT(6) -#define IP_CMSG_CHECKSUM BIT(7) -#define IP_CMSG_RECVFRAGSIZE BIT(8) +#define IP_CMSG_PKTINFO BIT(INET_FLAGS_PKTINFO) +#define IP_CMSG_TTL BIT(INET_FLAGS_TTL) +#define IP_CMSG_TOS BIT(INET_FLAGS_TOS) +#define IP_CMSG_RECVOPTS BIT(INET_FLAGS_RECVOPTS) +#define IP_CMSG_RETOPTS BIT(INET_FLAGS_RETOPTS) +#define IP_CMSG_PASSSEC BIT(INET_FLAGS_PASSSEC) +#define IP_CMSG_ORIGDSTADDR BIT(INET_FLAGS_ORIGDSTADDR) +#define IP_CMSG_CHECKSUM BIT(INET_FLAGS_CHECKSUM) +#define IP_CMSG_RECVFRAGSIZE BIT(INET_FLAGS_RECVFRAGSIZE) + +#define IP_CMSG_ALL (IP_CMSG_PKTINFO | IP_CMSG_TTL | \ + IP_CMSG_TOS | IP_CMSG_RECVOPTS | \ + IP_CMSG_RETOPTS | IP_CMSG_PASSSEC | \ + IP_CMSG_ORIGDSTADDR | IP_CMSG_CHECKSUM | \ + IP_CMSG_RECVFRAGSIZE) + +static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet) +{ + return READ_ONCE(inet->inet_flags) & IP_CMSG_ALL; +} + +#define inet_test_bit(nr, sk) \ + test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet_set_bit(nr, sk) \ + set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet_clear_bit(nr, sk) \ + clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet_assign_bit(nr, sk, val) \ + assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) static inline bool sk_is_inet(struct sock *sk) { diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index d41bce8927b2..66f55f3db5ec 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -171,8 +171,10 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, int tlen, int offset) { - struct inet_sock *inet = inet_sk(sk); - unsigned int flags = inet->cmsg_flags; + unsigned long flags = inet_cmsg_flags(inet_sk(sk)); + + if (!flags) + return; /* Ordered by supposed usage frequency */ if (flags & IP_CMSG_PKTINFO) { @@ -568,7 +570,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; - if (inet_sk(sk)->cmsg_flags) + if (inet_cmsg_flags(inet_sk(sk))) ip_cmsg_recv(msg, skb); } @@ -635,7 +637,7 @@ EXPORT_SYMBOL(ip_sock_set_mtu_discover); void ip_sock_set_pktinfo(struct sock *sk) { lock_sock(sk); - inet_sk(sk)->cmsg_flags |= IP_CMSG_PKTINFO; + inet_set_bit(PKTINFO, sk); release_sock(sk); } EXPORT_SYMBOL(ip_sock_set_pktinfo); @@ -990,67 +992,43 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, break; } case IP_PKTINFO: - if (val) - inet->cmsg_flags |= IP_CMSG_PKTINFO; - else - inet->cmsg_flags &= ~IP_CMSG_PKTINFO; + inet_assign_bit(PKTINFO, sk, val); break; case IP_RECVTTL: - if (val) - inet->cmsg_flags |= IP_CMSG_TTL; - else - inet->cmsg_flags &= ~IP_CMSG_TTL; + inet_assign_bit(TTL, sk, val); break; case IP_RECVTOS: - if (val) - inet->cmsg_flags |= IP_CMSG_TOS; - else - inet->cmsg_flags &= ~IP_CMSG_TOS; + inet_assign_bit(TOS, sk, val); break; case IP_RECVOPTS: - if (val) - inet->cmsg_flags |= IP_CMSG_RECVOPTS; - else - inet->cmsg_flags &= ~IP_CMSG_RECVOPTS; + inet_assign_bit(RECVOPTS, sk, val); break; case IP_RETOPTS: - if (val) - inet->cmsg_flags |= IP_CMSG_RETOPTS; - else - inet->cmsg_flags &= ~IP_CMSG_RETOPTS; + inet_assign_bit(RETOPTS, sk, val); break; case IP_PASSSEC: - if (val) - inet->cmsg_flags |= IP_CMSG_PASSSEC; - else - inet->cmsg_flags &= ~IP_CMSG_PASSSEC; + inet_assign_bit(PASSSEC, sk, val); break; case IP_RECVORIGDSTADDR: - if (val) - inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR; - else - inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR; + inet_assign_bit(ORIGDSTADDR, sk, val); break; case IP_CHECKSUM: if (val) { - if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) { + if (!(inet_test_bit(CHECKSUM, sk))) { inet_inc_convert_csum(sk); - inet->cmsg_flags |= IP_CMSG_CHECKSUM; + inet_set_bit(CHECKSUM, sk); } } else { - if (inet->cmsg_flags & IP_CMSG_CHECKSUM) { + if (inet_test_bit(CHECKSUM, sk)) { inet_dec_convert_csum(sk); - inet->cmsg_flags &= ~IP_CMSG_CHECKSUM; + inet_clear_bit(CHECKSUM, sk); } } break; case IP_RECVFRAGSIZE: if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM) goto e_inval; - if (val) - inet->cmsg_flags |= IP_CMSG_RECVFRAGSIZE; - else - inet->cmsg_flags &= ~IP_CMSG_RECVFRAGSIZE; + inet_assign_bit(RECVFRAGSIZE, sk, val); break; case IP_TOS: /* This sets both TOS and Precedence */ __ip_sock_set_tos(sk, val); @@ -1415,7 +1393,7 @@ e_inval: void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); - bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) || + bool prepare = inet_test_bit(PKTINFO, sk) || ipv6_sk_rxinfo(sk); if (prepare && skb_rtable(skb)) { @@ -1601,31 +1579,31 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, return 0; } case IP_PKTINFO: - val = (inet->cmsg_flags & IP_CMSG_PKTINFO) != 0; + val = inet_test_bit(PKTINFO, sk); break; case IP_RECVTTL: - val = (inet->cmsg_flags & IP_CMSG_TTL) != 0; + val = inet_test_bit(TTL, sk); break; case IP_RECVTOS: - val = (inet->cmsg_flags & IP_CMSG_TOS) != 0; + val = inet_test_bit(TOS, sk); break; case IP_RECVOPTS: - val = (inet->cmsg_flags & IP_CMSG_RECVOPTS) != 0; + val = inet_test_bit(RECVOPTS, sk); break; case IP_RETOPTS: - val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0; + val = inet_test_bit(RETOPTS, sk); break; case IP_PASSSEC: - val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0; + val = inet_test_bit(PASSSEC, sk); break; case IP_RECVORIGDSTADDR: - val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0; + val = inet_test_bit(ORIGDSTADDR, sk); break; case IP_CHECKSUM: - val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0; + val = inet_test_bit(CHECKSUM, sk); break; case IP_RECVFRAGSIZE: - val = (inet->cmsg_flags & IP_CMSG_RECVFRAGSIZE) != 0; + val = inet_test_bit(RECVFRAGSIZE, sk); break; case IP_TOS: val = inet->tos; @@ -1737,7 +1715,7 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, msg.msg_controllen = len; msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; - if (inet->cmsg_flags & IP_CMSG_PKTINFO) { + if (inet_test_bit(PKTINFO, sk)) { struct in_pktinfo info; info.ipi_addr.s_addr = inet->inet_rcv_saddr; @@ -1745,11 +1723,11 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, info.ipi_ifindex = inet->mc_index; put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } - if (inet->cmsg_flags & IP_CMSG_TTL) { + if (inet_test_bit(TTL, sk)) { int hlim = inet->mc_ttl; put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim); } - if (inet->cmsg_flags & IP_CMSG_TOS) { + if (inet_test_bit(TOS, sk)) { int tos = inet->rcv_tos; put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 25dd78cee179..7e8702cb6634 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -894,7 +894,7 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, *addr_len = sizeof(*sin); } - if (isk->cmsg_flags) + if (inet_cmsg_flags(isk)) ip_cmsg_recv(msg, skb); #if IS_ENABLED(CONFIG_IPV6) @@ -921,7 +921,8 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, if (skb->protocol == htons(ETH_P_IPV6) && inet6_sk(sk)->rxopt.all) pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb); - else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags) + else if (skb->protocol == htons(ETH_P_IP) && + inet_cmsg_flags(isk)) ip_cmsg_recv(msg, skb); #endif } else { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index cb381f5aa464..e6e813f4aa31 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -767,7 +767,7 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } - if (inet->cmsg_flags) + if (inet_cmsg_flags(inet)) ip_cmsg_recv(msg, skb); if (flags & MSG_TRUNC) copied = skb->len; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 3e2f29c14fa8..4b791133989c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1870,7 +1870,7 @@ try_again: if (udp_sk(sk)->gro_enabled) udp_cmsg_recv(msg, sk, skb); - if (inet->cmsg_flags) + if (inet_cmsg_flags(inet)) ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off); err = copied; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index d80d6024cafa..41ebc4e57473 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -524,7 +524,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) } else { ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin->sin6_addr); - if (inet_sk(sk)->cmsg_flags) + if (inet_cmsg_flags(inet_sk(sk))) ip_cmsg_recv(msg, skb); } } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1ea01b0d9be3..ebc6ae47cfea 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -420,7 +420,7 @@ try_again: ip6_datagram_recv_common_ctl(sk, msg, skb); if (is_udp4) { - if (inet->cmsg_flags) + if (inet_cmsg_flags(inet)) ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off); } else { diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index f9073bc7281f..9a2a9ed3ba47 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -552,7 +552,7 @@ static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg, memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } - if (inet->cmsg_flags) + if (inet_cmsg_flags(inet)) ip_cmsg_recv(msg, skb); if (flags & MSG_TRUNC) copied = skb->len; -- cgit v1.2.3 From 6b5f43ea08150e7ff72f734545101c58489ead5b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:35 +0000 Subject: inet: move inet->recverr to inet->inet_flags IP_RECVERR socket option can now be set/get without locking the socket. This patch potentially avoid data-races around inet->recverr. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/inet_sock.h | 5 +++-- net/dccp/ipv4.c | 4 +--- net/ipv4/inet_diag.c | 2 +- net/ipv4/ip_sockglue.c | 23 ++++++++++------------- net/ipv4/ping.c | 2 +- net/ipv4/raw.c | 14 ++++++++------ net/ipv4/tcp_ipv4.c | 5 ++--- net/ipv4/udp.c | 5 +++-- net/sctp/input.c | 2 +- 9 files changed, 30 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index e3b35b0015f3..552188aa5a2d 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -230,8 +230,7 @@ struct inet_sock { __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; - __u8 recverr:1, - is_icsk:1, + __u8 is_icsk:1, freebind:1, hdrincl:1, mc_loop:1, @@ -270,6 +269,8 @@ enum { INET_FLAGS_ORIGDSTADDR = 6, INET_FLAGS_CHECKSUM = 7, INET_FLAGS_RECVFRAGSIZE = 8, + + INET_FLAGS_RECVERR = 9, }; /* cmsg flags for inet */ diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8e919cfe6e23..8dd6837c476a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -247,7 +247,6 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) const u8 offset = iph->ihl << 2; const struct dccp_hdr *dh; struct dccp_sock *dp; - struct inet_sock *inet; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; @@ -361,8 +360,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) * --ANK (980905) */ - inet = inet_sk(sk); - if (!sock_owned_by_user(sk) && inet->recverr) { + if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) { sk->sk_err = err; sk_error_report(sk); } else { /* Only an error on timeout */ diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f7426926a104..25d5f76b66bd 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -182,7 +182,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, r->idiag_inode = sock_i_ino(sk); memset(&inet_sockopt, 0, sizeof(inet_sockopt)); - inet_sockopt.recverr = inet->recverr; + inet_sockopt.recverr = inet_test_bit(RECVERR, sk); inet_sockopt.is_icsk = inet->is_icsk; inet_sockopt.freebind = inet->freebind; inet_sockopt.hdrincl = inet->hdrincl; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 69b87518348a..8283d862a9db 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -446,12 +446,11 @@ EXPORT_SYMBOL_GPL(ip_icmp_error); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info) { - struct inet_sock *inet = inet_sk(sk); struct sock_exterr_skb *serr; struct iphdr *iph; struct sk_buff *skb; - if (!inet->recverr) + if (!inet_test_bit(RECVERR, sk)) return; skb = alloc_skb(sizeof(struct iphdr), GFP_ATOMIC); @@ -617,9 +616,7 @@ EXPORT_SYMBOL(ip_sock_set_freebind); void ip_sock_set_recverr(struct sock *sk) { - lock_sock(sk); - inet_sk(sk)->recverr = true; - release_sock(sk); + inet_set_bit(RECVERR, sk); } EXPORT_SYMBOL(ip_sock_set_recverr); @@ -978,6 +975,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, return -EINVAL; inet_assign_bit(RECVFRAGSIZE, sk, val); return 0; + case IP_RECVERR: + inet_assign_bit(RECVERR, sk, val); + if (!val) + skb_queue_purge(&sk->sk_error_queue); + return 0; } err = 0; @@ -1064,11 +1066,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, goto e_inval; inet->pmtudisc = val; break; - case IP_RECVERR: - inet->recverr = !!val; - if (!val) - skb_queue_purge(&sk->sk_error_queue); - break; case IP_RECVERR_RFC4884: if (val < 0 || val > 1) goto e_inval; @@ -1575,6 +1572,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_RECVFRAGSIZE: val = inet_test_bit(RECVFRAGSIZE, sk); goto copyval; + case IP_RECVERR: + val = inet_test_bit(RECVERR, sk); + goto copyval; } if (needs_rtnl) @@ -1649,9 +1649,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, } break; } - case IP_RECVERR: - val = inet->recverr; - break; case IP_RECVERR_RFC4884: val = inet->recverr_rfc4884; break; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 7e8702cb6634..75e0aee35eb7 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -580,7 +580,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info) * RFC1122: OK. Passes ICMP errors back to application, as per * 4.1.3.3. */ - if ((family == AF_INET && !inet_sock->recverr) || + if ((family == AF_INET && !inet_test_bit(RECVERR, sk)) || (family == AF_INET6 && !inet6_sk(sk)->recverr)) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index e6e813f4aa31..f4c27dc5714b 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -203,8 +203,9 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) struct inet_sock *inet = inet_sk(sk); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; - int err = 0; int harderr = 0; + bool recverr; + int err = 0; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) ipv4_sk_update_pmtu(skb, sk, info); @@ -218,7 +219,8 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) 2. Socket is connected (otherwise the error indication is useless without ip_recverr and error is hard. */ - if (!inet->recverr && sk->sk_state != TCP_ESTABLISHED) + recverr = inet_test_bit(RECVERR, sk); + if (!recverr && sk->sk_state != TCP_ESTABLISHED) return; switch (type) { @@ -245,7 +247,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) } } - if (inet->recverr) { + if (recverr) { const struct iphdr *iph = (const struct iphdr *)skb->data; u8 *payload = skb->data + (iph->ihl << 2); @@ -254,7 +256,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) ip_icmp_error(sk, skb, err, 0, info, payload); } - if (inet->recverr || harderr) { + if (recverr || harderr) { sk->sk_err = err; sk_error_report(sk); } @@ -413,7 +415,7 @@ error_free: kfree_skb(skb); error: IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); - if (err == -ENOBUFS && !inet->recverr) + if (err == -ENOBUFS && !inet_test_bit(RECVERR, sk)) err = 0; return err; } @@ -645,7 +647,7 @@ back_from_confirm: ip_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) { err = ip_push_pending_frames(sk, &fl4); - if (err == -ENOBUFS && !inet->recverr) + if (err == -ENOBUFS && !inet_test_bit(RECVERR, sk)) err = 0; } release_sock(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5b18a048f613..2a662d5f3072 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -477,7 +477,6 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) const struct iphdr *iph = (const struct iphdr *)skb->data; struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); struct tcp_sock *tp; - struct inet_sock *inet; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; @@ -625,8 +624,8 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) * --ANK (980905) */ - inet = inet_sk(sk); - if (!sock_owned_by_user(sk) && inet->recverr) { + if (!sock_owned_by_user(sk) && + inet_test_bit(RECVERR, sk)) { WRITE_ONCE(sk->sk_err, err); sk_error_report(sk); } else { /* Only an error on timeout */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 4b791133989c..0794a2c46a56 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -779,7 +779,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) (u8 *)(uh+1)); goto out; } - if (!inet->recverr) { + if (!inet_test_bit(RECVERR, sk)) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else @@ -962,7 +962,8 @@ csum_partial: send: err = ip_send_skb(sock_net(sk), skb); if (err) { - if (err == -ENOBUFS && !inet->recverr) { + if (err == -ENOBUFS && + !inet_test_bit(RECVERR, sk)) { UDP_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); err = 0; diff --git a/net/sctp/input.c b/net/sctp/input.c index 2613c4d74b16..17fcaa9b0df9 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -581,7 +581,7 @@ static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb, default: return; } - if (!sock_owned_by_user(sk) && inet_sk(sk)->recverr) { + if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) { sk->sk_err = err; sk_error_report(sk); } else { /* Only an error on timeout */ -- cgit v1.2.3 From 8e8cfb114d9f1e2efddb892f993c1ad61635c85e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:36 +0000 Subject: inet: move inet->recverr_rfc4884 to inet->inet_flags IP_RECVERR_RFC4884 socket option can now be set/read without locking the socket. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/inet_sock.h | 2 +- net/ipv4/inet_diag.c | 2 +- net/ipv4/ip_sockglue.c | 18 +++++++++--------- 3 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 552188aa5a2d..c01f1f64a861 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -238,7 +238,6 @@ struct inet_sock { mc_all:1, nodefrag:1; __u8 bind_address_no_port:1, - recverr_rfc4884:1, defer_connect:1; /* Indicates that fastopen_connect is set * and cookie exists so we defer connect * until first data frame is written @@ -271,6 +270,7 @@ enum { INET_FLAGS_RECVFRAGSIZE = 8, INET_FLAGS_RECVERR = 9, + INET_FLAGS_RECVERR_RFC4884 = 10, }; /* cmsg flags for inet */ diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 25d5f76b66bd..6255d6fdbc80 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -191,7 +191,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, inet_sockopt.mc_all = inet->mc_all; inet_sockopt.nodefrag = inet->nodefrag; inet_sockopt.bind_address_no_port = inet->bind_address_no_port; - inet_sockopt.recverr_rfc4884 = inet->recverr_rfc4884; + inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk); inet_sockopt.defer_connect = inet->defer_connect; if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt), &inet_sockopt)) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 8283d862a9db..f75f44ad7b11 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -433,7 +433,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, serr->port = port; if (skb_pull(skb, payload - skb->data)) { - if (inet_sk(sk)->recverr_rfc4884) + if (inet_test_bit(RECVERR_RFC4884, sk)) ipv4_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884); skb_reset_transport_header(skb); @@ -980,6 +980,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, if (!val) skb_queue_purge(&sk->sk_error_queue); return 0; + case IP_RECVERR_RFC4884: + if (val < 0 || val > 1) + return -EINVAL; + inet_assign_bit(RECVERR_RFC4884, sk, val); + return 0; } err = 0; @@ -1066,11 +1071,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, goto e_inval; inet->pmtudisc = val; break; - case IP_RECVERR_RFC4884: - if (val < 0 || val > 1) - goto e_inval; - inet->recverr_rfc4884 = !!val; - break; case IP_MULTICAST_TTL: if (sk->sk_type == SOCK_STREAM) goto e_inval; @@ -1575,6 +1575,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_RECVERR: val = inet_test_bit(RECVERR, sk); goto copyval; + case IP_RECVERR_RFC4884: + val = inet_test_bit(RECVERR_RFC4884, sk); + goto copyval; } if (needs_rtnl) @@ -1649,9 +1652,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, } break; } - case IP_RECVERR_RFC4884: - val = inet->recverr_rfc4884; - break; case IP_MULTICAST_TTL: val = inet->mc_ttl; break; -- cgit v1.2.3 From 3f7e753206bb20fc098b44ec40001befd1fe18d1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:37 +0000 Subject: inet: move inet->freebind to inet->inet_flags IP_FREEBIND socket option can now be set/read without locking the socket. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Reviewed-by: Matthieu Baerts Signed-off-by: David S. Miller --- include/net/inet_sock.h | 5 +++-- include/net/ipv6.h | 3 ++- net/ipv4/inet_diag.c | 2 +- net/ipv4/ip_sockglue.c | 21 +++++++++------------ net/ipv6/ipv6_sockglue.c | 4 ++-- net/mptcp/sockopt.c | 7 ++++--- net/sctp/protocol.c | 2 +- 7 files changed, 22 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c01f1f64a861..d6ba963534b4 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -231,7 +231,6 @@ struct inet_sock { __u8 mc_ttl; __u8 pmtudisc; __u8 is_icsk:1, - freebind:1, hdrincl:1, mc_loop:1, transparent:1, @@ -271,6 +270,7 @@ enum { INET_FLAGS_RECVERR = 9, INET_FLAGS_RECVERR_RFC4884 = 10, + INET_FLAGS_FREEBIND = 11, }; /* cmsg flags for inet */ @@ -423,7 +423,8 @@ static inline bool inet_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) || - inet->freebind || inet->transparent; + test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || + inet->transparent; } static inline bool inet_addr_valid_or_nonlocal(struct net *net, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 22643ffc2df8..fd570d77588e 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -937,7 +937,8 @@ static inline bool ipv6_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return net->ipv6.sysctl.ip_nonlocal_bind || - inet->freebind || inet->transparent; + test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || + inet->transparent; } /* Sysctl settings for net ipv6.auto_flowlabels */ diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 6255d6fdbc80..5a96f4f28eca 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -184,7 +184,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, memset(&inet_sockopt, 0, sizeof(inet_sockopt)); inet_sockopt.recverr = inet_test_bit(RECVERR, sk); inet_sockopt.is_icsk = inet->is_icsk; - inet_sockopt.freebind = inet->freebind; + inet_sockopt.freebind = inet_test_bit(FREEBIND, sk); inet_sockopt.hdrincl = inet->hdrincl; inet_sockopt.mc_loop = inet->mc_loop; inet_sockopt.transparent = inet->transparent; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index f75f44ad7b11..6af843106312 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -608,9 +608,7 @@ EXPORT_SYMBOL(ip_sock_set_tos); void ip_sock_set_freebind(struct sock *sk) { - lock_sock(sk); - inet_sk(sk)->freebind = true; - release_sock(sk); + inet_set_bit(FREEBIND, sk); } EXPORT_SYMBOL(ip_sock_set_freebind); @@ -985,6 +983,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, return -EINVAL; inet_assign_bit(RECVERR_RFC4884, sk, val); return 0; + case IP_FREEBIND: + if (optlen < 1) + return -EINVAL; + inet_assign_bit(FREEBIND, sk, val); + return 0; } err = 0; @@ -1310,12 +1313,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, inet->mc_all = val; break; - case IP_FREEBIND: - if (optlen < 1) - goto e_inval; - inet->freebind = !!val; - break; - case IP_IPSEC_POLICY: case IP_XFRM_POLICY: err = -EPERM; @@ -1578,6 +1575,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_RECVERR_RFC4884: val = inet_test_bit(RECVERR_RFC4884, sk); goto copyval; + case IP_FREEBIND: + val = inet_test_bit(FREEBIND, sk); + goto copyval; } if (needs_rtnl) @@ -1737,9 +1737,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, len -= msg.msg_controllen; return copy_to_sockptr(optlen, &len, sizeof(int)); } - case IP_FREEBIND: - val = inet->freebind; - break; case IP_TRANSPARENT: val = inet->transparent; break; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ca377159967c..3eb38436f8d4 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -641,7 +641,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optlen < sizeof(int)) goto e_inval; /* we also don't have a separate freebind bit for IPV6 */ - inet_sk(sk)->freebind = valbool; + inet_assign_bit(FREEBIND, sk, valbool); retv = 0; break; @@ -1334,7 +1334,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, break; case IPV6_FREEBIND: - val = inet_sk(sk)->freebind; + val = inet_test_bit(FREEBIND, sk); break; case IPV6_RECVORIGDSTADDR: diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 21bc46acbe38..ffbe2f5f5b44 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -419,7 +419,8 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, inet_sk(sk)->transparent = inet_sk(ssk)->transparent; break; case IPV6_FREEBIND: - inet_sk(sk)->freebind = inet_sk(ssk)->freebind; + inet_assign_bit(FREEBIND, sk, + inet_test_bit(FREEBIND, ssk)); break; } @@ -704,7 +705,7 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o switch (optname) { case IP_FREEBIND: - issk->freebind = inet_sk(sk)->freebind; + inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); break; case IP_TRANSPARENT: issk->transparent = inet_sk(sk)->transparent; @@ -1441,7 +1442,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) __tcp_sock_set_nodelay(ssk, !!msk->nodelay); inet_sk(ssk)->transparent = inet_sk(sk)->transparent; - inet_sk(ssk)->freebind = inet_sk(sk)->freebind; + inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); } static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 33c0895e101c..2185f44198de 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -360,7 +360,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) ret = inet_addr_type_table(net, addr->v4.sin_addr.s_addr, tb_id); if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && - !sp->inet.freebind && + !inet_test_bit(FREEBIND, sk) && !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind)) return 0; -- cgit v1.2.3 From cafbe182a467bf6799242fd7468438cf1ab833dc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:38 +0000 Subject: inet: move inet->hdrincl to inet->inet_flags IP_HDRINCL socket option can now be set/read without locking the socket. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/inet_sock.h | 4 ++-- net/ipv4/af_inet.c | 2 +- net/ipv4/inet_diag.c | 2 +- net/ipv4/ip_output.c | 5 +++-- net/ipv4/ip_sockglue.c | 18 ++++++++---------- net/ipv4/raw.c | 10 +++------- net/ipv4/route.c | 8 ++++---- net/ipv6/af_inet6.c | 2 +- net/ipv6/ip6_output.c | 5 +++-- net/ipv6/raw.c | 16 +++++----------- 10 files changed, 31 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index d6ba963534b4..ad1895e32e7d 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -231,7 +231,6 @@ struct inet_sock { __u8 mc_ttl; __u8 pmtudisc; __u8 is_icsk:1, - hdrincl:1, mc_loop:1, transparent:1, mc_all:1, @@ -271,6 +270,7 @@ enum { INET_FLAGS_RECVERR = 9, INET_FLAGS_RECVERR_RFC4884 = 10, INET_FLAGS_FREEBIND = 11, + INET_FLAGS_HDRINCL = 12, }; /* cmsg flags for inet */ @@ -397,7 +397,7 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { __u8 flags = 0; - if (inet_sk(sk)->transparent || inet_sk(sk)->hdrincl) + if (inet_sk(sk)->transparent || inet_test_bit(HDRINCL, sk)) flags |= FLOWI_FLAG_ANYSRC; return flags; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c59da65f19d2..5785fe9de58c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -338,7 +338,7 @@ lookup_protocol: if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) - inet->hdrincl = 1; + inet_set_bit(HDRINCL, sk); } if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 5a96f4f28eca..98f3eb0ce16a 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -185,7 +185,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, inet_sockopt.recverr = inet_test_bit(RECVERR, sk); inet_sockopt.is_icsk = inet->is_icsk; inet_sockopt.freebind = inet_test_bit(FREEBIND, sk); - inet_sockopt.hdrincl = inet->hdrincl; + inet_sockopt.hdrincl = inet_test_bit(HDRINCL, sk); inet_sockopt.mc_loop = inet->mc_loop; inet_sockopt.transparent = inet->transparent; inet_sockopt.mc_all = inet->mc_all; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index f28c87533a46..8f396eada1b6 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1039,7 +1039,7 @@ static int __ip_append_data(struct sock *sk, } } } else if ((flags & MSG_SPLICE_PAGES) && length) { - if (inet->hdrincl) + if (inet_test_bit(HDRINCL, sk)) return -EPERM; if (rt->dst.dev->features & NETIF_F_SG && getfrag == ip_generic_getfrag) @@ -1467,7 +1467,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ - if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_type == SOCK_RAW && + !inet_test_bit(HDRINCL, sk)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 6af843106312..763456fd4f4f 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -988,6 +988,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, return -EINVAL; inet_assign_bit(FREEBIND, sk, val); return 0; + case IP_HDRINCL: + if (sk->sk_type != SOCK_RAW) + return -ENOPROTOOPT; + inet_assign_bit(HDRINCL, sk, val); + return 0; } err = 0; @@ -1052,13 +1057,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, goto e_inval; inet->uc_ttl = val; break; - case IP_HDRINCL: - if (sk->sk_type != SOCK_RAW) { - err = -ENOPROTOOPT; - break; - } - inet->hdrincl = val ? 1 : 0; - break; case IP_NODEFRAG: if (sk->sk_type != SOCK_RAW) { err = -ENOPROTOOPT; @@ -1578,6 +1576,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_FREEBIND: val = inet_test_bit(FREEBIND, sk); goto copyval; + case IP_HDRINCL: + val = inet_test_bit(HDRINCL, sk); + goto copyval; } if (needs_rtnl) @@ -1625,9 +1626,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, inet->uc_ttl); break; } - case IP_HDRINCL: - val = inet->hdrincl; - break; case IP_NODEFRAG: val = inet->nodefrag; break; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index f4c27dc5714b..4b5db5d1edc2 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -251,7 +251,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) const struct iphdr *iph = (const struct iphdr *)skb->data; u8 *payload = skb->data + (iph->ihl << 2); - if (inet->hdrincl) + if (inet_test_bit(HDRINCL, sk)) payload = skb->data; ip_icmp_error(sk, skb, err, 0, info, payload); } @@ -491,12 +491,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (len > 0xFFFF) goto out; - /* hdrincl should be READ_ONCE(inet->hdrincl) - * but READ_ONCE() doesn't work with bit fields. - * Doing this indirectly yields the same result. - */ - hdrincl = inet->hdrincl; - hdrincl = READ_ONCE(hdrincl); + hdrincl = inet_test_bit(HDRINCL, sk); + /* * Check the flags. */ diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 92fede388d52..a4e153dd615b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -515,13 +515,12 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4, __u8 scope = RT_SCOPE_UNIVERSE; if (sk) { - const struct inet_sock *inet = inet_sk(sk); - oif = sk->sk_bound_dev_if; mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); - prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; + prot = inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : + sk->sk_protocol; } flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope, @@ -555,7 +554,8 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk) & IPTOS_RT_MASK, ip_sock_rt_scope(sk), - inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, + inet_test_bit(HDRINCL, sk) ? + IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk), daddr, inet->inet_saddr, 0, 0, sk->sk_uid); rcu_read_unlock(); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3ec0359d5c1f..ed9d207080ac 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -205,7 +205,7 @@ lookup_protocol: if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) - inet->hdrincl = 1; + inet_set_bit(HDRINCL, sk); } sk->sk_destruct = inet6_sock_destruct; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index bc96559bbf0f..f8a1f6bb3f87 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1591,7 +1591,7 @@ emsgsize: } } } else if ((flags & MSG_SPLICE_PAGES) && length) { - if (inet_sk(sk)->hdrincl) + if (inet_test_bit(HDRINCL, sk)) return -EPERM; if (rt->dst.dev->features & NETIF_F_SG && getfrag == ip_generic_getfrag) @@ -1995,7 +1995,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; - if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_socket->type == SOCK_RAW && + !inet_test_bit(HDRINCL, sk)) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ea16734f5e1f..0eae7661a85c 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -291,7 +291,6 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int err; int harderr; @@ -315,7 +314,7 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, } if (np->recverr) { u8 *payload = skb->data; - if (!inet->hdrincl) + if (!inet_test_bit(HDRINCL, sk)) payload += offset; ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload); } @@ -406,7 +405,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) skb->len, inet->inet_num, 0)); - if (inet->hdrincl) { + if (inet_test_bit(HDRINCL, sk)) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); @@ -762,12 +761,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; - /* hdrincl should be READ_ONCE(inet->hdrincl) - * but READ_ONCE() doesn't work with bit fields. - * Doing this indirectly yields the same result. - */ - hdrincl = inet->hdrincl; - hdrincl = READ_ONCE(hdrincl); + hdrincl = inet_test_bit(HDRINCL, sk); /* * Get and verify the address. @@ -1000,7 +994,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_HDRINCL: if (sk->sk_type != SOCK_RAW) return -EINVAL; - inet_sk(sk)->hdrincl = !!val; + inet_assign_bit(HDRINCL, sk, val); return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && @@ -1068,7 +1062,7 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case IPV6_HDRINCL: - val = inet_sk(sk)->hdrincl; + val = inet_test_bit(HDRINCL, sk); break; case IPV6_CHECKSUM: /* -- cgit v1.2.3 From b09bde5c3554d58cb711dac55a10ecc56d436966 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:39 +0000 Subject: inet: move inet->mc_loop to inet->inet_frags IP_MULTICAST_LOOP socket option can now be set/read without locking the socket. v3: fix build bot error reported in ipvs set_mcast_loop() Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/inet_sock.h | 2 +- net/core/sock.c | 2 +- net/ipv4/af_inet.c | 2 +- net/ipv4/inet_diag.c | 2 +- net/ipv4/ip_sockglue.c | 16 ++++++++-------- net/ipv4/udp_tunnel_core.c | 2 +- net/ipv6/af_inet6.c | 2 +- net/netfilter/ipvs/ip_vs_sync.c | 4 +--- net/sctp/socket.c | 2 +- 9 files changed, 16 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index ad1895e32e7d..6c4eeca59f60 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -231,7 +231,6 @@ struct inet_sock { __u8 mc_ttl; __u8 pmtudisc; __u8 is_icsk:1, - mc_loop:1, transparent:1, mc_all:1, nodefrag:1; @@ -271,6 +270,7 @@ enum { INET_FLAGS_RECVERR_RFC4884 = 10, INET_FLAGS_FREEBIND = 11, INET_FLAGS_HDRINCL = 12, + INET_FLAGS_MC_LOOP = 13, }; /* cmsg flags for inet */ diff --git a/net/core/sock.c b/net/core/sock.c index 525619776c6f..22d94394335f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -767,7 +767,7 @@ bool sk_mc_loop(struct sock *sk) return true; switch (sk->sk_family) { case AF_INET: - return inet_sk(sk)->mc_loop; + return inet_test_bit(MC_LOOP, sk); #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return inet6_sk(sk)->mc_loop; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5785fe9de58c..e847822df9b6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -356,7 +356,7 @@ lookup_protocol: sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; - inet->mc_loop = 1; + inet_set_bit(MC_LOOP, sk); inet->mc_ttl = 1; inet->mc_all = 1; inet->mc_index = 0; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 98f3eb0ce16a..cc797261893b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -186,7 +186,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, inet_sockopt.is_icsk = inet->is_icsk; inet_sockopt.freebind = inet_test_bit(FREEBIND, sk); inet_sockopt.hdrincl = inet_test_bit(HDRINCL, sk); - inet_sockopt.mc_loop = inet->mc_loop; + inet_sockopt.mc_loop = inet_test_bit(MC_LOOP, sk); inet_sockopt.transparent = inet->transparent; inet_sockopt.mc_all = inet->mc_all; inet_sockopt.nodefrag = inet->nodefrag; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 763456fd4f4f..be569032b612 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -993,6 +993,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; inet_assign_bit(HDRINCL, sk, val); return 0; + case IP_MULTICAST_LOOP: + if (optlen < 1) + return -EINVAL; + inet_assign_bit(MC_LOOP, sk, val); + return 0; } err = 0; @@ -1083,11 +1088,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, goto e_inval; inet->mc_ttl = val; break; - case IP_MULTICAST_LOOP: - if (optlen < 1) - goto e_inval; - inet->mc_loop = !!val; - break; case IP_UNICAST_IF: { struct net_device *dev = NULL; @@ -1579,6 +1579,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_HDRINCL: val = inet_test_bit(HDRINCL, sk); goto copyval; + case IP_MULTICAST_LOOP: + val = inet_test_bit(MC_LOOP, sk); + goto copyval; } if (needs_rtnl) @@ -1653,9 +1656,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_MULTICAST_TTL: val = inet->mc_ttl; break; - case IP_MULTICAST_LOOP: - val = inet->mc_loop; - break; case IP_UNICAST_IF: val = (__force int)htonl((__u32) inet->uc_index); break; diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 5f8104cf082d..9b18f371af0d 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -63,7 +63,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct sock *sk = sock->sk; /* Disable multicast loopback */ - inet_sk(sk)->mc_loop = 0; + inet_clear_bit(MC_LOOP, sk); /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */ inet_inc_convert_csum(sk); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index ed9d207080ac..8e9d4c1f0e83 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -229,7 +229,7 @@ lookup_protocol: */ inet->uc_ttl = -1; - inet->mc_loop = 1; + inet_set_bit(MC_LOOP, sk); inet->mc_ttl = 1; inet->mc_index = 0; RCU_INIT_POINTER(inet->mc_list, NULL); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 264f2f87a437..da5af28ff57b 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1297,11 +1297,9 @@ static void set_sock_size(struct sock *sk, int mode, int val) */ static void set_mcast_loop(struct sock *sk, u_char loop) { - struct inet_sock *inet = inet_sk(sk); - /* setsockopt(sock, SOL_IP, IP_MULTICAST_LOOP, &loop, sizeof(loop)); */ lock_sock(sk); - inet->mc_loop = loop ? 1 : 0; + inet_assign_bit(MC_LOOP, sk, loop); #ifdef CONFIG_IP_VS_IPV6 if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6e3d28aa587c..04b390892827 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9482,7 +9482,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_id = get_random_u16(); newinet->uc_ttl = inet->uc_ttl; - newinet->mc_loop = 1; + inet_set_bit(MC_LOOP, newsk); newinet->mc_ttl = 1; newinet->mc_index = 0; newinet->mc_list = NULL; -- cgit v1.2.3 From 307b4ac6dc18436076cdd314aa3e556be077bf2d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:40 +0000 Subject: inet: move inet->mc_all to inet->inet_frags IP_MULTICAST_ALL socket option can now be set/read without locking the socket. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/inet_sock.h | 2 +- net/ipv4/af_inet.c | 2 +- net/ipv4/igmp.c | 2 +- net/ipv4/inet_diag.c | 2 +- net/ipv4/ip_sockglue.c | 22 +++++++++++----------- 5 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 6c4eeca59f60..fffd34fa6a7c 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -232,7 +232,6 @@ struct inet_sock { __u8 pmtudisc; __u8 is_icsk:1, transparent:1, - mc_all:1, nodefrag:1; __u8 bind_address_no_port:1, defer_connect:1; /* Indicates that fastopen_connect is set @@ -271,6 +270,7 @@ enum { INET_FLAGS_FREEBIND = 11, INET_FLAGS_HDRINCL = 12, INET_FLAGS_MC_LOOP = 13, + INET_FLAGS_MC_ALL = 14, }; /* cmsg flags for inet */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e847822df9b6..47c9cdd7687f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -358,7 +358,7 @@ lookup_protocol: inet->uc_ttl = -1; inet_set_bit(MC_LOOP, sk); inet->mc_ttl = 1; - inet->mc_all = 1; + inet_set_bit(MC_ALL, sk); inet->mc_index = 0; inet->mc_list = NULL; inet->rcv_tos = 0; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 48ff5f13e797..0c9e768e5628 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2658,7 +2658,7 @@ int ip_mc_sf_allow(const struct sock *sk, __be32 loc_addr, __be32 rmt_addr, (sdif && pmc->multi.imr_ifindex == sdif))) break; } - ret = inet->mc_all; + ret = inet_test_bit(MC_ALL, sk); if (!pmc) goto unlock; psl = rcu_dereference(pmc->sflist); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index cc797261893b..e009dab80c35 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -188,7 +188,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, inet_sockopt.hdrincl = inet_test_bit(HDRINCL, sk); inet_sockopt.mc_loop = inet_test_bit(MC_LOOP, sk); inet_sockopt.transparent = inet->transparent; - inet_sockopt.mc_all = inet->mc_all; + inet_sockopt.mc_all = inet_test_bit(MC_ALL, sk); inet_sockopt.nodefrag = inet->nodefrag; inet_sockopt.bind_address_no_port = inet->bind_address_no_port; inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index be569032b612..2f27c30a4ecc 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -998,6 +998,14 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, return -EINVAL; inet_assign_bit(MC_LOOP, sk, val); return 0; + case IP_MULTICAST_ALL: + if (optlen < 1) + return -EINVAL; + if (val != 0 && val != 1) + return -EINVAL; + inet_assign_bit(MC_ALL, sk, val); + return 0; + } err = 0; @@ -1303,14 +1311,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, else err = ip_set_mcast_msfilter(sk, optval, optlen); break; - case IP_MULTICAST_ALL: - if (optlen < 1) - goto e_inval; - if (val != 0 && val != 1) - goto e_inval; - inet->mc_all = val; - break; - case IP_IPSEC_POLICY: case IP_XFRM_POLICY: err = -EPERM; @@ -1582,6 +1582,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_MULTICAST_LOOP: val = inet_test_bit(MC_LOOP, sk); goto copyval; + case IP_MULTICAST_ALL: + val = inet_test_bit(MC_ALL, sk); + goto copyval; } if (needs_rtnl) @@ -1694,9 +1697,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, else err = ip_get_mcast_msfilter(sk, optval, optlen, len); goto out; - case IP_MULTICAST_ALL: - val = inet->mc_all; - break; case IP_PKTOPTIONS: { struct msghdr msg; -- cgit v1.2.3 From 4bd0623f04eef65c0a324000fad73c4d3a677f8e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:41 +0000 Subject: inet: move inet->transparent to inet->inet_flags IP_TRANSPARENT socket option can now be set/read without locking the socket. v2: removed unused issk variable in mptcp_setsockopt_sol_ip_set_transparent() v4: rebased after commit 3f326a821b99 ("mptcp: change the mpc check helper to return a sk") Signed-off-by: Eric Dumazet Cc: Paolo Abeni Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Reviewed-by: Matthieu Baerts Signed-off-by: David S. Miller --- include/net/inet_sock.h | 6 +++--- include/net/ipv6.h | 2 +- include/net/route.h | 2 +- include/net/tcp.h | 2 +- net/ipv4/inet_diag.c | 2 +- net/ipv4/inet_timewait_sock.c | 2 +- net/ipv4/ip_sockglue.c | 28 +++++++++++++--------------- net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_minisocks.c | 3 +-- net/ipv6/ipv6_sockglue.c | 4 ++-- net/mptcp/sockopt.c | 11 +++++------ 11 files changed, 30 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index fffd34fa6a7c..cefd9a60dc6d 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -231,7 +231,6 @@ struct inet_sock { __u8 mc_ttl; __u8 pmtudisc; __u8 is_icsk:1, - transparent:1, nodefrag:1; __u8 bind_address_no_port:1, defer_connect:1; /* Indicates that fastopen_connect is set @@ -271,6 +270,7 @@ enum { INET_FLAGS_HDRINCL = 12, INET_FLAGS_MC_LOOP = 13, INET_FLAGS_MC_ALL = 14, + INET_FLAGS_TRANSPARENT = 15, }; /* cmsg flags for inet */ @@ -397,7 +397,7 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { __u8 flags = 0; - if (inet_sk(sk)->transparent || inet_test_bit(HDRINCL, sk)) + if (inet_test_bit(TRANSPARENT, sk) || inet_test_bit(HDRINCL, sk)) flags |= FLOWI_FLAG_ANYSRC; return flags; } @@ -424,7 +424,7 @@ static inline bool inet_can_nonlocal_bind(struct net *net, { return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) || test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || - inet->transparent; + test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } static inline bool inet_addr_valid_or_nonlocal(struct net *net, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index fd570d77588e..d40d8238d4c2 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -938,7 +938,7 @@ static inline bool ipv6_can_nonlocal_bind(struct net *net, { return net->ipv6.sysctl.ip_nonlocal_bind || test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || - inet->transparent; + test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } /* Sysctl settings for net ipv6.auto_flowlabels */ diff --git a/include/net/route.h b/include/net/route.h index d9ca98d2366f..51a45b1887b5 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -298,7 +298,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, { __u8 flow_flags = 0; - if (inet_sk(sk)->transparent) + if (inet_test_bit(TRANSPARENT, sk)) flow_flags |= FLOWI_FLAG_ANYSRC; flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk), diff --git a/include/net/tcp.h b/include/net/tcp.h index 6d77c08d83b7..07b21d9a9620 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2031,7 +2031,7 @@ static inline bool inet_sk_transparent(const struct sock *sk) case TCP_NEW_SYN_RECV: return inet_rsk(inet_reqsk(sk))->no_srccheck; } - return inet_sk(sk)->transparent; + return inet_test_bit(TRANSPARENT, sk); } /* Determines whether this is a thin stream (which may suffer from diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e009dab80c35..45fefd2f31fd 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -187,7 +187,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, inet_sockopt.freebind = inet_test_bit(FREEBIND, sk); inet_sockopt.hdrincl = inet_test_bit(HDRINCL, sk); inet_sockopt.mc_loop = inet_test_bit(MC_LOOP, sk); - inet_sockopt.transparent = inet->transparent; + inet_sockopt.transparent = inet_test_bit(TRANSPARENT, sk); inet_sockopt.mc_all = inet_test_bit(MC_ALL, sk); inet_sockopt.nodefrag = inet->nodefrag; inet_sockopt.bind_address_no_port = inet->bind_address_no_port; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 2c1b245dba8e..dd37a5bf6881 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -203,7 +203,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, tw->tw_reuseport = sk->sk_reuseport; tw->tw_hash = sk->sk_hash; tw->tw_ipv6only = 0; - tw->tw_transparent = inet->transparent; + tw->tw_transparent = inet_test_bit(TRANSPARENT, sk); tw->tw_prot = sk->sk_prot_creator; atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); twsk_net_set(tw, sock_net(sk)); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 2f27c30a4ecc..3f5323a230b3 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1005,7 +1005,16 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, return -EINVAL; inet_assign_bit(MC_ALL, sk, val); return 0; - + case IP_TRANSPARENT: + if (!!val && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && + !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { + err = -EPERM; + break; + } + if (optlen < 1) + goto e_inval; + inet_assign_bit(TRANSPARENT, sk, val); + return 0; } err = 0; @@ -1319,17 +1328,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, err = xfrm_user_policy(sk, optname, optval, optlen); break; - case IP_TRANSPARENT: - if (!!val && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && - !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { - err = -EPERM; - break; - } - if (optlen < 1) - goto e_inval; - inet->transparent = !!val; - break; - case IP_MINTTL: if (optlen < 1) goto e_inval; @@ -1585,6 +1583,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_MULTICAST_ALL: val = inet_test_bit(MC_ALL, sk); goto copyval; + case IP_TRANSPARENT: + val = inet_test_bit(TRANSPARENT, sk); + goto copyval; } if (needs_rtnl) @@ -1735,9 +1736,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, len -= msg.msg_controllen; return copy_to_sockptr(optlen, &len, sizeof(int)); } - case IP_TRANSPARENT: - val = inet->transparent; - break; case IP_MINTTL: val = inet->min_ttl; break; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d34d52fdfdb1..06fe1cf645d5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -7000,7 +7000,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb, sk); - inet_rsk(req)->no_srccheck = inet_sk(sk)->transparent; + inet_rsk(req)->no_srccheck = inet_test_bit(TRANSPARENT, sk); /* Note: tcp_v6_init_req() might override ir_iif for link locals */ inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 13ee12983c42..b98d476f1594 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -289,9 +289,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (tw) { struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); - struct inet_sock *inet = inet_sk(sk); - tw->tw_transparent = inet->transparent; + tw->tw_transparent = inet_test_bit(TRANSPARENT, sk); tw->tw_mark = sk->sk_mark; tw->tw_priority = sk->sk_priority; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 3eb38436f8d4..eb334122512c 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -633,7 +633,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optlen < sizeof(int)) goto e_inval; /* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */ - inet_sk(sk)->transparent = valbool; + inet_assign_bit(TRANSPARENT, sk, valbool); retv = 0; break; @@ -1330,7 +1330,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } case IPV6_TRANSPARENT: - val = inet_sk(sk)->transparent; + val = inet_test_bit(TRANSPARENT, sk); break; case IPV6_FREEBIND: diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index ffbe2f5f5b44..8260202c0066 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -416,7 +416,8 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, sk->sk_ipv6only = ssk->sk_ipv6only; break; case IPV6_TRANSPARENT: - inet_sk(sk)->transparent = inet_sk(ssk)->transparent; + inet_assign_bit(TRANSPARENT, sk, + inet_test_bit(TRANSPARENT, ssk)); break; case IPV6_FREEBIND: inet_assign_bit(FREEBIND, sk, @@ -685,7 +686,6 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o sockptr_t optval, unsigned int optlen) { struct sock *sk = (struct sock *)msk; - struct inet_sock *issk; struct sock *ssk; int err; @@ -701,14 +701,13 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o return PTR_ERR(ssk); } - issk = inet_sk(ssk); - switch (optname) { case IP_FREEBIND: inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); break; case IP_TRANSPARENT: - issk->transparent = inet_sk(sk)->transparent; + inet_assign_bit(TRANSPARENT, ssk, + inet_test_bit(TRANSPARENT, sk)); break; default: release_sock(sk); @@ -1441,7 +1440,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) __tcp_sock_set_cork(ssk, !!msk->cork); __tcp_sock_set_nodelay(ssk, !!msk->nodelay); - inet_sk(ssk)->transparent = inet_sk(sk)->transparent; + inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk)); inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); } -- cgit v1.2.3 From b1c0356a58577ce0a583e3044bf801877fc0b5de Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:42 +0000 Subject: inet: move inet->is_icsk to inet->inet_flags We move single bit fields to inet->inet_flags to avoid races. