From 133e1e5acd4a63c4a0dcc413e90d5decdbce9c4a Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Mon, 25 Jan 2016 18:04:15 -0500 Subject: audit: stop an old auditd being starved out by a new auditd Nothing prevents a new auditd starting up and replacing a valid audit_pid when an old auditd is still running, effectively starving out the old auditd since audit_pid no longer points to the old valid auditd. If no message to auditd has been attempted since auditd died unnaturally or got killed, audit_pid will still indicate it is alive. There isn't an easy way to detect if an old auditd is still running on the existing audit_pid other than attempting to send a message to see if it fails. An -ECONNREFUSED almost certainly means it disappeared and can be replaced. Other errors are not so straightforward and may indicate transient problems that will resolve themselves and the old auditd will recover. Yet others will likely need manual intervention for which a new auditd will not solve the problem. Send a new message type (AUDIT_REPLACE) to the old auditd containing a u32 with the PID of the new auditd. If the audit replace message succeeds (or doesn't fail with certainty), fail to register the new auditd and return an error (-EEXIST). This is expected to make the patch preventing an old auditd orphaning a new auditd redundant. V3: Switch audit message type from 1000 to 1300 block. Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- kernel/audit.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index d6dd95cc59e6..2fd63d6879c5 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -809,6 +809,16 @@ static int audit_set_feature(struct sk_buff *skb) return 0; } +static int audit_replace(pid_t pid) +{ + struct sk_buff *skb = audit_make_reply(0, 0, AUDIT_REPLACE, 0, 0, + &pid, sizeof(pid)); + + if (!skb) + return -ENOMEM; + return netlink_unicast(audit_sock, skb, audit_nlk_portid, 0); +} + static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { u32 seq; @@ -870,9 +880,13 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } if (s.mask & AUDIT_STATUS_PID) { int new_pid = s.pid; + pid_t requesting_pid = task_tgid_vnr(current); - if ((!new_pid) && (task_tgid_vnr(current) != audit_pid)) + if ((!new_pid) && (requesting_pid != audit_pid)) return -EACCES; + if (audit_pid && new_pid && + audit_replace(requesting_pid) != -ECONNREFUSED) + return -EEXIST; if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, audit_pid, 1); audit_pid = new_pid; -- cgit v1.2.3 From 935c9e7ff06abf12c45155f75ec2f712d3768095 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Mon, 25 Jan 2016 18:04:15 -0500 Subject: audit: log failed attempts to change audit_pid configuration Failed attempts to change the audit_pid configuration are not presently logged. One case is an attempt to starve an old auditd by starting up a new auditd when the old one is still alive and active. The other case is an attempt to orphan a new auditd when an old auditd shuts down. Log both as AUDIT_CONFIG_CHANGE messages with failure result. Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- kernel/audit.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index 2fd63d6879c5..8fa7533bf106 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -882,11 +882,15 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) int new_pid = s.pid; pid_t requesting_pid = task_tgid_vnr(current); - if ((!new_pid) && (requesting_pid != audit_pid)) + if ((!new_pid) && (requesting_pid != audit_pid)) { + audit_log_config_change("audit_pid", new_pid, audit_pid, 0); return -EACCES; + } if (audit_pid && new_pid && - audit_replace(requesting_pid) != -ECONNREFUSED) + audit_replace(requesting_pid) != -ECONNREFUSED) { + audit_log_config_change("audit_pid", new_pid, audit_pid, 0); return -EEXIST; + } if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, audit_pid, 1); audit_pid = new_pid; -- cgit v1.2.3 From 37282a77954aa2dbb339d15902290f25b868d2e8 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 22:55:31 -0800 Subject: tty: audit: Combine push functions tty_audit_push() and tty_audit_push_current() perform identical tasks; eliminate the tty_audit_push() implementation and the tty_audit_push_current() name. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_audit.c | 35 +++-------------------------------- include/linux/tty.h | 8 ++------ kernel/audit.c | 2 +- 3 files changed, 6 insertions(+), 39 deletions(-) (limited to 'kernel') diff --git a/drivers/tty/tty_audit.c b/drivers/tty/tty_audit.c index 5ae48396e265..6b82c3ce321f 100644 --- a/drivers/tty/tty_audit.c +++ b/drivers/tty/tty_audit.c @@ -172,12 +172,11 @@ void tty_audit_tiocsti(struct tty_struct *tty, char ch) } /** - * tty_audit_push_current - Flush current's pending audit data + * tty_audit_push - Flush current's pending audit data * - * Try to lock sighand and get a reference to the tty audit buffer if available. - * Flush the buffer or return an appropriate error code. + * Returns 0 if success, -EPERM if tty audit is disabled */ -int tty_audit_push_current(void) +int tty_audit_push(void) { struct tty_audit_buf *buf = ERR_PTR(-EPERM); unsigned long flags; @@ -309,31 +308,3 @@ void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size) mutex_unlock(&buf->mutex); tty_audit_buf_put(buf); } - -/** - * tty_audit_push - Push buffered data out - * - * Make sure no audit data is pending on the current process. - */ -void tty_audit_push(void) -{ - struct tty_audit_buf *buf; - unsigned long flags; - - spin_lock_irqsave(¤t->sighand->siglock, flags); - if (likely(!current->signal->audit_tty)) { - spin_unlock_irqrestore(¤t->sighand->siglock, flags); - return; - } - buf = current->signal->tty_audit_buf; - if (buf) - atomic_inc(&buf->count); - spin_unlock_irqrestore(¤t->sighand->siglock, flags); - - if (buf) { - mutex_lock(&buf->mutex); - tty_audit_buf_push(buf); - mutex_unlock(&buf->mutex); - tty_audit_buf_put(buf); - } -} diff --git a/include/linux/tty.h b/include/linux/tty.h index 83d74dcfb3c8..dea7d54d00d4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -597,8 +597,7 @@ extern void tty_audit_add_data(struct tty_struct *tty, const void *data, extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); -extern void tty_audit_push(void); -extern int tty_audit_push_current(void); +extern int tty_audit_push(void); #else static inline void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size) @@ -613,10 +612,7 @@ static inline void tty_audit_exit(void) static inline void tty_audit_fork(struct signal_struct *sig) { } -static inline void tty_audit_push(void) -{ -} -static inline int tty_audit_push_current(void) +static inline int tty_audit_push(void) { return 0; } diff --git a/kernel/audit.c b/kernel/audit.c index 3a3e5deeda8d..610f221df069 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -920,7 +920,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (err == 1) { /* match or error */ err = 0; if (msg_type == AUDIT_USER_TTY) { - err = tty_audit_push_current(); + err = tty_audit_push(); if (err) break; } -- cgit v1.2.3 From 2e28d38ae1d9ced6ac2deb4001aca3f267304cdb Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 22:55:33 -0800 Subject: tty: audit: Handle tty audit enable atomically The audit_tty and audit_tty_log_passwd fields are actually bool values, so merge into single memory location to access atomically. NB: audit log operations may still occur after tty audit is disabled which is consistent with the existing functionality Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_audit.c | 53 ++++++++++++++++++++----------------------------- include/linux/audit.h | 4 ++++ include/linux/sched.h | 1 - kernel/audit.c | 25 +++++++++++------------ 4 files changed, 38 insertions(+), 45 deletions(-) (limited to 'kernel') diff --git a/drivers/tty/tty_audit.c b/drivers/tty/tty_audit.c index 50380d87061d..3d90f88c5ff9 100644 --- a/drivers/tty/tty_audit.c +++ b/drivers/tty/tty_audit.c @@ -131,7 +131,6 @@ void tty_audit_exit(void) void tty_audit_fork(struct signal_struct *sig) { sig->audit_tty = current->signal->audit_tty; - sig->audit_tty_log_passwd = current->signal->audit_tty_log_passwd; } /** @@ -141,11 +140,9 @@ void tty_audit_tiocsti(struct tty_struct *tty, char ch) { struct tty_audit_buf *buf; dev_t dev; - int should_audit; unsigned long flags; spin_lock_irqsave(¤t->sighand->siglock, flags); - should_audit = current->signal->audit_tty; buf = current->signal->tty_audit_buf; if (buf) atomic_inc(&buf->count); @@ -160,7 +157,7 @@ void tty_audit_tiocsti(struct tty_struct *tty, char ch) tty_audit_buf_put(buf); } - if (should_audit && audit_enabled) { + if (audit_enabled && (current->signal->audit_tty & AUDIT_TTY_ENABLE)) { kuid_t auid; unsigned int sessionid; @@ -177,29 +174,25 @@ void tty_audit_tiocsti(struct tty_struct *tty, char ch) */ int tty_audit_push(void) { - struct tty_audit_buf *buf = ERR_PTR(-EPERM); + struct tty_audit_buf *buf; unsigned long flags; + if (~current->signal->audit_tty & AUDIT_TTY_ENABLE) + return -EPERM; + spin_lock_irqsave(¤t->sighand->siglock, flags); - if (current->signal->audit_tty) { - buf = current->signal->tty_audit_buf; - if (buf) - atomic_inc(&buf->count); - } + buf = current->signal->tty_audit_buf; + if (buf) + atomic_inc(&buf->count); spin_unlock_irqrestore(¤t->sighand->siglock, flags); - /* - * Return 0 when signal->audit_tty set - * but current->signal->tty_audit_buf == NULL. - */ - if (!buf || IS_ERR(buf)) - return PTR_ERR(buf); - - mutex_lock(&buf->mutex); - tty_audit_buf_push(buf); - mutex_unlock(&buf->mutex); + if (buf) { + mutex_lock(&buf->mutex); + tty_audit_buf_push(buf); + mutex_unlock(&buf->mutex); - tty_audit_buf_put(buf); + tty_audit_buf_put(buf); + } return 0; } @@ -218,8 +211,6 @@ static struct tty_audit_buf *tty_audit_buf_get(void) buf = NULL; buf2 = NULL; spin_lock_irqsave(¤t->sighand->siglock, flags); - if (likely(!current->signal->audit_tty)) - goto out; buf = current->signal->tty_audit_buf; if (buf) { atomic_inc(&buf->count); @@ -233,9 +224,10 @@ static struct tty_audit_buf *tty_audit_buf_get(void) return NULL; } - spin_lock_irqsave(¤t->sighand->siglock, flags); - if (!current->signal->audit_tty) + if (~current->signal->audit_tty & AUDIT_TTY_ENABLE) goto out; + + spin_lock_irqsave(¤t->sighand->siglock, flags); buf = current->signal->tty_audit_buf; if (!buf) { current->signal->tty_audit_buf = buf2; @@ -259,9 +251,8 @@ static struct tty_audit_buf *tty_audit_buf_get(void) void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size) { struct tty_audit_buf *buf; - int audit_log_tty_passwd; - unsigned long flags; unsigned int icanon = !!L_ICANON(tty); + unsigned int audit_tty; dev_t dev; if (unlikely(size == 0)) @@ -271,10 +262,10 @@ void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size) && tty->driver->subtype == PTY_TYPE_MASTER) return; - spin_lock_irqsave(¤t->sighand->siglock, flags); - audit_log_tty_passwd = current->signal->audit_tty_log_passwd; - spin_unlock_irqrestore(¤t->sighand->siglock, flags); - if (!audit_log_tty_passwd && icanon && !L_ECHO(tty)) + audit_tty = READ_ONCE(current->signal->audit_tty); + if (~audit_tty & AUDIT_TTY_ENABLE) + return; + if ((~audit_tty & AUDIT_TTY_LOG_PASSWD) && icanon && !L_ECHO(tty)) return; buf = tty_audit_buf_get(); diff --git a/include/linux/audit.h b/include/linux/audit.h index b40ed5df5542..e38e3fc13ea8 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -109,6 +109,10 @@ extern int audit_classify_compat_syscall(int abi, unsigned syscall); /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 +/* bit values for ->signal->audit_tty */ +#define AUDIT_TTY_ENABLE BIT(0) +#define AUDIT_TTY_LOG_PASSWD BIT(1) + struct filename; extern void audit_log_session_info(struct audit_buffer *ab); diff --git a/include/linux/sched.h b/include/linux/sched.h index a10494a94cc3..a389222e9703 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -775,7 +775,6 @@ struct signal_struct { #endif #ifdef CONFIG_AUDIT unsigned audit_tty; - unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif diff --git a/kernel/audit.c b/kernel/audit.c index 610f221df069..2651e423b2dc 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1030,20 +1030,19 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) break; case AUDIT_TTY_GET: { struct audit_tty_status s; - struct task_struct *tsk = current; + unsigned int t; - spin_lock(&tsk->sighand->siglock); - s.enabled = tsk->signal->audit_tty; - s.log_passwd = tsk->signal->audit_tty_log_passwd; - spin_unlock(&tsk->sighand->siglock); + t = READ_ONCE(current->signal->audit_tty); + s.enabled = t & AUDIT_TTY_ENABLE; + s.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD); audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_TTY_SET: { struct audit_tty_status s, old; - struct task_struct *tsk = current; struct audit_buffer *ab; + unsigned int t; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ @@ -1053,14 +1052,14 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) (s.log_passwd != 0 && s.log_passwd != 1)) err = -EINVAL; - spin_lock(&tsk->sighand->siglock); - old.enabled = tsk->signal->audit_tty; - old.log_passwd = tsk->signal->audit_tty_log_passwd; - if (!err) { - tsk->signal->audit_tty = s.enabled; - tsk->signal->audit_tty_log_passwd = s.log_passwd; + if (err) + t = READ_ONCE(current->signal->audit_tty); + else { + t = s.enabled | (-s.log_passwd & AUDIT_TTY_LOG_PASSWD); + t = xchg(¤t->signal->audit_tty, t); } - spin_unlock(&tsk->sighand->siglock); + old.enabled = t & AUDIT_TTY_ENABLE; + old.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD); audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=tty_set old-enabled=%d new-enabled=%d" -- cgit v1.2.3 From e11b956e9ebef098cc4f81964a1f57e40fe75cd4 Mon Sep 17 00:00:00 2001 From: Li Bin Date: Sat, 30 Jan 2016 11:54:03 +0800 Subject: kernel/Makefile: remove the useless CFLAGS_REMOVE_cgroup-debug.o The file cgroup-debug.c had been removed from commit fe6934354f8e (cgroups: move the cgroup debug subsys into cgroup.c to access internal state). Remain the CFLAGS_REMOVE_cgroup-debug.o = $(CC_FLAGS_FTRACE) useless in kernel/Makefile. Signed-off-by: Li Bin Acked-by: Zefan Li Signed-off-by: Tejun Heo --- kernel/Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/Makefile b/kernel/Makefile index 53abf008ecb3..baa55e50a315 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -14,8 +14,7 @@ obj-y = fork.o exec_domain.o panic.o \ obj-$(CONFIG_MULTIUSER) += groups.o ifdef CONFIG_FUNCTION_TRACER -# Do not trace debug files and internal ftrace files -CFLAGS_REMOVE_cgroup-debug.o = $(CC_FLAGS_FTRACE) +# Do not trace internal ftrace files CFLAGS_REMOVE_irq_work.o = $(CC_FLAGS_FTRACE) endif -- cgit v1.2.3 From 0306e481d479a58eff17c27adf213fbb5822946b Mon Sep 17 00:00:00 2001 From: Shilpasri G Bhat Date: Wed, 3 Feb 2016 01:11:40 +0530 Subject: cpufreq: powernv/tracing: Add powernv_throttle tracepoint This patch adds the powernv_throttle tracepoint to trace the CPU frequency throttling event, which is used by the powernv-cpufreq driver in POWER8. Signed-off-by: Shilpasri G Bhat Reviewed-by: Gautham R. Shenoy Signed-off-by: Rafael J. Wysocki --- include/trace/events/power.h | 22 ++++++++++++++++++++++ kernel/trace/power-traces.c | 1 + 2 files changed, 23 insertions(+) (limited to 'kernel') diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 284244ebfe8d..19e50300ce7d 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -38,6 +38,28 @@ DEFINE_EVENT(cpu, cpu_idle, TP_ARGS(state, cpu_id) ); +TRACE_EVENT(powernv_throttle, + + TP_PROTO(int chip_id, const char *reason, int pmax), + + TP_ARGS(chip_id, reason, pmax), + + TP_STRUCT__entry( + __field(int, chip_id) + __string(reason, reason) + __field(int, pmax) + ), + + TP_fast_assign( + __entry->chip_id = chip_id; + __assign_str(reason, reason); + __entry->pmax = pmax; + ), + + TP_printk("Chip %d Pmax %d %s", __entry->chip_id, + __entry->pmax, __get_str(reason)) +); + TRACE_EVENT(pstate_sample, TP_PROTO(u32 core_busy, diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c index eb4220a132ec..81b87451c0ea 100644 --- a/kernel/trace/power-traces.c +++ b/kernel/trace/power-traces.c @@ -15,4 +15,5 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume); EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle); +EXPORT_TRACEPOINT_SYMBOL_GPL(powernv_throttle); -- cgit v1.2.3 From 824bd0ce6c7c43a9e1e210abf124958e54d88342 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 1 Feb 2016 22:39:53 -0800 Subject: bpf: introduce BPF_MAP_TYPE_PERCPU_HASH map Introduce BPF_MAP_TYPE_PERCPU_HASH map type which is used to do accurate counters without need to use BPF_XADD instruction which turned out to be too costly for high-performance network monitoring. In the typical use case the 'key' is the flow tuple or other long living object that sees a lot of events per second. bpf_map_lookup_elem() returns per-cpu area. Example: struct { u32 packets; u32 bytes; } * ptr = bpf_map_lookup_elem(&map, &key); /* ptr points to this_cpu area of the value, so the following * increments will not collide with other cpus */ ptr->packets ++; ptr->bytes += skb->len; bpf_update_elem() atomically creates a new element where all per-cpu values are zero initialized and this_cpu value is populated with given 'value'. Note that non-per-cpu hash map always allocates new element and then deletes old after rcu grace period to maintain atomicity of update. Per-cpu hash map updates element values in-place. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + kernel/bpf/hashtab.c | 275 +++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 229 insertions(+), 47 deletions(-) (limited to 'kernel') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index aa6f8571de13..43ae40c8763e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -81,6 +81,7 @@ enum bpf_map_type { BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PROG_ARRAY, BPF_MAP_TYPE_PERF_EVENT_ARRAY, + BPF_MAP_TYPE_PERCPU_HASH, }; enum bpf_prog_type { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index c5b30fd8a315..2be5f6e8bb04 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -31,21 +31,27 @@ struct bpf_htab { struct htab_elem { struct hlist_node hash_node; struct rcu_head rcu; - u32 hash; + union { + u32 hash; + u32 key_size; + }; char key[0] __aligned(8); }; /* Called from syscall */ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { + bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_HASH; struct bpf_htab *htab; int err, i; + u64 cost; htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) return ERR_PTR(-ENOMEM); /* mandatory map attributes */ + htab->map.map_type = attr->map_type; htab->map.key_size = attr->key_size; htab->map.value_size = attr->value_size; htab->map.max_entries = attr->max_entries; @@ -77,24 +83,34 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ goto free_htab; + if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE) + /* make sure the size for pcpu_alloc() is reasonable */ + goto free_htab; + htab->elem_size = sizeof(struct htab_elem) + - round_up(htab->map.key_size, 8) + - htab->map.value_size; + round_up(htab->map.key_size, 8); + if (percpu) + htab->elem_size += sizeof(void *); + else + htab->elem_size += htab->map.value_size; /* prevent zero size kmalloc and check for u32 overflow */ if (htab->n_buckets == 0 || htab->n_buckets > U32_MAX / sizeof(struct bucket)) goto free_htab; - if ((u64) htab->n_buckets * sizeof(struct bucket) + - (u64) htab->elem_size * htab->map.max_entries >= - U32_MAX - PAGE_SIZE) + cost = (u64) htab->n_buckets * sizeof(struct bucket) + + (u64) htab->elem_size * htab->map.max_entries; + + if (percpu) + cost += (u64) round_up(htab->map.value_size, 8) * + num_possible_cpus() * htab->map.max_entries; + + if (cost >= U32_MAX - PAGE_SIZE) /* make sure page count doesn't overflow */ goto free_htab; - htab->map.pages = round_up(htab->n_buckets * sizeof(struct bucket) + - htab->elem_size * htab->map.max_entries, - PAGE_SIZE) >> PAGE_SHIFT; + htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; err = -ENOMEM; htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket), @@ -148,7 +164,7 @@ static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash, } /* Called from syscall or from eBPF program */ -static void *htab_map_lookup_elem(struct bpf_map *map, void *key) +static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_head *head; @@ -166,6 +182,13 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key) l = lookup_elem_raw(head, hash, key, key_size); + return l; +} + +static void *htab_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct htab_elem *l = __htab_map_lookup_elem(map, key); + if (l) return l->key + round_up(map->key_size, 8); @@ -230,65 +253,139 @@ find_first_elem: return -ENOENT; } + +static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, + void __percpu *pptr) +{ + *(void __percpu **)(l->key + key_size) = pptr; +} + +static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size) +{ + return *(void __percpu **)(l->key + key_size); +} + +static void htab_percpu_elem_free(struct htab_elem *l) +{ + free_percpu(htab_elem_get_ptr(l, l->key_size)); + kfree(l); +} + +static void htab_percpu_elem_free_rcu(struct rcu_head *head) +{ + struct htab_elem *l = container_of(head, struct htab_elem, rcu); + + htab_percpu_elem_free(l); +} + +static void free_htab_elem(struct htab_elem *l, bool percpu, u32 key_size) +{ + if (percpu) { + l->key_size = key_size; + call_rcu(&l->rcu, htab_percpu_elem_free_rcu); + } else { + kfree_rcu(l, rcu); + } +} + +static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, + void *value, u32 key_size, u32 hash, + bool percpu) +{ + u32 size = htab->map.value_size; + struct htab_elem *l_new; + void __percpu *pptr; + + l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (!l_new) + return NULL; + + memcpy(l_new->key, key, key_size); + if (percpu) { + /* round up value_size to 8 bytes */ + size = round_up(size, 8); + + /* alloc_percpu zero-fills */ + pptr = __alloc_percpu_gfp(size, 8, GFP_ATOMIC | __GFP_NOWARN); + if (!pptr) { + kfree(l_new); + return NULL; + } + + /* copy true value_size bytes */ + memcpy(this_cpu_ptr(pptr), value, htab->map.value_size); + htab_elem_set_ptr(l_new, key_size, pptr); + } else { + memcpy(l_new->key + round_up(key_size, 8), value, size); + } + + l_new->hash = hash; + return l_new; +} + +static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, + u64 map_flags) +{ + if (!l_old && unlikely(atomic_read(&htab->count) >= htab->map.max_entries)) + /* if elem with this 'key' doesn't exist and we've reached + * max_entries limit, fail insertion of new elem + */ + return -E2BIG; + + if (l_old && map_flags == BPF_NOEXIST) + /* elem already exists */ + return -EEXIST; + + if (!l_old && map_flags == BPF_EXIST) + /* elem doesn't exist, cannot update it */ + return -ENOENT; + + return 0; +} + /* Called from syscall or from eBPF program */ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct htab_elem *l_new, *l_old; + struct htab_elem *l_new = NULL, *l_old; struct hlist_head *head; - struct bucket *b; unsigned long flags; - u32 key_size; + struct bucket *b; + u32 key_size, hash; int ret; - if (map_flags > BPF_EXIST) + if (unlikely(map_flags > BPF_EXIST)) /* unknown flags */ return -EINVAL; WARN_ON_ONCE(!rcu_read_lock_held()); - /* allocate new element outside of lock */ - l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (!l_new) - return -ENOMEM; - key_size = map->key_size; - memcpy(l_new->key, key, key_size); - memcpy(l_new->key + round_up(key_size, 8), value, map->value_size); + hash = htab_map_hash(key, key_size); + + /* allocate new element outside of the lock, since + * we're most likley going to insert it + */ + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false); + if (!l_new) + return -ENOMEM; - l_new->hash = htab_map_hash(l_new->key, key_size); - b = __select_bucket(htab, l_new->hash); + b = __select_bucket(htab, hash); head = &b->head; /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); - l_old = lookup_elem_raw(head, l_new->hash, key, key_size); + l_old = lookup_elem_raw(head, hash, key, key_size); - if (!l_old && unlikely(atomic_read(&htab->count) >= map->max_entries)) { - /* if elem with this 'key' doesn't exist and we've reached - * max_entries limit, fail insertion of new elem - */ - ret = -E2BIG; + ret = check_flags(htab, l_old, map_flags); + if (ret) goto err; - } - if (l_old && map_flags == BPF_NOEXIST) { - /* elem already exists */ - ret = -EEXIST; - goto err; - } - - if (!l_old && map_flags == BPF_EXIST) { - /* elem doesn't exist, cannot update it */ - ret = -ENOENT; - goto err; - } - - /* add new element to the head of the list, so that concurrent - * search will find it before old elem + /* add new element to the head of the list, so that + * concurrent search will find it before old elem */ hlist_add_head_rcu(&l_new->hash_node, head); if (l_old) { @@ -298,7 +395,6 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, atomic_inc(&htab->count); } raw_spin_unlock_irqrestore(&b->lock, flags); - return 0; err: raw_spin_unlock_irqrestore(&b->lock, flags); @@ -306,10 +402,64 @@ err: return ret; } +static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct htab_elem *l_new = NULL, *l_old; + struct hlist_head *head; + unsigned long flags; + struct bucket *b; + u32 key_size, hash; + int ret; + + if (unlikely(map_flags > BPF_EXIST)) + /* unknown flags */ + return -EINVAL; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + key_size = map->key_size; + + hash = htab_map_hash(key, key_size); + + b = __select_bucket(htab, hash); + head = &b->head; + + /* bpf_map_update_elem() can be called in_irq() */ + raw_spin_lock_irqsave(&b->lock, flags); + + l_old = lookup_elem_raw(head, hash, key, key_size); + + ret = check_flags(htab, l_old, map_flags); + if (ret) + goto err; + + if (l_old) { + /* per-cpu hash map can update value in-place */ + memcpy(this_cpu_ptr(htab_elem_get_ptr(l_old, key_size)), + value, htab->map.value_size); + } else { + l_new = alloc_htab_elem(htab, key, value, key_size, + hash, true); + if (!l_new) { + ret = -ENOMEM; + goto err; + } + hlist_add_head_rcu(&l_new->hash_node, head); + atomic_inc(&htab->count); + } + ret = 0; +err: + raw_spin_unlock_irqrestore(&b->lock, flags); + return ret; +} + /* Called from syscall or from eBPF program */ static int htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + bool percpu = map->map_type == BPF_MAP_TYPE_PERCPU_HASH; struct hlist_head *head; struct bucket *b; struct htab_elem *l; @@ -332,7 +482,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) if (l) { hlist_del_rcu(&l->hash_node); atomic_dec(&htab->count); - kfree_rcu(l, rcu); + free_htab_elem(l, percpu, key_size); ret = 0; } @@ -352,7 +502,12 @@ static void delete_all_elements(struct bpf_htab *htab) hlist_for_each_entry_safe(l, n, head, hash_node) { hlist_del_rcu(&l->hash_node); atomic_dec(&htab->count); - kfree(l); + if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) { + l->key_size = htab->map.key_size; + htab_percpu_elem_free(l); + } else { + kfree(l); + } } } } @@ -391,9 +546,35 @@ static struct bpf_map_type_list htab_type __read_mostly = { .type = BPF_MAP_TYPE_HASH, }; +/* Called from eBPF program */ +static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct htab_elem *l = __htab_map_lookup_elem(map, key); + + if (l) + return this_cpu_ptr(htab_elem_get_ptr(l, map->key_size)); + else + return NULL; +} + +static const struct bpf_map_ops htab_percpu_ops = { + .map_alloc = htab_map_alloc, + .map_free = htab_map_free, + .map_get_next_key = htab_map_get_next_key, + .map_lookup_elem = htab_percpu_map_lookup_elem, + .map_update_elem = htab_percpu_map_update_elem, + .map_delete_elem = htab_map_delete_elem, +}; + +static struct bpf_map_type_list htab_percpu_type __read_mostly = { + .ops = &htab_percpu_ops, + .type = BPF_MAP_TYPE_PERCPU_HASH, +}; + static int __init register_htab_map(void) { bpf_register_map_type(&htab_type); + bpf_register_map_type(&htab_percpu_type); return 0; } late_initcall(register_htab_map); -- cgit v1.2.3 From a10423b87a7eae75da79ce80a8d9475047a674ee Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 1 Feb 2016 22:39:54 -0800 Subject: bpf: introduce BPF_MAP_TYPE_PERCPU_ARRAY map Primary use case is a histogram array of latency where bpf program computes the latency of block requests or other events and stores histogram of latency into array of 64 elements. All cpus are constantly running, so normal increment is not accurate, bpf_xadd causes cache ping-pong and this per-cpu approach allows fastest collision-free counters. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/arraymap.c | 102 ++++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 93 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 83d1926c61e4..141fb0d45731 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -151,6 +151,7 @@ struct bpf_array { union { char value[0] __aligned(8); void *ptrs[0] __aligned(8); + void __percpu *pptrs[0] __aligned(8); }; }; #define MAX_TAIL_CALL_CNT 32 diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 43ae40c8763e..2ee0fde1bf96 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -82,6 +82,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PROG_ARRAY, BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_MAP_TYPE_PERCPU_HASH, + BPF_MAP_TYPE_PERCPU_ARRAY, }; enum bpf_prog_type { diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 89ebbc4d1164..b9bf1d7949ca 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -17,11 +17,39 @@ #include #include +static void bpf_array_free_percpu(struct bpf_array *array) +{ + int i; + + for (i = 0; i < array->map.max_entries; i++) + free_percpu(array->pptrs[i]); +} + +static int bpf_array_alloc_percpu(struct bpf_array *array) +{ + void __percpu *ptr; + int i; + + for (i = 0; i < array->map.max_entries; i++) { + ptr = __alloc_percpu_gfp(array->elem_size, 8, + GFP_USER | __GFP_NOWARN); + if (!ptr) { + bpf_array_free_percpu(array); + return -ENOMEM; + } + array->pptrs[i] = ptr; + } + + return 0; +} + /* Called from syscall */ static struct bpf_map *array_map_alloc(union bpf_attr *attr) { + bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; struct bpf_array *array; - u32 elem_size, array_size; + u64 array_size; + u32 elem_size; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -36,12 +64,16 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) elem_size = round_up(attr->value_size, 8); - /* check round_up into zero and u32 overflow */ - if (elem_size == 0 || - attr->max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size) + array_size = sizeof(*array); + if (percpu) + array_size += (u64) attr->max_entries * sizeof(void *); + else + array_size += (u64) attr->max_entries * elem_size; + + /* make sure there is no u32 overflow later in round_up() */ + if (array_size >= U32_MAX - PAGE_SIZE) return ERR_PTR(-ENOMEM); - array_size = sizeof(*array) + attr->max_entries * elem_size; /* allocate all map elements and zero-initialize them */ array = kzalloc(array_size, GFP_USER | __GFP_NOWARN); @@ -52,12 +84,25 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) } /* copy mandatory map attributes */ + array->map.map_type = attr->map_type; array->map.key_size = attr->key_size; array->map.value_size = attr->value_size; array->map.max_entries = attr->max_entries; - array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT; array->elem_size = elem_size; + if (!percpu) + goto out; + + array_size += (u64) attr->max_entries * elem_size * num_possible_cpus(); + + if (array_size >= U32_MAX - PAGE_SIZE || + elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) { + kvfree(array); + return ERR_PTR(-ENOMEM); + } +out: + array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT; + return &array->map; } @@ -67,12 +112,24 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; - if (index >= array->map.max_entries) + if (unlikely(index >= array->map.max_entries)) return NULL; return array->value + array->elem_size * index; } +/* Called from eBPF program */ +static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + + if (unlikely(index >= array->map.max_entries)) + return NULL; + + return this_cpu_ptr(array->pptrs[index]); +} + /* Called from syscall */ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { @@ -99,19 +156,24 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; - if (map_flags > BPF_EXIST) + if (unlikely(map_flags > BPF_EXIST)) /* unknown flags */ return -EINVAL; - if (index >= array->map.max_entries) + if (unlikely(index >= array->map.max_entries)) /* all elements were pre-allocated, cannot insert a new one */ return -E2BIG; - if (map_flags == BPF_NOEXIST) + if (unlikely(map_flags == BPF_NOEXIST)) /* all elements already exist */ return -EEXIST; - memcpy(array->value + array->elem_size * index, value, map->value_size); + if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + memcpy(this_cpu_ptr(array->pptrs[index]), + value, map->value_size); + else + memcpy(array->value + array->elem_size * index, + value, map->value_size); return 0; } @@ -133,6 +195,9 @@ static void array_map_free(struct bpf_map *map) */ synchronize_rcu(); + if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + bpf_array_free_percpu(array); + kvfree(array); } @@ -150,9 +215,24 @@ static struct bpf_map_type_list array_type __read_mostly = { .type = BPF_MAP_TYPE_ARRAY, }; +static const struct bpf_map_ops percpu_array_ops = { + .map_alloc = array_map_alloc, + .map_free = array_map_free, + .map_get_next_key = array_map_get_next_key, + .map_lookup_elem = percpu_array_map_lookup_elem, + .map_update_elem = array_map_update_elem, + .map_delete_elem = array_map_delete_elem, +}; + +static struct bpf_map_type_list percpu_array_type __read_mostly = { + .ops = &percpu_array_ops, + .type = BPF_MAP_TYPE_PERCPU_ARRAY, +}; + static int __init register_array_map(void) { bpf_register_map_type(&array_type); + bpf_register_map_type(&percpu_array_type); return 0; } late_initcall(register_array_map); -- cgit v1.2.3 From 15a07b33814d14ca817887dbea8530728dc0fbe4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 1 Feb 2016 22:39:55 -0800 Subject: bpf: add lookup/update support for per-cpu hash and array maps The functions bpf_map_lookup_elem(map, key, value) and bpf_map_update_elem(map, key, value, flags) need to get/set values from all-cpus for per-cpu hash and array maps, so that user space can aggregate/update them as necessary. Example of single counter aggregation in user space: unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); long values[nr_cpus]; long value = 0; bpf_lookup_elem(fd, key, values); for (i = 0; i < nr_cpus; i++) value += values[i]; The user space must provide round_up(value_size, 8) * nr_cpus array to get/set values, since kernel will use 'long' copy of per-cpu values to try to copy good counters atomically. It's a best-effort, since bpf programs and user space are racing to access the same memory. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 23 ++++++++++++++ kernel/bpf/arraymap.c | 64 +++++++++++++++++++++++++++++++++++++++ kernel/bpf/hashtab.c | 83 +++++++++++++++++++++++++++++++++++++++++++++------ kernel/bpf/syscall.c | 57 ++++++++++++++++++++++++----------- 4 files changed, 201 insertions(+), 26 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 141fb0d45731..90ee6ab24bc5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -183,6 +183,29 @@ int bpf_prog_new_fd(struct bpf_prog *prog); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname); +int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); +int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); +int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, + u64 flags); +int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, + u64 flags); + +/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and + * forced to use 'long' read/writes to try to atomically copy long counters. + * Best-effort only. No barriers here, since it _will_ race with concurrent + * updates from BPF programs. Called from bpf syscall and mostly used with + * size 8 or 16 bytes, so ask compiler to inline it. + */ +static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) +{ + const long *lsrc = src; + long *ldst = dst; + + size /= sizeof(long); + while (size--) + *ldst++ = *lsrc++; +} + /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index b9bf1d7949ca..bd3bdf2486a7 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -130,6 +130,32 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) return this_cpu_ptr(array->pptrs[index]); } +int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + void __percpu *pptr; + int cpu, off = 0; + u32 size; + + if (unlikely(index >= array->map.max_entries)) + return -ENOENT; + + /* per_cpu areas are zero-filled and bpf programs can only + * access 'value_size' of them, so copying rounded areas + * will not leak any kernel data + */ + size = round_up(map->value_size, 8); + rcu_read_lock(); + pptr = array->pptrs[index]; + for_each_possible_cpu(cpu) { + bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size); + off += size; + } + rcu_read_unlock(); + return 0; +} + /* Called from syscall */ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { @@ -177,6 +203,44 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, return 0; } +int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + void __percpu *pptr; + int cpu, off = 0; + u32 size; + + if (unlikely(map_flags > BPF_EXIST)) + /* unknown flags */ + return -EINVAL; + + if (unlikely(index >= array->map.max_entries)) + /* all elements were pre-allocated, cannot insert a new one */ + return -E2BIG; + + if (unlikely(map_flags == BPF_NOEXIST)) + /* all elements already exist */ + return -EEXIST; + + /* the user space will provide round_up(value_size, 8) bytes that + * will be copied into per-cpu area. bpf programs can only access + * value_size of it. During lookup the same extra bytes will be + * returned or zeros which were zero-filled by percpu_alloc, + * so no kernel data leaks possible + */ + size = round_up(map->value_size, 8); + rcu_read_lock(); + pptr = array->pptrs[index]; + for_each_possible_cpu(cpu) { + bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size); + off += size; + } + rcu_read_unlock(); + return 0; +} + /* Called from syscall or from eBPF program */ static int array_map_delete_elem(struct bpf_map *map, void *key) { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 2be5f6e8bb04..fd5db8fe9360 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -290,7 +290,7 @@ static void free_htab_elem(struct htab_elem *l, bool percpu, u32 key_size) static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, - bool percpu) + bool percpu, bool onallcpus) { u32 size = htab->map.value_size; struct htab_elem *l_new; @@ -312,8 +312,18 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, return NULL; } - /* copy true value_size bytes */ - memcpy(this_cpu_ptr(pptr), value, htab->map.value_size); + if (!onallcpus) { + /* copy true value_size bytes */ + memcpy(this_cpu_ptr(pptr), value, htab->map.value_size); + } else { + int off = 0, cpu; + + for_each_possible_cpu(cpu) { + bpf_long_memcpy(per_cpu_ptr(pptr, cpu), + value + off, size); + off += size; + } + } htab_elem_set_ptr(l_new, key_size, pptr); } else { memcpy(l_new->key + round_up(key_size, 8), value, size); @@ -368,7 +378,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, /* allocate new element outside of the lock, since * we're most likley going to insert it */ - l_new = alloc_htab_elem(htab, key, value, key_size, hash, false); + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); if (!l_new) return -ENOMEM; @@ -402,8 +412,9 @@ err: return ret; } -static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags, + bool onallcpus) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; @@ -436,12 +447,25 @@ static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, goto err; if (l_old) { + void __percpu *pptr = htab_elem_get_ptr(l_old, key_size); + u32 size = htab->map.value_size; + /* per-cpu hash map can update value in-place */ - memcpy(this_cpu_ptr(htab_elem_get_ptr(l_old, key_size)), - value, htab->map.value_size); + if (!onallcpus) { + memcpy(this_cpu_ptr(pptr), value, size); + } else { + int off = 0, cpu; + + size = round_up(size, 8); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(per_cpu_ptr(pptr, cpu), + value + off, size); + off += size; + } + } } else { l_new = alloc_htab_elem(htab, key, value, key_size, - hash, true); + hash, true, onallcpus); if (!l_new) { ret = -ENOMEM; goto err; @@ -455,6 +479,12 @@ err: return ret; } +static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + return __htab_percpu_map_update_elem(map, key, value, map_flags, false); +} + /* Called from syscall or from eBPF program */ static int htab_map_delete_elem(struct bpf_map *map, void *key) { @@ -557,6 +587,41 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) +{ + struct htab_elem *l; + void __percpu *pptr; + int ret = -ENOENT; + int cpu, off = 0; + u32 size; + + /* per_cpu areas are zero-filled and bpf programs can only + * access 'value_size' of them, so copying rounded areas + * will not leak any kernel data + */ + size = round_up(map->value_size, 8); + rcu_read_lock(); + l = __htab_map_lookup_elem(map, key); + if (!l) + goto out; + pptr = htab_elem_get_ptr(l, map->key_size); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(value + off, + per_cpu_ptr(pptr, cpu), size); + off += size; + } + ret = 0; +out: + rcu_read_unlock(); + return ret; +} + +int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __htab_percpu_map_update_elem(map, key, value, map_flags, true); +} + static const struct bpf_map_ops htab_percpu_ops = { .map_alloc = htab_map_alloc, .map_free = htab_map_free, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 637397059f76..c95a753c2007 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -239,6 +239,7 @@ static int map_lookup_elem(union bpf_attr *attr) int ufd = attr->map_fd; struct bpf_map *map; void *key, *value, *ptr; + u32 value_size; struct fd f; int err; @@ -259,23 +260,35 @@ static int map_lookup_elem(union bpf_attr *attr) if (copy_from_user(key, ukey, map->key_size) != 0) goto free_key; + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + value_size = round_up(map->value_size, 8) * num_possible_cpus(); + else + value_size = map->value_size; + err = -ENOMEM; - value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN); + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; - rcu_read_lock(); - ptr = map->ops->map_lookup_elem(map, key); - if (ptr) - memcpy(value, ptr, map->value_size); - rcu_read_unlock(); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { + err = bpf_percpu_hash_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + err = bpf_percpu_array_copy(map, key, value); + } else { + rcu_read_lock(); + ptr = map->ops->map_lookup_elem(map, key); + if (ptr) + memcpy(value, ptr, value_size); + rcu_read_unlock(); + err = ptr ? 0 : -ENOENT; + } - err = -ENOENT; - if (!ptr) + if (err) goto free_value; err = -EFAULT; - if (copy_to_user(uvalue, value, map->value_size) != 0) + if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; err = 0; @@ -298,6 +311,7 @@ static int map_update_elem(union bpf_attr *attr) int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; + u32 value_size; struct fd f; int err; @@ -318,21 +332,30 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(key, ukey, map->key_size) != 0) goto free_key; + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + value_size = round_up(map->value_size, 8) * num_possible_cpus(); + else + value_size = map->value_size; + err = -ENOMEM; - value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN); + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; err = -EFAULT; - if (copy_from_user(value, uvalue, map->value_size) != 0) + if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; - /* eBPF program that use maps are running under rcu_read_lock(), - * therefore all map accessors rely on this fact, so do the same here - */ - rcu_read_lock(); - err = map->ops->map_update_elem(map, key, value, attr->flags); - rcu_read_unlock(); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { + err = bpf_percpu_hash_update(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + err = bpf_percpu_array_update(map, key, value, attr->flags); + } else { + rcu_read_lock(); + err = map->ops->map_update_elem(map, key, value, attr->flags); + rcu_read_unlock(); + } free_value: kfree(value); -- cgit v1.2.3 From fd97646b05957348e01be3d9de5c3d979b25c819 Mon Sep 17 00:00:00 2001 From: Wei Yuan Date: Sat, 6 Feb 2016 15:39:47 +0800 Subject: audit: Fix typo in comment Signed-off-by: Weiyuan Signed-off-by: Paul Moore --- kernel/audit_watch.c | 2 +- kernel/auditfilter.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 656c7e93ac0d..0348b12b5a4d 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -185,7 +185,7 @@ static struct audit_watch *audit_init_watch(char *path) return watch; } -/* Translate a watch string to kernel respresentation. */ +/* Translate a watch string to kernel representation. */ int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op) { struct audit_watch *watch; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index b8ff9e193753..94ca7b1e5e7e 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -158,7 +158,7 @@ char *audit_unpack_string(void **bufp, size_t *remain, size_t len) return str; } -/* Translate an inode field to kernel respresentation. */ +/* Translate an inode field to kernel representation. */ static inline int audit_to_inode(struct audit_krule *krule, struct audit_field *f) { @@ -415,7 +415,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) return 0; } -/* Translate struct audit_rule_data to kernel's rule respresentation. */ +/* Translate struct audit_rule_data to kernel's rule representation. */ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, size_t datasz) { @@ -593,7 +593,7 @@ static inline size_t audit_pack_string(void **bufp, const char *str) return len; } -/* Translate kernel rule respresentation to struct audit_rule_data. */ +/* Translate kernel rule representation to struct audit_rule_data. */ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) { struct audit_rule_data *data; -- cgit v1.2.3 From f7b382b988233b5851eddf4531651ffe4133e88c Mon Sep 17 00:00:00 2001 From: Abhilash Jindal Date: Sun, 31 Jan 2016 14:29:01 -0500 Subject: PM/freezer: y2038, use boottime to compare tstamps Wall time obtained from do_gettimeofday gives 32 bit timeval which can only represent time until January 2038. This patch moves to ktime_t, a 64-bit time. Also, wall time is susceptible to sudden jumps due to user setting the time or due to NTP. Boot time is constantly increasing time better suited for subtracting two timestamps. Signed-off-by: Abhilash Jindal Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- kernel/power/process.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/power/process.c b/kernel/power/process.c index 564f786df470..df058bed53ce 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -30,13 +30,12 @@ static int try_to_freeze_tasks(bool user_only) unsigned long end_time; unsigned int todo; bool wq_busy = false; - struct timeval start, end; - u64 elapsed_msecs64; + ktime_t start, end, elapsed; unsigned int elapsed_msecs; bool wakeup = false; int sleep_usecs = USEC_PER_MSEC; - do_gettimeofday(&start); + start = ktime_get_boottime(); end_time = jiffies + msecs_to_jiffies(freeze_timeout_msecs); @@ -78,10 +77,9 @@ static int try_to_freeze_tasks(bool user_only) sleep_usecs *= 2; } - do_gettimeofday(&end); - elapsed_msecs64 = timeval_to_ns(&end) - timeval_to_ns(&start); - do_div(elapsed_msecs64, NSEC_PER_MSEC); - elapsed_msecs = elapsed_msecs64; + end = ktime_get_boottime(); + elapsed = ktime_sub(end, start); + elapsed_msecs = ktime_to_ms(elapsed); if (todo) { pr_cont("\n"); -- cgit v1.2.3 From 22e09b333f0b395b3eb6ab6efa4b3284e2c06810 Mon Sep 17 00:00:00 2001 From: saurabh Date: Wed, 28 Oct 2015 08:54:01 +0530 Subject: PM / suspend: replacing printk replacing printk(s) with appropriate pr_info and pr_err in order to fix checkpatch.pl warnings Signed-off-by: Saurabh Sengar Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- kernel/power/suspend.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index f9fe133c13e2..230a77225e2e 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -248,7 +248,7 @@ static int suspend_test(int level) { #ifdef CONFIG_PM_DEBUG if (pm_test_level == level) { - printk(KERN_INFO "suspend debug: Waiting for %d second(s).\n", + pr_info("suspend debug: Waiting for %d second(s).\n", pm_test_delay); mdelay(pm_test_delay * 1000); return 1; @@ -320,7 +320,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) error = dpm_suspend_late(PMSG_SUSPEND); if (error) { - printk(KERN_ERR "PM: late suspend of devices failed\n"); + pr_err("PM: late suspend of devices failed\n"); goto Platform_finish; } error = platform_suspend_prepare_late(state); @@ -329,7 +329,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) error = dpm_suspend_noirq(PMSG_SUSPEND); if (error) { - printk(KERN_ERR "PM: noirq suspend of devices failed\n"); + pr_err("PM: noirq suspend of devices failed\n"); goto Platform_early_resume; } error = platform_suspend_prepare_noirq(state); -- cgit v1.2.3 From 223ffb29f9723a4b485cacf6dc7e6d639fffc322 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 11 Feb 2016 13:34:49 -0500 Subject: cgroup: provide cgroup_nov1= to disable controllers in v1 mounts Testing cgroup2 can be painful with system software automatically mounting and populating all cgroup controllers in v1 mode. Sometimes they can be unmounted from rc.local, sometimes even that is too late. Provide a commandline option to disable certain controllers in v1 mounts, so that they remain available for cgroup2 mounts. Example use: cgroup_no_v1=memory,cpu cgroup_no_v1=all Disabling will be confirmed at boot-time as such: [ 0.013770] Disabling cpu control group subsystem in v1 mounts [ 0.016004] Disabling memory control group subsystem in v1 mounts Signed-off-by: Johannes Weiner Signed-off-by: Tejun Heo --- kernel/cgroup.c | 43 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d27904c193da..7ad61915967f 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -180,6 +180,9 @@ EXPORT_SYMBOL_GPL(cgrp_dfl_root); */ static bool cgrp_dfl_root_visible; +/* Controllers blocked by the commandline in v1 */ +static unsigned long cgroup_no_v1_mask; + /* some controllers are not supported in the default hierarchy */ static unsigned long cgrp_dfl_root_inhibit_ss_mask; @@ -241,6 +244,11 @@ static bool cgroup_ssid_enabled(int ssid) return static_key_enabled(cgroup_subsys_enabled_key[ssid]); } +static bool cgroup_ssid_no_v1(int ssid) +{ + return cgroup_no_v1_mask & (1 << ssid); +} + /** * cgroup_on_dfl - test whether a cgroup is on the default hierarchy * @cgrp: the cgroup of interest @@ -1678,6 +1686,8 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) continue; if (!cgroup_ssid_enabled(i)) continue; + if (cgroup_ssid_no_v1(i)) + continue; /* Mutually exclusive option 'all' + subsystem name */ if (all_ss) @@ -1698,7 +1708,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) */ if (all_ss || (!one_ss && !opts->none && !opts->name)) for_each_subsys(ss, i) - if (cgroup_ssid_enabled(i)) + if (cgroup_ssid_enabled(i) && !cgroup_ssid_no_v1(i)) opts->subsys_mask |= (1 << i); /* @@ -5324,6 +5334,10 @@ int __init cgroup_init(void) continue; } + if (cgroup_ssid_no_v1(ssid)) + printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n", + ss->name); + cgrp_dfl_root.subsys_mask |= 1 << ss->id; if (!ss->dfl_cftypes) @@ -5750,6 +5764,33 @@ static int __init cgroup_disable(char *str) } __setup("cgroup_disable=", cgroup_disable); +static int __init cgroup_no_v1(char *str) +{ + struct cgroup_subsys *ss; + char *token; + int i; + + while ((token = strsep(&str, ",")) != NULL) { + if (!*token) + continue; + + if (!strcmp(token, "all")) { + cgroup_no_v1_mask = ~0UL; + break; + } + + for_each_subsys(ss, i) { + if (strcmp(token, ss->name) && + strcmp(token, ss->legacy_name)) + continue; + + cgroup_no_v1_mask |= 1 << i; + } + } + return 1; +} +__setup("cgroup_no_v1=", cgroup_no_v1); + /** * css_tryget_online_from_dir - get corresponding css from a cgroup dentry * @dentry: directory dentry of interest -- cgit v1.2.3 From fc4fa6e112c0f999fab022a4eb7f6614bb47c7ab Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Sun, 13 Dec 2015 15:26:11 +0900 Subject: treewide: Fix typo in printk This patch fix spelling typos found in printk and Kconfig. Signed-off-by: Masanari Iida Acked-by: Randy Dunlap Signed-off-by: Jiri Kosina --- drivers/atm/firestream.c | 2 +- drivers/crypto/nx/nx-842.c | 2 +- drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c | 2 +- drivers/input/touchscreen/wdt87xx_i2c.c | 2 +- drivers/net/ethernet/nuvoton/w90p910_ether.c | 2 +- drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c | 2 +- drivers/usb/gadget/legacy/Kconfig | 3 +-- kernel/time/timekeeping.c | 2 +- lib/842/842_decompress.c | 2 +- net/openvswitch/vport-geneve.c | 2 +- tools/testing/selftests/timers/alarmtimer-suspend.c | 2 +- 11 files changed, 11 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index 82f2ae0d7cc4..a969a7e443be 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -168,7 +168,7 @@ static char *res_strings[] = { "reserved 14", "Unrecognized cell", "reserved 16", - "reassemby abort: AAL5 abort", + "reassembly abort: AAL5 abort", "packet purged", "packet ageing timeout", "channel ageing timeout", diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c index 046c1c45411b..d94e25df503b 100644 --- a/drivers/crypto/nx/nx-842.c +++ b/drivers/crypto/nx/nx-842.c @@ -308,7 +308,7 @@ int nx842_crypto_compress(struct crypto_tfm *tfm, h = !n && add_header ? hdrsize : 0; if (ignore) - pr_warn("interal error, ignore is set %x\n", ignore); + pr_warn("internal error, ignore is set %x\n", ignore); ret = compress(ctx, &p, &hdr->group[n], &c, &ignore, h); if (ret) diff --git a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c index 85dc3f989ff7..704d08744116 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c @@ -64,7 +64,7 @@ const char *usnic_ib_qp_grp_state_to_string(enum ib_qp_state state) case IB_QPS_ERR: return "ERR"; default: - return "UNKOWN STATE"; + return "UNKNOWN STATE"; } } diff --git a/drivers/input/touchscreen/wdt87xx_i2c.c b/drivers/input/touchscreen/wdt87xx_i2c.c index 515c20a6e10f..73861ad22df4 100644 --- a/drivers/input/touchscreen/wdt87xx_i2c.c +++ b/drivers/input/touchscreen/wdt87xx_i2c.c @@ -848,7 +848,7 @@ static int wdt87xx_do_update_firmware(struct i2c_client *client, error = wdt87xx_get_sysparam(client, &wdt->param); if (error) dev_err(&client->dev, - "failed to refresh system paramaters: %d\n", error); + "failed to refresh system parameters: %d\n", error); out: enable_irq(client->irq); mutex_unlock(&wdt->fw_mutex); diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c index afa445842f3e..52d9a94aebb9 100644 --- a/drivers/net/ethernet/nuvoton/w90p910_ether.c +++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c @@ -1038,7 +1038,7 @@ static int w90p910_ether_probe(struct platform_device *pdev) error = register_netdev(dev); if (error != 0) { - dev_err(&pdev->dev, "Regiter EMC w90p910 FAILED\n"); + dev_err(&pdev->dev, "Register EMC w90p910 FAILED\n"); error = -ENODEV; goto failed_put_rmiiclk; } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c index b57cfd965196..95dcbff4673b 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c @@ -626,7 +626,7 @@ static void rtl8821ae_dm_find_minimum_rssi(struct ieee80211_hw *hw) rtl_dm_dig->min_undec_pwdb_for_dm = rtlpriv->dm.entry_min_undec_sm_pwdb; RT_TRACE(rtlpriv, COMP_BB_POWERSAVING, DBG_LOUD, - "AP Ext Port or disconnet PWDB = 0x%x\n", + "AP Ext Port or disconnect PWDB = 0x%x\n", rtl_dm_dig->min_undec_pwdb_for_dm); } RT_TRACE(rtlpriv, COMP_DIG, DBG_LOUD, diff --git a/drivers/usb/gadget/legacy/Kconfig b/drivers/usb/gadget/legacy/Kconfig index 4d682ad7bf23..fb1cdd9af472 100644 --- a/drivers/usb/gadget/legacy/Kconfig +++ b/drivers/usb/gadget/legacy/Kconfig @@ -103,8 +103,7 @@ config USB_ETH - CDC Ethernet Emulation Model (EEM) is a newer standard that has a simpler interface that can be used by more USB hardware. - RNDIS support is an additional option, more demanding than than - subset. + RNDIS support is an additional option, more demanding than subset. Within the USB device, this gadget driver exposes a network device "usbX", where X depends on what other networking devices you have. diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b1356b7ae570..0d4cc7601df7 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -131,7 +131,7 @@ static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset) printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); } else { if (offset > (max_cycles >> 1)) { - printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the the '%s' clock's 50%% safety margin (%lld)\n", + printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n", offset, name, max_cycles >> 1); printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); } diff --git a/lib/842/842_decompress.c b/lib/842/842_decompress.c index 8881dad2a6a0..a2a941f8112d 100644 --- a/lib/842/842_decompress.c +++ b/lib/842/842_decompress.c @@ -250,7 +250,7 @@ static int do_op(struct sw842_param *p, u8 o) case OP_ACTION_NOOP: break; default: - pr_err("Interal error, invalid op %x\n", op); + pr_err("Internal error, invalid op %x\n", op); return -EINVAL; } diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index efb736bb6855..69f1de58a3b4 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -133,6 +133,6 @@ static void __exit ovs_geneve_tnl_exit(void) module_init(ovs_geneve_tnl_init); module_exit(ovs_geneve_tnl_exit); -MODULE_DESCRIPTION("OVS: Geneve swiching port"); +MODULE_DESCRIPTION("OVS: Geneve switching port"); MODULE_LICENSE("GPL"); MODULE_ALIAS("vport-type-5"); diff --git a/tools/testing/selftests/timers/alarmtimer-suspend.c b/tools/testing/selftests/timers/alarmtimer-suspend.c index 72cacf5383dd..2b361b830395 100644 --- a/tools/testing/selftests/timers/alarmtimer-suspend.c +++ b/tools/testing/selftests/timers/alarmtimer-suspend.c @@ -153,7 +153,7 @@ int main(void) alarmcount = 0; if (timer_create(alarm_clock_id, &se, &tm1) == -1) { - printf("timer_create failled, %s unspported?\n", + printf("timer_create failed, %s unsupported?\n", clockstring(alarm_clock_id)); break; } -- cgit v1.2.3 From 1e9877902dc7e11d2be038371c6fbf2dfcd469d7 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:01:54 -0800 Subject: mm/gup: Introduce get_user_pages_remote() For protection keys, we need to understand whether protections should be enforced in software or not. In general, we enforce protections when working on our own task, but not when on others. We call these "current" and "remote" operations. This patch introduces a new get_user_pages() variant: get_user_pages_remote() Which is a replacement for when get_user_pages() is called on non-current tsk/mm. We also introduce a new gup flag: FOLL_REMOTE which can be used for the "__" gup variants to get this new behavior. The uprobes is_trap_at_addr() location holds mmap_sem and calls get_user_pages(current->mm) on an instruction address. This makes it a pretty unique gup caller. Being an instruction access and also really originating from the kernel (vs. the app), I opted to consider this a 'remote' access where protection keys will not be enforced. Without protection keys, this patch should not change any behavior. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrea Arcangeli Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Kirill A. Shutemov Cc: Linus Torvalds Cc: Naoya Horiguchi Cc: Peter Zijlstra Cc: Rik van Riel Cc: Srikar Dronamraju Cc: Vlastimil Babka Cc: jack@suse.cz Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210154.3F0E51EA@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- drivers/gpu/drm/etnaviv/etnaviv_gem.c | 6 +++--- drivers/gpu/drm/i915/i915_gem_userptr.c | 10 +++++----- drivers/infiniband/core/umem_odp.c | 8 ++++---- fs/exec.c | 8 ++++++-- include/linux/mm.h | 5 +++++ kernel/events/uprobes.c | 10 ++++++++-- mm/gup.c | 27 ++++++++++++++++++++++----- mm/memory.c | 2 +- mm/process_vm_access.c | 11 ++++++++--- security/tomoyo/domain.c | 9 ++++++++- virt/kvm/async_pf.c | 8 +++++++- 11 files changed, 77 insertions(+), 27 deletions(-) (limited to 'kernel') diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 4b519e4309b2..97d4457be8d2 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -753,9 +753,9 @@ static struct page **etnaviv_gem_userptr_do_get_pages( down_read(&mm->mmap_sem); while (pinned < npages) { - ret = get_user_pages(task, mm, ptr, npages - pinned, - !etnaviv_obj->userptr.ro, 0, - pvec + pinned, NULL); + ret = get_user_pages_remote(task, mm, ptr, npages - pinned, + !etnaviv_obj->userptr.ro, 0, + pvec + pinned, NULL); if (ret < 0) break; diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index 59e45b3a6937..90dbf8121210 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -584,11 +584,11 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) down_read(&mm->mmap_sem); while (pinned < npages) { - ret = get_user_pages(work->task, mm, - obj->userptr.ptr + pinned * PAGE_SIZE, - npages - pinned, - !obj->userptr.read_only, 0, - pvec + pinned, NULL); + ret = get_user_pages_remote(work->task, mm, + obj->userptr.ptr + pinned * PAGE_SIZE, + npages - pinned, + !obj->userptr.read_only, 0, + pvec + pinned, NULL); if (ret < 0) break; diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index e69bf266049d..75077a018675 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -572,10 +572,10 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt, * complex (and doesn't gain us much performance in most use * cases). */ - npages = get_user_pages(owning_process, owning_mm, user_virt, - gup_num_pages, - access_mask & ODP_WRITE_ALLOWED_BIT, 0, - local_page_list, NULL); + npages = get_user_pages_remote(owning_process, owning_mm, + user_virt, gup_num_pages, + access_mask & ODP_WRITE_ALLOWED_BIT, + 0, local_page_list, NULL); up_read(&owning_mm->mmap_sem); if (npages < 0) diff --git a/fs/exec.c b/fs/exec.c index dcd4ac7d3f1e..d885b98b6a00 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -198,8 +198,12 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, return NULL; } #endif - ret = get_user_pages(current, bprm->mm, pos, - 1, write, 1, &page, NULL); + /* + * We are doing an exec(). 'current' is the process + * doing the exec and bprm->mm is the new process's mm. + */ + ret = get_user_pages_remote(current, bprm->mm, pos, 1, write, + 1, &page, NULL); if (ret <= 0) return NULL; diff --git a/include/linux/mm.h b/include/linux/mm.h index b1d4b8c7f7cd..faf3b709eead 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1225,6 +1225,10 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int foll_flags, struct page **pages, struct vm_area_struct **vmas, int *nonblocking); +long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + struct vm_area_struct **vmas); long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, @@ -2170,6 +2174,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_MLOCK 0x1000 /* lock present pages */ +#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 0167679182c0..8eef5f55d3f0 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -299,7 +299,7 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, retry: /* Read the page with vaddr into memory */ - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma); + ret = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma); if (ret <= 0) return ret; @@ -1700,7 +1700,13 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) if (likely(result == 0)) goto out; - result = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL); + /* + * The NULL 'tsk' here ensures that any faults that occur here + * will not be accounted to the task. 'mm' *is* current->mm, + * but we treat this as a 'remote' access since it is + * essentially a kernel access to the memory. + */ + result = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &page, NULL); if (result < 0) return result; diff --git a/mm/gup.c b/mm/gup.c index 7bf19ffa2199..36ca850936c9 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -870,7 +870,7 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, EXPORT_SYMBOL(get_user_pages_unlocked); /* - * get_user_pages() - pin user pages in memory + * get_user_pages_remote() - pin user pages in memory * @tsk: the task_struct to use for page fault accounting, or * NULL if faults are not to be recorded. * @mm: mm_struct of target mm @@ -924,12 +924,29 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * should use get_user_pages because it cannot pass * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ -long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, int write, - int force, struct page **pages, struct vm_area_struct **vmas) +long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + struct vm_area_struct **vmas) { return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, - pages, vmas, NULL, false, FOLL_TOUCH); + pages, vmas, NULL, false, + FOLL_TOUCH | FOLL_REMOTE); +} +EXPORT_SYMBOL(get_user_pages_remote); + +/* + * This is the same as get_user_pages_remote() for the time + * being. + */ +long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + struct vm_area_struct **vmas) +{ + return __get_user_pages_locked(tsk, mm, start, nr_pages, + write, force, pages, vmas, NULL, false, + FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages); diff --git a/mm/memory.c b/mm/memory.c index 38090ca37a08..8bfbad0cca8c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3685,7 +3685,7 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, void *maddr; struct page *page = NULL; - ret = get_user_pages(tsk, mm, addr, 1, + ret = get_user_pages_remote(tsk, mm, addr, 1, write, 1, &page, &vma); if (ret <= 0) { #ifndef CONFIG_HAVE_IOREMAP_PROT diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 5d453e58ddbf..07514d41ebcc 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -98,9 +98,14 @@ static int process_vm_rw_single_vec(unsigned long addr, int pages = min(nr_pages, max_pages_per_loop); size_t bytes; - /* Get the pages we're interested in */ - pages = get_user_pages_unlocked(task, mm, pa, pages, - vm_write, 0, process_pages); + /* + * Get the pages we're interested in. We must + * add FOLL_REMOTE because task/mm might not + * current/current->mm + */ + pages = __get_user_pages_unlocked(task, mm, pa, pages, + vm_write, 0, process_pages, + FOLL_REMOTE); if (pages <= 0) return -EFAULT; diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index 38651454ed08..ade7c6cad172 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -874,7 +874,14 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, } /* Same with get_arg_page(bprm, pos, 0) in fs/exec.c */ #ifdef CONFIG_MMU - if (get_user_pages(current, bprm->mm, pos, 1, 0, 1, &page, NULL) <= 0) + /* + * This is called at execve() time in order to dig around + * in the argv/environment of the new proceess + * (represented by bprm). 'current' is the process doing + * the execve(). + */ + if (get_user_pages_remote(current, bprm->mm, pos, 1, + 0, 1, &page, NULL) <= 0) return false; #else page = bprm->page[pos / PAGE_SIZE]; diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 353159922456..d604e87a510a 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -79,7 +79,13 @@ static void async_pf_execute(struct work_struct *work) might_sleep(); - get_user_pages_unlocked(NULL, mm, addr, 1, 1, 0, NULL); + /* + * This work is run asynchromously to the task which owns + * mm and might be done in another context, so we must + * use FOLL_REMOTE. + */ + __get_user_pages_unlocked(NULL, mm, addr, 1, 1, 0, NULL, FOLL_REMOTE); + kvm_async_page_present_sync(vcpu, apf); spin_lock(&vcpu->async_pf.lock); -- cgit v1.2.3 From a79a908fd2b080977b45bf103184b81c9d11ad07 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 29 Jan 2016 02:54:06 -0600 Subject: cgroup: introduce cgroup namespaces Introduce the ability to create new cgroup namespace. The newly created cgroup namespace remembers the cgroup of the process at the point of creation of the cgroup namespace (referred as cgroupns-root). The main purpose of cgroup namespace is to virtualize the contents of /proc/self/cgroup file. Processes inside a cgroup namespace are only able to see paths relative to their namespace root (unless they are moved outside of their cgroupns-root, at which point they will see a relative path from their cgroupns-root). For a correctly setup container this enables container-tools (like libcontainer, lxc, lmctfy, etc.) to create completely virtualized containers without leaking system level cgroup hierarchy to the task. This patch only implements the 'unshare' part of the cgroupns. Signed-off-by: Aditya Kali Signed-off-by: Serge Hallyn Signed-off-by: Tejun Heo --- fs/proc/namespaces.c | 3 + include/linux/cgroup.h | 49 ++++++++++++++ include/linux/nsproxy.h | 2 + include/linux/proc_ns.h | 4 ++ kernel/cgroup.c | 173 +++++++++++++++++++++++++++++++++++++++++++++++- kernel/cpuset.c | 8 +-- kernel/fork.c | 2 +- kernel/nsproxy.c | 19 +++++- 8 files changed, 250 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 276f12431dbf..72cb26f85d58 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -28,6 +28,9 @@ static const struct proc_ns_operations *ns_entries[] = { &userns_operations, #endif &mntns_operations, +#ifdef CONFIG_CGROUPS + &cgroupns_operations, +#endif }; static const char *proc_ns_get_link(struct dentry *dentry, diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 2162dca88dc0..a20320c666fd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -17,6 +17,11 @@ #include #include #include +#include +#include +#include +#include +#include #include @@ -611,4 +616,48 @@ static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ +struct cgroup_namespace { + atomic_t count; + struct ns_common ns; + struct user_namespace *user_ns; + struct css_set *root_cset; +}; + +extern struct cgroup_namespace init_cgroup_ns; + +#ifdef CONFIG_CGROUPS + +void free_cgroup_ns(struct cgroup_namespace *ns); + +struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, + struct user_namespace *user_ns, + struct cgroup_namespace *old_ns); + +char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns); + +#else /* !CONFIG_CGROUPS */ + +static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } +static inline struct cgroup_namespace * +copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, + struct cgroup_namespace *old_ns) +{ + return old_ns; +} + +#endif /* !CONFIG_CGROUPS */ + +static inline void get_cgroup_ns(struct cgroup_namespace *ns) +{ + if (ns) + atomic_inc(&ns->count); +} + +static inline void put_cgroup_ns(struct cgroup_namespace *ns) +{ + if (ns && atomic_dec_and_test(&ns->count)) + free_cgroup_ns(ns); +} + #endif /* _LINUX_CGROUP_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 35fa08fd7739..ac0d65bef5d0 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -8,6 +8,7 @@ struct mnt_namespace; struct uts_namespace; struct ipc_namespace; struct pid_namespace; +struct cgroup_namespace; struct fs_struct; /* @@ -33,6 +34,7 @@ struct nsproxy { struct mnt_namespace *mnt_ns; struct pid_namespace *pid_ns_for_children; struct net *net_ns; + struct cgroup_namespace *cgroup_ns; }; extern struct nsproxy init_nsproxy; diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 42dfc615dbf8..de0e7719d4c5 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -9,6 +9,8 @@ struct pid_namespace; struct nsproxy; struct path; +struct task_struct; +struct inode; struct proc_ns_operations { const char *name; @@ -24,6 +26,7 @@ extern const struct proc_ns_operations ipcns_operations; extern const struct proc_ns_operations pidns_operations; extern const struct proc_ns_operations userns_operations; extern const struct proc_ns_operations mntns_operations; +extern const struct proc_ns_operations cgroupns_operations; /* * We always define these enumerators @@ -34,6 +37,7 @@ enum { PROC_UTS_INIT_INO = 0xEFFFFFFEU, PROC_USER_INIT_INO = 0xEFFFFFFDU, PROC_PID_INIT_INO = 0xEFFFFFFCU, + PROC_CGROUP_INIT_INO = 0xEFFFFFFBU, }; #ifdef CONFIG_PROC_FS diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7ad61915967f..b001c5d36bec 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -59,6 +59,9 @@ #include #include #include +#include +#include +#include #include /* @@ -212,6 +215,15 @@ static unsigned long have_fork_callback __read_mostly; static unsigned long have_exit_callback __read_mostly; static unsigned long have_free_callback __read_mostly; +/* cgroup namespace for init task */ +struct cgroup_namespace init_cgroup_ns = { + .count = { .counter = 2, }, + .user_ns = &init_user_ns, + .ns.ops = &cgroupns_operations, + .ns.inum = PROC_CGROUP_INIT_INO, + .root_cset = &init_css_set, +}; + /* Ditto for the can_fork callback. */ static unsigned long have_canfork_callback __read_mostly; @@ -2177,6 +2189,35 @@ static struct file_system_type cgroup2_fs_type = { .kill_sb = cgroup_kill_sb, }; +static char *cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns) +{ + struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); + int ret; + + ret = kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); + if (ret < 0 || ret >= buflen) + return NULL; + return buf; +} + +char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns) +{ + char *ret; + + mutex_lock(&cgroup_mutex); + spin_lock_bh(&css_set_lock); + + ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); + + spin_unlock_bh(&css_set_lock); + mutex_unlock(&cgroup_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(cgroup_path_ns); + /** * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy * @task: target task @@ -2204,7 +2245,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) if (root) { cgrp = task_cgroup_from_root(task, root); - path = cgroup_path(cgrp, buf, buflen); + path = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns); } else { /* if no hierarchy exists, everyone is in "/" */ if (strlcpy(buf, "/", buflen) < buflen) @@ -5297,6 +5338,8 @@ int __init cgroup_init(void) BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files)); + get_user_ns(init_cgroup_ns.user_ns); + mutex_lock(&cgroup_mutex); /* Add init_css_set to the hash table */ @@ -5438,7 +5481,8 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, * " (deleted)" is appended to the cgroup path. */ if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { - path = cgroup_path(cgrp, buf, PATH_MAX); + path = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, + current->nsproxy->cgroup_ns); if (!path) { retval = -ENAMETOOLONG; goto out_unlock; @@ -5720,7 +5764,9 @@ static void cgroup_release_agent(struct work_struct *work) if (!pathbuf || !agentbuf) goto out; - path = cgroup_path(cgrp, pathbuf, PATH_MAX); + spin_lock_bh(&css_set_lock); + path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); + spin_unlock_bh(&css_set_lock); if (!path) goto out; @@ -5931,6 +5977,127 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ +/* cgroup namespaces */ + +static struct cgroup_namespace *alloc_cgroup_ns(void) +{ + struct cgroup_namespace *new_ns; + int ret; + + new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL); + if (!new_ns) + return ERR_PTR(-ENOMEM); + ret = ns_alloc_inum(&new_ns->ns); + if (ret) { + kfree(new_ns); + return ERR_PTR(ret); + } + atomic_set(&new_ns->count, 1); + new_ns->ns.ops = &cgroupns_operations; + return new_ns; +} + +void free_cgroup_ns(struct cgroup_namespace *ns) +{ + put_css_set(ns->root_cset); + put_user_ns(ns->user_ns); + ns_free_inum(&ns->ns); + kfree(ns); +} +EXPORT_SYMBOL(free_cgroup_ns); + +struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, + struct user_namespace *user_ns, + struct cgroup_namespace *old_ns) +{ + struct cgroup_namespace *new_ns = NULL; + struct css_set *cset = NULL; + int err; + + BUG_ON(!old_ns); + + if (!(flags & CLONE_NEWCGROUP)) { + get_cgroup_ns(old_ns); + return old_ns; + } + + /* Allow only sysadmin to create cgroup namespace. */ + err = -EPERM; + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + goto err_out; + + mutex_lock(&cgroup_mutex); + spin_lock_bh(&css_set_lock); + + cset = task_css_set(current); + get_css_set(cset); + + spin_unlock_bh(&css_set_lock); + mutex_unlock(&cgroup_mutex); + + err = -ENOMEM; + new_ns = alloc_cgroup_ns(); + if (!new_ns) + goto err_out; + + new_ns->user_ns = get_user_ns(user_ns); + new_ns->root_cset = cset; + + return new_ns; + +err_out: + if (cset) + put_css_set(cset); + kfree(new_ns); + return ERR_PTR(err); +} + +static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) +{ + return container_of(ns, struct cgroup_namespace, ns); +} + +static int cgroupns_install(struct nsproxy *nsproxy, void *ns) +{ + pr_info("setns not supported for cgroup namespace"); + return -EINVAL; +} + +static struct ns_common *cgroupns_get(struct task_struct *task) +{ + struct cgroup_namespace *ns = NULL; + struct nsproxy *nsproxy; + + task_lock(task); + nsproxy = task->nsproxy; + if (nsproxy) { + ns = nsproxy->cgroup_ns; + get_cgroup_ns(ns); + } + task_unlock(task); + + return ns ? &ns->ns : NULL; +} + +static void cgroupns_put(struct ns_common *ns) +{ + put_cgroup_ns(to_cg_ns(ns)); +} + +const struct proc_ns_operations cgroupns_operations = { + .name = "cgroup", + .type = CLONE_NEWCGROUP, + .get = cgroupns_get, + .put = cgroupns_put, + .install = cgroupns_install, +}; + +static __init int cgroup_namespaces_init(void) +{ + return 0; +} +subsys_initcall(cgroup_namespaces_init); + #ifdef CONFIG_CGROUP_DEBUG static struct cgroup_subsys_state * debug_css_alloc(struct cgroup_subsys_state *parent_css) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 41989ab4db57..d393125b228c 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2714,10 +2714,10 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, goto out; retval = -ENAMETOOLONG; - rcu_read_lock(); - css = task_css(tsk, cpuset_cgrp_id); - p = cgroup_path(css->cgroup, buf, PATH_MAX); - rcu_read_unlock(); + css = task_get_css(tsk, cpuset_cgrp_id); + p = cgroup_path_ns(css->cgroup, buf, PATH_MAX, + current->nsproxy->cgroup_ns); + css_put(css); if (!p) goto out_free; seq_puts(m, p); diff --git a/kernel/fork.c b/kernel/fork.c index 2e391c754ae7..6611a6267949 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1884,7 +1884,7 @@ static int check_unshare_flags(unsigned long unshare_flags) if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| - CLONE_NEWUSER|CLONE_NEWPID)) + CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 49746c81ad8d..782102e59eed 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -25,6 +25,7 @@ #include #include #include +#include static struct kmem_cache *nsproxy_cachep; @@ -39,6 +40,9 @@ struct nsproxy init_nsproxy = { #ifdef CONFIG_NET .net_ns = &init_net, #endif +#ifdef CONFIG_CGROUPS + .cgroup_ns = &init_cgroup_ns, +#endif }; static inline struct nsproxy *create_nsproxy(void) @@ -92,6 +96,13 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_pid; } + new_nsp->cgroup_ns = copy_cgroup_ns(flags, user_ns, + tsk->nsproxy->cgroup_ns); + if (IS_ERR(new_nsp->cgroup_ns)) { + err = PTR_ERR(new_nsp->cgroup_ns); + goto out_cgroup; + } + new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns); if (IS_ERR(new_nsp->net_ns)) { err = PTR_ERR(new_nsp->net_ns); @@ -101,6 +112,8 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, return new_nsp; out_net: + put_cgroup_ns(new_nsp->cgroup_ns); +out_cgroup: if (new_nsp->pid_ns_for_children) put_pid_ns(new_nsp->pid_ns_for_children); out_pid: @@ -128,7 +141,8 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) struct nsproxy *new_ns; if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWPID | CLONE_NEWNET)))) { + CLONE_NEWPID | CLONE_NEWNET | + CLONE_NEWCGROUP)))) { get_nsproxy(old_ns); return 0; } @@ -165,6 +179,7 @@ void free_nsproxy(struct nsproxy *ns) put_ipc_ns(ns->ipc_ns); if (ns->pid_ns_for_children) put_pid_ns(ns->pid_ns_for_children); + put_cgroup_ns(ns->cgroup_ns); put_net(ns->net_ns); kmem_cache_free(nsproxy_cachep, ns); } @@ -180,7 +195,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags, int err = 0; if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWNET | CLONE_NEWPID))) + CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP))) return 0; user_ns = new_cred ? new_cred->user_ns : current_user_ns(); -- cgit v1.2.3 From a0530e087e648263f81a81d62ca020f66b54bcb0 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 29 Jan 2016 02:54:07 -0600 Subject: cgroup: cgroup namespace setns support setns on a cgroup namespace is allowed only if task has CAP_SYS_ADMIN in its current user-namespace and over the user-namespace associated with target cgroupns. No implicit cgroup changes happen with attaching to another cgroupns. It is expected that the somone moves the attaching process under the target cgroupns-root. Signed-off-by: Aditya Kali Signed-off-by: Serge E. Hallyn Signed-off-by: Tejun Heo --- kernel/cgroup.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b001c5d36bec..b086a461be23 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -6057,10 +6057,23 @@ static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) return container_of(ns, struct cgroup_namespace, ns); } -static int cgroupns_install(struct nsproxy *nsproxy, void *ns) +static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns) { - pr_info("setns not supported for cgroup namespace"); - return -EINVAL; + struct cgroup_namespace *cgroup_ns = to_cg_ns(ns); + + if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) || + !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + /* Don't need to do anything if we are attaching to our own cgroupns. */ + if (cgroup_ns == nsproxy->cgroup_ns) + return 0; + + get_cgroup_ns(cgroup_ns); + put_cgroup_ns(nsproxy->cgroup_ns); + nsproxy->cgroup_ns = cgroup_ns; + + return 0; } static struct ns_common *cgroupns_get(struct task_struct *task) -- cgit v1.2.3 From ed82571b1a14ab2bfbede2bb2c209700495749fc Mon Sep 17 00:00:00 2001 From: Serge Hallyn Date: Fri, 29 Jan 2016 02:54:09 -0600 Subject: cgroup: mount cgroupns-root when inside non-init cgroupns This patch enables cgroup mounting inside userns when a process as appropriate privileges. The cgroup filesystem mounted is rooted at the cgroupns-root. Thus, in a container-setup, only the hierarchy under the cgroupns-root is exposed inside the container. This allows container management tools to run inside the containers without depending on any global state. Signed-off-by: Serge Hallyn Signed-off-by: Tejun Heo Signed-off-by: Tejun Heo --- kernel/cgroup.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b086a461be23..24989022ff62 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1994,6 +1994,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, { bool is_v2 = fs_type == &cgroup2_fs_type; struct super_block *pinned_sb = NULL; + struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup_subsys *ss; struct cgroup_root *root; struct cgroup_sb_opts opts; @@ -2002,6 +2003,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, int i; bool new_sb; + get_cgroup_ns(ns); + + /* Check if the caller has permission to mount. */ + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) { + put_cgroup_ns(ns); + return ERR_PTR(-EPERM); + } + /* * The first time anyone tries to mount a cgroup, enable the list * linking each css_set to its tasks and fix up all existing tasks. @@ -2012,6 +2021,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, if (is_v2) { if (data) { pr_err("cgroup2: unknown option \"%s\"\n", (char *)data); + put_cgroup_ns(ns); return ERR_PTR(-EINVAL); } cgrp_dfl_root_visible = true; @@ -2117,6 +2127,16 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, goto out_unlock; } + /* + * We know this subsystem has not yet been bound. Users in a non-init + * user namespace may only mount hierarchies with no bound subsystems, + * i.e. 'none,name=user1' + */ + if (!opts.none && !capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out_unlock; + } + root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) { ret = -ENOMEM; @@ -2135,12 +2155,37 @@ out_free: kfree(opts.release_agent); kfree(opts.name); - if (ret) + if (ret) { + put_cgroup_ns(ns); return ERR_PTR(ret); + } out_mount: dentry = kernfs_mount(fs_type, flags, root->kf_root, is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC, &new_sb); + + /* + * In non-init cgroup namespace, instead of root cgroup's + * dentry, we return the dentry corresponding to the + * cgroupns->root_cgrp. + */ + if (!IS_ERR(dentry) && ns != &init_cgroup_ns) { + struct dentry *nsdentry; + struct cgroup *cgrp; + + mutex_lock(&cgroup_mutex); + spin_lock_bh(&css_set_lock); + + cgrp = cset_cgroup_from_root(ns->root_cset, root); + + spin_unlock_bh(&css_set_lock); + mutex_unlock(&cgroup_mutex); + + nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb); + dput(dentry); + dentry = nsdentry; + } + if (IS_ERR(dentry) || !new_sb) cgroup_put(&root->cgrp); @@ -2153,6 +2198,7 @@ out_mount: deactivate_super(pinned_sb); } + put_cgroup_ns(ns); return dentry; } -- cgit v1.2.3 From 1c53753e0df1ae4d21661053459e7c024a43f1d3 Mon Sep 17 00:00:00 2001 From: Serge Hallyn Date: Fri, 29 Jan 2016 02:54:11 -0600 Subject: Add FS_USERNS_FLAG to cgroup fs allowing root in a non-init user namespace to mount it. This should now be safe, because 1. non-init-root cannot mount a previously unbound subsystem 2. the task doing the mount must be privileged with respect to the user namespace owning the cgroup namespace 3. the mounted subsystem will have its current cgroup as the root dentry. the permissions will be unchanged, so tasks will receive no new privilege over the cgroups which they did not have on the original mounts. Signed-off-by: Serge Hallyn --- kernel/cgroup.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 24989022ff62..afb1205fc789 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2227,12 +2227,14 @@ static struct file_system_type cgroup_fs_type = { .name = "cgroup", .mount = cgroup_mount, .kill_sb = cgroup_kill_sb, + .fs_flags = FS_USERNS_MOUNT, }; static struct file_system_type cgroup2_fs_type = { .name = "cgroup2", .mount = cgroup_mount, .kill_sb = cgroup_kill_sb, + .fs_flags = FS_USERNS_MOUNT, }; static char *cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, -- cgit v1.2.3 From 23217b443b4b0439c8b55d3be0482d3cd7fbc5ac Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 17 Feb 2016 21:04:41 +0100 Subject: workqueue: Replace usage of init_name with dev_set_name() The init_name property of the device struct is sort of a hack and should only be used for statically allocated devices. Since the device is dynamically allocated here it is safe to use the proper way to set a devices name by calling dev_set_name(). Signed-off-by: Lars-Peter Clausen Signed-off-by: Tejun Heo --- kernel/workqueue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 7ff5dc7d2ac5..3a1c99b0c1b3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5222,8 +5222,8 @@ int workqueue_sysfs_register(struct workqueue_struct *wq) wq_dev->wq = wq; wq_dev->dev.bus = &wq_subsys; - wq_dev->dev.init_name = wq->name; wq_dev->dev.release = wq_device_release; + dev_set_name(&wq_dev->dev, "%s", wq->name); /* * unbound_attrs are created separately. Suppress uevent until -- cgit v1.2.3 From cd0ea35ff5511cde299a61c21a95889b4a71464e Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:12 -0800 Subject: signals, pkeys: Notify userspace about protection key faults A protection key fault is very similar to any other access error. There must be a VMA, etc... We even want to take the same action (SIGSEGV) that we do with a normal access fault. However, we do need to let userspace know that something is different. We do this the same way what we did with SEGV_BNDERR with Memory Protection eXtensions (MPX): define a new SEGV code: SEGV_PKUERR. We add a siginfo field: si_pkey that reveals to userspace which protection key was set on the PTE that we faulted on. There is no other easy way for userspace to figure this out. They could parse smaps but that would be a bit cruel. We share space with in siginfo with _addr_bnd. #BR faults from MPX are completely separate from page faults (#PF) that trigger from protection key violations, so we never need both at the same time. Note that _pkey is a 64-bit value. The current hardware only supports 4-bit protection keys. We do this because there is _plenty_ of space in _sigfault and it is possible that future processors would support more than 4 bits of protection keys. The x86 code to actually fill in the siginfo is in the next patch. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Al Viro Cc: Amanieu d'Antras Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Palmer Dabbelt Cc: Peter Zijlstra Cc: Richard Weinberger Cc: Rik van Riel Cc: Sasha Levin Cc: Vegard Nossum Cc: Vladimir Davydov Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210212.3A9B83AC@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/uapi/asm-generic/siginfo.h | 17 ++++++++++++----- kernel/signal.c | 4 ++++ 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 1e3552037a5a..90384d55225b 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -91,10 +91,15 @@ typedef struct siginfo { int _trapno; /* TRAP # which caused the signal */ #endif short _addr_lsb; /* LSB of the reported address */ - struct { - void __user *_lower; - void __user *_upper; - } _addr_bnd; + union { + /* used when si_code=SEGV_BNDERR */ + struct { + void __user *_lower; + void __user *_upper; + } _addr_bnd; + /* used when si_code=SEGV_PKUERR */ + u64 _pkey; + }; } _sigfault; /* SIGPOLL */ @@ -137,6 +142,7 @@ typedef struct siginfo { #define si_addr_lsb _sifields._sigfault._addr_lsb #define si_lower _sifields._sigfault._addr_bnd._lower #define si_upper _sifields._sigfault._addr_bnd._upper +#define si_pkey _sifields._sigfault._pkey #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd #ifdef __ARCH_SIGSYS @@ -206,7 +212,8 @@ typedef struct siginfo { #define SEGV_MAPERR (__SI_FAULT|1) /* address not mapped to object */ #define SEGV_ACCERR (__SI_FAULT|2) /* invalid permissions for mapped object */ #define SEGV_BNDERR (__SI_FAULT|3) /* failed address bound checks */ -#define NSIGSEGV 3 +#define SEGV_PKUERR (__SI_FAULT|4) /* failed protection key checks */ +#define NSIGSEGV 4 /* * SIGBUS si_codes diff --git a/kernel/signal.c b/kernel/signal.c index 0508544c8ced..fe8ed298373c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2708,6 +2708,10 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) err |= __put_user(from->si_lower, &to->si_lower); err |= __put_user(from->si_upper, &to->si_upper); } +#endif +#ifdef SEGV_PKUERR + if (from->si_signo == SIGSEGV && from->si_code == SEGV_PKUERR) + err |= __put_user(from->si_pkey, &to->si_pkey); #endif break; case __SI_CHLD: -- cgit v1.2.3 From d22025570e2ebfc68819b35c5d457e53d9337217 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 18 Feb 2016 11:44:24 -0500 Subject: cgroup: fix alloc_cgroup_ns() error handling in copy_cgroup_ns() alloc_cgroup_ns() returns an ERR_PTR value on error but copy_cgroup_ns() was checking for NULL for error. Fix it. Signed-off-by: Tejun Heo Reported-by: Dan Carpenter --- kernel/cgroup.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index afb1205fc789..d92d91a4bb3e 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -6083,10 +6083,11 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, spin_unlock_bh(&css_set_lock); mutex_unlock(&cgroup_mutex); - err = -ENOMEM; new_ns = alloc_cgroup_ns(); - if (!new_ns) + if (IS_ERR(new_ns)) { + err = PTR_ERR(new_ns); goto err_out; + } new_ns->user_ns = get_user_ns(user_ns); new_ns->root_cset = cset; -- cgit v1.2.3 From 6bbd9a05a1f9839873a9290b5b7c6fafde8447ba Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Fri, 19 Feb 2016 13:53:10 -0500 Subject: bpf: grab rcu read lock for bpf_percpu_hash_update bpf_percpu_hash_update() expects rcu lock to be held and warns if it's not, which pointed out a missing rcu read lock. Fixes: 15a07b338 ("bpf: add lookup/update support for per-cpu hash and array maps") Signed-off-by: Sasha Levin Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/hashtab.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index fd5db8fe9360..a68e95133fcd 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -619,7 +619,13 @@ out: int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 map_flags) { - return __htab_percpu_map_update_elem(map, key, value, map_flags, true); + int ret; + + rcu_read_lock(); + ret = __htab_percpu_map_update_elem(map, key, value, map_flags, true); + rcu_read_unlock(); + + return ret; } static const struct bpf_map_ops htab_percpu_ops = { -- cgit v1.2.3 From 568b329a02f75ed3aaae5eb2cca384cb9e09cb29 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 17 Feb 2016 19:58:57 -0800 Subject: perf: generalize perf_callchain . avoid walking the stack when there is no room left in the buffer . generalize get_perf_callchain() to be called from bpf helper Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- arch/x86/include/asm/stacktrace.h | 2 +- arch/x86/kernel/cpu/perf_event.c | 4 ++-- arch/x86/kernel/dumpstack.c | 6 ++++-- arch/x86/kernel/stacktrace.c | 18 +++++++++++------- arch/x86/oprofile/backtrace.c | 3 ++- include/linux/perf_event.h | 13 +++++++++++-- kernel/events/callchain.c | 32 ++++++++++++++++++++------------ kernel/events/internal.h | 2 -- 8 files changed, 51 insertions(+), 29 deletions(-) (limited to 'kernel') diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 70bbe39043a9..7c247e7404be 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -37,7 +37,7 @@ print_context_stack_bp(struct thread_info *tinfo, /* Generic stack tracer with callbacks */ struct stacktrace_ops { - void (*address)(void *data, unsigned long address, int reliable); + int (*address)(void *data, unsigned long address, int reliable); /* On negative return stop dumping */ int (*stack)(void *data, char *name); walk_stack_t walk_stack; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1b443db2db50..d276b31ca473 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -2180,11 +2180,11 @@ static int backtrace_stack(void *data, char *name) return 0; } -static void backtrace_address(void *data, unsigned long addr, int reliable) +static int backtrace_address(void *data, unsigned long addr, int reliable) { struct perf_callchain_entry *entry = data; - perf_callchain_store(entry, addr); + return perf_callchain_store(entry, addr); } static const struct stacktrace_ops backtrace_ops = { diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 9c30acfadae2..0d1ff4b407d4 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -135,7 +135,8 @@ print_context_stack_bp(struct thread_info *tinfo, if (!__kernel_text_address(addr)) break; - ops->address(data, addr, 1); + if (ops->address(data, addr, 1)) + break; frame = frame->next_frame; ret_addr = &frame->return_address; print_ftrace_graph_addr(addr, data, ops, tinfo, graph); @@ -154,10 +155,11 @@ static int print_trace_stack(void *data, char *name) /* * Print one address/symbol entries per line. */ -static void print_trace_address(void *data, unsigned long addr, int reliable) +static int print_trace_address(void *data, unsigned long addr, int reliable) { touch_nmi_watchdog(); printk_stack_address(addr, reliable, data); + return 0; } static const struct stacktrace_ops print_trace_ops = { diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index fdd0c6430e5a..9ee98eefc44d 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -14,30 +14,34 @@ static int save_stack_stack(void *data, char *name) return 0; } -static void +static int __save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched) { struct stack_trace *trace = data; #ifdef CONFIG_FRAME_POINTER if (!reliable) - return; + return 0; #endif if (nosched && in_sched_functions(addr)) - return; + return 0; if (trace->skip > 0) { trace->skip--; - return; + return 0; } - if (trace->nr_entries < trace->max_entries) + if (trace->nr_entries < trace->max_entries) { trace->entries[trace->nr_entries++] = addr; + return 0; + } else { + return -1; /* no more room, stop walking the stack */ + } } -static void save_stack_address(void *data, unsigned long addr, int reliable) +static int save_stack_address(void *data, unsigned long addr, int reliable) { return __save_stack_address(data, addr, reliable, false); } -static void +static int save_stack_address_nosched(void *data, unsigned long addr, int reliable) { return __save_stack_address(data, addr, reliable, true); diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 4e664bdb535a..cb31a4440e58 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -23,12 +23,13 @@ static int backtrace_stack(void *data, char *name) return 0; } -static void backtrace_address(void *data, unsigned long addr, int reliable) +static int backtrace_address(void *data, unsigned long addr, int reliable) { unsigned int *depth = data; if ((*depth)--) oprofile_add_trace(addr); + return 0; } static struct stacktrace_ops backtrace_ops = { diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b35a61a481fa..7da3c25999df 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -964,11 +964,20 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs); +extern struct perf_callchain_entry * +get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, + bool crosstask, bool add_mark); +extern int get_callchain_buffers(void); +extern void put_callchain_buffers(void); -static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) +static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) { - if (entry->nr < PERF_MAX_STACK_DEPTH) + if (entry->nr < PERF_MAX_STACK_DEPTH) { entry->ip[entry->nr++] = ip; + return 0; + } else { + return -1; /* no more room, stop walking the stack */ + } } extern int sysctl_perf_event_paranoid; diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 9c418002b8c1..343c22f5e867 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -159,15 +159,24 @@ put_callchain_entry(int rctx) struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs) { - int rctx; - struct perf_callchain_entry *entry; - - int kernel = !event->attr.exclude_callchain_kernel; - int user = !event->attr.exclude_callchain_user; + bool kernel = !event->attr.exclude_callchain_kernel; + bool user = !event->attr.exclude_callchain_user; + /* Disallow cross-task user callchains. */ + bool crosstask = event->ctx->task && event->ctx->task != current; if (!kernel && !user) return NULL; + return get_perf_callchain(regs, 0, kernel, user, crosstask, true); +} + +struct perf_callchain_entry * +get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, + bool crosstask, bool add_mark) +{ + struct perf_callchain_entry *entry; + int rctx; + entry = get_callchain_entry(&rctx); if (rctx == -1) return NULL; @@ -175,10 +184,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) if (!entry) goto exit_put; - entry->nr = 0; + entry->nr = init_nr; if (kernel && !user_mode(regs)) { - perf_callchain_store(entry, PERF_CONTEXT_KERNEL); + if (add_mark) + perf_callchain_store(entry, PERF_CONTEXT_KERNEL); perf_callchain_kernel(entry, regs); } @@ -191,13 +201,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) } if (regs) { - /* - * Disallow cross-task user callchains. - */ - if (event->ctx->task && event->ctx->task != current) + if (crosstask) goto exit_put; - perf_callchain_store(entry, PERF_CONTEXT_USER); + if (add_mark) + perf_callchain_store(entry, PERF_CONTEXT_USER); perf_callchain_user(entry, regs); } } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 2bbad9c1274c..4199b6d193f5 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -182,8 +182,6 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) /* Callchain handling */ extern struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs); -extern int get_callchain_buffers(void); -extern void put_callchain_buffers(void); static inline int get_recursion_context(int *recursion) { -- cgit v1.2.3 From d5a3b1f691865be576c2bffa708549b8cdccda19 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 17 Feb 2016 19:58:58 -0800 Subject: bpf: introduce BPF_MAP_TYPE_STACK_TRACE add new map type to store stack traces and corresponding helper bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id @ctx: struct pt_regs* @map: pointer to stack_trace map @flags: bits 0-7 - numer of stack frames to skip bit 8 - collect user stack instead of kernel bit 9 - compare stacks by hash only bit 10 - if two different stacks hash into the same stackid discard old other bits - reserved Return: >= 0 stackid on success or negative error stackid is a 32-bit integer handle that can be further combined with other data (including other stackid) and used as a key into maps. Userspace will access stackmap using standard lookup/delete syscall commands to retrieve full stack trace for given stackid. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 21 +++++ kernel/bpf/Makefile | 3 + kernel/bpf/stackmap.c | 237 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 6 +- kernel/trace/bpf_trace.c | 2 + 6 files changed, 269 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/stackmap.c (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 90ee6ab24bc5..0cadbb7456c0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -237,6 +237,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; +extern const struct bpf_func_proto bpf_get_stackid_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2ee0fde1bf96..d3e77da8e9e8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -83,6 +83,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_MAP_TYPE_PERCPU_HASH, BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, }; enum bpf_prog_type { @@ -272,6 +273,20 @@ enum bpf_func_id { */ BPF_FUNC_perf_event_output, BPF_FUNC_skb_load_bytes, + + /** + * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id + * @ctx: struct pt_regs* + * @map: pointer to stack_trace map + * @flags: bits 0-7 - numer of stack frames to skip + * bit 8 - collect user stack instead of kernel + * bit 9 - compare stacks by hash only + * bit 10 - if two different stacks hash into the same stackid + * discard old + * other bits - reserved + * Return: >= 0 stackid on success or negative error + */ + BPF_FUNC_get_stackid, __BPF_FUNC_MAX_ID, }; @@ -294,6 +309,12 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) +/* BPF_FUNC_get_stackid flags. */ +#define BPF_F_SKIP_FIELD_MASK 0xffULL +#define BPF_F_USER_STACK (1ULL << 8) +#define BPF_F_FAST_STACK_CMP (1ULL << 9) +#define BPF_F_REUSE_STACKID (1ULL << 10) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 13272582eee0..8a932d079c24 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -2,3 +2,6 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o +ifeq ($(CONFIG_PERF_EVENTS),y) +obj-$(CONFIG_BPF_SYSCALL) += stackmap.o +endif diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c new file mode 100644 index 000000000000..8a60ee14a977 --- /dev/null +++ b/kernel/bpf/stackmap.c @@ -0,0 +1,237 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include + +struct stack_map_bucket { + struct rcu_head rcu; + u32 hash; + u32 nr; + u64 ip[]; +}; + +struct bpf_stack_map { + struct bpf_map map; + u32 n_buckets; + struct stack_map_bucket __rcu *buckets[]; +}; + +/* Called from syscall */ +static struct bpf_map *stack_map_alloc(union bpf_attr *attr) +{ + u32 value_size = attr->value_size; + struct bpf_stack_map *smap; + u64 cost, n_buckets; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + value_size < 8 || value_size % 8 || + value_size / 8 > PERF_MAX_STACK_DEPTH) + return ERR_PTR(-EINVAL); + + /* hash table size must be power of 2 */ + n_buckets = roundup_pow_of_two(attr->max_entries); + + cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-E2BIG); + + smap = kzalloc(cost, GFP_USER | __GFP_NOWARN); + if (!smap) { + smap = vzalloc(cost); + if (!smap) + return ERR_PTR(-ENOMEM); + } + + err = -E2BIG; + cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_smap; + + smap->map.map_type = attr->map_type; + smap->map.key_size = attr->key_size; + smap->map.value_size = value_size; + smap->map.max_entries = attr->max_entries; + smap->n_buckets = n_buckets; + smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + err = get_callchain_buffers(); + if (err) + goto free_smap; + + return &smap->map; + +free_smap: + kvfree(smap); + return ERR_PTR(err); +} + +static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +{ + struct pt_regs *regs = (struct pt_regs *) (long) r1; + struct bpf_map *map = (struct bpf_map *) (long) r2; + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct perf_callchain_entry *trace; + struct stack_map_bucket *bucket, *new_bucket, *old_bucket; + u32 max_depth = map->value_size / 8; + /* stack_map_alloc() checks that max_depth <= PERF_MAX_STACK_DEPTH */ + u32 init_nr = PERF_MAX_STACK_DEPTH - max_depth; + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + u32 hash, id, trace_nr, trace_len; + bool user = flags & BPF_F_USER_STACK; + bool kernel = !user; + u64 *ips; + + if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | + BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) + return -EINVAL; + + trace = get_perf_callchain(regs, init_nr, kernel, user, false, false); + + if (unlikely(!trace)) + /* couldn't fetch the stack trace */ + return -EFAULT; + + /* get_perf_callchain() guarantees that trace->nr >= init_nr + * and trace-nr <= PERF_MAX_STACK_DEPTH, so trace_nr <= max_depth + */ + trace_nr = trace->nr - init_nr; + + if (trace_nr <= skip) + /* skipping more than usable stack trace */ + return -EFAULT; + + trace_nr -= skip; + trace_len = trace_nr * sizeof(u64); + ips = trace->ip + skip + init_nr; + hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); + id = hash & (smap->n_buckets - 1); + bucket = rcu_dereference(smap->buckets[id]); + + if (bucket && bucket->hash == hash) { + if (flags & BPF_F_FAST_STACK_CMP) + return id; + if (bucket->nr == trace_nr && + memcmp(bucket->ip, ips, trace_len) == 0) + return id; + } + + /* this call stack is not in the map, try to add it */ + if (bucket && !(flags & BPF_F_REUSE_STACKID)) + return -EEXIST; + + new_bucket = kmalloc(sizeof(struct stack_map_bucket) + map->value_size, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!new_bucket)) + return -ENOMEM; + + memcpy(new_bucket->ip, ips, trace_len); + memset(new_bucket->ip + trace_len / 8, 0, map->value_size - trace_len); + new_bucket->hash = hash; + new_bucket->nr = trace_nr; + + old_bucket = xchg(&smap->buckets[id], new_bucket); + if (old_bucket) + kfree_rcu(old_bucket, rcu); + return id; +} + +const struct bpf_func_proto bpf_get_stackid_proto = { + .func = bpf_get_stackid, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, +}; + +/* Called from syscall or from eBPF program */ +static void *stack_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct stack_map_bucket *bucket; + u32 id = *(u32 *)key; + + if (unlikely(id >= smap->n_buckets)) + return NULL; + bucket = rcu_dereference(smap->buckets[id]); + return bucket ? bucket->ip : NULL; +} + +static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -EINVAL; +} + +static int stack_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return -EINVAL; +} + +/* Called from syscall or from eBPF program */ +static int stack_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct stack_map_bucket *old_bucket; + u32 id = *(u32 *)key; + + if (unlikely(id >= smap->n_buckets)) + return -E2BIG; + + old_bucket = xchg(&smap->buckets[id], NULL); + if (old_bucket) { + kfree_rcu(old_bucket, rcu); + return 0; + } else { + return -ENOENT; + } +} + +/* Called when map->refcnt goes to zero, either from workqueue or from syscall */ +static void stack_map_free(struct bpf_map *map) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + int i; + + synchronize_rcu(); + + for (i = 0; i < smap->n_buckets; i++) + if (smap->buckets[i]) + kfree_rcu(smap->buckets[i], rcu); + kvfree(smap); + put_callchain_buffers(); +} + +static const struct bpf_map_ops stack_map_ops = { + .map_alloc = stack_map_alloc, + .map_free = stack_map_free, + .map_get_next_key = stack_map_get_next_key, + .map_lookup_elem = stack_map_lookup_elem, + .map_update_elem = stack_map_update_elem, + .map_delete_elem = stack_map_delete_elem, +}; + +static struct bpf_map_type_list stack_map_type __read_mostly = { + .ops = &stack_map_ops, + .type = BPF_MAP_TYPE_STACK_TRACE, +}; + +static int __init register_stack_map(void) +{ + bpf_register_map_type(&stack_map_type); + return 0; +} +late_initcall(register_stack_map); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d1d3e8f57de9..42ba4ccc020b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -246,6 +246,7 @@ static const struct { {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call}, {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read}, {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output}, + {BPF_MAP_TYPE_STACK_TRACE, BPF_FUNC_get_stackid}, }; static void print_verifier_state(struct verifier_env *env) @@ -911,8 +912,11 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) * don't allow any other map type to be passed into * the special func; */ - if (bool_func && bool_map != bool_func) + if (bool_func && bool_map != bool_func) { + verbose("cannot pass map_type %d into func %d\n", + map->map_type, func_id); return -EINVAL; + } } return 0; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 326a75e884db..4b8caa392b86 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -299,6 +299,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_perf_event_read_proto; case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto; + case BPF_FUNC_get_stackid: + return &bpf_get_stackid_proto; default: return NULL; } -- cgit v1.2.3 From a1db74209483a24c861c848b4bb79a4d945ef6fa Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 30 Dec 2015 07:35:30 -0500 Subject: module: replace copy_module_from_fd with kernel version Replace copy_module_from_fd() with kernel_read_file_from_fd(). Although none of the upstreamed LSMs define a kernel_module_from_file hook, IMA is called, based on policy, to prevent unsigned kernel modules from being loaded by the original kernel module syscall and to measure/appraise signed kernel modules. The security function security_kernel_module_from_file() was called prior to reading a kernel module. Preventing unsigned kernel modules from being loaded by the original kernel module syscall remains on the pre-read kernel_read_file() security hook. Instead of reading the kernel module twice, once for measuring/appraising and again for loading the kernel module, the signature validation is moved to the kernel_post_read_file() security hook. This patch removes the security_kernel_module_from_file() hook and security call. Signed-off-by: Mimi Zohar Acked-by: Kees Cook Acked-by: Luis R. Rodriguez Cc: Rusty Russell --- include/linux/fs.h | 1 + include/linux/ima.h | 6 ---- include/linux/lsm_hooks.h | 7 ---- include/linux/security.h | 5 --- kernel/module.c | 68 +++++---------------------------------- security/integrity/ima/ima_main.c | 35 ++++++++------------ security/security.c | 12 ------- 7 files changed, 22 insertions(+), 112 deletions(-) (limited to 'kernel') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9c85deae1bf2..fb08b668c37a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2578,6 +2578,7 @@ extern int do_pipe_flags(int *, int); enum kernel_read_file_id { READING_FIRMWARE = 1, + READING_MODULE, READING_MAX_ID }; diff --git a/include/linux/ima.h b/include/linux/ima.h index 6adcaea8101c..e6516cbbe9bf 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -18,7 +18,6 @@ extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask, int opened); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); -extern int ima_module_check(struct file *file); extern int ima_read_file(struct file *file, enum kernel_read_file_id id); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); @@ -44,11 +43,6 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) return 0; } -static inline int ima_module_check(struct file *file) -{ - return 0; -} - static inline int ima_read_file(struct file *file, enum kernel_read_file_id id) { return 0; diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d32b7bd13635..cdee11cbcdf1 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -546,12 +546,6 @@ * userspace to load a kernel module with the given name. * @kmod_name name of the module requested by the kernel * Return 0 if successful. - * @kernel_module_from_file: - * Load a kernel module from userspace. - * @file contains the file structure pointing to the file containing - * the kernel module to load. If the module is being loaded from a blob, - * this argument will be NULL. - * Return 0 if permission is granted. * @kernel_read_file: * Read a file specified by userspace. * @file contains the file structure pointing to the file being read @@ -1725,7 +1719,6 @@ struct security_hook_heads { struct list_head kernel_read_file; struct list_head kernel_post_read_file; struct list_head kernel_module_request; - struct list_head kernel_module_from_file; struct list_head task_fix_setuid; struct list_head task_setpgid; struct list_head task_getpgid; diff --git a/include/linux/security.h b/include/linux/security.h index 071fb747fdbb..157f0cb1e4d2 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -859,11 +859,6 @@ static inline int security_kernel_module_request(char *kmod_name) return 0; } -static inline int security_kernel_module_from_file(struct file *file) -{ - return 0; -} - static inline int security_kernel_read_file(struct file *file, enum kernel_read_file_id id) { diff --git a/kernel/module.c b/kernel/module.c index 8358f4697c0c..955410928696 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2654,7 +2654,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len, if (info->len < sizeof(*(info->hdr))) return -ENOEXEC; - err = security_kernel_module_from_file(NULL); + err = security_kernel_read_file(NULL, READING_MODULE); if (err) return err; @@ -2672,63 +2672,6 @@ static int copy_module_from_user(const void __user *umod, unsigned long len, return 0; } -/* Sets info->hdr and info->len. */ -static int copy_module_from_fd(int fd, struct load_info *info) -{ - struct fd f = fdget(fd); - int err; - struct kstat stat; - loff_t pos; - ssize_t bytes = 0; - - if (!f.file) - return -ENOEXEC; - - err = security_kernel_module_from_file(f.file); - if (err) - goto out; - - err = vfs_getattr(&f.file->f_path, &stat); - if (err) - goto out; - - if (stat.size > INT_MAX) { - err = -EFBIG; - goto out; - } - - /* Don't hand 0 to vmalloc, it whines. */ - if (stat.size == 0) { - err = -EINVAL; - goto out; - } - - info->hdr = vmalloc(stat.size); - if (!info->hdr) { - err = -ENOMEM; - goto out; - } - - pos = 0; - while (pos < stat.size) { - bytes = kernel_read(f.file, pos, (char *)(info->hdr) + pos, - stat.size - pos); - if (bytes < 0) { - vfree(info->hdr); - err = bytes; - goto out; - } - if (bytes == 0) - break; - pos += bytes; - } - info->len = pos; - -out: - fdput(f); - return err; -} - static void free_copy(struct load_info *info) { vfree(info->hdr); @@ -3589,8 +3532,10 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) { - int err; struct load_info info = { }; + loff_t size; + void *hdr; + int err; err = may_init_module(); if (err) @@ -3602,9 +3547,12 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) |MODULE_INIT_IGNORE_VERMAGIC)) return -EINVAL; - err = copy_module_from_fd(fd, &info); + err = kernel_read_file_from_fd(fd, &hdr, &size, INT_MAX, + READING_MODULE); if (err) return err; + info.hdr = hdr; + info.len = size; return load_module(&info, uargs, flags); } diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index bbb80df28fb1..5da0b9c00072 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -315,28 +315,6 @@ int ima_file_check(struct file *file, int mask, int opened) } EXPORT_SYMBOL_GPL(ima_file_check); -/** - * ima_module_check - based on policy, collect/store/appraise measurement. - * @file: pointer to the file to be measured/appraised - * - * Measure/appraise kernel modules based on policy. - * - * On success return 0. On integrity appraisal error, assuming the file - * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. - */ -int ima_module_check(struct file *file) -{ - if (!file) { -#ifndef CONFIG_MODULE_SIG_FORCE - if ((ima_appraise & IMA_APPRAISE_MODULES) && - (ima_appraise & IMA_APPRAISE_ENFORCE)) - return -EACCES; /* INTEGRITY_UNKNOWN */ -#endif - return 0; /* We rely on module signature checking */ - } - return process_measurement(file, NULL, 0, MAY_EXEC, MODULE_CHECK, 0); -} - /** * ima_read_file - pre-measure/appraise hook decision based on policy * @file: pointer to the file to be measured/appraised/audit @@ -350,6 +328,14 @@ int ima_module_check(struct file *file) */ int ima_read_file(struct file *file, enum kernel_read_file_id read_id) { + if (!file && read_id == READING_MODULE) { +#ifndef CONFIG_MODULE_SIG_FORCE + if ((ima_appraise & IMA_APPRAISE_MODULES) && + (ima_appraise & IMA_APPRAISE_ENFORCE)) + return -EACCES; /* INTEGRITY_UNKNOWN */ +#endif + return 0; /* We rely on module signature checking */ + } return 0; } @@ -378,6 +364,9 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size, return 0; } + if (!file && read_id == READING_MODULE) /* MODULE_SIG_FORCE enabled */ + return 0; + if (!file || !buf || size == 0) { /* should never happen */ if (ima_appraise & IMA_APPRAISE_ENFORCE) return -EACCES; @@ -386,6 +375,8 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size, if (read_id == READING_FIRMWARE) func = FIRMWARE_CHECK; + else if (read_id == READING_MODULE) + func = MODULE_CHECK; return process_measurement(file, buf, size, MAY_READ, func, 0); } diff --git a/security/security.c b/security/security.c index 8e699f98a600..3644b0344d29 100644 --- a/security/security.c +++ b/security/security.c @@ -889,16 +889,6 @@ int security_kernel_module_request(char *kmod_name) return call_int_hook(kernel_module_request, 0, kmod_name); } -int security_kernel_module_from_file(struct file *file) -{ - int ret; - - ret = call_int_hook(kernel_module_from_file, 0, file); - if (ret) - return ret; - return ima_module_check(file); -} - int security_kernel_read_file(struct file *file, enum kernel_read_file_id id) { int ret; @@ -1705,8 +1695,6 @@ struct security_hook_heads security_hook_heads = { LIST_HEAD_INIT(security_hook_heads.kernel_create_files_as), .kernel_module_request = LIST_HEAD_INIT(security_hook_heads.kernel_module_request), - .kernel_module_from_file = - LIST_HEAD_INIT(security_hook_heads.kernel_module_from_file), .kernel_read_file = LIST_HEAD_INIT(security_hook_heads.kernel_read_file), .kernel_post_read_file = -- cgit v1.2.3 From b804defe4297157a9ff45863769efe9a01953398 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Thu, 14 Jan 2016 20:59:14 -0500 Subject: kexec: replace call to copy_file_from_fd() with kernel version Replace copy_file_from_fd() with kernel_read_file_from_fd(). Two new identifiers named READING_KEXEC_IMAGE and READING_KEXEC_INITRAMFS are defined for measuring, appraising or auditing the kexec image and initramfs. Changelog v3: - return -EBADF, not -ENOEXEC - identifier change - split patch, moving copy_file_from_fd() to a separate patch - split patch, moving IMA changes to a separate patch v0: - use kstat file size type loff_t, not size_t - Calculate the file hash from the in memory buffer - Dave Young Signed-off-by: Mimi Zohar Acked-by: Kees Cook Acked-by: Luis R. Rodriguez Cc: Eric Biederman Acked-by: Dave Young --- include/linux/fs.h | 2 ++ kernel/kexec_file.c | 73 +++++++---------------------------------------------- 2 files changed, 11 insertions(+), 64 deletions(-) (limited to 'kernel') diff --git a/include/linux/fs.h b/include/linux/fs.h index fb08b668c37a..52567252288e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2579,6 +2579,8 @@ extern int do_pipe_flags(int *, int); enum kernel_read_file_id { READING_FIRMWARE = 1, READING_MODULE, + READING_KEXEC_IMAGE, + READING_KEXEC_INITRAMFS, READING_MAX_ID }; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 007b791f676d..b696c3f3708f 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -33,65 +34,6 @@ size_t __weak kexec_purgatory_size = 0; static int kexec_calculate_store_digests(struct kimage *image); -static int copy_file_from_fd(int fd, void **buf, unsigned long *buf_len) -{ - struct fd f = fdget(fd); - int ret; - struct kstat stat; - loff_t pos; - ssize_t bytes = 0; - - if (!f.file) - return -EBADF; - - ret = vfs_getattr(&f.file->f_path, &stat); - if (ret) - goto out; - - if (stat.size > INT_MAX) { - ret = -EFBIG; - goto out; - } - - /* Don't hand 0 to vmalloc, it whines. */ - if (stat.size == 0) { - ret = -EINVAL; - goto out; - } - - *buf = vmalloc(stat.size); - if (!*buf) { - ret = -ENOMEM; - goto out; - } - - pos = 0; - while (pos < stat.size) { - bytes = kernel_read(f.file, pos, (char *)(*buf) + pos, - stat.size - pos); - if (bytes < 0) { - vfree(*buf); - ret = bytes; - goto out; - } - - if (bytes == 0) - break; - pos += bytes; - } - - if (pos != stat.size) { - ret = -EBADF; - vfree(*buf); - goto out; - } - - *buf_len = pos; -out: - fdput(f); - return ret; -} - /* Architectures can provide this probe function */ int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long buf_len) @@ -182,16 +124,17 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, { int ret = 0; void *ldata; + loff_t size; - ret = copy_file_from_fd(kernel_fd, &image->kernel_buf, - &image->kernel_buf_len); + ret = kernel_read_file_from_fd(kernel_fd, &image->kernel_buf, + &size, INT_MAX, READING_KEXEC_IMAGE); if (ret) return ret; + image->kernel_buf_len = size; /* Call arch image probe handlers */ ret = arch_kexec_kernel_image_probe(image, image->kernel_buf, image->kernel_buf_len); - if (ret) goto out; @@ -206,10 +149,12 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, #endif /* It is possible that there no initramfs is being loaded */ if (!(flags & KEXEC_FILE_NO_INITRAMFS)) { - ret = copy_file_from_fd(initrd_fd, &image->initrd_buf, - &image->initrd_buf_len); + ret = kernel_read_file_from_fd(initrd_fd, &image->initrd_buf, + &size, INT_MAX, + READING_KEXEC_INITRAMFS); if (ret) goto out; + image->initrd_buf_len = size; } if (cmdline_len) { -- cgit v1.2.3 From 8e2fe1d9f1a20924f98ea46931a1d7fb092aa876 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 19 Feb 2016 23:05:22 +0100 Subject: bpf: add new arg_type that allows for 0 sized stack buffer Currently, when we pass a buffer from the eBPF stack into a helper function, the function proto indicates argument types as ARG_PTR_TO_STACK and ARG_CONST_STACK_SIZE pair. If R contains the former, then R must be of the latter type. Then, verifier checks whether the buffer points into eBPF stack, is initialized, etc. The verifier also guarantees that the constant value passed in R is greater than 0, so helper functions don't need to test for it and can always assume a non-NULL initialized buffer as well as non-0 buffer size. This patch adds a new argument types ARG_CONST_STACK_SIZE_OR_ZERO that allows to also pass NULL as R and 0 as R into the helper function. Such helper functions, of course, need to be able to handle these cases internally then. Verifier guarantees that either R == NULL && R == 0 or R != NULL && R != 0 (like the case of ARG_CONST_STACK_SIZE), any other combinations are not possible to load. I went through various options of extending the verifier, and introducing the type ARG_CONST_STACK_SIZE_OR_ZERO seems to have most minimal changes needed to the verifier. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + kernel/bpf/verifier.c | 42 ++++++++++++++++++++++++++++++++---------- 2 files changed, 33 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0cadbb7456c0..51e498e5470e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -65,6 +65,7 @@ enum bpf_arg_type { */ ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */ ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */ + ARG_CONST_STACK_SIZE_OR_ZERO, /* number of bytes accessed from stack or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 42ba4ccc020b..36dc497deaa3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -779,15 +779,24 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn) * bytes from that pointer, make sure that it's within stack boundary * and all elements of stack are initialized */ -static int check_stack_boundary(struct verifier_env *env, - int regno, int access_size) +static int check_stack_boundary(struct verifier_env *env, int regno, + int access_size, bool zero_size_allowed) { struct verifier_state *state = &env->cur_state; struct reg_state *regs = state->regs; int off, i; - if (regs[regno].type != PTR_TO_STACK) + if (regs[regno].type != PTR_TO_STACK) { + if (zero_size_allowed && access_size == 0 && + regs[regno].type == CONST_IMM && + regs[regno].imm == 0) + return 0; + + verbose("R%d type=%s expected=%s\n", regno, + reg_type_str[regs[regno].type], + reg_type_str[PTR_TO_STACK]); return -EACCES; + } off = regs[regno].imm; if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || @@ -830,15 +839,24 @@ static int check_func_arg(struct verifier_env *env, u32 regno, return 0; } - if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY || + if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - } else if (arg_type == ARG_CONST_STACK_SIZE) { + } else if (arg_type == ARG_CONST_STACK_SIZE || + arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) { expected_type = CONST_IMM; } else if (arg_type == ARG_CONST_MAP_PTR) { expected_type = CONST_PTR_TO_MAP; } else if (arg_type == ARG_PTR_TO_CTX) { expected_type = PTR_TO_CTX; + } else if (arg_type == ARG_PTR_TO_STACK) { + expected_type = PTR_TO_STACK; + /* One exception here. In case function allows for NULL to be + * passed in as argument, it's a CONST_IMM type. Final test + * happens during stack boundary checking. + */ + if (reg->type == CONST_IMM && reg->imm == 0) + expected_type = CONST_IMM; } else { verbose("unsupported arg_type %d\n", arg_type); return -EFAULT; @@ -868,8 +886,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->key\n"); return -EACCES; } - err = check_stack_boundary(env, regno, (*mapp)->key_size); - + err = check_stack_boundary(env, regno, (*mapp)->key_size, + false); } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity @@ -879,9 +897,12 @@ static int check_func_arg(struct verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->value\n"); return -EACCES; } - err = check_stack_boundary(env, regno, (*mapp)->value_size); + err = check_stack_boundary(env, regno, (*mapp)->value_size, + false); + } else if (arg_type == ARG_CONST_STACK_SIZE || + arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) { + bool zero_size_allowed = (arg_type == ARG_CONST_STACK_SIZE_OR_ZERO); - } else if (arg_type == ARG_CONST_STACK_SIZE) { /* bpf_xxx(..., buf, len) call will access 'len' bytes * from stack pointer 'buf'. Check it * note: regno == len, regno - 1 == buf @@ -891,7 +912,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno, verbose("ARG_CONST_STACK_SIZE cannot be first argument\n"); return -EACCES; } - err = check_stack_boundary(env, regno - 1, reg->imm); + err = check_stack_boundary(env, regno - 1, reg->imm, + zero_size_allowed); } return err; -- cgit v1.2.3 From b598dde354de22d87f664a7b99b8c21437da8efb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Feb 2016 22:25:45 -0500 Subject: cgroup: fix error return value of cgroup_addrm_files() cgroup_addrm_files() incorrectly returned 0 after add failure. Fix it. Signed-off-by: Tejun Heo Acked-by: Johannes Weiner --- kernel/cgroup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7ad61915967f..68b032df77f5 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3369,7 +3369,7 @@ static int cgroup_addrm_files(struct cgroup_subsys_state *css, bool is_add) { struct cftype *cft, *cft_end = NULL; - int ret; + int ret = 0; lockdep_assert_held(&cgroup_mutex); @@ -3398,7 +3398,7 @@ restart: cgroup_rm_file(cgrp, cft); } } - return 0; + return ret; } static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) -- cgit v1.2.3 From 5eb385cc5ae1b31fbcdd727854a00c5a083f6b9b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Feb 2016 22:25:46 -0500 Subject: Revert "cgroup: add cgroup_subsys->css_e_css_changed()" This reverts commit 56c807ba4e91f0980567b6a69de239677879b17f. cgroup_subsys->css_e_css_changed() was supposed to be used by cgroup writeback support; however, the change to per-inode cgroup association made it unnecessary and the callback doesn't have any user. Remove it. Signed-off-by: Tejun Heo Acked-by: Johannes Weiner --- include/linux/cgroup-defs.h | 1 - kernel/cgroup.c | 18 ------------------ 2 files changed, 19 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 789471dba6fb..4f3c0dac26b5 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -434,7 +434,6 @@ struct cgroup_subsys { void (*css_released)(struct cgroup_subsys_state *css); void (*css_free)(struct cgroup_subsys_state *css); void (*css_reset)(struct cgroup_subsys_state *css); - void (*css_e_css_changed)(struct cgroup_subsys_state *css); int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 68b032df77f5..7727b6e43e10 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3127,24 +3127,6 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, } } - /* - * The effective csses of all the descendants (excluding @cgrp) may - * have changed. Subsystems can optionally subscribe to this event - * by implementing ->css_e_css_changed() which is invoked if any of - * the effective csses seen from the css's cgroup may have changed. - */ - for_each_subsys(ss, ssid) { - struct cgroup_subsys_state *this_css = cgroup_css(cgrp, ss); - struct cgroup_subsys_state *css; - - if (!ss->css_e_css_changed || !this_css) - continue; - - css_for_each_descendant_pre(css, this_css) - if (css != this_css) - ss->css_e_css_changed(css); - } - kernfs_activate(cgrp->kn); ret = 0; out_unlock: -- cgit v1.2.3 From 8699b7762a623c46ced891b3cf490058b56cf99c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Feb 2016 22:25:46 -0500 Subject: cgroup: s/child_subsys_mask/subtree_ss_mask/ For consistency with cgroup->subtree_control. * cgroup->child_subsys_mask -> cgroup->subtree_ss_mask * cgroup_calc_child_subsys_mask() -> cgroup_calc_subtree_ss_mask() * cgroup_refresh_child_subsys_mask() -> cgroup_refresh_subtree_ss_mask() No functional changes. Signed-off-by: Tejun Heo Acked-by: Johannes Weiner --- include/linux/cgroup-defs.h | 11 +++++------ kernel/cgroup.c | 48 ++++++++++++++++++++++----------------------- 2 files changed, 29 insertions(+), 30 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4f3c0dac26b5..c68ae7f0fb5f 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -253,13 +253,12 @@ struct cgroup { /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through - * "cgroup.subtree_control" while ->child_subsys_mask is the - * effective one which may have more subsystems enabled. - * Controller knobs are made available iff it's enabled in - * ->subtree_control. + * "cgroup.subtree_control" while ->child_ss_mask is the effective + * one which may have more subsystems enabled. Controller knobs + * are made available iff it's enabled in ->subtree_control. */ - unsigned int subtree_control; - unsigned int child_subsys_mask; + unsigned long subtree_control; + unsigned long subtree_ss_mask; /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7727b6e43e10..f3cd67bfe6c0 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -391,10 +391,10 @@ static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, /* * This function is used while updating css associations and thus - * can't test the csses directly. Use ->child_subsys_mask. + * can't test the csses directly. Use ->subtree_ss_mask. */ while (cgroup_parent(cgrp) && - !(cgroup_parent(cgrp)->child_subsys_mask & (1 << ss->id))) + !(cgroup_parent(cgrp)->subtree_ss_mask & (1 << ss->id))) cgrp = cgroup_parent(cgrp); return cgroup_css(cgrp, ss); @@ -1256,7 +1256,7 @@ static umode_t cgroup_file_mode(const struct cftype *cft) } /** - * cgroup_calc_child_subsys_mask - calculate child_subsys_mask + * cgroup_calc_subtree_ss_mask - calculate subtree_ss_mask * @cgrp: the target cgroup * @subtree_control: the new subtree_control mask to consider * @@ -1268,8 +1268,8 @@ static umode_t cgroup_file_mode(const struct cftype *cft) * @subtree_control is to be applied to @cgrp. The returned mask is always * a superset of @subtree_control and follows the usual hierarchy rules. */ -static unsigned long cgroup_calc_child_subsys_mask(struct cgroup *cgrp, - unsigned long subtree_control) +static unsigned long cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, + unsigned long subtree_control) { struct cgroup *parent = cgroup_parent(cgrp); unsigned long cur_ss_mask = subtree_control; @@ -1293,7 +1293,7 @@ static unsigned long cgroup_calc_child_subsys_mask(struct cgroup *cgrp, * to non-default hierarchies. */ if (parent) - new_ss_mask &= parent->child_subsys_mask; + new_ss_mask &= parent->subtree_ss_mask; else new_ss_mask &= cgrp->root->subsys_mask; @@ -1306,16 +1306,16 @@ static unsigned long cgroup_calc_child_subsys_mask(struct cgroup *cgrp, } /** - * cgroup_refresh_child_subsys_mask - update child_subsys_mask + * cgroup_refresh_subtree_ss_mask - update subtree_ss_mask * @cgrp: the target cgroup * - * Update @cgrp->child_subsys_mask according to the current - * @cgrp->subtree_control using cgroup_calc_child_subsys_mask(). + * Update @cgrp->subtree_ss_mask according to the current + * @cgrp->subtree_control using cgroup_calc_subtree_ss_mask(). */ -static void cgroup_refresh_child_subsys_mask(struct cgroup *cgrp) +static void cgroup_refresh_subtree_ss_mask(struct cgroup *cgrp) { - cgrp->child_subsys_mask = - cgroup_calc_child_subsys_mask(cgrp, cgrp->subtree_control); + cgrp->subtree_ss_mask = + cgroup_calc_subtree_ss_mask(cgrp, cgrp->subtree_control); } /** @@ -1542,7 +1542,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root, src_root->subsys_mask &= ~(1 << ssid); scgrp->subtree_control &= ~(1 << ssid); - cgroup_refresh_child_subsys_mask(scgrp); + cgroup_refresh_subtree_ss_mask(scgrp); /* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; @@ -1550,7 +1550,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root, static_branch_enable(cgroup_subsys_on_dfl_key[ssid]); } else { dcgrp->subtree_control |= 1 << ssid; - cgroup_refresh_child_subsys_mask(dcgrp); + cgroup_refresh_subtree_ss_mask(dcgrp); static_branch_disable(cgroup_subsys_on_dfl_key[ssid]); } @@ -2523,11 +2523,11 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp, lockdep_assert_held(&cgroup_mutex); /* - * Except for the root, child_subsys_mask must be zero for a cgroup + * Except for the root, subtree_ss_mask must be zero for a cgroup * with tasks so that child cgroups don't compete against tasks. */ if (dst_cgrp && cgroup_on_dfl(dst_cgrp) && cgroup_parent(dst_cgrp) && - dst_cgrp->child_subsys_mask) + dst_cgrp->subtree_ss_mask) return -EBUSY; /* look up the dst cset for each src cset and link it to src */ @@ -2880,7 +2880,7 @@ static int cgroup_subtree_control_show(struct seq_file *seq, void *v) * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy * @cgrp: root of the subtree to update csses for * - * @cgrp's child_subsys_mask has changed and its subtree's (self excluded) + * @cgrp's subtree_ss_mask has changed and its subtree's (self excluded) * css associations need to be updated accordingly. This function looks up * all css_sets which are attached to the subtree, creates the matching * updated css_sets and migrates the tasks to the new ones. @@ -2902,7 +2902,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) { struct cgrp_cset_link *link; - /* self is not affected by child_subsys_mask change */ + /* self is not affected by subtree_ss_mask change */ if (css->cgroup == cgrp) continue; @@ -3034,9 +3034,9 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, * depending on subsystem dependencies. */ old_sc = cgrp->subtree_control; - old_ss = cgrp->child_subsys_mask; + old_ss = cgrp->subtree_ss_mask; new_sc = (old_sc | enable) & ~disable; - new_ss = cgroup_calc_child_subsys_mask(cgrp, new_sc); + new_ss = cgroup_calc_subtree_ss_mask(cgrp, new_sc); css_enable = ~old_ss & new_ss; css_disable = old_ss & ~new_ss; @@ -3069,7 +3069,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, } cgrp->subtree_control = new_sc; - cgrp->child_subsys_mask = new_ss; + cgrp->subtree_ss_mask = new_ss; /* * Create new csses or make the existing ones visible. A css is @@ -3135,7 +3135,7 @@ out_unlock: err_undo_css: cgrp->subtree_control = old_sc; - cgrp->child_subsys_mask = old_ss; + cgrp->subtree_ss_mask = old_ss; for_each_subsys(ss, ssid) { if (!(enable & (1 << ssid))) @@ -4969,7 +4969,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, /* let's create and online css's */ for_each_subsys(ss, ssid) { - if (parent->child_subsys_mask & (1 << ssid)) { + if (parent->subtree_ss_mask & (1 << ssid)) { ret = create_css(cgrp, ss, parent->subtree_control & (1 << ssid)); if (ret) @@ -4983,7 +4983,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, */ if (!cgroup_on_dfl(cgrp)) { cgrp->subtree_control = parent->subtree_control; - cgroup_refresh_child_subsys_mask(cgrp); + cgroup_refresh_subtree_ss_mask(cgrp); } kernfs_activate(kn); -- cgit v1.2.3 From b4e0eeafba61b141c3af22d6636be3f477c5d3bd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Feb 2016 22:25:46 -0500 Subject: cgroup: convert for_each_subsys_which() to do-while style for_each_subsys_which() allows iterating subsystems specified in a subsystem bitmask; unfortunately, it requires the mask to be an unsigned long l-value which can be inconvenient and makes it awkward to use a smaller type for subsystem masks. This patch converts for_each_subsy_which() to do-while style which allows it to drop the l-value requirement. The new iterator is named do_each_subsys_mask() / while_each_subsys_mask(). Signed-off-by: Tejun Heo Cc: Aleksa Sarai Acked-by: Johannes Weiner --- kernel/cgroup.c | 72 ++++++++++++++++++++++++++++++++------------------------- 1 file changed, 40 insertions(+), 32 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f3cd67bfe6c0..5d102980dc27 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -514,22 +514,28 @@ static int notify_on_release(const struct cgroup *cgrp) (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) /** - * for_each_subsys_which - filter for_each_subsys with a bitmask + * do_each_subsys_mask - filter for_each_subsys with a bitmask * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end - * @ss_maskp: a pointer to the bitmask + * @ss_mask: the bitmask * * The block will only run for cases where the ssid-th bit (1 << ssid) of - * mask is set to 1. + * @ss_mask is set. */ -#define for_each_subsys_which(ss, ssid, ss_maskp) \ - if (!CGROUP_SUBSYS_COUNT) /* to avoid spurious gcc warning */ \ +#define do_each_subsys_mask(ss, ssid, ss_mask) do { \ + unsigned long __ss_mask = (ss_mask); \ + if (!CGROUP_SUBSYS_COUNT) { /* to avoid spurious gcc warning */ \ (ssid) = 0; \ - else \ - for_each_set_bit(ssid, ss_maskp, CGROUP_SUBSYS_COUNT) \ - if (((ss) = cgroup_subsys[ssid]) && false) \ - break; \ - else + break; \ + } \ + for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \ + (ss) = cgroup_subsys[ssid]; \ + { + +#define while_each_subsys_mask() \ + } \ + } \ +} while (false) /* iterate across the hierarchies */ #define for_each_root(root) \ @@ -1284,8 +1290,9 @@ static unsigned long cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, while (true) { unsigned long new_ss_mask = cur_ss_mask; - for_each_subsys_which(ss, ssid, &cur_ss_mask) + do_each_subsys_mask(ss, ssid, cur_ss_mask) { new_ss_mask |= ss->depends_on; + } while_each_subsys_mask(); /* * Mask out subsystems which aren't available. This can @@ -1469,7 +1476,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root, lockdep_assert_held(&cgroup_mutex); - for_each_subsys_which(ss, ssid, &ss_mask) { + do_each_subsys_mask(ss, ssid, ss_mask) { /* if @ss has non-root csses attached to it, can't move */ if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss))) return -EBUSY; @@ -1477,14 +1484,14 @@ static int rebind_subsystems(struct cgroup_root *dst_root, /* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY; - } + } while_each_subsys_mask(); /* skip creating root files on dfl_root for inhibited subsystems */ tmp_ss_mask = ss_mask; if (dst_root == &cgrp_dfl_root) tmp_ss_mask &= ~cgrp_dfl_root_inhibit_ss_mask; - for_each_subsys_which(ss, ssid, &tmp_ss_mask) { + do_each_subsys_mask(ss, ssid, tmp_ss_mask) { struct cgroup *scgrp = &ss->root->cgrp; int tssid; @@ -1507,19 +1514,19 @@ static int rebind_subsystems(struct cgroup_root *dst_root, continue; } - for_each_subsys_which(ss, tssid, &tmp_ss_mask) { + do_each_subsys_mask(ss, tssid, tmp_ss_mask) { if (tssid == ssid) break; css_clear_dir(cgroup_css(scgrp, ss), dcgrp); - } + } while_each_subsys_mask(); return ret; - } + } while_each_subsys_mask(); /* * Nothing can fail from this point on. Remove files for the * removed subsystems and rebind each subsystem. */ - for_each_subsys_which(ss, ssid, &ss_mask) { + do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); @@ -1556,7 +1563,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root, if (ss->bind) ss->bind(css); - } + } while_each_subsys_mask(); kernfs_activate(dcgrp->kn); return 0; @@ -2838,12 +2845,12 @@ static void cgroup_print_ss_mask(struct seq_file *seq, unsigned long ss_mask) bool printed = false; int ssid; - for_each_subsys_which(ss, ssid, &ss_mask) { + do_each_subsys_mask(ss, ssid, ss_mask) { if (printed) seq_putc(seq, ' '); seq_printf(seq, "%s", ss->name); printed = true; - } + } while_each_subsys_mask(); if (printed) seq_putc(seq, '\n'); } @@ -2956,11 +2963,9 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, */ buf = strstrip(buf); while ((tok = strsep(&buf, " "))) { - unsigned long tmp_ss_mask = ~cgrp_dfl_root_inhibit_ss_mask; - if (tok[0] == '\0') continue; - for_each_subsys_which(ss, ssid, &tmp_ss_mask) { + do_each_subsys_mask(ss, ssid, ~cgrp_dfl_root_inhibit_ss_mask) { if (!cgroup_ssid_enabled(ssid) || strcmp(tok + 1, ss->name)) continue; @@ -2975,7 +2980,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, return -EINVAL; } break; - } + } while_each_subsys_mask(); if (ssid == CGROUP_SUBSYS_COUNT) return -EINVAL; } @@ -3049,7 +3054,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, * still around. In such cases, wait till it's gone using * offline_waitq. */ - for_each_subsys_which(ss, ssid, &css_enable) { + do_each_subsys_mask(ss, ssid, css_enable) { cgroup_for_each_live_child(child, cgrp) { DEFINE_WAIT(wait); @@ -3066,7 +3071,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, return restart_syscall(); } - } + } while_each_subsys_mask(); cgrp->subtree_control = new_sc; cgrp->subtree_ss_mask = new_ss; @@ -5509,11 +5514,11 @@ int cgroup_can_fork(struct task_struct *child) struct cgroup_subsys *ss; int i, j, ret; - for_each_subsys_which(ss, i, &have_canfork_callback) { + do_each_subsys_mask(ss, i, have_canfork_callback) { ret = ss->can_fork(child); if (ret) goto out_revert; - } + } while_each_subsys_mask(); return 0; @@ -5598,8 +5603,9 @@ void cgroup_post_fork(struct task_struct *child) * css_set; otherwise, @child might change state between ->fork() * and addition to css_set. */ - for_each_subsys_which(ss, i, &have_fork_callback) + do_each_subsys_mask(ss, i, have_fork_callback) { ss->fork(child); + } while_each_subsys_mask(); } /** @@ -5642,8 +5648,9 @@ void cgroup_exit(struct task_struct *tsk) } /* see cgroup_post_fork() for details */ - for_each_subsys_which(ss, i, &have_exit_callback) + do_each_subsys_mask(ss, i, have_exit_callback) { ss->exit(tsk); + } while_each_subsys_mask(); } void cgroup_free(struct task_struct *task) @@ -5652,8 +5659,9 @@ void cgroup_free(struct task_struct *task) struct cgroup_subsys *ss; int ssid; - for_each_subsys_which(ss, ssid, &have_free_callback) + do_each_subsys_mask(ss, ssid, have_free_callback) { ss->free(task); + } while_each_subsys_mask(); put_css_set(cset); } -- cgit v1.2.3 From 996cd1fb7383cf087496e8a441bb10b9873b1eb6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Feb 2016 22:25:46 -0500 Subject: cgroup: use do_each_subsys_mask() where applicable There are several places in cgroup_subtree_control_write() which can use do_each_subsys_mask() instead of manual mask testing. Use it. No functional changes. Signed-off-by: Tejun Heo Acked-by: Johannes Weiner --- kernel/cgroup.c | 35 ++++++++++++----------------------- 1 file changed, 12 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 5d102980dc27..1e561bd990b9 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3082,10 +3082,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, * dependency. An invisible css is made visible when the userland * explicitly enables it. */ - for_each_subsys(ss, ssid) { - if (!(enable & (1 << ssid))) - continue; - + do_each_subsys_mask(ss, ssid, enable) { cgroup_for_each_live_child(child, cgrp) { if (css_enable & (1 << ssid)) ret = create_css(child, ss, @@ -3096,7 +3093,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, if (ret) goto err_undo_css; } - } + } while_each_subsys_mask(); /* * At this point, cgroup_e_css() results reflect the new csses @@ -3115,10 +3112,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, * state if it's made visible again later. Controllers which may * be depended upon should provide ->css_reset() for this purpose. */ - for_each_subsys(ss, ssid) { - if (!(disable & (1 << ssid))) - continue; - + do_each_subsys_mask(ss, ssid, disable) { cgroup_for_each_live_child(child, cgrp) { struct cgroup_subsys_state *css = cgroup_css(child, ss); @@ -3130,7 +3124,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, ss->css_reset(css); } } - } + } while_each_subsys_mask(); kernfs_activate(cgrp->kn); ret = 0; @@ -3142,10 +3136,7 @@ err_undo_css: cgrp->subtree_control = old_sc; cgrp->subtree_ss_mask = old_ss; - for_each_subsys(ss, ssid) { - if (!(enable & (1 << ssid))) - continue; - + do_each_subsys_mask(ss, ssid, enable) { cgroup_for_each_live_child(child, cgrp) { struct cgroup_subsys_state *css = cgroup_css(child, ss); @@ -3157,7 +3148,7 @@ err_undo_css: else css_clear_dir(css, NULL); } - } + } while_each_subsys_mask(); goto out_unlock; } @@ -4973,14 +4964,12 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, goto out_destroy; /* let's create and online css's */ - for_each_subsys(ss, ssid) { - if (parent->subtree_ss_mask & (1 << ssid)) { - ret = create_css(cgrp, ss, - parent->subtree_control & (1 << ssid)); - if (ret) - goto out_destroy; - } - } + do_each_subsys_mask(ss, ssid, parent->subtree_ss_mask) { + ret = create_css(cgrp, ss, + parent->subtree_control & (1 << ssid)); + if (ret) + goto out_destroy; + } while_each_subsys_mask(); /* * On the default hierarchy, a child doesn't automatically inherit -- cgit v1.2.3 From 6e5c830770f9045a17b1b931c3e11fbd5591e630 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Feb 2016 22:25:47 -0500 Subject: cgroup: make cgroup subsystem masks u16 After the recent do_each_subsys_mask() conversion, there's no reason to use ulong for subsystem masks. We'll be adding more subsystem masks to persistent data structures, let's reduce its size to u16 which should be enough for now and the foreseeable future. This doesn't create any noticeable behavior differences. v2: Johannes spotted that the initial patch missed cgroup_no_v1_mask. Converted. Signed-off-by: Tejun Heo Acked-by: Johannes Weiner --- include/linux/cgroup-defs.h | 4 ++-- kernel/cgroup.c | 50 ++++++++++++++++++++++----------------------- 2 files changed, 26 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index c68ae7f0fb5f..0abf6aa86c81 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -257,8 +257,8 @@ struct cgroup { * one which may have more subsystems enabled. Controller knobs * are made available iff it's enabled in ->subtree_control. */ - unsigned long subtree_control; - unsigned long subtree_ss_mask; + u16 subtree_control; + u16 subtree_ss_mask; /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 1e561bd990b9..7669f68077b8 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -181,10 +181,10 @@ EXPORT_SYMBOL_GPL(cgrp_dfl_root); static bool cgrp_dfl_root_visible; /* Controllers blocked by the commandline in v1 */ -static unsigned long cgroup_no_v1_mask; +static u16 cgroup_no_v1_mask; /* some controllers are not supported in the default hierarchy */ -static unsigned long cgrp_dfl_root_inhibit_ss_mask; +static u16 cgrp_dfl_root_inhibit_ss_mask; /* The list of hierarchy roots */ @@ -208,19 +208,18 @@ static u64 css_serial_nr_next = 1; * fork/exit handlers to call. This avoids us having to do extra work in the * fork/exit path to check which subsystems have fork/exit callbacks. */ -static unsigned long have_fork_callback __read_mostly; -static unsigned long have_exit_callback __read_mostly; -static unsigned long have_free_callback __read_mostly; +static u16 have_fork_callback __read_mostly; +static u16 have_exit_callback __read_mostly; +static u16 have_free_callback __read_mostly; /* Ditto for the can_fork callback. */ -static unsigned long have_canfork_callback __read_mostly; +static u16 have_canfork_callback __read_mostly; static struct file_system_type cgroup2_fs_type; static struct cftype cgroup_dfl_base_files[]; static struct cftype cgroup_legacy_base_files[]; -static int rebind_subsystems(struct cgroup_root *dst_root, - unsigned long ss_mask); +static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); static void css_task_iter_advance(struct css_task_iter *it); static int cgroup_destroy_locked(struct cgroup *cgrp); static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss, @@ -1274,11 +1273,10 @@ static umode_t cgroup_file_mode(const struct cftype *cft) * @subtree_control is to be applied to @cgrp. The returned mask is always * a superset of @subtree_control and follows the usual hierarchy rules. */ -static unsigned long cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, - unsigned long subtree_control) +static u16 cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, u16 subtree_control) { struct cgroup *parent = cgroup_parent(cgrp); - unsigned long cur_ss_mask = subtree_control; + u16 cur_ss_mask = subtree_control; struct cgroup_subsys *ss; int ssid; @@ -1288,7 +1286,7 @@ static unsigned long cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, return cur_ss_mask; while (true) { - unsigned long new_ss_mask = cur_ss_mask; + u16 new_ss_mask = cur_ss_mask; do_each_subsys_mask(ss, ssid, cur_ss_mask) { new_ss_mask |= ss->depends_on; @@ -1466,12 +1464,11 @@ err: return ret; } -static int rebind_subsystems(struct cgroup_root *dst_root, - unsigned long ss_mask) +static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; - unsigned long tmp_ss_mask; + u16 tmp_ss_mask; int ssid, i, ret; lockdep_assert_held(&cgroup_mutex); @@ -1507,7 +1504,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root, */ if (dst_root == &cgrp_dfl_root) { if (cgrp_dfl_root_visible) { - pr_warn("failed to create files (%d) while rebinding 0x%lx to default root\n", + pr_warn("failed to create files (%d) while rebinding 0x%x to default root\n", ret, ss_mask); pr_warn("you may retry by moving them to a different hierarchy and unbinding\n"); } @@ -1599,7 +1596,7 @@ static int cgroup_show_options(struct seq_file *seq, } struct cgroup_sb_opts { - unsigned long subsys_mask; + u16 subsys_mask; unsigned int flags; char *release_agent; bool cpuset_clone_children; @@ -1612,13 +1609,13 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) { char *token, *o = data; bool all_ss = false, one_ss = false; - unsigned long mask = -1UL; + u16 mask = U16_MAX; struct cgroup_subsys *ss; int nr_opts = 0; int i; #ifdef CONFIG_CPUSETS - mask = ~(1U << cpuset_cgrp_id); + mask = ~((u16)1 << cpuset_cgrp_id); #endif memset(opts, 0, sizeof(*opts)); @@ -1745,7 +1742,7 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data) int ret = 0; struct cgroup_root *root = cgroup_root_from_kf(kf_root); struct cgroup_sb_opts opts; - unsigned long added_mask, removed_mask; + u16 added_mask, removed_mask; if (root == &cgrp_dfl_root) { pr_err("remount is not allowed\n"); @@ -1893,7 +1890,7 @@ static void init_cgroup_root(struct cgroup_root *root, set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); } -static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask) +static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) { LIST_HEAD(tmp_links); struct cgroup *root_cgrp = &root->cgrp; @@ -2839,7 +2836,7 @@ static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) return 0; } -static void cgroup_print_ss_mask(struct seq_file *seq, unsigned long ss_mask) +static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) { struct cgroup_subsys *ss; bool printed = false; @@ -2950,8 +2947,8 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - unsigned long enable = 0, disable = 0; - unsigned long css_enable, css_disable, old_sc, new_sc, old_ss, new_ss; + u16 enable = 0, disable = 0; + u16 css_enable, css_disable, old_sc, new_sc, old_ss, new_ss; struct cgroup *cgrp, *child; struct cgroup_subsys *ss; char *tok; @@ -5255,7 +5252,7 @@ int __init cgroup_init_early(void) return 0; } -static unsigned long cgroup_disable_mask __initdata; +static u16 cgroup_disable_mask __initdata; /** * cgroup_init - cgroup initialization @@ -5269,6 +5266,7 @@ int __init cgroup_init(void) unsigned long key; int ssid; + BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16); BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files)); @@ -5754,7 +5752,7 @@ static int __init cgroup_no_v1(char *str) continue; if (!strcmp(token, "all")) { - cgroup_no_v1_mask = ~0UL; + cgroup_no_v1_mask = U16_MAX; break; } -- cgit v1.2.3 From a7165264429b7b0d95557f306f310e77407fc2ee Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 23 Feb 2016 10:00:50 -0500 Subject: cgroup: s/cgrp_dfl_root_/cgrp_dfl_/ These var names are unnecessarily unwiedly and another similar variable will be added. Let's shorten them. Signed-off-by: Tejun Heo --- kernel/cgroup.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7669f68077b8..afbed523b22f 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -178,13 +178,13 @@ EXPORT_SYMBOL_GPL(cgrp_dfl_root); * The default hierarchy always exists but is hidden until mounted for the * first time. This is for backward compatibility. */ -static bool cgrp_dfl_root_visible; +static bool cgrp_dfl_visible; /* Controllers blocked by the commandline in v1 */ static u16 cgroup_no_v1_mask; /* some controllers are not supported in the default hierarchy */ -static u16 cgrp_dfl_root_inhibit_ss_mask; +static u16 cgrp_dfl_inhibit_ss_mask; /* The list of hierarchy roots */ @@ -1486,7 +1486,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) /* skip creating root files on dfl_root for inhibited subsystems */ tmp_ss_mask = ss_mask; if (dst_root == &cgrp_dfl_root) - tmp_ss_mask &= ~cgrp_dfl_root_inhibit_ss_mask; + tmp_ss_mask &= ~cgrp_dfl_inhibit_ss_mask; do_each_subsys_mask(ss, ssid, tmp_ss_mask) { struct cgroup *scgrp = &ss->root->cgrp; @@ -1503,7 +1503,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) * Just warn about it and continue. */ if (dst_root == &cgrp_dfl_root) { - if (cgrp_dfl_root_visible) { + if (cgrp_dfl_visible) { pr_warn("failed to create files (%d) while rebinding 0x%x to default root\n", ret, ss_mask); pr_warn("you may retry by moving them to a different hierarchy and unbinding\n"); @@ -2006,7 +2006,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, pr_err("cgroup2: unknown option \"%s\"\n", (char *)data); return ERR_PTR(-EINVAL); } - cgrp_dfl_root_visible = true; + cgrp_dfl_visible = true; root = &cgrp_dfl_root; cgroup_get(&root->cgrp); goto out_mount; @@ -2858,7 +2858,7 @@ static int cgroup_root_controllers_show(struct seq_file *seq, void *v) struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgrp->root->subsys_mask & - ~cgrp_dfl_root_inhibit_ss_mask); + ~cgrp_dfl_inhibit_ss_mask); return 0; } @@ -2962,7 +2962,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, while ((tok = strsep(&buf, " "))) { if (tok[0] == '\0') continue; - do_each_subsys_mask(ss, ssid, ~cgrp_dfl_root_inhibit_ss_mask) { + do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) { if (!cgroup_ssid_enabled(ssid) || strcmp(tok + 1, ss->name)) continue; @@ -5315,7 +5315,7 @@ int __init cgroup_init(void) cgrp_dfl_root.subsys_mask |= 1 << ss->id; if (!ss->dfl_cftypes) - cgrp_dfl_root_inhibit_ss_mask |= 1 << ss->id; + cgrp_dfl_inhibit_ss_mask |= 1 << ss->id; if (ss->dfl_cftypes == ss->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); @@ -5386,7 +5386,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct cgroup *cgrp; int ssid, count = 0; - if (root == &cgrp_dfl_root && !cgrp_dfl_root_visible) + if (root == &cgrp_dfl_root && !cgrp_dfl_visible) continue; seq_printf(m, "%d:", root->hierarchy_id); -- cgit v1.2.3 From b38e42e962dbc2fbc3839ce70750881db7c9277e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 23 Feb 2016 10:00:50 -0500 Subject: cgroup: convert cgroup_subsys flag fields to bool bitfields Signed-off-by: Tejun Heo Cc: Li Zefan Cc: Ingo Molnar Cc: Peter Zijlstra --- include/linux/cgroup-defs.h | 6 +++--- kernel/cpuset.c | 2 +- kernel/sched/core.c | 2 +- kernel/sched/cpuacct.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 0abf6aa86c81..8fc3f0452289 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -444,7 +444,7 @@ struct cgroup_subsys { void (*free)(struct task_struct *task); void (*bind)(struct cgroup_subsys_state *root_css); - int early_init; + bool early_init:1; /* * If %false, this subsystem is properly hierarchical - @@ -458,8 +458,8 @@ struct cgroup_subsys { * cases. Eventually, all subsystems will be made properly * hierarchical and this will go away. */ - bool broken_hierarchy; - bool warned_broken_hierarchy; + bool broken_hierarchy:1; + bool warned_broken_hierarchy:1; /* the following two fields are initialized automtically during boot */ int id; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 41989ab4db57..90899837ea78 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2089,7 +2089,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = { .attach = cpuset_attach, .bind = cpuset_bind, .legacy_cftypes = files, - .early_init = 1, + .early_init = true, }; /** diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 44253adb3c36..0f5abc6e4ff3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8706,7 +8706,7 @@ struct cgroup_subsys cpu_cgrp_subsys = { .can_attach = cpu_cgroup_can_attach, .attach = cpu_cgroup_attach, .legacy_cftypes = cpu_files, - .early_init = 1, + .early_init = true, }; #endif /* CONFIG_CGROUP_SCHED */ diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index dd7cbb55bbf2..2ddaebf7469a 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -279,5 +279,5 @@ struct cgroup_subsys cpuacct_cgrp_subsys = { .css_alloc = cpuacct_css_alloc, .css_free = cpuacct_css_free, .legacy_cftypes = files, - .early_init = 1, + .early_init = true, }; -- cgit v1.2.3 From f17fc25f2b4f4bd8edafe36af6d7379eb9db27a0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 23 Feb 2016 10:00:51 -0500 Subject: cgroup: make css_tryget_online_from_dir() also recognize cgroup2 fs The function currently returns -EBADF for a directory on the default hierarchy. Make it also recognize cgroup2_fs_type. This will be used for perf_event cgroup2 support. Signed-off-by: Tejun Heo --- kernel/cgroup.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index afbed523b22f..2b114368666c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -5781,12 +5781,13 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); + struct file_system_type *s_type = dentry->d_sb->s_type; struct cgroup_subsys_state *css = NULL; struct cgroup *cgrp; /* is @dentry a cgroup dir? */ - if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || - kernfs_type(kn) != KERNFS_DIR) + if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) || + !kn || kernfs_type(kn) != KERNFS_DIR) return ERR_PTR(-EBADF); rcu_read_lock(); -- cgit v1.2.3 From 62716ea0f2ea4253984008fd4a96a532674ac58f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 23 Feb 2016 10:00:51 -0500 Subject: cgroup: use ->subtree_control when testing no internal process rule No internal process rule is enforced by cgroup_migrate_prepare_dst() during process migration. It tests whether the target cgroup's ->child_subsys_mask is zero which is different from "subtree_control" write path which tests ->subtree_control. This hasn't mattered because up until now, both ->child_subsys_mask and ->subtree_control are zero or non-zero at the same time. However, with the planned addition of implicit controllers, this will no longer be true. This patch prepares for the change by making cgorup_migrate_prepare_dst() test ->subtree_control instead. Signed-off-by: Tejun Heo --- kernel/cgroup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2b114368666c..ac5451e7c458 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2527,11 +2527,11 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp, lockdep_assert_held(&cgroup_mutex); /* - * Except for the root, subtree_ss_mask must be zero for a cgroup + * Except for the root, subtree_control must be zero for a cgroup * with tasks so that child cgroups don't compete against tasks. */ if (dst_cgrp && cgroup_on_dfl(dst_cgrp) && cgroup_parent(dst_cgrp) && - dst_cgrp->subtree_ss_mask) + dst_cgrp->subtree_control) return -EBUSY; /* look up the dst cset for each src cset and link it to src */ -- cgit v1.2.3 From 63253ad814db726d43c04011c752d83b7aaca998 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Fri, 26 Feb 2016 13:07:38 +0800 Subject: cgroup: fix a mistake in warning message There is a mistake about the print format name:id <--> %d:%s, which the name is 'char *' type and id is 'int' type. Change "name:id" to "id:name" instead to be consistent with "cgroup_subsys %d:%s". Signed-off-by: Xiubo Li Acked-by: Zefan Li Signed-off-by: Tejun Heo --- kernel/cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index ac5451e7c458..fcfad82149b1 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -5235,7 +5235,7 @@ int __init cgroup_init_early(void) for_each_subsys(ss, i) { WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, - "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n", + "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n", i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, ss->id, ss->name); WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, -- cgit v1.2.3 From 39853cc0cdcf1b11f00f7f81e2f515a4d68ed209 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Sun, 28 Feb 2016 22:22:37 -0600 Subject: bpf: Mark __bpf_prog_run() stack frame as non-standard objtool reports the following false positive warnings: kernel/bpf/core.o: warning: objtool: __bpf_prog_run()+0x5c: sibling call from callable instruction with changed frame pointer kernel/bpf/core.o: warning: objtool: __bpf_prog_run()+0x60: function has unreachable instruction kernel/bpf/core.o: warning: objtool: __bpf_prog_run()+0x64: function has unreachable instruction [...] It's confused by the following dynamic jump instruction in __bpf_prog_run():: jmp *(%r12,%rax,8) which corresponds to the following line in the C code: goto *jumptable[insn->code]; There's no way for objtool to deterministically find all possible branch targets for a dynamic jump, so it can't verify this code. In this case the jumps all stay within the function, and there's nothing unusual going on related to the stack, so we can whitelist the function. Signed-off-by: Josh Poimboeuf Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Bernd Petrovitsch Cc: Borislav Petkov Cc: Chris J Arges Cc: Jiri Slaby Cc: Linus Torvalds Cc: Michal Marek Cc: Namhyung Kim Cc: Pedro Alves Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: live-patching@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/b90e6bf3fdbfb5c4cc1b164b965502e53cf48935.1456719558.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- kernel/bpf/core.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 972d9a8e4ac4..be0abf669ced 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -27,6 +27,7 @@ #include #include #include +#include #include @@ -649,6 +650,7 @@ load_byte: WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); return 0; } +STACK_FRAME_NON_STANDARD(__bpf_prog_run); /* jump table */ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) -- cgit v1.2.3 From 8e05e96ac949c80704d0a38420bf60dcf18c938f Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Sun, 28 Feb 2016 22:22:38 -0600 Subject: sched: Mark __schedule() stack frame as non-standard objtool reports the following warnings for __schedule(): kernel/sched/core.o: warning: objtool:__schedule()+0x3c0: duplicate frame pointer save kernel/sched/core.o: warning: objtool:__schedule()+0x3fd: sibling call from callable instruction with changed frame pointer kernel/sched/core.o: warning: objtool:__schedule()+0x40a: call without frame pointer save/setup kernel/sched/core.o: warning: objtool:__schedule()+0x7fd: frame pointer state mismatch kernel/sched/core.o: warning: objtool:__schedule()+0x421: frame pointer state mismatch Basically it's confused by two unusual attributes of the switch_to() macro: 1. It saves prev's frame pointer to the old stack and restores next's frame pointer from the new stack. 2. For new tasks it jumps directly to ret_from_fork. Eventually it would probably be a good idea to clean up the ret_from_fork hack so that new tasks are created with a valid initial stack, as suggested by Andy: https://lkml.kernel.org/r/CALCETrWsqCw4L1qKO9j9L5F+4ED4viuLQTFc=n1pKBZfFPQUFg@mail.gmail.com Then __schedule() could return normally into the new code and objtool hopefully wouldn't have a problem anymore. In the meantime, mark its stack frame as non-standard so we can have a baseline with no objtool warnings. The marker also serves as a reminder that this code could be improved a bit. Signed-off-by: Josh Poimboeuf Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Bernd Petrovitsch Cc: Borislav Petkov Cc: Chris J Arges Cc: Jiri Slaby Cc: Linus Torvalds Cc: Michal Marek Cc: Namhyung Kim Cc: Pedro Alves Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: live-patching@vger.kernel.org Link: http://lkml.kernel.org/r/91190e324ebd7fcd01748d508d0dfd4693e84d91.1456719558.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9503d590e5ef..641043dfc773 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -74,6 +74,7 @@ #include #include #include +#include #include #include @@ -3288,6 +3289,7 @@ static void __sched notrace __schedule(bool preempt) balance_callback(rq); } +STACK_FRAME_NON_STANDARD(__schedule); /* switch_to() */ static inline void sched_submit_work(struct task_struct *tsk) { -- cgit v1.2.3 From 049369487e2068294b61cee19233be0ffac7d243 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Sun, 28 Feb 2016 22:22:39 -0600 Subject: sched: Always inline context_switch() When CONFIG_GCOV is enabled, gcc decides to put context_switch() out-of-line, which is inconsistent with its normal behavior. It also causes an objtool warning because __schedule() no longer inlines context_switch(), so the "STACK_FRAME_NON_STANDARD(__schedule)" statement loses its effect. Signed-off-by: Josh Poimboeuf Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Bernd Petrovitsch Cc: Borislav Petkov Cc: Chris J Arges Cc: Jiri Slaby Cc: Linus Torvalds Cc: Michal Marek Cc: Namhyung Kim Cc: Pedro Alves Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: live-patching@vger.kernel.org Link: http://lkml.kernel.org/r/d62aee926b6e303394e34a06999a964dc2773cf6.1456719558.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 641043dfc773..bb0daabe0ffe 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2763,7 +2763,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) /* * context_switch - switch to the new MM and the new thread's register state. */ -static inline struct rq * +static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { -- cgit v1.2.3 From ede5147d515694e012cd958ec874b9daf8a65fec Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 24 Feb 2016 14:37:53 +0000 Subject: Handle ISO 8601 leap seconds and encodings of midnight in mktime64() Handle the following ISO 8601 features in mktime64(): (1) Leap seconds. Leap seconds are indicated by the seconds parameter being the value 60. Handle this by treating it the same as 00 of the following minute. It has been pointed out that a minute may contain two leap seconds. However, pending discussion of what that looks like and how to handle it, I'm not going to concern myself with it. (2) Alternate encodings of midnight. Two different encodings of midnight are permitted - 00:00:00 and 24:00:00 - the first is midnight today and the second is midnight tomorrow and is exactly equivalent to the first with tomorrow's date. As it happens, we don't actually need to change mktime64() to handle either of these - just comment them as valid parameters. These facility will be used by the X.509 parser. Doing it in mktime64() makes the policy common to the whole kernel and easier to find. Signed-off-by: David Howells Acked-by: Arnd Bergmann cc: John Stultz cc: Rudolf Polzer cc: One Thousand Gnomes --- kernel/time/time.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/time.c b/kernel/time/time.c index 86751c68e08d..be115b020d27 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -322,6 +322,13 @@ EXPORT_SYMBOL(timespec_trunc); * -year/100+year/400 terms, and add 10.] * * This algorithm was first published by Gauss (I think). + * + * A leap second can be indicated by calling this function with sec as + * 60 (allowable under ISO 8601). The leap second is treated the same + * as the following second since they don't exist in UNIX time. + * + * An encoding of midnight at the end of the day as 24:00:00 - ie. midnight + * tomorrow - (allowable under ISO 8601) is supported. */ time64_t mktime64(const unsigned int year0, const unsigned int mon0, const unsigned int day, const unsigned int hour, @@ -338,7 +345,7 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0, return ((((time64_t) (year/4 - year/100 + year/400 + 367*mon/12 + day) + year*365 - 719499 - )*24 + hour /* now have hours */ + )*24 + hour /* now have hours - midnight tomorrow handled here */ )*60 + min /* now have minutes */ )*60 + sec; /* finally seconds */ } -- cgit v1.2.3 From fa5ff8a1c43fc7b78353059899edf3cbedf54e9f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 28 Feb 2016 08:59:33 -0500 Subject: cgroup: fix and restructure error handling in copy_cgroup_ns() copy_cgroup_ns()'s error handling was broken and the attempt to fix it d22025570e2e ("cgroup: fix alloc_cgroup_ns() error handling in copy_cgroup_ns()") was broken too in that it ended up trying an ERR_PTR() value. There's only one place where copy_cgroup_ns() needs to perform cleanup after failure. Simplify and fix the error handling by removing the goto's. Signed-off-by: Tejun Heo Reported-by: Dan Carpenter Acked-by: Serge E. Hallyn --- kernel/cgroup.c | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d92d91a4bb3e..2c88149da848 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -6058,9 +6058,8 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns) { - struct cgroup_namespace *new_ns = NULL; - struct css_set *cset = NULL; - int err; + struct cgroup_namespace *new_ns; + struct css_set *cset; BUG_ON(!old_ns); @@ -6070,9 +6069,8 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, } /* Allow only sysadmin to create cgroup namespace. */ - err = -EPERM; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) - goto err_out; + return ERR_PTR(-EPERM); mutex_lock(&cgroup_mutex); spin_lock_bh(&css_set_lock); @@ -6085,20 +6083,14 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, new_ns = alloc_cgroup_ns(); if (IS_ERR(new_ns)) { - err = PTR_ERR(new_ns); - goto err_out; + put_css_set(cset); + return new_ns; } new_ns->user_ns = get_user_ns(user_ns); new_ns->root_cset = cset; return new_ns; - -err_out: - if (cset) - put_css_set(cset); - kfree(new_ns); - return ERR_PTR(err); } static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) -- cgit v1.2.3 From 89053aa9c711bd455a68844b4ed37c8b72ef1daa Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 1 Mar 2016 10:36:07 +0000 Subject: MODSIGN: linux/string.h should be #included to get memcpy() linux/string.h should be #included in module_signing.c to get memcpy(), lest the following occur: kernel/module_signing.c: In function 'mod_verify_sig': kernel/module_signing.c:57:2: error: implicit declaration of function 'memcpy' [-Werror=implicit-function-declaration] memcpy(&ms, mod + (modlen - sizeof(ms)), sizeof(ms)); ^ Reported-by: kbuild test robot Signed-off-by: David Howells --- kernel/module_signing.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/module_signing.c b/kernel/module_signing.c index 6528a79d998d..9cfa46d8d14f 100644 --- a/kernel/module_signing.c +++ b/kernel/module_signing.c @@ -11,6 +11,7 @@ #include #include +#include #include #include #include "module-internal.h" -- cgit v1.2.3 From fa06235b8eb0ae87a962e023243dba1eb4e7160d Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 1 Mar 2016 19:56:30 +0300 Subject: cgroup: reset css on destruction An associated css can be around for quite a while after a cgroup directory has been removed. In general, it makes sense to reset it to defaults so as not to worry about any remnants. For instance, memory cgroup needs to reset memory.low, otherwise pages charged to a dead cgroup might never get reclaimed. There's ->css_reset callback, which would fit perfectly for the purpose. Currently, it's only called when a subsystem is disabled in the unified hierarchy and there are other subsystems dependant on it. Let's call it on css destruction as well. Suggested-by: Johannes Weiner Signed-off-by: Vladimir Davydov Signed-off-by: Tejun Heo --- kernel/cgroup.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index fcfad82149b1..46529502e9d5 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4787,6 +4787,9 @@ static void offline_css(struct cgroup_subsys_state *css) if (!(css->flags & CSS_ONLINE)) return; + if (ss->css_reset) + ss->css_reset(css); + if (ss->css_offline) ss->css_offline(css); -- cgit v1.2.3 From 9b7f6597f013d449d6700d11820faf91ee0ec985 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 2 Mar 2016 12:53:31 +0100 Subject: sched/core: Get rid of 'cpu' argument in wq_worker_sleeping() Given that wq_worker_sleeping() could only be called for a CPU it is running on, we do not need passing a CPU ID as an argument. Suggested-by: Oleg Nesterov Cc: Oleg Nesterov Cc: Peter Zijlstra Signed-off-by: Alexander Gordeev Signed-off-by: Tejun Heo --- kernel/sched/core.c | 2 +- kernel/workqueue.c | 5 ++--- kernel/workqueue_internal.h | 2 +- 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 63d3a24e081a..81ff7f2ad37a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3257,7 +3257,7 @@ static void __sched notrace __schedule(bool preempt) if (prev->flags & PF_WQ_WORKER) { struct task_struct *to_wakeup; - to_wakeup = wq_worker_sleeping(prev, cpu); + to_wakeup = wq_worker_sleeping(prev); if (to_wakeup) try_to_wake_up_local(to_wakeup); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3a1c99b0c1b3..16f4986205e9 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -858,7 +858,6 @@ void wq_worker_waking_up(struct task_struct *task, int cpu) /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep - * @cpu: CPU in question, must be the current CPU number * * This function is called during schedule() when a busy worker is * going to sleep. Worker on the same cpu can be woken up by @@ -870,7 +869,7 @@ void wq_worker_waking_up(struct task_struct *task, int cpu) * Return: * Worker task on @cpu to wake up, %NULL if none. */ -struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) +struct task_struct *wq_worker_sleeping(struct task_struct *task) { struct worker *worker = kthread_data(task), *to_wakeup = NULL; struct worker_pool *pool; @@ -886,7 +885,7 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) pool = worker->pool; /* this can only happen on the local cpu */ - if (WARN_ON_ONCE(cpu != raw_smp_processor_id() || pool->cpu != cpu)) + if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id())) return NULL; /* diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 45215870ac6c..8635417c587b 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -69,6 +69,6 @@ static inline struct worker *current_wq_worker(void) * sched/core.c and workqueue.c. */ void wq_worker_waking_up(struct task_struct *task, int cpu); -struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu); +struct task_struct *wq_worker_sleeping(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ -- cgit v1.2.3 From 2378d8b8ba3d2adffb4f98c0c60ee2f448b3be69 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:57 -0500 Subject: cgroup: re-hash init_css_set after subsystems are initialized css_sets are hashed by their subsys[] contents and in cgroup_init() init_css_set is hashed early, before subsystem inits, when all entries in its subsys[] are NULL, so that cgroup_dfl_root initialization can find and link to it. As subsystems are initialized, init_css_set.subsys[] is filled up but the hashing is never updated making init_css_set hashed in the wrong place. While incorrect, this doesn't cause a critical failure as css_set management code would create an identical css_set dynamically. Fix it by rehashing init_css_set after subsystems are initialized. While at it, drop unnecessary @key local variable. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 46529502e9d5..e97772b42dfb 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -5266,7 +5266,6 @@ static u16 cgroup_disable_mask __initdata; int __init cgroup_init(void) { struct cgroup_subsys *ss; - unsigned long key; int ssid; BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16); @@ -5276,9 +5275,12 @@ int __init cgroup_init(void) mutex_lock(&cgroup_mutex); - /* Add init_css_set to the hash table */ - key = css_set_hash(init_css_set.subsys); - hash_add(css_set_table, &init_css_set.hlist, key); + /* + * Add init_css_set to the hash table so that dfl_root can link to + * it during init. + */ + hash_add(css_set_table, &init_css_set.hlist, + css_set_hash(init_css_set.subsys)); BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); @@ -5331,6 +5333,11 @@ int __init cgroup_init(void) ss->bind(init_css_set.subsys[ssid]); } + /* init_css_set.subsys[] has been updated, re-hash */ + hash_del(&init_css_set.hlist); + hash_add(css_set_table, &init_css_set.hlist, + css_set_hash(init_css_set.subsys)); + WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup")); WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); -- cgit v1.2.3 From 20b454a61fba59be13de52b4493898583ea26d20 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:57 -0500 Subject: cgroup: suppress spurious de-populated events During task migration, tasks may transfer between two css_sets which are associated with the same cgroup. If those tasks are the only tasks in the cgroup, this currently triggers a spurious de-populated event on the cgroup. Fix it by bumping up populated count before bumping it down during migration to ensure that it doesn't reach zero spuriously. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e97772b42dfb..5d452e7fcb4f 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -678,6 +678,9 @@ static void css_set_move_task(struct task_struct *task, { lockdep_assert_held(&css_set_lock); + if (to_cset && !css_set_populated(to_cset)) + css_set_update_populated(to_cset, true); + if (from_cset) { struct css_task_iter *it, *pos; @@ -711,8 +714,6 @@ static void css_set_move_task(struct task_struct *task, */ WARN_ON_ONCE(task->flags & PF_EXITING); - if (!css_set_populated(to_cset)) - css_set_update_populated(to_cset, true); rcu_assign_pointer(task->cgroups, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); -- cgit v1.2.3 From 6cd0f5bbaf594f40a97d01dbc565dda41f30d37c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:58 -0500 Subject: cgroup: separate out interface file creation from css creation Currently, interface files are created when a css is created depending on whether @visible is set. This patch separates out the two into separate steps to help code refactoring and eventually allow cgroups which aren't visible through cgroup fs. Move css_populate_dir() out of create_css() and drop @visible. While at it, rename the function to css_create() for consistency. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 72 ++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 43 insertions(+), 29 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 5d452e7fcb4f..4178e45becb4 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -222,8 +222,8 @@ static struct cftype cgroup_legacy_base_files[]; static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); static void css_task_iter_advance(struct css_task_iter *it); static int cgroup_destroy_locked(struct cgroup *cgrp); -static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss, - bool visible); +static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, + struct cgroup_subsys *ss); static void css_release(struct percpu_ref *ref); static void kill_css(struct cgroup_subsys_state *css); static int cgroup_addrm_files(struct cgroup_subsys_state *css, @@ -3082,14 +3082,26 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, */ do_each_subsys_mask(ss, ssid, enable) { cgroup_for_each_live_child(child, cgrp) { - if (css_enable & (1 << ssid)) - ret = create_css(child, ss, - cgrp->subtree_control & (1 << ssid)); - else + if (css_enable & (1 << ssid)) { + struct cgroup_subsys_state *css; + + css = css_create(child, ss); + if (IS_ERR(css)) { + ret = PTR_ERR(css); + goto err_undo_css; + } + + if (cgrp->subtree_control & (1 << ssid)) { + ret = css_populate_dir(css, NULL); + if (ret) + goto err_undo_css; + } + } else { ret = css_populate_dir(cgroup_css(child, ss), NULL); - if (ret) - goto err_undo_css; + if (ret) + goto err_undo_css; + } } } while_each_subsys_mask(); @@ -4717,7 +4729,9 @@ static void css_release_work_fn(struct work_struct *work) * Those are supported by RCU protecting clearing of * cgrp->kn->priv backpointer. */ - RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); + if (cgrp->kn) + RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, + NULL); } mutex_unlock(&cgroup_mutex); @@ -4801,17 +4815,16 @@ static void offline_css(struct cgroup_subsys_state *css) } /** - * create_css - create a cgroup_subsys_state + * css_create - create a cgroup_subsys_state * @cgrp: the cgroup new css will be associated with * @ss: the subsys of new css - * @visible: whether to create control knobs for the new css or not * * Create a new css associated with @cgrp - @ss pair. On success, the new - * css is online and installed in @cgrp with all interface files created if - * @visible. Returns 0 on success, -errno on failure. + * css is online and installed in @cgrp. This function doesn't create the + * interface files. Returns 0 on success, -errno on failure. */ -static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss, - bool visible) +static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, + struct cgroup_subsys *ss) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss); @@ -4822,7 +4835,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss, css = ss->css_alloc(parent_css); if (IS_ERR(css)) - return PTR_ERR(css); + return css; init_and_link_css(css, ss, cgrp); @@ -4835,12 +4848,6 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss, goto err_free_percpu_ref; css->id = err; - if (visible) { - err = css_populate_dir(css, NULL); - if (err) - goto err_free_id; - } - /* @css is ready to be brought online now, make it visible */ list_add_tail_rcu(&css->sibling, &parent_css->children); cgroup_idr_replace(&ss->css_idr, css, css->id); @@ -4858,18 +4865,16 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss, ss->warned_broken_hierarchy = true; } - return 0; + return css; err_list_del: list_del_rcu(&css->sibling); - css_clear_dir(css, NULL); -err_free_id: cgroup_idr_remove(&ss->css_idr, css->id); err_free_percpu_ref: percpu_ref_exit(&css->refcnt); err_free_css: call_rcu(&css->rcu_head, css_free_rcu_fn); - return err; + return ERR_PTR(err); } static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, @@ -4966,10 +4971,19 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, /* let's create and online css's */ do_each_subsys_mask(ss, ssid, parent->subtree_ss_mask) { - ret = create_css(cgrp, ss, - parent->subtree_control & (1 << ssid)); - if (ret) + struct cgroup_subsys_state *css; + + css = css_create(cgrp, ss); + if (IS_ERR(css)) { + ret = PTR_ERR(css); goto out_destroy; + } + + if (parent->subtree_control & (1 << ssid)) { + ret = css_populate_dir(css, NULL); + if (ret) + goto out_destroy; + } } while_each_subsys_mask(); /* -- cgit v1.2.3 From 88cb04b96a1934ecbfd1d324e7cde55890c1a576 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:58 -0500 Subject: cgroup: explicitly track whether a cgroup_subsys_state is visible to userland Currently, whether a css (cgroup_subsys_state) has its interface files created is not tracked and assumed to change together with the owning cgroup's lifecycle. cgroup directory and interface creation is being separated out from internal object creation to help refactoring and eventually allow cgroups which are not visible through cgroupfs. This patch adds CSS_VISIBLE to track whether a css has its interface files created and perform management operations only when necessary which helps decoupling interface file handling from internal object lifecycle. After this patch, all css interface file management functions can be called regardless of the current state and will achieve the expected result. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- include/linux/cgroup-defs.h | 1 + kernel/cgroup.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8fc3f0452289..7593c1a46786 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -45,6 +45,7 @@ enum { CSS_NO_REF = (1 << 0), /* no reference counting for this css */ CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ + CSS_VISIBLE = (1 << 3), /* css is visible to userland */ }; /* bits in struct cgroup flags field */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 4178e45becb4..a9a53ca942f3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1421,6 +1421,11 @@ static void css_clear_dir(struct cgroup_subsys_state *css, struct cgroup *cgrp = cgrp_override ?: css->cgroup; struct cftype *cfts; + if (!(css->flags & CSS_VISIBLE)) + return; + + css->flags &= ~CSS_VISIBLE; + list_for_each_entry(cfts, &css->ss->cfts, node) cgroup_addrm_files(css, cgrp, cfts, false); } @@ -1439,6 +1444,9 @@ static int css_populate_dir(struct cgroup_subsys_state *css, struct cftype *cfts, *failed_cfts; int ret; + if (css->flags & CSS_VISIBLE) + return 0; + if (!css->ss) { if (cgroup_on_dfl(cgrp)) cfts = cgroup_dfl_base_files; @@ -1455,6 +1463,9 @@ static int css_populate_dir(struct cgroup_subsys_state *css, goto err; } } + + css->flags |= CSS_VISIBLE; + return 0; err: list_for_each_entry(cfts, &css->ss->cfts, node) { @@ -3403,7 +3414,7 @@ static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) css_for_each_descendant_pre(css, cgroup_css(root, ss)) { struct cgroup *cgrp = css->cgroup; - if (cgroup_is_dead(cgrp)) + if (!(css->flags & CSS_VISIBLE)) continue; ret = cgroup_addrm_files(css, cgrp, cfts, is_add); -- cgit v1.2.3 From 195e9b6c4b09434dad6ec3c163fdf037e16b3c96 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:58 -0500 Subject: cgroup: reorder operations in cgroup_mkdir() Currently, operations to initialize internal objects and create interface directory and files are intermixed in cgroup_mkdir(). We're in the process of refactoring cgroup and css management paths to separate them out to eventually allow cgroups which aren't visible through cgroup fs. This patch reorders operations inside cgroup_mkdir() so that interface directory and file handling comes after internal object initialization. This will enable further refactoring. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 61 ++++++++++++++++++++++++++++----------------------------- 1 file changed, 30 insertions(+), 31 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a9a53ca942f3..a6d484a667aa 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4945,20 +4945,6 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); - /* create the directory */ - kn = kernfs_create_dir(parent->kn, name, mode, cgrp); - if (IS_ERR(kn)) { - ret = PTR_ERR(kn); - goto out_free_id; - } - cgrp->kn = kn; - - /* - * This extra ref will be put in cgroup_free_fn() and guarantees - * that @cgrp->kn is always accessible. - */ - kernfs_get(kn); - cgrp->self.serial_nr = css_serial_nr_next++; /* allocation complete, commit to creation */ @@ -4972,15 +4958,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, */ cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id); - ret = cgroup_kn_set_ugid(kn); - if (ret) - goto out_destroy; - - ret = css_populate_dir(&cgrp->self, NULL); - if (ret) - goto out_destroy; - - /* let's create and online css's */ + /* create the csses */ do_each_subsys_mask(ss, ssid, parent->subtree_ss_mask) { struct cgroup_subsys_state *css; @@ -4989,12 +4967,6 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, ret = PTR_ERR(css); goto out_destroy; } - - if (parent->subtree_control & (1 << ssid)) { - ret = css_populate_dir(css, NULL); - if (ret) - goto out_destroy; - } } while_each_subsys_mask(); /* @@ -5006,13 +4978,40 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, cgroup_refresh_subtree_ss_mask(cgrp); } + /* create the directory */ + kn = kernfs_create_dir(parent->kn, name, mode, cgrp); + if (IS_ERR(kn)) { + ret = PTR_ERR(kn); + goto out_destroy; + } + cgrp->kn = kn; + + /* + * This extra ref will be put in cgroup_free_fn() and guarantees + * that @cgrp->kn is always accessible. + */ + kernfs_get(kn); + + ret = cgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + ret = css_populate_dir(&cgrp->self, NULL); + if (ret) + goto out_destroy; + + do_each_subsys_mask(ss, ssid, parent->subtree_control) { + ret = css_populate_dir(cgroup_css(cgrp, ss), NULL); + if (ret) + goto out_destroy; + } while_each_subsys_mask(); + + /* let's create and online css's */ kernfs_activate(kn); ret = 0; goto out_unlock; -out_free_id: - cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: -- cgit v1.2.3 From a5bca2152036de826595723437c5cbe8f6c13983 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:58 -0500 Subject: cgroup: factor out cgroup_create() out of cgroup_mkdir() We're in the process of refactoring cgroup and css management paths to separate them out to eventually allow cgroups which aren't visible through cgroup fs. This patch factors out cgroup_create() out of cgroup_mkdir(). cgroup_create() contains all internal object creation and initialization. cgroup_mkdir() uses cgroup_create() to create the internal cgroup and adds interface directory and file creation. This patch doesn't cause any behavior differences. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 72 ++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 43 insertions(+), 29 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a6d484a667aa..e1b3d0fead05 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4888,33 +4888,19 @@ err_free_css: return ERR_PTR(err); } -static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, - umode_t mode) +static struct cgroup *cgroup_create(struct cgroup *parent) { - struct cgroup *parent, *cgrp, *tcgrp; - struct cgroup_root *root; + struct cgroup_root *root = parent->root; struct cgroup_subsys *ss; - struct kernfs_node *kn; - int level, ssid, ret; - - /* Do not accept '\n' to prevent making /proc//cgroup unparsable. - */ - if (strchr(name, '\n')) - return -EINVAL; - - parent = cgroup_kn_lock_live(parent_kn); - if (!parent) - return -ENODEV; - root = parent->root; - level = parent->level + 1; + struct cgroup *cgrp, *tcgrp; + int level = parent->level + 1; + int ssid, ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ cgrp = kzalloc(sizeof(*cgrp) + sizeof(cgrp->ancestor_ids[0]) * (level + 1), GFP_KERNEL); - if (!cgrp) { - ret = -ENOMEM; - goto out_unlock; - } + if (!cgrp) + return ERR_PTR(-ENOMEM); ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) @@ -4978,6 +4964,40 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, cgroup_refresh_subtree_ss_mask(cgrp); } + return cgrp; + +out_cancel_ref: + percpu_ref_exit(&cgrp->self.refcnt); +out_free_cgrp: + kfree(cgrp); + return ERR_PTR(ret); +out_destroy: + cgroup_destroy_locked(cgrp); + return ERR_PTR(ret); +} + +static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, + umode_t mode) +{ + struct cgroup *parent, *cgrp; + struct cgroup_subsys *ss; + struct kernfs_node *kn; + int ssid, ret; + + /* do not accept '\n' to prevent making /proc//cgroup unparsable */ + if (strchr(name, '\n')) + return -EINVAL; + + parent = cgroup_kn_lock_live(parent_kn); + if (!parent) + return -ENODEV; + + cgrp = cgroup_create(parent); + if (IS_ERR(cgrp)) { + ret = PTR_ERR(cgrp); + goto out_unlock; + } + /* create the directory */ kn = kernfs_create_dir(parent->kn, name, mode, cgrp); if (IS_ERR(kn)) { @@ -5012,17 +5032,11 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, ret = 0; goto out_unlock; -out_cancel_ref: - percpu_ref_exit(&cgrp->self.refcnt); -out_free_cgrp: - kfree(cgrp); +out_destroy: + cgroup_destroy_locked(cgrp); out_unlock: cgroup_kn_unlock(parent_kn); return ret; - -out_destroy: - cgroup_destroy_locked(cgrp); - goto out_unlock; } /* -- cgit v1.2.3 From 5531dc915ba10b78a80dcffa48d7360d3c0bab61 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:58 -0500 Subject: cgroup: introduce cgroup_control() and cgroup_ss_mask() When a controller is enabled and visible on a non-root cgroup is determined by subtree_control and subtree_ss_mask of the parent cgroup. For a root cgroup, by the type of the hierarchy and which controllers are attached to it. Deciding the above on each usage is fragile and unnecessarily complicates the users. This patch introduces cgroup_control() and cgroup_ss_mask() which calculate and return the [visibly] enabled subsyste mask for the specified cgroup and conver the existing usages. * cgroup_e_css() is restructured for simplicity. * cgroup_calc_subtree_ss_mask() and cgroup_subtree_control_write() no longer need to distinguish root and non-root cases. * With cgroup_control(), cgroup_controllers_show() can now handle both root and non-root cases. cgroup_root_controllers_show() is removed. v2: cgroup_control() updated to yield the correct result on v1 hierarchies too. cgroup_subtree_control_write() converted. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 72 +++++++++++++++++++++++++++++---------------------------- 1 file changed, 37 insertions(+), 35 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e1b3d0fead05..2cb4b5419852 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -346,6 +346,32 @@ static struct cgroup *cgroup_parent(struct cgroup *cgrp) return NULL; } +/* subsystems visibly enabled on a cgroup */ +static u16 cgroup_control(struct cgroup *cgrp) +{ + struct cgroup *parent = cgroup_parent(cgrp); + u16 root_ss_mask = cgrp->root->subsys_mask; + + if (parent) + return parent->subtree_control; + + if (cgroup_on_dfl(cgrp)) + root_ss_mask &= ~cgrp_dfl_inhibit_ss_mask; + + return root_ss_mask; +} + +/* subsystems enabled on a cgroup */ +static u16 cgroup_ss_mask(struct cgroup *cgrp) +{ + struct cgroup *parent = cgroup_parent(cgrp); + + if (parent) + return parent->subtree_ss_mask; + + return cgrp->root->subsys_mask; +} + /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest @@ -385,16 +411,15 @@ static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, if (!ss) return &cgrp->self; - if (!(cgrp->root->subsys_mask & (1 << ss->id))) - return NULL; - /* * This function is used while updating css associations and thus - * can't test the csses directly. Use ->subtree_ss_mask. + * can't test the csses directly. Test ss_mask. */ - while (cgroup_parent(cgrp) && - !(cgroup_parent(cgrp)->subtree_ss_mask & (1 << ss->id))) + while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) { cgrp = cgroup_parent(cgrp); + if (!cgrp) + return NULL; + } return cgroup_css(cgrp, ss); } @@ -1276,7 +1301,6 @@ static umode_t cgroup_file_mode(const struct cftype *cft) */ static u16 cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, u16 subtree_control) { - struct cgroup *parent = cgroup_parent(cgrp); u16 cur_ss_mask = subtree_control; struct cgroup_subsys *ss; int ssid; @@ -1298,10 +1322,7 @@ static u16 cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, u16 subtree_control) * happen only if some depended-upon subsystems were bound * to non-default hierarchies. */ - if (parent) - new_ss_mask &= parent->subtree_ss_mask; - else - new_ss_mask &= cgrp->root->subsys_mask; + new_ss_mask &= cgroup_ss_mask(cgrp); if (new_ss_mask == cur_ss_mask) break; @@ -2864,22 +2885,12 @@ static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) seq_putc(seq, '\n'); } -/* show controllers which are currently attached to the default hierarchy */ -static int cgroup_root_controllers_show(struct seq_file *seq, void *v) -{ - struct cgroup *cgrp = seq_css(seq)->cgroup; - - cgroup_print_ss_mask(seq, cgrp->root->subsys_mask & - ~cgrp_dfl_inhibit_ss_mask); - return 0; -} - /* show controllers which are enabled from the parent */ static int cgroup_controllers_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - cgroup_print_ss_mask(seq, cgroup_parent(cgrp)->subtree_control); + cgroup_print_ss_mask(seq, cgroup_control(cgrp)); return 0; } @@ -3005,10 +3016,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, continue; } - /* unavailable or not enabled on the parent? */ - if (!(cgrp_dfl_root.subsys_mask & (1 << ssid)) || - (cgroup_parent(cgrp) && - !(cgroup_parent(cgrp)->subtree_control & (1 << ssid)))) { + if (!(cgroup_control(cgrp) & (1 << ssid))) { ret = -ENOENT; goto out_unlock; } @@ -4566,12 +4574,6 @@ static struct cftype cgroup_dfl_base_files[] = { }, { .name = "cgroup.controllers", - .flags = CFTYPE_ONLY_ON_ROOT, - .seq_show = cgroup_root_controllers_show, - }, - { - .name = "cgroup.controllers", - .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_controllers_show, }, { @@ -4945,7 +4947,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id); /* create the csses */ - do_each_subsys_mask(ss, ssid, parent->subtree_ss_mask) { + do_each_subsys_mask(ss, ssid, cgroup_ss_mask(cgrp)) { struct cgroup_subsys_state *css; css = css_create(cgrp, ss); @@ -4960,7 +4962,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent) * subtree_control from the parent. Each is configured manually. */ if (!cgroup_on_dfl(cgrp)) { - cgrp->subtree_control = parent->subtree_control; + cgrp->subtree_control = cgroup_control(cgrp); cgroup_refresh_subtree_ss_mask(cgrp); } @@ -5020,7 +5022,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, if (ret) goto out_destroy; - do_each_subsys_mask(ss, ssid, parent->subtree_control) { + do_each_subsys_mask(ss, ssid, cgroup_control(cgrp)) { ret = css_populate_dir(cgroup_css(cgrp, ss), NULL); if (ret) goto out_destroy; -- cgit v1.2.3 From 1b9b96a12b5433ccc477265111122720ccb4965e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:59 -0500 Subject: cgroup: factor out cgroup_drain_offline() from cgroup_subtree_control_write() Factor out async css offline draining into cgroup_drain_offline(). * Nest subsystem walk inside child walk. The child walk will later be converted to subtree walk which is a bit more expensive. * Relocate the draining above subsystem mask preparation, which doesn't create any behavior differences but helps further refactoring. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 77 ++++++++++++++++++++++++++++++++++++++------------------- 1 file changed, 52 insertions(+), 25 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2cb4b5419852..d295e6a91cdc 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2965,6 +2965,53 @@ out_finish: return ret; } +/** + * cgroup_drain_offline - wait for previously offlined csses to go away + * @cgrp: parent of the target cgroups + * + * Because css offlining is asynchronous, userland may try to re-enable a + * controller while the previous css is still around. This function drains + * the previous css instances of @cgrp's children. + * + * Must be called with cgroup_mutex held. Returns %false if there were no + * dying css instances. Returns %true if there were one or more and this + * function waited. On %true return, cgroup_mutex has been dropped and + * re-acquired inbetween which anything could have happened. The caller + * typically would have to start over. + */ +static bool cgroup_drain_offline(struct cgroup *cgrp) +{ + struct cgroup *dsct; + struct cgroup_subsys *ss; + int ssid; + + lockdep_assert_held(&cgroup_mutex); + + cgroup_for_each_live_child(dsct, cgrp) { + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cgroup_css(dsct, ss); + DEFINE_WAIT(wait); + + if (!css) + continue; + + cgroup_get(dsct); + prepare_to_wait(&dsct->offline_waitq, &wait, + TASK_UNINTERRUPTIBLE); + + mutex_unlock(&cgroup_mutex); + schedule(); + finish_wait(&dsct->offline_waitq, &wait); + mutex_lock(&cgroup_mutex); + + cgroup_put(dsct); + return true; + } + } + + return false; +} + /* change the enabled child controllers for a cgroup in the default hierarchy */ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, @@ -3050,6 +3097,11 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, goto out_unlock; } + if (cgroup_drain_offline(cgrp)) { + cgroup_kn_unlock(of->kn); + return restart_syscall(); + } + /* * Update subsys masks and calculate what needs to be done. More * subsystems than specified may need to be enabled or disabled @@ -3065,31 +3117,6 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, enable |= css_enable; disable |= css_disable; - /* - * Because css offlining is asynchronous, userland might try to - * re-enable the same controller while the previous instance is - * still around. In such cases, wait till it's gone using - * offline_waitq. - */ - do_each_subsys_mask(ss, ssid, css_enable) { - cgroup_for_each_live_child(child, cgrp) { - DEFINE_WAIT(wait); - - if (!cgroup_css(child, ss)) - continue; - - cgroup_get(child); - prepare_to_wait(&child->offline_waitq, &wait, - TASK_UNINTERRUPTIBLE); - cgroup_kn_unlock(of->kn); - schedule(); - finish_wait(&child->offline_waitq, &wait); - cgroup_put(child); - - return restart_syscall(); - } - } while_each_subsys_mask(); - cgrp->subtree_control = new_sc; cgrp->subtree_ss_mask = new_ss; -- cgit v1.2.3 From 12b3bb6af862477f96e1adac51b201a143a8f3c4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:59 -0500 Subject: cgroup: factor out cgroup_apply_control_disable() from cgroup_subtree_control_write() Factor out css disabling and hiding into cgroup_apply_control_disable(). * Nest subsystem walk inside child walk. The child walk will later be converted to subtree walk which is a bit more expensive. * Instead of operating on the differential masks @css_enable and @css_disable, simply disable or hide csses according to the current cgroup_control() and cgroup_ss_mask(). This leads to the same result and is simpler and more robust. * This allows error handling path to share the same code. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 74 ++++++++++++++++++++++++++++++++------------------------- 1 file changed, 41 insertions(+), 33 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d295e6a91cdc..97cb1315bcac 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3012,6 +3012,43 @@ static bool cgroup_drain_offline(struct cgroup *cgrp) return false; } +/** + * cgroup_apply_control_disable - kill or hide csses according to control + * @cgrp: parent of the target cgroups + * + * Walk @cgrp's children and kill and hide csses so that they match + * cgroup_ss_mask() and cgroup_visible_mask(). + * + * A css is hidden when the userland requests it to be disabled while other + * subsystems are still depending on it. The css must not actively control + * resources and be in the vanilla state if it's made visible again later. + * Controllers which may be depended upon should provide ->css_reset() for + * this purpose. + */ +static void cgroup_apply_control_disable(struct cgroup *cgrp) +{ + struct cgroup *dsct; + struct cgroup_subsys *ss; + int ssid; + + cgroup_for_each_live_child(dsct, cgrp) { + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cgroup_css(dsct, ss); + + if (!css) + continue; + + if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) { + kill_css(css); + } else if (!(cgroup_control(dsct) & (1 << ss->id))) { + css_clear_dir(css, NULL); + if (ss->css_reset) + ss->css_reset(css); + } + } + } +} + /* change the enabled child controllers for a cgroup in the default hierarchy */ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, @@ -3160,27 +3197,8 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, if (ret) goto err_undo_css; - /* - * All tasks are migrated out of disabled csses. Kill or hide - * them. A css is hidden when the userland requests it to be - * disabled while other subsystems are still depending on it. The - * css must not actively control resources and be in the vanilla - * state if it's made visible again later. Controllers which may - * be depended upon should provide ->css_reset() for this purpose. - */ - do_each_subsys_mask(ss, ssid, disable) { - cgroup_for_each_live_child(child, cgrp) { - struct cgroup_subsys_state *css = cgroup_css(child, ss); - - if (css_disable & (1 << ssid)) { - kill_css(css); - } else { - css_clear_dir(css, NULL); - if (ss->css_reset) - ss->css_reset(css); - } - } - } while_each_subsys_mask(); + /* all tasks are migrated out of disabled csses, commit disable */ + cgroup_apply_control_disable(cgrp); kernfs_activate(cgrp->kn); ret = 0; @@ -3189,22 +3207,12 @@ out_unlock: return ret ?: nbytes; err_undo_css: + /* restore masks and shoot down new csses */ cgrp->subtree_control = old_sc; cgrp->subtree_ss_mask = old_ss; - do_each_subsys_mask(ss, ssid, enable) { - cgroup_for_each_live_child(child, cgrp) { - struct cgroup_subsys_state *css = cgroup_css(child, ss); - - if (!css) - continue; + cgroup_apply_control_disable(cgrp); - if (css_enable & (1 << ssid)) - kill_css(css); - else - css_clear_dir(css, NULL); - } - } while_each_subsys_mask(); goto out_unlock; } -- cgit v1.2.3 From bdb53bd797dcef46d1a252b9529f8fd511bf714c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:59 -0500 Subject: cgroup: factor out cgroup_apply_control_enable() from cgroup_subtree_control_write() Factor out css enabling and showing into cgroup_apply_control_enable(). * Nest subsystem walk inside child walk. The child walk will later be converted to subtree walk which is a bit more expensive. * Instead of operating on the differential masks @css_enable, simply enable or show csses according to the current cgroup_control() and cgroup_ss_mask(). This leads to the same result and is simpler and more robust. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 77 +++++++++++++++++++++++++++++++++++---------------------- 1 file changed, 47 insertions(+), 30 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 97cb1315bcac..1193038d0729 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3012,6 +3012,49 @@ static bool cgroup_drain_offline(struct cgroup *cgrp) return false; } +/** + * cgroup_apply_control_enable - enable or show csses according to control + * @cgrp: parent of the target cgroups + * + * Walk @cgrp's children and create new csses or make the existing ones + * visible. A css is created invisible if it's being implicitly enabled + * through dependency. An invisible css is made visible when the userland + * explicitly enables it. + * + * Returns 0 on success, -errno on failure. On failure, csses which have + * been processed already aren't cleaned up. The caller is responsible for + * cleaning up with cgroup_apply_control_disble(). + */ +static int cgroup_apply_control_enable(struct cgroup *cgrp) +{ + struct cgroup *dsct; + struct cgroup_subsys *ss; + int ssid, ret; + + cgroup_for_each_live_child(dsct, cgrp) { + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cgroup_css(dsct, ss); + + if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) + continue; + + if (!css) { + css = css_create(dsct, ss); + if (IS_ERR(css)) + return PTR_ERR(css); + } + + if (cgroup_control(dsct) & (1 << ss->id)) { + ret = css_populate_dir(css, NULL); + if (ret) + return ret; + } + } + } + + return 0; +} + /** * cgroup_apply_control_disable - kill or hide csses according to control * @cgrp: parent of the target cgroups @@ -3157,36 +3200,10 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, cgrp->subtree_control = new_sc; cgrp->subtree_ss_mask = new_ss; - /* - * Create new csses or make the existing ones visible. A css is - * created invisible if it's being implicitly enabled through - * dependency. An invisible css is made visible when the userland - * explicitly enables it. - */ - do_each_subsys_mask(ss, ssid, enable) { - cgroup_for_each_live_child(child, cgrp) { - if (css_enable & (1 << ssid)) { - struct cgroup_subsys_state *css; - - css = css_create(child, ss); - if (IS_ERR(css)) { - ret = PTR_ERR(css); - goto err_undo_css; - } - - if (cgrp->subtree_control & (1 << ssid)) { - ret = css_populate_dir(css, NULL); - if (ret) - goto err_undo_css; - } - } else { - ret = css_populate_dir(cgroup_css(child, ss), - NULL); - if (ret) - goto err_undo_css; - } - } - } while_each_subsys_mask(); + /* prepare csses */ + ret = cgroup_apply_control_enable(cgrp); + if (ret) + goto err_undo_css; /* * At this point, cgroup_e_css() results reflect the new csses -- cgit v1.2.3 From ce3f1d9d19371045981a64815227bab822554878 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:59 -0500 Subject: cgroup: make cgroup_drain_offline() and cgroup_apply_control_{disable|enable}() recursive The three factored out css management operations - cgroup_drain_offline() and cgroup_apply_control_{disable|enable}() - only depend on the current state of the target cgroups and idempotent and thus can be easily made to operate on the subtree instead of the immediate children. This patch introduces the iterators which walk live subtree and converts the three functions to operate on the subtree including self instead of the children. While this leads to spurious walking and be slightly more expensive, it will allow them to be used for wider scope of operations. Note that cgroup_drain_offline() now tests for whether a css is dying before trying to drain it. This is to avoid trying to drain live csses as there can be mix of live and dying csses in a subtree unlike children of the same parent. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 41 +++++++++++++++++++++++++++++++---------- 1 file changed, 31 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 1193038d0729..0398f2a6673b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -573,6 +573,24 @@ static int notify_on_release(const struct cgroup *cgrp) ; \ else +/* walk live descendants in preorder */ +#define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ + css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ + if (({ lockdep_assert_held(&cgroup_mutex); \ + (dsct) = (d_css)->cgroup; \ + cgroup_is_dead(dsct); })) \ + ; \ + else + +/* walk live descendants in postorder */ +#define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \ + css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \ + if (({ lockdep_assert_held(&cgroup_mutex); \ + (dsct) = (d_css)->cgroup; \ + cgroup_is_dead(dsct); })) \ + ; \ + else + static void cgroup_release_agent(struct work_struct *work); static void check_for_release(struct cgroup *cgrp); @@ -2967,11 +2985,11 @@ out_finish: /** * cgroup_drain_offline - wait for previously offlined csses to go away - * @cgrp: parent of the target cgroups + * @cgrp: root of the target subtree * * Because css offlining is asynchronous, userland may try to re-enable a * controller while the previous css is still around. This function drains - * the previous css instances of @cgrp's children. + * the previous css instances of @cgrp's subtree. * * Must be called with cgroup_mutex held. Returns %false if there were no * dying css instances. Returns %true if there were one or more and this @@ -2982,17 +3000,18 @@ out_finish: static bool cgroup_drain_offline(struct cgroup *cgrp) { struct cgroup *dsct; + struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&cgroup_mutex); - cgroup_for_each_live_child(dsct, cgrp) { + cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); DEFINE_WAIT(wait); - if (!css) + if (!css || !percpu_ref_is_dying(&css->refcnt)) continue; cgroup_get(dsct); @@ -3014,9 +3033,9 @@ static bool cgroup_drain_offline(struct cgroup *cgrp) /** * cgroup_apply_control_enable - enable or show csses according to control - * @cgrp: parent of the target cgroups + * @cgrp: root of the target subtree * - * Walk @cgrp's children and create new csses or make the existing ones + * Walk @cgrp's subtree and create new csses or make the existing ones * visible. A css is created invisible if it's being implicitly enabled * through dependency. An invisible css is made visible when the userland * explicitly enables it. @@ -3028,10 +3047,11 @@ static bool cgroup_drain_offline(struct cgroup *cgrp) static int cgroup_apply_control_enable(struct cgroup *cgrp) { struct cgroup *dsct; + struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid, ret; - cgroup_for_each_live_child(dsct, cgrp) { + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); @@ -3057,9 +3077,9 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp) /** * cgroup_apply_control_disable - kill or hide csses according to control - * @cgrp: parent of the target cgroups + * @cgrp: root of the target subtree * - * Walk @cgrp's children and kill and hide csses so that they match + * Walk @cgrp's subtree and kill and hide csses so that they match * cgroup_ss_mask() and cgroup_visible_mask(). * * A css is hidden when the userland requests it to be disabled while other @@ -3071,10 +3091,11 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp) static void cgroup_apply_control_disable(struct cgroup *cgrp) { struct cgroup *dsct; + struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; - cgroup_for_each_live_child(dsct, cgrp) { + cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); -- cgit v1.2.3 From 15a27c362d54378f17ec078579b2f6af88495a3f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:57:59 -0500 Subject: cgroup: introduce cgroup_{save|propagate|restore}_control() While controllers are being enabled and disabled in cgroup_subtree_control_write(), the original subsystem masks are stashed in local variables so that they can be restored if the operation fails in the middle. This patch adds dedicated fields to struct cgroup to be used instead of the local variables and implements functions to stash the current values, propagate the changes and restore them recursively. Combined with the previous changes, this makes subsystem management operations fully recursive and modularlized. This will be used to expand cgroup core functionalities. While at it, remove now unused @css_enable and @css_disable from cgroup_subtree_control_write(). Signed-off-by: Tejun Heo Acked-by: Zefan Li --- include/linux/cgroup-defs.h | 2 ++ kernel/cgroup.c | 82 ++++++++++++++++++++++++++++++++++----------- 2 files changed, 64 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 7593c1a46786..aae8c94de4b3 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -260,6 +260,8 @@ struct cgroup { */ u16 subtree_control; u16 subtree_ss_mask; + u16 old_subtree_control; + u16 old_subtree_ss_mask; /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0398f2a6673b..452a90e455fa 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3031,6 +3031,62 @@ static bool cgroup_drain_offline(struct cgroup *cgrp) return false; } +/** + * cgroup_save_control - save control masks of a subtree + * @cgrp: root of the target subtree + * + * Save ->subtree_control and ->subtree_ss_mask to the respective old_ + * prefixed fields for @cgrp's subtree including @cgrp itself. + */ +static void cgroup_save_control(struct cgroup *cgrp) +{ + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; + + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { + dsct->old_subtree_control = dsct->subtree_control; + dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; + } +} + +/** + * cgroup_propagate_control - refresh control masks of a subtree + * @cgrp: root of the target subtree + * + * For @cgrp and its subtree, ensure ->subtree_ss_mask matches + * ->subtree_control and propagate controller availability through the + * subtree so that descendants don't have unavailable controllers enabled. + */ +static void cgroup_propagate_control(struct cgroup *cgrp) +{ + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; + + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { + dsct->subtree_control &= cgroup_control(dsct); + dsct->subtree_ss_mask = cgroup_calc_subtree_ss_mask(dsct, + dsct->subtree_control); + } +} + +/** + * cgroup_restore_control - restore control masks of a subtree + * @cgrp: root of the target subtree + * + * Restore ->subtree_control and ->subtree_ss_mask from the respective old_ + * prefixed fields for @cgrp's subtree including @cgrp itself. + */ +static void cgroup_restore_control(struct cgroup *cgrp) +{ + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; + + cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { + dsct->subtree_control = dsct->old_subtree_control; + dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; + } +} + /** * cgroup_apply_control_enable - enable or show csses according to control * @cgrp: root of the target subtree @@ -3119,7 +3175,6 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, loff_t off) { u16 enable = 0, disable = 0; - u16 css_enable, css_disable, old_sc, new_sc, old_ss, new_ss; struct cgroup *cgrp, *child; struct cgroup_subsys *ss; char *tok; @@ -3203,25 +3258,14 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, return restart_syscall(); } - /* - * Update subsys masks and calculate what needs to be done. More - * subsystems than specified may need to be enabled or disabled - * depending on subsystem dependencies. - */ - old_sc = cgrp->subtree_control; - old_ss = cgrp->subtree_ss_mask; - new_sc = (old_sc | enable) & ~disable; - new_ss = cgroup_calc_subtree_ss_mask(cgrp, new_sc); + /* save and update control masks and prepare csses */ + cgroup_save_control(cgrp); - css_enable = ~old_ss & new_ss; - css_disable = old_ss & ~new_ss; - enable |= css_enable; - disable |= css_disable; + cgrp->subtree_control |= enable; + cgrp->subtree_control &= ~disable; - cgrp->subtree_control = new_sc; - cgrp->subtree_ss_mask = new_ss; + cgroup_propagate_control(cgrp); - /* prepare csses */ ret = cgroup_apply_control_enable(cgrp); if (ret) goto err_undo_css; @@ -3246,9 +3290,7 @@ out_unlock: err_undo_css: /* restore masks and shoot down new csses */ - cgrp->subtree_control = old_sc; - cgrp->subtree_ss_mask = old_ss; - + cgroup_restore_control(cgrp); cgroup_apply_control_disable(cgrp); goto out_unlock; -- cgit v1.2.3 From f7b2814bb9b6cb1d69333e1592c702260fcb4184 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:58:00 -0500 Subject: cgroup: factor out cgroup_{apply|finalize}_control() from cgroup_subtree_control_write() Factor out cgroup_{apply|finalize}_control() so that control mask update can be done in several simple steps. This patch doesn't introduce behavior changes. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 81 +++++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 58 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 452a90e455fa..2adf0433a3cf 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3169,6 +3169,62 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp) } } +/** + * cgroup_apply_control - apply control mask updates to the subtree + * @cgrp: root of the target subtree + * + * subsystems can be enabled and disabled in a subtree using the following + * steps. + * + * 1. Call cgroup_save_control() to stash the current state. + * 2. Update ->subtree_control masks in the subtree as desired. + * 3. Call cgroup_apply_control() to apply the changes. + * 4. Optionally perform other related operations. + * 5. Call cgroup_finalize_control() to finish up. + * + * This function implements step 3 and propagates the mask changes + * throughout @cgrp's subtree, updates csses accordingly and perform + * process migrations. + */ +static int cgroup_apply_control(struct cgroup *cgrp) +{ + int ret; + + cgroup_propagate_control(cgrp); + + ret = cgroup_apply_control_enable(cgrp); + if (ret) + return ret; + + /* + * At this point, cgroup_e_css() results reflect the new csses + * making the following cgroup_update_dfl_csses() properly update + * css associations of all tasks in the subtree. + */ + ret = cgroup_update_dfl_csses(cgrp); + if (ret) + return ret; + + return 0; +} + +/** + * cgroup_finalize_control - finalize control mask update + * @cgrp: root of the target subtree + * @ret: the result of the update + * + * Finalize control mask update. See cgroup_apply_control() for more info. + */ +static void cgroup_finalize_control(struct cgroup *cgrp, int ret) +{ + if (ret) { + cgroup_restore_control(cgrp); + cgroup_propagate_control(cgrp); + } + + cgroup_apply_control_disable(cgrp); +} + /* change the enabled child controllers for a cgroup in the default hierarchy */ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, @@ -3264,36 +3320,15 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, cgrp->subtree_control |= enable; cgrp->subtree_control &= ~disable; - cgroup_propagate_control(cgrp); + ret = cgroup_apply_control(cgrp); - ret = cgroup_apply_control_enable(cgrp); - if (ret) - goto err_undo_css; - - /* - * At this point, cgroup_e_css() results reflect the new csses - * making the following cgroup_update_dfl_csses() properly update - * css associations of all tasks in the subtree. - */ - ret = cgroup_update_dfl_csses(cgrp); - if (ret) - goto err_undo_css; - - /* all tasks are migrated out of disabled csses, commit disable */ - cgroup_apply_control_disable(cgrp); + cgroup_finalize_control(cgrp, ret); kernfs_activate(cgrp->kn); ret = 0; out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; - -err_undo_css: - /* restore masks and shoot down new csses */ - cgroup_restore_control(cgrp); - cgroup_apply_control_disable(cgrp); - - goto out_unlock; } static int cgroup_events_show(struct seq_file *seq, void *v) -- cgit v1.2.3 From 945ba1996888809cf510a8da000a9c20a9fab5ad Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:58:00 -0500 Subject: cgroup: combine cgroup_mutex locking and offline css draining cgroup_drain_offline() is used to wait for csses being offlined to uninstall itself from cgroup->subsys[] array so that new csses can be installed. The function's only user, cgroup_subtree_control_write(), calls it after performing some checks and restarts the whole process via restart_syscall() if draining has to release cgroup_mutex to wait. This can be simplified by draining before other synchronized operations so that there's nothing to restart. This patch converts cgroup_drain_offline() to cgroup_lock_and_drain_offline() which performs both locking and draining and updates cgroup_kn_lock_live() use it instead of cgroup_mutex() if requested. This combined locking and draining operations are easier to use and less error-prone. While at it, add WARNs in control_apply functions which triggers if the subtree isn't properly drained. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 55 +++++++++++++++++++++++++++---------------------------- 1 file changed, 27 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2adf0433a3cf..bbeb35f14eda 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -220,6 +220,7 @@ static struct cftype cgroup_dfl_base_files[]; static struct cftype cgroup_legacy_base_files[]; static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); +static void cgroup_lock_and_drain_offline(struct cgroup *cgrp); static void css_task_iter_advance(struct css_task_iter *it); static int cgroup_destroy_locked(struct cgroup *cgrp); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, @@ -1391,19 +1392,22 @@ static void cgroup_kn_unlock(struct kernfs_node *kn) /** * cgroup_kn_lock_live - locking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced + * @drain_offline: perform offline draining on the cgroup * * This helper is to be used by a cgroup kernfs method currently servicing * @kn. It breaks the active protection, performs cgroup locking and * verifies that the associated cgroup is alive. Returns the cgroup if * alive; otherwise, %NULL. A successful return should be undone by a - * matching cgroup_kn_unlock() invocation. + * matching cgroup_kn_unlock() invocation. If @drain_offline is %true, the + * cgroup is drained of offlining csses before return. * * Any cgroup kernfs method implementation which requires locking the * associated cgroup should use this helper. It avoids nesting cgroup * locking under kernfs active protection and allows all kernfs operations * including self-removal. */ -static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn) +static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, + bool drain_offline) { struct cgroup *cgrp; @@ -1422,7 +1426,10 @@ static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn) return NULL; kernfs_break_active_protection(kn); - mutex_lock(&cgroup_mutex); + if (drain_offline) + cgroup_lock_and_drain_offline(cgrp); + else + mutex_lock(&cgroup_mutex); if (!cgroup_is_dead(cgrp)) return cgrp; @@ -2761,7 +2768,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; - cgrp = cgroup_kn_lock_live(of->kn); + cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; @@ -2859,7 +2866,7 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); - cgrp = cgroup_kn_lock_live(of->kn); + cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; spin_lock(&release_agent_path_lock); @@ -2984,27 +2991,23 @@ out_finish: } /** - * cgroup_drain_offline - wait for previously offlined csses to go away + * cgroup_lock_and_drain_offline - lock cgroup_mutex and drain offlined csses * @cgrp: root of the target subtree * * Because css offlining is asynchronous, userland may try to re-enable a - * controller while the previous css is still around. This function drains - * the previous css instances of @cgrp's subtree. - * - * Must be called with cgroup_mutex held. Returns %false if there were no - * dying css instances. Returns %true if there were one or more and this - * function waited. On %true return, cgroup_mutex has been dropped and - * re-acquired inbetween which anything could have happened. The caller - * typically would have to start over. + * controller while the previous css is still around. This function grabs + * cgroup_mutex and drains the previous css instances of @cgrp's subtree. */ -static bool cgroup_drain_offline(struct cgroup *cgrp) +static void cgroup_lock_and_drain_offline(struct cgroup *cgrp) + __acquires(&cgroup_mutex) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; - lockdep_assert_held(&cgroup_mutex); +restart: + mutex_lock(&cgroup_mutex); cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { @@ -3021,14 +3024,11 @@ static bool cgroup_drain_offline(struct cgroup *cgrp) mutex_unlock(&cgroup_mutex); schedule(); finish_wait(&dsct->offline_waitq, &wait); - mutex_lock(&cgroup_mutex); cgroup_put(dsct); - return true; + goto restart; } } - - return false; } /** @@ -3111,6 +3111,8 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp) for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); + WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt)); + if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) continue; @@ -3155,6 +3157,8 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp) for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); + WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt)); + if (!css) continue; @@ -3264,7 +3268,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, return -EINVAL; } - cgrp = cgroup_kn_lock_live(of->kn); + cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENODEV; @@ -3309,11 +3313,6 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, goto out_unlock; } - if (cgroup_drain_offline(cgrp)) { - cgroup_kn_unlock(of->kn); - return restart_syscall(); - } - /* save and update control masks and prepare csses */ cgroup_save_control(cgrp); @@ -5140,7 +5139,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, if (strchr(name, '\n')) return -EINVAL; - parent = cgroup_kn_lock_live(parent_kn); + parent = cgroup_kn_lock_live(parent_kn, false); if (!parent) return -ENODEV; @@ -5339,7 +5338,7 @@ static int cgroup_rmdir(struct kernfs_node *kn) struct cgroup *cgrp; int ret = 0; - cgrp = cgroup_kn_lock_live(kn); + cgrp = cgroup_kn_lock_live(kn, false); if (!cgrp) return 0; -- cgit v1.2.3 From 03970d3c11faf870dc5126bb2e84fd1d692af1b7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:58:00 -0500 Subject: cgroup: use cgroup_apply_enable_control() in cgroup creation path cgroup_create() manually updates control masks and creates child csses which cgroup_mkdir() then manually populates. Both can be simplified by using cgroup_apply_enable_control() and friends. The only catch is that it calls css_populate_dir() with NULL cgroup->kn during cgroup_create(). This is worked around by making the function noop on NULL kn. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 38 ++++++++++++++------------------------ 1 file changed, 14 insertions(+), 24 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index bbeb35f14eda..ee6951b1e35d 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1490,7 +1490,7 @@ static int css_populate_dir(struct cgroup_subsys_state *css, struct cftype *cfts, *failed_cfts; int ret; - if (css->flags & CSS_VISIBLE) + if ((css->flags & CSS_VISIBLE) || !cgrp->kn) return 0; if (!css->ss) { @@ -5042,10 +5042,9 @@ err_free_css: static struct cgroup *cgroup_create(struct cgroup *parent) { struct cgroup_root *root = parent->root; - struct cgroup_subsys *ss; struct cgroup *cgrp, *tcgrp; int level = parent->level + 1; - int ssid, ret; + int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ cgrp = kzalloc(sizeof(*cgrp) + @@ -5095,25 +5094,19 @@ static struct cgroup *cgroup_create(struct cgroup *parent) */ cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id); - /* create the csses */ - do_each_subsys_mask(ss, ssid, cgroup_ss_mask(cgrp)) { - struct cgroup_subsys_state *css; - - css = css_create(cgrp, ss); - if (IS_ERR(css)) { - ret = PTR_ERR(css); - goto out_destroy; - } - } while_each_subsys_mask(); - /* * On the default hierarchy, a child doesn't automatically inherit * subtree_control from the parent. Each is configured manually. */ - if (!cgroup_on_dfl(cgrp)) { + if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); - cgroup_refresh_subtree_ss_mask(cgrp); - } + + cgroup_propagate_control(cgrp); + + /* @cgrp doesn't have dir yet so the following will only create csses */ + ret = cgroup_apply_control_enable(cgrp); + if (ret) + goto out_destroy; return cgrp; @@ -5131,9 +5124,8 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; - struct cgroup_subsys *ss; struct kernfs_node *kn; - int ssid, ret; + int ret; /* do not accept '\n' to prevent making /proc//cgroup unparsable */ if (strchr(name, '\n')) @@ -5171,11 +5163,9 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, if (ret) goto out_destroy; - do_each_subsys_mask(ss, ssid, cgroup_control(cgrp)) { - ret = css_populate_dir(cgroup_css(cgrp, ss), NULL); - if (ret) - goto out_destroy; - } while_each_subsys_mask(); + ret = cgroup_apply_control_enable(cgrp); + if (ret) + goto out_destroy; /* let's create and online css's */ kernfs_activate(kn); -- cgit v1.2.3 From 334c3679ec4b2b113c35ebe37d2018b112dd5013 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:58:01 -0500 Subject: cgroup: reimplement rebind_subsystems() using cgroup_apply_control() and friends rebind_subsystem() open codes quite a bit of css and interface file manipulations. It tries to be fail-safe but doesn't quite achieve it. It can be greatly simplified by using the new css management helpers. This patch reimplements rebind_subsytsems() using cgroup_apply_control() and friends. * The half-baked rollback on file creation failure is dropped. It is an extremely cold path, failure isn't critical, and, aside from kernel bugs, the only reason it can fail is memory allocation failure which pretty much doesn't happen for small allocations. * As cgroup_apply_control_disable() is now used to clean up root cgroup on rebind, make sure that it doesn't end up killing root csses. * All callers of rebind_subsystems() are updated to use cgroup_lock_and_drain_offline() as the apply_control functions require drained subtree. * This leaves cgroup_refresh_subtree_ss_mask() without any user. Removed. * css_populate_dir() and css_clear_dir() no longer needs @cgrp_override parameter. Dropped. * While at it, add WARN_ON() to rebind_subsystem() calls which are expected to always succeed just in case. While the rules visible to userland aren't changed, this reimplementation not only simplifies rebind_subsystems() but also allows it to disable and enable csses recursively. This can be used to implement more flexible rebinding. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 107 +++++++++++++++----------------------------------------- 1 file changed, 28 insertions(+), 79 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index ee6951b1e35d..98e644b0a532 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -221,6 +221,8 @@ static struct cftype cgroup_legacy_base_files[]; static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); static void cgroup_lock_and_drain_offline(struct cgroup *cgrp); +static int cgroup_apply_control(struct cgroup *cgrp); +static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_advance(struct css_task_iter *it); static int cgroup_destroy_locked(struct cgroup *cgrp); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, @@ -1160,13 +1162,13 @@ static void cgroup_destroy_root(struct cgroup_root *root) struct cgroup *cgrp = &root->cgrp; struct cgrp_cset_link *link, *tmp_link; - mutex_lock(&cgroup_mutex); + cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); BUG_ON(atomic_read(&root->nr_cgrps)); BUG_ON(!list_empty(&cgrp->self.children)); /* Rebind all subsystems back to the default hierarchy */ - rebind_subsystems(&cgrp_dfl_root, root->subsys_mask); + WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask)); /* * Release all the links from cset_links to this hierarchy's @@ -1351,19 +1353,6 @@ static u16 cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, u16 subtree_control) return cur_ss_mask; } -/** - * cgroup_refresh_subtree_ss_mask - update subtree_ss_mask - * @cgrp: the target cgroup - * - * Update @cgrp->subtree_ss_mask according to the current - * @cgrp->subtree_control using cgroup_calc_subtree_ss_mask(). - */ -static void cgroup_refresh_subtree_ss_mask(struct cgroup *cgrp) -{ - cgrp->subtree_ss_mask = - cgroup_calc_subtree_ss_mask(cgrp, cgrp->subtree_control); -} - /** * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced @@ -1459,12 +1448,10 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) /** * css_clear_dir - remove subsys files in a cgroup directory * @css: taget css - * @cgrp_override: specify if target cgroup is different from css->cgroup */ -static void css_clear_dir(struct cgroup_subsys_state *css, - struct cgroup *cgrp_override) +static void css_clear_dir(struct cgroup_subsys_state *css) { - struct cgroup *cgrp = cgrp_override ?: css->cgroup; + struct cgroup *cgrp = css->cgroup; struct cftype *cfts; if (!(css->flags & CSS_VISIBLE)) @@ -1479,14 +1466,12 @@ static void css_clear_dir(struct cgroup_subsys_state *css, /** * css_populate_dir - create subsys files in a cgroup directory * @css: target css - * @cgrp_overried: specify if target cgroup is different from css->cgroup * * On failure, no file is added. */ -static int css_populate_dir(struct cgroup_subsys_state *css, - struct cgroup *cgrp_override) +static int css_populate_dir(struct cgroup_subsys_state *css) { - struct cgroup *cgrp = cgrp_override ?: css->cgroup; + struct cgroup *cgrp = css->cgroup; struct cftype *cfts, *failed_cfts; int ret; @@ -1526,7 +1511,6 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; - u16 tmp_ss_mask; int ssid, i, ret; lockdep_assert_held(&cgroup_mutex); @@ -1541,46 +1525,6 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) return -EBUSY; } while_each_subsys_mask(); - /* skip creating root files on dfl_root for inhibited subsystems */ - tmp_ss_mask = ss_mask; - if (dst_root == &cgrp_dfl_root) - tmp_ss_mask &= ~cgrp_dfl_inhibit_ss_mask; - - do_each_subsys_mask(ss, ssid, tmp_ss_mask) { - struct cgroup *scgrp = &ss->root->cgrp; - int tssid; - - ret = css_populate_dir(cgroup_css(scgrp, ss), dcgrp); - if (!ret) - continue; - - /* - * Rebinding back to the default root is not allowed to - * fail. Using both default and non-default roots should - * be rare. Moving subsystems back and forth even more so. - * Just warn about it and continue. - */ - if (dst_root == &cgrp_dfl_root) { - if (cgrp_dfl_visible) { - pr_warn("failed to create files (%d) while rebinding 0x%x to default root\n", - ret, ss_mask); - pr_warn("you may retry by moving them to a different hierarchy and unbinding\n"); - } - continue; - } - - do_each_subsys_mask(ss, tssid, tmp_ss_mask) { - if (tssid == ssid) - break; - css_clear_dir(cgroup_css(scgrp, ss), dcgrp); - } while_each_subsys_mask(); - return ret; - } while_each_subsys_mask(); - - /* - * Nothing can fail from this point on. Remove files for the - * removed subsystems and rebind each subsystem. - */ do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; @@ -1589,8 +1533,12 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) WARN_ON(!css || cgroup_css(dcgrp, ss)); - css_clear_dir(css, NULL); + /* disable from the source */ + src_root->subsys_mask &= ~(1 << ssid); + WARN_ON(cgroup_apply_control(scgrp)); + cgroup_finalize_control(scgrp, 0); + /* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); rcu_assign_pointer(dcgrp->subsys[ssid], css); ss->root = dst_root; @@ -1602,20 +1550,20 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) &dcgrp->e_csets[ss->id]); spin_unlock_bh(&css_set_lock); - src_root->subsys_mask &= ~(1 << ssid); - scgrp->subtree_control &= ~(1 << ssid); - cgroup_refresh_subtree_ss_mask(scgrp); - /* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; if (dst_root == &cgrp_dfl_root) { static_branch_enable(cgroup_subsys_on_dfl_key[ssid]); } else { dcgrp->subtree_control |= 1 << ssid; - cgroup_refresh_subtree_ss_mask(dcgrp); static_branch_disable(cgroup_subsys_on_dfl_key[ssid]); } + ret = cgroup_apply_control(dcgrp); + if (ret) + pr_warn("partial failure to rebind %s controller (err=%d)\n", + ss->name, ret); + if (ss->bind) ss->bind(css); } while_each_subsys_mask(); @@ -1807,7 +1755,7 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data) return -EINVAL; } - mutex_lock(&cgroup_mutex); + cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); /* See what subsystems are wanted */ ret = parse_cgroupfs_options(data, &opts); @@ -1840,7 +1788,7 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data) if (ret) goto out_unlock; - rebind_subsystems(&cgrp_dfl_root, removed_mask); + WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); if (opts.release_agent) { spin_lock(&release_agent_path_lock); @@ -1991,7 +1939,7 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) } root_cgrp->kn = root->kf_root->kn; - ret = css_populate_dir(&root_cgrp->self, NULL); + ret = css_populate_dir(&root_cgrp->self); if (ret) goto destroy_root; @@ -2070,7 +2018,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, goto out_mount; } - mutex_lock(&cgroup_mutex); + cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); /* First find the desired set of subsystems */ ret = parse_cgroupfs_options(data, &opts); @@ -3123,7 +3071,7 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp) } if (cgroup_control(dsct) & (1 << ss->id)) { - ret = css_populate_dir(css, NULL); + ret = css_populate_dir(css); if (ret) return ret; } @@ -3162,10 +3110,11 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp) if (!css) continue; - if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) { + if (css->parent && + !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css(css); } else if (!(cgroup_control(dsct) & (1 << ss->id))) { - css_clear_dir(css, NULL); + css_clear_dir(css); if (ss->css_reset) ss->css_reset(css); } @@ -5159,7 +5108,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, if (ret) goto out_destroy; - ret = css_populate_dir(&cgrp->self, NULL); + ret = css_populate_dir(&cgrp->self); if (ret) goto out_destroy; @@ -5231,7 +5180,7 @@ static void kill_css(struct cgroup_subsys_state *css) * This must happen before css is disassociated with its cgroup. * See seq_css() for details. */ - css_clear_dir(css, NULL); + css_clear_dir(css); /* * Killing would put the base ref, but we need to keep it alive -- cgit v1.2.3 From 5ced2518bd3e3a4f01e2122122211f217cd99f4f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:58:01 -0500 Subject: cgroup: make cgroup_calc_subtree_ss_mask() take @this_ss_mask cgroup_calc_subtree_ss_mask() currently takes @cgrp and @subtree_control. @cgrp is used for two purposes - to decide whether it's for default hierarchy and the mask of available subsystems. The former doesn't matter as the results are the same regardless. The latter can be specified directly through a subsystem mask. This patch makes cgroup_calc_subtree_ss_mask() perform the same calculations for both default and legacy hierarchies and take @this_ss_mask for available subsystems. @cgrp is no longer used and dropped. This is to allow using the function in contexts where available controllers can't be decided from the cgroup. v2: cgroup_refres_subtree_ss_mask() is removed by a previous patch. Updated accordingly. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 98e644b0a532..58e02e9aa970 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1309,18 +1309,17 @@ static umode_t cgroup_file_mode(const struct cftype *cft) /** * cgroup_calc_subtree_ss_mask - calculate subtree_ss_mask - * @cgrp: the target cgroup * @subtree_control: the new subtree_control mask to consider + * @this_ss_mask: available subsystems * * On the default hierarchy, a subsystem may request other subsystems to be * enabled together through its ->depends_on mask. In such cases, more * subsystems than specified in "cgroup.subtree_control" may be enabled. * * This function calculates which subsystems need to be enabled if - * @subtree_control is to be applied to @cgrp. The returned mask is always - * a superset of @subtree_control and follows the usual hierarchy rules. + * @subtree_control is to be applied while restricted to @this_ss_mask. */ -static u16 cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, u16 subtree_control) +static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask) { u16 cur_ss_mask = subtree_control; struct cgroup_subsys *ss; @@ -1328,9 +1327,6 @@ static u16 cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, u16 subtree_control) lockdep_assert_held(&cgroup_mutex); - if (!cgroup_on_dfl(cgrp)) - return cur_ss_mask; - while (true) { u16 new_ss_mask = cur_ss_mask; @@ -1343,7 +1339,7 @@ static u16 cgroup_calc_subtree_ss_mask(struct cgroup *cgrp, u16 subtree_control) * happen only if some depended-upon subsystems were bound * to non-default hierarchies. */ - new_ss_mask &= cgroup_ss_mask(cgrp); + new_ss_mask &= this_ss_mask; if (new_ss_mask == cur_ss_mask) break; @@ -3012,8 +3008,9 @@ static void cgroup_propagate_control(struct cgroup *cgrp) cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->subtree_control &= cgroup_control(dsct); - dsct->subtree_ss_mask = cgroup_calc_subtree_ss_mask(dsct, - dsct->subtree_control); + dsct->subtree_ss_mask = + cgroup_calc_subtree_ss_mask(dsct->subtree_control, + cgroup_ss_mask(dsct)); } } -- cgit v1.2.3 From 04313591ae487da8b5781a0d8d444073a3fdee0d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:58:01 -0500 Subject: cgroup: allocate 2x cgrp_cset_links when setting up a new root During prep, cgroup_setup_root() allocates cgrp_cset_links matching the number of existing css_sets to later link the new root. This is fine for now as the only operation which can happen inbetween is rebind_subsystems() and rebinding of empty subsystems doesn't create new css_sets. However, while not yet allowed, with the recent reimplementation, rebind_subsystems() can rebind subsystems with descendant csses and thus can create new css_sets. This patch makes cgroup_setup_root() allocate 2x of the existing css_sets so that later use of live subsystem rebinding doesn't blow up. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 58e02e9aa970..40ed329482dd 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1915,10 +1915,11 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) /* * We're accessing css_set_count without locking css_set_lock here, * but that's OK - it can only be increased by someone holding - * cgroup_lock, and that's us. The worst that can happen is that we - * have some link structures left over + * cgroup_lock, and that's us. Later rebinding may disable + * controllers on the default hierarchy and thus create new csets, + * which can't be more than the existing ones. Allocate 2x. */ - ret = allocate_cgrp_cset_links(css_set_count, &tmp_links); + ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links); if (ret) goto cancel_ref; -- cgit v1.2.3 From 549626047df99f1129d4e742cce741055bdc2dcb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Mar 2016 09:58:01 -0500 Subject: cgroup: update css iteration in cgroup_update_dfl_csses() The existing sequences of operations ensure that the offlining csses are drained before cgroup_update_dfl_csses(), so even though cgroup_update_dfl_csses() uses css_for_each_descendant_pre() to walk the target cgroups, it doesn't end up operating on dead cgroups. Also, the function explicitly excludes the subtree root from operation. This is fragile and inconsistent with the rest of css update operations. This patch updates cgroup_update_dfl_csses() to use cgroup_for_each_live_descendant_pre() instead and include the subtree root. Signed-off-by: Tejun Heo Acked-by: Zefan Li --- kernel/cgroup.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 40ed329482dd..c63fce0c5b24 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2877,16 +2877,17 @@ static int cgroup_subtree_control_show(struct seq_file *seq, void *v) * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy * @cgrp: root of the subtree to update csses for * - * @cgrp's subtree_ss_mask has changed and its subtree's (self excluded) - * css associations need to be updated accordingly. This function looks up - * all css_sets which are attached to the subtree, creates the matching - * updated css_sets and migrates the tasks to the new ones. + * @cgrp's control masks have changed and its subtree's css associations + * need to be updated accordingly. This function looks up all css_sets + * which are attached to the subtree, creates the matching updated css_sets + * and migrates the tasks to the new ones. */ static int cgroup_update_dfl_csses(struct cgroup *cgrp) { LIST_HEAD(preloaded_csets); struct cgroup_taskset tset = CGROUP_TASKSET_INIT(tset); - struct cgroup_subsys_state *css; + struct cgroup_subsys_state *d_css; + struct cgroup *dsct; struct css_set *src_cset; int ret; @@ -2896,14 +2897,10 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) /* look up all csses currently attached to @cgrp's subtree */ spin_lock_bh(&css_set_lock); - css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) { + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { struct cgrp_cset_link *link; - /* self is not affected by subtree_ss_mask change */ - if (css->cgroup == cgrp) - continue; - - list_for_each_entry(link, &css->cgroup->cset_links, cset_link) + list_for_each_entry(link, &dsct->cset_links, cset_link) cgroup_migrate_add_src(link->cset, cgrp, &preloaded_csets); } -- cgit v1.2.3 From 4e8ae72a75aae285ec5b93518b9680da198afd0d Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 3 Mar 2016 21:49:27 +0000 Subject: X.509: Make algo identifiers text instead of enum Make the identifier public key and digest algorithm fields text instead of enum. Signed-off-by: David Howells Acked-by: Herbert Xu --- crypto/asymmetric_keys/mscode_parser.c | 14 +++++++------- crypto/asymmetric_keys/pkcs7_parser.c | 18 ++++++++---------- crypto/asymmetric_keys/pkcs7_verify.c | 8 +++----- crypto/asymmetric_keys/public_key.c | 24 ++++-------------------- crypto/asymmetric_keys/verify_pefile.c | 4 ++-- crypto/asymmetric_keys/verify_pefile.h | 2 +- crypto/asymmetric_keys/x509_cert_parser.c | 26 +++++++++++++------------- crypto/asymmetric_keys/x509_public_key.c | 17 ++++++++--------- include/crypto/public_key.h | 30 ++++-------------------------- kernel/module_signing.c | 6 ++++++ security/integrity/digsig_asymmetric.c | 7 ++++--- security/integrity/integrity.h | 2 +- 12 files changed, 61 insertions(+), 97 deletions(-) (limited to 'kernel') diff --git a/crypto/asymmetric_keys/mscode_parser.c b/crypto/asymmetric_keys/mscode_parser.c index adcef59eec0b..3242cbfaeaa2 100644 --- a/crypto/asymmetric_keys/mscode_parser.c +++ b/crypto/asymmetric_keys/mscode_parser.c @@ -86,25 +86,25 @@ int mscode_note_digest_algo(void *context, size_t hdrlen, oid = look_up_OID(value, vlen); switch (oid) { case OID_md4: - ctx->digest_algo = HASH_ALGO_MD4; + ctx->digest_algo = "md4"; break; case OID_md5: - ctx->digest_algo = HASH_ALGO_MD5; + ctx->digest_algo = "md5"; break; case OID_sha1: - ctx->digest_algo = HASH_ALGO_SHA1; + ctx->digest_algo = "sha1"; break; case OID_sha256: - ctx->digest_algo = HASH_ALGO_SHA256; + ctx->digest_algo = "sha256"; break; case OID_sha384: - ctx->digest_algo = HASH_ALGO_SHA384; + ctx->digest_algo = "sha384"; break; case OID_sha512: - ctx->digest_algo = HASH_ALGO_SHA512; + ctx->digest_algo = "sha512"; break; case OID_sha224: - ctx->digest_algo = HASH_ALGO_SHA224; + ctx->digest_algo = "sha224"; break; case OID__NR: diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c index cbbd03fd94f8..40de03f49ff8 100644 --- a/crypto/asymmetric_keys/pkcs7_parser.c +++ b/crypto/asymmetric_keys/pkcs7_parser.c @@ -218,25 +218,25 @@ int pkcs7_sig_note_digest_algo(void *context, size_t hdrlen, switch (ctx->last_oid) { case OID_md4: - ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_MD4; + ctx->sinfo->sig.hash_algo = "md4"; break; case OID_md5: - ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_MD5; + ctx->sinfo->sig.hash_algo = "md5"; break; case OID_sha1: - ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_SHA1; + ctx->sinfo->sig.hash_algo = "sha1"; break; case OID_sha256: - ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_SHA256; + ctx->sinfo->sig.hash_algo = "sha256"; break; case OID_sha384: - ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_SHA384; + ctx->sinfo->sig.hash_algo = "sha384"; break; case OID_sha512: - ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_SHA512; + ctx->sinfo->sig.hash_algo = "sha512"; break; case OID_sha224: - ctx->sinfo->sig.pkey_hash_algo = HASH_ALGO_SHA224; + ctx->sinfo->sig.hash_algo = "sha224"; default: printk("Unsupported digest algo: %u\n", ctx->last_oid); return -ENOPKG; @@ -255,7 +255,7 @@ int pkcs7_sig_note_pkey_algo(void *context, size_t hdrlen, switch (ctx->last_oid) { case OID_rsaEncryption: - ctx->sinfo->sig.pkey_algo = PKEY_ALGO_RSA; + ctx->sinfo->sig.pkey_algo = "rsa"; break; default: printk("Unsupported pkey algo: %u\n", ctx->last_oid); @@ -615,8 +615,6 @@ int pkcs7_sig_note_signature(void *context, size_t hdrlen, { struct pkcs7_parse_context *ctx = context; - BUG_ON(ctx->sinfo->sig.pkey_algo != PKEY_ALGO_RSA); - ctx->sinfo->sig.s = kmemdup(value, vlen, GFP_KERNEL); if (!ctx->sinfo->sig.s) return -ENOMEM; diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c index f5db1378c096..50be2a15e531 100644 --- a/crypto/asymmetric_keys/pkcs7_verify.c +++ b/crypto/asymmetric_keys/pkcs7_verify.c @@ -31,17 +31,15 @@ static int pkcs7_digest(struct pkcs7_message *pkcs7, void *digest; int ret; - kenter(",%u,%u", sinfo->index, sinfo->sig.pkey_hash_algo); + kenter(",%u,%s", sinfo->index, sinfo->sig.hash_algo); - if (sinfo->sig.pkey_hash_algo >= PKEY_HASH__LAST || - !hash_algo_name[sinfo->sig.pkey_hash_algo]) + if (!sinfo->sig.hash_algo) return -ENOPKG; /* Allocate the hashing algorithm we're going to need and find out how * big the hash operational data will be. */ - tfm = crypto_alloc_shash(hash_algo_name[sinfo->sig.pkey_hash_algo], - 0, 0); + tfm = crypto_alloc_shash(sinfo->sig.hash_algo, 0, 0); if (IS_ERR(tfm)) return (PTR_ERR(tfm) == -ENOENT) ? -ENOPKG : PTR_ERR(tfm); diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index 27ebc2f44394..0f8b264b3961 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -24,19 +24,6 @@ MODULE_LICENSE("GPL"); -const char *const pkey_algo_name[PKEY_ALGO__LAST] = { - [PKEY_ALGO_DSA] = "dsa", - [PKEY_ALGO_RSA] = "rsa", -}; -EXPORT_SYMBOL_GPL(pkey_algo_name); - -const char *const pkey_id_type_name[PKEY_ID_TYPE__LAST] = { - [PKEY_ID_PGP] = "PGP", - [PKEY_ID_X509] = "X509", - [PKEY_ID_PKCS7] = "PKCS#7", -}; -EXPORT_SYMBOL_GPL(pkey_id_type_name); - /* * Provide a part of a description of the key for /proc/keys. */ @@ -46,9 +33,7 @@ static void public_key_describe(const struct key *asymmetric_key, struct public_key *key = asymmetric_key->payload.data[asym_crypto]; if (key) - seq_printf(m, "%s.%s", - pkey_id_type_name[key->id_type], - pkey_algo_name[key->pkey_algo]); + seq_printf(m, "%s.%s", key->id_type, key->pkey_algo); } /* @@ -103,15 +88,14 @@ int public_key_verify_signature(const struct public_key *pkey, BUG_ON(!sig->digest); BUG_ON(!sig->s); - alg_name = pkey_algo_name[sig->pkey_algo]; - if (sig->pkey_algo == PKEY_ALGO_RSA) { + alg_name = sig->pkey_algo; + if (strcmp(sig->pkey_algo, "rsa") == 0) { /* The data wangled by the RSA algorithm is typically padded * and encoded in some manner, such as EMSA-PKCS1-1_5 [RFC3447 * sec 8.2]. */ if (snprintf(alg_name_buf, CRYPTO_MAX_ALG_NAME, - "pkcs1pad(rsa,%s)", - hash_algo_name[sig->pkey_hash_algo] + "pkcs1pad(rsa,%s)", sig->hash_algo ) >= CRYPTO_MAX_ALG_NAME) return -EINVAL; alg_name = alg_name_buf; diff --git a/crypto/asymmetric_keys/verify_pefile.c b/crypto/asymmetric_keys/verify_pefile.c index 897b734dabf9..7e8c2338ae25 100644 --- a/crypto/asymmetric_keys/verify_pefile.c +++ b/crypto/asymmetric_keys/verify_pefile.c @@ -328,12 +328,12 @@ static int pefile_digest_pe(const void *pebuf, unsigned int pelen, void *digest; int ret; - kenter(",%u", ctx->digest_algo); + kenter(",%s", ctx->digest_algo); /* Allocate the hashing algorithm we're going to need and find out how * big the hash operational data will be. */ - tfm = crypto_alloc_shash(hash_algo_name[ctx->digest_algo], 0, 0); + tfm = crypto_alloc_shash(ctx->digest_algo, 0, 0); if (IS_ERR(tfm)) return (PTR_ERR(tfm) == -ENOENT) ? -ENOPKG : PTR_ERR(tfm); diff --git a/crypto/asymmetric_keys/verify_pefile.h b/crypto/asymmetric_keys/verify_pefile.h index 55d5f7ebc45a..a133eb81a492 100644 --- a/crypto/asymmetric_keys/verify_pefile.h +++ b/crypto/asymmetric_keys/verify_pefile.h @@ -28,7 +28,7 @@ struct pefile_context { /* PKCS#7 MS Individual Code Signing content */ const void *digest; /* Digest */ unsigned digest_len; /* Digest length */ - enum hash_algo digest_algo; /* Digest algorithm */ + const char *digest_algo; /* Digest algorithm */ }; #define kenter(FMT, ...) \ diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index c02c200a7136..4a29bac70060 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -188,33 +188,33 @@ int x509_note_pkey_algo(void *context, size_t hdrlen, return -ENOPKG; /* Unsupported combination */ case OID_md4WithRSAEncryption: - ctx->cert->sig.pkey_hash_algo = HASH_ALGO_MD5; - ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA; + ctx->cert->sig.hash_algo = "md4"; + ctx->cert->sig.pkey_algo = "rsa"; break; case OID_sha1WithRSAEncryption: - ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA1; - ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA; + ctx->cert->sig.hash_algo = "sha1"; + ctx->cert->sig.pkey_algo = "rsa"; break; case OID_sha256WithRSAEncryption: - ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA256; - ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA; + ctx->cert->sig.hash_algo = "sha256"; + ctx->cert->sig.pkey_algo = "rsa"; break; case OID_sha384WithRSAEncryption: - ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA384; - ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA; + ctx->cert->sig.hash_algo = "sha384"; + ctx->cert->sig.pkey_algo = "rsa"; break; case OID_sha512WithRSAEncryption: - ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA512; - ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA; + ctx->cert->sig.hash_algo = "sha512"; + ctx->cert->sig.pkey_algo = "rsa"; break; case OID_sha224WithRSAEncryption: - ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA224; - ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA; + ctx->cert->sig.hash_algo = "sha224"; + ctx->cert->sig.pkey_algo = "rsa"; break; } @@ -396,7 +396,7 @@ int x509_extract_key_data(void *context, size_t hdrlen, if (ctx->last_oid != OID_rsaEncryption) return -ENOPKG; - ctx->cert->pub->pkey_algo = PKEY_ALGO_RSA; + ctx->cert->pub->pkey_algo = "rsa"; /* Discard the BIT STRING metadata */ ctx->key = value + 1; diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c index 7092d5cbb5d3..733c046aacc6 100644 --- a/crypto/asymmetric_keys/x509_public_key.c +++ b/crypto/asymmetric_keys/x509_public_key.c @@ -176,7 +176,7 @@ int x509_get_sig_params(struct x509_certificate *cert) /* Allocate the hashing algorithm we're going to need and find out how * big the hash operational data will be. */ - tfm = crypto_alloc_shash(hash_algo_name[cert->sig.pkey_hash_algo], 0, 0); + tfm = crypto_alloc_shash(cert->sig.hash_algo, 0, 0); if (IS_ERR(tfm)) { if (PTR_ERR(tfm) == -ENOENT) { cert->unsupported_crypto = true; @@ -291,21 +291,20 @@ static int x509_key_preparse(struct key_preparsed_payload *prep) pr_devel("Cert Issuer: %s\n", cert->issuer); pr_devel("Cert Subject: %s\n", cert->subject); - if (cert->pub->pkey_algo >= PKEY_ALGO__LAST || - cert->sig.pkey_algo >= PKEY_ALGO__LAST || - cert->sig.pkey_hash_algo >= PKEY_HASH__LAST || - !hash_algo_name[cert->sig.pkey_hash_algo]) { + if (!cert->pub->pkey_algo || + !cert->sig.pkey_algo || + !cert->sig.hash_algo) { ret = -ENOPKG; goto error_free_cert; } - pr_devel("Cert Key Algo: %s\n", pkey_algo_name[cert->pub->pkey_algo]); + pr_devel("Cert Key Algo: %s\n", cert->pub->pkey_algo); pr_devel("Cert Valid period: %lld-%lld\n", cert->valid_from, cert->valid_to); pr_devel("Cert Signature: %s + %s\n", - pkey_algo_name[cert->sig.pkey_algo], - hash_algo_name[cert->sig.pkey_hash_algo]); + cert->sig.pkey_algo, + cert->sig.hash_algo); - cert->pub->id_type = PKEY_ID_X509; + cert->pub->id_type = "X509"; /* Check the signature on the key if it appears to be self-signed */ if ((!cert->akid_skid && !cert->akid_id) || diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h index 80ab099a3edf..aa730ea7faf8 100644 --- a/include/crypto/public_key.h +++ b/include/crypto/public_key.h @@ -14,28 +14,6 @@ #ifndef _LINUX_PUBLIC_KEY_H #define _LINUX_PUBLIC_KEY_H -#include - -enum pkey_algo { - PKEY_ALGO_DSA, - PKEY_ALGO_RSA, - PKEY_ALGO__LAST -}; - -extern const char *const pkey_algo_name[PKEY_ALGO__LAST]; - -/* asymmetric key implementation supports only up to SHA224 */ -#define PKEY_HASH__LAST (HASH_ALGO_SHA224 + 1) - -enum pkey_id_type { - PKEY_ID_PGP, /* OpenPGP generated key ID */ - PKEY_ID_X509, /* X.509 arbitrary subjectKeyIdentifier */ - PKEY_ID_PKCS7, /* Signature in PKCS#7 message */ - PKEY_ID_TYPE__LAST -}; - -extern const char *const pkey_id_type_name[PKEY_ID_TYPE__LAST]; - /* * The use to which an asymmetric key is being put. */ @@ -59,8 +37,8 @@ extern const char *const key_being_used_for[NR__KEY_BEING_USED_FOR]; struct public_key { void *key; u32 keylen; - enum pkey_algo pkey_algo : 8; - enum pkey_id_type id_type : 8; + const char *id_type; + const char *pkey_algo; }; extern void public_key_destroy(void *payload); @@ -73,8 +51,8 @@ struct public_key_signature { u32 s_size; /* Number of bytes in signature */ u8 *digest; u8 digest_size; /* Number of bytes in digest */ - enum pkey_algo pkey_algo : 8; - enum hash_algo pkey_hash_algo : 8; + const char *pkey_algo; + const char *hash_algo; }; extern struct asymmetric_key_subtype public_key_subtype; diff --git a/kernel/module_signing.c b/kernel/module_signing.c index 9cfa46d8d14f..64b9dead4a07 100644 --- a/kernel/module_signing.c +++ b/kernel/module_signing.c @@ -16,6 +16,12 @@ #include #include "module-internal.h" +enum pkey_id_type { + PKEY_ID_PGP, /* OpenPGP generated key ID */ + PKEY_ID_X509, /* X.509 arbitrary subjectKeyIdentifier */ + PKEY_ID_PKCS7, /* Signature in PKCS#7 message */ +}; + /* * Module signature information block. * diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c index 69a92e6db23d..80052ed8d467 100644 --- a/security/integrity/digsig_asymmetric.c +++ b/security/integrity/digsig_asymmetric.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -94,7 +95,7 @@ int asymmetric_verify(struct key *keyring, const char *sig, if (siglen != __be16_to_cpu(hdr->sig_size)) return -EBADMSG; - if (hdr->hash_algo >= PKEY_HASH__LAST) + if (hdr->hash_algo >= HASH_ALGO__LAST) return -ENOPKG; key = request_asymmetric_key(keyring, __be32_to_cpu(hdr->keyid)); @@ -103,8 +104,8 @@ int asymmetric_verify(struct key *keyring, const char *sig, memset(&pks, 0, sizeof(pks)); - pks.pkey_algo = PKEY_ALGO_RSA; - pks.pkey_hash_algo = hdr->hash_algo; + pks.pkey_algo = "rsa"; + pks.hash_algo = hash_algo_name[hdr->hash_algo]; pks.digest = (u8 *)data; pks.digest_size = datalen; pks.s = hdr->sig; diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index 5efe2ecc538d..c7708d9a1b41 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -94,7 +94,7 @@ struct ima_digest_data { struct signature_v2_hdr { uint8_t type; /* xattr type */ uint8_t version; /* signature format version */ - uint8_t hash_algo; /* Digest algorithm [enum pkey_hash_algo] */ + uint8_t hash_algo; /* Digest algorithm [enum hash_algo] */ uint32_t keyid; /* IMA key identifier - not X509/PGP specific */ uint16_t sig_size; /* signature size */ uint8_t sig[0]; /* signature payload */ -- cgit v1.2.3 From e9532e69b8d1d1284e8ecf8d2586de34aec61244 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 4 Mar 2016 15:59:42 +0100 Subject: sched/cputime: Fix steal time accounting vs. CPU hotplug On CPU hotplug the steal time accounting can keep a stale rq->prev_steal_time value over CPU down and up. So after the CPU comes up again the delta calculation in steal_account_process_tick() wreckages itself due to the unsigned math: u64 steal = paravirt_steal_clock(smp_processor_id()); steal -= this_rq()->prev_steal_time; So if steal is smaller than rq->prev_steal_time we end up with an insane large value which then gets added to rq->prev_steal_time, resulting in a permanent wreckage of the accounting. As a consequence the per CPU stats in /proc/stat become stale. Nice trick to tell the world how idle the system is (100%) while the CPU is 100% busy running tasks. Though we prefer realistic numbers. None of the accounting values which use a previous value to account for fractions is reset at CPU hotplug time. update_rq_clock_task() has a sanity check for prev_irq_time and prev_steal_time_rq, but that sanity check solely deals with clock warps and limits the /proc/stat visible wreckage. The prev_time values are still wrong. Solution is simple: Reset rq->prev_*_time when the CPU is plugged in again. Signed-off-by: Thomas Gleixner Acked-by: Rik van Riel Cc: Cc: Frederic Weisbecker Cc: Glauber Costa Cc: Linus Torvalds Cc: Peter Zijlstra Fixes: commit 095c0aa83e52 "sched: adjust scheduler cpu power for stolen time" Fixes: commit aa483808516c "sched: Remove irq time from available CPU power" Fixes: commit e6e6685accfa "KVM guest: Steal time accounting" Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1603041539490.3686@nanos Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 1 + kernel/sched/sched.h | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ab814bf100e1..406182af99ac 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5627,6 +5627,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_UP_PREPARE: rq->calc_load_update = calc_load_update; + account_reset_rq(rq); break; case CPU_ONLINE: diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 30ea2d871ba7..4f6598ae4c31 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1738,3 +1738,16 @@ static inline u64 irq_time_read(int cpu) } #endif /* CONFIG_64BIT */ #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +static inline void account_reset_rq(struct rq *rq) +{ +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + rq->prev_irq_time = 0; +#endif +#ifdef CONFIG_PARAVIRT + rq->prev_steal_time = 0; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + rq->prev_steal_time_rq = 0; +#endif +} -- cgit v1.2.3 From d39cdd2036a63eef17a14efbd969405ca5612886 Mon Sep 17 00:00:00 2001 From: Chunyu Hu Date: Tue, 8 Mar 2016 21:37:01 +0800 Subject: tracing: Make tracer_flags use the right set_flag callback When I was updating the ftrace_stress test of ltp. I encountered a strange phenomemon, excute following steps: echo nop > /sys/kernel/debug/tracing/current_tracer echo 0 > /sys/kernel/debug/tracing/options/funcgraph-cpu bash: echo: write error: Invalid argument check dmesg: [ 1024.903855] nop_test_refuse flag set to 0: we refuse.Now cat trace_options to see the result The reason is that the trace option test will randomly setup trace option under tracing/options no matter what the current_tracer is. but the set_tracer_option is always using the set_flag callback from the current_tracer. This patch adds a pointer to tracer_flags and make it point to the tracer it belongs to. When the option is setup, the set_flag of the right tracer will be used no matter what the the current_tracer is. And the old dummy_tracer_flags is used for all the tracers which doesn't have a tracer_flags, having issue to use it to save the pointer of a tracer. So remove it and use dynamic dummy tracer_flags for tracers needing a dummy tracer_flags, as a result, there are no tracers sharing tracer_flags, so remove the check code. And save the current tracer to trace_option_dentry seems not good as it may waste mem space when mount the debug/trace fs more than one time. Link: http://lkml.kernel.org/r/1457444222-8654-1-git-send-email-chuhu@redhat.com Signed-off-by: Chunyu Hu [ Fixed up function tracer options to work with the change ] Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 28 ++++++++++++++-------------- kernel/trace/trace.h | 1 + kernel/trace/trace_functions.c | 6 ++++++ 3 files changed, 21 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d9293402ee68..b401a1892dc6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -74,11 +74,6 @@ static struct tracer_opt dummy_tracer_opt[] = { { } }; -static struct tracer_flags dummy_tracer_flags = { - .val = 0, - .opts = dummy_tracer_opt -}; - static int dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { @@ -1258,12 +1253,20 @@ int __init register_tracer(struct tracer *type) if (!type->set_flag) type->set_flag = &dummy_set_flag; - if (!type->flags) - type->flags = &dummy_tracer_flags; - else + if (!type->flags) { + /*allocate a dummy tracer_flags*/ + type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL); + if (!type->flags) + return -ENOMEM; + type->flags->val = 0; + type->flags->opts = dummy_tracer_opt; + } else if (!type->flags->opts) type->flags->opts = dummy_tracer_opt; + /* store the tracer for __set_tracer_option */ + type->flags->trace = type; + ret = run_tracer_selftest(type); if (ret < 0) goto out; @@ -3505,7 +3508,7 @@ static int __set_tracer_option(struct trace_array *tr, struct tracer_flags *tracer_flags, struct tracer_opt *opts, int neg) { - struct tracer *trace = tr->current_trace; + struct tracer *trace = tracer_flags->trace; int ret; ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg); @@ -6391,11 +6394,8 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer) return; for (i = 0; i < tr->nr_topts; i++) { - /* - * Check if these flags have already been added. - * Some tracers share flags. - */ - if (tr->topts[i].tracer->flags == tracer->flags) + /* Make sure there's no duplicate flags. */ + if (WARN_ON_ONCE(tr->topts[i].tracer->flags == tracer->flags)) return; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8414fa40bf27..b4cae47f283e 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -345,6 +345,7 @@ struct tracer_opt { struct tracer_flags { u32 val; struct tracer_opt *opts; + struct tracer *trace; }; /* Makes more easy to define a tracer opt */ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index fcd41a166405..5a095c2e4b69 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -219,6 +219,8 @@ static void tracing_stop_function_trace(struct trace_array *tr) unregister_ftrace_function(tr->ops); } +static struct tracer function_trace; + static int func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { @@ -228,6 +230,10 @@ func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK)) break; + /* We can change this flag when not running. */ + if (tr->current_trace != &function_trace) + break; + unregister_ftrace_function(tr->ops); if (set) { -- cgit v1.2.3 From 4ef56902fba4d9949918c6266e67ba7d05fba7a4 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:43 -0600 Subject: tracing: Make ftrace_event_field checking functions available Make is_string_field() and is_function_field() accessible outside of trace_event_filters.c for other users of ftrace_event_fields. Link: http://lkml.kernel.org/r/2d3f00d3311702e556e82eed7754bae6f017939f.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Reviewed-by: Masami Hiramatsu Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 12 ++++++++++++ kernel/trace/trace_events_filter.c | 12 ------------ 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b4cae47f283e..81a8359e9c29 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1112,6 +1112,18 @@ struct filter_pred { unsigned short right; }; +static inline bool is_string_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_STATIC_STRING || + field->filter_type == FILTER_PTR_STRING; +} + +static inline bool is_function_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_TRACE_FN; +} + extern enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not); extern void print_event_filter(struct trace_event_file *file, diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 6816302542b2..b3f5051cd4e9 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -961,18 +961,6 @@ int filter_assign_type(const char *type) return FILTER_OTHER; } -static bool is_function_field(struct ftrace_event_field *field) -{ - return field->filter_type == FILTER_TRACE_FN; -} - -static bool is_string_field(struct ftrace_event_field *field) -{ - return field->filter_type == FILTER_DYN_STRING || - field->filter_type == FILTER_STATIC_STRING || - field->filter_type == FILTER_PTR_STRING; -} - static bool is_legal_op(struct ftrace_event_field *field, int op) { if (is_string_field(field) && -- cgit v1.2.3 From ab4bf008928e8fc73fe1cbaa9249792d36845345 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:44 -0600 Subject: tracing: Make event trigger functions available Make various event trigger utility functions available outside of trace_events_trigger.c so that new triggers can be defined outside of that file. Link: http://lkml.kernel.org/r/4a40c1695dd43cac6cd475d72e13ffe30ba84bff.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 14 ++++++++++++++ kernel/trace/trace_events_trigger.c | 28 +++++++++++++--------------- 2 files changed, 27 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 81a8359e9c29..b2bc956e2b0d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1175,6 +1175,20 @@ struct event_trigger_data { struct list_head list; }; +extern void trigger_data_free(struct event_trigger_data *data); +extern int event_trigger_init(struct event_trigger_ops *ops, + struct event_trigger_data *data); +extern int trace_event_trigger_enable_disable(struct trace_event_file *file, + int trigger_enable); +extern void update_cond_flag(struct trace_event_file *file); +extern void unregister_trigger(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *test, + struct trace_event_file *file); +extern int set_trigger_filter(char *filter_str, + struct event_trigger_data *trigger_data, + struct trace_event_file *file); +extern int register_event_command(struct event_command *cmd); + /** * struct event_trigger_ops - callbacks for trace event triggers * diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index b38f617b6181..f40424f35dcb 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -28,8 +28,7 @@ static LIST_HEAD(trigger_commands); static DEFINE_MUTEX(trigger_cmd_mutex); -static void -trigger_data_free(struct event_trigger_data *data) +void trigger_data_free(struct event_trigger_data *data) { if (data->cmd_ops->set_filter) data->cmd_ops->set_filter(NULL, data, NULL); @@ -306,7 +305,7 @@ const struct file_operations event_trigger_fops = { * Currently we only register event commands from __init, so mark this * __init too. */ -static __init int register_event_command(struct event_command *cmd) +__init int register_event_command(struct event_command *cmd) { struct event_command *p; int ret = 0; @@ -395,9 +394,8 @@ event_trigger_print(const char *name, struct seq_file *m, * * Return: 0 on success, errno otherwise */ -static int -event_trigger_init(struct event_trigger_ops *ops, - struct event_trigger_data *data) +int event_trigger_init(struct event_trigger_ops *ops, + struct event_trigger_data *data) { data->ref++; return 0; @@ -425,8 +423,8 @@ event_trigger_free(struct event_trigger_ops *ops, trigger_data_free(data); } -static int trace_event_trigger_enable_disable(struct trace_event_file *file, - int trigger_enable) +int trace_event_trigger_enable_disable(struct trace_event_file *file, + int trigger_enable) { int ret = 0; @@ -483,7 +481,7 @@ clear_event_triggers(struct trace_array *tr) * its TRIGGER_COND bit set, otherwise the TRIGGER_COND bit should be * cleared. */ -static void update_cond_flag(struct trace_event_file *file) +void update_cond_flag(struct trace_event_file *file) { struct event_trigger_data *data; bool set_cond = false; @@ -560,9 +558,9 @@ out: * Usually used directly as the @unreg method in event command * implementations. */ -static void unregister_trigger(char *glob, struct event_trigger_ops *ops, - struct event_trigger_data *test, - struct trace_event_file *file) +void unregister_trigger(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *test, + struct trace_event_file *file) { struct event_trigger_data *data; bool unregistered = false; @@ -696,9 +694,9 @@ event_trigger_callback(struct event_command *cmd_ops, * * Return: 0 on success, errno otherwise */ -static int set_trigger_filter(char *filter_str, - struct event_trigger_data *trigger_data, - struct trace_event_file *file) +int set_trigger_filter(char *filter_str, + struct event_trigger_data *trigger_data, + struct trace_event_file *file) { struct event_trigger_data *data = trigger_data; struct event_filter *filter = NULL, *tmp; -- cgit v1.2.3 From c4a5923055c9e0c87dfc0387f7cda5ee2bbac3c1 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:45 -0600 Subject: tracing: Add event record param to trigger_ops.func() Some triggers may need access to the trace event, so pass it in. Also fix up the existing trigger funcs and their callers. Link: http://lkml.kernel.org/r/543e31e9fc445ef61077421ab219033401c39846.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- include/linux/trace_events.h | 7 ++++--- kernel/trace/trace.h | 6 ++++-- kernel/trace/trace_events_trigger.c | 36 +++++++++++++++++++----------------- 3 files changed, 27 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 925730bc9fc1..0d6930e941e8 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -430,7 +430,8 @@ extern int call_filter_check_discard(struct trace_event_call *call, void *rec, extern enum event_trigger_type event_triggers_call(struct trace_event_file *file, void *rec); extern void event_triggers_post_call(struct trace_event_file *file, - enum event_trigger_type tt); + enum event_trigger_type tt, + void *rec); bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); @@ -517,7 +518,7 @@ event_trigger_unlock_commit(struct trace_event_file *file, trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc); if (tt) - event_triggers_post_call(file, tt); + event_triggers_post_call(file, tt, entry); } /** @@ -550,7 +551,7 @@ event_trigger_unlock_commit_regs(struct trace_event_file *file, irq_flags, pc, regs); if (tt) - event_triggers_post_call(file, tt); + event_triggers_post_call(file, tt, entry); } #ifdef CONFIG_BPF_EVENTS diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b2bc956e2b0d..c10456e72106 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1201,7 +1201,8 @@ extern int register_event_command(struct event_command *cmd); * @func: The trigger 'probe' function called when the triggering * event occurs. The data passed into this callback is the data * that was supplied to the event_command @reg() function that - * registered the trigger (see struct event_command). + * registered the trigger (see struct event_command) along with + * the trace record, rec. * * @init: An optional initialization function called for the trigger * when the trigger is registered (via the event_command reg() @@ -1226,7 +1227,8 @@ extern int register_event_command(struct event_command *cmd); * (see trace_event_triggers.c). */ struct event_trigger_ops { - void (*func)(struct event_trigger_data *data); + void (*func)(struct event_trigger_data *data, + void *rec); int (*init)(struct event_trigger_ops *ops, struct event_trigger_data *data); void (*free)(struct event_trigger_ops *ops, diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index f40424f35dcb..0a62887c63c0 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -73,7 +73,7 @@ event_triggers_call(struct trace_event_file *file, void *rec) list_for_each_entry_rcu(data, &file->triggers, list) { if (!rec) { - data->ops->func(data); + data->ops->func(data, rec); continue; } filter = rcu_dereference_sched(data->filter); @@ -83,7 +83,7 @@ event_triggers_call(struct trace_event_file *file, void *rec) tt |= data->cmd_ops->trigger_type; continue; } - data->ops->func(data); + data->ops->func(data, rec); } return tt; } @@ -93,6 +93,7 @@ EXPORT_SYMBOL_GPL(event_triggers_call); * event_triggers_post_call - Call 'post_triggers' for a trace event * @file: The trace_event_file associated with the event * @tt: enum event_trigger_type containing a set bit for each trigger to invoke + * @rec: The trace entry for the event * * For each trigger associated with an event, invoke the trigger * function registered with the associated trigger command, if the @@ -103,13 +104,14 @@ EXPORT_SYMBOL_GPL(event_triggers_call); */ void event_triggers_post_call(struct trace_event_file *file, - enum event_trigger_type tt) + enum event_trigger_type tt, + void *rec) { struct event_trigger_data *data; list_for_each_entry_rcu(data, &file->triggers, list) { if (data->cmd_ops->trigger_type & tt) - data->ops->func(data); + data->ops->func(data, rec); } } EXPORT_SYMBOL_GPL(event_triggers_post_call); @@ -745,7 +747,7 @@ int set_trigger_filter(char *filter_str, } static void -traceon_trigger(struct event_trigger_data *data) +traceon_trigger(struct event_trigger_data *data, void *rec) { if (tracing_is_on()) return; @@ -754,7 +756,7 @@ traceon_trigger(struct event_trigger_data *data) } static void -traceon_count_trigger(struct event_trigger_data *data) +traceon_count_trigger(struct event_trigger_data *data, void *rec) { if (tracing_is_on()) return; @@ -769,7 +771,7 @@ traceon_count_trigger(struct event_trigger_data *data) } static void -traceoff_trigger(struct event_trigger_data *data) +traceoff_trigger(struct event_trigger_data *data, void *rec) { if (!tracing_is_on()) return; @@ -778,7 +780,7 @@ traceoff_trigger(struct event_trigger_data *data) } static void -traceoff_count_trigger(struct event_trigger_data *data) +traceoff_count_trigger(struct event_trigger_data *data, void *rec) { if (!tracing_is_on()) return; @@ -874,13 +876,13 @@ static struct event_command trigger_traceoff_cmd = { #ifdef CONFIG_TRACER_SNAPSHOT static void -snapshot_trigger(struct event_trigger_data *data) +snapshot_trigger(struct event_trigger_data *data, void *rec) { tracing_snapshot(); } static void -snapshot_count_trigger(struct event_trigger_data *data) +snapshot_count_trigger(struct event_trigger_data *data, void *rec) { if (!data->count) return; @@ -888,7 +890,7 @@ snapshot_count_trigger(struct event_trigger_data *data) if (data->count != -1) (data->count)--; - snapshot_trigger(data); + snapshot_trigger(data, rec); } static int @@ -967,13 +969,13 @@ static __init int register_trigger_snapshot_cmd(void) { return 0; } #define STACK_SKIP 3 static void -stacktrace_trigger(struct event_trigger_data *data) +stacktrace_trigger(struct event_trigger_data *data, void *rec) { trace_dump_stack(STACK_SKIP); } static void -stacktrace_count_trigger(struct event_trigger_data *data) +stacktrace_count_trigger(struct event_trigger_data *data, void *rec) { if (!data->count) return; @@ -981,7 +983,7 @@ stacktrace_count_trigger(struct event_trigger_data *data) if (data->count != -1) (data->count)--; - stacktrace_trigger(data); + stacktrace_trigger(data, rec); } static int @@ -1052,7 +1054,7 @@ struct enable_trigger_data { }; static void -event_enable_trigger(struct event_trigger_data *data) +event_enable_trigger(struct event_trigger_data *data, void *rec) { struct enable_trigger_data *enable_data = data->private_data; @@ -1063,7 +1065,7 @@ event_enable_trigger(struct event_trigger_data *data) } static void -event_enable_count_trigger(struct event_trigger_data *data) +event_enable_count_trigger(struct event_trigger_data *data, void *rec) { struct enable_trigger_data *enable_data = data->private_data; @@ -1077,7 +1079,7 @@ event_enable_count_trigger(struct event_trigger_data *data) if (data->count != -1) (data->count)--; - event_enable_trigger(data); + event_enable_trigger(data, rec); } static int -- cgit v1.2.3 From dbfeaa7abae4f105afdf8ed4f85b5879cff136ea Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:46 -0600 Subject: tracing: Add get_syscall_name() Add a utility function to grab the syscall name from the syscall metadata, given a syscall id. Link: http://lkml.kernel.org/r/be26a8dfe3f15e16a837799f1c1e2b4d62742843.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 5 +++++ kernel/trace/trace_syscalls.c | 11 +++++++++++ 2 files changed, 16 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c10456e72106..0044b91d5469 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1394,8 +1394,13 @@ int perf_ftrace_event_register(struct trace_event_call *call, #ifdef CONFIG_FTRACE_SYSCALLS void init_ftrace_syscalls(void); +const char *get_syscall_name(int syscall); #else static inline void init_ftrace_syscalls(void) { } +static inline const char *get_syscall_name(int syscall) +{ + return NULL; +} #endif #ifdef CONFIG_EVENT_TRACING diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 0655afbea83f..50be5602217c 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -106,6 +106,17 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr) return syscalls_metadata[nr]; } +const char *get_syscall_name(int syscall) +{ + struct syscall_metadata *entry; + + entry = syscall_nr_to_meta(syscall); + if (!entry) + return NULL; + + return entry->name; +} + static enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags, struct trace_event *event) -- cgit v1.2.3 From 104f281044a9c2ac86b851bbebbf74500172b625 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:47 -0600 Subject: tracing: Add a per-event-trigger 'paused' field Add a simple per-trigger 'paused' flag, allowing individual triggers to pause. We could leave it to individual triggers that need this functionality to do it themselves, but we also want to allow other events to control pausing, so add it to the trigger data. Link: http://lkml.kernel.org/r/fed37e4879684d7dcc57fe00ce0cbf170032b06d.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 1 + kernel/trace/trace_events_trigger.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0044b91d5469..f1868677f856 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1172,6 +1172,7 @@ struct event_trigger_data { struct event_filter __rcu *filter; char *filter_str; void *private_data; + bool paused; struct list_head list; }; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 0a62887c63c0..e4d8b3763175 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -72,6 +72,8 @@ event_triggers_call(struct trace_event_file *file, void *rec) return tt; list_for_each_entry_rcu(data, &file->triggers, list) { + if (data->paused) + continue; if (!rec) { data->ops->func(data, rec); continue; @@ -110,6 +112,8 @@ event_triggers_post_call(struct trace_event_file *file, struct event_trigger_data *data; list_for_each_entry_rcu(data, &file->triggers, list) { + if (data->paused) + continue; if (data->cmd_ops->trigger_type & tt) data->ops->func(data, rec); } -- cgit v1.2.3 From a5863dae84e2da83a1e5de485a7f150d0c28f08e Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:48 -0600 Subject: tracing: Add needs_rec flag to event triggers Add a new needs_rec flag for triggers that require unconditional access to trace records in order to function. Normally a trigger requires access to the contents of a trace record only if it has a filter associated with it (since filters need the contents of a record in order to make a filtering decision). Some types of triggers, such as 'hist' triggers, require access to trace record contents independent of the presence of filters, so add a new flag for those triggers. Link: http://lkml.kernel.org/r/7be8fa38f9b90fdb6c47ca0f98d20a07b9fd512b.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 7 +++++++ kernel/trace/trace_events_trigger.c | 3 ++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f1868677f856..8c6aefbb24d2 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1292,6 +1292,12 @@ struct event_trigger_ops { * itself logs to the trace buffer, this flag should be set, * otherwise it can be left unspecified. * + * @needs_rec: A flag that says whether or not this command needs + * access to the trace record in order to perform its function, + * regardless of whether or not it has a filter associated with + * it (filters make a trigger require access to the trace record + * but are not always present). + * * All the methods below, except for @set_filter(), must be * implemented. * @@ -1332,6 +1338,7 @@ struct event_command { char *name; enum event_trigger_type trigger_type; bool post_trigger; + bool needs_rec; int (*func)(struct event_command *cmd_ops, struct trace_event_file *file, char *glob, char *cmd, char *params); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index e4d8b3763175..a11bb4780f82 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -493,7 +493,8 @@ void update_cond_flag(struct trace_event_file *file) bool set_cond = false; list_for_each_entry_rcu(data, &file->triggers, list) { - if (data->filter || data->cmd_ops->post_trigger) { + if (data->filter || data->cmd_ops->post_trigger || + data->cmd_ops->needs_rec) { set_cond = true; break; } -- cgit v1.2.3 From a88e1cfb1d3081ffb34864d9cf8a5c289630f48e Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:49 -0600 Subject: tracing: Add an unreg_all() callback to trigger commands Add a new unreg_all() callback that can be used to remove all command-specific triggers from an event and arrange to have it called whenever a trigger file is opened with O_TRUNC set. Commands that don't want truncate semantics, or existing commands that don't implement this function simply do nothing and their triggers remain intact. Link: http://lkml.kernel.org/r/2b7d62854d01f28c19185e1bbb8f826f385edfba.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 9 +++++++-- kernel/trace/trace_events_trigger.c | 13 +++++++++++++ 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8c6aefbb24d2..f4dd0adf71df 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1298,8 +1298,8 @@ struct event_trigger_ops { * it (filters make a trigger require access to the trace record * but are not always present). * - * All the methods below, except for @set_filter(), must be - * implemented. + * All the methods below, except for @set_filter() and @unreg_all(), + * must be implemented. * * @func: The callback function responsible for parsing and * registering the trigger written to the 'trigger' file by the @@ -1324,6 +1324,10 @@ struct event_trigger_ops { * This is usually implemented by the generic utility function * @unregister_trigger() (see trace_event_triggers.c). * + * @unreg_all: An optional function called to remove all the triggers + * from the list of triggers associated with the event. Called + * when a trigger file is opened in truncate mode. + * * @set_filter: An optional function called to parse and set a filter * for the trigger. If no @set_filter() method is set for the * event command, filters set by the user for the command will be @@ -1350,6 +1354,7 @@ struct event_command { struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file); + void (*unreg_all)(struct trace_event_file *file); int (*set_filter)(char *filter_str, struct event_trigger_data *data, struct trace_event_file *file); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index a11bb4780f82..cbb7ee531983 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -193,6 +193,19 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) return -ENODEV; } + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) { + struct trace_event_file *event_file; + struct event_command *p; + + event_file = event_file_data(file); + + list_for_each_entry(p, &trigger_commands, list) { + if (p->unreg_all) + p->unreg_all(event_file); + } + } + if (file->f_mode & FMODE_READ) { ret = seq_open(file, &event_triggers_seq_ops); if (!ret) { -- cgit v1.2.3 From 353206f5ca05eb65704b2b3ec9a331b4fdfd3257 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 22 Feb 2016 15:55:09 -0500 Subject: tracing: Use flags instead of bool in trigger structure gcc isn't known for handling bool in structures. Instead of using bool, use an integer mask and use bit flags instead. Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 71 +++++++++++++++++++++++-------------- kernel/trace/trace_events_trigger.c | 8 ++--- 2 files changed, 49 insertions(+), 30 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f4dd0adf71df..39588c23dd8b 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1273,30 +1273,7 @@ struct event_trigger_ops { * values are defined by adding new values to the trigger_type * enum in include/linux/trace_events.h. * - * @post_trigger: A flag that says whether or not this command needs - * to have its action delayed until after the current event has - * been closed. Some triggers need to avoid being invoked while - * an event is currently in the process of being logged, since - * the trigger may itself log data into the trace buffer. Thus - * we make sure the current event is committed before invoking - * those triggers. To do that, the trigger invocation is split - * in two - the first part checks the filter using the current - * trace record; if a command has the @post_trigger flag set, it - * sets a bit for itself in the return value, otherwise it - * directly invokes the trigger. Once all commands have been - * either invoked or set their return flag, the current record is - * either committed or discarded. At that point, if any commands - * have deferred their triggers, those commands are finally - * invoked following the close of the current event. In other - * words, if the event_trigger_ops @func() probe implementation - * itself logs to the trace buffer, this flag should be set, - * otherwise it can be left unspecified. - * - * @needs_rec: A flag that says whether or not this command needs - * access to the trace record in order to perform its function, - * regardless of whether or not it has a filter associated with - * it (filters make a trigger require access to the trace record - * but are not always present). + * @flags: See the enum event_command_flags below. * * All the methods below, except for @set_filter() and @unreg_all(), * must be implemented. @@ -1341,8 +1318,7 @@ struct event_command { struct list_head list; char *name; enum event_trigger_type trigger_type; - bool post_trigger; - bool needs_rec; + int flags; int (*func)(struct event_command *cmd_ops, struct trace_event_file *file, char *glob, char *cmd, char *params); @@ -1361,6 +1337,49 @@ struct event_command { struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param); }; +/** + * enum event_command_flags - flags for struct event_command + * + * @POST_TRIGGER: A flag that says whether or not this command needs + * to have its action delayed until after the current event has + * been closed. Some triggers need to avoid being invoked while + * an event is currently in the process of being logged, since + * the trigger may itself log data into the trace buffer. Thus + * we make sure the current event is committed before invoking + * those triggers. To do that, the trigger invocation is split + * in two - the first part checks the filter using the current + * trace record; if a command has the @post_trigger flag set, it + * sets a bit for itself in the return value, otherwise it + * directly invokes the trigger. Once all commands have been + * either invoked or set their return flag, the current record is + * either committed or discarded. At that point, if any commands + * have deferred their triggers, those commands are finally + * invoked following the close of the current event. In other + * words, if the event_trigger_ops @func() probe implementation + * itself logs to the trace buffer, this flag should be set, + * otherwise it can be left unspecified. + * + * @NEEDS_REC: A flag that says whether or not this command needs + * access to the trace record in order to perform its function, + * regardless of whether or not it has a filter associated with + * it (filters make a trigger require access to the trace record + * but are not always present). + */ +enum event_command_flags { + EVENT_CMD_FL_POST_TRIGGER = 1, + EVENT_CMD_FL_NEEDS_REC = 2, +}; + +static inline bool event_command_post_trigger(struct event_command *cmd_ops) +{ + return cmd_ops->flags & EVENT_CMD_FL_POST_TRIGGER; +} + +static inline bool event_command_needs_rec(struct event_command *cmd_ops) +{ + return cmd_ops->flags & EVENT_CMD_FL_NEEDS_REC; +} + extern int trace_event_enable_disable(struct trace_event_file *file, int enable, int soft_disable); extern int tracing_alloc_snapshot(void); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index cbb7ee531983..d67992f3bb0e 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -81,7 +81,7 @@ event_triggers_call(struct trace_event_file *file, void *rec) filter = rcu_dereference_sched(data->filter); if (filter && !filter_match_preds(filter, rec)) continue; - if (data->cmd_ops->post_trigger) { + if (event_command_post_trigger(data->cmd_ops)) { tt |= data->cmd_ops->trigger_type; continue; } @@ -506,8 +506,8 @@ void update_cond_flag(struct trace_event_file *file) bool set_cond = false; list_for_each_entry_rcu(data, &file->triggers, list) { - if (data->filter || data->cmd_ops->post_trigger || - data->cmd_ops->needs_rec) { + if (data->filter || event_command_post_trigger(data->cmd_ops) || + event_command_needs_rec(data->cmd_ops)) { set_cond = true; break; } @@ -1035,7 +1035,7 @@ stacktrace_get_trigger_ops(char *cmd, char *param) static struct event_command trigger_stacktrace_cmd = { .name = "stacktrace", .trigger_type = ETT_STACKTRACE, - .post_trigger = true, + .flags = EVENT_CMD_FL_POST_TRIGGER, .func = event_trigger_callback, .reg = register_trigger, .unreg = unregister_trigger, -- cgit v1.2.3 From 1cf8067b541884366b7db3a328342073fed2f38f Mon Sep 17 00:00:00 2001 From: Chunyu Hu Date: Tue, 8 Mar 2016 21:37:02 +0800 Subject: tracing: Fix typoes in code comment and printk in trace_nop.c echo nop > /sys/kernel/debug/tracing/options/current_tracer echo 1 > /sys/kernel/debug/tracing/options/test_nop_accept echo 0 > /sys/kernel/debug/tracing/options/test_nop_accept echo 1 > /sys/kernel/debug/tracing/options/test_nop_refuse Before the fix, the dmesg is a bit ugly since a align issue. [ 191.973081] nop_test_accept flag set to 1: we accept. Now cat trace_options to see the result [ 195.156942] nop_test_refuse flag set to 1: we refuse.Now cat trace_options to see the result After the fix, the dmesg will show aligned log for nop_test_refuse and nop_test_accept. [ 2718.032413] nop_test_refuse flag set to 1: we refuse. Now cat trace_options to see the result [ 2734.253360] nop_test_accept flag set to 1: we accept. Now cat trace_options to see the result Link: http://lkml.kernel.org/r/1457444222-8654-2-git-send-email-chuhu@redhat.com Signed-off-by: Chunyu Hu Signed-off-by: Steven Rostedt --- kernel/trace/trace_nop.