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 4 ++-- include/net/inet_sock.h | 5 ++--- net/ipv4/af_inet.c | 2 +- net/ipv4/cipso_ipv4.c | 4 ++-- net/ipv4/inet_diag.c | 2 +- net/ipv4/ip_sockglue.c | 4 ++-- net/ipv6/af_inet6.c | 2 +- net/ipv6/ipv6_sockglue.c | 4 ++-- 8 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index be3c858a2ebb..5d2fcc137b88 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -342,9 +342,9 @@ static inline bool inet_csk_in_pingpong_mode(struct sock *sk) return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; } -static inline bool inet_csk_has_ulp(struct sock *sk) +static inline bool inet_csk_has_ulp(const struct sock *sk) { - return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops; + return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops; } #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index cefd9a60dc6d..38f7fc1c4dac 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -201,7 +201,6 @@ struct rtable; * @inet_id - ID counter for DF pkts * @tos - TOS * @mc_ttl - Multicasting TTL - * @is_icsk - is this an inet_connection_sock? * @uc_index - Unicast outgoing device index * @mc_index - Multicast device index * @mc_list - Group array @@ -230,8 +229,7 @@ struct inet_sock { __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; - __u8 is_icsk:1, - nodefrag:1; + __u8 nodefrag:1; __u8 bind_address_no_port:1, defer_connect:1; /* Indicates that fastopen_connect is set * and cookie exists so we defer connect @@ -271,6 +269,7 @@ enum { INET_FLAGS_MC_LOOP = 13, INET_FLAGS_MC_ALL = 14, INET_FLAGS_TRANSPARENT = 15, + INET_FLAGS_IS_ICSK = 16, }; /* cmsg flags for inet */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 47c9cdd7687f..0f46b71f8a98 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -331,7 +331,7 @@ lookup_protocol: sk->sk_reuse = SK_CAN_REUSE; inet = inet_sk(sk); - inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; + inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); inet->nodefrag = 0; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 79ae7204e8ed..d048aa833293 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1881,7 +1881,7 @@ int cipso_v4_sock_setattr(struct sock *sk, old = rcu_dereference_protected(sk_inet->inet_opt, lockdep_sock_is_held(sk)); - if (sk_inet->is_icsk) { + if (inet_test_bit(IS_ICSK, sk)) { sk_conn = inet_csk(sk); if (old) sk_conn->icsk_ext_hdr_len -= old->opt.optlen; @@ -2051,7 +2051,7 @@ void cipso_v4_sock_delattr(struct sock *sk) sk_inet = inet_sk(sk); hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt); - if (sk_inet->is_icsk && hdr_delta > 0) { + if (inet_test_bit(IS_ICSK, sk) && hdr_delta > 0) { struct inet_connection_sock *sk_conn = inet_csk(sk); sk_conn->icsk_ext_hdr_len -= hdr_delta; sk_conn->icsk_sync_mss(sk, sk_conn->icsk_pmtu_cookie); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 45fefd2f31fd..ada198fc1a92 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -183,7 +183,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, memset(&inet_sockopt, 0, sizeof(inet_sockopt)); inet_sockopt.recverr = inet_test_bit(RECVERR, sk); - inet_sockopt.is_icsk = inet->is_icsk; + inet_sockopt.is_icsk = inet_test_bit(IS_ICSK, sk); inet_sockopt.freebind = inet_test_bit(FREEBIND, sk); inet_sockopt.hdrincl = inet_test_bit(HDRINCL, sk); inet_sockopt.mc_loop = inet_test_bit(MC_LOOP, sk); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 3f5323a230b3..dac471ed067b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1034,7 +1034,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, break; old = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); - if (inet->is_icsk) { + if (inet_test_bit(IS_ICSK, sk)) { struct inet_connection_sock *icsk = inet_csk(sk); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET || @@ -1209,7 +1209,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, struct ip_mreqn mreq; err = -EPROTO; - if (inet_sk(sk)->is_icsk) + if (inet_test_bit(IS_ICSK, sk)) break; if (optlen < sizeof(struct ip_mreq)) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8e9d4c1f0e83..d8c56c7aba96 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -200,7 +200,7 @@ lookup_protocol: sk->sk_reuse = SK_CAN_REUSE; inet = inet_sk(sk); - inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; + inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); if (SOCK_RAW == sock->type) { inet->inet_num = protocol; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index eb334122512c..d19577a94bcc 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -102,7 +102,7 @@ int ip6_ra_control(struct sock *sk, int sel) struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt) { - if (inet_sk(sk)->is_icsk) { + if (inet_test_bit(IS_ICSK, sk)) { if (opt && !((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) { @@ -831,7 +831,7 @@ done: goto e_inval; retv = -EPROTO; - if (inet_sk(sk)->is_icsk) + if (inet_test_bit(IS_ICSK, sk)) break; retv = -EFAULT; -- cgit v1.2.3 From f04b8d3478a3a63f17d8dc0dc6da16a828b48df0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:43 +0000 Subject: inet: move inet->nodefrag to inet->inet_flags IP_NODEFRAG socket option can now be set/read without locking the socket. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/inet_sock.h | 2 +- net/ipv4/af_inet.c | 2 +- net/ipv4/inet_diag.c | 2 +- net/ipv4/ip_sockglue.c | 18 ++++++++---------- net/ipv4/netfilter/nf_defrag_ipv4.c | 2 +- net/netfilter/ipvs/ip_vs_core.c | 4 ++-- 6 files changed, 14 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 38f7fc1c4dac..0e6e1b017efb 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -229,7 +229,6 @@ struct inet_sock { __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; - __u8 nodefrag:1; __u8 bind_address_no_port:1, defer_connect:1; /* Indicates that fastopen_connect is set * and cookie exists so we defer connect @@ -270,6 +269,7 @@ enum { INET_FLAGS_MC_ALL = 14, INET_FLAGS_TRANSPARENT = 15, INET_FLAGS_IS_ICSK = 16, + INET_FLAGS_NODEFRAG = 17, }; /* cmsg flags for inet */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0f46b71f8a98..2fb9948b5230 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -333,7 +333,7 @@ lookup_protocol: inet = inet_sk(sk); inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); - inet->nodefrag = 0; + inet_clear_bit(NODEFRAG, sk); if (SOCK_RAW == sock->type) { inet->inet_num = protocol; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index ada198fc1a92..39606caad484 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -189,7 +189,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, inet_sockopt.mc_loop = inet_test_bit(MC_LOOP, sk); inet_sockopt.transparent = inet_test_bit(TRANSPARENT, sk); inet_sockopt.mc_all = inet_test_bit(MC_ALL, sk); - inet_sockopt.nodefrag = inet->nodefrag; + inet_sockopt.nodefrag = inet_test_bit(NODEFRAG, sk); inet_sockopt.bind_address_no_port = inet->bind_address_no_port; inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk); inet_sockopt.defer_connect = inet->defer_connect; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index dac471ed067b..ec946c13ea20 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1015,6 +1015,11 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, goto e_inval; inet_assign_bit(TRANSPARENT, sk, val); return 0; + case IP_NODEFRAG: + if (sk->sk_type != SOCK_RAW) + return -ENOPROTOOPT; + inet_assign_bit(NODEFRAG, sk, val); + return 0; } err = 0; @@ -1079,13 +1084,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, goto e_inval; inet->uc_ttl = val; break; - case IP_NODEFRAG: - if (sk->sk_type != SOCK_RAW) { - err = -ENOPROTOOPT; - break; - } - inet->nodefrag = val ? 1 : 0; - break; case IP_BIND_ADDRESS_NO_PORT: inet->bind_address_no_port = val ? 1 : 0; break; @@ -1586,6 +1584,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_TRANSPARENT: val = inet_test_bit(TRANSPARENT, sk); goto copyval; + case IP_NODEFRAG: + val = inet_test_bit(NODEFRAG, sk); + goto copyval; } if (needs_rtnl) @@ -1633,9 +1634,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, inet->uc_ttl); break; } - case IP_NODEFRAG: - val = inet->nodefrag; - break; case IP_BIND_ADDRESS_NO_PORT: val = inet->bind_address_no_port; break; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index a9ba7de092c4..265b39bc435b 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -66,7 +66,7 @@ static unsigned int ipv4_conntrack_defrag(void *priv, struct sock *sk = skb->sk; if (sk && sk_fullsock(sk) && (sk->sk_family == PF_INET) && - inet_sk(sk)->nodefrag) + inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; #if IS_ENABLED(CONFIG_NF_CONNTRACK) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index cb83ca506c5c..3230506ae3ff 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1346,7 +1346,7 @@ ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { - if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) + if (sk->sk_family == PF_INET && inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; } @@ -1946,7 +1946,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { - if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) + if (sk->sk_family == PF_INET && inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; } -- cgit v1.2.3 From ca571e2eb7eb6202aa367e01c811aab023272f38 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:44 +0000 Subject: inet: move inet->bind_address_no_port to inet->inet_flags IP_BIND_ADDRESS_NO_PORT socket option can now be set/read without locking the socket. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/inet_sock.h | 4 ++-- net/ipv4/af_inet.c | 2 +- net/ipv4/inet_diag.c | 2 +- net/ipv4/ip_sockglue.c | 12 ++++++------ net/ipv6/af_inet6.c | 2 +- 5 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 0e6e1b017efb..5eca2e70cbb2 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -229,8 +229,7 @@ struct inet_sock { __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; - __u8 bind_address_no_port:1, - defer_connect:1; /* Indicates that fastopen_connect is set + __u8 defer_connect:1; /* Indicates that fastopen_connect is set * and cookie exists so we defer connect * until first data frame is written */ @@ -270,6 +269,7 @@ enum { INET_FLAGS_TRANSPARENT = 15, INET_FLAGS_IS_ICSK = 16, INET_FLAGS_NODEFRAG = 17, + INET_FLAGS_BIND_ADDRESS_NO_PORT = 18, }; /* cmsg flags for inet */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 2fb9948b5230..26e7cd9cb059 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -529,7 +529,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, inet->inet_saddr = 0; /* Use device */ /* Make sure we are allowed to bind here. */ - if (snum || !(inet->bind_address_no_port || + if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { err = sk->sk_prot->get_port(sk, snum); if (err) { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 39606caad484..128966dea554 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -190,7 +190,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, inet_sockopt.transparent = inet_test_bit(TRANSPARENT, sk); inet_sockopt.mc_all = inet_test_bit(MC_ALL, sk); inet_sockopt.nodefrag = inet_test_bit(NODEFRAG, sk); - inet_sockopt.bind_address_no_port = inet->bind_address_no_port; + inet_sockopt.bind_address_no_port = inet_test_bit(BIND_ADDRESS_NO_PORT, sk); inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk); inet_sockopt.defer_connect = inet->defer_connect; if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt), diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ec946c13ea20..cfa65a0b0900 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1020,6 +1020,9 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; inet_assign_bit(NODEFRAG, sk, val); return 0; + case IP_BIND_ADDRESS_NO_PORT: + inet_assign_bit(BIND_ADDRESS_NO_PORT, sk, val); + return 0; } err = 0; @@ -1084,9 +1087,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, goto e_inval; inet->uc_ttl = val; break; - case IP_BIND_ADDRESS_NO_PORT: - inet->bind_address_no_port = val ? 1 : 0; - break; case IP_MTU_DISCOVER: if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) goto e_inval; @@ -1587,6 +1587,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_NODEFRAG: val = inet_test_bit(NODEFRAG, sk); goto copyval; + case IP_BIND_ADDRESS_NO_PORT: + val = inet_test_bit(BIND_ADDRESS_NO_PORT, sk); + goto copyval; } if (needs_rtnl) @@ -1634,9 +1637,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, inet->uc_ttl); break; } - case IP_BIND_ADDRESS_NO_PORT: - val = inet->bind_address_no_port; - break; case IP_MTU_DISCOVER: val = inet->pmtudisc; break; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d8c56c7aba96..368824fe9719 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -399,7 +399,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, sk->sk_ipv6only = 1; /* Make sure we are allowed to bind here. */ - if (snum || !(inet->bind_address_no_port || + if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { err = sk->sk_prot->get_port(sk, snum); if (err) { -- cgit v1.2.3 From 08e39c0dfa29f233f5a621f7d274b793a080c769 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 08:15:45 +0000 Subject: inet: move inet->defer_connect to inet->inet_flags Make room in struct inet_sock by removing this bit field, using one available bit in inet_flags instead. Also move local_port_range to fill the resulting hole, saving 8 bytes on 64bit arches. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Reviewed-by: Simon Horman Reviewed-by: Matthieu Baerts Signed-off-by: David S. Miller --- include/net/inet_sock.h | 10 ++++------ net/ipv4/af_inet.c | 4 ++-- net/ipv4/inet_diag.c | 2 +- net/ipv4/tcp.c | 12 +++++++----- net/ipv4/tcp_fastopen.c | 2 +- net/mptcp/protocol.c | 10 ++++++---- 6 files changed, 21 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 5eca2e70cbb2..acbb93d7607a 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -229,21 +229,18 @@ struct inet_sock { __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; - __u8 defer_connect:1; /* Indicates that fastopen_connect is set - * and cookie exists so we defer connect - * until first data frame is written - */ __u8 rcv_tos; __u8 convert_csum; int uc_index; int mc_index; __be32 mc_addr; - struct ip_mc_socklist __rcu *mc_list; - struct inet_cork_full cork; struct { __u16 lo; __u16 hi; } local_port_range; + + struct ip_mc_socklist __rcu *mc_list; + struct inet_cork_full cork; }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ @@ -270,6 +267,7 @@ enum { INET_FLAGS_IS_ICSK = 16, INET_FLAGS_NODEFRAG = 17, INET_FLAGS_BIND_ADDRESS_NO_PORT = 18, + INET_FLAGS_DEFER_CONNECT = 19, }; /* cmsg flags for inet */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 26e7cd9cb059..e07ee60625d9 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -656,7 +656,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, err = -EISCONN; goto out; case SS_CONNECTING: - if (inet_sk(sk)->defer_connect) + if (inet_test_bit(DEFER_CONNECT, sk)) err = is_sendmsg ? -EINPROGRESS : -EISCONN; else err = -EALREADY; @@ -679,7 +679,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTING; - if (!err && inet_sk(sk)->defer_connect) + if (!err && inet_test_bit(DEFER_CONNECT, sk)) goto out; /* Just entered SS_CONNECTING state; the only diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 128966dea554..e13a84433413 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -192,7 +192,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, inet_sockopt.nodefrag = inet_test_bit(NODEFRAG, sk); inet_sockopt.bind_address_no_port = inet_test_bit(BIND_ADDRESS_NO_PORT, sk); inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk); - inet_sockopt.defer_connect = inet->defer_connect; + inet_sockopt.defer_connect = inet_test_bit(DEFER_CONNECT, sk); if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt), &inet_sockopt)) goto errout; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4fbc7ff8c53c..cee1e548660c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -583,7 +583,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (urg_data & TCP_URG_VALID) mask |= EPOLLPRI; - } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { + } else if (state == TCP_SYN_SENT && + inet_test_bit(DEFER_CONNECT, sk)) { /* Active TCP fastopen socket with defer_connect * Return EPOLLOUT so application can call write() * in order for kernel to generate SYN+data @@ -1007,7 +1008,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, tp->fastopen_req->size = size; tp->fastopen_req->uarg = uarg; - if (inet->defer_connect) { + if (inet_test_bit(DEFER_CONNECT, sk)) { err = tcp_connect(sk); /* Same failure procedure as in tcp_v4/6_connect */ if (err) { @@ -1025,7 +1026,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, if (tp->fastopen_req) { *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); - inet->defer_connect = 0; + inet_clear_bit(DEFER_CONNECT, sk); } return err; } @@ -1066,7 +1067,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) zc = MSG_SPLICE_PAGES; } - if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && + if (unlikely(flags & MSG_FASTOPEN || + inet_test_bit(DEFER_CONNECT, sk)) && !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg); if (err == -EINPROGRESS && copied_syn > 0) @@ -3088,7 +3090,7 @@ int tcp_disconnect(struct sock *sk, int flags) /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); - inet->defer_connect = 0; + inet_clear_bit(DEFER_CONNECT, sk); tp->fastopen_client_fail = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 85e4953f1182..8ed54e7334a9 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -451,7 +451,7 @@ bool tcp_fastopen_defer_connect(struct sock *sk, int *err) if (tp->fastopen_connect && !tp->fastopen_req) { if (tcp_fastopen_cookie_check(sk, &mss, &cookie)) { - inet_sk(sk)->defer_connect = 1; + inet_set_bit(DEFER_CONNECT, sk); return true; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 6ea0a1da8068..6019a3cf1625 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1686,7 +1686,7 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, if (!mptcp_disconnect(sk, 0)) sk->sk_socket->state = SS_UNCONNECTED; } - inet_sk(sk)->defer_connect = 0; + inet_clear_bit(DEFER_CONNECT, sk); return ret; } @@ -1704,7 +1704,8 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) lock_sock(sk); - if (unlikely(inet_sk(sk)->defer_connect || msg->msg_flags & MSG_FASTOPEN)) { + if (unlikely(inet_test_bit(DEFER_CONNECT, sk) || + msg->msg_flags & MSG_FASTOPEN)) { int copied_syn = 0; ret = mptcp_sendmsg_fastopen(sk, msg, len, &copied_syn); @@ -3601,7 +3602,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err < 0) goto out; - inet_sk(sk)->defer_connect = inet_sk(ssk)->defer_connect; + inet_assign_bit(DEFER_CONNECT, sk, inet_test_bit(DEFER_CONNECT, ssk)); out: if (!msk->fastopening) @@ -3827,7 +3828,8 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, mask |= EPOLLOUT | EPOLLWRNORM; else mask |= mptcp_check_writeable(msk); - } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { + } else if (state == TCP_SYN_SENT && + inet_test_bit(DEFER_CONNECT, sk)) { /* cf tcp_poll() note about TFO */ mask |= EPOLLOUT | EPOLLWRNORM; } -- cgit v1.2.3 From ac8a52962164a50e693fa021d3564d7745b83a7f Mon Sep 17 00:00:00 2001 From: Abel Wu Date: Mon, 14 Aug 2023 15:09:11 +0800 Subject: net-memcg: Fix scope of sockmem pressure indicators Now there are two indicators of socket memory pressure sit inside struct mem_cgroup, socket_pressure and tcpmem_pressure, indicating memory reclaim pressure in memcg->memory and ->tcpmem respectively. When in legacy mode (cgroupv1), the socket memory is charged into ->tcpmem which is independent of ->memory, so socket_pressure has nothing to do with socket's pressure at all. Things could be worse by taking socket_pressure into consideration in legacy mode, as a pressure in ->memory can lead to premature reclamation/throttling in socket. While for the default mode (cgroupv2), the socket memory is charged into ->memory, and ->tcpmem/->tcpmem_pressure are simply not used. So {socket,tcpmem}_pressure are only used in default/legacy mode respectively for indicating socket memory pressure. This patch fixes the pieces of code that make mixed use of both. Fixes: 8e8ae645249b ("mm: memcontrol: hook up vmpressure to socket pressure") Signed-off-by: Abel Wu Acked-by: Shakeel Butt Signed-off-by: David S. Miller --- include/linux/memcontrol.h | 9 +++++++-- mm/vmpressure.c | 8 ++++++++ 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5818af8eca5a..dbf26bc89dd4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -284,6 +284,11 @@ struct mem_cgroup { atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; + /* + * Hint of reclaim pressure for socket memroy management. Note + * that this indicator should NOT be used in legacy cgroup mode + * where socket memory is accounted/charged separately. + */ unsigned long socket_pressure; /* Legacy tcp memory accounting */ @@ -1727,8 +1732,8 @@ void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) - return true; + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return !!memcg->tcpmem_pressure; do { if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; diff --git a/mm/vmpressure.c b/mm/vmpressure.c index b52644771cc4..22c6689d9302 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -244,6 +244,14 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, if (mem_cgroup_disabled()) return; + /* + * The in-kernel users only care about the reclaim efficiency + * for this @memcg rather than the whole subtree, and there + * isn't and won't be any in-kernel user in a legacy cgroup. + */ + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !tree) + return; + vmpr = memcg_to_vmpressure(memcg); /* -- cgit v1.2.3 From 3dec89b14d37ee635e772636dad3f09f78f1ab87 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Tue, 15 Aug 2023 11:07:05 -0700 Subject: net/ipv6: Remove expired routes with a separated list of routes. FIB6 GC walks trees of fib6_tables to remove expired routes. Walking a tree can be expensive if the number of routes in a table is big, even if most of them are permanent. Checking routes in a separated list of routes having expiration will avoid this potential issue. Signed-off-by: Kui-Feng Lee Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 64 ++++++++++++++++++++++++++++++++++++++++----------- net/ipv6/ip6_fib.c | 55 ++++++++++++++++++++++++++++++++++++++----- net/ipv6/route.c | 6 ++--- 3 files changed, 103 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 05e6f756feaf..c9ff23cf313e 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -179,6 +179,9 @@ struct fib6_info { refcount_t fib6_ref; unsigned long expires; + + struct hlist_node gc_link; + struct dst_metrics *fib6_metrics; #define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] @@ -247,19 +250,6 @@ static inline bool fib6_requires_src(const struct fib6_info *rt) return rt->fib6_src.plen > 0; } -static inline void fib6_clean_expires(struct fib6_info *f6i) -{ - f6i->fib6_flags &= ~RTF_EXPIRES; - f6i->expires = 0; -} - -static inline void fib6_set_expires(struct fib6_info *f6i, - unsigned long expires) -{ - f6i->expires = expires; - f6i->fib6_flags |= RTF_EXPIRES; -} - static inline bool fib6_check_expired(const struct fib6_info *f6i) { if (f6i->fib6_flags & RTF_EXPIRES) @@ -267,6 +257,11 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i) return false; } +static inline bool fib6_has_expires(const struct fib6_info *f6i) +{ + return f6i->fib6_flags & RTF_EXPIRES; +} + /* Function to safely get fn->fn_sernum for passed in rt * and store result in passed in cookie. * Return true if we can get cookie safely @@ -388,6 +383,7 @@ struct fib6_table { struct inet_peer_base tb6_peers; unsigned int flags; unsigned int fib_seq; + struct hlist_head tb6_gc_hlist; /* GC candidates */ #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; @@ -504,6 +500,48 @@ void fib6_gc_cleanup(void); int fib6_init(void); +/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be + * NULL. + */ +static inline void fib6_set_expires_locked(struct fib6_info *f6i, + unsigned long expires) +{ + struct fib6_table *tb6; + + tb6 = f6i->fib6_table; + f6i->expires = expires; + if (tb6 && !fib6_has_expires(f6i)) + hlist_add_head(&f6i->gc_link, &tb6->tb6_gc_hlist); + f6i->fib6_flags |= RTF_EXPIRES; +} + +/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be + * NULL. If fib6_table is NULL, the fib6_info will no be inserted into the + * list of GC candidates until it is inserted into a table. + */ +static inline void fib6_set_expires(struct fib6_info *f6i, + unsigned long expires) +{ + spin_lock_bh(&f6i->fib6_table->tb6_lock); + fib6_set_expires_locked(f6i, expires); + spin_unlock_bh(&f6i->fib6_table->tb6_lock); +} + +static inline void fib6_clean_expires_locked(struct fib6_info *f6i) +{ + if (fib6_has_expires(f6i)) + hlist_del_init(&f6i->gc_link); + f6i->fib6_flags &= ~RTF_EXPIRES; + f6i->expires = 0; +} + +static inline void fib6_clean_expires(struct fib6_info *f6i) +{ + spin_lock_bh(&f6i->fib6_table->tb6_lock); + fib6_clean_expires_locked(f6i); + spin_unlock_bh(&f6i->fib6_table->tb6_lock); +} + struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index bac768d36cc1..28b01a068412 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -160,6 +160,8 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); + INIT_HLIST_NODE(&f6i->gc_link); + return f6i; } @@ -246,6 +248,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); + INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; @@ -1057,6 +1060,8 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, lockdep_is_held(&table->tb6_lock)); } } + + fib6_clean_expires_locked(rt); } /* @@ -1118,9 +1123,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) - fib6_clean_expires(iter); + fib6_clean_expires_locked(iter); else - fib6_set_expires(iter, rt->expires); + fib6_set_expires_locked(iter, + rt->expires); if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, @@ -1479,6 +1485,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); + + if (fib6_has_expires(rt)) + hlist_add_head(&rt->gc_link, &table->tb6_gc_hlist); + fib6_start_gc(info->nl_net, rt); } @@ -2285,9 +2295,8 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -static int fib6_age(struct fib6_info *rt, void *arg) +static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { - struct fib6_gc_args *gc_args = arg; unsigned long now = jiffies; /* @@ -2295,7 +2304,7 @@ static int fib6_age(struct fib6_info *rt, void *arg) * Routes are expired even if they are in use. */ - if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { + if (fib6_has_expires(rt) && rt->expires) { if (time_after(now, rt->expires)) { RT6_TRACE("expiring %p\n", rt); return -1; @@ -2312,6 +2321,40 @@ static int fib6_age(struct fib6_info *rt, void *arg) return 0; } +static void fib6_gc_table(struct net *net, + struct fib6_table *tb6, + struct fib6_gc_args *gc_args) +{ + struct fib6_info *rt; + struct hlist_node *n; + struct nl_info info = { + .nl_net = net, + .skip_notify = false, + }; + + hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) + if (fib6_age(rt, gc_args) == -1) + fib6_del(rt, &info); +} + +static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) +{ + struct fib6_table *table; + struct hlist_head *head; + unsigned int h; + + rcu_read_lock(); + for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { + head = &net->ipv6.fib_table_hash[h]; + hlist_for_each_entry_rcu(table, head, tb6_hlist) { + spin_lock_bh(&table->tb6_lock); + fib6_gc_table(net, table, gc_args); + spin_unlock_bh(&table->tb6_lock); + } + } + rcu_read_unlock(); +} + void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; @@ -2327,7 +2370,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = 0; - fib6_clean_all(net, fib6_age, &gc_args); + fib6_gc_all(net, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 10751df16dab..db10c36f34bb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3761,10 +3761,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, rt->dst_nocount = true; if (cfg->fc_flags & RTF_EXPIRES) - fib6_set_expires(rt, jiffies + - clock_t_to_jiffies(cfg->fc_expires)); + fib6_set_expires_locked(rt, jiffies + + clock_t_to_jiffies(cfg->fc_expires)); else - fib6_clean_expires(rt); + fib6_clean_expires_locked(rt); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; -- cgit v1.2.3 From dd2e84bb3804103ad1c26a21deb4b35b0e166746 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 28 Jul 2023 17:52:05 +0200 Subject: virtchnl: fix fake 1-elem arrays in structs allocated as `nents + 1` - 1 The two most problematic virtchnl structures are virtchnl_rss_key and virtchnl_rss_lut. Their "flex" arrays have the type of u8, thus, when allocating / checking, the actual size is calculated as `sizeof + nents - 1 byte`. But their sizeof() is not 1 byte larger than the size of such structure with proper flex array, it's two bytes larger due to the padding. That said, their size is always 1 byte larger unless there are no tail elements -- then it's +2 bytes. Add virtchnl_struct_size() macro which will handle this case (and later other cases as well). Make its calling conv the same as we call struct_size() to allow it to be drop-in, even though it's unlikely to become possible to switch to generic API. The macro will calculate a proper size of a structure with a flex array at the end, so that it becomes transparent for the compilers, but add the difference from the old values, so that the real size of sorta-ABI-messages doesn't change. Use it on the allocation side in IAVF and the receiving side (defined as static inline in virtchnl.h) for the mentioned two structures. Signed-off-by: Alexander Lobakin Reviewed-by: Kees Cook Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 6 ++--- include/linux/avf/virtchnl.h | 31 ++++++++++++++++++------- 2 files changed, 25 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index be3c007ce90a..10f03054a603 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1085,8 +1085,7 @@ void iavf_set_rss_key(struct iavf_adapter *adapter) adapter->current_op); return; } - len = sizeof(struct virtchnl_rss_key) + - (adapter->rss_key_size * sizeof(u8)) - 1; + len = virtchnl_struct_size(vrk, key, adapter->rss_key_size); vrk = kzalloc(len, GFP_KERNEL); if (!vrk) return; @@ -1117,8 +1116,7 @@ void iavf_set_rss_lut(struct iavf_adapter *adapter) adapter->current_op); return; } - len = sizeof(struct virtchnl_rss_lut) + - (adapter->rss_lut_size * sizeof(u8)) - 1; + len = virtchnl_struct_size(vrl, lut, adapter->rss_lut_size); vrl = kzalloc(len, GFP_KERNEL); if (!vrl) return; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index c15221dcb75e..3ab207c14809 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -866,18 +866,20 @@ VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_promisc_info); struct virtchnl_rss_key { u16 vsi_id; u16 key_len; - u8 key[1]; /* RSS hash key, packed bytes */ + u8 key[]; /* RSS hash key, packed bytes */ }; -VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key); +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rss_key); +#define virtchnl_rss_key_LEGACY_SIZEOF 6 struct virtchnl_rss_lut { u16 vsi_id; u16 lut_entries; - u8 lut[1]; /* RSS lookup table */ + u8 lut[]; /* RSS lookup table */ }; -VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut); +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rss_lut); +#define virtchnl_rss_lut_LEGACY_SIZEOF 6 /* VIRTCHNL_OP_GET_RSS_HENA_CAPS * VIRTCHNL_OP_SET_RSS_HENA @@ -1367,6 +1369,17 @@ struct virtchnl_fdir_del { VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del); +#define __vss_byone(p, member, count, old) \ + (struct_size(p, member, count) + (old - 1 - struct_size(p, member, 0))) + +#define __vss(type, func, p, member, count) \ + struct type: func(p, member, count, type##_LEGACY_SIZEOF) + +#define virtchnl_struct_size(p, m, c) \ + _Generic(*p, \ + __vss(virtchnl_rss_key, __vss_byone, p, m, c), \ + __vss(virtchnl_rss_lut, __vss_byone, p, m, c)) + /** * virtchnl_vc_validate_vf_msg * @ver: Virtchnl version info @@ -1479,19 +1492,21 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, } break; case VIRTCHNL_OP_CONFIG_RSS_KEY: - valid_len = sizeof(struct virtchnl_rss_key); + valid_len = virtchnl_rss_key_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_rss_key *vrk = (struct virtchnl_rss_key *)msg; - valid_len += vrk->key_len - 1; + valid_len = virtchnl_struct_size(vrk, key, + vrk->key_len); } break; case VIRTCHNL_OP_CONFIG_RSS_LUT: - valid_len = sizeof(struct virtchnl_rss_lut); + valid_len = virtchnl_rss_lut_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; - valid_len += vrl->lut_entries - 1; + valid_len = virtchnl_struct_size(vrl, lut, + vrl->lut_entries); } break; case VIRTCHNL_OP_GET_RSS_HENA_CAPS: -- cgit v1.2.3 From 5e7f59fa07f86f554c301c7a383bba54d5ef9819 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 28 Jul 2023 17:52:06 +0200 Subject: virtchnl: fix fake 1-elem arrays in structures allocated as `nents + 1` There are five virtchnl structures, which are allocated and checked in the code as `nents + 1`, meaning that they always have memory for one excessive element regardless of their actual number. This comes from that their sizeof() includes space for 1 element and then they get allocated via struct_size() or its open-coded equivalents, passing the actual number of elements. Expand virtchnl_struct_size() to handle such structures and replace those 1-elem arrays with proper flex ones. Also fix several places which open-code %IAVF_VIRTCHNL_VF_RESOURCE_SIZE. Finally, let the virtchnl_ether_addr_list size be computed automatically when there's no enough space for the whole list, otherwise we have to open-code reverse struct_size() logics. Signed-off-by: Alexander Lobakin Reviewed-by: Kees Cook Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 2 +- drivers/net/ethernet/intel/iavf/iavf.h | 6 +-- drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 44 ++++++++--------- drivers/net/ethernet/intel/ice/ice_virtchnl.c | 2 +- include/linux/avf/virtchnl.h | 57 +++++++++++++--------- 5 files changed, 59 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 98aca9f8b602..a6983c2d7c30 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2103,7 +2103,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) goto err; } - len = struct_size(vfres, vsi_res, num_vsis); + len = virtchnl_struct_size(vfres, vsi_res, num_vsis); vfres = kzalloc(len, GFP_KERNEL); if (!vfres) { aq_ret = -ENOMEM; diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 8cbdebc5b698..85fba85fbb23 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -92,9 +92,9 @@ struct iavf_vsi { #define IAVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */ #define IAVF_MBPS_QUANTA 50 -#define IAVF_VIRTCHNL_VF_RESOURCE_SIZE (sizeof(struct virtchnl_vf_resource) + \ - (IAVF_MAX_VF_VSI * \ - sizeof(struct virtchnl_vsi_resource))) +#define IAVF_VIRTCHNL_VF_RESOURCE_SIZE \ + virtchnl_struct_size((struct virtchnl_vf_resource *)NULL, \ + vsi_res, IAVF_MAX_VF_VSI) /* MAX_MSIX_Q_VECTORS of these are allocated, * but we only use one per queue-specific vector. diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 10f03054a603..4fdac698eb38 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -215,8 +215,7 @@ int iavf_get_vf_config(struct iavf_adapter *adapter) u16 len; int err; - len = sizeof(struct virtchnl_vf_resource) + - IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource); + len = IAVF_VIRTCHNL_VF_RESOURCE_SIZE; event.buf_len = len; event.msg_buf = kzalloc(len, GFP_KERNEL); if (!event.msg_buf) @@ -284,7 +283,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter) return; } adapter->current_op = VIRTCHNL_OP_CONFIG_VSI_QUEUES; - len = struct_size(vqci, qpair, pairs); + len = virtchnl_struct_size(vqci, qpair, pairs); vqci = kzalloc(len, GFP_KERNEL); if (!vqci) return; @@ -397,7 +396,7 @@ void iavf_map_queues(struct iavf_adapter *adapter) q_vectors = adapter->num_msix_vectors - NONQ_VECS; - len = struct_size(vimi, vecmap, adapter->num_msix_vectors); + len = virtchnl_struct_size(vimi, vecmap, adapter->num_msix_vectors); vimi = kzalloc(len, GFP_KERNEL); if (!vimi) return; @@ -476,13 +475,11 @@ void iavf_add_ether_addrs(struct iavf_adapter *adapter) } adapter->current_op = VIRTCHNL_OP_ADD_ETH_ADDR; - len = struct_size(veal, list, count); + len = virtchnl_struct_size(veal, list, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add MAC changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - - sizeof(struct virtchnl_ether_addr_list)) / - sizeof(struct virtchnl_ether_addr); - len = struct_size(veal, list, count); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(veal, list, --count); more = true; } @@ -547,13 +544,11 @@ void iavf_del_ether_addrs(struct iavf_adapter *adapter) } adapter->current_op = VIRTCHNL_OP_DEL_ETH_ADDR; - len = struct_size(veal, list, count); + len = virtchnl_struct_size(veal, list, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many delete MAC changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - - sizeof(struct virtchnl_ether_addr_list)) / - sizeof(struct virtchnl_ether_addr); - len = struct_size(veal, list, count); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(veal, list, --count); more = true; } veal = kzalloc(len, GFP_ATOMIC); @@ -687,12 +682,12 @@ void iavf_add_vlans(struct iavf_adapter *adapter) adapter->current_op = VIRTCHNL_OP_ADD_VLAN; - len = sizeof(*vvfl) + (count * sizeof(u16)); + len = virtchnl_struct_size(vvfl, vlan_id, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(*vvfl)) / - sizeof(u16); - len = sizeof(*vvfl) + (count * sizeof(u16)); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(vvfl, vlan_id, + --count); more = true; } vvfl = kzalloc(len, GFP_ATOMIC); @@ -838,12 +833,12 @@ void iavf_del_vlans(struct iavf_adapter *adapter) adapter->current_op = VIRTCHNL_OP_DEL_VLAN; - len = sizeof(*vvfl) + (count * sizeof(u16)); + len = virtchnl_struct_size(vvfl, vlan_id, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many delete VLAN changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(*vvfl)) / - sizeof(u16); - len = sizeof(*vvfl) + (count * sizeof(u16)); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(vvfl, vlan_id, + --count); more = true; } vvfl = kzalloc(len, GFP_ATOMIC); @@ -2173,9 +2168,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } break; case VIRTCHNL_OP_GET_VF_RESOURCES: { - u16 len = sizeof(struct virtchnl_vf_resource) + - IAVF_MAX_VF_VSI * - sizeof(struct virtchnl_vsi_resource); + u16 len = IAVF_VIRTCHNL_VF_RESOURCE_SIZE; + memcpy(adapter->vf_res, msg, min(msglen, len)); iavf_validate_num_queues(adapter); iavf_vf_parse_hw_config(&adapter->hw, adapter->vf_res); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 85d996531502..4a02ed91ba73 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -428,7 +428,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) goto err; } - len = sizeof(struct virtchnl_vf_resource); + len = virtchnl_struct_size(vfres, vsi_res, 0); vfres = kzalloc(len, GFP_KERNEL); if (!vfres) { diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 3ab207c14809..c1a20b533fc0 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -268,10 +268,11 @@ struct virtchnl_vf_resource { u32 rss_key_size; u32 rss_lut_size; - struct virtchnl_vsi_resource vsi_res[1]; + struct virtchnl_vsi_resource vsi_res[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(36, virtchnl_vf_resource); +VIRTCHNL_CHECK_STRUCT_LEN(20, virtchnl_vf_resource); +#define virtchnl_vf_resource_LEGACY_SIZEOF 36 /* VIRTCHNL_OP_CONFIG_TX_QUEUE * VF sends this message to set up parameters for one TX queue. @@ -340,10 +341,11 @@ struct virtchnl_vsi_queue_config_info { u16 vsi_id; u16 num_queue_pairs; u32 pad; - struct virtchnl_queue_pair_info qpair[1]; + struct virtchnl_queue_pair_info qpair[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vsi_queue_config_info); +#define virtchnl_vsi_queue_config_info_LEGACY_SIZEOF 72 /* VIRTCHNL_OP_REQUEST_QUEUES * VF sends this message to request the PF to allocate additional queues to @@ -385,10 +387,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_vector_map); struct virtchnl_irq_map_info { u16 num_vectors; - struct virtchnl_vector_map vecmap[1]; + struct virtchnl_vector_map vecmap[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(14, virtchnl_irq_map_info); +VIRTCHNL_CHECK_STRUCT_LEN(2, virtchnl_irq_map_info); +#define virtchnl_irq_map_info_LEGACY_SIZEOF 14 /* VIRTCHNL_OP_ENABLE_QUEUES * VIRTCHNL_OP_DISABLE_QUEUES @@ -459,10 +462,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr); struct virtchnl_ether_addr_list { u16 vsi_id; u16 num_elements; - struct virtchnl_ether_addr list[1]; + struct virtchnl_ether_addr list[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_ether_addr_list); +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_ether_addr_list); +#define virtchnl_ether_addr_list_LEGACY_SIZEOF 12 /* VIRTCHNL_OP_ADD_VLAN * VF sends this message to add one or more VLAN tag filters for receives. @@ -481,10 +485,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_ether_addr_list); struct virtchnl_vlan_filter_list { u16 vsi_id; u16 num_elements; - u16 vlan_id[1]; + u16 vlan_id[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_vlan_filter_list); +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_vlan_filter_list); +#define virtchnl_vlan_filter_list_LEGACY_SIZEOF 6 /* This enum is used for all of the VIRTCHNL_VF_OFFLOAD_VLAN_V2_CAPS related * structures and opcodes. @@ -1372,11 +1377,19 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del); #define __vss_byone(p, member, count, old) \ (struct_size(p, member, count) + (old - 1 - struct_size(p, member, 0))) +#define __vss_full(p, member, count, old) \ + (struct_size(p, member, count) + (old - struct_size(p, member, 0))) + #define __vss(type, func, p, member, count) \ struct type: func(p, member, count, type##_LEGACY_SIZEOF) #define virtchnl_struct_size(p, m, c) \ _Generic(*p, \ + __vss(virtchnl_vf_resource, __vss_full, p, m, c), \ + __vss(virtchnl_vsi_queue_config_info, __vss_full, p, m, c), \ + __vss(virtchnl_irq_map_info, __vss_full, p, m, c), \ + __vss(virtchnl_ether_addr_list, __vss_full, p, m, c), \ + __vss(virtchnl_vlan_filter_list, __vss_full, p, m, c), \ __vss(virtchnl_rss_key, __vss_byone, p, m, c), \ __vss(virtchnl_rss_lut, __vss_byone, p, m, c)) @@ -1414,24 +1427,23 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, valid_len = sizeof(struct virtchnl_rxq_info); break; case VIRTCHNL_OP_CONFIG_VSI_QUEUES: - valid_len = sizeof(struct virtchnl_vsi_queue_config_info); + valid_len = virtchnl_vsi_queue_config_info_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_vsi_queue_config_info *vqc = (struct virtchnl_vsi_queue_config_info *)msg; - valid_len += (vqc->num_queue_pairs * - sizeof(struct - virtchnl_queue_pair_info)); + valid_len = virtchnl_struct_size(vqc, qpair, + vqc->num_queue_pairs); if (vqc->num_queue_pairs == 0) err_msg_format = true; } break; case VIRTCHNL_OP_CONFIG_IRQ_MAP: - valid_len = sizeof(struct virtchnl_irq_map_info); + valid_len = virtchnl_irq_map_info_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_irq_map_info *vimi = (struct virtchnl_irq_map_info *)msg; - valid_len += (vimi->num_vectors * - sizeof(struct virtchnl_vector_map)); + valid_len = virtchnl_struct_size(vimi, vecmap, + vimi->num_vectors); if (vimi->num_vectors == 0) err_msg_format = true; } @@ -1442,23 +1454,24 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, break; case VIRTCHNL_OP_ADD_ETH_ADDR: case VIRTCHNL_OP_DEL_ETH_ADDR: - valid_len = sizeof(struct virtchnl_ether_addr_list); + valid_len = virtchnl_ether_addr_list_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_ether_addr_list *veal = (struct virtchnl_ether_addr_list *)msg; - valid_len += veal->num_elements * - sizeof(struct virtchnl_ether_addr); + valid_len = virtchnl_struct_size(veal, list, + veal->num_elements); if (veal->num_elements == 0) err_msg_format = true; } break; case VIRTCHNL_OP_ADD_VLAN: case VIRTCHNL_OP_DEL_VLAN: - valid_len = sizeof(struct virtchnl_vlan_filter_list); + valid_len = virtchnl_vlan_filter_list_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_vlan_filter_list *vfl = (struct virtchnl_vlan_filter_list *)msg; - valid_len += vfl->num_elements * sizeof(u16); + valid_len = virtchnl_struct_size(vfl, vlan_id, + vfl->num_elements); if (vfl->num_elements == 0) err_msg_format = true; } -- cgit v1.2.3 From b0654e64dbaf62f565b5f2b4fbd92202e88dcba3 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 28 Jul 2023 17:52:07 +0200 Subject: virtchnl: fix fake 1-elem arrays for structures allocated as `nents` Finally, fix 3 structures which are allocated technically correctly, i.e. the calculated size equals to the one that struct_size() would return, except for sizeof(). For &virtchnl_vlan_filter_list_v2, use the same approach when there are no enough space as taken previously for &virtchnl_vlan_filter_list, i.e. let the maximum size be calculated automatically instead of trying to guestimate it using maths. Signed-off-by: Alexander Lobakin Reviewed-by: Kees Cook Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 7 ++-- drivers/net/ethernet/intel/iavf/iavf_client.c | 4 +-- drivers/net/ethernet/intel/iavf/iavf_client.h | 2 +- drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 25 +++++--------- include/linux/avf/virtchnl.h | 39 +++++++++++++--------- 5 files changed, 40 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index a6983c2d7c30..8ea1a238dcef 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -506,6 +506,7 @@ i40e_config_rdma_qvlist(struct i40e_vf *vf, struct virtchnl_rdma_qv_info *qv_info; u32 v_idx, i, reg_idx, reg; u32 next_q_idx, next_q_type; + size_t size; u32 msix_vf; int ret = 0; @@ -521,9 +522,9 @@ i40e_config_rdma_qvlist(struct i40e_vf *vf, } kfree(vf->qvlist_info); - vf->qvlist_info = kzalloc(struct_size(vf->qvlist_info, qv_info, - qvlist_info->num_vectors - 1), - GFP_KERNEL); + size = virtchnl_struct_size(vf->qvlist_info, qv_info, + qvlist_info->num_vectors); + vf->qvlist_info = kzalloc(size, GFP_KERNEL); if (!vf->qvlist_info) { ret = -ENOMEM; goto err_out; diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.c b/drivers/net/ethernet/intel/iavf/iavf_client.c index 93c903c02c64..e6051b6355aa 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_client.c +++ b/drivers/net/ethernet/intel/iavf/iavf_client.c @@ -469,8 +469,8 @@ static int iavf_client_setup_qvlist(struct iavf_info *ldev, } v_qvlist_info = (struct virtchnl_rdma_qvlist_info *)qvlist_info; - msg_size = struct_size(v_qvlist_info, qv_info, - v_qvlist_info->num_vectors - 1); + msg_size = virtchnl_struct_size(v_qvlist_info, qv_info, + v_qvlist_info->num_vectors); adapter->client_pending |= BIT(VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP); err = iavf_aq_send_msg_to_pf(&adapter->hw, diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.h b/drivers/net/ethernet/intel/iavf/iavf_client.h index c5d51d7dc7cc..500269bc0f5b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_client.h +++ b/drivers/net/ethernet/intel/iavf/iavf_client.h @@ -53,7 +53,7 @@ struct iavf_qv_info { struct iavf_qvlist_info { u32 num_vectors; - struct iavf_qv_info qv_info[1]; + struct iavf_qv_info qv_info[]; }; #define IAVF_CLIENT_MSIX_ALL 0xFFFFFFFF diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 4fdac698eb38..f9727e9c3d63 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -727,15 +727,12 @@ void iavf_add_vlans(struct iavf_adapter *adapter) more = true; } - len = sizeof(*vvfl_v2) + ((count - 1) * - sizeof(struct virtchnl_vlan_filter)); + len = virtchnl_struct_size(vvfl_v2, filters, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(*vvfl_v2)) / - sizeof(struct virtchnl_vlan_filter); - len = sizeof(*vvfl_v2) + - ((count - 1) * - sizeof(struct virtchnl_vlan_filter)); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(vvfl_v2, filters, + --count); more = true; } @@ -879,16 +876,12 @@ void iavf_del_vlans(struct iavf_adapter *adapter) adapter->current_op = VIRTCHNL_OP_DEL_VLAN_V2; - len = sizeof(*vvfl_v2) + - ((count - 1) * sizeof(struct virtchnl_vlan_filter)); + len = virtchnl_struct_size(vvfl_v2, filters, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); - count = (IAVF_MAX_AQ_BUF_SIZE - - sizeof(*vvfl_v2)) / - sizeof(struct virtchnl_vlan_filter); - len = sizeof(*vvfl_v2) + - ((count - 1) * - sizeof(struct virtchnl_vlan_filter)); + while (len > IAVF_MAX_AQ_BUF_SIZE) + len = virtchnl_struct_size(vvfl_v2, filters, + --count); more = true; } @@ -1492,7 +1485,7 @@ void iavf_enable_channels(struct iavf_adapter *adapter) return; } - len = struct_size(vti, list, adapter->num_tc - 1); + len = virtchnl_struct_size(vti, list, adapter->num_tc); vti = kzalloc(len, GFP_KERNEL); if (!vti) return; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index c1a20b533fc0..d0807ad43f93 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -716,10 +716,11 @@ struct virtchnl_vlan_filter_list_v2 { u16 vport_id; u16 num_elements; u8 pad[4]; - struct virtchnl_vlan_filter filters[1]; + struct virtchnl_vlan_filter filters[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_vlan_filter_list_v2); +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vlan_filter_list_v2); +#define virtchnl_vlan_filter_list_v2_LEGACY_SIZEOF 40 /* VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 * VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 @@ -918,10 +919,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_channel_info); struct virtchnl_tc_info { u32 num_tc; u32 pad; - struct virtchnl_channel_info list[1]; + struct virtchnl_channel_info list[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_tc_info); +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_tc_info); +#define virtchnl_tc_info_LEGACY_SIZEOF 24 /* VIRTCHNL_ADD_CLOUD_FILTER * VIRTCHNL_DEL_CLOUD_FILTER @@ -1059,10 +1061,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_rdma_qv_info); struct virtchnl_rdma_qvlist_info { u32 num_vectors; - struct virtchnl_rdma_qv_info qv_info[1]; + struct virtchnl_rdma_qv_info qv_info[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_rdma_qvlist_info); +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rdma_qvlist_info); +#define virtchnl_rdma_qvlist_info_LEGACY_SIZEOF 16 /* VF reset states - these are written into the RSTAT register: * VFGEN_RSTAT on the VF @@ -1377,6 +1380,9 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del); #define __vss_byone(p, member, count, old) \ (struct_size(p, member, count) + (old - 1 - struct_size(p, member, 0))) +#define __vss_byelem(p, member, count, old) \ + (struct_size(p, member, count - 1) + (old - struct_size(p, member, 0))) + #define __vss_full(p, member, count, old) \ (struct_size(p, member, count) + (old - struct_size(p, member, 0))) @@ -1390,6 +1396,9 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del); __vss(virtchnl_irq_map_info, __vss_full, p, m, c), \ __vss(virtchnl_ether_addr_list, __vss_full, p, m, c), \ __vss(virtchnl_vlan_filter_list, __vss_full, p, m, c), \ + __vss(virtchnl_vlan_filter_list_v2, __vss_byelem, p, m, c), \ + __vss(virtchnl_tc_info, __vss_byelem, p, m, c), \ + __vss(virtchnl_rdma_qvlist_info, __vss_byelem, p, m, c), \ __vss(virtchnl_rss_key, __vss_byone, p, m, c), \ __vss(virtchnl_rss_lut, __vss_byone, p, m, c)) @@ -1495,13 +1504,13 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_RELEASE_RDMA_IRQ_MAP: break; case VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP: - valid_len = sizeof(struct virtchnl_rdma_qvlist_info); + valid_len = virtchnl_rdma_qvlist_info_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_rdma_qvlist_info *qv = (struct virtchnl_rdma_qvlist_info *)msg; - valid_len += ((qv->num_vectors - 1) * - sizeof(struct virtchnl_rdma_qv_info)); + valid_len = virtchnl_struct_size(qv, qv_info, + qv->num_vectors); } break; case VIRTCHNL_OP_CONFIG_RSS_KEY: @@ -1534,12 +1543,12 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, valid_len = sizeof(struct virtchnl_vf_res_request); break; case VIRTCHNL_OP_ENABLE_CHANNELS: - valid_len = sizeof(struct virtchnl_tc_info); + valid_len = virtchnl_tc_info_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_tc_info *vti = (struct virtchnl_tc_info *)msg; - valid_len += (vti->num_tc - 1) * - sizeof(struct virtchnl_channel_info); + valid_len = virtchnl_struct_size(vti, list, + vti->num_tc); if (vti->num_tc == 0) err_msg_format = true; } @@ -1566,13 +1575,13 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, break; case VIRTCHNL_OP_ADD_VLAN_V2: case VIRTCHNL_OP_DEL_VLAN_V2: - valid_len = sizeof(struct virtchnl_vlan_filter_list_v2); + valid_len = virtchnl_vlan_filter_list_v2_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_vlan_filter_list_v2 *vfl = (struct virtchnl_vlan_filter_list_v2 *)msg; - valid_len += (vfl->num_elements - 1) * - sizeof(struct virtchnl_vlan_filter); + valid_len = virtchnl_struct_size(vfl, filters, + vfl->num_elements); if (vfl->num_elements == 0) { err_msg_format = true; -- cgit v1.2.3 From 4072d97ddc447ce9dd8f7a39cdf6f92d2031bb01 Mon Sep 17 00:00:00 2001 From: François Michel Date: Tue, 15 Aug 2023 11:23:38 +0200 Subject: netem: add prng attribute to netem_sched_data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add prng attribute to struct netem_sched_data and allows setting the seed of the PRNG through netlink using the new TCA_NETEM_PRNG_SEED attribute. The PRNG attribute is not actually used yet. Signed-off-by: François Michel Reviewed-by: Simon Horman Acked-by: Stephen Hemminger Link: https://lore.kernel.org/r/20230815092348.1449179-2-francois.michel@uclouvain.be Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_sched.h | 1 + net/sched/sch_netem.c | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 00f6ff0aff1f..3f85ae578056 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -603,6 +603,7 @@ enum { TCA_NETEM_JITTER64, TCA_NETEM_SLOT, TCA_NETEM_SLOT_DIST, + TCA_NETEM_PRNG_SEED, __TCA_NETEM_MAX, }; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 38d9aa0cd30e..621c6acfd644 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -105,6 +105,11 @@ struct netem_sched_data { u32 rho; } delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor; + struct prng { + u64 seed; + struct rnd_state prng_state; + } prng; + struct disttable *delay_dist; enum { @@ -922,6 +927,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_LATENCY64] = { .type = NLA_S64 }, [TCA_NETEM_JITTER64] = { .type = NLA_S64 }, [TCA_NETEM_SLOT] = { .len = sizeof(struct tc_netem_slot) }, + [TCA_NETEM_PRNG_SEED] = { .type = NLA_U64 }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -1040,6 +1046,12 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, /* capping jitter to the range acceptable by tabledist() */ q->jitter = min_t(s64, abs(q->jitter), INT_MAX); + if (tb[TCA_NETEM_PRNG_SEED]) + q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]); + else + q->prng.seed = get_random_u64(); + prandom_seed_state(&q->prng.prng_state, q->prng.seed); + unlock: sch_tree_unlock(sch); @@ -1203,6 +1215,10 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) goto nla_put_failure; } + if (nla_put_u64_64bit(skb, TCA_NETEM_PRNG_SEED, q->prng.seed, + TCA_NETEM_PAD)) + goto nla_put_failure; + return nla_nest_end(skb, nla); nla_put_failure: -- cgit v1.2.3 From a171fbec88a2c730b108c7147ac5e7b2f5a02b47 Mon Sep 17 00:00:00 2001 From: Yan Zhai Date: Thu, 17 Aug 2023 19:58:14 -0700 Subject: lwt: Check LWTUNNEL_XMIT_CONTINUE strictly LWTUNNEL_XMIT_CONTINUE is implicitly assumed in ip(6)_finish_output2, such that any positive return value from a xmit hook could cause unexpected continue behavior, despite that related skb may have been freed. This could be error-prone for future xmit hook ops. One of the possible errors is to return statuses of dst_output directly. To make the code safer, redefine LWTUNNEL_XMIT_CONTINUE value to distinguish from dst_output statuses and check the continue condition explicitly. Fixes: 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure") Suggested-by: Dan Carpenter Signed-off-by: Yan Zhai Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/96b939b85eda00e8df4f7c080f770970a4c5f698.1692326837.git.yan@cloudflare.com --- include/net/lwtunnel.h | 5 ++++- net/ipv4/ip_output.c | 2 +- net/ipv6/ip6_output.c | 2 +- 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 6f15e6fa154e..53bd2d02a4f0 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -16,9 +16,12 @@ #define LWTUNNEL_STATE_INPUT_REDIRECT BIT(1) #define LWTUNNEL_STATE_XMIT_REDIRECT BIT(2) +/* LWTUNNEL_XMIT_CONTINUE should be distinguishable from dst_output return + * values (NET_XMIT_xxx and NETDEV_TX_xxx in linux/netdevice.h) for safety. + */ enum { LWTUNNEL_XMIT_DONE, - LWTUNNEL_XMIT_CONTINUE, + LWTUNNEL_XMIT_CONTINUE = 0x100, }; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index ce6257860a40..43ba4b77b248 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -216,7 +216,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); - if (res < 0 || res == LWTUNNEL_XMIT_DONE) + if (res != LWTUNNEL_XMIT_CONTINUE) return res; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index f8a1f6bb3f87..0665e8b09968 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -113,7 +113,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); - if (res < 0 || res == LWTUNNEL_XMIT_DONE) + if (res != LWTUNNEL_XMIT_CONTINUE) return res; } -- cgit v1.2.3 From bbed596c74a527e0d0d30bc56732f26407f12d6e Mon Sep 17 00:00:00 2001 From: Guangguan Wang Date: Thu, 17 Aug 2023 21:20:32 +0800 Subject: net/smc: Extend SMCR v2 linkgroup netlink attribute Add SMC_NLA_LGR_R_V2_MAX_CONNS and SMC_NLA_LGR_R_V2_MAX_LINKS to SMCR v2 linkgroup netlink attribute SMC_NLA_LGR_R_V2 for linkgroup's detail info showing. Signed-off-by: Guangguan Wang Reviewed-by: Jan Karcher Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 2 ++ net/smc/smc_core.c | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index bb4dacca31e7..837fcd4b0abc 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -107,6 +107,8 @@ enum { enum { SMC_NLA_LGR_R_V2_UNSPEC, SMC_NLA_LGR_R_V2_DIRECT, /* u8 */ + SMC_NLA_LGR_R_V2_MAX_CONNS, /* u8 */ + SMC_NLA_LGR_R_V2_MAX_LINKS, /* u8 */ __SMC_NLA_LGR_R_V2_MAX, SMC_NLA_LGR_R_V2_MAX = __SMC_NLA_LGR_R_V2_MAX - 1 }; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index aae8d3f5c3cf..bd01dd31e4bd 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -319,6 +319,10 @@ static int smc_nl_fill_smcr_lgr_v2(struct smc_link_group *lgr, goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_DIRECT, !lgr->uses_gateway)) goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_CONNS, lgr->max_conns)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_LINKS, lgr->max_links)) + goto errv2attr; nla_nest_end(skb, v2_attrs); return 0; -- cgit v1.2.3 From 4025d3e73abde4f65f4b04d4b1d8449b00e31473 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 18 Aug 2023 09:40:39 +0000 Subject: net: add skb_queue_purge_reason and __skb_queue_purge_reason skb_queue_purge() and __skb_queue_purge() become wrappers around the new generic functions. New SKB_DROP_REASON_QUEUE_PURGE drop reason is added, but users can start adding more specific reasons. Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/skbuff.h | 23 +++++++++++++++++++---- include/net/dropreason-core.h | 3 +++ net/core/skbuff.c | 11 +++++++---- 3 files changed, 29 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index aa57e2eca33b..9aec136bc690 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3149,20 +3149,35 @@ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) } /** - * __skb_queue_purge - empty a list + * __skb_queue_purge_reason - empty a list * @list: list to empty + * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ -static inline void __skb_queue_purge(struct sk_buff_head *list) +static inline void __skb_queue_purge_reason(struct sk_buff_head *list, + enum skb_drop_reason reason) { struct sk_buff *skb; + while ((skb = __skb_dequeue(list)) != NULL) - kfree_skb(skb); + kfree_skb_reason(skb, reason); +} + +static inline void __skb_queue_purge(struct sk_buff_head *list) +{ + __skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); +} + +void skb_queue_purge_reason(struct sk_buff_head *list, + enum skb_drop_reason reason); + +static inline void skb_queue_purge(struct sk_buff_head *list) +{ + skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } -void skb_queue_purge(struct sk_buff_head *list); unsigned int skb_rbtree_purge(struct rb_root *root); diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index f291a3b0f9e5..a587e83fc169 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -79,6 +79,7 @@ FN(IPV6_NDISC_BAD_CODE) \ FN(IPV6_NDISC_BAD_OPTIONS) \ FN(IPV6_NDISC_NS_OTHERHOST) \ + FN(QUEUE_PURGE) \ FNe(MAX) /** @@ -342,6 +343,8 @@ enum skb_drop_reason { * for another host. */ SKB_DROP_REASON_IPV6_NDISC_NS_OTHERHOST, + /** @SKB_DROP_REASON_QUEUE_PURGE: bulk free. */ + SKB_DROP_REASON_QUEUE_PURGE, /** * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which * shouldn't be used as a real 'reason' - only for tracing code gen diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9b5bc621daf7..117d36b1fae3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3701,20 +3701,23 @@ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list) EXPORT_SYMBOL(skb_dequeue_tail); /** - * skb_queue_purge - empty a list + * skb_queue_purge_reason - empty a list * @list: list to empty + * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function takes the list * lock and is atomic with respect to other list locking functions. */ -void skb_queue_purge(struct sk_buff_head *list) +void skb_queue_purge_reason(struct sk_buff_head *list, + enum skb_drop_reason reason) { struct sk_buff *skb; + while ((skb = skb_dequeue(list)) != NULL) - kfree_skb(skb); + kfree_skb_reason(skb, reason); } -EXPORT_SYMBOL(skb_queue_purge); +EXPORT_SYMBOL(skb_queue_purge_reason); /** * skb_rbtree_purge - empty a skb rbtree -- cgit v1.2.3 From f132fdd9dc81e045bcf95005d418a31fbe9d942f Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Mon, 2 May 2022 14:40:56 +0300 Subject: macsec: add functions to get macsec real netdevice and check offload Given a macsec net_device add two functions to return the real net_device for that device, and check if that macsec device is offloaded or not. This is needed for auxiliary drivers that implement MACsec offload, but have flows which are triggered over the macsec net_device, this allows the drivers in such cases to verify if the device is offloaded or not, and to access the real device of that macsec device, which would belong to the driver, and would be needed for the offload procedure. Signed-off-by: Patrisious Haddad Reviewed-by: Raed Salem Reviewed-by: Mark Zhang Signed-off-by: Leon Romanovsky --- drivers/net/macsec.c | 12 ++++++++++++ include/net/macsec.h | 2 ++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 984dfa5d6c11..4895af1c5b7b 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -4240,6 +4240,18 @@ static struct net *macsec_get_link_net(const struct net_device *dev) return dev_net(macsec_priv(dev)->real_dev); } +struct net_device *macsec_get_real_dev(const struct net_device *dev) +{ + return macsec_priv(dev)->real_dev; +} +EXPORT_SYMBOL_GPL(macsec_get_real_dev); + +bool macsec_netdev_is_offloaded(struct net_device *dev) +{ + return macsec_is_offloaded(macsec_priv(dev)); +} +EXPORT_SYMBOL_GPL(macsec_netdev_is_offloaded); + static size_t macsec_get_size(const struct net_device *dev) { return nla_total_size_64bit(8) + /* IFLA_MACSEC_SCI */ diff --git a/include/net/macsec.h b/include/net/macsec.h index 441ed8fd4b5f..75a6f4863c83 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -312,6 +312,8 @@ static inline bool macsec_send_sci(const struct macsec_secy *secy) return tx_sc->send_sci || (secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb); } +struct net_device *macsec_get_real_dev(const struct net_device *dev); +bool macsec_netdev_is_offloaded(struct net_device *dev); static inline void *macsec_netdev_priv(const struct net_device *dev) { -- cgit v1.2.3 From 2e92f669b86d70a26a77b088c74e1cb6d26322e1 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Tue, 6 Dec 2022 14:33:49 +0200 Subject: net/mlx5e: Move MACsec flow steering and statistics database from ethernet to core Since now MACsec flow steering (macsec_fs) and MACsec statistics (stats) are maintained by the core driver, move their data as well to be saved inside core structures instead of staying part of ethernet MACsec database. In addition cleanup all MACsec stats functions from the ethernet MACsec code and move what's needed to be part of macsec_fs instead. Signed-off-by: Patrisious Haddad Signed-off-by: Leon Romanovsky --- .../ethernet/mellanox/mlx5/core/en_accel/macsec.c | 25 ++++------------------ .../ethernet/mellanox/mlx5/core/en_accel/macsec.h | 2 -- .../mellanox/mlx5/core/en_accel/macsec_stats.c | 6 ++++-- .../ethernet/mellanox/mlx5/core/lib/macsec_fs.c | 11 ++++++++++ .../ethernet/mellanox/mlx5/core/lib/macsec_fs.h | 1 + include/linux/mlx5/driver.h | 3 +++ 6 files changed, 23 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 831d83094abd..5e8ad355c67f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -124,7 +124,6 @@ struct mlx5e_macsec_device { struct mlx5e_macsec { struct list_head macsec_device_list_head; int num_of_devices; - struct mlx5_macsec_fs *macsec_fs; struct mutex lock; /* Protects mlx5e_macsec internal contexts */ /* Tx sci -> fs id mapping handling */ @@ -135,9 +134,6 @@ struct mlx5e_macsec { struct mlx5_core_dev *mdev; - /* Stats manage */ - struct mlx5_macsec_stats stats; - /* ASO */ struct mlx5e_macsec_aso aso; @@ -343,7 +339,7 @@ static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, if (!sa->macsec_rule) return; - mlx5_macsec_fs_del_rule(macsec->macsec_fs, sa->macsec_rule, action); + mlx5_macsec_fs_del_rule(macsec->mdev->macsec_fs, sa->macsec_rule, action); mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id); sa->macsec_rule = NULL; } @@ -386,7 +382,7 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : MLX5_ACCEL_MACSEC_ACTION_DECRYPT; - macsec_rule = mlx5_macsec_fs_add_rule(macsec->macsec_fs, ctx, &rule_attrs, &sa->fs_id); + macsec_rule = mlx5_macsec_fs_add_rule(mdev->macsec_fs, ctx, &rule_attrs, &sa->fs_id); if (!macsec_rule) { err = -ENOMEM; goto destroy_macsec_object; @@ -1677,19 +1673,6 @@ bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev) return true; } -void mlx5e_macsec_get_stats_fill(struct mlx5e_macsec *macsec, void *macsec_stats) -{ - mlx5_macsec_fs_get_stats_fill(macsec->macsec_fs, macsec_stats); -} - -struct mlx5_macsec_stats *mlx5e_macsec_get_stats(struct mlx5e_macsec *macsec) -{ - if (!macsec) - return NULL; - - return &macsec->stats; -} - static const struct macsec_ops macsec_offload_ops = { .mdo_add_txsa = mlx5e_macsec_add_txsa, .mdo_upd_txsa = mlx5e_macsec_upd_txsa, @@ -1827,7 +1810,7 @@ int mlx5e_macsec_init(struct mlx5e_priv *priv) goto err_out; } - macsec->macsec_fs = macsec_fs; + mdev->macsec_fs = macsec_fs; macsec->nb.notifier_call = macsec_obj_change_event; mlx5_notifier_register(mdev, &macsec->nb); @@ -1857,7 +1840,7 @@ void mlx5e_macsec_cleanup(struct mlx5e_priv *priv) return; mlx5_notifier_unregister(mdev, &macsec->nb); - mlx5_macsec_fs_cleanup(macsec->macsec_fs); + mlx5_macsec_fs_cleanup(mdev->macsec_fs); destroy_workqueue(macsec->wq); mlx5e_macsec_aso_cleanup(&macsec->aso, mdev); rhashtable_destroy(&macsec->sci_hash); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h index 47dc1d4448d9..2ecd769585f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h @@ -37,8 +37,6 @@ static inline bool mlx5e_macsec_is_rx_flow(struct mlx5_cqe64 *cqe) void mlx5e_macsec_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb, struct mlx5_cqe64 *cqe); bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev); -void mlx5e_macsec_get_stats_fill(struct mlx5e_macsec *macsec, void *macsec_stats); -struct mlx5_macsec_stats *mlx5e_macsec_get_stats(struct mlx5e_macsec *macsec); #else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c index 8326a593b3fb..4559ee16a11a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c @@ -52,6 +52,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(macsec_hw) static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(macsec_hw) { + struct mlx5_macsec_fs *macsec_fs; int i; if (!priv->macsec) @@ -60,9 +61,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(macsec_hw) if (!mlx5e_is_macsec_device(priv->mdev)) return idx; - mlx5e_macsec_get_stats_fill(priv->macsec, mlx5e_macsec_get_stats(priv->macsec)); + macsec_fs = priv->mdev->macsec_fs; + mlx5_macsec_fs_get_stats_fill(macsec_fs, mlx5_macsec_fs_get_stats(macsec_fs)); for (i = 0; i < NUM_MACSEC_HW_COUNTERS; i++) - data[idx++] = MLX5E_READ_CTR64_CPU(mlx5e_macsec_get_stats(priv->macsec), + data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_macsec_fs_get_stats(macsec_fs), mlx5e_macsec_hw_stats_desc, i); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c index c585d61324bf..11f9c5a8e43a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c @@ -106,6 +106,9 @@ struct mlx5_macsec_fs { struct net_device *netdev; struct mlx5_macsec_tx *tx_fs; struct mlx5_macsec_rx *rx_fs; + + /* Stats manage */ + struct mlx5_macsec_stats stats; }; static void macsec_fs_destroy_groups(struct mlx5_macsec_flow_table *ft) @@ -1355,6 +1358,14 @@ void mlx5_macsec_fs_get_stats_fill(struct mlx5_macsec_fs *macsec_fs, void *macse &stats->macsec_rx_pkts_drop, &stats->macsec_rx_bytes_drop); } +struct mlx5_macsec_stats *mlx5_macsec_fs_get_stats(struct mlx5_macsec_fs *macsec_fs) +{ + if (!macsec_fs) + return NULL; + + return &macsec_fs->stats; +} + union mlx5_macsec_rule * mlx5_macsec_fs_add_rule(struct mlx5_macsec_fs *macsec_fs, const struct macsec_context *macsec_ctx, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h index 6a749e036e68..c0c28d08eae5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.h @@ -56,6 +56,7 @@ void mlx5_macsec_fs_del_rule(struct mlx5_macsec_fs *macsec_fs, int action); void mlx5_macsec_fs_get_stats_fill(struct mlx5_macsec_fs *macsec_fs, void *macsec_stats); +struct mlx5_macsec_stats *mlx5_macsec_fs_get_stats(struct mlx5_macsec_fs *macsec_fs); #endif diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 25d0528f9219..0e80241c270f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -805,6 +805,9 @@ struct mlx5_core_dev { u32 vsc_addr; struct mlx5_hv_vhca *hv_vhca; struct mlx5_thermal *thermal; +#ifdef CONFIG_MLX5_MACSEC + struct mlx5_macsec_fs *macsec_fs; +#endif }; struct mlx5_db { -- cgit v1.2.3 From 758ce14aee825f8f3ca8f76c9991c108094cae8b Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Tue, 3 May 2022 08:37:48 +0300 Subject: RDMA/mlx5: Implement MACsec gid addition and deletion Handle MACsec IP ambiguity issue, since mlx5 hw can't support programming both the MACsec and the physical gid when they have the same IP address, because it wouldn't know to whom to steer the traffic. Hence in such case we delete the physical gid from the hw gid table, which would then cause all traffic sent over it to fail, and we'll only be able to send traffic over the MACsec gid. Signed-off-by: Patrisious Haddad Reviewed-by: Raed Salem Reviewed-by: Mark Zhang Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/Makefile | 1 + drivers/infiniband/hw/mlx5/macsec.c | 155 +++++++++++++++++++++ drivers/infiniband/hw/mlx5/macsec.h | 25 ++++ drivers/infiniband/hw/mlx5/main.c | 37 +++-- drivers/infiniband/hw/mlx5/mlx5_ib.h | 7 + .../ethernet/mellanox/mlx5/core/en_accel/macsec.c | 31 ----- .../ethernet/mellanox/mlx5/core/en_accel/macsec.h | 2 - include/linux/mlx5/driver.h | 44 ++++++ 8 files changed, 260 insertions(+), 42 deletions(-) create mode 100644 drivers/infiniband/hw/mlx5/macsec.c create mode 100644 drivers/infiniband/hw/mlx5/macsec.h (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/Makefile b/drivers/infiniband/hw/mlx5/Makefile index 612ee8190a2d..72a526236c2e 100644 --- a/drivers/infiniband/hw/mlx5/Makefile +++ b/drivers/infiniband/hw/mlx5/Makefile @@ -28,3 +28,4 @@ mlx5_ib-$(CONFIG_INFINIBAND_USER_ACCESS) += devx.o \ fs.o \ qos.o \ std_types.o +mlx5_ib-$(CONFIG_MLX5_MACSEC) += macsec.o diff --git a/drivers/infiniband/hw/mlx5/macsec.c b/drivers/infiniband/hw/mlx5/macsec.c new file mode 100644 index 000000000000..349ad13af75d --- /dev/null +++ b/drivers/infiniband/hw/mlx5/macsec.c @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */ + +#include "macsec.h" + +struct mlx5_reserved_gids { + int macsec_index; + const struct ib_gid_attr *physical_gid; +}; + +int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev) +{ + int i, j, max_gids; + + if (!mlx5_is_macsec_roce_supported(dev->mdev)) { + mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n"); + return 0; + } + + max_gids = MLX5_CAP_ROCE(dev->mdev, roce_address_table_size); + for (i = 0; i < dev->num_ports; i++) { + dev->port[i].reserved_gids = kcalloc(max_gids, + sizeof(*dev->port[i].reserved_gids), + GFP_KERNEL); + if (!dev->port[i].reserved_gids) + goto err; + + for (j = 0; j < max_gids; j++) + dev->port[i].reserved_gids[j].macsec_index = -1; + } + + return 0; +err: + while (i >= 0) { + kfree(dev->port[i].reserved_gids); + i--; + } + return -ENOMEM; +} + +void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev) +{ + int i; + + if (!mlx5_is_macsec_roce_supported(dev->mdev)) + mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n"); + + for (i = 0; i < dev->num_ports; i++) + kfree(dev->port[i].reserved_gids); +} + +int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr) +{ + struct mlx5_ib_dev *dev = to_mdev(attr->device); + const struct ib_gid_attr *physical_gid; + struct mlx5_reserved_gids *mgids; + struct net_device *ndev; + int ret = 0; + + if (attr->gid_type != IB_GID_TYPE_ROCE_UDP_ENCAP) + return 0; + + if (!mlx5_is_macsec_roce_supported(dev->mdev)) { + mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n"); + return 0; + } + + rcu_read_lock(); + ndev = rcu_dereference(attr->ndev); + if (!ndev) { + rcu_read_unlock(); + return -ENODEV; + } + + if (!netif_is_macsec(ndev) || !macsec_netdev_is_offloaded(ndev)) { + rcu_read_unlock(); + return 0; + } + rcu_read_unlock(); + + physical_gid = rdma_find_gid(attr->device, &attr->gid, + attr->gid_type, NULL); + if (IS_ERR(physical_gid)) + return 0; + + ret = set_roce_addr(to_mdev(physical_gid->device), + physical_gid->port_num, + physical_gid->index, NULL, + physical_gid); + if (ret) + goto gid_err; + + mgids = &dev->port[attr->port_num - 1].reserved_gids[physical_gid->index]; + mgids->macsec_index = attr->index; + mgids->physical_gid = physical_gid; + + return 0; + +gid_err: + rdma_put_gid_attr(physical_gid); + return ret; +} + +void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr) +{ + struct mlx5_ib_dev *dev = to_mdev(attr->device); + struct mlx5_reserved_gids *mgids; + struct net_device *ndev; + int i, max_gids; + + if (attr->gid_type != IB_GID_TYPE_ROCE_UDP_ENCAP) + return; + + if (!mlx5_is_macsec_roce_supported(dev->mdev)) { + mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n"); + return; + } + + mgids = &dev->port[attr->port_num - 1].reserved_gids[attr->index]; + if (mgids->macsec_index != -1) { /* Checking if physical gid has ambiguous IP */ + rdma_put_gid_attr(mgids->physical_gid); + mgids->macsec_index = -1; + return; + } + + rcu_read_lock(); + ndev = rcu_dereference(attr->ndev); + if (!ndev) { + rcu_read_unlock(); + return; + } + + if (!netif_is_macsec(ndev) || !macsec_netdev_is_offloaded(ndev)) { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + + max_gids = MLX5_CAP_ROCE(dev->mdev, roce_address_table_size); + for (i = 0; i < max_gids; i++) { /* Checking if macsec gid has ambiguous IP */ + mgids = &dev->port[attr->port_num - 1].reserved_gids[i]; + if (mgids->macsec_index == attr->index) { + const struct ib_gid_attr *physical_gid = mgids->physical_gid; + + set_roce_addr(to_mdev(physical_gid->device), + physical_gid->port_num, + physical_gid->index, + &physical_gid->gid, physical_gid); + + rdma_put_gid_attr(physical_gid); + mgids->macsec_index = -1; + break; + } + } +} diff --git a/drivers/infiniband/hw/mlx5/macsec.h b/drivers/infiniband/hw/mlx5/macsec.h new file mode 100644 index 000000000000..b60f8f046d6f --- /dev/null +++ b/drivers/infiniband/hw/mlx5/macsec.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */ + +#ifndef __MLX5_MACSEC_H__ +#define __MLX5_MACSEC_H__ + +#include +#include +#include +#include "mlx5_ib.h" + +#ifdef CONFIG_MLX5_MACSEC +struct mlx5_reserved_gids; + +int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr); +void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr); +int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev); +void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev); +#else +static inline int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr) { return 0; } +static inline void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr) {} +static inline int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev) { return 0; } +static inline void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev) {} +#endif +#endif /* __MLX5_MACSEC_H__ */ diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index f0b394ed7452..f463cf8b7501 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -46,6 +46,7 @@ #include #include #include +#include "macsec.h" #define UVERBS_MODULE_NAME mlx5_ib #include @@ -564,9 +565,9 @@ out: return err; } -static int set_roce_addr(struct mlx5_ib_dev *dev, u32 port_num, - unsigned int index, const union ib_gid *gid, - const struct ib_gid_attr *attr) +int set_roce_addr(struct mlx5_ib_dev *dev, u32 port_num, + unsigned int index, const union ib_gid *gid, + const struct ib_gid_attr *attr) { enum ib_gid_type gid_type; u16 vlan_id = 0xffff; @@ -607,6 +608,12 @@ static int set_roce_addr(struct mlx5_ib_dev *dev, u32 port_num, static int mlx5_ib_add_gid(const struct ib_gid_attr *attr, __always_unused void **context) { + int ret; + + ret = mlx5r_add_gid_macsec_operations(attr); + if (ret) + return ret; + return set_roce_addr(to_mdev(attr->device), attr->port_num, attr->index, &attr->gid, attr); } @@ -614,8 +621,15 @@ static int mlx5_ib_add_gid(const struct ib_gid_attr *attr, static int mlx5_ib_del_gid(const struct ib_gid_attr *attr, __always_unused void **context) { - return set_roce_addr(to_mdev(attr->device), attr->port_num, - attr->index, NULL, attr); + int ret; + + ret = set_roce_addr(to_mdev(attr->device), attr->port_num, + attr->index, NULL, attr); + if (ret) + return ret; + + mlx5r_del_gid_macsec_operations(attr); + return 0; } __be16 mlx5_get_roce_udp_sport_min(const struct mlx5_ib_dev *dev, @@ -3644,13 +3658,13 @@ static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) mutex_destroy(&dev->cap_mask_mutex); WARN_ON(!xa_empty(&dev->sig_mrs)); WARN_ON(!bitmap_empty(dev->dm.memic_alloc_pages, MLX5_MAX_MEMIC_PAGES)); + mlx5r_macsec_dealloc_gids(dev); } static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) { struct mlx5_core_dev *mdev = dev->mdev; - int err; - int i; + int err, i; dev->ib_dev.node_type = RDMA_NODE_IB_CA; dev->ib_dev.local_dma_lkey = 0 /* not supported for now */; @@ -3670,10 +3684,14 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) if (err) return err; - err = mlx5_ib_init_multiport_master(dev); + err = mlx5r_macsec_alloc_gids(dev); if (err) return err; + err = mlx5_ib_init_multiport_master(dev); + if (err) + goto err; + err = set_has_smi_cap(dev); if (err) goto err_mp; @@ -3697,7 +3715,8 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) spin_lock_init(&dev->dm.lock); dev->dm.dev = mdev; return 0; - +err: + mlx5r_macsec_dealloc_gids(dev); err_mp: mlx5_ib_cleanup_multiport_master(dev); return err; diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 9c33d960af3c..a4b940b5035f 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -26,6 +26,7 @@ #include "srq.h" #include "qp.h" +#include "macsec.h" #define mlx5_ib_dbg(_dev, format, arg...) \ dev_dbg(&(_dev)->ib_dev.dev, "%s:%d:(pid %d): " format, __func__, \ @@ -870,6 +871,9 @@ struct mlx5_ib_port { struct mlx5_ib_dbg_cc_params *dbg_cc_params; struct mlx5_roce roce; struct mlx5_eswitch_rep *rep; +#ifdef CONFIG_MLX5_MACSEC + struct mlx5_reserved_gids *reserved_gids; +#endif }; struct mlx5_ib_dbg_param { @@ -1648,4 +1652,7 @@ static inline bool mlx5_umem_needs_ats(struct mlx5_ib_dev *dev, return access_flags & IB_ACCESS_RELAXED_ORDERING; } +int set_roce_addr(struct mlx5_ib_dev *dev, u32 port_num, + unsigned int index, const union ib_gid *gid, + const struct ib_gid_attr *attr); #endif /* MLX5_IB_H */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index b4f3f4f10af3..c9c1db971652 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -1607,37 +1607,6 @@ static void mlx5e_macsec_aso_cleanup(struct mlx5e_macsec_aso *aso, struct mlx5_c mlx5_core_dealloc_pd(mdev, aso->pdn); } -bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev) -{ - if (!(MLX5_CAP_GEN_64(mdev, general_obj_types) & - MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD)) - return false; - - if (!MLX5_CAP_GEN(mdev, log_max_dek)) - return false; - - if (!MLX5_CAP_MACSEC(mdev, log_max_macsec_offload)) - return false; - - if (!MLX5_CAP_FLOWTABLE_NIC_RX(mdev, macsec_decrypt) || - !MLX5_CAP_FLOWTABLE_NIC_RX(mdev, reformat_remove_macsec)) - return false; - - if (!MLX5_CAP_FLOWTABLE_NIC_TX(mdev, macsec_encrypt) || - !MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_macsec)) - return false; - - if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_encrypt) && - !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_encrypt)) - return false; - - if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_decrypt) && - !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_decrypt)) - return false; - - return true; -} - static const struct macsec_ops macsec_offload_ops = { .mdo_add_txsa = mlx5e_macsec_add_txsa, .mdo_upd_txsa = mlx5e_macsec_upd_txsa, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h index 2ecd769585f4..27df72e23106 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.h @@ -36,7 +36,6 @@ static inline bool mlx5e_macsec_is_rx_flow(struct mlx5_cqe64 *cqe) void mlx5e_macsec_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb, struct mlx5_cqe64 *cqe); -bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev); #else @@ -49,7 +48,6 @@ static inline void mlx5e_macsec_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb, struct mlx5_cqe64 *cqe) {} -static inline bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev) { return false; } #endif /* CONFIG_MLX5_MACSEC */ #endif /* __MLX5_ACCEL_EN_MACSEC_H__ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 0e80241c270f..21954e7aeeba 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1323,6 +1323,50 @@ static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev) return mlx5_is_roce_on(dev); } +static inline bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev) +{ + if (!(MLX5_CAP_GEN_64(mdev, general_obj_types) & + MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD)) + return false; + + if (!MLX5_CAP_GEN(mdev, log_max_dek)) + return false; + + if (!MLX5_CAP_MACSEC(mdev, log_max_macsec_offload)) + return false; + + if (!MLX5_CAP_FLOWTABLE_NIC_RX(mdev, macsec_decrypt) || + !MLX5_CAP_FLOWTABLE_NIC_RX(mdev, reformat_remove_macsec)) + return false; + + if (!MLX5_CAP_FLOWTABLE_NIC_TX(mdev, macsec_encrypt) || + !MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_macsec)) + return false; + + if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_encrypt) && + !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_encrypt)) + return false; + + if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_decrypt) && + !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_decrypt)) + return false; + + return true; +} + +#define NIC_RDMA_BOTH_DIRS_CAPS (MLX5_FT_NIC_RX_2_NIC_RX_RDMA | MLX5_FT_NIC_TX_RDMA_2_NIC_TX) + +static inline bool mlx5_is_macsec_roce_supported(struct mlx5_core_dev *mdev) +{ + if (((MLX5_CAP_GEN_2(mdev, flow_table_type_2_type) & + NIC_RDMA_BOTH_DIRS_CAPS) != NIC_RDMA_BOTH_DIRS_CAPS) || + !MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, max_modify_header_actions) || + !mlx5e_is_macsec_device(mdev)) + return false; + + return true; +} + enum { MLX5_OCTWORD = 16, }; -- cgit v1.2.3 From afcb21d5a89b40c3062aa48d39ab5340abf7dcd8 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 11 Aug 2022 05:20:02 +0300 Subject: net/mlx5: Add MACsec priorities in RDMA namespaces Add MACsec flow steering priorities in RDMA namespaces. This allows adding tables/rules to forward RoCEv2 traffic to the MACsec crypto tables in NIC_TX domain, and accept RoCEv2 traffic from NIC_RX domain. Signed-off-by: Patrisious Haddad Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 35 +++++++++++++++++++++-- include/linux/mlx5/fs.h | 2 ++ 2 files changed, 34 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 4ef04aa28771..cc27908bb113 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -224,6 +224,7 @@ static struct init_tree_node egress_root_fs = { enum { RDMA_RX_IPSEC_PRIO, + RDMA_RX_MACSEC_PRIO, RDMA_RX_COUNTERS_PRIO, RDMA_RX_BYPASS_PRIO, RDMA_RX_KERNEL_PRIO, @@ -237,9 +238,13 @@ enum { #define RDMA_RX_KERNEL_MIN_LEVEL (RDMA_RX_BYPASS_MIN_LEVEL + 1) #define RDMA_RX_COUNTERS_MIN_LEVEL (RDMA_RX_KERNEL_MIN_LEVEL + 2) +#define RDMA_RX_MACSEC_NUM_PRIOS 1 +#define RDMA_RX_MACSEC_PRIO_NUM_LEVELS 2 +#define RDMA_RX_MACSEC_MIN_LEVEL (RDMA_RX_COUNTERS_MIN_LEVEL + RDMA_RX_MACSEC_NUM_PRIOS) + static struct init_tree_node rdma_rx_root_fs = { .type = FS_TYPE_NAMESPACE, - .ar_size = 4, + .ar_size = 5, .children = (struct init_tree_node[]) { [RDMA_RX_IPSEC_PRIO] = ADD_PRIO(0, RDMA_RX_IPSEC_MIN_LEVEL, 0, @@ -247,6 +252,12 @@ static struct init_tree_node rdma_rx_root_fs = { ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, ADD_MULTIPLE_PRIO(RDMA_RX_IPSEC_NUM_PRIOS, RDMA_RX_IPSEC_NUM_LEVELS))), + [RDMA_RX_MACSEC_PRIO] = + ADD_PRIO(0, RDMA_RX_MACSEC_MIN_LEVEL, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(RDMA_RX_MACSEC_NUM_PRIOS, + RDMA_RX_MACSEC_PRIO_NUM_LEVELS))), [RDMA_RX_COUNTERS_PRIO] = ADD_PRIO(0, RDMA_RX_COUNTERS_MIN_LEVEL, 0, FS_CHAINING_CAPS, @@ -270,6 +281,7 @@ static struct init_tree_node rdma_rx_root_fs = { enum { RDMA_TX_COUNTERS_PRIO, RDMA_TX_IPSEC_PRIO, + RDMA_TX_MACSEC_PRIO, RDMA_TX_BYPASS_PRIO, }; @@ -280,9 +292,13 @@ enum { #define RDMA_TX_IPSEC_PRIO_NUM_LEVELS 1 #define RDMA_TX_IPSEC_MIN_LEVEL (RDMA_TX_COUNTERS_MIN_LEVEL + RDMA_TX_IPSEC_NUM_PRIOS) +#define RDMA_TX_MACSEC_NUM_PRIOS 1 +#define RDMA_TX_MACESC_PRIO_NUM_LEVELS 1 +#define RDMA_TX_MACSEC_MIN_LEVEL (RDMA_TX_COUNTERS_MIN_LEVEL + RDMA_TX_MACSEC_NUM_PRIOS) + static struct init_tree_node rdma_tx_root_fs = { .type = FS_TYPE_NAMESPACE, - .ar_size = 3, + .ar_size = 4, .children = (struct init_tree_node[]) { [RDMA_TX_COUNTERS_PRIO] = ADD_PRIO(0, RDMA_TX_COUNTERS_MIN_LEVEL, 0, @@ -296,7 +312,12 @@ static struct init_tree_node rdma_tx_root_fs = { ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, ADD_MULTIPLE_PRIO(RDMA_TX_IPSEC_NUM_PRIOS, RDMA_TX_IPSEC_PRIO_NUM_LEVELS))), - + [RDMA_TX_MACSEC_PRIO] = + ADD_PRIO(0, RDMA_TX_MACSEC_MIN_LEVEL, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(RDMA_TX_MACSEC_NUM_PRIOS, + RDMA_TX_MACESC_PRIO_NUM_LEVELS))), [RDMA_TX_BYPASS_PRIO] = ADD_PRIO(0, RDMA_TX_BYPASS_MIN_LEVEL, 0, FS_CHAINING_CAPS_RDMA_TX, @@ -2403,6 +2424,14 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, root_ns = steering->rdma_tx_root_ns; prio = RDMA_TX_IPSEC_PRIO; break; + case MLX5_FLOW_NAMESPACE_RDMA_RX_MACSEC: + root_ns = steering->rdma_rx_root_ns; + prio = RDMA_RX_MACSEC_PRIO; + break; + case MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC: + root_ns = steering->rdma_tx_root_ns; + prio = RDMA_TX_MACSEC_PRIO; + break; default: /* Must be NIC RX */ WARN_ON(!is_nic_rx_ns(type)); root_ns = steering->root_ns; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 2cb404c7ea13..091ff1240959 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -105,6 +105,8 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS, MLX5_FLOW_NAMESPACE_RDMA_RX_IPSEC, MLX5_FLOW_NAMESPACE_RDMA_TX_IPSEC, + MLX5_FLOW_NAMESPACE_RDMA_RX_MACSEC, + MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC, }; enum { -- cgit v1.2.3 From ac7ea1c78f0edb910af1c17a3fb01345944bcb39 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 13 Apr 2023 12:04:42 +0300 Subject: net/mlx5: Add RoCE MACsec steering infrastructure in core Adds all the core steering helper functions that are needed in order to setup RoCE steering rules which includes both the RX and TX rules addition and deletion. As well as exporting the function to be ready to use from the IB driver where we expose functions to allow deletion of all rules, which is needed when a GID is deleted, or a deletion of a specific rule when an SA is deleted, and a similar manner for the rules addition. These functions are used in a later patch by IB driver to trigger the rules addition/deletion when needed. Signed-off-by: Patrisious Haddad Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 1 + .../ethernet/mellanox/mlx5/core/lib/macsec_fs.c | 399 ++++++++++++++++++++- include/linux/mlx5/device.h | 2 + include/linux/mlx5/driver.h | 2 + include/linux/mlx5/macsec.h | 32 ++ 5 files changed, 427 insertions(+), 9 deletions(-) create mode 100644 include/linux/mlx5/macsec.h (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 91dcb0dcad10..4e651c2f65c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -967,6 +967,7 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns, max_actions = MLX5_CAP_ESW_INGRESS_ACL(dev, max_modify_header_actions); table_type = FS_FT_ESW_INGRESS_ACL; break; + case MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC: case MLX5_FLOW_NAMESPACE_RDMA_TX: max_actions = MLX5_CAP_FLOWTABLE_RDMA_TX(dev, max_modify_header_actions); table_type = FS_FT_RDMA_TX; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c index 552ab425ae39..2f2cb67717cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/macsec_fs.c @@ -4,6 +4,8 @@ #include #include #include +#include +#include #include "fs_core.h" #include "lib/macsec_fs.h" #include "mlx5_core.h" @@ -46,6 +48,10 @@ /* MACsec RX flow steering */ #define MLX5_ETH_WQE_FT_META_MACSEC_MASK 0x3E +/* MACsec fs_id handling for steering */ +#define macsec_fs_set_tx_fs_id(fs_id) (MLX5_ETH_WQE_FT_META_MACSEC | (fs_id) << 2) +#define macsec_fs_set_rx_fs_id(fs_id) ((fs_id) | BIT(30)) + struct mlx5_sectag_header { __be16 ethertype; u8 tci_an; @@ -54,6 +60,14 @@ struct mlx5_sectag_header { u8 sci[MACSEC_SCI_LEN]; /* optional */ } __packed; +struct mlx5_roce_macsec_tx_rule { + u32 fs_id; + u16 gid_idx; + struct list_head entry; + struct mlx5_flow_handle *rule; + struct mlx5_modify_hdr *meta_modhdr; +}; + struct mlx5_macsec_tx_rule { struct mlx5_flow_handle *rule; struct mlx5_pkt_reformat *pkt_reformat; @@ -104,6 +118,14 @@ struct mlx5_macsec_tx { struct mlx5_flow_table *ft_rdma_tx; }; +struct mlx5_roce_macsec_rx_rule { + u32 fs_id; + u16 gid_idx; + struct mlx5_flow_handle *op; + struct mlx5_flow_handle *ip; + struct list_head entry; +}; + struct mlx5_macsec_rx_rule { struct mlx5_flow_handle *rule[RX_NUM_OF_RULES_PER_SA]; struct mlx5_modify_hdr *meta_modhdr; @@ -574,7 +596,7 @@ static int macsec_fs_tx_setup_fte(struct mlx5_macsec_fs *macsec_fs, MLX5_SET(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_a, MLX5_ETH_WQE_FT_META_MACSEC_MASK); MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_a, - MLX5_ETH_WQE_FT_META_MACSEC | id << 2); + macsec_fs_set_tx_fs_id(id)); *fs_id = id; flow_act->crypto.type = MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_MACSEC; @@ -776,7 +798,7 @@ static void macsec_fs_tx_del_rule(struct mlx5_macsec_fs *macsec_fs, static union mlx5_macsec_rule * macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs, const struct macsec_context *macsec_ctx, - struct mlx5_macsec_rule_attrs *attrs) + struct mlx5_macsec_rule_attrs *attrs, u32 *fs_id) { char reformatbf[MLX5_MACSEC_TAG_LEN + MACSEC_SCI_LEN]; struct mlx5_pkt_reformat_params reformat_params = {}; @@ -791,7 +813,6 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs, struct mlx5_flow_spec *spec; size_t reformat_size; int err = 0; - u32 fs_id; tx_tables = &tx_fs->tables; @@ -831,7 +852,7 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs, } tx_rule->pkt_reformat = flow_act.pkt_reformat; - err = macsec_fs_tx_setup_fte(macsec_fs, spec, &flow_act, attrs->macsec_obj_id, &fs_id); + err = macsec_fs_tx_setup_fte(macsec_fs, spec, &flow_act, attrs->macsec_obj_id, fs_id); if (err) { mlx5_core_err(mdev, "Failed to add packet reformat for MACsec TX crypto rule, err=%d\n", @@ -839,7 +860,7 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs, goto err; } - tx_rule->fs_id = fs_id; + tx_rule->fs_id = *fs_id; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT | @@ -854,7 +875,7 @@ macsec_fs_tx_add_rule(struct mlx5_macsec_fs *macsec_fs, } tx_rule->rule = rule; - err = macsec_fs_id_add(&macsec_fs->macsec_devices_list, fs_id, macsec_ctx->secy->netdev, + err = macsec_fs_id_add(&macsec_fs->macsec_devices_list, *fs_id, macsec_ctx->secy->netdev, &macsec_fs->sci_hash, attrs->sci, true); if (err) { mlx5_core_err(mdev, "Failed to save fs_id, err=%d\n", err); @@ -1743,7 +1764,7 @@ macsec_fs_rx_add_rule(struct mlx5_macsec_fs *macsec_fs, /* Set bit[15-0] fs id */ MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(set_action_in, action, data, MLX5_MACSEC_RX_METADAT_HANDLE(fs_id) | BIT(30)); + MLX5_SET(set_action_in, action, data, macsec_fs_set_rx_fs_id(fs_id)); MLX5_SET(set_action_in, action, offset, 0); MLX5_SET(set_action_in, action, length, 32); @@ -1902,6 +1923,114 @@ static void macsec_fs_rx_cleanup(struct mlx5_macsec_fs *macsec_fs) macsec_fs->rx_fs = NULL; } +static void set_ipaddr_spec_v4(struct sockaddr_in *in, struct mlx5_flow_spec *spec, bool is_dst_ip) +{ + MLX5_SET(fte_match_param, spec->match_value, + outer_headers.ip_version, MLX5_FS_IPV4_VERSION); + + if (is_dst_ip) { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4); + memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4), + &in->sin_addr.s_addr, 4); + } else { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4); + memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4), + &in->sin_addr.s_addr, 4); + } +} + +static void set_ipaddr_spec_v6(struct sockaddr_in6 *in6, struct mlx5_flow_spec *spec, + bool is_dst_ip) +{ + MLX5_SET(fte_match_param, spec->match_value, + outer_headers.ip_version, MLX5_FS_IPV6_VERSION); + + if (is_dst_ip) { + memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + 0xff, 16); + memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + &in6->sin6_addr, 16); + } else { + memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), + 0xff, 16); + memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), + &in6->sin6_addr, 16); + } +} + +static void set_ipaddr_spec(const struct sockaddr *addr, + struct mlx5_flow_spec *spec, bool is_dst_ip) +{ + struct sockaddr_in6 *in6; + + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + outer_headers.ip_version); + + if (addr->sa_family == AF_INET) { + struct sockaddr_in *in = (struct sockaddr_in *)addr; + + set_ipaddr_spec_v4(in, spec, is_dst_ip); + return; + } + + in6 = (struct sockaddr_in6 *)addr; + set_ipaddr_spec_v6(in6, spec, is_dst_ip); +} + +static void macsec_fs_del_roce_rule_rx(struct mlx5_roce_macsec_rx_rule *rx_rule) +{ + mlx5_del_flow_rules(rx_rule->op); + mlx5_del_flow_rules(rx_rule->ip); + list_del(&rx_rule->entry); + kfree(rx_rule); +} + +static void macsec_fs_del_roce_rules_rx(struct mlx5_macsec_fs *macsec_fs, u32 fs_id, + struct list_head *rx_rules_list) +{ + struct mlx5_roce_macsec_rx_rule *rx_rule, *next; + + if (!mlx5_is_macsec_roce_supported(macsec_fs->mdev)) + return; + + list_for_each_entry_safe(rx_rule, next, rx_rules_list, entry) { + if (rx_rule->fs_id == fs_id) + macsec_fs_del_roce_rule_rx(rx_rule); + } +} + +static void macsec_fs_del_roce_rule_tx(struct mlx5_core_dev *mdev, + struct mlx5_roce_macsec_tx_rule *tx_rule) +{ + mlx5_del_flow_rules(tx_rule->rule); + mlx5_modify_header_dealloc(mdev, tx_rule->meta_modhdr); + list_del(&tx_rule->entry); + kfree(tx_rule); +} + +static void macsec_fs_del_roce_rules_tx(struct mlx5_macsec_fs *macsec_fs, u32 fs_id, + struct list_head *tx_rules_list) +{ + struct mlx5_roce_macsec_tx_rule *tx_rule, *next; + + if (!mlx5_is_macsec_roce_supported(macsec_fs->mdev)) + return; + + list_for_each_entry_safe(tx_rule, next, tx_rules_list, entry) { + if (tx_rule->fs_id == fs_id) + macsec_fs_del_roce_rule_tx(macsec_fs->mdev, tx_rule); + } +} + void mlx5_macsec_fs_get_stats_fill(struct mlx5_macsec_fs *macsec_fs, void *macsec_stats) { struct mlx5_macsec_stats *stats = (struct mlx5_macsec_stats *)macsec_stats; @@ -1954,20 +2083,270 @@ mlx5_macsec_fs_add_rule(struct mlx5_macsec_fs *macsec_fs, struct mlx5_macsec_rule_attrs *attrs, u32 *sa_fs_id) { - return (attrs->action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) ? - macsec_fs_tx_add_rule(macsec_fs, macsec_ctx, attrs) : + struct mlx5_macsec_event_data data = {.macsec_fs = macsec_fs, + .macdev = macsec_ctx->secy->netdev, + .is_tx = + (attrs->action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) + }; + union mlx5_macsec_rule *macsec_rule; + u32 tx_new_fs_id; + + macsec_rule = (attrs->action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) ? + macsec_fs_tx_add_rule(macsec_fs, macsec_ctx, attrs, &tx_new_fs_id) : macsec_fs_rx_add_rule(macsec_fs, macsec_ctx, attrs, *sa_fs_id); + + data.fs_id = (data.is_tx) ? tx_new_fs_id : *sa_fs_id; + if (macsec_rule) + blocking_notifier_call_chain(&macsec_fs->mdev->macsec_nh, + MLX5_DRIVER_EVENT_MACSEC_SA_ADDED, + &data); + + return macsec_rule; } void mlx5_macsec_fs_del_rule(struct mlx5_macsec_fs *macsec_fs, union mlx5_macsec_rule *macsec_rule, int action, void *macdev, u32 sa_fs_id) { + struct mlx5_macsec_event_data data = {.macsec_fs = macsec_fs, + .macdev = macdev, + .is_tx = (action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) + }; + + data.fs_id = (data.is_tx) ? macsec_rule->tx_rule.fs_id : sa_fs_id; + blocking_notifier_call_chain(&macsec_fs->mdev->macsec_nh, + MLX5_DRIVER_EVENT_MACSEC_SA_DELETED, + &data); + (action == MLX5_ACCEL_MACSEC_ACTION_ENCRYPT) ? macsec_fs_tx_del_rule(macsec_fs, &macsec_rule->tx_rule, macdev) : macsec_fs_rx_del_rule(macsec_fs, &macsec_rule->rx_rule, macdev, sa_fs_id); } +static int mlx5_macsec_fs_add_roce_rule_rx(struct mlx5_macsec_fs *macsec_fs, u32 fs_id, u16 gid_idx, + const struct sockaddr *addr, + struct list_head *rx_rules_list) +{ + struct mlx5_macsec_rx *rx_fs = macsec_fs->rx_fs; + struct mlx5_roce_macsec_rx_rule *rx_rule; + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *new_rule; + struct mlx5_flow_spec *spec; + int err = 0; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + rx_rule = kzalloc(sizeof(*rx_rule), GFP_KERNEL); + if (!rx_rule) { + err = -ENOMEM; + goto out; + } + + set_ipaddr_spec(addr, spec, true); + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + dest.ft = rx_fs->roce.ft_macsec_op_check; + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + new_rule = mlx5_add_flow_rules(rx_fs->roce.ft_ip_check, spec, &flow_act, + &dest, 1); + if (IS_ERR(new_rule)) { + err = PTR_ERR(new_rule); + goto ip_rule_err; + } + rx_rule->ip = new_rule; + + memset(&flow_act, 0, sizeof(flow_act)); + memset(spec, 0, sizeof(*spec)); + + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_5); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_5, + macsec_fs_set_rx_fs_id(fs_id)); + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW; + new_rule = mlx5_add_flow_rules(rx_fs->roce.ft_macsec_op_check, spec, &flow_act, + NULL, 0); + if (IS_ERR(new_rule)) { + err = PTR_ERR(new_rule); + goto op_rule_err; + } + rx_rule->op = new_rule; + rx_rule->gid_idx = gid_idx; + rx_rule->fs_id = fs_id; + list_add_tail(&rx_rule->entry, rx_rules_list); + + goto out; + +op_rule_err: + mlx5_del_flow_rules(rx_rule->ip); + rx_rule->ip = NULL; +ip_rule_err: + kfree(rx_rule); +out: + kvfree(spec); + return err; +} + +static int mlx5_macsec_fs_add_roce_rule_tx(struct mlx5_macsec_fs *macsec_fs, u32 fs_id, u16 gid_idx, + const struct sockaddr *addr, + struct list_head *tx_rules_list) +{ + u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + struct mlx5_macsec_tx *tx_fs = macsec_fs->tx_fs; + struct mlx5_core_dev *mdev = macsec_fs->mdev; + struct mlx5_modify_hdr *modify_hdr = NULL; + struct mlx5_roce_macsec_tx_rule *tx_rule; + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *new_rule; + struct mlx5_flow_spec *spec; + int err = 0; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + tx_rule = kzalloc(sizeof(*tx_rule), GFP_KERNEL); + if (!tx_rule) { + err = -ENOMEM; + goto out; + } + + set_ipaddr_spec(addr, spec, false); + + MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_A); + MLX5_SET(set_action_in, action, data, macsec_fs_set_tx_fs_id(fs_id)); + MLX5_SET(set_action_in, action, offset, 0); + MLX5_SET(set_action_in, action, length, 32); + + modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC, + 1, action); + if (IS_ERR(modify_hdr)) { + err = PTR_ERR(modify_hdr); + mlx5_core_err(mdev, "Fail to alloc ROCE MACsec set modify_header_id err=%d\n", + err); + modify_hdr = NULL; + goto modify_hdr_err; + } + tx_rule->meta_modhdr = modify_hdr; + + flow_act.modify_hdr = modify_hdr; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + + dest.type = MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE; + dest.ft = tx_fs->tables.ft_crypto.t; + new_rule = mlx5_add_flow_rules(tx_fs->ft_rdma_tx, spec, &flow_act, &dest, 1); + if (IS_ERR(new_rule)) { + err = PTR_ERR(new_rule); + mlx5_core_err(mdev, "Failed to add ROCE TX rule, err=%d\n", err); + goto rule_err; + } + tx_rule->rule = new_rule; + tx_rule->gid_idx = gid_idx; + tx_rule->fs_id = fs_id; + list_add_tail(&tx_rule->entry, tx_rules_list); + + goto out; + +rule_err: + mlx5_modify_header_dealloc(mdev, tx_rule->meta_modhdr); +modify_hdr_err: + kfree(tx_rule); +out: + kvfree(spec); + return err; +} + +void mlx5_macsec_del_roce_rule(u16 gid_idx, struct mlx5_macsec_fs *macsec_fs, + struct list_head *tx_rules_list, struct list_head *rx_rules_list) +{ + struct mlx5_roce_macsec_rx_rule *rx_rule, *next_rx; + struct mlx5_roce_macsec_tx_rule *tx_rule, *next_tx; + + list_for_each_entry_safe(tx_rule, next_tx, tx_rules_list, entry) { + if (tx_rule->gid_idx == gid_idx) + macsec_fs_del_roce_rule_tx(macsec_fs->mdev, tx_rule); + } + + list_for_each_entry_safe(rx_rule, next_rx, rx_rules_list, entry) { + if (rx_rule->gid_idx == gid_idx) + macsec_fs_del_roce_rule_rx(rx_rule); + } +} +EXPORT_SYMBOL_GPL(mlx5_macsec_del_roce_rule); + +int mlx5_macsec_add_roce_rule(void *macdev, const struct sockaddr *addr, u16 gid_idx, + struct list_head *tx_rules_list, struct list_head *rx_rules_list, + struct mlx5_macsec_fs *macsec_fs) +{ + struct mlx5_macsec_device *iter, *macsec_device = NULL; + struct mlx5_core_dev *mdev = macsec_fs->mdev; + struct mlx5_fs_id *fs_id_iter; + unsigned long index = 0; + int err; + + list_for_each_entry(iter, &macsec_fs->macsec_devices_list, macsec_devices_list_entry) { + if (iter->macdev == macdev) { + macsec_device = iter; + break; + } + } + + if (!macsec_device) + return 0; + + xa_for_each(&macsec_device->tx_id_xa, index, fs_id_iter) { + err = mlx5_macsec_fs_add_roce_rule_tx(macsec_fs, fs_id_iter->id, gid_idx, addr, + tx_rules_list); + if (err) { + mlx5_core_err(mdev, "MACsec offload: Failed to add roce TX rule\n"); + goto out; + } + } + + index = 0; + xa_for_each(&macsec_device->rx_id_xa, index, fs_id_iter) { + err = mlx5_macsec_fs_add_roce_rule_rx(macsec_fs, fs_id_iter->id, gid_idx, addr, + rx_rules_list); + if (err) { + mlx5_core_err(mdev, "MACsec offload: Failed to add roce TX rule\n"); + goto out; + } + } + + return 0; +out: + mlx5_macsec_del_roce_rule(gid_idx, macsec_fs, tx_rules_list, rx_rules_list); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_macsec_add_roce_rule); + +void mlx5_macsec_add_roce_sa_rules(u32 fs_id, const struct sockaddr *addr, u16 gid_idx, + struct list_head *tx_rules_list, + struct list_head *rx_rules_list, + struct mlx5_macsec_fs *macsec_fs, bool is_tx) +{ + (is_tx) ? + mlx5_macsec_fs_add_roce_rule_tx(macsec_fs, fs_id, gid_idx, addr, + tx_rules_list) : + mlx5_macsec_fs_add_roce_rule_rx(macsec_fs, fs_id, gid_idx, addr, + rx_rules_list); +} +EXPORT_SYMBOL_GPL(mlx5_macsec_add_roce_sa_rules); + +void mlx5_macsec_del_roce_sa_rules(u32 fs_id, struct mlx5_macsec_fs *macsec_fs, + struct list_head *tx_rules_list, + struct list_head *rx_rules_list, bool is_tx) +{ + (is_tx) ? + macsec_fs_del_roce_rules_tx(macsec_fs, fs_id, tx_rules_list) : + macsec_fs_del_roce_rules_rx(macsec_fs, fs_id, rx_rules_list); +} +EXPORT_SYMBOL_GPL(mlx5_macsec_del_roce_sa_rules); + void mlx5_macsec_fs_cleanup(struct mlx5_macsec_fs *macsec_fs) { macsec_fs_rx_cleanup(macsec_fs); @@ -2015,6 +2394,8 @@ mlx5_macsec_fs_init(struct mlx5_core_dev *mdev) goto tx_cleanup; } + BLOCKING_INIT_NOTIFIER_HEAD(&mdev->macsec_nh); + return macsec_fs; tx_cleanup: diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 80cc12a9a531..ca93a5ef9dac 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -364,6 +364,8 @@ enum mlx5_event { enum mlx5_driver_event { MLX5_DRIVER_EVENT_TYPE_TRAP = 0, MLX5_DRIVER_EVENT_UPLINK_NETDEV, + MLX5_DRIVER_EVENT_MACSEC_SA_ADDED, + MLX5_DRIVER_EVENT_MACSEC_SA_DELETED, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 21954e7aeeba..21014bc34516 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -807,6 +807,8 @@ struct mlx5_core_dev { struct mlx5_thermal *thermal; #ifdef CONFIG_MLX5_MACSEC struct mlx5_macsec_fs *macsec_fs; + /* MACsec notifier chain to sync MACsec core and IB database */ + struct blocking_notifier_head macsec_nh; #endif }; diff --git a/include/linux/mlx5/macsec.h b/include/linux/mlx5/macsec.h new file mode 100644 index 000000000000..f7ff4c2a95d0 --- /dev/null +++ b/include/linux/mlx5/macsec.