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c index 8bb2071474dd..49f61fe96a6b 100644 --- a/kernel/trace/trace_nop.c +++ b/kernel/trace/trace_nop.c @@ -56,7 +56,7 @@ static void nop_trace_reset(struct trace_array *tr) } /* It only serves as a signal handler and a callback to - * accept or refuse tthe setting of a flag. + * accept or refuse the setting of a flag. * If you don't implement it, then the flag setting will be * automatically accepted. */ @@ -75,7 +75,7 @@ static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) if (bit == TRACE_NOP_OPT_REFUSE) { printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse." - "Now cat trace_options to see the result\n", + " Now cat trace_options to see the result\n", set); return -EINVAL; } -- cgit v1.2.3 From 58cdb1ceb15aab7b34719ad225ff023775d774e7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Mar 2016 11:51:25 -0500 Subject: cgroup: fix incorrect destination cgroup in cgroup_update_dfl_csses() cgroup_update_dfl_csses() should move each task in the subtree to self; however, it was incorrectly calling cgroup_migrate_add_src() with the root of the subtree as @dst_cgrp. Fortunately, cgroup_migrate_add_src() currently uses @dst_cgrp only to determine the hierarchy and the bug doesn't cause any actual breakages. Fix it. Signed-off-by: Tejun Heo --- kernel/cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c63fce0c5b24..50879aadcbd0 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2901,7 +2901,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) struct cgrp_cset_link *link; list_for_each_entry(link, &dsct->cset_links, cset_link) - cgroup_migrate_add_src(link->cset, cgrp, + cgroup_migrate_add_src(link->cset, dsct, &preloaded_csets); } spin_unlock_bh(&css_set_lock); -- cgit v1.2.3 From 6c694c88255b2052d9922d62df6df7c9e152eeeb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Mar 2016 11:51:25 -0500 Subject: cgroup: move migration destination verification out of cgroup_migrate_prepare_dst() cgroup_migrate_prepare_dst() verifies whether the destination cgroup is allowable; however, the test doesn't really belong there. It's too deep and common in the stack and as a result the test itself is gated by another test. Separate the test out into cgroup_may_migrate_to() and update cgroup_attach_task() and cgroup_transfer_tasks() to perform the test directly. This doesn't cause any behavior differences. Signed-off-by: Tejun Heo --- kernel/cgroup.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 50879aadcbd0..8a02076d4317 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2443,6 +2443,20 @@ out_release_tset: return ret; } +/** + * cgroup_may_migrate_to - verify whether a cgroup can be migration destination + * @dst_cgrp: destination cgroup to test + * + * On the default hierarchy, except for the root, subtree_control must be + * zero for migration destination cgroups with tasks so that child cgroups + * don't compete against tasks. + */ +static bool cgroup_may_migrate_to(struct cgroup *dst_cgrp) +{ + return !cgroup_on_dfl(dst_cgrp) || !cgroup_parent(dst_cgrp) || + !dst_cgrp->subtree_control; +} + /** * cgroup_migrate_finish - cleanup after attach * @preloaded_csets: list of preloaded css_sets @@ -2529,14 +2543,6 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp, lockdep_assert_held(&cgroup_mutex); - /* - * Except for the root, subtree_control must be zero for a cgroup - * with tasks so that child cgroups don't compete against tasks. - */ - if (dst_cgrp && cgroup_on_dfl(dst_cgrp) && cgroup_parent(dst_cgrp) && - dst_cgrp->subtree_control) - return -EBUSY; - /* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, preloaded_csets, mg_preload_node) { struct css_set *dst_cset; @@ -2634,6 +2640,9 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *task; int ret; + if (!cgroup_may_migrate_to(dst_cgrp)) + return -EBUSY; + /* look up all src csets */ spin_lock_bh(&css_set_lock); rcu_read_lock(); @@ -4136,6 +4145,9 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) struct task_struct *task; int ret; + if (!cgroup_may_migrate_to(to)) + return -EBUSY; + mutex_lock(&cgroup_mutex); /* all tasks in @from are being moved, all csets are source */ -- cgit v1.2.3 From 37ff9f8f474216d0cfca7565a4e0caa521ee6e7e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Mar 2016 11:51:26 -0500 Subject: cgroup: make cgroup[_taskset]_migrate() take cgroup_root instead of cgroup On the default hierarchy, a migration can be multi-source and/or multi-destination. cgroup_taskest_migrate() used to incorrectly assume single destination cgroup but the bug has been fixed by 1f7dd3e5a6e4 ("cgroup: fix handling of multi-destination migration from subtree_control enabling"). Since the commit, @dst_cgrp to cgroup[_taskset]_migrate() is only used to determine which subsystems are affected or which cgroup_root the migration is taking place in. As such, @dst_cgrp is misleading. This patch replaces @dst_cgrp with @root. Signed-off-by: Tejun Heo --- kernel/cgroup.c | 70 ++++++++++++++++++++++++++++----------------------------- 1 file changed, 35 insertions(+), 35 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 8a02076d4317..5dd761355033 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2355,38 +2355,38 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, } /** - * cgroup_taskset_migrate - migrate a taskset to a cgroup + * cgroup_taskset_migrate - migrate a taskset * @tset: taget taskset - * @dst_cgrp: destination cgroup + * @root: cgroup root the migration is taking place on * - * Migrate tasks in @tset to @dst_cgrp. This function fails iff one of the - * ->can_attach callbacks fails and guarantees that either all or none of - * the tasks in @tset are migrated. @tset is consumed regardless of - * success. + * Migrate tasks in @tset as setup by migration preparation functions. + * This function fails iff one of the ->can_attach callbacks fails and + * guarantees that either all or none of the tasks in @tset are migrated. + * @tset is consumed regardless of success. */ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, - struct cgroup *dst_cgrp) + struct cgroup_root *root) { - struct cgroup_subsys_state *css, *failed_css = NULL; + struct cgroup_subsys *ss; struct task_struct *task, *tmp_task; struct css_set *cset, *tmp_cset; - int i, ret; + int ssid, failed_ssid, ret; /* methods shouldn't be called if no task is actually migrating */ if (list_empty(&tset->src_csets)) return 0; /* check that we can legitimately attach to the cgroup */ - for_each_e_css(css, i, dst_cgrp) { - if (css->ss->can_attach) { - tset->ssid = i; - ret = css->ss->can_attach(tset); + do_each_subsys_mask(ss, ssid, root->subsys_mask) { + if (ss->can_attach) { + tset->ssid = ssid; + ret = ss->can_attach(tset); if (ret) { - failed_css = css; + failed_ssid = ssid; goto out_cancel_attach; } } - } + } while_each_subsys_mask(); /* * Now that we're guaranteed success, proceed to move all tasks to @@ -2413,25 +2413,25 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, */ tset->csets = &tset->dst_csets; - for_each_e_css(css, i, dst_cgrp) { - if (css->ss->attach) { - tset->ssid = i; - css->ss->attach(tset); + do_each_subsys_mask(ss, ssid, root->subsys_mask) { + if (ss->attach) { + tset->ssid = ssid; + ss->attach(tset); } - } + } while_each_subsys_mask(); ret = 0; goto out_release_tset; out_cancel_attach: - for_each_e_css(css, i, dst_cgrp) { - if (css == failed_css) + do_each_subsys_mask(ss, ssid, root->subsys_mask) { + if (ssid == failed_ssid) break; - if (css->ss->cancel_attach) { - tset->ssid = i; - css->ss->cancel_attach(tset); + if (ss->cancel_attach) { + tset->ssid = ssid; + ss->cancel_attach(tset); } - } + } while_each_subsys_mask(); out_release_tset: spin_lock_bh(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); @@ -2586,11 +2586,11 @@ err: * cgroup_migrate - migrate a process or task to a cgroup * @leader: the leader of the process or the task to migrate * @threadgroup: whether @leader points to the whole process or a single task - * @cgrp: the destination cgroup + * @root: cgroup root migration is taking place on * - * Migrate a process or task denoted by @leader to @cgrp. If migrating a - * process, the caller must be holding cgroup_threadgroup_rwsem. The - * caller is also responsible for invoking cgroup_migrate_add_src() and + * Migrate a process or task denoted by @leader. If migrating a process, + * the caller must be holding cgroup_threadgroup_rwsem. The caller is also + * responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). * @@ -2601,7 +2601,7 @@ err: * actually starting migrating. */ static int cgroup_migrate(struct task_struct *leader, bool threadgroup, - struct cgroup *cgrp) + struct cgroup_root *root) { struct cgroup_taskset tset = CGROUP_TASKSET_INIT(tset); struct task_struct *task; @@ -2622,7 +2622,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup, rcu_read_unlock(); spin_unlock_bh(&css_set_lock); - return cgroup_taskset_migrate(&tset, cgrp); + return cgroup_taskset_migrate(&tset, root); } /** @@ -2659,7 +2659,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, /* prepare dst csets and commit */ ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets); if (!ret) - ret = cgroup_migrate(leader, threadgroup, dst_cgrp); + ret = cgroup_migrate(leader, threadgroup, dst_cgrp->root); cgroup_migrate_finish(&preloaded_csets); return ret; @@ -2934,7 +2934,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) } spin_unlock_bh(&css_set_lock); - ret = cgroup_taskset_migrate(&tset, cgrp); + ret = cgroup_taskset_migrate(&tset, cgrp->root); out_finish: cgroup_migrate_finish(&preloaded_csets); percpu_up_write(&cgroup_threadgroup_rwsem); @@ -4172,7 +4172,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) css_task_iter_end(&it); if (task) { - ret = cgroup_migrate(task, false, to); + ret = cgroup_migrate(task, false, to->root); put_task_struct(task); } } while (task && !ret); -- cgit v1.2.3 From e4857982f49d21c05a84351b56724bf353022355 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Mar 2016 11:51:26 -0500 Subject: cgroup: use css_set->mg_dst_cgrp for the migration target cgroup Migration can be multi-target on the default hierarchy when a controller is enabled - processes belonging to each child cgroup have to be moved to the child cgroup itself to refresh css association. This isn't a problem for cgroup_migrate_add_src() as each source css_set still maps to single source and target cgroups; however, cgroup_migrate_prepare_dst() is called once after all source css_sets are added and thus might not have a single destination cgroup. This is currently worked around by specifying NULL for @dst_cgrp and using the source's default cgroup as destination as the only multi-target migration in use is self-targetting. While this works, it's subtle and clunky. As all taget cgroups are already specified while preparing the source css_sets, this clunkiness can easily be removed by recording the target cgroup in each source css_set. This patch adds css_set->mg_dst_cgrp which is recorded on cgroup_migrate_src() and used by cgroup_migrate_prepare_dst(). This also makes migration code ready for arbitrary multi-target migration. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 9 +++++---- kernel/cgroup.c | 26 +++++++++++++------------- 2 files changed, 18 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index aae8c94de4b3..590291d56049 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -191,12 +191,13 @@ struct css_set { /* * If this cset is acting as the source of migration the following - * two fields are set. mg_src_cgrp is the source cgroup of the - * on-going migration and mg_dst_cset is the destination cset the - * target tasks on this cset should be migrated to. Protected by - * cgroup_mutex. + * two fields are set. mg_src_cgrp and mg_dst_cgrp are + * respectively the source and destination cgroups of the on-going + * migration. mg_dst_cset is the destination cset the target tasks + * on this cset should be migrated to. Protected by cgroup_mutex. */ struct cgroup *mg_src_cgrp; + struct cgroup *mg_dst_cgrp; struct css_set *mg_dst_cset; /* diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 5dd761355033..fbd3e99a4e98 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2473,6 +2473,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) spin_lock_bh(&css_set_lock); list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) { cset->mg_src_cgrp = NULL; + cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_preload_node); put_css_set_locked(cset); @@ -2511,32 +2512,31 @@ static void cgroup_migrate_add_src(struct css_set *src_cset, return; WARN_ON(src_cset->mg_src_cgrp); + WARN_ON(src_cset->mg_dst_cgrp); WARN_ON(!list_empty(&src_cset->mg_tasks)); WARN_ON(!list_empty(&src_cset->mg_node)); src_cset->mg_src_cgrp = src_cgrp; + src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); list_add(&src_cset->mg_preload_node, preloaded_csets); } /** * cgroup_migrate_prepare_dst - prepare destination css_sets for migration - * @dst_cgrp: the destination cgroup (may be %NULL) * @preloaded_csets: list of preloaded source css_sets * - * Tasks are about to be moved to @dst_cgrp and all the source css_sets - * have been preloaded to @preloaded_csets. This function looks up and - * pins all destination css_sets, links each to its source, and append them - * to @preloaded_csets. If @dst_cgrp is %NULL, the destination of each - * source css_set is assumed to be its cgroup on the default hierarchy. + * Tasks are about to be moved and all the source css_sets have been + * preloaded to @preloaded_csets. This function looks up and pins all + * destination css_sets, links each to its source, and append them to + * @preloaded_csets. * * This function must be called after cgroup_migrate_add_src() has been * called on each migration source css_set. After migration is performed * using cgroup_migrate(), cgroup_migrate_finish() must be called on * @preloaded_csets. */ -static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp, - struct list_head *preloaded_csets) +static int cgroup_migrate_prepare_dst(struct list_head *preloaded_csets) { LIST_HEAD(csets); struct css_set *src_cset, *tmp_cset; @@ -2547,8 +2547,7 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp, list_for_each_entry_safe(src_cset, tmp_cset, preloaded_csets, mg_preload_node) { struct css_set *dst_cset; - dst_cset = find_css_set(src_cset, - dst_cgrp ?: src_cset->dfl_cgrp); + dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp); if (!dst_cset) goto err; @@ -2561,6 +2560,7 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp, */ if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; + src_cset->mg_dst_cgrp = NULL; list_del_init(&src_cset->mg_preload_node); put_css_set(src_cset); put_css_set(dst_cset); @@ -2657,7 +2657,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, spin_unlock_bh(&css_set_lock); /* prepare dst csets and commit */ - ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets); + ret = cgroup_migrate_prepare_dst(&preloaded_csets); if (!ret) ret = cgroup_migrate(leader, threadgroup, dst_cgrp->root); @@ -2916,7 +2916,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) spin_unlock_bh(&css_set_lock); /* NULL dst indicates self on default hierarchy */ - ret = cgroup_migrate_prepare_dst(NULL, &preloaded_csets); + ret = cgroup_migrate_prepare_dst(&preloaded_csets); if (ret) goto out_finish; @@ -4156,7 +4156,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) cgroup_migrate_add_src(link->cset, to, &preloaded_csets); spin_unlock_bh(&css_set_lock); - ret = cgroup_migrate_prepare_dst(to, &preloaded_csets); + ret = cgroup_migrate_prepare_dst(&preloaded_csets); if (ret) goto out_err; -- cgit v1.2.3 From f6d635ad341d5cc0b9c7ab46adfbf3bf5886cee4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Mar 2016 11:51:26 -0500 Subject: cgroup: implement cgroup_subsys->implicit_on_dfl Some controllers, perf_event for now and possibly freezer in the future, don't really make sense to control explicitly through "cgroup.subtree_control". For example, the primary role of perf_event is identifying the cgroups of tasks; however, because the controller also keeps a small amount of state per cgroup, it can't be replaced with simple cgroup membership tests. This patch implements cgroup_subsys->implicit_on_dfl flag. When set, the controller is implicitly enabled on all cgroups on the v2 hierarchy so that utility type controllers such as perf_event can be enabled and function transparently. An implicit controller doesn't show up in "cgroup.controllers" or "cgroup.subtree_control", is exempt from no internal process rule and can be stolen from the default hierarchy even if there are non-root csses. v2: Reimplemented on top of the recent updates to css handling and subsystem rebinding. Rebinding implicit subsystems is now a simple matter of exempting it from the busy subsystem check. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 13 +++++++++++++ kernel/cgroup.c | 38 +++++++++++++++++++++++++++++++------- 2 files changed, 44 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 590291d56049..34b42f03fcd8 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -450,6 +450,19 @@ struct cgroup_subsys { bool early_init:1; + /* + * If %true, the controller, on the default hierarchy, doesn't show + * up in "cgroup.controllers" or "cgroup.subtree_control", is + * implicitly enabled on all cgroups on the default hierarchy, and + * bypasses the "no internal process" constraint. This is for + * utility type controllers which is transparent to userland. + * + * An implicit controller can be stolen from the default hierarchy + * anytime and thus must be okay with offline csses from previous + * hierarchies coexisting with csses for the current one. + */ + bool implicit_on_dfl:1; + /* * If %false, this subsystem is properly hierarchical - * configuration, resource accounting and restriction on a parent diff --git a/kernel/cgroup.c b/kernel/cgroup.c index fbd3e99a4e98..e22df5d81e59 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -186,6 +186,9 @@ static u16 cgroup_no_v1_mask; /* some controllers are not supported in the default hierarchy */ static u16 cgrp_dfl_inhibit_ss_mask; +/* some controllers are implicitly enabled on the default hierarchy */ +static unsigned long cgrp_dfl_implicit_ss_mask; + /* The list of hierarchy roots */ static LIST_HEAD(cgroup_roots); @@ -359,8 +362,8 @@ static u16 cgroup_control(struct cgroup *cgrp) return parent->subtree_control; if (cgroup_on_dfl(cgrp)) - root_ss_mask &= ~cgrp_dfl_inhibit_ss_mask; - + root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask | + cgrp_dfl_implicit_ss_mask); return root_ss_mask; } @@ -1327,6 +1330,8 @@ static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask) lockdep_assert_held(&cgroup_mutex); + cur_ss_mask |= cgrp_dfl_implicit_ss_mask; + while (true) { u16 new_ss_mask = cur_ss_mask; @@ -1512,8 +1517,13 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) lockdep_assert_held(&cgroup_mutex); do_each_subsys_mask(ss, ssid, ss_mask) { - /* if @ss has non-root csses attached to it, can't move */ - if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss))) + /* + * If @ss has non-root csses attached to it, can't move. + * If @ss is an implicit controller, it is exempt from this + * rule and can be stolen. + */ + if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) && + !ss->implicit_on_dfl) return -EBUSY; /* can't move between two non-dummy roots either */ @@ -3039,6 +3049,18 @@ static void cgroup_restore_control(struct cgroup *cgrp) } } +static bool css_visible(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + + if (cgroup_control(cgrp) & (1 << ss->id)) + return true; + if (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) + return false; + return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl; +} + /** * cgroup_apply_control_enable - enable or show csses according to control * @cgrp: root of the target subtree @@ -3074,7 +3096,7 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp) return PTR_ERR(css); } - if (cgroup_control(dsct) & (1 << ss->id)) { + if (css_visible(css)) { ret = css_populate_dir(css); if (ret) return ret; @@ -3117,7 +3139,7 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp) if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css(css); - } else if (!(cgroup_control(dsct) & (1 << ss->id))) { + } else if (!css_visible(css)) { css_clear_dir(css); if (ss->css_reset) ss->css_reset(css); @@ -5455,7 +5477,9 @@ int __init cgroup_init(void) cgrp_dfl_root.subsys_mask |= 1 << ss->id; - if (!ss->dfl_cftypes) + if (ss->implicit_on_dfl) + cgrp_dfl_implicit_ss_mask |= 1 << ss->id; + else if (!ss->dfl_cftypes) cgrp_dfl_inhibit_ss_mask |= 1 << ss->id; if (ss->dfl_cftypes == ss->legacy_cftypes) { -- cgit v1.2.3 From b121d1e74d1f24654bdc3165d3db1ca149501356 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:13 -0800 Subject: bpf: prevent kprobe+bpf deadlocks if kprobe is placed within update or delete hash map helpers that hold bucket spin lock and triggered bpf program is trying to grab the spinlock for the same bucket on the same cpu, it will deadlock. Fix it by extending existing recursion prevention mechanism. Note, map_lookup and other tracing helpers don't have this problem, since they don't hold any locks and don't modify global data. bpf_trace_printk has its own recursive check and ok as well. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 3 +++ kernel/bpf/syscall.c | 13 +++++++++++++ kernel/trace/bpf_trace.c | 2 -- 3 files changed, 16 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 51e498e5470e..4b070827200d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -10,6 +10,7 @@ #include #include #include +#include struct bpf_map; @@ -163,6 +164,8 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f const struct bpf_func_proto *bpf_get_trace_printk_proto(void); #ifdef CONFIG_BPF_SYSCALL +DECLARE_PER_CPU(int, bpf_prog_active); + void bpf_register_prog_type(struct bpf_prog_type_list *tl); void bpf_register_map_type(struct bpf_map_type_list *tl); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c95a753c2007..dc99f6a000f5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -18,6 +18,8 @@ #include #include +DEFINE_PER_CPU(int, bpf_prog_active); + int sysctl_unprivileged_bpf_disabled __read_mostly; static LIST_HEAD(bpf_map_types); @@ -347,6 +349,11 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from + * inside bpf map update or delete otherwise deadlocks are possible + */ + preempt_disable(); + __this_cpu_inc(bpf_prog_active); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { @@ -356,6 +363,8 @@ static int map_update_elem(union bpf_attr *attr) err = map->ops->map_update_elem(map, key, value, attr->flags); rcu_read_unlock(); } + __this_cpu_dec(bpf_prog_active); + preempt_enable(); free_value: kfree(value); @@ -394,9 +403,13 @@ static int map_delete_elem(union bpf_attr *attr) if (copy_from_user(key, ukey, map->key_size) != 0) goto free_key; + preempt_disable(); + __this_cpu_inc(bpf_prog_active); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); + __this_cpu_dec(bpf_prog_active); + preempt_enable(); free_key: kfree(key); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4b8caa392b86..3e4ffb3ace5f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -13,8 +13,6 @@ #include #include "trace.h" -static DEFINE_PER_CPU(int, bpf_prog_active); - /** * trace_call_bpf - invoke BPF program * @prog: BPF program -- cgit v1.2.3 From e19494edab82f55a633911f25094581891bdc351 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:14 -0800 Subject: bpf: introduce percpu_freelist Introduce simple percpu_freelist to keep single list of elements spread across per-cpu singly linked lists. /* push element into the list */ void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); /* pop element from the list */ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *); The object is pushed to the current cpu list. Pop first trying to get the object from the current cpu list, if it's empty goes to the neigbour cpu list. For bpf program usage pattern the collision rate is very low, since programs push and pop the objects typically on the same cpu. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/Makefile | 2 +- kernel/bpf/percpu_freelist.c | 100 +++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/percpu_freelist.h | 31 ++++++++++++++ 3 files changed, 132 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/percpu_freelist.c create mode 100644 kernel/bpf/percpu_freelist.h (limited to 'kernel') diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 8a932d079c24..eed911d091da 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,7 +1,7 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o -obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o +obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o endif diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c new file mode 100644 index 000000000000..5c51d1985b51 --- /dev/null +++ b/kernel/bpf/percpu_freelist.c @@ -0,0 +1,100 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include "percpu_freelist.h" + +int pcpu_freelist_init(struct pcpu_freelist *s) +{ + int cpu; + + s->freelist = alloc_percpu(struct pcpu_freelist_head); + if (!s->freelist) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct pcpu_freelist_head *head = per_cpu_ptr(s->freelist, cpu); + + raw_spin_lock_init(&head->lock); + head->first = NULL; + } + return 0; +} + +void pcpu_freelist_destroy(struct pcpu_freelist *s) +{ + free_percpu(s->freelist); +} + +static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, + struct pcpu_freelist_node *node) +{ + raw_spin_lock(&head->lock); + node->next = head->first; + head->first = node; + raw_spin_unlock(&head->lock); +} + +void pcpu_freelist_push(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist); + + __pcpu_freelist_push(head, node); +} + +void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, + u32 nr_elems) +{ + struct pcpu_freelist_head *head; + unsigned long flags; + int i, cpu, pcpu_entries; + + pcpu_entries = nr_elems / num_possible_cpus() + 1; + i = 0; + + /* disable irq to workaround lockdep false positive + * in bpf usage pcpu_freelist_populate() will never race + * with pcpu_freelist_push() + */ + local_irq_save(flags); + for_each_possible_cpu(cpu) { +again: + head = per_cpu_ptr(s->freelist, cpu); + __pcpu_freelist_push(head, buf); + i++; + buf += elem_size; + if (i == nr_elems) + break; + if (i % pcpu_entries) + goto again; + } + local_irq_restore(flags); +} + +struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +{ + struct pcpu_freelist_head *head; + struct pcpu_freelist_node *node; + int orig_cpu, cpu; + + orig_cpu = cpu = raw_smp_processor_id(); + while (1) { + head = per_cpu_ptr(s->freelist, cpu); + raw_spin_lock(&head->lock); + node = head->first; + if (node) { + head->first = node->next; + raw_spin_unlock(&head->lock); + return node; + } + raw_spin_unlock(&head->lock); + cpu = cpumask_next(cpu, cpu_possible_mask); + if (cpu >= nr_cpu_ids) + cpu = 0; + if (cpu == orig_cpu) + return NULL; + } +} diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h new file mode 100644 index 000000000000..3049aae8ea1e --- /dev/null +++ b/kernel/bpf/percpu_freelist.h @@ -0,0 +1,31 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef __PERCPU_FREELIST_H__ +#define __PERCPU_FREELIST_H__ +#include +#include + +struct pcpu_freelist_head { + struct pcpu_freelist_node *first; + raw_spinlock_t lock; +}; + +struct pcpu_freelist { + struct pcpu_freelist_head __percpu *freelist; +}; + +struct pcpu_freelist_node { + struct pcpu_freelist_node *next; +}; + +void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); +struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *); +void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, + u32 nr_elems); +int pcpu_freelist_init(struct pcpu_freelist *); +void pcpu_freelist_destroy(struct pcpu_freelist *s); +#endif -- cgit v1.2.3 From 6c90598174322b8888029e40dd84a4eb01f56afe Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:15 -0800 Subject: bpf: pre-allocate hash map elements If kprobe is placed on spin_unlock then calling kmalloc/kfree from bpf programs is not safe, since the following dead lock is possible: kfree->spin_lock(kmem_cache_node->lock)...spin_unlock->kprobe-> bpf_prog->map_update->kmalloc->spin_lock(of the same kmem_cache_node->lock) and deadlocks. The following solutions were considered and some implemented, but eventually discarded - kmem_cache_create for every map - add recursion check to slow-path of slub - use reserved memory in bpf_map_update for in_irq or in preempt_disabled - kmalloc via irq_work At the end pre-allocation of all map elements turned out to be the simplest solution and since the user is charged upfront for all the memory, such pre-allocation doesn't affect the user space visible behavior. Since it's impossible to tell whether kprobe is triggered in a safe location from kmalloc point of view, use pre-allocation by default and introduce new BPF_F_NO_PREALLOC flag. While testing of per-cpu hash maps it was discovered that alloc_percpu(GFP_ATOMIC) has odd corner cases and often fails to allocate memory even when 90% of it is free. The pre-allocation of per-cpu hash elements solves this problem as well. Turned out that bpf_map_update() quickly followed by bpf_map_lookup()+bpf_map_delete() is very common pattern used in many of iovisor/bcc/tools, so there is additional benefit of pre-allocation, since such use cases are must faster. Since all hash map elements are now pre-allocated we can remove atomic increment of htab->count and save few more cycles. Also add bpf_map_precharge_memlock() to check rlimit_memlock early to avoid large malloc/free done by users who don't have sufficient limits. Pre-allocation is done with vmalloc and alloc/free is done via percpu_freelist. Here are performance numbers for different pre-allocation algorithms that were implemented, but discarded in favor of percpu_freelist: 1 cpu: pcpu_ida 2.1M pcpu_ida nolock 2.3M bt 2.4M kmalloc 1.8M hlist+spinlock 2.3M pcpu_freelist 2.6M 4 cpu: pcpu_ida 1.5M pcpu_ida nolock 1.8M bt w/smp_align 1.7M bt no/smp_align 1.1M kmalloc 0.7M hlist+spinlock 0.2M pcpu_freelist 2.0M 8 cpu: pcpu_ida 0.7M bt w/smp_align 0.8M kmalloc 0.4M pcpu_freelist 1.5M 32 cpu: kmalloc 0.13M pcpu_freelist 0.49M pcpu_ida nolock is a modified percpu_ida algorithm without percpu_ida_cpu locks and without cross-cpu tag stealing. It's faster than existing percpu_ida, but not as fast as pcpu_freelist. bt is a variant of block/blk-mq-tag.c simlified and customized for bpf use case. bt w/smp_align is using cache line for every 'long' (similar to blk-mq-tag). bt no/smp_align allocates 'long' bitmasks continuously to save memory. It's comparable to percpu_ida and in some cases faster, but slower than percpu_freelist hlist+spinlock is the simplest free list with single spinlock. As expeceted it has very bad scaling in SMP. kmalloc is existing implementation which is still available via BPF_F_NO_PREALLOC flag. It's significantly slower in single cpu and in 8 cpu setup it's 3 times slower than pre-allocation with pcpu_freelist, but saves memory, so in cases where map->max_entries can be large and number of map update/delete per second is low, it may make sense to use it. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 + include/uapi/linux/bpf.h | 3 + kernel/bpf/hashtab.c | 240 +++++++++++++++++++++++++++++++++-------------- kernel/bpf/syscall.c | 15 ++- 4 files changed, 186 insertions(+), 74 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4b070827200d..efd1d4ca95c6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -37,6 +37,7 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; + u32 map_flags; u32 pages; struct user_struct *user; const struct bpf_map_ops *ops; @@ -178,6 +179,7 @@ struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); +int bpf_map_precharge_memlock(u32 pages); extern int sysctl_unprivileged_bpf_disabled; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9221f653fee3..0e30b19012a5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -101,12 +101,15 @@ enum bpf_prog_type { #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ +#define BPF_F_NO_PREALLOC (1U << 0) + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ __u32 key_size; /* size of key in bytes */ __u32 value_size; /* size of value in bytes */ __u32 max_entries; /* max number of entries in a map */ + __u32 map_flags; /* prealloc or not */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index a68e95133fcd..fff3650d52fc 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1,4 +1,5 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -13,6 +14,7 @@ #include #include #include +#include "percpu_freelist.h" struct bucket { struct hlist_head head; @@ -22,6 +24,8 @@ struct bucket { struct bpf_htab { struct bpf_map map; struct bucket *buckets; + void *elems; + struct pcpu_freelist freelist; atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ @@ -29,15 +33,86 @@ struct bpf_htab { /* each htab element is struct htab_elem + key + value */ struct htab_elem { - struct hlist_node hash_node; - struct rcu_head rcu; union { - u32 hash; - u32 key_size; + struct hlist_node hash_node; + struct bpf_htab *htab; + struct pcpu_freelist_node fnode; }; + struct rcu_head rcu; + u32 hash; char key[0] __aligned(8); }; +static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, + void __percpu *pptr) +{ + *(void __percpu **)(l->key + key_size) = pptr; +} + +static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size) +{ + return *(void __percpu **)(l->key + key_size); +} + +static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i) +{ + return (struct htab_elem *) (htab->elems + i * htab->elem_size); +} + +static void htab_free_elems(struct bpf_htab *htab) +{ + int i; + + if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH) + goto free_elems; + + for (i = 0; i < htab->map.max_entries; i++) { + void __percpu *pptr; + + pptr = htab_elem_get_ptr(get_htab_elem(htab, i), + htab->map.key_size); + free_percpu(pptr); + } +free_elems: + vfree(htab->elems); +} + +static int prealloc_elems_and_freelist(struct bpf_htab *htab) +{ + int err = -ENOMEM, i; + + htab->elems = vzalloc(htab->elem_size * htab->map.max_entries); + if (!htab->elems) + return -ENOMEM; + + if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH) + goto skip_percpu_elems; + + for (i = 0; i < htab->map.max_entries; i++) { + u32 size = round_up(htab->map.value_size, 8); + void __percpu *pptr; + + pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN); + if (!pptr) + goto free_elems; + htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size, + pptr); + } + +skip_percpu_elems: + err = pcpu_freelist_init(&htab->freelist); + if (err) + goto free_elems; + + pcpu_freelist_populate(&htab->freelist, htab->elems, htab->elem_size, + htab->map.max_entries); + return 0; + +free_elems: + htab_free_elems(htab); + return err; +} + /* Called from syscall */ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { @@ -46,6 +121,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) int err, i; u64 cost; + if (attr->map_flags & ~BPF_F_NO_PREALLOC) + /* reserved bits should not be used */ + return ERR_PTR(-EINVAL); + htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) return ERR_PTR(-ENOMEM); @@ -55,6 +134,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->map.key_size = attr->key_size; htab->map.value_size = attr->value_size; htab->map.max_entries = attr->max_entries; + htab->map.map_flags = attr->map_flags; /* check sanity of attributes. * value_size == 0 may be allowed in the future to use map as a set @@ -92,7 +172,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (percpu) htab->elem_size += sizeof(void *); else - htab->elem_size += htab->map.value_size; + htab->elem_size += round_up(htab->map.value_size, 8); /* prevent zero size kmalloc and check for u32 overflow */ if (htab->n_buckets == 0 || @@ -112,6 +192,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + /* if map size is larger than memlock limit, reject it early */ + err = bpf_map_precharge_memlock(htab->map.pages); + if (err) + goto free_htab; + err = -ENOMEM; htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket), GFP_USER | __GFP_NOWARN); @@ -127,10 +212,16 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) raw_spin_lock_init(&htab->buckets[i].lock); } - atomic_set(&htab->count, 0); + if (!(attr->map_flags & BPF_F_NO_PREALLOC)) { + err = prealloc_elems_and_freelist(htab); + if (err) + goto free_buckets; + } return &htab->map; +free_buckets: + kvfree(htab->buckets); free_htab: kfree(htab); return ERR_PTR(err); @@ -249,42 +340,42 @@ find_first_elem: } } - /* itereated over all buckets and all elements */ + /* iterated over all buckets and all elements */ return -ENOENT; } - -static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, - void __percpu *pptr) -{ - *(void __percpu **)(l->key + key_size) = pptr; -} - -static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size) -{ - return *(void __percpu **)(l->key + key_size); -} - -static void htab_percpu_elem_free(struct htab_elem *l) +static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { - free_percpu(htab_elem_get_ptr(l, l->key_size)); + if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) + free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); kfree(l); + } -static void htab_percpu_elem_free_rcu(struct rcu_head *head) +static void htab_elem_free_rcu(struct rcu_head *head) { struct htab_elem *l = container_of(head, struct htab_elem, rcu); + struct bpf_htab *htab = l->htab; - htab_percpu_elem_free(l); + /* must increment bpf_prog_active to avoid kprobe+bpf triggering while + * we're calling kfree, otherwise deadlock is possible if kprobes + * are placed somewhere inside of slub + */ + preempt_disable(); + __this_cpu_inc(bpf_prog_active); + htab_elem_free(htab, l); + __this_cpu_dec(bpf_prog_active); + preempt_enable(); } -static void free_htab_elem(struct htab_elem *l, bool percpu, u32 key_size) +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { - if (percpu) { - l->key_size = key_size; - call_rcu(&l->rcu, htab_percpu_elem_free_rcu); + if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) { + pcpu_freelist_push(&htab->freelist, &l->fnode); } else { - kfree_rcu(l, rcu); + atomic_dec(&htab->count); + l->htab = htab; + call_rcu(&l->rcu, htab_elem_free_rcu); } } @@ -293,23 +384,39 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, bool percpu, bool onallcpus) { u32 size = htab->map.value_size; + bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC); struct htab_elem *l_new; void __percpu *pptr; - l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (!l_new) - return NULL; + if (prealloc) { + l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist); + if (!l_new) + return ERR_PTR(-E2BIG); + } else { + if (atomic_inc_return(&htab->count) > htab->map.max_entries) { + atomic_dec(&htab->count); + return ERR_PTR(-E2BIG); + } + l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (!l_new) + return ERR_PTR(-ENOMEM); + } memcpy(l_new->key, key, key_size); if (percpu) { /* round up value_size to 8 bytes */ size = round_up(size, 8); - /* alloc_percpu zero-fills */ - pptr = __alloc_percpu_gfp(size, 8, GFP_ATOMIC | __GFP_NOWARN); - if (!pptr) { - kfree(l_new); - return NULL; + if (prealloc) { + pptr = htab_elem_get_ptr(l_new, key_size); + } else { + /* alloc_percpu zero-fills */ + pptr = __alloc_percpu_gfp(size, 8, + GFP_ATOMIC | __GFP_NOWARN); + if (!pptr) { + kfree(l_new); + return ERR_PTR(-ENOMEM); + } } if (!onallcpus) { @@ -324,7 +431,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, off += size; } } - htab_elem_set_ptr(l_new, key_size, pptr); + if (!prealloc) + htab_elem_set_ptr(l_new, key_size, pptr); } else { memcpy(l_new->key + round_up(key_size, 8), value, size); } @@ -336,12 +444,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, u64 map_flags) { - if (!l_old && unlikely(atomic_read(&htab->count) >= htab->map.max_entries)) - /* if elem with this 'key' doesn't exist and we've reached - * max_entries limit, fail insertion of new elem - */ - return -E2BIG; - if (l_old && map_flags == BPF_NOEXIST) /* elem already exists */ return -EEXIST; @@ -375,13 +477,6 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, hash = htab_map_hash(key, key_size); - /* allocate new element outside of the lock, since - * we're most likley going to insert it - */ - l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); - if (!l_new) - return -ENOMEM; - b = __select_bucket(htab, hash); head = &b->head; @@ -394,21 +489,24 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (ret) goto err; + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); + if (IS_ERR(l_new)) { + /* all pre-allocated elements are in use or memory exhausted */ + ret = PTR_ERR(l_new); + goto err; + } + /* add new element to the head of the list, so that * concurrent search will find it before old elem */ hlist_add_head_rcu(&l_new->hash_node, head); if (l_old) { hlist_del_rcu(&l_old->hash_node); - kfree_rcu(l_old, rcu); - } else { - atomic_inc(&htab->count); + free_htab_elem(htab, l_old); } - raw_spin_unlock_irqrestore(&b->lock, flags); - return 0; + ret = 0; err: raw_spin_unlock_irqrestore(&b->lock, flags); - kfree(l_new); return ret; } @@ -466,12 +564,11 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, } else { l_new = alloc_htab_elem(htab, key, value, key_size, hash, true, onallcpus); - if (!l_new) { - ret = -ENOMEM; + if (IS_ERR(l_new)) { + ret = PTR_ERR(l_new); goto err; } hlist_add_head_rcu(&l_new->hash_node, head); - atomic_inc(&htab->count); } ret = 0; err: @@ -489,7 +586,6 @@ static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, static int htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - bool percpu = map->map_type == BPF_MAP_TYPE_PERCPU_HASH; struct hlist_head *head; struct bucket *b; struct htab_elem *l; @@ -511,8 +607,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) if (l) { hlist_del_rcu(&l->hash_node); - atomic_dec(&htab->count); - free_htab_elem(l, percpu, key_size); + free_htab_elem(htab, l); ret = 0; } @@ -531,17 +626,10 @@ static void delete_all_elements(struct bpf_htab *htab) hlist_for_each_entry_safe(l, n, head, hash_node) { hlist_del_rcu(&l->hash_node); - atomic_dec(&htab->count); - if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) { - l->key_size = htab->map.key_size; - htab_percpu_elem_free(l); - } else { - kfree(l); - } + htab_elem_free(htab, l); } } } - /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void htab_map_free(struct bpf_map *map) { @@ -554,10 +642,16 @@ static void htab_map_free(struct bpf_map *map) */ synchronize_rcu(); - /* some of kfree_rcu() callbacks for elements of this map may not have - * executed. It's ok. Proceed to free residual elements and map itself + /* some of free_htab_elem() callbacks for elements of this map may + * not have executed. Wait for them. */ - delete_all_elements(htab); + rcu_barrier(); + if (htab->map.map_flags & BPF_F_NO_PREALLOC) { + delete_all_elements(htab); + } else { + htab_free_elems(htab); + pcpu_freelist_destroy(&htab->freelist); + } kvfree(htab->buckets); kfree(htab); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index dc99f6a000f5..cbd94b2144ff 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -48,6 +48,19 @@ void bpf_register_map_type(struct bpf_map_type_list *tl) list_add(&tl->list_node, &bpf_map_types); } +int bpf_map_precharge_memlock(u32 pages) +{ + struct user_struct *user = get_current_user(); + unsigned long memlock_limit, cur; + + memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + cur = atomic_long_read(&user->locked_vm); + free_uid(user); + if (cur + pages > memlock_limit) + return -EPERM; + return 0; +} + static int bpf_map_charge_memlock(struct bpf_map *map) { struct user_struct *user = get_current_user(); @@ -153,7 +166,7 @@ int bpf_map_new_fd(struct bpf_map *map) offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL -#define BPF_MAP_CREATE_LAST_FIELD max_entries +#define BPF_MAP_CREATE_LAST_FIELD map_flags /* called via syscall */ static int map_create(union bpf_attr *attr) { -- cgit v1.2.3 From 823707b68d6e6c4b1be619b039c7045fef1740e6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:16 -0800 Subject: bpf: check for reserved flag bits in array and stack maps Suggested-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/arraymap.c | 2 +- kernel/bpf/stackmap.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index bd3bdf2486a7..76d5a794e426 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -53,7 +53,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size == 0) + attr->value_size == 0 || attr->map_flags) return ERR_PTR(-EINVAL); if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1)) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 8a60ee14a977..f0a02c344358 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -35,6 +35,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); + if (attr->map_flags) + return ERR_PTR(-EINVAL); + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || value_size < 8 || value_size % 8 || -- cgit v1.2.3 From 557c0c6e7df8e14a46bd7560d193fa5bbc00a858 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:17 -0800 Subject: bpf: convert stackmap to pre-allocation It was observed that calling bpf_get_stackid() from a kprobe inside slub or from spin_unlock causes similar deadlock as with hashmap, therefore convert stackmap to use pre-allocated memory. The call_rcu is no longer feasible mechanism, since delayed freeing causes bpf_get_stackid() to fail unpredictably when number of actual stacks is significantly less than user requested max_entries. Since elements are no longer freed into slub, we can push elements into freelist immediately and let them be recycled. However the very unlikley race between user space map_lookup() and program-side recycling is possible: cpu0 cpu1 ---- ---- user does lookup(stackidX) starts copying ips into buffer delete(stackidX) calls bpf_get_stackid() which recyles the element and overwrites with new stack trace To avoid user space seeing a partial stack trace consisting of two merged stack traces, do bucket = xchg(, NULL); copy; xchg(,bucket); to preserve consistent stack trace delivery to user space. Now we can move memset(,0) of left-over element value from critical path of bpf_get_stackid() into slow-path of user space lookup. Also disallow lookup() from bpf program, since it's useless and program shouldn't be messing with collected stack trace. Note that similar race between user space lookup and kernel side updates is also present in hashmap, but it's not a new race. bpf programs were always allowed to modify hash and array map elements while user space is copying them. Fixes: d5a3b1f69186 ("bpf: introduce BPF_MAP_TYPE_STACK_TRACE") Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + kernel/bpf/stackmap.c | 86 ++++++++++++++++++++++++++++++++++++++++----------- kernel/bpf/syscall.c | 2 ++ 3 files changed, 71 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index efd1d4ca95c6..21ee41b92e8a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -195,6 +195,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); +int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index f0a02c344358..499d9e933f8e 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -10,9 +10,10 @@ #include #include #include +#include "percpu_freelist.h" struct stack_map_bucket { - struct rcu_head rcu; + struct pcpu_freelist_node fnode; u32 hash; u32 nr; u64 ip[]; @@ -20,10 +21,34 @@ struct stack_map_bucket { struct bpf_stack_map { struct bpf_map map; + void *elems; + struct pcpu_freelist freelist; u32 n_buckets; - struct stack_map_bucket __rcu *buckets[]; + struct stack_map_bucket *buckets[]; }; +static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) +{ + u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; + int err; + + smap->elems = vzalloc(elem_size * smap->map.max_entries); + if (!smap->elems) + return -ENOMEM; + + err = pcpu_freelist_init(&smap->freelist); + if (err) + goto free_elems; + + pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size, + smap->map.max_entries); + return 0; + +free_elems: + vfree(smap->elems); + return err; +} + /* Called from syscall */ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) { @@ -70,12 +95,22 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) smap->n_buckets = n_buckets; smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + err = bpf_map_precharge_memlock(smap->map.pages); + if (err) + goto free_smap; + err = get_callchain_buffers(); if (err) goto free_smap; + err = prealloc_elems_and_freelist(smap); + if (err) + goto put_buffers; + return &smap->map; +put_buffers: + put_callchain_buffers(); free_smap: kvfree(smap); return ERR_PTR(err); @@ -121,7 +156,7 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) ips = trace->ip + skip + init_nr; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); id = hash & (smap->n_buckets - 1); - bucket = rcu_dereference(smap->buckets[id]); + bucket = READ_ONCE(smap->buckets[id]); if (bucket && bucket->hash == hash) { if (flags & BPF_F_FAST_STACK_CMP) @@ -135,19 +170,18 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) if (bucket && !(flags & BPF_F_REUSE_STACKID)) return -EEXIST; - new_bucket = kmalloc(sizeof(struct stack_map_bucket) + map->value_size, - GFP_ATOMIC | __GFP_NOWARN); + new_bucket = (struct stack_map_bucket *) + pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; memcpy(new_bucket->ip, ips, trace_len); - memset(new_bucket->ip + trace_len / 8, 0, map->value_size - trace_len); new_bucket->hash = hash; new_bucket->nr = trace_nr; old_bucket = xchg(&smap->buckets[id], new_bucket); if (old_bucket) - kfree_rcu(old_bucket, rcu); + pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return id; } @@ -160,17 +194,34 @@ const struct bpf_func_proto bpf_get_stackid_proto = { .arg3_type = ARG_ANYTHING, }; -/* Called from syscall or from eBPF program */ +/* Called from eBPF program */ static void *stack_map_lookup_elem(struct bpf_map *map, void *key) +{ + return NULL; +} + +/* Called from syscall */ +int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); - struct stack_map_bucket *bucket; - u32 id = *(u32 *)key; + struct stack_map_bucket *bucket, *old_bucket; + u32 id = *(u32 *)key, trace_len; if (unlikely(id >= smap->n_buckets)) - return NULL; - bucket = rcu_dereference(smap->buckets[id]); - return bucket ? bucket->ip : NULL; + return -ENOENT; + + bucket = xchg(&smap->buckets[id], NULL); + if (!bucket) + return -ENOENT; + + trace_len = bucket->nr * sizeof(u64); + memcpy(value, bucket->ip, trace_len); + memset(value + trace_len, 0, map->value_size - trace_len); + + old_bucket = xchg(&smap->buckets[id], bucket); + if (old_bucket) + pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); + return 0; } static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key) @@ -196,7 +247,7 @@ static int stack_map_delete_elem(struct bpf_map *map, void *key) old_bucket = xchg(&smap->buckets[id], NULL); if (old_bucket) { - kfree_rcu(old_bucket, rcu); + pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return 0; } else { return -ENOENT; @@ -207,13 +258,12 @@ static int stack_map_delete_elem(struct bpf_map *map, void *key) static void stack_map_free(struct bpf_map *map) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); - int i; + /* wait for bpf programs to complete before freeing stack map */ synchronize_rcu(); - for (i = 0; i < smap->n_buckets; i++) - if (smap->buckets[i]) - kfree_rcu(smap->buckets[i], rcu); + vfree(smap->elems); + pcpu_freelist_destroy(&smap->freelist); kvfree(smap); put_callchain_buffers(); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cbd94b2144ff..2978d0d08869 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -290,6 +290,8 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { + err = bpf_stackmap_copy(map, key, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); -- cgit v1.2.3 From e237a5518425155faa508a087f28269f58074b92 Mon Sep 17 00:00:00 2001 From: Chen Fan Date: Mon, 15 Feb 2016 12:52:01 +0800 Subject: x86/ACPI/PCI: Recognize that Interrupt Line 255 means "not connected" Per the x86-specific footnote to PCI spec r3.0, sec 6.2.4, the value 255 in the Interrupt Line register means "unknown" or "no connection." Previously, when we couldn't derive an IRQ from the _PRT, we fell back to using the value from Interrupt Line as an IRQ. It's questionable whether we should do that at all, but the spec clearly suggests we shouldn't do it for the value 255 on x86. Calling request_irq() with IRQ 255 may succeed, but the driver won't receive any interrupts. Or, if IRQ 255 is shared with another device, it may succeed, and the driver's ISR will be called at random times when the *other* device interrupts. Or it may fail if another device is using IRQ 255 with incompatible flags. What we *want* is for request_irq() to fail predictably so the driver can fall back to polling. On x86, assume 255 in the Interrupt Line means the INTx line is not connected. In that case, set dev->irq to IRQ_NOTCONNECTED so request_irq() will fail gracefully with -ENOTCONN. We found this problem on a system where Secure Boot firmware assigned Interrupt Line 255 to an i801_smbus device and another device was already using MSI-X IRQ 255. This was in v3.10, where i801_probe() fails if request_irq() fails: i801_smbus 0000:00:1f.3: enabling device (0140 -> 0143) i801_smbus 0000:00:1f.3: can't derive routing for PCI INT C i801_smbus 0000:00:1f.3: PCI INT C: no GSI genirq: Flags mismatch irq 255. 00000080 (i801_smbus) vs. 00000000 (megasa) CPU: 0 PID: 2487 Comm: kworker/0:1 Not tainted 3.10.0-229.el7.x86_64 #1 Hardware name: FUJITSU PRIMEQUEST 2800E2/D3736, BIOS PRIMEQUEST 2000 Serie5 Call Trace: dump_stack+0x19/0x1b __setup_irq+0x54a/0x570 request_threaded_irq+0xcc/0x170 i801_probe+0x32f/0x508 [i2c_i801] local_pci_probe+0x45/0xa0 i801_smbus 0000:00:1f.3: Failed to allocate irq 255: -16 i801_smbus: probe of 0000:00:1f.3 failed with error -16 After aeb8a3d16ae0 ("i2c: i801: Check if interrupts are disabled"), i801_probe() will fall back to polling if request_irq() fails. But we still need this patch because request_irq() may succeed or fail depending on other devices in the system. If request_irq() fails, i801_smbus will work by falling back to polling, but if it succeeds, i801_smbus won't work because it expects interrupts that it may not receive. Signed-off-by: Chen Fan Acked-by: Thomas Gleixner Acked-by: Bjorn Helgaas Signed-off-by: Rafael J. Wysocki --- drivers/acpi/pci_irq.c | 29 +++++++++++++++++++++++++---- include/linux/interrupt.h | 10 ++++++++++ kernel/irq/manage.c | 9 ++++++++- 3 files changed, 43 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index c8e169e46673..2c45dd3acc17 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -33,6 +33,7 @@ #include #include #include +#include #define PREFIX "ACPI: " @@ -387,6 +388,23 @@ static inline int acpi_isa_register_gsi(struct pci_dev *dev) } #endif +static inline bool acpi_pci_irq_valid(struct pci_dev *dev, u8 pin) +{ +#ifdef CONFIG_X86 + /* + * On x86 irq line 0xff means "unknown" or "no connection" + * (PCI 3.0, Section 6.2.4, footnote on page 223). + */ + if (dev->irq == 0xff) { + dev->irq = IRQ_NOTCONNECTED; + dev_warn(&dev->dev, "PCI INT %c: not connected\n", + pin_name(pin)); + return false; + } +#endif + return true; +} + int acpi_pci_irq_enable(struct pci_dev *dev) { struct acpi_prt_entry *entry; @@ -431,11 +449,14 @@ int acpi_pci_irq_enable(struct pci_dev *dev) } else gsi = -1; - /* - * No IRQ known to the ACPI subsystem - maybe the BIOS / - * driver reported one, then use it. Exit in any case. - */ if (gsi < 0) { + /* + * No IRQ known to the ACPI subsystem - maybe the BIOS / + * driver reported one, then use it. Exit in any case. + */ + if (!acpi_pci_irq_valid(dev, pin)) + return 0; + if (acpi_isa_register_gsi(dev)) dev_warn(&dev->dev, "PCI INT %c: no GSI\n", pin_name(pin)); diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 0e95fcc75b2a..358076eda364 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -125,6 +125,16 @@ struct irqaction { extern irqreturn_t no_action(int cpl, void *dev_id); +/* + * If a (PCI) device interrupt is not connected we set dev->irq to + * IRQ_NOTCONNECTED. This causes request_irq() to fail with -ENOTCONN, so we + * can distingiush that case from other error returns. + * + * 0x80000000 is guaranteed to be outside the available range of interrupts + * and easy to distinguish from other possible incorrect values. + */ +#define IRQ_NOTCONNECTED (1U << 31) + extern int __must_check request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 841187239adc..e79e60f50bce 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1609,6 +1609,9 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, struct irq_desc *desc; int retval; + if (irq == IRQ_NOTCONNECTED) + return -ENOTCONN; + /* * Sanity-check: shared interrupts must pass in a real dev-ID, * otherwise we'll have trouble later trying to figure out @@ -1699,9 +1702,13 @@ EXPORT_SYMBOL(request_threaded_irq); int request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id) { - struct irq_desc *desc = irq_to_desc(irq); + struct irq_desc *desc; int ret; + if (irq == IRQ_NOTCONNECTED) + return -ENOTCONN; + + desc = irq_to_desc(irq); if (!desc) return -EINVAL; -- cgit v1.2.3 From 34e2c555f3e13c90e9284e23d00f03be8a6e06c5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 15 Feb 2016 20:20:42 +0100 Subject: cpufreq: Add mechanism for registering utilization update callbacks Introduce a mechanism by which parts of the cpufreq subsystem ("setpolicy" drivers or the core) can register callbacks to be executed from cpufreq_update_util() which is invoked by the scheduler's update_load_avg() on CPU utilization changes. This allows the "setpolicy" drivers to dispense with their timers and do all of the computations they need and frequency/voltage adjustments in the update_load_avg() code path, among other things. The update_load_avg() changes were suggested by Peter Zijlstra. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar Acked-by: Peter Zijlstra (Intel) Acked-by: Ingo Molnar --- drivers/cpufreq/cpufreq.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/cpufreq.h | 34 ++++++++++++++++++++++++++++++++++ kernel/sched/deadline.c | 4 ++++ kernel/sched/fair.c | 26 +++++++++++++++++++++++++- kernel/sched/rt.c | 4 ++++ kernel/sched/sched.h | 1 + 6 files changed, 113 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 34b17447e0d1..e172b2a02c1d 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -102,6 +102,51 @@ static LIST_HEAD(cpufreq_governor_list); static struct cpufreq_driver *cpufreq_driver; static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data); static DEFINE_RWLOCK(cpufreq_driver_lock); + +static DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); + +/** + * cpufreq_set_update_util_data - Populate the CPU's update_util_data pointer. + * @cpu: The CPU to set the pointer for. + * @data: New pointer value. + * + * Set and publish the update_util_data pointer for the given CPU. That pointer + * points to a struct update_util_data object containing a callback function + * to call from cpufreq_update_util(). That function will be called from an RCU + * read-side critical section, so it must not sleep. + * + * Callers must use RCU callbacks to free any memory that might be accessed + * via the old update_util_data pointer or invoke synchronize_rcu() right after + * this function to avoid use-after-free. + */ +void cpufreq_set_update_util_data(int cpu, struct update_util_data *data) +{ + rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data); +} +EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data); + +/** + * cpufreq_update_util - Take a note about CPU utilization changes. + * @time: Current time. + * @util: Current utilization. + * @max: Utilization ceiling. + * + * This function is called by the scheduler on every invocation of + * update_load_avg() on the CPU whose utilization is being updated. + */ +void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) +{ + struct update_util_data *data; + + rcu_read_lock(); + + data = rcu_dereference(*this_cpu_ptr(&cpufreq_update_util_data)); + if (data && data->func) + data->func(data, time, util, max); + + rcu_read_unlock(); +} + DEFINE_MUTEX(cpufreq_governor_lock); /* Flag to suspend/resume CPUFreq governors */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index d0bf555b6bbf..704d85bf7242 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -151,6 +151,36 @@ static inline bool policy_is_shared(struct cpufreq_policy *policy) extern struct kobject *cpufreq_global_kobject; #ifdef CONFIG_CPU_FREQ +void cpufreq_update_util(u64 time, unsigned long util, unsigned long max); + +/** + * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed. + * @time: Current time. + * + * The way cpufreq is currently arranged requires it to evaluate the CPU + * performance state (frequency/voltage) on a regular basis to prevent it from + * being stuck in a completely inadequate performance level for too long. + * That is not guaranteed to happen if the updates are only triggered from CFS, + * though, because they may not be coming in if RT or deadline tasks are active + * all the time (or there are RT and DL tasks only). + * + * As a workaround for that issue, this function is called by the RT and DL + * sched classes to trigger extra cpufreq updates to prevent it from stalling, + * but that really is a band-aid. Going forward it should be replaced with + * solutions targeted more specifically at RT and DL tasks. + */ +static inline void cpufreq_trigger_update(u64 time) +{ + cpufreq_update_util(time, ULONG_MAX, 0); +} + +struct update_util_data { + void (*func)(struct update_util_data *data, + u64 time, unsigned long util, unsigned long max); +}; + +void cpufreq_set_update_util_data(int cpu, struct update_util_data *data); + unsigned int cpufreq_get(unsigned int cpu); unsigned int cpufreq_quick_get(unsigned int cpu); unsigned int cpufreq_quick_get_max(unsigned int cpu); @@ -162,6 +192,10 @@ int cpufreq_update_policy(unsigned int cpu); bool have_governor_per_policy(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); #else +static inline void cpufreq_update_util(u64 time, unsigned long util, + unsigned long max) {} +static inline void cpufreq_trigger_update(u64 time) {} + static inline unsigned int cpufreq_get(unsigned int cpu) { return 0; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index cd64c979d0e1..21a0aa6f810d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -726,6 +726,10 @@ static void update_curr_dl(struct rq *rq) if (!dl_task(curr) || !on_dl_rq(dl_se)) return; + /* Kick cpufreq (see the comment in linux/cpufreq.h). */ + if (cpu_of(rq) == smp_processor_id()) + cpufreq_trigger_update(rq_clock(rq)); + /* * Consumed budget is computed considering the time as * observed by schedulable tasks (excluding time spent diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 56b7d4b83947..e2987a7e489d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2824,7 +2824,8 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) { struct cfs_rq *cfs_rq = cfs_rq_of(se); u64 now = cfs_rq_clock_task(cfs_rq); - int cpu = cpu_of(rq_of(cfs_rq)); + struct rq *rq = rq_of(cfs_rq); + int cpu = cpu_of(rq); /* * Track task load average for carrying it to new CPU after migrated, and @@ -2836,6 +2837,29 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg) update_tg_load_avg(cfs_rq, 0); + + if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) { + unsigned long max = rq->cpu_capacity_orig; + + /* + * There are a few boundary cases this might miss but it should + * get called often enough that that should (hopefully) not be + * a real problem -- added to that it only calls on the local + * CPU, so if we enqueue remotely we'll miss an update, but + * the next tick/schedule should update. + * + * It will not get called when we go idle, because the idle + * thread is a different class (!fair), nor will the utilization + * number include things like RT tasks. + * + * As is, the util number is not freq-invariant (we'd have to + * implement arch_scale_freq_capacity() for that). + * + * See cpu_util(). + */ + cpufreq_update_util(rq_clock(rq), + min(cfs_rq->avg.util_avg, max), max); + } } static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 8ec86abe0ea1..27f5b03cbdbe 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -945,6 +945,10 @@ static void update_curr_rt(struct rq *rq) if (curr->sched_class != &rt_sched_class) return; + /* Kick cpufreq (see the comment in linux/cpufreq.h). */ + if (cpu_of(rq) == smp_processor_id()) + cpufreq_trigger_update(rq_clock(rq)); + delta_exec = rq_clock_task(rq) - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) return; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 10f16374df7f..f042190c8002 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -9,6 +9,7 @@ #include #include #include +#include #include "cpupri.h" #include "cpudeadline.h" -- cgit v1.2.3 From 4e0d8f7eff3fbfa3e3ac5782669c078f590dc9e2 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 9 Mar 2016 12:47:03 -0700 Subject: resource: Change __request_region to inherit from immediate parent __request_region() sets 'flags' of a new resource from @parent as it inherits the parent's attribute. When a target resource has a conflict, this function inserts the new resource entry under the conflicted entry by updating @parent. In this case, the new resource entry needs to inherit attribute from the updated parent. This conflict is a typical case since __request_region() is used to allocate a new resource from a specific resource range. For instance, request_mem_region() calls __request_region() with @parent set to &iomem_resource, which is the root entry of the whole iomem range. When this request results in inserting a new entry "DEV-A" under "BUS-1", "DEV-A" needs to inherit from the immediate parent "BUS-1" as it holds specific attribute for the range. root (&iomem_resource) : + "BUS-1" + "DEV-A" Change __request_region() to set 'flags' and 'desc' of a new entry from the immediate parent. Signed-off-by: Toshi Kani Cc: Ingo Molnar Cc: Borislav Petkov Cc: Andrew Morton Cc: Dan Williams Signed-off-by: Dan Williams --- kernel/resource.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 4d466052426b..5a56e8f24058 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1085,15 +1085,16 @@ struct resource * __request_region(struct resource *parent, res->name = name; res->start = start; res->end = start + n - 1; - res->flags = resource_type(parent) | resource_ext_type(parent); - res->flags |= IORESOURCE_BUSY | flags; - res->desc = IORES_DESC_NONE; write_lock(&resource_lock); for (;;) { struct resource *conflict; + res->flags = resource_type(parent) | resource_ext_type(parent); + res->flags |= IORESOURCE_BUSY | flags; + res->desc = parent->desc; + conflict = __request_resource(parent, res); if (!conflict) break; -- cgit v1.2.3 From ff3cc952d3f009e6c376cc40651b87187ce364a6 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 9 Mar 2016 12:47:04 -0700 Subject: resource: Add remove_resource interface insert_resource() and insert_resource_conflict() are called by resource producers to insert a new resource. When there is any conflict, they move conflicting resources down to the children of the new resource. There is no destructor of these interfaces, however. Add remove_resource(), which removes a resource previously inserted by insert_resource() or insert_resource_conflict(), and moves the children up to where they were before. __release_resource() is changed to have @release_child, so that this function can be used for remove_resource() as well. Also add comments to clarify that these functions are intended for producers of resources to avoid any confusion with request/release_resource() for consumers. Signed-off-by: Toshi Kani Cc: Ingo Molnar Cc: Borislav Petkov Cc: Andrew Morton Cc: Dan Williams Signed-off-by: Dan Williams --- include/linux/ioport.h | 1 + kernel/resource.c | 51 +++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 47 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index afb45597fb5f..8017b8bf45fa 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -174,6 +174,7 @@ extern void reserve_region_with_split(struct resource *root, extern struct resource *insert_resource_conflict(struct resource *parent, struct resource *new); extern int insert_resource(struct resource *parent, struct resource *new); extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new); +extern int remove_resource(struct resource *old); extern void arch_remove_reservations(struct resource *avail); extern int allocate_resource(struct resource *root, struct resource *new, resource_size_t size, resource_size_t min, diff --git a/kernel/resource.c b/kernel/resource.c index 5a56e8f24058..effb6ee2c3e8 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -233,9 +233,9 @@ static struct resource * __request_resource(struct resource *root, struct resour } } -static int __release_resource(struct resource *old) +static int __release_resource(struct resource *old, bool release_child) { - struct resource *tmp, **p; + struct resource *tmp, **p, *chd; p = &old->parent->child; for (;;) { @@ -243,7 +243,17 @@ static int __release_resource(struct resource *old) if (!tmp) break; if (tmp == old) { - *p = tmp->sibling; + if (release_child || !(tmp->child)) { + *p = tmp->sibling; + } else { + for (chd = tmp->child;; chd = chd->sibling) { + chd->parent = tmp->parent; + if (!(chd->sibling)) + break; + } + *p = tmp->child; + chd->sibling = tmp->sibling; + } old->parent = NULL; return 0; } @@ -325,7 +335,7 @@ int release_resource(struct resource *old) int retval; write_lock(&resource_lock); - retval = __release_resource(old); + retval = __release_resource(old, true); write_unlock(&resource_lock); return retval; } @@ -679,7 +689,7 @@ static int reallocate_resource(struct resource *root, struct resource *old, old->start = new.start; old->end = new.end; } else { - __release_resource(old); + __release_resource(old, true); *old = new; conflict = __request_resource(root, old); BUG_ON(conflict); @@ -825,6 +835,9 @@ static struct resource * __insert_resource(struct resource *parent, struct resou * entirely fit within the range of the new resource, then the new * resource is inserted and the conflicting resources become children of * the new resource. + * + * This function is intended for producers of resources, such as FW modules + * and bus drivers. */ struct resource *insert_resource_conflict(struct resource *parent, struct resource *new) { @@ -842,6 +855,9 @@ struct resource *insert_resource_conflict(struct resource *parent, struct resour * @new: new resource to insert * * Returns 0 on success, -EBUSY if the resource can't be inserted. + * + * This function is intended for producers of resources, such as FW modules + * and bus drivers. */ int insert_resource(struct resource *parent, struct resource *new) { @@ -885,6 +901,31 @@ void insert_resource_expand_to_fit(struct resource *root, struct resource *new) write_unlock(&resource_lock); } +/** + * remove_resource - Remove a resource in the resource tree + * @old: resource to remove + * + * Returns 0 on success, -EINVAL if the resource is not valid. + * + * This function removes a resource previously inserted by insert_resource() + * or insert_resource_conflict(), and moves the children (if any) up to + * where they were before. insert_resource() and insert_resource_conflict() + * insert a new resource, and move any conflicting resources down to the + * children of the new resource. + * + * insert_resource(), insert_resource_conflict() and remove_resource() are + * intended for producers of resources, such as FW modules and bus drivers. + */ +int remove_resource(struct resource *old) +{ + int retval; + + write_lock(&resource_lock); + retval = __release_resource(old, false); + write_unlock(&resource_lock); + return retval; +} + static int __adjust_resource(struct resource *res, resource_size_t start, resource_size_t size) { -- cgit v1.2.3 From 8095d0f225fe31eaac4a013177b77ed5283278f8 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 9 Mar 2016 12:47:05 -0700 Subject: resource: Export insert_resource and remove_resource insert_resource() and remove_resouce() are called by producers of resources, such as FW modules and bus drivers. These modules may be implemented as loadable modules. Export insert_resource() and remove_resouce() so that they can be called from such modules. link: https://lkml.org/lkml/2016/3/8/872 Signed-off-by: Toshi Kani Cc: Linus Torvalds Cc: Ingo Molnar Cc: Borislav Petkov Cc: Andrew Morton Cc: Dan Williams Signed-off-by: Dan Williams --- kernel/resource.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index effb6ee2c3e8..2e78ead30934 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -866,6 +866,7 @@ int insert_resource(struct resource *parent, struct resource *new) conflict = insert_resource_conflict(parent, new); return conflict ? -EBUSY : 0; } +EXPORT_SYMBOL_GPL(insert_resource); /** * insert_resource_expand_to_fit - Insert a resource into the resource tree @@ -925,6 +926,7 @@ int remove_resource(struct resource *old) write_unlock(&resource_lock); return retval; } +EXPORT_SYMBOL_GPL(remove_resource); static int __adjust_resource(struct resource *res, resource_size_t start, resource_size_t size) -- cgit v1.2.3 From f995b5f720a72dfe7a1b33a43f2841b4e72d53b7 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 9 Mar 2016 15:20:59 +0100 Subject: livepatch: Fix the error message about unresolvable ambiguity klp_find_callback() stops the search when sympos is not defined and a second symbol of the same name is found. It means that the current error message about the unresolvable ambiguity always prints "(2 matches)". Let's remove this information. The total number of occurrences is not much helpful. The author of the patch still must put a non-trivial effort into searching the right position in the object file. [jkosina@suse.cz: fixed grammar as suggested by Josh] Signed-off-by: Petr Mladek Acked-by: Josh Poimboeuf Acked-by: Chris J Arges Signed-off-by: Jiri Kosina --- kernel/livepatch/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index bc2c85c064c1..780f00cdb7e5 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -190,8 +190,8 @@ static int klp_find_object_symbol(const char *objname, const char *name, if (args.addr == 0) pr_err("symbol '%s' not found in symbol table\n", name); else if (args.count > 1 && sympos == 0) { - pr_err("unresolvable ambiguity (%lu matches) on symbol '%s' in object '%s'\n", - args.count, name, objname); + pr_err("unresolvable ambiguity for symbol '%s' in object '%s'\n", + name, objname); } else if (sympos != args.count && sympos > 0) { pr_err("symbol position %lu for symbol '%s' in object '%s' not found\n", sympos, name, objname ? objname : "vmlinux"); -- cgit v1.2.3 From b8cdc05173f05d212627b7aba7ec47fa334a79f2 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 9 Mar 2016 18:56:49 -0800 Subject: bpf: bpf_stackmap_copy depends on CONFIG_PERF_EVENTS 0-day bot reported build error: kernel/built-in.o: In function `map_lookup_elem': >> kernel/bpf/.tmp_syscall.o:(.text+0x329b3c): undefined reference to `bpf_stackmap_copy' when CONFIG_BPF_SYSCALL is set and CONFIG_PERF_EVENTS is not. Add weak definition to resolve it. This code path in map_lookup_elem() is never taken when CONFIG_PERF_EVENTS is not set. Fixes: 557c0c6e7df8 ("bpf: convert stackmap to pre-allocation") Reported-by: Fengguang Wu Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2978d0d08869..2a2efe1bc76c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -244,6 +244,11 @@ static void __user *u64_to_ptr(__u64 val) return (void __user *) (unsigned long) val; } +int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) +{ + return -ENOTSUPP; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value -- cgit v1.2.3 From cdc4e47da8f4c32eeb6b2061a8a834f4362a12b7 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 9 Mar 2016 20:02:33 -0800 Subject: bpf: avoid copying junk bytes in bpf_get_current_comm() Lots of places in the kernel use memcpy(buf, comm, TASK_COMM_LEN); but the result is typically passed to print("%s", buf) and extra bytes after zero don't cause any harm. In bpf the result of bpf_get_current_comm() is used as the part of map key and was causing spurious hash map mismatches. Use strlcpy() to guarantee zero-terminated string. bpf verifier checks that output buffer is zero-initialized, so even for short task names the output buffer don't have junk bytes. Note it's not a security concern, since kprobe+bpf is root only. Fixes: ffeedafbf023 ("bpf: introduce current->pid, tgid, uid, gid, comm accessors") Reported-by: Tobias Waldekranz Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/helpers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 4504ca66118d..50da680c479f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -166,7 +166,7 @@ static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5) if (!task) return -EINVAL; - memcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm))); + strlcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm))); return 0; } -- cgit v1.2.3 From adaf9fcd136970e480d7ca834c0cf25ce922ea74 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 10 Mar 2016 20:44:47 +0100 Subject: cpufreq: Move scheduler-related code to the sched directory Create cpufreq.c under kernel/sched/ and move the cpufreq code related to the scheduler to that file and to sched.h. Redefine cpufreq_update_util() as a static inline function to avoid function calls at its call sites in the scheduler code (as suggested by Peter Zijlstra). Also move the definition of struct update_util_data and declaration of cpufreq_set_update_util_data() from include/linux/cpufreq.h to include/linux/sched.h. Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) --- drivers/cpufreq/cpufreq.c | 53 -------------------------------------- drivers/cpufreq/cpufreq_governor.c | 1 + include/linux/cpufreq.h | 34 ------------------------ include/linux/sched.h | 9 +++++++ kernel/sched/Makefile | 1 + kernel/sched/cpufreq.c | 37 ++++++++++++++++++++++++++ kernel/sched/sched.h | 49 ++++++++++++++++++++++++++++++++++- 7 files changed, 96 insertions(+), 88 deletions(-) create mode 100644 kernel/sched/cpufreq.c (limited to 'kernel') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 6eca12ab71d7..58e1a39b4d22 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -103,59 +103,6 @@ static struct cpufreq_driver *cpufreq_driver; static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data); static DEFINE_RWLOCK(cpufreq_driver_lock); -static DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); - -/** - * cpufreq_set_update_util_data - Populate the CPU's update_util_data pointer. - * @cpu: The CPU to set the pointer for. - * @data: New pointer value. - * - * Set and publish the update_util_data pointer for the given CPU. That pointer - * points to a struct update_util_data object containing a callback function - * to call from cpufreq_update_util(). That function will be called from an RCU - * read-side critical section, so it must not sleep. - * - * Callers must use RCU-sched callbacks to free any memory that might be - * accessed via the old update_util_data pointer or invoke synchronize_sched() - * right after this function to avoid use-after-free. - */ -void cpufreq_set_update_util_data(int cpu, struct update_util_data *data) -{ - if (WARN_ON(data && !data->func)) - return; - - rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data); -} -EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data); - -/** - * cpufreq_update_util - Take a note about CPU utilization changes. - * @time: Current time. - * @util: Current utilization. - * @max: Utilization ceiling. - * - * This function is called by the scheduler on every invocation of - * update_load_avg() on the CPU whose utilization is being updated. - * - * It can only be called from RCU-sched read-side critical sections. - */ -void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) -{ - struct update_util_data *data; - -#ifdef CONFIG_LOCKDEP - WARN_ON(debug_locks && !rcu_read_lock_sched_held()); -#endif - - data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)); - /* - * If this isn't inside of an RCU-sched read-side critical section, data - * may become NULL after the check below. - */ - if (data) - data->func(data, time, util, max); -} - /* Flag to suspend/resume CPUFreq governors */ static bool cpufreq_suspended; diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index db46190bb246..1c25ef405616 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -18,6 +18,7 @@ #include #include +#include #include #include "cpufreq_governor.h" diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index a50c5b2e3bf2..a5ea52f793f3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -146,36 +146,6 @@ static inline bool policy_is_shared(struct cpufreq_policy *policy) extern struct kobject *cpufreq_global_kobject; #ifdef CONFIG_CPU_FREQ -void cpufreq_update_util(u64 time, unsigned long util, unsigned long max); - -/** - * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed. - * @time: Current time. - * - * The way cpufreq is currently arranged requires it to evaluate the CPU - * performance state (frequency/voltage) on a regular basis to prevent it from - * being stuck in a completely inadequate performance level for too long. - * That is not guaranteed to happen if the updates are only triggered from CFS, - * though, because they may not be coming in if RT or deadline tasks are active - * all the time (or there are RT and DL tasks only). - * - * As a workaround for that issue, this function is called by the RT and DL - * sched classes to trigger extra cpufreq updates to prevent it from stalling, - * but that really is a band-aid. Going forward it should be replaced with - * solutions targeted more specifically at RT and DL tasks. - */ -static inline void cpufreq_trigger_update(u64 time) -{ - cpufreq_update_util(time, ULONG_MAX, 0); -} - -struct update_util_data { - void (*func)(struct update_util_data *data, - u64 time, unsigned long util, unsigned long max); -}; - -void cpufreq_set_update_util_data(int cpu, struct update_util_data *data); - unsigned int cpufreq_get(unsigned int cpu); unsigned int cpufreq_quick_get(unsigned int cpu); unsigned int cpufreq_quick_get_max(unsigned int cpu); @@ -187,10 +157,6 @@ int cpufreq_update_policy(unsigned int cpu); bool have_governor_per_policy(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); #else -static inline void cpufreq_update_util(u64 time, unsigned long util, - unsigned long max) {} -static inline void cpufreq_trigger_update(u64 time) {} - static inline unsigned int cpufreq_get(unsigned int cpu) { return 0; diff --git a/include/linux/sched.h b/include/linux/sched.h index a10494a94cc3..913e755ef7b8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3207,4 +3207,13 @@ static inline unsigned long rlimit_max(unsigned int limit) return task_rlimit_max(current, limit); } +#ifdef CONFIG_CPU_FREQ +struct update_util_data { + void (*func)(struct update_util_data *data, + u64 time, unsigned long util, unsigned long max); +}; + +void cpufreq_set_update_util_data(int cpu, struct update_util_data *data); +#endif /* CONFIG_CPU_FREQ */ + #endif diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 67687973ce80..9507522164ac 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -19,3 +19,4 @@ obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o +obj-$(CONFIG_CPU_FREQ) += cpufreq.o diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c new file mode 100644 index 000000000000..928c4ba32f68 --- /dev/null +++ b/kernel/sched/cpufreq.c @@ -0,0 +1,37 @@ +/* + * Scheduler code and data structures related to cpufreq. + * + * Copyright (C) 2016, Intel Corporation + * Author: Rafael J. Wysocki + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "sched.h" + +DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); + +/** + * cpufreq_set_update_util_data - Populate the CPU's update_util_data pointer. + * @cpu: The CPU to set the pointer for. + * @data: New pointer value. + * + * Set and publish the update_util_data pointer for the given CPU. That pointer + * points to a struct update_util_data object containing a callback function + * to call from cpufreq_update_util(). That function will be called from an RCU + * read-side critical section, so it must not sleep. + * + * Callers must use RCU-sched callbacks to free any memory that might be + * accessed via the old update_util_data pointer or invoke synchronize_sched() + * right after this function to avoid use-after-free. + */ +void cpufreq_set_update_util_data(int cpu, struct update_util_data *data) +{ + if (WARN_ON(data && !data->func)) + return; + + rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data); +} +EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index f042190c8002..faf7e2758dd0 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -9,7 +9,6 @@ #include #include #include -#include #include "cpupri.h" #include "cpudeadline.h" @@ -1739,3 +1738,51 @@ static inline u64 irq_time_read(int cpu) } #endif /* CONFIG_64BIT */ #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#ifdef CONFIG_CPU_FREQ +DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); + +/** + * cpufreq_update_util - Take a note about CPU utilization changes. + * @time: Current time. + * @util: Current utilization. + * @max: Utilization ceiling. + * + * This function is called by the scheduler on every invocation of + * update_load_avg() on the CPU whose utilization is being updated. + * + * It can only be called from RCU-sched read-side critical sections. + */ +static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) +{ + struct update_util_data *data; + + data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)); + if (data) + data->func(data, time, util, max); +} + +/** + * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed. + * @time: Current time. + * + * The way cpufreq is currently arranged requires it to evaluate the CPU + * performance state (frequency/voltage) on a regular basis to prevent it from + * being stuck in a completely inadequate performance level for too long. + * That is not guaranteed to happen if the updates are only triggered from CFS, + * though, because they may not be coming in if RT or deadline tasks are active + * all the time (or there are RT and DL tasks only). + * + * As a workaround for that issue, this function is called by the RT and DL + * sched classes to trigger extra cpufreq updates to prevent it from stalling, + * but that really is a band-aid. Going forward it should be replaced with + * solutions targeted more specifically at RT and DL tasks. + */ +static inline void cpufreq_trigger_update(u64 time) +{ + cpufreq_update_util(time, ULONG_MAX, 0); +} +#else +static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {} +static inline void cpufreq_trigger_update(u64 time) {} +#endif /* CONFIG_CPU_FREQ */ -- cgit v1.2.3 From 22aceb317678057dced5f1d6e3ac15acdb863e7b Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Thu, 10 Mar 2016 12:07:38 +0100 Subject: workqueue: Fix comment for work_on_cpu() Function is processed in thread context, not in user context. Cc: Tejun Heo Cc: Lai Jiangshan Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Signed-off-by: Tejun Heo --- kernel/workqueue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 16f4986205e9..c3692d9eda55 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4695,7 +4695,7 @@ static void work_for_cpu_fn(struct work_struct *work) } /** - * work_on_cpu - run a function in user context on a particular cpu + * work_on_cpu - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg -- cgit v1.2.3 From 25528213fe9f75f4e286f08d35a73ca2bb634a50 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Mar 2016 14:52:49 -0700 Subject: tags: Fix DEFINE_PER_CPU expansions $ make tags GEN tags ctags: Warning: drivers/acpi/processor_idle.c:64: null expansion of name pattern "\1" ctags: Warning: drivers/xen/events/events_2l.c:41: null expansion of name pattern "\1" ctags: Warning: kernel/locking/lockdep.c:151: null expansion of name pattern "\1" ctags: Warning: kernel/rcu/rcutorture.c:133: null expansion of name pattern "\1" ctags: Warning: kernel/rcu/rcutorture.c:135: null expansion of name pattern "\1" ctags: Warning: kernel/workqueue.c:323: null expansion of name pattern "\1" ctags: Warning: net/ipv4/syncookies.c:53: null expansion of name pattern "\1" ctags: Warning: net/ipv6/syncookies.c:44: null expansion of name pattern "\1" ctags: Warning: net/rds/page.c:45: null expansion of name pattern "\1" Which are all the result of the DEFINE_PER_CPU pattern: scripts/tags.sh:200: '/\ Acked-by: David S. Miller Acked-by: Rafael J. Wysocki Cc: Tejun Heo Cc: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/acpi/processor_idle.c | 4 ++-- drivers/xen/events/events_2l.c | 5 +++-- kernel/locking/lockdep.c | 3 +-- kernel/rcu/rcutorture.c | 6 ++---- kernel/workqueue.c | 3 +-- net/ipv4/syncookies.c | 3 +-- net/ipv6/syncookies.c | 3 +-- net/rds/page.c | 4 ++-- 8 files changed, 13 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 175c86bee3a9..9ca2b2fefd76 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -61,8 +61,8 @@ module_param(latency_factor, uint, 0644); static DEFINE_PER_CPU(struct cpuidle_device *, acpi_cpuidle_device); -static DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], - acpi_cstate); +static +DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], acpi_cstate); static int disabled_by_idle_boot_param(void) { diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c index 7dd46312c180..403fe3955393 100644 --- a/drivers/xen/events/events_2l.c +++ b/drivers/xen/events/events_2l.c @@ -38,8 +38,9 @@ /* Find the first set bit in a evtchn mask */ #define EVTCHN_FIRST_BIT(w) find_first_bit(BM(&(w)), BITS_PER_EVTCHN_WORD) -static DEFINE_PER_CPU(xen_ulong_t [EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD], - cpu_evtchn_mask); +#define EVTCHN_MASK_SIZE (EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD) + +static DEFINE_PER_CPU(xen_ulong_t [EVTCHN_MASK_SIZE], cpu_evtchn_mask); static unsigned evtchn_2l_max_channels(void) { diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index f894a2cd9b2a..53ab2f85d77e 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -148,8 +148,7 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock) } #ifdef CONFIG_LOCK_STAT -static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], - cpu_lock_stats); +static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], cpu_lock_stats); static inline u64 lockstat_clock(void) { diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index d2988d047d66..4d5cc6aa7e1e 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -130,10 +130,8 @@ static struct rcu_torture __rcu *rcu_torture_current; static unsigned long rcu_torture_current_version; static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN]; static DEFINE_SPINLOCK(rcu_torture_lock); -static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], - rcu_torture_count) = { 0 }; -static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], - rcu_torture_batch) = { 0 }; +static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) = { 0 }; +static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) = { 0 }; static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1]; static atomic_t n_rcu_torture_alloc; static atomic_t n_rcu_torture_alloc_fail; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 7ff5dc7d2ac5..16e13d8628a3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -320,8 +320,7 @@ static bool wq_debug_force_rr_cpu = false; module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* the per-cpu worker pools */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], - cpu_worker_pools); +static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 643a86c49020..2d5589b61e9f 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -50,8 +50,7 @@ static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly; #define TSBITS 6 #define TSMASK (((__u32)1 << TSBITS) - 1) -static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], - ipv4_cookie_scratch); +static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv4_cookie_scratch); static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, u32 count, int c) diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 2906ef20795e..aae3e5ca63ea 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -41,8 +41,7 @@ static __u16 const msstab[] = { 9000 - 60, }; -static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], - ipv6_cookie_scratch); +static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv6_cookie_scratch); static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, u32 count, int c) diff --git a/net/rds/page.c b/net/rds/page.c index 5a14e6d6a926..616f21f4e7d7 100644 --- a/net/rds/page.c +++ b/net/rds/page.c @@ -42,8 +42,8 @@ struct rds_page_remainder { unsigned long r_offset; }; -static DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, - rds_page_remainders); +static +DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders); /* * returns 0 on success or -errno on failure. -- cgit v1.2.3 From 07061aab2f750bbf61337b922aa8a245b5da85e1 Mon Sep 17 00:00:00 2001 From: Andreas Ziegler Date: Tue, 15 Mar 2016 14:55:33 -0700 Subject: mm: fix two typos in comments for to_vmem_altmap() Commit 4b94ffdc4163 ("x86, mm: introduce vmem_altmap to augment vmemmap_populate()"), introduced the to_vmem_altmap() function. The comments in this function contain two typos (one misspelling of the Kconfig option CONFIG_SPARSEMEM_VMEMMAP, and one missing letter 'n'), let's fix them up. Signed-off-by: Andreas Ziegler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/memremap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/memremap.c b/kernel/memremap.c index fb9b88787ebc..584febd13e2e 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -391,7 +391,7 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) /* * 'memmap_start' is the virtual address for the first "struct * page" in this range of the vmemmap array. In the case of - * CONFIG_SPARSE_VMEMMAP a page_to_pfn conversion is simple + * CONFIG_SPARSEMEM_VMEMMAP a page_to_pfn conversion is simple * pointer arithmetic, so we can perform this to_vmem_altmap() * conversion without concern for the initialization state of * the struct page fields. @@ -400,7 +400,7 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) struct dev_pagemap *pgmap; /* - * Uncoditionally retrieve a dev_pagemap associated with the + * Unconditionally retrieve a dev_pagemap associated with the * given physical address, this is only for use in the * arch_{add|remove}_memory() for setting up and tearing down * the memmap. -- cgit v1.2.3 From 1414c7f4f7d72d138fff35f00151d15749b5beda Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 15 Mar 2016 14:56:30 -0700 Subject: mm/page_poisoning.c: allow for zero poisoning By default, page poisoning uses a poison value (0xaa) on free. If this is changed to 0, the page is not only sanitized but zeroing on alloc with __GFP_ZERO can be skipped as well. The tradeoff is that detecting corruption from the poisoning is harder to detect. This feature also cannot be used with hibernation since pages are not guaranteed to be zeroed after hibernation. Credit to Grsecurity/PaX team for inspiring this work Signed-off-by: Laura Abbott Acked-by: Rafael J. Wysocki Cc: "Kirill A. Shutemov" Cc: Vlastimil Babka Cc: Michal Hocko Cc: Kees Cook Cc: Mathias Krause Cc: Dave Hansen Cc: Jianyu Zhan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ include/linux/poison.h | 4 ++++ kernel/power/hibernate.c | 17 +++++++++++++++++ mm/Kconfig.debug | 14 ++++++++++++++ mm/page_alloc.c | 11 ++++++++++- mm/page_ext.c | 10 ++++++++-- mm/page_poison.c | 7 +++++-- 7 files changed, 60 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/include/linux/mm.h b/include/linux/mm.h index 99dcc8f36e28..b97243d6aa49 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2179,10 +2179,12 @@ extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); extern void kernel_poison_pages(struct page *page, int numpages, int enable); +extern bool page_is_poisoned(struct page *page); #else static inline bool page_poisoning_enabled(void) { return false; } static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } +static inline bool page_is_poisoned(struct page *page) { return false; } #endif #ifdef CONFIG_DEBUG_PAGEALLOC diff --git a/include/linux/poison.h b/include/linux/poison.h index 4a27153574e2..51334edec506 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -30,7 +30,11 @@ #define TIMER_ENTRY_STATIC ((void *) 0x300 + POISON_POINTER_DELTA) /********** mm/debug-pagealloc.c **********/ +#ifdef CONFIG_PAGE_POISONING_ZERO +#define PAGE_POISON 0x00 +#else #define PAGE_POISON 0xaa +#endif /********** mm/page_alloc.c ************/ diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index b7342a24f559..aa0f26b58426 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -1158,6 +1158,22 @@ static int __init kaslr_nohibernate_setup(char *str) return nohibernate_setup(str); } +static int __init page_poison_nohibernate_setup(char *str) +{ +#ifdef CONFIG_PAGE_POISONING_ZERO + /* + * The zeroing option for page poison skips the checks on alloc. + * since hibernation doesn't save free pages there's no way to + * guarantee the pages will still be zeroed. + */ + if (!strcmp(str, "on")) { + pr_info("Disabling hibernation due to page poisoning\n"); + return nohibernate_setup(str); + } +#endif + return 1; +} + __setup("noresume", noresume_setup); __setup("resume_offset=", resume_offset_setup); __setup("resume=", resume_setup); @@ -1166,3 +1182,4 @@ __setup("resumewait", resumewait_setup); __setup("resumedelay=", resumedelay_setup); __setup("nohibernate", nohibernate_setup); __setup("kaslr", kaslr_nohibernate_setup); +__setup("page_poison=", page_poison_nohibernate_setup); diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 1f99f9a0deae..5c50b238b770 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -65,3 +65,17 @@ config PAGE_POISONING_NO_SANITY If you are only interested in sanitization, say Y. Otherwise say N. + +config PAGE_POISONING_ZERO + bool "Use zero for poisoning instead of random data" + depends on PAGE_POISONING + ---help--- + Instead of using the existing poison value, fill the pages with + zeros. This makes it harder to detect when errors are occurring + due to sanitization but the zeroing at free means that it is + no longer necessary to write zeros when GFP_ZERO is used on + allocation. + + Enabling page poisoning with this option will disable hibernation + + If unsure, say N diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2a08349fbab2..50897dcaefdb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1405,15 +1405,24 @@ static inline int check_new_page(struct page *page) return 0; } +static inline bool free_pages_prezeroed(bool poisoned) +{ + return IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) && + page_poisoning_enabled() && poisoned; +} + static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, int alloc_flags) { int i; + bool poisoned = true; for (i = 0; i < (1 << order); i++) { struct page *p = page + i; if (unlikely(check_new_page(p))) return 1; + if (poisoned) + poisoned &= page_is_poisoned(p); } set_page_private(page, 0); @@ -1424,7 +1433,7 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, kernel_poison_pages(page, 1 << order, 1); kasan_alloc_pages(page, order); - if (gfp_flags & __GFP_ZERO) + if (!free_pages_prezeroed(poisoned) && (gfp_flags & __GFP_ZERO)) for (i = 0; i < (1 << order); i++) clear_highpage(page + i); diff --git a/mm/page_ext.c b/mm/page_ext.c index 292ca7b8debd..2d864e64f7fe 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -106,12 +106,15 @@ struct page_ext *lookup_page_ext(struct page *page) struct page_ext *base; base = NODE_DATA(page_to_nid(page))->node_page_ext; -#ifdef CONFIG_DEBUG_VM +#if defined(CONFIG_DEBUG_VM) || defined(CONFIG_PAGE_POISONING) /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. + * + * This check is also necessary for ensuring page poisoning + * works as expected when enabled */ if (unlikely(!base)) return NULL; @@ -180,12 +183,15 @@ struct page_ext *lookup_page_ext(struct page *page) { unsigned long pfn = page_to_pfn(page); struct mem_section *section = __pfn_to_section(pfn); -#ifdef CONFIG_DEBUG_VM +#if defined(CONFIG_DEBUG_VM) || defined(CONFIG_PAGE_POISONING) /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. + * + * This check is also necessary for ensuring page poisoning + * works as expected when enabled */ if (!section->page_ext) return NULL; diff --git a/mm/page_poison.c b/mm/page_poison.c index 89d3bc773633..479e7ea2bea6 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -71,11 +71,14 @@ static inline void clear_page_poison(struct page *page) __clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); } -static inline bool page_poison(struct page *page) +bool page_is_poisoned(struct page *page) { struct page_ext *page_ext; page_ext = lookup_page_ext(page); + if (!page_ext) + return false; + return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); } @@ -137,7 +140,7 @@ static void unpoison_page(struct page *page) { void *addr; - if (!page_poison(page)) + if (!page_is_poisoned(page)) return; addr = kmap_atomic(page); -- cgit v1.2.3 From 2213e9a66bb87d8344a1256b4ef568220d9587fb Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 15 Mar 2016 14:58:19 -0700 Subject: kallsyms: add support for relative offsets in kallsyms address table Similar to how relative extables are implemented, it is possible to emit the kallsyms table in such a way that it contains offsets relative to some anchor point in the kernel image rather than absolute addresses. On 64-bit architectures, it cuts the size of the kallsyms address table in half, since offsets between kernel symbols can typically be expressed in 32 bits. This saves several hundreds of kilobytes of permanent .rodata on average. In addition, the kallsyms address table is no longer subject to dynamic relocation when CONFIG_RELOCATABLE is in effect, so the relocation work done after decompression now doesn't have to do relocation updates for all these values. This saves up to 24 bytes (i.e., the size of a ELF64 RELA relocation table entry) per value, which easily adds up to a couple of megabytes of uncompressed __init data on ppc64 or arm64. Even if these relocation entries typically compress well, the combined size reduction of 2.8 MB uncompressed for a ppc64_defconfig build (of which 2.4 MB is __init data) results in a ~500 KB space saving in the compressed image. Since it is useful for some architectures (like x86) to retain the ability to emit absolute values as well, this patch also adds support for capturing both absolute and relative values when KALLSYMS_ABSOLUTE_PERCPU is in effect, by emitting absolute per-cpu addresses as positive 32-bit values, and addresses relative to the lowest encountered relative symbol as negative values, which are subtracted from the runtime address of this base symbol to produce the actual address. Support for the above is enabled by default for all architectures except IA-64 and Tile-GX, whose symbols are too far apart to capture in this manner. Signed-off-by: Ard Biesheuvel Tested-by: Guenter Roeck Reviewed-by: Kees Cook Tested-by: Kees Cook Cc: Heiko Carstens Cc: Michael Ellerman Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Benjamin Herrenschmidt Cc: Michal Marek Cc: Rusty Russell Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 18 +++++++++++ kernel/kallsyms.c | 42 ++++++++++++++++++++------ scripts/kallsyms.c | 79 ++++++++++++++++++++++++++++++++++++++++++------- scripts/link-vmlinux.sh | 4 +++ scripts/namespace.pl | 2 ++ 5 files changed, 126 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/init/Kconfig b/init/Kconfig index b17824a875fa..fd664b3ab99e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1424,6 +1424,24 @@ config KALLSYMS_ABSOLUTE_PERCPU bool default X86_64 && SMP +config KALLSYMS_BASE_RELATIVE + bool + depends on KALLSYMS + default !IA64 && !(TILE && 64BIT) + help + Instead of emitting them as absolute values in the native word size, + emit the symbol references in the kallsyms table as 32-bit entries, + each containing a relative value in the range [base, base + U32_MAX] + or, when KALLSYMS_ABSOLUTE_PERCPU is in effect, each containing either + an absolute value in the range [0, S32_MAX] or a relative value in the + range [base, base + S32_MAX], where base is the lowest relative symbol + address encountered in the image. + + On 64-bit builds, this reduces the size of the address table by 50%, + but more importantly, it results in entries whose values are build + time constants, and no relocation pass is required at runtime to fix + up the entries based on the runtime load address of the kernel. + config PRINTK default y bool "Enable support for printk" if EXPERT diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 5c5987f10819..fafd1a3ef0da 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -38,6 +38,7 @@ * during the second link stage. */ extern const unsigned long kallsyms_addresses[] __weak; +extern const int kallsyms_offsets[] __weak; extern const u8 kallsyms_names[] __weak; /* @@ -47,6 +48,9 @@ extern const u8 kallsyms_names[] __weak; extern const unsigned long kallsyms_num_syms __attribute__((weak, section(".rodata"))); +extern const unsigned long kallsyms_relative_base +__attribute__((weak, section(".rodata"))); + extern const u8 kallsyms_token_table[] __weak; extern const u16 kallsyms_token_index[] __weak; @@ -176,6 +180,23 @@ static unsigned int get_symbol_offset(unsigned long pos) return name - kallsyms_names; } +static unsigned long kallsyms_sym_address(int idx) +{ + if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE)) + return kallsyms_addresses[idx]; + + /* values are unsigned offsets if --absolute-percpu is not in effect */ + if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU)) + return kallsyms_relative_base + (u32)kallsyms_offsets[idx]; + + /* ...otherwise, positive offsets are absolute values */ + if (kallsyms_offsets[idx] >= 0) + return kallsyms_offsets[idx]; + + /* ...and negative offsets are relative to kallsyms_relative_base - 1 */ + return kallsyms_relative_base - 1 - kallsyms_offsets[idx]; +} + /* Lookup the address for this symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name) { @@ -187,7 +208,7 @@ unsigned long kallsyms_lookup_name(const char *name) off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); if (strcmp(namebuf, name) == 0) - return kallsyms_addresses[i]; + return kallsyms_sym_address(i); } return module_kallsyms_lookup_name(name); } @@ -204,7 +225,7 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, for (i = 0, off = 0; i < kallsyms_num_syms; i++) { off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - ret = fn(data, namebuf, NULL, kallsyms_addresses[i]); + ret = fn(data, namebuf, NULL, kallsyms_sym_address(i)); if (ret != 0) return ret; } @@ -220,7 +241,10 @@ static unsigned long get_symbol_pos(unsigned long addr, unsigned long i, low, high, mid; /* This kernel should never had been booted. */ - BUG_ON(!kallsyms_addresses); + if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE)) + BUG_ON(!kallsyms_addresses); + else + BUG_ON(!kallsyms_offsets); /* Do a binary search on the sorted kallsyms_addresses array. */ low = 0; @@ -228,7 +252,7 @@ static unsigned long get_symbol_pos(unsigned long addr, while (high - low > 1) { mid = low + (high - low) / 2; - if (kallsyms_addresses[mid] <= addr) + if (kallsyms_sym_address(mid) <= addr) low = mid; else high = mid; @@ -238,15 +262,15 @@ static unsigned long get_symbol_pos(unsigned long addr, * Search for the first aliased symbol. Aliased * symbols are symbols with the same address. */ - while (low && kallsyms_addresses[low-1] == kallsyms_addresses[low]) + while (low && kallsyms_sym_address(low-1) == kallsyms_sym_address(low)) --low; - symbol_start = kallsyms_addresses[low]; + symbol_start = kallsyms_sym_address(low); /* Search for next non-aliased symbol. */ for (i = low + 1; i < kallsyms_num_syms; i++) { - if (kallsyms_addresses[i] > symbol_start) { - symbol_end = kallsyms_addresses[i]; + if (kallsyms_sym_address(i) > symbol_start) { + symbol_end = kallsyms_sym_address(i); break; } } @@ -470,7 +494,7 @@ static unsigned long get_ksymbol_core(struct kallsym_iter *iter) unsigned off = iter->nameoff; iter->module_name[0] = '\0'; - iter->value = kallsyms_addresses[iter->pos]; + iter->value = kallsyms_sym_address(iter->pos); iter->type = kallsyms_get_symbol_type(off); diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index d39a1eeb080e..638b143ee60f 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -22,6 +22,7 @@ #include #include #include +#include #ifndef ARRAY_SIZE #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0])) @@ -43,6 +44,7 @@ struct addr_range { }; static unsigned long long _text; +static unsigned long long relative_base; static struct addr_range text_ranges[] = { { "_stext", "_etext" }, { "_sinittext", "_einittext" }, @@ -62,6 +64,7 @@ static int all_symbols = 0; static int absolute_percpu = 0; static char symbol_prefix_char = '\0'; static unsigned long long kernel_start_addr = 0; +static int base_relative = 0; int token_profit[0x10000]; @@ -75,7 +78,7 @@ static void usage(void) fprintf(stderr, "Usage: kallsyms [--all-symbols] " "[--symbol-prefix=] " "[--page-offset=] " - "< in.map > out.S\n"); + "[--base-relative] < in.map > out.S\n"); exit(1); } @@ -205,6 +208,8 @@ static int symbol_valid(struct sym_entry *s) */ static char *special_symbols[] = { "kallsyms_addresses", + "kallsyms_offsets", + "kallsyms_relative_base", "kallsyms_num_syms", "kallsyms_names", "kallsyms_markers", @@ -349,16 +354,48 @@ static void write_src(void) printf("\t.section .rodata, \"a\"\n"); - /* Provide proper symbols relocatability by their '_text' - * relativeness. The symbol names cannot be used to construct - * normal symbol references as the list of symbols contains - * symbols that are declared static and are private to their - * .o files. This prevents .tmp_kallsyms.o or any other - * object from referencing them. + /* Provide proper symbols relocatability by their relativeness + * to a fixed anchor point in the runtime image, either '_text' + * for absolute address tables, in which case the linker will + * emit the final addresses at build time. Otherwise, use the + * offset relative to the lowest value encountered of all relative + * symbols, and emit non-relocatable fixed offsets that will be fixed + * up at runtime. + * + * The symbol names cannot be used to construct normal symbol + * references as the list of symbols contains symbols that are + * declared static and are private to their .o files. This prevents + * .tmp_kallsyms.o or any other object from referencing them. */ - output_label("kallsyms_addresses"); + if (!base_relative) + output_label("kallsyms_addresses"); + else + output_label("kallsyms_offsets"); + for (i = 0; i < table_cnt; i++) { - if (!symbol_absolute(&table[i])) { + if (base_relative) { + long long offset; + int overflow; + + if (!absolute_percpu) { + offset = table[i].addr - relative_base; + overflow = (offset < 0 || offset > UINT_MAX); + } else if (symbol_absolute(&table[i])) { + offset = table[i].addr; + overflow = (offset < 0 || offset > INT_MAX); + } else { + offset = relative_base - table[i].addr - 1; + overflow = (offset < INT_MIN || offset >= 0); + } + if (overflow) { + fprintf(stderr, "kallsyms failure: " + "%s symbol value %#llx out of range in relative mode\n", + symbol_absolute(&table[i]) ? "absolute" : "relative", + table[i].addr); + exit(EXIT_FAILURE); + } + printf("\t.long\t%#x\n", (int)offset); + } else if (!symbol_absolute(&table[i])) { if (_text <= table[i].addr) printf("\tPTR\t_text + %#llx\n", table[i].addr - _text); @@ -371,6 +408,12 @@ static void write_src(void) } printf("\n"); + if (base_relative) { + output_label("kallsyms_relative_base"); + printf("\tPTR\t_text - %#llx\n", _text - relative_base); + printf("\n"); + } + output_label("kallsyms_num_syms"); printf("\tPTR\t%d\n", table_cnt); printf("\n"); @@ -695,6 +738,18 @@ static void make_percpus_absolute(void) } } +/* find the minimum non-absolute symbol address */ +static void record_relative_base(void) +{ + unsigned int i; + + relative_base = -1ULL; + for (i = 0; i < table_cnt; i++) + if (!symbol_absolute(&table[i]) && + table[i].addr < relative_base) + relative_base = table[i].addr; +} + int main(int argc, char **argv) { if (argc >= 2) { @@ -713,7 +768,9 @@ int main(int argc, char **argv) } else if (strncmp(argv[i], "--page-offset=", 14) == 0) { const char *p = &argv[i][14]; kernel_start_addr = strtoull(p, NULL, 16); - } else + } else if (strcmp(argv[i], "--base-relative") == 0) + base_relative = 1; + else usage(); } } else if (argc != 1) @@ -722,6 +779,8 @@ int main(int argc, char **argv) read_map(stdin); if (absolute_percpu) make_percpus_absolute(); + if (base_relative) + record_relative_base(); sort_symbols(); optimize_token_table(); write_src(); diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 7a08bf9a9576..453ede9d2f3d 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -90,6 +90,10 @@ kallsyms() kallsymopt="${kallsymopt} --absolute-percpu" fi + if [ -n "${CONFIG_KALLSYMS_BASE_RELATIVE}" ]; then + kallsymopt="${kallsymopt} --base-relative" + fi + local aflags="${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} \ ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS}" diff --git a/scripts/namespace.pl b/scripts/namespace.pl index a71be6b7cdec..9f3c9d47a4a5 100755 --- a/scripts/namespace.pl +++ b/scripts/namespace.pl @@ -117,6 +117,8 @@ my %nameexception = ( 'kallsyms_names' => 1, 'kallsyms_num_syms' => 1, 'kallsyms_addresses'=> 1, + 'kallsyms_offsets' => 1, + 'kallsyms_relative_base'=> 1, '__this_module' => 1, '_etext' => 1, '_edata' => 1, -- cgit v1.2.3 From 2b021cbf3cb6208f0d40fd2f1869f237934340ed Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 15 Mar 2016 20:43:04 -0400 Subject: cgroup: ignore css_sets associated with dead cgroups during migration Before 2e91fa7f6d45 ("cgroup: keep zombies associated with their original cgroups"), all dead tasks were associated with init_css_set. If a zombie task is requested for migration, while migration prep operations would still be performed on init_css_set, the actual migration would ignore zombie tasks. As init_css_set is always valid, this worked fine. However, after 2e91fa7f6d45, zombie tasks stay with the css_set it was associated with at the time of death. Let's say a task T associated with cgroup A on hierarchy H-1 and cgroup B on hiearchy H-2. After T becomes a zombie, it would still remain associated with A and B. If A only contains zombie tasks, it can be removed. On removal, A gets marked offline but stays pinned until all zombies are drained. At this point, if migration is initiated on T to a cgroup C on hierarchy H-2, migration path would try to prepare T's css_set for migration and trigger the following. WARNING: CPU: 0 PID: 1576 at kernel/cgroup.c:474 cgroup_get+0x121/0x160() CPU: 0 PID: 1576 Comm: bash Not tainted 4.4.0-work+ #289 ... Call Trace: [] dump_stack+0x4e/0x82 [] warn_slowpath_common+0x78/0xb0 [] warn_slowpath_null+0x15/0x20 [] cgroup_get+0x121/0x160 [] link_css_set+0x7b/0x90 [] find_css_set+0x3bc/0x5e0 [] cgroup_migrate_prepare_dst+0x89/0x1f0 [] cgroup_attach_task+0x157/0x230 [] __cgroup_procs_write+0x2b7/0x470 [] cgroup_tasks_write+0xc/0x10 [] cgroup_file_write+0x30/0x1b0 [] kernfs_fop_write+0x13c/0x180 [] __vfs_write+0x23/0xe0 [] vfs_write+0xa4/0x1a0 [] SyS_write+0x44/0xa0 [] entry_SYSCALL_64_fastpath+0x12/0x6f It doesn't make sense to prepare migration for css_sets pointing to dead cgroups as they are guaranteed to contain only zombies which are ignored later during migration. This patch makes cgroup destruction path mark all affected css_sets as dead and updates the migration path to ignore them during preparation. Signed-off-by: Tejun Heo Fixes: 2e91fa7f6d45 ("cgroup: keep zombies associated with their original cgroups") Cc: stable@vger.kernel.org # v4.4+ --- include/linux/cgroup-defs.h | 3 +++ kernel/cgroup.c | 20 ++++++++++++++++++-- 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 34b42f03fcd8..3e39ae5bc799 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -212,6 +212,9 @@ struct css_set { /* all css_task_iters currently walking this cset */ struct list_head task_iters; + /* dead and being drained, ignore for migration */ + bool dead; + /* For RCU-protected deletion */ struct rcu_head rcu_head; }; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e22df5d81e59..d57318950076 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2516,6 +2516,14 @@ static void cgroup_migrate_add_src(struct css_set *src_cset, lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); + /* + * If ->dead, @src_set is associated with one or more dead cgroups + * and doesn't contain any migratable tasks. Ignore it early so + * that the rest of migration path doesn't get confused by it. + */ + if (src_cset->dead) + return; + src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); if (!list_empty(&src_cset->mg_preload_node)) @@ -5258,6 +5266,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { struct cgroup_subsys_state *css; + struct cgrp_cset_link *link; int ssid; lockdep_assert_held(&cgroup_mutex); @@ -5278,11 +5287,18 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) return -EBUSY; /* - * Mark @cgrp dead. This prevents further task migration and child - * creation by disabling cgroup_lock_live_group(). + * Mark @cgrp and the associated csets dead. The former prevents + * further task migration and child creation by disabling + * cgroup_lock_live_group(). The latter makes the csets ignored by + * the migration path. */ cgrp->self.flags &= ~CSS_ONLINE; + spin_lock_bh(&css_set_lock); + list_for_each_entry(link, &cgrp->cset_links, cset_link) + link->cset->dead = true; + spin_unlock_bh(&css_set_lock); + /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) kill_css(css); -- cgit v1.2.3 From cfe02a8a973e7e5f66926b8ae38dfce404b19e29 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 15 Mar 2016 00:21:06 +0100 Subject: cgroup: avoid false positive gcc-6 warning When all subsystems are disabled, gcc notices that cgroup_subsys_enabled_key is a zero-length array and that any access to it must be out of bounds: In file included from ../include/linux/cgroup.h:19:0, from ../kernel/cgroup.c:31: ../kernel/cgroup.c: In function 'cgroup_add_cftypes': ../kernel/cgroup.c:261:53: error: array subscript is above array bounds [-Werror=array-bounds] return static_key_enabled(cgroup_subsys_enabled_key[ssid]); ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~ ../include/linux/jump_label.h:271:40: note: in definition of macro 'static_key_enabled' static_key_count((struct static_key *)x) > 0; \ ^ We should never call the function in this particular case, so this is not a bug. In order to silence the warning, this adds an explicit check for the CGROUP_SUBSYS_COUNT==0 case. Signed-off-by: Arnd Bergmann Signed-off-by: Tejun Heo --- kernel/cgroup.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d57318950076..3fe02c152799 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -246,6 +246,9 @@ static int cgroup_addrm_files(struct cgroup_subsys_state *css, */ static bool cgroup_ssid_enabled(int ssid) { + if (CGROUP_SUBSYS_COUNT == 0) + return false; + return static_key_enabled(cgroup_subsys_enabled_key[ssid]); } -- cgit v1.2.3 From 4c973d1620ae08f5cbe27644c5f5b974c8f594ec Mon Sep 17 00:00:00 2001 From: Jessica Yu Date: Wed, 16 Mar 2016 20:55:38 -0400 Subject: modules: split part of complete_formation() into prepare_coming_module() Put all actions in complete_formation() that are performed after module->state is set to MODULE_STATE_COMING into a separate function prepare_coming_module(). This split prepares for the removal of the livepatch module notifiers in favor of hard-coding function calls to klp_module_{coming,going} in the module loader. The complete_formation -> prepare_coming_module split will also make error handling easier since we can jump to the appropriate error label to do any module GOING cleanup after all the COMING-actions have completed. Signed-off-by: Jessica Yu Reviewed-by: Josh Poimboeuf Reviewed-by: Petr Mladek Acked-by: Rusty Russell Signed-off-by: Jiri Kosina --- kernel/module.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index 794ebe8e878d..6dbfad415d51 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3392,9 +3392,6 @@ static int complete_formation(struct module *mod, struct load_info *info) mod->state = MODULE_STATE_COMING; mutex_unlock(&module_mutex); - ftrace_module_enable(mod); - blocking_notifier_call_chain(&module_notify_list, - MODULE_STATE_COMING, mod); return 0; out: @@ -3402,6 +3399,14 @@ out: return err; } +static int prepare_coming_module(struct module *mod) +{ + ftrace_module_enable(mod); + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_COMING, mod); + return 0; +} + static int unknown_module_param_cb(char *param, char *val, const char *modname, void *arg) { @@ -3516,13 +3521,17 @@ static int load_module(struct load_info *info, const char __user *uargs, if (err) goto ddebug_cleanup; + err = prepare_coming_module(mod); + if (err) + goto bug_cleanup; + /* Module is ready to execute: parsing args may do that. */ after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, -32768, 32767, mod, unknown_module_param_cb); if (IS_ERR(after_dashes)) { err = PTR_ERR(after_dashes); - goto bug_cleanup; + goto coming_cleanup; } else if (after_dashes) { pr_warn("%s: parameters '%s' after `--' ignored\n", mod->name, after_dashes); @@ -3531,7 +3540,7 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Link in to syfs. */ err = mod_sysfs_setup(mod, info, mod->kp, mod->num_kp); if (err < 0) - goto bug_cleanup; + goto coming_cleanup; /* Get rid of temporary copy. */ free_copy(info); @@ -3541,15 +3550,16 @@ static int load_module(struct load_info *info, const char __user *uargs, return do_init_module(mod); + coming_cleanup: + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_GOING, mod); + bug_cleanup: /* module_bug_cleanup needs module_mutex protection */ mutex_lock(&module_mutex); module_bug_cleanup(mod); mutex_unlock(&module_mutex); - blocking_notifier_call_chain(&module_notify_list, - MODULE_STATE_GOING, mod); - /* we can't deallocate the module until we clear memory protection */ module_disable_ro(mod); module_disable_nx(mod); -- cgit v1.2.3 From 7e545d6eca20ce8ef7f66a63146cbff82b2ba760 Mon Sep 17 00:00:00 2001 From: Jessica Yu Date: Wed, 16 Mar 2016 20:55:39 -0400 Subject: livepatch/module: remove livepatch module notifier Remove the livepatch module notifier in favor of directly enabling and disabling patches to modules in the module loader. Hard-coding the function calls ensures that ftrace_module_enable() is run before klp_module_coming() during module load, and that klp_module_going() is run before ftrace_release_mod() during module unload. This way, ftrace and livepatch code is run in the correct order during the module load/unload sequence without dependence on the module notifier call chain. Signed-off-by: Jessica Yu Reviewed-by: Petr Mladek Acked-by: Josh Poimboeuf Acked-by: Rusty Russell Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 13 ++++ kernel/livepatch/core.c | 147 ++++++++++++++++++++++------------------------ kernel/module.c | 10 ++++ 3 files changed, 94 insertions(+), 76 deletions(-) (limited to 'kernel') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index c05679701e10..bd830d590465 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -24,6 +24,8 @@ #include #include +#if IS_ENABLED(CONFIG_LIVEPATCH) + #include enum klp_state { @@ -132,4 +134,15 @@ int klp_unregister_patch(struct klp_patch *); int klp_enable_patch(struct klp_patch *); int klp_disable_patch(struct klp_patch *); +/* Called from the module loader during module coming/going states */ +int klp_module_coming(struct module *mod); +void klp_module_going(struct module *mod); + +#else /* !CONFIG_LIVEPATCH */ + +static inline int klp_module_coming(struct module *mod) { return 0; } +static inline void klp_module_going(struct module *mod) { } + +#endif /* CONFIG_LIVEPATCH */ + #endif /* _LINUX_LIVEPATCH_H_ */ diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 780f00cdb7e5..d68fbf63b083 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -99,12 +99,12 @@ static void klp_find_object_module(struct klp_object *obj) /* * We do not want to block removal of patched modules and therefore * we do not take a reference here. The patches are removed by - * a going module handler instead. + * klp_module_going() instead. */ mod = find_module(obj->name); /* - * Do not mess work of the module coming and going notifiers. - * Note that the patch might still be needed before the going handler + * Do not mess work of klp_module_coming() and klp_module_going(). + * Note that the patch might still be needed before klp_module_going() * is called. Module functions can be called even in the GOING state * until mod->exit() finishes. This is especially important for * patches that modify semantic of the functions. @@ -866,103 +866,108 @@ int klp_register_patch(struct klp_patch *patch) } EXPORT_SYMBOL_GPL(klp_register_patch); -static int klp_module_notify_coming(struct klp_patch *patch, - struct klp_object *obj) +int klp_module_coming(struct module *mod) { - struct module *pmod = patch->mod; - struct module *mod = obj->mod; int ret; + struct klp_patch *patch; + struct klp_object *obj; - ret = klp_init_object_loaded(patch, obj); - if (ret) { - pr_warn("failed to initialize patch '%s' for module '%s' (%d)\n", - pmod->name, mod->name, ret); - return ret; - } + if (WARN_ON(mod->state != MODULE_STATE_COMING)) + return -EINVAL; - if (patch->state == KLP_DISABLED) - return 0; + mutex_lock(&klp_mutex); + /* + * Each module has to know that klp_module_coming() + * has been called. We never know what module will + * get patched by a new patch. + */ + mod->klp_alive = true; - pr_notice("applying patch '%s' to loading module '%s'\n", - pmod->name, mod->name); + list_for_each_entry(patch, &klp_patches, list) { + klp_for_each_object(patch, obj) { + if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) + continue; - ret = klp_enable_object(obj); - if (ret) - pr_warn("failed to apply patch '%s' to module '%s' (%d)\n", - pmod->name, mod->name, ret); - return ret; -} + obj->mod = mod; -static void klp_module_notify_going(struct klp_patch *patch, - struct klp_object *obj) -{ - struct module *pmod = patch->mod; - struct module *mod = obj->mod; + ret = klp_init_object_loaded(patch, obj); + if (ret) { + pr_warn("failed to initialize patch '%s' for module '%s' (%d)\n", + patch->mod->name, obj->mod->name, ret); + goto err; + } - if (patch->state == KLP_DISABLED) - goto disabled; + if (patch->state == KLP_DISABLED) + break; + + pr_notice("applying patch '%s' to loading module '%s'\n", + patch->mod->name, obj->mod->name); + + ret = klp_enable_object(obj); + if (ret) { + pr_warn("failed to apply patch '%s' to module '%s' (%d)\n", + patch->mod->name, obj->mod->name, ret); + goto err; + } + + break; + } + } - pr_notice("reverting patch '%s' on unloading module '%s'\n", - pmod->name, mod->name); + mutex_unlock(&klp_mutex); - klp_disable_object(obj); + return 0; -disabled: +err: + /* + * If a patch is unsuccessfully applied, return + * error to the module loader. + */ + pr_warn("patch '%s' failed for module '%s', refusing to load module '%s'\n", + patch->mod->name, obj->mod->name, obj->mod->name); + mod->klp_alive = false; klp_free_object_loaded(obj); + mutex_unlock(&klp_mutex); + + return ret; } -static int klp_module_notify(struct notifier_block *nb, unsigned long action, - void *data) +void klp_module_going(struct module *mod) { - int ret; - struct module *mod = data; struct klp_patch *patch; struct klp_object *obj; - if (action != MODULE_STATE_COMING && action != MODULE_STATE_GOING) - return 0; + if (WARN_ON(mod->state != MODULE_STATE_GOING && + mod->state != MODULE_STATE_COMING)) + return; mutex_lock(&klp_mutex); - /* - * Each module has to know that the notifier has been called. - * We never know what module will get patched by a new patch. + * Each module has to know that klp_module_going() + * has been called. We never know what module will + * get patched by a new patch. */ - if (action == MODULE_STATE_COMING) - mod->klp_alive = true; - else /* MODULE_STATE_GOING */ - mod->klp_alive = false; + mod->klp_alive = false; list_for_each_entry(patch, &klp_patches, list) { klp_for_each_object(patch, obj) { if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) continue; - if (action == MODULE_STATE_COMING) { - obj->mod = mod; - ret = klp_module_notify_coming(patch, obj); - if (ret) { - obj->mod = NULL; - pr_warn("patch '%s' is in an inconsistent state!\n", - patch->mod->name); - } - } else /* MODULE_STATE_GOING */ - klp_module_notify_going(patch, obj); + if (patch->state != KLP_DISABLED) { + pr_notice("reverting patch '%s' on unloading module '%s'\n", + patch->mod->name, obj->mod->name); + klp_disable_object(obj); + } + klp_free_object_loaded(obj); break; } } mutex_unlock(&klp_mutex); - - return 0; } -static struct notifier_block klp_module_nb = { - .notifier_call = klp_module_notify, - .priority = INT_MIN+1, /* called late but before ftrace notifier */ -}; - static int __init klp_init(void) { int ret; @@ -973,21 +978,11 @@ static int __init klp_init(void) return -EINVAL; } - ret = register_module_notifier(&klp_module_nb); - if (ret) - return ret; - klp_root_kobj = kobject_create_and_add("livepatch", kernel_kobj); - if (!klp_root_kobj) { - ret = -ENOMEM; - goto unregister; - } + if (!klp_root_kobj) + return -ENOMEM; return 0; - -unregister: - unregister_module_notifier(&klp_module_nb); - return ret; } module_init(klp_init); diff --git a/kernel/module.c b/kernel/module.c index 6dbfad415d51..4b65fbb10bdc 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include #include @@ -984,6 +985,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, mod->exit(); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + klp_module_going(mod); ftrace_release_mod(mod); async_synchronize_full(); @@ -3315,6 +3317,7 @@ fail: module_put(mod); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + klp_module_going(mod); ftrace_release_mod(mod); free_module(mod); wake_up_all(&module_wq); @@ -3401,7 +3404,13 @@ out: static int prepare_coming_module(struct module *mod) { + int err; + ftrace_module_enable(mod); + err = klp_module_coming(mod); + if (err) + return err; + blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_COMING, mod); return 0; @@ -3553,6 +3562,7 @@ static int load_module(struct load_info *info, const char __user *uargs, coming_cleanup: blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + klp_module_going(mod); bug_cleanup: /* module_bug_cleanup needs module_mutex protection */ -- cgit v1.2.3 From a1ee1932aa6bea0bb074f5e3ced112664e4637ed Mon Sep 17 00:00:00 2001 From: Joshua Hunt Date: Thu, 17 Mar 2016 14:17:23 -0700 Subject: watchdog: don't run proc_watchdog_update if new value is same as old While working on a script to restore all sysctl params before a series of tests I found that writing any value into the /proc/sys/kernel/{nmi_watchdog,soft_watchdog,watchdog,watchdog_thresh} causes them to call proc_watchdog_update(). NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter. NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter. NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter. NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter. There doesn't appear to be a reason for doing this work every time a write occurs, so only do it when the values change. Signed-off-by: Josh Hunt Acked-by: Don Zickus Reviewed-by: Aaron Tomlin Cc: Ulrich Obergfell Cc: [4.1.x+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/watchdog.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/watchdog.c b/kernel/watchdog.c index b3ace6ebbba3..9acb29f280ec 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -923,6 +923,9 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, * both lockup detectors are disabled if proc_watchdog_update() * returns an error. */ + if (old == new) + goto out; + err = proc_watchdog_update(); } out: @@ -967,7 +970,7 @@ int proc_soft_watchdog(struct ctl_table *table, int write, int proc_watchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old; + int err, old, new; get_online_cpus(); mutex_lock(&watchdog_proc_mutex); @@ -987,6 +990,10 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, /* * Update the sample period. Restore on failure. */ + new = ACCESS_ONCE(watchdog_thresh); + if (old == new) + goto out; + set_sample_period(); err = proc_watchdog_update(); if (err) { -- cgit v1.2.3 From 12580e4b54ba8a1b22ec977c200be0174ca42348 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 17 Mar 2016 14:17:38 -0700 Subject: mm: memcontrol: report kernel stack usage in cgroup2 memory.stat Show how much memory is allocated to kernel stacks. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroup-v2.txt | 4 ++++ include/linux/memcontrol.h | 3 ++- kernel/fork.c | 10 +++++++++- mm/memcontrol.c | 2 ++ 4 files changed, 17 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt index e4e0c1d78cee..e2f4e7948a66 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -843,6 +843,10 @@ PAGE_SIZE multiple when read back. Amount of memory used to cache filesystem data, including tmpfs and shared memory. + kernel_stack + + Amount of memory allocated to kernel stacks. + slab Amount of memory used for storing in-kernel data diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e7af4834ffea..d6300313b298 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -52,9 +52,10 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, /* default hierarchy stats */ - MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS, + MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS, MEMCG_SLAB_RECLAIMABLE, MEMCG_SLAB_UNRECLAIMABLE, + MEMCG_SOCK, MEMCG_NR_STAT, }; diff --git a/kernel/fork.c b/kernel/fork.c index 2e391c754ae7..accb7221d547 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -164,12 +164,20 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); + if (page) + memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, + 1 << THREAD_SIZE_ORDER); + return page ? page_address(page) : NULL; } static inline void free_thread_info(struct thread_info *ti) { - free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); + struct page *page = virt_to_page(ti); + + memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, + -(1 << THREAD_SIZE_ORDER)); + __free_kmem_pages(page, THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_info_cache; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3ad64bf464fd..4b7dda7c2e74 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5106,6 +5106,8 @@ static int memory_stat_show(struct seq_file *m, void *v) (u64)stat[MEM_CGROUP_STAT_RSS] * PAGE_SIZE); seq_printf(m, "file %llu\n", (u64)stat[MEM_CGROUP_STAT_CACHE] * PAGE_SIZE); + seq_printf(m, "kernel_stack %llu\n", + (u64)stat[MEMCG_KERNEL_STACK] * PAGE_SIZE); seq_printf(m, "slab %llu\n", (u64)(stat[MEMCG_SLAB_RECLAIMABLE] + stat[MEMCG_SLAB_UNRECLAIMABLE]) * PAGE_SIZE); -- cgit v1.2.3 From 795ae7a0de6b834a0cc202aa55c190ef81496665 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 17 Mar 2016 14:19:14 -0700 Subject: mm: scale kswapd watermarks in proportion to memory In machines with 140G of memory and enterprise flash storage, we have seen read and write bursts routinely exceed the kswapd watermarks and cause thundering herds in direct reclaim. Unfortunately, the only way to tune kswapd aggressiveness is through adjusting min_free_kbytes - the system's emergency reserves - which is entirely unrelated to the system's latency requirements. In order to get kswapd to maintain a 250M buffer of free memory, the emergency reserves need to be set to 1G. That is a lot of memory wasted for no good reason. On the other hand, it's reasonable to assume that allocation bursts and overall allocation concurrency scale with memory capacity, so it makes sense to make kswapd aggressiveness a function of that as well. Change the kswapd watermark scale factor from the currently fixed 25% of the tunable emergency reserve to a tunable 0.1% of memory. Beyond 1G of memory, this will produce bigger watermark steps than the current formula in default settings. Ensure that the new formula never chooses steps smaller than that, i.e. 25% of the emergency reserve. On a 140G machine, this raises the default watermark steps - the distance between min and low, and low and high - from 16M to 143M. Signed-off-by: Johannes Weiner Acked-by: Mel Gorman Acked-by: Rik van Riel Acked-by: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 18 ++++++++++++++++++ include/linux/mm.h | 1 + include/linux/mmzone.h | 2 ++ kernel/sysctl.c | 10 ++++++++++ mm/page_alloc.c | 29 +++++++++++++++++++++++++++-- 5 files changed, 58 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 89a887c76629..cb0368459da3 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -803,6 +803,24 @@ performance impact. Reclaim code needs to take various locks to find freeable directory and inode objects. With vfs_cache_pressure=1000, it will look for ten times more freeable objects than there are. +============================================================= + +watermark_scale_factor: + +This factor controls the aggressiveness of kswapd. It defines the +amount of memory left in a node/system before kswapd is woken up and +how much memory needs to be free before kswapd goes back to sleep. + +The unit is in fractions of 10,000. The default value of 10 means the +distances between watermarks are 0.1% of the available memory in the +node/system. The maximum value is 1000, or 10% of memory. + +A high rate of threads entering direct reclaim (allocstall) or kswapd +going to sleep prematurely (kswapd_low_wmark_hit_quickly) can indicate +that the number of free pages kswapd maintains for latency reasons is +too small for the allocation bursts occurring in the system. This knob +can then be used to tune kswapd aggressiveness accordingly. + ============================================================== zone_reclaim_mode: diff --git a/include/linux/mm.h b/include/linux/mm.h index 75d1907b9009..f7fd64227d3a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1889,6 +1889,7 @@ extern void zone_pcp_reset(struct zone *zone); /* page_alloc.c */ extern int min_free_kbytes; +extern int watermark_scale_factor; /* nommu.c */ extern atomic_long_t mmap_pages_allocated; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bdd9a270a813..c60df9257cc7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -841,6 +841,8 @@ static inline int is_highmem(struct zone *zone) struct ctl_table; int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, + void __user *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f5102fabef7f..725587f10667 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -126,6 +126,7 @@ static int __maybe_unused two = 2; static int __maybe_unused four = 4; static unsigned long one_ul = 1; static int one_hundred = 100; +static int one_thousand = 1000; #ifdef CONFIG_PRINTK static int ten_thousand = 10000; #endif @@ -1403,6 +1404,15 @@ static struct ctl_table vm_table[] = { .proc_handler = min_free_kbytes_sysctl_handler, .extra1 = &zero, }, + { + .procname = "watermark_scale_factor", + .data = &watermark_scale_factor, + .maxlen = sizeof(watermark_scale_factor), + .mode = 0644, + .proc_handler = watermark_scale_factor_sysctl_handler, + .extra1 = &one, + .extra2 = &one_thousand, + }, { .procname = "percpu_pagelist_fraction", .data = &percpu_pagelist_fraction, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 941b802e11ec..d156310aedeb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -249,6 +249,7 @@ compound_page_dtor * const compound_page_dtors[] = { int min_free_kbytes = 1024; int user_min_free_kbytes = -1; +int watermark_scale_factor = 10; static unsigned long __meminitdata nr_kernel_pages; static unsigned long __meminitdata nr_all_pages; @@ -6347,8 +6348,17 @@ static void __setup_per_zone_wmarks(void) zone->watermark[WMARK_MIN] = tmp; } - zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); - zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); + /* + * Set the kswapd watermarks distance according to the + * scale factor in proportion to available memory, but + * ensure a minimum size on small systems. + */ + tmp = max_t(u64, tmp >> 2, + mult_frac(zone->managed_pages, + watermark_scale_factor, 10000)); + + zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp; + zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2; __mod_zone_page_state(zone, NR_ALLOC_BATCH, high_wmark_pages(zone) - low_wmark_pages(zone) - @@ -6489,6 +6499,21 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, return 0; } +int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + if (write) + setup_per_zone_wmarks(); + + return 0; +} + #ifdef CONFIG_NUMA int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) -- cgit v1.2.3 From da8b44d5a9f8bf26da637b7336508ca534d6b319 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 17 Mar 2016 14:20:51 -0700 Subject: timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc//timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc//timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz Cc: Arjan van de Ven Cc: Thomas Gleixner Cc: Oren Laadan Cc: Ruchi Kandoi Cc: Rom Lemarchand Cc: Kees Cook Cc: Android Kernel Team Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventpoll.c | 2 +- fs/select.c | 8 ++++---- include/linux/freezer.h | 2 +- include/linux/hrtimer.h | 12 +++++++----- include/linux/poll.h | 2 +- include/linux/sched.h | 4 ++-- kernel/sys.c | 5 ++++- kernel/time/hrtimer.c | 8 ++++---- kernel/time/timer.c | 4 ++-- 9 files changed, 26 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/fs/eventpoll.c b/fs/eventpoll.c index cde60741cad2..8a74a2a52e0f 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1616,7 +1616,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, { int res = 0, eavail, timed_out = 0; unsigned long flags; - long slack = 0; + u64 slack = 0; wait_queue_t wait; ktime_t expires, *to = NULL; diff --git a/fs/select.c b/fs/select.c index 79d0d4953cad..869293988c2a 100644 --- a/fs/select.c +++ b/fs/select.c @@ -70,9 +70,9 @@ static long __estimate_accuracy(struct timespec *tv) return slack; } -long select_estimate_accuracy(struct timespec *tv) +u64 select_estimate_accuracy(struct timespec *tv) { - unsigned long ret; + u64 ret; struct timespec now; /* @@ -402,7 +402,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) struct poll_wqueues table; poll_table *wait; int retval, i, timed_out = 0; - unsigned long slack = 0; + u64 slack = 0; unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_end = 0; @@ -784,7 +784,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait, poll_table* pt = &wait->pt; ktime_t expire, *to = NULL; int timed_out = 0, count = 0; - unsigned long slack = 0; + u64 slack = 0; unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_end = 0; diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 6b7fd9cf5ea2..dd03e837ebb7 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -231,7 +231,7 @@ static inline long freezable_schedule_timeout_killable_unsafe(long timeout) * call this with locks held. */ static inline int freezable_schedule_hrtimeout_range(ktime_t *expires, - unsigned long delta, const enum hrtimer_mode mode) + u64 delta, const enum hrtimer_mode mode) { int __retval; freezer_do_not_count(); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 2ead22dd74a0..c98c6539e2c2 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -220,7 +220,7 @@ static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time timer->node.expires = ktime_add_safe(time, delta); } -static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta) +static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); @@ -378,7 +378,7 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } /* Basic timer operations: */ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, - unsigned long range_ns, const enum hrtimer_mode mode); + u64 range_ns, const enum hrtimer_mode mode); /** * hrtimer_start - (re)start an hrtimer on the current CPU @@ -399,7 +399,7 @@ extern int hrtimer_try_to_cancel(struct hrtimer *timer); static inline void hrtimer_start_expires(struct hrtimer *timer, enum hrtimer_mode mode) { - unsigned long delta; + u64 delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); @@ -477,10 +477,12 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *tsk); -extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, +extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); extern int schedule_hrtimeout_range_clock(ktime_t *expires, - unsigned long delta, const enum hrtimer_mode mode, int clock); + u64 delta, + const enum hrtimer_mode mode, + int clock); extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ diff --git a/include/linux/poll.h b/include/linux/poll.h index c08386fb3e08..9fb4f40d9a26 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -96,7 +96,7 @@ extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack); -extern long select_estimate_accuracy(struct timespec *tv); +extern u64 select_estimate_accuracy(struct timespec *tv); static inline int poll_schedule(struct poll_wqueues *pwq, int state) diff --git a/include/linux/sched.h b/include/linux/sched.h index eb7f2f84009b..3284d07edec7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1792,8 +1792,8 @@ struct task_struct { * time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ - unsigned long timer_slack_ns; - unsigned long default_timer_slack_ns; + u64 timer_slack_ns; + u64 default_timer_slack_ns; #ifdef CONFIG_KASAN unsigned int kasan_depth; diff --git a/kernel/sys.c b/kernel/sys.c index 78947de6f969..cf8ba545c7d3 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2169,7 +2169,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = perf_event_task_enable(); break; case PR_GET_TIMERSLACK: - error = current->timer_slack_ns; + if (current->timer_slack_ns > ULONG_MAX) + error = ULONG_MAX; + else + error = current->timer_slack_ns; break; case PR_SET_TIMERSLACK: if (arg2 <= 0) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index fa909f9fd559..58a321c34cfb 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -979,7 +979,7 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, * relative (HRTIMER_MODE_REL) */ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, - unsigned long delta_ns, const enum hrtimer_mode mode) + u64 delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base, *new_base; unsigned long flags; @@ -1548,7 +1548,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; - unsigned long slack; + u64 slack; slack = current->timer_slack_ns; if (dl_task(current) || rt_task(current)) @@ -1724,7 +1724,7 @@ void __init hrtimers_init(void) * @clock: timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME */ int __sched -schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta, +schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, int clock) { struct hrtimer_sleeper t; @@ -1792,7 +1792,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta, * * Returns 0 when the timer has expired otherwise -EINTR */ -int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, +int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode) { return schedule_hrtimeout_range_clock(expires, delta, mode, diff --git a/kernel/time/timer.c b/kernel/time/timer.c index bbc5d1114583..d1798fa0c743 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1698,10 +1698,10 @@ EXPORT_SYMBOL(msleep_interruptible); static void __sched do_usleep_range(unsigned long min, unsigned long max) { ktime_t kmin; - unsigned long delta; + u64 delta; kmin = ktime_set(0, min * NSEC_PER_USEC); - delta = (max - min) * NSEC_PER_USEC; + delta = (u64)(max - min) * NSEC_PER_USEC; schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL); } -- cgit v1.2.3 From a8199371afc27946d72f0d53e938e78d2ea0bae3 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 17 Mar 2016 14:21:20 -0700 Subject: printk: move can_use_console() out of console_trylock_for_printk() console_unlock() allows to cond_resched() if its caller has set `console_may_schedule' to 1 (this functionality is present since 8d91f8b15361 ("printk: do cond_resched() between lines while outputting to consoles"). The rules are: -- console_lock() always sets `console_may_schedule' to 1 -- console_trylock() always sets `console_may_schedule' to 0 printk() calls console_unlock() with preemption desabled, which basically can lead to RCU stalls, watchdog soft lockups, etc. if something is simultaneously calling printk() frequent enough (IOW, console_sem owner always has new data to send to console divers and can't leave console_unlock() for a long time). printk()->console_trylock() callers do not necessarily execute in atomic contexts, and some of them can cond_resched() in console_unlock(). console_trylock() can set `console_may_schedule' to 1 (allow cond_resched() later in consoe_unlock()) when it's safe. This patch (of 3): vprintk_emit() disables preemption around console_trylock_for_printk() and console_unlock() calls for a strong reason -- can_use_console() check. The thing is that vprintl_emit() can be called on a CPU that is not fully brought up yet (!cpu_online()), which potentially can cause problems if console driver wants to access per-cpu data. A console driver can explicitly state that it's safe to call it from !online cpu by setting CON_ANYTIME bit in console ->flags. That's why for !cpu_online() can_use_console() iterates all the console to find out if there is a CON_ANYTIME console, otherwise console_unlock() must be avoided. can_use_console() ensures that console_unlock() call is safe in vprintk_emit() only; console_lock() and console_trylock() are not covered by this check. Even though call_console_drivers(), invoked from console_cont_flush() and console_unlock(), tests `!cpu_online() && CON_ANYTIME' for_each_console(), it may be too late, which can result in messages loss. Assume that we have 2 cpus -- CPU0 is online, CPU1 is !online, and no CON_ANYTIME consoles available. CPU0 online CPU1 !online console_trylock() ... console_unlock() console_cont_flush spin_lock logbuf_lock if (!cont.len) { spin_unlock logbuf_lock return } for (;;) { vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock spin_lock logbuf_lock !console_trylock_for_printk msg_print_text return console_idx = log_next() console_seq++ console_prev = msg->flags spin_unlock logbuf_lock call_console_drivers() for_each_console(con) { if (!cpu_online() && !