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */ + +#ifndef MLX5_MACSEC_H +#define MLX5_MACSEC_H + +#ifdef CONFIG_MLX5_MACSEC +struct mlx5_macsec_event_data { + struct mlx5_macsec_fs *macsec_fs; + void *macdev; + u32 fs_id; + bool is_tx; +}; + +int mlx5_macsec_add_roce_rule(void *macdev, const struct sockaddr *addr, u16 gid_idx, + struct list_head *tx_rules_list, struct list_head *rx_rules_list, + struct mlx5_macsec_fs *macsec_fs); + +void mlx5_macsec_del_roce_rule(u16 gid_idx, struct mlx5_macsec_fs *macsec_fs, + struct list_head *tx_rules_list, struct list_head *rx_rules_list); + +void mlx5_macsec_add_roce_sa_rules(u32 fs_id, const struct sockaddr *addr, u16 gid_idx, + struct list_head *tx_rules_list, + struct list_head *rx_rules_list, + struct mlx5_macsec_fs *macsec_fs, bool is_tx); + +void mlx5_macsec_del_roce_sa_rules(u32 fs_id, struct mlx5_macsec_fs *macsec_fs, + struct list_head *tx_rules_list, + struct list_head *rx_rules_list, bool is_tx); + +#endif +#endif /* MLX5_MACSEC_H */ -- cgit v1.2.3 From 58dbd6428a6819e55a3c52ec60126b5d00804a38 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 13 Apr 2023 12:04:59 +0300 Subject: RDMA/mlx5: Handles RoCE MACsec steering rules addition and deletion Add RoCE MACsec rules when a gid is added for the MACsec netdevice and handle their cleanup when the gid is removed or the MACsec SA is deleted. Also support alias IP for the MACsec device, as long as we don't have more ips than what the gid table can hold. In addition handle the case where a gid is added but there are still no SAs added for the MACsec device, so the rules are added later on when the SAs are added. Signed-off-by: Patrisious Haddad Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/macsec.c | 235 +++++++++++++++++++++++++++++++++-- drivers/infiniband/hw/mlx5/macsec.h | 8 +- drivers/infiniband/hw/mlx5/main.c | 6 +- drivers/infiniband/hw/mlx5/mlx5_ib.h | 10 ++ include/linux/mlx5/driver.h | 4 +- 5 files changed, 246 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/macsec.c b/drivers/infiniband/hw/mlx5/macsec.c index 349ad13af75d..3c56eb5eddf3 100644 --- a/drivers/infiniband/hw/mlx5/macsec.c +++ b/drivers/infiniband/hw/mlx5/macsec.c @@ -2,13 +2,174 @@ /* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */ #include "macsec.h" +#include struct mlx5_reserved_gids { int macsec_index; const struct ib_gid_attr *physical_gid; }; -int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev) +struct mlx5_roce_gids { + struct list_head roce_gid_list_entry; + u16 gid_idx; + union { + struct sockaddr_in sockaddr_in; + struct sockaddr_in6 sockaddr_in6; + } addr; +}; + +struct mlx5_macsec_device { + struct list_head macsec_devices_list_entry; + void *macdev; + struct list_head macsec_roce_gids; + struct list_head tx_rules_list; + struct list_head rx_rules_list; +}; + +static void cleanup_macsec_device(struct mlx5_macsec_device *macsec_device) +{ + if (!list_empty(&macsec_device->tx_rules_list) || + !list_empty(&macsec_device->rx_rules_list) || + !list_empty(&macsec_device->macsec_roce_gids)) + return; + + list_del(&macsec_device->macsec_devices_list_entry); + kfree(macsec_device); +} + +static struct mlx5_macsec_device *get_macsec_device(void *macdev, + struct list_head *macsec_devices_list) +{ + struct mlx5_macsec_device *iter, *macsec_device = NULL; + + list_for_each_entry(iter, macsec_devices_list, macsec_devices_list_entry) { + if (iter->macdev == macdev) { + macsec_device = iter; + break; + } + } + + if (macsec_device) + return macsec_device; + + macsec_device = kzalloc(sizeof(*macsec_device), GFP_KERNEL); + if (!macsec_device) + return NULL; + + macsec_device->macdev = macdev; + INIT_LIST_HEAD(&macsec_device->tx_rules_list); + INIT_LIST_HEAD(&macsec_device->rx_rules_list); + INIT_LIST_HEAD(&macsec_device->macsec_roce_gids); + list_add(&macsec_device->macsec_devices_list_entry, macsec_devices_list); + + return macsec_device; +} + +static void mlx5_macsec_del_roce_gid(struct mlx5_macsec_device *macsec_device, u16 gid_idx) +{ + struct mlx5_roce_gids *current_gid, *next_gid; + + list_for_each_entry_safe(current_gid, next_gid, &macsec_device->macsec_roce_gids, + roce_gid_list_entry) + if (current_gid->gid_idx == gid_idx) { + list_del(¤t_gid->roce_gid_list_entry); + kfree(current_gid); + } +} + +static void mlx5_macsec_save_roce_gid(struct mlx5_macsec_device *macsec_device, + const struct sockaddr *addr, u16 gid_idx) +{ + struct mlx5_roce_gids *roce_gids; + + roce_gids = kzalloc(sizeof(*roce_gids), GFP_KERNEL); + if (!roce_gids) + return; + + roce_gids->gid_idx = gid_idx; + if (addr->sa_family == AF_INET) + memcpy(&roce_gids->addr.sockaddr_in, addr, sizeof(roce_gids->addr.sockaddr_in)); + else + memcpy(&roce_gids->addr.sockaddr_in6, addr, sizeof(roce_gids->addr.sockaddr_in6)); + + list_add_tail(&roce_gids->roce_gid_list_entry, &macsec_device->macsec_roce_gids); +} + +static void handle_macsec_gids(struct list_head *macsec_devices_list, + struct mlx5_macsec_event_data *data) +{ + struct mlx5_macsec_device *macsec_device; + struct mlx5_roce_gids *gid; + + macsec_device = get_macsec_device(data->macdev, macsec_devices_list); + if (!macsec_device) + return; + + list_for_each_entry(gid, &macsec_device->macsec_roce_gids, roce_gid_list_entry) { + mlx5_macsec_add_roce_sa_rules(data->fs_id, (struct sockaddr *)&gid->addr, + gid->gid_idx, &macsec_device->tx_rules_list, + &macsec_device->rx_rules_list, data->macsec_fs, + data->is_tx); + } +} + +static void del_sa_roce_rule(struct list_head *macsec_devices_list, + struct mlx5_macsec_event_data *data) +{ + struct mlx5_macsec_device *macsec_device; + + macsec_device = get_macsec_device(data->macdev, macsec_devices_list); + WARN_ON(!macsec_device); + + mlx5_macsec_del_roce_sa_rules(data->fs_id, data->macsec_fs, + &macsec_device->tx_rules_list, + &macsec_device->rx_rules_list, data->is_tx); +} + +static int macsec_event(struct notifier_block *nb, unsigned long event, void *data) +{ + struct mlx5_macsec *macsec = container_of(nb, struct mlx5_macsec, blocking_events_nb); + + mutex_lock(&macsec->lock); + switch (event) { + case MLX5_DRIVER_EVENT_MACSEC_SA_ADDED: + handle_macsec_gids(&macsec->macsec_devices_list, data); + break; + case MLX5_DRIVER_EVENT_MACSEC_SA_DELETED: + del_sa_roce_rule(&macsec->macsec_devices_list, data); + break; + default: + mutex_unlock(&macsec->lock); + return NOTIFY_DONE; + } + mutex_unlock(&macsec->lock); + return NOTIFY_OK; +} + +void mlx5r_macsec_event_register(struct mlx5_ib_dev *dev) +{ + if (!mlx5_is_macsec_roce_supported(dev->mdev)) { + mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n"); + return; + } + + dev->macsec.blocking_events_nb.notifier_call = macsec_event; + blocking_notifier_chain_register(&dev->mdev->macsec_nh, + &dev->macsec.blocking_events_nb); +} + +void mlx5r_macsec_event_unregister(struct mlx5_ib_dev *dev) +{ + if (!mlx5_is_macsec_roce_supported(dev->mdev)) { + mlx5_ib_dbg(dev, "RoCE MACsec not supported due to capabilities\n"); + return; + } + + blocking_notifier_chain_unregister(&dev->mdev->macsec_nh, + &dev->macsec.blocking_events_nb); +} + +int mlx5r_macsec_init_gids_and_devlist(struct mlx5_ib_dev *dev) { int i, j, max_gids; @@ -29,6 +190,9 @@ int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev) dev->port[i].reserved_gids[j].macsec_index = -1; } + INIT_LIST_HEAD(&dev->macsec.macsec_devices_list); + mutex_init(&dev->macsec.lock); + return 0; err: while (i >= 0) { @@ -47,15 +211,22 @@ void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev) for (i = 0; i < dev->num_ports; i++) kfree(dev->port[i].reserved_gids); + + mutex_destroy(&dev->macsec.lock); } int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr) { struct mlx5_ib_dev *dev = to_mdev(attr->device); + struct mlx5_macsec_device *macsec_device; const struct ib_gid_attr *physical_gid; struct mlx5_reserved_gids *mgids; struct net_device *ndev; int ret = 0; + union { + struct sockaddr_in sockaddr_in; + struct sockaddr_in6 sockaddr_in6; + } addr; if (attr->gid_type != IB_GID_TYPE_ROCE_UDP_ENCAP) return 0; @@ -76,34 +247,62 @@ int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr) rcu_read_unlock(); return 0; } + dev_hold(ndev); rcu_read_unlock(); + mutex_lock(&dev->macsec.lock); + macsec_device = get_macsec_device(ndev, &dev->macsec.macsec_devices_list); + if (!macsec_device) { + ret = -ENOMEM; + goto dev_err; + } + physical_gid = rdma_find_gid(attr->device, &attr->gid, attr->gid_type, NULL); - if (IS_ERR(physical_gid)) - return 0; + if (!IS_ERR(physical_gid)) { + ret = set_roce_addr(to_mdev(physical_gid->device), + physical_gid->port_num, + physical_gid->index, NULL, + physical_gid); + if (ret) + goto gid_err; - ret = set_roce_addr(to_mdev(physical_gid->device), - physical_gid->port_num, - physical_gid->index, NULL, - physical_gid); - if (ret) - goto gid_err; + mgids = &dev->port[attr->port_num - 1].reserved_gids[physical_gid->index]; + mgids->macsec_index = attr->index; + mgids->physical_gid = physical_gid; + } - mgids = &dev->port[attr->port_num - 1].reserved_gids[physical_gid->index]; - mgids->macsec_index = attr->index; - mgids->physical_gid = physical_gid; + /* Proceed with adding steering rules, regardless if there was gid ambiguity or not.*/ + rdma_gid2ip((struct sockaddr *)&addr, &attr->gid); + ret = mlx5_macsec_add_roce_rule(ndev, (struct sockaddr *)&addr, attr->index, + &macsec_device->tx_rules_list, + &macsec_device->rx_rules_list, dev->mdev->macsec_fs); + if (ret && !IS_ERR(physical_gid)) + goto rule_err; - return 0; + mlx5_macsec_save_roce_gid(macsec_device, (struct sockaddr *)&addr, attr->index); + + dev_put(ndev); + mutex_unlock(&dev->macsec.lock); + return ret; +rule_err: + set_roce_addr(to_mdev(physical_gid->device), physical_gid->port_num, + physical_gid->index, &physical_gid->gid, physical_gid); + mgids->macsec_index = -1; gid_err: rdma_put_gid_attr(physical_gid); + cleanup_macsec_device(macsec_device); +dev_err: + dev_put(ndev); + mutex_unlock(&dev->macsec.lock); return ret; } void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr) { struct mlx5_ib_dev *dev = to_mdev(attr->device); + struct mlx5_macsec_device *macsec_device; struct mlx5_reserved_gids *mgids; struct net_device *ndev; int i, max_gids; @@ -134,8 +333,10 @@ void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr) rcu_read_unlock(); return; } + dev_hold(ndev); rcu_read_unlock(); + mutex_lock(&dev->macsec.lock); max_gids = MLX5_CAP_ROCE(dev->mdev, roce_address_table_size); for (i = 0; i < max_gids; i++) { /* Checking if macsec gid has ambiguous IP */ mgids = &dev->port[attr->port_num - 1].reserved_gids[i]; @@ -152,4 +353,12 @@ void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr) break; } } + macsec_device = get_macsec_device(ndev, &dev->macsec.macsec_devices_list); + mlx5_macsec_del_roce_rule(attr->index, dev->mdev->macsec_fs, + &macsec_device->tx_rules_list, &macsec_device->rx_rules_list); + mlx5_macsec_del_roce_gid(macsec_device, attr->index); + cleanup_macsec_device(macsec_device); + + dev_put(ndev); + mutex_unlock(&dev->macsec.lock); } diff --git a/drivers/infiniband/hw/mlx5/macsec.h b/drivers/infiniband/hw/mlx5/macsec.h index b60f8f046d6f..9b77ba90f0f4 100644 --- a/drivers/infiniband/hw/mlx5/macsec.h +++ b/drivers/infiniband/hw/mlx5/macsec.h @@ -14,12 +14,16 @@ struct mlx5_reserved_gids; int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr); void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr); -int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev); +int mlx5r_macsec_init_gids_and_devlist(struct mlx5_ib_dev *dev); void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev); +void mlx5r_macsec_event_register(struct mlx5_ib_dev *dev); +void mlx5r_macsec_event_unregister(struct mlx5_ib_dev *dev); #else static inline int mlx5r_add_gid_macsec_operations(const struct ib_gid_attr *attr) { return 0; } static inline void mlx5r_del_gid_macsec_operations(const struct ib_gid_attr *attr) {} -static inline int mlx5r_macsec_alloc_gids(struct mlx5_ib_dev *dev) { return 0; } +static inline int mlx5r_macsec_init_gids_and_devlist(struct mlx5_ib_dev *dev) { return 0; } static inline void mlx5r_macsec_dealloc_gids(struct mlx5_ib_dev *dev) {} +static inline void mlx5r_macsec_event_register(struct mlx5_ib_dev *dev) {} +static inline void mlx5r_macsec_event_unregister(struct mlx5_ib_dev *dev) {} #endif #endif /* __MLX5_MACSEC_H__ */ diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index f463cf8b7501..b4cc16a19757 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3684,7 +3684,7 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) if (err) return err; - err = mlx5r_macsec_alloc_gids(dev); + err = mlx5r_macsec_init_gids_and_devlist(dev); if (err) return err; @@ -4125,11 +4125,15 @@ static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev) { dev->mdev_events.notifier_call = mlx5_ib_event; mlx5_notifier_register(dev->mdev, &dev->mdev_events); + + mlx5r_macsec_event_register(dev); + return 0; } static void mlx5_ib_stage_dev_notifier_cleanup(struct mlx5_ib_dev *dev) { + mlx5r_macsec_event_unregister(dev); mlx5_notifier_unregister(dev->mdev, &dev->mdev_events); } diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index a4b940b5035f..16713baf0d06 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1090,6 +1090,12 @@ struct mlx5_special_mkeys { __be32 terminate_scatter_list_mkey; }; +struct mlx5_macsec { + struct mutex lock; /* Protects mlx5_macsec internal contexts */ + struct list_head macsec_devices_list; + struct notifier_block blocking_events_nb; +}; + struct mlx5_ib_dev { struct ib_device ib_dev; struct mlx5_core_dev *mdev; @@ -1149,6 +1155,10 @@ struct mlx5_ib_dev { u16 pkey_table_len; u8 lag_ports; struct mlx5_special_mkeys mkeys; + +#ifdef CONFIG_MLX5_MACSEC + struct mlx5_macsec macsec; +#endif }; static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 21014bc34516..728bcd6d184c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1325,6 +1325,7 @@ static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev) return mlx5_is_roce_on(dev); } +#ifdef CONFIG_MLX5_MACSEC static inline bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev) { if (!(MLX5_CAP_GEN_64(mdev, general_obj_types) & @@ -1363,11 +1364,12 @@ static inline bool mlx5_is_macsec_roce_supported(struct mlx5_core_dev *mdev) if (((MLX5_CAP_GEN_2(mdev, flow_table_type_2_type) & NIC_RDMA_BOTH_DIRS_CAPS) != NIC_RDMA_BOTH_DIRS_CAPS) || !MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, max_modify_header_actions) || - !mlx5e_is_macsec_device(mdev)) + !mlx5e_is_macsec_device(mdev) || !mdev->macsec_fs) return false; return true; } +#endif enum { MLX5_OCTWORD = 16, -- cgit v1.2.3 From 0f158b32a9b146c9b86783efccfd9ed02c744623 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 18 Aug 2023 17:41:45 +0000 Subject: net: selectively purge error queue in IP_RECVERR / IPV6_RECVERR Setting IP_RECVERR and IPV6_RECVERR options to zero currently purges the socket error queue, which was probably not expected for zerocopy and tx_timestamp users. I discovered this issue while preparing commit 6b5f43ea0815 ("inet: move inet->recverr to inet->inet_flags"), I presume this change does not need to be backported to stable kernels. Add skb_errqueue_purge() helper to purge error messages only. Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Cc: Soheil Hassas Yeganeh Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + net/core/skbuff.c | 21 +++++++++++++++++++++ net/ipv4/ip_sockglue.c | 2 +- net/ipv6/ipv6_sockglue.c | 2 +- 4 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9aec136bc690..4174c4b82d13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3180,6 +3180,7 @@ static inline void skb_queue_purge(struct sk_buff_head *list) } unsigned int skb_rbtree_purge(struct rb_root *root); +void skb_errqueue_purge(struct sk_buff_head *list); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 117d36b1fae3..faa6c86da2a5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3745,6 +3745,27 @@ unsigned int skb_rbtree_purge(struct rb_root *root) return sum; } +void skb_errqueue_purge(struct sk_buff_head *list) +{ + struct sk_buff *skb, *next; + struct sk_buff_head kill; + unsigned long flags; + + __skb_queue_head_init(&kill); + + spin_lock_irqsave(&list->lock, flags); + skb_queue_walk_safe(list, skb, next) { + if (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY || + SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) + continue; + __skb_unlink(skb, list); + __skb_queue_tail(&kill, skb); + } + spin_unlock_irqrestore(&list->lock, flags); + __skb_queue_purge(&kill); +} +EXPORT_SYMBOL(skb_errqueue_purge); + /** * skb_queue_head - queue a buffer at the list head * @list: list to use diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 61b2e7bc7031..54ad0f0d5c2d 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -976,7 +976,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, case IP_RECVERR: inet_assign_bit(RECVERR, sk, val); if (!val) - skb_queue_purge(&sk->sk_error_queue); + skb_errqueue_purge(&sk->sk_error_queue); return 0; case IP_RECVERR_RFC4884: if (val < 0 || val > 1) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index d19577a94bcc..0e2a0847b387 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -923,7 +923,7 @@ done: goto e_inval; np->recverr = valbool; if (!val) - skb_queue_purge(&sk->sk_error_queue); + skb_errqueue_purge(&sk->sk_error_queue); retv = 0; break; case IPV6_FLOWINFO_SEND: -- cgit v1.2.3 From c5487f8d91868eeab17a59cf4d164ea113f90252 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 9 Aug 2023 10:34:13 +0200 Subject: bpf: Switch BPF_F_KPROBE_MULTI_RETURN macro to enum Switching BPF_F_KPROBE_MULTI_RETURN macro to anonymous enum, so it'd show up in vmlinux.h. There's not functional change compared to having this as macro. Acked-by: Yafang Shao Suggested-by: Andrii Nakryiko Signed-off-by: Jiri Olsa Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230809083440.3209381-2-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 4 +++- tools/include/uapi/linux/bpf.h | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d21deb46f49f..a4e55e5e84a7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1186,7 +1186,9 @@ enum bpf_perf_event_type { /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. */ -#define BPF_F_KPROBE_MULTI_RETURN (1U << 0) +enum { + BPF_F_KPROBE_MULTI_RETURN = (1U << 0) +}; /* link_create.netfilter.flags used in LINK_CREATE command for * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation. diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d21deb46f49f..a4e55e5e84a7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1186,7 +1186,9 @@ enum bpf_perf_event_type { /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. */ -#define BPF_F_KPROBE_MULTI_RETURN (1U << 0) +enum { + BPF_F_KPROBE_MULTI_RETURN = (1U << 0) +}; /* link_create.netfilter.flags used in LINK_CREATE command for * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation. -- cgit v1.2.3 From 89ae89f53d201143560f1e9ed4bfa62eee34f88e Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 9 Aug 2023 10:34:15 +0200 Subject: bpf: Add multi uprobe link Adding new multi uprobe link that allows to attach bpf program to multiple uprobes. Uprobes to attach are specified via new link_create uprobe_multi union: struct { __aligned_u64 path; __aligned_u64 offsets; __aligned_u64 ref_ctr_offsets; __u32 cnt; __u32 flags; } uprobe_multi; Uprobes are defined for single binary specified in path and multiple calling sites specified in offsets array with optional reference counters specified in ref_ctr_offsets array. All specified arrays have length of 'cnt'. The 'flags' supports single bit for now that marks the uprobe as return probe. Acked-by: Andrii Nakryiko Acked-by: Yafang Shao Signed-off-by: Jiri Olsa Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230809083440.3209381-4-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/trace_events.h | 6 ++ include/uapi/linux/bpf.h | 16 +++ kernel/bpf/syscall.c | 14 ++- kernel/trace/bpf_trace.c | 233 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 16 +++ 5 files changed, 282 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index e66d04dbe56a..5b85cf18c350 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -752,6 +752,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr); int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { @@ -798,6 +799,11 @@ bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } +static inline int +bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif enum { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a4e55e5e84a7..e48780951fc7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1039,6 +1039,7 @@ enum bpf_attach_type { BPF_NETFILTER, BPF_TCX_INGRESS, BPF_TCX_EGRESS, + BPF_TRACE_UPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -1057,6 +1058,7 @@ enum bpf_link_type { BPF_LINK_TYPE_STRUCT_OPS = 9, BPF_LINK_TYPE_NETFILTER = 10, BPF_LINK_TYPE_TCX = 11, + BPF_LINK_TYPE_UPROBE_MULTI = 12, MAX_BPF_LINK_TYPE, }; @@ -1190,6 +1192,13 @@ enum { BPF_F_KPROBE_MULTI_RETURN = (1U << 0) }; +/* link_create.uprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_UPROBE_MULTI attach type to create return probe. + */ +enum { + BPF_F_UPROBE_MULTI_RETURN = (1U << 0) +}; + /* link_create.netfilter.flags used in LINK_CREATE command for * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation. */ @@ -1626,6 +1635,13 @@ union bpf_attr { }; __u64 expected_revision; } tcx; + struct { + __aligned_u64 path; + __aligned_u64 offsets; + __aligned_u64 ref_ctr_offsets; + __u32 cnt; + __u32 flags; + } uprobe_multi; }; } link_create; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b14036cccd08..fe291b000814 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2815,10 +2815,12 @@ static void bpf_link_free_id(int id) /* Clean up bpf_link and corresponding anon_inode file and FD. After * anon_inode is created, bpf_link can't be just kfree()'d due to deferred - * anon_inode's release() call. This helper marksbpf_link as + * anon_inode's release() call. This helper marks bpf_link as * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt * is not decremented, it's the responsibility of a calling code that failed * to complete bpf_link initialization. + * This helper eventually calls link's dealloc callback, but does not call + * link's release callback. */ void bpf_link_cleanup(struct bpf_link_primer *primer) { @@ -3756,8 +3758,12 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_MULTI) return -EINVAL; + if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI && + attach_type != BPF_TRACE_UPROBE_MULTI) + return -EINVAL; if (attach_type != BPF_PERF_EVENT && - attach_type != BPF_TRACE_KPROBE_MULTI) + attach_type != BPF_TRACE_KPROBE_MULTI && + attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; return 0; case BPF_PROG_TYPE_SCHED_CLS: @@ -4953,8 +4959,10 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) case BPF_PROG_TYPE_KPROBE: if (attr->link_create.attach_type == BPF_PERF_EVENT) ret = bpf_perf_link_attach(attr, prog); - else + else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI) ret = bpf_kprobe_multi_link_attach(attr, prog); + else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI) + ret = bpf_uprobe_multi_link_attach(attr, prog); break; default: ret = -EINVAL; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 792445e1f3f0..f0b54a3480f8 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -2970,3 +2971,235 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) return 0; } #endif + +#ifdef CONFIG_UPROBES +struct bpf_uprobe_multi_link; + +struct bpf_uprobe { + struct bpf_uprobe_multi_link *link; + loff_t offset; + struct uprobe_consumer consumer; +}; + +struct bpf_uprobe_multi_link { + struct path path; + struct bpf_link link; + u32 cnt; + struct bpf_uprobe *uprobes; +}; + +struct bpf_uprobe_multi_run_ctx { + struct bpf_run_ctx run_ctx; + unsigned long entry_ip; +}; + +static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes, + u32 cnt) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + uprobe_unregister(d_real_inode(path->dentry), uprobes[i].offset, + &uprobes[i].consumer); + } +} + +static void bpf_uprobe_multi_link_release(struct bpf_link *link) +{ + struct bpf_uprobe_multi_link *umulti_link; + + umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); + bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt); +} + +static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link) +{ + struct bpf_uprobe_multi_link *umulti_link; + + umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); + path_put(&umulti_link->path); + kvfree(umulti_link->uprobes); + kfree(umulti_link); +} + +static const struct bpf_link_ops bpf_uprobe_multi_link_lops = { + .release = bpf_uprobe_multi_link_release, + .dealloc = bpf_uprobe_multi_link_dealloc, +}; + +static int uprobe_prog_run(struct bpf_uprobe *uprobe, + unsigned long entry_ip, + struct pt_regs *regs) +{ + struct bpf_uprobe_multi_link *link = uprobe->link; + struct bpf_uprobe_multi_run_ctx run_ctx = { + .entry_ip = entry_ip, + }; + struct bpf_prog *prog = link->link.prog; + bool sleepable = prog->aux->sleepable; + struct bpf_run_ctx *old_run_ctx; + int err = 0; + + if (sleepable) + rcu_read_lock_trace(); + else + rcu_read_lock(); + + migrate_disable(); + + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + err = bpf_prog_run(link->link.prog, regs); + bpf_reset_run_ctx(old_run_ctx); + + migrate_enable(); + + if (sleepable) + rcu_read_unlock_trace(); + else + rcu_read_unlock(); + return err; +} + +static int +uprobe_multi_link_handler(struct uprobe_consumer *con, struct pt_regs *regs) +{ + struct bpf_uprobe *uprobe; + + uprobe = container_of(con, struct bpf_uprobe, consumer); + return uprobe_prog_run(uprobe, instruction_pointer(regs), regs); +} + +static int +uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs) +{ + struct bpf_uprobe *uprobe; + + uprobe = container_of(con, struct bpf_uprobe, consumer); + return uprobe_prog_run(uprobe, func, regs); +} + +int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_uprobe_multi_link *link = NULL; + unsigned long __user *uref_ctr_offsets; + unsigned long *ref_ctr_offsets = NULL; + struct bpf_link_primer link_primer; + struct bpf_uprobe *uprobes = NULL; + unsigned long __user *uoffsets; + void __user *upath; + u32 flags, cnt, i; + struct path path; + char *name; + int err; + + /* no support for 32bit archs yet */ + if (sizeof(u64) != sizeof(void *)) + return -EOPNOTSUPP; + + if (prog->expected_attach_type != BPF_TRACE_UPROBE_MULTI) + return -EINVAL; + + flags = attr->link_create.uprobe_multi.flags; + if (flags & ~BPF_F_UPROBE_MULTI_RETURN) + return -EINVAL; + + /* + * path, offsets and cnt are mandatory, + * ref_ctr_offsets is optional + */ + upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); + uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); + cnt = attr->link_create.uprobe_multi.cnt; + + if (!upath || !uoffsets || !cnt) + return -EINVAL; + + uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets); + + name = strndup_user(upath, PATH_MAX); + if (IS_ERR(name)) { + err = PTR_ERR(name); + return err; + } + + err = kern_path(name, LOOKUP_FOLLOW, &path); + kfree(name); + if (err) + return err; + + if (!d_is_reg(path.dentry)) { + err = -EBADF; + goto error_path_put; + } + + err = -ENOMEM; + + link = kzalloc(sizeof(*link), GFP_KERNEL); + uprobes = kvcalloc(cnt, sizeof(*uprobes), GFP_KERNEL); + + if (!uprobes || !link) + goto error_free; + + if (uref_ctr_offsets) { + ref_ctr_offsets = kvcalloc(cnt, sizeof(*ref_ctr_offsets), GFP_KERNEL); + if (!ref_ctr_offsets) + goto error_free; + } + + for (i = 0; i < cnt; i++) { + if (uref_ctr_offsets && __get_user(ref_ctr_offsets[i], uref_ctr_offsets + i)) { + err = -EFAULT; + goto error_free; + } + if (__get_user(uprobes[i].offset, uoffsets + i)) { + err = -EFAULT; + goto error_free; + } + + uprobes[i].link = link; + + if (flags & BPF_F_UPROBE_MULTI_RETURN) + uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler; + else + uprobes[i].consumer.handler = uprobe_multi_link_handler; + } + + link->cnt = cnt; + link->uprobes = uprobes; + link->path = path; + + bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI, + &bpf_uprobe_multi_link_lops, prog); + + for (i = 0; i < cnt; i++) { + err = uprobe_register_refctr(d_real_inode(link->path.dentry), + uprobes[i].offset, + ref_ctr_offsets ? ref_ctr_offsets[i] : 0, + &uprobes[i].consumer); + if (err) { + bpf_uprobe_unregister(&path, uprobes, i); + goto error_free; + } + } + + err = bpf_link_prime(&link->link, &link_primer); + if (err) + goto error_free; + + kvfree(ref_ctr_offsets); + return bpf_link_settle(&link_primer); + +error_free: + kvfree(ref_ctr_offsets); + kvfree(uprobes); + kfree(link); +error_path_put: + path_put(&path); + return err; +} +#else /* !CONFIG_UPROBES */ +int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_UPROBES */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a4e55e5e84a7..e48780951fc7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1039,6 +1039,7 @@ enum bpf_attach_type { BPF_NETFILTER, BPF_TCX_INGRESS, BPF_TCX_EGRESS, + BPF_TRACE_UPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -1057,6 +1058,7 @@ enum bpf_link_type { BPF_LINK_TYPE_STRUCT_OPS = 9, BPF_LINK_TYPE_NETFILTER = 10, BPF_LINK_TYPE_TCX = 11, + BPF_LINK_TYPE_UPROBE_MULTI = 12, MAX_BPF_LINK_TYPE, }; @@ -1190,6 +1192,13 @@ enum { BPF_F_KPROBE_MULTI_RETURN = (1U << 0) }; +/* link_create.uprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_UPROBE_MULTI attach type to create return probe. + */ +enum { + BPF_F_UPROBE_MULTI_RETURN = (1U << 0) +}; + /* link_create.netfilter.flags used in LINK_CREATE command for * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation. */ @@ -1626,6 +1635,13 @@ union bpf_attr { }; __u64 expected_revision; } tcx; + struct { + __aligned_u64 path; + __aligned_u64 offsets; + __aligned_u64 ref_ctr_offsets; + __u32 cnt; + __u32 flags; + } uprobe_multi; }; } link_create; -- cgit v1.2.3 From 0b779b61f651851df5c5c42938a6c441eb1b5100 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 9 Aug 2023 10:34:16 +0200 Subject: bpf: Add cookies support for uprobe_multi link Adding support to specify cookies array for uprobe_multi link. The cookies array share indexes and length with other uprobe_multi arrays (offsets/ref_ctr_offsets). The cookies[i] value defines cookie for i-the uprobe and will be returned by bpf_get_attach_cookie helper when called from ebpf program hooked to that specific uprobe. Acked-by: Andrii Nakryiko Acked-by: Yafang Shao Signed-off-by: Jiri Olsa Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230809083440.3209381-5-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 2 +- kernel/trace/bpf_trace.c | 45 ++++++++++++++++++++++++++++++++++++++---- tools/include/uapi/linux/bpf.h | 1 + 4 files changed, 44 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e48780951fc7..d7f4f50b1e58 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1639,6 +1639,7 @@ union bpf_attr { __aligned_u64 path; __aligned_u64 offsets; __aligned_u64 ref_ctr_offsets; + __aligned_u64 cookies; __u32 cnt; __u32 flags; } uprobe_multi; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index fe291b000814..ef17cd05262e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4882,7 +4882,7 @@ err_put: return err; } -#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies +#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.flags static int link_create(union bpf_attr *attr, bpfptr_t uattr) { struct bpf_prog *prog; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f0b54a3480f8..0d59cac30c7e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -87,6 +87,8 @@ static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx); static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx); +static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx); + /** * trace_call_bpf - invoke BPF program * @call: tracepoint event @@ -1104,6 +1106,18 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_1(bpf_get_attach_cookie_uprobe_multi, struct pt_regs *, regs) +{ + return bpf_uprobe_multi_cookie(current->bpf_ctx); +} + +static const struct bpf_func_proto bpf_get_attach_cookie_proto_umulti = { + .func = bpf_get_attach_cookie_uprobe_multi, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx) { struct bpf_trace_run_ctx *run_ctx; @@ -1550,9 +1564,11 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) &bpf_get_func_ip_proto_kprobe_multi : &bpf_get_func_ip_proto_kprobe; case BPF_FUNC_get_attach_cookie: - return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ? - &bpf_get_attach_cookie_proto_kmulti : - &bpf_get_attach_cookie_proto_trace; + if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI) + return &bpf_get_attach_cookie_proto_kmulti; + if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI) + return &bpf_get_attach_cookie_proto_umulti; + return &bpf_get_attach_cookie_proto_trace; default: return bpf_tracing_func_proto(func_id, prog); } @@ -2978,6 +2994,7 @@ struct bpf_uprobe_multi_link; struct bpf_uprobe { struct bpf_uprobe_multi_link *link; loff_t offset; + u64 cookie; struct uprobe_consumer consumer; }; @@ -2991,6 +3008,7 @@ struct bpf_uprobe_multi_link { struct bpf_uprobe_multi_run_ctx { struct bpf_run_ctx run_ctx; unsigned long entry_ip; + struct bpf_uprobe *uprobe; }; static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes, @@ -3034,6 +3052,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, struct bpf_uprobe_multi_link *link = uprobe->link; struct bpf_uprobe_multi_run_ctx run_ctx = { .entry_ip = entry_ip, + .uprobe = uprobe, }; struct bpf_prog *prog = link->link.prog; bool sleepable = prog->aux->sleepable; @@ -3078,6 +3097,14 @@ uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, s return uprobe_prog_run(uprobe, func, regs); } +static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx) +{ + struct bpf_uprobe_multi_run_ctx *run_ctx; + + run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, run_ctx); + return run_ctx->uprobe->cookie; +} + int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_uprobe_multi_link *link = NULL; @@ -3086,6 +3113,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr struct bpf_link_primer link_primer; struct bpf_uprobe *uprobes = NULL; unsigned long __user *uoffsets; + u64 __user *ucookies; void __user *upath; u32 flags, cnt, i; struct path path; @@ -3105,7 +3133,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr /* * path, offsets and cnt are mandatory, - * ref_ctr_offsets is optional + * ref_ctr_offsets and cookies are optional */ upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); @@ -3115,6 +3143,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr return -EINVAL; uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets); + ucookies = u64_to_user_ptr(attr->link_create.uprobe_multi.cookies); name = strndup_user(upath, PATH_MAX); if (IS_ERR(name)) { @@ -3147,6 +3176,10 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr } for (i = 0; i < cnt; i++) { + if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) { + err = -EFAULT; + goto error_free; + } if (uref_ctr_offsets && __get_user(ref_ctr_offsets[i], uref_ctr_offsets + i)) { err = -EFAULT; goto error_free; @@ -3202,4 +3235,8 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr { return -EOPNOTSUPP; } +static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx) +{ + return 0; +} #endif /* CONFIG_UPROBES */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e48780951fc7..d7f4f50b1e58 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1639,6 +1639,7 @@ union bpf_attr { __aligned_u64 path; __aligned_u64 offsets; __aligned_u64 ref_ctr_offsets; + __aligned_u64 cookies; __u32 cnt; __u32 flags; } uprobe_multi; -- cgit v1.2.3 From b733eeade4204423711793595c3c8d78a2fa8b2e Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 9 Aug 2023 10:34:17 +0200 Subject: bpf: Add pid filter support for uprobe_multi link Adding support to specify pid for uprobe_multi link and the uprobes are created only for task with given pid value. Using the consumer.filter filter callback for that, so the task gets filtered during the uprobe installation. We still need to check the task during runtime in the uprobe handler, because the handler could get executed if there's another system wide consumer on the same uprobe (thanks Oleg for the insight). Cc: Oleg Nesterov Reviewed-by: Oleg Nesterov Signed-off-by: Jiri Olsa Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230809083440.3209381-6-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 2 +- kernel/trace/bpf_trace.c | 33 +++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 1 + 4 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d7f4f50b1e58..8790b3962e4b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1642,6 +1642,7 @@ union bpf_attr { __aligned_u64 cookies; __u32 cnt; __u32 flags; + __u32 pid; } uprobe_multi; }; } link_create; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ef17cd05262e..10666d17b9e3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4882,7 +4882,7 @@ err_put: return err; } -#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.flags +#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid static int link_create(union bpf_attr *attr, bpfptr_t uattr) { struct bpf_prog *prog; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0d59cac30c7e..e45aebed62f5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3003,6 +3003,7 @@ struct bpf_uprobe_multi_link { struct bpf_link link; u32 cnt; struct bpf_uprobe *uprobes; + struct task_struct *task; }; struct bpf_uprobe_multi_run_ctx { @@ -3035,6 +3036,8 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link) struct bpf_uprobe_multi_link *umulti_link; umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); + if (umulti_link->task) + put_task_struct(umulti_link->task); path_put(&umulti_link->path); kvfree(umulti_link->uprobes); kfree(umulti_link); @@ -3059,6 +3062,9 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, struct bpf_run_ctx *old_run_ctx; int err = 0; + if (link->task && current != link->task) + return 0; + if (sleepable) rcu_read_lock_trace(); else @@ -3079,6 +3085,16 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, return err; } +static bool +uprobe_multi_link_filter(struct uprobe_consumer *con, enum uprobe_filter_ctx ctx, + struct mm_struct *mm) +{ + struct bpf_uprobe *uprobe; + + uprobe = container_of(con, struct bpf_uprobe, consumer); + return uprobe->link->task->mm == mm; +} + static int uprobe_multi_link_handler(struct uprobe_consumer *con, struct pt_regs *regs) { @@ -3112,12 +3128,14 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr unsigned long *ref_ctr_offsets = NULL; struct bpf_link_primer link_primer; struct bpf_uprobe *uprobes = NULL; + struct task_struct *task = NULL; unsigned long __user *uoffsets; u64 __user *ucookies; void __user *upath; u32 flags, cnt, i; struct path path; char *name; + pid_t pid; int err; /* no support for 32bit archs yet */ @@ -3161,6 +3179,15 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error_path_put; } + pid = attr->link_create.uprobe_multi.pid; + if (pid) { + rcu_read_lock(); + task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + rcu_read_unlock(); + if (!task) + goto error_path_put; + } + err = -ENOMEM; link = kzalloc(sizeof(*link), GFP_KERNEL); @@ -3195,11 +3222,15 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler; else uprobes[i].consumer.handler = uprobe_multi_link_handler; + + if (pid) + uprobes[i].consumer.filter = uprobe_multi_link_filter; } link->cnt = cnt; link->uprobes = uprobes; link->path = path; + link->task = task; bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI, &bpf_uprobe_multi_link_lops, prog); @@ -3226,6 +3257,8 @@ error_free: kvfree(ref_ctr_offsets); kvfree(uprobes); kfree(link); + if (task) + put_task_struct(task); error_path_put: path_put(&path); return err; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d7f4f50b1e58..8790b3962e4b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1642,6 +1642,7 @@ union bpf_attr { __aligned_u64 cookies; __u32 cnt; __u32 flags; + __u32 pid; } uprobe_multi; }; } link_create; -- cgit v1.2.3 From 93ca82447c3eab149b5b2588ab8bd9aa2eacef7c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Aug 2023 14:15:23 -0700 Subject: wifi: cfg80211: Annotate struct cfg80211_acl_data with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct cfg80211_acl_data. Additionally, since the element count member must be set before accessing the annotated flexible array member, move its initialization earlier. [1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci Cc: Johannes Berg Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Justin Stitt Reviewed-by: Gustavo A. R. Silva Reviewed-by: Jeff Johnson Link: https://lore.kernel.org/r/20230817211531.4193219-1-keescook@chromium.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- net/wireless/nl80211.c | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d6fa7c8767ad..eb73b5af5d04 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1282,7 +1282,7 @@ struct cfg80211_acl_data { int n_acl_entries; /* Keep it last */ - struct mac_address mac_addrs[]; + struct mac_address mac_addrs[] __counted_by(n_acl_entries); }; /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8bcf8e293308..80633e815311 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4889,13 +4889,12 @@ static struct cfg80211_acl_data *parse_acl_data(struct wiphy *wiphy, acl = kzalloc(struct_size(acl, mac_addrs, n_entries), GFP_KERNEL); if (!acl) return ERR_PTR(-ENOMEM); + acl->n_acl_entries = n_entries; nla_for_each_nested(attr, info->attrs[NL80211_ATTR_MAC_ADDRS], tmp) { memcpy(acl->mac_addrs[i].addr, nla_data(attr), ETH_ALEN); i++; } - - acl->n_acl_entries = n_entries; acl->acl_policy = acl_policy; return acl; -- cgit v1.2.3 From c14679d7005a4d26289eadb4f5fe499aca78ef7c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Aug 2023 14:15:25 -0700 Subject: wifi: cfg80211: Annotate struct cfg80211_mbssid_elems with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct cfg80211_mbssid_elems. Additionally, since the element count member must be set before accessing the annotated flexible array member, move its initialization earlier. [1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci Cc: Johannes Berg Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: Jeff Johnson Link: https://lore.kernel.org/r/20230817211531.4193219-3-keescook@chromium.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- net/wireless/nl80211.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index eb73b5af5d04..5c7d091b3925 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1187,7 +1187,7 @@ struct cfg80211_mbssid_elems { struct { const u8 *data; size_t len; - } elem[]; + } elem[] __counted_by(cnt); }; /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 80633e815311..9ba4266368db 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5438,13 +5438,13 @@ nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); if (!elems) return ERR_PTR(-ENOMEM); + elems->cnt = num_elems; nla_for_each_nested(nl_elems, attrs, rem_elems) { elems->elem[i].data = nla_data(nl_elems); elems->elem[i].len = nla_len(nl_elems); i++; } - elems->cnt = num_elems; return elems; } -- cgit v1.2.3 From 342bc7c9e877847d602c4a67c3135051df07cc4d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Aug 2023 14:15:26 -0700 Subject: wifi: cfg80211: Annotate struct cfg80211_pmsr_request with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct cfg80211_pmsr_request. Additionally, since the element count member must be set before accessing the annotated flexible array member, move its initialization earlier. [1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci Cc: Johannes Berg Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: Jeff Johnson Link: https://lore.kernel.org/r/20230817211531.4193219-4-keescook@chromium.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- net/wireless/pmsr.c | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5c7d091b3925..e9ca4726a732 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3948,7 +3948,7 @@ struct cfg80211_pmsr_request { struct list_head list; - struct cfg80211_pmsr_request_peer peers[]; + struct cfg80211_pmsr_request_peer peers[] __counted_by(n_peers); }; /** diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 77000a264855..9611aa0bd051 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -291,6 +291,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) req = kzalloc(struct_size(req, peers, count), GFP_KERNEL); if (!req) return -ENOMEM; + req->n_peers = count; if (info->attrs[NL80211_ATTR_TIMEOUT]) req->timeout = nla_get_u32(info->attrs[NL80211_ATTR_TIMEOUT]); @@ -321,8 +322,6 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) goto out_err; idx++; } - - req->n_peers = count; req->cookie = cfg80211_assign_cookie(rdev); req->nl_portid = info->snd_portid; -- cgit v1.2.3 From 7b6d7087031b69f0694cbef4485616c905664feb Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Aug 2023 14:15:27 -0700 Subject: wifi: cfg80211: Annotate struct cfg80211_rnr_elems with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct cfg80211_rnr_elems. Additionally, since the element count member must be set before accessing the annotated flexible array member, move its initialization earlier. [1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci Cc: Johannes Berg Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: Jeff Johnson Link: https://lore.kernel.org/r/20230817211531.4193219-5-keescook@chromium.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- net/wireless/nl80211.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e9ca4726a732..6efe216c01d2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1204,7 +1204,7 @@ struct cfg80211_rnr_elems { struct { const u8 *data; size_t len; - } elem[]; + } elem[] __counted_by(cnt); }; /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9ba4266368db..0ffebf1a1eb6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5470,13 +5470,13 @@ nl80211_parse_rnr_elems(struct wiphy *wiphy, struct nlattr *attrs, elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); if (!elems) return ERR_PTR(-ENOMEM); + elems->cnt = num_elems; nla_for_each_nested(nl_elems, attrs, rem_elems) { elems->elem[i].data = nla_data(nl_elems); elems->elem[i].len = nla_len(nl_elems); i++; } - elems->cnt = num_elems; return elems; } -- cgit v1.2.3 From e3eac9f32ec04112b39e01b574ac739382469bf9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Aug 2023 14:15:28 -0700 Subject: wifi: cfg80211: Annotate struct cfg80211_scan_request with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct cfg80211_scan_request. Additionally, since the element count member must be set before accessing the annotated flexible array member, move its initialization earlier. [1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci Cc: Johannes Berg Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: Jeff Johnson Link: https://lore.kernel.org/r/20230817211531.4193219-6-keescook@chromium.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6efe216c01d2..a2afc94a5408 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2544,7 +2544,7 @@ struct cfg80211_scan_request { struct cfg80211_scan_6ghz_params *scan_6ghz_params; /* keep last */ - struct ieee80211_channel *channels[]; + struct ieee80211_channel *channels[] __counted_by(n_channels); }; static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask) -- cgit v1.2.3 From 545d3523dff0cf61ccd65da1c352f7c7c21fcfb0 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Aug 2023 14:15:29 -0700 Subject: wifi: cfg80211: Annotate struct cfg80211_tid_config with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct cfg80211_tid_config. [1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci Cc: Johannes Berg Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: Jeff Johnson Link: https://lore.kernel.org/r/20230817211531.4193219-7-keescook@chromium.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a2afc94a5408..423fe9b85cb0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -811,7 +811,7 @@ struct cfg80211_tid_cfg { struct cfg80211_tid_config { const u8 *peer; u32 n_tid_conf; - struct cfg80211_tid_cfg tid_conf[]; + struct cfg80211_tid_cfg tid_conf[] __counted_by(n_tid_conf); }; /** -- cgit v1.2.3 From 43c2817225fce05701f062a996255007481935e2 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Mon, 21 Aug 2023 16:41:04 +0800 Subject: net: remove unnecessary input parameter 'how' in ifdown function When the ifdown function in the dst_ops structure is referenced, the input parameter 'how' is always true. In the current implementation of the ifdown interface, ip6_dst_ifdown does not use the input parameter 'how', xfrm6_dst_ifdown and xfrm4_dst_ifdown functions use the input parameter 'unregister'. But false judgment on 'unregister' in xfrm6_dst_ifdown and xfrm4_dst_ifdown is false, so remove the input parameter 'how' in ifdown function. Signed-off-by: Zhengchao Shao Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230821084104.3812233-1-shaozhengchao@huawei.com Signed-off-by: Paolo Abeni --- include/net/dst_ops.h | 2 +- net/core/dst.c | 2 +- net/ipv4/xfrm4_policy.c | 11 +---------- net/ipv6/route.c | 5 ++--- net/ipv6/xfrm6_policy.c | 6 +----- 5 files changed, 6 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 632086b2f644..6d1c8541183d 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -23,7 +23,7 @@ struct dst_ops { u32 * (*cow_metrics)(struct dst_entry *, unsigned long); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, - struct net_device *dev, int how); + struct net_device *dev); struct dst_entry * (*negative_advice)(struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, diff --git a/net/core/dst.c b/net/core/dst.c index 79d9306ad1ee..980e2fd2f013 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -152,7 +152,7 @@ void dst_dev_put(struct dst_entry *dst) dst->obsolete = DST_OBSOLETE_DEAD; if (dst->ops->ifdown) - dst->ops->ifdown(dst, dev, true); + dst->ops->ifdown(dst, dev); dst->input = dst_discard; dst->output = dst_discard_out; dst->dev = blackhole_netdev; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 9403bbaf1b61..cdcc0f6b4f0a 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -124,22 +124,13 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) xfrm_dst_destroy(xdst); } -static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int unregister) -{ - if (!unregister) - return; - - xfrm_dst_ifdown(dst, dev); -} - static struct dst_ops xfrm4_dst_ops_template = { .family = AF_INET, .update_pmtu = xfrm4_update_pmtu, .redirect = xfrm4_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, - .ifdown = xfrm4_dst_ifdown, + .ifdown = xfrm_dst_ifdown, .local_out = __ip_local_out, .gc_thresh = 32768, }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a5b74b91c8f3..846aec8e0093 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -90,7 +90,7 @@ unsigned int ip6_mtu(const struct dst_entry *dst); static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, - struct net_device *dev, int how); + struct net_device *dev); static void ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); @@ -371,8 +371,7 @@ static void ip6_dst_destroy(struct dst_entry *dst) fib6_info_release(from); } -static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int how) +static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index eecc5e59da17..188224a76685 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -124,14 +124,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) xfrm_dst_destroy(xdst); } -static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int unregister) +static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { struct xfrm_dst *xdst; - if (!unregister) - return; - xdst = (struct xfrm_dst *)dst; if (xdst->u.rt6.rt6i_idev->dev == dev) { struct inet6_dev *loopback_idev = -- cgit v1.2.3 From a7ed3465daa240bdf01a5420f64336fee879c09d Mon Sep 17 00:00:00 2001 From: "GONG, Ruiqi" Date: Wed, 9 Aug 2023 15:45:03 +0800 Subject: netfilter: ebtables: fix fortify warnings in size_entry_mwt() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When compiling with gcc 13 and CONFIG_FORTIFY_SOURCE=y, the following warning appears: In function ‘fortify_memcpy_chk’, inlined from ‘size_entry_mwt’ at net/bridge/netfilter/ebtables.c:2118:2: ./include/linux/fortify-string.h:592:25: error: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror=attribute-warning] 592 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The compiler is complaining: memcpy(&offsets[1], &entry->watchers_offset, sizeof(offsets) - sizeof(offsets[0])); where memcpy reads beyong &entry->watchers_offset to copy {watchers,target,next}_offset altogether into offsets[]. Silence the warning by wrapping these three up via struct_group(). Signed-off-by: GONG, Ruiqi Reviewed-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: Florian Westphal --- include/uapi/linux/netfilter_bridge/ebtables.h | 14 ++++++++------ net/bridge/netfilter/ebtables.c | 3 +-- 2 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter_bridge/ebtables.h b/include/uapi/linux/netfilter_bridge/ebtables.h index a494cf43a755..b0caad82b693 100644 --- a/include/uapi/linux/netfilter_bridge/ebtables.h +++ b/include/uapi/linux/netfilter_bridge/ebtables.h @@ -182,12 +182,14 @@ struct ebt_entry { unsigned char sourcemsk[ETH_ALEN]; unsigned char destmac[ETH_ALEN]; unsigned char destmsk[ETH_ALEN]; - /* sizeof ebt_entry + matches */ - unsigned int watchers_offset; - /* sizeof ebt_entry + matches + watchers */ - unsigned int target_offset; - /* sizeof ebt_entry + matches + watchers + target */ - unsigned int next_offset; + __struct_group(/* no tag */, offsets, /* no attrs */, + /* sizeof ebt_entry + matches */ + unsigned int watchers_offset; + /* sizeof ebt_entry + matches + watchers */ + unsigned int target_offset; + /* sizeof ebt_entry + matches + watchers + target */ + unsigned int next_offset; + ); unsigned char elems[0] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); }; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 757ec46fc45a..aa23479b20b2 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2115,8 +2115,7 @@ static int size_entry_mwt(const struct ebt_entry *entry, const unsigned char *ba return ret; offsets[0] = sizeof(struct ebt_entry); /* matches come first */ - memcpy(&offsets[1], &entry->watchers_offset, - sizeof(offsets) - sizeof(offsets[0])); + memcpy(&offsets[1], &entry->offsets, sizeof(entry->offsets)); if (state->buf_kern_start) { buf_start = state->buf_kern_start + state->buf_kern_offset; -- cgit v1.2.3 From a2f02c9920b2cc3c6cc1f2c2aee37354e6edd801 Mon Sep 17 00:00:00 2001 From: "GONG, Ruiqi" Date: Wed, 9 Aug 2023 15:51:36 +0800 Subject: netfilter: ebtables: replace zero-length array members As suggested by Kees[1], replace the old-style 0-element array members of multiple structs in ebtables.h with modern C99 flexible array. [1]: https://lore.kernel.org/all/5E8E0F9C-EE3F-4B0D-B827-DC47397E2A4A@kernel.org/ [ fw@strlen.de: keep struct ebt_entry_target as-is, causes compiler warning: "variable sized type 'struct ebt_entry_target' not at the end of a struct or class is a GNU extension" ] Link: https://github.com/KSPP/linux/issues/21 Signed-off-by: GONG, Ruiqi Reviewed-by: Kees Cook Signed-off-by: Florian Westphal --- include/uapi/linux/netfilter_bridge/ebtables.