(con->flags & CON_ANYTIME)) continue; } /* * no message printed, we lost it */ vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock !console_trylock_for_printk return /* * go to the beginning of the loop, * find out there are new messages, * lose it */ } console_trylock()/console_lock() call on CPU1 may come from cpu notifiers registered on that CPU. Since notifiers are not getting unregistered when CPU is going DOWN, all of the notifiers receive notifications during CPU UP. For example, on my x86_64, I see around 50 notification sent from offline CPU to itself [swapper/2] from cpu:2 to:2 action:CPU_STARTING hotplug_hrtick [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_main_cpu_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_queue_reinit_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING console_cpu_notify while doing echo 0 > /sys/devices/system/cpu/cpu2/online echo 1 > /sys/devices/system/cpu/cpu2/online So grabbing the console_sem lock while CPU is !online is possible, in theory. This patch moves can_use_console() check out of console_trylock_for_printk(). Instead it calls it in console_unlock(), so now console_lock()/console_unlock() are also 'protected' by can_use_console(). This also means that console_trylock_for_printk() is not really needed anymore and can be removed. Signed-off-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Cc: Jan Kara Cc: Tejun Heo Cc: Kyle McMartin Cc: Dave Jones Cc: Calvin Owens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 97 ++++++++++++++++++++++---------------------------- 1 file changed, 42 insertions(+), 55 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index c963ba534a78..2523332bd998 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1483,58 +1483,6 @@ static void zap_locks(void) sema_init(&console_sem, 1); } -/* - * Check if we have any console that is capable of printing while cpu is - * booting or shutting down. Requires console_sem. - */ -static int have_callable_console(void) -{ - struct console *con; - - for_each_console(con) - if (con->flags & CON_ANYTIME) - return 1; - - return 0; -} - -/* - * Can we actually use the console at this time on this cpu? - * - * Console drivers may assume that per-cpu resources have been allocated. So - * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't - * call them until this CPU is officially up. - */ -static inline int can_use_console(unsigned int cpu) -{ - return cpu_online(cpu) || have_callable_console(); -} - -/* - * Try to get console ownership to actually show the kernel - * messages from a 'printk'. Return true (and with the - * console_lock held, and 'console_locked' set) if it - * is successful, false otherwise. - */ -static int console_trylock_for_printk(void) -{ - unsigned int cpu = smp_processor_id(); - - if (!console_trylock()) - return 0; - /* - * If we can't use the console, we need to release the console - * semaphore by hand to avoid flushing the buffer. We need to hold the - * console semaphore in order to do this test safely. - */ - if (!can_use_console(cpu)) { - console_locked = 0; - up_console_sem(); - return 0; - } - return 1; -} - int printk_delay_msec __read_mostly; static inline void printk_delay(void) @@ -1681,7 +1629,6 @@ asmlinkage int vprintk_emit(int facility, int level, boot_delay_msec(level); printk_delay(); - /* This stops the holder of console_sem just where we want him */ local_irq_save(flags); this_cpu = smp_processor_id(); @@ -1705,6 +1652,7 @@ asmlinkage int vprintk_emit(int facility, int level, } lockdep_off(); + /* This stops the holder of console_sem just where we want him */ raw_spin_lock(&logbuf_lock); logbuf_cpu = this_cpu; @@ -1821,7 +1769,7 @@ asmlinkage int vprintk_emit(int facility, int level, * semaphore. The release will print out buffers and wake up * /dev/kmsg and syslog() users. */ - if (console_trylock_for_printk()) + if (console_trylock()) console_unlock(); preempt_enable(); lockdep_on(); @@ -2184,6 +2132,33 @@ int is_console_locked(void) return console_locked; } +/* + * Check if we have any console that is capable of printing while cpu is + * booting or shutting down. Requires console_sem. + */ +static int have_callable_console(void) +{ + struct console *con; + + for_each_console(con) + if (con->flags & CON_ANYTIME) + return 1; + + return 0; +} + +/* + * Can we actually use the console at this time on this cpu? + * + * Console drivers may assume that per-cpu resources have been allocated. So + * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't + * call them until this CPU is officially up. + */ +static inline int can_use_console(void) +{ + return cpu_online(raw_smp_processor_id()) || have_callable_console(); +} + static void console_cont_flush(char *text, size_t size) { unsigned long flags; @@ -2254,9 +2229,21 @@ void console_unlock(void) do_cond_resched = console_may_schedule; console_may_schedule = 0; +again: + /* + * We released the console_sem lock, so we need to recheck if + * cpu is online and (if not) is there at least one CON_ANYTIME + * console. + */ + if (!can_use_console()) { + console_locked = 0; + up_console_sem(); + return; + } + /* flush buffered message fragment immediately to console */ console_cont_flush(text, sizeof(text)); -again: + for (;;) { struct printk_log *msg; size_t ext_len = 0; -- cgit v1.2.3 From 6b97a20d3a7909daa06625d4440c2c52d7bf08d7 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 17 Mar 2016 14:21:23 -0700 Subject: printk: set may_schedule for some of console_trylock() callers console_unlock() allows to cond_resched() if its caller has set `console_may_schedule' to 1, since 8d91f8b15361 ("printk: do cond_resched() between lines while outputting to consoles"). The rules are: -- console_lock() always sets `console_may_schedule' to 1 -- console_trylock() always sets `console_may_schedule' to 0 However, console_trylock() callers (among them is printk()) do not always call printk() from atomic contexts, and some of them can cond_resched() in console_unlock(), so console_trylock() can set `console_may_schedule' to 1 for such processes. For !CONFIG_PREEMPT_COUNT kernels, however, console_trylock() always sets `console_may_schedule' to 0. It's possible to drop explicit preempt_disable()/preempt_enable() in vprintk_emit(), because console_unlock() and console_trylock() are now smart enough: a) console_unlock() does not cond_resched() when it's unsafe (console_trylock() takes care of that) b) console_unlock() does can_use_console() check. Signed-off-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Cc: Jan Kara Cc: Tejun Heo Cc: Kyle McMartin Cc: Dave Jones Cc: Calvin Owens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 2523332bd998..a6d023c3b852 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1757,13 +1757,6 @@ asmlinkage int vprintk_emit(int facility, int level, /* If called from the scheduler, we can not call up(). */ if (!in_sched) { lockdep_off(); - /* - * Disable preemption to avoid being preempted while holding - * console_sem which would prevent anyone from printing to - * console - */ - preempt_disable(); - /* * Try to acquire and then immediately release the console * semaphore. The release will print out buffers and wake up @@ -1771,7 +1764,6 @@ asmlinkage int vprintk_emit(int facility, int level, */ if (console_trylock()) console_unlock(); - preempt_enable(); lockdep_on(); } @@ -2122,7 +2114,20 @@ int console_trylock(void) return 0; } console_locked = 1; - console_may_schedule = 0; + /* + * When PREEMPT_COUNT disabled we can't reliably detect if it's + * safe to schedule (e.g. calling printk while holding a spin_lock), + * because preempt_disable()/preempt_enable() are just barriers there + * and preempt_count() is always 0. + * + * RCU read sections have a separate preemption counter when + * PREEMPT_RCU enabled thus we must take extra care and check + * rcu_preempt_depth(), otherwise RCU read sections modify + * preempt_count(). + */ + console_may_schedule = !oops_in_progress && + preemptible() && + !rcu_preempt_depth(); return 1; } EXPORT_SYMBOL(console_trylock); -- cgit v1.2.3 From adaf6590ee7db23c3a124fb9f213c90c15cecf96 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 17 Mar 2016 14:21:27 -0700 Subject: printk: check CON_ENABLED in have_callable_console() have_callable_console() must also test CON_ENABLED bit, not just CON_ANYTIME. We may have disabled CON_ANYTIME console so printk can wrongly assume that it's safe to call_console_drivers(). Signed-off-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Cc: Jan Kara Cc: Tejun Heo Cc: Kyle McMartin Cc: Dave Jones Cc: Calvin Owens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index a6d023c3b852..d5fd844e5b08 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2146,7 +2146,8 @@ static int have_callable_console(void) struct console *con; for_each_console(con) - if (con->flags & CON_ANYTIME) + if ((con->flags & CON_ENABLED) && + (con->flags & CON_ANYTIME)) return 1; return 0; -- cgit v1.2.3 From f468908bb55a0b01d9424c74f8ec8eb906835150 Mon Sep 17 00:00:00 2001 From: Ivan Delalande Date: Thu, 17 Mar 2016 14:21:30 -0700 Subject: printk: add clear_idx symbol to vmcoreinfo This allows us to extract from the vmcore only the messages emitted since the last time the ring buffer was cleared. We just have to make sure its value is always up-to-date, when old messages are discarded to free space in log_make_free_space() for example. Signed-off-by: Zeyu Zhao Signed-off-by: Ivan Delalande Cc: Kay Sievers Cc: Neil Horman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index d5fd844e5b08..bfbf284e4218 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -367,16 +367,20 @@ static int logbuf_has_space(u32 msg_size, bool empty) static int log_make_free_space(u32 msg_size) { - while (log_first_seq < log_next_seq) { - if (logbuf_has_space(msg_size, false)) - return 0; + while (log_first_seq < log_next_seq && + !logbuf_has_space(msg_size, false)) { /* drop old messages until we have enough contiguous space */ log_first_idx = log_next(log_first_idx); log_first_seq++; } + if (clear_seq < log_first_seq) { + clear_seq = log_first_seq; + clear_idx = log_first_idx; + } + /* sequence numbers are equal, so the log buffer is empty */ - if (logbuf_has_space(msg_size, true)) + if (logbuf_has_space(msg_size, log_first_seq == log_next_seq)) return 0; return -ENOMEM; @@ -854,6 +858,7 @@ void log_buf_kexec_setup(void) VMCOREINFO_SYMBOL(log_buf); VMCOREINFO_SYMBOL(log_buf_len); VMCOREINFO_SYMBOL(log_first_idx); + VMCOREINFO_SYMBOL(clear_idx); VMCOREINFO_SYMBOL(log_next_idx); /* * Export struct printk_log size and field offsets. User space tools can @@ -1216,12 +1221,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear) u32 idx; enum log_flags prev; - if (clear_seq < log_first_seq) { - /* messages are gone, move to first available one */ - clear_seq = log_first_seq; - clear_idx = log_first_idx; - } - /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. -- cgit v1.2.3 From 4cc7ecb7f2a60e8deb783b8fbf7c1ae467acb920 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Mar 2016 14:23:00 -0700 Subject: param: convert some "on"/"off" users to strtobool This changes several users of manual "on"/"off" parsing to use strtobool. Some side-effects: - these uses will now parse y/n/1/0 meaningfully too - the early_param uses will now bubble up parse errors Signed-off-by: Kees Cook Acked-by: Heiko Carstens Acked-by: Michael Ellerman Cc: Amitkumar Karwar Cc: Andy Shevchenko Cc: Daniel Borkmann Cc: Joe Perches Cc: Kalle Valo Cc: Martin Schwidefsky Cc: Nishant Sarmukadam Cc: Rasmus Villemoes Cc: Steve French Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/rtasd.c | 9 ++------- arch/powerpc/platforms/pseries/hotplug-cpu.c | 10 ++-------- arch/s390/kernel/time.c | 8 ++------ arch/s390/kernel/topology.c | 7 ++----- arch/x86/kernel/aperture_64.c | 12 ++---------- include/linux/tick.h | 2 +- kernel/time/hrtimer.c | 10 ++-------- kernel/time/tick-sched.c | 10 ++-------- 8 files changed, 15 insertions(+), 53 deletions(-) (limited to 'kernel') diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 5a2c049c1c61..aa610ce8742f 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -49,7 +49,7 @@ static unsigned int rtas_error_log_buffer_max; static unsigned int event_scan; static unsigned int rtas_event_scan_rate; -static int full_rtas_msgs = 0; +static bool full_rtas_msgs; /* Stop logging to nvram after first fatal error */ static int logging_enabled; /* Until we initialize everything, @@ -592,11 +592,6 @@ __setup("surveillance=", surveillance_setup); static int __init rtasmsgs_setup(char *str) { - if (strcmp(str, "on") == 0) - full_rtas_msgs = 1; - else if (strcmp(str, "off") == 0) - full_rtas_msgs = 0; - - return 1; + return (kstrtobool(str, &full_rtas_msgs) == 0); } __setup("rtasmsgs=", rtasmsgs_setup); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 32274f72fe3f..282837a1d74b 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -47,20 +47,14 @@ static DEFINE_PER_CPU(enum cpu_state_vals, current_state) = CPU_STATE_OFFLINE; static enum cpu_state_vals default_offline_state = CPU_STATE_OFFLINE; -static int cede_offline_enabled __read_mostly = 1; +static bool cede_offline_enabled __read_mostly = true; /* * Enable/disable cede_offline when available. */ static int __init setup_cede_offline(char *str) { - if (!strcmp(str, "off")) - cede_offline_enabled = 0; - else if (!strcmp(str, "on")) - cede_offline_enabled = 1; - else - return 0; - return 1; + return (kstrtobool(str, &cede_offline_enabled) == 0); } __setup("cede_offline=", setup_cede_offline); diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index c4e5f183f225..9409d32f285e 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -1432,7 +1432,7 @@ device_initcall(etr_init_sysfs); /* * Server Time Protocol (STP) code. */ -static int stp_online; +static bool stp_online; static struct stp_sstpi stp_info; static void *stp_page; @@ -1443,11 +1443,7 @@ static struct timer_list stp_timer; static int __init early_parse_stp(char *p) { - if (strncmp(p, "off", 3) == 0) - stp_online = 0; - else if (strncmp(p, "on", 2) == 0) - stp_online = 1; - return 0; + return kstrtobool(p, &stp_online); } early_param("stp", early_parse_stp); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 40b8102fdadb..64298a867589 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -37,7 +37,7 @@ static void set_topology_timer(void); static void topology_work_fn(struct work_struct *work); static struct sysinfo_15_1_x *tl_info; -static int topology_enabled = 1; +static bool topology_enabled = true; static DECLARE_WORK(topology_work, topology_work_fn); /* @@ -444,10 +444,7 @@ static const struct cpumask *cpu_book_mask(int cpu) static int __init early_parse_topology(char *p) { - if (strncmp(p, "off", 3)) - return 0; - topology_enabled = 0; - return 0; + return kstrtobool(p, &topology_enabled); } early_param("topology", early_parse_topology); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 6e85f713641d..0a2bb1f62e72 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -227,19 +227,11 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp) return 0; } -static int gart_fix_e820 __initdata = 1; +static bool gart_fix_e820 __initdata = true; static int __init parse_gart_mem(char *p) { - if (!p) - return -EINVAL; - - if (!strncmp(p, "off", 3)) - gart_fix_e820 = 0; - else if (!strncmp(p, "on", 2)) - gart_fix_e820 = 1; - - return 0; + return kstrtobool(p, &gart_fix_e820); } early_param("gart_fix_e820", parse_gart_mem); diff --git a/include/linux/tick.h b/include/linux/tick.h index 21f73649a4dc..62be0786d6d0 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -111,7 +111,7 @@ enum tick_dep_bits { #define TICK_DEP_MASK_CLOCK_UNSTABLE (1 << TICK_DEP_BIT_CLOCK_UNSTABLE) #ifdef CONFIG_NO_HZ_COMMON -extern int tick_nohz_enabled; +extern bool tick_nohz_enabled; extern int tick_nohz_tick_stopped(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 58a321c34cfb..fa0b983290cf 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -515,7 +515,7 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) /* * High resolution timer enabled ? */ -static int hrtimer_hres_enabled __read_mostly = 1; +static bool hrtimer_hres_enabled __read_mostly = true; unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; EXPORT_SYMBOL_GPL(hrtimer_resolution); @@ -524,13 +524,7 @@ EXPORT_SYMBOL_GPL(hrtimer_resolution); */ static int __init setup_hrtimer_hres(char *str) { - if (!strcmp(str, "off")) - hrtimer_hres_enabled = 0; - else if (!strcmp(str, "on")) - hrtimer_hres_enabled = 1; - else - return 0; - return 1; + return (kstrtobool(str, &hrtimer_hres_enabled) == 0); } __setup("highres=", setup_hrtimer_hres); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 969e6704c3c9..195fe7d2caad 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -486,20 +486,14 @@ void __init tick_nohz_init(void) /* * NO HZ enabled ? */ -int tick_nohz_enabled __read_mostly = 1; +bool tick_nohz_enabled __read_mostly = true; unsigned long tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ static int __init setup_tick_nohz(char *str) { - if (!strcmp(str, "off")) - tick_nohz_enabled = 0; - else if (!strcmp(str, "on")) - tick_nohz_enabled = 1; - else - return 0; - return 1; + return (kstrtobool(str, &tick_nohz_enabled) == 0); } __setup("nohz=", setup_tick_nohz); -- cgit v1.2.3 From 2553b67a1fbe7bf202e4e8070ab0b00d3d3a06a2 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 17 Mar 2016 14:23:04 -0700 Subject: lib/bug.c: use common WARN helper The traceoff_on_warning option doesn't have any effect on s390, powerpc, arm64, parisc, and sh because there are two different types of WARN implementations: 1) The above mentioned architectures treat WARN() as a special case of a BUG() exception. They handle warnings in report_bug() in lib/bug.c. 2) All other architectures just call warn_slowpath_*() directly. Their warnings are handled in warn_slowpath_common() in kernel/panic.c. Support traceoff_on_warning on all architectures and prevent any future divergence by using a single common function to emit the warning. Also remove the '()' from '%pS()', because the parentheses look funky: [ 45.607629] WARNING: at /root/warn_mod/warn_mod.c:17 .init_dummy+0x20/0x40 [warn_mod]() Reported-by: Chunyu Hu Signed-off-by: Josh Poimboeuf Acked-by: Heiko Carstens Tested-by: Prarit Bhargava Acked-by: Prarit Bhargava Acked-by: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/bug.h | 6 ++++++ kernel/panic.c | 41 ++++++++++++++++++++++++++--------------- lib/bug.c | 26 ++------------------------ 3 files changed, 34 insertions(+), 39 deletions(-) (limited to 'kernel') diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index fdf6fa078422..f90588abbfd4 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -81,6 +81,12 @@ extern void warn_slowpath_null(const char *file, const int line); do { printk(arg); __WARN_TAINT(taint); } while (0) #endif +/* used internally by panic.c */ +struct warn_args; + +void __warn(const char *file, int line, void *caller, unsigned taint, + struct pt_regs *regs, struct warn_args *args); + #ifndef WARN_ON #define WARN_ON(condition) ({ \ int __ret_warn_on = !!(condition); \ diff --git a/kernel/panic.c b/kernel/panic.c index d96469de72dc..fa400852bf6c 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -24,6 +24,7 @@ #include #include #include +#include #define PANIC_TIMER_STEP 100 #define PANIC_BLINK_SPD 18 @@ -449,20 +450,25 @@ void oops_exit(void) kmsg_dump(KMSG_DUMP_OOPS); } -#ifdef WANT_WARN_ON_SLOWPATH -struct slowpath_args { +struct warn_args { const char *fmt; va_list args; }; -static void warn_slowpath_common(const char *file, int line, void *caller, - unsigned taint, struct slowpath_args *args) +void __warn(const char *file, int line, void *caller, unsigned taint, + struct pt_regs *regs, struct warn_args *args) { disable_trace_on_warning(); pr_warn("------------[ cut here ]------------\n"); - pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS()\n", - raw_smp_processor_id(), current->pid, file, line, caller); + + if (file) + pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", + raw_smp_processor_id(), current->pid, file, line, + caller); + else + pr_warn("WARNING: CPU: %d PID: %d at %pS\n", + raw_smp_processor_id(), current->pid, caller); if (args) vprintk(args->fmt, args->args); @@ -479,20 +485,27 @@ static void warn_slowpath_common(const char *file, int line, void *caller, } print_modules(); - dump_stack(); + + if (regs) + show_regs(regs); + else + dump_stack(); + print_oops_end_marker(); + /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); } +#ifdef WANT_WARN_ON_SLOWPATH void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...) { - struct slowpath_args args; + struct warn_args args; args.fmt = fmt; va_start(args.args, fmt); - warn_slowpath_common(file, line, __builtin_return_address(0), - TAINT_WARN, &args); + __warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL, + &args); va_end(args.args); } EXPORT_SYMBOL(warn_slowpath_fmt); @@ -500,20 +513,18 @@ EXPORT_SYMBOL(warn_slowpath_fmt); void warn_slowpath_fmt_taint(const char *file, int line, unsigned taint, const char *fmt, ...) { - struct slowpath_args args; + struct warn_args args; args.fmt = fmt; va_start(args.args, fmt); - warn_slowpath_common(file, line, __builtin_return_address(0), - taint, &args); + __warn(file, line, __builtin_return_address(0), taint, NULL, &args); va_end(args.args); } EXPORT_SYMBOL(warn_slowpath_fmt_taint); void warn_slowpath_null(const char *file, int line) { - warn_slowpath_common(file, line, __builtin_return_address(0), - TAINT_WARN, NULL); + __warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL, NULL); } EXPORT_SYMBOL(warn_slowpath_null); #endif diff --git a/lib/bug.c b/lib/bug.c index 6cde380f09de..bc3656e944d2 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -167,30 +167,8 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) if (warning) { /* this is a WARN_ON rather than BUG/BUG_ON */ - pr_warn("------------[ cut here ]------------\n"); - - if (file) - pr_warn("WARNING: at %s:%u\n", file, line); - else - pr_warn("WARNING: at %p [verbose debug info unavailable]\n", - (void *)bugaddr); - - if (panic_on_warn) { - /* - * This thread may hit another WARN() in the panic path. - * Resetting this prevents additional WARN() from - * panicking the system on this thread. Other threads - * are blocked by the panic_mutex in panic(). - */ - panic_on_warn = 0; - panic("panic_on_warn set ...\n"); - } - - print_modules(); - show_regs(regs); - print_oops_end_marker(); - /* Just a warning, don't kill lockdep. */ - add_taint(BUG_GET_TAINT(bug), LOCKDEP_STILL_OK); + __warn(file, line, (void *)bugaddr, BUG_GET_TAINT(bug), regs, + NULL); return BUG_TRAP_TYPE_WARN; } -- cgit v1.2.3 From 84b6d3e6149c5280bc18b42e2f12efdaf354e49c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 16 Mar 2016 15:34:32 +0100 Subject: ftrace: Make ftrace_hash_rec_enable return update bool Change __ftrace_hash_rec_update to return true in case we need to update dynamic ftrace call records. It return false in case no update is needed. Link: http://lkml.kernel.org/r/1458138873-1553-5-git-send-email-jolsa@kernel.org Acked-by: Namhyung Kim Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 57a6eea84694..11ffcfd3804e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1610,7 +1610,7 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) return keep_regs; } -static void __ftrace_hash_rec_update(struct ftrace_ops *ops, +static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) { @@ -1618,12 +1618,13 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, struct ftrace_hash *other_hash; struct ftrace_page *pg; struct dyn_ftrace *rec; + bool update = false; int count = 0; int all = 0; /* Only update if the ops has been registered */ if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) - return; + return false; /* * In the filter_hash case: @@ -1650,7 +1651,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, * then there's nothing to do. */ if (ftrace_hash_empty(hash)) - return; + return false; } do_for_each_ftrace_rec(pg, rec) { @@ -1694,7 +1695,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, if (inc) { rec->flags++; if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX)) - return; + return false; /* * If there's only a single callback registered to a @@ -1720,7 +1721,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, rec->flags |= FTRACE_FL_REGS; } else { if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0)) - return; + return false; rec->flags--; /* @@ -1753,22 +1754,28 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, */ } count++; + + /* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */ + update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE; + /* Shortcut, if we handled all records, we are done. */ if (!all && count == hash->count) - return; + return update; } while_for_each_ftrace_rec(); + + return update; } -static void ftrace_hash_rec_disable(struct ftrace_ops *ops, +static bool ftrace_hash_rec_disable(struct ftrace_ops *ops, int filter_hash) { - __ftrace_hash_rec_update(ops, filter_hash, 0); + return __ftrace_hash_rec_update(ops, filter_hash, 0); } -static void ftrace_hash_rec_enable(struct ftrace_ops *ops, +static bool ftrace_hash_rec_enable(struct ftrace_ops *ops, int filter_hash) { - __ftrace_hash_rec_update(ops, filter_hash, 1); + return __ftrace_hash_rec_update(ops, filter_hash, 1); } static void ftrace_hash_rec_update_modify(struct ftrace_ops *ops, -- cgit v1.2.3 From 7f50d06bb6b825d34f069c6c7a1aab96ad0b94d9 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 16 Mar 2016 15:34:33 +0100 Subject: ftrace: Update dynamic ftrace calls only if necessary Currently dynamic ftrace calls are updated any time the ftrace_ops is un/registered. If we do this update only when it's needed, we save lot of time for perf system wide ftrace function sampling/counting. The reason is that for system wide sampling/counting, perf creates event for each cpu in the system. Each event then registers separate copy of ftrace_ops, which ends up in FTRACE_UPDATE_CALLS updates. On servers with many cpus that means serious stall (240 cpus server): Counting: # time ./perf stat -e ftrace:function -a sleep 1 Performance counter stats for 'system wide': 370,663 ftrace:function 1.401427505 seconds time elapsed real 3m51.743s user 0m0.023s sys 3m48.569s Sampling: # time ./perf record -e ftrace:function -a sleep 1 [ perf record: Woken up 0 times to write data ] Warning: Processed 141200 events and lost 5 chunks! [ perf record: Captured and wrote 10.703 MB perf.data (135950 samples) ] real 2m31.429s user 0m0.213s sys 2m29.494s There's no reason to do the FTRACE_UPDATE_CALLS update for each event in perf case, because all the ftrace_ops always share the same filter, so the updated calls are always the same. It's required that only first ftrace_ops registration does the FTRACE_UPDATE_CALLS update (also sometimes the second if the first one used the trampoline), but the rest can be only cheaply linked into the ftrace_ops list. Counting: # time ./perf stat -e ftrace:function -a sleep 1 Performance counter stats for 'system wide': 398,571 ftrace:function 1.377503733 seconds time elapsed real 0m2.787s user 0m0.005s sys 0m1.883s Sampling: # time ./perf record -e ftrace:function -a sleep 1 [ perf record: Woken up 0 times to write data ] Warning: Processed 261730 events and lost 9 chunks! [ perf record: Captured and wrote 19.907 MB perf.data (256293 samples) ] real 1m31.948s user 0m0.309s sys 1m32.051s Link: http://lkml.kernel.org/r/1458138873-1553-6-git-send-email-jolsa@kernel.org Acked-by: Namhyung Kim Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 11ffcfd3804e..d3850cbb840f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2651,7 +2651,6 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) return ret; ftrace_start_up++; - command |= FTRACE_UPDATE_CALLS; /* * Note that ftrace probes uses this to start up @@ -2672,7 +2671,8 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) return ret; } - ftrace_hash_rec_enable(ops, 1); + if (ftrace_hash_rec_enable(ops, 1)) + command |= FTRACE_UPDATE_CALLS; ftrace_startup_enable(command); @@ -2702,11 +2702,11 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) /* Disabling ipmodify never fails */ ftrace_hash_ipmodify_disable(ops); - ftrace_hash_rec_disable(ops, 1); - ops->flags &= ~FTRACE_OPS_FL_ENABLED; + if (ftrace_hash_rec_disable(ops, 1)) + command |= FTRACE_UPDATE_CALLS; - command |= FTRACE_UPDATE_CALLS; + ops->flags &= ~FTRACE_OPS_FL_ENABLED; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; -- cgit v1.2.3 From 6363c6b599ae67b779d01a48642a7c0d7d721814 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 15 Mar 2016 22:12:34 +0800 Subject: ftrace: Use kasprintf() in ftrace_profile_tracefs() Use kasprintf() instead of kmalloc() and snprintf(). Link: http://lkml.kernel.org/r/135a7bc36e51fd9eaa57124dd2140285b771f738.1458050835.git.geliangtang@163.com Acked-by: Namhyung Kim Signed-off-by: Geliang Tang Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d3850cbb840f..6a93faafbea4 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1030,8 +1030,7 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) for_each_possible_cpu(cpu) { stat = &per_cpu(ftrace_profile_stats, cpu); - /* allocate enough for function name + cpu number */ - name = kmalloc(32, GFP_KERNEL); + name = kasprintf(GFP_KERNEL, "function%d", cpu); if (!name) { /* * The files created are permanent, if something happens @@ -1043,7 +1042,6 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) return; } stat->stat = function_stats; - snprintf(name, 32, "function%d", cpu); stat->stat.name = name; ret = register_stat_tracer(&stat->stat); if (ret) { -- cgit v1.2.3 From c8ca003b2fde177b83de87f9f20f6a5933fb50bf Mon Sep 17 00:00:00 2001 From: Chunyu Hu Date: Mon, 14 Mar 2016 20:35:41 +0800 Subject: tracing: Fix return while holding a lock in register_tracer() commit d39cdd2036a6 ("tracing: Make tracer_flags use the right set_flag callback") introduces a potential mutex deadlock issue, as it forgets to free the mutex when allocaing the tracer_flags gets fail. The issue was found by Dan Carpenter through Smatch static code check tool. Link: http://lkml.kernel.org/r/1457958941-30265-1-git-send-email-chuhu@redhat.com Fixes: d39cdd2036a6 ("tracing: Make tracer_flags use the right set_flag callback") Reported-by: Dan Carpenter Signed-off-by: Chunyu Hu Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b401a1892dc6..0ae46048f724 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1256,8 +1256,10 @@ int __init register_tracer(struct tracer *type) if (!type->flags) { /*allocate a dummy tracer_flags*/ type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL); - if (!type->flags) - return -ENOMEM; + if (!type->flags) { + ret = -ENOMEM; + goto out; + } type->flags->val = 0; type->flags->opts = dummy_tracer_opt; } else -- cgit v1.2.3 From cb86e05390debcc084cfdb0a71ed4c5dbbec517d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 18 Mar 2016 12:27:43 -0400 Subject: tracing: Have preempt(irqs)off trace preempt disabled functions Joel Fernandes reported that the function tracing of preempt disabled sections was not being reported when running either the preemptirqsoff or preemptoff tracers. This was due to the fact that the function tracer callback for those tracers checked if irqs were disabled before tracing. But this fails when we want to trace preempt off locations as well. Joel explained that he wanted to see funcitons where interrupts are enabled but preemption was disabled. The expected output he wanted: <...>-2265 1d.h1 3419us : preempt_count_sub <-irq_exit <...>-2265 1d..1 3419us : __do_softirq <-irq_exit <...>-2265 1d..1 3419us : msecs_to_jiffies <-__do_softirq <...>-2265 1d..1 3420us : irqtime_account_irq <-__do_softirq <...>-2265 1d..1 3420us : __local_bh_disable_ip <-__do_softirq <...>-2265 1..s1 3421us : run_timer_softirq <-__do_softirq <...>-2265 1..s1 3421us : hrtimer_run_pending <-run_timer_softirq <...>-2265 1..s1 3421us : _raw_spin_lock_irq <-run_timer_softirq <...>-2265 1d.s1 3422us : preempt_count_add <-_raw_spin_lock_irq <...>-2265 1d.s2 3422us : _raw_spin_unlock_irq <-run_timer_softirq <...>-2265 1..s2 3422us : preempt_count_sub <-_raw_spin_unlock_irq <...>-2265 1..s1 3423us : rcu_bh_qs <-__do_softirq <...>-2265 1d.s1 3423us : irqtime_account_irq <-__do_softirq <...>-2265 1d.s1 3423us : __local_bh_enable <-__do_softirq There's a comment saying that the irq disabled check is because there's a possible race that tracing_cpu may be set when the function is executed. But I don't remember that race. For now, I added a check for preemption being enabled too to not record the function, as there would be no race if that was the case. I need to re-investigate this, as I'm now thinking that the tracing_cpu will always be correct. But no harm in keeping the check for now, except for the slight performance hit. Link: http://lkml.kernel.org/r/1457770386-88717-1-git-send-email-agnel.joel@gmail.com Fixes: 5e6d2b9cfa3a "tracing: Use one prologue for the preempt irqs off tracer function tracers" Cc: stable@vget.kernel.org # 2.6.37+ Reported-by: Joel Fernandes Signed-off-by: Steven Rostedt --- kernel/trace/trace_irqsoff.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index e4e56589ec1d..be3222b7d72e 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -109,8 +109,12 @@ static int func_prolog_dec(struct trace_array *tr, return 0; local_save_flags(*flags); - /* slight chance to get a false positive on tracing_cpu */ - if (!irqs_disabled_flags(*flags)) + /* + * Slight chance to get a false positive on tracing_cpu, + * although I'm starting to think there isn't a chance. + * Leave this for now just to be paranoid. + */ + if (!irqs_disabled_flags(*flags) && !preempt_count()) return 0; *data = per_cpu_ptr(tr->trace_buffer.data, cpu); -- cgit v1.2.3 From a29054d9478d0435ab01b7544da4f674ab13f533 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 18 Mar 2016 15:46:48 -0400 Subject: tracing: Fix crash from reading trace_pipe with sendfile If tracing contains data and the trace_pipe file is read with sendfile(), then it can trigger a NULL pointer dereference and various BUG_ON within the VM code. There's a patch to fix this in the splice_to_pipe() code, but it's also a good idea to not let that happen from trace_pipe either. Link: http://lkml.kernel.org/r/1457641146-9068-1-git-send-email-rabin@rab.in Cc: stable@vger.kernel.org # 2.6.30+ Reported-by: Rabin Vincent Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 0ae46048f724..cb2b708e4ea7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4954,7 +4954,10 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, spd.nr_pages = i; - ret = splice_to_pipe(pipe, &spd); + if (i) + ret = splice_to_pipe(pipe, &spd); + else + ret = 0; out: splice_shrink_spd(&spd); return ret; -- cgit v1.2.3 From 741f3a69f101250dc6b171b88e14ea51b099b1a9 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov <0x7f454c46@gmail.com> Date: Mon, 19 Oct 2015 21:10:26 +0300 Subject: tracing: Remove redundant reset per-CPU buff in irqsoff tracer There is no reason to do it twice: from commit b6f11df26fdc28 ("trace: Call tracing_reset_online_cpus before tracer->init()") resetting of per-CPU buffers done before tracer->init() call. tracer->init() calls {irqs,preempt,preemptirqs}off_tracer_init() and it calls __irqsoff_tracer_init(), which resets per-CPU ringbuffer second time. It's slowpath, but anyway. Link: http://lkml.kernel.org/r/1445278226-16187-1-git-send-email-0x7f454c46@gmail.com Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com> Signed-off-by: Steven Rostedt --- kernel/trace/trace_irqsoff.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index be3222b7d72e..03cdff84d026 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -626,7 +626,6 @@ static int __irqsoff_tracer_init(struct trace_array *tr) irqsoff_trace = tr; /* make sure that the tracer is visible */ smp_wmb(); - tracing_reset_online_cpus(&tr->trace_buffer); ftrace_init_array_ops(tr, irqsoff_tracer_call); -- cgit v1.2.3 From 2f5177f0fd7e531b26d54633be62d1d4cb94621c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Mar 2016 16:22:45 +0100 Subject: sched/cgroup: Fix/cleanup cgroup teardown/init The CPU controller hasn't kept up with the various changes in the whole cgroup initialization / destruction sequence, and commit: 2e91fa7f6d45 ("cgroup: keep zombies associated with their original cgroups") caused it to explode. The reason for this is that zombies do not inhibit css_offline() from being called, but do stall css_released(). Now we tear down the cfs_rq structures on css_offline() but zombies can run after that, leading to use-after-free issues. The solution is to move the tear-down to css_released(), which guarantees nobody (including no zombies) is still using our cgroup. Furthermore, a few simple cleanups are possible too. There doesn't appear to be any point to us using css_online() (anymore?) so fold that in css_alloc(). And since cgroup code guarantees an RCU grace period between css_released() and css_free() we can forgo using call_rcu() and free the stuff immediately. Suggested-by: Tejun Heo Reported-by: Kazuki Yamaguchi Reported-by: Niklas Cassel Tested-by: Niklas Cassel Signed-off-by: Peter Zijlstra (Intel) Acked-by: Tejun Heo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 2e91fa7f6d45 ("cgroup: keep zombies associated with their original cgroups") Link: http://lkml.kernel.org/r/20160316152245.GY6344@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 35 ++++++++++++++--------------------- 1 file changed, 14 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4d872e19244b..2a87bdde8d4e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7536,7 +7536,7 @@ void set_curr_task(int cpu, struct task_struct *p) /* task_group_lock serializes the addition/removal of task groups */ static DEFINE_SPINLOCK(task_group_lock); -static void free_sched_group(struct task_group *tg) +static void sched_free_group(struct task_group *tg) { free_fair_sched_group(tg); free_rt_sched_group(tg); @@ -7562,7 +7562,7 @@ struct task_group *sched_create_group(struct task_group *parent) return tg; err: - free_sched_group(tg); + sched_free_group(tg); return ERR_PTR(-ENOMEM); } @@ -7582,17 +7582,16 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) } /* rcu callback to free various structures associated with a task group */ -static void free_sched_group_rcu(struct rcu_head *rhp) +static void sched_free_group_rcu(struct rcu_head *rhp) { /* now it should be safe to free those cfs_rqs */ - free_sched_group(container_of(rhp, struct task_group, rcu)); + sched_free_group(container_of(rhp, struct task_group, rcu)); } -/* Destroy runqueue etc associated with a task group */ void sched_destroy_group(struct task_group *tg) { /* wait for possible concurrent references to cfs_rqs complete */ - call_rcu(&tg->rcu, free_sched_group_rcu); + call_rcu(&tg->rcu, sched_free_group_rcu); } void sched_offline_group(struct task_group *tg) @@ -8051,31 +8050,26 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (IS_ERR(tg)) return ERR_PTR(-ENOMEM); + sched_online_group(tg, parent); + return &tg->css; } -static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) +static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); - struct task_group *parent = css_tg(css->parent); - if (parent) - sched_online_group(tg, parent); - return 0; + sched_offline_group(tg); } static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); - sched_destroy_group(tg); -} - -static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) -{ - struct task_group *tg = css_tg(css); - - sched_offline_group(tg); + /* + * Relies on the RCU grace period between css_released() and this. + */ + sched_free_group(tg); } static void cpu_cgroup_fork(struct task_struct *task) @@ -8435,9 +8429,8 @@ static struct cftype cpu_files[] = { struct cgroup_subsys cpu_cgrp_subsys = { .css_alloc = cpu_cgroup_css_alloc, + .css_released = cpu_cgroup_css_released, .css_free = cpu_cgroup_css_free, - .css_online = cpu_cgroup_css_online, - .css_offline = cpu_cgroup_css_offline, .fork = cpu_cgroup_fork, .can_attach = cpu_cgroup_can_attach, .attach = cpu_cgroup_attach, -- cgit v1.2.3 From 3a47d5124a957358274e9ca7b115b2f3a914f56d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 9 Mar 2016 13:04:03 +0100 Subject: sched/fair: Fix fairness issue on migration Pavan reported that in the presence of very light tasks (or cgroups) the placement of migrated tasks can cause severe fairness issues. The problem is that enqueue_entity() places the task before it updates time, thereby it can place the task far in the past (remember that light tasks will shoot virtual time forward at a high speed, so in relation to the pre-existing light task, we can land far in the past). This is done because update_curr() needs the current task, and we might be placing the current task. The obvious solution is to differentiate between the current and any other task; placing the current before we update time, and placing any other task after, such that !curr tasks end up at the current moment in time, and not in the past. Reported-by: Pavan Kondeti Tested-by: Pavan Kondeti Signed-off-by: Peter Zijlstra (Intel) Cc: Ben Segall Cc: Linus Torvalds Cc: Matt Fleming Cc: Mike Galbraith Cc: Morten Rasmussen Cc: Paul Turner Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: byungchul.park@lge.com Link: http://lkml.kernel.org/r/20160309120403.GK6344@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 33130529e9b5..3c114d971d84 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3157,17 +3157,25 @@ static inline void check_schedstat_required(void) static void enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { + bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING); + bool curr = cfs_rq->curr == se; + /* - * Update the normalized vruntime before updating min_vruntime - * through calling update_curr(). + * If we're the current task, we must renormalise before calling + * update_curr(). */ - if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING)) + if (renorm && curr) se->vruntime += cfs_rq->min_vruntime; + update_curr(cfs_rq); + /* - * Update run-time statistics of the 'current'. + * Otherwise, renormalise after, such that we're placed at the current + * moment in time, instead of some random moment in the past. */ - update_curr(cfs_rq); + if (renorm && !curr) + se->vruntime += cfs_rq->min_vruntime; + enqueue_entity_load_avg(cfs_rq, se); account_entity_enqueue(cfs_rq, se); update_cfs_shares(cfs_rq); @@ -3183,7 +3191,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_stats_enqueue(cfs_rq, se); check_spread(cfs_rq, se); } - if (se != cfs_rq->curr) + if (!curr) __enqueue_entity(cfs_rq, se); se->on_rq = 1; -- cgit v1.2.3 From d4335581dc30ec6545999c7443bb9fead274a980 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Wed, 9 Mar 2016 14:59:08 +0000 Subject: sched/fair: Add comments to explain select_idle_sibling() It's not entirely obvious how the main loop in select_idle_sibling() works on first glance. Sprinkle a few comments to explain the design and intention behind the loop based on some conversations with Mike and Peter. Signed-off-by: Matt Fleming Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mel Gorman Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1457535548-15329-1-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3c114d971d84..303d6392b389 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5055,7 +5055,19 @@ static int select_idle_sibling(struct task_struct *p, int target) return i; /* - * Otherwise, iterate the domains and find an elegible idle cpu. + * Otherwise, iterate the domains and find an eligible idle cpu. + * + * A completely idle sched group at higher domains is more + * desirable than an idle group at a lower level, because lower + * domains have smaller groups and usually share hardware + * resources which causes tasks to contend on them, e.g. x86 + * hyperthread siblings in the lowest domain (SMT) can contend + * on the shared cpu pipeline. + * + * However, while we prefer idle groups at higher domains + * finding an idle cpu at the lowest domain is still better than + * returning 'target', which we've already established, isn't + * idle. */ sd = rcu_dereference(per_cpu(sd_llc, target)); for_each_lower_domain(sd) { @@ -5065,11 +5077,16 @@ static int select_idle_sibling(struct task_struct *p, int target) tsk_cpus_allowed(p))) goto next; + /* Ensure the entire group is idle */ for_each_cpu(i, sched_group_cpus(sg)) { if (i == target || !idle_cpu(i)) goto next; } + /* + * It doesn't matter which cpu we pick, the + * whole group is idle. + */ target = cpumask_first_and(sched_group_cpus(sg), tsk_cpus_allowed(p)); goto done; -- cgit v1.2.3 From 1a736b77a3f50910843d076623204ba6e5057dc1 Mon Sep 17 00:00:00 2001 From: Dongsheng Yang Date: Mon, 21 Dec 2015 19:14:42 +0800 Subject: sched/cpuacct: Rename parameter in cpuusage_write() for readability The name of the 'reset' parameter to cpuusage_write() is quite confusing, because the only valid value we allow is '0', so !reset is actually the case that resets ... Rename it to 'val' and explain it in a comment that we only allow 0. Signed-off-by: Dongsheng Yang Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: cgroups@vger.kernel.org Cc: tj@kernel.org Link: http://lkml.kernel.org/r/1450696483-2864-1-git-send-email-yangds.fnst@cn.fujitsu.com Signed-off-by: Ingo Molnar --- kernel/sched/cpuacct.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index dd7cbb55bbf2..9c2bbf7efa1a 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -145,13 +145,16 @@ static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft) } static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft, - u64 reset) + u64 val) { struct cpuacct *ca = css_ca(css); int err = 0; int i; - if (reset) { + /* + * Only allow '0' here to do a reset. + */ + if (val) { err = -EINVAL; goto out; } -- cgit v1.2.3 From 73e6aafd9ea81498d31361f01db84a0118da2d1c Mon Sep 17 00:00:00 2001 From: Zhao Lei Date: Thu, 17 Mar 2016 12:19:43 +0800 Subject: sched/cpuacct: Simplify the cpuacct code - Use for() instead of while() loop in some functions to make the code simpler. - Use this_cpu_ptr() instead of per_cpu_ptr() to make the code cleaner and a bit faster. Suggested-by: Peter Zijlstra Signed-off-by: Zhao Lei Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Tejun Heo Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/d8a7ef9592f55224630cb26dea239f05b6398a4e.1458187654.git.zhaolei@cn.fujitsu.com Signed-off-by: Ingo Molnar --- kernel/sched/cpuacct.c | 28 +++++----------------------- kernel/sched/cpuacct.h | 4 ++-- 2 files changed, 7 insertions(+), 25 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 9c2bbf7efa1a..434c2fa41352 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -238,23 +238,10 @@ static struct cftype files[] = { void cpuacct_charge(struct task_struct *tsk, u64 cputime) { struct cpuacct *ca; - int cpu; - - cpu = task_cpu(tsk); rcu_read_lock(); - - ca = task_ca(tsk); - - while (true) { - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - *cpuusage += cputime; - - ca = parent_ca(ca); - if (!ca) - break; - } - + for (ca = task_ca(tsk); ca; ca = parent_ca(ca)) + *this_cpu_ptr(ca->cpuusage) += cputime; rcu_read_unlock(); } @@ -263,18 +250,13 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime) * * Note: it's the caller that updates the account of the root cgroup. */ -void cpuacct_account_field(struct task_struct *p, int index, u64 val) +void cpuacct_account_field(struct task_struct *tsk, int index, u64 val) { - struct kernel_cpustat *kcpustat; struct cpuacct *ca; rcu_read_lock(); - ca = task_ca(p); - while (ca != &root_cpuacct) { - kcpustat = this_cpu_ptr(ca->cpustat); - kcpustat->cpustat[index] += val; - ca = parent_ca(ca); - } + for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca)) + this_cpu_ptr(ca->cpustat)->cpustat[index] += val; rcu_read_unlock(); } diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h index ed605624a5e7..ba72807c73d4 100644 --- a/kernel/sched/cpuacct.h +++ b/kernel/sched/cpuacct.h @@ -1,7 +1,7 @@ #ifdef CONFIG_CGROUP_CPUACCT extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); -extern void cpuacct_account_field(struct task_struct *p, int index, u64 val); +extern void cpuacct_account_field(struct task_struct *tsk, int index, u64 val); #else @@ -10,7 +10,7 @@ static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) } static inline void -cpuacct_account_field(struct task_struct *p, int index, u64 val) +cpuacct_account_field(struct task_struct *tsk, int index, u64 val) { } -- cgit v1.2.3 From 3debb0a9ddb16526de8b456491b7db60114f7b5e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 22 Mar 2016 17:30:58 -0400 Subject: tracing: Fix trace_printk() to print when not using bprintk() The trace_printk() code will allocate extra buffers if the compile detects that a trace_printk() is used. To do this, the format of the trace_printk() is saved to the __trace_printk_fmt section, and if that section is bigger than zero, the buffers are allocated (along with a message that this has happened). If trace_printk() uses a format that is not a constant, and thus something not guaranteed to be around when the print happens, the compiler optimizes the fmt out, as it is not used, and the __trace_printk_fmt section is not filled. This means the kernel will not allocate the special buffers needed for the trace_printk() and the trace_printk() will not write anything to the tracing buffer. Adding a "__used" to the variable in the __trace_printk_fmt section will keep it around, even though it is set to NULL. This will keep the string from being printed in the debugfs/tracing/printk_formats section as it is not needed. Reported-by: Vlastimil Babka Fixes: 07d777fe8c398 "tracing: Add percpu buffers for trace_printk()" Cc: stable@vger.kernel.org # v3.5+ Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 6 +++--- kernel/trace/trace_printk.c | 3 +++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f31638c6e873..95452f72349a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -635,7 +635,7 @@ do { \ #define do_trace_printk(fmt, args...) \ do { \ - static const char *trace_printk_fmt \ + static const char *trace_printk_fmt __used \ __attribute__((section("__trace_printk_fmt"))) = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ @@ -679,7 +679,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); */ #define trace_puts(str) ({ \ - static const char *trace_printk_fmt \ + static const char *trace_printk_fmt __used \ __attribute__((section("__trace_printk_fmt"))) = \ __builtin_constant_p(str) ? str : NULL; \ \ @@ -701,7 +701,7 @@ extern void trace_dump_stack(int skip); #define ftrace_vprintk(fmt, vargs) \ do { \ if (__builtin_constant_p(fmt)) { \ - static const char *trace_printk_fmt \ + static const char *trace_printk_fmt __used \ __attribute__((section("__trace_printk_fmt"))) = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 060df67dbdd1..f96f0383f6c6 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -296,6 +296,9 @@ static int t_show(struct seq_file *m, void *v) const char *str = *fmt; int i; + if (!*fmt) + return 0; + seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt); /* -- cgit v1.2.3 From 7e6867bf831c71fe0e47438831ae3a94d4c7ab3c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 18 Mar 2016 16:28:04 +0100 Subject: tracing: Record and show NMI state The latency tracer format has a nice column to indicate IRQ state, but this is not able to tell us about NMI state. When tracing perf interrupt handlers (which often run in NMI context) it is very useful to see how the events nest. Link: http://lkml.kernel.org/r/20160318153022.105068893@infradead.org Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 1 + kernel/trace/trace.h | 1 + kernel/trace/trace_output.c | 10 +++++++--- 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index cb2b708e4ea7..7bdf8ba323ec 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1664,6 +1664,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, #else TRACE_FLAG_IRQS_NOSUPPORT | #endif + ((pc & NMI_MASK ) ? TRACE_FLAG_NMI : 0) | ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 39588c23dd8b..3fff4adfd431 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -125,6 +125,7 @@ enum trace_flag_type { TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, + TRACE_FLAG_NMI = 0x40, }; #define TRACE_BUF_SIZE 1024 diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 282982195e09..0bb9cf2d53e6 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -389,7 +389,9 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) char irqs_off; int hardirq; int softirq; + int nmi; + nmi = entry->flags & TRACE_FLAG_NMI; hardirq = entry->flags & TRACE_FLAG_HARDIRQ; softirq = entry->flags & TRACE_FLAG_SOFTIRQ; @@ -415,10 +417,12 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) } hardsoft_irq = + (nmi && hardirq) ? 'Z' : + nmi ? 'z' : (hardirq && softirq) ? 'H' : - hardirq ? 'h' : - softirq ? 's' : - '.'; + hardirq ? 'h' : + softirq ? 's' : + '.' ; trace_seq_printf(s, "%c%c%c", irqs_off, need_resched, hardsoft_irq); -- cgit v1.2.3 From b4aa14a63cb3194d8eab355fcee194838ab09121 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 22 Mar 2016 14:24:39 -0700 Subject: kernel/hung_task.c: use timeout diff when timeout is updated When new timeout is written to /proc/sys/kernel/hung_task_timeout_secs, khungtaskd is interrupted and again sleeps for full timeout duration. This means that hang task will not be checked if new timeout is written periodically within old timeout duration and/or checking of hang task will be delayed for up to previous timeout duration. Fix this by remembering last time khungtaskd checked hang task. This change will allow other watchdog tasks (if any) to share khungtaskd by sleeping for minimal timeout diff of all watchdog tasks. Doing more watchdog tasks from khungtaskd will reduce the possibility of printk() collisions by multiple watchdog threads. Signed-off-by: Tetsuo Handa Cc: Oleg Nesterov Cc: Aaron Tomlin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/hung_task.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/hung_task.c b/kernel/hung_task.c index e0f90c2b57aa..d234022805dc 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -185,10 +185,12 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) rcu_read_unlock(); } -static unsigned long timeout_jiffies(unsigned long timeout) +static long hung_timeout_jiffies(unsigned long last_checked, + unsigned long timeout) { /* timeout of 0 will disable the watchdog */ - return timeout ? timeout * HZ : MAX_SCHEDULE_TIMEOUT; + return timeout ? last_checked - jiffies + timeout * HZ : + MAX_SCHEDULE_TIMEOUT; } /* @@ -224,18 +226,21 @@ EXPORT_SYMBOL_GPL(reset_hung_task_detector); */ static int watchdog(void *dummy) { + unsigned long hung_last_checked = jiffies; + set_user_nice(current, 0); for ( ; ; ) { unsigned long timeout = sysctl_hung_task_timeout_secs; + long t = hung_timeout_jiffies(hung_last_checked, timeout); - while (schedule_timeout_interruptible(timeout_jiffies(timeout))) - timeout = sysctl_hung_task_timeout_secs; - - if (atomic_xchg(&reset_hung_task, 0)) + if (t <= 0) { + if (!atomic_xchg(&reset_hung_task, 0)) + check_hung_uninterruptible_tasks(timeout); + hung_last_checked = jiffies; continue; - - check_hung_uninterruptible_tasks(timeout); + } + schedule_timeout_interruptible(t); } return 0; -- cgit v1.2.3 From 5c38065e021bc76f97fc08997f6d7fc7ea3fb7a7 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 22 Mar 2016 14:24:52 -0700 Subject: seccomp: check in_compat_syscall, not is_compat_task, in strict mode Seccomp wants to know the syscall bitness, not the caller task bitness, when it selects the syscall whitelist. As far as I know, this makes no difference on any architecture, so it's not a security problem. (It generates identical code everywhere except sparc, and, on sparc, the syscall numbering is the same for both ABIs.) Signed-off-by: Andy Lutomirski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/seccomp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 15a1795bbba1..e1e5a354854e 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -395,7 +395,7 @@ seccomp_prepare_user_filter(const char __user *user_filter) struct seccomp_filter *filter = ERR_PTR(-EFAULT); #ifdef CONFIG_COMPAT - if (is_compat_task()) { + if (in_compat_syscall()) { struct compat_sock_fprog fprog32; if (copy_from_user(&fprog32, user_filter, sizeof(fprog32))) goto out; @@ -529,7 +529,7 @@ static void __secure_computing_strict(int this_syscall) { int *syscall_whitelist = mode1_syscalls; #ifdef CONFIG_COMPAT - if (is_compat_task()) + if (in_compat_syscall()) syscall_whitelist = mode1_syscalls_32; #endif do { -- cgit v1.2.3 From 5c465217a930d4bbb7dd35a56bde1eea5bbd14d6 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 22 Mar 2016 14:24:55 -0700 Subject: ptrace: in PEEK_SIGINFO, check syscall bitness, not task bitness Users of the 32-bit ptrace() ABI expect the full 32-bit ABI. siginfo translation should check ptrace() ABI, not caller task ABI. This is an ABI change on SPARC. Let's hope that no one relied on the old buggy ABI. Signed-off-by: Andy Lutomirski Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/ptrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 2341efe7fe02..c79b91d09e35 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -681,7 +681,7 @@ static int ptrace_peek_siginfo(struct task_struct *child, break; #ifdef CONFIG_COMPAT - if (unlikely(is_compat_task())) { + if (unlikely(in_compat_syscall())) { compat_siginfo_t __user *uinfo = compat_ptr(data); if (copy_siginfo_to_user32(uinfo, &info) || -- cgit v1.2.3 From efbc0fbf34927bd4d3d49b50b370990be82809c2 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 22 Mar 2016 14:24:58 -0700 Subject: auditsc: for seccomp events, log syscall compat state using in_compat_syscall Except on SPARC, this is what the code always did. SPARC compat seccomp was buggy, although the impact of the bug was limited because SPARC 32-bit and 64-bit syscall numbers are the same. Signed-off-by: Andy Lutomirski Cc: Paul Moore Cc: Eric Paris Cc: David Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/auditsc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 195ffaee50b9..7d0e3cf8abe1 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2412,8 +2412,8 @@ void __audit_seccomp(unsigned long syscall, long signr, int code) return; audit_log_task(ab); audit_log_format(ab, " sig=%ld arch=%x syscall=%ld compat=%d ip=0x%lx code=0x%x", - signr, syscall_get_arch(), syscall, is_compat_task(), - KSTK_EIP(current), code); + signr, syscall_get_arch(), syscall, + in_compat_syscall(), KSTK_EIP(current), code); audit_log_end(ab); } -- cgit v1.2.3 From 1333ab03150478df8d6f5673a91df1e50dc6ab97 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 22 Mar 2016 14:25:33 -0700 Subject: ptrace: change __ptrace_unlink() to clear ->ptrace under ->siglock This test-case (simplified version of generated by syzkaller) #include #include #include void test(void) { for (;;) { if (fork()) { wait(NULL); continue; } ptrace(PTRACE_SEIZE, getppid(), 0, 0); ptrace(PTRACE_INTERRUPT, getppid(), 0, 0); _exit(0); } } int main(void) { int np; for (np = 0; np < 8; ++np) if (!fork()) test(); while (wait(NULL) > 0) ; return 0; } triggers the 2nd WARN_ON_ONCE(!signr) warning in do_jobctl_trap(). The problem is that __ptrace_unlink() clears task->jobctl under siglock but task->ptrace is cleared without this lock held; this fools the "else" branch which assumes that !PT_SEIZED means PT_PTRACED. Note also that most of other PTRACE_SEIZE checks can race with detach from the exiting tracer too. Say, the callers of ptrace_trap_notify() assume that SEIZED can't go away after it was checked. Signed-off-by: Oleg Nesterov Reported-by: Dmitry Vyukov Cc: Tejun Heo Cc: syzkaller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/ptrace.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index c79b91d09e35..d49bfa1e53e6 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -73,12 +73,11 @@ void __ptrace_unlink(struct task_struct *child) { BUG_ON(!child->ptrace); - child->ptrace = 0; child->parent = child->real_parent; list_del_init(&child->ptrace_entry); spin_lock(&child->sighand->siglock); - + child->ptrace = 0; /* * Clear all pending traps and TRAPPING. TRAPPING should be * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. -- cgit v1.2.3 From 378c6520e7d29280f400ef2ceaf155c86f05a71a Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 22 Mar 2016 14:25:36 -0700 Subject: fs/coredump: prevent fsuid=0 dumps into user-controlled directories This commit fixes the following security hole affecting systems where all of the following conditions are fulfilled: - The fs.suid_dumpable sysctl is set to 2. - The kernel.core_pattern sysctl's value starts with "/". (Systems where kernel.core_pattern starts with "|/" are not affected.) - Unprivileged user namespace creation is permitted. (This is true on Linux >=3.8, but some distributions disallow it by default using a distro patch.) Under these conditions, if a program executes under secure exec rules, causing it to run with the SUID_DUMP_ROOT flag, then unshares its user namespace, changes its root directory and crashes, the coredump will be written using fsuid=0 and a path derived from kernel.core_pattern - but this path is interpreted relative to the root directory of the process, allowing the attacker to control where a coredump will be written with root privileges. To fix the security issue, always interpret core_pattern for dumps that are written under SUID_DUMP_ROOT relative to the root directory of init. Signed-off-by: Jann Horn Acked-by: Kees Cook Cc: Al Viro Cc: "Eric W. Biederman" Cc: Andy Lutomirski Cc: Oleg Nesterov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/drivers/mconsole_kern.c | 2 +- fs/coredump.c | 30 ++++++++++++++++++++++++++---- fs/fhandle.c | 2 +- fs/open.c | 6 ++---- include/linux/fs.h | 2 +- kernel/sysctl_binary.c | 2 +- 6 files changed, 32 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index b821b13d343a..8a6b57108ac2 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -133,7 +133,7 @@ void mconsole_proc(struct mc_request *req) ptr += strlen("proc"); ptr = skip_spaces(ptr); - file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY); + file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0); if (IS_ERR(file)) { mconsole_reply(req, "Failed to open file", 1, 0); printk(KERN_ERR "open /proc/%s: %ld\n", ptr, PTR_ERR(file)); diff --git a/fs/coredump.c b/fs/coredump.c index 9ea87e9fdccf..47c32c3bfa1d 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -32,6 +32,9 @@ #include #include #include +#include +#include +#include #include #include @@ -649,6 +652,8 @@ void do_coredump(const siginfo_t *siginfo) } } else { struct inode *inode; + int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW | + O_LARGEFILE | O_EXCL; if (cprm.limit < binfmt->min_coredump) goto fail_unlock; @@ -687,10 +692,27 @@ void do_coredump(const siginfo_t *siginfo) * what matters is that at least one of the two processes * writes its coredump successfully, not which one. */ - cprm.file = filp_open(cn.corename, - O_CREAT | 2 | O_NOFOLLOW | - O_LARGEFILE | O_EXCL, - 0600); + if (need_suid_safe) { + /* + * Using user namespaces, normal user tasks can change + * their current->fs->root to point to arbitrary + * directories. Since the intention of the "only dump + * with a fully qualified path" rule is to control where + * coredumps may be placed using root privileges, + * current->fs->root must not be used. Instead, use the + * root directory of init_task. + */ + struct path root; + + task_lock(&init_task); + get_fs_root(init_task.fs, &root); + task_unlock(&init_task); + cprm.file = file_open_root(root.dentry, root.mnt, + cn.corename, open_flags, 0600); + path_put(&root); + } else { + cprm.file = filp_open(cn.corename, open_flags, 0600); + } if (IS_ERR(cprm.file)) goto fail_unlock; diff --git a/fs/fhandle.c b/fs/fhandle.c index d59712dfa3e7..ca3c3dd01789 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -228,7 +228,7 @@ long do_handle_open(int mountdirfd, path_put(&path); return fd; } - file = file_open_root(path.dentry, path.mnt, "", open_flag); + file = file_open_root(path.dentry, path.mnt, "", open_flag, 0); if (IS_ERR(file)) { put_unused_fd(fd); retval = PTR_ERR(file); diff --git a/fs/open.c b/fs/open.c index 55bdc75e2172..17cb6b1dab75 100644 --- a/fs/open.c +++ b/fs/open.c @@ -992,14 +992,12 @@ struct file *filp_open(const char *filename, int flags, umode_t mode) EXPORT_SYMBOL(filp_open); struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt, - const char *filename, int flags) + const char *filename, int flags, umode_t mode) { struct open_flags op; - int err = build_open_flags(flags, 0, &op); + int err = build_open_flags(flags, mode, &op); if (err) return ERR_PTR(err); - if (flags & O_CREAT) - return ERR_PTR(-EINVAL); return do_file_open_root(dentry, mnt, filename, &op); } EXPORT_SYMBOL(file_open_root); diff --git a/include/linux/fs.h b/include/linux/fs.h index 35d99266ca9a..14a97194b34b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2263,7 +2263,7 @@ extern long do_sys_open(int dfd, const char __user *filename, int flags, extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, - const char *, int); + const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 7e7746a42a62..10a1d7dc9313 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1321,7 +1321,7 @@ static ssize_t binary_sysctl(const int *name, int nlen, } mnt = task_active_pid_ns(current)->proc_mnt; - file = file_open_root(mnt->mnt_root, mnt, pathname, flags); + file = file_open_root(mnt->mnt_root, mnt, pathname, flags, 0); result = PTR_ERR(file); if (IS_ERR(file)) goto out_putname; -- cgit v1.2.3 From ebc41f20d77f6ad91f1f2d2af5147dc9bb6b5eea Mon Sep 17 00:00:00 2001 From: Hidehiro Kawai Date: Tue, 22 Mar 2016 14:27:17 -0700 Subject: panic: change nmi_panic from macro to function Commit 1717f2096b54 ("panic, x86: Fix re-entrance problem due to panic on NMI") and commit 58c5661f2144 ("panic, x86: Allow CPUs to save registers even if looping in NMI context") introduced nmi_panic() which prevents concurrent/recursive execution of panic(). It also saves registers for the crash dump on x86. However, there are some cases where NMI handlers still use panic(). This patch set partially replaces them with nmi_panic() in those cases. Even this patchset is applied, some NMI or similar handlers (e.g. MCE handler) continue to use panic(). This is because I can't test them well and actual problems won't happen. For example, the possibility that normal panic and panic on MCE happen simultaneously is very low. This patch (of 3): Convert nmi_panic() to a proper function and export it instead of exporting internal implementation details to modules, for obvious reasons. Signed-off-by: Hidehiro Kawai Acked-by: Borislav Petkov Acked-by: Michal Nazarewicz Cc: Michal Hocko Cc: Rasmus Villemoes Cc: Nicolas Iooss Cc: Javi Merino Cc: Gobinda Charan Maji Cc: "Steven Rostedt (Red Hat)" Cc: Thomas Gleixner Cc: Vitaly Kuznetsov Cc: HATAYAMA Daisuke Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 21 +-------------------- kernel/panic.c | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index b82646ee70eb..a13c52ccd8ac 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -255,7 +255,7 @@ extern long (*panic_blink)(int state); __printf(1, 2) void panic(const char *fmt, ...) __noreturn __cold; -void nmi_panic_self_stop(struct pt_regs *); +void nmi_panic(struct pt_regs *regs, const char *msg); extern void oops_enter(void); extern void oops_exit(void); void print_oops_end_marker(void); @@ -456,25 +456,6 @@ extern bool crash_kexec_post_notifiers; extern atomic_t panic_cpu; #define PANIC_CPU_INVALID -1 -/* - * A variant of panic() called from NMI context. We return if we've already - * panicked on this CPU. If another CPU already panicked, loop in - * nmi_panic_self_stop() which can provide architecture dependent code such - * as saving register state for crash dump. - */ -#define nmi_panic(regs, fmt, ...) \ -do { \ - int old_cpu, cpu; \ - \ - cpu = raw_smp_processor_id(); \ - old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); \ - \ - if (old_cpu == PANIC_CPU_INVALID) \ - panic(fmt, ##__VA_ARGS__); \ - else if (old_cpu != cpu) \ - nmi_panic_self_stop(regs); \ -} while (0) - /* * Only to be used by arch init code. If the user over-wrote the default * CONFIG_PANIC_TIMEOUT, honor it. diff --git a/kernel/panic.c b/kernel/panic.c index fa400852bf6c..535c96510a44 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -73,6 +73,26 @@ void __weak nmi_panic_self_stop(struct pt_regs *regs) atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); +/* + * A variant of panic() called from NMI context. We return if we've already + * panicked on this CPU. If another CPU already panicked, loop in + * nmi_panic_self_stop() which can provide architecture dependent code such + * as saving register state for crash dump. + */ +void nmi_panic(struct pt_regs *regs, const char *msg) +{ + int old_cpu, cpu; + + cpu = raw_smp_processor_id(); + old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); + + if (old_cpu == PANIC_CPU_INVALID) + panic("%s", msg); + else if (old_cpu != cpu) + nmi_panic_self_stop(regs); +} +EXPORT_SYMBOL(nmi_panic); + /** * panic - halt the system * @fmt: The text string to print -- cgit v1.2.3 From ade356b99a4187578609f2a91c4d2ed88e4e70dc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 22 Mar 2016 14:27:26 -0700 Subject: profile: hide unused functions when !CONFIG_PROC_FS A couple of functions and variables in the profile implementation are used only on SMP systems by the procfs code, but are unused if either procfs is disabled or in uniprocessor kernels. gcc prints a harmless warning about the unused symbols: kernel/profile.c:243:13: error: 'profile_flip_buffers' defined but not used [-Werror=unused-function] static void profile_flip_buffers(void) ^ kernel/profile.c:266:13: error: 'profile_discard_flip_buffers' defined but not used [-Werror=unused-function] static void profile_discard_flip_buffers(void) ^ kernel/profile.c:330:12: error: 'profile_cpu_callback' defined but not used [-Werror=unused-function] static int profile_cpu_callback(struct notifier_block *info, ^ This adds further #ifdef to the file, to annotate exactly in which cases they are used. I have done several thousand ARM randconfig kernels with this patch applied and no longer get any warnings in this file. Signed-off-by: Arnd Bergmann Cc: Vlastimil Babka Cc: Robin Holt Cc: Johannes Weiner Cc: Christoph Lameter Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/profile.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/profile.c b/kernel/profile.c index 51369697466e..c2199e9901c9 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -44,7 +44,7 @@ int prof_on __read_mostly; EXPORT_SYMBOL_GPL(prof_on); static cpumask_var_t prof_cpu_mask; -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits); static DEFINE_PER_CPU(int, cpu_profile_flip); static DEFINE_MUTEX(profile_flip_mutex); @@ -202,7 +202,7 @@ int profile_event_unregister(enum profile_type type, struct notifier_block *n) } EXPORT_SYMBOL_GPL(profile_event_unregister); -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) /* * Each cpu has a pair of open-addressed hashtables for pending * profile hits. read_profile() IPI's all cpus to request them -- cgit v1.2.3 From 5c9a8750a6409c63a0f01d51a9024861022f6593 Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Tue, 22 Mar 2016 14:27:30 -0700 Subject: kernel: add kcov code coverage kcov provides code coverage collection for coverage-guided fuzzing (randomized testing). Coverage-guided fuzzing is a testing technique that uses coverage feedback to determine new interesting inputs to a system. A notable user-space example is AFL (http://lcamtuf.coredump.cx/afl/). However, this technique is not widely used for kernel testing due to missing compiler and kernel support. kcov does not aim to collect as much coverage as possible. It aims to collect more or less stable coverage that is function of syscall inputs. To achieve this goal it does not collect coverage in soft/hard interrupts and instrumentation of some inherently non-deterministic or non-interesting parts of kernel is disbled (e.g. scheduler, locking). Currently there is a single coverage collection mode (tracing), but the API anticipates additional collection modes. Initially I also implemented a second mode which exposes coverage in a fixed-size hash table of counters (what Quentin used in his original patch). I've dropped the second mode for simplicity. This patch adds the necessary support on kernel side. The complimentary compiler support was added in gcc revision 231296. We've used this support to build syzkaller system call fuzzer, which has found 90 kernel bugs in just 2 months: https://github.com/google/syzkaller/wiki/Found-Bugs We've also found 30+ bugs in our internal systems with syzkaller. Another (yet unexplored) direction where kcov coverage would greatly help is more traditional "blob mutation". For example, mounting a random blob as a filesystem, or receiving a random blob over wire. Why not gcov. Typical fuzzing loop looks as follows: (1) reset coverage, (2) execute a bit of code, (3) collect coverage, repeat. A typical coverage can be just a dozen of basic blocks (e.g. an invalid input). In such context gcov becomes prohibitively expensive as reset/collect coverage steps depend on total number of basic blocks/edges in program (in case of kernel it is about 2M). Cost of kcov depends only on number of executed basic blocks/edges. On top of that, kernel requires per-thread coverage because there are always background threads and unrelated processes that also produce coverage. With inlined gcov instrumentation per-thread coverage is not possible. kcov exposes kernel PCs and control flow to user-space which is insecure. But debugfs should not be mapped as user accessible. Based on a patch by Quentin Casasnovas. [akpm@linux-foundation.org: make task_struct.kcov_mode have type `enum kcov_mode'] [akpm@linux-foundation.org: unbreak allmodconfig] [akpm@linux-foundation.org: follow x86 Makefile layout standards] Signed-off-by: Dmitry Vyukov Reviewed-by: Kees Cook Cc: syzkaller Cc: Vegard Nossum Cc: Catalin Marinas Cc: Tavis Ormandy Cc: Will Deacon Cc: Quentin Casasnovas Cc: Kostya Serebryany Cc: Eric Dumazet Cc: Alexander Potapenko Cc: Kees Cook Cc: Bjorn Helgaas Cc: Sasha Levin Cc: David Drysdale Cc: Ard Biesheuvel Cc: Andrey Ryabinin Cc: Kirill A. Shutemov Cc: Jiri Slaby Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kcov.txt | 111 ++++++++++++++ Makefile | 11 +- arch/x86/Kconfig | 1 + arch/x86/boot/Makefile | 7 + arch/x86/boot/compressed/Makefile | 3 + arch/x86/entry/vdso/Makefile | 3 + arch/x86/kernel/Makefile | 6 + arch/x86/kernel/apic/Makefile | 4 + arch/x86/kernel/cpu/Makefile | 4 + arch/x86/lib/Makefile | 3 + arch/x86/mm/Makefile | 3 + arch/x86/realmode/rm/Makefile | 3 + drivers/firmware/efi/libstub/Makefile | 3 + include/linux/kcov.h | 29 ++++ include/linux/sched.h | 11 ++ include/uapi/linux/kcov.h | 10 ++ kernel/Makefile | 12 ++ kernel/exit.c | 2 + kernel/fork.c | 3 + kernel/kcov.c | 273 ++++++++++++++++++++++++++++++++++ kernel/locking/Makefile | 3 + kernel/rcu/Makefile | 4 + kernel/sched/Makefile | 4 + lib/Kconfig.debug | 21 +++ lib/Makefile | 12 ++ mm/Makefile | 15 ++ mm/kasan/Makefile | 1 + scripts/Makefile.lib | 6 + 28 files changed, 567 insertions(+), 1 deletion(-) create mode 100644 Documentation/kcov.txt create mode 100644 include/linux/kcov.h create mode 100644 include/uapi/linux/kcov.h create mode 100644 kernel/kcov.c (limited to 'kernel') diff --git a/Documentation/kcov.txt b/Documentation/kcov.txt new file mode 100644 index 000000000000..779ff4ab1c1d --- /dev/null +++ b/Documentation/kcov.txt @@ -0,0 +1,111 @@ +kcov: code coverage for fuzzing +=============================== + +kcov exposes kernel code coverage information in a form suitable for coverage- +guided fuzzing (randomized testing). Coverage data of a running kernel is +exported via the "kcov" debugfs file. Coverage collection is enabled on a task +basis, and thus it can capture precise coverage of a single system call. + +Note that kcov does not aim to collect as much coverage as possible. It aims +to collect more or less stable coverage that is function of syscall inputs. +To achieve this goal it does not collect coverage in soft/hard interrupts +and instrumentation of some inherently non-deterministic parts of kernel is +disbled (e.g. scheduler, locking). + +Usage: +====== + +Configure kernel with: + + CONFIG_KCOV=y + +CONFIG_KCOV requires gcc built on revision 231296 or later. +Profiling data will only become accessible once debugfs has been mounted: + + mount -t debugfs none /sys/kernel/debug + +The following program demonstrates kcov usage from within a test program: + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) +#define KCOV_ENABLE _IO('c', 100) +#define KCOV_DISABLE _IO('c', 101) +#define COVER_SIZE (64<<10) + +int main(int argc, char **argv) +{ + int fd; + unsigned long *cover, n, i; + + /* A single fd descriptor allows coverage collection on a single + * thread. + */ + fd = open("/sys/kernel/debug/kcov", O_RDWR); + if (fd == -1) + perror("open"), exit(1); + /* Setup trace mode and trace size. */ + if (ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE)) + perror("ioctl"), exit(1); + /* Mmap buffer shared between kernel- and user-space. */ + cover = (unsigned long*)mmap(NULL, COVER_SIZE * sizeof(unsigned long), + PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if ((void*)cover == MAP_FAILED) + perror("mmap"), exit(1); + /* Enable coverage collection on the current thread. */ + if (ioctl(fd, KCOV_ENABLE, 0)) + perror("ioctl"), exit(1); + /* Reset coverage from the tail of the ioctl() call. */ + __atomic_store_n(&cover[0], 0, __ATOMIC_RELAXED); + /* That's the target syscal call. */ + read(-1, NULL, 0); + /* Read number of PCs collected. */ + n = __atomic_load_n(&cover[0], __ATOMIC_RELAXED); + for (i = 0; i < n; i++) + printf("0x%lx\n", cover[i + 1]); + /* Disable coverage collection for the current thread. After this call + * coverage can be enabled for a different thread. + */ + if (ioctl(fd, KCOV_DISABLE, 0)) + perror("ioctl"), exit(1); + /* Free resources. */ + if (munmap(cover, COVER_SIZE * sizeof(unsigned long))) + perror("munmap"), exit(1); + if (close(fd)) + perror("close"), exit(1); + return 0; +} + +After piping through addr2line output of the program looks as follows: + +SyS_read +fs/read_write.c:562 +__fdget_pos +fs/file.c:774 +__fget_light +fs/file.c:746 +__fget_light +fs/file.c:750 +__fget_light +fs/file.c:760 +__fdget_pos +fs/file.c:784 +SyS_read +fs/read_write.c:562 + +If a program needs to collect coverage from several threads (independently), +it needs to open /sys/kernel/debug/kcov in each thread separately. + +The interface is fine-grained to allow efficient forking of test processes. +That is, a parent process opens /sys/kernel/debug/kcov, enables trace mode, +mmaps coverage buffer and then forks child processes in a loop. Child processes +only need to enable coverage (disable happens automatically on thread end). diff --git a/Makefile b/Makefile index e055b969c325..b98a4f70d1b5 100644 --- a/Makefile +++ b/Makefile @@ -365,6 +365,7 @@ LDFLAGS_MODULE = CFLAGS_KERNEL = AFLAGS_KERNEL = CFLAGS_GCOV = -fprofile-arcs -ftest-coverage +CFLAGS_KCOV = -fsanitize-coverage=trace-pc # Use USERINCLUDE when you must reference the UAPI directories only. @@ -411,7 +412,7 @@ export MAKE AWK GENKSYMS INSTALLKERNEL PERL PYTHON UTS_MACHINE export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS LDFLAGS -export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_GCOV CFLAGS_KASAN CFLAGS_UBSAN +export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_GCOV CFLAGS_KCOV CFLAGS_KASAN CFLAGS_UBSAN export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL @@ -673,6 +674,14 @@ endif endif KBUILD_CFLAGS += $(stackp-flag) +ifdef CONFIG_KCOV + ifeq ($(call cc-option, $(CFLAGS_KCOV)),) + $(warning Cannot use CONFIG_KCOV: \ + -fsanitize-coverage=trace-pc is not supported by compiler) + CFLAGS_KCOV = + endif +endif + ifeq ($(cc-name),clang) KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,) KBUILD_CPPFLAGS += $(call cc-option,-Wno-unknown-warning-option,) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8b680a5cb25b..54478b7635de 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -28,6 +28,7 @@ config X86 select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_MMIO_FLUSH select ARCH_HAS_SG_CHAIN diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 0bf6749522d9..b1ef9e489084 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -12,6 +12,13 @@ KASAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y +# Kernel does not boot with kcov instrumentation here. +# One of the problems observed was insertion of __sanitizer_cov_trace_pc() +# callback into middle of per-cpu data enabling code. Thus the callback observed +# inconsistent state and crashed. We are interested mostly in syscall coverage, +# so boot code is not interesting anyway. +KCOV_INSTRUMENT := n + # If you want to preset the SVGA mode, uncomment the next line and # set SVGA_MODE to whatever number you want. # Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode. diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 5e1d26e09407..6915ff2bd996 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -19,6 +19,9 @@ KASAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y +# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. +KCOV_INSTRUMENT := n + targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index f9fb859c98b9..6874da5f67fc 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -7,6 +7,9 @@ KASAN_SANITIZE := n UBSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y +# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. +KCOV_INSTRUMENT := n + VDSO64-$(CONFIG_X86_64) := y VDSOX32-$(CONFIG_X86_X32_ABI) := y VDSO32-$(CONFIG_X86_32) := y diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index d5fb0871aba3..adaae2c781c1 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -25,6 +25,12 @@ OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_mcount_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y +# If instrumentation of this dir is enabled, boot hangs during first second. +# Probably could be more selective here, but note that files related to irqs, +# boot, dumpstack/stacktrace, etc are either non-interesting or can lead to +# non-deterministic coverage. +KCOV_INSTRUMENT := n + CFLAGS_irq.o := -I$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 8bb12ddc5db8..8e63ebdcbd0b 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -2,6 +2,10 @@ # Makefile for local APIC drivers and for the IO-APIC code # +# Leads to non-deterministic coverage that is not a function of syscall inputs. +# In particualr, smp_apic_timer_interrupt() is called in random places. +KCOV_INSTRUMENT := n + obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o ipi.o vector.o obj-y += hw_nmi.o diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 0d373d7affc8..4a8697f7d4ef 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -8,6 +8,10 @@ CFLAGS_REMOVE_common.o = -pg CFLAGS_REMOVE_perf_event.o = -pg endif +# If these files are instrumented, boot hangs during the first second. +KCOV_INSTRUMENT_common.o := n +KCOV_INSTRUMENT_perf_event.o := n + # Make sure load_percpu_segment has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_common.o := $(nostackp) diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index a501fa25da41..72a576752a7e 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -2,6 +2,9 @@ # Makefile for x86 specific library files. # +# Produces uninteresting flaky coverage. +KCOV_INSTRUMENT_delay.o := n + inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt quiet_cmd_inat_tables = GEN $@ diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 67cf2e1e557b..f98913258c63 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,3 +1,6 @@ +# Kernel does not boot with instrumentation of tlb.c. +KCOV_INSTRUMENT_tlb.o := n + obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o physaddr.o gup.o setup_nx.o diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 053abe7b0ef7..b95964610ea7 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -9,6 +9,9 @@ KASAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y +# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. +KCOV_INSTRUMENT := n + always := realmode.bin realmode.relocs wakeup-objs := wakeup_asm.o wakemain.o video-mode.o diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index a15841eced4e..da99bbb74aeb 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -25,6 +25,9 @@ KASAN_SANITIZE := n UBSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y +# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. +KCOV_INSTRUMENT := n + lib-y := efi-stub-helper.o # include the stub's generic dependencies from lib/ when building for ARM/arm64 diff --git a/include/linux/kcov.h b/include/linux/kcov.h new file mode 100644 index 000000000000..2883ac98c280 --- /dev/null +++ b/include/linux/kcov.h @@ -0,0 +1,29 @@ +#ifndef _LINUX_KCOV_H +#define _LINUX_KCOV_H + +#include + +struct task_struct; + +#ifdef CONFIG_KCOV + +void kcov_task_init(struct task_struct *t); +void kcov_task_exit(struct task_struct *t); + +enum kcov_mode { + /* Coverage collection is not enabled yet. */ + KCOV_MODE_DISABLED = 0, + /* + * Tracing coverage collection mode. + * Covered PCs are collected in a per-task buffer. + */ + KCOV_MODE_TRACE = 1, +}; + +#else + +static inline void kcov_task_init(struct task_struct *t) {} +static inline void kcov_task_exit(struct task_struct *t) {} + +#endif /* CONFIG_KCOV */ +#endif /* _LINUX_KCOV_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 084ed9fba620..34495d2d2d7b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -51,6 +51,7 @@ struct sched_param { #include #include #include +#include #include #include #include @@ -1818,6 +1819,16 @@ struct task_struct { /* bitmask and counter of trace recursion */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ +#ifdef CONFIG_KCOV + /* Coverage collection mode enabled for this task (0 if disabled). */ + enum kcov_mode kcov_mode; + /* Size of the kcov_area. */ + unsigned kcov_size; + /* Buffer for coverage collection. */ + void *kcov_area; + /* kcov desciptor wired with this task or NULL. */ + struct kcov *kcov; +#endif #ifdef CONFIG_MEMCG struct mem_cgroup *memcg_in_oom; gfp_t memcg_oom_gfp_mask; diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h new file mode 100644 index 000000000000..574e22ec640d --- /dev/null +++ b/include/uapi/linux/kcov.h @@ -0,0 +1,10 @@ +#ifndef _LINUX_KCOV_IOCTLS_H +#define _LINUX_KCOV_IOCTLS_H + +#include + +#define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) +#define KCOV_ENABLE _IO('c', 100) +#define KCOV_DISABLE _IO('c', 101) + +#endif /* _LINUX_KCOV_IOCTLS_H */ diff --git a/kernel/Makefile b/kernel/Makefile index baa55e50a315..f0c40bf49d9f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -18,6 +18,17 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_irq_work.o = $(CC_FLAGS_FTRACE) endif +# Prevents flicker of uninteresting __do_softirq()/__local_bh_disable_ip() +# in coverage traces. +KCOV_INSTRUMENT_softirq.o := n +# These are called from save_stack_trace() on slub debug path, +# and produce insane amounts of uninteresting coverage. +KCOV_INSTRUMENT_module.o := n +KCOV_INSTRUMENT_extable.o := n +# Don't self-instrument. +KCOV_INSTRUMENT_kcov.o := n +KASAN_SANITIZE_kcov.o := n + # cond_syscall is currently not LTO compatible CFLAGS_sys_ni.o = $(DISABLE_LTO) @@ -68,6 +79,7 @@ obj-$(CONFIG_AUDITSYSCALL) += auditsc.o obj-$(CONFIG_AUDIT_WATCH) += audit_watch.o audit_fsnotify.o obj-$(CONFIG_AUDIT_TREE) += audit_tree.o obj-$(CONFIG_GCOV_KERNEL) += gcov/ +obj-$(CONFIG_KCOV) += kcov.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += debug/ obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o diff --git a/kernel/exit.c b/kernel/exit.c index 10e088237fed..953d1a1c0387 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include @@ -655,6 +656,7 @@ void do_exit(long code) TASKS_RCU(int tasks_rcu_i); profile_task_exit(tsk); + kcov_task_exit(tsk); WARN_ON(blk_needs_flush_plug(tsk)); diff --git a/kernel/fork.c b/kernel/fork.c index 5b8d1e7ceeea..d277e83ed3e0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -75,6 +75,7 @@ #include #include #include +#include #include #include @@ -392,6 +393,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) account_kernel_stack(ti, 1); + kcov_task_init(tsk); + return tsk; free_ti: diff --git a/kernel/kcov.c b/kernel/kcov.c new file mode 100644 index 000000000000..3efbee0834a8 --- /dev/null +++ b/kernel/kcov.c @@ -0,0 +1,273 @@ +#define pr_fmt(fmt) "kcov: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * kcov descriptor (one per opened debugfs file). + * State transitions of the descriptor: + * - initial state after open() + * - then there must be a single ioctl(KCOV_INIT_TRACE) call + * - then, mmap() call (several calls are allowed but not useful) + * - then, repeated enable/disable for a task (only one task a time allowed) + */ +struct kcov { + /* + * Reference counter. We keep one for: + * - opened file descriptor + * - task with enabled coverage (we can't unwire it from another task) + */ + atomic_t refcount; + /* The lock protects mode, size, area and t. */ + spinlock_t lock; + enum kcov_mode mode; + /* Size of arena (in long's for KCOV_MODE_TRACE). */ + unsigned size; + /* Coverage buffer shared with user space. */ + void *area; + /* Task for which we collect coverage, or NULL. */ + struct task_struct *t; +}; + +/* + * Entry point from instrumented code. + * This is called once per basic-block/edge. + */ +void __sanitizer_cov_trace_pc(void) +{ + struct task_struct *t; + enum kcov_mode mode; + + t = current; + /* + * We are interested in code coverage as a function of a syscall inputs, + * so we ignore code executed in interrupts. + */ + if (!t || in_interrupt()) + return; + mode = READ_ONCE(t->kcov_mode); + if (mode == KCOV_MODE_TRACE) { + unsigned long *area; + unsigned long pos; + + /* + * There is some code that runs in interrupts but for which + * in_interrupt() returns false (e.g. preempt_schedule_irq()). + * READ_ONCE()/barrier() effectively provides load-acquire wrt + * interrupts, there are paired barrier()/WRITE_ONCE() in + * kcov_ioctl_locked(). + */ + barrier(); + area = t->kcov_area; + /* The first word is number of subsequent PCs. */ + pos = READ_ONCE(area[0]) + 1; + if (likely(pos < t->kcov_size)) { + area[pos] = _RET_IP_; + WRITE_ONCE(area[0], pos); + } + } +} +EXPORT_SYMBOL(__sanitizer_cov_trace_pc); + +static void kcov_get(struct kcov *kcov) +{ + atomic_inc(&kcov->refcount); +} + +static void kcov_put(struct kcov *kcov) +{ + if (atomic_dec_and_test(&kcov->refcount)) { + vfree(kcov->area); + kfree(kcov); + } +} + +void kcov_task_init(struct task_struct *t) +{ + t->kcov_mode = KCOV_MODE_DISABLED; + t->kcov_size = 0; + t->kcov_area = NULL; + t->kcov = NULL; +} + +void kcov_task_exit(struct task_struct *t) +{ + struct kcov *kcov; + + kcov = t->kcov; + if (kcov == NULL) + return; + spin_lock(&kcov->lock); + if (WARN_ON(kcov->t != t)) { + spin_unlock(&kcov->lock); + return; + } + /* Just to not leave dangling references behind. */ + kcov_task_init(t); + kcov->t = NULL; + spin_unlock(&kcov->lock); + kcov_put(kcov); +} + +static int kcov_mmap(struct file *filep, struct vm_area_struct *vma) +{ + int res = 0; + void *area; + struct kcov *kcov = vma->vm_file->private_data; + unsigned long size, off; + struct page *page; + + area = vmalloc_user(vma->vm_end - vma->vm_start); + if (!area) + return -ENOMEM; + + spin_lock(&kcov->lock); + size = kcov->size * sizeof(unsigned long); + if (kcov->mode == KCOV_MODE_DISABLED || vma->vm_pgoff != 0 || + vma->vm_end - vma->vm_start != size) { + res = -EINVAL; + goto exit; + } + if (!kcov->area) { + kcov->area = area; + vma->vm_flags |= VM_DONTEXPAND; + spin_unlock(&kcov->lock); + for (off = 0; off < size; off += PAGE_SIZE) { + page = vmalloc_to_page(kcov->area + off); + if (vm_insert_page(vma, vma->vm_start + off, page)) + WARN_ONCE(1, "vm_insert_page() failed"); + } + return 0; + } +exit: + spin_unlock(&kcov->lock); + vfree(area); + return res; +} + +static int kcov_open(struct inode *inode, struct file *filep) +{ + struct kcov *kcov; + + kcov = kzalloc(sizeof(*kcov), GFP_KERNEL); + if (!kcov) + return -ENOMEM; + atomic_set(&kcov->refcount, 1); + spin_lock_init(&kcov->lock); + filep->private_data = kcov; + return nonseekable_open(inode, filep); +} + +static int kcov_close(struct inode *inode, struct file *filep) +{ + kcov_put(filep->private_data); + return 0; +} + +static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, + unsigned long arg) +{ + struct task_struct *t; + unsigned long size, unused; + + switch (cmd) { + case KCOV_INIT_TRACE: + /* + * Enable kcov in trace mode and setup buffer size. + * Must happen before anything else. + */ + if (kcov->mode != KCOV_MODE_DISABLED) + return -EBUSY; + /* + * Size must be at least 2 to hold current position and one PC. + * Later we allocate size * sizeof(unsigned long) memory, + * that must not overflow. + */ + size = arg; + if (size < 2 || size > INT_MAX / sizeof(unsigned long)) + return -EINVAL; + kcov->size = size; + kcov->mode = KCOV_MODE_TRACE; + return 0; + case KCOV_ENABLE: + /* + * Enable coverage for the current task. + * At this point user must have been enabled trace mode, + * and mmapped the file. Coverage collection is disabled only + * at task exit or voluntary by KCOV_DISABLE. After that it can + * be enabled for another task. + */ + unused = arg; + if (unused != 0 || kcov->mode == KCOV_MODE_DISABLED || + kcov->area == NULL) + return -EINVAL; + if (kcov->t != NULL) + return -EBUSY; + t = current; + /* Cache in task struct for performance. */ + t->kcov_size = kcov->size; + t->kcov_area = kcov->area; + /* See comment in __sanitizer_cov_trace_pc(). */ + barrier(); + WRITE_ONCE(t->kcov_mode, kcov->mode); + t->kcov = kcov; + kcov->t = t; + /* This is put either in kcov_task_exit() or in KCOV_DISABLE. */ + kcov_get(kcov); + return 0; + case KCOV_DISABLE: + /* Disable coverage for the current task. */ + unused = arg; + if (unused != 0 || current->kcov != kcov) + return -EINVAL; + t = current; + if (WARN_ON(kcov->t != t)) + return -EINVAL; + kcov_task_init(t); + kcov->t = NULL; + kcov_put(kcov); + return 0; + default: + return -ENOTTY; + } +} + +static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) +{ + struct kcov *kcov; + int res; + + kcov = filep->private_data; + spin_lock(&kcov->lock); + res = kcov_ioctl_locked(kcov, cmd, arg); + spin_unlock(&kcov->lock); + return res; +} + +static const struct file_operations kcov_fops = { + .open = kcov_open, + .unlocked_ioctl = kcov_ioctl, + .mmap = kcov_mmap, + .release = kcov_close, +}; + +static int __init kcov_init(void) +{ + if (!debugfs_create_file("kcov", 0600, NULL, NULL, &kcov_fops)) { + pr_err("failed to create kcov in debugfs\n"); + return -ENOMEM; + } + return 0; +} + +device_initcall(kcov_init); diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 8e96f6cc2a4a..31322a4275cd 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -1,3 +1,6 @@ +# Any varying coverage in these files is non-deterministic +# and is generally not a function of system call inputs. +KCOV_INSTRUMENT := n obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index 61a16569ffbf..032b2c015beb 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -1,3 +1,7 @@ +# Any varying coverage in these files is non-deterministic +# and is generally not a function of system call inputs. +KCOV_INSTRUMENT := n + obj-y += update.o sync.o obj-$(CONFIG_SRCU) += srcu.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 302d6ebd64f7..414d9c16da42 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -2,6 +2,10 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE) endif +# These files are disabled because they produce non-interesting flaky coverage +# that is not a function of syscall inputs. E.g. involuntary context switches. +KCOV_INSTRUMENT := n + ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) # According to Alan Modra , the -fno-omit-frame-pointer is # needed for x86 only. Why this used to be enabled for all architectures is beyond diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 5a60f45cd9bb..532d4d52d1df 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -696,6 +696,27 @@ source "lib/Kconfig.kasan" endmenu # "Memory Debugging" +config ARCH_HAS_KCOV + bool + help + KCOV does not have any arch-specific code, but currently it is enabled + only for x86_64. KCOV requires testing on other archs, and most likely + disabling of instrumentation for some early boot code. + +config KCOV + bool "Code coverage for fuzzing" + depends on ARCH_HAS_KCOV + select DEBUG_FS + help + KCOV exposes kernel code coverage information in a form suitable + for coverage-guided fuzzing (randomized testing). + + If RANDOMIZE_BASE is enabled, PC values will not be stable across + different machines and across reboots. If you need stable PC values, + disable RANDOMIZE_BASE. + + For more details, see Documentation/kcov.txt. + config DEBUG_SHIRQ bool "Debug shared IRQ handlers" depends on DEBUG_KERNEL diff --git a/lib/Makefile b/lib/Makefile index 4962d14c450f..a1de5b61ff40 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -7,6 +7,18 @@ ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS)) endif +# These files are disabled because they produce lots of non-interesting and/or +# flaky coverage that is not a function of syscall inputs. For example, +# rbtree can be global and individual rotations don't correlate with inputs. +KCOV_INSTRUMENT_string.o := n +KCOV_INSTRUMENT_rbtree.o := n +KCOV_INSTRUMENT_list_debug.o := n +KCOV_INSTRUMENT_debugobjects.o := n +KCOV_INSTRUMENT_dynamic_debug.o := n +# Kernel does not boot if we instrument this file as it uses custom calling +# convention (see CONFIG_ARCH_HWEIGHT_CFLAGS). +KCOV_INSTRUMENT_hweight.o := n + lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o timerqueue.o\ idr.o int_sqrt.o extable.o \ diff --git a/mm/Makefile b/mm/Makefile index 6da300a1414b..f5e797cbd128 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -5,6 +5,21 @@ KASAN_SANITIZE_slab_common.o := n KASAN_SANITIZE_slub.o := n +# These files are disabled because they produce non-interesting and/or +# flaky coverage that is not a function of syscall inputs. E.g. slab is out of +# free pages, or a task is migrated between nodes. +KCOV_INSTRUMENT_slab_common.o := n +KCOV_INSTRUMENT_slob.o := n +KCOV_INSTRUMENT_slab.o := n +KCOV_INSTRUMENT_slub.o := n +KCOV_INSTRUMENT_page_alloc.o := n +KCOV_INSTRUMENT_debug-pagealloc.o := n +KCOV_INSTRUMENT_kmemleak.o := n +KCOV_INSTRUMENT_kmemcheck.o := n +KCOV_INSTRUMENT_memcontrol.o := n +KCOV_INSTRUMENT_mmzone.o := n +KCOV_INSTRUMENT_vmstat.o := n + mmu-y := nommu.o mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index a61460d9f5b0..131daadf40e4 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -1,5 +1,6 @@ KASAN_SANITIZE := n UBSAN_SANITIZE_kasan.o := n +KCOV_INSTRUMENT := n CFLAGS_REMOVE_kasan.o = -pg # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index ad50d5859ac4..ddf83d0181e7 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -136,6 +136,12 @@ _c_flags += $(if $(patsubst n%,, \ $(CFLAGS_UBSAN)) endif +ifeq ($(CONFIG_KCOV),y) +_c_flags += $(if $(patsubst n%,, \ + $(KCOV_INSTRUMENT_$(basetarget).o)$(KCOV_INSTRUMENT)y), \ + $(CFLAGS_KCOV)) +endif + # If building the kernel in a separate objtree expand all occurrences # of -Idir to -I$(srctree)/dir except for absolute paths (starting with '/'). -- cgit v1.2.3 From 41b27154874b3a40d6673052d08c8e9fd0c6404f Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Tue, 22 Mar 2016 14:27:54 -0700 Subject: kernel/signal.c: add compile-time check for __ARCH_SI_PREAMBLE_SIZE The value of __ARCH_SI_PREAMBLE_SIZE defines the size (including padding) of the part of the struct siginfo that is before the union, and it is then used to calculate the needed padding (SI_PAD_SIZE) to make the size of struct siginfo equal to 128 (SI_MAX_SIZE) bytes. Depending on the target architecture and word width it equals to either 3 or 4 times sizeof int. Since the very beginning we had __ARCH_SI_PREAMBLE_SIZE wrong on the parisc architecture for the 64bit kernel build. It's even more frustrating, because it can easily be checked at compile time if the value was defined correctly. This patch adds such a check for the correctness of __ARCH_SI_PREAMBLE_SIZE in the hope that it will prevent existing and future architectures from running into the same problem. I refrained from replacing __ARCH_SI_PREAMBLE_SIZE by offsetof() in copy_siginfo() in include/asm-generic/siginfo.h, because a) it doesn't make any difference and b) it's used in the Documentation/kmemcheck.txt example. I ran this patch through the 0-DAY kernel test infrastructure and only the parisc architecture triggered as expected. That means that this patch should be OK for all major architectures. Signed-off-by: Helge Deller Cc: Stephen Rothwell Cc: Michael Ellerman Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index fe8ed298373c..aa9bf00749c1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3585,6 +3585,10 @@ __weak const char *arch_vma_name(struct vm_area_struct *vma) void __init signals_init(void) { + /* If this check fails, the __ARCH_SI_PREAMBLE_SIZE value is wrong! */ + BUILD_BUG_ON(__ARCH_SI_PREAMBLE_SIZE + != offsetof(struct siginfo, _sifields._pad)); + sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC); } -- cgit v1.2.3 From cf61e2a1487d833e4748dead4096584de70bf742 Mon Sep 17 00:00:00 2001 From: Brian Starkey Date: Tue, 22 Mar 2016 14:27:57 -0700 Subject: memremap: don't modify flags These patches implement a MEMREMAP_WC flag for memremap(), which can be used to obtain writecombine mappings. This is then used for setting up dma_coherent_mem regions which use the DMA_MEMORY_MAP flag. The motivation is to fix an alignment fault on arm64, and the suggestion to implement MEMREMAP_WC for this case was made at [1]. That particular issue is handled in patch 4, which makes sure that the appropriate memset function is used when zeroing allocations mapped as IO memory. This patch (of 4): Don't modify the flags input argument to memremap(). MEMREMAP_WB is already a special case so we can check for it directly instead of clearing flag bits in each mapper. Signed-off-by: Brian Starkey Cc: Catalin Marinas Cc: Dan Williams Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/memremap.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/memremap.c b/kernel/memremap.c index 584febd13e2e..e5e685e6ff2a 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -64,6 +64,9 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); void *addr = NULL; + if (!flags) + return NULL; + if (is_ram == REGION_MIXED) { WARN_ONCE(1, "memremap attempted on mixed range %pa size: %#lx\n", &offset, (unsigned long) size); @@ -72,7 +75,6 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) /* Try all mapping types requested until one returns non-NULL */ if (flags & MEMREMAP_WB) { - flags &= ~MEMREMAP_WB; /* * MEMREMAP_WB is special in that it can be satisifed * from the direct map. Some archs depend on the @@ -86,21 +88,19 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) } /* - * If we don't have a mapping yet and more request flags are - * pending then we will be attempting to establish a new virtual + * If we don't have a mapping yet and other request flags are + * present then we will be attempting to establish a new virtual * address mapping. Enforce that this mapping is not aliasing * System RAM. */ - if (!addr && is_ram == REGION_INTERSECTS && flags) { + if (!addr && is_ram == REGION_INTERSECTS && flags != MEMREMAP_WB) { WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n", &offset, (unsigned long) size); return NULL; } - if (!addr && (flags & MEMREMAP_WT)) { - flags &= ~MEMREMAP_WT; + if (!addr && (flags & MEMREMAP_WT)) addr = ioremap_wt(offset, size); - } return addr; } -- cgit v1.2.3 From c907e0eb43a522de60fb651c011c553f87273222 Mon Sep 17 00:00:00 2001 From: Brian Starkey Date: Tue, 22 Mar 2016 14:28:00 -0700 Subject: memremap: add MEMREMAP_WC flag Add a flag to memremap() for writecombine mappings. Mappings satisfied by this flag will not be cached, however writes may be delayed or combined into more efficient bursts. This is most suitable for buffers written sequentially by the CPU for use by other DMA devices. Signed-off-by: Brian Starkey Reviewed-by: Catalin Marinas Cc: Dan Williams Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/io.h | 1 + kernel/memremap.c | 13 +++++++++++-- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/include/linux/io.h b/include/linux/io.h index 32403b5716e5..e2c8419278c1 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -135,6 +135,7 @@ enum { /* See memremap() kernel-doc for usage description... */ MEMREMAP_WB = 1 << 0, MEMREMAP_WT = 1 << 1, + MEMREMAP_WC = 1 << 2, }; void *memremap(resource_size_t offset, size_t size, unsigned long flags); diff --git a/kernel/memremap.c b/kernel/memremap.c index e5e685e6ff2a..a6d382312e6f 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -41,11 +41,13 @@ static void *try_ram_remap(resource_size_t offset, size_t size) * memremap() - remap an iomem_resource as cacheable memory * @offset: iomem resource start address * @size: size of remap - * @flags: either MEMREMAP_WB or MEMREMAP_WT + * @flags: any of MEMREMAP_WB, MEMREMAP_WT and MEMREMAP_WC * * memremap() is "ioremap" for cases where it is known that the resource * being mapped does not have i/o side effects and the __iomem - * annotation is not applicable. + * annotation is not applicable. In the case of multiple flags, the different + * mapping types will be attempted in the order listed below until one of + * them succeeds. * * MEMREMAP_WB - matches the default mapping for System RAM on * the architecture. This is usually a read-allocate write-back cache. @@ -57,6 +59,10 @@ static void *try_ram_remap(resource_size_t offset, size_t size) * cache or are written through to memory and never exist in a * cache-dirty state with respect to program visibility. Attempts to * map System RAM with this mapping type will fail. + * + * MEMREMAP_WC - establish a writecombine mapping, whereby writes may + * be coalesced together (e.g. in the CPU's write buffers), but is otherwise + * uncached. Attempts to map System RAM with this mapping type will fail. */ void *memremap(resource_size_t offset, size_t size, unsigned long flags) { @@ -102,6 +108,9 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) if (!addr && (flags & MEMREMAP_WT)) addr = ioremap_wt(offset, size); + if (!addr && (flags & MEMREMAP_WC)) + addr = ioremap_wc(offset, size); + return addr; } EXPORT_SYMBOL(memremap); -- cgit v1.2.3 From a395d6a7e3d6e3d1d316376db0c4c8b5d2995930 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 22 Mar 2016 14:28:09 -0700 Subject: kernel/...: convert pr_warning to pr_warn Use the more common logging method with the eventual goal of removing pr_warning altogether. Miscellanea: - Realign arguments - Coalesce formats - Add missing space between a few coalesced formats Signed-off-by: Joe Perches Acked-by: Rafael J. Wysocki [kernel/power/suspend.c] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/irq/manage.c | 4 ++-- kernel/power/suspend.c | 3 +-- kernel/time/tick-sched.c | 8 ++++---- kernel/trace/blktrace.c | 4 ++-- kernel/trace/ftrace.c | 7 +++---- kernel/trace/trace.c | 40 ++++++++++++++++++------------------ kernel/trace/trace_functions_graph.c | 6 +++--- kernel/trace/trace_kprobe.c | 27 ++++++++++-------------- kernel/trace/trace_mmiotrace.c | 2 +- kernel/trace/trace_probe.c | 4 ++-- kernel/trace/trace_stat.c | 3 +-- kernel/trace/trace_uprobe.c | 2 +- kernel/tracepoint.c | 2 +- 13 files changed, 52 insertions(+), 60 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 64731e84c982..cc1cc641d653 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1322,8 +1322,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (nmsk != omsk) /* hope the handler works with current trigger mode */ - pr_warning("irq %d uses trigger mode %u; requested %u\n", - irq, nmsk, omsk); + pr_warn("irq %d uses trigger mode %u; requested %u\n", + irq, nmsk, omsk); } *old_ptr = new; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 230a77225e2e..5b70d64b871e 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -473,8 +473,7 @@ static int enter_state(suspend_state_t state) if (state == PM_SUSPEND_FREEZE) { #ifdef CONFIG_PM_DEBUG if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) { - pr_warning("PM: Unsupported test mode for suspend to idle," - "please choose none/freezer/devices/platform.\n"); + pr_warn("PM: Unsupported test mode for suspend to idle, please choose none/freezer/devices/platform.\n"); return -EAGAIN; } #endif diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 195fe7d2caad..084b79f5917e 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -378,7 +378,7 @@ static int __init tick_nohz_full_setup(char *str) { alloc_bootmem_cpumask_var(&tick_nohz_full_mask); if (cpulist_parse(str, tick_nohz_full_mask) < 0) { - pr_warning("NOHZ: Incorrect nohz_full cpumask\n"); + pr_warn("NO_HZ: Incorrect nohz_full cpumask\n"); free_bootmem_cpumask_var(tick_nohz_full_mask); return 1; } @@ -446,8 +446,7 @@ void __init tick_nohz_init(void) * interrupts to avoid circular dependency on the tick */ if (!arch_irq_work_has_interrupt()) { - pr_warning("NO_HZ: Can't run full dynticks because arch doesn't " - "support irq work self-IPIs\n"); + pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n"); cpumask_clear(tick_nohz_full_mask); cpumask_copy(housekeeping_mask, cpu_possible_mask); tick_nohz_full_running = false; @@ -457,7 +456,8 @@ void __init tick_nohz_init(void) cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { - pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu); + pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", + cpu); cpumask_clear_cpu(cpu, tick_nohz_full_mask); } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2aeb6ffc0a1e..f94e7a21f52d 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1437,12 +1437,12 @@ static struct trace_event trace_blk_event = { static int __init init_blk_tracer(void) { if (!register_trace_event(&trace_blk_event)) { - pr_warning("Warning: could not register block events\n"); + pr_warn("Warning: could not register block events\n"); return 1; } if (register_tracer(&blk_tracer) != 0) { - pr_warning("Warning: could not register the block tracer\n"); + pr_warn("Warning: could not register the block tracer\n"); unregister_trace_event(&trace_blk_event); return 1; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 57a6eea84694..2ece9f1a3e5a 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1058,8 +1058,7 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) entry = tracefs_create_file("function_profile_enabled", 0644, d_tracer, NULL, &ftrace_profile_fops); if (!entry) - pr_warning("Could not create tracefs " - "'function_profile_enabled' entry\n"); + pr_warn("Could not create tracefs 'function_profile_enabled' entry\n"); } #else /* CONFIG_FUNCTION_PROFILER */ @@ -2314,8 +2313,8 @@ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_curr(rec); if (FTRACE_WARN_ON(!ops)) { - pr_warning("Bad trampoline accounting at: %p (%pS)\n", - (void *)rec->ip, (void *)rec->ip); + pr_warn("Bad trampoline accounting at: %p (%pS)\n", + (void *)rec->ip, (void *)rec->ip); /* Ftrace is shutting down, return anything */ return (unsigned long)FTRACE_ADDR; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d9293402ee68..032b388bea66 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2071,20 +2071,20 @@ void trace_printk_init_buffers(void) /* trace_printk() is for debug use only. Don't use it in production. */ - pr_warning("\n"); - pr_warning("**********************************************************\n"); - pr_warning("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); - pr_warning("** **\n"); - pr_warning("** trace_printk() being used. Allocating extra memory. **\n"); - pr_warning("** **\n"); - pr_warning("** This means that this is a DEBUG kernel and it is **\n"); - pr_warning("** unsafe for production use. **\n"); - pr_warning("** **\n"); - pr_warning("** If you see this message and you are not debugging **\n"); - pr_warning("** the kernel, report this immediately to your vendor! **\n"); - pr_warning("** **\n"); - pr_warning("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); - pr_warning("**********************************************************\n"); + pr_warn("\n"); + pr_warn("**********************************************************\n"); + pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); + pr_warn("** **\n"); + pr_warn("** trace_printk() being used. Allocating extra memory. **\n"); + pr_warn("** **\n"); + pr_warn("** This means that this is a DEBUG kernel and it is **\n"); + pr_warn("** unsafe for production use. **\n"); + pr_warn("** **\n"); + pr_warn("** If you see this message and you are not debugging **\n"); + pr_warn("** the kernel, report this immediately to your vendor! **\n"); + pr_warn("** **\n"); + pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); + pr_warn("**********************************************************\n"); /* Expand the buffers to set size */ tracing_update_buffers(); @@ -4101,7 +4101,7 @@ trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start, */ map_array = kmalloc(sizeof(*map_array) * (len + 2), GFP_KERNEL); if (!map_array) { - pr_warning("Unable to allocate trace enum mapping\n"); + pr_warn("Unable to allocate trace enum mapping\n"); return; } @@ -6131,7 +6131,7 @@ tracing_init_tracefs_percpu(struct trace_array *tr, long cpu) snprintf(cpu_dir, 30, "cpu%ld", cpu); d_cpu = tracefs_create_dir(cpu_dir, d_percpu); if (!d_cpu) { - pr_warning("Could not create tracefs '%s' entry\n", cpu_dir); + pr_warn("Could not create tracefs '%s' entry\n", cpu_dir); return; } @@ -6318,7 +6318,7 @@ struct dentry *trace_create_file(const char *name, ret = tracefs_create_file(name, mode, parent, data, fops); if (!ret) - pr_warning("Could not create tracefs '%s' entry\n", name); + pr_warn("Could not create tracefs '%s' entry\n", name); return ret; } @@ -6337,7 +6337,7 @@ static struct dentry *trace_options_init_dentry(struct trace_array *tr) tr->options = tracefs_create_dir("options", d_tracer); if (!tr->options) { - pr_warning("Could not create tracefs directory 'options'\n"); + pr_warn("Could not create tracefs directory 'options'\n"); return NULL; } @@ -7248,8 +7248,8 @@ __init static int tracer_alloc_buffers(void) if (trace_boot_clock) { ret = tracing_set_clock(&global_trace, trace_boot_clock); if (ret < 0) - pr_warning("Trace clock %s not defined, going back to default\n", - trace_boot_clock); + pr_warn("Trace clock %s not defined, going back to default\n", + trace_boot_clock); } /* diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index a663cbb84107..91d6a63a2ea7 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -1350,7 +1350,7 @@ void graph_trace_open(struct trace_iterator *iter) out_err_free: kfree(data); out_err: - pr_warning("function graph tracer: not enough memory\n"); + pr_warn("function graph tracer: not enough memory\n"); } void graph_trace_close(struct trace_iterator *iter) @@ -1468,12 +1468,12 @@ static __init int init_graph_trace(void) max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1); if (!register_trace_event(&graph_trace_entry_event)) { - pr_warning("Warning: could not register graph trace events\n"); + pr_warn("Warning: could not register graph trace events\n"); return 1; } if (!register_trace_event(&graph_trace_ret_event)) { - pr_warning("Warning: could not register graph trace events\n"); + pr_warn("Warning: could not register graph trace events\n"); return 1; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 21b81a41dae5..919e0ddd8fcc 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -459,16 +459,14 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) if (ret == 0) tk->tp.flags |= TP_FLAG_REGISTERED; else { - pr_warning("Could not insert probe at %s+%lu: %d\n", - trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret); + pr_warn("Could not insert probe at %s+%lu: %d\n", + trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret); if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) { - pr_warning("This probe might be able to register after" - "target module is loaded. Continue.\n"); + pr_warn("This probe might be able to register after target module is loaded. Continue.\n"); ret = 0; } else if (ret == -EILSEQ) { - pr_warning("Probing address(0x%p) is not an " - "instruction boundary.\n", - tk->rp.kp.addr); + pr_warn("Probing address(0x%p) is not an instruction boundary.\n", + tk->rp.kp.addr); ret = -EINVAL; } } @@ -529,7 +527,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk) /* Register new event */ ret = register_kprobe_event(tk); if (ret) { - pr_warning("Failed to register probe event(%d)\n", ret); + pr_warn("Failed to register probe event(%d)\n", ret); goto end; } @@ -564,10 +562,9 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, __unregister_trace_kprobe(tk); ret = __register_trace_kprobe(tk); if (ret) - pr_warning("Failed to re-register probe %s on" - "%s: %d\n", - trace_event_name(&tk->tp.call), - mod->name, ret); + pr_warn("Failed to re-register probe %s on %s: %d\n", + trace_event_name(&tk->tp.call), + mod->name, ret); } } mutex_unlock(&probe_lock); @@ -1336,16 +1333,14 @@ static __init int init_kprobe_trace(void) /* Event list interface */ if (!entry) - pr_warning("Could not create tracefs " - "'kprobe_events' entry\n"); + pr_warn("Could not create tracefs 'kprobe_events' entry\n"); /* Profile interface */ entry = tracefs_create_file("kprobe_profile", 0444, d_tracer, NULL, &kprobe_profile_ops); if (!entry) - pr_warning("Could not create tracefs " - "'kprobe_profile' entry\n"); + pr_warn("Could not create tracefs 'kprobe_profile' entry\n"); return 0; } fs_initcall(init_kprobe_trace); diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 2be8c4f2403d..68f376ca6d3f 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -146,7 +146,7 @@ static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp, /* XXX: This is later than where events were lost. */ trace_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n); if (!overrun_detected) - pr_warning("mmiotrace has lost events.\n"); + pr_warn("mmiotrace has lost events\n"); overrun_detected = true; goto print_out; } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 1769a81da8a7..1d372fa6fefb 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -636,8 +636,8 @@ ssize_t traceprobe_probes_write(struct file *file, const char __user *buffer, *tmp = '\0'; size = tmp - kbuf + 1; } else if (done + size < count) { - pr_warning("Line length is too long: " - "Should be less than %d.", WRITE_BUFSIZE); + pr_warn("Line length is too long: Should be less than %d\n", + WRITE_BUFSIZE); ret = -EINVAL; goto out; } diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 6cf935316769..413ff108fbd0 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -281,8 +281,7 @@ static int tracing_stat_init(void) stat_dir = tracefs_create_dir("trace_stat", d_tracing); if (!stat_dir) - pr_warning("Could not create tracefs " - "'trace_stat' entry\n"); + pr_warn("Could not create tracefs 'trace_stat' entry\n"); return 0; } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index d2f6d0be3503..7915142c89e4 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -334,7 +334,7 @@ static int register_trace_uprobe(struct trace_uprobe *tu) ret = register_uprobe_event(tu); if (ret) { - pr_warning("Failed to register probe event(%d)\n", ret); + pr_warn("Failed to register probe event(%d)\n", ret); goto end; } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index ecd536de603a..d0639d917899 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -491,7 +491,7 @@ static __init int init_tracepoints(void) ret = register_module_notifier(&tracepoint_module_nb); if (ret) - pr_warning("Failed to register tracepoint module enter notifier\n"); + pr_warn("Failed to register tracepoint module enter notifier\n"); return ret; } -- cgit v1.2.3 From 276142730c39c9839465a36a90e5674a8c34e839 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 23 Mar 2016 00:11:20 +0100 Subject: PM / sleep: Clear pm_suspend_global_flags upon hibernate When suspending to RAM, waking up and later suspending to disk, we gratuitously runtime resume devices after the thaw phase. This does not occur if we always suspend to RAM or always to disk. pm_complete_with_resume_check(), which gets called from pci_pm_complete() among others, schedules a runtime resume if PM_SUSPEND_FLAG_FW_RESUME is set. The flag is set during a suspend-to-RAM cycle. It is cleared at the beginning of the suspend-to-RAM cycle but not afterwards and it is not cleared during a suspend-to-disk cycle at all. Fix it. Fixes: ef25ba047601 (PM / sleep: Add flags to indicate platform firmware involvement) Signed-off-by: Lukas Wunner Cc: 4.4+ # 4.4+ Signed-off-by: Rafael J. Wysocki --- kernel/power/hibernate.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index b7342a24f559..b7dd5718836e 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -339,6 +339,7 @@ int hibernation_snapshot(int platform_mode) pm_message_t msg; int error; + pm_suspend_clear_flags(); error = platform_begin(platform_mode); if (error) goto Close; -- cgit v1.2.3 From 322cea2f41adb62c975f46a3242f4e3b43226fa1 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 25 Mar 2016 00:30:25 +0100 Subject: bpf: add missing map_flags to bpf_map_show_fdinfo Add map_flags attribute to bpf_map_show_fdinfo(), so that tools like tc can check for them when loading objects from a pinned entry, e.g. if user intent wrt allocation (BPF_F_NO_PREALLOC) is different to the pinned object, it can bail out. Follow-up to 6c9059817432 ("bpf: pre-allocate hash map elements"), so that tc can still support this with v4.6. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2a2efe1bc76c..adc5e4bd74f8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -137,11 +137,13 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "map_type:\t%u\n" "key_size:\t%u\n" "value_size:\t%u\n" - "max_entries:\t%u\n", + "max_entries:\t%u\n" + "map_flags:\t%#x\n", map->map_type, map->key_size, map->value_size, - map->max_entries); + map->max_entries, + map->map_flags); } #endif -- cgit v1.2.3 From 69b27baf00fa9b7b14b3263c105390d1683425b2 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 25 Mar 2016 14:20:21 -0700 Subject: sched: add schedule_timeout_idle() This will be needed in the patch "mm, oom: introduce oom reaper". Acked-by: Michal Hocko Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + kernel/time/timer.c | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'kernel') diff --git a/include/linux/sched.h b/include/linux/sched.h index 589c4780b077..478b41de7f7d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -426,6 +426,7 @@ extern signed long schedule_timeout(signed long timeout); extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); +extern signed long schedule_timeout_idle(signed long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index d1798fa0c743..73164c3aa56b 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1566,6 +1566,17 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout) } EXPORT_SYMBOL(schedule_timeout_uninterruptible); +/* + * Like schedule_timeout_uninterruptible(), except this task will not contribute + * to load average. + */ +signed long __sched schedule_timeout_idle(signed long timeout) +{ + __set_current_state(TASK_IDLE); + return schedule_timeout(timeout); +} +EXPORT_SYMBOL(schedule_timeout_idle); + #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct tvec_base *new_base, struct hlist_head *head) { -- cgit v1.2.3 From 36324a990cf578b57828c04cd85ac62cd25cf5a4 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 25 Mar 2016 14:20:27 -0700 Subject: oom: clear TIF_MEMDIE after oom_reaper managed to unmap the address space When oom_reaper manages to unmap all the eligible vmas there shouldn't be much of the freable memory held by the oom victim left anymore so it makes sense to clear the TIF_MEMDIE flag for the victim and allow the OOM killer to select another task. The lack of TIF_MEMDIE also means that the victim cannot access memory reserves anymore but that shouldn't be a problem because it would get the access again if it needs to allocate and hits the OOM killer again due to the fatal_signal_pending resp. PF_EXITING check. We can safely hide the task from the OOM killer because it is clearly not a good candidate anymore as everyhing reclaimable has been torn down already. This patch will allow to cap the time an OOM victim can keep TIF_MEMDIE and thus hold off further global OOM killer actions granted the oom reaper is able to take mmap_sem for the associated mm struct. This is not guaranteed now but further steps should make sure that mmap_sem for write should be blocked killable which will help to reduce such a lock contention. This is not done by this patch. Note that exit_oom_victim might be called on a remote task from __oom_reap_task now so we have to check and clear the flag atomically otherwise we might race and underflow oom_victims or wake up waiters too early. Signed-off-by: Michal Hocko Suggested-by: Johannes Weiner Suggested-by: Tetsuo Handa Cc: Andrea Argangeli Cc: David Rientjes Cc: Hugh Dickins Cc: Mel Gorman Cc: Oleg Nesterov Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 2 +- kernel/exit.c | 2 +- mm/oom_kill.c | 73 +++++++++++++++++++++++++++++++++++------------------ 3 files changed, 50 insertions(+), 27 deletions(-) (limited to 'kernel') diff --git a/include/linux/oom.h b/include/linux/oom.h index 03e6257321f0..45993b840ed6 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -91,7 +91,7 @@ extern enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, extern bool out_of_memory(struct oom_control *oc); -extern void exit_oom_victim(void); +extern void exit_oom_victim(struct task_struct *tsk); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); diff --git a/kernel/exit.c b/kernel/exit.c index 953d1a1c0387..fd90195667e1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -435,7 +435,7 @@ static void exit_mm(struct task_struct *tsk) mm_update_next_owner(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) - exit_oom_victim(); + exit_oom_victim(tsk); } static struct task_struct *find_alive_thread(struct task_struct *p) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f7ed6ece0719..2830b1c6483e 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -416,20 +416,36 @@ bool oom_killer_disabled __read_mostly; * victim (if that is possible) to help the OOM killer to move on. */ static struct task_struct *oom_reaper_th; -static struct mm_struct *mm_to_reap; +static struct task_struct *task_to_reap; static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait); -static bool __oom_reap_vmas(struct mm_struct *mm) +static bool __oom_reap_task(struct task_struct *tsk) { struct mmu_gather tlb; struct vm_area_struct *vma; + struct mm_struct *mm; + struct task_struct *p; struct zap_details details = {.check_swap_entries = true, .ignore_dirty = true}; bool ret = true; - /* We might have raced with exit path */ - if (!atomic_inc_not_zero(&mm->mm_users)) + /* + * Make sure we find the associated mm_struct even when the particular + * thread has already terminated and cleared its mm. + * We might have race with exit path so consider our work done if there + * is no mm. + */ + p = find_lock_task_mm(tsk); + if (!p) + return true; + + mm = p->mm; + if (!atomic_inc_not_zero(&mm->mm_users)) { + task_unlock(p); return true; + } + + task_unlock(p); if (!down_read_trylock(&mm->mmap_sem)) { ret = false; @@ -464,60 +480,66 @@ static bool __oom_reap_vmas(struct mm_struct *mm) } tlb_finish_mmu(&tlb, 0, -1); up_read(&mm->mmap_sem); + + /* + * Clear TIF_MEMDIE because the task shouldn't be sitting on a + * reasonably reclaimable memory anymore. OOM killer can continue + * by selecting other victim if unmapping hasn't led to any + * improvements. This also means that selecting this task doesn't + * make any sense. + */ + tsk->signal->oom_score_adj = OOM_SCORE_ADJ_MIN; + exit_oom_victim(tsk); out: mmput(mm); return ret; } -static void oom_reap_vmas(struct mm_struct *mm) +static void oom_reap_task(struct task_struct *tsk) { int attempts = 0; /* Retry the down_read_trylock(mmap_sem) a few times */ - while (attempts++ < 10 && !__oom_reap_vmas(mm)) + while (attempts++ < 10 && !__oom_reap_task(tsk)) schedule_timeout_idle(HZ/10); /* Drop a reference taken by wake_oom_reaper */ - mmdrop(mm); + put_task_struct(tsk); } static int oom_reaper(void *unused) { while (true) { - struct mm_struct *mm; + struct task_struct *tsk; wait_event_freezable(oom_reaper_wait, - (mm = READ_ONCE(mm_to_reap))); - oom_reap_vmas(mm); - WRITE_ONCE(mm_to_reap, NULL); + (tsk = READ_ONCE(task_to_reap))); + oom_reap_task(tsk); + WRITE_ONCE(task_to_reap, NULL); } return 0; } -static void wake_oom_reaper(struct mm_struct *mm) +static void wake_oom_reaper(struct task_struct *tsk) { - struct mm_struct *old_mm; + struct task_struct *old_tsk; if (!oom_reaper_th) return; - /* - * Pin the given mm. Use mm_count instead of mm_users because - * we do not want to delay the address space tear down. - */ - atomic_inc(&mm->mm_count); + get_task_struct(tsk); /* * Make sure that only a single mm is ever queued for the reaper * because multiple are not necessary and the operation might be * disruptive so better reduce it to the bare minimum. */ - old_mm = cmpxchg(&mm_to_reap, NULL, mm); - if (!old_mm) + old_tsk = cmpxchg(&task_to_reap, NULL, tsk); + if (!old_tsk) wake_up(&oom_reaper_wait); else - mmdrop(mm); + put_task_struct(tsk); } static int __init oom_init(void) @@ -532,7 +554,7 @@ static int __init oom_init(void) } subsys_initcall(oom_init) #else -static void wake_oom_reaper(struct mm_struct *mm) +static void wake_oom_reaper(struct task_struct *tsk) { } #endif @@ -563,9 +585,10 @@ void mark_oom_victim(struct task_struct *tsk) /** * exit_oom_victim - note the exit of an OOM victim */ -void exit_oom_victim(void) +void exit_oom_victim(struct task_struct *tsk) { - clear_thread_flag(TIF_MEMDIE); + if (!test_and_clear_tsk_thread_flag(tsk, TIF_MEMDIE)) + return; if (!atomic_dec_return(&oom_victims)) wake_up_all(&oom_victims_wait); @@ -748,7 +771,7 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, rcu_read_unlock(); if (can_oom_reap) - wake_oom_reaper(mm); + wake_oom_reaper(victim); mmdrop(mm); put_task_struct(victim); -- cgit v1.2.3 From be7635e7287e0e8013af3c89a6354a9e0182594c Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 25 Mar 2016 14:22:05 -0700 Subject: arch, ftrace: for KASAN put hard/soft IRQ entries into separate sections KASAN needs to know whether the allocation happens in an IRQ handler. This lets us strip everything below the IRQ entry point to reduce the number of unique stack traces needed to be stored. Move the definition of __irq_entry to so that the users don't need to pull in . Also introduce the __softirq_entry macro which is similar to __irq_entry, but puts the corresponding functions to the .softirqentry.text section. Signed-off-by: Alexander Potapenko Acked-by: Steven Rostedt Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/exception.h | 2 +- arch/arm/kernel/vmlinux.lds.S | 1 + arch/arm64/include/asm/exception.h | 2 +- arch/arm64/kernel/vmlinux.lds.S | 1 + arch/blackfin/kernel/vmlinux.lds.S | 1 + arch/c6x/kernel/vmlinux.lds.S | 1 + arch/metag/kernel/vmlinux.lds.S | 1 + arch/microblaze/kernel/vmlinux.lds.S | 1 + arch/mips/kernel/vmlinux.lds.S | 1 + arch/nios2/kernel/vmlinux.lds.S | 1 + arch/openrisc/kernel/vmlinux.lds.S | 1 + arch/parisc/kernel/vmlinux.lds.S | 1 + arch/powerpc/kernel/vmlinux.lds.S | 1 + arch/s390/kernel/vmlinux.lds.S | 1 + arch/sh/kernel/vmlinux.lds.S | 1 + arch/sparc/kernel/vmlinux.lds.S | 1 + arch/tile/kernel/vmlinux.lds.S | 1 + arch/x86/kernel/vmlinux.lds.S | 1 + include/asm-generic/vmlinux.lds.h | 12 +++++++++++- include/linux/ftrace.h | 11 ----------- include/linux/interrupt.h | 20 ++++++++++++++++++++ kernel/softirq.c | 2 +- kernel/trace/trace_functions_graph.c | 1 + 23 files changed, 51 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h index 5abaf5bbd985..bf1991263d2d 100644 --- a/arch/arm/include/asm/exception.h +++ b/arch/arm/include/asm/exception.h @@ -7,7 +7,7 @@ #ifndef __ASM_ARM_EXCEPTION_H #define __ASM_ARM_EXCEPTION_H -#include +#include #define __exception __attribute__((section(".exception.text"))) #ifdef CONFIG_FUNCTION_GRAPH_TRACER diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 1fab979daeaf..e2c6da096cef 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -108,6 +108,7 @@ SECTIONS *(.exception.text) __exception_text_end = .; IRQENTRY_TEXT + SOFTIRQENTRY_TEXT TEXT_TEXT SCHED_TEXT LOCK_TEXT diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 6cb7e1a6bc02..0c2eec490abf 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -18,7 +18,7 @@ #ifndef __ASM_EXCEPTION_H #define __ASM_EXCEPTION_H -#include +#include #define __exception __attribute__((section(".exception.text"))) #ifdef CONFIG_FUNCTION_GRAPH_TRACER diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 37f624df68fa..5a1939a74ff3 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -103,6 +103,7 @@ SECTIONS *(.exception.text) __exception_text_end = .; IRQENTRY_TEXT + SOFTIRQENTRY_TEXT TEXT_TEXT SCHED_TEXT LOCK_TEXT diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S index c9eec84aa258..d920b959ff3a 100644 --- a/arch/blackfin/kernel/vmlinux.lds.S +++ b/arch/blackfin/kernel/vmlinux.lds.S @@ -35,6 +35,7 @@ SECTIONS #endif LOCK_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT KPROBES_TEXT #ifdef CONFIG_ROMKERNEL __sinittext = .; diff --git a/arch/c6x/kernel/vmlinux.lds.S b/arch/c6x/kernel/vmlinux.lds.S index 5a6e141d1641..50bc10f97bcb 100644 --- a/arch/c6x/kernel/vmlinux.lds.S +++ b/arch/c6x/kernel/vmlinux.lds.S @@ -72,6 +72,7 @@ SECTIONS SCHED_TEXT LOCK_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT KPROBES_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/metag/kernel/vmlinux.lds.S b/arch/metag/kernel/vmlinux.lds.S index e12055e88bfe..150ace92c7ad 100644 --- a/arch/metag/kernel/vmlinux.lds.S +++ b/arch/metag/kernel/vmlinux.lds.S @@ -24,6 +24,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.text.*) *(.gnu.warning) } diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S index be9488d69734..0a47f0410554 100644 --- a/arch/microblaze/kernel/vmlinux.lds.S +++ b/arch/microblaze/kernel/vmlinux.lds.S @@ -36,6 +36,7 @@ SECTIONS { LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT . = ALIGN (4) ; _etext = . ; } diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index 0a93e83cd014..54d653ee17e1 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -58,6 +58,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.text.*) *(.fixup) *(.gnu.warning) diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S index 326fab40a9de..e23e89539967 100644 --- a/arch/nios2/kernel/vmlinux.lds.S +++ b/arch/nios2/kernel/vmlinux.lds.S @@ -39,6 +39,7 @@ SECTIONS SCHED_TEXT LOCK_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT KPROBES_TEXT } =0 _etext = .; diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index 2d69a853b742..d936de4c07ca 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -50,6 +50,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.fixup) *(.text.__*) _etext = .; diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 308f29081d46..f3ead0b6ce46 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -72,6 +72,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.text.do_softirq) *(.text.sys_exit) *(.text.do_sigaltstack) diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index d41fd0af8980..2dd91f79de05 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -55,6 +55,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT #ifdef CONFIG_PPC32 *(.got1) diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 445657fe658c..0f41a8286378 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -28,6 +28,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) } :text = 0x0700 diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index db88cbf9eafd..235a4101999f 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -39,6 +39,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) _etext = .; /* End of text section */ diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index f1a2f688b28a..aadd321aa05d 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -48,6 +48,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.gnu.warning) } = 0 _etext = .; diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S index 0e059a0101ea..378f5d8d1ec8 100644 --- a/arch/tile/kernel/vmlinux.lds.S +++ b/arch/tile/kernel/vmlinux.lds.S @@ -45,6 +45,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT __fix_text_end = .; /* tile-cpack won't rearrange before this */ ALIGN_FUNCTION(); *(.hottext*) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index d239639e0c1d..4c941f88d405 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -101,6 +101,7 @@ SECTIONS KPROBES_TEXT ENTRY_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) /* End of text section */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 8f5a12ab2f2b..339125bb4d2c 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -456,7 +456,7 @@ *(.entry.text) \ VMLINUX_SYMBOL(__entry_text_end) = .; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) #define IRQENTRY_TEXT \ ALIGN_FUNCTION(); \ VMLINUX_SYMBOL(__irqentry_text_start) = .; \ @@ -466,6 +466,16 @@ #define IRQENTRY_TEXT #endif +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) +#define SOFTIRQENTRY_TEXT \ + ALIGN_FUNCTION(); \ + VMLINUX_SYMBOL(__softirqentry_text_start) = .; \ + *(.softirqentry.text) \ + VMLINUX_SYMBOL(__softirqentry_text_end) = .; +#else +#define SOFTIRQENTRY_TEXT +#endif + /* Section used for early init (in .S files) */ #define HEAD_TEXT *(.head.text) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 6d9df3f7e334..dea12a6e413b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -811,16 +811,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, */ #define __notrace_funcgraph notrace -/* - * We want to which function is an entrypoint of a hardirq. - * That will help us to put a signal on output. - */ -#define __irq_entry __attribute__((__section__(".irqentry.text"))) - -/* Limits of hardirq entrypoints */ -extern char __irqentry_text_start[]; -extern char __irqentry_text_end[]; - #define FTRACE_NOTRACE_DEPTH 65536 #define FTRACE_RETFUNC_DEPTH 50 #define FTRACE_RETSTACK_ALLOC_SIZE 32 @@ -857,7 +847,6 @@ static inline void unpause_graph_tracing(void) #else /* !CONFIG_FUNCTION_GRAPH_TRACER */ #define __notrace_funcgraph -#define __irq_entry #define INIT_FTRACE_GRAPH static inline void ftrace_graph_init_task(struct task_struct *t) { } diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 358076eda364..9fcabeb07787 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -683,4 +683,24 @@ extern int early_irq_init(void); extern int arch_probe_nr_irqs(void); extern int arch_early_irq_init(void); +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) +/* + * We want to know which function is an entrypoint of a hardirq or a softirq. + */ +#define __irq_entry __attribute__((__section__(".irqentry.text"))) +#define __softirq_entry \ + __attribute__((__section__(".softirqentry.text"))) + +/* Limits of hardirq entrypoints */ +extern char __irqentry_text_start[]; +extern char __irqentry_text_end[]; +/* Limits of softirq entrypoints */ +extern char __softirqentry_text_start[]; +extern char __softirqentry_text_end[]; + +#else +#define __irq_entry +#define __softirq_entry +#endif + #endif diff --git a/kernel/softirq.c b/kernel/softirq.c index 8aae49dd7da8..17caf4b63342 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -227,7 +227,7 @@ static inline bool lockdep_softirq_start(void) { return false; } static inline void lockdep_softirq_end(bool in_hardirq) { } #endif -asmlinkage __visible void __do_softirq(void) +asmlinkage __visible void __softirq_entry __do_softirq(void) { unsigned long end = jiffies + MAX_SOFTIRQ_TIME; unsigned long old_flags = current->flags; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 91d6a63a2ea7..3a0244ff7ea8 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -8,6 +8,7 @@ */ #include #include +#include #include #include -- cgit v1.2.3 From f009a7a767e792d5ab0b46c08d46236ea5271dd9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 24 Mar 2016 15:38:00 +0100 Subject: timers/nohz: Convert tick dependency mask to atomic_t The tick dependency mask was intially unsigned long because this is the type on which clear_bit() operates on and fetch_or() accepts it. But now that we have atomic_fetch_or(), we can instead use atomic_andnot() to clear the bit. This consolidates the type of our tick dependency mask, reduce its size on structures and benefit from possible architecture optimizations on atomic_t operations. Suggested-by: Linus Torvalds Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1458830281-4255-3-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- kernel/time/tick-sched.c | 61 ++++++++++++++++++++++++------------------------ kernel/time/tick-sched.h | 2 +- 3 files changed, 33 insertions(+), 34 deletions(-) (limited to 'kernel') diff --git a/include/linux/sched.h b/include/linux/sched.h index 60bba7e032dc..52c4847b05e2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -720,7 +720,7 @@ struct signal_struct { struct task_cputime cputime_expires; #ifdef CONFIG_NO_HZ_FULL - unsigned long tick_dep_mask; + atomic_t tick_dep_mask; #endif struct list_head cpu_timers[3]; @@ -1549,7 +1549,7 @@ struct task_struct { #endif #ifdef CONFIG_NO_HZ_FULL - unsigned long tick_dep_mask; + atomic_t tick_dep_mask; #endif unsigned long nvcsw, nivcsw; /* context switch counts */ u64 start_time; /* monotonic time in nsec */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 084b79f5917e..58e3310c9b21 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -157,52 +157,50 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) cpumask_var_t tick_nohz_full_mask; cpumask_var_t housekeeping_mask; bool tick_nohz_full_running; -static unsigned long tick_dep_mask; +static atomic_t tick_dep_mask; -static void trace_tick_dependency(unsigned long dep) +static bool check_tick_dependency(atomic_t *dep) { - if (dep & TICK_DEP_MASK_POSIX_TIMER) { + int val = atomic_read(dep); + + if (val & TICK_DEP_MASK_POSIX_TIMER) { trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER); - return; + return true; } - if (dep & TICK_DEP_MASK_PERF_EVENTS) { + if (val & TICK_DEP_MASK_PERF_EVENTS) { trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS); - return; + return true; } - if (dep & TICK_DEP_MASK_SCHED) { + if (val & TICK_DEP_MASK_SCHED) { trace_tick_stop(0, TICK_DEP_MASK_SCHED); - return; + return true; } - if (dep & TICK_DEP_MASK_CLOCK_UNSTABLE) + if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) { trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE); + return true; + } + + return false; } static bool can_stop_full_tick(struct tick_sched *ts) { WARN_ON_ONCE(!irqs_disabled()); - if (tick_dep_mask) { - trace_tick_dependency(tick_dep_mask); + if (check_tick_dependency(&tick_dep_mask)) return false; - } - if (ts->tick_dep_mask) { - trace_tick_dependency(ts->tick_dep_mask); + if (check_tick_dependency(&ts->tick_dep_mask)) return false; - } - if (current->tick_dep_mask) { - trace_tick_dependency(current->tick_dep_mask); + if (check_tick_dependency(¤t->tick_dep_mask)) return false; - } - if (current->signal->tick_dep_mask) { - trace_tick_dependency(current->signal->tick_dep_mask); + if (check_tick_dependency(¤t->signal->tick_dep_mask)) return false; - } return true; } @@ -259,12 +257,12 @@ static void tick_nohz_full_kick_all(void) preempt_enable(); } -static void tick_nohz_dep_set_all(unsigned long *dep, +static void tick_nohz_dep_set_all(atomic_t *dep, enum tick_dep_bits bit) { - unsigned long prev; + int prev; - prev = fetch_or(dep, BIT_MASK(bit)); + prev = atomic_fetch_or(dep, BIT(bit)); if (!prev) tick_nohz_full_kick_all(); } @@ -280,7 +278,7 @@ void tick_nohz_dep_set(enum tick_dep_bits bit) void tick_nohz_dep_clear(enum tick_dep_bits bit) { - clear_bit(bit, &tick_dep_mask); + atomic_andnot(BIT(bit), &tick_dep_mask); } /* @@ -289,12 +287,12 @@ void tick_nohz_dep_clear(enum tick_dep_bits bit) */ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { - unsigned long prev; + int prev; struct tick_sched *ts; ts = per_cpu_ptr(&tick_cpu_sched, cpu); - prev = fetch_or(&ts->tick_dep_mask, BIT_MASK(bit)); + prev = atomic_fetch_or(&ts->tick_dep_mask, BIT(bit)); if (!prev) { preempt_disable(); /* Perf needs local kick that is NMI safe */ @@ -313,7 +311,7 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); - clear_bit(bit, &ts->tick_dep_mask); + atomic_andnot(BIT(bit), &ts->tick_dep_mask); } /* @@ -331,7 +329,7 @@ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { - clear_bit(bit, &tsk->tick_dep_mask); + atomic_andnot(BIT(bit), &tsk->tick_dep_mask); } /* @@ -345,7 +343,7 @@ void tick_nohz_dep_set_signal(struct signal_struct *sig, enum tick_dep_bits bit) void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit) { - clear_bit(bit, &sig->tick_dep_mask); + atomic_andnot(BIT(bit), &sig->tick_dep_mask); } /* @@ -366,7 +364,8 @@ void __tick_nohz_task_switch(void) ts = this_cpu_ptr(&tick_cpu_sched); if (ts->tick_stopped) { - if (current->tick_dep_mask || current->signal->tick_dep_mask) + if (atomic_read(¤t->tick_dep_mask) || + atomic_read(¤t->signal->tick_dep_mask)) tick_nohz_full_kick(); } out: diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index eb4e32566a83..bf38226e5c17 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -60,7 +60,7 @@ struct tick_sched { u64 next_timer; ktime_t idle_expires; int do_timer_last; - unsigned long tick_dep_mask; + atomic_t tick_dep_mask; }; extern struct tick_sched *tick_get_tick_sched(int cpu); -- cgit v1.2.3 From 5529578a27288d11d4d15635c258c6dde0f0fb10 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 24 Mar 2016 15:38:01 +0100 Subject: locking/atomic, sched: Unexport fetch_or() This patch functionally reverts: 5fd7a09cfb8c ("atomic: Export fetch_or()") During the merge Linus observed that the generic version of fetch_or() was messy: " This makes the ugly "fetch_or()" macro that the scheduler used internally a new generic helper, and does a bad job at it. " e23604edac2a Merge branch 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Now that we have introduced atomic_fetch_or(), fetch_or() is only used by the scheduler in order to deal with thread_info flags which type can vary across architectures. Lets confine fetch_or() back to the scheduler so that we encourage future users to use the more robust and well typed atomic_t version instead. While at it, fetch_or() gets robustified, pasting improvements from a previous patch by Ingo Molnar that avoids needless expression re-evaluations in the loop. Reported-by: Linus Torvalds Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1458830281-4255-4-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 21 --------------------- kernel/sched/core.c | 18 ++++++++++++++++++ 2 files changed, 18 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 3d64c0852164..506c3531832e 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -579,27 +579,6 @@ static inline int atomic_fetch_or(atomic_t *p, int mask) } #endif -/** - * fetch_or - perform *ptr |= mask and return old value of *ptr - * @ptr: pointer to value - * @mask: mask to OR on the value - * - * cmpxchg based fetch_or, macro so it works for different integer types - */ -#ifndef fetch_or -#define fetch_or(ptr, mask) \ -({ typeof(*(ptr)) __old, __val = *(ptr); \ - for (;;) { \ - __old = cmpxchg((ptr), __val, __val | (mask)); \ - if (__old == __val) \ - break; \ - __val = __old; \ - } \ - __old; \ -}) -#endif - - #ifdef CONFIG_GENERIC_ATOMIC64 #include #endif diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d8465eeab8b3..8b489fcac37b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -321,6 +321,24 @@ static inline void init_hrtick(void) } #endif /* CONFIG_SCHED_HRTICK */ +/* + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#define fetch_or(ptr, mask) \ + ({ \ + typeof(ptr) _ptr = (ptr); \ + typeof(mask) _mask = (mask); \ + typeof(*_ptr) _old, _val = *_ptr; \ + \ + for (;;) { \ + _old = cmpxchg(_ptr, _val, _val | _mask); \ + if (_old == _val) \ + break; \ + _val = _old; \ + } \ + _old; \ +}) + #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) /* * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, -- cgit v1.2.3 From 39e2e173fb1f900959d3a25c21c65fa88b06c6ee Mon Sep 17 00:00:00 2001 From: Alfredo Alvarez Fernandez Date: Wed, 30 Mar 2016 19:03:36 +0200 Subject: locking/lockdep: Print chain_key collision information A sequence of pairs [class_idx -> corresponding chain_key iteration] is printed for both the current held_lock chain and the cached chain. That exposes the two different class_idx sequences that led to that particular hash value. This helps with debugging hash chain collision reports. Signed-off-by: Alfredo Alvarez Fernandez Acked-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-fsdevel@vger.kernel.org Cc: sedat.dilek@gmail.com Cc: tytso@mit.edu Link: http://lkml.kernel.org/r/1459357416-19190-1-git-send-email-alfredoalvarezernandez@gmail.com Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 79 ++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 77 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 53ab2f85d77e..2324ba5310db 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1999,6 +1999,77 @@ static inline int get_first_held_lock(struct task_struct *curr, return ++i; } +/* + * Returns the next chain_key iteration + */ +static u64 print_chain_key_iteration(int class_idx, u64 chain_key) +{ + u64 new_chain_key = iterate_chain_key(chain_key, class_idx); + + printk(" class_idx:%d -> chain_key:%016Lx", + class_idx, + (unsigned long long)new_chain_key); + return new_chain_key; +} + +static void +print_chain_keys_held_locks(struct task_struct *curr, struct held_lock *hlock_next) +{ + struct held_lock *hlock; + u64 chain_key = 0; + int depth = curr->lockdep_depth; + int i; + + printk("depth: %u\n", depth + 1); + for (i = get_first_held_lock(curr, hlock_next); i < depth; i++) { + hlock = curr->held_locks + i; + chain_key = print_chain_key_iteration(hlock->class_idx, chain_key); + + print_lock(hlock); + } + + print_chain_key_iteration(hlock_next->class_idx, chain_key); + print_lock(hlock_next); +} + +static void print_chain_keys_chain(struct lock_chain *chain) +{ + int i; + u64 chain_key = 0; + int class_id; + + printk("depth: %u\n", chain->depth); + for (i = 0; i < chain->depth; i++) { + class_id = chain_hlocks[chain->base + i]; + chain_key = print_chain_key_iteration(class_id + 1, chain_key); + + print_lock_name(lock_classes + class_id); + printk("\n"); + } +} + +static void print_collision(struct task_struct *curr, + struct held_lock *hlock_next, + struct lock_chain *chain) +{ + printk("\n"); + printk("======================\n"); + printk("[chain_key collision ]\n"); + print_kernel_ident(); + printk("----------------------\n"); + printk("%s/%d: ", current->comm, task_pid_nr(current)); + printk("Hash chain already cached but the contents don't match!