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter_bridge/ebtables.h b/include/uapi/linux/netfilter_bridge/ebtables.h index b0caad82b693..4ff328f3d339 100644 --- a/include/uapi/linux/netfilter_bridge/ebtables.h +++ b/include/uapi/linux/netfilter_bridge/ebtables.h @@ -87,7 +87,7 @@ struct ebt_entries { /* nr. of entries */ unsigned int nentries; /* entry list */ - char data[0] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); + char data[] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); }; /* used for the bitmask of struct ebt_entry */ @@ -129,7 +129,7 @@ struct ebt_entry_match { } u; /* size of data */ unsigned int match_size; - unsigned char data[0] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); + unsigned char data[] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); }; struct ebt_entry_watcher { @@ -142,7 +142,7 @@ struct ebt_entry_watcher { } u; /* size of data */ unsigned int watcher_size; - unsigned char data[0] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); + unsigned char data[] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); }; struct ebt_entry_target { @@ -190,7 +190,7 @@ struct ebt_entry { /* sizeof ebt_entry + matches + watchers + target */ unsigned int next_offset; ); - unsigned char elems[0] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); + unsigned char elems[] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); }; static __inline__ struct ebt_entry_target * -- cgit v1.2.3 From 49e62a0462a2d669e35f97eb3e0a6f2aab20518d Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 21 Aug 2023 21:02:18 +0800 Subject: net: mscc: ocelot: Remove unused declarations Commit 6c30384eb1de ("net: mscc: ocelot: register devlink ports") declared but never implemented ocelot_devlink_init() and ocelot_devlink_teardown(). Commit 2096805497e2 ("net: mscc: ocelot: automatically detect VCAP constants") declared but never implemented ocelot_detect_vcap_constants(). Commit 403ffc2c34de ("net: mscc: ocelot: add support for preemptible traffic classes") declared but never implemented ocelot_port_update_preemptible_tcs(). Signed-off-by: Yue Haibing Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230821130218.19096-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot.h | 2 -- drivers/net/ethernet/mscc/ocelot_vcap.h | 1 - include/soc/mscc/ocelot.h | 1 - 3 files changed, 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index 87f2055c242c..e50be508c166 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -97,8 +97,6 @@ int ocelot_netdev_to_port(struct net_device *dev); int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target, struct device_node *portnp); void ocelot_release_port(struct ocelot_port *ocelot_port); -int ocelot_devlink_init(struct ocelot *ocelot); -void ocelot_devlink_teardown(struct ocelot *ocelot); int ocelot_port_devlink_init(struct ocelot *ocelot, int port, enum devlink_port_flavour flavour); void ocelot_port_devlink_teardown(struct ocelot *ocelot, int port); diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.h b/drivers/net/ethernet/mscc/ocelot_vcap.h index 523611ccc48f..6f546695faa5 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.h +++ b/drivers/net/ethernet/mscc/ocelot_vcap.h @@ -15,7 +15,6 @@ int ocelot_vcap_filter_stats_update(struct ocelot *ocelot, struct ocelot_vcap_filter *rule); -void ocelot_detect_vcap_constants(struct ocelot *ocelot); int ocelot_vcap_init(struct ocelot *ocelot); int ocelot_setup_tc_cls_flower(struct ocelot_port_private *priv, diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index a8c2817335b9..1e1b40f4e664 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -1165,7 +1165,6 @@ int ocelot_port_get_mm(struct ocelot *ocelot, int port, struct ethtool_mm_state *state); int ocelot_port_mqprio(struct ocelot *ocelot, int port, struct tc_mqprio_qopt_offload *mqprio); -void ocelot_port_update_preemptible_tcs(struct ocelot *ocelot, int port); #if IS_ENABLED(CONFIG_BRIDGE_MRP) int ocelot_mrp_add(struct ocelot *ocelot, int port, -- cgit v1.2.3 From 7bdfda42f043fce2e590252f264e0832b31a3e92 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 7 Aug 2023 22:50:32 +0800 Subject: wifi: wext: Remove unused declaration dev_get_wireless_info() Commit 556829657397 ("[NL80211]: add netlink interface to cfg80211") declared but never implemented this, remove it. Commit 11433ee450eb ("[WEXT]: Move to net/wireless") rename net/core/wireless.c to net/wireless/wext.c, then commit 3d23e349d807 ("wext: refactor") refactor wext.c to wext-core.c, fix the wext comment. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230807145032.44768-1-yuehaibing@huawei.com Signed-off-by: Johannes Berg --- include/net/iw_handler.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index d2ea5863eedc..b2cf243ebe44 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -426,17 +426,10 @@ struct iw_public_data { /**************************** PROTOTYPES ****************************/ /* - * Functions part of the Wireless Extensions (defined in net/core/wireless.c). - * Those may be called only within the kernel. + * Functions part of the Wireless Extensions (defined in net/wireless/wext-core.c). + * Those may be called by driver modules. */ -/* First : function strictly used inside the kernel */ - -/* Handle /proc/net/wireless, called in net/code/dev.c */ -int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length); - -/* Second : functions that may be called by driver modules */ - /* Send a single event to user space */ void wireless_send_event(struct net_device *dev, unsigned int cmd, union iwreq_data *wrqu, const char *extra); -- cgit v1.2.3 From 1dcf396b4223143fcd3ef6d5e2acdbb6f7bea2e5 Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Thu, 13 Jul 2023 16:29:36 +0300 Subject: wifi: cfg80211: improve documentation for flag fields Fix and hopefully improve documentation for 'flag' fields of a few types by adding references to relevant enumerations. Signed-off-by: Dmitry Antipov Link: https://lore.kernel.org/r/20230713132957.275859-1-dmantipov@yandex.ru Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 423fe9b85cb0..070ac0c62bd4 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -263,7 +263,7 @@ enum ieee80211_privacy { * are only for driver use when pointers to this structure are * passed around. * - * @flags: rate-specific flags + * @flags: rate-specific flags from &enum ieee80211_rate_flags * @bitrate: bitrate in units of 100 Kbps * @hw_value: driver/hardware value for this rate * @hw_value_short: driver/hardware value for this rate when @@ -1353,7 +1353,7 @@ struct cfg80211_unsol_bcast_probe_resp { * @twt_responder: Enable Target Wait Time * @he_required: stations must support HE * @sae_h2e_required: stations must support direct H2E technique in SAE - * @flags: flags, as defined in enum cfg80211_ap_settings_flags + * @flags: flags, as defined in &enum nl80211_ap_settings_flags * @he_obss_pd: OBSS Packet Detection settings * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters @@ -2156,7 +2156,7 @@ enum mpath_info_flags { * @sn: target sequence number * @metric: metric (cost) of this mesh path * @exptime: expiration time for the mesh path from now, in msecs - * @flags: mesh path flags + * @flags: mesh path flags from &enum mesh_path_flags * @discovery_timeout: total mesh path discovery timeout, in msecs * @discovery_retries: mesh path discovery retries * @generation: generation number for nl80211 dumps. @@ -2496,7 +2496,7 @@ struct cfg80211_scan_6ghz_params { * the actual dwell time may be shorter. * @duration_mandatory: if set, the scan duration must be as specified by the * %duration field. - * @flags: bit field of flags controlling operation + * @flags: control flags from &enum nl80211_scan_flags * @rates: bitmap of rates to advertise for each band * @wiphy: the wiphy this was for * @scan_start: time (in jiffies) when the scan started @@ -2616,7 +2616,7 @@ struct cfg80211_bss_select_adjust { * @scan_width: channel width for scanning * @ie: optional information element(s) to add into Probe Request or %NULL * @ie_len: length of ie in octets - * @flags: bit field of flags controlling operation + * @flags: control flags from &enum nl80211_scan_flags * @match_sets: sets of parameters to be matched for a scan result * entry to be considered valid and to be passed to the host * (others are filtered out). @@ -8118,7 +8118,7 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr, * @link_id: the ID of the link the frame was received on * @buf: Management frame (header + body) * @len: length of the frame data - * @flags: flags, as defined in enum nl80211_rxmgmt_flags + * @flags: flags, as defined in &enum nl80211_rxmgmt_flags * @rx_tstamp: Hardware timestamp of frame RX in nanoseconds * @ack_tstamp: Hardware timestamp of ack TX in nanoseconds */ -- cgit v1.2.3 From a49a0d4e573e22f47218668ee4137cdcdc391652 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 10 Jul 2023 16:03:02 -0700 Subject: wifi: cfg80211: remove dead/unused enum value Drop an unused (extra) enum value to prevent a kernel-doc warning. cfg80211.h:1492: warning: Excess enum value 'STATION_PARAM_APPLY_STA_TXPOWER' description in 'station_parameters_apply_mask' Fixes: 2d8b08fef0af ("wifi: cfg80211: fix kernel-doc warnings all over the file") Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Johannes Berg Cc: linux-wireless@vger.kernel.org Cc: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/20230710230312.31197-3-rdunlap@infradead.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 070ac0c62bd4..3a4b684f89bf 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1482,7 +1482,6 @@ struct iface_combination_params { * @STATION_PARAM_APPLY_UAPSD: apply new uAPSD parameters (uapsd_queues, max_sp) * @STATION_PARAM_APPLY_CAPABILITY: apply new capability * @STATION_PARAM_APPLY_PLINK_STATE: apply new plink state - * @STATION_PARAM_APPLY_STA_TXPOWER: apply tx power for STA * * Not all station parameters have in-band "no change" signalling, * for those that don't these flags will are used. -- cgit v1.2.3 From 266a5cd768da7e243cd26bc6840ce48cad1c907e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 10 Jul 2023 16:03:06 -0700 Subject: wifi: radiotap: fix kernel-doc notation warnings Fix a typo (82011 -> 80211) to prevent a kernel-doc warning. Add one missing function parameter description to prevent a kernel-doc warning. ieee80211_radiotap.h:52: warning: expecting prototype for struct ieee82011_radiotap_header. Prototype was for struct ieee80211_radiotap_header instead ieee80211_radiotap.h:581: warning: Function parameter or member 'data' not described in 'ieee80211_get_radiotap_len' Fixes: 42f82e2e62ae ("wireless: radiotap: rewrite the radiotap header file") Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Johannes Berg Cc: linux-wireless@vger.kernel.org Link: https://lore.kernel.org/r/20230710230312.31197-7-rdunlap@infradead.org Signed-off-by: Johannes Berg --- include/net/ieee80211_radiotap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index c4722a9963de..2338f8d2a8b3 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -21,7 +21,7 @@ #include /** - * struct ieee82011_radiotap_header - base radiotap header + * struct ieee80211_radiotap_header - base radiotap header */ struct ieee80211_radiotap_header { /** @@ -575,6 +575,7 @@ enum ieee80211_radiotap_eht_usig_tb { /** * ieee80211_get_radiotap_len - get radiotap header length + * @data: pointer to the header */ static inline u16 ieee80211_get_radiotap_len(const char *data) { -- cgit v1.2.3 From c6662a4b3ecf03aa832125e9705a185402cd3b17 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 10 Jul 2023 16:03:09 -0700 Subject: wifi: mac80211: fix kernel-doc notation warning Add description for struct member 'agg' to prevent a kernel-doc warning. mac80211.h:2289: warning: Function parameter or member 'agg' not described in 'ieee80211_link_sta' Fixes: 4c51541ddb78 ("wifi: mac80211: keep A-MSDU data in sta and per-link") Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Johannes Berg Cc: Benjamin Berg Cc: linux-wireless@vger.kernel.org Link: https://lore.kernel.org/r/20230710230312.31197-10-rdunlap@infradead.org [reword the kernel-doc comment] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 3a8a2d2c58c3..d7fa0a55067e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2259,6 +2259,7 @@ struct ieee80211_sta_aggregates { * @he_cap: HE capabilities of this STA * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities * @eht_cap: EHT capabilities of this STA + * @agg: per-link data for multi-link aggregation * @bandwidth: current bandwidth the station can receive with * @rx_nss: in HT/VHT, the maximum number of spatial streams the * station can receive at the moment, changed by operating mode -- cgit v1.2.3 From a7a2ef0c4b3efbd7d6f3fabd87dbbc0b3f2de5af Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 23 Jun 2023 17:24:00 +0200 Subject: mac80211: make ieee80211_tx_info padding explicit While looking at a bug, I got rather confused by the layout of the 'status' field in ieee80211_tx_info. Apparently, the intention is that status_driver_data[] is used for driver specific data, and fills up the size of the union to 40 bytes, just like the other ones. This is indeed what actually happens, but only because of the combination of two mistakes: - "void *status_driver_data[18 / sizeof(void *)];" is intended to be 18 bytes long but is actually two bytes shorter because of rounding-down in the division, to a multiple of the pointer size (4 bytes or 8 bytes). - The other fields combined are intended to be 22 bytes long, but are actually 24 bytes because of padding in front of the unaligned tx_time member, and in front of the pointer array. The two mistakes cancel out. so the size ends up fine, but it seems more helpful to make this explicit, by having a multiple of 8 bytes in the size calculation and explicitly describing the padding. Fixes: ea5907db2a9cc ("mac80211: fix struct ieee80211_tx_info size") Fixes: 02219b3abca59 ("mac80211: add WMM admission control support") Signed-off-by: Arnd Bergmann Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20230623152443.2296825-2-arnd@kernel.org Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d7fa0a55067e..f1420e5af5de 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1192,9 +1192,11 @@ struct ieee80211_tx_info { u8 ampdu_ack_len; u8 ampdu_len; u8 antenna; + u8 pad; u16 tx_time; u8 flags; - void *status_driver_data[18 / sizeof(void *)]; + u8 pad2; + void *status_driver_data[16 / sizeof(void *)]; } status; struct { struct ieee80211_tx_rate driver_rates[ -- cgit v1.2.3 From 9e261e6da0a814f4ee1856ab06b19c25190aeffb Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Tue, 22 Aug 2023 09:30:17 -0700 Subject: wifi: Fix ieee80211.h kernel-doc issues The kernel-doc script identified multiple issues in ieee80211.h, so fix them. In the process update some references to the latest applicable specification. include/linux/ieee80211.h:848: warning: Function parameter or member 'count' not described in 'ieee80211_quiet_ie' include/linux/ieee80211.h:848: warning: Function parameter or member 'period' not described in 'ieee80211_quiet_ie' include/linux/ieee80211.h:848: warning: Function parameter or member 'duration' not described in 'ieee80211_quiet_ie' include/linux/ieee80211.h:848: warning: Function parameter or member 'offset' not described in 'ieee80211_quiet_ie' include/linux/ieee80211.h:860: warning: Function parameter or member 'token' not described in 'ieee80211_msrment_ie' include/linux/ieee80211.h:860: warning: Function parameter or member 'mode' not described in 'ieee80211_msrment_ie' include/linux/ieee80211.h:860: warning: Function parameter or member 'type' not described in 'ieee80211_msrment_ie' include/linux/ieee80211.h:860: warning: Function parameter or member 'request' not described in 'ieee80211_msrment_ie' include/linux/ieee80211.h:871: warning: Function parameter or member 'mode' not described in 'ieee80211_channel_sw_ie' include/linux/ieee80211.h:871: warning: Function parameter or member 'new_ch_num' not described in 'ieee80211_channel_sw_ie' include/linux/ieee80211.h:871: warning: Function parameter or member 'count' not described in 'ieee80211_channel_sw_ie' include/linux/ieee80211.h:883: warning: Function parameter or member 'mode' not described in 'ieee80211_ext_chansw_ie' include/linux/ieee80211.h:883: warning: Function parameter or member 'new_operating_class' not described in 'ieee80211_ext_chansw_ie' include/linux/ieee80211.h:883: warning: Function parameter or member 'new_ch_num' not described in 'ieee80211_ext_chansw_ie' include/linux/ieee80211.h:883: warning: Function parameter or member 'count' not described in 'ieee80211_ext_chansw_ie' include/linux/ieee80211.h:905: warning: Function parameter or member 'mesh_ttl' not described in 'ieee80211_mesh_chansw_params_ie' include/linux/ieee80211.h:905: warning: Function parameter or member 'mesh_flags' not described in 'ieee80211_mesh_chansw_params_ie' include/linux/ieee80211.h:905: warning: Function parameter or member 'mesh_reason' not described in 'ieee80211_mesh_chansw_params_ie' include/linux/ieee80211.h:905: warning: Function parameter or member 'mesh_pre_value' not described in 'ieee80211_mesh_chansw_params_ie' include/linux/ieee80211.h:913: warning: Function parameter or member 'new_channel_width' not described in 'ieee80211_wide_bw_chansw_ie' include/linux/ieee80211.h:913: warning: Function parameter or member 'new_center_freq_seg0' not described in 'ieee80211_wide_bw_chansw_ie' include/linux/ieee80211.h:913: warning: Function parameter or member 'new_center_freq_seg1' not described in 'ieee80211_wide_bw_chansw_ie' include/linux/ieee80211.h:926: warning: expecting prototype for struct ieee80211_tim. Prototype was for struct ieee80211_tim_ie instead include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_psel' not described in 'ieee80211_meshconf_ie' include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_pmetric' not described in 'ieee80211_meshconf_ie' include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_congest' not described in 'ieee80211_meshconf_ie' include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_synch' not described in 'ieee80211_meshconf_ie' include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_auth' not described in 'ieee80211_meshconf_ie' include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_form' not described in 'ieee80211_meshconf_ie' include/linux/ieee80211.h:941: warning: Function parameter or member 'meshconf_cap' not described in 'ieee80211_meshconf_ie' include/linux/ieee80211.h:964: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * mesh channel switch parameters element's flag indicator include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_flags' not described in 'ieee80211_rann_ie' include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_hopcount' not described in 'ieee80211_rann_ie' include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_ttl' not described in 'ieee80211_rann_ie' include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_addr' not described in 'ieee80211_rann_ie' include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_seq' not described in 'ieee80211_rann_ie' include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_interval' not described in 'ieee80211_rann_ie' include/linux/ieee80211.h:984: warning: Function parameter or member 'rann_metric' not described in 'ieee80211_rann_ie' include/linux/ieee80211.h:1019: warning: expecting prototype for enum ieee80211_opmode_bits. Prototype was for enum ieee80211_vht_opmode_bits instead include/linux/ieee80211.h:1052: warning: Function parameter or member 'tx_power' not described in 'ieee80211_tpc_report_ie' include/linux/ieee80211.h:1052: warning: Function parameter or member 'link_margin' not described in 'ieee80211_tpc_report_ie' include/linux/ieee80211.h:1073: warning: Function parameter or member 'compat_info' not described in 'ieee80211_s1g_bcn_compat_ie' include/linux/ieee80211.h:1073: warning: Function parameter or member 'beacon_int' not described in 'ieee80211_s1g_bcn_compat_ie' include/linux/ieee80211.h:1073: warning: Function parameter or member 'tsf_completion' not described in 'ieee80211_s1g_bcn_compat_ie' include/linux/ieee80211.h:1086: warning: Function parameter or member 'ch_width' not described in 'ieee80211_s1g_oper_ie' include/linux/ieee80211.h:1086: warning: Function parameter or member 'oper_class' not described in 'ieee80211_s1g_oper_ie' include/linux/ieee80211.h:1086: warning: Function parameter or member 'primary_ch' not described in 'ieee80211_s1g_oper_ie' include/linux/ieee80211.h:1086: warning: Function parameter or member 'oper_ch' not described in 'ieee80211_s1g_oper_ie' include/linux/ieee80211.h:1086: warning: Function parameter or member 'basic_mcs_nss' not described in 'ieee80211_s1g_oper_ie' include/linux/ieee80211.h:1097: warning: Function parameter or member 'aid' not described in 'ieee80211_aid_response_ie' include/linux/ieee80211.h:1097: warning: Function parameter or member 'switch_count' not described in 'ieee80211_aid_response_ie' include/linux/ieee80211.h:1097: warning: Function parameter or member 'response_int' not described in 'ieee80211_aid_response_ie' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_STATUS' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_MINOR_REASON' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_CAPABILITY' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_DEVICE_ID' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_GO_INTENT' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_GO_CONFIG_TIMEOUT' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_LISTEN_CHANNEL' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_GROUP_BSSID' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_EXT_LISTEN_TIMING' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_INTENDED_IFACE_ADDR' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_MANAGABILITY' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_CHANNEL_LIST' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_ABSENCE_NOTICE' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_DEVICE_INFO' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_GROUP_INFO' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_GROUP_ID' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_INTERFACE' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_OPER_CHANNEL' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_INVITE_FLAGS' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_VENDOR_SPECIFIC' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1519: warning: Enum value 'IEEE80211_P2P_ATTR_MAX' not described in enum 'ieee80211_p2p_attr_id' include/linux/ieee80211.h:1554: warning: Function parameter or member 'frame_control' not described in 'ieee80211_bar' include/linux/ieee80211.h:1554: warning: Function parameter or member 'duration' not described in 'ieee80211_bar' include/linux/ieee80211.h:1554: warning: Function parameter or member 'ra' not described in 'ieee80211_bar' include/linux/ieee80211.h:1554: warning: Function parameter or member 'ta' not described in 'ieee80211_bar' include/linux/ieee80211.h:1554: warning: Function parameter or member 'control' not described in 'ieee80211_bar' include/linux/ieee80211.h:1554: warning: Function parameter or member 'start_seq_num' not described in 'ieee80211_bar' include/linux/ieee80211.h:1579: warning: Function parameter or member 'reserved' not described in 'ieee80211_mcs_info' include/linux/ieee80211.h:1618: warning: Function parameter or member 'cap_info' not described in 'ieee80211_ht_cap' include/linux/ieee80211.h:1618: warning: Function parameter or member 'ampdu_params_info' not described in 'ieee80211_ht_cap' include/linux/ieee80211.h:1618: warning: Function parameter or member 'mcs' not described in 'ieee80211_ht_cap' include/linux/ieee80211.h:1618: warning: Function parameter or member 'extended_ht_cap_info' not described in 'ieee80211_ht_cap' include/linux/ieee80211.h:1618: warning: Function parameter or member 'tx_BF_cap_info' not described in 'ieee80211_ht_cap' include/linux/ieee80211.h:1618: warning: Function parameter or member 'antenna_selection_info' not described in 'ieee80211_ht_cap' include/linux/ieee80211.h:1704: warning: Function parameter or member 'primary_chan' not described in 'ieee80211_ht_operation' include/linux/ieee80211.h:1704: warning: Function parameter or member 'ht_param' not described in 'ieee80211_ht_operation' include/linux/ieee80211.h:1704: warning: Function parameter or member 'operation_mode' not described in 'ieee80211_ht_operation' include/linux/ieee80211.h:1704: warning: Function parameter or member 'stbc_param' not described in 'ieee80211_ht_operation' include/linux/ieee80211.h:1704: warning: Function parameter or member 'basic_set' not described in 'ieee80211_ht_operation' include/linux/ieee80211.h:1872: warning: Function parameter or member 'mac_cap_info' not described in 'ieee80211_he_cap_elem' include/linux/ieee80211.h:1872: warning: Function parameter or member 'phy_cap_info' not described in 'ieee80211_he_cap_elem' include/linux/ieee80211.h:1936: warning: Function parameter or member 'he_oper_params' not described in 'ieee80211_he_operation' include/linux/ieee80211.h:1936: warning: Function parameter or member 'he_mcs_nss_set' not described in 'ieee80211_he_operation' include/linux/ieee80211.h:1936: warning: Function parameter or member 'optional' not described in 'ieee80211_he_operation' include/linux/ieee80211.h:1948: warning: Function parameter or member 'he_sr_control' not described in 'ieee80211_he_spr' include/linux/ieee80211.h:1948: warning: Function parameter or member 'optional' not described in 'ieee80211_he_spr' include/linux/ieee80211.h:1960: warning: Function parameter or member 'aifsn' not described in 'ieee80211_he_mu_edca_param_ac_rec' include/linux/ieee80211.h:1960: warning: Function parameter or member 'ecw_min_max' not described in 'ieee80211_he_mu_edca_param_ac_rec' include/linux/ieee80211.h:1960: warning: Function parameter or member 'mu_edca_timer' not described in 'ieee80211_he_mu_edca_param_ac_rec' include/linux/ieee80211.h:1974: warning: Function parameter or member 'mu_qos_info' not described in 'ieee80211_mu_edca_param_set' include/linux/ieee80211.h:1974: warning: Function parameter or member 'ac_be' not described in 'ieee80211_mu_edca_param_set' include/linux/ieee80211.h:1974: warning: Function parameter or member 'ac_bk' not described in 'ieee80211_mu_edca_param_set' include/linux/ieee80211.h:1974: warning: Function parameter or member 'ac_vi' not described in 'ieee80211_mu_edca_param_set' include/linux/ieee80211.h:1974: warning: Function parameter or member 'ac_vo' not described in 'ieee80211_mu_edca_param_set' include/linux/ieee80211.h:2194: warning: Enum value 'IEEE80211_REG_LPI_AP' not described in enum 'ieee80211_ap_reg_power' include/linux/ieee80211.h:2194: warning: Enum value 'IEEE80211_REG_SP_AP' not described in enum 'ieee80211_ap_reg_power' include/linux/ieee80211.h:2194: warning: Enum value 'IEEE80211_REG_VLP_AP' not described in enum 'ieee80211_ap_reg_power' include/linux/ieee80211.h:2194: warning: Excess enum value 'IEEE80211_REG_SP' description in 'ieee80211_ap_reg_power' include/linux/ieee80211.h:2194: warning: Excess enum value 'IEEE80211_REG_VLP' description in 'ieee80211_ap_reg_power' include/linux/ieee80211.h:2194: warning: Excess enum value 'IEEE80211_REG_LPI' description in 'ieee80211_ap_reg_power' include/linux/ieee80211.h:2577: warning: cannot understand function prototype: 'struct ieee80211_he_6ghz_oper ' include/linux/ieee80211.h:2624: warning: Function parameter or member 'tx_power_info' not described in 'ieee80211_tx_pwr_env' include/linux/ieee80211.h:2624: warning: Function parameter or member 'tx_power' not described in 'ieee80211_tx_pwr_env' include/linux/ieee80211.h:4485: warning: expecting prototype for RSNX Capabilities(). Prototype was for WLAN_RSNX_CAPA_PROTECTED_TWT() instead include/linux/ieee80211.h:4734: warning: expecting prototype for ieee80211_mle_get_eml_sync_delay(). Prototype was for ieee80211_mle_get_eml_med_sync_delay() instead 117 warnings as Errors Signed-off-by: Jeff Johnson Link: https://lore.kernel.org/r/20230822-kerneldoc-v1-1-0d42ce5029bf@quicinc.com Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 235 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 177 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 4b998090898e..bd2f6e19c357 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -836,9 +836,14 @@ enum ieee80211_preq_target_flags { }; /** - * struct ieee80211_quiet_ie + * struct ieee80211_quiet_ie - Quiet element + * @count: Quiet Count + * @period: Quiet Period + * @duration: Quiet Duration + * @offset: Quiet Offset * - * This structure refers to "Quiet information element" + * This structure represents the payload of the "Quiet element" as + * described in IEEE Std 802.11-2020 section 9.4.2.22. */ struct ieee80211_quiet_ie { u8 count; @@ -848,9 +853,15 @@ struct ieee80211_quiet_ie { } __packed; /** - * struct ieee80211_msrment_ie + * struct ieee80211_msrment_ie - Measurement element + * @token: Measurement Token + * @mode: Measurement Report Mode + * @type: Measurement Type + * @request: Measurement Request or Measurement Report * - * This structure refers to "Measurement Request/Report information element" + * This structure represents the payload of both the "Measurement + * Request element" and the "Measurement Report element" as described + * in IEEE Std 802.11-2020 sections 9.4.2.20 and 9.4.2.21. */ struct ieee80211_msrment_ie { u8 token; @@ -860,9 +871,14 @@ struct ieee80211_msrment_ie { } __packed; /** - * struct ieee80211_channel_sw_ie + * struct ieee80211_channel_sw_ie - Channel Switch Announcement element + * @mode: Channel Switch Mode + * @new_ch_num: New Channel Number + * @count: Channel Switch Count * - * This structure refers to "Channel Switch Announcement information element" + * This structure represents the payload of the "Channel Switch + * Announcement element" as described in IEEE Std 802.11-2020 section + * 9.4.2.18. */ struct ieee80211_channel_sw_ie { u8 mode; @@ -871,9 +887,14 @@ struct ieee80211_channel_sw_ie { } __packed; /** - * struct ieee80211_ext_chansw_ie + * struct ieee80211_ext_chansw_ie - Extended Channel Switch Announcement element + * @mode: Channel Switch Mode + * @new_operating_class: New Operating Class + * @new_ch_num: New Channel Number + * @count: Channel Switch Count * - * This structure represents the "Extended Channel Switch Announcement element" + * This structure represents the "Extended Channel Switch Announcement + * element" as described in IEEE Std 802.11-2020 section 9.4.2.52. */ struct ieee80211_ext_chansw_ie { u8 mode; @@ -894,8 +915,14 @@ struct ieee80211_sec_chan_offs_ie { /** * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE + * @mesh_ttl: Time To Live + * @mesh_flags: Flags + * @mesh_reason: Reason Code + * @mesh_pre_value: Precedence Value * - * This structure represents the "Mesh Channel Switch Paramters element" + * This structure represents the payload of the "Mesh Channel Switch + * Parameters element" as described in IEEE Std 802.11-2020 section + * 9.4.2.102. */ struct ieee80211_mesh_chansw_params_ie { u8 mesh_ttl; @@ -906,6 +933,13 @@ struct ieee80211_mesh_chansw_params_ie { /** * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE + * @new_channel_width: New Channel Width + * @new_center_freq_seg0: New Channel Center Frequency Segment 0 + * @new_center_freq_seg1: New Channel Center Frequency Segment 1 + * + * This structure represents the payload of the "Wide Bandwidth + * Channel Switch element" as described in IEEE Std 802.11-2020 + * section 9.4.2.160. */ struct ieee80211_wide_bw_chansw_ie { u8 new_channel_width; @@ -913,9 +947,14 @@ struct ieee80211_wide_bw_chansw_ie { } __packed; /** - * struct ieee80211_tim + * struct ieee80211_tim_ie - Traffic Indication Map information element + * @dtim_count: DTIM Count + * @dtim_period: DTIM Period + * @bitmap_ctrl: Bitmap Control + * @virtual_map: Partial Virtual Bitmap * - * This structure refers to "Traffic Indication Map information element" + * This structure represents the payload of the "TIM element" as + * described in IEEE Std 802.11-2020 section 9.4.2.5. */ struct ieee80211_tim_ie { u8 dtim_count; @@ -926,9 +965,17 @@ struct ieee80211_tim_ie { } __packed; /** - * struct ieee80211_meshconf_ie + * struct ieee80211_meshconf_ie - Mesh Configuration element + * @meshconf_psel: Active Path Selection Protocol Identifier + * @meshconf_pmetric: Active Path Selection Metric Identifier + * @meshconf_congest: Congestion Control Mode Identifier + * @meshconf_synch: Synchronization Method Identifier + * @meshconf_auth: Authentication Protocol Identifier + * @meshconf_form: Mesh Formation Info + * @meshconf_cap: Mesh Capability (see &enum mesh_config_capab_flags) * - * This structure refers to "Mesh Configuration information element" + * This structure represents the payload of the "Mesh Configuration + * element" as described in IEEE Std 802.11-2020 section 9.4.2.97. */ struct ieee80211_meshconf_ie { u8 meshconf_psel; @@ -950,6 +997,9 @@ struct ieee80211_meshconf_ie { * is ongoing * @IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL: STA is in deep sleep mode or has * neighbors in deep sleep mode + * + * Enumerates the "Mesh Capability" as described in IEEE Std + * 802.11-2020 section 9.4.2.97.7. */ enum mesh_config_capab_flags { IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS = 0x01, @@ -960,7 +1010,7 @@ enum mesh_config_capab_flags { #define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1 -/** +/* * mesh channel switch parameters element's flag indicator * */ @@ -969,9 +1019,17 @@ enum mesh_config_capab_flags { #define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2) /** - * struct ieee80211_rann_ie + * struct ieee80211_rann_ie - RANN (root announcement) element + * @rann_flags: Flags + * @rann_hopcount: Hop Count + * @rann_ttl: Element TTL + * @rann_addr: Root Mesh STA Address + * @rann_seq: HWMP Sequence Number + * @rann_interval: Interval + * @rann_metric: Metric * - * This structure refers to "Root Announcement information element" + * This structure represents the payload of the "RANN element" as + * described in IEEE Std 802.11-2020 section 9.4.2.111. */ struct ieee80211_rann_ie { u8 rann_flags; @@ -993,7 +1051,7 @@ enum ieee80211_ht_chanwidth_values { }; /** - * enum ieee80211_opmode_bits - VHT operating mode field bits + * enum ieee80211_vht_opmode_bits - VHT operating mode field bits * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: 20 MHz channel width * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width @@ -1042,9 +1100,12 @@ enum ieee80211_s1g_chanwidth { #define WLAN_USER_POSITION_LEN 16 /** - * struct ieee80211_tpc_report_ie + * struct ieee80211_tpc_report_ie - TPC Report element + * @tx_power: Transmit Power + * @link_margin: Link Margin * - * This structure refers to "TPC Report element" + * This structure represents the payload of the "TPC Report element" as + * described in IEEE Std 802.11-2020 section 9.4.2.16. */ struct ieee80211_tpc_report_ie { u8 tx_power; @@ -1062,9 +1123,14 @@ struct ieee80211_addba_ext_ie { } __packed; /** - * struct ieee80211_s1g_bcn_compat_ie + * struct ieee80211_s1g_bcn_compat_ie - S1G Beacon Compatibility element + * @compat_info: Compatibility Information + * @beacon_int: Beacon Interval + * @tsf_completion: TSF Completion * - * S1G Beacon Compatibility element + * This structure represents the payload of the "S1G Beacon + * Compatibility element" as described in IEEE Std 802.11-2020 section + * 9.4.2.196. */ struct ieee80211_s1g_bcn_compat_ie { __le16 compat_info; @@ -1073,9 +1139,15 @@ struct ieee80211_s1g_bcn_compat_ie { } __packed; /** - * struct ieee80211_s1g_oper_ie + * struct ieee80211_s1g_oper_ie - S1G Operation element + * @ch_width: S1G Operation Information Channel Width + * @oper_class: S1G Operation Information Operating Class + * @primary_ch: S1G Operation Information Primary Channel Number + * @oper_ch: S1G Operation Information Channel Center Frequency + * @basic_mcs_nss: Basic S1G-MCS and NSS Set * - * S1G Operation element + * This structure represents the payload of the "S1G Operation + * element" as described in IEEE Std 802.11-2020 section 9.4.2.212. */ struct ieee80211_s1g_oper_ie { u8 ch_width; @@ -1086,9 +1158,13 @@ struct ieee80211_s1g_oper_ie { } __packed; /** - * struct ieee80211_aid_response_ie + * struct ieee80211_aid_response_ie - AID Response element + * @aid: AID/Group AID + * @switch_count: AID Switch Count + * @response_int: AID Response Interval * - * AID Response element + * This structure represents the payload of the "AID Response element" + * as described in IEEE Std 802.11-2020 section 9.4.2.194. */ struct ieee80211_aid_response_ie { __le16 aid; @@ -1489,7 +1565,7 @@ struct ieee80211_tdls_data { /* * Peer-to-Peer IE attribute related definitions. */ -/** +/* * enum ieee80211_p2p_attr_id - identifies type of peer-to-peer attribute. */ enum ieee80211_p2p_attr_id { @@ -1539,11 +1615,17 @@ struct ieee80211_p2p_noa_attr { #define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F /** - * struct ieee80211_bar - HT Block Ack Request + * struct ieee80211_bar - Block Ack Request frame format + * @frame_control: Frame Control + * @duration: Duration + * @ra: RA + * @ta: TA + * @control: BAR Control + * @start_seq_num: Starting Sequence Number (see Figure 9-37) * - * This structure refers to "HT BlockAckReq" as - * described in 802.11n draft section 7.2.1.7.1 - */ + * This structure represents the "BlockAckReq frame format" + * as described in IEEE Std 802.11-2020 section 9.3.1.7. +*/ struct ieee80211_bar { __le16 frame_control; __le16 duration; @@ -1563,13 +1645,17 @@ struct ieee80211_bar { #define IEEE80211_HT_MCS_MASK_LEN 10 /** - * struct ieee80211_mcs_info - MCS information + * struct ieee80211_mcs_info - Supported MCS Set field * @rx_mask: RX mask * @rx_highest: highest supported RX rate. If set represents * the highest supported RX data rate in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest RX data rate supported. * @tx_params: TX parameters + * @reserved: Reserved bits + * + * This structure represents the "Supported MCS Set field" as + * described in IEEE Std 802.11-2020 section 9.4.2.55.4. */ struct ieee80211_mcs_info { u8 rx_mask[IEEE80211_HT_MCS_MASK_LEN]; @@ -1600,10 +1686,16 @@ struct ieee80211_mcs_info { (IEEE80211_HT_MCS_UNEQUAL_MODULATION_START / 8) /** - * struct ieee80211_ht_cap - HT capabilities + * struct ieee80211_ht_cap - HT capabilities element + * @cap_info: HT Capability Information + * @ampdu_params_info: A-MPDU Parameters + * @mcs: Supported MCS Set + * @extended_ht_cap_info: HT Extended Capabilities + * @tx_BF_cap_info: Transmit Beamforming Capabilities + * @antenna_selection_info: ASEL Capability * - * This structure is the "HT capabilities element" as - * described in 802.11n D5.0 7.3.2.57 + * This structure represents the payload of the "HT Capabilities + * element" as described in IEEE Std 802.11-2020 section 9.4.2.55. */ struct ieee80211_ht_cap { __le16 cap_info; @@ -1691,9 +1783,14 @@ enum ieee80211_min_mpdu_spacing { /** * struct ieee80211_ht_operation - HT operation IE + * @primary_chan: Primary Channel + * @ht_param: HT Operation Information parameters + * @operation_mode: HT Operation Information operation mode + * @stbc_param: HT Operation Information STBC params + * @basic_set: Basic HT-MCS Set * - * This structure is the "HT operation element" as - * described in 802.11n-2009 7.3.2.57 + * This structure represents the payload of the "HT Operation + * element" as described in IEEE Std 802.11-2020 section 9.4.2.56. */ struct ieee80211_ht_operation { u8 primary_chan; @@ -1862,9 +1959,12 @@ struct ieee80211_vht_operation { /** * struct ieee80211_he_cap_elem - HE capabilities element + * @mac_cap_info: HE MAC Capabilities Information + * @phy_cap_info: HE PHY Capabilities Information * - * This structure is the "HE capabilities element" fixed fields as - * described in P802.11ax_D4.0 section 9.4.2.242.2 and 9.4.2.242.3 + * This structure represents the fixed fields of the payload of the + * "HE capabilities element" as described in IEEE Std 802.11ax-2021 + * sections 9.4.2.248.2 and 9.4.2.248.3. */ struct ieee80211_he_cap_elem { u8 mac_cap_info[6]; @@ -1923,35 +2023,45 @@ struct ieee80211_he_mcs_nss_supp { } __packed; /** - * struct ieee80211_he_operation - HE capabilities element + * struct ieee80211_he_operation - HE Operation element + * @he_oper_params: HE Operation Parameters + BSS Color Information + * @he_mcs_nss_set: Basic HE-MCS And NSS Set + * @optional: Optional fields VHT Operation Information, Max Co-Hosted + * BSSID Indicator, and 6 GHz Operation Information * - * This structure is the "HE operation element" fields as - * described in P802.11ax_D4.0 section 9.4.2.243 + * This structure represents the payload of the "HE Operation + * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.249. */ struct ieee80211_he_operation { __le32 he_oper_params; __le16 he_mcs_nss_set; - /* Optional 0,1,3,4,5,7 or 8 bytes: depends on @he_oper_params */ u8 optional[]; } __packed; /** - * struct ieee80211_he_spr - HE spatial reuse element + * struct ieee80211_he_spr - Spatial Reuse Parameter Set element + * @he_sr_control: SR Control + * @optional: Optional fields Non-SRG OBSS PD Max Offset, SRG OBSS PD + * Min Offset, SRG OBSS PD Max Offset, SRG BSS Color + * Bitmap, and SRG Partial BSSID Bitmap * - * This structure is the "HE spatial reuse element" element as - * described in P802.11ax_D4.0 section 9.4.2.241 + * This structure represents the payload of the "Spatial Reuse + * Parameter Set element" as described in IEEE Std 802.11ax-2021 + * section 9.4.2.252. */ struct ieee80211_he_spr { u8 he_sr_control; - /* Optional 0 to 19 bytes: depends on @he_sr_control */ u8 optional[]; } __packed; /** * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field + * @aifsn: ACI/AIFSN + * @ecw_min_max: ECWmin/ECWmax + * @mu_edca_timer: MU EDCA Timer * - * This structure is the "MU AC Parameter Record" fields as - * described in P802.11ax_D4.0 section 9.4.2.245 + * This structure represents the "MU AC Parameter Record" as described + * in IEEE Std 802.11ax-2021 section 9.4.2.251, Figure 9-788p. */ struct ieee80211_he_mu_edca_param_ac_rec { u8 aifsn; @@ -1961,9 +2071,14 @@ struct ieee80211_he_mu_edca_param_ac_rec { /** * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element + * @mu_qos_info: QoS Info + * @ac_be: MU AC_BE Parameter Record + * @ac_bk: MU AC_BK Parameter Record + * @ac_vi: MU AC_VI Parameter Record + * @ac_vo: MU AC_VO Parameter Record * - * This structure is the "MU EDCA Parameter Set element" fields as - * described in P802.11ax_D4.0 section 9.4.2.245 + * This structure represents the payload of the "MU EDCA Parameter Set + * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.251. */ struct ieee80211_mu_edca_param_set { u8 mu_qos_info; @@ -2177,9 +2292,9 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, * enum ieee80211_ap_reg_power - regulatory power for a Access Point * * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode - * @IEEE80211_REG_LPI: Indoor Access Point - * @IEEE80211_REG_SP: Standard power Access Point - * @IEEE80211_REG_VLP: Very low power Access Point + * @IEEE80211_REG_LPI_AP: Indoor Access Point + * @IEEE80211_REG_SP_AP: Standard power Access Point + * @IEEE80211_REG_VLP_AP: Very low power Access Point * @IEEE80211_REG_AP_POWER_AFTER_LAST: internal * @IEEE80211_REG_AP_POWER_MAX: maximum value */ @@ -2567,7 +2682,7 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) #define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 /** - * ieee80211_he_6ghz_oper - HE 6 GHz operation Information field + * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field * @primary: primary channel * @control: control flags * @ccfs0: channel center frequency segment 0 @@ -2614,9 +2729,13 @@ enum ieee80211_tx_power_intrpt_type { }; /** - * struct ieee80211_tx_pwr_env + * struct ieee80211_tx_pwr_env - Transmit Power Envelope + * @tx_power_info: Transmit Power Information field + * @tx_power: Maximum Transmit Power field * - * This structure represents the "Transmit Power Envelope element" + * This structure represents the payload of the "Transmit Power + * Envelope element" as described in IEEE Std 802.11ax-2021 section + * 9.4.2.161 */ struct ieee80211_tx_pwr_env { u8 tx_power_info; @@ -4478,7 +4597,7 @@ static inline bool for_each_element_completed(const struct element *element, return (const u8 *)element == (const u8 *)data + datalen; } -/** +/* * RSNX Capabilities: * bits 0-3: Field length (n-1) */ @@ -4721,7 +4840,7 @@ ieee80211_mle_get_bss_param_ch_cnt(const struct ieee80211_multi_link_elem *mle) } /** - * ieee80211_mle_get_eml_sync_delay - returns the medium sync delay + * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay * @data: pointer to the multi link EHT IE * * The element is assumed to be of the correct type (BASIC) and big enough, -- cgit v1.2.3 From 740ebe35bd3f5c4ff8ec60e5e521e47ea8f5492c Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Mon, 21 Aug 2023 15:25:14 -0700 Subject: mptcp: add struct mptcp_sched_ops This patch defines struct mptcp_sched_ops, which has three struct members, name, owner and list, and four function pointers: init(), release() and get_subflow(). The scheduler function get_subflow() have a struct mptcp_sched_data parameter, which contains a reinject flag for retrans or not, a subflows number and a mptcp_subflow_context array. Add the scheduler registering, unregistering and finding functions to add, delete and find a packet scheduler on the global list mptcp_sched_list. Acked-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Link: https://lore.kernel.org/r/20230821-upstream-net-next-20230818-v1-3-0c860fb256a8@kernel.org Signed-off-by: Jakub Kicinski --- include/net/mptcp.h | 21 ++++++++++++++++++++ net/mptcp/Makefile | 2 +- net/mptcp/protocol.h | 3 +++ net/mptcp/sched.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 81 insertions(+), 1 deletion(-) create mode 100644 net/mptcp/sched.c (limited to 'include') diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 3c5c68618fcc..fb996124b3d5 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -96,6 +96,27 @@ struct mptcp_out_options { #endif }; +#define MPTCP_SCHED_NAME_MAX 16 +#define MPTCP_SUBFLOWS_MAX 8 + +struct mptcp_sched_data { + bool reinject; + u8 subflows; + struct mptcp_subflow_context *contexts[MPTCP_SUBFLOWS_MAX]; +}; + +struct mptcp_sched_ops { + int (*get_subflow)(struct mptcp_sock *msk, + struct mptcp_sched_data *data); + + char name[MPTCP_SCHED_NAME_MAX]; + struct module *owner; + struct list_head list; + + void (*init)(struct mptcp_sock *msk); + void (*release)(struct mptcp_sock *msk); +} ____cacheline_aligned_in_smp; + #ifdef CONFIG_MPTCP void mptcp_init(void); diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile index a3829ce548f9..84e531f86b82 100644 --- a/net/mptcp/Makefile +++ b/net/mptcp/Makefile @@ -2,7 +2,7 @@ obj-$(CONFIG_MPTCP) += mptcp.o mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \ - mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o + mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o sched.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index cbf9a9e176b2..985e8f86668d 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -655,6 +655,9 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, void mptcp_info2sockaddr(const struct mptcp_addr_info *info, struct sockaddr_storage *addr, unsigned short family); +struct mptcp_sched_ops *mptcp_sched_find(const char *name); +int mptcp_register_scheduler(struct mptcp_sched_ops *sched); +void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched); static inline bool __tcp_can_send(const struct sock *ssk) { diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c new file mode 100644 index 000000000000..c5d3bbafba71 --- /dev/null +++ b/net/mptcp/sched.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Multipath TCP + * + * Copyright (c) 2022, SUSE. + */ + +#define pr_fmt(fmt) "MPTCP: " fmt + +#include +#include +#include +#include +#include +#include "protocol.h" + +static DEFINE_SPINLOCK(mptcp_sched_list_lock); +static LIST_HEAD(mptcp_sched_list); + +/* Must be called with rcu read lock held */ +struct mptcp_sched_ops *mptcp_sched_find(const char *name) +{ + struct mptcp_sched_ops *sched, *ret = NULL; + + list_for_each_entry_rcu(sched, &mptcp_sched_list, list) { + if (!strcmp(sched->name, name)) { + ret = sched; + break; + } + } + + return ret; +} + +int mptcp_register_scheduler(struct mptcp_sched_ops *sched) +{ + if (!sched->get_subflow) + return -EINVAL; + + spin_lock(&mptcp_sched_list_lock); + if (mptcp_sched_find(sched->name)) { + spin_unlock(&mptcp_sched_list_lock); + return -EEXIST; + } + list_add_tail_rcu(&sched->list, &mptcp_sched_list); + spin_unlock(&mptcp_sched_list_lock); + + pr_debug("%s registered", sched->name); + return 0; +} + +void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched) +{ + spin_lock(&mptcp_sched_list_lock); + list_del_rcu(&sched->list); + spin_unlock(&mptcp_sched_list_lock); +} -- cgit v1.2.3 From eb6603246ab9a3787e9603f0fd6a321b46623e46 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 21 Aug 2023 21:00:02 +0800 Subject: qed/qede: Remove unused declarations Commit 8cd160a29415 ("qede: convert to new udp_tunnel_nic infra") removed qede_udp_tunnel_{add,del}() but not the declarations. Commit 0ebcebbef1cc ("qed: Read device port count from the shmem") removed qed_device_num_engines() but not its declaration. Commit 1e128c81290a ("qed: Add support for hardware offloaded FCoE.") declared but never implemented qed_fcoe_set_pf_params(). Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed.h | 1 - drivers/net/ethernet/qlogic/qede/qede.h | 3 --- include/linux/qed/qed_fcoe_if.h | 3 --- 3 files changed, 7 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index d613095b78e0..1d719726f72b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -909,7 +909,6 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev, u32 min_pf_rate); void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); -int qed_device_num_engines(struct qed_dev *cdev); void qed_set_fw_mac_addr(__le16 *fw_msb, __le16 *fw_mid, __le16 *fw_lsb, u8 *mac); diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 4d83ceebdc49..042a75f34060 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -556,9 +556,6 @@ void qede_config_rx_mode(struct net_device *ndev); void qede_fill_rss_params(struct qede_dev *edev, struct qed_update_vport_rss_params *rss, u8 *update); -void qede_udp_tunnel_add(struct net_device *dev, struct udp_tunnel_info *ti); -void qede_udp_tunnel_del(struct net_device *dev, struct udp_tunnel_info *ti); - int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp); #ifdef CONFIG_DCB diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h index 90e3045b2dcb..0d3b6ed21628 100644 --- a/include/linux/qed/qed_fcoe_if.h +++ b/include/linux/qed/qed_fcoe_if.h @@ -67,9 +67,6 @@ struct qed_fcoe_cb_ops { u32 (*get_login_failures)(void *cookie); }; -void qed_fcoe_set_pf_params(struct qed_dev *cdev, - struct qed_fcoe_pf_params *params); - /** * struct qed_fcoe_ops - qed FCoE operations. * @common: common operations pointer -- cgit v1.2.3 From 71ab55a9af80fcffe1f42b9b8dba4d0e3dd0c351 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Mon, 21 Aug 2023 15:12:15 +0200 Subject: mlx4: Get rid of the mlx4_interface.get_dev callback Simplify the mlx4 driver interface by removing mlx4_get_protocol_dev() and the associated mlx4_interface.get_dev callbacks. This is done in preparation to use an auxiliary bus to model the mlx4 driver structure. The change is motivated by the following situation: * The mlx4_en interface is being initialized by mlx4_en_add() and mlx4_en_activate(). * The latter activate function calls mlx4_en_init_netdev() -> register_netdev() to register a new net_device. * A netdev event NETDEV_REGISTER is raised for the device. * The netdev notififier mlx4_ib_netdev_event() is called and it invokes mlx4_ib_scan_netdevs() -> mlx4_get_protocol_dev() -> mlx4_en_get_netdev() [via mlx4_interface.get_dev]. This chain creates a problem when mlx4_en gets switched to be an auxiliary driver. It contains two device calls which would both need to take a respective device lock. Avoid this situation by updating mlx4_ib_scan_netdevs() to no longer call mlx4_get_protocol_dev() but instead to utilize the information passed in net_device.parent and net_device.dev_port. This data is sufficient to determine that an updated port is one that the mlx4_ib driver should take care of and to keep mlx4_ib_dev.iboe.netdevs up to date. Following that, update mlx4_ib_get_netdev() to also not call mlx4_get_protocol_dev() and instead scan all current netdevs to find find a matching one. Note that mlx4_ib_get_netdev() is called early from ib_register_device() and cannot use data tracked in mlx4_ib_dev.iboe.netdevs which is not at that point yet set. Finally, remove function mlx4_get_protocol_dev() and the mlx4_interface.get_dev callbacks (only mlx4_en_get_netdev()) as they became unused. Signed-off-by: Petr Pavlu Tested-by: Leon Romanovsky Reviewed-by: Leon Romanovsky Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 89 ++++++++++++++-------------- drivers/net/ethernet/mellanox/mlx4/en_main.c | 8 --- drivers/net/ethernet/mellanox/mlx4/intf.c | 21 ------- include/linux/mlx4/driver.h | 3 - 4 files changed, 43 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index b18e9f2adc82..7dd70d778b6b 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -125,12 +125,14 @@ static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, u32 port_num) { struct mlx4_ib_dev *ibdev = to_mdev(device); - struct net_device *dev; + struct net_device *dev, *ret = NULL; rcu_read_lock(); - dev = mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port_num); + for_each_netdev_rcu(&init_net, dev) { + if (dev->dev.parent != ibdev->ib_dev.dev.parent || + dev->dev_port + 1 != port_num) + continue; - if (dev) { if (mlx4_is_bonded(ibdev->dev)) { struct net_device *upper = NULL; @@ -143,11 +145,14 @@ static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, dev = active; } } + + dev_hold(dev); + ret = dev; + break; } - dev_hold(dev); rcu_read_unlock(); - return dev; + return ret; } static int mlx4_ib_update_gids_v1(struct gid_entry *gids, @@ -2319,61 +2324,53 @@ unlock: mutex_unlock(&ibdev->qp1_proxy_lock[port - 1]); } -static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev, - struct net_device *dev, - unsigned long event) +static void mlx4_ib_scan_netdev(struct mlx4_ib_dev *ibdev, + struct net_device *dev, + unsigned long event) { - struct mlx4_ib_iboe *iboe; - int update_qps_port = -1; - int port; + struct mlx4_ib_iboe *iboe = &ibdev->iboe; ASSERT_RTNL(); - iboe = &ibdev->iboe; + if (dev->dev.parent != ibdev->ib_dev.dev.parent) + return; spin_lock_bh(&iboe->lock); - mlx4_foreach_ib_transport_port(port, ibdev->dev) { - - iboe->netdevs[port - 1] = - mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port); - if (dev == iboe->netdevs[port - 1] && - (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER || - event == NETDEV_UP || event == NETDEV_CHANGE)) - update_qps_port = port; + iboe->netdevs[dev->dev_port] = event != NETDEV_UNREGISTER ? dev : NULL; - if (dev == iboe->netdevs[port - 1] && - (event == NETDEV_UP || event == NETDEV_DOWN)) { - enum ib_port_state port_state; - struct ib_event ibev = { }; - - if (ib_get_cached_port_state(&ibdev->ib_dev, port, - &port_state)) - continue; + if (event == NETDEV_UP || event == NETDEV_DOWN) { + enum ib_port_state port_state; + struct ib_event ibev = { }; - if (event == NETDEV_UP && - (port_state != IB_PORT_ACTIVE || - iboe->last_port_state[port - 1] != IB_PORT_DOWN)) - continue; - if (event == NETDEV_DOWN && - (port_state != IB_PORT_DOWN || - iboe->last_port_state[port - 1] != IB_PORT_ACTIVE)) - continue; - iboe->last_port_state[port - 1] = port_state; + if (ib_get_cached_port_state(&ibdev->ib_dev, dev->dev_port + 1, + &port_state)) + goto iboe_out; - ibev.device = &ibdev->ib_dev; - ibev.element.port_num = port; - ibev.event = event == NETDEV_UP ? IB_EVENT_PORT_ACTIVE : - IB_EVENT_PORT_ERR; - ib_dispatch_event(&ibev); - } + if (event == NETDEV_UP && + (port_state != IB_PORT_ACTIVE || + iboe->last_port_state[dev->dev_port] != IB_PORT_DOWN)) + goto iboe_out; + if (event == NETDEV_DOWN && + (port_state != IB_PORT_DOWN || + iboe->last_port_state[dev->dev_port] != IB_PORT_ACTIVE)) + goto iboe_out; + iboe->last_port_state[dev->dev_port] = port_state; + ibev.device = &ibdev->ib_dev; + ibev.element.port_num = dev->dev_port + 1; + ibev.event = event == NETDEV_UP ? IB_EVENT_PORT_ACTIVE : + IB_EVENT_PORT_ERR; + ib_dispatch_event(&ibev); } + +iboe_out: spin_unlock_bh(&iboe->lock); - if (update_qps_port > 0) - mlx4_ib_update_qps(ibdev, dev, update_qps_port); + if (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER || + event == NETDEV_UP || event == NETDEV_CHANGE) + mlx4_ib_update_qps(ibdev, dev, dev->dev_port + 1); } static int mlx4_ib_netdev_event(struct notifier_block *this, @@ -2386,7 +2383,7 @@ static int mlx4_ib_netdev_event(struct notifier_block *this, return NOTIFY_DONE; ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb); - mlx4_ib_scan_netdevs(ibdev, dev, event); + mlx4_ib_scan_netdev(ibdev, dev, event); return NOTIFY_DONE; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index f1259bdb1a29..6a42bec6bd85 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -183,13 +183,6 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev) } } -static void *mlx4_en_get_netdev(struct mlx4_dev *dev, void *ctx, u8 port) -{ - struct mlx4_en_dev *endev = ctx; - - return endev->pndev[port]; -} - static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr, enum mlx4_dev_event event, unsigned long port) { @@ -354,7 +347,6 @@ static struct mlx4_interface mlx4_en_interface = { .add = mlx4_en_add, .remove = mlx4_en_remove, .event = mlx4_en_event, - .get_dev = mlx4_en_get_netdev, .protocol = MLX4_PROT_ETH, .activate = mlx4_en_activate, }; diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 65482f004e50..28d7da925d36 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -245,27 +245,6 @@ void mlx4_unregister_device(struct mlx4_dev *dev) mutex_unlock(&intf_mutex); } -void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port) -{ - struct mlx4_priv *priv = mlx4_priv(dev); - struct mlx4_device_context *dev_ctx; - unsigned long flags; - void *result = NULL; - - spin_lock_irqsave(&priv->ctx_lock, flags); - - list_for_each_entry(dev_ctx, &priv->ctx_list, list) - if (dev_ctx->intf->protocol == proto && dev_ctx->intf->get_dev) { - result = dev_ctx->intf->get_dev(dev, dev_ctx->context, port); - break; - } - - spin_unlock_irqrestore(&priv->ctx_lock, flags); - - return result; -} -EXPORT_SYMBOL_GPL(mlx4_get_protocol_dev); - struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port) { struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 1834c8fad12e..923951e19300 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -59,7 +59,6 @@ struct mlx4_interface { void (*remove)(struct mlx4_dev *dev, void *context); void (*event) (struct mlx4_dev *dev, void *context, enum mlx4_dev_event event, unsigned long param); - void * (*get_dev)(struct mlx4_dev *dev, void *context, u8 port); void (*activate)(struct mlx4_dev *dev, void *context); struct list_head list; enum mlx4_protocol protocol; @@ -88,8 +87,6 @@ struct mlx4_port_map { int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p); -void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port); - struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port); #endif /* MLX4_DRIVER_H */ -- cgit v1.2.3 From 7ba189ac52acab44129f09b302069e5a86fd92c2 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Mon, 21 Aug 2023 15:12:17 +0200 Subject: mlx4: Use 'void *' as the event param of mlx4_dispatch_event() Function mlx4_dispatch_event() takes an 'unsigned long' as its event parameter. The actual value is none (MLX4_DEV_EVENT_CATASTROPHIC_ERROR), a pointer to mlx4_eqe (MLX4_DEV_EVENT_PORT_MGMT_CHANGE), or a 32-bit integer (remaining events). In preparation to switch mlx4_en and mlx4_ib to be an auxiliary device, the mlx4_interface.event callback is replaced with a notifier and function mlx4_dispatch_event() gets updated to invoke atomic_notifier_call_chain(). This requires forwarding the input 'param' value from the former function to the latter. A problem is that the notifier call takes 'void *' as its 'param' value, compared to 'unsigned long' used by mlx4_dispatch_event(). Re-passing the value would need either punning it to 'void *' or passing down the address of the input 'param'. Both approaches create a number of unnecessary casts. Change instead the input 'param' of mlx4_dispatch_event() from 'unsigned long' to 'void *'. A mlx4_eqe pointer can be passed directly, callers using an int value are adjusted to pass its address. Signed-off-by: Petr Pavlu Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 14 ++++++++++---- drivers/net/ethernet/mellanox/mlx4/catas.c | 2 +- drivers/net/ethernet/mellanox/mlx4/cmd.c | 4 ++-- drivers/net/ethernet/mellanox/mlx4/en_main.c | 17 +++++++++++++++-- drivers/net/ethernet/mellanox/mlx4/eq.c | 15 ++++++++------- drivers/net/ethernet/mellanox/mlx4/intf.c | 2 +- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 2 +- include/linux/mlx4/driver.h | 2 +- 8 files changed, 39 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 7dd70d778b6b..2c5fd8174b3c 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -3174,7 +3174,7 @@ void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev, } static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, - enum mlx4_dev_event event, unsigned long param) + enum mlx4_dev_event event, void *param) { struct ib_event ibev; struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr); @@ -3194,10 +3194,16 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, return; } - if (event == MLX4_DEV_EVENT_PORT_MGMT_CHANGE) + switch (event) { + case MLX4_DEV_EVENT_CATASTROPHIC_ERROR: + break; + case MLX4_DEV_EVENT_PORT_MGMT_CHANGE: eqe = (struct mlx4_eqe *)param; - else - p = (int) param; + break; + default: + p = *(int *)param; + break; + } switch (event) { case MLX4_DEV_EVENT_PORT_UP: diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index 0eb7b83637d8..0d8a362c2673 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -194,7 +194,7 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist) mutex_unlock(&persist->device_state_mutex); /* At that step HW was already reset, now notify clients */ - mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0); + mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, NULL); mlx4_cmd_wake_completions(dev); return; diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index c56d2194cbfc..f5b1f8c7834f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2113,7 +2113,7 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, if (MLX4_COMM_CMD_FLR == slave_state[slave].last_cmd) goto inform_slave_state; - mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_SHUTDOWN, slave); + mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_SHUTDOWN, &slave); /* write the version in the event field */ reply |= mlx4_comm_get_version(); @@ -2152,7 +2152,7 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, if (mlx4_master_activate_admin_state(priv, slave)) goto reset_slave; slave_state[slave].active = true; - mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_INIT, slave); + mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_INIT, &slave); break; case MLX4_COMM_CMD_VHCR_POST: if ((slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_EN) && diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index be8ba34c9025..83dae886ade6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -184,10 +184,22 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev) } static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr, - enum mlx4_dev_event event, unsigned long port) + enum mlx4_dev_event event, void *param) { struct mlx4_en_dev *mdev = (struct mlx4_en_dev *) endev_ptr; struct mlx4_en_priv *priv; + int port; + + switch (event) { + case MLX4_DEV_EVENT_CATASTROPHIC_ERROR: + case MLX4_DEV_EVENT_PORT_MGMT_CHANGE: + case MLX4_DEV_EVENT_SLAVE_INIT: + case MLX4_DEV_EVENT_SLAVE_SHUTDOWN: + break; + default: + port = *(int *)param; + break; + } switch (event) { case MLX4_DEV_EVENT_PORT_UP: @@ -205,6 +217,7 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr, mlx4_err(mdev, "Internal error detected, restarting device\n"); break; + case MLX4_DEV_EVENT_PORT_MGMT_CHANGE: case MLX4_DEV_EVENT_SLAVE_INIT: case MLX4_DEV_EVENT_SLAVE_SHUTDOWN: break; @@ -213,7 +226,7 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr, !mdev->pndev[port]) return; mlx4_warn(mdev, "Unhandled event %d for port %d\n", event, - (int) port); + port); } } diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 414e390e6b48..6598b10a9ff4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -501,7 +501,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) int port; int slave = 0; int ret; - u32 flr_slave; + int flr_slave; u8 update_slave_state; int i; enum slave_port_gen_event gen_event; @@ -606,8 +606,8 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) port = be32_to_cpu(eqe->event.port_change.port) >> 28; slaves_port = mlx4_phys_to_slaves_pport(dev, port); if (eqe->subtype == MLX4_PORT_CHANGE_SUBTYPE_DOWN) { - mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_DOWN, - port); + mlx4_dispatch_event( + dev, MLX4_DEV_EVENT_PORT_DOWN, &port); mlx4_priv(dev)->sense.do_sense_port[port] = 1; if (!mlx4_is_master(dev)) break; @@ -647,7 +647,8 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) } } } else { - mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_UP, port); + mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_UP, + &port); mlx4_priv(dev)->sense.do_sense_port[port] = 0; @@ -758,7 +759,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) } spin_unlock_irqrestore(&priv->mfunc.master.slave_state_lock, flags); mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_SHUTDOWN, - flr_slave); + &flr_slave); queue_work(priv->mfunc.master.comm_wq, &priv->mfunc.master.slave_flr_event_work); break; @@ -787,8 +788,8 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) break; case MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT: - mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_MGMT_CHANGE, - (unsigned long) eqe); + mlx4_dispatch_event( + dev, MLX4_DEV_EVENT_PORT_MGMT_CHANGE, eqe); break; case MLX4_EVENT_TYPE_RECOVERABLE_ERROR_EVENT: diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 28d7da925d36..a761971cd0c4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -180,7 +180,7 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable) } void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, - unsigned long param) + void *param) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_device_context *dev_ctx; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 6ccf340660d9..de5699a4ddaa 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -1048,7 +1048,7 @@ int mlx4_restart_one(struct pci_dev *pdev); int mlx4_register_device(struct mlx4_dev *dev); void mlx4_unregister_device(struct mlx4_dev *dev); void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, - unsigned long param); + void *param); struct mlx4_dev_cap; struct mlx4_init_hca_param; diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 923951e19300..032d7f5bfef6 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -58,7 +58,7 @@ struct mlx4_interface { void * (*add) (struct mlx4_dev *dev); void (*remove)(struct mlx4_dev *dev, void *context); void (*event) (struct mlx4_dev *dev, void *context, - enum mlx4_dev_event event, unsigned long param); + enum mlx4_dev_event event, void *param); void (*activate)(struct mlx4_dev *dev, void *context); struct list_head list; enum mlx4_protocol protocol; -- cgit v1.2.3 From 73d68002a02efd370dba6b8fc570427326e36d1a Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Mon, 21 Aug 2023 15:12:18 +0200 Subject: mlx4: Replace the mlx4_interface.event callback with a notifier Use a notifier to implement mlx4_dispatch_event() in preparation to switch mlx4_en and mlx4_ib to be an auxiliary device. A problem is that if the mlx4_interface.event callback was replaced with something as mlx4_adrv.event then the implementation of mlx4_dispatch_event() would need to acquire a lock on a given device before executing this callback. That is necessary because otherwise there is no guarantee that the associated driver cannot get unbound when the callback is running. However, taking this lock is not possible because mlx4_dispatch_event() can be invoked from the hardirq context. Using an atomic notifier allows the driver to accurately record when it wants to receive these events and solves this problem. A handler registration is done by both mlx4_en and mlx4_ib at the end of their mlx4_interface.add callback. This matches the current situation when mlx4_add_device() would enable events for a given device immediately after this callback, by adding the device on the mlx4_priv.list. Signed-off-by: Petr Pavlu Tested-by: Leon Romanovsky Acked-by: Tariq Toukan Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 40 ++++++++++++++++++---------- drivers/infiniband/hw/mlx4/mlx4_ib.h | 2 ++ drivers/net/ethernet/mellanox/mlx4/en_main.c | 26 ++++++++++++------ drivers/net/ethernet/mellanox/mlx4/intf.c | 24 ++++++++++++----- drivers/net/ethernet/mellanox/mlx4/main.c | 2 ++ drivers/net/ethernet/mellanox/mlx4/mlx4.h | 2 ++ drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 ++ include/linux/mlx4/driver.h | 8 ++++-- 8 files changed, 75 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 2c5fd8174b3c..6debee494a16 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -82,6 +82,8 @@ static const char mlx4_ib_version[] = static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init); static enum rdma_link_layer mlx4_ib_port_link_layer(struct ib_device *device, u32 port_num); +static int mlx4_ib_event(struct notifier_block *this, unsigned long event, + void *param); static struct workqueue_struct *wq; @@ -2836,6 +2838,12 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) do_slave_init(ibdev, j, 1); } } + + /* register mlx4 core notifier */ + ibdev->mlx_nb.notifier_call = mlx4_ib_event; + err = mlx4_register_event_notifier(dev, &ibdev->mlx_nb); + WARN(err, "failed to register mlx4 event notifier (%d)", err); + return ibdev; err_notif: @@ -2953,6 +2961,8 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) int p; int i; + mlx4_unregister_event_notifier(dev, &ibdev->mlx_nb); + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) devlink_port_type_clear(mlx4_get_devlink_port(dev, i)); ibdev->ib_active = false; @@ -3173,11 +3183,13 @@ void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev, } } -static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, - enum mlx4_dev_event event, void *param) +static int mlx4_ib_event(struct notifier_block *this, unsigned long event, + void *param) { + struct mlx4_ib_dev *ibdev = + container_of(this, struct mlx4_ib_dev, mlx_nb); + struct mlx4_dev *dev = ibdev->dev; struct ib_event ibev; - struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr); struct mlx4_eqe *eqe = NULL; struct ib_event_work *ew; int p = 0; @@ -3187,11 +3199,11 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, (event == MLX4_DEV_EVENT_PORT_DOWN))) { ew = kmalloc(sizeof(*ew), GFP_ATOMIC); if (!ew) - return; + return NOTIFY_DONE; INIT_WORK(&ew->work, handle_bonded_port_state_event); ew->ib_dev = ibdev; queue_work(wq, &ew->work); - return; + return NOTIFY_DONE; } switch (event) { @@ -3208,7 +3220,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, switch (event) { case MLX4_DEV_EVENT_PORT_UP: if (p > ibdev->num_ports) - return; + return NOTIFY_DONE; if (!mlx4_is_slave(dev) && rdma_port_get_link_layer(&ibdev->ib_dev, p) == IB_LINK_LAYER_INFINIBAND) { @@ -3223,7 +3235,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, case MLX4_DEV_EVENT_PORT_DOWN: if (p > ibdev->num_ports) - return; + return NOTIFY_DONE; ibev.event = IB_EVENT_PORT_ERR; break; @@ -3236,7 +3248,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, case MLX4_DEV_EVENT_PORT_MGMT_CHANGE: ew = kmalloc(sizeof *ew, GFP_ATOMIC); if (!ew) - return; + return NOTIFY_DONE; INIT_WORK(&ew->work, handle_port_mgmt_change_event); memcpy(&ew->ib_eqe, eqe, sizeof *eqe); @@ -3246,7 +3258,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, queue_work(wq, &ew->work); else handle_port_mgmt_change_event(&ew->work); - return; + return NOTIFY_DONE; case MLX4_DEV_EVENT_SLAVE_INIT: /* here, p is the slave id */ @@ -3262,7 +3274,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, 1); } } - return; + return NOTIFY_DONE; case MLX4_DEV_EVENT_SLAVE_SHUTDOWN: if (mlx4_is_master(dev)) { @@ -3278,22 +3290,22 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, } /* here, p is the slave id */ do_slave_init(ibdev, p, 0); - return; + return NOTIFY_DONE; default: - return; + return NOTIFY_DONE; } - ibev.device = ibdev_ptr; + ibev.device = &ibdev->ib_dev; ibev.element.port_num = mlx4_is_bonded(ibdev->dev) ? 1 : (u8)p; ib_dispatch_event(&ibev); + return NOTIFY_DONE; } static struct mlx4_interface mlx4_ib_interface = { .add = mlx4_ib_add, .remove = mlx4_ib_remove, - .event = mlx4_ib_event, .protocol = MLX4_PROT_IB_IPV6, .flags = MLX4_INTFF_BONDING }; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 17fee1e73a45..41ca1114a995 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -38,6 +38,7 @@ #include #include #include +#include #include #include @@ -644,6 +645,7 @@ struct mlx4_ib_dev { spinlock_t reset_flow_resource_lock; struct list_head qp_list; struct mlx4_ib_diag_counters diag_counters[MLX4_DIAG_COUNTERS_TYPES]; + struct notifier_block mlx_nb; }; struct ib_event_work { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index 83dae886ade6..31bf625b8158 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -183,10 +183,12 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev) } } -static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr, - enum mlx4_dev_event event, void *param) +static int mlx4_en_event(struct notifier_block *this, unsigned long event, + void *param) { - struct mlx4_en_dev *mdev = (struct mlx4_en_dev *) endev_ptr; + struct mlx4_en_dev *mdev = + container_of(this, struct mlx4_en_dev, mlx_nb); + struct mlx4_dev *dev = mdev->dev; struct mlx4_en_priv *priv; int port; @@ -205,7 +207,7 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr, case MLX4_DEV_EVENT_PORT_UP: case MLX4_DEV_EVENT_PORT_DOWN: if (!mdev->pndev[port]) - return; + return NOTIFY_DONE; priv = netdev_priv(mdev->pndev[port]); /* To prevent races, we poll the link state in a separate task rather than changing it here */ @@ -224,10 +226,12 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr, default: if (port < 1 || port > dev->caps.num_ports || !mdev->pndev[port]) - return; - mlx4_warn(mdev, "Unhandled event %d for port %d\n", event, + return NOTIFY_DONE; + mlx4_warn(mdev, "Unhandled event %d for port %d\n", (int)event, port); } + + return NOTIFY_DONE; } static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr) @@ -235,6 +239,8 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr) struct mlx4_en_dev *mdev = endev_ptr; int i; + mlx4_unregister_event_notifier(dev, &mdev->mlx_nb); + mutex_lock(&mdev->state_lock); mdev->device_up = false; mutex_unlock(&mdev->state_lock); @@ -276,7 +282,7 @@ static void mlx4_en_activate(struct mlx4_dev *dev, void *ctx) static void *mlx4_en_add(struct mlx4_dev *dev) { struct mlx4_en_dev *mdev; - int i; + int err, i; printk_once(KERN_INFO "%s", mlx4_en_version); @@ -339,6 +345,11 @@ static void *mlx4_en_add(struct mlx4_dev *dev) mutex_init(&mdev->state_lock); mdev->device_up = true; + /* register mlx4 core notifier */ + mdev->mlx_nb.notifier_call = mlx4_en_event; + err = mlx4_register_event_notifier(dev, &mdev->mlx_nb); + WARN(err, "failed to register mlx4 event notifier (%d)", err); + return mdev; err_mr: @@ -359,7 +370,6 @@ err_free_res: static struct mlx4_interface mlx4_en_interface = { .add = mlx4_en_add, .remove = mlx4_en_remove, - .event = mlx4_en_event, .protocol = MLX4_PROT_ETH, .activate = mlx4_en_activate, }; diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index a761971cd0c4..fecb63e69607 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -183,17 +183,27 @@ void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, void *param) { struct mlx4_priv *priv = mlx4_priv(dev); - struct mlx4_device_context *dev_ctx; - unsigned long flags; - spin_lock_irqsave(&priv->ctx_lock, flags); + atomic_notifier_call_chain(&priv->event_nh, type, param); +} - list_for_each_entry(dev_ctx, &priv->ctx_list, list) - if (dev_ctx->intf->event) - dev_ctx->intf->event(dev, dev_ctx->context, type, param); +int mlx4_register_event_notifier(struct mlx4_dev *dev, + struct notifier_block *nb) +{ + struct mlx4_priv *priv = mlx4_priv(dev); - spin_unlock_irqrestore(&priv->ctx_lock, flags); + return atomic_notifier_chain_register(&priv->event_nh, nb); +} +EXPORT_SYMBOL(mlx4_register_event_notifier); + +int mlx4_unregister_event_notifier(struct mlx4_dev *dev, + struct notifier_block *nb) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + return atomic_notifier_chain_unregister(&priv->event_nh, nb); } +EXPORT_SYMBOL(mlx4_unregister_event_notifier); int mlx4_register_device(struct mlx4_dev *dev) { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 8a5409b00530..5f3ba8385e23 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3378,6 +3378,8 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data, INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); + ATOMIC_INIT_NOTIFIER_HEAD(&priv->event_nh); + mutex_init(&priv->port_mutex); mutex_init(&priv->bond_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index de5699a4ddaa..8dbea814a2f5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -878,6 +879,7 @@ struct mlx4_priv { struct list_head dev_list; struct list_head ctx_list; spinlock_t ctx_lock; + struct atomic_notifier_head event_nh; int pci_dev_data; int removed; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 72a3fea36702..efe3f97b874f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -433,6 +434,7 @@ struct mlx4_en_dev { struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_clock_info; struct notifier_block netdev_nb; + struct notifier_block mlx_nb; }; diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 032d7f5bfef6..228da8ed7e75 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -34,6 +34,7 @@ #define MLX4_DRIVER_H #include +#include #include struct mlx4_dev; @@ -57,8 +58,6 @@ enum { struct mlx4_interface { void * (*add) (struct mlx4_dev *dev); void (*remove)(struct mlx4_dev *dev, void *context); - void (*event) (struct mlx4_dev *dev, void *context, - enum mlx4_dev_event event, void *param); void (*activate)(struct mlx4_dev *dev, void *context); struct list_head list; enum mlx4_protocol protocol; @@ -87,6 +86,11 @@ struct mlx4_port_map { int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p); +int mlx4_register_event_notifier(struct mlx4_dev *dev, + struct notifier_block *nb); +int mlx4_unregister_event_notifier(struct mlx4_dev *dev, + struct notifier_block *nb); + struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port); #endif /* MLX4_DRIVER_H */ -- cgit v1.2.3 From 13f857111cb23f2a8dbcd0271c3ff1824913d980 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Mon, 21 Aug 2023 15:12:19 +0200 Subject: mlx4: Get rid of the mlx4_interface.activate callback The mlx4_interface.activate callback was introduced in commit 79857cd31fe7 ("net/mlx4: Postpone the registration of net_device"). It dealt with a situation when a netdev notifier received a NETDEV_REGISTER event for a new net_device created by mlx4_en but the same device was not yet visible to mlx4_get_protocol_dev(). The callback can be removed now that mlx4_get_protocol_dev() is gone. Signed-off-by: Petr Pavlu Tested-by: Leon Romanovsky Reviewed-by: Leon Romanovsky Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_main.c | 37 ++++++++++++---------------- drivers/net/ethernet/mellanox/mlx4/intf.c | 2 -- include/linux/mlx4/driver.h | 1 - 3 files changed, 16 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index 31bf625b8158..39c9befeb638 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -259,26 +259,6 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr) kfree(mdev); } -static void mlx4_en_activate(struct mlx4_dev *dev, void *ctx) -{ - int i; - struct mlx4_en_dev *mdev = ctx; - - /* Create a netdev for each port */ - mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) { - mlx4_info(mdev, "Activating port:%d\n", i); - if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i])) - mdev->pndev[i] = NULL; - } - - /* register netdev notifier */ - mdev->netdev_nb.notifier_call = mlx4_en_netdev_event; - if (register_netdevice_notifier(&mdev->netdev_nb)) { - mdev->netdev_nb.notifier_call = NULL; - mlx4_err(mdev, "Failed to create netdev notifier\n"); - } -} - static void *mlx4_en_add(struct mlx4_dev *dev) { struct mlx4_en_dev *mdev; @@ -350,6 +330,22 @@ static void *mlx4_en_add(struct mlx4_dev *dev) err = mlx4_register_event_notifier(dev, &mdev->mlx_nb); WARN(err, "failed to register mlx4 event notifier (%d)", err); + /* Setup ports */ + + /* Create a netdev for each port */ + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) { + mlx4_info(mdev, "Activating port:%d\n", i); + if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i])) + mdev->pndev[i] = NULL; + } + + /* register netdev notifier */ + mdev->netdev_nb.notifier_call = mlx4_en_netdev_event; + if (register_netdevice_notifier(&mdev->netdev_nb)) { + mdev->netdev_nb.notifier_call = NULL; + mlx4_err(mdev, "Failed to create netdev notifier\n"); + } + return mdev; err_mr: @@ -371,7 +367,6 @@ static struct mlx4_interface mlx4_en_interface = { .add = mlx4_en_add, .remove = mlx4_en_remove, .protocol = MLX4_PROT_ETH, - .activate = mlx4_en_activate, }; static void mlx4_en_verify_params(void) diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index fecb63e69607..8cbc1bcdfe77 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -64,8 +64,6 @@ static void mlx4_add_device(struct mlx4_interface *intf, struct mlx4_priv *priv) spin_lock_irq(&priv->ctx_lock); list_add_tail(&dev_ctx->list, &priv->ctx_list); spin_unlock_irq(&priv->ctx_lock); - if (intf->activate) - intf->activate(&priv->dev, dev_ctx->context); } else kfree(dev_ctx); diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 228da8ed7e75..0f8c9ba4c574 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -58,7 +58,6 @@ enum { struct mlx4_interface { void * (*add) (struct mlx4_dev *dev); void (*remove)(struct mlx4_dev *dev, void *context); - void (*activate)(struct mlx4_dev *dev, void *context); struct list_head list; enum mlx4_protocol protocol; int flags; -- cgit v1.2.3 From e2fb47d4eb5cd245c38c8c57d969ac6b12efc764 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Mon, 21 Aug 2023 15:12:20 +0200 Subject: mlx4: Move the bond work to the core driver Function mlx4_en_queue_bond_work() is used in mlx4_en to start a bond reconfiguration. It gathers data about a new port map setting, takes a reference on the netdev that triggered the change and queues a work object on mlx4_en_priv.mdev.workqueue to perform the operation. The scheduled work is mlx4_en_bond_work() which calls mlx4_bond()/mlx4_unbond() and consequently mlx4_do_bond(). At the same time, function mlx4_change_port_types() in mlx4_core might be invoked to change the port type configuration. As part of its logic, it re-registers the whole device by calling mlx4_unregister_device(), followed by mlx4_register_device(). The two operations can result in concurrent access to the data about currently active interfaces on the device. Functions mlx4_register_device() and mlx4_unregister_device() lock the intf_mutex to gain exclusive access to this data. The current implementation of mlx4_do_bond() doesn't do that which could result in an unexpected behavior. An updated version of mlx4_do_bond() for use with an auxiliary bus goes and locks the intf_mutex when accessing a new auxiliary device array. However, doing so can then result in the following deadlock: * A two-port mlx4 device is configured as an Ethernet bond. * One of the ports is changed from eth to ib, for instance, by writing into a mlx4_port sysfs attribute file. * mlx4_change_port_types() is called to update port types. It invokes mlx4_unregister_device() to unregister the device which locks the intf_mutex and starts removing all associated interfaces. * Function mlx4_en_remove() gets invoked and starts destroying its first netdev. This triggers mlx4_en_netdev_event() which recognizes that the configured bond is broken. It runs mlx4_en_queue_bond_work() which takes a reference on the netdev. Removing the netdev now cannot proceed until the work is completed. * Work function mlx4_en_bond_work() gets scheduled. It calls mlx4_unbond() -> mlx4_do_bond(). The latter function tries to lock the intf_mutex but that is not possible because it is held already by mlx4_unregister_device(). This particular case could be possibly solved by unregistering the mlx4_en_netdev_event() notifier in mlx4_en_remove() earlier, but it seems better to decouple mlx4_en more and break this reference order. Avoid then this scenario by recognizing that the bond reconfiguration operates only on a mlx4_dev. The logic to queue and execute the bond work can be moved into the mlx4_core driver. Only a reference on the respective mlx4_dev object is needed to be taken during the work's lifetime. This removes a call from mlx4_en that can directly result in needing to lock the intf_mutex, it remains a privilege of the core driver. Signed-off-by: Petr Pavlu Tested-by: Leon Romanovsky Reviewed-by: Leon Romanovsky Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 62 +----------------------- drivers/net/ethernet/mellanox/mlx4/main.c | 65 +++++++++++++++++++++++--- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 5 ++ include/linux/mlx4/device.h | 13 ++++++ include/linux/mlx4/driver.h | 19 -------- 5 files changed, 77 insertions(+), 87 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 7066c426b95c..33bbcced8105 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2894,63 +2894,6 @@ static const struct xdp_metadata_ops mlx4_xdp_metadata_ops = { .xmo_rx_hash = mlx4_en_xdp_rx_hash, }; -struct mlx4_en_bond { - struct work_struct work; - struct mlx4_en_priv *priv; - int is_bonded; - struct mlx4_port_map port_map; -}; - -static void mlx4_en_bond_work(struct work_struct *work) -{ - struct mlx4_en_bond *bond = container_of(work, - struct mlx4_en_bond, - work); - int err = 0; - struct mlx4_dev *dev = bond->priv->mdev->dev; - - if (bond->is_bonded) { - if (!mlx4_is_bonded(dev)) { - err = mlx4_bond(dev); - if (err) - en_err(bond->priv, "Fail to bond device\n"); - } - if (!err) { - err = mlx4_port_map_set(dev, &bond->port_map); - if (err) - en_err(bond->priv, "Fail to set port map [%d][%d]: %d\n", - bond->port_map.port1, - bond->port_map.port2, - err); - } - } else if (mlx4_is_bonded(dev)) { - err = mlx4_unbond(dev); - if (err) - en_err(bond->priv, "Fail to unbond device\n"); - } - dev_put(bond->priv->dev); - kfree(bond); -} - -static int mlx4_en_queue_bond_work(struct mlx4_en_priv *priv, int is_bonded, - u8 v2p_p1, u8 v2p_p2) -{ - struct mlx4_en_bond *bond; - - bond = kzalloc(sizeof(*bond), GFP_ATOMIC); - if (!bond) - return -ENOMEM; - - INIT_WORK(&bond->work, mlx4_en_bond_work); - bond->priv = priv; - bond->is_bonded = is_bonded; - bond->port_map.port1 = v2p_p1; - bond->port_map.port2 = v2p_p2; - dev_hold(priv->dev); - queue_work(priv->mdev->workqueue, &bond->work); - return 0; -} - int mlx4_en_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -2960,7 +2903,6 @@ int mlx4_en_netdev_event(struct notifier_block *this, struct mlx4_dev *dev; int i, num_eth_ports = 0; bool do_bond = true; - struct mlx4_en_priv *priv; u8 v2p_port1 = 0; u8 v2p_port2 = 0; @@ -2995,7 +2937,6 @@ int mlx4_en_netdev_event(struct notifier_block *this, if ((do_bond && (event != NETDEV_BONDING_INFO)) || !port) return NOTIFY_DONE; - priv = netdev_priv(ndev); if (do_bond) { struct netdev_notifier_bonding_info *notifier_info = ptr; struct netdev_bonding_info *bonding_info = @@ -3062,8 +3003,7 @@ int mlx4_en_netdev_event(struct notifier_block *this, } } - mlx4_en_queue_bond_work(priv, do_bond, - v2p_port1, v2p_port2); + mlx4_queue_bond_work(dev, do_bond, v2p_port1, v2p_port2); return NOTIFY_DONE; } diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 5f3ba8385e23..0ed490b99163 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1441,7 +1441,7 @@ static int mlx4_mf_unbond(struct mlx4_dev *dev) return ret; } -int mlx4_bond(struct mlx4_dev *dev) +static int mlx4_bond(struct mlx4_dev *dev) { int ret = 0; struct mlx4_priv *priv = mlx4_priv(dev); @@ -1467,9 +1467,8 @@ int mlx4_bond(struct mlx4_dev *dev) return ret; } -EXPORT_SYMBOL_GPL(mlx4_bond); -int mlx4_unbond(struct mlx4_dev *dev) +static int mlx4_unbond(struct mlx4_dev *dev) { int ret = 0; struct mlx4_priv *priv = mlx4_priv(dev); @@ -1496,10 +1495,8 @@ int mlx4_unbond(struct mlx4_dev *dev) return ret; } -EXPORT_SYMBOL_GPL(mlx4_unbond); - -int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p) +static int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p) { u8 port1 = v2p->port1; u8 port2 = v2p->port2; @@ -1541,7 +1538,61 @@ int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p) mutex_unlock(&priv->bond_mutex); return err; } -EXPORT_SYMBOL_GPL(mlx4_port_map_set); + +struct mlx4_bond { + struct work_struct work; + struct mlx4_dev *dev; + int is_bonded; + struct mlx4_port_map port_map; +}; + +static void mlx4_bond_work(struct work_struct *work) +{ + struct mlx4_bond *bond = container_of(work, struct mlx4_bond, work); + int err = 0; + + if (bond->is_bonded) { + if (!mlx4_is_bonded(bond->dev)) { + err = mlx4_bond(bond->dev); + if (err) + mlx4_err(bond->dev, "Fail to bond device\n"); + } + if (!err) { + err = mlx4_port_map_set(bond->dev, &bond->port_map); + if (err) + mlx4_err(bond->dev, + "Fail to set port map [%d][%d]: %d\n", + bond->port_map.port1, + bond->port_map.port2, err); + } + } else if (mlx4_is_bonded(bond->dev)) { + err = mlx4_unbond(bond->dev); + if (err) + mlx4_err(bond->dev, "Fail to unbond device\n"); + } + put_device(&bond->dev->persist->pdev->dev); + kfree(bond); +} + +int mlx4_queue_bond_work(struct mlx4_dev *dev, int is_bonded, u8 v2p_p1, + u8 v2p_p2) +{ + struct mlx4_bond *bond; + + bond = kzalloc(sizeof(*bond), GFP_ATOMIC); + if (!bond) + return -ENOMEM; + + INIT_WORK(&bond->work, mlx4_bond_work); + get_device(&dev->persist->pdev->dev); + bond->dev = dev; + bond->is_bonded = is_bonded; + bond->port_map.port1 = v2p_p1; + bond->port_map.port2 = v2p_p2; + queue_work(mlx4_wq, &bond->work); + return 0; +} +EXPORT_SYMBOL(mlx4_queue_bond_work); static int mlx4_load_fw(struct mlx4_dev *dev) { diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 8dbea814a2f5..73b4fdfd63f4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -863,6 +863,11 @@ struct mlx4_steer { struct list_head steer_entries[MLX4_NUM_STEERS]; }; +struct mlx4_port_map { + u8 port1; + u8 port2; +}; + enum { MLX4_PCI_DEV_IS_VF = 1 << 0, MLX4_PCI_DEV_FORCE_SENSE_PORT = 1 << 1, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6646634a0b9d..049d8a4b044d 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1087,6 +1087,19 @@ static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset) (offset & (PAGE_SIZE - 1)); } +static inline int mlx4_is_bonded(struct mlx4_dev *dev) +{ + return !!(dev->flags & MLX4_FLAG_BONDED); +} + +static inline int mlx4_is_mf_bonded(struct mlx4_dev *dev) +{ + return (mlx4_is_bonded(dev) && mlx4_is_mfunc(dev)); +} + +int mlx4_queue_bond_work(struct mlx4_dev *dev, int is_bonded, u8 v2p_p1, + u8 v2p_p2); + int mlx4_pd_alloc(struct mlx4_dev *dev, u32 *pdn); void mlx4_pd_free(struct mlx4_dev *dev, u32 pdn); int mlx4_xrcd_alloc(struct mlx4_dev *dev, u32 *xrcdn); diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 0f8c9ba4c574..781d5a0c2faa 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -66,25 +66,6 @@ struct mlx4_interface { int mlx4_register_interface(struct mlx4_interface *intf); void mlx4_unregister_interface(struct mlx4_interface *intf); -int mlx4_bond(struct mlx4_dev *dev); -int mlx4_unbond(struct mlx4_dev *dev); -static inline int mlx4_is_bonded(struct mlx4_dev *dev) -{ - return !!(dev->flags & MLX4_FLAG_BONDED); -} - -static inline int mlx4_is_mf_bonded(struct mlx4_dev *dev) -{ - return (mlx4_is_bonded(dev) && mlx4_is_mfunc(dev)); -} - -struct mlx4_port_map { - u8 port1; - u8 port2; -}; - -int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p); - int mlx4_register_event_notifier(struct mlx4_dev *dev, struct notifier_block *nb); int mlx4_unregister_event_notifier(struct mlx4_dev *dev, -- cgit v1.2.3 From 8c2d2b87719bad9c1db4a7919e74f7818a8ca3de Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Mon, 21 Aug 2023 15:12:22 +0200 Subject: mlx4: Register mlx4 devices to an auxiliary virtual bus Add an auxiliary virtual bus to model the mlx4 driver structure. The code is added along the current custom device management logic. Subsequent patches switch mlx4_en and mlx4_ib to the auxiliary bus and the old interface is then removed. Structure mlx4_priv gains a new adev dynamic array to keep track of its auxiliary devices. Access to the array is protected by the global mlx4_intf mutex. Functions mlx4_register_device() and mlx4_unregister_device() are updated to expose auxiliary devices on the bus in order to load mlx4_en and/or mlx4_ib. Functions mlx4_register_auxiliary_driver() and mlx4_unregister_auxiliary_driver() are added to substitute mlx4_register_interface() and mlx4_unregister_interface(), respectively. Function mlx4_do_bond() is adjusted to walk over the adev array and re-adds a specific auxiliary device if its driver sets the MLX4_INTFF_BONDING flag. Signed-off-by: Petr Pavlu Tested-by: Leon Romanovsky Reviewed-by: Leon Romanovsky Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/Kconfig | 1 + drivers/net/ethernet/mellanox/mlx4/intf.c | 230 ++++++++++++++++++++++++++++- drivers/net/ethernet/mellanox/mlx4/main.c | 17 ++- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 6 + include/linux/mlx4/device.h | 7 + include/linux/mlx4/driver.h | 11 ++ 6 files changed, 268 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig index 1b4b1f642317..825e05fb8607 100644 --- a/drivers/net/ethernet/mellanox/mlx4/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig @@ -27,6 +27,7 @@ config MLX4_EN_DCB config MLX4_CORE tristate depends on PCI + select AUXILIARY_BUS select NET_DEVLINK default n diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index d578f754d882..79b1eaa62ac2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -48,6 +48,89 @@ struct mlx4_device_context { static LIST_HEAD(intf_list); static LIST_HEAD(dev_list); static DEFINE_MUTEX(intf_mutex); +static DEFINE_IDA(mlx4_adev_ida); + +static const struct mlx4_adev_device { + const char *suffix; + bool (*is_supported)(struct mlx4_dev *dev); +} mlx4_adev_devices[1] = {}; + +int mlx4_adev_init(struct mlx4_dev *dev) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + priv->adev_idx = ida_alloc(&mlx4_adev_ida, GFP_KERNEL); + if (priv->adev_idx < 0) + return priv->adev_idx; + + priv->adev = kcalloc(ARRAY_SIZE(mlx4_adev_devices), + sizeof(struct mlx4_adev *), GFP_KERNEL); + if (!priv->adev) { + ida_free(&mlx4_adev_ida, priv->adev_idx); + return -ENOMEM; + } + + return 0; +} + +void mlx4_adev_cleanup(struct mlx4_dev *dev) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + kfree(priv->adev); + ida_free(&mlx4_adev_ida, priv->adev_idx); +} + +static void adev_release(struct device *dev) +{ + struct mlx4_adev *mlx4_adev = + container_of(dev, struct mlx4_adev, adev.dev); + struct mlx4_priv *priv = mlx4_priv(mlx4_adev->mdev); + int idx = mlx4_adev->idx; + + kfree(mlx4_adev); + priv->adev[idx] = NULL; +} + +static struct mlx4_adev *add_adev(struct mlx4_dev *dev, int idx) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + const char *suffix = mlx4_adev_devices[idx].suffix; + struct auxiliary_device *adev; + struct mlx4_adev *madev; + int ret; + + madev = kzalloc(sizeof(*madev), GFP_KERNEL); + if (!madev) + return ERR_PTR(-ENOMEM); + + adev = &madev->adev; + adev->id = priv->adev_idx; + adev->name = suffix; + adev->dev.parent = &dev->persist->pdev->dev; + adev->dev.release = adev_release; + madev->mdev = dev; + madev->idx = idx; + + ret = auxiliary_device_init(adev); + if (ret) { + kfree(madev); + return ERR_PTR(ret); + } + + ret = auxiliary_device_add(adev); + if (ret) { + auxiliary_device_uninit(adev); + return ERR_PTR(ret); + } + return madev; +} + +static void del_adev(struct auxiliary_device *adev) +{ + auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); +} static void mlx4_add_device(struct mlx4_interface *intf, struct mlx4_priv *priv) { @@ -120,12 +203,24 @@ void mlx4_unregister_interface(struct mlx4_interface *intf) } EXPORT_SYMBOL_GPL(mlx4_unregister_interface); +int mlx4_register_auxiliary_driver(struct mlx4_adrv *madrv) +{ + return auxiliary_driver_register(&madrv->adrv); +} +EXPORT_SYMBOL_GPL(mlx4_register_auxiliary_driver); + +void mlx4_unregister_auxiliary_driver(struct mlx4_adrv *madrv) +{ + auxiliary_driver_unregister(&madrv->adrv); +} +EXPORT_SYMBOL_GPL(mlx4_unregister_auxiliary_driver); + int mlx4_do_bond(struct mlx4_dev *dev, bool enable) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_device_context *dev_ctx = NULL, *temp_dev_ctx; unsigned long flags; - int ret; + int i, ret; LIST_HEAD(bond_list); if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP)) @@ -177,6 +272,57 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable) dev_ctx->intf->protocol, enable ? "enabled" : "disabled"); } + + mutex_lock(&intf_mutex); + + for (i = 0; i < ARRAY_SIZE(mlx4_adev_devices); i++) { + struct mlx4_adev *madev = priv->adev[i]; + struct mlx4_adrv *madrv; + enum mlx4_protocol protocol; + + if (!madev) + continue; + + device_lock(&madev->adev.dev); + if (!madev->adev.dev.driver) { + device_unlock(&madev->adev.dev); + continue; + } + + madrv = container_of(madev->adev.dev.driver, struct mlx4_adrv, + adrv.driver); + if (!(madrv->flags & MLX4_INTFF_BONDING)) { + device_unlock(&madev->adev.dev); + continue; + } + + if (mlx4_is_mfunc(dev)) { + mlx4_dbg(dev, + "SRIOV, disabled HA mode for intf proto %d\n", + madrv->protocol); + device_unlock(&madev->adev.dev); + continue; + } + + protocol = madrv->protocol; + device_unlock(&madev->adev.dev); + + del_adev(&madev->adev); + priv->adev[i] = add_adev(dev, i); + if (IS_ERR(priv->adev[i])) { + mlx4_warn(dev, "Device[%d] (%s) failed to load\n", i, + mlx4_adev_devices[i].suffix); + priv->adev[i] = NULL; + continue; + } + + mlx4_dbg(dev, + "Interface for protocol %d restarted with bonded mode %s\n", + protocol, enable ? "enabled" : "disabled"); + } + + mutex_unlock(&intf_mutex); + return 0; } @@ -206,10 +352,80 @@ int mlx4_unregister_event_notifier(struct mlx4_dev *dev, } EXPORT_SYMBOL(mlx4_unregister_event_notifier); +static int add_drivers(struct mlx4_dev *dev) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + int i, ret = 0; + + for (i = 0; i < ARRAY_SIZE(mlx4_adev_devices); i++) { + bool is_supported = false; + + if (priv->adev[i]) + continue; + + if (mlx4_adev_devices[i].is_supported) + is_supported = mlx4_adev_devices[i].is_supported(dev); + + if (!is_supported) + continue; + + priv->adev[i] = add_adev(dev, i); + if (IS_ERR(priv->adev[i])) { + mlx4_warn(dev, "Device[%d] (%s) failed to load\n", i, + mlx4_adev_devices[i].suffix); + /* We continue to rescan drivers and leave to the caller + * to make decision if to release everything or + * continue. */ + ret = PTR_ERR(priv->adev[i]); + priv->adev[i] = NULL; + } + } + return ret; +} + +static void delete_drivers(struct mlx4_dev *dev) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + bool delete_all; + int i; + + delete_all = !(dev->persist->interface_state & MLX4_INTERFACE_STATE_UP); + + for (i = ARRAY_SIZE(mlx4_adev_devices) - 1; i >= 0; i--) { + bool is_supported = false; + + if (!priv->adev[i]) + continue; + + if (mlx4_adev_devices[i].is_supported && !delete_all) + is_supported = mlx4_adev_devices[i].is_supported(dev); + + if (is_supported) + continue; + + del_adev(&priv->adev[i]->adev); + priv->adev[i] = NULL; + } +} + +/* This function is used after mlx4_dev is reconfigured. + */ +static int rescan_drivers_locked(struct mlx4_dev *dev) +{ + lockdep_assert_held(&intf_mutex); + + delete_drivers(dev); + if (!