\n"); + + printk("Held locks:"); + print_chain_keys_held_locks(curr, hlock_next); + + printk("Locks in cached chain:"); + print_chain_keys_chain(chain); + + printk("\nstack backtrace:\n"); + dump_stack(); +} + /* * Checks whether the chain and the current held locks are consistent * in depth and also in content. If they are not it most likely means @@ -2014,14 +2085,18 @@ static int check_no_collision(struct task_struct *curr, i = get_first_held_lock(curr, hlock); - if (DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))) + if (DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))) { + print_collision(curr, hlock, chain); return 0; + } for (j = 0; j < chain->depth - 1; j++, i++) { id = curr->held_locks[i].class_idx - 1; - if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) + if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) { + print_collision(curr, hlock, chain); return 0; + } } #endif return 1; -- cgit v1.2.3 From 09cbfeaf1a5a67bfb3201e0c83c810cecb2efa5a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 1 Apr 2016 15:29:47 +0300 Subject: mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> ; - >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> ; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov Acked-by: Michal Hocko Signed-off-by: Linus Torvalds --- arch/arc/mm/cache.c | 2 +- arch/arm/mm/flush.c | 4 +- arch/parisc/kernel/cache.c | 2 +- arch/powerpc/platforms/cell/spufs/inode.c | 4 +- arch/s390/hypfs/inode.c | 4 +- block/bio.c | 8 +- block/blk-core.c | 2 +- block/blk-settings.c | 12 +- block/blk-sysfs.c | 8 +- block/cfq-iosched.c | 2 +- block/compat_ioctl.c | 4 +- block/ioctl.c | 4 +- block/partition-generic.c | 8 +- drivers/block/aoe/aoeblk.c | 2 +- drivers/block/brd.c | 2 +- drivers/block/drbd/drbd_nl.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- drivers/gpu/drm/armada/armada_gem.c | 4 +- drivers/gpu/drm/drm_gem.c | 4 +- drivers/gpu/drm/i915/i915_gem.c | 8 +- drivers/gpu/drm/i915/i915_gem_userptr.c | 2 +- drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- drivers/gpu/drm/ttm/ttm_tt.c | 4 +- drivers/gpu/drm/via/via_dmablit.c | 2 +- drivers/md/bitmap.c | 2 +- drivers/media/v4l2-core/videobuf-dma-sg.c | 2 +- drivers/misc/ibmasm/ibmasmfs.c | 4 +- drivers/misc/vmw_vmci/vmci_queue_pair.c | 2 +- drivers/mmc/core/host.c | 6 +- drivers/mmc/host/sh_mmcif.c | 2 +- drivers/mmc/host/tmio_mmc_dma.c | 4 +- drivers/mmc/host/tmio_mmc_pio.c | 2 +- drivers/mmc/host/usdhi6rol0.c | 2 +- drivers/mtd/devices/block2mtd.c | 6 +- drivers/mtd/nand/nandsim.c | 6 +- drivers/nvdimm/btt.c | 2 +- drivers/nvdimm/pmem.c | 2 +- drivers/oprofile/oprofilefs.c | 4 +- drivers/scsi/sd.c | 2 +- drivers/scsi/st.c | 4 +- .../lustre/include/linux/libcfs/libcfs_private.h | 2 +- .../lustre/include/linux/libcfs/linux/linux-mem.h | 4 +- .../lustre/lnet/klnds/socklnd/socklnd_lib.c | 2 +- drivers/staging/lustre/lnet/libcfs/debug.c | 2 +- drivers/staging/lustre/lnet/libcfs/tracefile.c | 16 +- drivers/staging/lustre/lnet/libcfs/tracefile.h | 6 +- drivers/staging/lustre/lnet/lnet/lib-md.c | 2 +- drivers/staging/lustre/lnet/lnet/lib-move.c | 6 +- drivers/staging/lustre/lnet/lnet/lib-socket.c | 4 +- drivers/staging/lustre/lnet/lnet/router.c | 6 +- drivers/staging/lustre/lnet/selftest/brw_test.c | 20 +- drivers/staging/lustre/lnet/selftest/conctl.c | 4 +- drivers/staging/lustre/lnet/selftest/conrpc.c | 10 +- drivers/staging/lustre/lnet/selftest/framework.c | 2 +- drivers/staging/lustre/lnet/selftest/rpc.c | 2 +- drivers/staging/lustre/lnet/selftest/selftest.h | 2 +- .../lustre/include/linux/lustre_patchless_compat.h | 2 +- .../lustre/lustre/include/lustre/lustre_idl.h | 2 +- drivers/staging/lustre/lustre/include/lustre_mdc.h | 4 +- drivers/staging/lustre/lustre/include/lustre_net.h | 6 +- drivers/staging/lustre/lustre/include/obd.h | 2 +- .../staging/lustre/lustre/include/obd_support.h | 2 +- drivers/staging/lustre/lustre/lclient/lcommon_cl.c | 4 +- drivers/staging/lustre/lustre/ldlm/ldlm_lib.c | 12 +- drivers/staging/lustre/lustre/ldlm/ldlm_pool.c | 2 +- drivers/staging/lustre/lustre/ldlm/ldlm_request.c | 2 +- drivers/staging/lustre/lustre/llite/dir.c | 18 +- .../staging/lustre/lustre/llite/llite_internal.h | 8 +- drivers/staging/lustre/lustre/llite/llite_lib.c | 8 +- drivers/staging/lustre/lustre/llite/llite_mmap.c | 8 +- drivers/staging/lustre/lustre/llite/lloop.c | 12 +- drivers/staging/lustre/lustre/llite/lproc_llite.c | 18 +- drivers/staging/lustre/lustre/llite/rw.c | 22 +- drivers/staging/lustre/lustre/llite/rw26.c | 28 +-- drivers/staging/lustre/lustre/llite/vvp_io.c | 8 +- drivers/staging/lustre/lustre/llite/vvp_page.c | 8 +- drivers/staging/lustre/lustre/lmv/lmv_obd.c | 4 +- drivers/staging/lustre/lustre/mdc/mdc_request.c | 6 +- drivers/staging/lustre/lustre/mgc/mgc_request.c | 22 +- drivers/staging/lustre/lustre/obdclass/cl_page.c | 6 +- drivers/staging/lustre/lustre/obdclass/class_obd.c | 6 +- .../lustre/lustre/obdclass/linux/linux-obdo.c | 4 +- .../lustre/lustre/obdclass/linux/linux-sysctl.c | 6 +- drivers/staging/lustre/lustre/obdclass/lu_object.c | 6 +- .../staging/lustre/lustre/obdecho/echo_client.c | 30 +-- drivers/staging/lustre/lustre/osc/lproc_osc.c | 16 +- drivers/staging/lustre/lustre/osc/osc_cache.c | 42 ++-- drivers/staging/lustre/lustre/osc/osc_page.c | 6 +- drivers/staging/lustre/lustre/osc/osc_request.c | 26 +- drivers/staging/lustre/lustre/ptlrpc/client.c | 6 +- drivers/staging/lustre/lustre/ptlrpc/import.c | 2 +- .../staging/lustre/lustre/ptlrpc/lproc_ptlrpc.c | 4 +- drivers/staging/lustre/lustre/ptlrpc/recover.c | 2 +- drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c | 2 +- drivers/usb/gadget/function/f_fs.c | 4 +- drivers/usb/gadget/legacy/inode.c | 4 +- drivers/usb/storage/scsiglue.c | 2 +- drivers/video/fbdev/pvr2fb.c | 2 +- fs/9p/vfs_addr.c | 18 +- fs/9p/vfs_file.c | 4 +- fs/9p/vfs_super.c | 2 +- fs/affs/file.c | 26 +- fs/afs/dir.c | 2 +- fs/afs/file.c | 4 +- fs/afs/mntpt.c | 6 +- fs/afs/super.c | 4 +- fs/afs/write.c | 26 +- fs/binfmt_elf.c | 2 +- fs/binfmt_elf_fdpic.c | 2 +- fs/block_dev.c | 4 +- fs/btrfs/check-integrity.c | 60 ++--- fs/btrfs/compression.c | 84 +++---- fs/btrfs/disk-io.c | 14 +- fs/btrfs/extent-tree.c | 4 +- fs/btrfs/extent_io.c | 262 ++++++++++----------- fs/btrfs/extent_io.h | 6 +- fs/btrfs/file-item.c | 4 +- fs/btrfs/file.c | 40 ++-- fs/btrfs/free-space-cache.c | 30 +-- fs/btrfs/inode-map.c | 10 +- fs/btrfs/inode.c | 104 ++++---- fs/btrfs/ioctl.c | 84 +++---- fs/btrfs/lzo.c | 32 +-- fs/btrfs/raid56.c | 28 +-- fs/btrfs/reada.c | 30 +-- fs/btrfs/relocation.c | 16 +- fs/btrfs/scrub.c | 24 +- fs/btrfs/send.c | 16 +- fs/btrfs/tests/extent-io-tests.c | 42 ++-- fs/btrfs/tests/free-space-tests.c | 2 +- fs/btrfs/volumes.c | 14 +- fs/btrfs/zlib.c | 38 +-- fs/buffer.c | 100 ++++---- fs/cachefiles/rdwr.c | 38 +-- fs/ceph/addr.c | 114 ++++----- fs/ceph/caps.c | 2 +- fs/ceph/dir.c | 4 +- fs/ceph/file.c | 32 +-- fs/ceph/inode.c | 6 +- fs/ceph/mds_client.c | 2 +- fs/ceph/mds_client.h | 2 +- fs/ceph/super.c | 8 +- fs/cifs/cifsfs.c | 2 +- fs/cifs/cifssmb.c | 16 +- fs/cifs/connect.c | 2 +- fs/cifs/file.c | 94 ++++---- fs/cifs/inode.c | 10 +- fs/configfs/mount.c | 4 +- fs/cramfs/inode.c | 30 +-- fs/crypto/crypto.c | 8 +- fs/dax.c | 30 +-- fs/direct-io.c | 26 +- fs/dlm/lowcomms.c | 8 +- fs/ecryptfs/crypto.c | 22 +- fs/ecryptfs/inode.c | 4 +- fs/ecryptfs/keystore.c | 2 +- fs/ecryptfs/main.c | 8 +- fs/ecryptfs/mmap.c | 44 ++-- fs/ecryptfs/read_write.c | 14 +- fs/efivarfs/super.c | 4 +- fs/exofs/dir.c | 30 +-- fs/exofs/inode.c | 34 +-- fs/exofs/namei.c | 4 +- fs/ext2/dir.c | 32 +-- fs/ext2/namei.c | 6 +- fs/ext4/crypto.c | 8 +- fs/ext4/dir.c | 4 +- fs/ext4/file.c | 4 +- fs/ext4/inline.c | 18 +- fs/ext4/inode.c | 116 ++++----- fs/ext4/mballoc.c | 36 +-- fs/ext4/move_extent.c | 16 +- fs/ext4/page-io.c | 4 +- fs/ext4/readpage.c | 10 +- fs/ext4/super.c | 4 +- fs/ext4/symlink.c | 4 +- fs/f2fs/data.c | 52 ++-- fs/f2fs/debug.c | 6 +- fs/f2fs/dir.c | 4 +- fs/f2fs/f2fs.h | 2 +- fs/f2fs/file.c | 74 +++--- fs/f2fs/inline.c | 10 +- fs/f2fs/namei.c | 4 +- fs/f2fs/node.c | 10 +- fs/f2fs/recovery.c | 2 +- fs/f2fs/segment.c | 16 +- fs/f2fs/super.c | 4 +- fs/freevxfs/vxfs_immed.c | 4 +- fs/freevxfs/vxfs_lookup.c | 12 +- fs/freevxfs/vxfs_subr.c | 2 +- fs/fs-writeback.c | 2 +- fs/fscache/page.c | 10 +- fs/fuse/dev.c | 26 +- fs/fuse/file.c | 72 +++--- fs/fuse/inode.c | 16 +- fs/gfs2/aops.c | 44 ++-- fs/gfs2/bmap.c | 12 +- fs/gfs2/file.c | 16 +- fs/gfs2/meta_io.c | 4 +- fs/gfs2/quota.c | 14 +- fs/gfs2/rgrp.c | 5 +- fs/hfs/bnode.c | 12 +- fs/hfs/btree.c | 20 +- fs/hfs/inode.c | 8 +- fs/hfsplus/bitmap.c | 2 +- fs/hfsplus/bnode.c | 90 +++---- fs/hfsplus/btree.c | 22 +- fs/hfsplus/inode.c | 8 +- fs/hfsplus/super.c | 2 +- fs/hfsplus/xattr.c | 6 +- fs/hostfs/hostfs_kern.c | 18 +- fs/hugetlbfs/inode.c | 8 +- fs/isofs/compress.c | 36 +-- fs/isofs/inode.c | 2 +- fs/jbd2/commit.c | 4 +- fs/jbd2/journal.c | 2 +- fs/jbd2/transaction.c | 4 +- fs/jffs2/debug.c | 8 +- fs/jffs2/file.c | 23 +- fs/jffs2/fs.c | 8 +- fs/jffs2/gc.c | 8 +- fs/jffs2/nodelist.c | 8 +- fs/jffs2/write.c | 7 +- fs/jfs/jfs_metapage.c | 42 ++-- fs/jfs/jfs_metapage.h | 4 +- fs/jfs/super.c | 2 +- fs/kernfs/mount.c | 4 +- fs/libfs.c | 24 +- fs/logfs/dev_bdev.c | 2 +- fs/logfs/dev_mtd.c | 10 +- fs/logfs/dir.c | 12 +- fs/logfs/file.c | 26 +- fs/logfs/readwrite.c | 20 +- fs/logfs/segment.c | 28 +-- fs/logfs/super.c | 16 +- fs/minix/dir.c | 18 +- fs/minix/namei.c | 4 +- fs/mpage.c | 20 +- fs/ncpfs/dir.c | 10 +- fs/ncpfs/ncplib_kernel.h | 2 +- fs/nfs/blocklayout/blocklayout.c | 24 +- fs/nfs/blocklayout/blocklayout.h | 4 +- fs/nfs/client.c | 8 +- fs/nfs/dir.c | 4 +- fs/nfs/direct.c | 8 +- fs/nfs/file.c | 20 +- fs/nfs/internal.h | 6 +- fs/nfs/nfs4xdr.c | 2 +- fs/nfs/objlayout/objio_osd.c | 2 +- fs/nfs/pagelist.c | 6 +- fs/nfs/pnfs.c | 6 +- fs/nfs/read.c | 16 +- fs/nfs/write.c | 4 +- fs/nilfs2/bmap.c | 2 +- fs/nilfs2/btnode.c | 10 +- fs/nilfs2/dir.c | 32 +-- fs/nilfs2/gcinode.c | 2 +- fs/nilfs2/inode.c | 4 +- fs/nilfs2/mdt.c | 14 +- fs/nilfs2/namei.c | 4 +- fs/nilfs2/page.c | 18 +- fs/nilfs2/recovery.c | 4 +- fs/nilfs2/segment.c | 2 +- fs/ntfs/aops.c | 48 ++-- fs/ntfs/aops.h | 2 +- fs/ntfs/attrib.c | 28 +-- fs/ntfs/bitmap.c | 10 +- fs/ntfs/compress.c | 56 ++--- fs/ntfs/dir.c | 40 ++-- fs/ntfs/file.c | 54 ++--- fs/ntfs/index.c | 12 +- fs/ntfs/inode.c | 8 +- fs/ntfs/lcnalloc.c | 6 +- fs/ntfs/logfile.c | 16 +- fs/ntfs/mft.c | 34 +-- fs/ntfs/ntfs.h | 2 +- fs/ntfs/super.c | 58 ++--- fs/ocfs2/alloc.c | 28 +-- fs/ocfs2/aops.c | 48 ++-- fs/ocfs2/cluster/heartbeat.c | 10 +- fs/ocfs2/dlmfs/dlmfs.c | 4 +- fs/ocfs2/file.c | 14 +- fs/ocfs2/mmap.c | 6 +- fs/ocfs2/ocfs2.h | 20 +- fs/ocfs2/refcounttree.c | 22 +- fs/ocfs2/super.c | 4 +- fs/orangefs/inode.c | 10 +- fs/orangefs/orangefs-bufmap.c | 4 +- fs/orangefs/orangefs-utils.c | 2 +- fs/pipe.c | 6 +- fs/proc/task_mmu.c | 2 +- fs/proc/vmcore.c | 4 +- fs/pstore/inode.c | 4 +- fs/qnx6/dir.c | 16 +- fs/qnx6/inode.c | 4 +- fs/qnx6/qnx6.h | 2 +- fs/ramfs/inode.c | 4 +- fs/reiserfs/file.c | 4 +- fs/reiserfs/inode.c | 44 ++-- fs/reiserfs/ioctl.c | 4 +- fs/reiserfs/journal.c | 4 +- fs/reiserfs/stree.c | 4 +- fs/reiserfs/tail_conversion.c | 4 +- fs/reiserfs/xattr.c | 18 +- fs/splice.c | 32 +-- fs/squashfs/block.c | 4 +- fs/squashfs/cache.c | 14 +- fs/squashfs/decompressor.c | 2 +- fs/squashfs/file.c | 22 +- fs/squashfs/file_direct.c | 22 +- fs/squashfs/lz4_wrapper.c | 8 +- fs/squashfs/lzo_wrapper.c | 8 +- fs/squashfs/page_actor.c | 4 +- fs/squashfs/page_actor.h | 2 +- fs/squashfs/super.c | 2 +- fs/squashfs/symlink.c | 6 +- fs/squashfs/xz_wrapper.c | 4 +- fs/squashfs/zlib_wrapper.c | 4 +- fs/sync.c | 4 +- fs/sysv/dir.c | 18 +- fs/sysv/namei.c | 4 +- fs/ubifs/file.c | 52 ++-- fs/ubifs/super.c | 4 +- fs/ubifs/ubifs.h | 4 +- fs/udf/file.c | 6 +- fs/udf/inode.c | 4 +- fs/ufs/balloc.c | 6 +- fs/ufs/dir.c | 32 +-- fs/ufs/inode.c | 4 +- fs/ufs/namei.c | 6 +- fs/ufs/util.c | 4 +- fs/ufs/util.h | 2 +- fs/xfs/libxfs/xfs_bmap.c | 4 +- fs/xfs/xfs_aops.c | 18 +- fs/xfs/xfs_bmap_util.c | 4 +- fs/xfs/xfs_file.c | 12 +- fs/xfs/xfs_linux.h | 2 +- fs/xfs/xfs_mount.c | 2 +- fs/xfs/xfs_mount.h | 4 +- fs/xfs/xfs_pnfs.c | 4 +- fs/xfs/xfs_super.c | 4 +- include/linux/bio.h | 2 +- include/linux/blkdev.h | 2 +- include/linux/buffer_head.h | 4 +- include/linux/ceph/libceph.h | 4 +- include/linux/f2fs_fs.h | 4 +- include/linux/fs.h | 4 +- include/linux/nfs_page.h | 2 +- include/linux/pagemap.h | 14 +- include/linux/swap.h | 2 +- ipc/mqueue.c | 4 +- kernel/events/uprobes.c | 8 +- mm/fadvise.c | 8 +- mm/filemap.c | 126 +++++----- mm/hugetlb.c | 8 +- mm/madvise.c | 6 +- mm/memory-failure.c | 2 +- mm/memory.c | 54 ++--- mm/mincore.c | 4 +- mm/nommu.c | 2 +- mm/page-writeback.c | 12 +- mm/page_io.c | 2 +- mm/readahead.c | 20 +- mm/rmap.c | 2 +- mm/shmem.c | 130 +++++----- mm/swap.c | 12 +- mm/swap_state.c | 12 +- mm/swapfile.c | 12 +- mm/truncate.c | 40 ++-- mm/userfaultfd.c | 4 +- mm/zswap.c | 4 +- net/ceph/messenger.c | 6 +- net/ceph/pagelist.c | 4 +- net/ceph/pagevec.c | 30 +-- net/sunrpc/auth_gss/auth_gss.c | 8 +- net/sunrpc/auth_gss/gss_krb5_crypto.c | 2 +- net/sunrpc/auth_gss/gss_krb5_wrap.c | 4 +- net/sunrpc/cache.c | 4 +- net/sunrpc/rpc_pipe.c | 4 +- net/sunrpc/socklib.c | 6 +- net/sunrpc/xdr.c | 48 ++-- 381 files changed, 2722 insertions(+), 2721 deletions(-) (limited to 'kernel') diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index d7709e3930a3..9e5eddbb856f 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -628,7 +628,7 @@ void flush_dcache_page(struct page *page) /* kernel reading from page with U-mapping */ phys_addr_t paddr = (unsigned long)page_address(page); - unsigned long vaddr = page->index << PAGE_CACHE_SHIFT; + unsigned long vaddr = page->index << PAGE_SHIFT; if (addr_not_cache_congruent(paddr, vaddr)) __flush_dcache_page(paddr, vaddr); diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index d0ba3551d49a..3cced8455727 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -235,7 +235,7 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page) */ if (mapping && cache_is_vipt_aliasing()) flush_pfn_alias(page_to_pfn(page), - page->index << PAGE_CACHE_SHIFT); + page->index << PAGE_SHIFT); } static void __flush_dcache_aliases(struct address_space *mapping, struct page *page) @@ -250,7 +250,7 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p * data in the current VM view associated with this page. * - aliasing VIPT: we only need to find one mapping of this page. */ - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff = page->index; flush_dcache_mmap_lock(mapping); vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 91c2a39cd5aa..67001277256c 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -319,7 +319,7 @@ void flush_dcache_page(struct page *page) if (!mapping) return; - pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff = page->index; /* We have carefully arranged in arch_get_unmapped_area() that * *any* mappings of a file are always congruently mapped (whether diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index dfa863876778..6ca5f0525e57 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -732,8 +732,8 @@ spufs_fill_super(struct super_block *sb, void *data, int silent) return -ENOMEM; sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = SPUFS_MAGIC; sb->s_op = &s_ops; sb->s_fs_info = info; diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 0f3da2cb2bd6..255c7eec4481 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -278,8 +278,8 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent) sbi->uid = current_uid(); sbi->gid = current_gid(); sb->s_fs_info = sbi; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = HYPFS_MAGIC; sb->s_op = &hypfs_s_ops; if (hypfs_parse_options(data, sb)) diff --git a/block/bio.c b/block/bio.c index f124a0a624fc..168531517694 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1339,7 +1339,7 @@ struct bio *bio_map_user_iov(struct request_queue *q, * release the pages we didn't map into the bio, if any */ while (j < page_limit) - page_cache_release(pages[j++]); + put_page(pages[j++]); } kfree(pages); @@ -1365,7 +1365,7 @@ struct bio *bio_map_user_iov(struct request_queue *q, for (j = 0; j < nr_pages; j++) { if (!pages[j]) break; - page_cache_release(pages[j]); + put_page(pages[j]); } out: kfree(pages); @@ -1385,7 +1385,7 @@ static void __bio_unmap_user(struct bio *bio) if (bio_data_dir(bio) == READ) set_page_dirty_lock(bvec->bv_page); - page_cache_release(bvec->bv_page); + put_page(bvec->bv_page); } bio_put(bio); @@ -1658,7 +1658,7 @@ void bio_check_pages_dirty(struct bio *bio) struct page *page = bvec->bv_page; if (PageDirty(page) || PageCompound(page)) { - page_cache_release(page); + put_page(page); bvec->bv_page = NULL; } else { nr_clean_pages++; diff --git a/block/blk-core.c b/block/blk-core.c index 827f8badd143..b60537b2c35b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -706,7 +706,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) goto fail_id; q->backing_dev_info.ra_pages = - (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; + (VM_MAX_READAHEAD * 1024) / PAGE_SIZE; q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK; q->backing_dev_info.name = "block"; q->node = node_id; diff --git a/block/blk-settings.c b/block/blk-settings.c index c7bb666aafd1..331e4eee0dda 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -239,8 +239,8 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto struct queue_limits *limits = &q->limits; unsigned int max_sectors; - if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) { - max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9); + if ((max_hw_sectors << 9) < PAGE_SIZE) { + max_hw_sectors = 1 << (PAGE_SHIFT - 9); printk(KERN_INFO "%s: set to minimum %d\n", __func__, max_hw_sectors); } @@ -329,8 +329,8 @@ EXPORT_SYMBOL(blk_queue_max_segments); **/ void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size) { - if (max_size < PAGE_CACHE_SIZE) { - max_size = PAGE_CACHE_SIZE; + if (max_size < PAGE_SIZE) { + max_size = PAGE_SIZE; printk(KERN_INFO "%s: set to minimum %d\n", __func__, max_size); } @@ -760,8 +760,8 @@ EXPORT_SYMBOL_GPL(blk_queue_dma_drain); **/ void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask) { - if (mask < PAGE_CACHE_SIZE - 1) { - mask = PAGE_CACHE_SIZE - 1; + if (mask < PAGE_SIZE - 1) { + mask = PAGE_SIZE - 1; printk(KERN_INFO "%s: set to minimum %lx\n", __func__, mask); } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index dd93763057ce..995b58d46ed1 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -76,7 +76,7 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count) static ssize_t queue_ra_show(struct request_queue *q, char *page) { unsigned long ra_kb = q->backing_dev_info.ra_pages << - (PAGE_CACHE_SHIFT - 10); + (PAGE_SHIFT - 10); return queue_var_show(ra_kb, (page)); } @@ -90,7 +90,7 @@ queue_ra_store(struct request_queue *q, const char *page, size_t count) if (ret < 0) return ret; - q->backing_dev_info.ra_pages = ra_kb >> (PAGE_CACHE_SHIFT - 10); + q->backing_dev_info.ra_pages = ra_kb >> (PAGE_SHIFT - 10); return ret; } @@ -117,7 +117,7 @@ static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page) if (blk_queue_cluster(q)) return queue_var_show(queue_max_segment_size(q), (page)); - return queue_var_show(PAGE_CACHE_SIZE, (page)); + return queue_var_show(PAGE_SIZE, (page)); } static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page) @@ -198,7 +198,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) { unsigned long max_sectors_kb, max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1, - page_kb = 1 << (PAGE_CACHE_SHIFT - 10); + page_kb = 1 << (PAGE_SHIFT - 10); ssize_t ret = queue_var_store(&max_sectors_kb, page, count); if (ret < 0) diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index e3c591dd8f19..4a349787bc62 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -4075,7 +4075,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, * idle timer unplug to continue working. */ if (cfq_cfqq_wait_request(cfqq)) { - if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE || + if (blk_rq_bytes(rq) > PAGE_SIZE || cfqd->busy_queues > 1) { cfq_del_timer(cfqd, cfqq); cfq_clear_cfqq_wait_request(cfqq); diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index f678c733df40..556826ac7cb4 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -710,7 +710,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) return -EINVAL; bdi = blk_get_backing_dev_info(bdev); return compat_put_long(arg, - (bdi->ra_pages * PAGE_CACHE_SIZE) / 512); + (bdi->ra_pages * PAGE_SIZE) / 512); case BLKROGET: /* compatible */ return compat_put_int(arg, bdev_read_only(bdev) != 0); case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */ @@ -729,7 +729,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EACCES; bdi = blk_get_backing_dev_info(bdev); - bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE; + bdi->ra_pages = (arg * 512) / PAGE_SIZE; return 0; case BLKGETSIZE: size = i_size_read(bdev->bd_inode); diff --git a/block/ioctl.c b/block/ioctl.c index d8996bbd7f12..4ff1f92f89ca 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -550,7 +550,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, if (!arg) return -EINVAL; bdi = blk_get_backing_dev_info(bdev); - return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512); + return put_long(arg, (bdi->ra_pages * PAGE_SIZE) / 512); case BLKROGET: return put_int(arg, bdev_read_only(bdev) != 0); case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ @@ -578,7 +578,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, if(!capable(CAP_SYS_ADMIN)) return -EACCES; bdi = blk_get_backing_dev_info(bdev); - bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE; + bdi->ra_pages = (arg * 512) / PAGE_SIZE; return 0; case BLKBSZSET: return blkdev_bszset(bdev, mode, argp); diff --git a/block/partition-generic.c b/block/partition-generic.c index 5d8701941054..2c6ae2aed2c4 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -566,8 +566,8 @@ static struct page *read_pagecache_sector(struct block_device *bdev, sector_t n) { struct address_space *mapping = bdev->bd_inode->i_mapping; - return read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)), - NULL); + return read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_SHIFT-9)), + NULL); } unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) @@ -584,9 +584,9 @@ unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) if (PageError(page)) goto fail; p->v = page; - return (unsigned char *)page_address(page) + ((n & ((1 << (PAGE_CACHE_SHIFT - 9)) - 1)) << 9); + return (unsigned char *)page_address(page) + ((n & ((1 << (PAGE_SHIFT - 9)) - 1)) << 9); fail: - page_cache_release(page); + put_page(page); } p->v = NULL; return NULL; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index dd73e1ff1759..ec9d8610b25f 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -397,7 +397,7 @@ aoeblk_gdalloc(void *vp) WARN_ON(d->flags & DEVFL_UP); blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS); q->backing_dev_info.name = "aoe"; - q->backing_dev_info.ra_pages = READ_AHEAD / PAGE_CACHE_SIZE; + q->backing_dev_info.ra_pages = READ_AHEAD / PAGE_SIZE; d->bufpool = mp; d->blkq = gd->queue = q; q->queuedata = d; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index f7ecc287d733..51a071e32221 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -374,7 +374,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector, struct page *page, int rw) { struct brd_device *brd = bdev->bd_disk->private_data; - int err = brd_do_bvec(brd, page, PAGE_CACHE_SIZE, 0, rw, sector); + int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, rw, sector); page_endio(page, rw & WRITE, err); return err; } diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 226eb0c9f0fb..1fd1dccebb6b 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1178,7 +1178,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi blk_queue_max_hw_sectors(q, max_hw_sectors); /* This is the workaround for "bio would need to, but cannot, be split" */ blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS); - blk_queue_segment_boundary(q, PAGE_CACHE_SIZE-1); + blk_queue_segment_boundary(q, PAGE_SIZE-1); if (b) { struct drbd_connection *connection = first_peer_device(device)->connection; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index ab34190859a8..c018b021707c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -616,7 +616,7 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm) set_page_dirty(page); mark_page_accessed(page); - page_cache_release(page); + put_page(page); } sg_free_table(ttm->sg); diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index 6e731db31aa4..aca7f9cc6109 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -481,7 +481,7 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach, release: for_each_sg(sgt->sgl, sg, num, i) - page_cache_release(sg_page(sg)); + put_page(sg_page(sg)); free_table: sg_free_table(sgt); free_sgt: @@ -502,7 +502,7 @@ static void armada_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach, if (dobj->obj.filp) { struct scatterlist *sg; for_each_sg(sgt->sgl, sg, sgt->nents, i) - page_cache_release(sg_page(sg)); + put_page(sg_page(sg)); } sg_free_table(sgt); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 2e8c77e71e1f..da0c5320789f 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -534,7 +534,7 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj) fail: while (i--) - page_cache_release(pages[i]); + put_page(pages[i]); drm_free_large(pages); return ERR_CAST(p); @@ -569,7 +569,7 @@ void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages, mark_page_accessed(pages[i]); /* Undo the reference we took when populating the table */ - page_cache_release(pages[i]); + put_page(pages[i]); } drm_free_large(pages); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 3d31d3ac589e..dabc08987b5e 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -177,7 +177,7 @@ i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj) drm_clflush_virt_range(vaddr, PAGE_SIZE); kunmap_atomic(src); - page_cache_release(page); + put_page(page); vaddr += PAGE_SIZE; } @@ -243,7 +243,7 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj) set_page_dirty(page); if (obj->madv == I915_MADV_WILLNEED) mark_page_accessed(page); - page_cache_release(page); + put_page(page); vaddr += PAGE_SIZE; } obj->dirty = 0; @@ -2206,7 +2206,7 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj) if (obj->madv == I915_MADV_WILLNEED) mark_page_accessed(page); - page_cache_release(page); + put_page(page); } obj->dirty = 0; @@ -2346,7 +2346,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) err_pages: sg_mark_end(sg); for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) - page_cache_release(sg_page_iter_page(&sg_iter)); + put_page(sg_page_iter_page(&sg_iter)); sg_free_table(st); kfree(st); diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index 6be40f3ba2c7..18ba8139e922 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -683,7 +683,7 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj) set_page_dirty(page); mark_page_accessed(page); - page_cache_release(page); + put_page(page); } obj->dirty = 0; diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 6d8c32377c6f..0deb7f047be0 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -609,7 +609,7 @@ static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm) set_page_dirty(page); mark_page_accessed(page); - page_cache_release(page); + put_page(page); } sg_free_table(ttm->sg); diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 4e19d0f9cc30..077ae9b2865d 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -311,7 +311,7 @@ int ttm_tt_swapin(struct ttm_tt *ttm) goto out_err; copy_highpage(to_page, from_page); - page_cache_release(from_page); + put_page(from_page); } if (!(ttm->page_flags & TTM_PAGE_FLAG_PERSISTENT_SWAP)) @@ -361,7 +361,7 @@ int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage) copy_highpage(to_page, from_page); set_page_dirty(to_page); mark_page_accessed(to_page); - page_cache_release(to_page); + put_page(to_page); } ttm_tt_unpopulate(ttm); diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c index e797dfc07ae3..7e2a12c4fed2 100644 --- a/drivers/gpu/drm/via/via_dmablit.c +++ b/drivers/gpu/drm/via/via_dmablit.c @@ -188,7 +188,7 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg) if (NULL != (page = vsg->pages[i])) { if (!PageReserved(page) && (DMA_FROM_DEVICE == vsg->direction)) SetPageDirty(page); - page_cache_release(page); + put_page(page); } } case dr_via_pages_alloc: diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 7df6b4f1548a..bef71751aade 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -322,7 +322,7 @@ __clear_page_buffers(struct page *page) { ClearPagePrivate(page); set_page_private(page, 0); - page_cache_release(page); + put_page(page); } static void free_buffers(struct page *page) { diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c index df4c052c6bd6..f300f060b3f3 100644 --- a/drivers/media/v4l2-core/videobuf-dma-sg.c +++ b/drivers/media/v4l2-core/videobuf-dma-sg.c @@ -349,7 +349,7 @@ int videobuf_dma_free(struct videobuf_dmabuf *dma) if (dma->pages) { for (i = 0; i < dma->nr_pages; i++) - page_cache_release(dma->pages[i]); + put_page(dma->pages[i]); kfree(dma->pages); dma->pages = NULL; } diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c index e8b933111e0d..9c677f3f3c26 100644 --- a/drivers/misc/ibmasm/ibmasmfs.c +++ b/drivers/misc/ibmasm/ibmasmfs.c @@ -116,8 +116,8 @@ static int ibmasmfs_fill_super (struct super_block *sb, void *data, int silent) { struct inode *root; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = IBMASMFS_MAGIC; sb->s_op = &ibmasmfs_s_ops; sb->s_time_gran = 1; diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index f42d9c4e4561..f84a4275ca29 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -728,7 +728,7 @@ static void qp_release_pages(struct page **pages, if (dirty) set_page_dirty(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); pages[i] = NULL; } } diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 1d94607611d8..6e4c55a4aab5 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -356,11 +356,11 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) * They have to set these according to their abilities. */ host->max_segs = 1; - host->max_seg_size = PAGE_CACHE_SIZE; + host->max_seg_size = PAGE_SIZE; - host->max_req_size = PAGE_CACHE_SIZE; + host->max_req_size = PAGE_SIZE; host->max_blk_size = 512; - host->max_blk_count = PAGE_CACHE_SIZE / 512; + host->max_blk_count = PAGE_SIZE / 512; return host; } diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index 8d870ce9f944..d9a655f47d41 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -1513,7 +1513,7 @@ static int sh_mmcif_probe(struct platform_device *pdev) mmc->caps |= pd->caps; mmc->max_segs = 32; mmc->max_blk_size = 512; - mmc->max_req_size = PAGE_CACHE_SIZE * mmc->max_segs; + mmc->max_req_size = PAGE_SIZE * mmc->max_segs; mmc->max_blk_count = mmc->max_req_size / mmc->max_blk_size; mmc->max_seg_size = mmc->max_req_size; diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c index 675435873823..7fb0c034dcb6 100644 --- a/drivers/mmc/host/tmio_mmc_dma.c +++ b/drivers/mmc/host/tmio_mmc_dma.c @@ -63,7 +63,7 @@ static void tmio_mmc_start_dma_rx(struct tmio_mmc_host *host) } } - if ((!aligned && (host->sg_len > 1 || sg->length > PAGE_CACHE_SIZE || + if ((!aligned && (host->sg_len > 1 || sg->length > PAGE_SIZE || (align & PAGE_MASK))) || !multiple) { ret = -EINVAL; goto pio; @@ -133,7 +133,7 @@ static void tmio_mmc_start_dma_tx(struct tmio_mmc_host *host) } } - if ((!aligned && (host->sg_len > 1 || sg->length > PAGE_CACHE_SIZE || + if ((!aligned && (host->sg_len > 1 || sg->length > PAGE_SIZE || (align & PAGE_MASK))) || !multiple) { ret = -EINVAL; goto pio; diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c index 03f6e74c1906..0521b4662748 100644 --- a/drivers/mmc/host/tmio_mmc_pio.c +++ b/drivers/mmc/host/tmio_mmc_pio.c @@ -1125,7 +1125,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host, mmc->caps2 |= pdata->capabilities2; mmc->max_segs = 32; mmc->max_blk_size = 512; - mmc->max_blk_count = (PAGE_CACHE_SIZE / mmc->max_blk_size) * + mmc->max_blk_count = (PAGE_SIZE / mmc->max_blk_size) * mmc->max_segs; mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count; mmc->max_seg_size = mmc->max_req_size; diff --git a/drivers/mmc/host/usdhi6rol0.c b/drivers/mmc/host/usdhi6rol0.c index b2752fe711f2..807c06e203c3 100644 --- a/drivers/mmc/host/usdhi6rol0.c +++ b/drivers/mmc/host/usdhi6rol0.c @@ -1789,7 +1789,7 @@ static int usdhi6_probe(struct platform_device *pdev) /* Set .max_segs to some random number. Feel free to adjust. */ mmc->max_segs = 32; mmc->max_blk_size = 512; - mmc->max_req_size = PAGE_CACHE_SIZE * mmc->max_segs; + mmc->max_req_size = PAGE_SIZE * mmc->max_segs; mmc->max_blk_count = mmc->max_req_size / mmc->max_blk_size; /* * Setting .max_seg_size to 1 page would simplify our page-mapping code, diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index e2c0057737e6..7c887f111a7d 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -75,7 +75,7 @@ static int _block2mtd_erase(struct block2mtd_dev *dev, loff_t to, size_t len) break; } - page_cache_release(page); + put_page(page); pages--; index++; } @@ -124,7 +124,7 @@ static int block2mtd_read(struct mtd_info *mtd, loff_t from, size_t len, return PTR_ERR(page); memcpy(buf, page_address(page) + offset, cpylen); - page_cache_release(page); + put_page(page); if (retlen) *retlen += cpylen; @@ -164,7 +164,7 @@ static int _block2mtd_write(struct block2mtd_dev *dev, const u_char *buf, unlock_page(page); balance_dirty_pages_ratelimited(mapping); } - page_cache_release(page); + put_page(page); if (retlen) *retlen += cpylen; diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c index 1fd519503bb1..a58169a28741 100644 --- a/drivers/mtd/nand/nandsim.c +++ b/drivers/mtd/nand/nandsim.c @@ -1339,7 +1339,7 @@ static void put_pages(struct nandsim *ns) int i; for (i = 0; i < ns->held_cnt; i++) - page_cache_release(ns->held_pages[i]); + put_page(ns->held_pages[i]); } /* Get page cache pages in advance to provide NOFS memory allocation */ @@ -1349,8 +1349,8 @@ static int get_pages(struct nandsim *ns, struct file *file, size_t count, loff_t struct page *page; struct address_space *mapping = file->f_mapping; - start_index = pos >> PAGE_CACHE_SHIFT; - end_index = (pos + count - 1) >> PAGE_CACHE_SHIFT; + start_index = pos >> PAGE_SHIFT; + end_index = (pos + count - 1) >> PAGE_SHIFT; if (end_index - start_index + 1 > NS_MAX_HELD_PAGES) return -EINVAL; ns->held_cnt = 0; diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index c32cbb593600..f068b6513cd2 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1204,7 +1204,7 @@ static int btt_rw_page(struct block_device *bdev, sector_t sector, { struct btt *btt = bdev->bd_disk->private_data; - btt_do_bvec(btt, NULL, page, PAGE_CACHE_SIZE, 0, rw, sector); + btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, rw, sector); page_endio(page, rw & WRITE, 0); return 0; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index cc31c6f1f88e..12c86fa80c5f 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -151,7 +151,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, struct pmem_device *pmem = bdev->bd_disk->private_data; int rc; - rc = pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector); + rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, rw, sector); if (rw & WRITE) wmb_pmem(); diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c index b48ac6300c79..a0e5260bd006 100644 --- a/drivers/oprofile/oprofilefs.c +++ b/drivers/oprofile/oprofilefs.c @@ -239,8 +239,8 @@ static int oprofilefs_fill_super(struct super_block *sb, void *data, int silent) { struct inode *root_inode; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = OPROFILEFS_MAGIC; sb->s_op = &s_ops; sb->s_time_gran = 1; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 5a5457ac9cdb..1bd0753f678a 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2891,7 +2891,7 @@ static int sd_revalidate_disk(struct gendisk *disk) if (sdkp->opt_xfer_blocks && sdkp->opt_xfer_blocks <= dev_max && sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS && - sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_CACHE_SIZE) + sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_SIZE) rw_max = q->limits.io_opt = sdkp->opt_xfer_blocks * sdp->sector_size; else diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 71c5138ddf94..dbf1882cfbac 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -4941,7 +4941,7 @@ static int sgl_map_user_pages(struct st_buffer *STbp, out_unmap: if (res > 0) { for (j=0; j < res; j++) - page_cache_release(pages[j]); + put_page(pages[j]); res = 0; } kfree(pages); @@ -4963,7 +4963,7 @@ static int sgl_unmap_user_pages(struct st_buffer *STbp, /* FIXME: cache flush missing for rw==READ * FIXME: call the correct reference counting function */ - page_cache_release(page); + put_page(page); } kfree(STbp->mapped_pages); STbp->mapped_pages = NULL; diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h index dab486261154..13335437c69c 100644 --- a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h +++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h @@ -88,7 +88,7 @@ do { \ } while (0) #ifndef LIBCFS_VMALLOC_SIZE -#define LIBCFS_VMALLOC_SIZE (2 << PAGE_CACHE_SHIFT) /* 2 pages */ +#define LIBCFS_VMALLOC_SIZE (2 << PAGE_SHIFT) /* 2 pages */ #endif #define LIBCFS_ALLOC_PRE(size, mask) \ diff --git a/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h b/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h index 0f2fd79e5ec8..837eb22749c3 100644 --- a/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h +++ b/drivers/staging/lustre/include/linux/libcfs/linux/linux-mem.h @@ -57,7 +57,7 @@ #include "../libcfs_cpu.h" #endif -#define CFS_PAGE_MASK (~((__u64)PAGE_CACHE_SIZE-1)) +#define CFS_PAGE_MASK (~((__u64)PAGE_SIZE-1)) #define page_index(p) ((p)->index) #define memory_pressure_get() (current->flags & PF_MEMALLOC) @@ -67,7 +67,7 @@ #if BITS_PER_LONG == 32 /* limit to lowmem on 32-bit systems */ #define NUM_CACHEPAGES \ - min(totalram_pages, 1UL << (30 - PAGE_CACHE_SHIFT) * 3 / 4) + min(totalram_pages, 1UL << (30 - PAGE_SHIFT) * 3 / 4) #else #define NUM_CACHEPAGES totalram_pages #endif diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib.c index 3e1f24e77f64..d4ce06d0aeeb 100644 --- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib.c +++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib.c @@ -291,7 +291,7 @@ ksocknal_lib_kiov_vmap(lnet_kiov_t *kiov, int niov, for (nob = i = 0; i < niov; i++) { if ((kiov[i].kiov_offset && i > 0) || - (kiov[i].kiov_offset + kiov[i].kiov_len != PAGE_CACHE_SIZE && i < niov - 1)) + (kiov[i].kiov_offset + kiov[i].kiov_len != PAGE_SIZE && i < niov - 1)) return NULL; pages[i] = kiov[i].kiov_page; diff --git a/drivers/staging/lustre/lnet/libcfs/debug.c b/drivers/staging/lustre/lnet/libcfs/debug.c index c90e5102fe06..c3d628bac5b8 100644 --- a/drivers/staging/lustre/lnet/libcfs/debug.c +++ b/drivers/staging/lustre/lnet/libcfs/debug.c @@ -517,7 +517,7 @@ int libcfs_debug_init(unsigned long bufsize) max = TCD_MAX_PAGES; } else { max = max / num_possible_cpus(); - max <<= (20 - PAGE_CACHE_SHIFT); + max <<= (20 - PAGE_SHIFT); } rc = cfs_tracefile_init(max); diff --git a/drivers/staging/lustre/lnet/libcfs/tracefile.c b/drivers/staging/lustre/lnet/libcfs/tracefile.c index ec3bc04bd89f..244eb89eef68 100644 --- a/drivers/staging/lustre/lnet/libcfs/tracefile.c +++ b/drivers/staging/lustre/lnet/libcfs/tracefile.c @@ -182,7 +182,7 @@ cfs_trace_get_tage_try(struct cfs_trace_cpu_data *tcd, unsigned long len) if (tcd->tcd_cur_pages > 0) { __LASSERT(!list_empty(&tcd->tcd_pages)); tage = cfs_tage_from_list(tcd->tcd_pages.prev); - if (tage->used + len <= PAGE_CACHE_SIZE) + if (tage->used + len <= PAGE_SIZE) return tage; } @@ -260,7 +260,7 @@ static struct cfs_trace_page *cfs_trace_get_tage(struct cfs_trace_cpu_data *tcd, * from here: this will lead to infinite recursion. */ - if (len > PAGE_CACHE_SIZE) { + if (len > PAGE_SIZE) { pr_err("cowardly refusing to write %lu bytes in a page\n", len); return NULL; } @@ -349,7 +349,7 @@ int libcfs_debug_vmsg2(struct libcfs_debug_msg_data *msgdata, for (i = 0; i < 2; i++) { tage = cfs_trace_get_tage(tcd, needed + known_size + 1); if (!tage) { - if (needed + known_size > PAGE_CACHE_SIZE) + if (needed + known_size > PAGE_SIZE) mask |= D_ERROR; cfs_trace_put_tcd(tcd); @@ -360,7 +360,7 @@ int libcfs_debug_vmsg2(struct libcfs_debug_msg_data *msgdata, string_buf = (char *)page_address(tage->page) + tage->used + known_size; - max_nob = PAGE_CACHE_SIZE - tage->used - known_size; + max_nob = PAGE_SIZE - tage->used - known_size; if (max_nob <= 0) { printk(KERN_EMERG "negative max_nob: %d\n", max_nob); @@ -424,7 +424,7 @@ int libcfs_debug_vmsg2(struct libcfs_debug_msg_data *msgdata, __LASSERT(debug_buf == string_buf); tage->used += needed; - __LASSERT(tage->used <= PAGE_CACHE_SIZE); + __LASSERT(tage->used <= PAGE_SIZE); console: if ((mask & libcfs_printk) == 0) { @@ -835,7 +835,7 @@ EXPORT_SYMBOL(cfs_trace_copyout_string); int cfs_trace_allocate_string_buffer(char **str, int nob) { - if (nob > 2 * PAGE_CACHE_SIZE) /* string must be "sensible" */ + if (nob > 2 * PAGE_SIZE) /* string must be "sensible" */ return -EINVAL; *str = kmalloc(nob, GFP_KERNEL | __GFP_ZERO); @@ -951,7 +951,7 @@ int cfs_trace_set_debug_mb(int mb) } mb /= num_possible_cpus(); - pages = mb << (20 - PAGE_CACHE_SHIFT); + pages = mb << (20 - PAGE_SHIFT); cfs_tracefile_write_lock(); @@ -977,7 +977,7 @@ int cfs_trace_get_debug_mb(void) cfs_tracefile_read_unlock(); - return (total_pages >> (20 - PAGE_CACHE_SHIFT)) + 1; + return (total_pages >> (20 - PAGE_SHIFT)) + 1; } static int tracefiled(void *arg) diff --git a/drivers/staging/lustre/lnet/libcfs/tracefile.h b/drivers/staging/lustre/lnet/libcfs/tracefile.h index 4c77f9044dd3..ac84e7f4c859 100644 --- a/drivers/staging/lustre/lnet/libcfs/tracefile.h +++ b/drivers/staging/lustre/lnet/libcfs/tracefile.h @@ -87,7 +87,7 @@ void libcfs_unregister_panic_notifier(void); extern int libcfs_panic_in_progress; int cfs_trace_max_debug_mb(void); -#define TCD_MAX_PAGES (5 << (20 - PAGE_CACHE_SHIFT)) +#define TCD_MAX_PAGES (5 << (20 - PAGE_SHIFT)) #define TCD_STOCK_PAGES (TCD_MAX_PAGES) #define CFS_TRACEFILE_SIZE (500 << 20) @@ -96,7 +96,7 @@ int cfs_trace_max_debug_mb(void); /* * Private declare for tracefile */ -#define TCD_MAX_PAGES (5 << (20 - PAGE_CACHE_SHIFT)) +#define TCD_MAX_PAGES (5 << (20 - PAGE_SHIFT)) #define TCD_STOCK_PAGES (TCD_MAX_PAGES) #define CFS_TRACEFILE_SIZE (500 << 20) @@ -257,7 +257,7 @@ do { \ do { \ __LASSERT(tage); \ __LASSERT(tage->page); \ - __LASSERT(tage->used <= PAGE_CACHE_SIZE); \ + __LASSERT(tage->used <= PAGE_SIZE); \ __LASSERT(page_count(tage->page) > 0); \ } while (0) diff --git a/drivers/staging/lustre/lnet/lnet/lib-md.c b/drivers/staging/lustre/lnet/lnet/lib-md.c index c74514f99f90..75d31217bf92 100644 --- a/drivers/staging/lustre/lnet/lnet/lib-md.c +++ b/drivers/staging/lustre/lnet/lnet/lib-md.c @@ -139,7 +139,7 @@ lnet_md_build(lnet_libmd_t *lmd, lnet_md_t *umd, int unlink) for (i = 0; i < (int)niov; i++) { /* We take the page pointer on trust */ if (lmd->md_iov.kiov[i].kiov_offset + - lmd->md_iov.kiov[i].kiov_len > PAGE_CACHE_SIZE) + lmd->md_iov.kiov[i].kiov_len > PAGE_SIZE) return -EINVAL; /* invalid length */ total_length += lmd->md_iov.kiov[i].kiov_len; diff --git a/drivers/staging/lustre/lnet/lnet/lib-move.c b/drivers/staging/lustre/lnet/lnet/lib-move.c index 0009a8de77d5..f19aa9320e34 100644 --- a/drivers/staging/lustre/lnet/lnet/lib-move.c +++ b/drivers/staging/lustre/lnet/lnet/lib-move.c @@ -549,12 +549,12 @@ lnet_extract_kiov(int dst_niov, lnet_kiov_t *dst, if (len <= frag_len) { dst->kiov_len = len; LASSERT(dst->kiov_offset + dst->kiov_len - <= PAGE_CACHE_SIZE); + <= PAGE_SIZE); return niov; } dst->kiov_len = frag_len; - LASSERT(dst->kiov_offset + dst->kiov_len <= PAGE_CACHE_SIZE); + LASSERT(dst->kiov_offset + dst->kiov_len <= PAGE_SIZE); len -= frag_len; dst++; @@ -887,7 +887,7 @@ lnet_msg2bufpool(lnet_msg_t *msg) rbp = &the_lnet.ln_rtrpools[cpt][0]; LASSERT(msg->msg_len <= LNET_MTU); - while (msg->msg_len > (unsigned int)rbp->rbp_npages * PAGE_CACHE_SIZE) { + while (msg->msg_len > (unsigned int)rbp->rbp_npages * PAGE_SIZE) { rbp++; LASSERT(rbp < &the_lnet.ln_rtrpools[cpt][LNET_NRBPOOLS]); } diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c index cc0c2753dd63..891fd59401d7 100644 --- a/drivers/staging/lustre/lnet/lnet/lib-socket.c +++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c @@ -166,9 +166,9 @@ lnet_ipif_enumerate(char ***namesp) nalloc = 16; /* first guess at max interfaces */ toobig = 0; for (;;) { - if (nalloc * sizeof(*ifr) > PAGE_CACHE_SIZE) { + if (nalloc * sizeof(*ifr) > PAGE_SIZE) { toobig = 1; - nalloc = PAGE_CACHE_SIZE / sizeof(*ifr); + nalloc = PAGE_SIZE / sizeof(*ifr); CWARN("Too many interfaces: only enumerating first %d\n", nalloc); } diff --git a/drivers/staging/lustre/lnet/lnet/router.c b/drivers/staging/lustre/lnet/lnet/router.c index 61459cf9d58f..b01dc424c514 100644 --- a/drivers/staging/lustre/lnet/lnet/router.c +++ b/drivers/staging/lustre/lnet/lnet/router.c @@ -27,8 +27,8 @@ #define LNET_NRB_SMALL_PAGES 1 #define LNET_NRB_LARGE_MIN 256 /* min value for each CPT */ #define LNET_NRB_LARGE (LNET_NRB_LARGE_MIN * 4) -#define LNET_NRB_LARGE_PAGES ((LNET_MTU + PAGE_CACHE_SIZE - 1) >> \ - PAGE_CACHE_SHIFT) +#define LNET_NRB_LARGE_PAGES ((LNET_MTU + PAGE_SIZE - 1) >> \ + PAGE_SHIFT) static char *forwarding = ""; module_param(forwarding, charp, 0444); @@ -1338,7 +1338,7 @@ lnet_new_rtrbuf(lnet_rtrbufpool_t *rbp, int cpt) return NULL; } - rb->rb_kiov[i].kiov_len = PAGE_CACHE_SIZE; + rb->rb_kiov[i].kiov_len = PAGE_SIZE; rb->rb_kiov[i].kiov_offset = 0; rb->rb_kiov[i].kiov_page = page; } diff --git a/drivers/staging/lustre/lnet/selftest/brw_test.c b/drivers/staging/lustre/lnet/selftest/brw_test.c index eebc92412061..dcb6e506f592 100644 --- a/drivers/staging/lustre/lnet/selftest/brw_test.c +++ b/drivers/staging/lustre/lnet/selftest/brw_test.c @@ -90,7 +90,7 @@ brw_client_init(sfw_test_instance_t *tsi) * NB: this is not going to work for variable page size, * but we have to keep it for compatibility */ - len = npg * PAGE_CACHE_SIZE; + len = npg * PAGE_SIZE; } else { test_bulk_req_v1_t *breq = &tsi->tsi_u.bulk_v1; @@ -104,7 +104,7 @@ brw_client_init(sfw_test_instance_t *tsi) opc = breq->blk_opc; flags = breq->blk_flags; len = breq->blk_len; - npg = (len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + npg = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; } if (npg > LNET_MAX_IOV || npg <= 0) @@ -167,13 +167,13 @@ brw_fill_page(struct page *pg, int pattern, __u64 magic) if (pattern == LST_BRW_CHECK_SIMPLE) { memcpy(addr, &magic, BRW_MSIZE); - addr += PAGE_CACHE_SIZE - BRW_MSIZE; + addr += PAGE_SIZE - BRW_MSIZE; memcpy(addr, &magic, BRW_MSIZE); return; } if (pattern == LST_BRW_CHECK_FULL) { - for (i = 0; i < PAGE_CACHE_SIZE / BRW_MSIZE; i++) + for (i = 0; i < PAGE_SIZE / BRW_MSIZE; i++) memcpy(addr + i * BRW_MSIZE, &magic, BRW_MSIZE); return; } @@ -198,7 +198,7 @@ brw_check_page(struct page *pg, int pattern, __u64 magic) if (data != magic) goto bad_data; - addr += PAGE_CACHE_SIZE - BRW_MSIZE; + addr += PAGE_SIZE - BRW_MSIZE; data = *((__u64 *)addr); if (data != magic) goto bad_data; @@ -207,7 +207,7 @@ brw_check_page(struct page *pg, int pattern, __u64 magic) } if (pattern == LST_BRW_CHECK_FULL) { - for (i = 0; i < PAGE_CACHE_SIZE / BRW_MSIZE; i++) { + for (i = 0; i < PAGE_SIZE / BRW_MSIZE; i++) { data = *(((__u64 *)addr) + i); if (data != magic) goto bad_data; @@ -278,7 +278,7 @@ brw_client_prep_rpc(sfw_test_unit_t *tsu, opc = breq->blk_opc; flags = breq->blk_flags; npg = breq->blk_npg; - len = npg * PAGE_CACHE_SIZE; + len = npg * PAGE_SIZE; } else { test_bulk_req_v1_t *breq = &tsi->tsi_u.bulk_v1; @@ -292,7 +292,7 @@ brw_client_prep_rpc(sfw_test_unit_t *tsu, opc = breq->blk_opc; flags = breq->blk_flags; len = breq->blk_len; - npg = (len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + npg = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; } rc = sfw_create_test_rpc(tsu, dest, sn->sn_features, npg, len, &rpc); @@ -463,10 +463,10 @@ brw_server_handle(struct srpc_server_rpc *rpc) reply->brw_status = EINVAL; return 0; } - npg = reqst->brw_len >> PAGE_CACHE_SHIFT; + npg = reqst->brw_len >> PAGE_SHIFT; } else { - npg = (reqst->brw_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + npg = (reqst->brw_len + PAGE_SIZE - 1) >> PAGE_SHIFT; } replymsg->msg_ses_feats = reqstmsg->msg_ses_feats; diff --git a/drivers/staging/lustre/lnet/selftest/conctl.c b/drivers/staging/lustre/lnet/selftest/conctl.c index 5c7cb72eac9a..79ee6c0bf7c1 100644 --- a/drivers/staging/lustre/lnet/selftest/conctl.c +++ b/drivers/staging/lustre/lnet/selftest/conctl.c @@ -743,7 +743,7 @@ static int lst_test_add_ioctl(lstio_test_args_t *args) if (args->lstio_tes_param && (args->lstio_tes_param_len <= 0 || args->lstio_tes_param_len > - PAGE_CACHE_SIZE - sizeof(lstcon_test_t))) + PAGE_SIZE - sizeof(lstcon_test_t))) return -EINVAL; LIBCFS_ALLOC(batch_name, args->lstio_tes_bat_nmlen + 1); @@ -819,7 +819,7 @@ lstcon_ioctl_entry(unsigned int cmd, struct libcfs_ioctl_hdr *hdr) opc = data->ioc_u32[0]; - if (data->ioc_plen1 > PAGE_CACHE_SIZE) + if (data->ioc_plen1 > PAGE_SIZE) return -EINVAL; LIBCFS_ALLOC(buf, data->ioc_plen1); diff --git a/drivers/staging/lustre/lnet/selftest/conrpc.c b/drivers/staging/lustre/lnet/selftest/conrpc.c index bcd78888f9cc..35a227d0c657 100644 --- a/drivers/staging/lustre/lnet/selftest/conrpc.c +++ b/drivers/staging/lustre/lnet/selftest/conrpc.c @@ -786,8 +786,8 @@ lstcon_bulkrpc_v0_prep(lst_test_bulk_param_t *param, srpc_test_reqst_t *req) test_bulk_req_t *brq = &req->tsr_u.bulk_v0; brq->blk_opc = param->blk_opc; - brq->blk_npg = (param->blk_size + PAGE_CACHE_SIZE - 1) / - PAGE_CACHE_SIZE; + brq->blk_npg = (param->blk_size + PAGE_SIZE - 1) / + PAGE_SIZE; brq->blk_flags = param->blk_flags; return 0; @@ -822,7 +822,7 @@ lstcon_testrpc_prep(lstcon_node_t *nd, int transop, unsigned feats, if (transop == LST_TRANS_TSBCLIADD) { npg = sfw_id_pages(test->tes_span); nob = !(feats & LST_FEAT_BULK_LEN) ? - npg * PAGE_CACHE_SIZE : + npg * PAGE_SIZE : sizeof(lnet_process_id_packed_t) * test->tes_span; } @@ -851,8 +851,8 @@ lstcon_testrpc_prep(lstcon_node_t *nd, int transop, unsigned feats, LASSERT(nob > 0); len = !(feats & LST_FEAT_BULK_LEN) ? - PAGE_CACHE_SIZE : - min_t(int, nob, PAGE_CACHE_SIZE); + PAGE_SIZE : + min_t(int, nob, PAGE_SIZE); nob -= len; bulk->bk_iovs[i].kiov_offset = 0; diff --git a/drivers/staging/lustre/lnet/selftest/framework.c b/drivers/staging/lustre/lnet/selftest/framework.c index 926c3970c498..e2c532399366 100644 --- a/drivers/staging/lustre/lnet/selftest/framework.c +++ b/drivers/staging/lustre/lnet/selftest/framework.c @@ -1161,7 +1161,7 @@ sfw_add_test(struct srpc_server_rpc *rpc) int len; if (!(sn->sn_features & LST_FEAT_BULK_LEN)) { - len = npg * PAGE_CACHE_SIZE; + len = npg * PAGE_SIZE; } else { len = sizeof(lnet_process_id_packed_t) * diff --git a/drivers/staging/lustre/lnet/selftest/rpc.c b/drivers/staging/lustre/lnet/selftest/rpc.c index 69be7d6f48fa..7d7748d96332 100644 --- a/drivers/staging/lustre/lnet/selftest/rpc.c +++ b/drivers/staging/lustre/lnet/selftest/rpc.c @@ -90,7 +90,7 @@ void srpc_set_counters(const srpc_counters_t *cnt) static int srpc_add_bulk_page(srpc_bulk_t *bk, struct page *pg, int i, int nob) { - nob = min_t(int, nob, PAGE_CACHE_SIZE); + nob = min_t(int, nob, PAGE_SIZE); LASSERT(nob > 0); LASSERT(i >= 0 && i < bk->bk_niov); diff --git a/drivers/staging/lustre/lnet/selftest/selftest.h b/drivers/staging/lustre/lnet/selftest/selftest.h index 288522d4d7b9..5321ddec9580 100644 --- a/drivers/staging/lustre/lnet/selftest/selftest.h +++ b/drivers/staging/lustre/lnet/selftest/selftest.h @@ -393,7 +393,7 @@ typedef struct sfw_test_instance { /* XXX: trailing (PAGE_CACHE_SIZE % sizeof(lnet_process_id_t)) bytes at * the end of pages are not used */ #define SFW_MAX_CONCUR LST_MAX_CONCUR -#define SFW_ID_PER_PAGE (PAGE_CACHE_SIZE / sizeof(lnet_process_id_packed_t)) +#define SFW_ID_PER_PAGE (PAGE_SIZE / sizeof(lnet_process_id_packed_t)) #define SFW_MAX_NDESTS (LNET_MAX_IOV * SFW_ID_PER_PAGE) #define sfw_id_pages(n) (((n) + SFW_ID_PER_PAGE - 1) / SFW_ID_PER_PAGE) diff --git a/drivers/staging/lustre/lustre/include/linux/lustre_patchless_compat.h b/drivers/staging/lustre/lustre/include/linux/lustre_patchless_compat.h index 33e0b99e1fb4..c6c7f54637fb 100644 --- a/drivers/staging/lustre/lustre/include/linux/lustre_patchless_compat.h +++ b/drivers/staging/lustre/lustre/include/linux/lustre_patchless_compat.h @@ -52,7 +52,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page) return; if (PagePrivate(page)) - page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE); + page->mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE); cancel_dirty_page(page); ClearPageMappedToDisk(page); diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h index da8bc6eadd13..1e2ebe5cc998 100644 --- a/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h +++ b/drivers/staging/lustre/lustre/include/lustre/lustre_idl.h @@ -1031,7 +1031,7 @@ static inline int lu_dirent_size(struct lu_dirent *ent) #define LU_PAGE_SIZE (1UL << LU_PAGE_SHIFT) #define LU_PAGE_MASK (~(LU_PAGE_SIZE - 1)) -#define LU_PAGE_COUNT (1 << (PAGE_CACHE_SHIFT - LU_PAGE_SHIFT)) +#define LU_PAGE_COUNT (1 << (PAGE_SHIFT - LU_PAGE_SHIFT)) /** @} lu_dir */ diff --git a/drivers/staging/lustre/lustre/include/lustre_mdc.h b/drivers/staging/lustre/lustre/include/lustre_mdc.h index df94f9f3bef2..af77eb359c43 100644 --- a/drivers/staging/lustre/lustre/include/lustre_mdc.h +++ b/drivers/staging/lustre/lustre/include/lustre_mdc.h @@ -155,12 +155,12 @@ static inline void mdc_update_max_ea_from_body(struct obd_export *exp, if (cli->cl_max_mds_easize < body->max_mdsize) { cli->cl_max_mds_easize = body->max_mdsize; cli->cl_default_mds_easize = - min_t(__u32, body->max_mdsize, PAGE_CACHE_SIZE); + min_t(__u32, body->max_mdsize, PAGE_SIZE); } if (cli->cl_max_mds_cookiesize < body->max_cookiesize) { cli->cl_max_mds_cookiesize = body->max_cookiesize; cli->cl_default_mds_cookiesize = - min_t(__u32, body->max_cookiesize, PAGE_CACHE_SIZE); + min_t(__u32, body->max_cookiesize, PAGE_SIZE); } } } diff --git a/drivers/staging/lustre/lustre/include/lustre_net.h b/drivers/staging/lustre/lustre/include/lustre_net.h index 4fa1a18b7d15..a5e9095fbf36 100644 --- a/drivers/staging/lustre/lustre/include/lustre_net.h +++ b/drivers/staging/lustre/lustre/include/lustre_net.h @@ -99,13 +99,13 @@ */ #define PTLRPC_MAX_BRW_BITS (LNET_MTU_BITS + PTLRPC_BULK_OPS_BITS) #define PTLRPC_MAX_BRW_SIZE (1 << PTLRPC_MAX_BRW_BITS) -#define PTLRPC_MAX_BRW_PAGES (PTLRPC_MAX_BRW_SIZE >> PAGE_CACHE_SHIFT) +#define PTLRPC_MAX_BRW_PAGES (PTLRPC_MAX_BRW_SIZE >> PAGE_SHIFT) #define ONE_MB_BRW_SIZE (1 << LNET_MTU_BITS) #define MD_MAX_BRW_SIZE (1 << LNET_MTU_BITS) -#define MD_MAX_BRW_PAGES (MD_MAX_BRW_SIZE >> PAGE_CACHE_SHIFT) +#define MD_MAX_BRW_PAGES (MD_MAX_BRW_SIZE >> PAGE_SHIFT) #define DT_MAX_BRW_SIZE PTLRPC_MAX_BRW_SIZE -#define DT_MAX_BRW_PAGES (DT_MAX_BRW_SIZE >> PAGE_CACHE_SHIFT) +#define DT_MAX_BRW_PAGES (DT_MAX_BRW_SIZE >> PAGE_SHIFT) #define OFD_MAX_BRW_SIZE (1 << LNET_MTU_BITS) /* When PAGE_SIZE is a constant, we can check our arithmetic here with cpp! */ diff --git a/drivers/staging/lustre/lustre/include/obd.h b/drivers/staging/lustre/lustre/include/obd.h index 4a0f2e8b19f6..f4167db65b5d 100644 --- a/drivers/staging/lustre/lustre/include/obd.h +++ b/drivers/staging/lustre/lustre/include/obd.h @@ -1318,7 +1318,7 @@ bad_format: static inline int cli_brw_size(struct obd_device *obd) { - return obd->u.cli.cl_max_pages_per_rpc << PAGE_CACHE_SHIFT; + return obd->u.cli.cl_max_pages_per_rpc << PAGE_SHIFT; } #endif /* __OBD_H */ diff --git a/drivers/staging/lustre/lustre/include/obd_support.h b/drivers/staging/lustre/lustre/include/obd_support.h index 225262fa67b6..f8ee3a3254ba 100644 --- a/drivers/staging/lustre/lustre/include/obd_support.h +++ b/drivers/staging/lustre/lustre/include/obd_support.h @@ -500,7 +500,7 @@ extern char obd_jobid_var[]; #ifdef POISON_BULK #define POISON_PAGE(page, val) do { \ - memset(kmap(page), val, PAGE_CACHE_SIZE); \ + memset(kmap(page), val, PAGE_SIZE); \ kunmap(page); \ } while (0) #else diff --git a/drivers/staging/lustre/lustre/lclient/lcommon_cl.c b/drivers/staging/lustre/lustre/lclient/lcommon_cl.c index aced41ab93a1..96141d17d07f 100644 --- a/drivers/staging/lustre/lustre/lclient/lcommon_cl.c +++ b/drivers/staging/lustre/lustre/lclient/lcommon_cl.c @@ -758,9 +758,9 @@ int ccc_prep_size(const struct lu_env *env, struct cl_object *obj, * --bug 17336 */ loff_t size = cl_isize_read(inode); - loff_t cur_index = start >> PAGE_CACHE_SHIFT; + loff_t cur_index = start >> PAGE_SHIFT; loff_t size_index = (size - 1) >> - PAGE_CACHE_SHIFT; + PAGE_SHIFT; if ((size == 0 && cur_index != 0) || size_index < cur_index) diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_lib.c b/drivers/staging/lustre/lustre/ldlm/ldlm_lib.c index b586d5a88d00..7dd7df59aa1f 100644 --- a/drivers/staging/lustre/lustre/ldlm/ldlm_lib.c +++ b/drivers/staging/lustre/lustre/ldlm/ldlm_lib.c @@ -307,8 +307,8 @@ int client_obd_setup(struct obd_device *obddev, struct lustre_cfg *lcfg) cli->cl_avail_grant = 0; /* FIXME: Should limit this for the sum of all cl_dirty_max. */ cli->cl_dirty_max = OSC_MAX_DIRTY_DEFAULT * 1024 * 1024; - if (cli->cl_dirty_max >> PAGE_CACHE_SHIFT > totalram_pages / 8) - cli->cl_dirty_max = totalram_pages << (PAGE_CACHE_SHIFT - 3); + if (cli->cl_dirty_max >> PAGE_SHIFT > totalram_pages / 8) + cli->cl_dirty_max = totalram_pages << (PAGE_SHIFT - 3); INIT_LIST_HEAD(&cli->cl_cache_waiters); INIT_LIST_HEAD(&cli->cl_loi_ready_list); INIT_LIST_HEAD(&cli->cl_loi_hp_ready_list); @@ -353,15 +353,15 @@ int client_obd_setup(struct obd_device *obddev, struct lustre_cfg *lcfg) * In the future this should likely be increased. LU-1431 */ cli->cl_max_pages_per_rpc = min_t(int, PTLRPC_MAX_BRW_PAGES, - LNET_MTU >> PAGE_CACHE_SHIFT); + LNET_MTU >> PAGE_SHIFT); if (!strcmp(name, LUSTRE_MDC_NAME)) { cli->cl_max_rpcs_in_flight = MDC_MAX_RIF_DEFAULT; - } else if (totalram_pages >> (20 - PAGE_CACHE_SHIFT) <= 128 /* MB */) { + } else if (totalram_pages >> (20 - PAGE_SHIFT) <= 128 /* MB */) { cli->cl_max_rpcs_in_flight = 2; - } else if (totalram_pages >> (20 - PAGE_CACHE_SHIFT) <= 256 /* MB */) { + } else if (totalram_pages >> (20 - PAGE_SHIFT) <= 256 /* MB */) { cli->cl_max_rpcs_in_flight = 3; - } else if (totalram_pages >> (20 - PAGE_CACHE_SHIFT) <= 512 /* MB */) { + } else if (totalram_pages >> (20 - PAGE_SHIFT) <= 512 /* MB */) { cli->cl_max_rpcs_in_flight = 4; } else { cli->cl_max_rpcs_in_flight = OSC_MAX_RIF_DEFAULT; diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c b/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c index 3e937b050203..b913ba9cf97c 100644 --- a/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c +++ b/drivers/staging/lustre/lustre/ldlm/ldlm_pool.c @@ -107,7 +107,7 @@ /* * 50 ldlm locks for 1MB of RAM. */ -#define LDLM_POOL_HOST_L ((NUM_CACHEPAGES >> (20 - PAGE_CACHE_SHIFT)) * 50) +#define LDLM_POOL_HOST_L ((NUM_CACHEPAGES >> (20 - PAGE_SHIFT)) * 50) /* * Maximal possible grant step plan in %. diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_request.c b/drivers/staging/lustre/lustre/ldlm/ldlm_request.c index c7904a96f9af..74e193e52cd6 100644 --- a/drivers/staging/lustre/lustre/ldlm/ldlm_request.c +++ b/drivers/staging/lustre/lustre/ldlm/ldlm_request.c @@ -546,7 +546,7 @@ static inline int ldlm_req_handles_avail(int req_size, int off) { int avail; - avail = min_t(int, LDLM_MAXREQSIZE, PAGE_CACHE_SIZE - 512) - req_size; + avail = min_t(int, LDLM_MAXREQSIZE, PAGE_SIZE - 512) - req_size; if (likely(avail >= 0)) avail /= (int)sizeof(struct lustre_handle); else diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c index 4e0a3e583330..a7c02e07fd75 100644 --- a/drivers/staging/lustre/lustre/llite/dir.c +++ b/drivers/staging/lustre/lustre/llite/dir.c @@ -153,7 +153,7 @@ static int ll_dir_filler(void *_hash, struct page *page0) struct page **page_pool; struct page *page; struct lu_dirpage *dp; - int max_pages = ll_i2sbi(inode)->ll_md_brw_size >> PAGE_CACHE_SHIFT; + int max_pages = ll_i2sbi(inode)->ll_md_brw_size >> PAGE_SHIFT; int nrdpgs = 0; /* number of pages read actually */ int npages; int i; @@ -193,8 +193,8 @@ static int ll_dir_filler(void *_hash, struct page *page0) if (body->valid & OBD_MD_FLSIZE) cl_isize_write(inode, body->size); - nrdpgs = (request->rq_bulk->bd_nob_transferred+PAGE_CACHE_SIZE-1) - >> PAGE_CACHE_SHIFT; + nrdpgs = (request->rq_bulk->bd_nob_transferred+PAGE_SIZE-1) + >> PAGE_SHIFT; SetPageUptodate(page0); } unlock_page(page0); @@ -209,7 +209,7 @@ static int ll_dir_filler(void *_hash, struct page *page0) page = page_pool[i]; if (rc < 0 || i >= nrdpgs) { - page_cache_release(page); + put_page(page); continue; } @@ -230,7 +230,7 @@ static int ll_dir_filler(void *_hash, struct page *page0) CDEBUG(D_VFSTRACE, "page %lu add to page cache failed: %d\n", offset, ret); } - page_cache_release(page); + put_page(page); } if (page_pool != &page0) @@ -247,7 +247,7 @@ void ll_release_page(struct page *page, int remove) truncate_complete_page(page->mapping, page); unlock_page(page); } - page_cache_release(page); + put_page(page); } /* @@ -273,7 +273,7 @@ static struct page *ll_dir_page_locate(struct inode *dir, __u64 *hash, if (found > 0 && !radix_tree_exceptional_entry(page)) { struct lu_dirpage *dp; - page_cache_get(page); + get_page(page); spin_unlock_irq(&mapping->tree_lock); /* * In contrast to find_lock_page() we are sure that directory @@ -313,7 +313,7 @@ static struct page *ll_dir_page_locate(struct inode *dir, __u64 *hash, page = NULL; } } else { - page_cache_release(page); + put_page(page); page = ERR_PTR(-EIO); } @@ -1507,7 +1507,7 @@ skip_lmm: st.st_gid = body->gid; st.st_rdev = body->rdev; st.st_size = body->size; - st.st_blksize = PAGE_CACHE_SIZE; + st.st_blksize = PAGE_SIZE; st.st_blocks = body->blocks; st.st_atime = body->atime; st.st_mtime = body->mtime; diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h index 3e1572cb457b..e3c0f1dd4d31 100644 --- a/drivers/staging/lustre/lustre/llite/llite_internal.h +++ b/drivers/staging/lustre/lustre/llite/llite_internal.h @@ -310,10 +310,10 @@ static inline struct ll_inode_info *ll_i2info(struct inode *inode) /* default to about 40meg of readahead on a given system. That much tied * up in 512k readahead requests serviced at 40ms each is about 1GB/s. */ -#define SBI_DEFAULT_READAHEAD_MAX (40UL << (20 - PAGE_CACHE_SHIFT)) +#define SBI_DEFAULT_READAHEAD_MAX (40UL << (20 - PAGE_SHIFT)) /* default to read-ahead full files smaller than 2MB on the second read */ -#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_CACHE_SHIFT)) +#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_SHIFT)) enum ra_stat { RA_STAT_HIT = 0, @@ -975,13 +975,13 @@ struct vm_area_struct *our_vma(struct mm_struct *mm, unsigned long addr, static inline void ll_invalidate_page(struct page *vmpage) { struct address_space *mapping = vmpage->mapping; - loff_t offset = vmpage->index << PAGE_CACHE_SHIFT; + loff_t offset = vmpage->index << PAGE_SHIFT; LASSERT(PageLocked(vmpage)); if (!mapping) return; - ll_teardown_mmaps(mapping, offset, offset + PAGE_CACHE_SIZE); + ll_teardown_mmaps(mapping, offset, offset + PAGE_SIZE); truncate_complete_page(mapping, vmpage); } diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c index 6d6bb33e3655..b57a992688a8 100644 --- a/drivers/staging/lustre/lustre/llite/llite_lib.c +++ b/drivers/staging/lustre/lustre/llite/llite_lib.c @@ -85,7 +85,7 @@ static struct ll_sb_info *ll_init_sbi(struct super_block *sb) si_meminfo(&si); pages = si.totalram - si.totalhigh; - if (pages >> (20 - PAGE_CACHE_SHIFT) < 512) + if (pages >> (20 - PAGE_SHIFT) < 512) lru_page_max = pages / 2; else lru_page_max = (pages / 4) * 3; @@ -272,12 +272,12 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, valid != CLIENT_CONNECT_MDT_REQD) { char *buf; - buf = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL); + buf = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!buf) { err = -ENOMEM; goto out_md_fid; } - obd_connect_flags2str(buf, PAGE_CACHE_SIZE, + obd_connect_flags2str(buf, PAGE_SIZE, valid ^ CLIENT_CONNECT_MDT_REQD, ","); LCONSOLE_ERROR_MSG(0x170, "Server %s does not support feature(s) needed for correct operation of this client (%s). Please upgrade server or downgrade client.\n", sbi->ll_md_exp->exp_obd->obd_name, buf); @@ -335,7 +335,7 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt, if (data->ocd_connect_flags & OBD_CONNECT_BRW_SIZE) sbi->ll_md_brw_size = data->ocd_brw_size; else - sbi->ll_md_brw_size = PAGE_CACHE_SIZE; + sbi->ll_md_brw_size = PAGE_SIZE; if (data->ocd_connect_flags & OBD_CONNECT_LAYOUTLOCK) { LCONSOLE_INFO("Layout lock feature supported.\n"); diff --git a/drivers/staging/lustre/lustre/llite/llite_mmap.c b/drivers/staging/lustre/lustre/llite/llite_mmap.c index 69445a9f2011..5b484e62ffd0 100644 --- a/drivers/staging/lustre/lustre/llite/llite_mmap.c +++ b/drivers/staging/lustre/lustre/llite/llite_mmap.c @@ -58,7 +58,7 @@ void policy_from_vma(ldlm_policy_data_t *policy, size_t count) { policy->l_extent.start = ((addr - vma->vm_start) & CFS_PAGE_MASK) + - (vma->vm_pgoff << PAGE_CACHE_SHIFT); + (vma->vm_pgoff << PAGE_SHIFT); policy->l_extent.end = (policy->l_extent.start + count - 1) | ~CFS_PAGE_MASK; } @@ -321,7 +321,7 @@ static int ll_fault0(struct vm_area_struct *vma, struct vm_fault *vmf) vmpage = vio->u.fault.ft_vmpage; if (result != 0 && vmpage) { - page_cache_release(vmpage); + put_page(vmpage); vmf->page = NULL; } } @@ -360,7 +360,7 @@ restart: lock_page(vmpage); if (unlikely(!vmpage->mapping)) { /* unlucky */ unlock_page(vmpage); - page_cache_release(vmpage); + put_page(vmpage); vmf->page = NULL; if (!printed && ++count > 16) { @@ -457,7 +457,7 @@ int ll_teardown_mmaps(struct address_space *mapping, __u64 first, __u64 last) LASSERTF(last > first, "last %llu first %llu\n", last, first); if (mapping_mapped(mapping)) { rc = 0; - unmap_mapping_range(mapping, first + PAGE_CACHE_SIZE - 1, + unmap_mapping_range(mapping, first + PAGE_SIZE - 1, last - first + 1, 0); } diff --git a/drivers/staging/lustre/lustre/llite/lloop.c b/drivers/staging/lustre/lustre/llite/lloop.c index b725fc16cf49..f169c0db63b4 100644 --- a/drivers/staging/lustre/lustre/llite/lloop.c +++ b/drivers/staging/lustre/lustre/llite/lloop.c @@ -218,7 +218,7 @@ static int do_bio_lustrebacked(struct lloop_device *lo, struct bio *head) offset = (pgoff_t)(bio->bi_iter.bi_sector << 9) + lo->lo_offset; bio_for_each_segment(bvec, bio, iter) { BUG_ON(bvec.bv_offset != 0); - BUG_ON(bvec.bv_len != PAGE_CACHE_SIZE); + BUG_ON(bvec.bv_len != PAGE_SIZE); pages[page_count] = bvec.bv_page; offsets[page_count] = offset; @@ -232,7 +232,7 @@ static int do_bio_lustrebacked(struct lloop_device *lo, struct bio *head) (rw == WRITE) ? LPROC_LL_BRW_WRITE : LPROC_LL_BRW_READ, page_count); - pvec->ldp_size = page_count << PAGE_CACHE_SHIFT; + pvec->ldp_size = page_count << PAGE_SHIFT; pvec->ldp_nr = page_count; /* FIXME: in ll_direct_rw_pages, it has to allocate many cl_page{}s to @@ -507,7 +507,7 @@ static int loop_set_fd(struct lloop_device *lo, struct file *unused, set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0); - lo->lo_blocksize = PAGE_CACHE_SIZE; + lo->lo_blocksize = PAGE_SIZE; lo->lo_device = bdev; lo->lo_flags = lo_flags; lo->lo_backing_file = file; @@ -525,11 +525,11 @@ static int loop_set_fd(struct lloop_device *lo, struct file *unused, lo->lo_queue->queuedata = lo; /* queue parameters */ - CLASSERT(PAGE_CACHE_SIZE < (1 << (sizeof(unsigned short) * 8))); + CLASSERT(PAGE_SIZE < (1 << (sizeof(unsigned short) * 8))); blk_queue_logical_block_size(lo->lo_queue, - (unsigned short)PAGE_CACHE_SIZE); + (unsigned short)PAGE_SIZE); blk_queue_max_hw_sectors(lo->lo_queue, - LLOOP_MAX_SEGMENTS << (PAGE_CACHE_SHIFT - 9)); + LLOOP_MAX_SEGMENTS << (PAGE_SHIFT - 9)); blk_queue_max_segments(lo->lo_queue, LLOOP_MAX_SEGMENTS); set_capacity(disks[lo->lo_number], size); diff --git a/drivers/staging/lustre/lustre/llite/lproc_llite.c b/drivers/staging/lustre/lustre/llite/lproc_llite.c index 45941a6600fe..27ab1261400e 100644 --- a/drivers/staging/lustre/lustre/llite/lproc_llite.c +++ b/drivers/staging/lustre/lustre/llite/lproc_llite.c @@ -233,7 +233,7 @@ static ssize_t max_read_ahead_mb_show(struct kobject *kobj, pages_number = sbi->ll_ra_info.ra_max_pages; spin_unlock(&sbi->ll_lock); - mult = 1 << (20 - PAGE_CACHE_SHIFT); + mult = 1 << (20 - PAGE_SHIFT); return lprocfs_read_frac_helper(buf, PAGE_SIZE, pages_number, mult); } @@ -251,12 +251,12 @@ static ssize_t max_read_ahead_mb_store(struct kobject *kobj, if (rc) return rc; - pages_number *= 1 << (20 - PAGE_CACHE_SHIFT); /* MB -> pages */ + pages_number *= 1 << (20 - PAGE_SHIFT); /* MB -> pages */ if (pages_number > totalram_pages / 2) { CERROR("can't set file readahead more than %lu MB\n", - totalram_pages >> (20 - PAGE_CACHE_SHIFT + 1)); /*1/2 of RAM*/ + totalram_pages >> (20 - PAGE_SHIFT + 1)); /*1/2 of RAM*/ return -ERANGE; } @@ -281,7 +281,7 @@ static ssize_t max_read_ahead_per_file_mb_show(struct kobject *kobj, pages_number = sbi->ll_ra_info.ra_max_pages_per_file; spin_unlock(&sbi->ll_lock); - mult = 1 << (20 - PAGE_CACHE_SHIFT); + mult = 1 << (20 - PAGE_SHIFT); return lprocfs_read_frac_helper(buf, PAGE_SIZE, pages_number, mult); } @@ -326,7 +326,7 @@ static ssize_t max_read_ahead_whole_mb_show(struct kobject *kobj, pages_number = sbi->ll_ra_info.ra_max_read_ahead_whole_pages; spin_unlock(&sbi->ll_lock); - mult = 1 << (20 - PAGE_CACHE_SHIFT); + mult = 1 << (20 - PAGE_SHIFT); return lprocfs_read_frac_helper(buf, PAGE_SIZE, pages_number, mult); } @@ -349,7 +349,7 @@ static ssize_t max_read_ahead_whole_mb_store(struct kobject *kobj, */ if (pages_number > sbi->ll_ra_info.ra_max_pages_per_file) { CERROR("can't set max_read_ahead_whole_mb more than max_read_ahead_per_file_mb: %lu\n", - sbi->ll_ra_info.ra_max_pages_per_file >> (20 - PAGE_CACHE_SHIFT)); + sbi->ll_ra_info.ra_max_pages_per_file >> (20 - PAGE_SHIFT)); return -ERANGE; } @@ -366,7 +366,7 @@ static int ll_max_cached_mb_seq_show(struct seq_file *m, void *v) struct super_block *sb = m->private; struct ll_sb_info *sbi = ll_s2sbi(sb); struct cl_client_cache *cache = &sbi->ll_cache; - int shift = 20 - PAGE_CACHE_SHIFT; + int shift = 20 - PAGE_SHIFT; int max_cached_mb; int unused_mb; @@ -405,7 +405,7 @@ static ssize_t ll_max_cached_mb_seq_write(struct file *file, return -EFAULT; kernbuf[count] = 0; - mult = 1 << (20 - PAGE_CACHE_SHIFT); + mult = 1 << (20 - PAGE_SHIFT); buffer += lprocfs_find_named_value(kernbuf, "max_cached_mb:", &count) - kernbuf; rc = lprocfs_write_frac_helper(buffer, count, &pages_number, mult); @@ -415,7 +415,7 @@ static ssize_t ll_max_cached_mb_seq_write(struct file *file, if (pages_number < 0 || pages_number > totalram_pages) { CERROR("%s: can't set max cache more than %lu MB\n", ll_get_fsname(sb, NULL, 0), - totalram_pages >> (20 - PAGE_CACHE_SHIFT)); + totalram_pages >> (20 - PAGE_SHIFT)); return -ERANGE; } diff --git a/drivers/staging/lustre/lustre/llite/rw.c b/drivers/staging/lustre/lustre/llite/rw.c index 34614acf3f8e..4c7250ab54e6 100644 --- a/drivers/staging/lustre/lustre/llite/rw.c +++ b/drivers/staging/lustre/lustre/llite/rw.c @@ -146,10 +146,10 @@ static struct ll_cl_context *ll_cl_init(struct file *file, */ io->ci_lockreq = CILR_NEVER; - pos = vmpage->index << PAGE_CACHE_SHIFT; + pos = vmpage->index << PAGE_SHIFT; /* Create a temp IO to serve write. */ - result = cl_io_rw_init(env, io, CIT_WRITE, pos, PAGE_CACHE_SIZE); + result = cl_io_rw_init(env, io, CIT_WRITE, pos, PAGE_SIZE); if (result == 0) { cio->cui_fd = LUSTRE_FPRIVATE(file); cio->cui_iter = NULL; @@ -498,7 +498,7 @@ static int ll_read_ahead_page(const struct lu_env *env, struct cl_io *io, } if (rc != 1) unlock_page(vmpage); - page_cache_release(vmpage); + put_page(vmpage); } else { which = RA_STAT_FAILED_GRAB_PAGE; msg = "g_c_p_n failed"; @@ -527,7 +527,7 @@ static int ll_read_ahead_page(const struct lu_env *env, struct cl_io *io, * and max_read_ahead_per_file_mb otherwise the readahead budget can be used * up quickly which will affect read performance significantly. See LU-2816 */ -#define RAS_INCREASE_STEP(inode) (ONE_MB_BRW_SIZE >> PAGE_CACHE_SHIFT) +#define RAS_INCREASE_STEP(inode) (ONE_MB_BRW_SIZE >> PAGE_SHIFT) static inline int stride_io_mode(struct ll_readahead_state *ras) { @@ -739,7 +739,7 @@ int ll_readahead(const struct lu_env *env, struct cl_io *io, end = rpc_boundary; /* Truncate RA window to end of file */ - end = min(end, (unsigned long)((kms - 1) >> PAGE_CACHE_SHIFT)); + end = min(end, (unsigned long)((kms - 1) >> PAGE_SHIFT)); ras->ras_next_readahead = max(end, end + 1); RAS_CDEBUG(ras); @@ -776,7 +776,7 @@ int ll_readahead(const struct lu_env *env, struct cl_io *io, if (reserved != 0) ll_ra_count_put(ll_i2sbi(inode), reserved); - if (ra_end == end + 1 && ra_end == (kms >> PAGE_CACHE_SHIFT)) + if (ra_end == end + 1 && ra_end == (kms >> PAGE_SHIFT)) ll_ra_stats_inc(mapping, RA_STAT_EOF); /* if we didn't get to the end of the region we reserved from @@ -985,8 +985,8 @@ void ras_update(struct ll_sb_info *sbi, struct inode *inode, if (ras->ras_requests == 2 && !ras->ras_request_index) { __u64 kms_pages; - kms_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + kms_pages = (i_size_read(inode) + PAGE_SIZE - 1) >> + PAGE_SHIFT; CDEBUG(D_READA, "kmsp %llu mwp %lu mp %lu\n", kms_pages, ra->ra_max_read_ahead_whole_pages, ra->ra_max_pages_per_file); @@ -1173,7 +1173,7 @@ int ll_writepage(struct page *vmpage, struct writeback_control *wbc) * PageWriteback or clean the page. */ result = cl_sync_file_range(inode, offset, - offset + PAGE_CACHE_SIZE - 1, + offset + PAGE_SIZE - 1, CL_FSYNC_LOCAL, 1); if (result > 0) { /* actually we may have written more than one page. @@ -1211,7 +1211,7 @@ int ll_writepages(struct address_space *mapping, struct writeback_control *wbc) int ignore_layout = 0; if (wbc->range_cyclic) { - start = mapping->writeback_index << PAGE_CACHE_SHIFT; + start = mapping->writeback_index << PAGE_SHIFT; end = OBD_OBJECT_EOF; } else { start = wbc->range_start; @@ -1241,7 +1241,7 @@ int ll_writepages(struct address_space *mapping, struct writeback_control *wbc) if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) { if (end == OBD_OBJECT_EOF) end = i_size_read(inode); - mapping->writeback_index = (end >> PAGE_CACHE_SHIFT) + 1; + mapping->writeback_index = (end >> PAGE_SHIFT) + 1; } return result; } diff --git a/drivers/staging/lustre/lustre/llite/rw26.c b/drivers/staging/lustre/lustre/llite/rw26.c index 7a5db67bc680..69aa15e8e3ef 100644 --- a/drivers/staging/lustre/lustre/llite/rw26.c +++ b/drivers/staging/lustre/lustre/llite/rw26.c @@ -87,7 +87,7 @@ static void ll_invalidatepage(struct page *vmpage, unsigned int offset, * below because they are run with page locked and all our io is * happening with locked page too */ - if (offset == 0 && length == PAGE_CACHE_SIZE) { + if (offset == 0 && length == PAGE_SIZE) { env = cl_env_get(&refcheck); if (!IS_ERR(env)) { inode = vmpage->mapping->host; @@ -193,8 +193,8 @@ static inline int ll_get_user_pages(int rw, unsigned long user_addr, return -EFBIG; } - *max_pages = (user_addr + size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - *max_pages -= user_addr >> PAGE_CACHE_SHIFT; + *max_pages = (user_addr + size + PAGE_SIZE - 1) >> PAGE_SHIFT; + *max_pages -= user_addr >> PAGE_SHIFT; *pages = libcfs_kvzalloc(*max_pages * sizeof(**pages), GFP_NOFS); if (*pages) { @@ -217,7 +217,7 @@ static void ll_free_user_pages(struct page **pages, int npages, int do_dirty) for (i = 0; i < npages; i++) { if (do_dirty) set_page_dirty_lock(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); } kvfree(pages); } @@ -357,7 +357,7 @@ static ssize_t ll_direct_IO_26_seg(const struct lu_env *env, struct cl_io *io, * up to 22MB for 128kB kmalloc and up to 682MB for 4MB kmalloc. */ #define MAX_DIO_SIZE ((KMALLOC_MAX_SIZE / sizeof(struct brw_page) * \ - PAGE_CACHE_SIZE) & ~(DT_MAX_BRW_SIZE - 1)) + PAGE_SIZE) & ~(DT_MAX_BRW_SIZE - 1)) static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter, loff_t file_offset) { @@ -382,8 +382,8 @@ static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter, CDEBUG(D_VFSTRACE, "VFS Op:inode=%lu/%u(%p), size=%zd (max %lu), offset=%lld=%llx, pages %zd (max %lu)\n", inode->i_ino, inode->i_generation, inode, count, MAX_DIO_SIZE, - file_offset, file_offset, count >> PAGE_CACHE_SHIFT, - MAX_DIO_SIZE >> PAGE_CACHE_SHIFT); + file_offset, file_offset, count >> PAGE_SHIFT, + MAX_DIO_SIZE >> PAGE_SHIFT); /* Check that all user buffers are aligned as well */ if (iov_iter_alignment(iter) & ~CFS_PAGE_MASK) @@ -432,8 +432,8 @@ static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter, * page worth of page pointers = 4MB on i386. */ if (result == -ENOMEM && - size > (PAGE_CACHE_SIZE / sizeof(*pages)) * - PAGE_CACHE_SIZE) { + size > (PAGE_SIZE / sizeof(*pages)) * + PAGE_SIZE) { size = ((((size / 2) - 1) | ~CFS_PAGE_MASK) + 1) & CFS_PAGE_MASK; @@ -474,10 +474,10 @@ static int ll_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int rc; - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned from = pos & (PAGE_SIZE - 1); page = grab_cache_page_write_begin(mapping, index, flags); if (!page) @@ -488,7 +488,7 @@ static int ll_write_begin(struct file *file, struct address_space *mapping, rc = ll_prepare_write(file, page, from, from + len); if (rc) { unlock_page(page); - page_cache_release(page); + put_page(page); } return rc; } @@ -497,12 +497,12 @@ static int ll_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned from = pos & (PAGE_SIZE - 1); int rc; rc = ll_commit_write(file, page, from, from + copied); unlock_page(page); - page_cache_release(page); + put_page(page); return rc ?: copied; } diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c index fb0c26ee7ff3..75d4df71cab8 100644 --- a/drivers/staging/lustre/lustre/llite/vvp_io.c +++ b/drivers/staging/lustre/lustre/llite/vvp_io.c @@ -514,7 +514,7 @@ static int vvp_io_read_start(const struct lu_env *env, /* * XXX: explicit PAGE_CACHE_SIZE */ - bead->lrr_count = cl_index(obj, tot + PAGE_CACHE_SIZE - 1); + bead->lrr_count = cl_index(obj, tot + PAGE_SIZE - 1); ll_ra_read_in(file, bead); } @@ -959,7 +959,7 @@ static int vvp_io_prepare_write(const struct lu_env *env, * We're completely overwriting an existing page, so _don't_ * set it up to date until commit_write */ - if (from == 0 && to == PAGE_CACHE_SIZE) { + if (from == 0 && to == PAGE_SIZE) { CL_PAGE_HEADER(D_PAGE, env, pg, "full page write\n"); POISON_PAGE(page, 0x11); } else @@ -1022,7 +1022,7 @@ static int vvp_io_commit_write(const struct lu_env *env, set_page_dirty(vmpage); vvp_write_pending(cl2ccc(obj), cp); } else if (result == -EDQUOT) { - pgoff_t last_index = i_size_read(inode) >> PAGE_CACHE_SHIFT; + pgoff_t last_index = i_size_read(inode) >> PAGE_SHIFT; bool need_clip = true; /* @@ -1040,7 +1040,7 @@ static int vvp_io_commit_write(const struct lu_env *env, * being. */ if (last_index > pg->cp_index) { - to = PAGE_CACHE_SIZE; + to = PAGE_SIZE; need_clip = false; } else if (last_index == pg->cp_index) { int size_to = i_size_read(inode) & ~CFS_PAGE_MASK; diff --git a/drivers/staging/lustre/lustre/llite/vvp_page.c b/drivers/staging/lustre/lustre/llite/vvp_page.c index 850bae734075..33ca3eb34965 100644 --- a/drivers/staging/lustre/lustre/llite/vvp_page.c +++ b/drivers/staging/lustre/lustre/llite/vvp_page.c @@ -57,7 +57,7 @@ static void vvp_page_fini_common(struct ccc_page *cp) struct page *vmpage = cp->cpg_page; LASSERT(vmpage); - page_cache_release(vmpage); + put_page(vmpage); } static void vvp_page_fini(const struct lu_env *env, @@ -164,12 +164,12 @@ static int vvp_page_unmap(const struct lu_env *env, LASSERT(vmpage); LASSERT(PageLocked(vmpage)); - offset = vmpage->index << PAGE_CACHE_SHIFT; + offset = vmpage->index << PAGE_SHIFT; /* * XXX is it safe to call this with the page lock held? */ - ll_teardown_mmaps(vmpage->mapping, offset, offset + PAGE_CACHE_SIZE); + ll_teardown_mmaps(vmpage->mapping, offset, offset + PAGE_SIZE); return 0; } @@ -537,7 +537,7 @@ int vvp_page_init(const struct lu_env *env, struct cl_object *obj, CLOBINVRNT(env, obj, ccc_object_invariant(obj)); cpg->cpg_page = vmpage; - page_cache_get(vmpage); + get_page(vmpage); INIT_LIST_HEAD(&cpg->cpg_pending_linkage); if (page->cp_type == CPT_CACHEABLE) { diff --git a/drivers/staging/lustre/lustre/lmv/lmv_obd.c b/drivers/staging/lustre/lustre/lmv/lmv_obd.c index 0f776cf8a5aa..ce7e8b70dd44 100644 --- a/drivers/staging/lustre/lustre/lmv/lmv_obd.c +++ b/drivers/staging/lustre/lustre/lmv/lmv_obd.c @@ -2129,8 +2129,8 @@ static int lmv_readpage(struct obd_export *exp, struct md_op_data *op_data, if (rc != 0) return rc; - ncfspgs = ((*request)->rq_bulk->bd_nob_transferred + PAGE_CACHE_SIZE - 1) - >> PAGE_CACHE_SHIFT; + ncfspgs = ((*request)->rq_bulk->bd_nob_transferred + PAGE_SIZE - 1) + >> PAGE_SHIFT; nlupgs = (*request)->rq_bulk->bd_nob_transferred >> LU_PAGE_SHIFT; LASSERT(!((*request)->rq_bulk->bd_nob_transferred & ~LU_PAGE_MASK)); LASSERT(ncfspgs > 0 && ncfspgs <= op_data->op_npages); diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c index 55dd8ef9525b..b91d3ff18b02 100644 --- a/drivers/staging/lustre/lustre/mdc/mdc_request.c +++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c @@ -1002,10 +1002,10 @@ restart_bulk: /* NB req now owns desc and will free it when it gets freed */ for (i = 0; i < op_data->op_npages; i++) - ptlrpc_prep_bulk_page_pin(desc, pages[i], 0, PAGE_CACHE_SIZE); + ptlrpc_prep_bulk_page_pin(desc, pages[i], 0, PAGE_SIZE); mdc_readdir_pack(req, op_data->op_offset, - PAGE_CACHE_SIZE * op_data->op_npages, + PAGE_SIZE * op_data->op_npages, &op_data->op_fid1); ptlrpc_request_set_replen(req); @@ -1037,7 +1037,7 @@ restart_bulk: if (req->rq_bulk->bd_nob_transferred & ~LU_PAGE_MASK) { CERROR("Unexpected # bytes transferred: %d (%ld expected)\n", req->rq_bulk->bd_nob_transferred, - PAGE_CACHE_SIZE * op_data->op_npages); + PAGE_SIZE * op_data->op_npages); ptlrpc_req_finished(req); return -EPROTO; } diff --git a/drivers/staging/lustre/lustre/mgc/mgc_request.c b/drivers/staging/lustre/lustre/mgc/mgc_request.c index b7dc87248032..3924b095bfb0 100644 --- a/drivers/staging/lustre/lustre/mgc/mgc_request.c +++ b/drivers/staging/lustre/lustre/mgc/mgc_request.c @@ -1113,7 +1113,7 @@ static int mgc_import_event(struct obd_device *obd, } enum { - CONFIG_READ_NRPAGES_INIT = 1 << (20 - PAGE_CACHE_SHIFT), + CONFIG_READ_NRPAGES_INIT = 1 << (20 - PAGE_SHIFT), CONFIG_READ_NRPAGES = 4 }; @@ -1137,19 +1137,19 @@ static int mgc_apply_recover_logs(struct obd_device *mgc, LASSERT(cfg->cfg_instance); LASSERT(cfg->cfg_sb == cfg->cfg_instance); - inst = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL); + inst = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!inst) return -ENOMEM; - pos = snprintf(inst, PAGE_CACHE_SIZE, "%p", cfg->cfg_instance); - if (pos >= PAGE_CACHE_SIZE) { + pos = snprintf(inst, PAGE_SIZE, "%p", cfg->cfg_instance); + if (pos >= PAGE_SIZE) { kfree(inst); return -E2BIG; } ++pos; buf = inst + pos; - bufsz = PAGE_CACHE_SIZE - pos; + bufsz = PAGE_SIZE - pos; while (datalen > 0) { int entry_len = sizeof(*entry); @@ -1181,7 +1181,7 @@ static int mgc_apply_recover_logs(struct obd_device *mgc, /* Keep this swab for normal mixed endian handling. LU-1644 */ if (mne_swab) lustre_swab_mgs_nidtbl_entry(entry); - if (entry->mne_length > PAGE_CACHE_SIZE) { + if (entry->mne_length > PAGE_SIZE) { CERROR("MNE too large (%u)\n", entry->mne_length); break; } @@ -1371,7 +1371,7 @@ again: } body->mcb_offset = cfg->cfg_last_idx + 1; body->mcb_type = cld->cld_type; - body->mcb_bits = PAGE_CACHE_SHIFT; + body->mcb_bits = PAGE_SHIFT; body->mcb_units = nrpages; /* allocate bulk transfer descriptor */ @@ -1383,7 +1383,7 @@ again: } for (i = 0; i < nrpages; i++) - ptlrpc_prep_bulk_page_pin(desc, pages[i], 0, PAGE_CACHE_SIZE); + ptlrpc_prep_bulk_page_pin(desc, pages[i], 0, PAGE_SIZE); ptlrpc_request_set_replen(req); rc = ptlrpc_queue_wait(req); @@ -1411,7 +1411,7 @@ again: goto out; } - if (ealen > nrpages << PAGE_CACHE_SHIFT) { + if (ealen > nrpages << PAGE_SHIFT) { rc = -EINVAL; goto out; } @@ -1439,7 +1439,7 @@ again: ptr = kmap(pages[i]); rc2 = mgc_apply_recover_logs(obd, cld, res->mcr_offset, ptr, - min_t(int, ealen, PAGE_CACHE_SIZE), + min_t(int, ealen, PAGE_SIZE), mne_swab); kunmap(pages[i]); if (rc2 < 0) { @@ -1448,7 +1448,7 @@ again: break; } - ealen -= PAGE_CACHE_SIZE; + ealen -= PAGE_SIZE; } out: diff --git a/drivers/staging/lustre/lustre/obdclass/cl_page.c b/drivers/staging/lustre/lustre/obdclass/cl_page.c index 231a2f26c693..394580016638 100644 --- a/drivers/staging/lustre/lustre/obdclass/cl_page.c +++ b/drivers/staging/lustre/lustre/obdclass/cl_page.c @@ -1477,7 +1477,7 @@ loff_t cl_offset(const struct cl_object *obj, pgoff_t idx) /* * XXX for now. */ - return (loff_t)idx << PAGE_CACHE_SHIFT; + return (loff_t)idx << PAGE_SHIFT; } EXPORT_SYMBOL(cl_offset); @@ -1489,13 +1489,13 @@ pgoff_t cl_index(const struct cl_object *obj, loff_t offset) /* * XXX for now. */ - return offset >> PAGE_CACHE_SHIFT; + return offset >> PAGE_SHIFT; } EXPORT_SYMBOL(cl_index); int cl_page_size(const struct cl_object *obj) { - return 1 << PAGE_CACHE_SHIFT; + return 1 << PAGE_SHIFT; } EXPORT_SYMBOL(cl_page_size); diff --git a/drivers/staging/lustre/lustre/obdclass/class_obd.c b/drivers/staging/lustre/lustre/obdclass/class_obd.c index 1a938e1376f9..c2cf015962dd 100644 --- a/drivers/staging/lustre/lustre/obdclass/class_obd.c +++ b/drivers/staging/lustre/lustre/obdclass/class_obd.c @@ -461,9 +461,9 @@ static int obd_init_checks(void) CWARN("LPD64 wrong length! strlen(%s)=%d != 2\n", buf, len); ret = -EINVAL; } - if ((u64val & ~CFS_PAGE_MASK) >= PAGE_CACHE_SIZE) { + if ((u64val & ~CFS_PAGE_MASK) >= PAGE_SIZE) { CWARN("mask failed: u64val %llu >= %llu\n", u64val, - (__u64)PAGE_CACHE_SIZE); + (__u64)PAGE_SIZE); ret = -EINVAL; } @@ -509,7 +509,7 @@ static int __init obdclass_init(void) * For clients with less memory, a larger fraction is needed * for other purposes (mostly for BGL). */ - if (totalram_pages <= 512 << (20 - PAGE_CACHE_SHIFT)) + if (totalram_pages <= 512 << (20 - PAGE_SHIFT)) obd_max_dirty_pages = totalram_pages / 4; else obd_max_dirty_pages = totalram_pages / 2; diff --git a/drivers/staging/lustre/lustre/obdclass/linux/linux-obdo.c b/drivers/staging/lustre/lustre/obdclass/linux/linux-obdo.c index 9496c09b2b69..4a2baaff3dc1 100644 --- a/drivers/staging/lustre/lustre/obdclass/linux/linux-obdo.c +++ b/drivers/staging/lustre/lustre/obdclass/linux/linux-obdo.c @@ -71,8 +71,8 @@ void obdo_refresh_inode(struct inode *dst, struct obdo *src, u32 valid) if (valid & OBD_MD_FLBLKSZ && src->o_blksize > (1 << dst->i_blkbits)) dst->i_blkbits = ffs(src->o_blksize) - 1; - if (dst->i_blkbits < PAGE_CACHE_SHIFT) - dst->i_blkbits = PAGE_CACHE_SHIFT; + if (dst->i_blkbits < PAGE_SHIFT) + dst->i_blkbits = PAGE_SHIFT; /* allocation of space */ if (valid & OBD_MD_FLBLOCKS && src->o_blocks > dst->i_blocks) diff --git a/drivers/staging/lustre/lustre/obdclass/linux/linux-sysctl.c b/drivers/staging/lustre/lustre/obdclass/linux/linux-sysctl.c index fd333b9e968c..e6bf414a4444 100644 --- a/drivers/staging/lustre/lustre/obdclass/linux/linux-sysctl.c +++ b/drivers/staging/lustre/lustre/obdclass/linux/linux-sysctl.c @@ -100,7 +100,7 @@ static ssize_t max_dirty_mb_show(struct kobject *kobj, struct attribute *attr, char *buf) { return sprintf(buf, "%ul\n", - obd_max_dirty_pages / (1 << (20 - PAGE_CACHE_SHIFT))); + obd_max_dirty_pages / (1 << (20 - PAGE_SHIFT))); } static ssize_t max_dirty_mb_store(struct kobject *kobj, struct attribute *attr, @@ -113,14 +113,14 @@ static ssize_t max_dirty_mb_store(struct kobject *kobj, struct attribute *attr, if (rc) return rc; - val *= 1 << (20 - PAGE_CACHE_SHIFT); /* convert to pages */ + val *= 1 << (20 - PAGE_SHIFT); /* convert to pages */ if (val > ((totalram_pages / 10) * 9)) { /* Somebody wants to assign too much memory to dirty pages */ return -EINVAL; } - if (val < 4 << (20 - PAGE_CACHE_SHIFT)) { + if (val < 4 << (20 - PAGE_SHIFT)) { /* Less than 4 Mb for dirty cache is also bad */ return -EINVAL; } diff --git a/drivers/staging/lustre/lustre/obdclass/lu_object.c b/drivers/staging/lustre/lustre/obdclass/lu_object.c index 65a4746c89ca..978568ada8e9 100644 --- a/drivers/staging/lustre/lustre/obdclass/lu_object.c +++ b/drivers/staging/lustre/lustre/obdclass/lu_object.c @@ -840,8 +840,8 @@ static int lu_htable_order(void) #if BITS_PER_LONG == 32 /* limit hashtable size for lowmem systems to low RAM */ - if (cache_size > 1 << (30 - PAGE_CACHE_SHIFT)) - cache_size = 1 << (30 - PAGE_CACHE_SHIFT) * 3 / 4; + if (cache_size > 1 << (30 - PAGE_SHIFT)) + cache_size = 1 << (30 - PAGE_SHIFT) * 3 / 4; #endif /* clear off unreasonable cache setting. */ @@ -853,7 +853,7 @@ static int lu_htable_order(void) lu_cache_percent = LU_CACHE_PERCENT_DEFAULT; } cache_size = cache_size / 100 * lu_cache_percent * - (PAGE_CACHE_SIZE / 1024); + (PAGE_SIZE / 1024); for (bits = 1; (1 << bits) < cache_size; ++bits) { ; diff --git a/drivers/staging/lustre/lustre/obdecho/echo_client.c b/drivers/staging/lustre/lustre/obdecho/echo_client.c index 64ffe243f870..1e83669c204d 100644 --- a/drivers/staging/lustre/lustre/obdecho/echo_client.c +++ b/drivers/staging/lustre/lustre/obdecho/echo_client.c @@ -278,7 +278,7 @@ static void echo_page_fini(const struct lu_env *env, struct page *vmpage = ep->ep_vmpage; atomic_dec(&eco->eo_npages); - page_cache_release(vmpage); + put_page(vmpage); } static int echo_page_prep(const struct lu_env *env, @@ -373,7 +373,7 @@ static int echo_page_init(const struct lu_env *env, struct cl_object *obj, struct echo_object *eco = cl2echo_obj(obj); ep->ep_vmpage = vmpage; - page_cache_get(vmpage); + get_page(vmpage); mutex_init(&ep->ep_lock); cl_page_slice_add(page, &ep->ep_cl, obj, &echo_page_ops); atomic_inc(&eco->eo_npages); @@ -1138,7 +1138,7 @@ static int cl_echo_object_brw(struct echo_object *eco, int rw, u64 offset, LASSERT(rc == 0); rc = cl_echo_enqueue0(env, eco, offset, - offset + npages * PAGE_CACHE_SIZE - 1, + offset + npages * PAGE_SIZE - 1, rw == READ ? LCK_PR : LCK_PW, &lh.cookie, CEF_NEVER); if (rc < 0) @@ -1311,11 +1311,11 @@ echo_client_page_debug_setup(struct page *page, int rw, u64 id, int delta; /* no partial pages on the client */ - LASSERT(count == PAGE_CACHE_SIZE); + LASSERT(count == PAGE_SIZE); addr = kmap(page); - for (delta = 0; delta < PAGE_CACHE_SIZE; delta += OBD_ECHO_BLOCK_SIZE) { + for (delta = 0; delta < PAGE_SIZE; delta += OBD_ECHO_BLOCK_SIZE) { if (rw == OBD_BRW_WRITE) { stripe_off = offset + delta; stripe_id = id; @@ -1341,11 +1341,11 @@ static int echo_client_page_debug_check(struct page *page, u64 id, int rc2; /* no partial pages on the client */ - LASSERT(count == PAGE_CACHE_SIZE); + LASSERT(count == PAGE_SIZE); addr = kmap(page); - for (rc = delta = 0; delta < PAGE_CACHE_SIZE; delta += OBD_ECHO_BLOCK_SIZE) { + for (rc = delta = 0; delta < PAGE_SIZE; delta += OBD_ECHO_BLOCK_SIZE) { stripe_off = offset + delta; stripe_id = id; @@ -1391,7 +1391,7 @@ static int echo_client_kbrw(struct echo_device *ed, int rw, struct obdo *oa, return -EINVAL; /* XXX think again with misaligned I/O */ - npages = count >> PAGE_CACHE_SHIFT; + npages = count >> PAGE_SHIFT; if (rw == OBD_BRW_WRITE) brw_flags = OBD_BRW_ASYNC; @@ -1408,7 +1408,7 @@ static int echo_client_kbrw(struct echo_device *ed, int rw, struct obdo *oa, for (i = 0, pgp = pga, off = offset; i < npages; - i++, pgp++, off += PAGE_CACHE_SIZE) { + i++, pgp++, off += PAGE_SIZE) { LASSERT(!pgp->pg); /* for cleanup */ @@ -1418,7 +1418,7 @@ static int echo_client_kbrw(struct echo_device *ed, int rw, struct obdo *oa, goto out; pages[i] = pgp->pg; - pgp->count = PAGE_CACHE_SIZE; + pgp->count = PAGE_SIZE; pgp->off = off; pgp->flag = brw_flags; @@ -1473,8 +1473,8 @@ static int echo_client_prep_commit(const struct lu_env *env, if (count <= 0 || (count & (~CFS_PAGE_MASK)) != 0) return -EINVAL; - npages = batch >> PAGE_CACHE_SHIFT; - tot_pages = count >> PAGE_CACHE_SHIFT; + npages = batch >> PAGE_SHIFT; + tot_pages = count >> PAGE_SHIFT; lnb = kcalloc(npages, sizeof(struct niobuf_local), GFP_NOFS); rnb = kcalloc(npages, sizeof(struct niobuf_remote), GFP_NOFS); @@ -1497,9 +1497,9 @@ static int echo_client_prep_commit(const struct lu_env *env, if (tot_pages < npages) npages = tot_pages; - for (i = 0; i < npages; i++, off += PAGE_CACHE_SIZE) { + for (i = 0; i < npages; i++, off += PAGE_SIZE) { rnb[i].offset = off; - rnb[i].len = PAGE_CACHE_SIZE; + rnb[i].len = PAGE_SIZE; rnb[i].flags = brw_flags; } @@ -1878,7 +1878,7 @@ static int __init obdecho_init(void) { LCONSOLE_INFO("Echo OBD driver; http://www.lustre.org/\n"); - LASSERT(PAGE_CACHE_SIZE % OBD_ECHO_BLOCK_SIZE == 0); + LASSERT(PAGE_SIZE % OBD_ECHO_BLOCK_SIZE == 0); return echo_client_init(); } diff --git a/drivers/staging/lustre/lustre/osc/lproc_osc.c b/drivers/staging/lustre/lustre/osc/lproc_osc.c index 57c43c506ef2..a3358c39b2f1 100644 --- a/drivers/staging/lustre/lustre/osc/lproc_osc.c +++ b/drivers/staging/lustre/lustre/osc/lproc_osc.c @@ -162,15 +162,15 @@ static ssize_t max_dirty_mb_store(struct kobject *kobj, if (rc) return rc; - pages_number *= 1 << (20 - PAGE_CACHE_SHIFT); /* MB -> pages */ + pages_number *= 1 << (20 - PAGE_SHIFT); /* MB -> pages */ if (pages_number <= 0 || - pages_number > OSC_MAX_DIRTY_MB_MAX << (20 - PAGE_CACHE_SHIFT) || + pages_number > OSC_MAX_DIRTY_MB_MAX << (20 - PAGE_SHIFT) || pages_number > totalram_pages / 4) /* 1/4 of RAM */ return -ERANGE; client_obd_list_lock(&cli->cl_loi_list_lock); - cli->cl_dirty_max = (u32)(pages_number << PAGE_CACHE_SHIFT); + cli->cl_dirty_max = (u32)(pages_number << PAGE_SHIFT); osc_wake_cache_waiters(cli); client_obd_list_unlock(&cli->cl_loi_list_lock); @@ -182,7 +182,7 @@ static int osc_cached_mb_seq_show(struct seq_file *m, void *v) { struct obd_device *dev = m->private; struct client_obd *cli = &dev->u.cli; - int shift = 20 - PAGE_CACHE_SHIFT; + int shift = 20 - PAGE_SHIFT; seq_printf(m, "used_mb: %d\n" @@ -211,7 +211,7 @@ static ssize_t osc_cached_mb_seq_write(struct file *file, return -EFAULT; kernbuf[count] = 0; - mult = 1 << (20 - PAGE_CACHE_SHIFT); + mult = 1 << (20 - PAGE_SHIFT); buffer += lprocfs_find_named_value(kernbuf, "used_mb:", &count) - kernbuf; rc = lprocfs_write_frac_helper(buffer, count, &pages_number, mult); @@ -569,12 +569,12 @@ static ssize_t max_pages_per_rpc_store(struct kobject *kobj, /* if the max_pages is specified in bytes, convert to pages */ if (val >= ONE_MB_BRW_SIZE) - val >>= PAGE_CACHE_SHIFT; + val >>= PAGE_SHIFT; - chunk_mask = ~((1 << (cli->cl_chunkbits - PAGE_CACHE_SHIFT)) - 1); + chunk_mask = ~((1 << (cli->cl_chunkbits - PAGE_SHIFT)) - 1); /* max_pages_per_rpc must be chunk aligned */ val = (val + ~chunk_mask) & chunk_mask; - if (val == 0 || val > ocd->ocd_brw_size >> PAGE_CACHE_SHIFT) { + if (val == 0 || val > ocd->ocd_brw_size >> PAGE_SHIFT) { return -ERANGE; } client_obd_list_lock(&cli->cl_loi_list_lock); diff --git a/drivers/staging/lustre/lustre/osc/osc_cache.c b/drivers/staging/lustre/lustre/osc/osc_cache.c index 63363111380c..4e0a357ed43d 100644 --- a/drivers/staging/lustre/lustre/osc/osc_cache.c +++ b/drivers/staging/lustre/lustre/osc/osc_cache.c @@ -544,7 +544,7 @@ static int osc_extent_merge(const struct lu_env *env, struct osc_extent *cur, return -ERANGE; LASSERT(cur->oe_osclock == victim->oe_osclock); - ppc_bits = osc_cli(obj)->cl_chunkbits - PAGE_CACHE_SHIFT; + ppc_bits = osc_cli(obj)->cl_chunkbits - PAGE_SHIFT; chunk_start = cur->oe_start >> ppc_bits; chunk_end = cur->oe_end >> ppc_bits; if (chunk_start != (victim->oe_end >> ppc_bits) + 1 && @@ -647,8 +647,8 @@ static struct osc_extent *osc_extent_find(const struct lu_env *env, lock = cl_lock_at_pgoff(env, osc2cl(obj), index, NULL, 1, 0); LASSERT(lock->cll_descr.cld_mode >= CLM_WRITE); - LASSERT(cli->cl_chunkbits >= PAGE_CACHE_SHIFT); - ppc_bits = cli->cl_chunkbits - PAGE_CACHE_SHIFT; + LASSERT(cli->cl_chunkbits >= PAGE_SHIFT); + ppc_bits = cli->cl_chunkbits - PAGE_SHIFT; chunk_mask = ~((1 << ppc_bits) - 1); chunksize = 1 << cli->cl_chunkbits; chunk = index >> ppc_bits; @@ -871,8 +871,8 @@ int osc_extent_finish(const struct lu_env *env, struct osc_extent *ext, if (!sent) { lost_grant = ext->oe_grants; - } else if (blocksize < PAGE_CACHE_SIZE && - last_count != PAGE_CACHE_SIZE) { + } else if (blocksize < PAGE_SIZE && + last_count != PAGE_SIZE) { /* For short writes we shouldn't count parts of pages that * span a whole chunk on the OST side, or our accounting goes * wrong. Should match the code in filter_grant_check. @@ -884,7 +884,7 @@ int osc_extent_finish(const struct lu_env *env, struct osc_extent *ext, if (end) count += blocksize - end; - lost_grant = PAGE_CACHE_SIZE - count; + lost_grant = PAGE_SIZE - count; } if (ext->oe_grants > 0) osc_free_grant(cli, nr_pages, lost_grant); @@ -967,7 +967,7 @@ static int osc_extent_truncate(struct osc_extent *ext, pgoff_t trunc_index, struct osc_async_page *oap; struct osc_async_page *tmp; int pages_in_chunk = 0; - int ppc_bits = cli->cl_chunkbits - PAGE_CACHE_SHIFT; + int ppc_bits = cli->cl_chunkbits - PAGE_SHIFT; __u64 trunc_chunk = trunc_index >> ppc_bits; int grants = 0; int nr_pages = 0; @@ -1125,7 +1125,7 @@ static int osc_extent_make_ready(const struct lu_env *env, if (!(last->oap_async_flags & ASYNC_COUNT_STABLE)) { last->oap_count = osc_refresh_count(env, last, OBD_BRW_WRITE); LASSERT(last->oap_count > 0); - LASSERT(last->oap_page_off + last->oap_count <= PAGE_CACHE_SIZE); + LASSERT(last->oap_page_off + last->oap_count <= PAGE_SIZE); last->oap_async_flags |= ASYNC_COUNT_STABLE; } @@ -1134,7 +1134,7 @@ static int osc_extent_make_ready(const struct lu_env *env, */ list_for_each_entry(oap, &ext->oe_pages, oap_pending_item) { if (!(oap->oap_async_flags & ASYNC_COUNT_STABLE)) { - oap->oap_count = PAGE_CACHE_SIZE - oap->oap_page_off; + oap->oap_count = PAGE_SIZE - oap->oap_page_off; oap->oap_async_flags |= ASYNC_COUNT_STABLE; } } @@ -1158,7 +1158,7 @@ static int osc_extent_expand(struct osc_extent *ext, pgoff_t index, int *grants) struct osc_object *obj = ext->oe_obj; struct client_obd *cli = osc_cli(obj); struct osc_extent *next; - int ppc_bits = cli->cl_chunkbits - PAGE_CACHE_SHIFT; + int ppc_bits = cli->cl_chunkbits - PAGE_SHIFT; pgoff_t chunk = index >> ppc_bits; pgoff_t end_chunk; pgoff_t end_index; @@ -1293,9 +1293,9 @@ static int osc_refresh_count(const struct lu_env *env, return 0; else if (cl_offset(obj, page->cp_index + 1) > kms) /* catch sub-page write at end of file */ - return kms % PAGE_CACHE_SIZE; + return kms % PAGE_SIZE; else - return PAGE_CACHE_SIZE; + return PAGE_SIZE; } static int osc_completion(const struct lu_env *env, struct osc_async_page *oap, @@ -1376,10 +1376,10 @@ static void osc_consume_write_grant(struct client_obd *cli, assert_spin_locked(&cli->cl_loi_list_lock.lock); LASSERT(!(pga->flag & OBD_BRW_FROM_GRANT)); atomic_inc(&obd_dirty_pages); - cli->cl_dirty += PAGE_CACHE_SIZE; + cli->cl_dirty += PAGE_SIZE; pga->flag |= OBD_BRW_FROM_GRANT; CDEBUG(D_CACHE, "using %lu grant credits for brw %p page %p\n", - PAGE_CACHE_SIZE, pga, pga->pg); + PAGE_SIZE, pga, pga->pg); osc_update_next_shrink(cli); } @@ -1396,11 +1396,11 @@ static void osc_release_write_grant(struct client_obd *cli, pga->flag &= ~OBD_BRW_FROM_GRANT; atomic_dec(&obd_dirty_pages); - cli->cl_dirty -= PAGE_CACHE_SIZE; + cli->cl_dirty -= PAGE_SIZE; if (pga->flag & OBD_BRW_NOCACHE) { pga->flag &= ~OBD_BRW_NOCACHE; atomic_dec(&obd_dirty_transit_pages); - cli->cl_dirty_transit -= PAGE_CACHE_SIZE; + cli->cl_dirty_transit -= PAGE_SIZE; } } @@ -1469,7 +1469,7 @@ static void osc_free_grant(struct client_obd *cli, unsigned int nr_pages, client_obd_list_lock(&cli->cl_loi_list_lock); atomic_sub(nr_pages, &obd_dirty_pages); - cli->cl_dirty -= nr_pages << PAGE_CACHE_SHIFT; + cli->cl_dirty -= nr_pages << PAGE_SHIFT; cli->cl_lost_grant += lost_grant; if (cli->cl_avail_grant < grant && cli->cl_lost_grant >= grant) { /* borrow some grant from truncate to avoid the case that @@ -1512,11 +1512,11 @@ static int osc_enter_cache_try(struct client_obd *cli, if (rc < 0) return 0; - if (cli->cl_dirty + PAGE_CACHE_SIZE <= cli->cl_dirty_max && + if (cli->cl_dirty + PAGE_SIZE <= cli->cl_dirty_max && atomic_read(&obd_dirty_pages) + 1 <= obd_max_dirty_pages) { osc_consume_write_grant(cli, &oap->oap_brw_page); if (transient) { - cli->cl_dirty_transit += PAGE_CACHE_SIZE; + cli->cl_dirty_transit += PAGE_SIZE; atomic_inc(&obd_dirty_transit_pages); oap->oap_brw_flags |= OBD_BRW_NOCACHE; } @@ -1562,7 +1562,7 @@ static int osc_enter_cache(const struct lu_env *env, struct client_obd *cli, * of queued writes and create a discontiguous rpc stream */ if (OBD_FAIL_CHECK(OBD_FAIL_OSC_NO_GRANT) || - cli->cl_dirty_max < PAGE_CACHE_SIZE || + cli->cl_dirty_max < PAGE_SIZE || cli->cl_ar.ar_force_sync || loi->loi_ar.ar_force_sync) { rc = -EDQUOT; goto out; @@ -1632,7 +1632,7 @@ void osc_wake_cache_waiters(struct client_obd *cli) ocw->ocw_rc = -EDQUOT; /* we can't dirty more */ - if ((cli->cl_dirty + PAGE_CACHE_SIZE > cli->cl_dirty_max) || + if ((cli->cl_dirty + PAGE_SIZE > cli->cl_dirty_max) || (atomic_read(&obd_dirty_pages) + 1 > obd_max_dirty_pages)) { CDEBUG(D_CACHE, "no dirty room: dirty: %ld osc max %ld, sys max %d\n", diff --git a/drivers/staging/lustre/lustre/osc/osc_page.c b/drivers/staging/lustre/lustre/osc/osc_page.c index d720b1a1c18c..ce9ddd515f64 100644 --- a/drivers/staging/lustre/lustre/osc/osc_page.c +++ b/drivers/staging/lustre/lustre/osc/osc_page.c @@ -410,7 +410,7 @@ int osc_page_init(const struct lu_env *env, struct cl_object *obj, int result; opg->ops_from = 0; - opg->ops_to = PAGE_CACHE_SIZE; + opg->ops_to = PAGE_SIZE; result = osc_prep_async_page(osc, opg, vmpage, cl_offset(obj, page->cp_index)); @@ -487,9 +487,9 @@ static atomic_t osc_lru_waiters = ATOMIC_INIT(0); /* LRU pages are freed in batch mode. OSC should at least free this * number of pages to avoid running out of LRU budget, and.. */ -static const int lru_shrink_min = 2 << (20 - PAGE_CACHE_SHIFT); /* 2M */ +static const int lru_shrink_min = 2 << (20 - PAGE_SHIFT); /* 2M */ /* free this number at most otherwise it will take too long time to finish. */ -static const int lru_shrink_max = 32 << (20 - PAGE_CACHE_SHIFT); /* 32M */ +static const int lru_shrink_max = 32 << (20 - PAGE_SHIFT); /* 32M */ /* Check if we can free LRU slots from this OSC. If there exists LRU waiters, * we should free slots aggressively. In this way, slots are freed in a steady diff --git a/drivers/staging/lustre/lustre/osc/osc_request.c b/drivers/staging/lustre/lustre/osc/osc_request.c index 74805f1ae888..30526ebcad04 100644 --- a/drivers/staging/lustre/lustre/osc/osc_request.c +++ b/drivers/staging/lustre/lustre/osc/osc_request.c @@ -826,7 +826,7 @@ static void osc_announce_cached(struct client_obd *cli, struct obdo *oa, oa->o_undirty = 0; } else { long max_in_flight = (cli->cl_max_pages_per_rpc << - PAGE_CACHE_SHIFT)* + PAGE_SHIFT)* (cli->cl_max_rpcs_in_flight + 1); oa->o_undirty = max(cli->cl_dirty_max, max_in_flight); } @@ -909,11 +909,11 @@ static void osc_shrink_grant_local(struct client_obd *cli, struct obdo *oa) static int osc_shrink_grant(struct client_obd *cli) { __u64 target_bytes = (cli->cl_max_rpcs_in_flight + 1) * - (cli->cl_max_pages_per_rpc << PAGE_CACHE_SHIFT); + (cli->cl_max_pages_per_rpc << PAGE_SHIFT); client_obd_list_lock(&cli->cl_loi_list_lock); if (cli->cl_avail_grant <= target_bytes) - target_bytes = cli->cl_max_pages_per_rpc << PAGE_CACHE_SHIFT; + target_bytes = cli->cl_max_pages_per_rpc << PAGE_SHIFT; client_obd_list_unlock(&cli->cl_loi_list_lock); return osc_shrink_grant_to_target(cli, target_bytes); @@ -929,8 +929,8 @@ int osc_shrink_grant_to_target(struct client_obd *cli, __u64 target_bytes) * We don't want to shrink below a single RPC, as that will negatively * impact block allocation and long-term performance. */ - if (target_bytes < cli->cl_max_pages_per_rpc << PAGE_CACHE_SHIFT) - target_bytes = cli->cl_max_pages_per_rpc << PAGE_CACHE_SHIFT; + if (target_bytes < cli->cl_max_pages_per_rpc << PAGE_SHIFT) + target_bytes = cli->cl_max_pages_per_rpc << PAGE_SHIFT; if (target_bytes >= cli->cl_avail_grant) { client_obd_list_unlock(&cli->cl_loi_list_lock); @@ -978,7 +978,7 @@ static int osc_should_shrink_grant(struct client_obd *client) * cli_brw_size(obd->u.cli.cl_import->imp_obd->obd_self_export) * Keep comment here so that it can be found by searching. */ - int brw_size = client->cl_max_pages_per_rpc << PAGE_CACHE_SHIFT; + int brw_size = client->cl_max_pages_per_rpc << PAGE_SHIFT; if (client->cl_import->imp_state == LUSTRE_IMP_FULL && client->cl_avail_grant > brw_size) @@ -1052,7 +1052,7 @@ static void osc_init_grant(struct client_obd *cli, struct obd_connect_data *ocd) } /* determine the appropriate chunk size used by osc_extent. */ - cli->cl_chunkbits = max_t(int, PAGE_CACHE_SHIFT, ocd->ocd_blocksize); + cli->cl_chunkbits = max_t(int, PAGE_SHIFT, ocd->ocd_blocksize); client_obd_list_unlock(&cli->cl_loi_list_lock); CDEBUG(D_CACHE, "%s, setting cl_avail_grant: %ld cl_lost_grant: %ld chunk bits: %d\n", @@ -1317,9 +1317,9 @@ static int osc_brw_prep_request(int cmd, struct client_obd *cli, LASSERT(pg->count > 0); /* make sure there is no gap in the middle of page array */ LASSERTF(page_count == 1 || - (ergo(i == 0, poff + pg->count == PAGE_CACHE_SIZE) && + (ergo(i == 0, poff + pg->count == PAGE_SIZE) && ergo(i > 0 && i < page_count - 1, - poff == 0 && pg->count == PAGE_CACHE_SIZE) && + poff == 0 && pg->count == PAGE_SIZE) && ergo(i == page_count - 1, poff == 0)), "i: %d/%d pg: %p off: %llu, count: %u\n", i, page_count, pg, pg->off, pg->count); @@ -1877,7 +1877,7 @@ int osc_build_rpc(const struct lu_env *env, struct client_obd *cli, oap->oap_count; else LASSERT(oap->oap_page_off + oap->oap_count == - PAGE_CACHE_SIZE); + PAGE_SIZE); } } @@ -1993,7 +1993,7 @@ int osc_build_rpc(const struct lu_env *env, struct client_obd *cli, tmp->oap_request = ptlrpc_request_addref(req); client_obd_list_lock(&cli->cl_loi_list_lock); - starting_offset >>= PAGE_CACHE_SHIFT; + starting_offset >>= PAGE_SHIFT; if (cmd == OBD_BRW_READ) { cli->cl_r_in_flight++; lprocfs_oh_tally_log2(&cli->cl_read_page_hist, page_count); @@ -2790,12 +2790,12 @@ out: CFS_PAGE_MASK; if (OBD_OBJECT_EOF - fm_key->fiemap.fm_length <= - fm_key->fiemap.fm_start + PAGE_CACHE_SIZE - 1) + fm_key->fiemap.fm_start + PAGE_SIZE - 1) policy.l_extent.end = OBD_OBJECT_EOF; else policy.l_extent.end = (fm_key->fiemap.fm_start + fm_key->fiemap.fm_length + - PAGE_CACHE_SIZE - 1) & CFS_PAGE_MASK; + PAGE_SIZE - 1) & CFS_PAGE_MASK; ostid_build_res_name(&fm_key->oa.o_oi, &res_id); mode = ldlm_lock_match(exp->exp_obd->obd_namespace, diff --git a/drivers/staging/lustre/lustre/ptlrpc/client.c b/drivers/staging/lustre/lustre/ptlrpc/client.c index 1b7673eec4d7..cf3ac8eee9ee 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/client.c +++ b/drivers/staging/lustre/lustre/ptlrpc/client.c @@ -174,12 +174,12 @@ void __ptlrpc_prep_bulk_page(struct ptlrpc_bulk_desc *desc, LASSERT(page); LASSERT(pageoffset >= 0); LASSERT(len > 0); - LASSERT(pageoffset + len <= PAGE_CACHE_SIZE); + LASSERT(pageoffset + len <= PAGE_SIZE); desc->bd_nob += len; if (pin) - page_cache_get(page); + get_page(page); ptlrpc_add_bulk_page(desc, page, pageoffset, len); } @@ -206,7 +206,7 @@ void __ptlrpc_free_bulk(struct ptlrpc_bulk_desc *desc, int unpin) if (unpin) { for (i = 0; i < desc->bd_iov_count; i++) - page_cache_release(desc->bd_iov[i].kiov_page); + put_page(desc->bd_iov[i].kiov_page); } kfree(desc); diff --git a/drivers/staging/lustre/lustre/ptlrpc/import.c b/drivers/staging/lustre/lustre/ptlrpc/import.c index b4eddf291269..cd94fed0ffdf 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/import.c +++ b/drivers/staging/lustre/lustre/ptlrpc/import.c @@ -1092,7 +1092,7 @@ finish: if (ocd->ocd_connect_flags & OBD_CONNECT_BRW_SIZE) cli->cl_max_pages_per_rpc = - min(ocd->ocd_brw_size >> PAGE_CACHE_SHIFT, + min(ocd->ocd_brw_size >> PAGE_SHIFT, cli->cl_max_pages_per_rpc); else if (imp->imp_connect_op == MDS_CONNECT || imp->imp_connect_op == MGS_CONNECT) diff --git a/drivers/staging/lustre/lustre/ptlrpc/lproc_ptlrpc.c b/drivers/staging/lustre/lustre/ptlrpc/lproc_ptlrpc.c index cee04efb6fb5..c95a91ce26c9 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/lproc_ptlrpc.c +++ b/drivers/staging/lustre/lustre/ptlrpc/lproc_ptlrpc.c @@ -308,7 +308,7 @@ ptlrpc_lprocfs_req_history_max_seq_write(struct file *file, * hose a kernel by allowing the request history to grow too * far. */ - bufpages = (svc->srv_buf_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + bufpages = (svc->srv_buf_size + PAGE_SIZE - 1) >> PAGE_SHIFT; if (val > totalram_pages / (2 * bufpages)) return -ERANGE; @@ -1226,7 +1226,7 @@ int lprocfs_wr_import(struct file *file, const char __user *buffer, const char prefix[] = "connection="; const int prefix_len = sizeof(prefix) - 1; - if (count > PAGE_CACHE_SIZE - 1 || count <= prefix_len) + if (count > PAGE_SIZE - 1 || count <= prefix_len) return -EINVAL; kbuf = kzalloc(count + 1, GFP_NOFS); diff --git a/drivers/staging/lustre/lustre/ptlrpc/recover.c b/drivers/staging/lustre/lustre/ptlrpc/recover.c index 5f27d9c2e4ef..30d9a164e52d 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/recover.c +++ b/drivers/staging/lustre/lustre/ptlrpc/recover.c @@ -195,7 +195,7 @@ int ptlrpc_resend(struct obd_import *imp) } list_for_each_entry_safe(req, next, &imp->imp_sending_list, rq_list) { - LASSERTF((long)req > PAGE_CACHE_SIZE && req != LP_POISON, + LASSERTF((long)req > PAGE_SIZE && req != LP_POISON, "req %p bad\n", req); LASSERTF(req->rq_type != LI_POISON, "req %p freed\n", req); if (!ptlrpc_no_resend(req)) diff --git a/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c b/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c index 72d5b9bf5b29..d3872b8c9a6e 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c +++ b/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c @@ -58,7 +58,7 @@ * bulk encryption page pools * ****************************************/ -#define POINTERS_PER_PAGE (PAGE_CACHE_SIZE / sizeof(void *)) +#define POINTERS_PER_PAGE (PAGE_SIZE / sizeof(void *)) #define PAGES_PER_POOL (POINTERS_PER_PAGE) #define IDLE_IDX_MAX (100) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 8cfce105c7ee..e21ca2bd6839 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1147,8 +1147,8 @@ static int ffs_sb_fill(struct super_block *sb, void *_data, int silent) ffs->sb = sb; data->ffs_data = NULL; sb->s_fs_info = ffs; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = FUNCTIONFS_MAGIC; sb->s_op = &ffs_sb_operations; sb->s_time_gran = 1; diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 5cdaf0150a4e..e64479f882a5 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -1954,8 +1954,8 @@ gadgetfs_fill_super (struct super_block *sb, void *opts, int silent) return -ENODEV; /* superblock */ - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = GADGETFS_MAGIC; sb->s_op = &gadget_fs_operations; sb->s_time_gran = 1; diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index dba51362d2e2..90901861bfc0 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -123,7 +123,7 @@ static int slave_configure(struct scsi_device *sdev) unsigned int max_sectors = 64; if (us->fflags & US_FL_MAX_SECTORS_MIN) - max_sectors = PAGE_CACHE_SIZE >> 9; + max_sectors = PAGE_SIZE >> 9; if (queue_max_hw_sectors(sdev->request_queue) > max_sectors) blk_queue_max_hw_sectors(sdev->request_queue, max_sectors); diff --git a/drivers/video/fbdev/pvr2fb.c b/drivers/video/fbdev/pvr2fb.c index 71a923e53f93..3b1ca4411073 100644 --- a/drivers/video/fbdev/pvr2fb.c +++ b/drivers/video/fbdev/pvr2fb.c @@ -735,7 +735,7 @@ out: out_unmap: for (i = 0; i < nr_pages; i++) - page_cache_release(pages[i]); + put_page(pages[i]); kfree(pages); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index e9e04376c52c..ac9225e86bf3 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -153,7 +153,7 @@ static void v9fs_invalidate_page(struct page *page, unsigned int offset, * If called with zero offset, we should release * the private state assocated with the page */ - if (offset == 0 && length == PAGE_CACHE_SIZE) + if (offset == 0 && length == PAGE_SIZE) v9fs_fscache_invalidate_page(page); } @@ -166,10 +166,10 @@ static int v9fs_vfs_writepage_locked(struct page *page) struct bio_vec bvec; int err, len; - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; + if (page->index == size >> PAGE_SHIFT) + len = size & ~PAGE_MASK; else - len = PAGE_CACHE_SIZE; + len = PAGE_SIZE; bvec.bv_page = page; bvec.bv_offset = 0; @@ -271,7 +271,7 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping, int retval = 0; struct page *page; struct v9fs_inode *v9inode; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; struct inode *inode = mapping->host; @@ -288,11 +288,11 @@ start: if (PageUptodate(page)) goto out; - if (len == PAGE_CACHE_SIZE) + if (len == PAGE_SIZE) goto out; retval = v9fs_fid_readpage(v9inode->writeback_fid, page); - page_cache_release(page); + put_page(page); if (!retval) goto start; out: @@ -313,7 +313,7 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, /* * zero out the rest of the area */ - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned from = pos & (PAGE_SIZE - 1); zero_user(page, from + copied, len - copied); flush_dcache_page(page); @@ -331,7 +331,7 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, } set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); return copied; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index eadc894faea2..b84c291ba1eb 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -421,8 +421,8 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(file); loff_t i_size; unsigned long pg_start, pg_end; - pg_start = origin >> PAGE_CACHE_SHIFT; - pg_end = (origin + retval - 1) >> PAGE_CACHE_SHIFT; + pg_start = origin >> PAGE_SHIFT; + pg_end = (origin + retval - 1) >> PAGE_SHIFT; if (inode->i_mapping && inode->i_mapping->nrpages) invalidate_inode_pages2_range(inode->i_mapping, pg_start, pg_end); diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index bf495cedec26..de3ed8629196 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -87,7 +87,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, sb->s_op = &v9fs_super_ops; sb->s_bdi = &v9ses->bdi; if (v9ses->cache) - sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_CACHE_SIZE; + sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_SIZE; sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME; if (!v9ses->cache) diff --git a/fs/affs/file.c b/fs/affs/file.c index 22fc7c802d69..0cde550050e8 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -510,9 +510,9 @@ affs_do_readpage_ofs(struct page *page, unsigned to) pr_debug("%s(%lu, %ld, 0, %d)\n", __func__, inode->i_ino, page->index, to); - BUG_ON(to > PAGE_CACHE_SIZE); + BUG_ON(to > PAGE_SIZE); bsize = AFFS_SB(sb)->s_data_blksize; - tmp = page->index << PAGE_CACHE_SHIFT; + tmp = page->index << PAGE_SHIFT; bidx = tmp / bsize; boff = tmp % bsize; @@ -613,10 +613,10 @@ affs_readpage_ofs(struct file *file, struct page *page) int err; pr_debug("%s(%lu, %ld)\n", __func__, inode->i_ino, page->index); - to = PAGE_CACHE_SIZE; - if (((page->index + 1) << PAGE_CACHE_SHIFT) > inode->i_size) { - to = inode->i_size & ~PAGE_CACHE_MASK; - memset(page_address(page) + to, 0, PAGE_CACHE_SIZE - to); + to = PAGE_SIZE; + if (((page->index + 1) << PAGE_SHIFT) > inode->i_size) { + to = inode->i_size & ~PAGE_MASK; + memset(page_address(page) + to, 0, PAGE_SIZE - to); } err = affs_do_readpage_ofs(page, to); @@ -646,7 +646,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping return err; } - index = pos >> PAGE_CACHE_SHIFT; + index = pos >> PAGE_SHIFT; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; @@ -656,10 +656,10 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping return 0; /* XXX: inefficient but safe in the face of short writes */ - err = affs_do_readpage_ofs(page, PAGE_CACHE_SIZE); + err = affs_do_readpage_ofs(page, PAGE_SIZE); if (err) { unlock_page(page); - page_cache_release(page); + put_page(page); } return err; } @@ -677,7 +677,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, u32 tmp; int written; - from = pos & (PAGE_CACHE_SIZE - 1); + from = pos & (PAGE_SIZE - 1); to = pos + len; /* * XXX: not sure if this can handle short copies (len < copied), but @@ -692,7 +692,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, bh = NULL; written = 0; - tmp = (page->index << PAGE_CACHE_SHIFT) + from; + tmp = (page->index << PAGE_SHIFT) + from; bidx = tmp / bsize; boff = tmp % bsize; if (boff) { @@ -788,13 +788,13 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, done: affs_brelse(bh); - tmp = (page->index << PAGE_CACHE_SHIFT) + from; + tmp = (page->index << PAGE_SHIFT) + from; if (tmp > inode->i_size) inode->i_size = AFFS_I(inode)->mmu_private = tmp; err_first_bh: unlock_page(page); - page_cache_release(page); + put_page(page); return written; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index e10e17788f06..5fda2bc53cd7 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -181,7 +181,7 @@ error: static inline void afs_dir_put_page(struct page *page) { kunmap(page); - page_cache_release(page); + put_page(page); } /* diff --git a/fs/afs/file.c b/fs/afs/file.c index 999bc3caec92..6344aee4ac4b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -164,7 +164,7 @@ int afs_page_filler(void *data, struct page *page) _debug("cache said ENOBUFS"); default: go_on: - offset = page->index << PAGE_CACHE_SHIFT; + offset = page->index << PAGE_SHIFT; len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE); /* read the contents of the file from the server into the @@ -319,7 +319,7 @@ static void afs_invalidatepage(struct page *page, unsigned int offset, BUG_ON(!PageLocked(page)); /* we clean up only if the entire page is being invalidated */ - if (offset == 0 && length == PAGE_CACHE_SIZE) { + if (offset == 0 && length == PAGE_SIZE) { #ifdef CONFIG_AFS_FSCACHE if (PageFsCache(page)) { struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index ccd0b212e82a..81dd075356b9 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -93,7 +93,7 @@ int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key) kunmap(page); out_free: - page_cache_release(page); + put_page(page); out: _leave(" = %d", ret); return ret; @@ -189,7 +189,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) buf = kmap_atomic(page); memcpy(devname, buf, size); kunmap_atomic(buf); - page_cache_release(page); + put_page(page); page = NULL; } @@ -211,7 +211,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) return mnt; error: - page_cache_release(page); + put_page(page); error_no_page: free_page((unsigned long) options); error_no_options: diff --git a/fs/afs/super.c b/fs/afs/super.c index 81afefe7d8a6..fbdb022b75a2 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -315,8 +315,8 @@ static int afs_fill_super(struct super_block *sb, _enter(""); /* fill in the superblock */ - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = AFS_FS_MAGIC; sb->s_op = &afs_super_ops; sb->s_bdi = &as->volume->bdi; diff --git a/fs/afs/write.c b/fs/afs/write.c index dfef94f70667..65de439bdc4f 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -93,10 +93,10 @@ static int afs_fill_page(struct afs_vnode *vnode, struct key *key, _enter(",,%llu", (unsigned long long)pos); i_size = i_size_read(&vnode->vfs_inode); - if (pos + PAGE_CACHE_SIZE > i_size) + if (pos + PAGE_SIZE > i_size) len = i_size - pos; else - len = PAGE_CACHE_SIZE; + len = PAGE_SIZE; ret = afs_vnode_fetch_data(vnode, key, pos, len, page); if (ret < 0) { @@ -123,9 +123,9 @@ int afs_write_begin(struct file *file, struct address_space *mapping, struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); struct page *page; struct key *key = file->private_data; - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned from = pos & (PAGE_SIZE - 1); unsigned to = from + len; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; int ret; _enter("{%x:%u},{%lx},%u,%u", @@ -151,8 +151,8 @@ int afs_write_begin(struct file *file, struct address_space *mapping, *pagep = page; /* page won't leak in error case: it eventually gets cleaned off LRU */ - if (!PageUptodate(page) && len != PAGE_CACHE_SIZE) { - ret = afs_fill_page(vnode, key, index << PAGE_CACHE_SHIFT, page); + if (!PageUptodate(page) && len != PAGE_SIZE) { + ret = afs_fill_page(vnode, key, index << PAGE_SHIFT, page); if (ret < 0) { kfree(candidate); _leave(" = %d [prep]", ret); @@ -266,7 +266,7 @@ int afs_write_end(struct file *file, struct address_space *mapping, if (PageDirty(page)) _debug("dirtied"); unlock_page(page); - page_cache_release(page); + put_page(page); return copied; } @@ -480,7 +480,7 @@ static int afs_writepages_region(struct address_space *mapping, if (page->index > end) { *_next = index; - page_cache_release(page); + put_page(page); _leave(" = 0 [%lx]", *_next); return 0; } @@ -494,7 +494,7 @@ static int afs_writepages_region(struct address_space *mapping, if (page->mapping != mapping) { unlock_page(page); - page_cache_release(page); + put_page(page); continue; } @@ -515,7 +515,7 @@ static int afs_writepages_region(struct address_space *mapping, ret = afs_write_back_from_locked_page(wb, page); unlock_page(page); - page_cache_release(page); + put_page(page); if (ret < 0) { _leave(" = %d", ret); return ret; @@ -551,13 +551,13 @@ int afs_writepages(struct address_space *mapping, &next); mapping->writeback_index = next; } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) { - end = (pgoff_t)(LLONG_MAX >> PAGE_CACHE_SHIFT); + end = (pgoff_t)(LLONG_MAX >> PAGE_SHIFT); ret = afs_writepages_region(mapping, wbc, 0, end, &next); if (wbc->nr_to_write > 0) mapping->writeback_index = next; } else { - start = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + start = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; ret = afs_writepages_region(mapping, wbc, start, end, &next); } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 7d914c67a9d0..81381cc0dd17 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2292,7 +2292,7 @@ static int elf_core_dump(struct coredump_params *cprm) void *kaddr = kmap(page); stop = !dump_emit(cprm, kaddr, PAGE_SIZE); kunmap(page); - page_cache_release(page); + put_page(page); } else stop = !dump_skip(cprm, PAGE_SIZE); if (stop) diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index b1adb92e69de..083ea2bc60ab 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1533,7 +1533,7 @@ static bool elf_fdpic_dump_segments(struct coredump_params *cprm) void *kaddr = kmap(page); res = dump_emit(cprm, kaddr, PAGE_SIZE); kunmap(page); - page_cache_release(page); + put_page(page); } else { res = dump_skip(cprm, PAGE_SIZE); } diff --git a/fs/block_dev.c b/fs/block_dev.c index 3172c4e2f502..20a2c02b77c4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -331,7 +331,7 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping, ret = block_write_end(file, mapping, pos, len, copied, page, fsdata); unlock_page(page); - page_cache_release(page); + put_page(page); return ret; } @@ -1149,7 +1149,7 @@ void bd_set_size(struct block_device *bdev, loff_t size) inode_lock(bdev->bd_inode); i_size_write(bdev->bd_inode, size); inode_unlock(bdev->bd_inode); - while (bsize < PAGE_CACHE_SIZE) { + while (bsize < PAGE_SIZE) { if (size & bsize) break; bsize <<= 1; diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index e34a71b3e225..866789ede4cb 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -757,7 +757,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, BUG_ON(NULL == l); ret = btrfsic_read_block(state, &tmp_next_block_ctx); - if (ret < (int)PAGE_CACHE_SIZE) { + if (ret < (int)PAGE_SIZE) { printk(KERN_INFO "btrfsic: read @logical %llu failed!\n", tmp_next_block_ctx.start); @@ -1231,15 +1231,15 @@ static void btrfsic_read_from_block_data( size_t offset_in_page; char *kaddr; char *dst = (char *)dstv; - size_t start_offset = block_ctx->start & ((u64)PAGE_CACHE_SIZE - 1); - unsigned long i = (start_offset + offset) >> PAGE_CACHE_SHIFT; + size_t start_offset = block_ctx->start & ((u64)PAGE_SIZE - 1); + unsigned long i = (start_offset + offset) >> PAGE_SHIFT; WARN_ON(offset + len > block_ctx->len); - offset_in_page = (start_offset + offset) & (PAGE_CACHE_SIZE - 1); + offset_in_page = (start_offset + offset) & (PAGE_SIZE - 1); while (len > 0) { - cur = min(len, ((size_t)PAGE_CACHE_SIZE - offset_in_page)); - BUG_ON(i >= DIV_ROUND_UP(block_ctx->len, PAGE_CACHE_SIZE)); + cur = min(len, ((size_t)PAGE_SIZE - offset_in_page)); + BUG_ON(i >= DIV_ROUND_UP(block_ctx->len, PAGE_SIZE)); kaddr = block_ctx->datav[i]; memcpy(dst, kaddr + offset_in_page, cur); @@ -1605,8 +1605,8 @@ static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx) BUG_ON(!block_ctx->datav); BUG_ON(!block_ctx->pagev); - num_pages = (block_ctx->len + (u64)PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + num_pages = (block_ctx->len + (u64)PAGE_SIZE - 1) >> + PAGE_SHIFT; while (num_pages > 0) { num_pages--; if (block_ctx->datav[num_pages]) { @@ -1637,15 +1637,15 @@ static int btrfsic_read_block(struct btrfsic_state *state, BUG_ON(block_ctx->datav); BUG_ON(block_ctx->pagev); BUG_ON(block_ctx->mem_to_free); - if (block_ctx->dev_bytenr & ((u64)PAGE_CACHE_SIZE - 1)) { + if (block_ctx->dev_bytenr & ((u64)PAGE_SIZE - 1)) { printk(KERN_INFO "btrfsic: read_block() with unaligned bytenr %llu\n", block_ctx->dev_bytenr); return -1; } - num_pages = (block_ctx->len + (u64)PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + num_pages = (block_ctx->len + (u64)PAGE_SIZE - 1) >> + PAGE_SHIFT; block_ctx->mem_to_free = kzalloc((sizeof(*block_ctx->datav) + sizeof(*block_ctx->pagev)) * num_pages, GFP_NOFS); @@ -1676,8 +1676,8 @@ static int btrfsic_read_block(struct btrfsic_state *state, for (j = i; j < num_pages; j++) { ret = bio_add_page(bio, block_ctx->pagev[j], - PAGE_CACHE_SIZE, 0); - if (PAGE_CACHE_SIZE != ret) + PAGE_SIZE, 0); + if (PAGE_SIZE != ret) break; } if (j == i) { @@ -1693,7 +1693,7 @@ static int btrfsic_read_block(struct btrfsic_state *state, return -1; } bio_put(bio); - dev_bytenr += (j - i) * PAGE_CACHE_SIZE; + dev_bytenr += (j - i) * PAGE_SIZE; i = j; } for (i = 0; i < num_pages; i++) { @@ -1769,9 +1769,9 @@ static int btrfsic_test_for_metadata(struct btrfsic_state *state, u32 crc = ~(u32)0; unsigned int i; - if (num_pages * PAGE_CACHE_SIZE < state->metablock_size) + if (num_pages * PAGE_SIZE < state->metablock_size) return 1; /* not metadata */ - num_pages = state->metablock_size >> PAGE_CACHE_SHIFT; + num_pages = state->metablock_size >> PAGE_SHIFT; h = (struct btrfs_header *)datav[0]; if (memcmp(h->fsid, state->root->fs_info->fsid, BTRFS_UUID_SIZE)) @@ -1779,8 +1779,8 @@ static int btrfsic_test_for_metadata(struct btrfsic_state *state, for (i = 0; i < num_pages; i++) { u8 *data = i ? datav[i] : (datav[i] + BTRFS_CSUM_SIZE); - size_t sublen = i ? PAGE_CACHE_SIZE : - (PAGE_CACHE_SIZE - BTRFS_CSUM_SIZE); + size_t sublen = i ? PAGE_SIZE : + (PAGE_SIZE - BTRFS_CSUM_SIZE); crc = btrfs_crc32c(crc, data, sublen); } @@ -1826,14 +1826,14 @@ again: if (block->is_superblock) { bytenr = btrfs_super_bytenr((struct btrfs_super_block *) mapped_datav[0]); - if (num_pages * PAGE_CACHE_SIZE < + if (num_pages * PAGE_SIZE < BTRFS_SUPER_INFO_SIZE) { printk(KERN_INFO "btrfsic: cannot work with too short bios!\n"); return; } is_metadata = 1; - BUG_ON(BTRFS_SUPER_INFO_SIZE & (PAGE_CACHE_SIZE - 1)); + BUG_ON(BTRFS_SUPER_INFO_SIZE & (PAGE_SIZE - 1)); processed_len = BTRFS_SUPER_INFO_SIZE; if (state->print_mask & BTRFSIC_PRINT_MASK_TREE_BEFORE_SB_WRITE) { @@ -1844,7 +1844,7 @@ again: } if (is_metadata) { if (!block->is_superblock) { - if (num_pages * PAGE_CACHE_SIZE < + if (num_pages * PAGE_SIZE < state->metablock_size) { printk(KERN_INFO "btrfsic: cannot work with too short bios!\n"); @@ -1880,7 +1880,7 @@ again: } block->logical_bytenr = bytenr; } else { - if (num_pages * PAGE_CACHE_SIZE < + if (num_pages * PAGE_SIZE < state->datablock_size) { printk(KERN_INFO "btrfsic: cannot work with too short bios!\n"); @@ -2013,7 +2013,7 @@ again: block->logical_bytenr = bytenr; block->is_metadata = 1; if (block->is_superblock) { - BUG_ON(PAGE_CACHE_SIZE != + BUG_ON(PAGE_SIZE != BTRFS_SUPER_INFO_SIZE); ret = btrfsic_process_written_superblock( state, @@ -2172,8 +2172,8 @@ again: continue_loop: BUG_ON(!processed_len); dev_bytenr += processed_len; - mapped_datav += processed_len >> PAGE_CACHE_SHIFT; - num_pages -= processed_len >> PAGE_CACHE_SHIFT; + mapped_datav += processed_len >> PAGE_SHIFT; + num_pages -= processed_len >> PAGE_SHIFT; goto again; } @@ -2954,7 +2954,7 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio) goto leave; cur_bytenr = dev_bytenr; for (i = 0; i < bio->bi_vcnt; i++) { - BUG_ON(bio->bi_io_vec[i].bv_len != PAGE_CACHE_SIZE); + BUG_ON(bio->bi_io_vec[i].bv_len != PAGE_SIZE); mapped_datav[i] = kmap(bio->bi_io_vec[i].bv_page); if (!mapped_datav[i]) { while (i > 0) { @@ -3037,16 +3037,16 @@ int btrfsic_mount(struct btrfs_root *root, struct list_head *dev_head = &fs_devices->devices; struct btrfs_device *device; - if (root->nodesize & ((u64)PAGE_CACHE_SIZE - 1)) { + if (root->nodesize & ((u64)PAGE_SIZE - 1)) { printk(KERN_INFO "btrfsic: cannot handle nodesize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n", - root->nodesize, PAGE_CACHE_SIZE); + root->nodesize, PAGE_SIZE); return -1; } - if (root->sectorsize & ((u64)PAGE_CACHE_SIZE - 1)) { + if (root->sectorsize & ((u64)PAGE_SIZE - 1)) { printk(KERN_INFO "btrfsic: cannot handle sectorsize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n", - root->sectorsize, PAGE_CACHE_SIZE); + root->sectorsize, PAGE_SIZE); return -1; } state = kzalloc(sizeof(*state), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 3346cd8f9910..ff61a41ac90b 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -119,7 +119,7 @@ static int check_compressed_csum(struct inode *inode, csum = ~(u32)0; kaddr = kmap_atomic(page); - csum = btrfs_csum_data(kaddr, csum, PAGE_CACHE_SIZE); + csum = btrfs_csum_data(kaddr, csum, PAGE_SIZE); btrfs_csum_final(csum, (char *)&csum); kunmap_atomic(kaddr); @@ -190,7 +190,7 @@ csum_failed: for (index = 0; index < cb->nr_pages; index++) { page = cb->compressed_pages[index]; page->mapping = NULL; - page_cache_release(page); + put_page(page); } /* do io completion on the original bio */ @@ -224,8 +224,8 @@ out: static noinline void end_compressed_writeback(struct inode *inode, const struct compressed_bio *cb) { - unsigned long index = cb->start >> PAGE_CACHE_SHIFT; - unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_CACHE_SHIFT; + unsigned long index = cb->start >> PAGE_SHIFT; + unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_SHIFT; struct page *pages[16]; unsigned long nr_pages = end_index - index + 1; int i; @@ -247,7 +247,7 @@ static noinline void end_compressed_writeback(struct inode *inode, if (cb->errors) SetPageError(pages[i]); end_page_writeback(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); } nr_pages -= ret; index += ret; @@ -304,7 +304,7 @@ static void end_compressed_bio_write(struct bio *bio) for (index = 0; index < cb->nr_pages; index++) { page = cb->compressed_pages[index]; page->mapping = NULL; - page_cache_release(page); + put_page(page); } /* finally free the cb struct */ @@ -341,7 +341,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, int ret; int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; - WARN_ON(start & ((u64)PAGE_CACHE_SIZE - 1)); + WARN_ON(start & ((u64)PAGE_SIZE - 1)); cb = kmalloc(compressed_bio_size(root, compressed_len), GFP_NOFS); if (!cb) return -ENOMEM; @@ -374,14 +374,14 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, page->mapping = inode->i_mapping; if (bio->bi_iter.bi_size) ret = io_tree->ops->merge_bio_hook(WRITE, page, 0, - PAGE_CACHE_SIZE, + PAGE_SIZE, bio, 0); else ret = 0; page->mapping = NULL; - if (ret || bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < - PAGE_CACHE_SIZE) { + if (ret || bio_add_page(bio, page, PAGE_SIZE, 0) < + PAGE_SIZE) { bio_get(bio); /* @@ -410,15 +410,15 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, BUG_ON(!bio); bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; - bio_add_page(bio, page, PAGE_CACHE_SIZE, 0); + bio_add_page(bio, page, PAGE_SIZE, 0); } - if (bytes_left < PAGE_CACHE_SIZE) { + if (bytes_left < PAGE_SIZE) { btrfs_info(BTRFS_I(inode)->root->fs_info, "bytes left %lu compress len %lu nr %lu", bytes_left, cb->compressed_len, cb->nr_pages); } - bytes_left -= PAGE_CACHE_SIZE; - first_byte += PAGE_CACHE_SIZE; + bytes_left -= PAGE_SIZE; + first_byte += PAGE_SIZE; cond_resched(); } bio_get(bio); @@ -457,17 +457,17 @@ static noinline int add_ra_bio_pages(struct inode *inode, int misses = 0; page = cb->orig_bio->bi_io_vec[cb->orig_bio->bi_vcnt - 1].bv_page; - last_offset = (page_offset(page) + PAGE_CACHE_SIZE); + last_offset = (page_offset(page) + PAGE_SIZE); em_tree = &BTRFS_I(inode)->extent_tree; tree = &BTRFS_I(inode)->io_tree; if (isize == 0) return 0; - end_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT; + end_index = (i_size_read(inode) - 1) >> PAGE_SHIFT; while (last_offset < compressed_end) { - pg_index = last_offset >> PAGE_CACHE_SHIFT; + pg_index = last_offset >> PAGE_SHIFT; if (pg_index > end_index) break; @@ -488,11 +488,11 @@ static noinline int add_ra_bio_pages(struct inode *inode, break; if (add_to_page_cache_lru(page, mapping, pg_index, GFP_NOFS)) { - page_cache_release(page); + put_page(page); goto next; } - end = last_offset + PAGE_CACHE_SIZE - 1; + end = last_offset + PAGE_SIZE - 1; /* * at this point, we have a locked page in the page cache * for these bytes in the file. But, we have to make @@ -502,27 +502,27 @@ static noinline int add_ra_bio_pages(struct inode *inode, lock_extent(tree, last_offset, end); read_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, last_offset, - PAGE_CACHE_SIZE); + PAGE_SIZE); read_unlock(&em_tree->lock); if (!em || last_offset < em->start || - (last_offset + PAGE_CACHE_SIZE > extent_map_end(em)) || + (last_offset + PAGE_SIZE > extent_map_end(em)) || (em->block_start >> 9) != cb->orig_bio->bi_iter.bi_sector) { free_extent_map(em); unlock_extent(tree, last_offset, end); unlock_page(page); - page_cache_release(page); + put_page(page); break; } free_extent_map(em); if (page->index == end_index) { char *userpage; - size_t zero_offset = isize & (PAGE_CACHE_SIZE - 1); + size_t zero_offset = isize & (PAGE_SIZE - 1); if (zero_offset) { int zeros; - zeros = PAGE_CACHE_SIZE - zero_offset; + zeros = PAGE_SIZE - zero_offset; userpage = kmap_atomic(page); memset(userpage + zero_offset, 0, zeros); flush_dcache_page(page); @@ -531,19 +531,19 @@ static noinline int add_ra_bio_pages(struct inode *inode, } ret = bio_add_page(cb->orig_bio, page, - PAGE_CACHE_SIZE, 0); + PAGE_SIZE, 0); - if (ret == PAGE_CACHE_SIZE) { + if (ret == PAGE_SIZE) { nr_pages++; - page_cache_release(page); + put_page(page); } else { unlock_extent(tree, last_offset, end); unlock_page(page); - page_cache_release(page); + put_page(page); break; } next: - last_offset += PAGE_CACHE_SIZE; + last_offset += PAGE_SIZE; } return 0; } @@ -567,7 +567,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, struct extent_map_tree *em_tree; struct compressed_bio *cb; struct btrfs_root *root = BTRFS_I(inode)->root; - unsigned long uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE; + unsigned long uncompressed_len = bio->bi_vcnt * PAGE_SIZE; unsigned long compressed_len; unsigned long nr_pages; unsigned long pg_index; @@ -589,7 +589,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, read_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, page_offset(bio->bi_io_vec->bv_page), - PAGE_CACHE_SIZE); + PAGE_SIZE); read_unlock(&em_tree->lock); if (!em) return -EIO; @@ -617,7 +617,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, cb->compress_type = extent_compress_type(bio_flags); cb->orig_bio = bio; - nr_pages = DIV_ROUND_UP(compressed_len, PAGE_CACHE_SIZE); + nr_pages = DIV_ROUND_UP(compressed_len, PAGE_SIZE); cb->compressed_pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); if (!cb->compressed_pages) @@ -640,7 +640,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, add_ra_bio_pages(inode, em_start + em_len, cb); /* include any pages we added in add_ra-bio_pages */ - uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE; + uncompressed_len = bio->bi_vcnt * PAGE_SIZE; cb->len = uncompressed_len; comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS); @@ -653,18 +653,18 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, for (pg_index = 0; pg_index < nr_pages; pg_index++) { page = cb->compressed_pages[pg_index]; page->mapping = inode->i_mapping; - page->index = em_start >> PAGE_CACHE_SHIFT; + page->index = em_start >> PAGE_SHIFT; if (comp_bio->bi_iter.bi_size) ret = tree->ops->merge_bio_hook(READ, page, 0, - PAGE_CACHE_SIZE, + PAGE_SIZE, comp_bio, 0); else ret = 0; page->mapping = NULL; - if (ret || bio_add_page(comp_bio, page, PAGE_CACHE_SIZE, 0) < - PAGE_CACHE_SIZE) { + if (ret || bio_add_page(comp_bio, page, PAGE_SIZE, 0) < + PAGE_SIZE) { bio_get(comp_bio); ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, @@ -702,9 +702,9 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, comp_bio->bi_private = cb; comp_bio->bi_end_io = end_compressed_bio_read; - bio_add_page(comp_bio, page, PAGE_CACHE_SIZE, 0); + bio_add_page(comp_bio, page, PAGE_SIZE, 0); } - cur_disk_byte += PAGE_CACHE_SIZE; + cur_disk_byte += PAGE_SIZE; } bio_get(comp_bio); @@ -1013,8 +1013,8 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start, /* copy bytes from the working buffer into the pages */ while (working_bytes > 0) { - bytes = min(PAGE_CACHE_SIZE - *pg_offset, - PAGE_CACHE_SIZE - buf_offset); + bytes = min(PAGE_SIZE - *pg_offset, + PAGE_SIZE - buf_offset); bytes = min(bytes, working_bytes); kaddr = kmap_atomic(page_out); memcpy(kaddr + *pg_offset, buf + buf_offset, bytes); @@ -1027,7 +1027,7 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start, current_buf_start += bytes; /* check if we need to pick another page */ - if (*pg_offset == PAGE_CACHE_SIZE) { + if (*pg_offset == PAGE_SIZE) { (*pg_index)++; if (*pg_index >= vcnt) return 0; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4b02591b0301..942af3d2885f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1055,7 +1055,7 @@ static void btree_invalidatepage(struct page *page, unsigned int offset, (unsigned long long)page_offset(page)); ClearPagePrivate(page); set_page_private(page, 0); - page_cache_release(page); + put_page(page); } } @@ -1757,7 +1757,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi) if (err) return err; - bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE; + bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE; bdi->congested_fn = btrfs_congested_fn; bdi->congested_data = info; bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; @@ -2537,7 +2537,7 @@ int open_ctree(struct super_block *sb, err = ret; goto fail_bdi; } - fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE * + fs_info->dirty_metadata_batch = PAGE_SIZE * (1 + ilog2(nr_cpu_ids)); ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL); @@ -2782,7 +2782,7 @@ int open_ctree(struct super_block *sb, * flag our filesystem as having big metadata blocks if * they are bigger than the page size */ - if (btrfs_super_nodesize(disk_super) > PAGE_CACHE_SIZE) { + if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) { if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA)) printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n"); features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA; @@ -2832,7 +2832,7 @@ int open_ctree(struct super_block *sb, fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super); fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages, - SZ_4M / PAGE_CACHE_SIZE); + SZ_4M / PAGE_SIZE); tree_root->nodesize = nodesize; tree_root->sectorsize = sectorsize; @@ -4071,9 +4071,9 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, ret = -EINVAL; } /* Only PAGE SIZE is supported yet */ - if (sectorsize != PAGE_CACHE_SIZE) { + if (sectorsize != PAGE_SIZE) { printk(KERN_ERR "BTRFS: sectorsize %llu not supported yet, only support %lu\n", - sectorsize, PAGE_CACHE_SIZE); + sectorsize, PAGE_SIZE); ret = -EINVAL; } if (!is_power_of_2(nodesize) || nodesize < sectorsize || diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 53e12977bfd0..ce114ba9780a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3452,7 +3452,7 @@ again: num_pages = 1; num_pages *= 16; - num_pages *= PAGE_CACHE_SIZE; + num_pages *= PAGE_SIZE; ret = btrfs_check_data_free_space(inode, 0, num_pages); if (ret) @@ -4639,7 +4639,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, loops = 0; while (delalloc_bytes && loops < 3) { max_reclaim = min(delalloc_bytes, to_reclaim); - nr_pages = max_reclaim >> PAGE_CACHE_SHIFT; + nr_pages = max_reclaim >> PAGE_SHIFT; btrfs_writeback_inodes_sb_nr(root, nr_pages, items); /* * We need to wait for the async pages to actually start before diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 76a0c8597d98..93d696d248d9 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1363,23 +1363,23 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end) void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end) { - unsigned long index = start >> PAGE_CACHE_SHIFT; - unsigned long end_index = end >> PAGE_CACHE_SHIFT; + unsigned long index = start >> PAGE_SHIFT; + unsigned long end_index = end >> PAGE_SHIFT; struct page *page; while (index <= end_index) { page = find_get_page(inode->i_mapping, index); BUG_ON(!page); /* Pages should be in the extent_io_tree */ clear_page_dirty_for_io(page); - page_cache_release(page); + put_page(page); index++; } } void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end) { - unsigned long index = start >> PAGE_CACHE_SHIFT; - unsigned long end_index = end >> PAGE_CACHE_SHIFT; + unsigned long index = start >> PAGE_SHIFT; + unsigned long end_index = end >> PAGE_SHIFT; struct page *page; while (index <= end_index) { @@ -1387,7 +1387,7 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end) BUG_ON(!page); /* Pages should be in the extent_io_tree */ __set_page_dirty_nobuffers(page); account_page_redirty(page); - page_cache_release(page); + put_page(page); index++; } } @@ -1397,15 +1397,15 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end) */ static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end) { - unsigned long index = start >> PAGE_CACHE_SHIFT; - unsigned long end_index = end >> PAGE_CACHE_SHIFT; + unsigned long index = start >> PAGE_SHIFT; + unsigned long end_index = end >> PAGE_SHIFT; struct page *page; while (index <= end_index) { page = find_get_page(tree->mapping, index); BUG_ON(!page); /* Pages should be in the extent_io_tree */ set_page_writeback(page); - page_cache_release(page); + put_page(page); index++; } } @@ -1556,8 +1556,8 @@ static noinline void __unlock_for_delalloc(struct inode *inode, { int ret; struct page *pages[16]; - unsigned long index = start >> PAGE_CACHE_SHIFT; - unsigned long end_index = end >> PAGE_CACHE_SHIFT; + unsigned long index = start >> PAGE_SHIFT; + unsigned long end_index = end >> PAGE_SHIFT; unsigned long nr_pages = end_index - index + 1; int i; @@ -1571,7 +1571,7 @@ static noinline void __unlock_for_delalloc(struct inode *inode, for (i = 0; i < ret; i++) { if (pages[i] != locked_page) unlock_page(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); } nr_pages -= ret; index += ret; @@ -1584,9 +1584,9 @@ static noinline int lock_delalloc_pages(struct inode *inode, u64 delalloc_start, u64 delalloc_end) { - unsigned long index = delalloc_start >> PAGE_CACHE_SHIFT; + unsigned long index = delalloc_start >> PAGE_SHIFT; unsigned long start_index = index; - unsigned long end_index = delalloc_end >> PAGE_CACHE_SHIFT; + unsigned long end_index = delalloc_end >> PAGE_SHIFT; unsigned long pages_locked = 0; struct page *pages[16]; unsigned long nrpages; @@ -1619,11 +1619,11 @@ static noinline int lock_delalloc_pages(struct inode *inode, pages[i]->mapping != inode->i_mapping) { ret = -EAGAIN; unlock_page(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); goto done; } } - page_cache_release(pages[i]); + put_page(pages[i]); pages_locked++; } nrpages -= ret; @@ -1636,7 +1636,7 @@ done: __unlock_for_delalloc(inode, locked_page, delalloc_start, ((u64)(start_index + pages_locked - 1)) << - PAGE_CACHE_SHIFT); + PAGE_SHIFT); } return ret; } @@ -1696,7 +1696,7 @@ again: free_extent_state(cached_state); cached_state = NULL; if (!loops) { - max_bytes = PAGE_CACHE_SIZE; + max_bytes = PAGE_SIZE; loops = 1; goto again; } else { @@ -1735,8 +1735,8 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; int ret; struct page *pages[16]; - unsigned long index = start >> PAGE_CACHE_SHIFT; - unsigned long end_index = end >> PAGE_CACHE_SHIFT; + unsigned long index = start >> PAGE_SHIFT; + unsigned long end_index = end >> PAGE_SHIFT; unsigned long nr_pages = end_index - index + 1; int i; @@ -1757,7 +1757,7 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, SetPagePrivate2(pages[i]); if (pages[i] == locked_page) { - page_cache_release(pages[i]); + put_page(pages[i]); continue; } if (page_ops & PAGE_CLEAR_DIRTY) @@ -1770,7 +1770,7 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, end_page_writeback(pages[i]); if (page_ops & PAGE_UNLOCK) unlock_page(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); } nr_pages -= ret; index += ret; @@ -1961,7 +1961,7 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end, static void check_page_uptodate(struct extent_io_tree *tree, struct page *page) { u64 start = page_offset(page); - u64 end = start + PAGE_CACHE_SIZE - 1; + u64 end = start + PAGE_SIZE - 1; if (test_range_bit(tree, start, end, EXTENT_UPTODATE, 1, NULL)) SetPageUptodate(page); } @@ -2071,11 +2071,11 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb, struct page *p = eb->pages[i]; ret = repair_io_failure(root->fs_info->btree_inode, start, - PAGE_CACHE_SIZE, start, p, + PAGE_SIZE, start, p, start - page_offset(p), mirror_num); if (ret) break; - start += PAGE_CACHE_SIZE; + start += PAGE_SIZE; } return ret; @@ -2466,8 +2466,8 @@ static void end_bio_extent_writepage(struct bio *bio) * advance bv_offset and adjust bv_len to compensate. * Print a warning for nonzero offsets, and an error * if they don't add up to a full page. */ - if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) { - if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE) + if (bvec->bv_offset || bvec->bv_len != PAGE_SIZE) { + if (bvec->bv_offset + bvec->bv_len != PAGE_SIZE) btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info, "partial page write in btrfs with offset %u and length %u", bvec->bv_offset, bvec->bv_len); @@ -2541,8 +2541,8 @@ static void end_bio_extent_readpage(struct bio *bio) * advance bv_offset and adjust bv_len to compensate. * Print a warning for nonzero offsets, and an error * if they don't add up to a full page. */ - if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) { - if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE) + if (bvec->bv_offset || bvec->bv_len != PAGE_SIZE) { + if (bvec->bv_offset + bvec->bv_len != PAGE_SIZE) btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info, "partial page read in btrfs with offset %u and length %u", bvec->bv_offset, bvec->bv_len); @@ -2598,13 +2598,13 @@ static void end_bio_extent_readpage(struct bio *bio) readpage_ok: if (likely(uptodate)) { loff_t i_size = i_size_read(inode); - pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; + pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned off; /* Zero out the end if this page straddles i_size */ - off = i_size & (PAGE_CACHE_SIZE-1); + off = i_size & (PAGE_SIZE-1); if (page->index == end_index && off) - zero_user_segment(page, off, PAGE_CACHE_SIZE); + zero_user_segment(page, off, PAGE_SIZE); SetPageUptodate(page); } else { ClearPageUptodate(page); @@ -2768,7 +2768,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, struct bio *bio; int contig = 0; int old_compressed = prev_bio_flags & EXTENT_BIO_COMPRESSED; - size_t page_size = min_t(size_t, size, PAGE_CACHE_SIZE); + size_t page_size = min_t(size_t, size, PAGE_SIZE); if (bio_ret && *bio_ret) { bio = *bio_ret; @@ -2821,7 +2821,7 @@ static void attach_extent_buffer_page(struct extent_buffer *eb, { if (!PagePrivate(page)) { SetPagePrivate(page); - page_cache_get(page); + get_page(page); set_page_private(page, (unsigned long)eb); } else { WARN_ON(page->private != (unsigned long)eb); @@ -2832,7 +2832,7 @@ void set_page_extent_mapped(struct page *page) { if (!PagePrivate(page)) { SetPagePrivate(page); - page_cache_get(page); + get_page(page); set_page_private(page, EXTENT_PAGE_PRIVATE); } } @@ -2880,7 +2880,7 @@ static int __do_readpage(struct extent_io_tree *tree, { struct inode *inode = page->mapping->host; u64 start = page_offset(page); - u64 page_end = start + PAGE_CACHE_SIZE - 1; + u64 page_end = start + PAGE_SIZE - 1; u64 end; u64 cur = start; u64 extent_offset; @@ -2909,12 +2909,12 @@ static int __do_readpage(struct extent_io_tree *tree, } } - if (page->index == last_byte >> PAGE_CACHE_SHIFT) { + if (page->index == last_byte >> PAGE_SHIFT) { char *userpage; - size_t zero_offset = last_byte & (PAGE_CACHE_SIZE - 1); + size_t zero_offset = last_byte & (PAGE_SIZE - 1); if (zero_offset) { - iosize = PAGE_CACHE_SIZE - zero_offset; + iosize = PAGE_SIZE - zero_offset; userpage = kmap_atomic(page); memset(userpage + zero_offset, 0, iosize); flush_dcache_page(page); @@ -2922,14 +2922,14 @@ static int __do_readpage(struct extent_io_tree *tree, } } while (cur <= end) { - unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1; + unsigned long pnr = (last_byte >> PAGE_SHIFT) + 1; bool force_bio_submit = false; if (cur >= last_byte) { char *userpage; struct extent_state *cached = NULL; - iosize = PAGE_CACHE_SIZE - pg_offset; + iosize = PAGE_SIZE - pg_offset; userpage = kmap_atomic(page); memset(userpage + pg_offset, 0, iosize); flush_dcache_page(page); @@ -3112,7 +3112,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, for (index = 0; index < nr_pages; index++) { __do_readpage(tree, pages[index], get_extent, em_cached, bio, mirror_num, bio_flags, rw, prev_em_start); - page_cache_release(pages[index]); + put_page(pages[index]); } } @@ -3134,10 +3134,10 @@ static void __extent_readpages(struct extent_io_tree *tree, page_start = page_offset(pages[index]); if (!end) { start = page_start; - end = start + PAGE_CACHE_SIZE - 1; + end = start + PAGE_SIZE - 1; first_index = index; } else if (end + 1 == page_start) { - end += PAGE_CACHE_SIZE; + end += PAGE_SIZE; } else { __do_contiguous_readpages(tree, &pages[first_index], index - first_index, start, @@ -3145,7 +3145,7 @@ static void __extent_readpages(struct extent_io_tree *tree, bio, mirror_num, bio_flags, rw, prev_em_start); start = page_start; - end = start + PAGE_CACHE_SIZE - 1; + end = start + PAGE_SIZE - 1; first_index = index; } } @@ -3167,13 +3167,13 @@ static int __extent_read_full_page(struct extent_io_tree *tree, struct inode *inode = page->mapping->host; struct btrfs_ordered_extent *ordered; u64 start = page_offset(page); - u64 end = start + PAGE_CACHE_SIZE - 1; + u64 end = start + PAGE_SIZE - 1; int ret; while (1) { lock_extent(tree, start, end); ordered = btrfs_lookup_ordered_range(inode, start, - PAGE_CACHE_SIZE); + PAGE_SIZE); if (!ordered) break; unlock_extent(tree, start, end); @@ -3227,7 +3227,7 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode, unsigned long *nr_written) { struct extent_io_tree *tree = epd->tree; - u64 page_end = delalloc_start + PAGE_CACHE_SIZE - 1; + u64 page_end = delalloc_start + PAGE_SIZE - 1; u64 nr_delalloc; u64 delalloc_to_write = 0; u64 delalloc_end = 0; @@ -3269,8 +3269,8 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode, * PAGE_CACHE_SIZE */ delalloc_to_write += (delalloc_end - delalloc_start + - PAGE_CACHE_SIZE) >> - PAGE_CACHE_SHIFT; + PAGE_SIZE) >> + PAGE_SHIFT; delalloc_start = delalloc_end + 1; } if (wbc->nr_to_write < delalloc_to_write) { @@ -3319,7 +3319,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, { struct extent_io_tree *tree = epd->tree; u64 start = page_offset(page); - u64 page_end = start + PAGE_CACHE_SIZE - 1; + u64 page_end = start + PAGE_SIZE - 1; u64 end; u64 cur = start; u64 extent_offset; @@ -3434,7 +3434,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, if (ret) { SetPageError(page); } else { - unsigned long max_nr = (i_size >> PAGE_CACHE_SHIFT) + 1; + unsigned long max_nr = (i_size >> PAGE_SHIFT) + 1; set_range_writeback(tree, cur, cur + iosize - 1); if (!PageWriteback(page)) { @@ -3477,12 +3477,12 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, struct inode *inode = page->mapping->host; struct extent_page_data *epd = data; u64 start = page_offset(page); - u64 page_end = start + PAGE_CACHE_SIZE - 1; + u64 page_end = start + PAGE_SIZE - 1; int ret; int nr = 0; size_t pg_offset = 0; loff_t i_size = i_size_read(inode); - unsigned long end_index = i_size >> PAGE_CACHE_SHIFT; + unsigned long end_index = i_size >> PAGE_SHIFT; int write_flags; unsigned long nr_written = 0; @@ -3497,10 +3497,10 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, ClearPageError(page); - pg_offset = i_size & (PAGE_CACHE_SIZE - 1); + pg_offset = i_size & (PAGE_SIZE - 1); if (page->index > end_index || (page->index == end_index && !pg_offset)) { - page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE); + page->mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE); unlock_page(page); return 0; } @@ -3510,7 +3510,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, userpage = kmap_atomic(page); memset(userpage + pg_offset, 0, - PAGE_CACHE_SIZE - pg_offset); + PAGE_SIZE - pg_offset); kunmap_atomic(userpage); flush_dcache_page(page); } @@ -3748,7 +3748,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, clear_page_dirty_for_io(p); set_page_writeback(p); ret = submit_extent_page(rw, tree, wbc, p, offset >> 9, - PAGE_CACHE_SIZE, 0, bdev, &epd->bio, + PAGE_SIZE, 0, bdev, &epd->bio, -1, end_bio_extent_buffer_writepage, 0, epd->bio_flags, bio_flags, false); epd->bio_flags = bio_flags; @@ -3760,7 +3760,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, ret = -EIO; break; } - offset += PAGE_CACHE_SIZE; + offset += PAGE_SIZE; update_nr_written(p, wbc, 1); unlock_page(p); } @@ -3804,8 +3804,8 @@ int btree_write_cache_pages(struct address_space *mapping, index = mapping->writeback_index; /* Start from prev offset */ end = -1; } else { - index = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + index = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; scanned = 1; } if (wbc->sync_mode == WB_SYNC_ALL) @@ -3948,8 +3948,8 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, index = mapping->writeback_index; /* Start from prev offset */ end = -1; } else { - index = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + index = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; scanned = 1; } if (wbc->sync_mode == WB_SYNC_ALL) @@ -4083,8 +4083,8 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode, int ret = 0; struct address_space *mapping = inode->i_mapping; struct page *page; - unsigned long nr_pages = (end - start + PAGE_CACHE_SIZE) >> - PAGE_CACHE_SHIFT; + unsigned long nr_pages = (end - start + PAGE_SIZE) >> + PAGE_SHIFT; struct extent_page_data epd = { .bio = NULL, @@ -4102,18 +4102,18 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode, }; while (start <= end) { - page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT); + page = find_get_page(mapping, start >> PAGE_SHIFT); if (clear_page_dirty_for_io(page)) ret = __extent_writepage(page, &wbc_writepages, &epd); else { if (tree->ops && tree->ops->writepage_end_io_hook) tree->ops->writepage_end_io_hook(page, start, - start + PAGE_CACHE_SIZE - 1, + start + PAGE_SIZE - 1, NULL, 1); unlock_page(page); } - page_cache_release(page); - start += PAGE_CACHE_SIZE; + put_page(page); + start += PAGE_SIZE; } flush_epd_write_bio(&epd); @@ -4163,7 +4163,7 @@ int extent_readpages(struct extent_io_tree *tree, list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, GFP_NOFS)) { - page_cache_release(page); + put_page(page); continue; } @@ -4197,7 +4197,7 @@ int extent_invalidatepage(struct extent_io_tree *tree, { struct extent_state *cached_state = NULL; u64 start = page_offset(page); - u64 end = start + PAGE_CACHE_SIZE - 1; + u64 end = start + PAGE_SIZE - 1; size_t blocksize = page->mapping->host->i_sb->s_blocksize; start += ALIGN(offset, blocksize); @@ -4223,7 +4223,7 @@ static int try_release_extent_state(struct extent_map_tree *map, struct page *page, gfp_t mask) { u64 start = page_offset(page); - u64 end = start + PAGE_CACHE_SIZE - 1; + u64 end = start + PAGE_SIZE - 1; int ret = 1; if (test_range_bit(tree, start, end, @@ -4262,7 +4262,7 @@ int try_release_extent_mapping(struct extent_map_tree *map, { struct extent_map *em; u64 start = page_offset(page); - u64 end = start + PAGE_CACHE_SIZE - 1; + u64 end = start + PAGE_SIZE - 1; if (gfpflags_allow_blocking(mask) && page->mapping->host->i_size > SZ_16M) { @@ -4587,14 +4587,14 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb) ClearPagePrivate(page); set_page_private(page, 0); /* One for the page private */ - page_cache_release(page); + put_page(page); } if (mapped) spin_unlock(&page->mapping->private_lock); /* One for when we alloced the page */ - page_cache_release(page); + put_page(page); } while (index != 0); } @@ -4779,7 +4779,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, rcu_read_lock(); eb = radix_tree_lookup(&fs_info->buffer_radix, - start >> PAGE_CACHE_SHIFT); + start >> PAGE_SHIFT); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); /* @@ -4829,7 +4829,7 @@ again: goto free_eb; spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, - start >> PAGE_CACHE_SHIFT, eb); + start >> PAGE_SHIFT, eb); spin_unlock(&fs_info->buffer_lock); radix_tree_preload_end(); if (ret == -EEXIST) { @@ -4862,7 +4862,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, unsigned long len = fs_info->tree_root->nodesize; unsigned long num_pages = num_extent_pages(start, len); unsigned long i; - unsigned long index = start >> PAGE_CACHE_SHIFT; + unsigned long index = start >> PAGE_SHIFT; struct extent_buffer *eb; struct extent_buffer *exists = NULL; struct page *p; @@ -4896,7 +4896,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, if (atomic_inc_not_zero(&exists->refs)) { spin_unlock(&mapping->private_lock); unlock_page(p); - page_cache_release(p); + put_page(p); mark_extent_buffer_accessed(exists, p); goto free_eb; } @@ -4908,7 +4908,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, */ ClearPagePrivate(p); WARN_ON(PageDirty(p)); - page_cache_release(p); + put_page(p); } attach_extent_buffer_page(eb, p); spin_unlock(&mapping->private_lock); @@ -4931,7 +4931,7 @@ again: spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, - start >> PAGE_CACHE_SHIFT, eb); + start >> PAGE_SHIFT, eb); spin_unlock(&fs_info->buffer_lock); radix_tree_preload_end(); if (ret == -EEXIST) { @@ -4994,7 +4994,7 @@ static int release_extent_buffer(struct extent_buffer *eb) spin_lock(&fs_info->buffer_lock); radix_tree_delete(&fs_info->buffer_radix, - eb->start >> PAGE_CACHE_SHIFT); + eb->start >> PAGE_SHIFT); spin_unlock(&fs_info->buffer_lock); } else { spin_unlock(&eb->refs_lock); @@ -5168,8 +5168,8 @@ int read_extent_buffer_pages(struct extent_io_tree *tree, if (start) { WARN_ON(start < eb->start); - start_i = (start >> PAGE_CACHE_SHIFT) - - (eb->start >> PAGE_CACHE_SHIFT); + start_i = (start >> PAGE_SHIFT) - + (eb->start >> PAGE_SHIFT); } else { start_i = 0; } @@ -5252,18 +5252,18 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv, struct page *page; char *kaddr; char *dst = (char *)dstv; - size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1); - unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT; + size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1); + unsigned long i = (start_offset + start) >> PAGE_SHIFT; WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); - offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1); + offset = (start_offset + start) & (PAGE_SIZE - 1); while (len > 0) { page = eb->pages[i]; - cur = min(len, (PAGE_CACHE_SIZE - offset)); + cur = min(len, (PAGE_SIZE - offset)); kaddr = page_address(page); memcpy(dst, kaddr + offset, cur); @@ -5283,19 +5283,19 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv, struct page *page; char *kaddr; char __user *dst = (char __user *)dstv; - size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1); - unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT; + size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1); + unsigned long i = (start_offset + start) >> PAGE_SHIFT; int ret = 0; WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); - offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1); + offset = (start_offset + start) & (PAGE_SIZE - 1); while (len > 0) { page = eb->pages[i]; - cur = min(len, (PAGE_CACHE_SIZE - offset)); + cur = min(len, (PAGE_SIZE - offset)); kaddr = page_address(page); if (copy_to_user(dst, kaddr + offset, cur)) { ret = -EFAULT; @@ -5316,13 +5316,13 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, unsigned long *map_start, unsigned long *map_len) { - size_t offset = start & (PAGE_CACHE_SIZE - 1); + size_t offset = start & (PAGE_SIZE - 1); char *kaddr; struct page *p; - size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1); - unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT; + size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1); + unsigned long i = (start_offset + start) >> PAGE_SHIFT; unsigned long end_i = (start_offset + start + min_len - 1) >> - PAGE_CACHE_SHIFT; + PAGE_SHIFT; if (i != end_i) return -EINVAL; @@ -5332,7 +5332,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, *map_start = 0; } else { offset = 0; - *map_start = ((u64)i << PAGE_CACHE_SHIFT) - start_offset; + *map_start = ((u64)i << PAGE_SHIFT) - start_offset; } if (start + min_len > eb->len) { @@ -5345,7 +5345,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, p = eb->pages[i]; kaddr = page_address(p); *map = kaddr + offset; - *map_len = PAGE_CACHE_SIZE - offset; + *map_len = PAGE_SIZE - offset; return 0; } @@ -5358,19 +5358,19 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv, struct page *page; char *kaddr; char *ptr = (char *)ptrv; - size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1); - unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT; + size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1); + unsigned long i = (start_offset + start) >> PAGE_SHIFT; int ret = 0; WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); - offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1); + offset = (start_offset + start) & (PAGE_SIZE - 1); while (len > 0) { page = eb->pages[i]; - cur = min(len, (PAGE_CACHE_SIZE - offset)); + cur = min(len, (PAGE_SIZE - offset)); kaddr = page_address(page); ret = memcmp(ptr, kaddr + offset, cur); @@ -5393,19 +5393,19 @@ void write_extent_buffer(struct extent_buffer *eb, const void *srcv, struct page *page; char *kaddr; char *src = (char *)srcv; - size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1); - unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT; + size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1); + unsigned long i = (start_offset + start) >> PAGE_SHIFT; WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); - offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1); + offset = (start_offset + start) & (PAGE_SIZE - 1); while (len > 0) { page = eb->pages[i]; WARN_ON(!PageUptodate(page)); - cur = min(len, PAGE_CACHE_SIZE - offset); + cur = min(len, PAGE_SIZE - offset); kaddr = page_address(page); memcpy(kaddr + offset, src, cur); @@ -5423,19 +5423,19 @@ void memset_extent_buffer(struct extent_buffer *eb, char c, size_t offset; struct page *page; char *kaddr; - size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1); - unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT; + size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1); + unsigned long i = (start_offset + start) >> PAGE_SHIFT; WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); - offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1); + offset = (start_offset + start) & (PAGE_SIZE - 1); while (len > 0) { page = eb->pages[i]; WARN_ON(!PageUptodate(page)); - cur = min(len, PAGE_CACHE_SIZE - offset); + cur = min(len, PAGE_SIZE - offset); kaddr = page_address(page); memset(kaddr + offset, c, cur); @@ -5454,19 +5454,19 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src, size_t offset; struct page *page; char *kaddr; - size_t start_offset = dst->start & ((u64)PAGE_CACHE_SIZE - 1); - unsigned long i = (start_offset + dst_offset) >> PAGE_CACHE_SHIFT; + size_t start_offset = dst->start & ((u64)PAGE_SIZE - 1); + unsigned long i = (start_offset + dst_offset) >> PAGE_SHIFT; WARN_ON(src->len != dst_len); offset = (start_offset + dst_offset) & - (PAGE_CACHE_SIZE - 1); + (PAGE_SIZE - 1); while (len > 0) { page = dst->pages[i]; WARN_ON(!PageUptodate(page)); - cur = min(len, (unsigned long)(PAGE_CACHE_SIZE - offset)); + cur = min(len, (unsigned long)(PAGE_SIZE - offset)); kaddr = page_address(page); read_extent_buffer(src, kaddr + offset, src_offset, cur); @@ -5508,7 +5508,7 @@ static inline void eb_bitmap_offset(struct extent_buffer *eb, unsigned long *page_index, size_t *page_offset) { - size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1); + size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1); size_t byte_offset = BIT_BYTE(nr); size_t offset; @@ -5519,8 +5519,8 @@ static inline void eb_bitmap_offset(struct extent_buffer *eb, */ offset = start_offset + start + byte_offset; - *page_index = offset >> PAGE_CACHE_SHIFT; - *page_offset = offset & (PAGE_CACHE_SIZE - 1); + *page_index = offset >> PAGE_SHIFT; + *page_offset = offset & (PAGE_SIZE - 1); } /** @@ -5572,7 +5572,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start, len -= bits_to_set; bits_to_set = BITS_PER_BYTE; mask_to_set = ~0U; - if (++offset >= PAGE_CACHE_SIZE && len > 0) { + if (++offset >= PAGE_SIZE && len > 0) { offset = 0; page = eb->pages[++i]; WARN_ON(!PageUptodate(page)); @@ -5614,7 +5614,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start, len -= bits_to_clear; bits_to_clear = BITS_PER_BYTE; mask_to_clear = ~0U; - if (++offset >= PAGE_CACHE_SIZE && len > 0) { + if (++offset >= PAGE_SIZE && len > 0) { offset = 0; page = eb->pages[++i]; WARN_ON(!PageUptodate(page)); @@ -5661,7 +5661,7 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, size_t cur; size_t dst_off_in_page; size_t src_off_in_page; - size_t start_offset = dst->start & ((u64)PAGE_CACHE_SIZE - 1); + size_t start_offset = dst->start & ((u64)PAGE_SIZE - 1); unsigned long dst_i; unsigned long src_i; @@ -5680,17 +5680,17 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, while (len > 0) { dst_off_in_page = (start_offset + dst_offset) & - (PAGE_CACHE_SIZE - 1); + (PAGE_SIZE - 1); src_off_in_page = (start_offset + src_offset) & - (PAGE_CACHE_SIZE - 1); + (PAGE_SIZE - 1); - dst_i = (start_offset + dst_offset) >> PAGE_CACHE_SHIFT; - src_i = (start_offset + src_offset) >> PAGE_CACHE_SHIFT; + dst_i = (start_offset + dst_offset) >> PAGE_SHIFT; + src_i = (start_offset + src_offset) >> PAGE_SHIFT; - cur = min(len, (unsigned long)(PAGE_CACHE_SIZE - + cur = min(len, (unsigned long)(PAGE_SIZE - src_off_in_page)); cur = min_t(unsigned long, cur, - (unsigned long)(PAGE_CACHE_SIZE - dst_off_in_page)); + (unsigned long)(PAGE_SIZE - dst_off_in_page)); copy_pages(dst->pages[dst_i], dst->pages[src_i], dst_off_in_page, src_off_in_page, cur); @@ -5709,7 +5709,7 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, size_t src_off_in_page; unsigned long dst_end = dst_offset + len - 1; unsigned long src_end = src_offset + len - 1; - size_t start_offset = dst->start & ((u64)PAGE_CACHE_SIZE - 1); + size_t start_offset = dst->start & ((u64)PAGE_SIZE - 1); unsigned long dst_i; unsigned long src_i; @@ -5728,13 +5728,13 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, return; } while (len > 0) { - dst_i = (start_offset + dst_end) >> PAGE_CACHE_SHIFT; - src_i = (start_offset + src_end) >> PAGE_CACHE_SHIFT; + dst_i = (start_offset + dst_end) >> PAGE_SHIFT; + src_i = (start_offset + src_end) >> PAGE_SHIFT; dst_off_in_page = (start_offset + dst_end) & - (PAGE_CACHE_SIZE - 1); + (PAGE_SIZE - 1); src_off_in_page = (start_offset + src_end) & - (PAGE_CACHE_SIZE - 1); + (PAGE_SIZE - 1); cur = min_t(unsigned long, len, src_off_in_page + 1); cur = min(cur, dst_off_in_page + 1); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 5dbf92e68fbd..b5e0ade90e88 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -120,7 +120,7 @@ struct extent_state { }; #define INLINE_EXTENT_BUFFER_PAGES 16 -#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_CACHE_SIZE) +#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE) struct extent_buffer { u64 start; unsigned long len; @@ -365,8 +365,8 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb); static inline unsigned long num_extent_pages(u64 start, u64 len) { - return ((start + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT) - - (start >> PAGE_CACHE_SHIFT); + return ((start + len + PAGE_SIZE - 1) >> PAGE_SHIFT) - + (start >> PAGE_SHIFT); } static inline void extent_buffer_get(struct extent_buffer *eb) diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index b5baf5bdc8e1..7a7d6e253cfc 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -32,7 +32,7 @@ size) - 1)) #define MAX_CSUM_ITEMS(r, size) (min_t(u32, __MAX_CSUM_ITEMS(r, size), \ - PAGE_CACHE_SIZE)) + PAGE_SIZE)) #define MAX_ORDERED_SUM_BYTES(r) ((PAGE_SIZE - \ sizeof(struct btrfs_ordered_sum)) / \ @@ -203,7 +203,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root, csum = (u8 *)dst; } - if (bio->bi_iter.bi_size > PAGE_CACHE_SIZE * 8) + if (bio->bi_iter.bi_size > PAGE_SIZE * 8) path->reada = READA_FORWARD; WARN_ON(bio->bi_vcnt <= 0); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 15a09cb156ce..cf31a60c6284 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -414,11 +414,11 @@ static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes, size_t copied = 0; size_t total_copied = 0; int pg = 0; - int offset = pos & (PAGE_CACHE_SIZE - 1); + int offset = pos & (PAGE_SIZE - 1); while (write_bytes > 0) { size_t count = min_t(size_t, - PAGE_CACHE_SIZE - offset, write_bytes); + PAGE_SIZE - offset, write_bytes); struct page *page = prepared_pages[pg]; /* * Copy data from userspace to the current page @@ -448,7 +448,7 @@ static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes, if (unlikely(copied == 0)) break; - if (copied < PAGE_CACHE_SIZE - offset) { + if (copied < PAGE_SIZE - offset) { offset += copied; } else { pg++; @@ -473,7 +473,7 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) */ ClearPageChecked(pages[i]); unlock_page(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); } } @@ -1297,7 +1297,7 @@ static int prepare_uptodate_page(struct inode *inode, { int ret = 0; - if (((pos & (PAGE_CACHE_SIZE - 1)) || force_uptodate) && + if (((pos & (PAGE_SIZE - 1)) || force_uptodate) && !PageUptodate(page)) { ret = btrfs_readpage(NULL, page); if (ret) @@ -1323,7 +1323,7 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages, size_t write_bytes, bool force_uptodate) { int i; - unsigned long index = pos >> PAGE_CACHE_SHIFT; + unsigned long index = pos >> PAGE_SHIFT; gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); int err = 0; int faili; @@ -1345,7 +1345,7 @@ again: err = prepare_uptodate_page(inode, pages[i], pos + write_bytes, false); if (err) { - page_cache_release(pages[i]); + put_page(pages[i]); if (err == -EAGAIN) { err = 0; goto again; @@ -1360,7 +1360,7 @@ again: fail: while (faili >= 0) { unlock_page(pages[faili]); - page_cache_release(pages[faili]); + put_page(pages[faili]); faili--; } return err; @@ -1408,7 +1408,7 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages, cached_state, GFP_NOFS); for (i = 0; i < num_pages; i++) { unlock_page(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); } btrfs_start_ordered_extent(inode, ordered, 1); btrfs_put_ordered_extent(ordered); @@ -1497,8 +1497,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, bool force_page_uptodate = false; bool need_unlock; - nrptrs = min(DIV_ROUND_UP(iov_iter_count(i), PAGE_CACHE_SIZE), - PAGE_CACHE_SIZE / (sizeof(struct page *))); + nrptrs = min(DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE), + PAGE_SIZE / (sizeof(struct page *))); nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied); nrptrs = max(nrptrs, 8); pages = kmalloc_array(nrptrs, sizeof(struct page *), GFP_KERNEL); @@ -1506,13 +1506,13 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, return -ENOMEM; while (iov_iter_count(i) > 0) { - size_t offset = pos & (PAGE_CACHE_SIZE - 1); + size_t offset = pos & (PAGE_SIZE - 1); size_t sector_offset; size_t write_bytes = min(iov_iter_count(i), - nrptrs * (size_t)PAGE_CACHE_SIZE - + nrptrs * (size_t)PAGE_SIZE - offset); size_t num_pages = DIV_ROUND_UP(write_bytes + offset, - PAGE_CACHE_SIZE); + PAGE_SIZE); size_t reserve_bytes; size_t dirty_pages; size_t copied; @@ -1547,7 +1547,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, * write_bytes, so scale down. */ num_pages = DIV_ROUND_UP(write_bytes + offset, - PAGE_CACHE_SIZE); + PAGE_SIZE); reserve_bytes = round_up(write_bytes + sector_offset, root->sectorsize); goto reserve_metadata; @@ -1609,7 +1609,7 @@ again: } else { force_page_uptodate = false; dirty_pages = DIV_ROUND_UP(copied + offset, - PAGE_CACHE_SIZE); + PAGE_SIZE); } /* @@ -1641,7 +1641,7 @@ again: u64 __pos; __pos = round_down(pos, root->sectorsize) + - (dirty_pages << PAGE_CACHE_SHIFT); + (dirty_pages << PAGE_SHIFT); btrfs_delalloc_release_space(inode, __pos, release_bytes); } @@ -1682,7 +1682,7 @@ again: cond_resched(); balance_dirty_pages_ratelimited(inode->i_mapping); - if (dirty_pages < (root->nodesize >> PAGE_CACHE_SHIFT) + 1) + if (dirty_pages < (root->nodesize >> PAGE_SHIFT) + 1) btrfs_btree_balance_dirty(root); pos += copied; @@ -1738,8 +1738,8 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, goto out; written += written_buffered; iocb->ki_pos = pos + written_buffered; - invalidate_mapping_pages(file->f_mapping, pos >> PAGE_CACHE_SHIFT, - endbyte >> PAGE_CACHE_SHIFT); + invalidate_mapping_pages(file->f_mapping, pos >> PAGE_SHIFT, + endbyte >> PAGE_SHIFT); out: return written ? written : err; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 8f835bfa1bdd..5e6062c26129 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -29,7 +29,7 @@ #include "inode-map.h" #include "volumes.h" -#define BITS_PER_BITMAP (PAGE_CACHE_SIZE * 8) +#define BITS_PER_BITMAP (PAGE_SIZE * 8) #define MAX_CACHE_BYTES_PER_GIG SZ_32K struct btrfs_trim_range { @@ -295,7 +295,7 @@ static int readahead_cache(struct inode *inode) return -ENOMEM; file_ra_state_init(ra, inode->i_mapping); - last_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT; + last_index = (i_size_read(inode) - 1) >> PAGE_SHIFT; page_cache_sync_readahead(inode->i_mapping, ra, NULL, 0, last_index); @@ -310,14 +310,14 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, int num_pages; int check_crcs = 0; - num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); + num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID) check_crcs = 1; /* Make sure we can fit our crcs into the first page */ if (write && check_crcs && - (num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE) + (num_pages * sizeof(u32)) >= PAGE_SIZE) return -ENOSPC; memset(io_ctl, 0, sizeof(struct btrfs_io_ctl)); @@ -354,9 +354,9 @@ static void io_ctl_map_page(struct btrfs_io_ctl *io_ctl, int clear) io_ctl->page = io_ctl->pages[io_ctl->index++]; io_ctl->cur = page_address(io_ctl->page); io_ctl->orig = io_ctl->cur; - io_ctl->size = PAGE_CACHE_SIZE; + io_ctl->size = PAGE_SIZE; if (clear) - memset(io_ctl->cur, 0, PAGE_CACHE_SIZE); + memset(io_ctl->cur, 0, PAGE_SIZE); } static void io_ctl_drop_pages(struct btrfs_io_ctl *io_ctl) @@ -369,7 +369,7 @@ static void io_ctl_drop_pages(struct btrfs_io_ctl *io_ctl) if (io_ctl->pages[i]) { ClearPageChecked(io_ctl->pages[i]); unlock_page(io_ctl->pages[i]); - page_cache_release(io_ctl->pages[i]); + put_page(io_ctl->pages[i]); } } } @@ -475,7 +475,7 @@ static void io_ctl_set_crc(struct btrfs_io_ctl *io_ctl, int index) offset = sizeof(u32) * io_ctl->num_pages; crc = btrfs_csum_data(io_ctl->orig + offset, crc, - PAGE_CACHE_SIZE - offset); + PAGE_SIZE - offset); btrfs_csum_final(crc, (char *)&crc); io_ctl_unmap_page(io_ctl); tmp = page_address(io_ctl->pages[0]); @@ -503,7 +503,7 @@ static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index) io_ctl_map_page(io_ctl, 0); crc = btrfs_csum_data(io_ctl->orig + offset, crc, - PAGE_CACHE_SIZE - offset); + PAGE_SIZE - offset); btrfs_csum_final(crc, (char *)&crc); if (val != crc) { btrfs_err_rl(io_ctl->root->fs_info, @@ -561,7 +561,7 @@ static int io_ctl_add_bitmap(struct btrfs_io_ctl *io_ctl, void *bitmap) io_ctl_map_page(io_ctl, 0); } - memcpy(io_ctl->cur, bitmap, PAGE_CACHE_SIZE); + memcpy(io_ctl->cur, bitmap, PAGE_SIZE); io_ctl_set_crc(io_ctl, io_ctl->index - 1); if (io_ctl->index < io_ctl->num_pages) io_ctl_map_page(io_ctl, 0); @@ -621,7 +621,7 @@ static int io_ctl_read_bitmap(struct btrfs_io_ctl *io_ctl, if (ret) return ret; - memcpy(entry->bitmap, io_ctl->cur, PAGE_CACHE_SIZE); + memcpy(entry->bitmap, io_ctl->cur, PAGE_SIZE); io_ctl_unmap_page(io_ctl); return 0; @@ -775,7 +775,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, } else { ASSERT(num_bitmaps); num_bitmaps--; - e->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS); + e->bitmap = kzalloc(PAGE_SIZE, GFP_NOFS); if (!e->bitmap) { kmem_cache_free( btrfs_free_space_cachep, e); @@ -1660,7 +1660,7 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) * sure we don't go over our overall goal of MAX_CACHE_BYTES_PER_GIG as * we add more bitmaps. */ - bitmap_bytes = (ctl->total_bitmaps + 1) * PAGE_CACHE_SIZE; + bitmap_bytes = (ctl->total_bitmaps + 1) * PAGE_SIZE; if (bitmap_bytes >= max_bytes) { ctl->extents_thresh = 0; @@ -2111,7 +2111,7 @@ new_bitmap: } /* allocate the bitmap */ - info->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS); + info->bitmap = kzalloc(PAGE_SIZE, GFP_NOFS); spin_lock(&ctl->tree_lock); if (!info->bitmap) { ret = -ENOMEM; @@ -3580,7 +3580,7 @@ again: } if (!map) { - map = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS); + map = kzalloc(PAGE_SIZE, GFP_NOFS); if (!map) { kmem_cache_free(btrfs_free_space_cachep, info); return -ENOMEM; diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 1f0ec19b23f6..70107f7c9307 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -283,7 +283,7 @@ void btrfs_unpin_free_ino(struct btrfs_root *root) } #define INIT_THRESHOLD ((SZ_32K / 2) / sizeof(struct btrfs_free_space)) -#define INODES_PER_BITMAP (PAGE_CACHE_SIZE * 8) +#define INODES_PER_BITMAP (PAGE_SIZE * 8) /* * The goal is to keep the memory used by the free_ino tree won't @@ -317,7 +317,7 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) } ctl->extents_thresh = (max_bitmaps - ctl->total_bitmaps) * - PAGE_CACHE_SIZE / sizeof(*info); + PAGE_SIZE / sizeof(*info); } /* @@ -481,12 +481,12 @@ again: spin_lock(&ctl->tree_lock); prealloc = sizeof(struct btrfs_free_space) * ctl->free_extents; - prealloc = ALIGN(prealloc, PAGE_CACHE_SIZE); - prealloc += ctl->total_bitmaps * PAGE_CACHE_SIZE; + prealloc = ALIGN(prealloc, PAGE_SIZE); + prealloc += ctl->total_bitmaps * PAGE_SIZE; spin_unlock(&ctl->tree_lock); /* Just to make sure we have enough space */ - prealloc += 8 * PAGE_CACHE_SIZE; + prealloc += 8 * PAGE_SIZE; ret = btrfs_delalloc_reserve_space(inode, 0, prealloc); if (ret) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 41a5688ffdfe..2aaba58b4856 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -194,7 +194,7 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, while (compressed_size > 0) { cpage = compressed_pages[i]; cur_size = min_t(unsigned long, compressed_size, - PAGE_CACHE_SIZE); + PAGE_SIZE); kaddr = kmap_atomic(cpage); write_extent_buffer(leaf, kaddr, ptr, cur_size); @@ -208,13 +208,13 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, compress_type); } else { page = find_get_page(inode->i_mapping, - start >> PAGE_CACHE_SHIFT); + start >> PAGE_SHIFT); btrfs_set_file_extent_compression(leaf, ei, 0); kaddr = kmap_atomic(page); - offset = start & (PAGE_CACHE_SIZE - 1); + offset = start & (PAGE_SIZE - 1); write_extent_buffer(leaf, kaddr + offset, ptr, size); kunmap_atomic(kaddr); - page_cache_release(page); + put_page(page); } btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); @@ -322,7 +322,7 @@ out: * And at reserve time, it's always aligned to page size, so * just free one page here. */ - btrfs_qgroup_free_data(inode, 0, PAGE_CACHE_SIZE); + btrfs_qgroup_free_data(inode, 0, PAGE_SIZE); btrfs_free_path(path); btrfs_end_transaction(trans, root); return ret; @@ -435,8 +435,8 @@ static noinline void compress_file_range(struct inode *inode, actual_end = min_t(u64, isize, end + 1); again: will_compress = 0; - nr_pages = (end >> PAGE_CACHE_SHIFT) - (start >> PAGE_CACHE_SHIFT) + 1; - nr_pages = min_t(unsigned long, nr_pages, SZ_128K / PAGE_CACHE_SIZE); + nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1; + nr_pages = min_t(unsigned long, nr_pages, SZ_128K / PAGE_SIZE); /* * we don't want to send crud past the end of i_size through @@ -514,7 +514,7 @@ again: if (!ret) { unsigned long offset = total_compressed & - (PAGE_CACHE_SIZE - 1); + (PAGE_SIZE - 1); struct page *page = pages[nr_pages_ret - 1]; char *kaddr; @@ -524,7 +524,7 @@ again: if (offset) { kaddr = kmap_atomic(page); memset(kaddr + offset, 0, - PAGE_CACHE_SIZE - offset); + PAGE_SIZE - offset); kunmap_atomic(kaddr); } will_compress = 1; @@ -580,7 +580,7 @@ cont: * one last check to make sure the compression is really a * win, compare the page count read with the blocks on disk */ - total_in = ALIGN(total_in, PAGE_CACHE_SIZE); + total_in = ALIGN(total_in, PAGE_SIZE); if (total_compressed >= total_in) { will_compress = 0; } else { @@ -594,7 +594,7 @@ cont: */ for (i = 0; i < nr_pages_ret; i++) { WARN_ON(pages[i]->mapping); - page_cache_release(pages[i]); + put_page(pages[i]); } kfree(pages); pages = NULL; @@ -650,7 +650,7 @@ cleanup_and_bail_uncompressed: free_pages_out: for (i = 0; i < nr_pages_ret; i++) { WARN_ON(pages[i]->mapping); - page_cache_release(pages[i]); + put_page(pages[i]); } kfree(pages); } @@ -664,7 +664,7 @@ static void free_async_extent_pages(struct async_extent *async_extent) for (i = 0; i < async_extent->nr_pages; i++) { WARN_ON(async_extent->pages[i]->mapping); - page_cache_release(async_extent->pages[i]); + put_page(async_extent->pages[i]); } kfree(async_extent->pages); async_extent->nr_pages = 0; @@ -966,7 +966,7 @@ static noinline int cow_file_range(struct inode *inode, PAGE_END_WRITEBACK); *nr_written = *nr_written + - (end - start + PAGE_CACHE_SIZE) / PAGE_CACHE_SIZE; + (end - start + PAGE_SIZE) / PAGE_SIZE; *page_started = 1; goto out; } else if (ret < 0) { @@ -1106,8 +1106,8 @@ static noinline void async_cow_submit(struct btrfs_work *work) async_cow = container_of(work, struct async_cow, work); root = async_cow->root; - nr_pages = (async_cow->end - async_cow->start + PAGE_CACHE_SIZE) >> - PAGE_CACHE_SHIFT; + nr_pages = (async_cow->end - async_cow->start + PAGE_SIZE) >> + PAGE_SHIFT; /* * atomic_sub_return implies a barrier for waitqueue_active @@ -1164,8 +1164,8 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page, async_cow_start, async_cow_submit, async_cow_free); - nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >> - PAGE_CACHE_SHIFT; + nr_pages = (cur_end - start + PAGE_SIZE) >> + PAGE_SHIFT; atomic_add(nr_pages, &root->fs_info->async_delalloc_pages); btrfs_queue_work(root->fs_info->delalloc_workers, @@ -1960,7 +1960,7 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans, int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, struct extent_state **cached_state) { - WARN_ON((end & (PAGE_CACHE_SIZE - 1)) == 0); + WARN_ON((end & (PAGE_SIZE - 1)) == 0); return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end, cached_state, GFP_NOFS); } @@ -1993,7 +1993,7 @@ again: inode = page->mapping->host; page_start = page_offset(page); - page_end = page_offset(page) + PAGE_CACHE_SIZE - 1; + page_end = page_offset(page) + PAGE_SIZE - 1; lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end, &cached_state); @@ -2003,7 +2003,7 @@ again: goto out; ordered = btrfs_lookup_ordered_range(inode, page_start, - PAGE_CACHE_SIZE); + PAGE_SIZE); if (ordered) { unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end, &cached_state, GFP_NOFS); @@ -2014,7 +2014,7 @@ again: } ret = btrfs_delalloc_reserve_space(inode, page_start, - PAGE_CACHE_SIZE); + PAGE_SIZE); if (ret) { mapping_set_error(page->mapping, ret); end_extent_writepage(page, ret, page_start, page_end); @@ -2030,7 +2030,7 @@ out: &cached_state, GFP_NOFS); out_page: unlock_page(page); - page_cache_release(page); + put_page(page); kfree(fixup); } @@ -2063,7 +2063,7 @@ static int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end) return -EAGAIN; SetPageChecked(page); - page_cache_get(page); + get_page(page); btrfs_init_work(&fixup->work, btrfs_fixup_helper, btrfs_writepage_fixup_worker, NULL, NULL); fixup->page = page; @@ -4247,7 +4247,7 @@ static int truncate_inline_extent(struct inode *inode, if (btrfs_file_extent_compression(leaf, fi) != BTRFS_COMPRESS_NONE) { loff_t offset = new_size; - loff_t page_end = ALIGN(offset, PAGE_CACHE_SIZE); + loff_t page_end = ALIGN(offset, PAGE_SIZE); /* * Zero out the remaining of the last page of our inline extent, @@ -4633,7 +4633,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, struct extent_state *cached_state = NULL; char *kaddr; u32 blocksize = root->sectorsize; - pgoff_t index = from >> PAGE_CACHE_SHIFT; + pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (blocksize - 1); struct page *page; gfp_t mask = btrfs_alloc_write_mask(mapping); @@ -4668,7 +4668,7 @@ again: lock_page(page); if (page->mapping != mapping) { unlock_page(page); - page_cache_release(page); + put_page(page); goto again; } if (!PageUptodate(page)) { @@ -4686,7 +4686,7 @@ again: unlock_extent_cached(io_tree, block_start, block_end, &cached_state, GFP_NOFS); unlock_page(page); - page_cache_release(page); + put_page(page); btrfs_start_ordered_extent(inode, ordered, 1); btrfs_put_ordered_extent(ordered); goto again; @@ -4728,7 +4728,7 @@ out_unlock: btrfs_delalloc_release_space(inode, block_start, blocksize); unlock_page(page); - page_cache_release(page); + put_page(page); out: return ret; } @@ -6717,7 +6717,7 @@ static noinline int uncompress_inline(struct btrfs_path *path, read_extent_buffer(leaf, tmp, ptr, inline_size); - max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size); + max_size = min_t(unsigned long, PAGE_SIZE, max_size); ret = btrfs_decompress(compress_type, tmp, page, extent_offset, inline_size, max_size); kfree(tmp); @@ -6879,8 +6879,8 @@ next: size = btrfs_file_extent_inline_len(leaf, path->slots[0], item); extent_offset = page_offset(page) + pg_offset - extent_start; - copy_size = min_t(u64, PAGE_CACHE_SIZE - pg_offset, - size - extent_offset); + copy_size = min_t(u64, PAGE_SIZE - pg_offset, + size - extent_offset); em->start = extent_start + extent_offset; em->len = ALIGN(copy_size, root->sectorsize); em->orig_block_len = em->len; @@ -6899,9 +6899,9 @@ next: map = kmap(page); read_extent_buffer(leaf, map + pg_offset, ptr, copy_size); - if (pg_offset + copy_size < PAGE_CACHE_SIZE) { + if (pg_offset + copy_size < PAGE_SIZE) { memset(map + pg_offset + copy_size, 0, - PAGE_CACHE_SIZE - pg_offset - + PAGE_SIZE - pg_offset - copy_size); } kunmap(page); @@ -7336,12 +7336,12 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end) int start_idx; int end_idx; - start_idx = start >> PAGE_CACHE_SHIFT; + start_idx = start >> PAGE_SHIFT; /* * end is the last byte in the last page. end == start is legal */ - end_idx = end >> PAGE_CACHE_SHIFT; + end_idx = end >> PAGE_SHIFT; rcu_read_lock(); @@ -7382,7 +7382,7 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end) * include/linux/pagemap.h for details. */ if (unlikely(page != *pagep)) { - page_cache_release(page); + put_page(page); page = NULL; } } @@ -7390,7 +7390,7 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end) if (page) { if (page->index <= end_idx) found = true; - page_cache_release(page); + put_page(page); } rcu_read_unlock(); @@ -8719,7 +8719,7 @@ static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags) if (ret == 1) { ClearPagePrivate(page); set_page_private(page, 0); - page_cache_release(page); + put_page(page); } return ret; } @@ -8739,7 +8739,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; u64 page_start = page_offset(page); - u64 page_end = page_start + PAGE_CACHE_SIZE - 1; + u64 page_end = page_start + PAGE_SIZE - 1; u64 start; u64 end; int inode_evicting = inode->i_state & I_FREEING; @@ -8822,7 +8822,7 @@ again: * 2) Not written to disk * This means the reserved space should be freed here. */ - btrfs_qgroup_free_data(inode, page_start, PAGE_CACHE_SIZE); + btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DIRTY | @@ -8837,7 +8837,7 @@ again: if (PagePrivate(page)) { ClearPagePrivate(page); set_page_private(page, 0); - page_cache_release(page); + put_page(page); } } @@ -8874,11 +8874,11 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) u64 page_end; u64 end; - reserved_space = PAGE_CACHE_SIZE; + reserved_space = PAGE_SIZE; sb_start_pagefault(inode->i_sb); page_start = page_offset(page); - page_end = page_start + PAGE_CACHE_SIZE - 1; + page_end = page_start + PAGE_SIZE - 1; end = page_end; /* @@ -8934,15 +8934,15 @@ again: goto again; } - if (page->index == ((size - 1) >> PAGE_CACHE_SHIFT)) { + if (page->index == ((size - 1) >> PAGE_SHIFT)) { reserved_space = round_up(size - page_start, root->sectorsize); - if (reserved_space < PAGE_CACHE_SIZE) { + if (reserved_space < PAGE_SIZE) { end = page_start + reserved_space - 1; spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(inode, page_start, - PAGE_CACHE_SIZE - reserved_space); + PAGE_SIZE - reserved_space); } } @@ -8969,14 +8969,14 @@ again: ret = 0; /* page is wholly or partially inside EOF */ - if (page_start + PAGE_CACHE_SIZE > size) - zero_start = size & ~PAGE_CACHE_MASK; + if (page_start + PAGE_SIZE > size) + zero_start = size & ~PAGE_MASK; else - zero_start = PAGE_CACHE_SIZE; + zero_start = PAGE_SIZE; - if (zero_start != PAGE_CACHE_SIZE) { + if (zero_start != PAGE_SIZE) { kaddr = kmap(page); - memset(kaddr + zero_start, 0, PAGE_CACHE_SIZE - zero_start); + memset(kaddr + zero_start, 0, PAGE_SIZE - zero_start); flush_dcache_page(page); kunmap(page); } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 053e677839fe..94a0c8a3e871 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -898,7 +898,7 @@ static int check_defrag_in_cache(struct inode *inode, u64 offset, u32 thresh) u64 end; read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, offset, PAGE_CACHE_SIZE); + em = lookup_extent_mapping(em_tree, offset, PAGE_SIZE); read_unlock(&em_tree->lock); if (em) { @@ -988,7 +988,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start) struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_map *em; - u64 len = PAGE_CACHE_SIZE; + u64 len = PAGE_SIZE; /* * hopefully we have this extent in the tree already, try without @@ -1124,15 +1124,15 @@ static int cluster_pages_for_defrag(struct inode *inode, struct extent_io_tree *tree; gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); - file_end = (isize - 1) >> PAGE_CACHE_SHIFT; + file_end = (isize - 1) >> PAGE_SHIFT; if (!isize || start_index > file_end) return 0; page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); ret = btrfs_delalloc_reserve_space(inode, - start_index << PAGE_CACHE_SHIFT, - page_cnt << PAGE_CACHE_SHIFT); + start_index << PAGE_SHIFT, + page_cnt << PAGE_SHIFT); if (ret) return ret; i_done = 0; @@ -1148,7 +1148,7 @@ again: break; page_start = page_offset(page); - page_end = page_start + PAGE_CACHE_SIZE - 1; + page_end = page_start + PAGE_SIZE - 1; while (1) { lock_extent_bits(tree, page_start, page_end, &cached_state); @@ -1169,7 +1169,7 @@ again: */ if (page->mapping != inode->i_mapping) { unlock_page(page); - page_cache_release(page); + put_page(page); goto again; } } @@ -1179,7 +1179,7 @@ again: lock_page(page); if (!PageUptodate(page)) { unlock_page(page); - page_cache_release(page); + put_page(page); ret = -EIO; break; } @@ -1187,7 +1187,7 @@ again: if (page->mapping != inode->i_mapping) { unlock_page(page); - page_cache_release(page); + put_page(page); goto again; } @@ -1208,7 +1208,7 @@ again: wait_on_page_writeback(pages[i]); page_start = page_offset(pages[0]); - page_end = page_offset(pages[i_done - 1]) + PAGE_CACHE_SIZE; + page_end = page_offset(pages[i_done - 1]) + PAGE_SIZE; lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end - 1, &cached_state); @@ -1222,8 +1222,8 @@ again: BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(inode, - start_index << PAGE_CACHE_SHIFT, - (page_cnt - i_done) << PAGE_CACHE_SHIFT); + start_index << PAGE_SHIFT, + (page_cnt - i_done) << PAGE_SHIFT); } @@ -1240,17 +1240,17 @@ again: set_page_extent_mapped(pages[i]); set_page_dirty(pages[i]); unlock_page(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); } return i_done; out: for (i = 0; i < i_done; i++) { unlock_page(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); } btrfs_delalloc_release_space(inode, - start_index << PAGE_CACHE_SHIFT, - page_cnt << PAGE_CACHE_SHIFT); + start_index << PAGE_SHIFT, + page_cnt << PAGE_SHIFT); return ret; } @@ -1273,7 +1273,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, int defrag_count = 0; int compress_type = BTRFS_COMPRESS_ZLIB; u32 extent_thresh = range->extent_thresh; - unsigned long max_cluster = SZ_256K >> PAGE_CACHE_SHIFT; + unsigned long max_cluster = SZ_256K >> PAGE_SHIFT; unsigned long cluster = max_cluster; u64 new_align = ~((u64)SZ_128K - 1); struct page **pages = NULL; @@ -1317,9 +1317,9 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, /* find the last page to defrag */ if (range->start + range->len > range->start) { last_index = min_t(u64, isize - 1, - range->start + range->len - 1) >> PAGE_CACHE_SHIFT; + range->start + range->len - 1) >> PAGE_SHIFT; } else { - last_index = (isize - 1) >> PAGE_CACHE_SHIFT; + last_index = (isize - 1) >> PAGE_SHIFT; } if (newer_than) { @@ -1331,11 +1331,11 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, * we always align our defrag to help keep * the extents in the file evenly spaced */ - i = (newer_off & new_align) >> PAGE_CACHE_SHIFT; + i = (newer_off & new_align) >> PAGE_SHIFT; } else goto out_ra; } else { - i = range->start >> PAGE_CACHE_SHIFT; + i = range->start >> PAGE_SHIFT; } if (!max_to_defrag) max_to_defrag = last_index - i + 1; @@ -1348,7 +1348,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, inode->i_mapping->writeback_index = i; while (i <= last_index && defrag_count < max_to_defrag && - (i < DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE))) { + (i < DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE))) { /* * make sure we stop running if someone unmounts * the FS @@ -1362,7 +1362,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, break; } - if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT, + if (!should_defrag_range(inode, (u64)i << PAGE_SHIFT, extent_thresh, &last_len, &skip, &defrag_end, range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { @@ -1371,14 +1371,14 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, * the should_defrag function tells us how much to skip * bump our counter by the suggested amount */ - next = DIV_ROUND_UP(skip, PAGE_CACHE_SIZE); + next = DIV_ROUND_UP(skip, PAGE_SIZE); i = max(i + 1, next); continue; } if (!newer_than) { - cluster = (PAGE_CACHE_ALIGN(defrag_end) >> - PAGE_CACHE_SHIFT) - i; + cluster = (PAGE_ALIGN(defrag_end) >> + PAGE_SHIFT) - i; cluster = min(cluster, max_cluster); } else { cluster = max_cluster; @@ -1412,20 +1412,20 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, i += ret; newer_off = max(newer_off + 1, - (u64)i << PAGE_CACHE_SHIFT); + (u64)i << PAGE_SHIFT); ret = find_new_extents(root, inode, newer_than, &newer_off, SZ_64K); if (!ret) { range->start = newer_off; - i = (newer_off & new_align) >> PAGE_CACHE_SHIFT; + i = (newer_off & new_align) >> PAGE_SHIFT; } else { break; } } else { if (ret > 0) { i += ret; - last_len += ret << PAGE_CACHE_SHIFT; + last_len += ret << PAGE_SHIFT; } else { i++; last_len = 0; @@ -1722,7 +1722,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, if (vol_args->flags & BTRFS_SUBVOL_RDONLY) readonly = true; if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) { - if (vol_args->size > PAGE_CACHE_SIZE) { + if (vol_args->size > PAGE_SIZE) { ret = -EINVAL; goto free_args; } @@ -2806,12 +2806,12 @@ static struct page *extent_same_get_page(struct inode *inode, pgoff_t index) lock_page(page); if (!PageUptodate(page)) { unlock_page(page); - page_cache_release(page); + put_page(page); return ERR_PTR(-EIO); } if (page->mapping != inode->i_mapping) { unlock_page(page); - page_cache_release(page); + put_page(page); return ERR_PTR(-EAGAIN); } } @@ -2823,7 +2823,7 @@ static int gather_extent_pages(struct inode *inode, struct page **pages, int num_pages, u64 off) { int i; - pgoff_t index = off >> PAGE_CACHE_SHIFT; + pgoff_t index = off >> PAGE_SHIFT; for (i = 0; i < num_pages; i++) { again: @@ -2932,12 +2932,12 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp) pg = cmp->src_pages[i]; if (pg) { unlock_page(pg); - page_cache_release(pg); + put_page(pg); } pg = cmp->dst_pages[i]; if (pg) { unlock_page(pg); - page_cache_release(pg); + put_page(pg); } } kfree(cmp->src_pages); @@ -2949,7 +2949,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff, u64 len, struct cmp_pages *cmp) { int ret; - int num_pages = PAGE_CACHE_ALIGN(len) >> PAGE_CACHE_SHIFT; + int num_pages = PAGE_ALIGN(len) >> PAGE_SHIFT; struct page **src_pgarr, **dst_pgarr; /* @@ -2987,12 +2987,12 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst, int ret = 0; int i; struct page *src_page, *dst_page; - unsigned int cmp_len = PAGE_CACHE_SIZE; + unsigned int cmp_len = PAGE_SIZE; void *addr, *dst_addr; i = 0; while (len) { - if (len < PAGE_CACHE_SIZE) + if (len < PAGE_SIZE) cmp_len = len; BUG_ON(i >= cmp->num_pages); @@ -3191,7 +3191,7 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen, if (olen > BTRFS_MAX_DEDUPE_LEN) olen = BTRFS_MAX_DEDUPE_LEN; - if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) { + if (WARN_ON_ONCE(bs < PAGE_SIZE)) { /* * Btrfs does not support blocksize < page_size. As a * result, btrfs_cmp_data() won't correctly handle @@ -3891,8 +3891,8 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, * data immediately and not the previous data. */ truncate_inode_pages_range(&inode->i_data, - round_down(destoff, PAGE_CACHE_SIZE), - round_up(destoff + len, PAGE_CACHE_SIZE) - 1); + round_down(destoff, PAGE_SIZE), + round_up(destoff + len, PAGE_SIZE) - 1); out_unlock: if (!same_inode) btrfs_double_inode_unlock(src, inode); @@ -4124,7 +4124,7 @@ static long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) /* we generally have at most 6 or so space infos, one for each raid * level. So, a whole page should be more than enough for everyone */ - if (alloc_size > PAGE_CACHE_SIZE) + if (alloc_size > PAGE_SIZE) return -ENOMEM; space_args.total_spaces = 0; diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index a2f051347731..1adfbe7be6b8 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -55,8 +55,8 @@ static struct list_head *lzo_alloc_workspace(void) return ERR_PTR(-ENOMEM); workspace->mem = vmalloc(LZO1X_MEM_COMPRESS); - workspace->buf = vmalloc(lzo1x_worst_compress(PAGE_CACHE_SIZE)); - workspace->cbuf = vmalloc(lzo1x_worst_compress(PAGE_CACHE_SIZE)); + workspace->buf = vmalloc(lzo1x_worst_compress(PAGE_SIZE)); + workspace->cbuf = vmalloc(lzo1x_worst_compress(PAGE_SIZE)); if (!workspace->mem || !workspace->buf || !workspace->cbuf) goto fail; @@ -116,7 +116,7 @@ static int lzo_compress_pages(struct list_head *ws, *total_out = 0; *total_in = 0; - in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT); + in_page = find_get_page(mapping, start >> PAGE_SHIFT); data_in = kmap(in_page); /* @@ -133,10 +133,10 @@ static int lzo_compress_pages(struct list_head *ws, tot_out = LZO_LEN; pages[0] = out_page; nr_pages = 1; - pg_bytes_left = PAGE_CACHE_SIZE - LZO_LEN; + pg_bytes_left = PAGE_SIZE - LZO_LEN; /* compress at most one page of data each time */ - in_len = min(len, PAGE_CACHE_SIZE); + in_len = min(len, PAGE_SIZE); while (tot_in < len) { ret = lzo1x_1_compress(data_in, in_len, workspace->cbuf, &out_len, workspace->mem); @@ -201,7 +201,7 @@ static int lzo_compress_pages(struct list_head *ws, cpage_out = kmap(out_page); pages[nr_pages++] = out_page; - pg_bytes_left = PAGE_CACHE_SIZE; + pg_bytes_left = PAGE_SIZE; out_offset = 0; } } @@ -221,12 +221,12 @@ static int lzo_compress_pages(struct list_head *ws, bytes_left = len - tot_in; kunmap(in_page); - page_cache_release(in_page); + put_page(in_page); - start += PAGE_CACHE_SIZE; - in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT); + start += PAGE_SIZE; + in_page = find_get_page(mapping, start >> PAGE_SHIFT); data_in = kmap(in_page); - in_len = min(bytes_left, PAGE_CACHE_SIZE); + in_len = min(bytes_left, PAGE_SIZE); } if (tot_out > tot_in) @@ -248,7 +248,7 @@ out: if (in_page) { kunmap(in_page); - page_cache_release(in_page); + put_page(in_page); } return ret; @@ -266,7 +266,7 @@ static int lzo_decompress_biovec(struct list_head *ws, char *data_in; unsigned long page_in_index = 0; unsigned long page_out_index = 0; - unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_CACHE_SIZE); + unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE); unsigned long buf_start; unsigned long buf_offset = 0; unsigned long bytes; @@ -289,7 +289,7 @@ static int lzo_decompress_biovec(struct list_head *ws, tot_in = LZO_LEN; in_offset = LZO_LEN; tot_len = min_t(size_t, srclen, tot_len); - in_page_bytes_left = PAGE_CACHE_SIZE - LZO_LEN; + in_page_bytes_left = PAGE_SIZE - LZO_LEN; tot_out = 0; pg_offset = 0; @@ -345,12 +345,12 @@ cont: data_in = kmap(pages_in[++page_in_index]); - in_page_bytes_left = PAGE_CACHE_SIZE; + in_page_bytes_left = PAGE_SIZE; in_offset = 0; } } - out_len = lzo1x_worst_compress(PAGE_CACHE_SIZE); + out_len = lzo1x_worst_compress(PAGE_SIZE); ret = lzo1x_decompress_safe(buf, in_len, workspace->buf, &out_len); if (need_unmap) @@ -399,7 +399,7 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in, in_len = read_compress_length(data_in); data_in += LZO_LEN; - out_len = PAGE_CACHE_SIZE; + out_len = PAGE_SIZE; ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len); if (ret != LZO_E_OK) { printk(KERN_WARNING "BTRFS: decompress failed!\n"); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 55161369fab1..0b7792e02dd5 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -270,7 +270,7 @@ static void cache_rbio_pages(struct btrfs_raid_bio *rbio) s = kmap(rbio->bio_pages[i]); d = kmap(rbio->stripe_pages[i]); - memcpy(d, s, PAGE_CACHE_SIZE); + memcpy(d, s, PAGE_SIZE); kunmap(rbio->bio_pages[i]); kunmap(rbio->stripe_pages[i]); @@ -962,7 +962,7 @@ static struct page *page_in_rbio(struct btrfs_raid_bio *rbio, */ static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes) { - return DIV_ROUND_UP(stripe_len, PAGE_CACHE_SIZE) * nr_stripes; + return DIV_ROUND_UP(stripe_len, PAGE_SIZE) * nr_stripes; } /* @@ -1078,7 +1078,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, u64 disk_start; stripe = &rbio->bbio->stripes[stripe_nr]; - disk_start = stripe->physical + (page_index << PAGE_CACHE_SHIFT); + disk_start = stripe->physical + (page_index << PAGE_SHIFT); /* if the device is missing, just fail this stripe */ if (!stripe->dev->bdev) @@ -1096,8 +1096,8 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, if (last_end == disk_start && stripe->dev->bdev && !last->bi_error && last->bi_bdev == stripe->dev->bdev) { - ret = bio_add_page(last, page, PAGE_CACHE_SIZE, 0); - if (ret == PAGE_CACHE_SIZE) + ret = bio_add_page(last, page, PAGE_SIZE, 0); + if (ret == PAGE_SIZE) return 0; } } @@ -1111,7 +1111,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, bio->bi_bdev = stripe->dev->bdev; bio->bi_iter.bi_sector = disk_start >> 9; - bio_add_page(bio, page, PAGE_CACHE_SIZE, 0); + bio_add_page(bio, page, PAGE_SIZE, 0); bio_list_add(bio_list, bio); return 0; } @@ -1154,7 +1154,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio) bio_list_for_each(bio, &rbio->bio_list) { start = (u64)bio->bi_iter.bi_sector << 9; stripe_offset = start - rbio->bbio->raid_map[0]; - page_index = stripe_offset >> PAGE_CACHE_SHIFT; + page_index = stripe_offset >> PAGE_SHIFT; for (i = 0; i < bio->bi_vcnt; i++) { p = bio->bi_io_vec[i].bv_page; @@ -1253,7 +1253,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) } else { /* raid5 */ memcpy(pointers[nr_data], pointers[0], PAGE_SIZE); - run_xor(pointers + 1, nr_data - 1, PAGE_CACHE_SIZE); + run_xor(pointers + 1, nr_data - 1, PAGE_SIZE); } @@ -1914,7 +1914,7 @@ pstripe: /* Copy parity block into failed block to start with */ memcpy(pointers[faila], pointers[rbio->nr_data], - PAGE_CACHE_SIZE); + PAGE_SIZE); /* rearrange the pointer array */ p = pointers[faila]; @@ -1923,7 +1923,7 @@ pstripe: pointers[rbio->nr_data - 1] = p; /* xor in the rest */ - run_xor(pointers, rbio->nr_data - 1, PAGE_CACHE_SIZE); + run_xor(pointers, rbio->nr_data - 1, PAGE_SIZE); } /* if we're doing this rebuild as part of an rmw, go through * and set all of our private rbio pages in the @@ -2250,7 +2250,7 @@ void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page, ASSERT(logical + PAGE_SIZE <= rbio->bbio->raid_map[0] + rbio->stripe_len * rbio->nr_data); stripe_offset = (int)(logical - rbio->bbio->raid_map[0]); - index = stripe_offset >> PAGE_CACHE_SHIFT; + index = stripe_offset >> PAGE_SHIFT; rbio->bio_pages[index] = page; } @@ -2365,14 +2365,14 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, } else { /* raid5 */ memcpy(pointers[nr_data], pointers[0], PAGE_SIZE); - run_xor(pointers + 1, nr_data - 1, PAGE_CACHE_SIZE); + run_xor(pointers + 1, nr_data - 1, PAGE_SIZE); } /* Check scrubbing pairty and repair it */ p = rbio_stripe_page(rbio, rbio->scrubp, pagenr); parity = kmap(p); - if (memcmp(parity, pointers[rbio->scrubp], PAGE_CACHE_SIZE)) - memcpy(parity, pointers[rbio->scrubp], PAGE_CACHE_SIZE); + if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE)) + memcpy(parity, pointers[rbio->scrubp], PAGE_SIZE); else /* Parity is right, needn't writeback */ bitmap_clear(rbio->dbitmap, pagenr, 1); diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index b892914968c1..298631eaee78 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -226,7 +226,7 @@ int btree_readahead_hook(struct btrfs_fs_info *fs_info, /* find extent */ spin_lock(&fs_info->reada_lock); re = radix_tree_lookup(&fs_info->reada_tree, - start >> PAGE_CACHE_SHIFT); + start >> PAGE_SHIFT); if (re) re->refcnt++; spin_unlock(&fs_info->reada_lock); @@ -257,7 +257,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info, zone = NULL; spin_lock(&fs_info->reada_lock); ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone, - logical >> PAGE_CACHE_SHIFT, 1); + logical >> PAGE_SHIFT, 1); if (ret == 1 && logical >= zone->start && logical <= zone->end) { kref_get(&zone->refcnt); spin_unlock(&fs_info->reada_lock); @@ -294,13 +294,13 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info, spin_lock(&fs_info->reada_lock); ret = radix_tree_insert(&dev->reada_zones, - (unsigned long)(zone->end >> PAGE_CACHE_SHIFT), + (unsigned long)(zone->end >> PAGE_SHIFT), zone); if (ret == -EEXIST) { kfree(zone); ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone, - logical >> PAGE_CACHE_SHIFT, 1); + logical >> PAGE_SHIFT, 1); if (ret == 1 && logical >= zone->start && logical <= zone->end) kref_get(&zone->refcnt); else @@ -326,7 +326,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root, u64 length; int real_stripes; int nzones = 0; - unsigned long index = logical >> PAGE_CACHE_SHIFT; + unsigned long index = logical >> PAGE_SHIFT; int dev_replace_is_ongoing; int have_zone = 0; @@ -495,7 +495,7 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info, struct reada_extent *re) { int i; - unsigned long index = re->logical >> PAGE_CACHE_SHIFT; + unsigned long index = re->logical >> PAGE_SHIFT; spin_lock(&fs_info->reada_lock); if (--re->refcnt) { @@ -538,7 +538,7 @@ static void reada_zone_release(struct kref *kref) struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt); radix_tree_delete(&zone->device->reada_zones, - zone->end >> PAGE_CACHE_SHIFT); + zone->end >> PAGE_SHIFT); kfree(zone); } @@ -587,7 +587,7 @@ static int reada_add_block(struct reada_control *rc, u64 logical, static void reada_peer_zones_set_lock(struct reada_zone *zone, int lock) { int i; - unsigned long index = zone->end >> PAGE_CACHE_SHIFT; + unsigned long index = zone->end >> PAGE_SHIFT; for (i = 0; i < zone->ndevs; ++i) { struct reada_zone *peer; @@ -622,7 +622,7 @@ static int reada_pick_zone(struct btrfs_device *dev) (void **)&zone, index, 1); if (ret == 0) break; - index = (zone->end >> PAGE_CACHE_SHIFT) + 1; + index = (zone->end >> PAGE_SHIFT) + 1; if (zone->locked) { if (zone->elems > top_locked_elems) { top_locked_elems = zone->elems; @@ -673,7 +673,7 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info, * plugging to speed things up */ ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re, - dev->reada_next >> PAGE_CACHE_SHIFT, 1); + dev->reada_next >> PAGE_SHIFT, 1); if (ret == 0 || re->logical > dev->reada_curr_zone->end) { ret = reada_pick_zone(dev); if (!ret) { @@ -682,7 +682,7 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info, } re = NULL; ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re, - dev->reada_next >> PAGE_CACHE_SHIFT, 1); + dev->reada_next >> PAGE_SHIFT, 1); } if (ret == 0) { spin_unlock(&fs_info->reada_lock); @@ -838,7 +838,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) printk(KERN_CONT " curr off %llu", device->reada_next - zone->start); printk(KERN_CONT "\n"); - index = (zone->end >> PAGE_CACHE_SHIFT) + 1; + index = (zone->end >> PAGE_SHIFT) + 1; } cnt = 0; index = 0; @@ -864,7 +864,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) } } printk(KERN_CONT "\n"); - index = (re->logical >> PAGE_CACHE_SHIFT) + 1; + index = (re->logical >> PAGE_SHIFT) + 1; if (++cnt > 15) break; } @@ -880,7 +880,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) if (ret == 0) break; if (!re->scheduled) { - index = (re->logical >> PAGE_CACHE_SHIFT) + 1; + index = (re->logical >> PAGE_SHIFT) + 1; continue; } printk(KERN_DEBUG @@ -897,7 +897,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) } } printk(KERN_CONT "\n"); - index = (re->logical >> PAGE_CACHE_SHIFT) + 1; + index = (re->logical >> PAGE_SHIFT) + 1; } spin_unlock(&fs_info->reada_lock); } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 2bd0011450df..3c93968b539d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3129,10 +3129,10 @@ static int relocate_file_extent_cluster(struct inode *inode, if (ret) goto out; - index = (cluster->start - offset) >> PAGE_CACHE_SHIFT; - last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT; + index = (cluster->start - offset) >> PAGE_SHIFT; + last_index = (cluster->end - offset) >> PAGE_SHIFT; while (index <= last_index) { - ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE); + ret = btrfs_delalloc_reserve_metadata(inode, PAGE_SIZE); if (ret) goto out; @@ -3145,7 +3145,7 @@ static int relocate_file_extent_cluster(struct inode *inode, mask); if (!page) { btrfs_delalloc_release_metadata(inode, - PAGE_CACHE_SIZE); + PAGE_SIZE); ret = -ENOMEM; goto out; } @@ -3162,16 +3162,16 @@ static int relocate_file_extent_cluster(struct inode *inode, lock_page(page); if (!PageUptodate(page)) { unlock_page(page); - page_cache_release(page); + put_page(page); btrfs_delalloc_release_metadata(inode, - PAGE_CACHE_SIZE); + PAGE_SIZE); ret = -EIO; goto out; } } page_start = page_offset(page); - page_end = page_start + PAGE_CACHE_SIZE - 1; + page_end = page_start + PAGE_SIZE - 1; lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end); @@ -3191,7 +3191,7 @@ static int relocate_file_extent_cluster(struct inode *inode, unlock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end); unlock_page(page); - page_cache_release(page); + put_page(page); index++; balance_dirty_pages_ratelimited(inode->i_mapping); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 39dbdcbf4d13..4678f03e878e 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -703,7 +703,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx) if (IS_ERR(inode)) return PTR_ERR(inode); - index = offset >> PAGE_CACHE_SHIFT; + index = offset >> PAGE_SHIFT; page = find_or_create_page(inode->i_mapping, index, GFP_NOFS); if (!page) { @@ -1636,7 +1636,7 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock, if (spage->io_error) { void *mapped_buffer = kmap_atomic(spage->page); - memset(mapped_buffer, 0, PAGE_CACHE_SIZE); + memset(mapped_buffer, 0, PAGE_SIZE); flush_dcache_page(spage->page); kunmap_atomic(mapped_buffer); } @@ -4294,8 +4294,8 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, goto out; } - while (len >= PAGE_CACHE_SIZE) { - index = offset >> PAGE_CACHE_SHIFT; + while (len >= PAGE_SIZE) { + index = offset >> PAGE_SHIFT; again: page = find_or_create_page(inode->i_mapping, index, GFP_NOFS); if (!page) { @@ -4326,7 +4326,7 @@ again: */ if (page->mapping != inode->i_mapping) { unlock_page(page); - page_cache_release(page); + put_page(page); goto again; } if (!PageUptodate(page)) { @@ -4348,15 +4348,15 @@ again: ret = err; next_page: unlock_page(page); - page_cache_release(page); + put_page(page); if (ret) break; - offset += PAGE_CACHE_SIZE; - physical_for_dev_replace += PAGE_CACHE_SIZE; - nocow_ctx_logical += PAGE_CACHE_SIZE; - len -= PAGE_CACHE_SIZE; + offset += PAGE_SIZE; + physical_for_dev_replace += PAGE_SIZE; + nocow_ctx_logical += PAGE_SIZE; + len -= PAGE_SIZE; } ret = COPY_COMPLETE; out: @@ -4390,8 +4390,8 @@ static int write_page_nocow(struct scrub_ctx *sctx, bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = physical_for_dev_replace >> 9; bio->bi_bdev = dev->bdev; - ret = bio_add_page(bio, page, PAGE_CACHE_SIZE, 0); - if (ret != PAGE_CACHE_SIZE) { + ret = bio_add_page(bio, page, PAGE_SIZE, 0); + if (ret != PAGE_SIZE) { leave_with_eio: bio_put(bio); btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 19b7bf4284ee..8d358c547c59 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4449,9 +4449,9 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len) struct page *page; char *addr; struct btrfs_key key; - pgoff_t index = offset >> PAGE_CACHE_SHIFT; + pgoff_t index = offset >> PAGE_SHIFT; pgoff_t last_index; - unsigned pg_offset = offset & ~PAGE_CACHE_MASK; + unsigned pg_offset = offset & ~PAGE_MASK; ssize_t ret = 0; key.objectid = sctx->cur_ino; @@ -4471,7 +4471,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len) if (len == 0) goto out; - last_index = (offset + len - 1) >> PAGE_CACHE_SHIFT; + last_index = (offset + len - 1) >> PAGE_SHIFT; /* initial readahead */ memset(&sctx->ra, 0, sizeof(struct file_ra_state)); @@ -4481,7 +4481,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len) while (index <= last_index) { unsigned cur_len = min_t(unsigned, len, - PAGE_CACHE_SIZE - pg_offset); + PAGE_SIZE - pg_offset); page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL); if (!page) { ret = -ENOMEM; @@ -4493,7 +4493,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len) lock_page(page); if (!PageUptodate(page)) { unlock_page(page); - page_cache_release(page); + put_page(page); ret = -EIO; break; } @@ -4503,7 +4503,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len) memcpy(sctx->read_buf + ret, addr + pg_offset, cur_len); kunmap(page); unlock_page(page); - page_cache_release(page); + put_page(page); index++; pg_offset = 0; len -= cur_len; @@ -4804,7 +4804,7 @@ static int clone_range(struct send_ctx *sctx, type = btrfs_file_extent_type(leaf, ei); if (type == BTRFS_FILE_EXTENT_INLINE) { ext_len = btrfs_file_extent_inline_len(leaf, slot, ei); - ext_len = PAGE_CACHE_ALIGN(ext_len); + ext_len = PAGE_ALIGN(ext_len); } else { ext_len = btrfs_file_extent_num_bytes(leaf, ei); } @@ -4886,7 +4886,7 @@ static int send_write_or_clone(struct send_ctx *sctx, * but there may be items after this page. Make * sure to send the whole thing */ - len = PAGE_CACHE_ALIGN(len); + len = PAGE_ALIGN(len); } else { len = btrfs_file_extent_num_bytes(path->nodes[0], ei); } diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index 669b58201e36..ac3a06d28531 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -32,8 +32,8 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end, { int ret; struct page *pages[16]; - unsigned long index = start >> PAGE_CACHE_SHIFT; - unsigned long end_index = end >> PAGE_CACHE_SHIFT; + unsigned long index = start >> PAGE_SHIFT; + unsigned long end_index = end >> PAGE_SHIFT; unsigned long nr_pages = end_index - index + 1; int i; int count = 0; @@ -49,9 +49,9 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end, count++; if (flags & PROCESS_UNLOCK && PageLocked(pages[i])) unlock_page(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); if (flags & PROCESS_RELEASE) - page_cache_release(pages[i]); + put_page(pages[i]); } nr_pages -= ret; index += ret; @@ -93,7 +93,7 @@ static int test_find_delalloc(void) * everything to make sure our pages don't get evicted and screw up our * test. */ - for (index = 0; index < (total_dirty >> PAGE_CACHE_SHIFT); index++) { + for (index = 0; index < (total_dirty >> PAGE_SHIFT); index++) { page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL); if (!page) { test_msg("Failed to allocate test page\n"); @@ -104,7 +104,7 @@ static int test_find_delalloc(void) if (index) { unlock_page(page); } else { - page_cache_get(page); + get_page(page); locked_page = page; } } @@ -129,7 +129,7 @@ static int test_find_delalloc(void) } unlock_extent(&tmp, start, end); unlock_page(locked_page); - page_cache_release(locked_page); + put_page(locked_page); /* * Test this scenario @@ -139,7 +139,7 @@ static int test_find_delalloc(void) */ test_start = SZ_64M; locked_page = find_lock_page(inode->i_mapping, - test_start >> PAGE_CACHE_SHIFT); + test_start >> PAGE_SHIFT); if (!locked_page) { test_msg("Couldn't find the locked page\n"); goto out_bits; @@ -165,7 +165,7 @@ static int test_find_delalloc(void) } unlock_extent(&tmp, start, end); /* locked_page was unlocked above */ - page_cache_release(locked_page); + put_page(locked_page); /* * Test this scenario @@ -174,7 +174,7 @@ static int test_find_delalloc(void) */ test_start = max_bytes + 4096; locked_page = find_lock_page(inode->i_mapping, test_start >> - PAGE_CACHE_SHIFT); + PAGE_SHIFT); if (!locked_page) { test_msg("Could'nt find the locked page\n"); goto out_bits; @@ -225,13 +225,13 @@ static int test_find_delalloc(void) * range we want to find. */ page = find_get_page(inode->i_mapping, - (max_bytes + SZ_1M) >> PAGE_CACHE_SHIFT); + (max_bytes + SZ_1M) >> PAGE_SHIFT); if (!page) { test_msg("Couldn't find our page\n"); goto out_bits; } ClearPageDirty(page); - page_cache_release(page); + put_page(page); /* We unlocked it in the previous test */ lock_page(locked_page); @@ -249,9 +249,9 @@ static int test_find_delalloc(void) test_msg("Didn't find our range\n"); goto out_bits; } - if (start != test_start && end != test_start + PAGE_CACHE_SIZE - 1) { + if (start != test_start && end != test_start + PAGE_SIZE - 1) { test_msg("Expected start %Lu end %Lu, got start %Lu end %Lu\n", - test_start, test_start + PAGE_CACHE_SIZE - 1, start, + test_start, test_start + PAGE_SIZE - 1, start, end); goto out_bits; } @@ -265,7 +265,7 @@ out_bits: clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_KERNEL); out: if (locked_page) - page_cache_release(locked_page); + put_page(locked_page); process_page_range(inode, 0, total_dirty - 1, PROCESS_UNLOCK | PROCESS_RELEASE); iput(inode); @@ -298,9 +298,9 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb, return -EINVAL; } - bitmap_set(bitmap, (PAGE_CACHE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE, + bitmap_set(bitmap, (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE, sizeof(long) * BITS_PER_BYTE); - extent_buffer_bitmap_set(eb, PAGE_CACHE_SIZE - sizeof(long) / 2, 0, + extent_buffer_bitmap_set(eb, PAGE_SIZE - sizeof(long) / 2, 0, sizeof(long) * BITS_PER_BYTE); if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) { test_msg("Setting straddling pages failed\n"); @@ -309,10 +309,10 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb, bitmap_set(bitmap, 0, len * BITS_PER_BYTE); bitmap_clear(bitmap, - (PAGE_CACHE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE, + (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE, sizeof(long) * BITS_PER_BYTE); extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE); - extent_buffer_bitmap_clear(eb, PAGE_CACHE_SIZE - sizeof(long) / 2, 0, + extent_buffer_bitmap_clear(eb, PAGE_SIZE - sizeof(long) / 2, 0, sizeof(long) * BITS_PER_BYTE); if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) { test_msg("Clearing straddling pages failed\n"); @@ -353,7 +353,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb, static int test_eb_bitmaps(void) { - unsigned long len = PAGE_CACHE_SIZE * 4; + unsigned long len = PAGE_SIZE * 4; unsigned long *bitmap; struct extent_buffer *eb; int ret; @@ -379,7 +379,7 @@ static int test_eb_bitmaps(void) /* Do it over again with an extent buffer which isn't page-aligned. */ free_extent_buffer(eb); - eb = __alloc_dummy_extent_buffer(NULL, PAGE_CACHE_SIZE / 2, len); + eb = __alloc_dummy_extent_buffer(NULL, PAGE_SIZE / 2, len); if (!eb) { test_msg("Couldn't allocate test extent buffer\n"); kfree(bitmap); diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c index c9ad97b1e690..514247515312 100644 --- a/fs/btrfs/tests/free-space-tests.c +++ b/fs/btrfs/tests/free-space-tests.c @@ -22,7 +22,7 @@ #include "../disk-io.h" #include "../free-space-cache.h" -#define BITS_PER_BITMAP (PAGE_CACHE_SIZE * 8) +#define BITS_PER_BITMAP (PAGE_SIZE * 8) /* * This test just does basic sanity checking, making sure we can add an exten diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e2b54d546b7c..bd0f45fb38c4 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1025,16 +1025,16 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, } /* make sure our super fits in the device */ - if (bytenr + PAGE_CACHE_SIZE >= i_size_read(bdev->bd_inode)) + if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode)) goto error_bdev_put; /* make sure our super fits in the page */ - if (sizeof(*disk_super) > PAGE_CACHE_SIZE) + if (sizeof(*disk_super) > PAGE_SIZE) goto error_bdev_put; /* make sure our super doesn't straddle pages on disk */ - index = bytenr >> PAGE_CACHE_SHIFT; - if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_CACHE_SHIFT != index) + index = bytenr >> PAGE_SHIFT; + if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_SHIFT != index) goto error_bdev_put; /* pull in the page with our super */ @@ -1047,7 +1047,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, p = kmap(page); /* align our pointer to the offset of the super block */ - disk_super = p + (bytenr & ~PAGE_CACHE_MASK); + disk_super = p + (bytenr & ~PAGE_MASK); if (btrfs_super_bytenr(disk_super) != bytenr || btrfs_super_magic(disk_super) != BTRFS_MAGIC) @@ -1075,7 +1075,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, error_unmap: kunmap(page); - page_cache_release(page); + put_page(page); error_bdev_put: blkdev_put(bdev, flags); @@ -6527,7 +6527,7 @@ int btrfs_read_sys_array(struct btrfs_root *root) * but sb spans only this function. Add an explicit SetPageUptodate call * to silence the warning eg. on PowerPC 64. */ - if (PAGE_CACHE_SIZE > BTRFS_SUPER_INFO_SIZE) + if (PAGE_SIZE > BTRFS_SUPER_INFO_SIZE) SetPageUptodate(sb->pages[0]); write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE); diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 82990b8f872b..88d274e8ecf2 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -59,7 +59,7 @@ static struct list_head *zlib_alloc_workspace(void) workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL), zlib_inflate_workspacesize()); workspace->strm.workspace = vmalloc(workspacesize); - workspace->buf = kmalloc(PAGE_CACHE_SIZE, GFP_NOFS); + workspace->buf = kmalloc(PAGE_SIZE, GFP_NOFS); if (!workspace->strm.workspace || !workspace->buf) goto fail; @@ -103,7 +103,7 @@ static int zlib_compress_pages(struct list_head *ws, workspace->strm.total_in = 0; workspace->strm.total_out = 0; - in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT); + in_page = find_get_page(mapping, start >> PAGE_SHIFT); data_in = kmap(in_page); out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); @@ -117,8 +117,8 @@ static int zlib_compress_pages(struct list_head *ws, workspace->strm.next_in = data_in; workspace->strm.next_out = cpage_out; - workspace->strm.avail_out = PAGE_CACHE_SIZE; - workspace->strm.avail_in = min(len, PAGE_CACHE_SIZE); + workspace->strm.avail_out = PAGE_SIZE; + workspace->strm.avail_in = min(len, PAGE_SIZE); while (workspace->strm.total_in < len) { ret = zlib_deflate(&workspace->strm, Z_SYNC_FLUSH); @@ -156,7 +156,7 @@ static int zlib_compress_pages(struct list_head *ws, cpage_out = kmap(out_page); pages[nr_pages] = out_page; nr_pages++; - workspace->strm.avail_out = PAGE_CACHE_SIZE; + workspace->strm.avail_out = PAGE_SIZE; workspace->strm.next_out = cpage_out; } /* we're all done */ @@ -170,14 +170,14 @@ static int zlib_compress_pages(struct list_head *ws, bytes_left = len - workspace->strm.total_in; kunmap(in_page); - page_cache_release(in_page); + put_page(in_page); - start += PAGE_CACHE_SIZE; + start += PAGE_SIZE; in_page = find_get_page(mapping, - start >> PAGE_CACHE_SHIFT); + start >> PAGE_SHIFT); data_in = kmap(in_page); workspace->strm.avail_in = min(bytes_left, - PAGE_CACHE_SIZE); + PAGE_SIZE); workspace->strm.next_in = data_in; } } @@ -205,7 +205,7 @@ out: if (in_page) { kunmap(in_page); - page_cache_release(in_page); + put_page(in_page); } return ret; } @@ -223,18 +223,18 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in, size_t total_out = 0; unsigned long page_in_index = 0; unsigned long page_out_index = 0; - unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_CACHE_SIZE); + unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE); unsigned long buf_start; unsigned long pg_offset; data_in = kmap(pages_in[page_in_index]); workspace->strm.next_in = data_in; - workspace->strm.avail_in = min_t(size_t, srclen, PAGE_CACHE_SIZE); + workspace->strm.avail_in = min_t(size_t, srclen, PAGE_SIZE); workspace->strm.total_in = 0; workspace->strm.total_out = 0; workspace->strm.next_out = workspace->buf; - workspace->strm.avail_out = PAGE_CACHE_SIZE; + workspace->strm.avail_out = PAGE_SIZE; pg_offset = 0; /* If it's deflate, and it's got no preset dictionary, then @@ -274,7 +274,7 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in, } workspace->strm.next_out = workspace->buf; - workspace->strm.avail_out = PAGE_CACHE_SIZE; + workspace->strm.avail_out = PAGE_SIZE; if (workspace->strm.avail_in == 0) { unsigned long tmp; @@ -288,7 +288,7 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in, workspace->strm.next_in = data_in; tmp = srclen - workspace->strm.total_in; workspace->strm.avail_in = min(tmp, - PAGE_CACHE_SIZE); + PAGE_SIZE); } } if (ret != Z_STREAM_END) @@ -325,7 +325,7 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in, workspace->strm.total_in = 0; workspace->strm.next_out = workspace->buf; - workspace->strm.avail_out = PAGE_CACHE_SIZE; + workspace->strm.avail_out = PAGE_SIZE; workspace->strm.total_out = 0; /* If it's deflate, and it's got no preset dictionary, then we can tell zlib to skip the adler32 check. */ @@ -368,8 +368,8 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in, else buf_offset = 0; - bytes = min(PAGE_CACHE_SIZE - pg_offset, - PAGE_CACHE_SIZE - buf_offset); + bytes = min(PAGE_SIZE - pg_offset, + PAGE_SIZE - buf_offset); bytes = min(bytes, bytes_left); kaddr = kmap_atomic(dest_page); @@ -380,7 +380,7 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in, bytes_left -= bytes; next: workspace->strm.next_out = workspace->buf; - workspace->strm.avail_out = PAGE_CACHE_SIZE; + workspace->strm.avail_out = PAGE_SIZE; } if (ret != Z_STREAM_END && bytes_left != 0) diff --git a/fs/buffer.c b/fs/buffer.c index 33be29675358..af0d9a82a8ed 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -129,7 +129,7 @@ __clear_page_buffers(struct page *page) { ClearPagePrivate(page); set_page_private(page, 0); - page_cache_release(page); + put_page(page); } static void buffer_io_error(struct buffer_head *bh, char *msg) @@ -207,7 +207,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) struct page *page; int all_mapped = 1; - index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits); + index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; @@ -245,7 +245,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) } out_unlock: spin_unlock(&bd_mapping->private_lock); - page_cache_release(page); + put_page(page); out: return ret; } @@ -1040,7 +1040,7 @@ done: ret = (block < end_block) ? 1 : -ENXIO; failed: unlock_page(page); - page_cache_release(page); + put_page(page); return ret; } @@ -1533,7 +1533,7 @@ void block_invalidatepage(struct page *page, unsigned int offset, /* * Check for overflow */ - BUG_ON(stop > PAGE_CACHE_SIZE || stop < length); + BUG_ON(stop > PAGE_SIZE || stop < length); head = page_buffers(page); bh = head; @@ -1716,7 +1716,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, blocksize = bh->b_size; bbits = block_size_bits(blocksize); - block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + block = (sector_t)page->index << (PAGE_SHIFT - bbits); last_block = (i_size_read(inode) - 1) >> bbits; /* @@ -1894,7 +1894,7 @@ EXPORT_SYMBOL(page_zero_new_buffers); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned from = pos & (PAGE_SIZE - 1); unsigned to = from + len; struct inode *inode = page->mapping->host; unsigned block_start, block_end; @@ -1904,15 +1904,15 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len, struct buffer_head *bh, *head, *wait[2], **wait_bh=wait; BUG_ON(!PageLocked(page)); - BUG_ON(from > PAGE_CACHE_SIZE); - BUG_ON(to > PAGE_CACHE_SIZE); + BUG_ON(from > PAGE_SIZE); + BUG_ON(to > PAGE_SIZE); BUG_ON(from > to); head = create_page_buffers(page, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); - block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + block = (sector_t)page->index << (PAGE_SHIFT - bbits); for(bh = head, block_start = 0; bh != head || !block_start; block++, block_start=block_end, bh = bh->b_this_page) { @@ -2020,7 +2020,7 @@ static int __block_commit_write(struct inode *inode, struct page *page, int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, get_block_t *get_block) { - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int status; @@ -2031,7 +2031,7 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, status = __block_write_begin(page, pos, len, get_block); if (unlikely(status)) { unlock_page(page); - page_cache_release(page); + put_page(page); page = NULL; } @@ -2047,7 +2047,7 @@ int block_write_end(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; unsigned start; - start = pos & (PAGE_CACHE_SIZE - 1); + start = pos & (PAGE_SIZE - 1); if (unlikely(copied < len)) { /* @@ -2099,7 +2099,7 @@ int generic_write_end(struct file *file, struct address_space *mapping, } unlock_page(page); - page_cache_release(page); + put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); @@ -2136,9 +2136,9 @@ int block_is_partially_uptodate(struct page *page, unsigned long from, head = page_buffers(page); blocksize = head->b_size; - to = min_t(unsigned, PAGE_CACHE_SIZE - from, count); + to = min_t(unsigned, PAGE_SIZE - from, count); to = from + to; - if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize) + if (from < blocksize && to > PAGE_SIZE - blocksize) return 0; bh = head; @@ -2181,7 +2181,7 @@ int block_read_full_page(struct page *page, get_block_t *get_block) blocksize = head->b_size; bbits = block_size_bits(blocksize); - iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + iblock = (sector_t)page->index << (PAGE_SHIFT - bbits); lblock = (i_size_read(inode)+blocksize-1) >> bbits; bh = head; nr = 0; @@ -2295,16 +2295,16 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, unsigned zerofrom, offset, len; int err = 0; - index = pos >> PAGE_CACHE_SHIFT; - offset = pos & ~PAGE_CACHE_MASK; + index = pos >> PAGE_SHIFT; + offset = pos & ~PAGE_MASK; - while (index > (curidx = (curpos = *bytes)>>PAGE_CACHE_SHIFT)) { - zerofrom = curpos & ~PAGE_CACHE_MASK; + while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) { + zerofrom = curpos & ~PAGE_MASK; if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } - len = PAGE_CACHE_SIZE - zerofrom; + len = PAGE_SIZE - zerofrom; err = pagecache_write_begin(file, mapping, curpos, len, AOP_FLAG_UNINTERRUPTIBLE, @@ -2329,7 +2329,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, /* page covers the boundary, find the boundary offset */ if (index == curidx) { - zerofrom = curpos & ~PAGE_CACHE_MASK; + zerofrom = curpos & ~PAGE_MASK; /* if we will expand the thing last block will be filled */ if (offset <= zerofrom) { goto out; @@ -2375,7 +2375,7 @@ int cont_write_begin(struct file *file, struct address_space *mapping, if (err) return err; - zerofrom = *bytes & ~PAGE_CACHE_MASK; + zerofrom = *bytes & ~PAGE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; @@ -2430,10 +2430,10 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, } /* page is wholly or partially inside EOF */ - if (((page->index + 1) << PAGE_CACHE_SHIFT) > size) - end = size & ~PAGE_CACHE_MASK; + if (((page->index + 1) << PAGE_SHIFT) > size) + end = size & ~PAGE_MASK; else - end = PAGE_CACHE_SIZE; + end = PAGE_SIZE; ret = __block_write_begin(page, 0, end, get_block); if (!ret) @@ -2508,8 +2508,8 @@ int nobh_write_begin(struct address_space *mapping, int ret = 0; int is_mapped_to_disk = 1; - index = pos >> PAGE_CACHE_SHIFT; - from = pos & (PAGE_CACHE_SIZE - 1); + index = pos >> PAGE_SHIFT; + from = pos & (PAGE_SIZE - 1); to = from + len; page = grab_cache_page_write_begin(mapping, index, flags); @@ -2543,7 +2543,7 @@ int nobh_write_begin(struct address_space *mapping, goto out_release; } - block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits); + block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); /* * We loop across all blocks in the page, whether or not they are @@ -2551,7 +2551,7 @@ int nobh_write_begin(struct address_space *mapping, * page is fully mapped-to-disk. */ for (block_start = 0, block_in_page = 0, bh = head; - block_start < PAGE_CACHE_SIZE; + block_start < PAGE_SIZE; block_in_page++, block_start += blocksize, bh = bh->b_this_page) { int create; @@ -2623,7 +2623,7 @@ failed: out_release: unlock_page(page); - page_cache_release(page); + put_page(page); *pagep = NULL; return ret; @@ -2653,7 +2653,7 @@ int nobh_write_end(struct file *file, struct address_space *mapping, } unlock_page(page); - page_cache_release(page); + put_page(page); while (head) { bh = head; @@ -2675,7 +2675,7 @@ int nobh_writepage(struct page *page, get_block_t *get_block, { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); - const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; + const pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; int ret; @@ -2684,7 +2684,7 @@ int nobh_writepage(struct page *page, get_block_t *get_block, goto out; /* Is the page fully outside i_size? (truncate in progress) */ - offset = i_size & (PAGE_CACHE_SIZE-1); + offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { /* * The page may have dirty, unmapped buffers. For example, @@ -2707,7 +2707,7 @@ int nobh_writepage(struct page *page, get_block_t *get_block, * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ - zero_user_segment(page, offset, PAGE_CACHE_SIZE); + zero_user_segment(page, offset, PAGE_SIZE); out: ret = mpage_writepage(page, get_block, wbc); if (ret == -EAGAIN) @@ -2720,8 +2720,8 @@ EXPORT_SYMBOL(nobh_writepage); int nobh_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { - pgoff_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); + pgoff_t index = from >> PAGE_SHIFT; + unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize; sector_t iblock; unsigned length, pos; @@ -2738,7 +2738,7 @@ int nobh_truncate_page(struct address_space *mapping, return 0; length = blocksize - length; - iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; @@ -2748,7 +2748,7 @@ int nobh_truncate_page(struct address_space *mapping, if (page_has_buffers(page)) { has_buffers: unlock_page(page); - page_cache_release(page); + put_page(page); return block_truncate_page(mapping, from, get_block); } @@ -2772,7 +2772,7 @@ has_buffers: if (!PageUptodate(page)) { err = mapping->a_ops->readpage(NULL, page); if (err) { - page_cache_release(page); + put_page(page); goto out; } lock_page(page); @@ -2789,7 +2789,7 @@ has_buffers: unlock: unlock_page(page); - page_cache_release(page); + put_page(page); out: return err; } @@ -2798,8 +2798,8 @@ EXPORT_SYMBOL(nobh_truncate_page); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { - pgoff_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); + pgoff_t index = from >> PAGE_SHIFT; + unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize; sector_t iblock; unsigned length, pos; @@ -2816,7 +2816,7 @@ int block_truncate_page(struct address_space *mapping, return 0; length = blocksize - length; - iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; @@ -2865,7 +2865,7 @@ int block_truncate_page(struct address_space *mapping, unlock: unlock_page(page); - page_cache_release(page); + put_page(page); out: return err; } @@ -2879,7 +2879,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block, { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); - const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; + const pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; /* Is the page fully inside i_size? */ @@ -2888,14 +2888,14 @@ int block_write_full_page(struct page *page, get_block_t *get_block, end_buffer_async_write); /* Is the page fully outside i_size? (truncate in progress) */ - offset = i_size & (PAGE_CACHE_SIZE-1); + offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { /* * The page may have dirty, unmapped buffers. For example, * they may have been added in ext3_writepage(). Make them * freeable here, so the page does not leak. */ - do_invalidatepage(page, 0, PAGE_CACHE_SIZE); + do_invalidatepage(page, 0, PAGE_SIZE); unlock_page(page); return 0; /* don't care */ } @@ -2907,7 +2907,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block, * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ - zero_user_segment(page, offset, PAGE_CACHE_SIZE); + zero_user_segment(page, offset, PAGE_SIZE); return __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); } diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index c0f3da3926a0..afbdc418966d 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -194,10 +194,10 @@ static void cachefiles_read_copier(struct fscache_operation *_op) error = -EIO; } - page_cache_release(monitor->back_page); + put_page(monitor->back_page); fscache_end_io(op, monitor->netfs_page, error); - page_cache_release(monitor->netfs_page); + put_page(monitor->netfs_page); fscache_retrieval_complete(op, 1); fscache_put_retrieval(op); kfree(monitor); @@ -288,8 +288,8 @@ monitor_backing_page: _debug("- monitor add"); /* install the monitor */ - page_cache_get(monitor->netfs_page); - page_cache_get(backpage); + get_page(monitor->netfs_page); + get_page(backpage); monitor->back_page = backpage; monitor->monitor.private = backpage; add_page_wait_queue(backpage, &monitor->monitor); @@ -310,7 +310,7 @@ backing_page_already_present: _debug("- present"); if (newpage) { - page_cache_release(newpage); + put_page(newpage); newpage = NULL; } @@ -342,7 +342,7 @@ success: out: if (backpage) - page_cache_release(backpage); + put_page(backpage); if (monitor) { fscache_put_retrieval(monitor->op); kfree(monitor); @@ -363,7 +363,7 @@ io_error: goto out; nomem_page: - page_cache_release(newpage); + put_page(newpage); nomem_monitor: fscache_put_retrieval(monitor->op); kfree(monitor); @@ -530,7 +530,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, netpage->index, cachefiles_gfp); if (ret < 0) { if (ret == -EEXIST) { - page_cache_release(netpage); + put_page(netpage); fscache_retrieval_complete(op, 1); continue; } @@ -538,10 +538,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, } /* install a monitor */ - page_cache_get(netpage); + get_page(netpage); monitor->netfs_page = netpage; - page_cache_get(backpage); + get_page(backpage); monitor->back_page = backpage; monitor->monitor.private = backpage; add_page_wait_queue(backpage, &monitor->monitor); @@ -555,10 +555,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, unlock_page(backpage); } - page_cache_release(backpage); + put_page(backpage); backpage = NULL; - page_cache_release(netpage); + put_page(netpage); netpage = NULL; continue; @@ -603,7 +603,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, netpage->index, cachefiles_gfp); if (ret < 0) { if (ret == -EEXIST) { - page_cache_release(netpage); + put_page(netpage); fscache_retrieval_complete(op, 1); continue; } @@ -612,14 +612,14 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, copy_highpage(netpage, backpage); - page_cache_release(backpage); + put_page(backpage); backpage = NULL; fscache_mark_page_cached(op, netpage); /* the netpage is unlocked and marked up to date here */ fscache_end_io(op, netpage, 0); - page_cache_release(netpage); + put_page(netpage); netpage = NULL; fscache_retrieval_complete(op, 1); continue; @@ -632,11 +632,11 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, out: /* tidy up */ if (newpage) - page_cache_release(newpage); + put_page(newpage); if (netpage) - page_cache_release(netpage); + put_page(netpage); if (backpage) - page_cache_release(backpage); + put_page(backpage); if (monitor) { fscache_put_retrieval(op); kfree(monitor); @@ -644,7 +644,7 @@ out: list_for_each_entry_safe(netpage, _n, list, lru) { list_del(&netpage->lru); - page_cache_release(netpage); + put_page(netpage); fscache_retrieval_complete(op, 1); } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index fc5cae2a0db2..4801571f51cb 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -143,7 +143,7 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset, inode = page->mapping->host; ci = ceph_inode(inode); - if (offset != 0 || length != PAGE_CACHE_SIZE) { + if (offset != 0 || length != PAGE_SIZE) { dout("%p invalidatepage %p idx %lu partial dirty page %u~%u\n", inode, page, page->index, offset, length); return; @@ -197,10 +197,10 @@ static int readpage_nounlock(struct file *filp, struct page *page) &ceph_inode_to_client(inode)->client->osdc; int err = 0; u64 off = page_offset(page); - u64 len = PAGE_CACHE_SIZE; + u64 len = PAGE_SIZE; if (off >= i_size_read(inode)) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); return 0; } @@ -212,7 +212,7 @@ static int readpage_nounlock(struct file *filp, struct page *page) */ if (off == 0) return -EINVAL; - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); return 0; } @@ -234,9 +234,9 @@ static int readpage_nounlock(struct file *filp, struct page *page) ceph_fscache_readpage_cancel(inode, page); goto out; } - if (err < PAGE_CACHE_SIZE) + if (err < PAGE_SIZE) /* zero fill remainder of page */ - zero_user_segment(page, err, PAGE_CACHE_SIZE); + zero_user_segment(page, err, PAGE_SIZE); else flush_dcache_page(page); @@ -278,10 +278,10 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg) if (rc < 0 && rc != -ENOENT) goto unlock; - if (bytes < (int)PAGE_CACHE_SIZE) { + if (bytes < (int)PAGE_SIZE) { /* zero (remainder of) page */ int s = bytes < 0 ? 0 : bytes; - zero_user_segment(page, s, PAGE_CACHE_SIZE); + zero_user_segment(page, s, PAGE_SIZE); } dout("finish_read %p uptodate %p idx %lu\n", inode, page, page->index); @@ -290,8 +290,8 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg) ceph_readpage_to_fscache(inode, page); unlock: unlock_page(page); - page_cache_release(page); - bytes -= PAGE_CACHE_SIZE; + put_page(page); + bytes -= PAGE_SIZE; } kfree(osd_data->pages); } @@ -336,7 +336,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) if (max && nr_pages == max) break; } - len = nr_pages << PAGE_CACHE_SHIFT; + len = nr_pages << PAGE_SHIFT; dout("start_read %p nr_pages %d is %lld~%lld\n", inode, nr_pages, off, len); vino = ceph_vino(inode); @@ -364,7 +364,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) if (add_to_page_cache_lru(page, &inode->i_data, page->index, GFP_KERNEL)) { ceph_fscache_uncache_page(inode, page); - page_cache_release(page); + put_page(page); dout("start_read %p add_to_page_cache failed %p\n", inode, page); nr_pages = i; @@ -415,8 +415,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, if (rc == 0) goto out; - if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE) - max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1) + if (fsc->mount_options->rsize >= PAGE_SIZE) + max = (fsc->mount_options->rsize + PAGE_SIZE - 1) >> PAGE_SHIFT; dout("readpages %p file %p nr_pages %d max %d\n", inode, @@ -484,7 +484,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) long writeback_stat; u64 truncate_size; u32 truncate_seq; - int err = 0, len = PAGE_CACHE_SIZE; + int err = 0, len = PAGE_SIZE; dout("writepage %p idx %lu\n", page, page->index); @@ -725,9 +725,9 @@ static int ceph_writepages_start(struct address_space *mapping, } if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize) wsize = fsc->mount_options->wsize; - if (wsize < PAGE_CACHE_SIZE) - wsize = PAGE_CACHE_SIZE; - max_pages_ever = wsize >> PAGE_CACHE_SHIFT; + if (wsize < PAGE_SIZE) + wsize = PAGE_SIZE; + max_pages_ever = wsize >> PAGE_SHIFT; pagevec_init(&pvec, 0); @@ -737,8 +737,8 @@ static int ceph_writepages_start(struct address_space *mapping, end = -1; dout(" cyclic, start at %lu\n", start); } else { - start = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + start = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; should_loop = 0; @@ -887,7 +887,7 @@ get_more_pages: num_ops = 1 + do_sync; strip_unit_end = page->index + - ((len - 1) >> PAGE_CACHE_SHIFT); + ((len - 1) >> PAGE_SHIFT); BUG_ON(pages); max_pages = calc_pages_for(0, (u64)len); @@ -901,7 +901,7 @@ get_more_pages: len = 0; } else if (page->index != - (offset + len) >> PAGE_CACHE_SHIFT) { + (offset + len) >> PAGE_SHIFT) { if (num_ops >= (pool ? CEPH_OSD_SLAB_OPS : CEPH_OSD_MAX_OPS)) { redirty_page_for_writepage(wbc, page); @@ -929,7 +929,7 @@ get_more_pages: pages[locked_pages] = page; locked_pages++; - len += PAGE_CACHE_SIZE; + len += PAGE_SIZE; } /* did we get anything? */ @@ -981,7 +981,7 @@ new_request: BUG_ON(IS_ERR(req)); } BUG_ON(len < page_offset(pages[locked_pages - 1]) + - PAGE_CACHE_SIZE - offset); + PAGE_SIZE - offset); req->r_callback = writepages_finish; req->r_inode = inode; @@ -1011,7 +1011,7 @@ new_request: } set_page_writeback(pages[i]); - len += PAGE_CACHE_SIZE; + len += PAGE_SIZE; } if (snap_size != -1) { @@ -1020,7 +1020,7 @@ new_request: /* writepages_finish() clears writeback pages * according to the data length, so make sure * data length covers all locked pages */ - u64 min_len = len + 1 - PAGE_CACHE_SIZE; + u64 min_len = len + 1 - PAGE_SIZE; len = min(len, (u64)i_size_read(inode) - offset); len = max(len, min_len); } @@ -1135,8 +1135,8 @@ static int ceph_update_writeable_page(struct file *file, { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); - loff_t page_off = pos & PAGE_CACHE_MASK; - int pos_in_page = pos & ~PAGE_CACHE_MASK; + loff_t page_off = pos & PAGE_MASK; + int pos_in_page = pos & ~PAGE_MASK; int end_in_page = pos_in_page + len; loff_t i_size; int r; @@ -1191,7 +1191,7 @@ retry_locked: } /* full page? */ - if (pos_in_page == 0 && len == PAGE_CACHE_SIZE) + if (pos_in_page == 0 && len == PAGE_SIZE) return 0; /* past end of file? */ @@ -1199,12 +1199,12 @@ retry_locked: if (page_off >= i_size || (pos_in_page == 0 && (pos+len) >= i_size && - end_in_page - pos_in_page != PAGE_CACHE_SIZE)) { + end_in_page - pos_in_page != PAGE_SIZE)) { dout(" zeroing %p 0 - %d and %d - %d\n", - page, pos_in_page, end_in_page, (int)PAGE_CACHE_SIZE); + page, pos_in_page, end_in_page, (int)PAGE_SIZE); zero_user_segments(page, 0, pos_in_page, - end_in_page, PAGE_CACHE_SIZE); + end_in_page, PAGE_SIZE); return 0; } @@ -1228,7 +1228,7 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, { struct inode *inode = file_inode(file); struct page *page; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; int r; do { @@ -1242,7 +1242,7 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, r = ceph_update_writeable_page(file, pos, len, page); if (r < 0) - page_cache_release(page); + put_page(page); else *pagep = page; } while (r == -EAGAIN); @@ -1259,7 +1259,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = file_inode(file); - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned from = pos & (PAGE_SIZE - 1); int check_cap = 0; dout("write_end file %p inode %p page %p %d~%d (%d)\n", file, @@ -1279,7 +1279,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); if (check_cap) ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL); @@ -1322,11 +1322,11 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_file_info *fi = vma->vm_file->private_data; struct page *pinned_page = NULL; - loff_t off = vmf->pgoff << PAGE_CACHE_SHIFT; + loff_t off = vmf->pgoff << PAGE_SHIFT; int want, got, ret; dout("filemap_fault %p %llx.%llx %llu~%zd trying to get caps\n", - inode, ceph_vinop(inode), off, (size_t)PAGE_CACHE_SIZE); + inode, ceph_vinop(inode), off, (size_t)PAGE_SIZE); if (fi->fmode & CEPH_FILE_MODE_LAZY) want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO; else @@ -1343,7 +1343,7 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } } dout("filemap_fault %p %llu~%zd got cap refs on %s\n", - inode, off, (size_t)PAGE_CACHE_SIZE, ceph_cap_string(got)); + inode, off, (size_t)PAGE_SIZE, ceph_cap_string(got)); if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) || ci->i_inline_version == CEPH_INLINE_NONE) @@ -1352,16 +1352,16 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) ret = -EAGAIN; dout("filemap_fault %p %llu~%zd dropping cap refs on %s ret %d\n", - inode, off, (size_t)PAGE_CACHE_SIZE, ceph_cap_string(got), ret); + inode, off, (size_t)PAGE_SIZE, ceph_cap_string(got), ret); if (pinned_page) - page_cache_release(pinned_page); + put_page(pinned_page); ceph_put_cap_refs(ci, got); if (ret != -EAGAIN) return ret; /* read inline data */ - if (off >= PAGE_CACHE_SIZE) { + if (off >= PAGE_SIZE) { /* does not support inline data > PAGE_SIZE */ ret = VM_FAULT_SIGBUS; } else { @@ -1378,12 +1378,12 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) CEPH_STAT_CAP_INLINE_DATA, true); if (ret1 < 0 || off >= i_size_read(inode)) { unlock_page(page); - page_cache_release(page); + put_page(page); ret = VM_FAULT_SIGBUS; goto out; } - if (ret1 < PAGE_CACHE_SIZE) - zero_user_segment(page, ret1, PAGE_CACHE_SIZE); + if (ret1 < PAGE_SIZE) + zero_user_segment(page, ret1, PAGE_SIZE); else flush_dcache_page(page); SetPageUptodate(page); @@ -1392,7 +1392,7 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } out: dout("filemap_fault %p %llu~%zd read inline data ret %d\n", - inode, off, (size_t)PAGE_CACHE_SIZE, ret); + inode, off, (size_t)PAGE_SIZE, ret); return ret; } @@ -1430,10 +1430,10 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) } } - if (off + PAGE_CACHE_SIZE <= size) - len = PAGE_CACHE_SIZE; + if (off + PAGE_SIZE <= size) + len = PAGE_SIZE; else - len = size & ~PAGE_CACHE_MASK; + len = size & ~PAGE_MASK; dout("page_mkwrite %p %llx.%llx %llu~%zd getting caps i_size %llu\n", inode, ceph_vinop(inode), off, len, size); @@ -1519,7 +1519,7 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, return; if (PageUptodate(page)) { unlock_page(page); - page_cache_release(page); + put_page(page); return; } } @@ -1534,14 +1534,14 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, } if (page != locked_page) { - if (len < PAGE_CACHE_SIZE) - zero_user_segment(page, len, PAGE_CACHE_SIZE); + if (len < PAGE_SIZE) + zero_user_segment(page, len, PAGE_SIZE); else flush_dcache_page(page); SetPageUptodate(page); unlock_page(page); - page_cache_release(page); + put_page(page); } } @@ -1578,7 +1578,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page) from_pagecache = true; lock_page(page); } else { - page_cache_release(page); + put_page(page); page = NULL; } } @@ -1586,8 +1586,8 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page) if (page) { len = i_size_read(inode); - if (len > PAGE_CACHE_SIZE) - len = PAGE_CACHE_SIZE; + if (len > PAGE_SIZE) + len = PAGE_SIZE; } else { page = __page_cache_alloc(GFP_NOFS); if (!page) { @@ -1670,7 +1670,7 @@ out: if (page && page != locked_page) { if (from_pagecache) { unlock_page(page); - page_cache_release(page); + put_page(page); } else __free_pages(page, 0); } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index de17bb232ff8..cfaeef18cbca 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2510,7 +2510,7 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, *pinned_page = page; break; } - page_cache_release(page); + put_page(page); } /* * drop cap refs first because getattr while diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index fadc243dfb28..4fb2bbc2a272 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -129,7 +129,7 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx, struct inode *dir = d_inode(parent); struct dentry *dentry, *last = NULL; struct ceph_dentry_info *di; - unsigned nsize = PAGE_CACHE_SIZE / sizeof(struct dentry *); + unsigned nsize = PAGE_SIZE / sizeof(struct dentry *); int err = 0; loff_t ptr_pos = 0; struct ceph_readdir_cache_control cache_ctl = {}; @@ -154,7 +154,7 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx, } err = -EAGAIN; - pgoff = ptr_pos >> PAGE_CACHE_SHIFT; + pgoff = ptr_pos >> PAGE_SHIFT; if (!cache_ctl.page || pgoff != page_index(cache_ctl.page)) { ceph_readdir_cache_release(&cache_ctl); cache_ctl.page = find_lock_page(&dir->i_data, pgoff); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index ef38f01c1795..a79f9269831e 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -466,7 +466,7 @@ more: ret += zlen; } - didpages = (page_align + ret) >> PAGE_CACHE_SHIFT; + didpages = (page_align + ret) >> PAGE_SHIFT; pos += ret; read = pos - off; left -= ret; @@ -806,8 +806,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, if (write) { ret = invalidate_inode_pages2_range(inode->i_mapping, - pos >> PAGE_CACHE_SHIFT, - (pos + count) >> PAGE_CACHE_SHIFT); + pos >> PAGE_SHIFT, + (pos + count) >> PAGE_SHIFT); if (ret < 0) dout("invalidate_inode_pages2_range returned %d\n", ret); @@ -872,7 +872,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, * may block. */ truncate_inode_pages_range(inode->i_mapping, pos, - (pos+len) | (PAGE_CACHE_SIZE - 1)); + (pos+len) | (PAGE_SIZE - 1)); osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0); } @@ -1006,8 +1006,8 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, return ret; ret = invalidate_inode_pages2_range(inode->i_mapping, - pos >> PAGE_CACHE_SHIFT, - (pos + count) >> PAGE_CACHE_SHIFT); + pos >> PAGE_SHIFT, + (pos + count) >> PAGE_SHIFT); if (ret < 0) dout("invalidate_inode_pages2_range returned %d\n", ret); @@ -1036,7 +1036,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, * write from beginning of first page, * regardless of io alignment */ - num_pages = (len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + num_pages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL); if (IS_ERR(pages)) { @@ -1159,7 +1159,7 @@ again: dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n", inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret); if (pinned_page) { - page_cache_release(pinned_page); + put_page(pinned_page); pinned_page = NULL; } ceph_put_cap_refs(ci, got); @@ -1188,10 +1188,10 @@ again: if (retry_op == READ_INLINE) { BUG_ON(ret > 0 || read > 0); if (iocb->ki_pos < i_size && - iocb->ki_pos < PAGE_CACHE_SIZE) { + iocb->ki_pos < PAGE_SIZE) { loff_t end = min_t(loff_t, i_size, iocb->ki_pos + len); - end = min_t(loff_t, end, PAGE_CACHE_SIZE); + end = min_t(loff_t, end, PAGE_SIZE); if (statret < end) zero_user_segment(page, statret, end); ret = copy_page_to_iter(page, @@ -1463,21 +1463,21 @@ static inline void ceph_zero_partial_page( struct inode *inode, loff_t offset, unsigned size) { struct page *page; - pgoff_t index = offset >> PAGE_CACHE_SHIFT; + pgoff_t index = offset >> PAGE_SHIFT; page = find_lock_page(inode->i_mapping, index); if (page) { wait_on_page_writeback(page); - zero_user(page, offset & (PAGE_CACHE_SIZE - 1), size); + zero_user(page, offset & (PAGE_SIZE - 1), size); unlock_page(page); - page_cache_release(page); + put_page(page); } } static void ceph_zero_pagecache_range(struct inode *inode, loff_t offset, loff_t length) { - loff_t nearly = round_up(offset, PAGE_CACHE_SIZE); + loff_t nearly = round_up(offset, PAGE_SIZE); if (offset < nearly) { loff_t size = nearly - offset; if (length < size) @@ -1486,8 +1486,8 @@ static void ceph_zero_pagecache_range(struct inode *inode, loff_t offset, offset += size; length -= size; } - if (length >= PAGE_CACHE_SIZE) { - loff_t size = round_down(length, PAGE_CACHE_SIZE); + if (length >= PAGE_SIZE) { + loff_t size = round_down(length, PAGE_SIZE); truncate_pagecache_range(inode, offset, offset + size - 1); offset += size; length -= size; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index ed58b168904a..edfade037738 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1338,7 +1338,7 @@ void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl) { if (ctl->page) { kunmap(ctl->page); - page_cache_release(ctl->page); + put_page(ctl->page); ctl->page = NULL; } } @@ -1348,7 +1348,7 @@ static int fill_readdir_cache(struct inode *dir, struct dentry *dn, struct ceph_mds_request *req) { struct ceph_inode_info *ci = ceph_inode(dir); - unsigned nsize = PAGE_CACHE_SIZE / sizeof(struct dentry*); + unsigned nsize = PAGE_SIZE / sizeof(struct dentry*); unsigned idx = ctl->index % nsize; pgoff_t pgoff = ctl->index / nsize; @@ -1367,7 +1367,7 @@ static int fill_readdir_cache(struct inode *dir, struct dentry *dn, unlock_page(ctl->page); ctl->dentries = kmap(ctl->page); if (idx == 0) - memset(ctl->dentries, 0, PAGE_CACHE_SIZE); + memset(ctl->dentries, 0, PAGE_SIZE); } if (req->r_dir_release_cnt == atomic64_read(&ci->i_release_count) && diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 44852c3ae531..541ead4d8965 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1610,7 +1610,7 @@ again: while (!list_empty(&tmp_list)) { if (!msg) { msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPRELEASE, - PAGE_CACHE_SIZE, GFP_NOFS, false); + PAGE_SIZE, GFP_NOFS, false); if (!msg) goto out_err; head = msg->front.iov_base; diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 37712ccffcc6..ee69a537dba5 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -97,7 +97,7 @@ struct ceph_mds_reply_info_parsed { /* * cap releases are batched and sent to the MDS en masse. */ -#define CEPH_CAPS_PER_RELEASE ((PAGE_CACHE_SIZE - \ +#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE - \ sizeof(struct ceph_mds_cap_release)) / \ sizeof(struct ceph_mds_cap_item)) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index c973043deb0e..f12d5e2955c2 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -560,7 +560,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, /* set up mempools */ err = -ENOMEM; - page_count = fsc->mount_options->wsize >> PAGE_CACHE_SHIFT; + page_count = fsc->mount_options->wsize >> PAGE_SHIFT; size = sizeof (struct page *) * (page_count ? page_count : 1); fsc->wb_pagevec_pool = mempool_create_kmalloc_pool(10, size); if (!fsc->wb_pagevec_pool) @@ -912,13 +912,13 @@ static int ceph_register_bdi(struct super_block *sb, int err; /* set ra_pages based on rasize mount option? */ - if (fsc->mount_options->rasize >= PAGE_CACHE_SIZE) + if (fsc->mount_options->rasize >= PAGE_SIZE) fsc->backing_dev_info.ra_pages = - (fsc->mount_options->rasize + PAGE_CACHE_SIZE - 1) + (fsc->mount_options->rasize + PAGE_SIZE - 1) >> PAGE_SHIFT; else fsc->backing_dev_info.ra_pages = - VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE; + VM_MAX_READAHEAD * 1024 / PAGE_SIZE; err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld", atomic_long_inc_return(&bdi_seq)); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 1d86fc620e5c..89201564c346 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -962,7 +962,7 @@ static int cifs_clone_file_range(struct file *src_file, loff_t off, cifs_dbg(FYI, "about to flush pages\n"); /* should we flush first and last page first */ truncate_inode_pages_range(&target_inode->i_data, destoff, - PAGE_CACHE_ALIGN(destoff + len)-1); + PAGE_ALIGN(destoff + len)-1); if (target_tcon->ses->server->ops->duplicate_extents) rc = target_tcon->ses->server->ops->duplicate_extents(xid, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 76fcb50295a3..a894bf809ff7 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1929,17 +1929,17 @@ cifs_writev_requeue(struct cifs_writedata *wdata) wsize = server->ops->wp_retry_size(inode); if (wsize < rest_len) { - nr_pages = wsize / PAGE_CACHE_SIZE; + nr_pages = wsize / PAGE_SIZE; if (!nr_pages) { rc = -ENOTSUPP; break; } - cur_len = nr_pages * PAGE_CACHE_SIZE; - tailsz = PAGE_CACHE_SIZE; + cur_len = nr_pages * PAGE_SIZE; + tailsz = PAGE_SIZE; } else { - nr_pages = DIV_ROUND_UP(rest_len, PAGE_CACHE_SIZE); + nr_pages = DIV_ROUND_UP(rest_len, PAGE_SIZE); cur_len = rest_len; - tailsz = rest_len - (nr_pages - 1) * PAGE_CACHE_SIZE; + tailsz = rest_len - (nr_pages - 1) * PAGE_SIZE; } wdata2 = cifs_writedata_alloc(nr_pages, cifs_writev_complete); @@ -1957,7 +1957,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata) wdata2->sync_mode = wdata->sync_mode; wdata2->nr_pages = nr_pages; wdata2->offset = page_offset(wdata2->pages[0]); - wdata2->pagesz = PAGE_CACHE_SIZE; + wdata2->pagesz = PAGE_SIZE; wdata2->tailsz = tailsz; wdata2->bytes = cur_len; @@ -1975,7 +1975,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata) if (rc != 0 && rc != -EAGAIN) { SetPageError(wdata2->pages[j]); end_page_writeback(wdata2->pages[j]); - page_cache_release(wdata2->pages[j]); + put_page(wdata2->pages[j]); } } @@ -2018,7 +2018,7 @@ cifs_writev_complete(struct work_struct *work) else if (wdata->result < 0) SetPageError(page); end_page_writeback(page); - page_cache_release(page); + put_page(page); } if (wdata->result != -EAGAIN) mapping_set_error(inode->i_mapping, wdata->result); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a763cd3d9e7c..6f62ac821a84 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3630,7 +3630,7 @@ try_mount_again: cifs_sb->rsize = server->ops->negotiate_rsize(tcon, volume_info); /* tune readahead according to rsize */ - cifs_sb->bdi.ra_pages = cifs_sb->rsize / PAGE_CACHE_SIZE; + cifs_sb->bdi.ra_pages = cifs_sb->rsize / PAGE_SIZE; remote_path_check: #ifdef CONFIG_CIFS_DFS_UPCALL diff --git a/fs/cifs/file.c b/fs/cifs/file.c index ff882aeaccc6..5ce540dc6996 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1833,7 +1833,7 @@ refind_writable: static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) { struct address_space *mapping = page->mapping; - loff_t offset = (loff_t)page->index << PAGE_CACHE_SHIFT; + loff_t offset = (loff_t)page->index << PAGE_SHIFT; char *write_data; int rc = -EFAULT; int bytes_written = 0; @@ -1849,7 +1849,7 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) write_data = kmap(page); write_data += from; - if ((to > PAGE_CACHE_SIZE) || (from > to)) { + if ((to > PAGE_SIZE) || (from > to)) { kunmap(page); return -EIO; } @@ -1991,7 +1991,7 @@ wdata_prepare_pages(struct cifs_writedata *wdata, unsigned int found_pages, /* put any pages we aren't going to use */ for (i = nr_pages; i < found_pages; i++) { - page_cache_release(wdata->pages[i]); + put_page(wdata->pages[i]); wdata->pages[i] = NULL; } @@ -2009,11 +2009,11 @@ wdata_send_pages(struct cifs_writedata *wdata, unsigned int nr_pages, wdata->sync_mode = wbc->sync_mode; wdata->nr_pages = nr_pages; wdata->offset = page_offset(wdata->pages[0]); - wdata->pagesz = PAGE_CACHE_SIZE; + wdata->pagesz = PAGE_SIZE; wdata->tailsz = min(i_size_read(mapping->host) - page_offset(wdata->pages[nr_pages - 1]), - (loff_t)PAGE_CACHE_SIZE); - wdata->bytes = ((nr_pages - 1) * PAGE_CACHE_SIZE) + wdata->tailsz; + (loff_t)PAGE_SIZE); + wdata->bytes = ((nr_pages - 1) * PAGE_SIZE) + wdata->tailsz; if (wdata->cfile != NULL) cifsFileInfo_put(wdata->cfile); @@ -2047,15 +2047,15 @@ static int cifs_writepages(struct address_space *mapping, * If wsize is smaller than the page cache size, default to writing * one page at a time via cifs_writepage */ - if (cifs_sb->wsize < PAGE_CACHE_SIZE) + if (cifs_sb->wsize < PAGE_SIZE) return generic_writepages(mapping, wbc); if (wbc->range_cyclic) { index = mapping->writeback_index; /* Start from prev offset */ end = -1; } else { - index = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + index = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = true; scanned = true; @@ -2071,7 +2071,7 @@ retry: if (rc) break; - tofind = min((wsize / PAGE_CACHE_SIZE) - 1, end - index) + 1; + tofind = min((wsize / PAGE_SIZE) - 1, end - index) + 1; wdata = wdata_alloc_and_fillpages(tofind, mapping, end, &index, &found_pages); @@ -2111,7 +2111,7 @@ retry: else SetPageError(wdata->pages[i]); end_page_writeback(wdata->pages[i]); - page_cache_release(wdata->pages[i]); + put_page(wdata->pages[i]); } if (rc != -EAGAIN) mapping_set_error(mapping, rc); @@ -2154,7 +2154,7 @@ cifs_writepage_locked(struct page *page, struct writeback_control *wbc) xid = get_xid(); /* BB add check for wbc flags */ - page_cache_get(page); + get_page(page); if (!PageUptodate(page)) cifs_dbg(FYI, "ppw - page not up to date\n"); @@ -2170,7 +2170,7 @@ cifs_writepage_locked(struct page *page, struct writeback_control *wbc) */ set_page_writeback(page); retry_write: - rc = cifs_partialpagewrite(page, 0, PAGE_CACHE_SIZE); + rc = cifs_partialpagewrite(page, 0, PAGE_SIZE); if (rc == -EAGAIN && wbc->sync_mode == WB_SYNC_ALL) goto retry_write; else if (rc == -EAGAIN) @@ -2180,7 +2180,7 @@ retry_write: else SetPageUptodate(page); end_page_writeback(page); - page_cache_release(page); + put_page(page); free_xid(xid); return rc; } @@ -2214,12 +2214,12 @@ static int cifs_write_end(struct file *file, struct address_space *mapping, if (copied == len) SetPageUptodate(page); ClearPageChecked(page); - } else if (!PageUptodate(page) && copied == PAGE_CACHE_SIZE) + } else if (!PageUptodate(page) && copied == PAGE_SIZE) SetPageUptodate(page); if (!PageUptodate(page)) { char *page_data; - unsigned offset = pos & (PAGE_CACHE_SIZE - 1); + unsigned offset = pos & (PAGE_SIZE - 1); unsigned int xid; xid = get_xid(); @@ -2248,7 +2248,7 @@ static int cifs_write_end(struct file *file, struct address_space *mapping, } unlock_page(page); - page_cache_release(page); + put_page(page); return rc; } @@ -3286,9 +3286,9 @@ cifs_readv_complete(struct work_struct *work) (rdata->result == -EAGAIN && got_bytes)) cifs_readpage_to_fscache(rdata->mapping->host, page); - got_bytes -= min_t(unsigned int, PAGE_CACHE_SIZE, got_bytes); + got_bytes -= min_t(unsigned int, PAGE_SIZE, got_bytes); - page_cache_release(page); + put_page(page); rdata->pages[i] = NULL; } kref_put(&rdata->refcount, cifs_readdata_release); @@ -3307,21 +3307,21 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server, /* determine the eof that the server (probably) has */ eof = CIFS_I(rdata->mapping->host)->server_eof; - eof_index = eof ? (eof - 1) >> PAGE_CACHE_SHIFT : 0; + eof_index = eof ? (eof - 1) >> PAGE_SHIFT : 0; cifs_dbg(FYI, "eof=%llu eof_index=%lu\n", eof, eof_index); rdata->got_bytes = 0; - rdata->tailsz = PAGE_CACHE_SIZE; + rdata->tailsz = PAGE_SIZE; for (i = 0; i < nr_pages; i++) { struct page *page = rdata->pages[i]; - if (len >= PAGE_CACHE_SIZE) { + if (len >= PAGE_SIZE) { /* enough data to fill the page */ iov.iov_base = kmap(page); - iov.iov_len = PAGE_CACHE_SIZE; + iov.iov_len = PAGE_SIZE; cifs_dbg(FYI, "%u: idx=%lu iov_base=%p iov_len=%zu\n", i, page->index, iov.iov_base, iov.iov_len); - len -= PAGE_CACHE_SIZE; + len -= PAGE_SIZE; } else if (len > 0) { /* enough for partial page, fill and zero the rest */ iov.iov_base = kmap(page); @@ -3329,7 +3329,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server, cifs_dbg(FYI, "%u: idx=%lu iov_base=%p iov_len=%zu\n", i, page->index, iov.iov_base, iov.iov_len); memset(iov.iov_base + len, - '\0', PAGE_CACHE_SIZE - len); + '\0', PAGE_SIZE - len); rdata->tailsz = len; len = 0; } else if (page->index > eof_index) { @@ -3341,12 +3341,12 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server, * to prevent the VFS from repeatedly attempting to * fill them until the writes are flushed. */ - zero_user(page, 0, PAGE_CACHE_SIZE); + zero_user(page, 0, PAGE_SIZE); lru_cache_add_file(page); flush_dcache_page(page); SetPageUptodate(page); unlock_page(page); - page_cache_release(page); + put_page(page); rdata->pages[i] = NULL; rdata->nr_pages--; continue; @@ -3354,7 +3354,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server, /* no need to hold page hostage */ lru_cache_add_file(page); unlock_page(page); - page_cache_release(page); + put_page(page); rdata->pages[i] = NULL; rdata->nr_pages--; continue; @@ -3402,8 +3402,8 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, } /* move first page to the tmplist */ - *offset = (loff_t)page->index << PAGE_CACHE_SHIFT; - *bytes = PAGE_CACHE_SIZE; + *offset = (loff_t)page->index << PAGE_SHIFT; + *bytes = PAGE_SIZE; *nr_pages = 1; list_move_tail(&page->lru, tmplist); @@ -3415,7 +3415,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, break; /* would this page push the read over the rsize? */ - if (*bytes + PAGE_CACHE_SIZE > rsize) + if (*bytes + PAGE_SIZE > rsize) break; __SetPageLocked(page); @@ -3424,7 +3424,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, break; } list_move_tail(&page->lru, tmplist); - (*bytes) += PAGE_CACHE_SIZE; + (*bytes) += PAGE_SIZE; expected_index++; (*nr_pages)++; } @@ -3493,7 +3493,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, * reach this point however since we set ra_pages to 0 when the * rsize is smaller than a cache page. */ - if (unlikely(rsize < PAGE_CACHE_SIZE)) { + if (unlikely(rsize < PAGE_SIZE)) { add_credits_and_wake_if(server, credits, 0); return 0; } @@ -3512,7 +3512,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, list_del(&page->lru); lru_cache_add_file(page); unlock_page(page); - page_cache_release(page); + put_page(page); } rc = -ENOMEM; add_credits_and_wake_if(server, credits, 0); @@ -3524,7 +3524,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, rdata->offset = offset; rdata->bytes = bytes; rdata->pid = pid; - rdata->pagesz = PAGE_CACHE_SIZE; + rdata->pagesz = PAGE_SIZE; rdata->read_into_pages = cifs_readpages_read_into_pages; rdata->credits = credits; @@ -3542,7 +3542,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, page = rdata->pages[i]; lru_cache_add_file(page); unlock_page(page); - page_cache_release(page); + put_page(page); } /* Fallback to the readpage in error/reconnect cases */ kref_put(&rdata->refcount, cifs_readdata_release); @@ -3577,7 +3577,7 @@ static int cifs_readpage_worker(struct file *file, struct page *page, read_data = kmap(page); /* for reads over a certain size could initiate async read ahead */ - rc = cifs_read(file, read_data, PAGE_CACHE_SIZE, poffset); + rc = cifs_read(file, read_data, PAGE_SIZE, poffset); if (rc < 0) goto io_error; @@ -3587,8 +3587,8 @@ static int cifs_readpage_worker(struct file *file, struct page *page, file_inode(file)->i_atime = current_fs_time(file_inode(file)->i_sb); - if (PAGE_CACHE_SIZE > rc) - memset(read_data + rc, 0, PAGE_CACHE_SIZE - rc); + if (PAGE_SIZE > rc) + memset(read_data + rc, 0, PAGE_SIZE - rc); flush_dcache_page(page); SetPageUptodate(page); @@ -3608,7 +3608,7 @@ read_complete: static int cifs_readpage(struct file *file, struct page *page) { - loff_t offset = (loff_t)page->index << PAGE_CACHE_SHIFT; + loff_t offset = (loff_t)page->index << PAGE_SHIFT; int rc = -EACCES; unsigned int xid; @@ -3679,8 +3679,8 @@ static int cifs_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { int oncethru = 0; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; - loff_t offset = pos & (PAGE_CACHE_SIZE - 1); + pgoff_t index = pos >> PAGE_SHIFT; + loff_t offset = pos & (PAGE_SIZE - 1); loff_t page_start = pos & PAGE_MASK; loff_t i_size; struct page *page; @@ -3703,7 +3703,7 @@ start: * the server. If the write is short, we'll end up doing a sync write * instead. */ - if (len == PAGE_CACHE_SIZE) + if (len == PAGE_SIZE) goto out; /* @@ -3718,7 +3718,7 @@ start: (offset == 0 && (pos + len) >= i_size)) { zero_user_segments(page, 0, offset, offset + len, - PAGE_CACHE_SIZE); + PAGE_SIZE); /* * PageChecked means that the parts of the page * to which we're not writing are considered up @@ -3737,7 +3737,7 @@ start: * do a sync write instead since PG_uptodate isn't set. */ cifs_readpage_worker(file, page, &page_start); - page_cache_release(page); + put_page(page); oncethru = 1; goto start; } else { @@ -3764,7 +3764,7 @@ static void cifs_invalidate_page(struct page *page, unsigned int offset, { struct cifsInodeInfo *cifsi = CIFS_I(page->mapping->host); - if (offset == 0 && length == PAGE_CACHE_SIZE) + if (offset == 0 && length == PAGE_SIZE) cifs_fscache_invalidate_page(page, &cifsi->vfs_inode); } @@ -3772,7 +3772,7 @@ static int cifs_launder_page(struct page *page) { int rc = 0; loff_t range_start = page_offset(page); - loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1); + loff_t range_end = range_start + (loff_t)(PAGE_SIZE - 1); struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = 0, diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index aeb26dbfa1bf..5f9ad5c42180 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -59,7 +59,7 @@ static void cifs_set_ops(struct inode *inode) /* check if server can support readpages */ if (cifs_sb_master_tcon(cifs_sb)->ses->server->maxBuf < - PAGE_CACHE_SIZE + MAX_CIFS_HDR_SIZE) + PAGE_SIZE + MAX_CIFS_HDR_SIZE) inode->i_data.a_ops = &cifs_addr_ops_smallbuf; else inode->i_data.a_ops = &cifs_addr_ops; @@ -2019,8 +2019,8 @@ int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry, static int cifs_truncate_page(struct address_space *mapping, loff_t from) { - pgoff_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE - 1); + pgoff_t index = from >> PAGE_SHIFT; + unsigned offset = from & (PAGE_SIZE - 1); struct page *page; int rc = 0; @@ -2028,9 +2028,9 @@ static int cifs_truncate_page(struct address_space *mapping, loff_t from) if (!page) return -ENOMEM; - zero_user_segment(page, offset, PAGE_CACHE_SIZE); + zero_user_segment(page, offset, PAGE_SIZE); unlock_page(page); - page_cache_release(page); + put_page(page); return rc; } diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index a8f3b589a2df..cfd91320e869 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -71,8 +71,8 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent) struct inode *inode; struct dentry *root; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = CONFIGFS_MAGIC; sb->s_op = &configfs_ops; sb->s_time_gran = 1; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index b862bc219cd7..2096654dd26d 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -152,7 +152,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb, */ #define BLKS_PER_BUF_SHIFT (2) #define BLKS_PER_BUF (1 << BLKS_PER_BUF_SHIFT) -#define BUFFER_SIZE (BLKS_PER_BUF*PAGE_CACHE_SIZE) +#define BUFFER_SIZE (BLKS_PER_BUF*PAGE_SIZE) static unsigned char read_buffers[READ_BUFFERS][BUFFER_SIZE]; static unsigned buffer_blocknr[READ_BUFFERS]; @@ -173,8 +173,8 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i if (!len) return NULL; - blocknr = offset >> PAGE_CACHE_SHIFT; - offset &= PAGE_CACHE_SIZE - 1; + blocknr = offset >> PAGE_SHIFT; + offset &= PAGE_SIZE - 1; /* Check if an existing buffer already has the data.. */ for (i = 0; i < READ_BUFFERS; i++) { @@ -184,14 +184,14 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i continue; if (blocknr < buffer_blocknr[i]) continue; - blk_offset = (blocknr - buffer_blocknr[i]) << PAGE_CACHE_SHIFT; + blk_offset = (blocknr - buffer_blocknr[i]) << PAGE_SHIFT; blk_offset += offset; if (blk_offset + len > BUFFER_SIZE) continue; return read_buffers[i] + blk_offset; } - devsize = mapping->host->i_size >> PAGE_CACHE_SHIFT; + devsize = mapping->host->i_size >> PAGE_SHIFT; /* Ok, read in BLKS_PER_BUF pages completely first. */ for (i = 0; i < BLKS_PER_BUF; i++) { @@ -213,7 +213,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i wait_on_page_locked(page); if (!PageUptodate(page)) { /* asynchronous error */ - page_cache_release(page); + put_page(page); pages[i] = NULL; } } @@ -229,12 +229,12 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i struct page *page = pages[i]; if (page) { - memcpy(data, kmap(page), PAGE_CACHE_SIZE); + memcpy(data, kmap(page), PAGE_SIZE); kunmap(page); - page_cache_release(page); + put_page(page); } else - memset(data, 0, PAGE_CACHE_SIZE); - data += PAGE_CACHE_SIZE; + memset(data, 0, PAGE_SIZE); + data += PAGE_SIZE; } return read_buffers[buffer] + offset; } @@ -353,7 +353,7 @@ static int cramfs_statfs(struct dentry *dentry, struct kstatfs *buf) u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = CRAMFS_MAGIC; - buf->f_bsize = PAGE_CACHE_SIZE; + buf->f_bsize = PAGE_SIZE; buf->f_blocks = CRAMFS_SB(sb)->blocks; buf->f_bfree = 0; buf->f_bavail = 0; @@ -496,7 +496,7 @@ static int cramfs_readpage(struct file *file, struct page *page) int bytes_filled; void *pgdata; - maxblock = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + maxblock = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; bytes_filled = 0; pgdata = kmap(page); @@ -516,14 +516,14 @@ static int cramfs_readpage(struct file *file, struct page *page) if (compr_len == 0) ; /* hole */ - else if (unlikely(compr_len > (PAGE_CACHE_SIZE << 1))) { + else if (unlikely(compr_len > (PAGE_SIZE << 1))) { pr_err("bad compressed blocksize %u\n", compr_len); goto err; } else { mutex_lock(&read_mutex); bytes_filled = cramfs_uncompress_block(pgdata, - PAGE_CACHE_SIZE, + PAGE_SIZE, cramfs_read(sb, start_offset, compr_len), compr_len); mutex_unlock(&read_mutex); @@ -532,7 +532,7 @@ static int cramfs_readpage(struct file *file, struct page *page) } } - memset(pgdata + bytes_filled, 0, PAGE_CACHE_SIZE - bytes_filled); + memset(pgdata + bytes_filled, 0, PAGE_SIZE - bytes_filled); flush_dcache_page(page); kunmap(page); SetPageUptodate(page); diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 06cd1a22240b..7f5804537d30 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -175,10 +175,10 @@ static int do_page_crypto(struct inode *inode, FS_XTS_TWEAK_SIZE - sizeof(index)); sg_init_table(&dst, 1); - sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0); + sg_set_page(&dst, dest_page, PAGE_SIZE, 0); sg_init_table(&src, 1); - sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0); - skcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE, + sg_set_page(&src, src_page, PAGE_SIZE, 0); + skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE, xts_tweak); if (rw == FS_DECRYPT) res = crypto_skcipher_decrypt(req); @@ -287,7 +287,7 @@ int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk, struct bio *bio; int ret, err = 0; - BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE); + BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE); ctx = fscrypt_get_ctx(inode); if (IS_ERR(ctx)) diff --git a/fs/dax.c b/fs/dax.c index 90322eb7498c..1f954166704a 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -323,7 +323,7 @@ static int dax_load_hole(struct address_space *mapping, struct page *page, size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (vmf->pgoff >= size) { unlock_page(page); - page_cache_release(page); + put_page(page); return VM_FAULT_SIGBUS; } @@ -351,7 +351,7 @@ static int copy_user_bh(struct page *to, struct inode *inode, } #define NO_SECTOR -1 -#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_CACHE_SHIFT)) +#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT)) static int dax_radix_entry(struct address_space *mapping, pgoff_t index, sector_t sector, bool pmd_entry, bool dirty) @@ -506,8 +506,8 @@ int dax_writeback_mapping_range(struct address_space *mapping, if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL) return 0; - start_index = wbc->range_start >> PAGE_CACHE_SHIFT; - end_index = wbc->range_end >> PAGE_CACHE_SHIFT; + start_index = wbc->range_start >> PAGE_SHIFT; + end_index = wbc->range_end >> PAGE_SHIFT; pmd_index = DAX_PMD_INDEX(start_index); rcu_read_lock(); @@ -642,12 +642,12 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, page = find_get_page(mapping, vmf->pgoff); if (page) { if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) { - page_cache_release(page); + put_page(page); return VM_FAULT_RETRY; } if (unlikely(page->mapping != mapping)) { unlock_page(page); - page_cache_release(page); + put_page(page); goto repeat; } size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; @@ -711,10 +711,10 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, if (page) { unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT, - PAGE_CACHE_SIZE, 0); + PAGE_SIZE, 0); delete_from_page_cache(page); unlock_page(page); - page_cache_release(page); + put_page(page); page = NULL; } @@ -747,7 +747,7 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, unlock_page: if (page) { unlock_page(page); - page_cache_release(page); + put_page(page); } goto out; } @@ -1104,18 +1104,18 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length, get_block_t get_block) { struct buffer_head bh; - pgoff_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); + pgoff_t index = from >> PAGE_SHIFT; + unsigned offset = from & (PAGE_SIZE-1); int err; /* Block boundary? Nothing to do */ if (!length) return 0; - BUG_ON((offset + length) > PAGE_CACHE_SIZE); + BUG_ON((offset + length) > PAGE_SIZE); memset(&bh, 0, sizeof(bh)); bh.b_bdev = inode->i_sb->s_bdev; - bh.b_size = PAGE_CACHE_SIZE; + bh.b_size = PAGE_SIZE; err = get_block(inode, index, &bh, 0); if (err < 0) return err; @@ -1123,7 +1123,7 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length, struct block_device *bdev = bh.b_bdev; struct blk_dax_ctl dax = { .sector = to_sector(&bh, inode), - .size = PAGE_CACHE_SIZE, + .size = PAGE_SIZE, }; if (dax_map_atomic(bdev, &dax) < 0) @@ -1154,7 +1154,7 @@ EXPORT_SYMBOL_GPL(dax_zero_page_range); */ int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block) { - unsigned length = PAGE_CACHE_ALIGN(from) - from; + unsigned length = PAGE_ALIGN(from) - from; return dax_zero_page_range(inode, from, length, get_block); } EXPORT_SYMBOL_GPL(dax_truncate_page); diff --git a/fs/direct-io.c b/fs/direct-io.c index 476f1ecbd1f0..472037732daf 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -172,7 +172,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) */ if (dio->page_errors == 0) dio->page_errors = ret; - page_cache_get(page); + get_page(page); dio->pages[0] = page; sdio->head = 0; sdio->tail = 1; @@ -424,7 +424,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio) { while (sdio->head < sdio->tail) - page_cache_release(dio->pages[sdio->head++]); + put_page(dio->pages[sdio->head++]); } /* @@ -487,7 +487,7 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio) if (dio->rw == READ && !PageCompound(page) && dio->should_dirty) set_page_dirty_lock(page); - page_cache_release(page); + put_page(page); } err = bio->bi_error; bio_put(bio); @@ -696,7 +696,7 @@ static inline int dio_bio_add_page(struct dio_submit *sdio) */ if ((sdio->cur_page_len + sdio->cur_page_offset) == PAGE_SIZE) sdio->pages_in_io--; - page_cache_get(sdio->cur_page); + get_page(sdio->cur_page); sdio->final_block_in_bio = sdio->cur_page_block + (sdio->cur_page_len >> sdio->blkbits); ret = 0; @@ -810,13 +810,13 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, */ if (sdio->cur_page) { ret = dio_send_cur_page(dio, sdio, map_bh); - page_cache_release(sdio->cur_page); + put_page(sdio->cur_page); sdio->cur_page = NULL; if (ret) return ret; } - page_cache_get(page); /* It is in dio */ + get_page(page); /* It is in dio */ sdio->cur_page = page; sdio->cur_page_offset = offset; sdio->cur_page_len = len; @@ -830,7 +830,7 @@ out: if (sdio->boundary) { ret = dio_send_cur_page(dio, sdio, map_bh); dio_bio_submit(dio, sdio); - page_cache_release(sdio->cur_page); + put_page(sdio->cur_page); sdio->cur_page = NULL; } return ret; @@ -947,7 +947,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio, ret = get_more_blocks(dio, sdio, map_bh); if (ret) { - page_cache_release(page); + put_page(page); goto out; } if (!buffer_mapped(map_bh)) @@ -988,7 +988,7 @@ do_holes: /* AKPM: eargh, -ENOTBLK is a hack */ if (dio->rw & WRITE) { - page_cache_release(page); + put_page(page); return -ENOTBLK; } @@ -1001,7 +1001,7 @@ do_holes: if (sdio->block_in_file >= i_size_aligned >> blkbits) { /* We hit eof */ - page_cache_release(page); + put_page(page); goto out; } zero_user(page, from, 1 << blkbits); @@ -1041,7 +1041,7 @@ do_holes: sdio->next_block_for_io, map_bh); if (ret) { - page_cache_release(page); + put_page(page); goto out; } sdio->next_block_for_io += this_chunk_blocks; @@ -1057,7 +1057,7 @@ next_block: } /* Drop the ref which was taken in get_user_pages() */ - page_cache_release(page); + put_page(page); } out: return ret; @@ -1281,7 +1281,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, ret2 = dio_send_cur_page(dio, &sdio, &map_bh); if (retval == 0) retval = ret2; - page_cache_release(sdio.cur_page); + put_page(sdio.cur_page); sdio.cur_page = NULL; } if (sdio.bio) diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 00640e70ed7a..1ab012a27d9f 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -640,7 +640,7 @@ static int receive_from_sock(struct connection *con) con->rx_page = alloc_page(GFP_ATOMIC); if (con->rx_page == NULL) goto out_resched; - cbuf_init(&con->cb, PAGE_CACHE_SIZE); + cbuf_init(&con->cb, PAGE_SIZE); } /* @@ -657,7 +657,7 @@ static int receive_from_sock(struct connection *con) * buffer and the start of the currently used section (cb.base) */ if (cbuf_data(&con->cb) >= con->cb.base) { - iov[0].iov_len = PAGE_CACHE_SIZE - cbuf_data(&con->cb); + iov[0].iov_len = PAGE_SIZE - cbuf_data(&con->cb); iov[1].iov_len = con->cb.base; iov[1].iov_base = page_address(con->rx_page); nvec = 2; @@ -675,7 +675,7 @@ static int receive_from_sock(struct connection *con) ret = dlm_process_incoming_buffer(con->nodeid, page_address(con->rx_page), con->cb.base, con->cb.len, - PAGE_CACHE_SIZE); + PAGE_SIZE); if (ret == -EBADMSG) { log_print("lowcomms: addr=%p, base=%u, len=%u, read=%d", page_address(con->rx_page), con->cb.base, @@ -1416,7 +1416,7 @@ void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc) spin_lock(&con->writequeue_lock); e = list_entry(con->writequeue.prev, struct writequeue_entry, list); if ((&e->list == &con->writequeue) || - (PAGE_CACHE_SIZE - e->end < len)) { + (PAGE_SIZE - e->end < len)) { e = NULL; } else { offset = e->end; diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 64026e53722a..d09cb4cdd09f 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -286,7 +286,7 @@ int virt_to_scatterlist(const void *addr, int size, struct scatterlist *sg, pg = virt_to_page(addr); offset = offset_in_page(addr); sg_set_page(&sg[i], pg, 0, offset); - remainder_of_page = PAGE_CACHE_SIZE - offset; + remainder_of_page = PAGE_SIZE - offset; if (size >= remainder_of_page) { sg[i].length = remainder_of_page; addr += remainder_of_page; @@ -400,7 +400,7 @@ static loff_t lower_offset_for_page(struct ecryptfs_crypt_stat *crypt_stat, struct page *page) { return ecryptfs_lower_header_size(crypt_stat) + - ((loff_t)page->index << PAGE_CACHE_SHIFT); + ((loff_t)page->index << PAGE_SHIFT); } /** @@ -428,7 +428,7 @@ static int crypt_extent(struct ecryptfs_crypt_stat *crypt_stat, size_t extent_size = crypt_stat->extent_size; int rc; - extent_base = (((loff_t)page_index) * (PAGE_CACHE_SIZE / extent_size)); + extent_base = (((loff_t)page_index) * (PAGE_SIZE / extent_size)); rc = ecryptfs_derive_iv(extent_iv, crypt_stat, (extent_base + extent_offset)); if (rc) { @@ -498,7 +498,7 @@ int ecryptfs_encrypt_page(struct page *page) } for (extent_offset = 0; - extent_offset < (PAGE_CACHE_SIZE / crypt_stat->extent_size); + extent_offset < (PAGE_SIZE / crypt_stat->extent_size); extent_offset++) { rc = crypt_extent(crypt_stat, enc_extent_page, page, extent_offset, ENCRYPT); @@ -512,7 +512,7 @@ int ecryptfs_encrypt_page(struct page *page) lower_offset = lower_offset_for_page(crypt_stat, page); enc_extent_virt = kmap(enc_extent_page); rc = ecryptfs_write_lower(ecryptfs_inode, enc_extent_virt, lower_offset, - PAGE_CACHE_SIZE); + PAGE_SIZE); kunmap(enc_extent_page); if (rc < 0) { ecryptfs_printk(KERN_ERR, @@ -560,7 +560,7 @@ int ecryptfs_decrypt_page(struct page *page) lower_offset = lower_offset_for_page(crypt_stat, page); page_virt = kmap(page); - rc = ecryptfs_read_lower(page_virt, lower_offset, PAGE_CACHE_SIZE, + rc = ecryptfs_read_lower(page_virt, lower_offset, PAGE_SIZE, ecryptfs_inode); kunmap(page); if (rc < 0) { @@ -571,7 +571,7 @@ int ecryptfs_decrypt_page(struct page *page) } for (extent_offset = 0; - extent_offset < (PAGE_CACHE_SIZE / crypt_stat->extent_size); + extent_offset < (PAGE_SIZE / crypt_stat->extent_size); extent_offset++) { rc = crypt_extent(crypt_stat, page, page, extent_offset, DECRYPT); @@ -659,11 +659,11 @@ void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat) if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) crypt_stat->metadata_size = ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; else { - if (PAGE_CACHE_SIZE <= ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE) + if (PAGE_SIZE <= ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE) crypt_stat->metadata_size = ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; else - crypt_stat->metadata_size = PAGE_CACHE_SIZE; + crypt_stat->metadata_size = PAGE_SIZE; } } @@ -1442,7 +1442,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry) ECRYPTFS_VALIDATE_HEADER_SIZE); if (rc) { /* metadata is not in the file header, so try xattrs */ - memset(page_virt, 0, PAGE_CACHE_SIZE); + memset(page_virt, 0, PAGE_SIZE); rc = ecryptfs_read_xattr_region(page_virt, ecryptfs_inode); if (rc) { printk(KERN_DEBUG "Valid eCryptfs headers not found in " @@ -1475,7 +1475,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry) } out: if (page_virt) { - memset(page_virt, 0, PAGE_CACHE_SIZE); + memset(page_virt, 0, PAGE_SIZE); kmem_cache_free(ecryptfs_header_cache, page_virt); } return rc; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 121114e9a464..2a988f3a0cdb 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -765,8 +765,8 @@ static int truncate_upper(struct dentry *dentry, struct iattr *ia, * in which ia->ia_size is located. Fill in the end of * that page from (ia->ia_size & ~PAGE_CACHE_MASK) to * PAGE_CACHE_SIZE with zeros. */ - size_t num_zeros = (PAGE_CACHE_SIZE - - (ia->ia_size & ~PAGE_CACHE_MASK)); + size_t num_zeros = (PAGE_SIZE + - (ia->ia_size & ~PAGE_MASK)); if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) { truncate_setsize(inode, ia->ia_size); diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 9893d1538122..3cf1546dca82 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -1798,7 +1798,7 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, * added the our &auth_tok_list */ next_packet_is_auth_tok_packet = 1; while (next_packet_is_auth_tok_packet) { - size_t max_packet_size = ((PAGE_CACHE_SIZE - 8) - i); + size_t max_packet_size = ((PAGE_SIZE - 8) - i); switch (src[i]) { case ECRYPTFS_TAG_3_PACKET_TYPE: diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 8b0b4a73116d..1698132d0e57 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -695,12 +695,12 @@ static struct ecryptfs_cache_info { { .cache = &ecryptfs_header_cache, .name = "ecryptfs_headers", - .size = PAGE_CACHE_SIZE, + .size = PAGE_SIZE, }, { .cache = &ecryptfs_xattr_cache, .name = "ecryptfs_xattr_cache", - .size = PAGE_CACHE_SIZE, + .size = PAGE_SIZE, }, { .cache = &ecryptfs_key_record_cache, @@ -818,7 +818,7 @@ static int __init ecryptfs_init(void) { int rc; - if (ECRYPTFS_DEFAULT_EXTENT_SIZE > PAGE_CACHE_SIZE) { + if (ECRYPTFS_DEFAULT_EXTENT_SIZE > PAGE_SIZE) { rc = -EINVAL; ecryptfs_printk(KERN_ERR, "The eCryptfs extent size is " "larger than the host's page size, and so " @@ -826,7 +826,7 @@ static int __init ecryptfs_init(void) "default eCryptfs extent size is [%u] bytes; " "the page size is [%lu] bytes.\n", ECRYPTFS_DEFAULT_EXTENT_SIZE, - (unsigned long)PAGE_CACHE_SIZE); + (unsigned long)PAGE_SIZE); goto out; } rc = ecryptfs_init_kmem_caches(); diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 1f5865263b3e..e6b1d80952b9 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -122,7 +122,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page, struct ecryptfs_crypt_stat *crypt_stat) { loff_t extent_num_in_page = 0; - loff_t num_extents_per_page = (PAGE_CACHE_SIZE + loff_t num_extents_per_page = (PAGE_SIZE / crypt_stat->extent_size); int rc = 0; @@ -138,7 +138,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page, char *page_virt; page_virt = kmap_atomic(page); - memset(page_virt, 0, PAGE_CACHE_SIZE); + memset(page_virt, 0, PAGE_SIZE); /* TODO: Support more than one header extent */ if (view_extent_num == 0) { size_t written; @@ -164,8 +164,8 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page, - crypt_stat->metadata_size); rc = ecryptfs_read_lower_page_segment( - page, (lower_offset >> PAGE_CACHE_SHIFT), - (lower_offset & ~PAGE_CACHE_MASK), + page, (lower_offset >> PAGE_SHIFT), + (lower_offset & ~PAGE_MASK), crypt_stat->extent_size, page->mapping->host); if (rc) { printk(KERN_ERR "%s: Error attempting to read " @@ -198,7 +198,7 @@ static int ecryptfs_readpage(struct file *file, struct page *page) if (!crypt_stat || !