(dev->persist->interface_state & MLX4_INTERFACE_STATE_UP)) + return 0; + + return add_drivers(dev); +} + int mlx4_register_device(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_interface *intf; + int ret; mutex_lock(&intf_mutex); @@ -218,10 +434,18 @@ int mlx4_register_device(struct mlx4_dev *dev) list_for_each_entry(intf, &intf_list, list) mlx4_add_device(intf, priv); + ret = rescan_drivers_locked(dev); + mutex_unlock(&intf_mutex); + + if (ret) { + mlx4_unregister_device(dev); + return ret; + } + mlx4_start_catas_poll(dev); - return 0; + return ret; } void mlx4_unregister_device(struct mlx4_dev *dev) @@ -253,6 +477,8 @@ void mlx4_unregister_device(struct mlx4_dev *dev) list_del(&priv->dev_list); dev->persist->interface_state &= ~MLX4_INTERFACE_STATE_UP; + rescan_drivers_locked(dev); + mutex_unlock(&intf_mutex); } diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 0ed490b99163..c4ec7377aa71 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3429,6 +3429,10 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data, INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); + err = mlx4_adev_init(dev); + if (err) + return err; + ATOMIC_INIT_NOTIFIER_HEAD(&priv->event_nh); mutex_init(&priv->port_mutex); @@ -3455,10 +3459,11 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data, err = mlx4_get_ownership(dev); if (err) { if (err < 0) - return err; + goto err_adev; else { mlx4_warn(dev, "Multiple PFs not yet supported - Skipping PF\n"); - return -EINVAL; + err = -EINVAL; + goto err_adev; } } @@ -3806,6 +3811,9 @@ err_sriov: mlx4_free_ownership(dev); kfree(dev_cap); + +err_adev: + mlx4_adev_cleanup(dev); return err; } @@ -4186,6 +4194,8 @@ static void mlx4_unload_one(struct pci_dev *pdev) mlx4_slave_destroy_special_qp_cap(dev); kfree(dev->dev_vfs); + mlx4_adev_cleanup(dev); + mlx4_clean_dev(dev); priv->pci_dev_data = pci_dev_data; priv->removed = 1; @@ -4573,6 +4583,9 @@ static int __init mlx4_init(void) { int ret; + WARN_ONCE(strcmp(MLX4_ADEV_NAME, KBUILD_MODNAME), + "mlx4_core name not in sync with kernel module name"); + if (mlx4_verify_params()) return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 73b4fdfd63f4..36de79c8d053 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -884,6 +885,8 @@ struct mlx4_priv { struct list_head dev_list; struct list_head ctx_list; spinlock_t ctx_lock; + struct mlx4_adev **adev; + int adev_idx; struct atomic_notifier_head event_nh; int pci_dev_data; @@ -1052,6 +1055,9 @@ void mlx4_catas_end(struct mlx4_dev *dev); int mlx4_crdump_init(struct mlx4_dev *dev); void mlx4_crdump_end(struct mlx4_dev *dev); int mlx4_restart_one(struct pci_dev *pdev); + +int mlx4_adev_init(struct mlx4_dev *dev); +void mlx4_adev_cleanup(struct mlx4_dev *dev); int mlx4_register_device(struct mlx4_dev *dev); void mlx4_unregister_device(struct mlx4_dev *dev); void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 049d8a4b044d..27f42f713c89 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -33,6 +33,7 @@ #ifndef MLX4_DEVICE_H #define MLX4_DEVICE_H +#include #include #include #include @@ -889,6 +890,12 @@ struct mlx4_dev { u8 uar_page_shift; }; +struct mlx4_adev { + struct auxiliary_device adev; + struct mlx4_dev *mdev; + int idx; +}; + struct mlx4_clock_params { u64 offset; u8 bar; diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 781d5a0c2faa..9cf157d381c6 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -34,9 +34,12 @@ #define MLX4_DRIVER_H #include +#include #include #include +#define MLX4_ADEV_NAME "mlx4_core" + struct mlx4_dev; #define MLX4_MAC_MASK 0xffffffffffffULL @@ -63,8 +66,16 @@ struct mlx4_interface { int flags; }; +struct mlx4_adrv { + struct auxiliary_driver adrv; + enum mlx4_protocol protocol; + int flags; +}; + int mlx4_register_interface(struct mlx4_interface *intf); void mlx4_unregister_interface(struct mlx4_interface *intf); +int mlx4_register_auxiliary_driver(struct mlx4_adrv *madrv); +void mlx4_unregister_auxiliary_driver(struct mlx4_adrv *madrv); int mlx4_register_event_notifier(struct mlx4_dev *dev, struct notifier_block *nb); -- cgit v1.2.3 From c138cdb89a14ce00d45e77d3db18263e4b9f9465 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Mon, 21 Aug 2023 15:12:25 +0200 Subject: mlx4: Delete custom device management logic After the conversion to use the auxiliary bus, the custom device management is not needed anymore and can be deleted. Signed-off-by: Petr Pavlu Tested-by: Leon Romanovsky Reviewed-by: Leon Romanovsky Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/intf.c | 125 ------------------------------ drivers/net/ethernet/mellanox/mlx4/main.c | 28 ------- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 3 - include/linux/mlx4/driver.h | 10 --- 4 files changed, 166 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 7579031786ac..a371b970ac1e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -38,15 +38,6 @@ #include "mlx4.h" -struct mlx4_device_context { - struct list_head list; - struct list_head bond_list; - struct mlx4_interface *intf; - void *context; -}; - -static LIST_HEAD(intf_list); -static LIST_HEAD(dev_list); static DEFINE_MUTEX(intf_mutex); static DEFINE_IDA(mlx4_adev_ida); @@ -156,77 +147,6 @@ static void del_adev(struct auxiliary_device *adev) auxiliary_device_uninit(adev); } -static void mlx4_add_device(struct mlx4_interface *intf, struct mlx4_priv *priv) -{ - struct mlx4_device_context *dev_ctx; - - dev_ctx = kmalloc(sizeof(*dev_ctx), GFP_KERNEL); - if (!dev_ctx) - return; - - dev_ctx->intf = intf; - dev_ctx->context = intf->add(&priv->dev); - - if (dev_ctx->context) { - spin_lock_irq(&priv->ctx_lock); - list_add_tail(&dev_ctx->list, &priv->ctx_list); - spin_unlock_irq(&priv->ctx_lock); - } else - kfree(dev_ctx); - -} - -static void mlx4_remove_device(struct mlx4_interface *intf, struct mlx4_priv *priv) -{ - struct mlx4_device_context *dev_ctx; - - list_for_each_entry(dev_ctx, &priv->ctx_list, list) - if (dev_ctx->intf == intf) { - spin_lock_irq(&priv->ctx_lock); - list_del(&dev_ctx->list); - spin_unlock_irq(&priv->ctx_lock); - - intf->remove(&priv->dev, dev_ctx->context); - kfree(dev_ctx); - return; - } -} - -int mlx4_register_interface(struct mlx4_interface *intf) -{ - struct mlx4_priv *priv; - - if (!intf->add || !intf->remove) - return -EINVAL; - - mutex_lock(&intf_mutex); - - list_add_tail(&intf->list, &intf_list); - list_for_each_entry(priv, &dev_list, dev_list) { - mlx4_add_device(intf, priv); - } - - mutex_unlock(&intf_mutex); - - return 0; -} -EXPORT_SYMBOL_GPL(mlx4_register_interface); - -void mlx4_unregister_interface(struct mlx4_interface *intf) -{ - struct mlx4_priv *priv; - - mutex_lock(&intf_mutex); - - list_for_each_entry(priv, &dev_list, dev_list) - mlx4_remove_device(intf, priv); - - list_del(&intf->list); - - mutex_unlock(&intf_mutex); -} -EXPORT_SYMBOL_GPL(mlx4_unregister_interface); - int mlx4_register_auxiliary_driver(struct mlx4_adrv *madrv) { return auxiliary_driver_register(&madrv->adrv); @@ -242,10 +162,7 @@ EXPORT_SYMBOL_GPL(mlx4_unregister_auxiliary_driver); int mlx4_do_bond(struct mlx4_dev *dev, bool enable) { struct mlx4_priv *priv = mlx4_priv(dev); - struct mlx4_device_context *dev_ctx = NULL, *temp_dev_ctx; - unsigned long flags; int i, ret; - LIST_HEAD(bond_list); if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP)) return -EOPNOTSUPP; @@ -267,36 +184,6 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable) dev->flags &= ~MLX4_FLAG_BONDED; } - spin_lock_irqsave(&priv->ctx_lock, flags); - list_for_each_entry_safe(dev_ctx, temp_dev_ctx, &priv->ctx_list, list) { - if (!(dev_ctx->intf->flags & MLX4_INTFF_BONDING)) - continue; - - if (mlx4_is_mfunc(dev)) { - mlx4_dbg(dev, - "SRIOV, disabled HA mode for intf proto %d\n", - dev_ctx->intf->protocol); - continue; - } - - list_add_tail(&dev_ctx->bond_list, &bond_list); - list_del(&dev_ctx->list); - } - spin_unlock_irqrestore(&priv->ctx_lock, flags); - - list_for_each_entry(dev_ctx, &bond_list, bond_list) { - dev_ctx->intf->remove(dev, dev_ctx->context); - dev_ctx->context = dev_ctx->intf->add(dev); - - spin_lock_irqsave(&priv->ctx_lock, flags); - list_add_tail(&dev_ctx->list, &priv->ctx_list); - spin_unlock_irqrestore(&priv->ctx_lock, flags); - - mlx4_dbg(dev, "Interface for protocol %d restarted with bonded mode %s\n", - dev_ctx->intf->protocol, enable ? - "enabled" : "disabled"); - } - mutex_lock(&intf_mutex); for (i = 0; i < ARRAY_SIZE(mlx4_adev_devices); i++) { @@ -447,16 +334,11 @@ static int rescan_drivers_locked(struct mlx4_dev *dev) int mlx4_register_device(struct mlx4_dev *dev) { - struct mlx4_priv *priv = mlx4_priv(dev); - struct mlx4_interface *intf; int ret; mutex_lock(&intf_mutex); dev->persist->interface_state |= MLX4_INTERFACE_STATE_UP; - list_add_tail(&priv->dev_list, &dev_list); - list_for_each_entry(intf, &intf_list, list) - mlx4_add_device(intf, priv); ret = rescan_drivers_locked(dev); @@ -474,9 +356,6 @@ int mlx4_register_device(struct mlx4_dev *dev) void mlx4_unregister_device(struct mlx4_dev *dev) { - struct mlx4_priv *priv = mlx4_priv(dev); - struct mlx4_interface *intf; - if (!(dev->persist->interface_state & MLX4_INTERFACE_STATE_UP)) return; @@ -495,10 +374,6 @@ void mlx4_unregister_device(struct mlx4_dev *dev) } mutex_lock(&intf_mutex); - list_for_each_entry(intf, &intf_list, list) - mlx4_remove_device(intf, priv); - - list_del(&priv->dev_list); dev->persist->interface_state &= ~MLX4_INTERFACE_STATE_UP; rescan_drivers_locked(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index c4ec7377aa71..2581226836b5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -42,7 +42,6 @@ #include #include #include -#include #include #include @@ -1091,27 +1090,6 @@ free_mem: return err; } -static void mlx4_request_modules(struct mlx4_dev *dev) -{ - int port; - int has_ib_port = false; - int has_eth_port = false; -#define EN_DRV_NAME "mlx4_en" -#define IB_DRV_NAME "mlx4_ib" - - for (port = 1; port <= dev->caps.num_ports; port++) { - if (dev->caps.port_type[port] == MLX4_PORT_TYPE_IB) - has_ib_port = true; - else if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) - has_eth_port = true; - } - - if (has_eth_port) - request_module_nowait(EN_DRV_NAME); - if (has_ib_port || (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE)) - request_module_nowait(IB_DRV_NAME); -} - /* * Change the port configuration of the device. * Every user of this function must hold the port mutex. @@ -1147,7 +1125,6 @@ int mlx4_change_port_types(struct mlx4_dev *dev, mlx4_err(dev, "Failed to register device\n"); goto out; } - mlx4_request_modules(dev); } out: @@ -3426,9 +3403,6 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data, devl_assert_locked(devlink); dev = &priv->dev; - INIT_LIST_HEAD(&priv->ctx_list); - spin_lock_init(&priv->ctx_lock); - err = mlx4_adev_init(dev); if (err) return err; @@ -3732,8 +3706,6 @@ slave_start: if (err) goto err_port; - mlx4_request_modules(dev); - mlx4_sense_init(dev); mlx4_start_sense(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 36de79c8d053..d7d856d1758a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -882,9 +882,6 @@ enum { struct mlx4_priv { struct mlx4_dev dev; - struct list_head dev_list; - struct list_head ctx_list; - spinlock_t ctx_lock; struct mlx4_adev **adev; int adev_idx; struct atomic_notifier_head event_nh; diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 9cf157d381c6..69825223081f 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -58,22 +58,12 @@ enum { MLX4_INTFF_BONDING = 1 << 0 }; -struct mlx4_interface { - void * (*add) (struct mlx4_dev *dev); - void (*remove)(struct mlx4_dev *dev, void *context); - struct list_head list; - enum mlx4_protocol protocol; - int flags; -}; - struct mlx4_adrv { struct auxiliary_driver adrv; enum mlx4_protocol protocol; int flags; }; -int mlx4_register_interface(struct mlx4_interface *intf); -void mlx4_unregister_interface(struct mlx4_interface *intf); int mlx4_register_auxiliary_driver(struct mlx4_adrv *madrv); void mlx4_unregister_auxiliary_driver(struct mlx4_adrv *madrv); -- cgit v1.2.3 From 59da9885767a75df697c84c06aaf2296e10d85a4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 23 Aug 2023 10:56:32 +0200 Subject: net: dsa: use capital "OR" for multiple licenses in SPDX Documentation/process/license-rules.rst and checkpatch expect the SPDX identifier syntax for multiple licenses to use capital "OR". Correct it to keep consistent format and avoid copy-paste issues. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Kurt Kanzenbach Reviewed-by: FLorian Fainelli Link: https://lore.kernel.org/r/20230823085632.116725-1-krzysztof.kozlowski@linaro.org Signed-off-by: Jakub Kicinski --- drivers/net/dsa/b53/b53_serdes.c | 2 +- drivers/net/dsa/b53/b53_serdes.h | 2 +- drivers/net/dsa/hirschmann/hellcreek.c | 2 +- drivers/net/dsa/hirschmann/hellcreek.h | 2 +- include/linux/platform_data/hirschmann-hellcreek.h | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c index b0ccebcd3ffa..3f8a491ce885 100644 --- a/drivers/net/dsa/b53/b53_serdes.c +++ b/drivers/net/dsa/b53/b53_serdes.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Northstar Plus switch SerDes/SGMII PHY main logic * diff --git a/drivers/net/dsa/b53/b53_serdes.h b/drivers/net/dsa/b53/b53_serdes.h index ef81f5da5f81..3d367c4df4d9 100644 --- a/drivers/net/dsa/b53/b53_serdes.h +++ b/drivers/net/dsa/b53/b53_serdes.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* * Northstar Plus switch SerDes/SGMII PHY definitions * diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 720f4e4ed0b0..11ef1d7ea229 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: (GPL-2.0 or MIT) +// SPDX-License-Identifier: (GPL-2.0 OR MIT) /* * DSA driver for: * Hirschmann Hellcreek TSN switch. diff --git a/drivers/net/dsa/hirschmann/hellcreek.h b/drivers/net/dsa/hirschmann/hellcreek.h index 4a678f7d61ae..6874cb9dc361 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.h +++ b/drivers/net/dsa/hirschmann/hellcreek.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 or MIT) */ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ /* * DSA driver for: * Hirschmann Hellcreek TSN switch. diff --git a/include/linux/platform_data/hirschmann-hellcreek.h b/include/linux/platform_data/hirschmann-hellcreek.h index 6a000df5541f..8748680e9e3c 100644 --- a/include/linux/platform_data/hirschmann-hellcreek.h +++ b/include/linux/platform_data/hirschmann-hellcreek.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 or MIT) */ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ /* * Hirschmann Hellcreek TSN switch platform data. * -- cgit v1.2.3 From fbdc4bc47268953c80853489f696e02d61f9a2c6 Mon Sep 17 00:00:00 2001 From: Iulia Tanasescu Date: Thu, 17 Aug 2023 09:44:27 +0300 Subject: Bluetooth: ISO: Use defer setup to separate PA sync and BIG sync This commit implements defer setup support for the Broadcast Sink scenario: By setting defer setup on a broadcast socket before calling listen, the user is able to trigger the PA sync and BIG sync procedures separately. This is useful if the user first wants to synchronize to the periodic advertising transmitted by a Broadcast Source, and trigger the BIG sync procedure later on. If defer setup is set, once a PA sync established event arrives, a new hcon is created and notified to the ISO layer. A child socket associated with the PA sync connection will be added to the accept queue of the listening socket. Once the accept call returns the fd for the PA sync child socket, the user should call read on that fd. This will trigger the BIG create sync procedure, and the PA sync socket will become a listening socket itself. When the BIG sync established event is notified to the ISO layer, the bis connections will be added to the accept queue of the PA sync parent. The user should call accept on the PA sync socket to get the final bis connections. Signed-off-by: Iulia Tanasescu Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 30 +++++++- net/bluetooth/hci_conn.c | 13 +++- net/bluetooth/hci_event.c | 41 +++++++++- net/bluetooth/hci_sync.c | 15 ++++ net/bluetooth/iso.c | 160 +++++++++++++++++++++++++++++++-------- 5 files changed, 218 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index c53d74236e3a..6fb055e3c595 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -978,6 +978,8 @@ enum { HCI_CONN_CREATE_CIS, HCI_CONN_BIG_SYNC, HCI_CONN_BIG_SYNC_FAILED, + HCI_CONN_PA_SYNC, + HCI_CONN_PA_SYNC_FAILED, }; static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) @@ -1300,7 +1302,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_big_any_dst(struct hci_dev * if (c->type != ISO_LINK) continue; - if (handle == c->iso_qos.bcast.big) { + if (handle != BT_ISO_QOS_BIG_UNSET && handle == c->iso_qos.bcast.big) { rcu_read_unlock(); return c; } @@ -1311,6 +1313,29 @@ static inline struct hci_conn *hci_conn_hash_lookup_big_any_dst(struct hci_dev * return NULL; } +static inline struct hci_conn * +hci_conn_hash_lookup_pa_sync(struct hci_dev *hdev, __u8 big) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type != ISO_LINK || + !test_bit(HCI_CONN_PA_SYNC, &c->flags)) + continue; + + if (c->iso_qos.bcast.big == big) { + rcu_read_unlock(); + return c; + } + } + rcu_read_unlock(); + + return NULL; +} + static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev, __u8 type, __u16 state) { @@ -1435,7 +1460,8 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 data_len, __u8 *data); int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, __u8 sid, struct bt_iso_qos *qos); -int hci_le_big_create_sync(struct hci_dev *hdev, struct bt_iso_qos *qos, +int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, + struct bt_iso_qos *qos, __u16 sync_handle, __u8 num_bis, __u8 bis[]); int hci_conn_check_link_mode(struct hci_conn *conn); int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 95339623883c..8b0c8e631324 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -734,6 +734,7 @@ struct iso_list_data { }; int count; bool big_term; + bool pa_sync_term; bool big_sync_term; }; @@ -807,7 +808,10 @@ static int big_terminate_sync(struct hci_dev *hdev, void *data) if (d->big_sync_term) hci_le_big_terminate_sync(hdev, d->big); - return hci_le_pa_terminate_sync(hdev, d->sync_handle); + if (d->pa_sync_term) + return hci_le_pa_terminate_sync(hdev, d->sync_handle); + + return 0; } static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn) @@ -823,6 +827,7 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c d->big = big; d->sync_handle = conn->sync_handle; + d->pa_sync_term = test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags); d->big_sync_term = test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags); ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, @@ -2099,7 +2104,8 @@ int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, return hci_cmd_sync_queue(hdev, create_pa_sync, cp, create_pa_complete); } -int hci_le_big_create_sync(struct hci_dev *hdev, struct bt_iso_qos *qos, +int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, + struct bt_iso_qos *qos, __u16 sync_handle, __u8 num_bis, __u8 bis[]) { struct _packed { @@ -2115,6 +2121,9 @@ int hci_le_big_create_sync(struct hci_dev *hdev, struct bt_iso_qos *qos, if (err) return err; + if (hcon) + hcon->iso_qos.bcast.big = qos->bcast.big; + memset(&pdu, 0, sizeof(pdu)); pdu.cp.handle = qos->bcast.big; pdu.cp.sync_handle = cpu_to_le16(sync_handle); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 559b6080706c..b4b72070f5f6 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6581,20 +6581,39 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data, struct hci_ev_le_pa_sync_established *ev = data; int mask = hdev->link_mode; __u8 flags = 0; + struct hci_conn *bis; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - if (ev->status) - return; - hci_dev_lock(hdev); hci_dev_clear_flag(hdev, HCI_PA_SYNC); mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ISO_LINK, &flags); - if (!(mask & HCI_LM_ACCEPT)) + if (!(mask & HCI_LM_ACCEPT)) { hci_le_pa_term_sync(hdev, ev->handle); + goto unlock; + } + + if (!(flags & HCI_PROTO_DEFER)) + goto unlock; + + /* Add connection to indicate the PA sync event */ + bis = hci_conn_add(hdev, ISO_LINK, BDADDR_ANY, + HCI_ROLE_SLAVE); + if (!bis) + goto unlock; + + if (ev->status) + set_bit(HCI_CONN_PA_SYNC_FAILED, &bis->flags); + else + set_bit(HCI_CONN_PA_SYNC, &bis->flags); + + /* Notify connection to iso layer */ + hci_connect_cfm(bis, ev->status); + +unlock: hci_dev_unlock(hdev); } @@ -7045,6 +7064,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, { struct hci_evt_le_big_sync_estabilished *ev = data; struct hci_conn *bis; + struct hci_conn *pa_sync; int i; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -7055,6 +7075,15 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); + if (!ev->status) { + pa_sync = hci_conn_hash_lookup_pa_sync(hdev, ev->handle); + if (pa_sync) + /* Also mark the BIG sync established event on the + * associated PA sync hcon + */ + set_bit(HCI_CONN_BIG_SYNC, &pa_sync->flags); + } + for (i = 0; i < ev->num_bis; i++) { u16 handle = le16_to_cpu(ev->bis[i]); __le32 interval; @@ -7068,6 +7097,10 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis->handle = handle; } + if (ev->status != 0x42) + /* Mark PA sync as established */ + set_bit(HCI_CONN_PA_SYNC, &bis->flags); + bis->iso_qos.bcast.big = ev->handle; memset(&interval, 0, sizeof(interval)); memcpy(&interval, ev->latency, sizeof(ev->latency)); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index d10a0f36b947..0cb780817198 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -5384,6 +5384,21 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) err = hci_reject_conn_sync(hdev, conn, reason); break; case BT_OPEN: + hci_dev_lock(hdev); + + /* Cleanup bis or pa sync connections */ + if (test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags) || + test_and_clear_bit(HCI_CONN_PA_SYNC_FAILED, &conn->flags)) { + hci_conn_failed(conn, reason); + } else if (test_bit(HCI_CONN_PA_SYNC, &conn->flags) || + test_bit(HCI_CONN_BIG_SYNC, &conn->flags)) { + conn->state = BT_CLOSED; + hci_disconn_cfm(conn, reason); + hci_conn_del(conn); + } + + hci_dev_unlock(hdev); + return 0; case BT_BOUND: hci_dev_lock(hdev); hci_conn_failed(conn, reason); diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 3c03e49422c7..2a2c37789e1f 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -51,6 +51,7 @@ static void iso_sock_kill(struct sock *sk); /* iso_pinfo flags values */ enum { BT_SK_BIG_SYNC, + BT_SK_PA_SYNC, }; struct iso_pinfo { @@ -75,6 +76,8 @@ static struct bt_iso_qos default_qos; static bool check_ucast_qos(struct bt_iso_qos *qos); static bool check_bcast_qos(struct bt_iso_qos *qos); +static bool iso_match_sid(struct sock *sk, void *data); +static void iso_sock_disconn(struct sock *sk); /* ---- ISO timers ---- */ #define ISO_CONN_TIMEOUT (HZ * 40) @@ -598,6 +601,15 @@ static void iso_sock_cleanup_listen(struct sock *parent) iso_sock_kill(sk); } + /* If listening socket stands for a PA sync connection, + * properly disconnect the hcon and socket. + */ + if (iso_pi(parent)->conn && iso_pi(parent)->conn->hcon && + test_bit(HCI_CONN_PA_SYNC, &iso_pi(parent)->conn->hcon->flags)) { + iso_sock_disconn(parent); + return; + } + parent->sk_state = BT_CLOSED; sock_set_flag(parent, SOCK_ZAPPED); } @@ -619,6 +631,16 @@ static void iso_sock_kill(struct sock *sk) sock_put(sk); } +static void iso_sock_disconn(struct sock *sk) +{ + sk->sk_state = BT_DISCONN; + iso_sock_set_timer(sk, ISO_DISCONN_TIMEOUT); + iso_conn_lock(iso_pi(sk)->conn); + hci_conn_drop(iso_pi(sk)->conn->hcon); + iso_pi(sk)->conn->hcon = NULL; + iso_conn_unlock(iso_pi(sk)->conn); +} + static void __iso_sock_close(struct sock *sk) { BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket); @@ -631,20 +653,19 @@ static void __iso_sock_close(struct sock *sk) case BT_CONNECT: case BT_CONNECTED: case BT_CONFIG: - if (iso_pi(sk)->conn->hcon) { - sk->sk_state = BT_DISCONN; - iso_sock_set_timer(sk, ISO_DISCONN_TIMEOUT); - iso_conn_lock(iso_pi(sk)->conn); - hci_conn_drop(iso_pi(sk)->conn->hcon); - iso_pi(sk)->conn->hcon = NULL; - iso_conn_unlock(iso_pi(sk)->conn); - } else { + if (iso_pi(sk)->conn->hcon) + iso_sock_disconn(sk); + else iso_chan_del(sk, ECONNRESET); - } break; case BT_CONNECT2: - iso_chan_del(sk, ECONNRESET); + if (iso_pi(sk)->conn->hcon && + (test_bit(HCI_CONN_PA_SYNC, &iso_pi(sk)->conn->hcon->flags) || + test_bit(HCI_CONN_PA_SYNC_FAILED, &iso_pi(sk)->conn->hcon->flags))) + iso_sock_disconn(sk); + else + iso_chan_del(sk, ECONNRESET); break; case BT_DISCONN: iso_chan_del(sk, ECONNRESET); @@ -1139,6 +1160,29 @@ static void iso_conn_defer_accept(struct hci_conn *conn) hci_send_cmd(hdev, HCI_OP_LE_ACCEPT_CIS, sizeof(cp), &cp); } +static void iso_conn_big_sync(struct sock *sk) +{ + int err; + struct hci_dev *hdev; + + hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src, + iso_pi(sk)->src_type); + + if (!hdev) + return; + + if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { + err = hci_le_big_create_sync(hdev, iso_pi(sk)->conn->hcon, + &iso_pi(sk)->qos, + iso_pi(sk)->sync_handle, + iso_pi(sk)->bc_num_bis, + iso_pi(sk)->bc_bis); + if (err) + bt_dev_err(hdev, "hci_le_big_create_sync: %d", + err); + } +} + static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { @@ -1151,8 +1195,15 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); switch (sk->sk_state) { case BT_CONNECT2: - iso_conn_defer_accept(pi->conn->hcon); - sk->sk_state = BT_CONFIG; + if (pi->conn->hcon && + test_bit(HCI_CONN_PA_SYNC, &pi->conn->hcon->flags)) { + iso_conn_big_sync(sk); + sk->sk_state = BT_LISTEN; + set_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags); + } else { + iso_conn_defer_accept(pi->conn->hcon); + sk->sk_state = BT_CONFIG; + } release_sock(sk); return 0; case BT_CONNECT: @@ -1513,11 +1564,17 @@ static bool iso_match_big(struct sock *sk, void *data) return ev->handle == iso_pi(sk)->qos.bcast.big; } +static bool iso_match_pa_sync_flag(struct sock *sk, void *data) +{ + return test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags); +} + static void iso_conn_ready(struct iso_conn *conn) { - struct sock *parent; + struct sock *parent = NULL; struct sock *sk = conn->sk; - struct hci_ev_le_big_sync_estabilished *ev; + struct hci_ev_le_big_sync_estabilished *ev = NULL; + struct hci_ev_le_pa_sync_established *ev2 = NULL; struct hci_conn *hcon; BT_DBG("conn %p", conn); @@ -1529,15 +1586,32 @@ static void iso_conn_ready(struct iso_conn *conn) if (!hcon) return; - ev = hci_recv_event_data(hcon->hdev, - HCI_EVT_LE_BIG_SYNC_ESTABILISHED); - if (ev) + if (test_bit(HCI_CONN_BIG_SYNC, &hcon->flags) || + test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) { + ev = hci_recv_event_data(hcon->hdev, + HCI_EVT_LE_BIG_SYNC_ESTABILISHED); + + /* Get reference to PA sync parent socket, if it exists */ parent = iso_get_sock_listen(&hcon->src, &hcon->dst, - iso_match_big, ev); - else + iso_match_pa_sync_flag, NULL); + if (!parent && ev) + parent = iso_get_sock_listen(&hcon->src, + &hcon->dst, + iso_match_big, ev); + } else if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags) || + test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { + ev2 = hci_recv_event_data(hcon->hdev, + HCI_EV_LE_PA_SYNC_ESTABLISHED); + if (ev2) + parent = iso_get_sock_listen(&hcon->src, + &hcon->dst, + iso_match_sid, ev2); + } + + if (!parent) parent = iso_get_sock_listen(&hcon->src, - BDADDR_ANY, NULL, NULL); + BDADDR_ANY, NULL, NULL); if (!parent) return; @@ -1554,11 +1628,17 @@ static void iso_conn_ready(struct iso_conn *conn) iso_sock_init(sk, parent); bacpy(&iso_pi(sk)->src, &hcon->src); - iso_pi(sk)->src_type = hcon->src_type; + + /* Convert from HCI to three-value type */ + if (hcon->src_type == ADDR_LE_DEV_PUBLIC) + iso_pi(sk)->src_type = BDADDR_LE_PUBLIC; + else + iso_pi(sk)->src_type = BDADDR_LE_RANDOM; /* If hcon has no destination address (BDADDR_ANY) it means it - * was created by HCI_EV_LE_BIG_SYNC_ESTABILISHED so we need to - * initialize using the parent socket destination address. + * was created by HCI_EV_LE_BIG_SYNC_ESTABILISHED or + * HCI_EV_LE_PA_SYNC_ESTABLISHED so we need to initialize using + * the parent socket destination address. */ if (!bacmp(&hcon->dst, BDADDR_ANY)) { bacpy(&hcon->dst, &iso_pi(parent)->dst); @@ -1566,13 +1646,21 @@ static void iso_conn_ready(struct iso_conn *conn) hcon->sync_handle = iso_pi(parent)->sync_handle; } + if (ev2 && !ev2->status) { + iso_pi(sk)->sync_handle = iso_pi(parent)->sync_handle; + iso_pi(sk)->qos = iso_pi(parent)->qos; + iso_pi(sk)->bc_num_bis = iso_pi(parent)->bc_num_bis; + memcpy(iso_pi(sk)->bc_bis, iso_pi(parent)->bc_bis, ISO_MAX_NUM_BIS); + } + bacpy(&iso_pi(sk)->dst, &hcon->dst); iso_pi(sk)->dst_type = hcon->dst_type; hci_conn_hold(hcon); iso_chan_add(conn, sk, parent); - if (ev && ((struct hci_evt_le_big_sync_estabilished *)ev)->status) { + if ((ev && ((struct hci_evt_le_big_sync_estabilished *)ev)->status) || + (ev2 && ev2->status)) { /* Trigger error signal on child socket */ sk->sk_err = ECONNREFUSED; sk->sk_error_report(sk); @@ -1630,7 +1718,7 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) if (ev1) { sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, iso_match_sid, ev1); - if (sk) + if (sk && !ev1->status) iso_pi(sk)->sync_handle = le16_to_cpu(ev1->handle); goto done; @@ -1638,16 +1726,21 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) ev2 = hci_recv_event_data(hdev, HCI_EVT_LE_BIG_INFO_ADV_REPORT); if (ev2) { + /* Try to get PA sync listening socket, if it exists */ sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, - iso_match_sync_handle, ev2); + iso_match_pa_sync_flag, NULL); + if (!sk) + sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, + iso_match_sync_handle, ev2); if (sk) { int err; if (ev2->num_bis < iso_pi(sk)->bc_num_bis) iso_pi(sk)->bc_num_bis = ev2->num_bis; - if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { - err = hci_le_big_create_sync(hdev, + if (!test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) && + !test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { + err = hci_le_big_create_sync(hdev, NULL, &iso_pi(sk)->qos, iso_pi(sk)->sync_handle, iso_pi(sk)->bc_num_bis, @@ -1699,12 +1792,13 @@ static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); - /* Similar to the success case, if HCI_CONN_BIG_SYNC_FAILED is set, - * queue the failed bis connection into the accept queue of the - * listening socket and wake up userspace, to inform the user about - * the BIG sync failed event. + /* Similar to the success case, if HCI_CONN_BIG_SYNC_FAILED or + * HCI_CONN_PA_SYNC_FAILED is set, queue the failed connection + * into the accept queue of the listening socket and wake up + * userspace, to inform the user about the event. */ - if (!status || test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) { + if (!status || test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags) || + test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { struct iso_conn *conn; conn = iso_conn_add(hcon); -- cgit v1.2.3 From db08722fc7d46168fe31d9b8a7b29229dd959f9f Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 18 Aug 2023 14:19:27 -0700 Subject: Bluetooth: hci_core: Fix missing instances using HCI_MAX_AD_LENGTH There a few instances still using HCI_MAX_AD_LENGTH instead of using max_adv_len which takes care of detecting what is the actual maximum length depending on if the controller supports EA or not. Fixes: 112b5090c219 ("Bluetooth: MGMT: Fix always using HCI_MAX_AD_LENGTH") Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 6 +++--- net/bluetooth/eir.c | 2 +- net/bluetooth/mgmt.c | 6 +++--- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 6fb055e3c595..6e2988b11f99 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -83,7 +83,7 @@ struct discovery_state { u8 last_adv_addr_type; s8 last_adv_rssi; u32 last_adv_flags; - u8 last_adv_data[HCI_MAX_AD_LENGTH]; + u8 last_adv_data[HCI_MAX_EXT_AD_LENGTH]; u8 last_adv_data_len; bool report_invalid_rssi; bool result_filtering; @@ -290,7 +290,7 @@ struct adv_pattern { __u8 ad_type; __u8 offset; __u8 length; - __u8 value[HCI_MAX_AD_LENGTH]; + __u8 value[HCI_MAX_EXT_AD_LENGTH]; }; struct adv_rssi_thresholds { @@ -726,7 +726,7 @@ struct hci_conn { __u16 le_conn_interval; __u16 le_conn_latency; __u16 le_supv_timeout; - __u8 le_adv_data[HCI_MAX_AD_LENGTH]; + __u8 le_adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 le_adv_data_len; __u8 le_per_adv_data[HCI_MAX_PER_AD_LENGTH]; __u8 le_per_adv_data_len; diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c index 8a85f6cdfbc1..9214189279e8 100644 --- a/net/bluetooth/eir.c +++ b/net/bluetooth/eir.c @@ -33,7 +33,7 @@ u8 eir_append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len) size_t complete_len; /* no space left for name (+ NULL + type + len) */ - if ((HCI_MAX_AD_LENGTH - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3) + if ((max_adv_len(hdev) - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3) return ad_len; /* use complete name if present and fits */ diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d6c9b7bc8592..ba2e00646e8e 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -5381,9 +5381,9 @@ static u8 parse_adv_monitor_pattern(struct adv_monitor *m, u8 pattern_count, for (i = 0; i < pattern_count; i++) { offset = patterns[i].offset; length = patterns[i].length; - if (offset >= HCI_MAX_AD_LENGTH || - length > HCI_MAX_AD_LENGTH || - (offset + length) > HCI_MAX_AD_LENGTH) + if (offset >= HCI_MAX_EXT_AD_LENGTH || + length > HCI_MAX_EXT_AD_LENGTH || + (offset + length) > HCI_MAX_EXT_AD_LENGTH) return MGMT_STATUS_INVALID_PARAMS; p = kmalloc(sizeof(*p), GFP_KERNEL); -- cgit v1.2.3 From 9c0826310bfb784c9bac7d1d9454e304185446c5 Mon Sep 17 00:00:00 2001 From: Claudia Draghicescu Date: Fri, 30 Jun 2023 12:59:28 +0300 Subject: Bluetooth: ISO: Add support for periodic adv reports processing In the case of a Periodic Synchronized Receiver, the PA report received from a Broadcaster contains the BASE, which has information about codec and other parameters of a BIG. This isnformation is stored and the application can retrieve it using getsockopt(BT_ISO_BASE). Signed-off-by: Claudia Draghicescu Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci.h | 11 +++++++++++ net/bluetooth/hci_event.c | 23 +++++++++++++++++++++++ net/bluetooth/iso.c | 28 +++++++++++++++++++++++++++- 3 files changed, 61 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 5723405b833e..c58425d4c592 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -2771,6 +2771,17 @@ struct hci_ev_le_enh_conn_complete { __u8 clk_accurancy; } __packed; +#define HCI_EV_LE_PER_ADV_REPORT 0x0f +struct hci_ev_le_per_adv_report { + __le16 sync_handle; + __u8 tx_power; + __u8 rssi; + __u8 cte_type; + __u8 data_status; + __u8 length; + __u8 data[]; +} __packed; + #define HCI_EV_LE_EXT_ADV_SET_TERM 0x12 struct hci_evt_le_ext_adv_set_term { __u8 status; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index b4b72070f5f6..35f251041eeb 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6617,6 +6617,24 @@ unlock: hci_dev_unlock(hdev); } +static void hci_le_per_adv_report_evt(struct hci_dev *hdev, void *data, + struct sk_buff *skb) +{ + struct hci_ev_le_per_adv_report *ev = data; + int mask = hdev->link_mode; + __u8 flags = 0; + + bt_dev_dbg(hdev, "sync_handle 0x%4.4x", le16_to_cpu(ev->sync_handle)); + + hci_dev_lock(hdev); + + mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, ISO_LINK, &flags); + if (!(mask & HCI_LM_ACCEPT)) + hci_le_pa_term_sync(hdev, ev->sync_handle); + + hci_dev_unlock(hdev); +} + static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -7213,6 +7231,11 @@ static const struct hci_le_ev { HCI_LE_EV(HCI_EV_LE_PA_SYNC_ESTABLISHED, hci_le_pa_sync_estabilished_evt, sizeof(struct hci_ev_le_pa_sync_established)), + /* [0x0f = HCI_EV_LE_PER_ADV_REPORT] */ + HCI_LE_EV_VL(HCI_EV_LE_PER_ADV_REPORT, + hci_le_per_adv_report_evt, + sizeof(struct hci_ev_le_per_adv_report), + HCI_MAX_EVENT_SIZE), /* [0x12 = HCI_EV_LE_EXT_ADV_SET_TERM] */ HCI_LE_EV(HCI_EV_LE_EXT_ADV_SET_TERM, hci_le_ext_adv_term_evt, sizeof(struct hci_evt_le_ext_adv_set_term)), diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 2a2c37789e1f..16da946f5881 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1446,7 +1446,8 @@ static int iso_sock_getsockopt(struct socket *sock, int level, int optname, break; case BT_ISO_BASE: - if (sk->sk_state == BT_CONNECTED) { + if (sk->sk_state == BT_CONNECTED && + !bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) { base_len = iso_pi(sk)->conn->hcon->le_per_adv_data_len; base = iso_pi(sk)->conn->hcon->le_per_adv_data; } else { @@ -1655,6 +1656,9 @@ static void iso_conn_ready(struct iso_conn *conn) bacpy(&iso_pi(sk)->dst, &hcon->dst); iso_pi(sk)->dst_type = hcon->dst_type; + iso_pi(sk)->sync_handle = iso_pi(parent)->sync_handle; + memcpy(iso_pi(sk)->base, iso_pi(parent)->base, iso_pi(parent)->base_len); + iso_pi(sk)->base_len = iso_pi(parent)->base_len; hci_conn_hold(hcon); iso_chan_add(conn, sk, parent); @@ -1692,12 +1696,20 @@ static bool iso_match_sync_handle(struct sock *sk, void *data) return le16_to_cpu(ev->sync_handle) == iso_pi(sk)->sync_handle; } +static bool iso_match_sync_handle_pa_report(struct sock *sk, void *data) +{ + struct hci_ev_le_per_adv_report *ev = data; + + return le16_to_cpu(ev->sync_handle) == iso_pi(sk)->sync_handle; +} + /* ----- ISO interface with lower layer (HCI) ----- */ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct hci_ev_le_pa_sync_established *ev1; struct hci_evt_le_big_info_adv_report *ev2; + struct hci_ev_le_per_adv_report *ev3; struct sock *sk; int lm = 0; @@ -1713,6 +1725,9 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) * 2. HCI_EVT_LE_BIG_INFO_ADV_REPORT: When connect_ind is triggered by a * a BIG Info it attempts to check if there any listening socket with * the same sync_handle and if it does then attempt to create a sync. + * 3. HCI_EV_LE_PER_ADV_REPORT: When a PA report is received, it is stored + * in iso_pi(sk)->base so it can be passed up to user, in the case of a + * broadcast sink. */ ev1 = hci_recv_event_data(hdev, HCI_EV_LE_PA_SYNC_ESTABLISHED); if (ev1) { @@ -1752,6 +1767,17 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) } } } + } + + ev3 = hci_recv_event_data(hdev, HCI_EV_LE_PER_ADV_REPORT); + if (ev3) { + sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, + iso_match_sync_handle_pa_report, ev3); + + if (sk) { + memcpy(iso_pi(sk)->base, ev3->data, ev3->length); + iso_pi(sk)->base_len = ev3->length; + } } else { sk = iso_get_sock_listen(&hdev->bdaddr, BDADDR_ANY, NULL, NULL); } -- cgit v1.2.3 From 253f3399f4c09ce6f4e67350f839be0361b4d5ff Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Tue, 22 Aug 2023 12:02:03 -0700 Subject: Bluetooth: HCI: Introduce HCI_QUIRK_BROKEN_LE_CODED This introduces HCI_QUIRK_BROKEN_LE_CODED which is used to indicate that LE Coded PHY shall not be used, it is then set for some Intel models that claim to support it but when used causes many problems. Cc: stable@vger.kernel.org # 6.4.y+ Link: https://github.com/bluez/bluez/issues/577 Link: https://github.com/bluez/bluez/issues/582 Link: https://lore.kernel.org/linux-bluetooth/CABBYNZKco-v7wkjHHexxQbgwwSz-S=GZ=dZKbRE1qxT1h4fFbQ@mail.gmail.com/T/# Fixes: 288c90224eec ("Bluetooth: Enable all supported LE PHY by default") Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btintel.c | 6 ++++++ include/net/bluetooth/hci.h | 10 ++++++++++ include/net/bluetooth/hci_core.h | 4 +++- net/bluetooth/hci_sync.c | 5 ++++- 4 files changed, 23 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 9b239ce96fa4..2462796a512a 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -2787,6 +2787,9 @@ static int btintel_setup_combined(struct hci_dev *hdev) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); + /* These variants don't seem to support LE Coded PHY */ + set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks); + /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, ver.hw_variant); @@ -2858,6 +2861,9 @@ static int btintel_setup_combined(struct hci_dev *hdev) */ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); + /* These variants don't seem to support LE Coded PHY */ + set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks); + /* Set Valid LE States quirk */ set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index c58425d4c592..87d92accc26e 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -319,6 +319,16 @@ enum { * This quirk must be set before hci_register_dev is called. */ HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, + + /* + * When this quirk is set, LE Coded PHY shall not be used. This is + * required for some Intel controllers which erroneously claim to + * support it but it causes problems with extended scanning. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_LE_CODED, }; /* HCI device flags */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 6e2988b11f99..e6359f7346f1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1817,7 +1817,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define scan_2m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_2M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_2M)) -#define le_coded_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_CODED)) +#define le_coded_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_CODED) && \ + !test_bit(HCI_QUIRK_BROKEN_LE_CODED, \ + &(dev)->quirks)) #define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 0cb780817198..9b93653c6197 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4668,7 +4668,10 @@ static const struct { "advertised, but not supported."), HCI_QUIRK_BROKEN(SET_RPA_TIMEOUT, "HCI LE Set Random Private Address Timeout command is " - "advertised, but not supported.") + "advertised, but not supported."), + HCI_QUIRK_BROKEN(LE_CODED, + "HCI LE Coded PHY feature bit is set, " + "but its usage is not supported.") }; /* This function handles hdev setup stage: -- cgit v1.2.3 From d55595f04dcc8bd6f6ff33f451dda8de3f1232da Mon Sep 17 00:00:00 2001 From: Jiawen Wu Date: Wed, 23 Aug 2023 14:19:28 +0800 Subject: net: pcs: xpcs: add specific vendor supoprt for Wangxun 10Gb NICs Since Wangxun 10Gb NICs require some special configuration on the IP of Synopsys Designware XPCS, introduce dev_flag for different vendors. Read OUI from device identifier registers, to detect Wangxun devices. And xpcs_soft_reset() is skipped to avoid the reset of device identifier registers. Signed-off-by: Jiawen Wu Signed-off-by: David S. Miller --- drivers/net/pcs/pcs-xpcs.c | 35 ++++++++++++++++++++++++++++++++--- include/linux/pcs/pcs-xpcs.h | 7 +++++++ 2 files changed, 39 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 44b037646865..8b56b2f9f24d 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -238,6 +238,29 @@ static int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val) return xpcs_write_vendor(xpcs, MDIO_MMD_PCS, reg, val); } +static int xpcs_dev_flag(struct dw_xpcs *xpcs) +{ + int ret, oui; + + ret = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_DEVID1); + if (ret < 0) + return ret; + + oui = ret; + + ret = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_DEVID2); + if (ret < 0) + return ret; + + ret = (ret >> 10) & 0x3F; + oui |= ret << 16; + + if (oui == DW_OUI_WX) + xpcs->dev_flag = DW_DEV_TXGBE; + + return 0; +} + static int xpcs_poll_reset(struct dw_xpcs *xpcs, int dev) { /* Poll until the reset bit clears (50ms per retry == 0.6 sec) */ @@ -1284,6 +1307,10 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, goto out; } + ret = xpcs_dev_flag(xpcs); + if (ret) + goto out; + xpcs->pcs.ops = &xpcs_phylink_ops; xpcs->pcs.neg_mode = true; if (compat->an_mode == DW_10GBASER) @@ -1291,9 +1318,11 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, xpcs->pcs.poll = true; - ret = xpcs_soft_reset(xpcs, compat); - if (ret) - goto out; + if (xpcs->dev_flag != DW_DEV_TXGBE) { + ret = xpcs_soft_reset(xpcs, compat); + if (ret) + goto out; + } return xpcs; } diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index ff99cf7a5d0d..f37e8acfd351 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -20,12 +20,19 @@ #define DW_AN_C37_1000BASEX 4 #define DW_10GBASER 5 +/* device vendor OUI */ +#define DW_OUI_WX 0x0018fc80 + +/* dev_flag */ +#define DW_DEV_TXGBE BIT(0) + struct xpcs_id; struct dw_xpcs { struct mdio_device *mdiodev; const struct xpcs_id *id; struct phylink_pcs pcs; + int dev_flag; }; int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); -- cgit v1.2.3 From f629acc6f21043fdc80ae93cdafa6713888db0fd Mon Sep 17 00:00:00 2001 From: Jiawen Wu Date: Wed, 23 Aug 2023 14:19:29 +0800 Subject: net: pcs: xpcs: support to switch mode for Wangxun NICs According to chapter 6 of DesignWare Cores Ethernet PCS (version 3.20a) and custom design manual, add a configuration flow for switching interface mode. If the interface changes, the following setting is required: 1. wait VR_XS_PCS_DIG_STS bit(4, 2) [PSEQ_STATE] = 100b (Power-Good) 2. write SR_XS_PCS_CTRL2 to select various PCS type 3. write SR_PMA_CTRL1 and/or SR_XS_PCS_CTRL1 for link speed 4. program PMA registers 5. write VR_XS_PCS_DIG_CTRL1 bit(15) [VR_RST] = 1b (Vendor-Specific Soft Reset) 6. wait for VR_XS_PCS_DIG_CTRL1 bit(15) [VR_RST] to get cleared Only 10GBASE-R/SGMII/1000BASE-X modes are planned for the current Wangxun devices. And there is a quirk for Wangxun devices to switch mode although the interface in phylink state has not changed, since PCS will change to default 10GBASE-R when the ethernet driver(txgbe) do LAN reset. Signed-off-by: Jiawen Wu Signed-off-by: David S. Miller --- MAINTAINERS | 1 + drivers/net/pcs/Makefile | 2 +- drivers/net/pcs/pcs-xpcs-wx.c | 208 ++++++++++++++++++++++++++++++++++++++++++ drivers/net/pcs/pcs-xpcs.c | 13 ++- drivers/net/pcs/pcs-xpcs.h | 8 ++ include/linux/pcs/pcs-xpcs.h | 1 + 6 files changed, 227 insertions(+), 6 deletions(-) create mode 100644 drivers/net/pcs/pcs-xpcs-wx.c (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index dfc2ba0c20f3..5f527a9ae4b2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22925,6 +22925,7 @@ S: Maintained W: https://www.net-swift.com F: Documentation/networking/device_drivers/ethernet/wangxun/* F: drivers/net/ethernet/wangxun/ +F: drivers/net/pcs/pcs-xpcs-wx.c WATCHDOG DEVICE DRIVERS M: Wim Van Sebroeck diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile index ea662a7989b2..fb1694192ae6 100644 --- a/drivers/net/pcs/Makefile +++ b/drivers/net/pcs/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for Linux PCS drivers -pcs_xpcs-$(CONFIG_PCS_XPCS) := pcs-xpcs.o pcs-xpcs-nxp.o +pcs_xpcs-$(CONFIG_PCS_XPCS) := pcs-xpcs.o pcs-xpcs-nxp.o pcs-xpcs-wx.o obj-$(CONFIG_PCS_XPCS) += pcs_xpcs.o obj-$(CONFIG_PCS_LYNX) += pcs-lynx.o diff --git a/drivers/net/pcs/pcs-xpcs-wx.c b/drivers/net/pcs/pcs-xpcs-wx.c new file mode 100644 index 000000000000..1f228d5a1398 --- /dev/null +++ b/drivers/net/pcs/pcs-xpcs-wx.c @@ -0,0 +1,208 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2015 - 2023 Beijing WangXun Technology Co., Ltd. */ + +#include +#include +#include "pcs-xpcs.h" + +/* VR_XS_PMA_MMD */ +#define TXGBE_PMA_MMD 0x8020 +#define TXGBE_TX_GENCTL1 0x11 +#define TXGBE_TX_GENCTL1_VBOOST_LVL GENMASK(10, 8) +#define TXGBE_TX_GENCTL1_VBOOST_EN0 BIT(4) +#define TXGBE_TX_GEN_CTL2 0x12 +#define TXGBE_TX_GEN_CTL2_TX0_WIDTH(v) FIELD_PREP(GENMASK(9, 8), v) +#define TXGBE_TX_RATE_CTL 0x14 +#define TXGBE_TX_RATE_CTL_TX0_RATE(v) FIELD_PREP(GENMASK(2, 0), v) +#define TXGBE_RX_GEN_CTL2 0x32 +#define TXGBE_RX_GEN_CTL2_RX0_WIDTH(v) FIELD_PREP(GENMASK(9, 8), v) +#define TXGBE_RX_GEN_CTL3 0x33 +#define TXGBE_RX_GEN_CTL3_LOS_TRSHLD0 GENMASK(2, 0) +#define TXGBE_RX_RATE_CTL 0x34 +#define TXGBE_RX_RATE_CTL_RX0_RATE(v) FIELD_PREP(GENMASK(1, 0), v) +#define TXGBE_RX_EQ_ATTN_CTL 0x37 +#define TXGBE_RX_EQ_ATTN_LVL0 GENMASK(2, 0) +#define TXGBE_RX_EQ_CTL0 0x38 +#define TXGBE_RX_EQ_CTL0_VGA1_GAIN(v) FIELD_PREP(GENMASK(15, 12), v) +#define TXGBE_RX_EQ_CTL0_VGA2_GAIN(v) FIELD_PREP(GENMASK(11, 8), v) +#define TXGBE_RX_EQ_CTL0_CTLE_POLE(v) FIELD_PREP(GENMASK(7, 5), v) +#define TXGBE_RX_EQ_CTL0_CTLE_BOOST(v) FIELD_PREP(GENMASK(4, 0), v) +#define TXGBE_RX_EQ_CTL4 0x3C +#define TXGBE_RX_EQ_CTL4_CONT_OFF_CAN0 BIT(4) +#define TXGBE_RX_EQ_CTL4_CONT_ADAPT0 BIT(0) +#define TXGBE_AFE_DFE_ENABLE 0x3D +#define TXGBE_DFE_EN_0 BIT(4) +#define TXGBE_AFE_EN_0 BIT(0) +#define TXGBE_DFE_TAP_CTL0 0x3E +#define TXGBE_MPLLA_CTL0 0x51 +#define TXGBE_MPLLA_CTL2 0x53 +#define TXGBE_MPLLA_CTL2_DIV16P5_CLK_EN BIT(10) +#define TXGBE_MPLLA_CTL2_DIV10_CLK_EN BIT(9) +#define TXGBE_MPLLA_CTL3 0x57 +#define TXGBE_MISC_CTL0 0x70 +#define TXGBE_MISC_CTL0_PLL BIT(15) +#define TXGBE_MISC_CTL0_CR_PARA_SEL BIT(14) +#define TXGBE_MISC_CTL0_RX_VREF(v) FIELD_PREP(GENMASK(12, 8), v) +#define TXGBE_VCO_CAL_LD0 0x72 +#define TXGBE_VCO_CAL_REF0 0x76 + +static int txgbe_read_pma(struct dw_xpcs *xpcs, int reg) +{ + return xpcs_read(xpcs, MDIO_MMD_PMAPMD, TXGBE_PMA_MMD + reg); +} + +static int txgbe_write_pma(struct dw_xpcs *xpcs, int reg, u16 val) +{ + return xpcs_write(xpcs, MDIO_MMD_PMAPMD, TXGBE_PMA_MMD + reg, val); +} + +static void txgbe_pma_config_10gbaser(struct dw_xpcs *xpcs) +{ + int val; + + txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL0, 0x21); + txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL3, 0); + val = txgbe_read_pma(xpcs, TXGBE_TX_GENCTL1); + val = u16_replace_bits(val, 0x5, TXGBE_TX_GENCTL1_VBOOST_LVL); + txgbe_write_pma(xpcs, TXGBE_TX_GENCTL1, val); + txgbe_write_pma(xpcs, TXGBE_MISC_CTL0, TXGBE_MISC_CTL0_PLL | + TXGBE_MISC_CTL0_CR_PARA_SEL | TXGBE_MISC_CTL0_RX_VREF(0xF)); + txgbe_write_pma(xpcs, TXGBE_VCO_CAL_LD0, 0x549); + txgbe_write_pma(xpcs, TXGBE_VCO_CAL_REF0, 0x29); + txgbe_write_pma(xpcs, TXGBE_TX_RATE_CTL, 0); + txgbe_write_pma(xpcs, TXGBE_RX_RATE_CTL, 0); + txgbe_write_pma(xpcs, TXGBE_TX_GEN_CTL2, TXGBE_TX_GEN_CTL2_TX0_WIDTH(3)); + txgbe_write_pma(xpcs, TXGBE_RX_GEN_CTL2, TXGBE_RX_GEN_CTL2_RX0_WIDTH(3)); + txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL2, TXGBE_MPLLA_CTL2_DIV16P5_CLK_EN | + TXGBE_MPLLA_CTL2_DIV10_CLK_EN); + + txgbe_write_pma(xpcs, TXGBE_RX_EQ_CTL0, TXGBE_RX_EQ_CTL0_CTLE_POLE(2) | + TXGBE_RX_EQ_CTL0_CTLE_BOOST(5)); + val = txgbe_read_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL); + val &= ~TXGBE_RX_EQ_ATTN_LVL0; + txgbe_write_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL, val); + txgbe_write_pma(xpcs, TXGBE_DFE_TAP_CTL0, 0xBE); + val = txgbe_read_pma(xpcs, TXGBE_AFE_DFE_ENABLE); + val &= ~(TXGBE_DFE_EN_0 | TXGBE_AFE_EN_0); + txgbe_write_pma(xpcs, TXGBE_AFE_DFE_ENABLE, val); + val = txgbe_read_pma(xpcs, TXGBE_RX_EQ_CTL4); + val &= ~TXGBE_RX_EQ_CTL4_CONT_ADAPT0; + txgbe_write_pma(xpcs, TXGBE_RX_EQ_CTL4, val); +} + +static void txgbe_pma_config_1g(struct dw_xpcs *xpcs) +{ + int val; + + val = txgbe_read_pma(xpcs, TXGBE_TX_GENCTL1); + val = u16_replace_bits(val, 0x5, TXGBE_TX_GENCTL1_VBOOST_LVL); + val &= ~TXGBE_TX_GENCTL1_VBOOST_EN0; + txgbe_write_pma(xpcs, TXGBE_TX_GENCTL1, val); + txgbe_write_pma(xpcs, TXGBE_MISC_CTL0, TXGBE_MISC_CTL0_PLL | + TXGBE_MISC_CTL0_CR_PARA_SEL | TXGBE_MISC_CTL0_RX_VREF(0xF)); + + txgbe_write_pma(xpcs, TXGBE_RX_EQ_CTL0, TXGBE_RX_EQ_CTL0_VGA1_GAIN(7) | + TXGBE_RX_EQ_CTL0_VGA2_GAIN(7) | TXGBE_RX_EQ_CTL0_CTLE_BOOST(6)); + val = txgbe_read_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL); + val &= ~TXGBE_RX_EQ_ATTN_LVL0; + txgbe_write_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL, val); + txgbe_write_pma(xpcs, TXGBE_DFE_TAP_CTL0, 0); + val = txgbe_read_pma(xpcs, TXGBE_RX_GEN_CTL3); + val = u16_replace_bits(val, 0x4, TXGBE_RX_GEN_CTL3_LOS_TRSHLD0); + txgbe_write_pma(xpcs, TXGBE_RX_EQ_ATTN_CTL, val); + + txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL0, 0x20); + txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL3, 0x46); + txgbe_write_pma(xpcs, TXGBE_VCO_CAL_LD0, 0x540); + txgbe_write_pma(xpcs, TXGBE_VCO_CAL_REF0, 0x2A); + txgbe_write_pma(xpcs, TXGBE_AFE_DFE_ENABLE, 0); + txgbe_write_pma(xpcs, TXGBE_RX_EQ_CTL4, TXGBE_RX_EQ_CTL4_CONT_OFF_CAN0); + txgbe_write_pma(xpcs, TXGBE_TX_RATE_CTL, TXGBE_TX_RATE_CTL_TX0_RATE(3)); + txgbe_write_pma(xpcs, TXGBE_RX_RATE_CTL, TXGBE_RX_RATE_CTL_RX0_RATE(3)); + txgbe_write_pma(xpcs, TXGBE_TX_GEN_CTL2, TXGBE_TX_GEN_CTL2_TX0_WIDTH(1)); + txgbe_write_pma(xpcs, TXGBE_RX_GEN_CTL2, TXGBE_RX_GEN_CTL2_RX0_WIDTH(1)); + txgbe_write_pma(xpcs, TXGBE_MPLLA_CTL2, TXGBE_MPLLA_CTL2_DIV10_CLK_EN); +} + +static int txgbe_pcs_poll_power_up(struct dw_xpcs *xpcs) +{ + int val, ret; + + /* Wait xpcs power-up good */ + ret = read_poll_timeout(xpcs_read_vpcs, val, + (val & DW_PSEQ_ST) == DW_PSEQ_ST_GOOD, + 10000, 1000000, false, + xpcs, DW_VR_XS_PCS_DIG_STS); + if (ret < 0) + dev_err(&xpcs->mdiodev->dev, "xpcs power-up timeout\n"); + + return ret; +} + +static int txgbe_pma_init_done(struct dw_xpcs *xpcs) +{ + int val, ret; + + xpcs_write_vpcs(xpcs, DW_VR_XS_PCS_DIG_CTRL1, DW_VR_RST | DW_EN_VSMMD1); + + /* wait pma initialization done */ + ret = read_poll_timeout(xpcs_read_vpcs, val, !