(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) { rc = ecryptfs_read_lower_page_segment(page, page->index, 0, - PAGE_CACHE_SIZE, + PAGE_SIZE, page->mapping->host); } else if (crypt_stat->flags & ECRYPTFS_VIEW_AS_ENCRYPTED) { if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) { @@ -215,7 +215,7 @@ static int ecryptfs_readpage(struct file *file, struct page *page) } else { rc = ecryptfs_read_lower_page_segment( - page, page->index, 0, PAGE_CACHE_SIZE, + page, page->index, 0, PAGE_SIZE, page->mapping->host); if (rc) { printk(KERN_ERR "Error reading page; rc = " @@ -250,12 +250,12 @@ static int fill_zeros_to_end_of_page(struct page *page, unsigned int to) struct inode *inode = page->mapping->host; int end_byte_in_page; - if ((i_size_read(inode) / PAGE_CACHE_SIZE) != page->index) + if ((i_size_read(inode) / PAGE_SIZE) != page->index) goto out; - end_byte_in_page = i_size_read(inode) % PAGE_CACHE_SIZE; + end_byte_in_page = i_size_read(inode) % PAGE_SIZE; if (to > end_byte_in_page) end_byte_in_page = to; - zero_user_segment(page, end_byte_in_page, PAGE_CACHE_SIZE); + zero_user_segment(page, end_byte_in_page, PAGE_SIZE); out: return 0; } @@ -279,7 +279,7 @@ static int ecryptfs_write_begin(struct file *file, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; struct page *page; loff_t prev_page_end_size; int rc = 0; @@ -289,14 +289,14 @@ static int ecryptfs_write_begin(struct file *file, return -ENOMEM; *pagep = page; - prev_page_end_size = ((loff_t)index << PAGE_CACHE_SHIFT); + prev_page_end_size = ((loff_t)index << PAGE_SHIFT); if (!PageUptodate(page)) { struct ecryptfs_crypt_stat *crypt_stat = &ecryptfs_inode_to_private(mapping->host)->crypt_stat; if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) { rc = ecryptfs_read_lower_page_segment( - page, index, 0, PAGE_CACHE_SIZE, mapping->host); + page, index, 0, PAGE_SIZE, mapping->host); if (rc) { printk(KERN_ERR "%s: Error attempting to read " "lower page segment; rc = [%d]\n", @@ -322,7 +322,7 @@ static int ecryptfs_write_begin(struct file *file, SetPageUptodate(page); } else { rc = ecryptfs_read_lower_page_segment( - page, index, 0, PAGE_CACHE_SIZE, + page, index, 0, PAGE_SIZE, mapping->host); if (rc) { printk(KERN_ERR "%s: Error reading " @@ -336,9 +336,9 @@ static int ecryptfs_write_begin(struct file *file, } else { if (prev_page_end_size >= i_size_read(page->mapping->host)) { - zero_user(page, 0, PAGE_CACHE_SIZE); + zero_user(page, 0, PAGE_SIZE); SetPageUptodate(page); - } else if (len < PAGE_CACHE_SIZE) { + } else if (len < PAGE_SIZE) { rc = ecryptfs_decrypt_page(page); if (rc) { printk(KERN_ERR "%s: Error decrypting " @@ -371,11 +371,11 @@ static int ecryptfs_write_begin(struct file *file, * of page? Zero it out. */ if ((i_size_read(mapping->host) == prev_page_end_size) && (pos != 0)) - zero_user(page, 0, PAGE_CACHE_SIZE); + zero_user(page, 0, PAGE_SIZE); out: if (unlikely(rc)) { unlock_page(page); - page_cache_release(page); + put_page(page); *pagep = NULL; } return rc; @@ -437,7 +437,7 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode) } inode_lock(lower_inode); size = lower_inode->i_op->getxattr(lower_dentry, ECRYPTFS_XATTR_NAME, - xattr_virt, PAGE_CACHE_SIZE); + xattr_virt, PAGE_SIZE); if (size < 0) size = 8; put_unaligned_be64(i_size_read(ecryptfs_inode), xattr_virt); @@ -479,8 +479,8 @@ static int ecryptfs_write_end(struct file *file, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { - pgoff_t index = pos >> PAGE_CACHE_SHIFT; - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + pgoff_t index = pos >> PAGE_SHIFT; + unsigned from = pos & (PAGE_SIZE - 1); unsigned to = from + copied; struct inode *ecryptfs_inode = mapping->host; struct ecryptfs_crypt_stat *crypt_stat = @@ -500,7 +500,7 @@ static int ecryptfs_write_end(struct file *file, goto out; } if (!PageUptodate(page)) { - if (copied < PAGE_CACHE_SIZE) { + if (copied < PAGE_SIZE) { rc = 0; goto out; } @@ -533,7 +533,7 @@ static int ecryptfs_write_end(struct file *file, rc = copied; out: unlock_page(page); - page_cache_release(page); + put_page(page); return rc; } diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c index 09fe622274e4..158a3a39f82d 100644 --- a/fs/ecryptfs/read_write.c +++ b/fs/ecryptfs/read_write.c @@ -74,7 +74,7 @@ int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode, loff_t offset; int rc; - offset = ((((loff_t)page_for_lower->index) << PAGE_CACHE_SHIFT) + offset = ((((loff_t)page_for_lower->index) << PAGE_SHIFT) + offset_in_page); virt = kmap(page_for_lower); rc = ecryptfs_write_lower(ecryptfs_inode, virt, offset, size); @@ -123,9 +123,9 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset, else pos = offset; while (pos < (offset + size)) { - pgoff_t ecryptfs_page_idx = (pos >> PAGE_CACHE_SHIFT); - size_t start_offset_in_page = (pos & ~PAGE_CACHE_MASK); - size_t num_bytes = (PAGE_CACHE_SIZE - start_offset_in_page); + pgoff_t ecryptfs_page_idx = (pos >> PAGE_SHIFT); + size_t start_offset_in_page = (pos & ~PAGE_MASK); + size_t num_bytes = (PAGE_SIZE - start_offset_in_page); loff_t total_remaining_bytes = ((offset + size) - pos); if (fatal_signal_pending(current)) { @@ -165,7 +165,7 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset, * Fill in zero values to the end of the page */ memset(((char *)ecryptfs_page_virt + start_offset_in_page), 0, - PAGE_CACHE_SIZE - start_offset_in_page); + PAGE_SIZE - start_offset_in_page); } /* pos >= offset, we are now writing the data request */ @@ -186,7 +186,7 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset, ecryptfs_page, start_offset_in_page, data_offset); - page_cache_release(ecryptfs_page); + put_page(ecryptfs_page); if (rc) { printk(KERN_ERR "%s: Error encrypting " "page; rc = [%d]\n", __func__, rc); @@ -262,7 +262,7 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs, loff_t offset; int rc; - offset = ((((loff_t)page_index) << PAGE_CACHE_SHIFT) + offset_in_page); + offset = ((((loff_t)page_index) << PAGE_SHIFT) + offset_in_page); virt = kmap(page_for_ecryptfs); rc = ecryptfs_read_lower(virt, offset, size, ecryptfs_inode); if (rc > 0) diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index dd029d13ea61..553c5d2db4a4 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -197,8 +197,8 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) efivarfs_sb = sb; sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = EFIVARFS_MAGIC; sb->s_op = &efivarfs_ops; sb->s_d_op = &efivarfs_d_ops; diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c index e5bb2abf77f9..547b93cbea63 100644 --- a/fs/exofs/dir.c +++ b/fs/exofs/dir.c @@ -41,16 +41,16 @@ static inline unsigned exofs_chunk_size(struct inode *inode) static inline void exofs_put_page(struct page *page) { kunmap(page); - page_cache_release(page); + put_page(page); } static unsigned exofs_last_byte(struct inode *inode, unsigned long page_nr) { loff_t last_byte = inode->i_size; - last_byte -= page_nr << PAGE_CACHE_SHIFT; - if (last_byte > PAGE_CACHE_SIZE) - last_byte = PAGE_CACHE_SIZE; + last_byte -= page_nr << PAGE_SHIFT; + if (last_byte > PAGE_SIZE) + last_byte = PAGE_SIZE; return last_byte; } @@ -85,13 +85,13 @@ static void exofs_check_page(struct page *page) unsigned chunk_size = exofs_chunk_size(dir); char *kaddr = page_address(page); unsigned offs, rec_len; - unsigned limit = PAGE_CACHE_SIZE; + unsigned limit = PAGE_SIZE; struct exofs_dir_entry *p; char *error; /* if the page is the last one in the directory */ - if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) { - limit = dir->i_size & ~PAGE_CACHE_MASK; + if ((dir->i_size >> PAGE_SHIFT) == page->index) { + limit = dir->i_size & ~PAGE_MASK; if (limit & (chunk_size - 1)) goto Ebadsize; if (!limit) @@ -138,7 +138,7 @@ bad_entry: EXOFS_ERR( "ERROR [exofs_check_page]: bad entry in directory(0x%lx): %s - " "offset=%lu, inode=0x%llu, rec_len=%d, name_len=%d\n", - dir->i_ino, error, (page->index<i_ino, error, (page->index<inode_no)), rec_len, p->name_len); goto fail; @@ -147,7 +147,7 @@ Eend: EXOFS_ERR("ERROR [exofs_check_page]: " "entry in directory(0x%lx) spans the page boundary" "offset=%lu, inode=0x%llx\n", - dir->i_ino, (page->index<i_ino, (page->index<inode_no))); fail: SetPageChecked(page); @@ -237,8 +237,8 @@ exofs_readdir(struct file *file, struct dir_context *ctx) { loff_t pos = ctx->pos; struct inode *inode = file_inode(file); - unsigned int offset = pos & ~PAGE_CACHE_MASK; - unsigned long n = pos >> PAGE_CACHE_SHIFT; + unsigned int offset = pos & ~PAGE_MASK; + unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); unsigned chunk_mask = ~(exofs_chunk_size(inode)-1); int need_revalidate = (file->f_version != inode->i_version); @@ -254,7 +254,7 @@ exofs_readdir(struct file *file, struct dir_context *ctx) if (IS_ERR(page)) { EXOFS_ERR("ERROR: bad page in directory(0x%lx)\n", inode->i_ino); - ctx->pos += PAGE_CACHE_SIZE - offset; + ctx->pos += PAGE_SIZE - offset; return PTR_ERR(page); } kaddr = page_address(page); @@ -262,7 +262,7 @@ exofs_readdir(struct file *file, struct dir_context *ctx) if (offset) { offset = exofs_validate_entry(kaddr, offset, chunk_mask); - ctx->pos = (n<pos = (n<f_version = inode->i_version; need_revalidate = 0; @@ -449,7 +449,7 @@ int exofs_add_link(struct dentry *dentry, struct inode *inode) kaddr = page_address(page); dir_end = kaddr + exofs_last_byte(dir, n); de = (struct exofs_dir_entry *)kaddr; - kaddr += PAGE_CACHE_SIZE - reclen; + kaddr += PAGE_SIZE - reclen; while ((char *)de <= kaddr) { if ((char *)de == dir_end) { name_len = 0; @@ -602,7 +602,7 @@ int exofs_make_empty(struct inode *inode, struct inode *parent) kunmap_atomic(kaddr); err = exofs_commit_chunk(page, 0, chunk_size); fail: - page_cache_release(page); + put_page(page); return err; } diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 9eaf595aeaf8..49e1bd00b4ec 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -317,7 +317,7 @@ static int read_exec(struct page_collect *pcol) if (!pcol->ios) { int ret = ore_get_rw_state(&pcol->sbi->layout, &oi->oc, true, - pcol->pg_first << PAGE_CACHE_SHIFT, + pcol->pg_first << PAGE_SHIFT, pcol->length, &pcol->ios); if (ret) @@ -383,7 +383,7 @@ static int readpage_strip(void *data, struct page *page) struct inode *inode = pcol->inode; struct exofs_i_info *oi = exofs_i(inode); loff_t i_size = i_size_read(inode); - pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; + pgoff_t end_index = i_size >> PAGE_SHIFT; size_t len; int ret; @@ -397,9 +397,9 @@ static int readpage_strip(void *data, struct page *page) pcol->that_locked_page = page; if (page->index < end_index) - len = PAGE_CACHE_SIZE; + len = PAGE_SIZE; else if (page->index == end_index) - len = i_size & ~PAGE_CACHE_MASK; + len = i_size & ~PAGE_MASK; else len = 0; @@ -442,8 +442,8 @@ try_again: goto fail; } - if (len != PAGE_CACHE_SIZE) - zero_user(page, len, PAGE_CACHE_SIZE - len); + if (len != PAGE_SIZE) + zero_user(page, len, PAGE_SIZE - len); EXOFS_DBGMSG2(" readpage_strip(0x%lx, 0x%lx) len=0x%zx\n", inode->i_ino, page->index, len); @@ -609,7 +609,7 @@ static void __r4w_put_page(void *priv, struct page *page) if ((pcol->that_locked_page != page) && (ZERO_PAGE(0) != page)) { EXOFS_DBGMSG2("index=0x%lx\n", page->index); - page_cache_release(page); + put_page(page); return; } EXOFS_DBGMSG2("that_locked_page index=0x%lx\n", @@ -633,7 +633,7 @@ static int write_exec(struct page_collect *pcol) BUG_ON(pcol->ios); ret = ore_get_rw_state(&pcol->sbi->layout, &oi->oc, false, - pcol->pg_first << PAGE_CACHE_SHIFT, + pcol->pg_first << PAGE_SHIFT, pcol->length, &pcol->ios); if (unlikely(ret)) goto err; @@ -696,7 +696,7 @@ static int writepage_strip(struct page *page, struct inode *inode = pcol->inode; struct exofs_i_info *oi = exofs_i(inode); loff_t i_size = i_size_read(inode); - pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; + pgoff_t end_index = i_size >> PAGE_SHIFT; size_t len; int ret; @@ -708,9 +708,9 @@ static int writepage_strip(struct page *page, if (page->index < end_index) /* in this case, the page is within the limits of the file */ - len = PAGE_CACHE_SIZE; + len = PAGE_SIZE; else { - len = i_size & ~PAGE_CACHE_MASK; + len = i_size & ~PAGE_MASK; if (page->index > end_index || !len) { /* in this case, the page is outside the limits @@ -790,10 +790,10 @@ static int exofs_writepages(struct address_space *mapping, long start, end, expected_pages; int ret; - start = wbc->range_start >> PAGE_CACHE_SHIFT; + start = wbc->range_start >> PAGE_SHIFT; end = (wbc->range_end == LLONG_MAX) ? start + mapping->nrpages : - wbc->range_end >> PAGE_CACHE_SHIFT; + wbc->range_end >> PAGE_SHIFT; if (start || end) expected_pages = end - start + 1; @@ -881,15 +881,15 @@ int exofs_write_begin(struct file *file, struct address_space *mapping, } /* read modify write */ - if (!PageUptodate(page) && (len != PAGE_CACHE_SIZE)) { + if (!PageUptodate(page) && (len != PAGE_SIZE)) { loff_t i_size = i_size_read(mapping->host); - pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; + pgoff_t end_index = i_size >> PAGE_SHIFT; size_t rlen; if (page->index < end_index) - rlen = PAGE_CACHE_SIZE; + rlen = PAGE_SIZE; else if (page->index == end_index) - rlen = i_size & ~PAGE_CACHE_MASK; + rlen = i_size & ~PAGE_MASK; else rlen = 0; diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index c20d77df2679..622a686bb08b 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -292,11 +292,11 @@ static int exofs_rename(struct inode *old_dir, struct dentry *old_dentry, out_dir: if (dir_de) { kunmap(dir_page); - page_cache_release(dir_page); + put_page(dir_page); } out_old: kunmap(old_page); - page_cache_release(old_page); + put_page(old_page); out: return err; } diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 0c6638b40f21..1b45694de316 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -67,7 +67,7 @@ static inline unsigned ext2_chunk_size(struct inode *inode) static inline void ext2_put_page(struct page *page) { kunmap(page); - page_cache_release(page); + put_page(page); } /* @@ -79,9 +79,9 @@ ext2_last_byte(struct inode *inode, unsigned long page_nr) { unsigned last_byte = inode->i_size; - last_byte -= page_nr << PAGE_CACHE_SHIFT; - if (last_byte > PAGE_CACHE_SIZE) - last_byte = PAGE_CACHE_SIZE; + last_byte -= page_nr << PAGE_SHIFT; + if (last_byte > PAGE_SIZE) + last_byte = PAGE_SIZE; return last_byte; } @@ -118,12 +118,12 @@ static void ext2_check_page(struct page *page, int quiet) char *kaddr = page_address(page); u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count); unsigned offs, rec_len; - unsigned limit = PAGE_CACHE_SIZE; + unsigned limit = PAGE_SIZE; ext2_dirent *p; char *error; - if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) { - limit = dir->i_size & ~PAGE_CACHE_MASK; + if ((dir->i_size >> PAGE_SHIFT) == page->index) { + limit = dir->i_size & ~PAGE_MASK; if (limit & (chunk_size - 1)) goto Ebadsize; if (!limit) @@ -176,7 +176,7 @@ bad_entry: if (!quiet) ext2_error(sb, __func__, "bad entry in directory #%lu: : %s - " "offset=%lu, inode=%lu, rec_len=%d, name_len=%d", - dir->i_ino, error, (page->index<i_ino, error, (page->index<inode), rec_len, p->name_len); goto fail; @@ -186,7 +186,7 @@ Eend: ext2_error(sb, "ext2_check_page", "entry in directory #%lu spans the page boundary" "offset=%lu, inode=%lu", - dir->i_ino, (page->index<i_ino, (page->index<inode)); } fail: @@ -287,8 +287,8 @@ ext2_readdir(struct file *file, struct dir_context *ctx) loff_t pos = ctx->pos; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; - unsigned int offset = pos & ~PAGE_CACHE_MASK; - unsigned long n = pos >> PAGE_CACHE_SHIFT; + unsigned int offset = pos & ~PAGE_MASK; + unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); unsigned chunk_mask = ~(ext2_chunk_size(inode)-1); unsigned char *types = NULL; @@ -309,14 +309,14 @@ ext2_readdir(struct file *file, struct dir_context *ctx) ext2_error(sb, __func__, "bad page in #%lu", inode->i_ino); - ctx->pos += PAGE_CACHE_SIZE - offset; + ctx->pos += PAGE_SIZE - offset; return PTR_ERR(page); } kaddr = page_address(page); if (unlikely(need_revalidate)) { if (offset) { offset = ext2_validate_entry(kaddr, offset, chunk_mask); - ctx->pos = (n<pos = (n<f_version = inode->i_version; need_revalidate = 0; @@ -406,7 +406,7 @@ struct ext2_dir_entry_2 *ext2_find_entry (struct inode * dir, if (++n >= npages) n = 0; /* next page is past the blocks we've got */ - if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) { + if (unlikely(n > (dir->i_blocks >> (PAGE_SHIFT - 9)))) { ext2_error(dir->i_sb, __func__, "dir %lu size %lld exceeds block count %llu", dir->i_ino, dir->i_size, @@ -511,7 +511,7 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode) kaddr = page_address(page); dir_end = kaddr + ext2_last_byte(dir, n); de = (ext2_dirent *)kaddr; - kaddr += PAGE_CACHE_SIZE - reclen; + kaddr += PAGE_SIZE - reclen; while ((char *)de <= kaddr) { if ((char *)de == dir_end) { /* We hit i_size */ @@ -655,7 +655,7 @@ int ext2_make_empty(struct inode *inode, struct inode *parent) kunmap_atomic(kaddr); err = ext2_commit_chunk(page, 0, chunk_size); fail: - page_cache_release(page); + put_page(page); return err; } diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 7a2be8f7f3c3..d34843925b23 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -398,7 +398,7 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, ext2_set_link(old_inode, dir_de, dir_page, new_dir, 0); else { kunmap(dir_page); - page_cache_release(dir_page); + put_page(dir_page); } inode_dec_link_count(old_dir); } @@ -408,11 +408,11 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, out_dir: if (dir_de) { kunmap(dir_page); - page_cache_release(dir_page); + put_page(dir_page); } out_old: kunmap(old_page); - page_cache_release(old_page); + put_page(old_page); out: return err; } diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index edc053a81914..2580ef3346ca 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -283,10 +283,10 @@ static int ext4_page_crypto(struct inode *inode, EXT4_XTS_TWEAK_SIZE - sizeof(index)); sg_init_table(&dst, 1); - sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0); + sg_set_page(&dst, dest_page, PAGE_SIZE, 0); sg_init_table(&src, 1); - sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0); - skcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE, + sg_set_page(&src, src_page, PAGE_SIZE, 0); + skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE, xts_tweak); if (rw == EXT4_DECRYPT) res = crypto_skcipher_decrypt(req); @@ -396,7 +396,7 @@ int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk, (unsigned long) inode->i_ino, lblk, len); #endif - BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE); + BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE); ctx = ext4_get_crypto_ctx(inode); if (IS_ERR(ctx)) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 50ba27cbed03..561d7308b393 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -155,13 +155,13 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) err = ext4_map_blocks(NULL, inode, &map, 0); if (err > 0) { pgoff_t index = map.m_pblk >> - (PAGE_CACHE_SHIFT - inode->i_blkbits); + (PAGE_SHIFT - inode->i_blkbits); if (!ra_has_index(&file->f_ra, index)) page_cache_sync_readahead( sb->s_bdev->bd_inode->i_mapping, &file->f_ra, file, index, 1); - file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT; + file->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT; bh = ext4_bread(NULL, inode, map.m_lblk, 0); if (IS_ERR(bh)) { err = PTR_ERR(bh); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 6659e216385e..0caece398eb8 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -428,8 +428,8 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, lastoff = startoff; endoff = (loff_t)end_blk << blkbits; - index = startoff >> PAGE_CACHE_SHIFT; - end = endoff >> PAGE_CACHE_SHIFT; + index = startoff >> PAGE_SHIFT; + end = endoff >> PAGE_SHIFT; pagevec_init(&pvec, 0); do { diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 7cbdd3752ba5..7bc6c855cc18 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -482,7 +482,7 @@ static int ext4_read_inline_page(struct inode *inode, struct page *page) ret = ext4_read_inline_data(inode, kaddr, len, &iloc); flush_dcache_page(page); kunmap_atomic(kaddr); - zero_user_segment(page, len, PAGE_CACHE_SIZE); + zero_user_segment(page, len, PAGE_SIZE); SetPageUptodate(page); brelse(iloc.bh); @@ -507,7 +507,7 @@ int ext4_readpage_inline(struct inode *inode, struct page *page) if (!page->index) ret = ext4_read_inline_page(inode, page); else if (!PageUptodate(page)) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); } @@ -595,7 +595,7 @@ retry: if (ret) { unlock_page(page); - page_cache_release(page); + put_page(page); page = NULL; ext4_orphan_add(handle, inode); up_write(&EXT4_I(inode)->xattr_sem); @@ -621,7 +621,7 @@ retry: out: if (page) { unlock_page(page); - page_cache_release(page); + put_page(page); } if (sem_held) up_write(&EXT4_I(inode)->xattr_sem); @@ -690,7 +690,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, if (!ext4_has_inline_data(inode)) { ret = 0; unlock_page(page); - page_cache_release(page); + put_page(page); goto out_up_read; } @@ -815,7 +815,7 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, if (ret) { up_read(&EXT4_I(inode)->xattr_sem); unlock_page(page); - page_cache_release(page); + put_page(page); ext4_truncate_failed_write(inode); return ret; } @@ -829,7 +829,7 @@ out: up_read(&EXT4_I(inode)->xattr_sem); if (page) { unlock_page(page); - page_cache_release(page); + put_page(page); } return ret; } @@ -919,7 +919,7 @@ retry_journal: out_release_page: up_read(&EXT4_I(inode)->xattr_sem); unlock_page(page); - page_cache_release(page); + put_page(page); out_journal: ext4_journal_stop(handle); out: @@ -947,7 +947,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, i_size_changed = 1; } unlock_page(page); - page_cache_release(page); + put_page(page); /* * Don't mark the inode dirty under page lock. First, it unnecessarily diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index dab84a2530ff..8a43c683eef9 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1057,7 +1057,7 @@ int do_journal_get_write_access(handle_t *handle, static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned from = pos & (PAGE_SIZE - 1); unsigned to = from + len; struct inode *inode = page->mapping->host; unsigned block_start, block_end; @@ -1069,15 +1069,15 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, bool decrypt = false; BUG_ON(!PageLocked(page)); - BUG_ON(from > PAGE_CACHE_SIZE); - BUG_ON(to > PAGE_CACHE_SIZE); + BUG_ON(from > PAGE_SIZE); + BUG_ON(to > PAGE_SIZE); BUG_ON(from > to); if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); head = page_buffers(page); bbits = ilog2(blocksize); - block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + block = (sector_t)page->index << (PAGE_SHIFT - bbits); for (bh = head, block_start = 0; bh != head || !block_start; block++, block_start = block_end, bh = bh->b_this_page) { @@ -1159,8 +1159,8 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, * we allocate blocks but write fails for some reason */ needed_blocks = ext4_writepage_trans_blocks(inode) + 1; - index = pos >> PAGE_CACHE_SHIFT; - from = pos & (PAGE_CACHE_SIZE - 1); + index = pos >> PAGE_SHIFT; + from = pos & (PAGE_SIZE - 1); to = from + len; if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { @@ -1188,7 +1188,7 @@ retry_grab: retry_journal: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { - page_cache_release(page); + put_page(page); return PTR_ERR(handle); } @@ -1196,7 +1196,7 @@ retry_journal: if (page->mapping != mapping) { /* The page got truncated from under us */ unlock_page(page); - page_cache_release(page); + put_page(page); ext4_journal_stop(handle); goto retry_grab; } @@ -1252,7 +1252,7 @@ retry_journal: if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_journal; - page_cache_release(page); + put_page(page); return ret; } *pagep = page; @@ -1295,7 +1295,7 @@ static int ext4_write_end(struct file *file, ret = ext4_jbd2_file_inode(handle, inode); if (ret) { unlock_page(page); - page_cache_release(page); + put_page(page); goto errout; } } @@ -1315,7 +1315,7 @@ static int ext4_write_end(struct file *file, */ i_size_changed = ext4_update_inode_size(inode, pos + copied); unlock_page(page); - page_cache_release(page); + put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); @@ -1399,7 +1399,7 @@ static int ext4_journalled_write_end(struct file *file, int size_changed = 0; trace_ext4_journalled_write_end(inode, pos, len, copied); - from = pos & (PAGE_CACHE_SIZE - 1); + from = pos & (PAGE_SIZE - 1); to = from + len; BUG_ON(!ext4_handle_valid(handle)); @@ -1423,7 +1423,7 @@ static int ext4_journalled_write_end(struct file *file, ext4_set_inode_state(inode, EXT4_STATE_JDATA); EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; unlock_page(page); - page_cache_release(page); + put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); @@ -1537,7 +1537,7 @@ static void ext4_da_page_release_reservation(struct page *page, int num_clusters; ext4_fsblk_t lblk; - BUG_ON(stop > PAGE_CACHE_SIZE || stop < length); + BUG_ON(stop > PAGE_SIZE || stop < length); head = page_buffers(page); bh = head; @@ -1553,7 +1553,7 @@ static void ext4_da_page_release_reservation(struct page *page, clear_buffer_delay(bh); } else if (contiguous_blks) { lblk = page->index << - (PAGE_CACHE_SHIFT - inode->i_blkbits); + (PAGE_SHIFT - inode->i_blkbits); lblk += (curr_off >> inode->i_blkbits) - contiguous_blks; ext4_es_remove_extent(inode, lblk, contiguous_blks); @@ -1563,7 +1563,7 @@ static void ext4_da_page_release_reservation(struct page *page, } while ((bh = bh->b_this_page) != head); if (contiguous_blks) { - lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + lblk = page->index << (PAGE_SHIFT - inode->i_blkbits); lblk += (curr_off >> inode->i_blkbits) - contiguous_blks; ext4_es_remove_extent(inode, lblk, contiguous_blks); } @@ -1572,7 +1572,7 @@ static void ext4_da_page_release_reservation(struct page *page, * need to release the reserved space for that cluster. */ num_clusters = EXT4_NUM_B2C(sbi, to_release); while (num_clusters > 0) { - lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) + + lblk = (page->index << (PAGE_SHIFT - inode->i_blkbits)) + ((num_clusters - 1) << sbi->s_cluster_bits); if (sbi->s_cluster_ratio == 1 || !ext4_find_delalloc_cluster(inode, lblk)) @@ -1619,8 +1619,8 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, end = mpd->next_page - 1; if (invalidate) { ext4_lblk_t start, last; - start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits); + start = index << (PAGE_SHIFT - inode->i_blkbits); + last = end << (PAGE_SHIFT - inode->i_blkbits); ext4_es_remove_extent(inode, start, last - start + 1); } @@ -1636,7 +1636,7 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); if (invalidate) { - block_invalidatepage(page, 0, PAGE_CACHE_SIZE); + block_invalidatepage(page, 0, PAGE_SIZE); ClearPageUptodate(page); } unlock_page(page); @@ -2007,10 +2007,10 @@ static int ext4_writepage(struct page *page, trace_ext4_writepage(page); size = i_size_read(inode); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; + if (page->index == size >> PAGE_SHIFT) + len = size & ~PAGE_MASK; else - len = PAGE_CACHE_SIZE; + len = PAGE_SIZE; page_bufs = page_buffers(page); /* @@ -2034,7 +2034,7 @@ static int ext4_writepage(struct page *page, ext4_bh_delay_or_unwritten)) { redirty_page_for_writepage(wbc, page); if ((current->flags & PF_MEMALLOC) || - (inode->i_sb->s_blocksize == PAGE_CACHE_SIZE)) { + (inode->i_sb->s_blocksize == PAGE_SIZE)) { /* * For memory cleaning there's no point in writing only * some buffers. So just bail out. Warn if we came here @@ -2076,10 +2076,10 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) int err; BUG_ON(page->index != mpd->first_page); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; + if (page->index == size >> PAGE_SHIFT) + len = size & ~PAGE_MASK; else - len = PAGE_CACHE_SIZE; + len = PAGE_SIZE; clear_page_dirty_for_io(page); err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false); if (!err) @@ -2213,7 +2213,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) int nr_pages, i; struct inode *inode = mpd->inode; struct buffer_head *head, *bh; - int bpp_bits = PAGE_CACHE_SHIFT - inode->i_blkbits; + int bpp_bits = PAGE_SHIFT - inode->i_blkbits; pgoff_t start, end; ext4_lblk_t lblk; sector_t pblock; @@ -2274,7 +2274,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) * supports blocksize < pagesize as we will try to * convert potentially unmapped parts of inode. */ - mpd->io_submit.io_end->size += PAGE_CACHE_SIZE; + mpd->io_submit.io_end->size += PAGE_SIZE; /* Page fully mapped - let IO run! */ err = mpage_submit_page(mpd, page); if (err < 0) { @@ -2426,7 +2426,7 @@ update_disksize: * Update on-disk size after IO is submitted. Races with * truncate are avoided by checking i_size under i_data_sem. */ - disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT; + disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT; if (disksize > EXT4_I(inode)->i_disksize) { int err2; loff_t i_size; @@ -2562,7 +2562,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) mpd->next_page = page->index + 1; /* Add all dirty buffers to mpd */ lblk = ((ext4_lblk_t)page->index) << - (PAGE_CACHE_SHIFT - blkbits); + (PAGE_SHIFT - blkbits); head = page_buffers(page); err = mpage_process_page_bufs(mpd, head, head, lblk); if (err <= 0) @@ -2647,7 +2647,7 @@ static int ext4_writepages(struct address_space *mapping, * We may need to convert up to one extent per block in * the page and we may dirty the inode. */ - rsv_blocks = 1 + (PAGE_CACHE_SIZE >> inode->i_blkbits); + rsv_blocks = 1 + (PAGE_SIZE >> inode->i_blkbits); } /* @@ -2678,8 +2678,8 @@ static int ext4_writepages(struct address_space *mapping, mpd.first_page = writeback_index; mpd.last_page = -1; } else { - mpd.first_page = wbc->range_start >> PAGE_CACHE_SHIFT; - mpd.last_page = wbc->range_end >> PAGE_CACHE_SHIFT; + mpd.first_page = wbc->range_start >> PAGE_SHIFT; + mpd.last_page = wbc->range_end >> PAGE_SHIFT; } mpd.inode = inode; @@ -2838,7 +2838,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; handle_t *handle; - index = pos >> PAGE_CACHE_SHIFT; + index = pos >> PAGE_SHIFT; if (ext4_nonda_switch(inode->i_sb)) { *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; @@ -2881,7 +2881,7 @@ retry_journal: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, ext4_da_write_credits(inode, pos, len)); if (IS_ERR(handle)) { - page_cache_release(page); + put_page(page); return PTR_ERR(handle); } @@ -2889,7 +2889,7 @@ retry_journal: if (page->mapping != mapping) { /* The page got truncated from under us */ unlock_page(page); - page_cache_release(page); + put_page(page); ext4_journal_stop(handle); goto retry_grab; } @@ -2917,7 +2917,7 @@ retry_journal: ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_journal; - page_cache_release(page); + put_page(page); return ret; } @@ -2965,7 +2965,7 @@ static int ext4_da_write_end(struct file *file, len, copied, page, fsdata); trace_ext4_da_write_end(inode, pos, len, copied); - start = pos & (PAGE_CACHE_SIZE - 1); + start = pos & (PAGE_SIZE - 1); end = start + copied - 1; /* @@ -3187,7 +3187,7 @@ static int __ext4_journalled_invalidatepage(struct page *page, /* * If it's a full truncate we just forget about the pending dirtying */ - if (offset == 0 && length == PAGE_CACHE_SIZE) + if (offset == 0 && length == PAGE_SIZE) ClearPageChecked(page); return jbd2_journal_invalidatepage(journal, page, offset, length); @@ -3556,8 +3556,8 @@ void ext4_set_aops(struct inode *inode) static int __ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) { - ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); + ext4_fsblk_t index = from >> PAGE_SHIFT; + unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize, pos; ext4_lblk_t iblock; struct inode *inode = mapping->host; @@ -3565,14 +3565,14 @@ static int __ext4_block_zero_page_range(handle_t *handle, struct page *page; int err = 0; - page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, + page = find_or_create_page(mapping, from >> PAGE_SHIFT, mapping_gfp_constraint(mapping, ~__GFP_FS)); if (!page) return -ENOMEM; blocksize = inode->i_sb->s_blocksize; - iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits); + iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits); if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); @@ -3614,7 +3614,7 @@ static int __ext4_block_zero_page_range(handle_t *handle, ext4_encrypted_inode(inode)) { /* We expect the key to be set. */ BUG_ON(!ext4_has_encryption_key(inode)); - BUG_ON(blocksize != PAGE_CACHE_SIZE); + BUG_ON(blocksize != PAGE_SIZE); WARN_ON_ONCE(ext4_decrypt(page)); } } @@ -3638,7 +3638,7 @@ static int __ext4_block_zero_page_range(handle_t *handle, unlock: unlock_page(page); - page_cache_release(page); + put_page(page); return err; } @@ -3653,7 +3653,7 @@ static int ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) { struct inode *inode = mapping->host; - unsigned offset = from & (PAGE_CACHE_SIZE-1); + unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize = inode->i_sb->s_blocksize; unsigned max = blocksize - (offset & (blocksize - 1)); @@ -3678,7 +3678,7 @@ static int ext4_block_zero_page_range(handle_t *handle, static int ext4_block_truncate_page(handle_t *handle, struct address_space *mapping, loff_t from) { - unsigned offset = from & (PAGE_CACHE_SIZE-1); + unsigned offset = from & (PAGE_SIZE-1); unsigned length; unsigned blocksize; struct inode *inode = mapping->host; @@ -3816,7 +3816,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) */ if (offset + length > inode->i_size) { length = inode->i_size + - PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) - + PAGE_SIZE - (inode->i_size & (PAGE_SIZE - 1)) - offset; } @@ -4891,23 +4891,23 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) tid_t commit_tid = 0; int ret; - offset = inode->i_size & (PAGE_CACHE_SIZE - 1); + offset = inode->i_size & (PAGE_SIZE - 1); /* * All buffers in the last page remain valid? Then there's nothing to * do. We do the check mainly to optimize the common PAGE_CACHE_SIZE == * blocksize case */ - if (offset > PAGE_CACHE_SIZE - (1 << inode->i_blkbits)) + if (offset > PAGE_SIZE - (1 << inode->i_blkbits)) return; while (1) { page = find_lock_page(inode->i_mapping, - inode->i_size >> PAGE_CACHE_SHIFT); + inode->i_size >> PAGE_SHIFT); if (!page) return; ret = __ext4_journalled_invalidatepage(page, offset, - PAGE_CACHE_SIZE - offset); + PAGE_SIZE - offset); unlock_page(page); - page_cache_release(page); + put_page(page); if (ret != -EBUSY) return; commit_tid = 0; @@ -5546,10 +5546,10 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) goto out; } - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; + if (page->index == size >> PAGE_SHIFT) + len = size & ~PAGE_MASK; else - len = PAGE_CACHE_SIZE; + len = PAGE_SIZE; /* * Return if we have all the buffers mapped. This avoids the need to do * journal_start/journal_stop which can block and take a long time @@ -5580,7 +5580,7 @@ retry_alloc: ret = block_page_mkwrite(vma, vmf, get_block); if (!ret && ext4_should_journal_data(inode)) { if (ext4_walk_page_buffers(handle, page_buffers(page), 0, - PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) { + PAGE_SIZE, NULL, do_journal_get_write_access)) { unlock_page(page); ret = VM_FAULT_SIGBUS; ext4_journal_stop(handle); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 50e05df28f66..c12174711ce2 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -839,7 +839,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) sb = inode->i_sb; ngroups = ext4_get_groups_count(sb); blocksize = 1 << inode->i_blkbits; - blocks_per_page = PAGE_CACHE_SIZE / blocksize; + blocks_per_page = PAGE_SIZE / blocksize; groups_per_page = blocks_per_page >> 1; if (groups_per_page == 0) @@ -993,7 +993,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, e4b->bd_buddy_page = NULL; e4b->bd_bitmap_page = NULL; - blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; + blocks_per_page = PAGE_SIZE / sb->s_blocksize; /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. @@ -1028,11 +1028,11 @@ static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_page) { unlock_page(e4b->bd_bitmap_page); - page_cache_release(e4b->bd_bitmap_page); + put_page(e4b->bd_bitmap_page); } if (e4b->bd_buddy_page) { unlock_page(e4b->bd_buddy_page); - page_cache_release(e4b->bd_buddy_page); + put_page(e4b->bd_buddy_page); } } @@ -1125,7 +1125,7 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, might_sleep(); mb_debug(1, "load group %u\n", group); - blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; + blocks_per_page = PAGE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); e4b->bd_blkbits = sb->s_blocksize_bits; @@ -1167,7 +1167,7 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, * is yet to initialize the same. So * wait for it to initialize. */ - page_cache_release(page); + put_page(page); page = find_or_create_page(inode->i_mapping, pnum, gfp); if (page) { BUG_ON(page->mapping != inode->i_mapping); @@ -1203,7 +1203,7 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) - page_cache_release(page); + put_page(page); page = find_or_create_page(inode->i_mapping, pnum, gfp); if (page) { BUG_ON(page->mapping != inode->i_mapping); @@ -1238,11 +1238,11 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, err: if (page) - page_cache_release(page); + put_page(page); if (e4b->bd_bitmap_page) - page_cache_release(e4b->bd_bitmap_page); + put_page(e4b->bd_bitmap_page); if (e4b->bd_buddy_page) - page_cache_release(e4b->bd_buddy_page); + put_page(e4b->bd_buddy_page); e4b->bd_buddy = NULL; e4b->bd_bitmap = NULL; return ret; @@ -1257,9 +1257,9 @@ static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, static void ext4_mb_unload_buddy(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_page) - page_cache_release(e4b->bd_bitmap_page); + put_page(e4b->bd_bitmap_page); if (e4b->bd_buddy_page) - page_cache_release(e4b->bd_buddy_page); + put_page(e4b->bd_buddy_page); } @@ -2833,8 +2833,8 @@ static void ext4_free_data_callback(struct super_block *sb, /* No more items in the per group rb tree * balance refcounts from ext4_mb_free_metadata() */ - page_cache_release(e4b.bd_buddy_page); - page_cache_release(e4b.bd_bitmap_page); + put_page(e4b.bd_buddy_page); + put_page(e4b.bd_bitmap_page); } ext4_unlock_group(sb, entry->efd_group); kmem_cache_free(ext4_free_data_cachep, entry); @@ -4385,9 +4385,9 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac) ext4_mb_put_pa(ac, ac->ac_sb, pa); } if (ac->ac_bitmap_page) - page_cache_release(ac->ac_bitmap_page); + put_page(ac->ac_bitmap_page); if (ac->ac_buddy_page) - page_cache_release(ac->ac_buddy_page); + put_page(ac->ac_buddy_page); if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) mutex_unlock(&ac->ac_lg->lg_mutex); ext4_mb_collect_stats(ac); @@ -4599,8 +4599,8 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, * otherwise we'll refresh it from * on-disk bitmap and lose not-yet-available * blocks */ - page_cache_get(e4b->bd_buddy_page); - page_cache_get(e4b->bd_bitmap_page); + get_page(e4b->bd_buddy_page); + get_page(e4b->bd_bitmap_page); } while (*n) { parent = *n; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 4098acc701c3..675b67e5d5c2 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -156,7 +156,7 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2, page[1] = grab_cache_page_write_begin(mapping[1], index2, fl); if (!page[1]) { unlock_page(page[0]); - page_cache_release(page[0]); + put_page(page[0]); return -ENOMEM; } /* @@ -192,7 +192,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to) create_empty_buffers(page, blocksize, 0); head = page_buffers(page); - block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + block = (sector_t)page->index << (PAGE_SHIFT - inode->i_blkbits); for (bh = head, block_start = 0; bh != head || !block_start; block++, block_start = block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; @@ -268,7 +268,7 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, int i, err2, jblocks, retries = 0; int replaced_count = 0; int from = data_offset_in_page << orig_inode->i_blkbits; - int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; + int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits; struct super_block *sb = orig_inode->i_sb; struct buffer_head *bh = NULL; @@ -404,9 +404,9 @@ data_copy: unlock_pages: unlock_page(pagep[0]); - page_cache_release(pagep[0]); + put_page(pagep[0]); unlock_page(pagep[1]); - page_cache_release(pagep[1]); + put_page(pagep[1]); stop_journal: ext4_journal_stop(handle); if (*err == -ENOSPC && @@ -554,7 +554,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, struct inode *orig_inode = file_inode(o_filp); struct inode *donor_inode = file_inode(d_filp); struct ext4_ext_path *path = NULL; - int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; + int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits; ext4_lblk_t o_end, o_start = orig_blk; ext4_lblk_t d_start = donor_blk; int ret; @@ -648,9 +648,9 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, if (o_end - o_start < cur_len) cur_len = o_end - o_start; - orig_page_index = o_start >> (PAGE_CACHE_SHIFT - + orig_page_index = o_start >> (PAGE_SHIFT - orig_inode->i_blkbits); - donor_page_index = d_start >> (PAGE_CACHE_SHIFT - + donor_page_index = d_start >> (PAGE_SHIFT - donor_inode->i_blkbits); offset_in_page = o_start % blocks_per_page; if (cur_len > blocks_per_page- offset_in_page) diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index d77d15f4b674..93ad0acf704c 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -432,8 +432,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io, * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ - if (len < PAGE_CACHE_SIZE) - zero_user_segment(page, len, PAGE_CACHE_SIZE); + if (len < PAGE_SIZE) + zero_user_segment(page, len, PAGE_SIZE); /* * In the first loop we prepare and mark buffers to submit. We have to * mark all buffers in the page before submitting so that diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 5dc5e95063de..ea27aa1a778c 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -140,7 +140,7 @@ int ext4_mpage_readpages(struct address_space *mapping, struct inode *inode = mapping->host; const unsigned blkbits = inode->i_blkbits; - const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits; + const unsigned blocks_per_page = PAGE_SIZE >> blkbits; const unsigned blocksize = 1 << blkbits; sector_t block_in_file; sector_t last_block; @@ -173,7 +173,7 @@ int ext4_mpage_readpages(struct address_space *mapping, if (page_has_buffers(page)) goto confused; - block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits); + block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); last_block = block_in_file + nr_pages * blocks_per_page; last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits; if (last_block > last_block_in_file) @@ -217,7 +217,7 @@ int ext4_mpage_readpages(struct address_space *mapping, set_error_page: SetPageError(page); zero_user_segment(page, 0, - PAGE_CACHE_SIZE); + PAGE_SIZE); unlock_page(page); goto next_page; } @@ -250,7 +250,7 @@ int ext4_mpage_readpages(struct address_space *mapping, } if (first_hole != blocks_per_page) { zero_user_segment(page, first_hole << blkbits, - PAGE_CACHE_SIZE); + PAGE_SIZE); if (first_hole == 0) { SetPageUptodate(page); unlock_page(page); @@ -319,7 +319,7 @@ int ext4_mpage_readpages(struct address_space *mapping, unlock_page(page); next_page: if (pages) - page_cache_release(page); + put_page(page); } BUG_ON(pages && !list_empty(pages)); if (bio) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 539297515896..0bb74aacb8c0 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1784,7 +1784,7 @@ static int parse_options(char *options, struct super_block *sb, int blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); - if (blocksize < PAGE_CACHE_SIZE) { + if (blocksize < PAGE_SIZE) { ext4_msg(sb, KERN_ERR, "can't mount with " "dioread_nolock if block size != PAGE_SIZE"); return 0; @@ -3808,7 +3808,7 @@ no_journal: } if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) && - (blocksize != PAGE_CACHE_SIZE)) { + (blocksize != PAGE_SIZE)) { ext4_msg(sb, KERN_ERR, "Unsupported blocksize for fs encryption"); goto failed_mount_wq; diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index 6f7ee30a89ce..75ed5c2f0c16 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -80,12 +80,12 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry, if (res <= plen) paddr[res] = '\0'; if (cpage) - page_cache_release(cpage); + put_page(cpage); set_delayed_call(done, kfree_link, paddr); return paddr; errout: if (cpage) - page_cache_release(cpage); + put_page(cpage); kfree(paddr); return ERR_PTR(res); } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index e5c762b37239..53fec0872e60 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -223,7 +223,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) /* Allocate a new bio */ bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->rw)); - if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_put(bio); return -EFAULT; } @@ -265,8 +265,8 @@ alloc_new: bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; - if (bio_add_page(io->bio, bio_page, PAGE_CACHE_SIZE, 0) < - PAGE_CACHE_SIZE) { + if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < + PAGE_SIZE) { __submit_merged_bio(io); goto alloc_new; } @@ -406,7 +406,7 @@ got_it: * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata. */ if (dn.data_blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); unlock_page(page); return page; @@ -517,7 +517,7 @@ struct page *get_new_data_page(struct inode *inode, goto got_it; if (dn.data_blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); } else { f2fs_put_page(page, 1); @@ -530,8 +530,8 @@ struct page *get_new_data_page(struct inode *inode, } got_it: if (new_i_size && i_size_read(inode) < - ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)) { - i_size_write(inode, ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)); + ((loff_t)(index + 1) << PAGE_SHIFT)) { + i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT)); /* Only the directory inode sets new_i_size */ set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR); } @@ -570,9 +570,9 @@ alloc: /* update i_size */ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + dn->ofs_in_node; - if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT)) + if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT)) i_size_write(dn->inode, - ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT)); + ((loff_t)(fofs + 1) << PAGE_SHIFT)); return 0; } @@ -971,7 +971,7 @@ got_it: goto confused; } } else { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); unlock_page(page); goto next_page; @@ -1021,7 +1021,7 @@ submit_and_realloc: goto next_page; set_error_page: SetPageError(page); - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); unlock_page(page); goto next_page; confused: @@ -1032,7 +1032,7 @@ confused: unlock_page(page); next_page: if (pages) - page_cache_release(page); + put_page(page); } BUG_ON(pages && !list_empty(pages)); if (bio) @@ -1136,7 +1136,7 @@ static int f2fs_write_data_page(struct page *page, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); loff_t i_size = i_size_read(inode); const pgoff_t end_index = ((unsigned long long) i_size) - >> PAGE_CACHE_SHIFT; + >> PAGE_SHIFT; unsigned offset = 0; bool need_balance_fs = false; int err = 0; @@ -1157,11 +1157,11 @@ static int f2fs_write_data_page(struct page *page, * If the offset is out-of-range of file size, * this page does not have to be written to disk. */ - offset = i_size & (PAGE_CACHE_SIZE - 1); + offset = i_size & (PAGE_SIZE - 1); if ((page->index >= end_index + 1) || !offset) goto out; - zero_user_segment(page, offset, PAGE_CACHE_SIZE); + zero_user_segment(page, offset, PAGE_SIZE); write: if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; @@ -1267,8 +1267,8 @@ next: cycled = 0; end = -1; } else { - index = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + index = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ @@ -1448,11 +1448,11 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi, * the block addresses when there is no need to fill the page. */ if (!f2fs_has_inline_data(inode) && !f2fs_encrypted_inode(inode) && - len == PAGE_CACHE_SIZE) + len == PAGE_SIZE) return 0; if (f2fs_has_inline_data(inode) || - (pos & PAGE_CACHE_MASK) >= i_size_read(inode)) { + (pos & PAGE_MASK) >= i_size_read(inode)) { f2fs_lock_op(sbi); locked = true; } @@ -1513,7 +1513,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *page = NULL; - pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT; + pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT; bool need_balance = false; block_t blkaddr = NULL_ADDR; int err = 0; @@ -1561,22 +1561,22 @@ repeat: if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr); - if (len == PAGE_CACHE_SIZE) + if (len == PAGE_SIZE) goto out_update; if (PageUptodate(page)) goto out_clear; - if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) { - unsigned start = pos & (PAGE_CACHE_SIZE - 1); + if ((pos & PAGE_MASK) >= i_size_read(inode)) { + unsigned start = pos & (PAGE_SIZE - 1); unsigned end = start + len; /* Reading beyond i_size is simple: memset to zero */ - zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE); + zero_user_segments(page, 0, start, end, PAGE_SIZE); goto out_update; } if (blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); } else { struct f2fs_io_info fio = { .sbi = sbi, @@ -1688,7 +1688,7 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); if (inode->i_ino >= F2FS_ROOT_INO(sbi) && - (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE)) + (offset % PAGE_SIZE || length != PAGE_SIZE)) return; if (PageDirty(page)) { diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 4fb6ef88a34f..f4a61a5ff79f 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -164,7 +164,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) /* build curseg */ si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE; - si->base_mem += PAGE_CACHE_SIZE * NR_CURSEG_TYPE; + si->base_mem += PAGE_SIZE * NR_CURSEG_TYPE; /* build dirty segmap */ si->base_mem += sizeof(struct dirty_seglist_info); @@ -201,9 +201,9 @@ get_cache: si->page_mem = 0; npages = NODE_MAPPING(sbi)->nrpages; - si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT; + si->page_mem += (unsigned long long)npages << PAGE_SHIFT; npages = META_MAPPING(sbi)->nrpages; - si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT; + si->page_mem += (unsigned long long)npages << PAGE_SHIFT; } static int stat_show(struct seq_file *s, void *v) diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 80641ad82745..af819571bce7 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -17,8 +17,8 @@ static unsigned long dir_blocks(struct inode *inode) { - return ((unsigned long long) (i_size_read(inode) + PAGE_CACHE_SIZE - 1)) - >> PAGE_CACHE_SHIFT; + return ((unsigned long long) (i_size_read(inode) + PAGE_SIZE - 1)) + >> PAGE_SHIFT; } static unsigned int dir_buckets(unsigned int level, int dir_level) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index bbe2cd1265d0..7a4558d17f36 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1294,7 +1294,7 @@ static inline void f2fs_put_page(struct page *page, int unlock) f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page)); unlock_page(page); } - page_cache_release(page); + put_page(page); } static inline void f2fs_put_dnode(struct dnode_of_data *dn) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index b41c3579ea9e..443e07705c2a 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -74,11 +74,11 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, goto mapped; /* page is wholly or partially inside EOF */ - if (((loff_t)(page->index + 1) << PAGE_CACHE_SHIFT) > + if (((loff_t)(page->index + 1) << PAGE_SHIFT) > i_size_read(inode)) { unsigned offset; - offset = i_size_read(inode) & ~PAGE_CACHE_MASK; - zero_user_segment(page, offset, PAGE_CACHE_SIZE); + offset = i_size_read(inode) & ~PAGE_MASK; + zero_user_segment(page, offset, PAGE_SIZE); } set_page_dirty(page); SetPageUptodate(page); @@ -346,11 +346,11 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) goto found; } - pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT); + pgofs = (pgoff_t)(offset >> PAGE_SHIFT); dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence); - for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) { + for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) { set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA); if (err && err != -ENOENT) { @@ -370,7 +370,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) /* find data/hole in dnode block */ for (; dn.ofs_in_node < end_offset; dn.ofs_in_node++, pgofs++, - data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) { + data_ofs = (loff_t)pgofs << PAGE_SHIFT) { block_t blkaddr; blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); @@ -508,8 +508,8 @@ void truncate_data_blocks(struct dnode_of_data *dn) static int truncate_partial_data_page(struct inode *inode, u64 from, bool cache_only) { - unsigned offset = from & (PAGE_CACHE_SIZE - 1); - pgoff_t index = from >> PAGE_CACHE_SHIFT; + unsigned offset = from & (PAGE_SIZE - 1); + pgoff_t index = from >> PAGE_SHIFT; struct address_space *mapping = inode->i_mapping; struct page *page; @@ -529,7 +529,7 @@ static int truncate_partial_data_page(struct inode *inode, u64 from, return 0; truncate_out: f2fs_wait_on_page_writeback(page, DATA, true); - zero_user(page, offset, PAGE_CACHE_SIZE - offset); + zero_user(page, offset, PAGE_SIZE - offset); if (!cache_only || !f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode)) set_page_dirty(page); @@ -799,11 +799,11 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) if (ret) return ret; - pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; - pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; - off_start = offset & (PAGE_CACHE_SIZE - 1); - off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + off_start = offset & (PAGE_SIZE - 1); + off_end = (offset + len) & (PAGE_SIZE - 1); if (pg_start == pg_end) { ret = fill_zero(inode, pg_start, off_start, @@ -813,7 +813,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) } else { if (off_start) { ret = fill_zero(inode, pg_start++, off_start, - PAGE_CACHE_SIZE - off_start); + PAGE_SIZE - off_start); if (ret) return ret; } @@ -830,8 +830,8 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); - blk_start = (loff_t)pg_start << PAGE_CACHE_SHIFT; - blk_end = (loff_t)pg_end << PAGE_CACHE_SHIFT; + blk_start = (loff_t)pg_start << PAGE_SHIFT; + blk_end = (loff_t)pg_end << PAGE_SHIFT; truncate_inode_pages_range(mapping, blk_start, blk_end - 1); @@ -954,8 +954,8 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) if (ret) return ret; - pg_start = offset >> PAGE_CACHE_SHIFT; - pg_end = (offset + len) >> PAGE_CACHE_SHIFT; + pg_start = offset >> PAGE_SHIFT; + pg_end = (offset + len) >> PAGE_SHIFT; /* write out all dirty pages from offset */ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); @@ -1006,11 +1006,11 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, truncate_pagecache_range(inode, offset, offset + len - 1); - pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; - pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; - off_start = offset & (PAGE_CACHE_SIZE - 1); - off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + off_start = offset & (PAGE_SIZE - 1); + off_end = (offset + len) & (PAGE_SIZE - 1); if (pg_start == pg_end) { ret = fill_zero(inode, pg_start, off_start, @@ -1024,12 +1024,12 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, } else { if (off_start) { ret = fill_zero(inode, pg_start++, off_start, - PAGE_CACHE_SIZE - off_start); + PAGE_SIZE - off_start); if (ret) return ret; new_size = max_t(loff_t, new_size, - (loff_t)pg_start << PAGE_CACHE_SHIFT); + (loff_t)pg_start << PAGE_SHIFT); } for (index = pg_start; index < pg_end; index++) { @@ -1060,7 +1060,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, f2fs_unlock_op(sbi); new_size = max_t(loff_t, new_size, - (loff_t)(index + 1) << PAGE_CACHE_SHIFT); + (loff_t)(index + 1) << PAGE_SHIFT); } if (off_end) { @@ -1117,8 +1117,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) truncate_pagecache(inode, offset); - pg_start = offset >> PAGE_CACHE_SHIFT; - pg_end = (offset + len) >> PAGE_CACHE_SHIFT; + pg_start = offset >> PAGE_SHIFT; + pg_end = (offset + len) >> PAGE_SHIFT; delta = pg_end - pg_start; nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; @@ -1158,11 +1158,11 @@ static int expand_inode_data(struct inode *inode, loff_t offset, f2fs_balance_fs(sbi, true); - pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; - pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; - off_start = offset & (PAGE_CACHE_SIZE - 1); - off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + off_start = offset & (PAGE_SIZE - 1); + off_end = (offset + len) & (PAGE_SIZE - 1); f2fs_lock_op(sbi); @@ -1180,12 +1180,12 @@ noalloc: if (pg_start == pg_end) new_size = offset + len; else if (index == pg_start && off_start) - new_size = (loff_t)(index + 1) << PAGE_CACHE_SHIFT; + new_size = (loff_t)(index + 1) << PAGE_SHIFT; else if (index == pg_end) - new_size = ((loff_t)index << PAGE_CACHE_SHIFT) + + new_size = ((loff_t)index << PAGE_SHIFT) + off_end; else - new_size += PAGE_CACHE_SIZE; + new_size += PAGE_SIZE; } if (!(mode & FALLOC_FL_KEEP_SIZE) && @@ -1652,8 +1652,8 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, if (need_inplace_update(inode)) return -EINVAL; - pg_start = range->start >> PAGE_CACHE_SHIFT; - pg_end = (range->start + range->len) >> PAGE_CACHE_SHIFT; + pg_start = range->start >> PAGE_SHIFT; + pg_end = (range->start + range->len) >> PAGE_SHIFT; f2fs_balance_fs(sbi, true); @@ -1770,7 +1770,7 @@ clear_out: out: inode_unlock(inode); if (!err) - range->len = (u64)total << PAGE_CACHE_SHIFT; + range->len = (u64)total << PAGE_SHIFT; return err; } diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 358214e9f707..a2fbe6f427d3 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -51,7 +51,7 @@ void read_inline_data(struct page *page, struct page *ipage) f2fs_bug_on(F2FS_P_SB(page), page->index); - zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); + zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE); /* Copy the whole inline data block */ src_addr = inline_data_addr(ipage); @@ -93,7 +93,7 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page) } if (page->index) - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); else read_inline_data(page, ipage); @@ -375,7 +375,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, goto out; f2fs_wait_on_page_writeback(page, DATA, true); - zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); + zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE); dentry_blk = kmap_atomic(page); @@ -405,8 +405,8 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, stat_dec_inline_dir(dir); clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY); - if (i_size_read(dir) < PAGE_CACHE_SIZE) { - i_size_write(dir, PAGE_CACHE_SIZE); + if (i_size_read(dir) < PAGE_SIZE) { + i_size_write(dir, PAGE_SIZE); set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 7876f1052101..c1d9e9d2cb37 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -1051,12 +1051,12 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry, /* Null-terminate the name */ paddr[res] = '\0'; - page_cache_release(cpage); + put_page(cpage); set_delayed_call(done, kfree_link, paddr); return paddr; errout: fscrypt_fname_free_buffer(&pstr); - page_cache_release(cpage); + put_page(cpage); return ERR_PTR(res); } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 118321bd1a7f..1a33de9d84b1 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -46,11 +46,11 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) */ if (type == FREE_NIDS) { mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> - PAGE_CACHE_SHIFT; + PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == NAT_ENTRIES) { mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> - PAGE_CACHE_SHIFT; + PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == DIRTY_DENTS) { if (sbi->sb->s_bdi->wb.dirty_exceeded) @@ -62,13 +62,13 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) for (i = 0; i <= UPDATE_INO; i++) mem_size += (sbi->im[i].ino_num * - sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT; + sizeof(struct ino_entry)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else if (type == EXTENT_CACHE) { mem_size = (atomic_read(&sbi->total_ext_tree) * sizeof(struct extent_tree) + atomic_read(&sbi->total_ext_node) * - sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT; + sizeof(struct extent_node)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else { if (!sbi->sb->s_bdi->wb.dirty_exceeded) @@ -121,7 +121,7 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) src_addr = page_address(src_page); dst_addr = page_address(dst_page); - memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE); + memcpy(dst_addr, src_addr, PAGE_SIZE); set_page_dirty(dst_page); f2fs_put_page(src_page, 1); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 0b30cd2aeebd..011942f94d64 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -591,7 +591,7 @@ out: /* truncate meta pages to be used by the recovery */ truncate_inode_pages_range(META_MAPPING(sbi), - (loff_t)MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1); + (loff_t)MAIN_BLKADDR(sbi) << PAGE_SHIFT, -1); if (err) { truncate_inode_pages_final(NODE_MAPPING(sbi)); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 6f16b39f0b52..540669d6978e 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -885,12 +885,12 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) } } - sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE - + sum_in_page = (PAGE_SIZE - 2 * SUM_JOURNAL_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE; if (valid_sum_count <= sum_in_page) return 1; else if ((valid_sum_count - sum_in_page) <= - (PAGE_CACHE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE) + (PAGE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE) return 2; return 3; } @@ -909,9 +909,9 @@ void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) void *dst = page_address(page); if (src) - memcpy(dst, src, PAGE_CACHE_SIZE); + memcpy(dst, src, PAGE_SIZE); else - memset(dst, 0, PAGE_CACHE_SIZE); + memset(dst, 0, PAGE_SIZE); set_page_dirty(page); f2fs_put_page(page, 1); } @@ -1596,7 +1596,7 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) s = (struct f2fs_summary *)(kaddr + offset); seg_i->sum_blk->entries[j] = *s; offset += SUMMARY_SIZE; - if (offset + SUMMARY_SIZE <= PAGE_CACHE_SIZE - + if (offset + SUMMARY_SIZE <= PAGE_SIZE - SUM_FOOTER_SIZE) continue; @@ -1757,7 +1757,7 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) *summary = seg_i->sum_blk->entries[j]; written_size += SUMMARY_SIZE; - if (written_size + SUMMARY_SIZE <= PAGE_CACHE_SIZE - + if (written_size + SUMMARY_SIZE <= PAGE_SIZE - SUM_FOOTER_SIZE) continue; @@ -1844,7 +1844,7 @@ static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, src_addr = page_address(src_page); dst_addr = page_address(dst_page); - memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE); + memcpy(dst_addr, src_addr, PAGE_SIZE); set_page_dirty(dst_page); f2fs_put_page(src_page, 1); @@ -2171,7 +2171,7 @@ static int build_curseg(struct f2fs_sb_info *sbi) for (i = 0; i < NR_CURSEG_TYPE; i++) { mutex_init(&array[i].curseg_mutex); - array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL); + array[i].sum_blk = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!array[i].sum_blk) return -ENOMEM; init_rwsem(&array[i].journal_rwsem); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 15bb81f8dac2..53b766cdabf2 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1070,10 +1070,10 @@ static int sanity_check_raw_super(struct super_block *sb, } /* Currently, support only 4KB page cache size */ - if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) { + if (F2FS_BLKSIZE != PAGE_SIZE) { f2fs_msg(sb, KERN_INFO, "Invalid page_cache_size (%lu), supports only 4KB\n", - PAGE_CACHE_SIZE); + PAGE_SIZE); return 1; } diff --git a/fs/freevxfs/vxfs_immed.c b/fs/freevxfs/vxfs_immed.c index cb84f0fcc72a..bfc780c682fb 100644 --- a/fs/freevxfs/vxfs_immed.c +++ b/fs/freevxfs/vxfs_immed.c @@ -66,11 +66,11 @@ static int vxfs_immed_readpage(struct file *fp, struct page *pp) { struct vxfs_inode_info *vip = VXFS_INO(pp->mapping->host); - u_int64_t offset = (u_int64_t)pp->index << PAGE_CACHE_SHIFT; + u_int64_t offset = (u_int64_t)pp->index << PAGE_SHIFT; caddr_t kaddr; kaddr = kmap(pp); - memcpy(kaddr, vip->vii_immed.vi_immed + offset, PAGE_CACHE_SIZE); + memcpy(kaddr, vip->vii_immed.vi_immed + offset, PAGE_SIZE); kunmap(pp); flush_dcache_page(pp); diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c index 1cff72df0389..a49e0cfbb686 100644 --- a/fs/freevxfs/vxfs_lookup.c +++ b/fs/freevxfs/vxfs_lookup.c @@ -45,7 +45,7 @@ /* * Number of VxFS blocks per page. */ -#define VXFS_BLOCK_PER_PAGE(sbp) ((PAGE_CACHE_SIZE / (sbp)->s_blocksize)) +#define VXFS_BLOCK_PER_PAGE(sbp) ((PAGE_SIZE / (sbp)->s_blocksize)) static struct dentry * vxfs_lookup(struct inode *, struct dentry *, unsigned int); @@ -175,7 +175,7 @@ vxfs_inode_by_name(struct inode *dip, struct dentry *dp) if (de) { ino = de->d_ino; kunmap(pp); - page_cache_release(pp); + put_page(pp); } return (ino); @@ -255,8 +255,8 @@ vxfs_readdir(struct file *fp, struct dir_context *ctx) nblocks = dir_blocks(ip); pblocks = VXFS_BLOCK_PER_PAGE(sbp); - page = pos >> PAGE_CACHE_SHIFT; - offset = pos & ~PAGE_CACHE_MASK; + page = pos >> PAGE_SHIFT; + offset = pos & ~PAGE_MASK; block = (u_long)(pos >> sbp->s_blocksize_bits) % pblocks; for (; page < npages; page++, block = 0) { @@ -289,7 +289,7 @@ vxfs_readdir(struct file *fp, struct dir_context *ctx) continue; offset = (char *)de - kaddr; - ctx->pos = ((page << PAGE_CACHE_SHIFT) | offset) + 2; + ctx->pos = ((page << PAGE_SHIFT) | offset) + 2; if (!dir_emit(ctx, de->d_name, de->d_namelen, de->d_ino, DT_UNKNOWN)) { vxfs_put_page(pp); @@ -301,6 +301,6 @@ vxfs_readdir(struct file *fp, struct dir_context *ctx) vxfs_put_page(pp); offset = 0; } - ctx->pos = ((page << PAGE_CACHE_SHIFT) | offset) + 2; + ctx->pos = ((page << PAGE_SHIFT) | offset) + 2; return 0; } diff --git a/fs/freevxfs/vxfs_subr.c b/fs/freevxfs/vxfs_subr.c index 5d318c44f855..e806694d4145 100644 --- a/fs/freevxfs/vxfs_subr.c +++ b/fs/freevxfs/vxfs_subr.c @@ -50,7 +50,7 @@ inline void vxfs_put_page(struct page *pp) { kunmap(pp); - page_cache_release(pp); + put_page(pp); } /** diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index fee81e8768c9..592cea54cea0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -33,7 +33,7 @@ /* * 4MB minimal write chunk size */ -#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_CACHE_SHIFT - 10)) +#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) struct wb_completion { atomic_t cnt; diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 6b35fc4860a0..3078b679fcd1 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -113,7 +113,7 @@ try_again: wake_up_bit(&cookie->flags, 0); if (xpage) - page_cache_release(xpage); + put_page(xpage); __fscache_uncache_page(cookie, page); return true; @@ -164,7 +164,7 @@ static void fscache_end_page_write(struct fscache_object *object, } spin_unlock(&object->lock); if (xpage) - page_cache_release(xpage); + put_page(xpage); } /* @@ -884,7 +884,7 @@ void fscache_invalidate_writes(struct fscache_cookie *cookie) spin_unlock(&cookie->stores_lock); for (i = n - 1; i >= 0; i--) - page_cache_release(results[i]); + put_page(results[i]); } _leave(""); @@ -982,7 +982,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, radix_tree_tag_set(&cookie->stores, page->index, FSCACHE_COOKIE_PENDING_TAG); - page_cache_get(page); + get_page(page); /* we only want one writer at a time, but we do need to queue new * writers after exclusive ops */ @@ -1026,7 +1026,7 @@ submit_failed: radix_tree_delete(&cookie->stores, page->index); spin_unlock(&cookie->stores_lock); wake_cookie = __fscache_unuse_cookie(cookie); - page_cache_release(page); + put_page(page); ret = -ENOBUFS; goto nobufs; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index ebb5e37455a0..cbece1221417 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -897,7 +897,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) return err; } - page_cache_get(newpage); + get_page(newpage); if (!(buf->flags & PIPE_BUF_FLAG_LRU)) lru_cache_add_file(newpage); @@ -912,12 +912,12 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) if (err) { unlock_page(newpage); - page_cache_release(newpage); + put_page(newpage); return err; } unlock_page(oldpage); - page_cache_release(oldpage); + put_page(oldpage); cs->len = 0; return 0; @@ -951,7 +951,7 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page, fuse_copy_finish(cs); buf = cs->pipebufs; - page_cache_get(page); + get_page(page); buf->page = page; buf->offset = offset; buf->len = count; @@ -1435,7 +1435,7 @@ out_unlock: out: for (; page_nr < cs.nr_segs; page_nr++) - page_cache_release(bufs[page_nr].page); + put_page(bufs[page_nr].page); kfree(bufs); return ret; @@ -1632,8 +1632,8 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size, goto out_up_killsb; mapping = inode->i_mapping; - index = outarg.offset >> PAGE_CACHE_SHIFT; - offset = outarg.offset & ~PAGE_CACHE_MASK; + index = outarg.offset >> PAGE_SHIFT; + offset = outarg.offset & ~PAGE_MASK; file_size = i_size_read(inode); end = outarg.offset + outarg.size; if (end > file_size) { @@ -1652,13 +1652,13 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size, if (!page) goto out_iput; - this_num = min_t(unsigned, num, PAGE_CACHE_SIZE - offset); + this_num = min_t(unsigned, num, PAGE_SIZE - offset); err = fuse_copy_page(cs, &page, offset, this_num, 0); if (!err && offset == 0 && - (this_num == PAGE_CACHE_SIZE || file_size == end)) + (this_num == PAGE_SIZE || file_size == end)) SetPageUptodate(page); unlock_page(page); - page_cache_release(page); + put_page(page); if (err) goto out_iput; @@ -1697,7 +1697,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, size_t total_len = 0; int num_pages; - offset = outarg->offset & ~PAGE_CACHE_MASK; + offset = outarg->offset & ~PAGE_MASK; file_size = i_size_read(inode); num = outarg->size; @@ -1720,7 +1720,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, req->page_descs[0].offset = offset; req->end = fuse_retrieve_end; - index = outarg->offset >> PAGE_CACHE_SHIFT; + index = outarg->offset >> PAGE_SHIFT; while (num && req->num_pages < num_pages) { struct page *page; @@ -1730,7 +1730,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, if (!page) break; - this_num = min_t(unsigned, num, PAGE_CACHE_SIZE - offset); + this_num = min_t(unsigned, num, PAGE_SIZE - offset); req->pages[req->num_pages] = page; req->page_descs[req->num_pages].length = this_num; req->num_pages++; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 9dde38f12c07..719924d6c706 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -348,7 +348,7 @@ static bool fuse_range_is_writeback(struct inode *inode, pgoff_t idx_from, pgoff_t curr_index; BUG_ON(req->inode != inode); - curr_index = req->misc.write.in.offset >> PAGE_CACHE_SHIFT; + curr_index = req->misc.write.in.offset >> PAGE_SHIFT; if (idx_from < curr_index + req->num_pages && curr_index <= idx_to) { found = true; @@ -683,11 +683,11 @@ static void fuse_short_read(struct fuse_req *req, struct inode *inode, * present there. */ int i; - int start_idx = num_read >> PAGE_CACHE_SHIFT; - size_t off = num_read & (PAGE_CACHE_SIZE - 1); + int start_idx = num_read >> PAGE_SHIFT; + size_t off = num_read & (PAGE_SIZE - 1); for (i = start_idx; i < req->num_pages; i++) { - zero_user_segment(req->pages[i], off, PAGE_CACHE_SIZE); + zero_user_segment(req->pages[i], off, PAGE_SIZE); off = 0; } } else { @@ -704,7 +704,7 @@ static int fuse_do_readpage(struct file *file, struct page *page) struct fuse_req *req; size_t num_read; loff_t pos = page_offset(page); - size_t count = PAGE_CACHE_SIZE; + size_t count = PAGE_SIZE; u64 attr_ver; int err; @@ -789,7 +789,7 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req) else SetPageError(page); unlock_page(page); - page_cache_release(page); + put_page(page); } if (req->ff) fuse_file_put(req->ff, false); @@ -800,7 +800,7 @@ static void fuse_send_readpages(struct fuse_req *req, struct file *file) struct fuse_file *ff = file->private_data; struct fuse_conn *fc = ff->fc; loff_t pos = page_offset(req->pages[0]); - size_t count = req->num_pages << PAGE_CACHE_SHIFT; + size_t count = req->num_pages << PAGE_SHIFT; req->out.argpages = 1; req->out.page_zeroing = 1; @@ -836,7 +836,7 @@ static int fuse_readpages_fill(void *_data, struct page *page) if (req->num_pages && (req->num_pages == FUSE_MAX_PAGES_PER_REQ || - (req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_read || + (req->num_pages + 1) * PAGE_SIZE > fc->max_read || req->pages[req->num_pages - 1]->index + 1 != page->index)) { int nr_alloc = min_t(unsigned, data->nr_pages, FUSE_MAX_PAGES_PER_REQ); @@ -858,7 +858,7 @@ static int fuse_readpages_fill(void *_data, struct page *page) return -EIO; } - page_cache_get(page); + get_page(page); req->pages[req->num_pages] = page; req->page_descs[req->num_pages].length = PAGE_SIZE; req->num_pages++; @@ -1003,17 +1003,17 @@ static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file, for (i = 0; i < req->num_pages; i++) { struct page *page = req->pages[i]; - if (!req->out.h.error && !offset && count >= PAGE_CACHE_SIZE) + if (!req->out.h.error && !offset && count >= PAGE_SIZE) SetPageUptodate(page); - if (count > PAGE_CACHE_SIZE - offset) - count -= PAGE_CACHE_SIZE - offset; + if (count > PAGE_SIZE - offset) + count -= PAGE_SIZE - offset; else count = 0; offset = 0; unlock_page(page); - page_cache_release(page); + put_page(page); } return res; @@ -1024,7 +1024,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, struct iov_iter *ii, loff_t pos) { struct fuse_conn *fc = get_fuse_conn(mapping->host); - unsigned offset = pos & (PAGE_CACHE_SIZE - 1); + unsigned offset = pos & (PAGE_SIZE - 1); size_t count = 0; int err; @@ -1034,8 +1034,8 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, do { size_t tmp; struct page *page; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; - size_t bytes = min_t(size_t, PAGE_CACHE_SIZE - offset, + pgoff_t index = pos >> PAGE_SHIFT; + size_t bytes = min_t(size_t, PAGE_SIZE - offset, iov_iter_count(ii)); bytes = min_t(size_t, bytes, fc->max_write - count); @@ -1059,7 +1059,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, iov_iter_advance(ii, tmp); if (!tmp) { unlock_page(page); - page_cache_release(page); + put_page(page); bytes = min(bytes, iov_iter_single_seg_count(ii)); goto again; } @@ -1072,7 +1072,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, count += tmp; pos += tmp; offset += tmp; - if (offset == PAGE_CACHE_SIZE) + if (offset == PAGE_SIZE) offset = 0; if (!fc->big_writes) @@ -1086,8 +1086,8 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, static inline unsigned fuse_wr_pages(loff_t pos, size_t len) { return min_t(unsigned, - ((pos + len - 1) >> PAGE_CACHE_SHIFT) - - (pos >> PAGE_CACHE_SHIFT) + 1, + ((pos + len - 1) >> PAGE_SHIFT) - + (pos >> PAGE_SHIFT) + 1, FUSE_MAX_PAGES_PER_REQ); } @@ -1205,8 +1205,8 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out; invalidate_mapping_pages(file->f_mapping, - pos >> PAGE_CACHE_SHIFT, - endbyte >> PAGE_CACHE_SHIFT); + pos >> PAGE_SHIFT, + endbyte >> PAGE_SHIFT); written += written_buffered; iocb->ki_pos = pos + written_buffered; @@ -1315,8 +1315,8 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, size_t nmax = write ? fc->max_write : fc->max_read; loff_t pos = *ppos; size_t count = iov_iter_count(iter); - pgoff_t idx_from = pos >> PAGE_CACHE_SHIFT; - pgoff_t idx_to = (pos + count - 1) >> PAGE_CACHE_SHIFT; + pgoff_t idx_from = pos >> PAGE_SHIFT; + pgoff_t idx_to = (pos + count - 1) >> PAGE_SHIFT; ssize_t res = 0; struct fuse_req *req; int err = 0; @@ -1466,7 +1466,7 @@ __acquires(fc->lock) { struct fuse_inode *fi = get_fuse_inode(req->inode); struct fuse_write_in *inarg = &req->misc.write.in; - __u64 data_size = req->num_pages * PAGE_CACHE_SIZE; + __u64 data_size = req->num_pages * PAGE_SIZE; if (!fc->connected) goto out_free; @@ -1727,7 +1727,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req, list_del(&new_req->writepages_entry); list_for_each_entry(old_req, &fi->writepages, writepages_entry) { BUG_ON(old_req->inode != new_req->inode); - curr_index = old_req->misc.write.in.offset >> PAGE_CACHE_SHIFT; + curr_index = old_req->misc.write.in.offset >> PAGE_SHIFT; if (curr_index <= page->index && page->index < curr_index + old_req->num_pages) { found = true; @@ -1742,7 +1742,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req, new_req->num_pages = 1; for (tmp = old_req; tmp != NULL; tmp = tmp->misc.write.next) { BUG_ON(tmp->inode != new_req->inode); - curr_index = tmp->misc.write.in.offset >> PAGE_CACHE_SHIFT; + curr_index = tmp->misc.write.in.offset >> PAGE_SHIFT; if (tmp->num_pages == 1 && curr_index == page->index) { old_req = tmp; @@ -1799,7 +1799,7 @@ static int fuse_writepages_fill(struct page *page, if (req && req->num_pages && (is_writeback || req->num_pages == FUSE_MAX_PAGES_PER_REQ || - (req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_write || + (req->num_pages + 1) * PAGE_SIZE > fc->max_write || data->orig_pages[req->num_pages - 1]->index + 1 != page->index)) { fuse_writepages_send(data); data->req = NULL; @@ -1924,7 +1924,7 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; struct fuse_conn *fc = get_fuse_conn(file_inode(file)); struct page *page; loff_t fsize; @@ -1938,15 +1938,15 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping, fuse_wait_on_page_writeback(mapping->host, page->index); - if (PageUptodate(page) || len == PAGE_CACHE_SIZE) + if (PageUptodate(page) || len == PAGE_SIZE) goto success; /* * Check if the start this page comes after the end of file, in which * case the readpage can be optimized away. */ fsize = i_size_read(mapping->host); - if (fsize <= (pos & PAGE_CACHE_MASK)) { - size_t off = pos & ~PAGE_CACHE_MASK; + if (fsize <= (pos & PAGE_MASK)) { + size_t off = pos & ~PAGE_MASK; if (off) zero_user_segment(page, 0, off); goto success; @@ -1960,7 +1960,7 @@ success: cleanup: unlock_page(page); - page_cache_release(page); + put_page(page); error: return err; } @@ -1973,16 +1973,16 @@ static int fuse_write_end(struct file *file, struct address_space *mapping, if (!PageUptodate(page)) { /* Zero any unwritten bytes at the end of the page */ - size_t endoff = (pos + copied) & ~PAGE_CACHE_MASK; + size_t endoff = (pos + copied) & ~PAGE_MASK; if (endoff) - zero_user_segment(page, endoff, PAGE_CACHE_SIZE); + zero_user_segment(page, endoff, PAGE_SIZE); SetPageUptodate(page); } fuse_write_update_size(inode, pos + copied); set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); return copied; } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 4d69d5c0bedc..1ce67668a8e1 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -339,11 +339,11 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid, fuse_invalidate_attr(inode); if (offset >= 0) { - pg_start = offset >> PAGE_CACHE_SHIFT; + pg_start = offset >> PAGE_SHIFT; if (len <= 0) pg_end = -1; else - pg_end = (offset + len - 1) >> PAGE_CACHE_SHIFT; + pg_end = (offset + len - 1) >> PAGE_SHIFT; invalidate_inode_pages2_range(inode->i_mapping, pg_start, pg_end); } @@ -864,7 +864,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) process_init_limits(fc, arg); if (arg->minor >= 6) { - ra_pages = arg->max_readahead / PAGE_CACHE_SIZE; + ra_pages = arg->max_readahead / PAGE_SIZE; if (arg->flags & FUSE_ASYNC_READ) fc->async_read = 1; if (!(arg->flags & FUSE_POSIX_LOCKS)) @@ -901,7 +901,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) if (arg->time_gran && arg->time_gran <= 1000000000) fc->sb->s_time_gran = arg->time_gran; } else { - ra_pages = fc->max_read / PAGE_CACHE_SIZE; + ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; fc->no_flock = 1; } @@ -922,7 +922,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->major = FUSE_KERNEL_VERSION; arg->minor = FUSE_KERNEL_MINOR_VERSION; - arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE; + arg->max_readahead = fc->bdi.ra_pages * PAGE_SIZE; arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | @@ -955,7 +955,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) int err; fc->bdi.name = "fuse"; - fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; + fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE; /* fuse does it's own writeback accounting */ fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT; @@ -1053,8 +1053,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) goto err; #endif } else { - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; } sb->s_magic = FUSE_SUPER_MAGIC; sb->s_op = &fuse_super_operations; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index aa016e4b8bec..1bbbee945f46 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -101,7 +101,7 @@ static int gfs2_writepage_common(struct page *page, struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); loff_t i_size = i_size_read(inode); - pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; + pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl))) @@ -109,9 +109,9 @@ static int gfs2_writepage_common(struct page *page, if (current->journal_info) goto redirty; /* Is the page fully outside i_size? (truncate in progress) */ - offset = i_size & (PAGE_CACHE_SIZE-1); + offset = i_size & (PAGE_SIZE-1); if (page->index > end_index || (page->index == end_index && !offset)) { - page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE); + page->mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE); goto out; } return 1; @@ -238,7 +238,7 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping, { struct inode *inode = mapping->host; struct gfs2_sbd *sdp = GFS2_SB(inode); - unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize); + unsigned nrblocks = nr_pages * (PAGE_SIZE/inode->i_sb->s_blocksize); int i; int ret; @@ -366,8 +366,8 @@ static int gfs2_write_cache_jdata(struct address_space *mapping, cycled = 0; end = -1; } else { - index = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + index = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ @@ -458,7 +458,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) * so we need to supply one here. It doesn't happen often. */ if (unlikely(page->index)) { - zero_user(page, 0, PAGE_CACHE_SIZE); + zero_user(page, 0, PAGE_SIZE); SetPageUptodate(page); return 0; } @@ -471,7 +471,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) if (dsize > (dibh->b_size - sizeof(struct gfs2_dinode))) dsize = (dibh->b_size - sizeof(struct gfs2_dinode)); memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); - memset(kaddr + dsize, 0, PAGE_CACHE_SIZE - dsize); + memset(kaddr + dsize, 0, PAGE_SIZE - dsize); kunmap_atomic(kaddr); flush_dcache_page(page); brelse(dibh); @@ -560,8 +560,8 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, unsigned size) { struct address_space *mapping = ip->i_inode.i_mapping; - unsigned long index = *pos / PAGE_CACHE_SIZE; - unsigned offset = *pos & (PAGE_CACHE_SIZE - 1); + unsigned long index = *pos / PAGE_SIZE; + unsigned offset = *pos & (PAGE_SIZE - 1); unsigned copied = 0; unsigned amt; struct page *page; @@ -569,15 +569,15 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, do { amt = size - copied; - if (offset + size > PAGE_CACHE_SIZE) - amt = PAGE_CACHE_SIZE - offset; + if (offset + size > PAGE_SIZE) + amt = PAGE_SIZE - offset; page = read_cache_page(mapping, index, __gfs2_readpage, NULL); if (IS_ERR(page)) return PTR_ERR(page); p = kmap_atomic(page); memcpy(buf + copied, p + offset, amt); kunmap_atomic(p); - page_cache_release(page); + put_page(page); copied += amt; index++; offset = 0; @@ -651,8 +651,8 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, unsigned requested = 0; int alloc_required; int error = 0; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + pgoff_t index = pos >> PAGE_SHIFT; + unsigned from = pos & (PAGE_SIZE - 1); struct page *page; gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh); @@ -697,7 +697,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, rblocks += gfs2_rg_blocks(ip, requested); error = gfs2_trans_begin(sdp, rblocks, - PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize); + PAGE_SIZE/sdp->sd_sb.sb_bsize); if (error) goto out_trans_fail; @@ -727,7 +727,7 @@ out: return 0; unlock_page(page); - page_cache_release(page); + put_page(page); gfs2_trans_end(sdp); if (pos + len > ip->i_inode.i_size) @@ -827,7 +827,7 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh, if (!PageUptodate(page)) SetPageUptodate(page); unlock_page(page); - page_cache_release(page); + put_page(page); if (copied) { if (inode->i_size < to) @@ -877,7 +877,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); struct buffer_head *dibh; - unsigned int from = pos & (PAGE_CACHE_SIZE - 1); + unsigned int from = pos & (PAGE_SIZE - 1); unsigned int to = from + len; int ret; struct gfs2_trans *tr = current->journal_info; @@ -888,7 +888,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, ret = gfs2_meta_inode_buffer(ip, &dibh); if (unlikely(ret)) { unlock_page(page); - page_cache_release(page); + put_page(page); goto failed; } @@ -992,7 +992,7 @@ static void gfs2_invalidatepage(struct page *page, unsigned int offset, { struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host); unsigned int stop = offset + length; - int partial_page = (offset || length < PAGE_CACHE_SIZE); + int partial_page = (offset || length < PAGE_SIZE); struct buffer_head *bh, *head; unsigned long pos = 0; @@ -1082,7 +1082,7 @@ static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, * the first place, mapping->nr_pages will always be zero. */ if (mapping->nrpages) { - loff_t lstart = offset & ~(PAGE_CACHE_SIZE - 1); + loff_t lstart = offset & ~(PAGE_SIZE - 1); loff_t len = iov_iter_count(iter); loff_t end = PAGE_ALIGN(offset + len) - 1; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 0860f0b5b3f1..24ce1cdd434a 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -75,7 +75,7 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, dsize = dibh->b_size - sizeof(struct gfs2_dinode); memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); - memset(kaddr + dsize, 0, PAGE_CACHE_SIZE - dsize); + memset(kaddr + dsize, 0, PAGE_SIZE - dsize); kunmap(page); SetPageUptodate(page); @@ -98,7 +98,7 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, if (release) { unlock_page(page); - page_cache_release(page); + put_page(page); } return 0; @@ -932,8 +932,8 @@ static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from) { struct inode *inode = mapping->host; struct gfs2_inode *ip = GFS2_I(inode); - unsigned long index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); + unsigned long index = from >> PAGE_SHIFT; + unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize, iblock, length, pos; struct buffer_head *bh; struct page *page; @@ -945,7 +945,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from) blocksize = inode->i_sb->s_blocksize; length = blocksize - (offset & (blocksize - 1)); - iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits); + iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits); if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); @@ -989,7 +989,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from) mark_buffer_dirty(bh); unlock: unlock_page(page); - page_cache_release(page); + put_page(page); return err; } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index c9384f932975..208efc70ad49 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -354,8 +354,8 @@ static int gfs2_allocate_page_backing(struct page *page) { struct inode *inode = page->mapping->host; struct buffer_head bh; - unsigned long size = PAGE_CACHE_SIZE; - u64 lblock = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + unsigned long size = PAGE_SIZE; + u64 lblock = page->index << (PAGE_SHIFT - inode->i_blkbits); do { bh.b_state = 0; @@ -386,7 +386,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_alloc_parms ap = { .aflags = 0, }; unsigned long last_index; - u64 pos = page->index << PAGE_CACHE_SHIFT; + u64 pos = page->index << PAGE_SHIFT; unsigned int data_blocks, ind_blocks, rblocks; struct gfs2_holder gh; loff_t size; @@ -401,7 +401,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) if (ret) goto out; - gfs2_size_hint(vma->vm_file, pos, PAGE_CACHE_SIZE); + gfs2_size_hint(vma->vm_file, pos, PAGE_SIZE); gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); ret = gfs2_glock_nq(&gh); @@ -411,7 +411,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) set_bit(GLF_DIRTY, &ip->i_gl->gl_flags); set_bit(GIF_SW_PAGED, &ip->i_flags); - if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE)) { + if (!gfs2_write_alloc_required(ip, pos, PAGE_SIZE)) { lock_page(page); if (!PageUptodate(page) || page->mapping != inode->i_mapping) { ret = -EAGAIN; @@ -424,7 +424,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) if (ret) goto out_unlock; - gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks); + gfs2_write_calc_reserv(ip, PAGE_SIZE, &data_blocks, &ind_blocks); ap.target = data_blocks + ind_blocks; ret = gfs2_quota_lock_check(ip, &ap); if (ret) @@ -447,7 +447,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) lock_page(page); ret = -EINVAL; size = i_size_read(inode); - last_index = (size - 1) >> PAGE_CACHE_SHIFT; + last_index = (size - 1) >> PAGE_SHIFT; /* Check page index against inode size */ if (size == 0 || (page->index > last_index)) goto out_trans_end; @@ -873,7 +873,7 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t rblocks += data_blocks ? data_blocks : 1; error = gfs2_trans_begin(sdp, rblocks, - PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize); + PAGE_SIZE/sdp->sd_sb.sb_bsize); if (error) goto out_trans_fail; diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index e137d96f1b17..0448524c11bc 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -124,7 +124,7 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) if (mapping == NULL) mapping = &sdp->sd_aspace; - shift = PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift; + shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift; index = blkno >> shift; /* convert block to page */ bufnum = blkno - (index << shift); /* block buf index within page */ @@ -154,7 +154,7 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) map_bh(bh, sdp->sd_vfs, blkno); unlock_page(page); - page_cache_release(page); + put_page(page); return bh; } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index a39891344259..ce7d69a2fdc0 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -701,7 +701,7 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index, unsigned to_write = bytes, pg_off = off; int done = 0; - blk = index << (PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift); + blk = index << (PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift); boff = off % bsize; page = find_or_create_page(mapping, index, GFP_NOFS); @@ -753,13 +753,13 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index, flush_dcache_page(page); kunmap_atomic(kaddr); unlock_page(page); - page_cache_release(page); + put_page(page); return 0; unlock_out: unlock_page(page); - page_cache_release(page); + put_page(page); return -EIO; } @@ -773,13 +773,13 @@ static int gfs2_write_disk_quota(struct gfs2_inode *ip, struct gfs2_quota *qp, nbytes = sizeof(struct gfs2_quota); - pg_beg = loc >> PAGE_CACHE_SHIFT; - pg_off = loc % PAGE_CACHE_SIZE; + pg_beg = loc >> PAGE_SHIFT; + pg_off = loc % PAGE_SIZE; /* If the quota straddles a page boundary, split the write in two */ - if ((pg_off + nbytes) > PAGE_CACHE_SIZE) { + if ((pg_off + nbytes) > PAGE_SIZE) { pg_oflow = 1; - overflow = (pg_off + nbytes) - PAGE_CACHE_SIZE; + overflow = (pg_off + nbytes) - PAGE_SIZE; } ptr = qp; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 07c0265aa195..99a0bdac8796 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -918,9 +918,8 @@ static int read_rindex_entry(struct gfs2_inode *ip) goto fail; rgd->rd_gl->gl_object = rgd; - rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_CACHE_MASK; - rgd->rd_gl->gl_vm.end = PAGE_CACHE_ALIGN((rgd->rd_addr + - rgd->rd_length) * bsize) - 1; + rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_MASK; + rgd->rd_gl->gl_vm.end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1; rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr; rgd->rd_flags &= ~(GFS2_RDF_UPTODATE | GFS2_RDF_PREFERRED); if (rgd->rd_data > sdp->sd_max_rg_data) diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index 221719eac5de..d77d844b668b 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -278,14 +278,14 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) mapping = tree->inode->i_mapping; off = (loff_t)cnid * tree->node_size; - block = off >> PAGE_CACHE_SHIFT; - node->page_offset = off & ~PAGE_CACHE_MASK; + block = off >> PAGE_SHIFT; + node->page_offset = off & ~PAGE_MASK; for (i = 0; i < tree->pages_per_bnode; i++) { page = read_mapping_page(mapping, block++, NULL); if (IS_ERR(page)) goto fail; if (PageError(page)) { - page_cache_release(page); + put_page(page); goto fail; } node->page[i] = page; @@ -401,7 +401,7 @@ void hfs_bnode_free(struct hfs_bnode *node) for (i = 0; i < node->tree->pages_per_bnode; i++) if (node->page[i]) - page_cache_release(node->page[i]); + put_page(node->page[i]); kfree(node); } @@ -429,11 +429,11 @@ struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num) pagep = node->page; memset(kmap(*pagep) + node->page_offset, 0, - min((int)PAGE_CACHE_SIZE, (int)tree->node_size)); + min((int)PAGE_SIZE, (int)tree->node_size)); set_page_dirty(*pagep); kunmap(*pagep); for (i = 1; i < tree->pages_per_bnode; i++) { - memset(kmap(*++pagep), 0, PAGE_CACHE_SIZE); + memset(kmap(*++pagep), 0, PAGE_SIZE); set_page_dirty(*pagep); kunmap(*pagep); } diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 1ab19e660e69..37cdd955eceb 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -116,14 +116,14 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke } tree->node_size_shift = ffs(size) - 1; - tree->pages_per_bnode = (tree->node_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + tree->pages_per_bnode = (tree->node_size + PAGE_SIZE - 1) >> PAGE_SHIFT; kunmap(page); - page_cache_release(page); + put_page(page); return tree; fail_page: - page_cache_release(page); + put_page(page); free_inode: tree->inode->i_mapping->a_ops = &hfs_aops; iput(tree->inode); @@ -257,9 +257,9 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) off = off16; off += node->page_offset; - pagep = node->page + (off >> PAGE_CACHE_SHIFT); + pagep = node->page + (off >> PAGE_SHIFT); data = kmap(*pagep); - off &= ~PAGE_CACHE_MASK; + off &= ~PAGE_MASK; idx = 0; for (;;) { @@ -279,7 +279,7 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) } } } - if (++off >= PAGE_CACHE_SIZE) { + if (++off >= PAGE_SIZE) { kunmap(*pagep); data = kmap(*++pagep); off = 0; @@ -302,9 +302,9 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) len = hfs_brec_lenoff(node, 0, &off16); off = off16; off += node->page_offset; - pagep = node->page + (off >> PAGE_CACHE_SHIFT); + pagep = node->page + (off >> PAGE_SHIFT); data = kmap(*pagep); - off &= ~PAGE_CACHE_MASK; + off &= ~PAGE_MASK; } } @@ -348,9 +348,9 @@ void hfs_bmap_free(struct hfs_bnode *node) len = hfs_brec_lenoff(node, 0, &off); } off += node->page_offset + nidx / 8; - page = node->page[off >> PAGE_CACHE_SHIFT]; + page = node->page[off >> PAGE_SHIFT]; data = kmap(page); - off &= ~PAGE_CACHE_MASK; + off &= ~PAGE_MASK; m = 1 << (~nidx & 7); byte = data[off]; if (!(byte & m)) { diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 6686bf39a5b5..cb1e5faa2fb7 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -91,8 +91,8 @@ static int hfs_releasepage(struct page *page, gfp_t mask) if (!tree) return 0; - if (tree->node_size >= PAGE_CACHE_SIZE) { - nidx = page->index >> (tree->node_size_shift - PAGE_CACHE_SHIFT); + if (tree->node_size >= PAGE_SIZE) { + nidx = page->index >> (tree->node_size_shift - PAGE_SHIFT); spin_lock(&tree->hash_lock); node = hfs_bnode_findhash(tree, nidx); if (!node) @@ -105,8 +105,8 @@ static int hfs_releasepage(struct page *page, gfp_t mask) } spin_unlock(&tree->hash_lock); } else { - nidx = page->index << (PAGE_CACHE_SHIFT - tree->node_size_shift); - i = 1 << (PAGE_CACHE_SHIFT - tree->node_size_shift); + nidx = page->index << (PAGE_SHIFT - tree->node_size_shift); + i = 1 << (PAGE_SHIFT - tree->node_size_shift); spin_lock(&tree->hash_lock); do { node = hfs_bnode_findhash(tree, nidx++); diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c index d2954451519e..c0ae274c0a22 100644 --- a/fs/hfsplus/bitmap.c +++ b/fs/hfsplus/bitmap.c @@ -13,7 +13,7 @@ #include "hfsplus_fs.h" #include "hfsplus_raw.h" -#define PAGE_CACHE_BITS (PAGE_CACHE_SIZE * 8) +#define PAGE_CACHE_BITS (PAGE_SIZE * 8) int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset, u32 *max) diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index 63924662aaf3..ce014ceb89ef 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -24,16 +24,16 @@ void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) int l; off += node->page_offset; - pagep = node->page + (off >> PAGE_CACHE_SHIFT); - off &= ~PAGE_CACHE_MASK; + pagep = node->page + (off >> PAGE_SHIFT); + off &= ~PAGE_MASK; - l = min_t(int, len, PAGE_CACHE_SIZE - off); + l = min_t(int, len, PAGE_SIZE - off); memcpy(buf, kmap(*pagep) + off, l); kunmap(*pagep); while ((len -= l) != 0) { buf += l; - l = min_t(int, len, PAGE_CACHE_SIZE); + l = min_t(int, len, PAGE_SIZE); memcpy(buf, kmap(*++pagep), l); kunmap(*pagep); } @@ -77,17 +77,17 @@ void hfs_bnode_write(struct hfs_bnode *node, void *buf, int off, int len) int l; off += node->page_offset; - pagep = node->page + (off >> PAGE_CACHE_SHIFT); - off &= ~PAGE_CACHE_MASK; + pagep = node->page + (off >> PAGE_SHIFT); + off &= ~PAGE_MASK; - l = min_t(int, len, PAGE_CACHE_SIZE - off); + l = min_t(int, len, PAGE_SIZE - off); memcpy(kmap(*pagep) + off, buf, l); set_page_dirty(*pagep); kunmap(*pagep); while ((len -= l) != 0) { buf += l; - l = min_t(int, len, PAGE_CACHE_SIZE); + l = min_t(int, len, PAGE_SIZE); memcpy(kmap(*++pagep), buf, l); set_page_dirty(*pagep); kunmap(*pagep); @@ -107,16 +107,16 @@ void hfs_bnode_clear(struct hfs_bnode *node, int off, int len) int l; off += node->page_offset; - pagep = node->page + (off >> PAGE_CACHE_SHIFT); - off &= ~PAGE_CACHE_MASK; + pagep = node->page + (off >> PAGE_SHIFT); + off &= ~PAGE_MASK; - l = min_t(int, len, PAGE_CACHE_SIZE - off); + l = min_t(int, len, PAGE_SIZE - off); memset(kmap(*pagep) + off, 0, l); set_page_dirty(*pagep); kunmap(*pagep); while ((len -= l) != 0) { - l = min_t(int, len, PAGE_CACHE_SIZE); + l = min_t(int, len, PAGE_SIZE); memset(kmap(*++pagep), 0, l); set_page_dirty(*pagep); kunmap(*pagep); @@ -136,20 +136,20 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst, tree = src_node->tree; src += src_node->page_offset; dst += dst_node->page_offset; - src_page = src_node->page + (src >> PAGE_CACHE_SHIFT); - src &= ~PAGE_CACHE_MASK; - dst_page = dst_node->page + (dst >> PAGE_CACHE_SHIFT); - dst &= ~PAGE_CACHE_MASK; + src_page = src_node->page + (src >> PAGE_SHIFT); + src &= ~PAGE_MASK; + dst_page = dst_node->page + (dst >> PAGE_SHIFT); + dst &= ~PAGE_MASK; if (src == dst) { - l = min_t(int, len, PAGE_CACHE_SIZE - src); + l = min_t(int, len, PAGE_SIZE - src); memcpy(kmap(*dst_page) + src, kmap(*src_page) + src, l); kunmap(*src_page); set_page_dirty(*dst_page); kunmap(*dst_page); while ((len -= l) != 0) { - l = min_t(int, len, PAGE_CACHE_SIZE); + l = min_t(int, len, PAGE_SIZE); memcpy(kmap(*++dst_page), kmap(*++src_page), l); kunmap(*src_page); set_page_dirty(*dst_page); @@ -161,12 +161,12 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst, do { src_ptr = kmap(*src_page) + src; dst_ptr = kmap(*dst_page) + dst; - if (PAGE_CACHE_SIZE - src < PAGE_CACHE_SIZE - dst) { - l = PAGE_CACHE_SIZE - src; + if (PAGE_SIZE - src < PAGE_SIZE - dst) { + l = PAGE_SIZE - src; src = 0; dst += l; } else { - l = PAGE_CACHE_SIZE - dst; + l = PAGE_SIZE - dst; src += l; dst = 0; } @@ -195,11 +195,11 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) dst += node->page_offset; if (dst > src) { src += len - 1; - src_page = node->page + (src >> PAGE_CACHE_SHIFT); - src = (src & ~PAGE_CACHE_MASK) + 1; + src_page = node->page + (src >> PAGE_SHIFT); + src = (src & ~PAGE_MASK) + 1; dst += len - 1; - dst_page = node->page + (dst >> PAGE_CACHE_SHIFT); - dst = (dst & ~PAGE_CACHE_MASK) + 1; + dst_page = node->page + (dst >> PAGE_SHIFT); + dst = (dst & ~PAGE_MASK) + 1; if (src == dst) { while (src < len) { @@ -208,7 +208,7 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) set_page_dirty(*dst_page); kunmap(*dst_page); len -= src; - src = PAGE_CACHE_SIZE; + src = PAGE_SIZE; src_page--; dst_page--; } @@ -226,32 +226,32 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) dst_ptr = kmap(*dst_page) + dst; if (src < dst) { l = src; - src = PAGE_CACHE_SIZE; + src = PAGE_SIZE; dst -= l; } else { l = dst; src -= l; - dst = PAGE_CACHE_SIZE; + dst = PAGE_SIZE; } l = min(len, l); memmove(dst_ptr - l, src_ptr - l, l); kunmap(*src_page); set_page_dirty(*dst_page); kunmap(*dst_page); - if (dst == PAGE_CACHE_SIZE) + if (dst == PAGE_SIZE) dst_page--; else src_page--; } while ((len -= l)); } } else { - src_page = node->page + (src >> PAGE_CACHE_SHIFT); - src &= ~PAGE_CACHE_MASK; - dst_page = node->page + (dst >> PAGE_CACHE_SHIFT); - dst &= ~PAGE_CACHE_MASK; + src_page = node->page + (src >> PAGE_SHIFT); + src &= ~PAGE_MASK; + dst_page = node->page + (dst >> PAGE_SHIFT); + dst &= ~PAGE_MASK; if (src == dst) { - l = min_t(int, len, PAGE_CACHE_SIZE - src); + l = min_t(int, len, PAGE_SIZE - src); memmove(kmap(*dst_page) + src, kmap(*src_page) + src, l); kunmap(*src_page); @@ -259,7 +259,7 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) kunmap(*dst_page); while ((len -= l) != 0) { - l = min_t(int, len, PAGE_CACHE_SIZE); + l = min_t(int, len, PAGE_SIZE); memmove(kmap(*++dst_page), kmap(*++src_page), l); kunmap(*src_page); @@ -272,13 +272,13 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) do { src_ptr = kmap(*src_page) + src; dst_ptr = kmap(*dst_page) + dst; - if (PAGE_CACHE_SIZE - src < - PAGE_CACHE_SIZE - dst) { - l = PAGE_CACHE_SIZE - src; + if (PAGE_SIZE - src < + PAGE_SIZE - dst) { + l = PAGE_SIZE - src; src = 0; dst += l; } else { - l = PAGE_CACHE_SIZE - dst; + l = PAGE_SIZE - dst; src += l; dst = 0; } @@ -444,14 +444,14 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) mapping = tree->inode->i_mapping; off = (loff_t)cnid << tree->node_size_shift; - block = off >> PAGE_CACHE_SHIFT; - node->page_offset = off & ~PAGE_CACHE_MASK; + block = off >> PAGE_SHIFT; + node->page_offset = off & ~PAGE_MASK; for (i = 0; i < tree->pages_per_bnode; block++, i++) { page = read_mapping_page(mapping, block, NULL); if (IS_ERR(page)) goto fail; if (PageError(page)) { - page_cache_release(page); + put_page(page); goto fail; } node->page[i] = page; @@ -569,7 +569,7 @@ void hfs_bnode_free(struct hfs_bnode *node) for (i = 0; i < node->tree->pages_per_bnode; i++) if (node->page[i]) - page_cache_release(node->page[i]); + put_page(node->page[i]); kfree(node); } @@ -597,11 +597,11 @@ struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num) pagep = node->page; memset(kmap(*pagep) + node->page_offset, 0, - min_t(int, PAGE_CACHE_SIZE, tree->node_size)); + min_t(int, PAGE_SIZE, tree->node_size)); set_page_dirty(*pagep); kunmap(*pagep); for (i = 1; i < tree->pages_per_bnode; i++) { - memset(kmap(*++pagep), 0, PAGE_CACHE_SIZE); + memset(kmap(*++pagep), 0, PAGE_SIZE); set_page_dirty(*pagep); kunmap(*pagep); } diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index 3345c7553edc..d9d1a36ba826 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -236,15 +236,15 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) tree->node_size_shift = ffs(size) - 1; tree->pages_per_bnode = - (tree->node_size + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + (tree->node_size + PAGE_SIZE - 1) >> + PAGE_SHIFT; kunmap(page); - page_cache_release(page); + put_page(page); return tree; fail_page: - page_cache_release(page); + put_page(page); free_inode: tree->inode->i_mapping->a_ops = &hfsplus_aops; iput(tree->inode); @@ -380,9 +380,9 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) off = off16; off += node->page_offset; - pagep = node->page + (off >> PAGE_CACHE_SHIFT); + pagep = node->page + (off >> PAGE_SHIFT); data = kmap(*pagep); - off &= ~PAGE_CACHE_MASK; + off &= ~PAGE_MASK; idx = 0; for (;;) { @@ -403,7 +403,7 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) } } } - if (++off >= PAGE_CACHE_SIZE) { + if (++off >= PAGE_SIZE) { kunmap(*pagep); data = kmap(*++pagep); off = 0; @@ -426,9 +426,9 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) len = hfs_brec_lenoff(node, 0, &off16); off = off16; off += node->page_offset; - pagep = node->page + (off >> PAGE_CACHE_SHIFT); + pagep = node->page + (off >> PAGE_SHIFT); data = kmap(*pagep); - off &= ~PAGE_CACHE_MASK; + off &= ~PAGE_MASK; } } @@ -475,9 +475,9 @@ void hfs_bmap_free(struct hfs_bnode *node) len = hfs_brec_lenoff(node, 0, &off); } off += node->page_offset + nidx / 8; - page = node->page[off >> PAGE_CACHE_SHIFT]; + page = node->page[off >> PAGE_SHIFT]; data = kmap(page); - off &= ~PAGE_CACHE_MASK; + off &= ~PAGE_MASK; m = 1 << (~nidx & 7); byte = data[off]; if (!(byte & m)) { diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 1a6394cdb54e..b28f39865c3a 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -87,9 +87,9 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask) } if (!tree) return 0; - if (tree->node_size >= PAGE_CACHE_SIZE) { + if (tree->node_size >= PAGE_SIZE) { nidx = page->index >> - (tree->node_size_shift - PAGE_CACHE_SHIFT); + (tree->node_size_shift - PAGE_SHIFT); spin_lock(&tree->hash_lock); node = hfs_bnode_findhash(tree, nidx); if (!node) @@ -103,8 +103,8 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask) spin_unlock(&tree->hash_lock); } else { nidx = page->index << - (PAGE_CACHE_SHIFT - tree->node_size_shift); - i = 1 << (PAGE_CACHE_SHIFT - tree->node_size_shift); + (PAGE_SHIFT - tree->node_size_shift); + i = 1 << (PAGE_SHIFT - tree->node_size_shift); spin_lock(&tree->hash_lock); do { node = hfs_bnode_findhash(tree, nidx++); diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 5d54490a136d..c35911362ff9 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -438,7 +438,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) err = -EFBIG; last_fs_block = sbi->total_blocks - 1; last_fs_page = (last_fs_block << sbi->alloc_blksz_shift) >> - PAGE_CACHE_SHIFT; + PAGE_SHIFT; if ((last_fs_block > (sector_t)(~0ULL) >> (sbi->alloc_blksz_shift - 9)) || (last_fs_page > (pgoff_t)(~0ULL))) { diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index ab01530b4930..70e445ff0cff 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -220,7 +220,7 @@ check_attr_tree_state_again: index = 0; written = 0; - for (; written < node_size; index++, written += PAGE_CACHE_SIZE) { + for (; written < node_size; index++, written += PAGE_SIZE) { void *kaddr; page = read_mapping_page(mapping, index, NULL); @@ -231,11 +231,11 @@ check_attr_tree_state_again: kaddr = kmap_atomic(page); memcpy(kaddr, buf + written, - min_t(size_t, PAGE_CACHE_SIZE, node_size - written)); + min_t(size_t, PAGE_SIZE, node_size - written)); kunmap_atomic(kaddr); set_page_dirty(page); - page_cache_release(page); + put_page(page); } hfsplus_mark_inode_dirty(attr_file, HFSPLUS_I_ATTR_DIRTY); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index d1abbee281d1..7016653f3e41 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -410,12 +410,12 @@ static int hostfs_writepage(struct page *page, struct writeback_control *wbc) struct inode *inode = mapping->host; char *buffer; loff_t base = page_offset(page); - int count = PAGE_CACHE_SIZE; - int end_index = inode->i_size >> PAGE_CACHE_SHIFT; + int count = PAGE_SIZE; + int end_index = inode->i_size >> PAGE_SHIFT; int err; if (page->index >= end_index) - count = inode->i_size & (PAGE_CACHE_SIZE-1); + count = inode->i_size & (PAGE_SIZE-1); buffer = kmap(page); @@ -447,7 +447,7 @@ static int hostfs_readpage(struct file *file, struct page *page) buffer = kmap(page); bytes_read = read_file(FILE_HOSTFS_I(file)->fd, &start, buffer, - PAGE_CACHE_SIZE); + PAGE_SIZE); if (bytes_read < 0) { ClearPageUptodate(page); SetPageError(page); @@ -455,7 +455,7 @@ static int hostfs_readpage(struct file *file, struct page *page) goto out; } - memset(buffer + bytes_read, 0, PAGE_CACHE_SIZE - bytes_read); + memset(buffer + bytes_read, 0, PAGE_SIZE - bytes_read); ClearPageError(page); SetPageUptodate(page); @@ -471,7 +471,7 @@ static int hostfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; *pagep = grab_cache_page_write_begin(mapping, index, flags); if (!*pagep) @@ -485,14 +485,14 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping, { struct inode *inode = mapping->host; void *buffer; - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned from = pos & (PAGE_SIZE - 1); int err; buffer = kmap(page); err = write_file(FILE_HOSTFS_I(file)->fd, &pos, buffer + from, copied); kunmap(page); - if (!PageUptodate(page) && err == PAGE_CACHE_SIZE) + if (!PageUptodate(page) && err == PAGE_SIZE) SetPageUptodate(page); /* @@ -502,7 +502,7 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping, if (err > 0 && (pos > inode->i_size)) inode->i_size = pos; unlock_page(page); - page_cache_release(page); + put_page(page); return err; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index e1f465a389d5..afb7c7f05de5 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -213,12 +213,12 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset, int i, chunksize; /* Find which 4k chunk and offset with in that chunk */ - i = offset >> PAGE_CACHE_SHIFT; - offset = offset & ~PAGE_CACHE_MASK; + i = offset >> PAGE_SHIFT; + offset = offset & ~PAGE_MASK; while (size) { size_t n; - chunksize = PAGE_CACHE_SIZE; + chunksize = PAGE_SIZE; if (offset) chunksize -= offset; if (chunksize > size) @@ -285,7 +285,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) * We have the page, copy it to user space buffer. */ copied = hugetlbfs_read_actor(page, offset, to, nr); - page_cache_release(page); + put_page(page); } offset += copied; retval += copied; diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c index f311bf084015..2e4e834d1a98 100644 --- a/fs/isofs/compress.c +++ b/fs/isofs/compress.c @@ -26,7 +26,7 @@ #include "zisofs.h" /* This should probably be global. */ -static char zisofs_sink_page[PAGE_CACHE_SIZE]; +static char zisofs_sink_page[PAGE_SIZE]; /* * This contains the zlib memory allocation and the mutex for the @@ -70,11 +70,11 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start, for ( i = 0 ; i < pcount ; i++ ) { if (!pages[i]) continue; - memset(page_address(pages[i]), 0, PAGE_CACHE_SIZE); + memset(page_address(pages[i]), 0, PAGE_SIZE); flush_dcache_page(pages[i]); SetPageUptodate(pages[i]); } - return ((loff_t)pcount) << PAGE_CACHE_SHIFT; + return ((loff_t)pcount) << PAGE_SHIFT; } /* Because zlib is not thread-safe, do all the I/O at the top. */ @@ -121,11 +121,11 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start, if (pages[curpage]) { stream.next_out = page_address(pages[curpage]) + poffset; - stream.avail_out = PAGE_CACHE_SIZE - poffset; + stream.avail_out = PAGE_SIZE - poffset; poffset = 0; } else { stream.next_out = (void *)&zisofs_sink_page; - stream.avail_out = PAGE_CACHE_SIZE; + stream.avail_out = PAGE_SIZE; } } if (!stream.avail_in) { @@ -220,14 +220,14 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount, * pages with the data we have anyway... */ start_off = page_offset(pages[full_page]); - end_off = min_t(loff_t, start_off + PAGE_CACHE_SIZE, inode->i_size); + end_off = min_t(loff_t, start_off + PAGE_SIZE, inode->i_size); cstart_block = start_off >> zisofs_block_shift; cend_block = (end_off + (1 << zisofs_block_shift) - 1) >> zisofs_block_shift; - WARN_ON(start_off - (full_page << PAGE_CACHE_SHIFT) != - ((cstart_block << zisofs_block_shift) & PAGE_CACHE_MASK)); + WARN_ON(start_off - (full_page << PAGE_SHIFT) != + ((cstart_block << zisofs_block_shift) & PAGE_MASK)); /* Find the pointer to this specific chunk */ /* Note: we're not using isonum_731() here because the data is known aligned */ @@ -260,10 +260,10 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount, ret = zisofs_uncompress_block(inode, block_start, block_end, pcount, pages, poffset, &err); poffset += ret; - pages += poffset >> PAGE_CACHE_SHIFT; - pcount -= poffset >> PAGE_CACHE_SHIFT; - full_page -= poffset >> PAGE_CACHE_SHIFT; - poffset &= ~PAGE_CACHE_MASK; + pages += poffset >> PAGE_SHIFT; + pcount -= poffset >> PAGE_SHIFT; + full_page -= poffset >> PAGE_SHIFT; + poffset &= ~PAGE_MASK; if (err) { brelse(bh); @@ -282,7 +282,7 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount, if (poffset && *pages) { memset(page_address(*pages) + poffset, 0, - PAGE_CACHE_SIZE - poffset); + PAGE_SIZE - poffset); flush_dcache_page(*pages); SetPageUptodate(*pages); } @@ -302,12 +302,12 @@ static int zisofs_readpage(struct file *file, struct page *page) int i, pcount, full_page; unsigned int zisofs_block_shift = ISOFS_I(inode)->i_format_parm[1]; unsigned int zisofs_pages_per_cblock = - PAGE_CACHE_SHIFT <= zisofs_block_shift ? - (1 << (zisofs_block_shift - PAGE_CACHE_SHIFT)) : 0; + PAGE_SHIFT <= zisofs_block_shift ? + (1 << (zisofs_block_shift - PAGE_SHIFT)) : 0; struct page *pages[max_t(unsigned, zisofs_pages_per_cblock, 1)]; pgoff_t index = page->index, end_index; - end_index = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + end_index = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; /* * If this page is wholly outside i_size we just return zero; * do_generic_file_read() will handle this for us @@ -318,7 +318,7 @@ static int zisofs_readpage(struct file *file, struct page *page) return 0; } - if (PAGE_CACHE_SHIFT <= zisofs_block_shift) { + if (PAGE_SHIFT <= zisofs_block_shift) { /* We have already been given one page, this is the one we must do. */ full_page = index & (zisofs_pages_per_cblock - 1); @@ -351,7 +351,7 @@ static int zisofs_readpage(struct file *file, struct page *page) kunmap(pages[i]); unlock_page(pages[i]); if (i != full_page) - page_cache_release(pages[i]); + put_page(pages[i]); } } diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index bcd2d41b318a..131dedc920d8 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1021,7 +1021,7 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock, * the page with useless information without generating any * I/O errors. */ - if (b_off > ((inode->i_size + PAGE_CACHE_SIZE - 1) >> ISOFS_BUFFER_BITS(inode))) { + if (b_off > ((inode->i_size + PAGE_SIZE - 1) >> ISOFS_BUFFER_BITS(inode))) { printk(KERN_DEBUG "%s: block >= EOF (%lu, %llu)\n", __func__, b_off, (unsigned long long)inode->i_size); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 517f2de784cf..2ad98d6e19f4 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -81,11 +81,11 @@ static void release_buffer_page(struct buffer_head *bh) if (!trylock_page(page)) goto nope; - page_cache_get(page); + get_page(page); __brelse(bh); try_to_free_buffers(page); unlock_page(page); - page_cache_release(page); + put_page(page); return; nope: diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index de73a9516a54..435f0b26ac20 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2221,7 +2221,7 @@ void jbd2_journal_ack_err(journal_t *journal) int jbd2_journal_blocks_per_page(struct inode *inode) { - return 1 << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits); + return 1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits); } /* diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 01e4652d88f6..67c103867bf8 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2263,7 +2263,7 @@ int jbd2_journal_invalidatepage(journal_t *journal, struct buffer_head *head, *bh, *next; unsigned int stop = offset + length; unsigned int curr_off = 0; - int partial_page = (offset || length < PAGE_CACHE_SIZE); + int partial_page = (offset || length < PAGE_SIZE); int may_free = 1; int ret = 0; @@ -2272,7 +2272,7 @@ int jbd2_journal_invalidatepage(journal_t *journal, if (!page_has_buffers(page)) return 0; - BUG_ON(stop > PAGE_CACHE_SIZE || stop < length); + BUG_ON(stop > PAGE_SIZE || stop < length); /* We will potentially be playing with lists other than just the * data lists (especially for journaled data mode), so be diff --git a/fs/jffs2/debug.c b/fs/jffs2/debug.c index 1090eb64b90d..9d26b1b9fc01 100644 --- a/fs/jffs2/debug.c +++ b/fs/jffs2/debug.c @@ -95,15 +95,15 @@ __jffs2_dbg_fragtree_paranoia_check_nolock(struct jffs2_inode_info *f) rather than mucking around with actually reading the node and checking the compression type, which is the real way to tell a hole node. */ - if (frag->ofs & (PAGE_CACHE_SIZE-1) && frag_prev(frag) - && frag_prev(frag)->size < PAGE_CACHE_SIZE && frag_prev(frag)->node) { + if (frag->ofs & (PAGE_SIZE-1) && frag_prev(frag) + && frag_prev(frag)->size < PAGE_SIZE && frag_prev(frag)->node) { JFFS2_ERROR("REF_PRISTINE node at 0x%08x had a previous non-hole frag in the same page. Tell dwmw2.\n", ref_offset(fn->raw)); bitched = 1; } - if ((frag->ofs+frag->size) & (PAGE_CACHE_SIZE-1) && frag_next(frag) - && frag_next(frag)->size < PAGE_CACHE_SIZE && frag_next(frag)->node) { + if ((frag->ofs+frag->size) & (PAGE_SIZE-1) && frag_next(frag) + && frag_next(frag)->size < PAGE_SIZE && frag_next(frag)->node) { JFFS2_ERROR("REF_PRISTINE node at 0x%08x (%08x-%08x) had a following non-hole frag in the same page. Tell dwmw2.\n", ref_offset(fn->raw), frag->ofs, frag->ofs+frag->size); bitched = 1; diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index cad86bac3453..0e62dec3effc 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -87,14 +87,15 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg) int ret; jffs2_dbg(2, "%s(): ino #%lu, page at offset 0x%lx\n", - __func__, inode->i_ino, pg->index << PAGE_CACHE_SHIFT); + __func__, inode->i_ino, pg->index << PAGE_SHIFT); BUG_ON(!PageLocked(pg)); pg_buf = kmap(pg); /* FIXME: Can kmap fail? */ - ret = jffs2_read_inode_range(c, f, pg_buf, pg->index << PAGE_CACHE_SHIFT, PAGE_CACHE_SIZE); + ret = jffs2_read_inode_range(c, f, pg_buf, pg->index << PAGE_SHIFT, + PAGE_SIZE); if (ret) { ClearPageUptodate(pg); @@ -137,8 +138,8 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page *pg; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); - pgoff_t index = pos >> PAGE_CACHE_SHIFT; - uint32_t pageofs = index << PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; + uint32_t pageofs = index << PAGE_SHIFT; int ret = 0; pg = grab_cache_page_write_begin(mapping, index, flags); @@ -230,7 +231,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, out_page: unlock_page(pg); - page_cache_release(pg); + put_page(pg); return ret; } @@ -245,14 +246,14 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); struct jffs2_raw_inode *ri; - unsigned start = pos & (PAGE_CACHE_SIZE - 1); + unsigned start = pos & (PAGE_SIZE - 1); unsigned end = start + copied; unsigned aligned_start = start & ~3; int ret = 0; uint32_t writtenlen = 0; jffs2_dbg(1, "%s(): ino #%lu, page at 0x%lx, range %d-%d, flags %lx\n", - __func__, inode->i_ino, pg->index << PAGE_CACHE_SHIFT, + __func__, inode->i_ino, pg->index << PAGE_SHIFT, start, end, pg->flags); /* We need to avoid deadlock with page_cache_read() in @@ -261,7 +262,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, to re-lock it. */ BUG_ON(!PageUptodate(pg)); - if (end == PAGE_CACHE_SIZE) { + if (end == PAGE_SIZE) { /* When writing out the end of a page, write out the _whole_ page. This helps to reduce the number of nodes in files which have many short writes, like @@ -275,7 +276,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, jffs2_dbg(1, "%s(): Allocation of raw inode failed\n", __func__); unlock_page(pg); - page_cache_release(pg); + put_page(pg); return -ENOMEM; } @@ -292,7 +293,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, kmap(pg); ret = jffs2_write_inode_range(c, f, ri, page_address(pg) + aligned_start, - (pg->index << PAGE_CACHE_SHIFT) + aligned_start, + (pg->index << PAGE_SHIFT) + aligned_start, end - aligned_start, &writtenlen); kunmap(pg); @@ -329,6 +330,6 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, jffs2_dbg(1, "%s() returning %d\n", __func__, writtenlen > 0 ? writtenlen : ret); unlock_page(pg); - page_cache_release(pg); + put_page(pg); return writtenlen > 0 ? writtenlen : ret; } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index bead25ae8fe4..ae2ebb26b446 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -586,8 +586,8 @@ int jffs2_do_fill_super(struct super_block *sb, void *data, int silent) goto out_root; sb->s_maxbytes = 0xFFFFFFFF; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = JFFS2_SUPER_MAGIC; if (!(sb->s_flags & MS_RDONLY)) jffs2_start_garbage_collect_thread(c); @@ -685,7 +685,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c, struct inode *inode = OFNI_EDONI_2SFFJ(f); struct page *pg; - pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, + pg = read_cache_page(inode->i_mapping, offset >> PAGE_SHIFT, (void *)jffs2_do_readpage_unlock, inode); if (IS_ERR(pg)) return (void *)pg; @@ -701,7 +701,7 @@ void jffs2_gc_release_page(struct jffs2_sb_info *c, struct page *pg = (void *)*priv; kunmap(pg); - page_cache_release(pg); + put_page(pg); } static int jffs2_flash_setup(struct jffs2_sb_info *c) { diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index 7e553f286775..9ed0f26cf023 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -552,7 +552,7 @@ static int jffs2_garbage_collect_live(struct jffs2_sb_info *c, struct jffs2_era goto upnout; } /* We found a datanode. Do the GC */ - if((start >> PAGE_CACHE_SHIFT) < ((end-1) >> PAGE_CACHE_SHIFT)) { + if((start >> PAGE_SHIFT) < ((end-1) >> PAGE_SHIFT)) { /* It crosses a page boundary. Therefore, it must be a hole. */ ret = jffs2_garbage_collect_hole(c, jeb, f, fn, start, end); } else { @@ -1192,8 +1192,8 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era struct jffs2_node_frag *frag; uint32_t min, max; - min = start & ~(PAGE_CACHE_SIZE-1); - max = min + PAGE_CACHE_SIZE; + min = start & ~(PAGE_SIZE-1); + max = min + PAGE_SIZE; frag = jffs2_lookup_node_frag(&f->fragtree, start); @@ -1351,7 +1351,7 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era cdatalen = min_t(uint32_t, alloclen - sizeof(ri), end - offset); datalen = end - offset; - writebuf = pg_ptr + (offset & (PAGE_CACHE_SIZE -1)); + writebuf = pg_ptr + (offset & (PAGE_SIZE -1)); comprtype = jffs2_compress(c, f, writebuf, &comprbuf, &datalen, &cdatalen); diff --git a/fs/jffs2/nodelist.c b/fs/jffs2/nodelist.c index 9a5449bc3afb..b86c78d178c6 100644 --- a/fs/jffs2/nodelist.c +++ b/fs/jffs2/nodelist.c @@ -90,7 +90,7 @@ uint32_t jffs2_truncate_fragtree(struct jffs2_sb_info *c, struct rb_root *list, /* If the last fragment starts at the RAM page boundary, it is * REF_PRISTINE irrespective of its size. */ - if (frag->node && (frag->ofs & (PAGE_CACHE_SIZE - 1)) == 0) { + if (frag->node && (frag->ofs & (PAGE_SIZE - 1)) == 0) { dbg_fragtree2("marking the last fragment 0x%08x-0x%08x REF_PRISTINE.\n", frag->ofs, frag->ofs + frag->size); frag->node->raw->flash_offset = ref_offset(frag->node->raw) | REF_PRISTINE; @@ -237,7 +237,7 @@ static int jffs2_add_frag_to_fragtree(struct jffs2_sb_info *c, struct rb_root *r If so, both 'this' and the new node get marked REF_NORMAL so the GC can take a look. */ - if (lastend && (lastend-1) >> PAGE_CACHE_SHIFT == newfrag->ofs >> PAGE_CACHE_SHIFT) { + if (lastend && (lastend-1) >> PAGE_SHIFT == newfrag->ofs >> PAGE_SHIFT) { if (this->node) mark_ref_normal(this->node->raw); mark_ref_normal(newfrag->node->raw); @@ -382,7 +382,7 @@ int jffs2_add_full_dnode_to_inode(struct jffs2_sb_info *c, struct jffs2_inode_in /* If we now share a page with other nodes, mark either previous or next node REF_NORMAL, as appropriate. */ - if (newfrag->ofs & (PAGE_CACHE_SIZE-1)) { + if (newfrag->ofs & (PAGE_SIZE-1)) { struct jffs2_node_frag *prev = frag_prev(newfrag); mark_ref_normal(fn->raw); @@ -391,7 +391,7 @@ int jffs2_add_full_dnode_to_inode(struct jffs2_sb_info *c, struct jffs2_inode_in mark_ref_normal(prev->node->raw); } - if ((newfrag->ofs+newfrag->size) & (PAGE_CACHE_SIZE-1)) { + if ((newfrag->ofs+newfrag->size) & (PAGE_SIZE-1)) { struct jffs2_node_frag *next = frag_next(newfrag); if (next) { diff --git a/fs/jffs2/write.c b/fs/jffs2/write.c index b634de4c8101..7fb187ab2682 100644 --- a/fs/jffs2/write.c +++ b/fs/jffs2/write.c @@ -172,8 +172,8 @@ struct jffs2_full_dnode *jffs2_write_dnode(struct jffs2_sb_info *c, struct jffs2 beginning of a page and runs to the end of the file, or if it's a hole node, mark it REF_PRISTINE, else REF_NORMAL. */ - if ((je32_to_cpu(ri->dsize) >= PAGE_CACHE_SIZE) || - ( ((je32_to_cpu(ri->offset)&(PAGE_CACHE_SIZE-1))==0) && + if ((je32_to_cpu(ri->dsize) >= PAGE_SIZE) || + ( ((je32_to_cpu(ri->offset)&(PAGE_SIZE-1))==0) && (je32_to_cpu(ri->dsize)+je32_to_cpu(ri->offset) == je32_to_cpu(ri->isize)))) { flash_ofs |= REF_PRISTINE; } else { @@ -366,7 +366,8 @@ int jffs2_write_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f, break; } mutex_lock(&f->sem); - datalen = min_t(uint32_t, writelen, PAGE_CACHE_SIZE - (offset & (PAGE_CACHE_SIZE-1))); + datalen = min_t(uint32_t, writelen, + PAGE_SIZE - (offset & (PAGE_SIZE-1))); cdatalen = min_t(uint32_t, alloclen - sizeof(*ri), datalen); comprtype = jffs2_compress(c, f, buf, &comprbuf, &datalen, &cdatalen); diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index a3eb316b1ac3..b60e015cc757 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -80,7 +80,7 @@ static inline void lock_metapage(struct metapage *mp) static struct kmem_cache *metapage_cache; static mempool_t *metapage_mempool; -#define MPS_PER_PAGE (PAGE_CACHE_SIZE >> L2PSIZE) +#define MPS_PER_PAGE (PAGE_SIZE >> L2PSIZE) #if MPS_PER_PAGE > 1 @@ -316,7 +316,7 @@ static void last_write_complete(struct page *page) struct metapage *mp; unsigned int offset; - for (offset = 0; offset < PAGE_CACHE_SIZE; offset += PSIZE) { + for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) { mp = page_to_mp(page, offset); if (mp && test_bit(META_io, &mp->flag)) { if (mp->lsn) @@ -366,12 +366,12 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc) int bad_blocks = 0; page_start = (sector_t)page->index << - (PAGE_CACHE_SHIFT - inode->i_blkbits); + (PAGE_SHIFT - inode->i_blkbits); BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); set_page_writeback(page); - for (offset = 0; offset < PAGE_CACHE_SIZE; offset += PSIZE) { + for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) { mp = page_to_mp(page, offset); if (!mp || !test_bit(META_dirty, &mp->flag)) @@ -416,7 +416,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc) bio = NULL; } else inc_io(page); - xlen = (PAGE_CACHE_SIZE - offset) >> inode->i_blkbits; + xlen = (PAGE_SIZE - offset) >> inode->i_blkbits; pblock = metapage_get_blocks(inode, lblock, &xlen); if (!pblock) { printk(KERN_ERR "JFS: metapage_get_blocks failed\n"); @@ -485,7 +485,7 @@ static int metapage_readpage(struct file *fp, struct page *page) struct inode *inode = page->mapping->host; struct bio *bio = NULL; int block_offset; - int blocks_per_page = PAGE_CACHE_SIZE >> inode->i_blkbits; + int blocks_per_page = PAGE_SIZE >> inode->i_blkbits; sector_t page_start; /* address of page in fs blocks */ sector_t pblock; int xlen; @@ -494,7 +494,7 @@ static int metapage_readpage(struct file *fp, struct page *page) BUG_ON(!PageLocked(page)); page_start = (sector_t)page->index << - (PAGE_CACHE_SHIFT - inode->i_blkbits); + (PAGE_SHIFT - inode->i_blkbits); block_offset = 0; while (block_offset < blocks_per_page) { @@ -542,7 +542,7 @@ static int metapage_releasepage(struct page *page, gfp_t gfp_mask) int ret = 1; int offset; - for (offset = 0; offset < PAGE_CACHE_SIZE; offset += PSIZE) { + for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) { mp = page_to_mp(page, offset); if (!mp) @@ -568,7 +568,7 @@ static int metapage_releasepage(struct page *page, gfp_t gfp_mask) static void metapage_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { - BUG_ON(offset || length < PAGE_CACHE_SIZE); + BUG_ON(offset || length < PAGE_SIZE); BUG_ON(PageWriteback(page)); @@ -599,10 +599,10 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, inode->i_ino, lblock, absolute); l2bsize = inode->i_blkbits; - l2BlocksPerPage = PAGE_CACHE_SHIFT - l2bsize; + l2BlocksPerPage = PAGE_SHIFT - l2bsize; page_index = lblock >> l2BlocksPerPage; page_offset = (lblock - (page_index << l2BlocksPerPage)) << l2bsize; - if ((page_offset + size) > PAGE_CACHE_SIZE) { + if ((page_offset + size) > PAGE_SIZE) { jfs_err("MetaData crosses page boundary!!"); jfs_err("lblock = %lx, size = %d", lblock, size); dump_stack(); @@ -621,7 +621,7 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, mapping = inode->i_mapping; } - if (new && (PSIZE == PAGE_CACHE_SIZE)) { + if (new && (PSIZE == PAGE_SIZE)) { page = grab_cache_page(mapping, page_index); if (!page) { jfs_err("grab_cache_page failed!"); @@ -693,7 +693,7 @@ unlock: void grab_metapage(struct metapage * mp) { jfs_info("grab_metapage: mp = 0x%p", mp); - page_cache_get(mp->page); + get_page(mp->page); lock_page(mp->page); mp->count++; lock_metapage(mp); @@ -706,12 +706,12 @@ void force_metapage(struct metapage *mp) jfs_info("force_metapage: mp = 0x%p", mp); set_bit(META_forcewrite, &mp->flag); clear_bit(META_sync, &mp->flag); - page_cache_get(page); + get_page(page); lock_page(page); set_page_dirty(page); write_one_page(page, 1); clear_bit(META_forcewrite, &mp->flag); - page_cache_release(page); + put_page(page); } void hold_metapage(struct metapage *mp) @@ -726,7 +726,7 @@ void put_metapage(struct metapage *mp) unlock_page(mp->page); return; } - page_cache_get(mp->page); + get_page(mp->page); mp->count++; lock_metapage(mp); unlock_page(mp->page); @@ -746,7 +746,7 @@ void release_metapage(struct metapage * mp) assert(mp->count); if (--mp->count || mp->nohomeok) { unlock_page(page); - page_cache_release(page); + put_page(page); return; } @@ -764,13 +764,13 @@ void release_metapage(struct metapage * mp) drop_metapage(page, mp); unlock_page(page); - page_cache_release(page); + put_page(page); } void __invalidate_metapages(struct inode *ip, s64 addr, int len) { sector_t lblock; - int l2BlocksPerPage = PAGE_CACHE_SHIFT - ip->i_blkbits; + int l2BlocksPerPage = PAGE_SHIFT - ip->i_blkbits; int BlocksPerPage = 1 << l2BlocksPerPage; /* All callers are interested in block device's mapping */ struct address_space *mapping = @@ -788,7 +788,7 @@ void __invalidate_metapages(struct inode *ip, s64 addr, int len) page = find_lock_page(mapping, lblock >> l2BlocksPerPage); if (!page) continue; - for (offset = 0; offset < PAGE_CACHE_SIZE; offset += PSIZE) { + for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) { mp = page_to_mp(page, offset); if (!mp) continue; @@ -803,7 +803,7 @@ void __invalidate_metapages(struct inode *ip, s64 addr, int len) remove_from_logsync(mp); } unlock_page(page); - page_cache_release(page); + put_page(page); } } diff --git a/fs/jfs/jfs_metapage.h b/fs/jfs/jfs_metapage.h index 337e9e51ac06..a869fb4a20d6 100644 --- a/fs/jfs/jfs_metapage.h +++ b/fs/jfs/jfs_metapage.h @@ -106,7 +106,7 @@ static inline void metapage_nohomeok(struct metapage *mp) lock_page(page); if (!mp->nohomeok++) { mark_metapage_dirty(mp); - page_cache_get(page); + get_page(page); wait_on_page_writeback(page); } unlock_page(page); @@ -128,7 +128,7 @@ static inline void metapage_wait_for_io(struct metapage *mp) static inline void _metapage_homeok(struct metapage *mp) { if (!