(val & DW_VR_RST), + 100000, 10000000, false, + xpcs, DW_VR_XS_PCS_DIG_CTRL1); + if (ret < 0) + dev_err(&xpcs->mdiodev->dev, "xpcs pma initialization timeout\n"); + + return ret; +} + +static bool txgbe_xpcs_mode_quirk(struct dw_xpcs *xpcs) +{ + int ret; + + /* When txgbe do LAN reset, PCS will change to default 10GBASE-R mode */ + ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_CTRL2); + ret &= MDIO_PCS_CTRL2_TYPE; + if (ret == MDIO_PCS_CTRL2_10GBR && + xpcs->interface != PHY_INTERFACE_MODE_10GBASER) + return true; + + return false; +} + +int txgbe_xpcs_switch_mode(struct dw_xpcs *xpcs, phy_interface_t interface) +{ + int val, ret; + + switch (interface) { + case PHY_INTERFACE_MODE_10GBASER: + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + break; + default: + return 0; + } + + if (xpcs->interface == interface && !txgbe_xpcs_mode_quirk(xpcs)) + return 0; + + xpcs->interface = interface; + + ret = txgbe_pcs_poll_power_up(xpcs); + if (ret < 0) + return ret; + + if (interface == PHY_INTERFACE_MODE_10GBASER) { + xpcs_write(xpcs, MDIO_MMD_PCS, MDIO_CTRL2, MDIO_PCS_CTRL2_10GBR); + val = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_CTRL1); + val |= MDIO_CTRL1_SPEED10G; + xpcs_write(xpcs, MDIO_MMD_PMAPMD, MDIO_CTRL1, val); + txgbe_pma_config_10gbaser(xpcs); + } else { + xpcs_write(xpcs, MDIO_MMD_PCS, MDIO_CTRL2, MDIO_PCS_CTRL2_10GBX); + xpcs_write(xpcs, MDIO_MMD_PMAPMD, MDIO_CTRL1, 0); + xpcs_write(xpcs, MDIO_MMD_PCS, MDIO_CTRL1, 0); + txgbe_pma_config_1g(xpcs); + } + + return txgbe_pma_init_done(xpcs); +} diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 8b56b2f9f24d..4cd011405376 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -228,12 +228,12 @@ static int xpcs_write_vendor(struct dw_xpcs *xpcs, int dev, int reg, return xpcs_write(xpcs, dev, DW_VENDOR | reg, val); } -static int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg) +int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg) { return xpcs_read_vendor(xpcs, MDIO_MMD_PCS, reg); } -static int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val) +int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val) { return xpcs_write_vendor(xpcs, MDIO_MMD_PCS, reg, val); } @@ -841,6 +841,12 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, if (!compat) return -ENODEV; + if (xpcs->dev_flag == DW_DEV_TXGBE) { + ret = txgbe_xpcs_switch_mode(xpcs, interface); + if (ret) + return ret; + } + switch (compat->an_mode) { case DW_10GBASER: break; @@ -1313,9 +1319,6 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, xpcs->pcs.ops = &xpcs_phylink_ops; xpcs->pcs.neg_mode = true; - if (compat->an_mode == DW_10GBASER) - return xpcs; - xpcs->pcs.poll = true; if (xpcs->dev_flag != DW_DEV_TXGBE) { diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h index 68c6b5a62088..da61ad36946c 100644 --- a/drivers/net/pcs/pcs-xpcs.h +++ b/drivers/net/pcs/pcs-xpcs.h @@ -15,8 +15,13 @@ /* VR_XS_PCS */ #define DW_USXGMII_RST BIT(10) #define DW_USXGMII_EN BIT(9) +#define DW_VR_XS_PCS_DIG_CTRL1 0x0000 +#define DW_VR_RST BIT(15) +#define DW_EN_VSMMD1 BIT(13) #define DW_VR_XS_PCS_DIG_STS 0x0010 #define DW_RXFIFO_ERR GENMASK(6, 5) +#define DW_PSEQ_ST GENMASK(4, 2) +#define DW_PSEQ_ST_GOOD FIELD_PREP(GENMASK(4, 2), 0x4) /* SR_MII */ #define DW_USXGMII_FULL BIT(8) @@ -106,6 +111,9 @@ int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg); int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val); +int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg); +int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val); int nxp_sja1105_sgmii_pma_config(struct dw_xpcs *xpcs); int nxp_sja1110_sgmii_pma_config(struct dw_xpcs *xpcs); int nxp_sja1110_2500basex_pma_config(struct dw_xpcs *xpcs); +int txgbe_xpcs_switch_mode(struct dw_xpcs *xpcs, phy_interface_t interface); diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index f37e8acfd351..da3a6c30f6d2 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -32,6 +32,7 @@ struct dw_xpcs { struct mdio_device *mdiodev; const struct xpcs_id *id; struct phylink_pcs pcs; + phy_interface_t interface; int dev_flag; }; -- cgit v1.2.3 From a4f39c9f14a634e4cd35fcd338c239d11fcc73fc Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Wed, 23 Aug 2023 15:41:02 +0200 Subject: net: handle ARPHRD_PPP in dev_is_mac_header_xmit() The goal is to support a bpf_redirect() from an ethernet device (ingress) to a ppp device (egress). The l2 header is added automatically by the ppp driver, thus the ethernet header should be removed. CC: stable@vger.kernel.org Fixes: 27b29f63058d ("bpf: add bpf_redirect() helper") Signed-off-by: Nicolas Dichtel Tested-by: Siwar Zitouni Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller --- include/linux/if_arp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 1ed52441972f..10a1e81434cb 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -53,6 +53,10 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_NONE: case ARPHRD_RAWIP: case ARPHRD_PIMREG: + /* PPP adds its l2 header automatically in ppp_start_xmit(). + * This makes it look like an l3 device to __bpf_redirect() and tcf_mirred_init(). + */ + case ARPHRD_PPP: return false; default: return true; -- cgit v1.2.3 From 2a6d50b50d6d589d43a90d6ca990b8b811e67701 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Mon, 21 Aug 2023 12:33:06 -0700 Subject: bpf: Consider non-owning refs trusted Recent discussions around default kptr "trustedness" led to changes such as commit 6fcd486b3a0a ("bpf: Refactor RCU enforcement in the verifier."). One of the conclusions of those discussions, as expressed in code and comments in that patch, is that we'd like to move away from 'raw' PTR_TO_BTF_ID without some type flag or other register state indicating trustedness. Although PTR_TRUSTED and PTR_UNTRUSTED flags mark this state explicitly, the verifier currently considers trustedness implied by other register state. For example, owning refs to graph collection nodes must have a nonzero ref_obj_id, so they pass the is_trusted_reg check despite having no explicit PTR_{UN}TRUSTED flag. This patch makes trustedness of non-owning refs to graph collection nodes explicit as well. By definition, non-owning refs are currently trusted. Although the ref has no control over pointee lifetime, due to non-owning ref clobbering rules (see invalidate_non_owning_refs) dereferencing a non-owning ref is safe in the critical section controlled by bpf_spin_lock associated with its owning collection. Note that the previous statement does not hold true for nodes with shared ownership due to the use-after-free issue that this series is addressing. True shared ownership was disabled by commit 7deca5eae833 ("bpf: Disable bpf_refcount_acquire kfunc calls until race conditions are fixed"), though, so the statement holds for now. Further patches in the series will change the trustedness state of non-owning refs before re-enabling bpf_refcount_acquire. Let's add NON_OWN_REF type flag to BPF_REG_TRUSTED_MODIFIERS such that a non-owning ref reg state would pass is_trusted_reg check. Somewhat surprisingly, this doesn't result in any change to user-visible functionality elsewhere in the verifier: graph collection nodes are all marked MEM_ALLOC, which tends to be handled in separate codepaths from "raw" PTR_TO_BTF_ID. Regardless, let's be explicit here and document the current state of things before changing it elsewhere in the series. Signed-off-by: Dave Marchevsky Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230821193311.3290257-3-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index f70f9ac884d2..b6e58dab8e27 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -745,7 +745,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) } } -#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED) +#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED | NON_OWN_REF) static inline bool bpf_type_has_unsafe_modifiers(u32 type) { -- cgit v1.2.3 From 0816b8c6bf7fc87cec4273dc199e8f0764b9e7b1 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Mon, 21 Aug 2023 12:33:09 -0700 Subject: bpf: Consider non-owning refs to refcounted nodes RCU protected An earlier patch in the series ensures that the underlying memory of nodes with bpf_refcount - which can have multiple owners - is not reused until RCU grace period has elapsed. This prevents use-after-free with non-owning references that may point to recently-freed memory. While RCU read lock is held, it's safe to dereference such a non-owning ref, as by definition RCU GP couldn't have elapsed and therefore underlying memory couldn't have been reused. From the perspective of verifier "trustedness" non-owning refs to refcounted nodes are now trusted only in RCU CS and therefore should no longer pass is_trusted_reg, but rather is_rcu_reg. Let's mark them MEM_RCU in order to reflect this new state. Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230821193311.3290257-6-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 ++- kernel/bpf/verifier.c | 13 ++++++++++++- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index eced6400f778..12596af59c00 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -653,7 +653,8 @@ enum bpf_type_flag { MEM_RCU = BIT(13 + BPF_BASE_TYPE_BITS), /* Used to tag PTR_TO_BTF_ID | MEM_ALLOC references which are non-owning. - * Currently only valid for linked-list and rbtree nodes. + * Currently only valid for linked-list and rbtree nodes. If the nodes + * have a bpf_refcount_field, they must be tagged MEM_RCU as well. */ NON_OWN_REF = BIT(14 + BPF_BASE_TYPE_BITS), diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b875f511c3b7..4b638eb1bdad 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8007,6 +8007,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_BTF_ID | PTR_TRUSTED: case PTR_TO_BTF_ID | MEM_RCU: case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF: + case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU: /* When referenced PTR_TO_BTF_ID is passed to release function, * its fixed offset must be 0. In the other cases, fixed offset * can be non-zero. This was already checked above. So pass @@ -10473,6 +10474,7 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_verifier_state *state = env->cur_state; + struct btf_record *rec = reg_btf_record(reg); if (!state->active_lock.ptr) { verbose(env, "verifier internal error: ref_set_non_owning w/o active lock\n"); @@ -10485,6 +10487,9 @@ static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state } reg->type |= NON_OWN_REF; + if (rec->refcount_off >= 0) + reg->type |= MEM_RCU; + return 0; } @@ -11322,6 +11327,11 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_func_state *state; struct bpf_reg_state *reg; + if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) { + verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n"); + return -EACCES; + } + if (rcu_lock) { verbose(env, "nested rcu read lock (kernel function %s)\n", func_name); return -EINVAL; @@ -16684,7 +16694,8 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - if (env->cur_state->active_rcu_lock) { + if (env->cur_state->active_rcu_lock && + !in_rbtree_lock_required_cb(env)) { verbose(env, "bpf_rcu_read_unlock is missing\n"); return -EINVAL; } -- cgit v1.2.3 From 70934c7c99ad01778eef83e898df4c624e52492f Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 24 Aug 2023 14:37:53 +0100 Subject: net: phylink: add phylink_limit_mac_speed() Add a function which can be used to limit the phylink MAC capabilities to an upper speed limit. Signed-off-by: Russell King (Oracle) Link: https://lore.kernel.org/r/E1qZAX3-005pTi-K1@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- drivers/net/phy/phylink.c | 18 ++++++++++++++++++ include/linux/phylink.h | 2 ++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 160bce608c34..0d7354955d62 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -426,6 +426,24 @@ static struct { { MAC_10HD, SPEED_10, DUPLEX_HALF }, }; +/** + * phylink_limit_mac_speed - limit the phylink_config to a maximum speed + * @config: pointer to a &struct phylink_config + * @max_speed: maximum speed + * + * Mask off MAC capabilities for speeds higher than the @max_speed parameter. + * Any further motifications of config.mac_capabilities will override this. + */ +void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(phylink_caps_params) && + phylink_caps_params[i].speed > max_speed; i++) + config->mac_capabilities &= ~phylink_caps_params[i].mask; +} +EXPORT_SYMBOL_GPL(phylink_limit_mac_speed); + /** * phylink_cap_from_speed_duplex - Get mac capability from speed/duplex * @speed: the speed to search for diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 789c516c6b4a..7d07f8736431 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -223,6 +223,8 @@ struct phylink_config { unsigned long mac_capabilities; }; +void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); + /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. -- cgit v1.2.3 From e80af2acdef73d90ce56d6849d96f2a5862cec2c Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 24 Aug 2023 14:37:58 +0100 Subject: net: stmmac: convert plat->phylink_node to fwnode All users of plat->phylink_node first convert it to a fwnode. Rather than repeatedly convert to a fwnode, store it as a fwnode. To reflect this change, call it plat->port_node instead - it is used for more than just phylink. Signed-off-by: Russell King (Oracle) Link: https://lore.kernel.org/r/E1qZAX8-005pTo-OT@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 3 ++- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +- include/linux/stmmac.h | 2 +- 4 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7a9bbcf03ea5..a2dfb624e10c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1153,7 +1153,7 @@ static int stmmac_init_phy(struct net_device *dev) if (!phylink_expects_phy(priv->phylink)) return 0; - fwnode = of_fwnode_handle(priv->plat->phylink_node); + fwnode = priv->plat->port_node; if (!fwnode) fwnode = dev_fwnode(priv->device); @@ -1200,7 +1200,7 @@ static int stmmac_init_phy(struct net_device *dev) static int stmmac_phy_setup(struct stmmac_priv *priv) { struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; - struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node); + struct fwnode_handle *fwnode = priv->plat->port_node; int max_speed = priv->plat->max_speed; int mode = priv->plat->phy_interface; struct phylink *phylink; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index dd9e2fec5328..fa9e7e7040b9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -533,11 +533,11 @@ int stmmac_mdio_register(struct net_device *ndev) int err = 0; struct mii_bus *new_bus; struct stmmac_priv *priv = netdev_priv(ndev); - struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node); struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; struct device_node *mdio_node = priv->plat->mdio_node; struct device *dev = ndev->dev.parent; struct fwnode_handle *fixed_node; + struct fwnode_handle *fwnode; int addr, found, max_addr; if (!mdio_bus_data) @@ -601,6 +601,7 @@ int stmmac_mdio_register(struct net_device *ndev) stmmac_xgmac2_mdio_read_c45(new_bus, 0, 0, 0); /* If fixed-link is set, skip PHY scanning */ + fwnode = priv->plat->port_node; if (!fwnode) fwnode = dev_fwnode(priv->device); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index be8e79c7aa34..ff330423ee66 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -428,7 +428,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->phy_node = of_parse_phandle(np, "phy-handle", 0); /* PHYLINK automatically parses the phy-handle property */ - plat->phylink_node = np; + plat->port_node = of_fwnode_handle(np); /* Get max speed of operation from device tree */ of_property_read_u32(np, "max-speed", &plat->max_speed); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 784277d666eb..b2ccd827bb80 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -227,7 +227,7 @@ struct plat_stmmacenet_data { phy_interface_t phy_interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; - struct device_node *phylink_node; + struct fwnode_handle *port_node; struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; struct stmmac_est *est; -- cgit v1.2.3 From 62b6442c58dc17b168f69b37b398a9cab7cd90c9 Mon Sep 17 00:00:00 2001 From: Dima Chumak Date: Thu, 24 Aug 2023 23:28:29 -0700 Subject: devlink: Expose port function commands to control IPsec crypto offloads Expose port function commands to enable / disable IPsec crypto offloads, this is used to control the port IPsec capabilities. When IPsec crypto is disabled for a function of the port (default), function cannot offload any IPsec crypto operations (Encrypt/Decrypt and XFRM state offloading). When enabled, IPsec crypto operations can be offloaded by the function of the port. Example of a PCI VF port which supports IPsec crypto offloads: $ devlink port show pci/0000:06:00.0/1 pci/0000:06:00.0/1: type eth netdev enp6s0pf0vf0 flavour pcivf pfnum 0 vfnum 0 function: hw_addr 00:00:00:00:00:00 roce enable ipsec_crypto disable $ devlink port function set pci/0000:06:00.0/1 ipsec_crypto enable $ devlink port show pci/0000:06:00.0/1 pci/0000:06:00.0/1: type eth netdev enp6s0pf0vf0 flavour pcivf pfnum 0 vfnum 0 function: hw_addr 00:00:00:00:00:00 roce enable ipsec_crypto enable Signed-off-by: Dima Chumak Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230825062836.103744-2-saeed@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/networking/devlink/devlink-port.rst | 27 ++++++++++++ include/net/devlink.h | 15 +++++++ include/uapi/linux/devlink.h | 2 + net/devlink/leftover.c | 52 +++++++++++++++++++++++ 4 files changed, 96 insertions(+) (limited to 'include') diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index 3da590953ce8..6983b11559cb 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -128,6 +128,9 @@ Users may also set the RoCE capability of the function using Users may also set the function as migratable using 'devlink port function set migratable' command. +Users may also set the IPsec crypto capability of the function using +`devlink port function set ipsec_crypto` command. + Function attributes =================== @@ -240,6 +243,30 @@ Attach VF to the VM. Start the VM. Perform live migration. +IPsec crypto capability setup +----------------------------- +When user enables IPsec crypto capability for a VF, user application can offload +XFRM state crypto operation (Encrypt/Decrypt) to this VF. + +When IPsec crypto capability is disabled (default) for a VF, the XFRM state is +processed in software by the kernel. + +- Get IPsec crypto capability of the VF device:: + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 ipsec_crypto disabled + +- Set IPsec crypto capability of the VF device:: + + $ devlink port function set pci/0000:06:00.0/2 ipsec_crypto enable + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 ipsec_crypto enabled + Subfunction ============ diff --git a/include/net/devlink.h b/include/net/devlink.h index f7fec0791acc..1cf07a820a0e 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1583,6 +1583,15 @@ void devlink_free(struct devlink *devlink); * Should be used by device drivers set * the admin state of a function managed * by the devlink port. + * @port_fn_ipsec_crypto_get: Callback used to get port function's ipsec_crypto + * capability. Should be used by device drivers + * to report the current state of ipsec_crypto + * capability of a function managed by the devlink + * port. + * @port_fn_ipsec_crypto_set: Callback used to set port function's ipsec_crypto + * capability. Should be used by device drivers to + * enable/disable ipsec_crypto capability of a + * function managed by the devlink port. * * Note: Driver should return -EOPNOTSUPP if it doesn't support * port function (@port_fn_*) handling for a particular port. @@ -1620,6 +1629,12 @@ struct devlink_port_ops { int (*port_fn_state_set)(struct devlink_port *port, enum devlink_port_fn_state state, struct netlink_ext_ack *extack); + int (*port_fn_ipsec_crypto_get)(struct devlink_port *devlink_port, + bool *is_enable, + struct netlink_ext_ack *extack); + int (*port_fn_ipsec_crypto_set)(struct devlink_port *devlink_port, + bool enable, + struct netlink_ext_ack *extack); }; void devlink_port_init(struct devlink *devlink, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 3782d4219ac9..f9ae9a058ad2 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -661,6 +661,7 @@ enum devlink_resource_unit { enum devlink_port_fn_attr_cap { DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT, DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT, + DEVLINK_PORT_FN_ATTR_CAP_IPSEC_CRYPTO_BIT, /* Add new caps above */ __DEVLINK_PORT_FN_ATTR_CAPS_MAX, @@ -669,6 +670,7 @@ enum devlink_port_fn_attr_cap { #define DEVLINK_PORT_FN_CAP_ROCE _BITUL(DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT) #define DEVLINK_PORT_FN_CAP_MIGRATABLE \ _BITUL(DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT) +#define DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO _BITUL(DEVLINK_PORT_FN_ATTR_CAP_IPSEC_CRYPTO_BIT) enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index e2cd13958cc2..fcc1a06cae48 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -492,6 +492,28 @@ static int devlink_port_fn_migratable_fill(struct devlink_port *devlink_port, return 0; } +static int devlink_port_fn_ipsec_crypto_fill(struct devlink_port *devlink_port, + struct nla_bitfield32 *caps, + struct netlink_ext_ack *extack) +{ + bool is_enable; + int err; + + if (!devlink_port->ops->port_fn_ipsec_crypto_get || + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) + return 0; + + err = devlink_port->ops->port_fn_ipsec_crypto_get(devlink_port, &is_enable, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, is_enable); + return 0; +} + static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port, struct sk_buff *msg, struct netlink_ext_ack *extack, @@ -508,6 +530,10 @@ static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port, if (err) return err; + err = devlink_port_fn_ipsec_crypto_fill(devlink_port, &caps, extack); + if (err) + return err; + if (!caps.selector) return 0; err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value, @@ -838,6 +864,13 @@ devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable, extack); } +static int +devlink_port_fn_ipsec_crypto_set(struct devlink_port *devlink_port, bool enable, + struct netlink_ext_ack *extack) +{ + return devlink_port->ops->port_fn_ipsec_crypto_set(devlink_port, enable, extack); +} + static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, const struct nlattr *attr, struct netlink_ext_ack *extack) @@ -862,6 +895,13 @@ static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, if (err) return err; } + if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) { + err = devlink_port_fn_ipsec_crypto_set(devlink_port, caps_value & + DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, + extack); + if (err) + return err; + } return 0; } @@ -1226,6 +1266,18 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, return -EOPNOTSUPP; } } + if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) { + if (!ops->port_fn_ipsec_crypto_set) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Port doesn't support ipsec_crypto function attribute"); + return -EOPNOTSUPP; + } + if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "ipsec_crypto function attribute supported for VFs only"); + return -EOPNOTSUPP; + } + } } return 0; } -- cgit v1.2.3 From 390a24cbc39626a8a38c6d877a59f758fe209f2d Mon Sep 17 00:00:00 2001 From: Dima Chumak Date: Thu, 24 Aug 2023 23:28:30 -0700 Subject: devlink: Expose port function commands to control IPsec packet offloads Expose port function commands to enable / disable IPsec packet offloads, this is used to control the port IPsec capabilities. When IPsec packet is disabled for a function of the port (default), function cannot offload IPsec packet operations (encapsulation and XFRM policy offload). When enabled, IPsec packet operations can be offloaded by the function of the port, which includes crypto operation (Encrypt/Decrypt), IPsec encapsulation and XFRM state and policy offload. Example of a PCI VF port which supports IPsec packet offloads: $ devlink port show pci/0000:06:00.0/1 pci/0000:06:00.0/1: type eth netdev enp6s0pf0vf0 flavour pcivf pfnum 0 vfnum 0 function: hw_addr 00:00:00:00:00:00 roce enable ipsec_packet disable $ devlink port function set pci/0000:06:00.0/1 ipsec_packet enable $ devlink port show pci/0000:06:00.0/1 pci/0000:06:00.0/1: type eth netdev enp6s0pf0vf0 flavour pcivf pfnum 0 vfnum 0 function: hw_addr 00:00:00:00:00:00 roce enable ipsec_packet enable Signed-off-by: Dima Chumak Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230825062836.103744-3-saeed@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/networking/devlink/devlink-port.rst | 28 ++++++++++++ include/net/devlink.h | 15 +++++++ include/uapi/linux/devlink.h | 2 + net/devlink/leftover.c | 52 +++++++++++++++++++++++ 4 files changed, 97 insertions(+) (limited to 'include') diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index 6983b11559cb..f5adb910427a 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -131,6 +131,9 @@ Users may also set the function as migratable using Users may also set the IPsec crypto capability of the function using `devlink port function set ipsec_crypto` command. +Users may also set the IPsec packet capability of the function using +`devlink port function set ipsec_packet` command. + Function attributes =================== @@ -267,6 +270,31 @@ processed in software by the kernel. function: hw_addr 00:00:00:00:00:00 ipsec_crypto enabled +IPsec packet capability setup +----------------------------- +When user enables IPsec packet capability for a VF, user application can offload +XFRM state and policy crypto operation (Encrypt/Decrypt) to this VF, as well as +IPsec encapsulation. + +When IPsec packet capability is disabled (default) for a VF, the XFRM state and +policy is processed in software by the kernel. + +- Get IPsec packet capability of the VF device:: + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 ipsec_packet disabled + +- Set IPsec packet capability of the VF device:: + + $ devlink port function set pci/0000:06:00.0/2 ipsec_packet enable + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 ipsec_packet enabled + Subfunction ============ diff --git a/include/net/devlink.h b/include/net/devlink.h index 1cf07a820a0e..29fd1b4ee654 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1592,6 +1592,15 @@ void devlink_free(struct devlink *devlink); * capability. Should be used by device drivers to * enable/disable ipsec_crypto capability of a * function managed by the devlink port. + * @port_fn_ipsec_packet_get: Callback used to get port function's ipsec_packet + * capability. Should be used by device drivers + * to report the current state of ipsec_packet + * capability of a function managed by the devlink + * port. + * @port_fn_ipsec_packet_set: Callback used to set port function's ipsec_packet + * capability. Should be used by device drivers to + * enable/disable ipsec_packet capability of a + * function managed by the devlink port. * * Note: Driver should return -EOPNOTSUPP if it doesn't support * port function (@port_fn_*) handling for a particular port. @@ -1635,6 +1644,12 @@ struct devlink_port_ops { int (*port_fn_ipsec_crypto_set)(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack); + int (*port_fn_ipsec_packet_get)(struct devlink_port *devlink_port, + bool *is_enable, + struct netlink_ext_ack *extack); + int (*port_fn_ipsec_packet_set)(struct devlink_port *devlink_port, + bool enable, + struct netlink_ext_ack *extack); }; void devlink_port_init(struct devlink *devlink, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index f9ae9a058ad2..03875e078be8 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -662,6 +662,7 @@ enum devlink_port_fn_attr_cap { DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT, DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT, DEVLINK_PORT_FN_ATTR_CAP_IPSEC_CRYPTO_BIT, + DEVLINK_PORT_FN_ATTR_CAP_IPSEC_PACKET_BIT, /* Add new caps above */ __DEVLINK_PORT_FN_ATTR_CAPS_MAX, @@ -671,6 +672,7 @@ enum devlink_port_fn_attr_cap { #define DEVLINK_PORT_FN_CAP_MIGRATABLE \ _BITUL(DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT) #define DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO _BITUL(DEVLINK_PORT_FN_ATTR_CAP_IPSEC_CRYPTO_BIT) +#define DEVLINK_PORT_FN_CAP_IPSEC_PACKET _BITUL(DEVLINK_PORT_FN_ATTR_CAP_IPSEC_PACKET_BIT) enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index fcc1a06cae48..149752bc9f2d 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -514,6 +514,28 @@ static int devlink_port_fn_ipsec_crypto_fill(struct devlink_port *devlink_port, return 0; } +static int devlink_port_fn_ipsec_packet_fill(struct devlink_port *devlink_port, + struct nla_bitfield32 *caps, + struct netlink_ext_ack *extack) +{ + bool is_enable; + int err; + + if (!devlink_port->ops->port_fn_ipsec_packet_get || + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) + return 0; + + err = devlink_port->ops->port_fn_ipsec_packet_get(devlink_port, &is_enable, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_PACKET, is_enable); + return 0; +} + static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port, struct sk_buff *msg, struct netlink_ext_ack *extack, @@ -534,6 +556,10 @@ static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port, if (err) return err; + err = devlink_port_fn_ipsec_packet_fill(devlink_port, &caps, extack); + if (err) + return err; + if (!caps.selector) return 0; err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value, @@ -871,6 +897,13 @@ devlink_port_fn_ipsec_crypto_set(struct devlink_port *devlink_port, bool enable, return devlink_port->ops->port_fn_ipsec_crypto_set(devlink_port, enable, extack); } +static int +devlink_port_fn_ipsec_packet_set(struct devlink_port *devlink_port, bool enable, + struct netlink_ext_ack *extack) +{ + return devlink_port->ops->port_fn_ipsec_packet_set(devlink_port, enable, extack); +} + static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, const struct nlattr *attr, struct netlink_ext_ack *extack) @@ -902,6 +935,13 @@ static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, if (err) return err; } + if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) { + err = devlink_port_fn_ipsec_packet_set(devlink_port, caps_value & + DEVLINK_PORT_FN_CAP_IPSEC_PACKET, + extack); + if (err) + return err; + } return 0; } @@ -1278,6 +1318,18 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, return -EOPNOTSUPP; } } + if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) { + if (!ops->port_fn_ipsec_packet_set) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Port doesn't support ipsec_packet function attribute"); + return -EOPNOTSUPP; + } + if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "ipsec_packet function attribute supported for VFs only"); + return -EOPNOTSUPP; + } + } } return 0; } -- cgit v1.2.3 From 17c8da5a3423c9f3800a256dbaa685bae18e1264 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 24 Aug 2023 23:28:33 -0700 Subject: net/mlx5: Add IFC bits to support IPsec enable/disable Add hardware definitions to allow to control IPSec capabilities. Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Link: https://lore.kernel.org/r/20230825062836.103744-6-saeed@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 08dcb1f43be7..fc3db401f8a2 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -65,9 +65,11 @@ enum { enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, + MLX5_SET_HCA_CAP_OP_MOD_ETHERNET_OFFLOADS = 0x1, MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, MLX5_SET_HCA_CAP_OP_MOD_ROCE = 0x4, + MLX5_SET_HCA_CAP_OP_MOD_IPSEC = 0x15, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2 = 0x20, MLX5_SET_HCA_CAP_OP_MOD_PORT_SELECTION = 0x25, }; @@ -3451,6 +3453,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap; struct mlx5_ifc_macsec_cap_bits macsec_cap; struct mlx5_ifc_crypto_cap_bits crypto_cap; + struct mlx5_ifc_ipsec_cap_bits ipsec_cap; u8 reserved_at_0[0x8000]; }; -- cgit v1.2.3 From 8efd7b17a3b03242c97281d88463ad56e8f551f8 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 24 Aug 2023 23:28:34 -0700 Subject: net/mlx5: Provide an interface to block change of IPsec capabilities mlx5 HW can't perform IPsec offload operation simultaneously both on PF and VFs at the same time. While the previous patches added devlink knobs to change IPsec capabilities dynamically, there is a need to add a logic to block such IPsec capabilities for the cases when IPsec is already configured. Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Link: https://lore.kernel.org/r/20230825062836.103744-7-saeed@kernel.org Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c | 20 +++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 32 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 9 ++++++ include/linux/mlx5/driver.h | 1 + 4 files changed, 61 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 3b88a8bb7082..7d4ceb9b9c16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -38,6 +38,7 @@ #include #include "en.h" +#include "eswitch.h" #include "ipsec.h" #include "ipsec_rxtx.h" #include "en_rep.h" @@ -670,6 +671,11 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x, if (err) goto err_xfrm; + if (!mlx5_eswitch_block_ipsec(priv->mdev)) { + err = -EBUSY; + goto err_xfrm; + } + /* check esn */ if (x->props.flags & XFRM_STATE_ESN) mlx5e_ipsec_update_esn_state(sa_entry); @@ -678,7 +684,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x, err = mlx5_ipsec_create_work(sa_entry); if (err) - goto err_xfrm; + goto unblock_ipsec; err = mlx5e_ipsec_create_dwork(sa_entry); if (err) @@ -735,6 +741,8 @@ release_work: if (sa_entry->work) kfree(sa_entry->work->data); kfree(sa_entry->work); +unblock_ipsec: + mlx5_eswitch_unblock_ipsec(priv->mdev); err_xfrm: kfree(sa_entry); NL_SET_ERR_MSG_WEAK_MOD(extack, "Device failed to offload this state"); @@ -764,6 +772,7 @@ static void mlx5e_xfrm_del_state(struct xfrm_state *x) static void mlx5e_xfrm_free_state(struct xfrm_state *x) { struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x); + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ) goto sa_entry_free; @@ -780,6 +789,7 @@ static void mlx5e_xfrm_free_state(struct xfrm_state *x) if (sa_entry->work) kfree(sa_entry->work->data); kfree(sa_entry->work); + mlx5_eswitch_unblock_ipsec(ipsec->mdev); sa_entry_free: kfree(sa_entry); } @@ -1055,6 +1065,11 @@ static int mlx5e_xfrm_add_policy(struct xfrm_policy *x, pol_entry->x = x; pol_entry->ipsec = priv->ipsec; + if (!mlx5_eswitch_block_ipsec(priv->mdev)) { + err = -EBUSY; + goto ipsec_busy; + } + mlx5e_ipsec_build_accel_pol_attrs(pol_entry, &pol_entry->attrs); err = mlx5e_accel_ipsec_fs_add_pol(pol_entry); if (err) @@ -1064,6 +1079,8 @@ static int mlx5e_xfrm_add_policy(struct xfrm_policy *x, return 0; err_fs: + mlx5_eswitch_unblock_ipsec(priv->mdev); +ipsec_busy: kfree(pol_entry); NL_SET_ERR_MSG_MOD(extack, "Device failed to offload this policy"); return err; @@ -1074,6 +1091,7 @@ static void mlx5e_xfrm_del_policy(struct xfrm_policy *x) struct mlx5e_ipsec_pol_entry *pol_entry = to_ipsec_pol_entry(x); mlx5e_accel_ipsec_fs_del_pol(pol_entry); + mlx5_eswitch_unblock_ipsec(pol_entry->ipsec->mdev); } static void mlx5e_xfrm_free_policy(struct xfrm_policy *x) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index db1c2a076364..38a149dd479f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -48,6 +48,7 @@ #include "devlink.h" #include "ecpf.h" #include "en/mod_hdr.h" +#include "en_accel/ipsec.h" enum { MLX5_ACTION_NONE = 0, @@ -2336,3 +2337,34 @@ 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); + +bool mlx5_eswitch_block_ipsec(struct mlx5_core_dev *dev) +{ + struct mlx5_eswitch *esw = dev->priv.eswitch; + + if (!mlx5_esw_allowed(esw)) + return true; + + mutex_lock(&esw->state_lock); + if (esw->enabled_ipsec_vf_count) { + mutex_unlock(&esw->state_lock); + return false; + } + + dev->num_ipsec_offloads++; + mutex_unlock(&esw->state_lock); + return true; +} + +void mlx5_eswitch_unblock_ipsec(struct mlx5_core_dev *dev) +{ + struct mlx5_eswitch *esw = dev->priv.eswitch; + + if (!mlx5_esw_allowed(esw)) + /* Failure means no eswitch => core dev is not a PF */ + return; + + mutex_lock(&esw->state_lock); + dev->num_ipsec_offloads--; + mutex_unlock(&esw->state_lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index ed3abcd70c46..0e51fd066fcc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -380,6 +380,7 @@ struct mlx5_eswitch { struct blocking_notifier_head n_head; struct xarray paired; struct mlx5_devcom_comp_dev *devcom; + u16 enabled_ipsec_vf_count; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -855,6 +856,8 @@ mlx5_eswitch_get_slow_fdb(struct mlx5_eswitch *esw) int mlx5_eswitch_restore_ipsec_rule(struct mlx5_eswitch *esw, struct mlx5_flow_handle *rule, struct mlx5_esw_flow_attr *esw_attr, int attr_idx); +bool mlx5_eswitch_block_ipsec(struct mlx5_core_dev *dev); +void mlx5_eswitch_unblock_ipsec(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } @@ -916,6 +919,12 @@ static inline void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev) static inline int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev) { return 0; } static inline void mlx5_eswitch_unblock_mode(struct mlx5_core_dev *dev) {} +static inline bool mlx5_eswitch_block_ipsec(struct mlx5_core_dev *dev) +{ + return false; +} + +static inline void mlx5_eswitch_unblock_ipsec(struct mlx5_core_dev *dev) {} #endif /* CONFIG_MLX5_ESWITCH */ #endif /* __MLX5_ESWITCH_H__ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e95f10066eac..3033bbaeac81 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -813,6 +813,7 @@ struct mlx5_core_dev { /* MACsec notifier chain to sync MACsec core and IB database */ struct blocking_notifier_head macsec_nh; #endif + u64 num_ipsec_offloads; }; struct mlx5_db { -- cgit v1.2.3 From fd0fc6fdd8896a195cb7b0210a5ee46774718fc8 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 25 Aug 2023 23:35:09 +0200 Subject: tls: move tls_cipher_size_desc to net/tls/tls.h It's only used in net/tls/*, no need to bloat include/net/tls.h. Signed-off-by: Sabrina Dubroca Link: https://lore.kernel.org/r/dd9fad80415e5b3575b41f56b331871038362eab.1692977948.git.sd@queasysnail.net Signed-off-by: Jakub Kicinski --- include/net/tls.h | 10 ---------- net/tls/tls.h | 10 ++++++++++ 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 06fca9160346..a2b44578dcb7 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -51,16 +51,6 @@ struct tls_rec; -struct tls_cipher_size_desc { - unsigned int iv; - unsigned int key; - unsigned int salt; - unsigned int tag; - unsigned int rec_seq; -}; - -extern const struct tls_cipher_size_desc tls_cipher_size_desc[]; - /* Maximum data size carried in a TLS record */ #define TLS_MAX_PAYLOAD_SIZE ((size_t)1 << 14) diff --git a/net/tls/tls.h b/net/tls/tls.h index 164d6a955e26..7aae92972e00 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -51,6 +51,16 @@ #define TLS_DEC_STATS(net, field) \ SNMP_DEC_STATS((net)->mib.tls_statistics, field) +struct tls_cipher_size_desc { + unsigned int iv; + unsigned int key; + unsigned int salt; + unsigned int tag; + unsigned int rec_seq; +}; + +extern const struct tls_cipher_size_desc tls_cipher_size_desc[]; + /* TLS records are maintained in 'struct tls_rec'. It stores the memory pages * allocated or mapped for each TLS record. After encryption, the records are * stores in a linked list. -- cgit v1.2.3 From 72f93a3136ee18fd59fa6579f84c07e93424681e Mon Sep 17 00:00:00 2001 From: Antonio Napolitano Date: Sat, 26 Aug 2023 01:05:50 +0200 Subject: r8152: add vendor/device ID pair for D-Link DUB-E250 The D-Link DUB-E250 is an RTL8156 based 2.5G Ethernet controller. Add the vendor and product ID values to the driver. This makes Ethernet work with the adapter. Signed-off-by: Antonio Napolitano Link: https://lore.kernel.org/r/CV200KJEEUPC.WPKAHXCQJ05I@mercurius Signed-off-by: Jakub Kicinski --- drivers/net/usb/r8152.c | 1 + include/linux/usb/r8152.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index bb234cf0cea0..332c853ca99b 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9832,6 +9832,7 @@ static const struct usb_device_id rtl8152_table[] = { { USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041) }, { USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff) }, { USB_DEVICE(VENDOR_ID_TPLINK, 0x0601) }, + { USB_DEVICE(VENDOR_ID_DLINK, 0xb301) }, {} }; diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 20d88b1defc3..287e9d83fb8b 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -29,6 +29,7 @@ #define VENDOR_ID_LINKSYS 0x13b1 #define VENDOR_ID_NVIDIA 0x0955 #define VENDOR_ID_TPLINK 0x2357 +#define VENDOR_ID_DLINK 0x2001 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); -- cgit v1.2.3 From a014c35556b9045ece8426df2b38eb3c5e1c1aa0 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Sat, 26 Aug 2023 11:02:51 +0100 Subject: net: stmmac: clarify difference between "interface" and "phy_interface" Clarify the difference between "interface" and "phy_interface" in struct plat_stmmacenet_data, both by adding a comment, and also renaming "interface" to be "mac_interface". The difference between these are: MAC ----- optional PCS ----- SerDes ----- optional PHY ----- Media ^ ^ mac_interface phy_interface Note that phylink currently only deals with phy_interface. Signed-off-by: Russell King (Oracle) Link: https://lore.kernel.org/r/E1qZq83-005tts-6K@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c | 14 +++++++------- drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c | 20 ++++++++++---------- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c | 8 ++++---- drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 6 +++--- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ++++-- .../net/ethernet/stmicro/stmmac/stmmac_platform.c | 6 +++--- include/linux/stmmac.h | 15 ++++++++++++++- 12 files changed, 52 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index 535856fffaea..df34e34cc14f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -70,7 +70,7 @@ static int imx8mp_set_intf_mode(struct plat_stmmacenet_data *plat_dat) struct imx_priv_data *dwmac = plat_dat->bsp_priv; int val; - switch (plat_dat->interface) { + switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_MII: val = GPR_ENET_QOS_INTF_SEL_MII; break; @@ -87,7 +87,7 @@ static int imx8mp_set_intf_mode(struct plat_stmmacenet_data *plat_dat) break; default: pr_debug("imx dwmac doesn't support %d interface\n", - plat_dat->interface); + plat_dat->mac_interface); return -EINVAL; } @@ -110,7 +110,7 @@ static int imx93_set_intf_mode(struct plat_stmmacenet_data *plat_dat) struct imx_priv_data *dwmac = plat_dat->bsp_priv; int val; - switch (plat_dat->interface) { + switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_MII: val = MX93_GPR_ENET_QOS_INTF_SEL_MII; break; @@ -125,7 +125,7 @@ static int imx93_set_intf_mode(struct plat_stmmacenet_data *plat_dat) break; default: dev_dbg(dwmac->dev, "imx dwmac doesn't support %d interface\n", - plat_dat->interface); + plat_dat->mac_interface); return -EINVAL; } @@ -192,8 +192,8 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod plat_dat = dwmac->plat_dat; if (dwmac->ops->mac_rgmii_txclk_auto_adj || - (plat_dat->interface == PHY_INTERFACE_MODE_RMII) || - (plat_dat->interface == PHY_INTERFACE_MODE_MII)) + (plat_dat->mac_interface == PHY_INTERFACE_MODE_RMII) || + (plat_dat->mac_interface == PHY_INTERFACE_MODE_MII)) return; switch (speed) { @@ -260,7 +260,7 @@ static int imx_dwmac_mx93_reset(void *priv, void __iomem *ioaddr) value |= DMA_BUS_MODE_SFT_RESET; writel(value, ioaddr + DMA_BUS_MODE); - if (plat_dat->interface == PHY_INTERFACE_MODE_RMII) { + if (plat_dat->mac_interface == PHY_INTERFACE_MODE_RMII) { usleep_range(100, 200); writel(RMII_RESET_SPEED, ioaddr + MAC_CTRL_REG); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c index e22ef0d6bc73..0a20c3d24722 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c @@ -89,7 +89,7 @@ static int jz4775_mac_set_mode(struct plat_stmmacenet_data *plat_dat) struct ingenic_mac *mac = plat_dat->bsp_priv; unsigned int val; - switch (plat_dat->interface) { + switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_MII: val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) | FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_MII); @@ -118,7 +118,7 @@ static int jz4775_mac_set_mode(struct plat_stmmacenet_data *plat_dat) break; default: - dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface); + dev_err(mac->dev, "Unsupported interface %d", plat_dat->mac_interface); return -EINVAL; } @@ -130,13 +130,13 @@ static int x1000_mac_set_mode(struct plat_stmmacenet_data *plat_dat) { struct ingenic_mac *mac = plat_dat->bsp_priv; - switch (plat_dat->interface) { + switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_RMII: dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); break; default: - dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface); + dev_err(mac->dev, "Unsupported interface %d", plat_dat->mac_interface); return -EINVAL; } @@ -149,14 +149,14 @@ static int x1600_mac_set_mode(struct plat_stmmacenet_data *plat_dat) struct ingenic_mac *mac = plat_dat->bsp_priv; unsigned int val; - switch (plat_dat->interface) { + switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_RMII: val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII); dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); break; default: - dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface); + dev_err(mac->dev, "Unsupported interface %d", plat_dat->mac_interface); return -EINVAL; } @@ -169,7 +169,7 @@ static int x1830_mac_set_mode(struct plat_stmmacenet_data *plat_dat) struct ingenic_mac *mac = plat_dat->bsp_priv; unsigned int val; - switch (plat_dat->interface) { + switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_RMII: val = FIELD_PREP(MACPHYC_MODE_SEL_MASK, MACPHYC_MODE_SEL_RMII) | FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII); @@ -177,7 +177,7 @@ static int x1830_mac_set_mode(struct plat_stmmacenet_data *plat_dat) break; default: - dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface); + dev_err(mac->dev, "Unsupported interface %d", plat_dat->mac_interface); return -EINVAL; } @@ -190,7 +190,7 @@ static int x2000_mac_set_mode(struct plat_stmmacenet_data *plat_dat) struct ingenic_mac *mac = plat_dat->bsp_priv; unsigned int val; - switch (plat_dat->interface) { + switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_RMII: val = FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_ORIGIN) | FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_ORIGIN) | @@ -220,7 +220,7 @@ static int x2000_mac_set_mode(struct plat_stmmacenet_data *plat_dat) break; default: - dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface); + dev_err(mac->dev, "Unsupported interface %d", plat_dat->mac_interface); return -EINVAL; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index a25c187d3185..2cd6fce5c993 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -117,7 +117,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id } plat->phy_interface = phy_mode; - plat->interface = PHY_INTERFACE_MODE_GMII; + plat->mac_interface = PHY_INTERFACE_MODE_GMII; pci_set_master(pdev); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c index 18e84ba693a6..d0aa674ce705 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c @@ -50,9 +50,9 @@ static int lpc18xx_dwmac_probe(struct platform_device *pdev) goto err_remove_config_dt; } - if (plat_dat->interface == PHY_INTERFACE_MODE_MII) { + if (plat_dat->mac_interface == PHY_INTERFACE_MODE_MII) { ethmode = LPC18XX_CREG_CREG6_ETHMODE_MII; - } else if (plat_dat->interface == PHY_INTERFACE_MODE_RMII) { + } else if (plat_dat->mac_interface == PHY_INTERFACE_MODE_RMII) { ethmode = LPC18XX_CREG_CREG6_ETHMODE_RMII; } else { dev_err(&pdev->dev, "Only MII and RMII mode supported\n"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index 7580077383c0..cd796ec04132 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -587,7 +587,7 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev, { int i; - plat->interface = priv_plat->phy_mode; + plat->mac_interface = priv_plat->phy_mode; if (priv_plat->mac_wol) plat->flags |= STMMAC_FLAG_USE_PHY_WOL; else diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 7db176e8691f..9bf102bbc6a0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -236,7 +236,7 @@ static int socfpga_get_plat_phymode(struct socfpga_dwmac *dwmac) struct net_device *ndev = dev_get_drvdata(dwmac->dev); struct stmmac_priv *priv = netdev_priv(ndev); - return priv->plat->interface; + return priv->plat->mac_interface; } static void socfpga_sgmii_config(struct socfpga_dwmac *dwmac, bool enable) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c index 892612564694..9289bb87c3e3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c @@ -60,7 +60,7 @@ static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat) unsigned int mode; int err; - switch (plat_dat->interface) { + switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_RMII: mode = STARFIVE_DWMAC_PHY_INFT_RMII; break; @@ -72,7 +72,7 @@ static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat) default: dev_err(dwmac->dev, "unsupported interface %d\n", - plat_dat->interface); + plat_dat->mac_interface); return -EINVAL; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index 3a09085819dc..26ea8c687881 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -171,7 +171,7 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat) clk_rate = clk_get_rate(dwmac->clk_eth_ck); dwmac->enable_eth_ck = false; - switch (plat_dat->interface) { + switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_MII: if (clk_rate == ETH_CK_F_25M && dwmac->ext_phyclk) dwmac->enable_eth_ck = true; @@ -210,7 +210,7 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat) break; default: pr_debug("SYSCFG init : Do not manage %d interface\n", - plat_dat->interface); + plat_dat->mac_interface); /* Do not manage others interfaces */ return -EINVAL; } @@ -230,7 +230,7 @@ static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat) u32 reg = dwmac->mode_reg; int val; - switch (plat_dat->interface) { + switch (plat_dat->mac_interface) { case PHY_INTERFACE_MODE_MII: val = SYSCFG_MCU_ETH_SEL_MII; pr_debug("SYSCFG init : PHY_INTERFACE_MODE_MII\n"); @@ -241,7 +241,7 @@ static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat) break; default: pr_debug("SYSCFG init : Do not manage %d interface\n", - plat_dat->interface); + plat_dat->mac_interface); /* Do not manage others interfaces */ return -EINVAL; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index c23420863a8d..01e77368eef1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1016,7 +1016,7 @@ static int sun8i_dwmac_set_syscon(struct device *dev, if (gmac->variant->support_rmii) reg &= ~SYSCON_RMII_EN; - switch (plat->interface) { + switch (plat->mac_interface) { case PHY_INTERFACE_MODE_MII: /* default */ break; @@ -1031,7 +1031,7 @@ static int sun8i_dwmac_set_syscon(struct device *dev, break; default: dev_err(dev, "Unsupported interface mode: %s", - phy_modes(plat->interface)); + phy_modes(plat->mac_interface)); return -EINVAL; } @@ -1231,7 +1231,7 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) /* platform data specifying hardware features and callbacks. * hardware features were copied from Allwinner drivers. */ - plat_dat->interface = interface; + plat_dat->mac_interface = interface; plat_dat->rx_coe = STMMAC_RX_COE_TYPE2; plat_dat->tx_coe = 1; plat_dat->flags |= STMMAC_FLAG_HAS_SUN8I; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 33ca5c50bdcd..9a3182b9e767 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1119,7 +1119,7 @@ static const struct phylink_mac_ops stmmac_phylink_mac_ops = { */ static void stmmac_check_pcs_mode(struct stmmac_priv *priv) { - int interface = priv->plat->interface; + int interface = priv->plat->mac_interface; if (priv->dma_cap.pcs) { if ((interface == PHY_INTERFACE_MODE_RGMII) || @@ -1214,7 +1214,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) priv->phylink_config.ovr_an_inband = mdio_bus_data->xpcs_an_inband; - /* Set the platform/firmware specified interface mode */ + /* Set the platform/firmware specified interface mode. Note, phylink + * deals with the PHY interface mode, not the MAC interface mode. + */ __set_bit(mode, priv->phylink_config.supported_interfaces); /* If we have an xpcs, it defines which PHY interfaces are supported. */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index ff330423ee66..35f4b1484029 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -419,9 +419,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) return ERR_PTR(phy_mode); plat->phy_interface = phy_mode; - plat->interface = stmmac_of_get_mac_mode(np); - if (plat->interface < 0) - plat->interface = plat->phy_interface; + plat->mac_interface = stmmac_of_get_mac_mode(np); + if (plat->mac_interface < 0) + plat->mac_interface = plat->phy_interface; /* Some wrapper drivers still rely on phy_node. Let's save it while * they are not converted to phylink. */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index b2ccd827bb80..ce89cc3e4913 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -223,7 +223,20 @@ struct dwmac4_addrs { struct plat_stmmacenet_data { int bus_id; int phy_addr; - int interface; + /* MAC ----- optional PCS ----- SerDes ----- optional PHY ----- Media + * ^ ^ + * mac_interface phy_interface + * + * mac_interface is the MAC-side interface, which may be the same + * as phy_interface if there is no intervening PCS. If there is a + * PCS, then mac_interface describes the interface mode between the + * MAC and PCS, and phy_interface describes the interface mode + * between the PCS and PHY. + */ + phy_interface_t mac_interface; + /* phy_interface is the PHY-side interface - the interface used by + * an attached PHY. + */ phy_interface_t phy_interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; -- cgit v1.2.3