--mp->nohomeok) - page_cache_release(mp->page); + put_page(mp->page); } static inline void metapage_homeok(struct metapage *mp) diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 4f5d85ba8e23..78d599198bf5 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -596,7 +596,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) * Page cache is indexed by long. * I would use MAX_LFS_FILESIZE, but it's only half as big */ - sb->s_maxbytes = min(((u64) PAGE_CACHE_SIZE << 32) - 1, + sb->s_maxbytes = min(((u64) PAGE_SIZE << 32) - 1, (u64)sb->s_maxbytes); #endif sb->s_time_gran = 1; diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index b67dbccdaf88..f73541fbe7af 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -138,8 +138,8 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic) struct dentry *root; info->sb = sb; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = magic; sb->s_op = &kernfs_sops; sb->s_time_gran = 1; diff --git a/fs/libfs.c b/fs/libfs.c index 0ca80b2af420..f3fa82ce9b70 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -25,7 +25,7 @@ int simple_getattr(struct vfsmount *mnt, struct dentry *dentry, { struct inode *inode = d_inode(dentry); generic_fillattr(inode, stat); - stat->blocks = inode->i_mapping->nrpages << (PAGE_CACHE_SHIFT - 9); + stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9); return 0; } EXPORT_SYMBOL(simple_getattr); @@ -33,7 +33,7 @@ EXPORT_SYMBOL(simple_getattr); int simple_statfs(struct dentry *dentry, struct kstatfs *buf) { buf->f_type = dentry->d_sb->s_magic; - buf->f_bsize = PAGE_CACHE_SIZE; + buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; return 0; } @@ -395,7 +395,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping, struct page *page; pgoff_t index; - index = pos >> PAGE_CACHE_SHIFT; + index = pos >> PAGE_SHIFT; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) @@ -403,10 +403,10 @@ int simple_write_begin(struct file *file, struct address_space *mapping, *pagep = page; - if (!PageUptodate(page) && (len != PAGE_CACHE_SIZE)) { - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + if (!PageUptodate(page) && (len != PAGE_SIZE)) { + unsigned from = pos & (PAGE_SIZE - 1); - zero_user_segments(page, 0, from, from + len, PAGE_CACHE_SIZE); + zero_user_segments(page, 0, from, from + len, PAGE_SIZE); } return 0; } @@ -442,7 +442,7 @@ int simple_write_end(struct file *file, struct address_space *mapping, /* zero the stale part of the page if we did a short copy */ if (copied < len) { - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned from = pos & (PAGE_SIZE - 1); zero_user(page, from + copied, len - copied); } @@ -458,7 +458,7 @@ int simple_write_end(struct file *file, struct address_space *mapping, set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); return copied; } @@ -477,8 +477,8 @@ int simple_fill_super(struct super_block *s, unsigned long magic, struct dentry *dentry; int i; - s->s_blocksize = PAGE_CACHE_SIZE; - s->s_blocksize_bits = PAGE_CACHE_SHIFT; + s->s_blocksize = PAGE_SIZE; + s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = magic; s->s_op = &simple_super_operations; s->s_time_gran = 1; @@ -994,12 +994,12 @@ int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks) { u64 last_fs_block = num_blocks - 1; u64 last_fs_page = - last_fs_block >> (PAGE_CACHE_SHIFT - blocksize_bits); + last_fs_block >> (PAGE_SHIFT - blocksize_bits); if (unlikely(num_blocks == 0)) return 0; - if ((blocksize_bits < 9) || (blocksize_bits > PAGE_CACHE_SHIFT)) + if ((blocksize_bits < 9) || (blocksize_bits > PAGE_SHIFT)) return -EINVAL; if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) || diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c index a709d80c8ebc..cc26f8f215f5 100644 --- a/fs/logfs/dev_bdev.c +++ b/fs/logfs/dev_bdev.c @@ -64,7 +64,7 @@ static void writeseg_end_io(struct bio *bio) bio_for_each_segment_all(bvec, bio, i) { end_page_writeback(bvec->bv_page); - page_cache_release(bvec->bv_page); + put_page(bvec->bv_page); } bio_put(bio); if (atomic_dec_and_test(&super->s_pending_writes)) diff --git a/fs/logfs/dev_mtd.c b/fs/logfs/dev_mtd.c index 9c501449450d..b76a62b1978f 100644 --- a/fs/logfs/dev_mtd.c +++ b/fs/logfs/dev_mtd.c @@ -46,9 +46,9 @@ static int loffs_mtd_write(struct super_block *sb, loff_t ofs, size_t len, BUG_ON((ofs >= mtd->size) || (len > mtd->size - ofs)); BUG_ON(ofs != (ofs >> super->s_writeshift) << super->s_writeshift); - BUG_ON(len > PAGE_CACHE_SIZE); - page_start = ofs & PAGE_CACHE_MASK; - page_end = PAGE_CACHE_ALIGN(ofs + len) - 1; + BUG_ON(len > PAGE_SIZE); + page_start = ofs & PAGE_MASK; + page_end = PAGE_ALIGN(ofs + len) - 1; ret = mtd_write(mtd, ofs, len, &retlen, buf); if (ret || (retlen != len)) return -EIO; @@ -82,7 +82,7 @@ static int logfs_mtd_erase_mapping(struct super_block *sb, loff_t ofs, if (!page) continue; memset(page_address(page), 0xFF, PAGE_SIZE); - page_cache_release(page); + put_page(page); } return 0; } @@ -195,7 +195,7 @@ static int __logfs_mtd_writeseg(struct super_block *sb, u64 ofs, pgoff_t index, err = loffs_mtd_write(sb, page->index << PAGE_SHIFT, PAGE_SIZE, page_address(page)); unlock_page(page); - page_cache_release(page); + put_page(page); if (err) return err; } diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index 542468e9bfb4..ddbed2be5366 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -183,7 +183,7 @@ static struct page *logfs_get_dd_page(struct inode *dir, struct dentry *dentry) if (name->len != be16_to_cpu(dd->namelen) || memcmp(name->name, dd->name, name->len)) { kunmap_atomic(dd); - page_cache_release(page); + put_page(page); continue; } @@ -238,7 +238,7 @@ static int logfs_unlink(struct inode *dir, struct dentry *dentry) return PTR_ERR(page); } index = page->index; - page_cache_release(page); + put_page(page); mutex_lock(&super->s_dirop_mutex); logfs_add_transaction(dir, ta); @@ -316,7 +316,7 @@ static int logfs_readdir(struct file *file, struct dir_context *ctx) be16_to_cpu(dd->namelen), be64_to_cpu(dd->ino), dd->type); kunmap(page); - page_cache_release(page); + put_page(page); if (full) break; } @@ -349,7 +349,7 @@ static struct dentry *logfs_lookup(struct inode *dir, struct dentry *dentry, dd = kmap_atomic(page); ino = be64_to_cpu(dd->ino); kunmap_atomic(dd); - page_cache_release(page); + put_page(page); inode = logfs_iget(dir->i_sb, ino); if (IS_ERR(inode)) @@ -392,7 +392,7 @@ static int logfs_write_dir(struct inode *dir, struct dentry *dentry, err = logfs_write_buf(dir, page, WF_LOCK); unlock_page(page); - page_cache_release(page); + put_page(page); if (!err) grow_dir(dir, index); return err; @@ -561,7 +561,7 @@ static int logfs_get_dd(struct inode *dir, struct dentry *dentry, map = kmap_atomic(page); memcpy(dd, map, sizeof(*dd)); kunmap_atomic(map); - page_cache_release(page); + put_page(page); return 0; } diff --git a/fs/logfs/file.c b/fs/logfs/file.c index 61eaeb1b6cac..f01ddfb1a03b 100644 --- a/fs/logfs/file.c +++ b/fs/logfs/file.c @@ -15,21 +15,21 @@ static int logfs_write_begin(struct file *file, struct address_space *mapping, { struct inode *inode = mapping->host; struct page *page; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; *pagep = page; - if ((len == PAGE_CACHE_SIZE) || PageUptodate(page)) + if ((len == PAGE_SIZE) || PageUptodate(page)) return 0; - if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) { - unsigned start = pos & (PAGE_CACHE_SIZE - 1); + if ((pos & PAGE_MASK) >= i_size_read(inode)) { + unsigned start = pos & (PAGE_SIZE - 1); unsigned end = start + len; /* Reading beyond i_size is simple: memset to zero */ - zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE); + zero_user_segments(page, 0, start, end, PAGE_SIZE); return 0; } return logfs_readpage_nolock(page); @@ -41,11 +41,11 @@ static int logfs_write_end(struct file *file, struct address_space *mapping, { struct inode *inode = mapping->host; pgoff_t index = page->index; - unsigned start = pos & (PAGE_CACHE_SIZE - 1); + unsigned start = pos & (PAGE_SIZE - 1); unsigned end = start + copied; int ret = 0; - BUG_ON(PAGE_CACHE_SIZE != inode->i_sb->s_blocksize); + BUG_ON(PAGE_SIZE != inode->i_sb->s_blocksize); BUG_ON(page->index > I3_BLOCKS); if (copied < len) { @@ -61,8 +61,8 @@ static int logfs_write_end(struct file *file, struct address_space *mapping, if (copied == 0) goto out; /* FIXME: do we need to update inode? */ - if (i_size_read(inode) < (index << PAGE_CACHE_SHIFT) + end) { - i_size_write(inode, (index << PAGE_CACHE_SHIFT) + end); + if (i_size_read(inode) < (index << PAGE_SHIFT) + end) { + i_size_write(inode, (index << PAGE_SHIFT) + end); mark_inode_dirty_sync(inode); } @@ -75,7 +75,7 @@ static int logfs_write_end(struct file *file, struct address_space *mapping, } out: unlock_page(page); - page_cache_release(page); + put_page(page); return ret ? ret : copied; } @@ -118,7 +118,7 @@ static int logfs_writepage(struct page *page, struct writeback_control *wbc) { struct inode *inode = page->mapping->host; loff_t i_size = i_size_read(inode); - pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; + pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; u64 bix; level_t level; @@ -142,7 +142,7 @@ static int logfs_writepage(struct page *page, struct writeback_control *wbc) return __logfs_writepage(page); /* Is the page fully outside i_size? (truncate in progress) */ - offset = i_size & (PAGE_CACHE_SIZE-1); + offset = i_size & (PAGE_SIZE-1); if (bix > end_index || offset == 0) { unlock_page(page); return 0; /* don't care */ @@ -155,7 +155,7 @@ static int logfs_writepage(struct page *page, struct writeback_control *wbc) * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ - zero_user_segment(page, offset, PAGE_CACHE_SIZE); + zero_user_segment(page, offset, PAGE_SIZE); return __logfs_writepage(page); } diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c index 20973c9e52f8..3fb8c6d67303 100644 --- a/fs/logfs/readwrite.c +++ b/fs/logfs/readwrite.c @@ -281,7 +281,7 @@ static struct page *logfs_get_read_page(struct inode *inode, u64 bix, static void logfs_put_read_page(struct page *page) { unlock_page(page); - page_cache_release(page); + put_page(page); } static void logfs_lock_write_page(struct page *page) @@ -323,7 +323,7 @@ repeat: return NULL; err = add_to_page_cache_lru(page, mapping, index, GFP_NOFS); if (unlikely(err)) { - page_cache_release(page); + put_page(page); if (err == -EEXIST) goto repeat; return NULL; @@ -342,7 +342,7 @@ static void logfs_unlock_write_page(struct page *page) static void logfs_put_write_page(struct page *page) { logfs_unlock_write_page(page); - page_cache_release(page); + put_page(page); } static struct page *logfs_get_page(struct inode *inode, u64 bix, level_t level, @@ -562,7 +562,7 @@ static void indirect_free_block(struct super_block *sb, if (PagePrivate(page)) { ClearPagePrivate(page); - page_cache_release(page); + put_page(page); set_page_private(page, 0); } __free_block(sb, block); @@ -655,7 +655,7 @@ static void alloc_data_block(struct inode *inode, struct page *page) block->page = page; SetPagePrivate(page); - page_cache_get(page); + get_page(page); set_page_private(page, (unsigned long) block); block->ops = &indirect_block_ops; @@ -709,7 +709,7 @@ static u64 block_get_pointer(struct page *page, int index) static int logfs_read_empty(struct page *page) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); return 0; } @@ -1660,7 +1660,7 @@ static int truncate_data_block(struct inode *inode, struct page *page, if (err) return err; - zero_user_segment(page, size - pageofs, PAGE_CACHE_SIZE); + zero_user_segment(page, size - pageofs, PAGE_SIZE); return logfs_segment_write(inode, page, shadow); } @@ -1919,7 +1919,7 @@ static void move_page_to_inode(struct inode *inode, struct page *page) block->page = NULL; if (PagePrivate(page)) { ClearPagePrivate(page); - page_cache_release(page); + put_page(page); set_page_private(page, 0); } } @@ -1940,7 +1940,7 @@ static void move_inode_to_page(struct page *page, struct inode *inode) if (!PagePrivate(page)) { SetPagePrivate(page); - page_cache_get(page); + get_page(page); set_page_private(page, (unsigned long) block); } @@ -1971,7 +1971,7 @@ int logfs_read_inode(struct inode *inode) logfs_disk_to_inode(di, inode); kunmap_atomic(di); move_page_to_inode(inode, page); - page_cache_release(page); + put_page(page); return 0; } diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c index d270e4b2ab6b..1efd6055f4b0 100644 --- a/fs/logfs/segment.c +++ b/fs/logfs/segment.c @@ -90,9 +90,9 @@ int __logfs_buf_write(struct logfs_area *area, u64 ofs, void *buf, size_t len, if (!PagePrivate(page)) { SetPagePrivate(page); - page_cache_get(page); + get_page(page); } - page_cache_release(page); + put_page(page); buf += copylen; len -= copylen; @@ -117,9 +117,9 @@ static void pad_partial_page(struct logfs_area *area) memset(page_address(page) + offset, 0xff, len); if (!PagePrivate(page)) { SetPagePrivate(page); - page_cache_get(page); + get_page(page); } - page_cache_release(page); + put_page(page); } } @@ -129,20 +129,20 @@ static void pad_full_pages(struct logfs_area *area) struct logfs_super *super = logfs_super(sb); u64 ofs = dev_ofs(sb, area->a_segno, area->a_used_bytes); u32 len = super->s_segsize - area->a_used_bytes; - pgoff_t index = PAGE_CACHE_ALIGN(ofs) >> PAGE_CACHE_SHIFT; - pgoff_t no_indizes = len >> PAGE_CACHE_SHIFT; + pgoff_t index = PAGE_ALIGN(ofs) >> PAGE_SHIFT; + pgoff_t no_indizes = len >> PAGE_SHIFT; struct page *page; while (no_indizes) { page = get_mapping_page(sb, index, 0); BUG_ON(!page); /* FIXME: reserve a pool */ SetPageUptodate(page); - memset(page_address(page), 0xff, PAGE_CACHE_SIZE); + memset(page_address(page), 0xff, PAGE_SIZE); if (!PagePrivate(page)) { SetPagePrivate(page); - page_cache_get(page); + get_page(page); } - page_cache_release(page); + put_page(page); index++; no_indizes--; } @@ -411,7 +411,7 @@ int wbuf_read(struct super_block *sb, u64 ofs, size_t len, void *buf) if (IS_ERR(page)) return PTR_ERR(page); memcpy(buf, page_address(page) + offset, copylen); - page_cache_release(page); + put_page(page); buf += copylen; len -= copylen; @@ -499,7 +499,7 @@ static void move_btree_to_page(struct inode *inode, struct page *page, if (!PagePrivate(page)) { SetPagePrivate(page); - page_cache_get(page); + get_page(page); set_page_private(page, (unsigned long) block); } block->ops = &indirect_block_ops; @@ -554,7 +554,7 @@ void move_page_to_btree(struct page *page) if (PagePrivate(page)) { ClearPagePrivate(page); - page_cache_release(page); + put_page(page); set_page_private(page, 0); } block->ops = &btree_block_ops; @@ -723,9 +723,9 @@ void freeseg(struct super_block *sb, u32 segno) continue; if (PagePrivate(page)) { ClearPagePrivate(page); - page_cache_release(page); + put_page(page); } - page_cache_release(page); + put_page(page); } } diff --git a/fs/logfs/super.c b/fs/logfs/super.c index 54360293bcb5..5751082dba52 100644 --- a/fs/logfs/super.c +++ b/fs/logfs/super.c @@ -48,7 +48,7 @@ void emergency_read_end(struct page *page) if (page == emergency_page) mutex_unlock(&emergency_mutex); else - page_cache_release(page); + put_page(page); } static void dump_segfile(struct super_block *sb) @@ -206,7 +206,7 @@ static int write_one_sb(struct super_block *sb, logfs_set_segment_erased(sb, segno, ec, 0); logfs_write_ds(sb, ds, segno, ec); err = super->s_devops->write_sb(sb, page); - page_cache_release(page); + put_page(page); return err; } @@ -366,24 +366,24 @@ static struct page *find_super_block(struct super_block *sb) return NULL; last = super->s_devops->find_last_sb(sb, &super->s_sb_ofs[1]); if (!last || IS_ERR(last)) { - page_cache_release(first); + put_page(first); return NULL; } if (!logfs_check_ds(page_address(first))) { - page_cache_release(last); + put_page(last); return first; } /* First one didn't work, try the second superblock */ if (!logfs_check_ds(page_address(last))) { - page_cache_release(first); + put_page(first); return last; } /* Neither worked, sorry folks */ - page_cache_release(first); - page_cache_release(last); + put_page(first); + put_page(last); return NULL; } @@ -425,7 +425,7 @@ static int __logfs_read_sb(struct super_block *sb) super->s_data_levels = ds->ds_data_levels; super->s_total_levels = super->s_ifile_levels + super->s_iblock_levels + super->s_data_levels; - page_cache_release(page); + put_page(page); return 0; } diff --git a/fs/minix/dir.c b/fs/minix/dir.c index d19ac258105a..33957c07cd11 100644 --- a/fs/minix/dir.c +++ b/fs/minix/dir.c @@ -28,7 +28,7 @@ const struct file_operations minix_dir_operations = { static inline void dir_put_page(struct page *page) { kunmap(page); - page_cache_release(page); + put_page(page); } /* @@ -38,10 +38,10 @@ static inline void dir_put_page(struct page *page) static unsigned minix_last_byte(struct inode *inode, unsigned long page_nr) { - unsigned last_byte = PAGE_CACHE_SIZE; + unsigned last_byte = PAGE_SIZE; - if (page_nr == (inode->i_size >> PAGE_CACHE_SHIFT)) - last_byte = inode->i_size & (PAGE_CACHE_SIZE - 1); + if (page_nr == (inode->i_size >> PAGE_SHIFT)) + last_byte = inode->i_size & (PAGE_SIZE - 1); return last_byte; } @@ -92,8 +92,8 @@ static int minix_readdir(struct file *file, struct dir_context *ctx) if (pos >= inode->i_size) return 0; - offset = pos & ~PAGE_CACHE_MASK; - n = pos >> PAGE_CACHE_SHIFT; + offset = pos & ~PAGE_MASK; + n = pos >> PAGE_SHIFT; for ( ; n < npages; n++, offset = 0) { char *p, *kaddr, *limit; @@ -229,7 +229,7 @@ int minix_add_link(struct dentry *dentry, struct inode *inode) lock_page(page); kaddr = (char*)page_address(page); dir_end = kaddr + minix_last_byte(dir, n); - limit = kaddr + PAGE_CACHE_SIZE - sbi->s_dirsize; + limit = kaddr + PAGE_SIZE - sbi->s_dirsize; for (p = kaddr; p <= limit; p = minix_next_entry(p, sbi)) { de = (minix_dirent *)p; de3 = (minix3_dirent *)p; @@ -327,7 +327,7 @@ int minix_make_empty(struct inode *inode, struct inode *dir) } kaddr = kmap_atomic(page); - memset(kaddr, 0, PAGE_CACHE_SIZE); + memset(kaddr, 0, PAGE_SIZE); if (sbi->s_version == MINIX_V3) { minix3_dirent *de3 = (minix3_dirent *)kaddr; @@ -350,7 +350,7 @@ int minix_make_empty(struct inode *inode, struct inode *dir) err = dir_commit_chunk(page, 0, 2 * sbi->s_dirsize); fail: - page_cache_release(page); + put_page(page); return err; } diff --git a/fs/minix/namei.c b/fs/minix/namei.c index a795a11e50c7..2887d1d95ce2 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -243,11 +243,11 @@ static int minix_rename(struct inode * old_dir, struct dentry *old_dentry, out_dir: if (dir_de) { kunmap(dir_page); - page_cache_release(dir_page); + put_page(dir_page); } out_old: kunmap(old_page); - page_cache_release(old_page); + put_page(old_page); out: return err; } diff --git a/fs/mpage.c b/fs/mpage.c index 6bd9fd90964e..e7083bfbabb3 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -107,7 +107,7 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) * don't make any buffers if there is only one buffer on * the page and the page just needs to be set up to date */ - if (inode->i_blkbits == PAGE_CACHE_SHIFT && + if (inode->i_blkbits == PAGE_SHIFT && buffer_uptodate(bh)) { SetPageUptodate(page); return; @@ -145,7 +145,7 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages, { struct inode *inode = page->mapping->host; const unsigned blkbits = inode->i_blkbits; - const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits; + const unsigned blocks_per_page = PAGE_SIZE >> blkbits; const unsigned blocksize = 1 << blkbits; sector_t block_in_file; sector_t last_block; @@ -162,7 +162,7 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages, if (page_has_buffers(page)) goto confused; - block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits); + block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); last_block = block_in_file + nr_pages * blocks_per_page; last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits; if (last_block > last_block_in_file) @@ -249,7 +249,7 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages, } if (first_hole != blocks_per_page) { - zero_user_segment(page, first_hole << blkbits, PAGE_CACHE_SIZE); + zero_user_segment(page, first_hole << blkbits, PAGE_SIZE); if (first_hole == 0) { SetPageUptodate(page); unlock_page(page); @@ -380,7 +380,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, &first_logical_block, get_block, gfp); } - page_cache_release(page); + put_page(page); } BUG_ON(!list_empty(pages)); if (bio) @@ -472,7 +472,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc, struct inode *inode = page->mapping->host; const unsigned blkbits = inode->i_blkbits; unsigned long end_index; - const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits; + const unsigned blocks_per_page = PAGE_SIZE >> blkbits; sector_t last_block; sector_t block_in_file; sector_t blocks[MAX_BUF_PER_PAGE]; @@ -542,7 +542,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc, * The page has no buffers: map it to disk */ BUG_ON(!PageUptodate(page)); - block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits); + block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); last_block = (i_size - 1) >> blkbits; map_bh.b_page = page; for (page_block = 0; page_block < blocks_per_page; ) { @@ -574,7 +574,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc, first_unmapped = page_block; page_is_mapped: - end_index = i_size >> PAGE_CACHE_SHIFT; + end_index = i_size >> PAGE_SHIFT; if (page->index >= end_index) { /* * The page straddles i_size. It must be zeroed out on each @@ -584,11 +584,11 @@ page_is_mapped: * is zeroed when mapped, and writes to that region are not * written out to the file." */ - unsigned offset = i_size & (PAGE_CACHE_SIZE - 1); + unsigned offset = i_size & (PAGE_SIZE - 1); if (page->index > end_index || !offset) goto confused; - zero_user_segment(page, offset, PAGE_CACHE_SIZE); + zero_user_segment(page, offset, PAGE_SIZE); } /* diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index b7f8eaeea5d8..bfdad003ee56 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -510,7 +510,7 @@ static int ncp_readdir(struct file *file, struct dir_context *ctx) kunmap(ctl.page); SetPageUptodate(ctl.page); unlock_page(ctl.page); - page_cache_release(ctl.page); + put_page(ctl.page); ctl.page = NULL; } ctl.idx = 0; @@ -520,7 +520,7 @@ invalid_cache: if (ctl.page) { kunmap(ctl.page); unlock_page(ctl.page); - page_cache_release(ctl.page); + put_page(ctl.page); ctl.page = NULL; } ctl.cache = cache; @@ -554,14 +554,14 @@ finished: kunmap(ctl.page); SetPageUptodate(ctl.page); unlock_page(ctl.page); - page_cache_release(ctl.page); + put_page(ctl.page); } if (page) { cache->head = ctl.head; kunmap(page); SetPageUptodate(page); unlock_page(page); - page_cache_release(page); + put_page(page); } out: return result; @@ -649,7 +649,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx, kunmap(ctl.page); SetPageUptodate(ctl.page); unlock_page(ctl.page); - page_cache_release(ctl.page); + put_page(ctl.page); } ctl.cache = NULL; ctl.idx -= NCP_DIRCACHE_SIZE; diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h index 5233fbc1747a..17cfb743b5bf 100644 --- a/fs/ncpfs/ncplib_kernel.h +++ b/fs/ncpfs/ncplib_kernel.h @@ -191,7 +191,7 @@ struct ncp_cache_head { int eof; }; -#define NCP_DIRCACHE_SIZE ((int)(PAGE_CACHE_SIZE/sizeof(struct dentry *))) +#define NCP_DIRCACHE_SIZE ((int)(PAGE_SIZE/sizeof(struct dentry *))) union ncp_dir_cache { struct ncp_cache_head head; struct dentry *dentry[NCP_DIRCACHE_SIZE]; diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 02e4d87d2ed3..17a42e4eb872 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -231,7 +231,7 @@ bl_read_pagelist(struct nfs_pgio_header *header) size_t bytes_left = header->args.count; unsigned int pg_offset = header->args.pgbase, pg_len; struct page **pages = header->args.pages; - int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; + int pg_index = header->args.pgbase >> PAGE_SHIFT; const bool is_dio = (header->dreq != NULL); struct blk_plug plug; int i; @@ -263,13 +263,13 @@ bl_read_pagelist(struct nfs_pgio_header *header) } if (is_dio) { - if (pg_offset + bytes_left > PAGE_CACHE_SIZE) - pg_len = PAGE_CACHE_SIZE - pg_offset; + if (pg_offset + bytes_left > PAGE_SIZE) + pg_len = PAGE_SIZE - pg_offset; else pg_len = bytes_left; } else { BUG_ON(pg_offset != 0); - pg_len = PAGE_CACHE_SIZE; + pg_len = PAGE_SIZE; } if (is_hole(&be)) { @@ -339,9 +339,9 @@ static void bl_write_cleanup(struct work_struct *work) if (likely(!hdr->pnfs_error)) { struct pnfs_block_layout *bl = BLK_LSEG2EXT(hdr->lseg); - u64 start = hdr->args.offset & (loff_t)PAGE_CACHE_MASK; + u64 start = hdr->args.offset & (loff_t)PAGE_MASK; u64 end = (hdr->args.offset + hdr->args.count + - PAGE_CACHE_SIZE - 1) & (loff_t)PAGE_CACHE_MASK; + PAGE_SIZE - 1) & (loff_t)PAGE_MASK; ext_tree_mark_written(bl, start >> SECTOR_SHIFT, (end - start) >> SECTOR_SHIFT); @@ -373,7 +373,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync) loff_t offset = header->args.offset; size_t count = header->args.count; struct page **pages = header->args.pages; - int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; + int pg_index = header->args.pgbase >> PAGE_SHIFT; unsigned int pg_len; struct blk_plug plug; int i; @@ -392,7 +392,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync) blk_start_plug(&plug); /* we always write out the whole page */ - offset = offset & (loff_t)PAGE_CACHE_MASK; + offset = offset & (loff_t)PAGE_MASK; isect = offset >> SECTOR_SHIFT; for (i = pg_index; i < header->page_array.npages; i++) { @@ -408,7 +408,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync) extent_length = be.be_length - (isect - be.be_f_offset); } - pg_len = PAGE_CACHE_SIZE; + pg_len = PAGE_SIZE; bio = do_add_page_to_bio(bio, header->page_array.npages - i, WRITE, isect, pages[i], &map, &be, bl_end_io_write, par, @@ -820,7 +820,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) pgoff_t end; /* Optimize common case that writes from 0 to end of file */ - end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); + end = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (end != inode->i_mapping->nrpages) { rcu_read_lock(); end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); @@ -828,9 +828,9 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) } if (!end) - return i_size_read(inode) - (idx << PAGE_CACHE_SHIFT); + return i_size_read(inode) - (idx << PAGE_SHIFT); else - return (end - idx) << PAGE_CACHE_SHIFT; + return (end - idx) << PAGE_SHIFT; } static void diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index bc21205309e0..18e6fd0b9506 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -40,8 +40,8 @@ #include "../pnfs.h" #include "../netns.h" -#define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT) -#define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT) +#define PAGE_CACHE_SECTORS (PAGE_SIZE >> SECTOR_SHIFT) +#define PAGE_CACHE_SECTOR_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) #define SECTOR_SIZE (1 << SECTOR_SHIFT) struct pnfs_block_dev; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index d6d5d2a48e83..0c96528db94a 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -736,7 +736,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, server->rsize = max_rpc_payload; if (server->rsize > NFS_MAX_FILE_IO_SIZE) server->rsize = NFS_MAX_FILE_IO_SIZE; - server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + server->rpages = (server->rsize + PAGE_SIZE - 1) >> PAGE_SHIFT; server->backing_dev_info.name = "nfs"; server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD; @@ -745,13 +745,13 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, server->wsize = max_rpc_payload; if (server->wsize > NFS_MAX_FILE_IO_SIZE) server->wsize = NFS_MAX_FILE_IO_SIZE; - server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + server->wpages = (server->wsize + PAGE_SIZE - 1) >> PAGE_SHIFT; server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL); server->dtsize = nfs_block_size(fsinfo->dtpref, NULL); - if (server->dtsize > PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES) - server->dtsize = PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES; + if (server->dtsize > PAGE_SIZE * NFS_MAX_READDIR_PAGES) + server->dtsize = PAGE_SIZE * NFS_MAX_READDIR_PAGES; if (server->dtsize > server->rsize) server->dtsize = server->rsize; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 4bfa7d8bcade..adef506c5786 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -707,7 +707,7 @@ void cache_page_release(nfs_readdir_descriptor_t *desc) { if (!desc->page->mapping) nfs_readdir_clear_array(desc->page); - page_cache_release(desc->page); + put_page(desc->page); desc->page = NULL; } @@ -1923,7 +1923,7 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) * add_to_page_cache_lru() grabs an extra page refcount. * Drop it here to avoid leaking this page later. */ - page_cache_release(page); + put_page(page); } else __free_page(page); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 7a0cfd3266e5..c93826e4a8c6 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -269,7 +269,7 @@ static void nfs_direct_release_pages(struct page **pages, unsigned int npages) { unsigned int i; for (i = 0; i < npages; i++) - page_cache_release(pages[i]); + put_page(pages[i]); } void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, @@ -1003,7 +1003,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) iov_iter_count(iter)); pos = iocb->ki_pos; - end = (pos + iov_iter_count(iter) - 1) >> PAGE_CACHE_SHIFT; + end = (pos + iov_iter_count(iter) - 1) >> PAGE_SHIFT; inode_lock(inode); @@ -1013,7 +1013,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) if (mapping->nrpages) { result = invalidate_inode_pages2_range(mapping, - pos >> PAGE_CACHE_SHIFT, end); + pos >> PAGE_SHIFT, end); if (result) goto out_unlock; } @@ -1042,7 +1042,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) if (mapping->nrpages) { invalidate_inode_pages2_range(mapping, - pos >> PAGE_CACHE_SHIFT, end); + pos >> PAGE_SHIFT, end); } inode_unlock(inode); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 89bf093d342a..be01095b97ae 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -320,7 +320,7 @@ static int nfs_want_read_modify_write(struct file *file, struct page *page, loff_t pos, unsigned len) { unsigned int pglen = nfs_page_length(page); - unsigned int offset = pos & (PAGE_CACHE_SIZE - 1); + unsigned int offset = pos & (PAGE_SIZE - 1); unsigned int end = offset + len; if (pnfs_ld_read_whole_page(file->f_mapping->host)) { @@ -351,7 +351,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { int ret; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int once_thru = 0; @@ -380,12 +380,12 @@ start: ret = nfs_flush_incompatible(file, page); if (ret) { unlock_page(page); - page_cache_release(page); + put_page(page); } else if (!once_thru && nfs_want_read_modify_write(file, page, pos, len)) { once_thru = 1; ret = nfs_readpage(file, page); - page_cache_release(page); + put_page(page); if (!ret) goto start; } @@ -396,7 +396,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { - unsigned offset = pos & (PAGE_CACHE_SIZE - 1); + unsigned offset = pos & (PAGE_SIZE - 1); struct nfs_open_context *ctx = nfs_file_open_context(file); int status; @@ -413,20 +413,20 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, if (pglen == 0) { zero_user_segments(page, 0, offset, - end, PAGE_CACHE_SIZE); + end, PAGE_SIZE); SetPageUptodate(page); } else if (end >= pglen) { - zero_user_segment(page, end, PAGE_CACHE_SIZE); + zero_user_segment(page, end, PAGE_SIZE); if (offset == 0) SetPageUptodate(page); } else - zero_user_segment(page, pglen, PAGE_CACHE_SIZE); + zero_user_segment(page, pglen, PAGE_SIZE); } status = nfs_updatepage(file, page, offset, copied); unlock_page(page); - page_cache_release(page); + put_page(page); if (status < 0) return status; @@ -454,7 +454,7 @@ static void nfs_invalidate_page(struct page *page, unsigned int offset, dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %u, %u)\n", page, offset, length); - if (offset != 0 || length < PAGE_CACHE_SIZE) + if (offset != 0 || length < PAGE_SIZE) return; /* Cancel any unstarted writes on this page */ nfs_wb_page_cancel(page_file_mapping(page)->host, page); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 565f8135ae1f..f1d1d2c472e9 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -638,11 +638,11 @@ unsigned int nfs_page_length(struct page *page) if (i_size > 0) { pgoff_t page_index = page_file_index(page); - pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; + pgoff_t end_index = (i_size - 1) >> PAGE_SHIFT; if (page_index < end_index) - return PAGE_CACHE_SIZE; + return PAGE_SIZE; if (page_index == end_index) - return ((i_size - 1) & ~PAGE_CACHE_MASK) + 1; + return ((i_size - 1) & ~PAGE_MASK) + 1; } return 0; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 4e4441216804..88474a4fc669 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5001,7 +5001,7 @@ static int decode_space_limit(struct xdr_stream *xdr, blocksize = be32_to_cpup(p); maxsize = (uint64_t)nblocks * (uint64_t)blocksize; } - maxsize >>= PAGE_CACHE_SHIFT; + maxsize >>= PAGE_SHIFT; *pagemod_limit = min_t(u64, maxsize, ULONG_MAX); return 0; out_overflow: diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 9aebffb40505..049c1b1f2932 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -486,7 +486,7 @@ static void __r4w_put_page(void *priv, struct page *page) dprintk("%s: index=0x%lx\n", __func__, (page == ZERO_PAGE(0)) ? -1UL : page->index); if (ZERO_PAGE(0) != page) - page_cache_release(page); + put_page(page); return; } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 8ce4f61cbaa5..1f6db4231057 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -342,7 +342,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page, * update_nfs_request below if the region is not locked. */ req->wb_page = page; req->wb_index = page_file_index(page); - page_cache_get(page); + get_page(page); req->wb_offset = offset; req->wb_pgbase = offset; req->wb_bytes = count; @@ -392,7 +392,7 @@ static void nfs_clear_request(struct nfs_page *req) struct nfs_lock_context *l_ctx = req->wb_lock_context; if (page != NULL) { - page_cache_release(page); + put_page(page); req->wb_page = NULL; } if (l_ctx != NULL) { @@ -904,7 +904,7 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, return false; } else { if (req->wb_pgbase != 0 || - prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE) + prev->wb_pgbase + prev->wb_bytes != PAGE_SIZE) return false; } } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 2fa483e6dbe2..89a5ef4df08a 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -841,7 +841,7 @@ send_layoutget(struct pnfs_layout_hdr *lo, i_size = i_size_read(ino); - lgp->args.minlength = PAGE_CACHE_SIZE; + lgp->args.minlength = PAGE_SIZE; if (lgp->args.minlength > range->length) lgp->args.minlength = range->length; if (range->iomode == IOMODE_READ) { @@ -1618,13 +1618,13 @@ lookup_again: spin_unlock(&clp->cl_lock); } - pg_offset = arg.offset & ~PAGE_CACHE_MASK; + pg_offset = arg.offset & ~PAGE_MASK; if (pg_offset) { arg.offset -= pg_offset; arg.length += pg_offset; } if (arg.length != NFS4_MAX_UINT64) - arg.length = PAGE_CACHE_ALIGN(arg.length); + arg.length = PAGE_ALIGN(arg.length); lseg = send_layoutget(lo, ctx, &arg, gfp_flags); atomic_dec(&lo->plh_outstanding); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index eb31e23e7def..6776d7a7839e 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -46,7 +46,7 @@ static void nfs_readhdr_free(struct nfs_pgio_header *rhdr) static int nfs_return_empty_page(struct page *page) { - zero_user(page, 0, PAGE_CACHE_SIZE); + zero_user(page, 0, PAGE_SIZE); SetPageUptodate(page); unlock_page(page); return 0; @@ -118,8 +118,8 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, unlock_page(page); return PTR_ERR(new); } - if (len < PAGE_CACHE_SIZE) - zero_user_segment(page, len, PAGE_CACHE_SIZE); + if (len < PAGE_SIZE) + zero_user_segment(page, len, PAGE_SIZE); nfs_pageio_init_read(&pgio, inode, false, &nfs_async_read_completion_ops); @@ -295,7 +295,7 @@ int nfs_readpage(struct file *file, struct page *page) int error; dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", - page, PAGE_CACHE_SIZE, page_file_index(page)); + page, PAGE_SIZE, page_file_index(page)); nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); nfs_add_stats(inode, NFSIOS_READPAGES, 1); @@ -361,8 +361,8 @@ readpage_async_filler(void *data, struct page *page) if (IS_ERR(new)) goto out_error; - if (len < PAGE_CACHE_SIZE) - zero_user_segment(page, len, PAGE_CACHE_SIZE); + if (len < PAGE_SIZE) + zero_user_segment(page, len, PAGE_SIZE); if (!nfs_pageio_add_request(desc->pgio, new)) { nfs_list_remove_request(new); nfs_readpage_release(new); @@ -424,8 +424,8 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, pgm = &pgio.pg_mirrors[0]; NFS_I(inode)->read_io += pgm->pg_bytes_written; - npages = (pgm->pg_bytes_written + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >> + PAGE_SHIFT; nfs_add_stats(inode, NFSIOS_READPAGES, npages); read_complete: put_nfs_open_context(desc.ctx); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5754835a2886..5f4fd53e5764 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -150,7 +150,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c spin_lock(&inode->i_lock); i_size = i_size_read(inode); - end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; + end_index = (i_size - 1) >> PAGE_SHIFT; if (i_size > 0 && page_file_index(page) < end_index) goto out; end = page_file_offset(page) + ((loff_t)offset+count); @@ -1942,7 +1942,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder) { loff_t range_start = page_file_offset(page); - loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1); + loff_t range_end = range_start + (loff_t)(PAGE_SIZE - 1); struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = 0, diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index 27f75bcbeb30..a9fb3636c142 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -458,7 +458,7 @@ __u64 nilfs_bmap_data_get_key(const struct nilfs_bmap *bmap, struct buffer_head *pbh; __u64 key; - key = page_index(bh->b_page) << (PAGE_CACHE_SHIFT - + key = page_index(bh->b_page) << (PAGE_SHIFT - bmap->b_inode->i_blkbits); for (pbh = page_buffers(bh->b_page); pbh != bh; pbh = pbh->b_this_page) key++; diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index a35ae35e6932..e0c9daf9aa22 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -62,7 +62,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) set_buffer_uptodate(bh); unlock_page(bh->b_page); - page_cache_release(bh->b_page); + put_page(bh->b_page); return bh; } @@ -128,7 +128,7 @@ found: out_locked: unlock_page(page); - page_cache_release(page); + put_page(page); return err; } @@ -146,7 +146,7 @@ void nilfs_btnode_delete(struct buffer_head *bh) pgoff_t index = page_index(page); int still_dirty; - page_cache_get(page); + get_page(page); lock_page(page); wait_on_page_writeback(page); @@ -154,7 +154,7 @@ void nilfs_btnode_delete(struct buffer_head *bh) still_dirty = PageDirty(page); mapping = page->mapping; unlock_page(page); - page_cache_release(page); + put_page(page); if (!still_dirty && mapping) invalidate_inode_pages2_range(mapping, index, index); @@ -181,7 +181,7 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, obh = ctxt->bh; ctxt->newbh = NULL; - if (inode->i_blkbits == PAGE_CACHE_SHIFT) { + if (inode->i_blkbits == PAGE_SHIFT) { lock_page(obh->b_page); /* * We cannot call radix_tree_preload for the kernels older diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 6b8b92b19cec..e08f064e4bd7 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -58,7 +58,7 @@ static inline unsigned nilfs_chunk_size(struct inode *inode) static inline void nilfs_put_page(struct page *page) { kunmap(page); - page_cache_release(page); + put_page(page); } /* @@ -69,9 +69,9 @@ static unsigned nilfs_last_byte(struct inode *inode, unsigned long page_nr) { unsigned last_byte = inode->i_size; - last_byte -= page_nr << PAGE_CACHE_SHIFT; - if (last_byte > PAGE_CACHE_SIZE) - last_byte = PAGE_CACHE_SIZE; + last_byte -= page_nr << PAGE_SHIFT; + if (last_byte > PAGE_SIZE) + last_byte = PAGE_SIZE; return last_byte; } @@ -109,12 +109,12 @@ static void nilfs_check_page(struct page *page) unsigned chunk_size = nilfs_chunk_size(dir); char *kaddr = page_address(page); unsigned offs, rec_len; - unsigned limit = PAGE_CACHE_SIZE; + unsigned limit = PAGE_SIZE; struct nilfs_dir_entry *p; char *error; - if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) { - limit = dir->i_size & ~PAGE_CACHE_MASK; + if ((dir->i_size >> PAGE_SHIFT) == page->index) { + limit = dir->i_size & ~PAGE_MASK; if (limit & (chunk_size - 1)) goto Ebadsize; if (!limit) @@ -161,7 +161,7 @@ Espan: bad_entry: nilfs_error(sb, "nilfs_check_page", "bad entry in directory #%lu: %s - " "offset=%lu, inode=%lu, rec_len=%d, name_len=%d", - dir->i_ino, error, (page->index<i_ino, error, (page->index<inode), rec_len, p->name_len); goto fail; @@ -170,7 +170,7 @@ Eend: nilfs_error(sb, "nilfs_check_page", "entry in directory #%lu spans the page boundary" "offset=%lu, inode=%lu", - dir->i_ino, (page->index<i_ino, (page->index<inode)); fail: SetPageChecked(page); @@ -256,8 +256,8 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx) loff_t pos = ctx->pos; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; - unsigned int offset = pos & ~PAGE_CACHE_MASK; - unsigned long n = pos >> PAGE_CACHE_SHIFT; + unsigned int offset = pos & ~PAGE_MASK; + unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); /* unsigned chunk_mask = ~(nilfs_chunk_size(inode)-1); */ @@ -272,7 +272,7 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx) if (IS_ERR(page)) { nilfs_error(sb, __func__, "bad page in #%lu", inode->i_ino); - ctx->pos += PAGE_CACHE_SIZE - offset; + ctx->pos += PAGE_SIZE - offset; return -EIO; } kaddr = page_address(page); @@ -361,7 +361,7 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr, if (++n >= npages) n = 0; /* next page is past the blocks we've got */ - if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) { + if (unlikely(n > (dir->i_blocks >> (PAGE_SHIFT - 9)))) { nilfs_error(dir->i_sb, __func__, "dir %lu size %lld exceeds block count %llu", dir->i_ino, dir->i_size, @@ -401,7 +401,7 @@ ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr) if (de) { res = le64_to_cpu(de->inode); kunmap(page); - page_cache_release(page); + put_page(page); } return res; } @@ -460,7 +460,7 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode) kaddr = page_address(page); dir_end = kaddr + nilfs_last_byte(dir, n); de = (struct nilfs_dir_entry *)kaddr; - kaddr += PAGE_CACHE_SIZE - reclen; + kaddr += PAGE_SIZE - reclen; while ((char *)de <= kaddr) { if ((char *)de == dir_end) { /* We hit i_size */ @@ -603,7 +603,7 @@ int nilfs_make_empty(struct inode *inode, struct inode *parent) kunmap_atomic(kaddr); nilfs_commit_chunk(page, mapping, 0, chunk_size); fail: - page_cache_release(page); + put_page(page); return err; } diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 748ca238915a..0224b7826ace 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -115,7 +115,7 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, failed: unlock_page(bh->b_page); - page_cache_release(bh->b_page); + put_page(bh->b_page); return err; } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 21a1e2e0d92f..534631358b13 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -249,7 +249,7 @@ static int nilfs_set_page_dirty(struct page *page) if (nr_dirty) nilfs_set_file_dirty(inode, nr_dirty); } else if (ret) { - unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits); + unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits); nilfs_set_file_dirty(inode, nr_dirty); } @@ -291,7 +291,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = mapping->host; - unsigned start = pos & (PAGE_CACHE_SIZE - 1); + unsigned start = pos & (PAGE_SIZE - 1); unsigned nr_dirty; int err; diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 1125f40233ff..f6982b9153d5 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -110,7 +110,7 @@ static int nilfs_mdt_create_block(struct inode *inode, unsigned long block, failed_bh: unlock_page(bh->b_page); - page_cache_release(bh->b_page); + put_page(bh->b_page); brelse(bh); failed_unlock: @@ -170,7 +170,7 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff, failed_bh: unlock_page(bh->b_page); - page_cache_release(bh->b_page); + put_page(bh->b_page); brelse(bh); failed: return ret; @@ -363,7 +363,7 @@ int nilfs_mdt_delete_block(struct inode *inode, unsigned long block) int nilfs_mdt_forget_block(struct inode *inode, unsigned long block) { pgoff_t index = (pgoff_t)block >> - (PAGE_CACHE_SHIFT - inode->i_blkbits); + (PAGE_SHIFT - inode->i_blkbits); struct page *page; unsigned long first_block; int ret = 0; @@ -376,7 +376,7 @@ int nilfs_mdt_forget_block(struct inode *inode, unsigned long block) wait_on_page_writeback(page); first_block = (unsigned long)index << - (PAGE_CACHE_SHIFT - inode->i_blkbits); + (PAGE_SHIFT - inode->i_blkbits); if (page_has_buffers(page)) { struct buffer_head *bh; @@ -385,7 +385,7 @@ int nilfs_mdt_forget_block(struct inode *inode, unsigned long block) } still_dirty = PageDirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); if (still_dirty || invalidate_inode_pages2_range(inode->i_mapping, index, index) != 0) @@ -578,7 +578,7 @@ int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh) } unlock_page(page); - page_cache_release(page); + put_page(page); return 0; } @@ -597,7 +597,7 @@ nilfs_mdt_get_frozen_buffer(struct inode *inode, struct buffer_head *bh) bh_frozen = nilfs_page_get_nth_block(page, n); } unlock_page(page); - page_cache_release(page); + put_page(page); } return bh_frozen; } diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 7ccdb961eea9..151bc19d47c0 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -431,11 +431,11 @@ static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry, out_dir: if (dir_de) { kunmap(dir_page); - page_cache_release(dir_page); + put_page(dir_page); } out_old: kunmap(old_page); - page_cache_release(old_page); + put_page(old_page); out: nilfs_transaction_abort(old_dir->i_sb); return err; diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index c20df77eff99..489391561cda 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -50,7 +50,7 @@ __nilfs_get_page_block(struct page *page, unsigned long block, pgoff_t index, if (!page_has_buffers(page)) create_empty_buffers(page, 1 << blkbits, b_state); - first_block = (unsigned long)index << (PAGE_CACHE_SHIFT - blkbits); + first_block = (unsigned long)index << (PAGE_SHIFT - blkbits); bh = nilfs_page_get_nth_block(page, block - first_block); touch_buffer(bh); @@ -64,7 +64,7 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode, unsigned long b_state) { int blkbits = inode->i_blkbits; - pgoff_t index = blkoff >> (PAGE_CACHE_SHIFT - blkbits); + pgoff_t index = blkoff >> (PAGE_SHIFT - blkbits); struct page *page; struct buffer_head *bh; @@ -75,7 +75,7 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode, bh = __nilfs_get_page_block(page, blkoff, index, blkbits, b_state); if (unlikely(!bh)) { unlock_page(page); - page_cache_release(page); + put_page(page); return NULL; } return bh; @@ -288,7 +288,7 @@ repeat: __set_page_dirty_nobuffers(dpage); unlock_page(dpage); - page_cache_release(dpage); + put_page(dpage); unlock_page(page); } pagevec_release(&pvec); @@ -333,7 +333,7 @@ repeat: WARN_ON(PageDirty(dpage)); nilfs_copy_page(dpage, page, 0); unlock_page(dpage); - page_cache_release(dpage); + put_page(dpage); } else { struct page *page2; @@ -350,7 +350,7 @@ repeat: if (unlikely(err < 0)) { WARN_ON(err == -EEXIST); page->mapping = NULL; - page_cache_release(page); /* for cache */ + put_page(page); /* for cache */ } else { page->mapping = dmap; dmap->nrpages++; @@ -523,8 +523,8 @@ unsigned long nilfs_find_uncommitted_extent(struct inode *inode, if (inode->i_mapping->nrpages == 0) return 0; - index = start_blk >> (PAGE_CACHE_SHIFT - inode->i_blkbits); - nblocks_in_page = 1U << (PAGE_CACHE_SHIFT - inode->i_blkbits); + index = start_blk >> (PAGE_SHIFT - inode->i_blkbits); + nblocks_in_page = 1U << (PAGE_SHIFT - inode->i_blkbits); pagevec_init(&pvec, 0); @@ -537,7 +537,7 @@ repeat: if (length > 0 && pvec.pages[0]->index > index) goto out; - b = pvec.pages[0]->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + b = pvec.pages[0]->index << (PAGE_SHIFT - inode->i_blkbits); i = 0; do { page = pvec.pages[i]; diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 9b4f205d1173..5afa77fadc11 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -544,14 +544,14 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, blocksize, page, NULL); unlock_page(page); - page_cache_release(page); + put_page(page); (*nr_salvaged_blocks)++; goto next; failed_page: unlock_page(page); - page_cache_release(page); + put_page(page); failed_inode: printk(KERN_WARNING diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 3b65adaae7e4..4317f72568e6 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2070,7 +2070,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) goto failed_to_write; if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE || - nilfs->ns_blocksize_bits != PAGE_CACHE_SHIFT) { + nilfs->ns_blocksize_bits != PAGE_SHIFT) { /* * At this point, we avoid double buffering * for blocksize < pagesize because page dirty diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index 7521e11db728..a474e7ef92ea 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -74,7 +74,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) set_buffer_uptodate(bh); - file_ofs = ((s64)page->index << PAGE_CACHE_SHIFT) + + file_ofs = ((s64)page->index << PAGE_SHIFT) + bh_offset(bh); read_lock_irqsave(&ni->size_lock, flags); init_size = ni->initialized_size; @@ -142,7 +142,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) u32 rec_size; rec_size = ni->itype.index.block_size; - recs = PAGE_CACHE_SIZE / rec_size; + recs = PAGE_SIZE / rec_size; /* Should have been verified before we got here... */ BUG_ON(!recs); local_irq_save(flags); @@ -229,7 +229,7 @@ static int ntfs_read_block(struct page *page) * fully truncated, truncate will throw it away as soon as we unlock * it so no need to worry what we do with it. */ - iblock = (s64)page->index << (PAGE_CACHE_SHIFT - blocksize_bits); + iblock = (s64)page->index << (PAGE_SHIFT - blocksize_bits); read_lock_irqsave(&ni->size_lock, flags); lblock = (ni->allocated_size + blocksize - 1) >> blocksize_bits; init_size = ni->initialized_size; @@ -412,9 +412,9 @@ retry_readpage: vi = page->mapping->host; i_size = i_size_read(vi); /* Is the page fully outside i_size? (truncate in progress) */ - if (unlikely(page->index >= (i_size + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT)) { - zero_user(page, 0, PAGE_CACHE_SIZE); + if (unlikely(page->index >= (i_size + PAGE_SIZE - 1) >> + PAGE_SHIFT)) { + zero_user(page, 0, PAGE_SIZE); ntfs_debug("Read outside i_size - truncated?"); goto done; } @@ -463,7 +463,7 @@ retry_readpage: * ok to ignore the compressed flag here. */ if (unlikely(page->index > 0)) { - zero_user(page, 0, PAGE_CACHE_SIZE); + zero_user(page, 0, PAGE_SIZE); goto done; } if (!NInoAttr(ni)) @@ -509,7 +509,7 @@ retry_readpage: le16_to_cpu(ctx->attr->data.resident.value_offset), attr_len); /* Zero the remainder of the page. */ - memset(addr + attr_len, 0, PAGE_CACHE_SIZE - attr_len); + memset(addr + attr_len, 0, PAGE_SIZE - attr_len); flush_dcache_page(page); kunmap_atomic(addr); put_unm_err_out: @@ -599,7 +599,7 @@ static int ntfs_write_block(struct page *page, struct writeback_control *wbc) /* NOTE: Different naming scheme to ntfs_read_block()! */ /* The first block in the page. */ - block = (s64)page->index << (PAGE_CACHE_SHIFT - blocksize_bits); + block = (s64)page->index << (PAGE_SHIFT - blocksize_bits); read_lock_irqsave(&ni->size_lock, flags); i_size = i_size_read(vi); @@ -925,7 +925,7 @@ static int ntfs_write_mst_block(struct page *page, ntfs_volume *vol = ni->vol; u8 *kaddr; unsigned int rec_size = ni->itype.index.block_size; - ntfs_inode *locked_nis[PAGE_CACHE_SIZE / rec_size]; + ntfs_inode *locked_nis[PAGE_SIZE / rec_size]; struct buffer_head *bh, *head, *tbh, *rec_start_bh; struct buffer_head *bhs[MAX_BUF_PER_PAGE]; runlist_element *rl; @@ -949,7 +949,7 @@ static int ntfs_write_mst_block(struct page *page, (NInoAttr(ni) && ni->type == AT_INDEX_ALLOCATION))); bh_size = vol->sb->s_blocksize; bh_size_bits = vol->sb->s_blocksize_bits; - max_bhs = PAGE_CACHE_SIZE / bh_size; + max_bhs = PAGE_SIZE / bh_size; BUG_ON(!max_bhs); BUG_ON(max_bhs > MAX_BUF_PER_PAGE); @@ -961,13 +961,13 @@ static int ntfs_write_mst_block(struct page *page, BUG_ON(!bh); rec_size_bits = ni->itype.index.block_size_bits; - BUG_ON(!(PAGE_CACHE_SIZE >> rec_size_bits)); + BUG_ON(!(PAGE_SIZE >> rec_size_bits)); bhs_per_rec = rec_size >> bh_size_bits; BUG_ON(!bhs_per_rec); /* The first block in the page. */ rec_block = block = (sector_t)page->index << - (PAGE_CACHE_SHIFT - bh_size_bits); + (PAGE_SHIFT - bh_size_bits); /* The first out of bounds block for the data size. */ dblock = (i_size_read(vi) + bh_size - 1) >> bh_size_bits; @@ -1133,7 +1133,7 @@ lock_retry_remap: unsigned long mft_no; /* Get the mft record number. */ - mft_no = (((s64)page->index << PAGE_CACHE_SHIFT) + ofs) + mft_no = (((s64)page->index << PAGE_SHIFT) + ofs) >> rec_size_bits; /* Check whether to write this mft record. */ tni = NULL; @@ -1249,7 +1249,7 @@ do_mirror: continue; ofs = bh_offset(tbh); /* Get the mft record number. */ - mft_no = (((s64)page->index << PAGE_CACHE_SHIFT) + ofs) + mft_no = (((s64)page->index << PAGE_SHIFT) + ofs) >> rec_size_bits; if (mft_no < vol->mftmirr_size) ntfs_sync_mft_mirror(vol, mft_no, @@ -1300,7 +1300,7 @@ done: * Set page error if there is only one ntfs record in the page. * Otherwise we would loose per-record granularity. */ - if (ni->itype.index.block_size == PAGE_CACHE_SIZE) + if (ni->itype.index.block_size == PAGE_SIZE) SetPageError(page); NVolSetErrors(vol); } @@ -1308,7 +1308,7 @@ done: ntfs_debug("Page still contains one or more dirty ntfs " "records. Redirtying the page starting at " "record 0x%lx.", page->index << - (PAGE_CACHE_SHIFT - rec_size_bits)); + (PAGE_SHIFT - rec_size_bits)); redirty_page_for_writepage(wbc, page); unlock_page(page); } else { @@ -1365,13 +1365,13 @@ retry_writepage: BUG_ON(!PageLocked(page)); i_size = i_size_read(vi); /* Is the page fully outside i_size? (truncate in progress) */ - if (unlikely(page->index >= (i_size + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT)) { + if (unlikely(page->index >= (i_size + PAGE_SIZE - 1) >> + PAGE_SHIFT)) { /* * The page may have dirty, unmapped buffers. Make them * freeable here, so the page does not leak. */ - block_invalidatepage(page, 0, PAGE_CACHE_SIZE); + block_invalidatepage(page, 0, PAGE_SIZE); unlock_page(page); ntfs_debug("Write outside i_size - truncated?"); return 0; @@ -1414,10 +1414,10 @@ retry_writepage: /* NInoNonResident() == NInoIndexAllocPresent() */ if (NInoNonResident(ni)) { /* We have to zero every time due to mmap-at-end-of-file. */ - if (page->index >= (i_size >> PAGE_CACHE_SHIFT)) { + if (page->index >= (i_size >> PAGE_SHIFT)) { /* The page straddles i_size. */ - unsigned int ofs = i_size & ~PAGE_CACHE_MASK; - zero_user_segment(page, ofs, PAGE_CACHE_SIZE); + unsigned int ofs = i_size & ~PAGE_MASK; + zero_user_segment(page, ofs, PAGE_SIZE); } /* Handle mst protected attributes. */ if (NInoMstProtected(ni)) @@ -1500,7 +1500,7 @@ retry_writepage: le16_to_cpu(ctx->attr->data.resident.value_offset), addr, attr_len); /* Zero out of bounds area in the page cache page. */ - memset(addr + attr_len, 0, PAGE_CACHE_SIZE - attr_len); + memset(addr + attr_len, 0, PAGE_SIZE - attr_len); kunmap_atomic(addr); flush_dcache_page(page); flush_dcache_mft_record_page(ctx->ntfs_ino); diff --git a/fs/ntfs/aops.h b/fs/ntfs/aops.h index caecc58f529c..37cd7e45dcbc 100644 --- a/fs/ntfs/aops.h +++ b/fs/ntfs/aops.h @@ -40,7 +40,7 @@ static inline void ntfs_unmap_page(struct page *page) { kunmap(page); - page_cache_release(page); + put_page(page); } /** diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 250ed5b20c8f..44a39a099b54 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -152,7 +152,7 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx) if (old_ctx.base_ntfs_ino && old_ctx.ntfs_ino != old_ctx.base_ntfs_ino) { put_this_page = old_ctx.ntfs_ino->page; - page_cache_get(put_this_page); + get_page(put_this_page); } /* * Reinitialize the search context so we can lookup the @@ -275,7 +275,7 @@ retry_map: * the pieces anyway. */ if (put_this_page) - page_cache_release(put_this_page); + put_page(put_this_page); } return err; } @@ -1660,7 +1660,7 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) memcpy(kaddr, (u8*)a + le16_to_cpu(a->data.resident.value_offset), attr_size); - memset(kaddr + attr_size, 0, PAGE_CACHE_SIZE - attr_size); + memset(kaddr + attr_size, 0, PAGE_SIZE - attr_size); kunmap_atomic(kaddr); flush_dcache_page(page); SetPageUptodate(page); @@ -1748,7 +1748,7 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) if (page) { set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); } ntfs_debug("Done."); return 0; @@ -1835,7 +1835,7 @@ rl_err_out: ntfs_free(rl); page_err_out: unlock_page(page); - page_cache_release(page); + put_page(page); } if (err == -EINVAL) err = -EIO; @@ -2513,17 +2513,17 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val) BUG_ON(NInoEncrypted(ni)); mapping = VFS_I(ni)->i_mapping; /* Work out the starting index and page offset. */ - idx = ofs >> PAGE_CACHE_SHIFT; - start_ofs = ofs & ~PAGE_CACHE_MASK; + idx = ofs >> PAGE_SHIFT; + start_ofs = ofs & ~PAGE_MASK; /* Work out the ending index and page offset. */ end = ofs + cnt; - end_ofs = end & ~PAGE_CACHE_MASK; + end_ofs = end & ~PAGE_MASK; /* If the end is outside the inode size return -ESPIPE. */ if (unlikely(end > i_size_read(VFS_I(ni)))) { ntfs_error(vol->sb, "Request exceeds end of attribute."); return -ESPIPE; } - end >>= PAGE_CACHE_SHIFT; + end >>= PAGE_SHIFT; /* If there is a first partial page, need to do it the slow way. */ if (start_ofs) { page = read_mapping_page(mapping, idx, NULL); @@ -2536,7 +2536,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val) * If the last page is the same as the first page, need to * limit the write to the end offset. */ - size = PAGE_CACHE_SIZE; + size = PAGE_SIZE; if (idx == end) size = end_ofs; kaddr = kmap_atomic(page); @@ -2544,7 +2544,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val) flush_dcache_page(page); kunmap_atomic(kaddr); set_page_dirty(page); - page_cache_release(page); + put_page(page); balance_dirty_pages_ratelimited(mapping); cond_resched(); if (idx == end) @@ -2561,7 +2561,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val) return -ENOMEM; } kaddr = kmap_atomic(page); - memset(kaddr, val, PAGE_CACHE_SIZE); + memset(kaddr, val, PAGE_SIZE); flush_dcache_page(page); kunmap_atomic(kaddr); /* @@ -2585,7 +2585,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val) set_page_dirty(page); /* Finally unlock and release the page. */ unlock_page(page); - page_cache_release(page); + put_page(page); balance_dirty_pages_ratelimited(mapping); cond_resched(); } @@ -2602,7 +2602,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val) flush_dcache_page(page); kunmap_atomic(kaddr); set_page_dirty(page); - page_cache_release(page); + put_page(page); balance_dirty_pages_ratelimited(mapping); cond_resched(); } diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c index 0809cf876098..ec130c588d2b 100644 --- a/fs/ntfs/bitmap.c +++ b/fs/ntfs/bitmap.c @@ -67,8 +67,8 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit, * Calculate the indices for the pages containing the first and last * bits, i.e. @start_bit and @start_bit + @cnt - 1, respectively. */ - index = start_bit >> (3 + PAGE_CACHE_SHIFT); - end_index = (start_bit + cnt - 1) >> (3 + PAGE_CACHE_SHIFT); + index = start_bit >> (3 + PAGE_SHIFT); + end_index = (start_bit + cnt - 1) >> (3 + PAGE_SHIFT); /* Get the page containing the first bit (@start_bit). */ mapping = vi->i_mapping; @@ -82,7 +82,7 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit, kaddr = page_address(page); /* Set @pos to the position of the byte containing @start_bit. */ - pos = (start_bit >> 3) & ~PAGE_CACHE_MASK; + pos = (start_bit >> 3) & ~PAGE_MASK; /* Calculate the position of @start_bit in the first byte. */ bit = start_bit & 7; @@ -108,7 +108,7 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit, * Depending on @value, modify all remaining whole bytes in the page up * to @cnt. */ - len = min_t(s64, cnt >> 3, PAGE_CACHE_SIZE - pos); + len = min_t(s64, cnt >> 3, PAGE_SIZE - pos); memset(kaddr + pos, value ? 0xff : 0, len); cnt -= len << 3; @@ -132,7 +132,7 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit, * Depending on @value, modify all remaining whole bytes in the * page up to @cnt. */ - len = min_t(s64, cnt >> 3, PAGE_CACHE_SIZE); + len = min_t(s64, cnt >> 3, PAGE_SIZE); memset(kaddr, value ? 0xff : 0, len); cnt -= len << 3; } diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index f82498c35e78..b6074a56661b 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -104,7 +104,7 @@ static void zero_partial_compressed_page(struct page *page, unsigned int kp_ofs; ntfs_debug("Zeroing page region outside initialized size."); - if (((s64)page->index << PAGE_CACHE_SHIFT) >= initialized_size) { + if (((s64)page->index << PAGE_SHIFT) >= initialized_size) { /* * FIXME: Using clear_page() will become wrong when we get * PAGE_CACHE_SIZE != PAGE_SIZE but for now there is no problem. @@ -112,8 +112,8 @@ static void zero_partial_compressed_page(struct page *page, clear_page(kp); return; } - kp_ofs = initialized_size & ~PAGE_CACHE_MASK; - memset(kp + kp_ofs, 0, PAGE_CACHE_SIZE - kp_ofs); + kp_ofs = initialized_size & ~PAGE_MASK; + memset(kp + kp_ofs, 0, PAGE_SIZE - kp_ofs); return; } @@ -123,7 +123,7 @@ static void zero_partial_compressed_page(struct page *page, static inline void handle_bounds_compressed_page(struct page *page, const loff_t i_size, const s64 initialized_size) { - if ((page->index >= (initialized_size >> PAGE_CACHE_SHIFT)) && + if ((page->index >= (initialized_size >> PAGE_SHIFT)) && (initialized_size < i_size)) zero_partial_compressed_page(page, initialized_size); return; @@ -241,7 +241,7 @@ return_error: if (di == xpage) *xpage_done = 1; else - page_cache_release(dp); + put_page(dp); dest_pages[di] = NULL; } } @@ -274,7 +274,7 @@ return_error: cb = cb_sb_end; /* Advance destination position to next sub-block. */ - *dest_ofs = (*dest_ofs + NTFS_SB_SIZE) & ~PAGE_CACHE_MASK; + *dest_ofs = (*dest_ofs + NTFS_SB_SIZE) & ~PAGE_MASK; if (!*dest_ofs && (++*dest_index > dest_max_index)) goto return_overflow; goto do_next_sb; @@ -301,7 +301,7 @@ return_error: /* Advance destination position to next sub-block. */ *dest_ofs += NTFS_SB_SIZE; - if (!(*dest_ofs &= ~PAGE_CACHE_MASK)) { + if (!(*dest_ofs &= ~PAGE_MASK)) { finalize_page: /* * First stage: add current page index to array of @@ -335,7 +335,7 @@ do_next_tag: *dest_ofs += nr_bytes; } /* We have finished the current sub-block. */ - if (!(*dest_ofs &= ~PAGE_CACHE_MASK)) + if (!(*dest_ofs &= ~PAGE_MASK)) goto finalize_page; goto do_next_sb; } @@ -498,13 +498,13 @@ int ntfs_read_compressed_block(struct page *page) VCN vcn; LCN lcn; /* The first wanted vcn (minimum alignment is PAGE_CACHE_SIZE). */ - VCN start_vcn = (((s64)index << PAGE_CACHE_SHIFT) & ~cb_size_mask) >> + VCN start_vcn = (((s64)index << PAGE_SHIFT) & ~cb_size_mask) >> vol->cluster_size_bits; /* * The first vcn after the last wanted vcn (minimum alignment is again * PAGE_CACHE_SIZE. */ - VCN end_vcn = ((((s64)(index + 1UL) << PAGE_CACHE_SHIFT) + cb_size - 1) + VCN end_vcn = ((((s64)(index + 1UL) << PAGE_SHIFT) + cb_size - 1) & ~cb_size_mask) >> vol->cluster_size_bits; /* Number of compression blocks (cbs) in the wanted vcn range. */ unsigned int nr_cbs = (end_vcn - start_vcn) << vol->cluster_size_bits @@ -515,7 +515,7 @@ int ntfs_read_compressed_block(struct page *page) * guarantees of start_vcn and end_vcn, no need to round up here. */ unsigned int nr_pages = (end_vcn - start_vcn) << - vol->cluster_size_bits >> PAGE_CACHE_SHIFT; + vol->cluster_size_bits >> PAGE_SHIFT; unsigned int xpage, max_page, cur_page, cur_ofs, i; unsigned int cb_clusters, cb_max_ofs; int block, max_block, cb_max_page, bhs_size, nr_bhs, err = 0; @@ -549,7 +549,7 @@ int ntfs_read_compressed_block(struct page *page) * We have already been given one page, this is the one we must do. * Once again, the alignment guarantees keep it simple. */ - offset = start_vcn << vol->cluster_size_bits >> PAGE_CACHE_SHIFT; + offset = start_vcn << vol->cluster_size_bits >> PAGE_SHIFT; xpage = index - offset; pages[xpage] = page; /* @@ -560,13 +560,13 @@ int ntfs_read_compressed_block(struct page *page) i_size = i_size_read(VFS_I(ni)); initialized_size = ni->initialized_size; read_unlock_irqrestore(&ni->size_lock, flags); - max_page = ((i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT) - + max_page = ((i_size + PAGE_SIZE - 1) >> PAGE_SHIFT) - offset; /* Is the page fully outside i_size? (truncate in progress) */ if (xpage >= max_page) { kfree(bhs); kfree(pages); - zero_user(page, 0, PAGE_CACHE_SIZE); + zero_user(page, 0, PAGE_SIZE); ntfs_debug("Compressed read outside i_size - truncated?"); SetPageUptodate(page); unlock_page(page); @@ -591,7 +591,7 @@ int ntfs_read_compressed_block(struct page *page) continue; } unlock_page(page); - page_cache_release(page); + put_page(page); pages[i] = NULL; } } @@ -735,9 +735,9 @@ lock_retry_remap: ntfs_debug("Successfully read the compression block."); /* The last page and maximum offset within it for the current cb. */ - cb_max_page = (cur_page << PAGE_CACHE_SHIFT) + cur_ofs + cb_size; - cb_max_ofs = cb_max_page & ~PAGE_CACHE_MASK; - cb_max_page >>= PAGE_CACHE_SHIFT; + cb_max_page = (cur_page << PAGE_SHIFT) + cur_ofs + cb_size; + cb_max_ofs = cb_max_page & ~PAGE_MASK; + cb_max_page >>= PAGE_SHIFT; /* Catch end of file inside a compression block. */ if (cb_max_page > max_page) @@ -762,7 +762,7 @@ lock_retry_remap: clear_page(page_address(page)); else memset(page_address(page) + cur_ofs, 0, - PAGE_CACHE_SIZE - + PAGE_SIZE - cur_ofs); flush_dcache_page(page); kunmap(page); @@ -771,10 +771,10 @@ lock_retry_remap: if (cur_page == xpage) xpage_done = 1; else - page_cache_release(page); + put_page(page); pages[cur_page] = NULL; } - cb_pos += PAGE_CACHE_SIZE - cur_ofs; + cb_pos += PAGE_SIZE - cur_ofs; cur_ofs = 0; if (cb_pos >= cb_end) break; @@ -816,8 +816,8 @@ lock_retry_remap: page = pages[cur_page]; if (page) memcpy(page_address(page) + cur_ofs, cb_pos, - PAGE_CACHE_SIZE - cur_ofs); - cb_pos += PAGE_CACHE_SIZE - cur_ofs; + PAGE_SIZE - cur_ofs); + cb_pos += PAGE_SIZE - cur_ofs; cur_ofs = 0; if (cb_pos >= cb_end) break; @@ -850,10 +850,10 @@ lock_retry_remap: if (cur2_page == xpage) xpage_done = 1; else - page_cache_release(page); + put_page(page); pages[cur2_page] = NULL; } - cb_pos2 += PAGE_CACHE_SIZE - cur_ofs2; + cb_pos2 += PAGE_SIZE - cur_ofs2; cur_ofs2 = 0; if (cb_pos2 >= cb_end) break; @@ -884,7 +884,7 @@ lock_retry_remap: kunmap(page); unlock_page(page); if (prev_cur_page != xpage) - page_cache_release(page); + put_page(page); pages[prev_cur_page] = NULL; } } @@ -914,7 +914,7 @@ lock_retry_remap: kunmap(page); unlock_page(page); if (cur_page != xpage) - page_cache_release(page); + put_page(page); pages[cur_page] = NULL; } } @@ -961,7 +961,7 @@ err_out: kunmap(page); unlock_page(page); if (i != xpage) - page_cache_release(page); + put_page(page); } } kfree(pages); diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index b2eff5816adc..3cdce162592d 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -319,7 +319,7 @@ descend_into_child_node: * disk if necessary. */ page = ntfs_map_page(ia_mapping, vcn << - dir_ni->itype.index.vcn_size_bits >> PAGE_CACHE_SHIFT); + dir_ni->itype.index.vcn_size_bits >> PAGE_SHIFT); if (IS_ERR(page)) { ntfs_error(sb, "Failed to map directory index page, error %ld.", -PTR_ERR(page)); @@ -331,9 +331,9 @@ descend_into_child_node: fast_descend_into_child_node: /* Get to the index allocation block. */ ia = (INDEX_ALLOCATION*)(kaddr + ((vcn << - dir_ni->itype.index.vcn_size_bits) & ~PAGE_CACHE_MASK)); + dir_ni->itype.index.vcn_size_bits) & ~PAGE_MASK)); /* Bounds checks. */ - if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_CACHE_SIZE) { + if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) { ntfs_error(sb, "Out of bounds check failed. Corrupt directory " "inode 0x%lx or driver bug.", dir_ni->mft_no); goto unm_err_out; @@ -366,7 +366,7 @@ fast_descend_into_child_node: goto unm_err_out; } index_end = (u8*)ia + dir_ni->itype.index.block_size; - if (index_end > kaddr + PAGE_CACHE_SIZE) { + if (index_end > kaddr + PAGE_SIZE) { ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode " "0x%lx crosses page boundary. Impossible! " "Cannot access! This is probably a bug in the " @@ -559,9 +559,9 @@ found_it2: /* If vcn is in the same page cache page as old_vcn we * recycle the mapped page. */ if (old_vcn << vol->cluster_size_bits >> - PAGE_CACHE_SHIFT == vcn << + PAGE_SHIFT == vcn << vol->cluster_size_bits >> - PAGE_CACHE_SHIFT) + PAGE_SHIFT) goto fast_descend_into_child_node; unlock_page(page); ntfs_unmap_page(page); @@ -1246,15 +1246,15 @@ skip_index_root: goto iput_err_out; } /* Get the starting bit position in the current bitmap page. */ - cur_bmp_pos = bmp_pos & ((PAGE_CACHE_SIZE * 8) - 1); - bmp_pos &= ~(u64)((PAGE_CACHE_SIZE * 8) - 1); + cur_bmp_pos = bmp_pos & ((PAGE_SIZE * 8) - 1); + bmp_pos &= ~(u64)((PAGE_SIZE * 8) - 1); get_next_bmp_page: ntfs_debug("Reading bitmap with page index 0x%llx, bit ofs 0x%llx", - (unsigned long long)bmp_pos >> (3 + PAGE_CACHE_SHIFT), + (unsigned long long)bmp_pos >> (3 + PAGE_SHIFT), (unsigned long long)bmp_pos & - (unsigned long long)((PAGE_CACHE_SIZE * 8) - 1)); + (unsigned long long)((PAGE_SIZE * 8) - 1)); bmp_page = ntfs_map_page(bmp_mapping, - bmp_pos >> (3 + PAGE_CACHE_SHIFT)); + bmp_pos >> (3 + PAGE_SHIFT)); if (IS_ERR(bmp_page)) { ntfs_error(sb, "Reading index bitmap failed."); err = PTR_ERR(bmp_page); @@ -1270,9 +1270,9 @@ find_next_index_buffer: * If we have reached the end of the bitmap page, get the next * page, and put away the old one. */ - if (unlikely((cur_bmp_pos >> 3) >= PAGE_CACHE_SIZE)) { + if (unlikely((cur_bmp_pos >> 3) >= PAGE_SIZE)) { ntfs_unmap_page(bmp_page); - bmp_pos += PAGE_CACHE_SIZE * 8; + bmp_pos += PAGE_SIZE * 8; cur_bmp_pos = 0; goto get_next_bmp_page; } @@ -1285,8 +1285,8 @@ find_next_index_buffer: ntfs_debug("Handling index buffer 0x%llx.", (unsigned long long)bmp_pos + cur_bmp_pos); /* If the current index buffer is in the same page we reuse the page. */ - if ((prev_ia_pos & (s64)PAGE_CACHE_MASK) != - (ia_pos & (s64)PAGE_CACHE_MASK)) { + if ((prev_ia_pos & (s64)PAGE_MASK) != + (ia_pos & (s64)PAGE_MASK)) { prev_ia_pos = ia_pos; if (likely(ia_page != NULL)) { unlock_page(ia_page); @@ -1296,7 +1296,7 @@ find_next_index_buffer: * Map the page cache page containing the current ia_pos, * reading it from disk if necessary. */ - ia_page = ntfs_map_page(ia_mapping, ia_pos >> PAGE_CACHE_SHIFT); + ia_page = ntfs_map_page(ia_mapping, ia_pos >> PAGE_SHIFT); if (IS_ERR(ia_page)) { ntfs_error(sb, "Reading index allocation data failed."); err = PTR_ERR(ia_page); @@ -1307,10 +1307,10 @@ find_next_index_buffer: kaddr = (u8*)page_address(ia_page); } /* Get the current index buffer. */ - ia = (INDEX_ALLOCATION*)(kaddr + (ia_pos & ~PAGE_CACHE_MASK & - ~(s64)(ndir->itype.index.block_size - 1))); + ia = (INDEX_ALLOCATION*)(kaddr + (ia_pos & ~PAGE_MASK & + ~(s64)(ndir->itype.index.block_size - 1))); /* Bounds checks. */ - if (unlikely((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_CACHE_SIZE)) { + if (unlikely((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE)) { ntfs_error(sb, "Out of bounds check failed. Corrupt directory " "inode 0x%lx or driver bug.", vdir->i_ino); goto err_out; @@ -1348,7 +1348,7 @@ find_next_index_buffer: goto err_out; } index_end = (u8*)ia + ndir->itype.index.block_size; - if (unlikely(index_end > kaddr + PAGE_CACHE_SIZE)) { + if (unlikely(index_end > kaddr + PAGE_SIZE)) { ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode " "0x%lx crosses page boundary. Impossible! " "Cannot access! This is probably a bug in the " diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index bed4d427dfae..2dae60857544 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -220,8 +220,8 @@ do_non_resident_extend: m = NULL; } mapping = vi->i_mapping; - index = old_init_size >> PAGE_CACHE_SHIFT; - end_index = (new_init_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + index = old_init_size >> PAGE_SHIFT; + end_index = (new_init_size + PAGE_SIZE - 1) >> PAGE_SHIFT; do { /* * Read the page. If the page is not present, this will zero @@ -233,7 +233,7 @@ do_non_resident_extend: goto init_err_out; } if (unlikely(PageError(page))) { - page_cache_release(page); + put_page(page); err = -EIO; goto init_err_out; } @@ -242,13 +242,13 @@ do_non_resident_extend: * enough to make ntfs_writepage() work. */ write_lock_irqsave(&ni->size_lock, flags); - ni->initialized_size = (s64)(index + 1) << PAGE_CACHE_SHIFT; + ni->initialized_size = (s64)(index + 1) << PAGE_SHIFT; if (ni->initialized_size > new_init_size) ni->initialized_size = new_init_size; write_unlock_irqrestore(&ni->size_lock, flags); /* Set the page dirty so it gets written out. */ set_page_dirty(page); - page_cache_release(page); + put_page(page); /* * Play nice with the vm and the rest of the system. This is * very much needed as we can potentially be modifying the @@ -543,7 +543,7 @@ out: err_out: while (nr > 0) { unlock_page(pages[--nr]); - page_cache_release(pages[nr]); + put_page(pages[nr]); } goto out; } @@ -653,7 +653,7 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages, u = 0; do_next_page: page = pages[u]; - bh_pos = (s64)page->index << PAGE_CACHE_SHIFT; + bh_pos = (s64)page->index << PAGE_SHIFT; bh = head = page_buffers(page); do { VCN cdelta; @@ -810,11 +810,11 @@ map_buffer_cached: kaddr = kmap_atomic(page); if (bh_pos < pos) { - pofs = bh_pos & ~PAGE_CACHE_MASK; + pofs = bh_pos & ~PAGE_MASK; memset(kaddr + pofs, 0, pos - bh_pos); } if (bh_end > end) { - pofs = end & ~PAGE_CACHE_MASK; + pofs = end & ~PAGE_MASK; memset(kaddr + pofs, 0, bh_end - end); } kunmap_atomic(kaddr); @@ -942,7 +942,7 @@ rl_not_mapped_enoent: * unmapped. This can only happen when the cluster size is * less than the page cache size. */ - if (unlikely(vol->cluster_size < PAGE_CACHE_SIZE)) { + if (unlikely(vol->cluster_size < PAGE_SIZE)) { bh_cend = (bh_end + vol->cluster_size - 1) >> vol->cluster_size_bits; if ((bh_cend <= cpos || bh_cpos >= cend)) { @@ -1208,7 +1208,7 @@ rl_not_mapped_enoent: wait_on_buffer(bh); if (likely(buffer_uptodate(bh))) { page = bh->b_page; - bh_pos = ((s64)page->index << PAGE_CACHE_SHIFT) + + bh_pos = ((s64)page->index << PAGE_SHIFT) + bh_offset(bh); /* * If the buffer overflows the initialized size, need @@ -1350,7 +1350,7 @@ rl_not_mapped_enoent: bh = head = page_buffers(page); do { if (u == nr_pages && - ((s64)page->index << PAGE_CACHE_SHIFT) + + ((s64)page->index << PAGE_SHIFT) + bh_offset(bh) >= end) break; if (!buffer_new(bh)) @@ -1422,7 +1422,7 @@ static inline int ntfs_commit_pages_after_non_resident_write( bool partial; page = pages[u]; - bh_pos = (s64)page->index << PAGE_CACHE_SHIFT; + bh_pos = (s64)page->index << PAGE_SHIFT; bh = head = page_buffers(page); partial = false; do { @@ -1639,7 +1639,7 @@ static int ntfs_commit_pages_after_write(struct page **pages, if (end < attr_len) memcpy(kaddr + end, kattr + end, attr_len - end); /* Zero the region outside the end of the attribute value. */ - memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len); + memset(kaddr + attr_len, 0, PAGE_SIZE - attr_len); flush_dcache_page(page); SetPageUptodate(page); } @@ -1706,7 +1706,7 @@ static size_t ntfs_copy_from_user_iter(struct page **pages, unsigned nr_pages, unsigned len, copied; do { - len = PAGE_CACHE_SIZE - ofs; + len = PAGE_SIZE - ofs; if (len > bytes) len = bytes; copied = iov_iter_copy_from_user_atomic(*pages, &data, ofs, @@ -1724,14 +1724,14 @@ out: return total; err: /* Zero the rest of the target like __copy_from_user(). */ - len = PAGE_CACHE_SIZE - copied; + len = PAGE_SIZE - copied; do { if (len > bytes) len = bytes; zero_user(*pages, copied, len); bytes -= len; copied = 0; - len = PAGE_CACHE_SIZE; + len = PAGE_SIZE; } while (++pages < last_page); goto out; } @@ -1787,8 +1787,8 @@ static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i, * attributes. */ nr_pages = 1; - if (vol->cluster_size > PAGE_CACHE_SIZE && NInoNonResident(ni)) - nr_pages = vol->cluster_size >> PAGE_CACHE_SHIFT; + if (vol->cluster_size > PAGE_SIZE && NInoNonResident(ni)) + nr_pages = vol->cluster_size >> PAGE_SHIFT; last_vcn = -1; do { VCN vcn; @@ -1796,9 +1796,9 @@ static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i, unsigned ofs, do_pages, u; size_t copied; - start_idx = idx = pos >> PAGE_CACHE_SHIFT; - ofs = pos & ~PAGE_CACHE_MASK; - bytes = PAGE_CACHE_SIZE - ofs; + start_idx = idx = pos >> PAGE_SHIFT; + ofs = pos & ~PAGE_MASK; + bytes = PAGE_SIZE - ofs; do_pages = 1; if (nr_pages > 1) { vcn = pos >> vol->cluster_size_bits; @@ -1832,7 +1832,7 @@ static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i, if (lcn == LCN_HOLE) { start_idx = (pos & ~(s64) vol->cluster_size_mask) - >> PAGE_CACHE_SHIFT; + >> PAGE_SHIFT; bytes = vol->cluster_size - (pos & vol->cluster_size_mask); do_pages = nr_pages; @@ -1871,12 +1871,12 @@ again: if (unlikely(status)) { do { unlock_page(pages[--do_pages]); - page_cache_release(pages[do_pages]); + put_page(pages[do_pages]); } while (do_pages); break; } } - u = (pos >> PAGE_CACHE_SHIFT) - pages[0]->index; + u = (pos >> PAGE_SHIFT) - pages[0]->index; copied = ntfs_copy_from_user_iter(pages + u, do_pages - u, ofs, i, bytes); ntfs_flush_dcache_pages(pages + u, do_pages - u); @@ -1889,7 +1889,7 @@ again: } do { unlock_page(pages[--do_pages]); - page_cache_release(pages[do_pages]); + put_page(pages[do_pages]); } while (do_pages); if (unlikely(status < 0)) break; @@ -1921,7 +1921,7 @@ again: } } while (iov_iter_count(i)); if (cached_page) - page_cache_release(cached_page); + put_page(cached_page); ntfs_debug("Done. Returning %s (written 0x%lx, status %li).", written ? "written" : "status", (unsigned long)written, (long)status); diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c index 096c135691ae..02a83a46ead2 100644 --- a/fs/ntfs/index.c +++ b/fs/ntfs/index.c @@ -276,7 +276,7 @@ descend_into_child_node: * disk if necessary. */ page = ntfs_map_page(ia_mapping, vcn << - idx_ni->itype.index.vcn_size_bits >> PAGE_CACHE_SHIFT); + idx_ni->itype.index.vcn_size_bits >> PAGE_SHIFT); if (IS_ERR(page)) { ntfs_error(sb, "Failed to map index page, error %ld.", -PTR_ERR(page)); @@ -288,9 +288,9 @@ descend_into_child_node: fast_descend_into_child_node: /* Get to the index allocation block. */ ia = (INDEX_ALLOCATION*)(kaddr + ((vcn << - idx_ni->itype.index.vcn_size_bits) & ~PAGE_CACHE_MASK)); + idx_ni->itype.index.vcn_size_bits) & ~PAGE_MASK)); /* Bounds checks. */ - if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_CACHE_SIZE) { + if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) { ntfs_error(sb, "Out of bounds check failed. Corrupt inode " "0x%lx or driver bug.", idx_ni->mft_no); goto unm_err_out; @@ -323,7 +323,7 @@ fast_descend_into_child_node: goto unm_err_out; } index_end = (u8*)ia + idx_ni->itype.index.block_size; - if (index_end > kaddr + PAGE_CACHE_SIZE) { + if (index_end > kaddr + PAGE_SIZE) { ntfs_error(sb, "Index buffer (VCN 0x%llx) of inode 0x%lx " "crosses page boundary. Impossible! Cannot " "access! This is probably a bug in the " @@ -427,9 +427,9 @@ ia_done: * the mapped page. */ if (old_vcn << vol->cluster_size_bits >> - PAGE_CACHE_SHIFT == vcn << + PAGE_SHIFT == vcn << vol->cluster_size_bits >> - PAGE_CACHE_SHIFT) + PAGE_SHIFT) goto fast_descend_into_child_node; unlock_page(page); ntfs_unmap_page(page); diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index d284f07eda77..3eda6d4bcc65 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -868,12 +868,12 @@ skip_attr_list_load: ni->itype.index.block_size); goto unm_err_out; } - if (ni->itype.index.block_size > PAGE_CACHE_SIZE) { + if (ni->itype.index.block_size > PAGE_SIZE) { ntfs_error(vi->i_sb, "Index block size (%u) > " "PAGE_CACHE_SIZE (%ld) is not " "supported. Sorry.", ni->itype.index.block_size, - PAGE_CACHE_SIZE); + PAGE_SIZE); err = -EOPNOTSUPP; goto unm_err_out; } @@ -1585,10 +1585,10 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) "two.", ni->itype.index.block_size); goto unm_err_out; } - if (ni->itype.index.block_size > PAGE_CACHE_SIZE) { + if (ni->itype.index.block_size > PAGE_SIZE) { ntfs_error(vi->i_sb, "Index block size (%u) > PAGE_CACHE_SIZE " "(%ld) is not supported. Sorry.", - ni->itype.index.block_size, PAGE_CACHE_SIZE); + ni->itype.index.block_size, PAGE_SIZE); err = -EOPNOTSUPP; goto unm_err_out; } diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c index 1711b710b641..27a24a42f712 100644 --- a/fs/ntfs/lcnalloc.c +++ b/fs/ntfs/lcnalloc.c @@ -283,15 +283,15 @@ runlist_element *ntfs_cluster_alloc(ntfs_volume *vol, const VCN start_vcn, ntfs_unmap_page(page); } page = ntfs_map_page(mapping, last_read_pos >> - PAGE_CACHE_SHIFT); + PAGE_SHIFT); if (IS_ERR(page)) { err = PTR_ERR(page); ntfs_error(vol->sb, "Failed to map page."); goto out; } - buf_size = last_read_pos & ~PAGE_CACHE_MASK; + buf_size = last_read_pos & ~PAGE_MASK; buf = page_address(page) + buf_size; - buf_size = PAGE_CACHE_SIZE - buf_size; + buf_size = PAGE_SIZE - buf_size; if (unlikely(last_read_pos + buf_size > i_size)) buf_size = i_size - last_read_pos; buf_size <<= 3; diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c index c71de292c5ad..9d71213ca81e 100644 --- a/fs/ntfs/logfile.c +++ b/fs/ntfs/logfile.c @@ -381,7 +381,7 @@ static int ntfs_check_and_load_restart_page(struct inode *vi, * completely inside @rp, just copy it from there. Otherwise map all * the required pages and copy the data from them. */ - size = PAGE_CACHE_SIZE - (pos & ~PAGE_CACHE_MASK); + size = PAGE_SIZE - (pos & ~PAGE_MASK); if (size >= le32_to_cpu(rp->system_page_size)) { memcpy(trp, rp, le32_to_cpu(rp->system_page_size)); } else { @@ -394,8 +394,8 @@ static int ntfs_check_and_load_restart_page(struct inode *vi, /* Copy the remaining data one page at a time. */ have_read = size; to_read = le32_to_cpu(rp->system_page_size) - size; - idx = (pos + size) >> PAGE_CACHE_SHIFT; - BUG_ON((pos + size) & ~PAGE_CACHE_MASK); + idx = (pos + size) >> PAGE_SHIFT; + BUG_ON((pos + size) & ~PAGE_MASK); do { page = ntfs_map_page(vi->i_mapping, idx); if (IS_ERR(page)) { @@ -406,7 +406,7 @@ static int ntfs_check_and_load_restart_page(struct inode *vi, err = -EIO; goto err_out; } - size = min_t(int, to_read, PAGE_CACHE_SIZE); + size = min_t(int, to_read, PAGE_SIZE); memcpy((u8*)trp + have_read, page_address(page), size); ntfs_unmap_page(page); have_read += size; @@ -509,11 +509,11 @@ bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp) * log page size if the page cache size is between the default log page * size and twice that. */ - if (PAGE_CACHE_SIZE >= DefaultLogPageSize && PAGE_CACHE_SIZE <= + if (PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2) log_page_size = DefaultLogPageSize; else - log_page_size = PAGE_CACHE_SIZE; + log_page_size = PAGE_SIZE; log_page_mask = log_page_size - 1; /* * Use ntfs_ffs() instead of ffs() to enable the compiler to @@ -539,7 +539,7 @@ bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp) * to be empty. */ for (pos = 0; pos < size; pos <<= 1) { - pgoff_t idx = pos >> PAGE_CACHE_SHIFT; + pgoff_t idx = pos >> PAGE_SHIFT; if (!page || page->index != idx) { if (page) ntfs_unmap_page(page); @@ -550,7 +550,7 @@ bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp) goto err_out; } } - kaddr = (u8*)page_address(page) + (pos & ~PAGE_CACHE_MASK); + kaddr = (u8*)page_address(page) + (pos & ~PAGE_MASK); /* * A non-empty block means the logfile is not empty while an * empty block after a non-empty block has been encountered diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 3014a36a255b..37b2501caaa4 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -61,16 +61,16 @@ static inline MFT_RECORD *map_mft_record_page(ntfs_inode *ni) * here if the volume was that big... */ index = (u64)ni->mft_no << vol->mft_record_size_bits >> - PAGE_CACHE_SHIFT; - ofs = (ni->mft_no << vol->mft_record_size_bits) & ~PAGE_CACHE_MASK; + PAGE_SHIFT; + ofs = (ni->mft_no << vol->mft_record_size_bits) & ~PAGE_MASK; i_size = i_size_read(mft_vi); /* The maximum valid index into the page cache for $MFT's data. */ - end_index = i_size >> PAGE_CACHE_SHIFT; + end_index = i_size >> PAGE_SHIFT; /* If the wanted index is out of bounds the mft record doesn't exist. */ if (unlikely(index >= end_index)) { - if (index > end_index || (i_size & ~PAGE_CACHE_MASK) < ofs + + if (index > end_index || (i_size & ~PAGE_MASK) < ofs + vol->mft_record_size) { page = ERR_PTR(-ENOENT); ntfs_error(vol->sb, "Attempt to read mft record 0x%lx, " @@ -487,7 +487,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no, } /* Get the page containing the mirror copy of the mft record @m. */ page = ntfs_map_page(vol->mftmirr_ino->i_mapping, mft_no >> - (PAGE_CACHE_SHIFT - vol->mft_record_size_bits)); + (PAGE_SHIFT - vol->mft_record_size_bits)); if (IS_ERR(page)) { ntfs_error(vol->sb, "Failed to map mft mirror page."); err = PTR_ERR(page); @@ -497,7 +497,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no, BUG_ON(!PageUptodate(page)); ClearPageUptodate(page); /* Offset of the mft mirror record inside the page. */ - page_ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_CACHE_MASK; + page_ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_MASK; /* The address in the page of the mirror copy of the mft record @m. */ kmirr = page_address(page) + page_ofs; /* Copy the mst protected mft record to the mirror. */ @@ -1178,8 +1178,8 @@ static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol, for (; pass <= 2;) { /* Cap size to pass_end. */ ofs = data_pos >> 3; - page_ofs = ofs & ~PAGE_CACHE_MASK; - size = PAGE_CACHE_SIZE - page_ofs; + page_ofs = ofs & ~PAGE_MASK; + size = PAGE_SIZE - page_ofs; ll = ((pass_end + 7) >> 3) - ofs; if (size > ll) size = ll; @@ -1190,7 +1190,7 @@ static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol, */ if (size) { page = ntfs_map_page(mftbmp_mapping, - ofs >> PAGE_CACHE_SHIFT); + ofs >> PAGE_SHIFT); if (IS_ERR(page)) { ntfs_error(vol->sb, "Failed to read mft " "bitmap, aborting."); @@ -1328,13 +1328,13 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol) */ ll = lcn >> 3; page = ntfs_map_page(vol->lcnbmp_ino->i_mapping, - ll >> PAGE_CACHE_SHIFT); + ll >> PAGE_SHIFT); if (IS_ERR(page)) { up_write(&mftbmp_ni->runlist.lock); ntfs_error(vol->sb, "Failed to read from lcn bitmap."); return PTR_ERR(page); } - b = (u8*)page_address(page) + (ll & ~PAGE_CACHE_MASK); + b = (u8*)page_address(page) + (ll & ~PAGE_MASK); tb = 1 << (lcn & 7ull); down_write(&vol->lcnbmp_lock); if (*b != 0xff && !(*b & tb)) { @@ -2103,14 +2103,14 @@ static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no) * The index into the page cache and the offset within the page cache * page of the wanted mft record. */ - index = mft_no << vol->mft_record_size_bits >> PAGE_CACHE_SHIFT; - ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_CACHE_MASK; + index = mft_no << vol->mft_record_size_bits >> PAGE_SHIFT; + ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_MASK; /* The maximum valid index into the page cache for $MFT's data. */ i_size = i_size_read(mft_vi); - end_index = i_size >> PAGE_CACHE_SHIFT; + end_index = i_size >> PAGE_SHIFT; if (unlikely(index >= end_index)) { if (unlikely(index > end_index || ofs + vol->mft_record_size >= - (i_size & ~PAGE_CACHE_MASK))) { + (i_size & ~PAGE_MASK))) { ntfs_error(vol->sb, "Tried to format non-existing mft " "record 0x%llx.", (long long)mft_no); return -ENOENT; @@ -2515,8 +2515,8 @@ mft_rec_already_initialized: * We now have allocated and initialized the mft record. Calculate the * index of and the offset within the page cache page the record is in. */ - index = bit << vol->mft_record_size_bits >> PAGE_CACHE_SHIFT; - ofs = (bit << vol->mft_record_size_bits) & ~PAGE_CACHE_MASK; + index = bit << vol->mft_record_size_bits >> PAGE_SHIFT; + ofs = (bit << vol->mft_record_size_bits) & ~PAGE_MASK; /* Read, map, and pin the page containing the mft record. */ page = ntfs_map_page(vol->mft_ino->i_mapping, index); if (IS_ERR(page)) { diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h index c581e26a350d..12de47b96ca9 100644 --- a/fs/ntfs/ntfs.h +++ b/fs/ntfs/ntfs.h @@ -43,7 +43,7 @@ typedef enum { NTFS_MAX_NAME_LEN = 255, NTFS_MAX_ATTR_NAME_LEN = 255, NTFS_MAX_CLUSTER_SIZE = 64 * 1024, /* 64kiB */ - NTFS_MAX_PAGES_PER_CLUSTER = NTFS_MAX_CLUSTER_SIZE / PAGE_CACHE_SIZE, + NTFS_MAX_PAGES_PER_CLUSTER = NTFS_MAX_CLUSTER_SIZE / PAGE_SIZE, } NTFS_CONSTANTS; /* Global variables. */ diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 1b38abdaa3ed..ab2b0930054e 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -826,11 +826,11 @@ static bool parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) * We cannot support mft record sizes above the PAGE_CACHE_SIZE since * we store $MFT/$DATA, the table of mft records in the page cache. */ - if (vol->mft_record_size > PAGE_CACHE_SIZE) { + if (vol->mft_record_size > PAGE_SIZE) { ntfs_error(vol->sb, "Mft record size (%i) exceeds the " "PAGE_CACHE_SIZE on your system (%lu). " "This is not supported. Sorry.", - vol->mft_record_size, PAGE_CACHE_SIZE); + vol->mft_record_size, PAGE_SIZE); return false; } /* We cannot support mft record sizes below the sector size. */ @@ -1096,7 +1096,7 @@ static bool check_mft_mirror(ntfs_volume *vol) ntfs_debug("Entering."); /* Compare contents of $MFT and $MFTMirr. */ - mrecs_per_page = PAGE_CACHE_SIZE / vol->mft_record_size; + mrecs_per_page = PAGE_SIZE / vol->mft_record_size; BUG_ON(!mrecs_per_page); BUG_ON(!vol->mftmirr_size); mft_page = mirr_page = NULL; @@ -1615,20 +1615,20 @@ static bool load_and_init_attrdef(ntfs_volume *vol) if (!vol->attrdef) goto iput_failed; index = 0; - max_index = i_size >> PAGE_CACHE_SHIFT; - size = PAGE_CACHE_SIZE; + max_index = i_size >> PAGE_SHIFT; + size = PAGE_SIZE; while (index < max_index) { /* Read the attrdef table and copy it into the linear buffer. */ read_partial_attrdef_page: page = ntfs_map_page(ino->i_mapping, index); if (IS_ERR(page)) goto free_iput_failed; - memcpy((u8*)vol->attrdef + (index++ << PAGE_CACHE_SHIFT), + memcpy((u8*)vol->attrdef + (index++ << PAGE_SHIFT), page_address(page), size); ntfs_unmap_page(page); }; - if (size == PAGE_CACHE_SIZE) { - size = i_size & ~PAGE_CACHE_MASK; + if (size == PAGE_SIZE) { + size = i_size & ~PAGE_MASK; if (size) goto read_partial_attrdef_page; } @@ -1684,20 +1684,20 @@ static bool load_and_init_upcase(ntfs_volume *vol) if (!vol->upcase) goto iput_upcase_failed; index = 0; - max_index = i_size >> PAGE_CACHE_SHIFT; - size = PAGE_CACHE_SIZE; + max_index = i_size >> PAGE_SHIFT; + size = PAGE_SIZE; while (index < max_index) { /* Read the upcase table and copy it into the linear buffer. */ read_partial_upcase_page: page = ntfs_map_page(ino->i_mapping, index); if (IS_ERR(page)) goto iput_upcase_failed; - memcpy((char*)vol->upcase + (index++ << PAGE_CACHE_SHIFT), + memcpy((char*)vol->upcase + (index++ << PAGE_SHIFT), page_address(page), size); ntfs_unmap_page(page); }; - if (size == PAGE_CACHE_SIZE) { - size = i_size & ~PAGE_CACHE_MASK; + if (size == PAGE_SIZE) { + size = i_size & ~PAGE_MASK; if (size) goto read_partial_upcase_page; } @@ -2474,11 +2474,11 @@ static s64 get_nr_free_clusters(ntfs_volume *vol) * multiples of PAGE_CACHE_SIZE, rounding up so that if we have one * full and one partial page max_index = 2. */ - max_index = (((vol->nr_clusters + 7) >> 3) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + max_index = (((vol->nr_clusters + 7) >> 3) + PAGE_SIZE - 1) >> + PAGE_SHIFT; /* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */ ntfs_debug("Reading $Bitmap, max_index = 0x%lx, max_size = 0x%lx.", - max_index, PAGE_CACHE_SIZE / 4); + max_index, PAGE_SIZE / 4); for (index = 0; index < max_index; index++) { unsigned long *kaddr; @@ -2491,7 +2491,7 @@ static s64 get_nr_free_clusters(ntfs_volume *vol) if (IS_ERR(page)) { ntfs_debug("read_mapping_page() error. Skipping " "page (index 0x%lx).", index); - nr_free -= PAGE_CACHE_SIZE * 8; + nr_free -= PAGE_SIZE * 8; continue; } kaddr = kmap_atomic(page); @@ -2503,9 +2503,9 @@ static s64 get_nr_free_clusters(ntfs_volume *vol) * ntfs_readpage(). */ nr_free -= bitmap_weight(kaddr, - PAGE_CACHE_SIZE * BITS_PER_BYTE); + PAGE_SIZE * BITS_PER_BYTE); kunmap_atomic(kaddr); - page_cache_release(page); + put_page(page); } ntfs_debug("Finished reading $Bitmap, last index = 0x%lx.", index - 1); /* @@ -2549,7 +2549,7 @@ static unsigned long __get_nr_free_mft_records(ntfs_volume *vol, ntfs_debug("Entering."); /* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */ ntfs_debug("Reading $MFT/$BITMAP, max_index = 0x%lx, max_size = " - "0x%lx.", max_index, PAGE_CACHE_SIZE / 4); + "0x%lx.", max_index, PAGE_SIZE / 4); for (index = 0; index < max_index; index++) { unsigned long *kaddr; @@ -2562,7 +2562,7 @@ static unsigned long __get_nr_free_mft_records(ntfs_volume *vol, if (IS_ERR(page)) { ntfs_debug("read_mapping_page() error. Skipping " "page (index 0x%lx).", index); - nr_free -= PAGE_CACHE_SIZE * 8; + nr_free -= PAGE_SIZE * 8; continue; } kaddr = kmap_atomic(page); @@ -2574,9 +2574,9 @@ static unsigned long __get_nr_free_mft_records(ntfs_volume *vol, * ntfs_readpage(). */ nr_free -= bitmap_weight(kaddr, - PAGE_CACHE_SIZE * BITS_PER_BYTE); + PAGE_SIZE * BITS_PER_BYTE); kunmap_atomic(kaddr); - page_cache_release(page); + put_page(page); } ntfs_debug("Finished reading $MFT/$BITMAP, last index = 0x%lx.", index - 1); @@ -2618,17 +2618,17 @@ static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs) /* Type of filesystem. */ sfs->f_type = NTFS_SB_MAGIC; /* Optimal transfer block size. */ - sfs->f_bsize = PAGE_CACHE_SIZE; + sfs->f_bsize = PAGE_SIZE; /* * Total data blocks in filesystem in units of f_bsize and since * inodes are also stored in data blocs ($MFT is a file) this is just * the total clusters. */ sfs->f_blocks = vol->nr_clusters << vol->cluster_size_bits >> - PAGE_CACHE_SHIFT; + PAGE_SHIFT; /* Free data blocks in filesystem in units of f_bsize. */ size = get_nr_free_clusters(vol) << vol->cluster_size_bits >> - PAGE_CACHE_SHIFT; + PAGE_SHIFT; if (size < 0LL) size = 0LL; /* Free blocks avail to non-superuser, same as above on NTFS. */ @@ -2643,7 +2643,7 @@ static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs) * have one full and one partial page max_index = 2. */ max_index = ((((mft_ni->initialized_size >> vol->mft_record_size_bits) - + 7) >> 3) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + + 7) >> 3) + PAGE_SIZE - 1) >> PAGE_SHIFT; read_unlock_irqrestore(&mft_ni->size_lock, flags); /* Number of inodes in filesystem (at this point in time). */ sfs->f_files = size; @@ -2766,14 +2766,14 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) goto err_out_now; /* We support sector sizes up to the PAGE_CACHE_SIZE. */ - if (bdev_logical_block_size(sb->s_bdev) > PAGE_CACHE_SIZE) { + if (bdev_logical_block_size(sb->s_bdev) > PAGE_SIZE) { if (!silent) ntfs_error(sb, "Device has unsupported sector size " "(%i). The maximum supported sector " "size on this architecture is %lu " "bytes.", bdev_logical_block_size(sb->s_bdev), - PAGE_CACHE_SIZE); + PAGE_SIZE); goto err_out_now; } /* diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 70907d638b60..e361d1a0ca09 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -6671,7 +6671,7 @@ static void ocfs2_zero_cluster_pages(struct inode *inode, loff_t start, { int i; struct page *page; - unsigned int from, to = PAGE_CACHE_SIZE; + unsigned int from, to = PAGE_SIZE; struct super_block *sb = inode->i_sb; BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(sb))); @@ -6679,21 +6679,21 @@ static void ocfs2_zero_cluster_pages(struct inode *inode, loff_t start, if (numpages == 0) goto out; - to = PAGE_CACHE_SIZE; + to = PAGE_SIZE; for(i = 0; i < numpages; i++) { page = pages[i]; - from = start & (PAGE_CACHE_SIZE - 1); - if ((end >> PAGE_CACHE_SHIFT) == page->index) - to = end & (PAGE_CACHE_SIZE - 1); + from = start & (PAGE_SIZE - 1); + if ((end >> PAGE_SHIFT) == page->index) + to = end & (PAGE_SIZE - 1); - BUG_ON(from > PAGE_CACHE_SIZE); - BUG_ON(to > PAGE_CACHE_SIZE); + BUG_ON(from > PAGE_SIZE); + BUG_ON(to > PAGE_SIZE); ocfs2_map_and_dirty_page(inode, handle, from, to, page, 1, &phys); - start = (page->index + 1) << PAGE_CACHE_SHIFT; + start = (page->index + 1) << PAGE_SHIFT; } out: if (pages) @@ -6712,7 +6712,7 @@ int ocfs2_grab_pages(struct inode *inode, loff_t start, loff_t end, numpages = 0; last_page_bytes = PAGE_ALIGN(end); - index = start >> PAGE_CACHE_SHIFT; + index = start >> PAGE_SHIFT; do { pages[numpages] = find_or_create_page(mapping, index, GFP_NOFS); if (!pages[numpages]) { @@ -6723,7 +6723,7 @@ int ocfs2_grab_pages(struct inode *inode, loff_t start, loff_t end, numpages++; index++; - } while (index < (last_page_bytes >> PAGE_CACHE_SHIFT)); + } while (index < (last_page_bytes >> PAGE_SHIFT)); out: if (ret != 0) { @@ -6950,8 +6950,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, * to do that now. */ if (!ocfs2_sparse_alloc(osb) && - PAGE_CACHE_SIZE < osb->s_clustersize) - end = PAGE_CACHE_SIZE; + PAGE_SIZE < osb->s_clustersize) + end = PAGE_SIZE; ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages); if (ret) { @@ -6971,8 +6971,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, goto out_unlock; } - page_end = PAGE_CACHE_SIZE; - if (PAGE_CACHE_SIZE > osb->s_clustersize) + page_end = PAGE_SIZE; + if (PAGE_SIZE > osb->s_clustersize) page_end = osb->s_clustersize; for (i = 0; i < num_pages; i++) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 1581240a7ca0..ce5dc4f92935 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -234,7 +234,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page, size = i_size_read(inode); - if (size > PAGE_CACHE_SIZE || + if (size > PAGE_SIZE || size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) { ocfs2_error(inode->i_sb, "Inode %llu has with inline data has bad size: %Lu\n", @@ -247,7 +247,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page, if (size) memcpy(kaddr, di->id2.i_data.id_data, size); /* Clear the remaining part of the page */ - memset(kaddr + size, 0, PAGE_CACHE_SIZE - size); + memset(kaddr + size, 0, PAGE_SIZE - size); flush_dcache_page(page); kunmap_atomic(kaddr); @@ -282,7 +282,7 @@ static int ocfs2_readpage(struct file *file, struct page *page) { struct inode *inode = page->mapping->host; struct ocfs2_inode_info *oi = OCFS2_I(inode); - loff_t start = (loff_t)page->index << PAGE_CACHE_SHIFT; + loff_t start = (loff_t)page->index << PAGE_SHIFT; int ret, unlock = 1; trace_ocfs2_readpage((unsigned long long)oi->ip_blkno, @@ -385,7 +385,7 @@ static int ocfs2_readpages(struct file *filp, struct address_space *mapping, * drop out in that case as it's not worth handling here. */ last = list_entry(pages->prev, struct page, lru); - start = (loff_t)last->index << PAGE_CACHE_SHIFT; + start = (loff_t)last->index << PAGE_SHIFT; if (start >= i_size_read(inode)) goto out_unlock; @@ -511,12 +511,12 @@ static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb, unsigned int *start, unsigned int *end) { - unsigned int cluster_start = 0, cluster_end = PAGE_CACHE_SIZE; + unsigned int cluster_start = 0, cluster_end = PAGE_SIZE; - if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits)) { + if (unlikely(PAGE_SHIFT > osb->s_clustersize_bits)) { unsigned int cpp; - cpp = 1 << (PAGE_CACHE_SHIFT - osb->s_clustersize_bits); + cpp = 1 << (PAGE_SHIFT - osb->s_clustersize_bits); cluster_start = cpos % cpp; cluster_start = cluster_start << osb->s_clustersize_bits; @@ -687,10 +687,10 @@ next_bh: #if (PAGE_CACHE_SIZE >= OCFS2_MAX_CLUSTERSIZE) #define OCFS2_MAX_CTXT_PAGES 1 #else -#define OCFS2_MAX_CTXT_PAGES (OCFS2_MAX_CLUSTERSIZE / PAGE_CACHE_SIZE) +#define OCFS2_MAX_CTXT_PAGES (OCFS2_MAX_CLUSTERSIZE / PAGE_SIZE) #endif -#define OCFS2_MAX_CLUSTERS_PER_PAGE (PAGE_CACHE_SIZE / OCFS2_MIN_CLUSTERSIZE) +#define OCFS2_MAX_CLUSTERS_PER_PAGE (PAGE_SIZE / OCFS2_MIN_CLUSTERSIZE) struct ocfs2_unwritten_extent { struct list_head ue_node; @@ -785,7 +785,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages) if (pages[i]) { unlock_page(pages[i]); mark_page_accessed(pages[i]); - page_cache_release(pages[i]); + put_page(pages[i]); } } } @@ -808,7 +808,7 @@ static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc) } } mark_page_accessed(wc->w_target_page); - page_cache_release(wc->w_target_page); + put_page(wc->w_target_page); } ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages); } @@ -857,7 +857,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp, wc->w_di_bh = di_bh; wc->w_type = type; - if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits)) + if (unlikely(PAGE_SHIFT > osb->s_clustersize_bits)) wc->w_large_pages = 1; else wc->w_large_pages = 0; @@ -920,7 +920,7 @@ static void ocfs2_write_failure(struct inode *inode, loff_t user_pos, unsigned user_len) { int i; - unsigned from = user_pos & (PAGE_CACHE_SIZE - 1), + unsigned from = user_pos & (PAGE_SIZE - 1), to = user_pos + user_len; struct page *tmppage; @@ -960,7 +960,7 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno, (page_offset(page) <= user_pos)); if (page == wc->w_target_page) { - map_from = user_pos & (PAGE_CACHE_SIZE - 1); + map_from = user_pos & (PAGE_SIZE - 1); map_to = map_from + user_len; if (new) @@ -1034,7 +1034,7 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, struct inode *inode = mapping->host; loff_t last_byte; - target_index = user_pos >> PAGE_CACHE_SHIFT; + target_index = user_pos >> PAGE_SHIFT; /* * Figure out how many pages we'll be manipulating here. For @@ -1053,14 +1053,14 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, */ last_byte = max(user_pos + user_len, i_size_read(inode)); BUG_ON(last_byte < 1); - end_index = ((last_byte - 1) >> PAGE_CACHE_SHIFT) + 1; + end_index = ((last_byte - 1) >> PAGE_SHIFT) + 1; if ((start + wc->w_num_pages) > end_index) wc->w_num_pages = end_index - start; } else { wc->w_num_pages = 1; start = target_index; } - end_index = (user_pos + user_len - 1) >> PAGE_CACHE_SHIFT; + end_index = (user_pos + user_len - 1) >> PAGE_SHIFT; for(i = 0; i < wc->w_num_pages; i++) { index = start + i; @@ -1082,7 +1082,7 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, goto out; } - page_cache_get(mmap_page); + get_page(mmap_page); wc->w_pages[i] = mmap_page; wc->w_target_locked = true; } else if (index >= target_index && index <= end_index && @@ -1272,7 +1272,7 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb, { struct ocfs2_write_cluster_desc *desc; - wc->w_target_from = pos & (PAGE_CACHE_SIZE - 1); + wc->w_target_from = pos & (PAGE_SIZE - 1); wc->w_target_to = wc->w_target_from + len; if (alloc == 0) @@ -1309,7 +1309,7 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb, &wc->w_target_to); } else { wc->w_target_from = 0; - wc->w_target_to = PAGE_CACHE_SIZE; + wc->w_target_to = PAGE_SIZE; } } @@ -1981,7 +1981,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping, struct page *page, void *fsdata) { int i, ret; - unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1); + unsigned from, to, start = pos & (PAGE_SIZE - 1); struct inode *inode = mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_write_ctxt *wc = fsdata; @@ -2027,8 +2027,8 @@ int ocfs2_write_end_nolock(struct address_space *mapping, from = wc->w_target_from; to = wc->w_target_to; - BUG_ON(from > PAGE_CACHE_SIZE || - to > PAGE_CACHE_SIZE || + BUG_ON(from > PAGE_SIZE || + to > PAGE_SIZE || to < from); } else { /* @@ -2037,7 +2037,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping, * to flush their entire range. */ from = 0; - to = PAGE_CACHE_SIZE; + to = PAGE_SIZE; } if (page_has_buffers(tmppage)) { diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index bd15929b5f92..1934abb6b680 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -417,13 +417,13 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg, bio->bi_private = wc; bio->bi_end_io = o2hb_bio_end_io; - vec_start = (cs << bits) % PAGE_CACHE_SIZE; + vec_start = (cs << bits) % PAGE_SIZE; while(cs < max_slots) { current_page = cs / spp; page = reg->hr_slot_data[current_page]; - vec_len = min(PAGE_CACHE_SIZE - vec_start, - (max_slots-cs) * (PAGE_CACHE_SIZE/spp) ); + vec_len = min(PAGE_SIZE - vec_start, + (max_slots-cs) * (PAGE_SIZE/spp) ); mlog(ML_HB_BIO, "page %d, vec_len = %u, vec_start = %u\n", current_page, vec_len, vec_start); @@ -431,7 +431,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg, len = bio_add_page(bio, page, vec_len, vec_start); if (len != vec_len) break; - cs += vec_len / (PAGE_CACHE_SIZE/spp); + cs += vec_len / (PAGE_SIZE/spp); vec_start = 0; } @@ -1576,7 +1576,7 @@ static ssize_t o2hb_region_dev_show(struct config_item *item, char *page) static void o2hb_init_region_params(struct o2hb_region *reg) { - reg->hr_slots_per_page = PAGE_CACHE_SIZE >> reg->hr_block_bits; + reg->hr_slots_per_page = PAGE_SIZE >> reg->hr_block_bits; reg->hr_timeout_ms = O2HB_REGION_TIMEOUT_MS; mlog(ML_HEARTBEAT, "hr_start_block = %llu, hr_blocks = %u\n", diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 03768bb3aab1..47b3b2d4e775 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -571,8 +571,8 @@ static int dlmfs_fill_super(struct super_block * sb, int silent) { sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = DLMFS_MAGIC; sb->s_op = &dlmfs_ops; sb->s_root = d_make_root(dlmfs_get_root_inode(sb)); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index c18ab45f8d21..5308841756be 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -770,14 +770,14 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, { struct address_space *mapping = inode->i_mapping; struct page *page; - unsigned long index = abs_from >> PAGE_CACHE_SHIFT; + unsigned long index = abs_from >> PAGE_SHIFT; handle_t *handle; int ret = 0; unsigned zero_from, zero_to, block_start, block_end; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; BUG_ON(abs_from >= abs_to); - BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT)); + BUG_ON(abs_to > (((u64)index + 1) << PAGE_SHIFT)); BUG_ON(abs_from & (inode->i_blkbits - 1)); handle = ocfs2_zero_start_ordered_transaction(inode, di_bh); @@ -794,10 +794,10 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, } /* Get the offsets within the page that we want to zero */ - zero_from = abs_from & (PAGE_CACHE_SIZE - 1); - zero_to = abs_to & (PAGE_CACHE_SIZE - 1); + zero_from = abs_from & (PAGE_SIZE - 1); + zero_to = abs_to & (PAGE_SIZE - 1); if (!zero_to) - zero_to = PAGE_CACHE_SIZE; + zero_to = PAGE_SIZE; trace_ocfs2_write_zero_page( (unsigned long long)OCFS2_I(inode)->ip_blkno, @@ -851,7 +851,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, out_unlock: unlock_page(page); - page_cache_release(page); + put_page(page); out_commit_trans: if (handle) ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); @@ -959,7 +959,7 @@ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start, BUG_ON(range_start >= range_end); while (zero_pos < range_end) { - next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE; + next_pos = (zero_pos & PAGE_MASK) + PAGE_SIZE; if (next_pos > range_end) next_pos = range_end; rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh); diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 9ea081f4e6e4..71545ad4628c 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -65,13 +65,13 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh, struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; loff_t pos = page_offset(page); - unsigned int len = PAGE_CACHE_SIZE; + unsigned int len = PAGE_SIZE; pgoff_t last_index; struct page *locked_page = NULL; void *fsdata; loff_t size = i_size_read(inode); - last_index = (size - 1) >> PAGE_CACHE_SHIFT; + last_index = (size - 1) >> PAGE_SHIFT; /* * There are cases that lead to the page no longer bebongs to the @@ -102,7 +102,7 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh, * because the "write" would invalidate their data. */ if (page->index == last_index) - len = ((size - 1) & ~PAGE_CACHE_MASK) + 1; + len = ((size - 1) & ~PAGE_MASK) + 1; ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP, &locked_page, &fsdata, di_bh, page); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 6cf6538a0651..e63af7ddfe68 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -822,10 +822,10 @@ static inline unsigned int ocfs2_page_index_to_clusters(struct super_block *sb, u32 clusters = pg_index; unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits; - if (unlikely(PAGE_CACHE_SHIFT > cbits)) - clusters = pg_index << (PAGE_CACHE_SHIFT - cbits); - else if (PAGE_CACHE_SHIFT < cbits) - clusters = pg_index >> (cbits - PAGE_CACHE_SHIFT); + if (unlikely(PAGE_SHIFT > cbits)) + clusters = pg_index << (PAGE_SHIFT - cbits); + else if (PAGE_SHIFT < cbits) + clusters = pg_index >> (cbits - PAGE_SHIFT); return clusters; } @@ -839,10 +839,10 @@ static inline pgoff_t ocfs2_align_clusters_to_page_index(struct super_block *sb, unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits; pgoff_t index = clusters; - if (PAGE_CACHE_SHIFT > cbits) { - index = (pgoff_t)clusters >> (PAGE_CACHE_SHIFT - cbits); - } else if (PAGE_CACHE_SHIFT < cbits) { - index = (pgoff_t)clusters << (cbits - PAGE_CACHE_SHIFT); + if (PAGE_SHIFT > cbits) { + index = (pgoff_t)clusters >> (PAGE_SHIFT - cbits); + } else if (PAGE_SHIFT < cbits) { + index = (pgoff_t)clusters << (cbits - PAGE_SHIFT); } return index; @@ -853,8 +853,8 @@ static inline unsigned int ocfs2_pages_per_cluster(struct super_block *sb) unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits; unsigned int pages_per_cluster = 1; - if (PAGE_CACHE_SHIFT < cbits) - pages_per_cluster = 1 << (cbits - PAGE_CACHE_SHIFT); + if (PAGE_SHIFT < cbits) + pages_per_cluster = 1 << (cbits - PAGE_SHIFT); return pages_per_cluster; } diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 3eff031aaf26..881242c3a8d2 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2937,16 +2937,16 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, end = i_size_read(inode); while (offset < end) { - page_index = offset >> PAGE_CACHE_SHIFT; - map_end = ((loff_t)page_index + 1) << PAGE_CACHE_SHIFT; + page_index = offset >> PAGE_SHIFT; + map_end = ((loff_t)page_index + 1) << PAGE_SHIFT; if (map_end > end) map_end = end; /* from, to is the offset within the page. */ - from = offset & (PAGE_CACHE_SIZE - 1); - to = PAGE_CACHE_SIZE; - if (map_end & (PAGE_CACHE_SIZE - 1)) - to = map_end & (PAGE_CACHE_SIZE - 1); + from = offset & (PAGE_SIZE - 1); + to = PAGE_SIZE; + if (map_end & (PAGE_SIZE - 1)) + to = map_end & (PAGE_SIZE - 1); page = find_or_create_page(mapping, page_index, GFP_NOFS); if (!page) { @@ -2959,7 +2959,7 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, * In case PAGE_CACHE_SIZE <= CLUSTER_SIZE, This page * can't be dirtied before we CoW it out. */ - if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize) + if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) BUG_ON(PageDirty(page)); if (!PageUptodate(page)) { @@ -2987,7 +2987,7 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, mark_page_accessed(page); unlock: unlock_page(page); - page_cache_release(page); + put_page(page); page = NULL; offset = map_end; if (ret) @@ -3165,8 +3165,8 @@ int ocfs2_cow_sync_writeback(struct super_block *sb, } while (offset < end) { - page_index = offset >> PAGE_CACHE_SHIFT; - map_end = ((loff_t)page_index + 1) << PAGE_CACHE_SHIFT; + page_index = offset >> PAGE_SHIFT; + map_end = ((loff_t)page_index + 1) << PAGE_SHIFT; if (map_end > end) map_end = end; @@ -3182,7 +3182,7 @@ int ocfs2_cow_sync_writeback(struct super_block *sb, mark_page_accessed(page); unlock_page(page); - page_cache_release(page); + put_page(page); page = NULL; offset = map_end; if (ret) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 7db631e1c8b0..d7cae3327de5 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -605,8 +605,8 @@ static unsigned long long ocfs2_max_file_offset(unsigned int bbits, /* * We might be limited by page cache size. */ - if (bytes > PAGE_CACHE_SIZE) { - bytes = PAGE_CACHE_SIZE; + if (bytes > PAGE_SIZE) { + bytes = PAGE_SIZE; trim = 1; /* * Shift by 31 here so that we don't get larger than diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 2382e267b49e..0166faabf8f2 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -18,8 +18,8 @@ static int read_one_page(struct page *page) int max_block; ssize_t bytes_read = 0; struct inode *inode = page->mapping->host; - const __u32 blocksize = PAGE_CACHE_SIZE; /* inode->i_blksize */ - const __u32 blockbits = PAGE_CACHE_SHIFT; /* inode->i_blkbits */ + const __u32 blocksize = PAGE_SIZE; /* inode->i_blksize */ + const __u32 blockbits = PAGE_SHIFT; /* inode->i_blkbits */ struct iov_iter to; struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE}; @@ -86,7 +86,7 @@ static int orangefs_readpages(struct file *file, "failure adding page to cache, read_one_page returned: %d\n", ret); } else { - page_cache_release(page); + put_page(page); } } BUG_ON(!list_empty(pages)); @@ -328,7 +328,7 @@ static int orangefs_init_iops(struct inode *inode) case S_IFREG: inode->i_op = &orangefs_file_inode_operations; inode->i_fop = &orangefs_file_operations; - inode->i_blkbits = PAGE_CACHE_SHIFT; + inode->i_blkbits = PAGE_SHIFT; break; case S_IFLNK: inode->i_op = &orangefs_symlink_inode_operations; @@ -456,7 +456,7 @@ struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir, inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - inode->i_size = PAGE_CACHE_SIZE; + inode->i_size = PAGE_SIZE; inode->i_rdev = dev; error = insert_inode_locked4(inode, hash, orangefs_test_inode, ref); diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index 1f8acc9f9a88..75375e90a63f 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -170,7 +170,7 @@ orangefs_bufmap_unmap(struct orangefs_bufmap *bufmap) int i; for (i = 0; i < bufmap->page_count; i++) - page_cache_release(bufmap->page_array[i]); + put_page(bufmap->page_array[i]); } static void @@ -299,7 +299,7 @@ orangefs_bufmap_map(struct orangefs_bufmap *bufmap, for (i = 0; i < ret; i++) { SetPageError(bufmap->page_array[i]); - page_cache_release(bufmap->page_array[i]); + put_page(bufmap->page_array[i]); } return -ENOMEM; } diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c index 40f5163b56aa..8277aba65e87 100644 --- a/fs/orangefs/orangefs-utils.c +++ b/fs/orangefs/orangefs-utils.c @@ -303,7 +303,7 @@ int orangefs_inode_getattr(struct inode *inode, int new, int size) } break; case S_IFDIR: - inode->i_size = PAGE_CACHE_SIZE; + inode->i_size = PAGE_SIZE; orangefs_inode->blksize = (1 << inode->i_blkbits); spin_lock(&inode->i_lock); inode_set_bytes(inode, inode->i_size); diff --git a/fs/pipe.c b/fs/pipe.c index ab8dad3ccb6a..0d3f5165cb0b 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -134,7 +134,7 @@ static void anon_pipe_buf_release(struct pipe_inode_info *pipe, if (page_count(page) == 1 && !pipe->tmp_page) pipe->tmp_page = page; else - page_cache_release(page); + put_page(page); } /** @@ -180,7 +180,7 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); */ void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - page_cache_get(buf->page); + get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); @@ -211,7 +211,7 @@ EXPORT_SYMBOL(generic_pipe_buf_confirm); void generic_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - page_cache_release(buf->page); + put_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_release); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 9df431642042..229cb546bee0 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -553,7 +553,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (radix_tree_exceptional_entry(page)) mss->swap += PAGE_SIZE; else - page_cache_release(page); + put_page(page); return; } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 55bb57e6a30d..8afe10cf7df8 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -279,12 +279,12 @@ static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf) if (!page) return VM_FAULT_OOM; if (!PageUptodate(page)) { - offset = (loff_t) index << PAGE_CACHE_SHIFT; + offset = (loff_t) index << PAGE_SHIFT; buf = __va((page_to_pfn(page) << PAGE_SHIFT)); rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0); if (rc < 0) { unlock_page(page); - page_cache_release(page); + put_page(page); return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS; } SetPageUptodate(page); diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index dc645b66cd79..45d6110744cb 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -420,8 +420,8 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent) pstore_sb = sb; sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = PSTOREFS_MAGIC; sb->s_op = &pstore_ops; sb->s_time_gran = 1; diff --git a/fs/qnx6/dir.c b/fs/qnx6/dir.c index e1f37278cf97..144ceda4948e 100644 --- a/fs/qnx6/dir.c +++ b/fs/qnx6/dir.c @@ -35,9 +35,9 @@ static struct page *qnx6_get_page(struct inode *dir, unsigned long n) static unsigned last_entry(struct inode *inode, unsigned long page_nr) { unsigned long last_byte = inode->i_size; - last_byte -= page_nr << PAGE_CACHE_SHIFT; - if (last_byte > PAGE_CACHE_SIZE) - last_byte = PAGE_CACHE_SIZE; + last_byte -= page_nr << PAGE_SHIFT; + if (last_byte > PAGE_SIZE) + last_byte = PAGE_SIZE; return last_byte / QNX6_DIR_ENTRY_SIZE; } @@ -47,9 +47,9 @@ static struct qnx6_long_filename *qnx6_longname(struct super_block *sb, { struct qnx6_sb_info *sbi = QNX6_SB(sb); u32 s = fs32_to_cpu(sbi, de->de_long_inode); /* in block units */ - u32 n = s >> (PAGE_CACHE_SHIFT - sb->s_blocksize_bits); /* in pages */ + u32 n = s >> (PAGE_SHIFT - sb->s_blocksize_bits); /* in pages */ /* within page */ - u32 offs = (s << sb->s_blocksize_bits) & ~PAGE_CACHE_MASK; + u32 offs = (s << sb->s_blocksize_bits) & ~PAGE_MASK; struct address_space *mapping = sbi->longfile->i_mapping; struct page *page = read_mapping_page(mapping, n, NULL); if (IS_ERR(page)) @@ -115,8 +115,8 @@ static int qnx6_readdir(struct file *file, struct dir_context *ctx) struct qnx6_sb_info *sbi = QNX6_SB(s); loff_t pos = ctx->pos & ~(QNX6_DIR_ENTRY_SIZE - 1); unsigned long npages = dir_pages(inode); - unsigned long n = pos >> PAGE_CACHE_SHIFT; - unsigned start = (pos & ~PAGE_CACHE_MASK) / QNX6_DIR_ENTRY_SIZE; + unsigned long n = pos >> PAGE_SHIFT; + unsigned start = (pos & ~PAGE_MASK) / QNX6_DIR_ENTRY_SIZE; bool done = false; ctx->pos = pos; @@ -131,7 +131,7 @@ static int qnx6_readdir(struct file *file, struct dir_context *ctx) if (IS_ERR(page)) { pr_err("%s(): read failed\n", __func__); - ctx->pos = (n + 1) << PAGE_CACHE_SHIFT; + ctx->pos = (n + 1) << PAGE_SHIFT; return PTR_ERR(page); } de = ((struct qnx6_dir_entry *)page_address(page)) + start; diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 47bb1de07155..1192422a1c56 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -542,8 +542,8 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino) iget_failed(inode); return ERR_PTR(-EIO); } - n = (ino - 1) >> (PAGE_CACHE_SHIFT - QNX6_INODE_SIZE_BITS); - offs = (ino - 1) & (~PAGE_CACHE_MASK >> QNX6_INODE_SIZE_BITS); + n = (ino - 1) >> (PAGE_SHIFT - QNX6_INODE_SIZE_BITS); + offs = (ino - 1) & (~PAGE_MASK >> QNX6_INODE_SIZE_BITS); mapping = sbi->inodes->i_mapping; page = read_mapping_page(mapping, n, NULL); if (IS_ERR(page)) { diff --git a/fs/qnx6/qnx6.h b/fs/qnx6/qnx6.h index d3fb2b698800..f23b5c4a66ad 100644 --- a/fs/qnx6/qnx6.h +++ b/fs/qnx6/qnx6.h @@ -128,7 +128,7 @@ extern struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s, static inline void qnx6_put_page(struct page *page) { kunmap(page); - page_cache_release(page); + put_page(page); } extern unsigned qnx6_find_entry(int len, struct inode *dir, const char *name, diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 38981b037524..1ab6e6c2e60e 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -223,8 +223,8 @@ int ramfs_fill_super(struct super_block *sb, void *data, int silent) return err; sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = RAMFS_MAGIC; sb->s_op = &ramfs_ops; sb->s_time_gran = 1; diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 9424a4ba93a9..389773711de4 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -180,11 +180,11 @@ int reiserfs_commit_page(struct inode *inode, struct page *page, int partial = 0; unsigned blocksize; struct buffer_head *bh, *head; - unsigned long i_size_index = inode->i_size >> PAGE_CACHE_SHIFT; + unsigned long i_size_index = inode->i_size >> PAGE_SHIFT; int new; int logit = reiserfs_file_data_log(inode); struct super_block *s = inode->i_sb; - int bh_per_page = PAGE_CACHE_SIZE / s->s_blocksize; + int bh_per_page = PAGE_SIZE / s->s_blocksize; struct reiserfs_transaction_handle th; int ret = 0; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index ae9e5b308cf9..d5c2e9c865de 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -386,7 +386,7 @@ static int _get_block_create_0(struct inode *inode, sector_t block, goto finished; } /* read file tail into part of page */ - offset = (cpu_key_k_offset(&key) - 1) & (PAGE_CACHE_SIZE - 1); + offset = (cpu_key_k_offset(&key) - 1) & (PAGE_SIZE - 1); copy_item_head(&tmp_ih, ih); /* @@ -587,10 +587,10 @@ static int convert_tail_for_hole(struct inode *inode, return -EIO; /* always try to read until the end of the block */ - tail_start = tail_offset & (PAGE_CACHE_SIZE - 1); + tail_start = tail_offset & (PAGE_SIZE - 1); tail_end = (tail_start | (bh_result->b_size - 1)) + 1; - index = tail_offset >> PAGE_CACHE_SHIFT; + index = tail_offset >> PAGE_SHIFT; /* * hole_page can be zero in case of direct_io, we are sure * that we cannot get here if we write with O_DIRECT into tail page @@ -629,7 +629,7 @@ static int convert_tail_for_hole(struct inode *inode, unlock: if (tail_page != hole_page) { unlock_page(tail_page); - page_cache_release(tail_page); + put_page(tail_page); } out: return retval; @@ -2189,11 +2189,11 @@ static int grab_tail_page(struct inode *inode, * we want the page with the last byte in the file, * not the page that will hold the next byte for appending */ - unsigned long index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT; + unsigned long index = (inode->i_size - 1) >> PAGE_SHIFT; unsigned long pos = 0; unsigned long start = 0; unsigned long blocksize = inode->i_sb->s_blocksize; - unsigned long offset = (inode->i_size) & (PAGE_CACHE_SIZE - 1); + unsigned long offset = (inode->i_size) & (PAGE_SIZE - 1); struct buffer_head *bh; struct buffer_head *head; struct page *page; @@ -2251,7 +2251,7 @@ out: unlock: unlock_page(page); - page_cache_release(page); + put_page(page); return error; } @@ -2265,7 +2265,7 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps) { struct reiserfs_transaction_handle th; /* we want the offset for the first byte after the end of the file */ - unsigned long offset = inode->i_size & (PAGE_CACHE_SIZE - 1); + unsigned long offset = inode->i_size & (PAGE_SIZE - 1); unsigned blocksize = inode->i_sb->s_blocksize; unsigned length; struct page *page = NULL; @@ -2345,7 +2345,7 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps) } } unlock_page(page); - page_cache_release(page); + put_page(page); } reiserfs_write_unlock(inode->i_sb); @@ -2354,7 +2354,7 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps) out: if (page) { unlock_page(page); - page_cache_release(page); + put_page(page); } reiserfs_write_unlock(inode->i_sb); @@ -2426,7 +2426,7 @@ research: } else if (is_direct_le_ih(ih)) { char *p; p = page_address(bh_result->b_page); - p += (byte_offset - 1) & (PAGE_CACHE_SIZE - 1); + p += (byte_offset - 1) & (PAGE_SIZE - 1); copy_size = ih_item_len(ih) - pos_in_item; fs_gen = get_generation(inode->i_sb); @@ -2525,7 +2525,7 @@ static int reiserfs_write_full_page(struct page *page, struct writeback_control *wbc) { struct inode *inode = page->mapping->host; - unsigned long end_index = inode->i_size >> PAGE_CACHE_SHIFT; + unsigned long end_index = inode->i_size >> PAGE_SHIFT; int error = 0; unsigned long block; sector_t last_block; @@ -2535,7 +2535,7 @@ static int reiserfs_write_full_page(struct page *page, int checked = PageChecked(page); struct reiserfs_transaction_handle th; struct super_block *s = inode->i_sb; - int bh_per_page = PAGE_CACHE_SIZE / s->s_blocksize; + int bh_per_page = PAGE_SIZE / s->s_blocksize; th.t_trans_id = 0; /* no logging allowed when nonblocking or from PF_MEMALLOC */ @@ -2564,16 +2564,16 @@ static int reiserfs_write_full_page(struct page *page, if (page->index >= end_index) { unsigned last_offset; - last_offset = inode->i_size & (PAGE_CACHE_SIZE - 1); + last_offset = inode->i_size & (PAGE_SIZE - 1); /* no file contents in this page */ if (page->index >= end_index + 1 || !last_offset) { unlock_page(page); return 0; } - zero_user_segment(page, last_offset, PAGE_CACHE_SIZE); + zero_user_segment(page, last_offset, PAGE_SIZE); } bh = head; - block = page->index << (PAGE_CACHE_SHIFT - s->s_blocksize_bits); + block = page->index << (PAGE_SHIFT - s->s_blocksize_bits); last_block = (i_size_read(inode) - 1) >> inode->i_blkbits; /* first map all the buffers, logging any direct items we find */ do { @@ -2774,7 +2774,7 @@ static int reiserfs_write_begin(struct file *file, *fsdata = (void *)(unsigned long)flags; } - index = pos >> PAGE_CACHE_SHIFT; + index = pos >> PAGE_SHIFT; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; @@ -2822,7 +2822,7 @@ static int reiserfs_write_begin(struct file *file, } if (ret) { unlock_page(page); - page_cache_release(page); + put_page(page); /* Truncate allocated blocks */ reiserfs_truncate_failed_write(inode); } @@ -2909,7 +2909,7 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping, else th = NULL; - start = pos & (PAGE_CACHE_SIZE - 1); + start = pos & (PAGE_SIZE - 1); if (unlikely(copied < len)) { if (!PageUptodate(page)) copied = 0; @@ -2974,7 +2974,7 @@ out: if (locked) reiserfs_write_unlock(inode->i_sb); unlock_page(page); - page_cache_release(page); + put_page(page); if (pos + len > inode->i_size) reiserfs_truncate_failed_write(inode); @@ -2996,7 +2996,7 @@ int reiserfs_commit_write(struct file *f, struct page *page, unsigned from, unsigned to) { struct inode *inode = page->mapping->host; - loff_t pos = ((loff_t) page->index << PAGE_CACHE_SHIFT) + to; + loff_t pos = ((loff_t) page->index << PAGE_SHIFT) + to; int ret = 0; int update_sd = 0; struct reiserfs_transaction_handle *th = NULL; @@ -3181,7 +3181,7 @@ static void reiserfs_invalidatepage(struct page *page, unsigned int offset, struct inode *inode = page->mapping->host; unsigned int curr_off = 0; unsigned int stop = offset + length; - int partial_page = (offset || length < PAGE_CACHE_SIZE); + int partial_page = (offset || length < PAGE_SIZE); int ret = 1; BUG_ON(!PageLocked(page)); diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index 036a1fc0a8c3..57045f423893 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -203,7 +203,7 @@ int reiserfs_unpack(struct inode *inode, struct file *filp) * __reiserfs_write_begin on that page. This will force a * reiserfs_get_block to unpack the tail for us. */ - index = inode->i_size >> PAGE_CACHE_SHIFT; + index = inode->i_size >> PAGE_SHIFT; mapping = inode->i_mapping; page = grab_cache_page(mapping, index); retval = -ENOMEM; @@ -221,7 +221,7 @@ int reiserfs_unpack(struct inode *inode, struct file *filp) out_unlock: unlock_page(page); - page_cache_release(page); + put_page(page); out: inode_unlock(inode); diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 44c2bdced1c8..8c6487238bb3 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -605,12 +605,12 @@ static void release_buffer_page(struct buffer_head *bh) { struct page *page = bh->b_page; if (!page->mapping && trylock_page(page)) { - page_cache_get(page); + get_page(page); put_bh(bh); if (!page->mapping) try_to_free_buffers(page); unlock_page(page); - page_cache_release(page); + put_page(page); } else { put_bh(bh); } diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 24cbe013240f..5feacd689241 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -1342,7 +1342,7 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th, */ data = kmap_atomic(un_bh->b_page); - off = ((le_ih_k_offset(&s_ih) - 1) & (PAGE_CACHE_SIZE - 1)); + off = ((le_ih_k_offset(&s_ih) - 1) & (PAGE_SIZE - 1)); memcpy(data + off, ih_item_body(PATH_PLAST_BUFFER(path), &s_ih), ret_value); @@ -1511,7 +1511,7 @@ static void unmap_buffers(struct page *page, loff_t pos) if (page) { if (page_has_buffers(page)) { - tail_index = pos & (PAGE_CACHE_SIZE - 1); + tail_index = pos & (PAGE_SIZE - 1); cur_index = 0; head = page_buffers(page); bh = head; diff --git a/fs/reiserfs/tail_conversion.c b/fs/reiserfs/tail_conversion.c index f41e19b4bb42..2d5489b0a269 100644 --- a/fs/reiserfs/tail_conversion.c +++ b/fs/reiserfs/tail_conversion.c @@ -151,7 +151,7 @@ int direct2indirect(struct reiserfs_transaction_handle *th, struct inode *inode, */ if (up_to_date_bh) { unsigned pgoff = - (tail_offset + total_tail - 1) & (PAGE_CACHE_SIZE - 1); + (tail_offset + total_tail - 1) & (PAGE_SIZE - 1); char *kaddr = kmap_atomic(up_to_date_bh->b_page); memset(kaddr + pgoff, 0, blk_size - total_tail); kunmap_atomic(kaddr); @@ -271,7 +271,7 @@ int indirect2direct(struct reiserfs_transaction_handle *th, * the page was locked and this part of the page was up to date when * indirect2direct was called, so we know the bytes are still valid */ - tail = tail + (pos & (PAGE_CACHE_SIZE - 1)); + tail = tail + (pos & (PAGE_SIZE - 1)); PATH_LAST_POSITION(path)++; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 57e0b2310532..28f5f8b11370 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -415,7 +415,7 @@ out: static inline void reiserfs_put_page(struct page *page) { kunmap(page); - page_cache_release(page); + put_page(page); } static struct page *reiserfs_get_page(struct inode *dir, size_t n) @@ -427,7 +427,7 @@ static struct page *reiserfs_get_page(struct inode *dir, size_t n) * and an unlink/rmdir has just occurred - GFP_NOFS avoids this */ mapping_set_gfp_mask(mapping, GFP_NOFS); - page = read_mapping_page(mapping, n >> PAGE_CACHE_SHIFT, NULL); + page = read_mapping_page(mapping, n >> PAGE_SHIFT, NULL); if (!IS_ERR(page)) { kmap(page); if (PageError(page)) @@ -526,10 +526,10 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th, while (buffer_pos < buffer_size || buffer_pos == 0) { size_t chunk; size_t skip = 0; - size_t page_offset = (file_pos & (PAGE_CACHE_SIZE - 1)); + size_t page_offset = (file_pos & (PAGE_SIZE - 1)); - if (buffer_size - buffer_pos > PAGE_CACHE_SIZE) - chunk = PAGE_CACHE_SIZE; + if (buffer_size - buffer_pos > PAGE_SIZE) + chunk = PAGE_SIZE; else chunk = buffer_size - buffer_pos; @@ -546,8 +546,8 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th, struct reiserfs_xattr_header *rxh; skip = file_pos = sizeof(struct reiserfs_xattr_header); - if (chunk + skip > PAGE_CACHE_SIZE) - chunk = PAGE_CACHE_SIZE - skip; + if (chunk + skip > PAGE_SIZE) + chunk = PAGE_SIZE - skip; rxh = (struct reiserfs_xattr_header *)data; rxh->h_magic = cpu_to_le32(REISERFS_XATTR_MAGIC); rxh->h_hash = cpu_to_le32(xahash); @@ -675,8 +675,8 @@ reiserfs_xattr_get(struct inode *inode, const char *name, void *buffer, char *data; size_t skip = 0; - if (isize - file_pos > PAGE_CACHE_SIZE) - chunk = PAGE_CACHE_SIZE; + if (isize - file_pos > PAGE_SIZE) + chunk = PAGE_SIZE; else chunk = isize - file_pos; diff --git a/fs/splice.c b/fs/splice.c index 9947b5c69664..b018eb485019 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -88,7 +88,7 @@ out_unlock: static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - page_cache_release(buf->page); + put_page(buf->page); buf->flags &= ~PIPE_BUF_FLAG_LRU; } @@ -268,7 +268,7 @@ EXPORT_SYMBOL_GPL(splice_to_pipe); void spd_release_page(struct splice_pipe_desc *spd, unsigned int i) { - page_cache_release(spd->pages[i]); + put_page(spd->pages[i]); } /* @@ -328,9 +328,9 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, if (splice_grow_spd(pipe, &spd)) return -ENOMEM; - index = *ppos >> PAGE_CACHE_SHIFT; - loff = *ppos & ~PAGE_CACHE_MASK; - req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + index = *ppos >> PAGE_SHIFT; + loff = *ppos & ~PAGE_MASK; + req_pages = (len + loff + PAGE_SIZE - 1) >> PAGE_SHIFT; nr_pages = min(req_pages, spd.nr_pages_max); /* @@ -365,7 +365,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, error = add_to_page_cache_lru(page, mapping, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (unlikely(error)) { - page_cache_release(page); + put_page(page); if (error == -EEXIST) continue; break; @@ -385,7 +385,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, * Now loop over the map and see if we need to start IO on any * pages, fill in the partial map, etc. */ - index = *ppos >> PAGE_CACHE_SHIFT; + index = *ppos >> PAGE_SHIFT; nr_pages = spd.nr_pages; spd.nr_pages = 0; for (page_nr = 0; page_nr < nr_pages; page_nr++) { @@ -397,7 +397,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, /* * this_len is the max we'll use from this page */ - this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff); + this_len = min_t(unsigned long, len, PAGE_SIZE - loff); page = spd.pages[page_nr]; if (PageReadahead(page)) @@ -426,7 +426,7 @@ retry_lookup: error = -ENOMEM; break; } - page_cache_release(spd.pages[page_nr]); + put_page(spd.pages[page_nr]); spd.pages[page_nr] = page; } /* @@ -456,7 +456,7 @@ fill_it: * i_size must be checked after PageUptodate. */ isize = i_size_read(mapping->host); - end_index = (isize - 1) >> PAGE_CACHE_SHIFT; + end_index = (isize - 1) >> PAGE_SHIFT; if (unlikely(!isize || index > end_index)) break; @@ -470,7 +470,7 @@ fill_it: /* * max good bytes in this page */ - plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; + plen = ((isize - 1) & ~PAGE_MASK) + 1; if (plen <= loff) break; @@ -494,8 +494,8 @@ fill_it: * we got, 'nr_pages' is how many pages are in the map. */ while (page_nr < nr_pages) - page_cache_release(spd.pages[page_nr++]); - in->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT; + put_page(spd.pages[page_nr++]); + in->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT; if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); @@ -636,8 +636,8 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, goto shrink_ret; } - offset = *ppos & ~PAGE_CACHE_MASK; - nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + offset = *ppos & ~PAGE_MASK; + nr_pages = (len + offset + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) { struct page *page; @@ -647,7 +647,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, if (!page) goto err; - this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset); + this_len = min_t(size_t, len, PAGE_SIZE - offset); vec[i].iov_base = (void __user *) page_address(page); vec[i].iov_len = this_len; spd.pages[i] = page; diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 0cea9b9236d0..2c2618410d51 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -181,11 +181,11 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, in = min(bytes, msblk->devblksize - offset); bytes -= in; while (in) { - if (pg_offset == PAGE_CACHE_SIZE) { + if (pg_offset == PAGE_SIZE) { data = squashfs_next_page(output); pg_offset = 0; } - avail = min_t(int, in, PAGE_CACHE_SIZE - + avail = min_t(int, in, PAGE_SIZE - pg_offset); memcpy(data + pg_offset, bh[k]->b_data + offset, avail); diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index 1cb70a0b2168..27e501af0e8b 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -255,7 +255,7 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries, cache->unused = entries; cache->entries = entries; cache->block_size = block_size; - cache->pages = block_size >> PAGE_CACHE_SHIFT; + cache->pages = block_size >> PAGE_SHIFT; cache->pages = cache->pages ? cache->pages : 1; cache->name = name; cache->num_waiters = 0; @@ -275,7 +275,7 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries, } for (j = 0; j < cache->pages; j++) { - entry->data[j] = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL); + entry->data[j] = kmalloc(PAGE_SIZE, GFP_KERNEL); if (entry->data[j] == NULL) { ERROR("Failed to allocate %s buffer\n", name); goto cleanup; @@ -314,10 +314,10 @@ int squashfs_copy_data(void *buffer, struct squashfs_cache_entry *entry, return min(length, entry->length - offset); while (offset < entry->length) { - void *buff = entry->data[offset / PAGE_CACHE_SIZE] - + (offset % PAGE_CACHE_SIZE); + void *buff = entry->data[offset / PAGE_SIZE] + + (offset % PAGE_SIZE); int bytes = min_t(int, entry->length - offset, - PAGE_CACHE_SIZE - (offset % PAGE_CACHE_SIZE)); + PAGE_SIZE - (offset % PAGE_SIZE)); if (bytes >= remaining) { memcpy(buffer, buff, remaining); @@ -415,7 +415,7 @@ struct squashfs_cache_entry *squashfs_get_datablock(struct super_block *sb, */ void *squashfs_read_table(struct super_block *sb, u64 block, int length) { - int pages = (length + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + int pages = (length + PAGE_SIZE - 1) >> PAGE_SHIFT; int i, res; void *table, *buffer, **data; struct squashfs_page_actor *actor; @@ -436,7 +436,7 @@ void *squashfs_read_table(struct super_block *sb, u64 block, int length) goto failed2; } - for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE) + for (i = 0; i < pages; i++, buffer += PAGE_SIZE) data[i] = buffer; res = squashfs_read_data(sb, block, length | diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c index e9034bf6e5ae..d2bc13636f79 100644 --- a/fs/squashfs/decompressor.c +++ b/fs/squashfs/decompressor.c @@ -102,7 +102,7 @@ static void *get_comp_opts(struct super_block *sb, unsigned short flags) * Read decompressor specific options from file system if present */ if (SQUASHFS_COMP_OPTS(flags)) { - buffer = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL); + buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); if (buffer == NULL) { comp_opts = ERR_PTR(-ENOMEM); goto out; diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index e5c9689062ba..437de9e89221 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -175,7 +175,7 @@ static long long read_indexes(struct super_block *sb, int n, { int err, i; long long block = 0; - __le32 *blist = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL); + __le32 *blist = kmalloc(PAGE_SIZE, GFP_KERNEL); if (blist == NULL) { ERROR("read_indexes: Failed to allocate block_list\n"); @@ -183,7 +183,7 @@ static long long read_indexes(struct super_block *sb, int n, } while (n) { - int blocks = min_t(int, n, PAGE_CACHE_SIZE >> 2); + int blocks = min_t(int, n, PAGE_SIZE >> 2); err = squashfs_read_metadata(sb, blist, start_block, offset, blocks << 2); @@ -377,7 +377,7 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, struct inode *inode = page->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; void *pageaddr; - int i, mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1; + int i, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; int start_index = page->index & ~mask, end_index = start_index | mask; /* @@ -387,9 +387,9 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, * been called to fill. */ for (i = start_index; i <= end_index && bytes > 0; i++, - bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) { + bytes -= PAGE_SIZE, offset += PAGE_SIZE) { struct page *push_page; - int avail = buffer ? min_t(int, bytes, PAGE_CACHE_SIZE) : 0; + int avail = buffer ? min_t(int, bytes, PAGE_SIZE) : 0; TRACE("bytes %d, i %d, available_bytes %d\n", bytes, i, avail); @@ -404,14 +404,14 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, pageaddr = kmap_atomic(push_page); squashfs_copy_data(pageaddr, buffer, offset, avail); - memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail); + memset(pageaddr + avail, 0, PAGE_SIZE - avail); kunmap_atomic(pageaddr); flush_dcache_page(push_page); SetPageUptodate(push_page); skip_page: unlock_page(push_page); if (i != page->index) - page_cache_release(push_page); + put_page(push_page); } } @@ -454,7 +454,7 @@ static int squashfs_readpage(struct file *file, struct page *page) { struct inode *inode = page->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT); + int index = page->index >> (msblk->block_log - PAGE_SHIFT); int file_end = i_size_read(inode) >> msblk->block_log; int res; void *pageaddr; @@ -462,8 +462,8 @@ static int squashfs_readpage(struct file *file, struct page *page) TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n", page->index, squashfs_i(inode)->start); - if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT)) + if (page->index >= ((i_size_read(inode) + PAGE_SIZE - 1) >> + PAGE_SHIFT)) goto out; if (index < file_end || squashfs_i(inode)->fragment_block == @@ -487,7 +487,7 @@ error_out: SetPageError(page); out: pageaddr = kmap_atomic(page); - memset(pageaddr, 0, PAGE_CACHE_SIZE); + memset(pageaddr, 0, PAGE_SIZE); kunmap_atomic(pageaddr); flush_dcache_page(page); if (!PageError(page)) diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index 43e7a7eddac0..cb485d8e0e91 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -30,8 +30,8 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) struct inode *inode = target_page->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - int file_end = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT; - int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1; + int file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT; + int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; int start_index = target_page->index & ~mask; int end_index = start_index | mask; int i, n, pages, missing_pages, bytes, res = -ENOMEM; @@ -68,7 +68,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) if (PageUptodate(page[i])) { unlock_page(page[i]); - page_cache_release(page[i]); + put_page(page[i]); page[i] = NULL; missing_pages++; } @@ -96,10 +96,10 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) goto mark_errored; /* Last page may have trailing bytes not filled */ - bytes = res % PAGE_CACHE_SIZE; + bytes = res % PAGE_SIZE; if (bytes) { pageaddr = kmap_atomic(page[pages - 1]); - memset(pageaddr + bytes, 0, PAGE_CACHE_SIZE - bytes); + memset(pageaddr + bytes, 0, PAGE_SIZE - bytes); kunmap_atomic(pageaddr); } @@ -109,7 +109,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) SetPageUptodate(page[i]); unlock_page(page[i]); if (page[i] != target_page) - page_cache_release(page[i]); + put_page(page[i]); } kfree(actor); @@ -127,7 +127,7 @@ mark_errored: flush_dcache_page(page[i]); SetPageError(page[i]); unlock_page(page[i]); - page_cache_release(page[i]); + put_page(page[i]); } out: @@ -153,21 +153,21 @@ static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, } for (n = 0; n < pages && bytes > 0; n++, - bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) { - int avail = min_t(int, bytes, PAGE_CACHE_SIZE); + bytes -= PAGE_SIZE, offset += PAGE_SIZE) { + int avail = min_t(int, bytes, PAGE_SIZE); if (page[n] == NULL) continue; pageaddr = kmap_atomic(page[n]); squashfs_copy_data(pageaddr, buffer, offset, avail); - memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail); + memset(pageaddr + avail, 0, PAGE_SIZE - avail); kunmap_atomic(pageaddr); flush_dcache_page(page[n]); SetPageUptodate(page[n]); unlock_page(page[n]); if (page[n] != target_page) - page_cache_release(page[n]); + put_page(page[n]); } out: diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c index c31e2bc9c081..ff4468bd18b0 100644 --- a/fs/squashfs/lz4_wrapper.c +++ b/fs/squashfs/lz4_wrapper.c @@ -117,13 +117,13 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm, data = squashfs_first_page(output); buff = stream->output; while (data) { - if (bytes <= PAGE_CACHE_SIZE) { + if (bytes <= PAGE_SIZE) { memcpy(data, buff, bytes); break; } - memcpy(data, buff, PAGE_CACHE_SIZE); - buff += PAGE_CACHE_SIZE; - bytes -= PAGE_CACHE_SIZE; + memcpy(data, buff, PAGE_SIZE); + buff += PAGE_SIZE; + bytes -= PAGE_SIZE; data = squashfs_next_page(output); } squashfs_finish_page(output); diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c index 244b9fbfff7b..934c17e96590 100644 --- a/fs/squashfs/lzo_wrapper.c +++ b/fs/squashfs/lzo_wrapper.c @@ -102,13 +102,13 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm, data = squashfs_first_page(output); buff = stream->output; while (data) { - if (bytes <= PAGE_CACHE_SIZE) { + if (bytes <= PAGE_SIZE) { memcpy(data, buff, bytes); break; } else { - memcpy(data, buff, PAGE_CACHE_SIZE); - buff += PAGE_CACHE_SIZE; - bytes -= PAGE_CACHE_SIZE; + memcpy(data, buff, PAGE_SIZE); + buff += PAGE_SIZE; + bytes -= PAGE_SIZE; data = squashfs_next_page(output); } } diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c index 5a1c11f56441..9b7b1b6a7892 100644 --- a/fs/squashfs/page_actor.c +++ b/fs/squashfs/page_actor.c @@ -48,7 +48,7 @@ struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, if (actor == NULL) return NULL; - actor->length = length ? : pages * PAGE_CACHE_SIZE; + actor->length = length ? : pages * PAGE_SIZE; actor->buffer = buffer; actor->pages = pages; actor->next_page = 0; @@ -88,7 +88,7 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page, if (actor == NULL) return NULL; - actor->length = length ? : pages * PAGE_CACHE_SIZE; + actor->length = length ? : pages * PAGE_SIZE; actor->page = page; actor->pages = pages; actor->next_page = 0; diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h index 26dd82008b82..98537eab27e2 100644 --- a/fs/squashfs/page_actor.h +++ b/fs/squashfs/page_actor.h @@ -24,7 +24,7 @@ static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page, if (actor == NULL) return NULL; - actor->length = length ? : pages * PAGE_CACHE_SIZE; + actor->length = length ? : pages * PAGE_SIZE; actor->page = page; actor->pages = pages; actor->next_page = 0; diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 5e79bfa4f260..cf01e15a7b16 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -152,7 +152,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) * Check the system page size is not larger than the filesystem * block size (by default 128K). This is currently not supported. */ - if (PAGE_CACHE_SIZE > msblk->block_size) { + if (PAGE_SIZE > msblk->block_size) { ERROR("Page size > filesystem block size (%d). This is " "currently not supported!\n", msblk->block_size); goto failed_mount; diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c index dbcc2f54bad4..d688ef42a6a1 100644 --- a/fs/squashfs/symlink.c +++ b/fs/squashfs/symlink.c @@ -48,10 +48,10 @@ static int squashfs_symlink_readpage(struct file *file, struct page *page) struct inode *inode = page->mapping->host; struct super_block *sb = inode->i_sb; struct squashfs_sb_info *msblk = sb->s_fs_info; - int index = page->index << PAGE_CACHE_SHIFT; + int index = page->index << PAGE_SHIFT; u64 block = squashfs_i(inode)->start; int offset = squashfs_i(inode)->offset; - int length = min_t(int, i_size_read(inode) - index, PAGE_CACHE_SIZE); + int length = min_t(int, i_size_read(inode) - index, PAGE_SIZE); int bytes, copied; void *pageaddr; struct squashfs_cache_entry *entry; @@ -94,7 +94,7 @@ static int squashfs_symlink_readpage(struct file *file, struct page *page) copied = squashfs_copy_data(pageaddr + bytes, entry, offset, length - bytes); if (copied == length - bytes) - memset(pageaddr + length, 0, PAGE_CACHE_SIZE - length); + memset(pageaddr + length, 0, PAGE_SIZE - length); else block = entry->next_index; kunmap_atomic(pageaddr); diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c index c609624e4b8a..6bfaef73d065 100644 --- a/fs/squashfs/xz_wrapper.c +++ b/fs/squashfs/xz_wrapper.c @@ -141,7 +141,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, stream->buf.in_pos = 0; stream->buf.in_size = 0; stream->buf.out_pos = 0; - stream->buf.out_size = PAGE_CACHE_SIZE; + stream->buf.out_size = PAGE_SIZE; stream->buf.out = squashfs_first_page(output); do { @@ -158,7 +158,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, stream->buf.out = squashfs_next_page(output); if (stream->buf.out != NULL) { stream->buf.out_pos = 0; - total += PAGE_CACHE_SIZE; + total += PAGE_SIZE; } } diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c index 8727caba6882..2ec24d128bce 100644 --- a/fs/squashfs/zlib_wrapper.c +++ b/fs/squashfs/zlib_wrapper.c @@ -69,7 +69,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, int zlib_err, zlib_init = 0, k = 0; z_stream *stream = strm; - stream->avail_out = PAGE_CACHE_SIZE; + stream->avail_out = PAGE_SIZE; stream->next_out = squashfs_first_page(output); stream->avail_in = 0; @@ -85,7 +85,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, if (stream->avail_out == 0) { stream->next_out = squashfs_next_page(output); if (stream->next_out != NULL) - stream->avail_out = PAGE_CACHE_SIZE; + stream->avail_out = PAGE_SIZE; } if (!zlib_init) { diff --git a/fs/sync.c b/fs/sync.c index dd5d1711c7ac..2a54c1f22035 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -302,7 +302,7 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, goto out; if (sizeof(pgoff_t) == 4) { - if (offset >= (0x100000000ULL << PAGE_CACHE_SHIFT)) { + if (offset >= (0x100000000ULL << PAGE_SHIFT)) { /* * The range starts outside a 32 bit machine's * pagecache addressing capabilities. Let it "succeed" @@ -310,7 +310,7 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, ret = 0; goto out; } - if (endbyte >= (0x100000000ULL << PAGE_CACHE_SHIFT)) { + if (endbyte >= (0x100000000ULL << PAGE_SHIFT)) { /* * Out to EOF */ diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c index 63c1bcb224ee..c0f0a3e643eb 100644 --- a/fs/sysv/dir.c +++ b/fs/sysv/dir.c @@ -30,7 +30,7 @@ const struct file_operations sysv_dir_operations = { static inline void dir_put_page(struct page *page) { kunmap(page); - page_cache_release(page); + put_page(page); } static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len) @@ -73,8 +73,8 @@ static int sysv_readdir(struct file *file, struct dir_context *ctx) if (pos >= inode->i_size) return 0; - offset = pos & ~PAGE_CACHE_MASK; - n = pos >> PAGE_CACHE_SHIFT; + offset = pos & ~PAGE_MASK; + n = pos >> PAGE_SHIFT; for ( ; n < npages; n++, offset = 0) { char *kaddr, *limit; @@ -85,7 +85,7 @@ static int sysv_readdir(struct file *file, struct dir_context *ctx) continue; kaddr = (char *)page_address(page); de = (struct sysv_dir_entry *)(kaddr+offset); - limit = kaddr + PAGE_CACHE_SIZE - SYSV_DIRSIZE; + limit = kaddr + PAGE_SIZE - SYSV_DIRSIZE; for ( ;(char*)de <= limit; de++, ctx->pos += sizeof(*de)) { char *name = de->name; @@ -146,7 +146,7 @@ struct sysv_dir_entry *sysv_find_entry(struct dentry *dentry, struct page **res_ if (!IS_ERR(page)) { kaddr = (char*)page_address(page); de = (struct sysv_dir_entry *) kaddr; - kaddr += PAGE_CACHE_SIZE - SYSV_DIRSIZE; + kaddr += PAGE_SIZE - SYSV_DIRSIZE; for ( ; (char *) de <= kaddr ; de++) { if (!de->inode) continue; @@ -190,7 +190,7 @@ int sysv_add_link(struct dentry *dentry, struct inode *inode) goto out; kaddr = (char*)page_address(page); de = (struct sysv_dir_entry *)kaddr; - kaddr += PAGE_CACHE_SIZE - SYSV_DIRSIZE; + kaddr += PAGE_SIZE - SYSV_DIRSIZE; while ((char *)de <= kaddr) { if (!de->inode) goto got_it; @@ -261,7 +261,7 @@ int sysv_make_empty(struct inode *inode, struct inode *dir) kmap(page); base = (char*)page_address(page); - memset(base, 0, PAGE_CACHE_SIZE); + memset(base, 0, PAGE_SIZE); de = (struct sysv_dir_entry *) base; de->inode = cpu_to_fs16(SYSV_SB(inode->i_sb), inode->i_ino); @@ -273,7 +273,7 @@ int sysv_make_empty(struct inode *inode, struct inode *dir) kunmap(page); err = dir_commit_chunk(page, 0, 2 * SYSV_DIRSIZE); fail: - page_cache_release(page); + put_page(page); return err; } @@ -296,7 +296,7 @@ int sysv_empty_dir(struct inode * inode) kaddr = (char *)page_address(page); de = (struct sysv_dir_entry *)kaddr; - kaddr += PAGE_CACHE_SIZE-SYSV_DIRSIZE; + kaddr += PAGE_SIZE-SYSV_DIRSIZE; for ( ;(char *)de <= kaddr; de++) { if (!de->inode) diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index 11e83ed0b4bf..90b60c03b588 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -264,11 +264,11 @@ static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry, out_dir: if (dir_de) { kunmap(dir_page); - page_cache_release(dir_page); + put_page(dir_page); } out_old: kunmap(old_page); - page_cache_release(old_page); + put_page(old_page); out: return err; } diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 065c88f8e4b8..1a9c6640e604 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -121,7 +121,7 @@ static int do_readpage(struct page *page) if (block >= beyond) { /* Reading beyond inode */ SetPageChecked(page); - memset(addr, 0, PAGE_CACHE_SIZE); + memset(addr, 0, PAGE_SIZE); goto out; } @@ -223,7 +223,7 @@ static int write_begin_slow(struct address_space *mapping, { struct inode *inode = mapping->host; struct ubifs_info *c = inode->i_sb->s_fs_info; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; struct ubifs_budget_req req = { .new_page = 1 }; int uninitialized_var(err), appending = !!(pos + len > inode->i_size); struct page *page; @@ -254,13 +254,13 @@ static int write_begin_slow(struct address_space *mapping, } if (!PageUptodate(page)) { - if (!(pos & ~PAGE_CACHE_MASK) && len == PAGE_CACHE_SIZE) + if (!(pos & ~PAGE_MASK) && len == PAGE_SIZE) SetPageChecked(page); else { err = do_readpage(page); if (err) { unlock_page(page); - page_cache_release(page); + put_page(page); ubifs_release_budget(c, &req); return err; } @@ -428,7 +428,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; struct ubifs_info *c = inode->i_sb->s_fs_info; struct ubifs_inode *ui = ubifs_inode(inode); - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; int uninitialized_var(err), appending = !!(pos + len > inode->i_size); int skipped_read = 0; struct page *page; @@ -446,7 +446,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, if (!PageUptodate(page)) { /* The page is not loaded from the flash */ - if (!(pos & ~PAGE_CACHE_MASK) && len == PAGE_CACHE_SIZE) { + if (!(pos & ~PAGE_MASK) && len == PAGE_SIZE) { /* * We change whole page so no need to load it. But we * do not know whether this page exists on the media or @@ -462,7 +462,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, err = do_readpage(page); if (err) { unlock_page(page); - page_cache_release(page); + put_page(page); return err; } } @@ -494,7 +494,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, mutex_unlock(&ui->ui_mutex); } unlock_page(page); - page_cache_release(page); + put_page(page); return write_begin_slow(mapping, pos, len, pagep, flags); } @@ -549,7 +549,7 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, dbg_gen("ino %lu, pos %llu, pg %lu, len %u, copied %d, i_size %lld", inode->i_ino, pos, page->index, len, copied, inode->i_size); - if (unlikely(copied < len && len == PAGE_CACHE_SIZE)) { + if (unlikely(copied < len && len == PAGE_SIZE)) { /* * VFS copied less data to the page that it intended and * declared in its '->write_begin()' call via the @len @@ -593,7 +593,7 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, out: unlock_page(page); - page_cache_release(page); + put_page(page); return copied; } @@ -621,10 +621,10 @@ static int populate_page(struct ubifs_info *c, struct page *page, addr = zaddr = kmap(page); - end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; + end_index = (i_size - 1) >> PAGE_SHIFT; if (!i_size || page->index > end_index) { hole = 1; - memset(addr, 0, PAGE_CACHE_SIZE); + memset(addr, 0, PAGE_SIZE); goto out_hole; } @@ -673,7 +673,7 @@ static int populate_page(struct ubifs_info *c, struct page *page, } if (end_index == page->index) { - int len = i_size & (PAGE_CACHE_SIZE - 1); + int len = i_size & (PAGE_SIZE - 1); if (len && len < read) memset(zaddr + len, 0, read - len); @@ -773,7 +773,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu, isize = i_size_read(inode); if (isize == 0) goto out_free; - end_index = ((isize - 1) >> PAGE_CACHE_SHIFT); + end_index = ((isize - 1) >> PAGE_SHIFT); for (page_idx = 1; page_idx < page_cnt; page_idx++) { pgoff_t page_offset = offset + page_idx; @@ -788,7 +788,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu, if (!PageUptodate(page)) err = populate_page(c, page, bu, &n); unlock_page(page); - page_cache_release(page); + put_page(page); if (err) break; } @@ -905,7 +905,7 @@ static int do_writepage(struct page *page, int len) #ifdef UBIFS_DEBUG struct ubifs_inode *ui = ubifs_inode(inode); spin_lock(&ui->ui_lock); - ubifs_assert(page->index <= ui->synced_i_size >> PAGE_CACHE_SHIFT); + ubifs_assert(page->index <= ui->synced_i_size >> PAGE_SHIFT); spin_unlock(&ui->ui_lock); #endif @@ -1001,8 +1001,8 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) struct inode *inode = page->mapping->host; struct ubifs_inode *ui = ubifs_inode(inode); loff_t i_size = i_size_read(inode), synced_i_size; - pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; - int err, len = i_size & (PAGE_CACHE_SIZE - 1); + pgoff_t end_index = i_size >> PAGE_SHIFT; + int err, len = i_size & (PAGE_SIZE - 1); void *kaddr; dbg_gen("ino %lu, pg %lu, pg flags %#lx", @@ -1021,7 +1021,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) /* Is the page fully inside @i_size? */ if (page->index < end_index) { - if (page->index >= synced_i_size >> PAGE_CACHE_SHIFT) { + if (page->index >= synced_i_size >> PAGE_SHIFT) { err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) goto out_unlock; @@ -1034,7 +1034,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) * with this. */ } - return do_writepage(page, PAGE_CACHE_SIZE); + return do_writepage(page, PAGE_SIZE); } /* @@ -1045,7 +1045,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) * writes to that region are not written out to the file." */ kaddr = kmap_atomic(page); - memset(kaddr + len, 0, PAGE_CACHE_SIZE - len); + memset(kaddr + len, 0, PAGE_SIZE - len); flush_dcache_page(page); kunmap_atomic(kaddr); @@ -1138,7 +1138,7 @@ static int do_truncation(struct ubifs_info *c, struct inode *inode, truncate_setsize(inode, new_size); if (offset) { - pgoff_t index = new_size >> PAGE_CACHE_SHIFT; + pgoff_t index = new_size >> PAGE_SHIFT; struct page *page; page = find_lock_page(inode->i_mapping, index); @@ -1157,9 +1157,9 @@ static int do_truncation(struct ubifs_info *c, struct inode *inode, clear_page_dirty_for_io(page); if (UBIFS_BLOCKS_PER_PAGE_SHIFT) offset = new_size & - (PAGE_CACHE_SIZE - 1); + (PAGE_SIZE - 1); err = do_writepage(page, offset); - page_cache_release(page); + put_page(page); if (err) goto out_budg; /* @@ -1173,7 +1173,7 @@ static int do_truncation(struct ubifs_info *c, struct inode *inode, * having to read it. */ unlock_page(page); - page_cache_release(page); + put_page(page); } } } @@ -1285,7 +1285,7 @@ static void ubifs_invalidatepage(struct page *page, unsigned int offset, struct ubifs_info *c = inode->i_sb->s_fs_info; ubifs_assert(PagePrivate(page)); - if (offset || length < PAGE_CACHE_SIZE) + if (offset || length < PAGE_SIZE) /* Partial page remains dirty */ return; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index a233ba913be4..20daea9aa657 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2240,9 +2240,9 @@ static int __init ubifs_init(void) * We require that PAGE_CACHE_SIZE is greater-than-or-equal-to * UBIFS_BLOCK_SIZE. It is assumed that both are powers of 2. */ - if (PAGE_CACHE_SIZE < UBIFS_BLOCK_SIZE) { + if (PAGE_SIZE < UBIFS_BLOCK_SIZE) { pr_err("UBIFS error (pid %d): VFS page cache size is %u bytes, but UBIFS requires at least 4096 bytes", - current->pid, (unsigned int)PAGE_CACHE_SIZE); + current->pid, (unsigned int)PAGE_SIZE); return -EINVAL; } diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index c2a57e193a81..4cd7e569cd00 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -46,8 +46,8 @@ #define UBIFS_SUPER_MAGIC 0x24051905 /* Number of UBIFS blocks per VFS page */ -#define UBIFS_BLOCKS_PER_PAGE (PAGE_CACHE_SIZE / UBIFS_BLOCK_SIZE) -#define UBIFS_BLOCKS_PER_PAGE_SHIFT (PAGE_CACHE_SHIFT - UBIFS_BLOCK_SHIFT) +#define UBIFS_BLOCKS_PER_PAGE (PAGE_SIZE / UBIFS_BLOCK_SIZE) +#define UBIFS_BLOCKS_PER_PAGE_SHIFT (PAGE_SHIFT - UBIFS_BLOCK_SHIFT) /* "File system end of life" sequence number watermark */ #define SQNUM_WARN_WATERMARK 0xFFFFFFFF00000000ULL diff --git a/fs/udf/file.c b/fs/udf/file.c index 1af98963d860..877ba1c9b461 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -46,7 +46,7 @@ static void __udf_adinicb_readpage(struct page *page) kaddr = kmap(page); memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, inode->i_size); - memset(kaddr + inode->i_size, 0, PAGE_CACHE_SIZE - inode->i_size); + memset(kaddr + inode->i_size, 0, PAGE_SIZE - inode->i_size); flush_dcache_page(page); SetPageUptodate(page); kunmap(page); @@ -87,14 +87,14 @@ static int udf_adinicb_write_begin(struct file *file, { struct page *page; - if (WARN_ON_ONCE(pos >= PAGE_CACHE_SIZE)) + if (WARN_ON_ONCE(pos >= PAGE_SIZE)) return -EIO; page = grab_cache_page_write_begin(mapping, 0, flags); if (!page) return -ENOMEM; *pagep = page; - if (!PageUptodate(page) && len != PAGE_CACHE_SIZE) + if (!PageUptodate(page) && len != PAGE_SIZE) __udf_adinicb_readpage(page); return 0; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 166d3ed32c39..2dc461eeb415 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -287,7 +287,7 @@ int udf_expand_file_adinicb(struct inode *inode) if (!PageUptodate(page)) { kaddr = kmap(page); memset(kaddr + iinfo->i_lenAlloc, 0x00, - PAGE_CACHE_SIZE - iinfo->i_lenAlloc); + PAGE_SIZE - iinfo->i_lenAlloc); memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, iinfo->i_lenAlloc); flush_dcache_page(page); @@ -319,7 +319,7 @@ int udf_expand_file_adinicb(struct inode *inode) inode->i_data.a_ops = &udf_adinicb_aops; up_write(&iinfo->i_data_sem); } - page_cache_release(page); + put_page(page); mark_inode_dirty(inode); return err; diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index dc5fae601c24..0447b949c7f5 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -237,7 +237,7 @@ static void ufs_change_blocknr(struct inode *inode, sector_t beg, sector_t newb, struct page *locked_page) { const unsigned blks_per_page = - 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits); + 1 << (PAGE_SHIFT - inode->i_blkbits); const unsigned mask = blks_per_page - 1; struct address_space * const mapping = inode->i_mapping; pgoff_t index, cur_index, last_index; @@ -255,9 +255,9 @@ static void ufs_change_blocknr(struct inode *inode, sector_t beg, cur_index = locked_page->index; end = count + beg; - last_index = end >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + last_index = end >> (PAGE_SHIFT - inode->i_blkbits); for (i = beg; i < end; i = (i | mask) + 1) { - index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + index = i >> (PAGE_SHIFT - inode->i_blkbits); if (likely(cur_index != index)) { page = ufs_get_locked_page(mapping, index); diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index 74f2e80288bf..0b1457292734 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -62,7 +62,7 @@ static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len) static inline void ufs_put_page(struct page *page) { kunmap(page); - page_cache_release(page); + put_page(page); } ino_t ufs_inode_by_name(struct inode *dir, const struct qstr *qstr) @@ -111,13 +111,13 @@ static void ufs_check_page(struct page *page) struct super_block *sb = dir->i_sb; char *kaddr = page_address(page); unsigned offs, rec_len; - unsigned limit = PAGE_CACHE_SIZE; + unsigned limit = PAGE_SIZE; const unsigned chunk_mask = UFS_SB(sb)->s_uspi->s_dirblksize - 1; struct ufs_dir_entry *p; char *error; - if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) { - limit = dir->i_size & ~PAGE_CACHE_MASK; + if ((dir->i_size >> PAGE_SHIFT) == page->index) { + limit = dir->i_size & ~PAGE_MASK; if (limit & chunk_mask) goto Ebadsize; if (!limit) @@ -170,7 +170,7 @@ Einumber: bad_entry: ufs_error (sb, "ufs_check_page", "bad entry in directory #%lu: %s - " "offset=%lu, rec_len=%d, name_len=%d", - dir->i_ino, error, (page->index<i_ino, error, (page->index<i_ino, (page->index<i_ino, (page->index<i_size; - last_byte -= page_nr << PAGE_CACHE_SHIFT; - if (last_byte > PAGE_CACHE_SIZE) - last_byte = PAGE_CACHE_SIZE; + last_byte -= page_nr << PAGE_SHIFT; + if (last_byte > PAGE_SIZE) + last_byte = PAGE_SIZE; return last_byte; } @@ -341,7 +341,7 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode) kaddr = page_address(page); dir_end = kaddr + ufs_last_byte(dir, n); de = (struct ufs_dir_entry *)kaddr; - kaddr += PAGE_CACHE_SIZE - reclen; + kaddr += PAGE_SIZE - reclen; while ((char *)de <= kaddr) { if ((char *)de == dir_end) { /* We hit i_size */ @@ -432,8 +432,8 @@ ufs_readdir(struct file *file, struct dir_context *ctx) loff_t pos = ctx->pos; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; - unsigned int offset = pos & ~PAGE_CACHE_MASK; - unsigned long n = pos >> PAGE_CACHE_SHIFT; + unsigned int offset = pos & ~PAGE_MASK; + unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); unsigned chunk_mask = ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1); int need_revalidate = file->f_version != inode->i_version; @@ -454,14 +454,14 @@ ufs_readdir(struct file *file, struct dir_context *ctx) ufs_error(sb, __func__, "bad page in #%lu", inode->i_ino); - ctx->pos += PAGE_CACHE_SIZE - offset; + ctx->pos += PAGE_SIZE - offset; return -EIO; } kaddr = page_address(page); if (unlikely(need_revalidate)) { if (offset) { offset = ufs_validate_entry(sb, kaddr, offset, chunk_mask); - ctx->pos = (n<pos = (n<f_version = inode->i_version; need_revalidate = 0; @@ -574,7 +574,7 @@ int ufs_make_empty(struct inode * inode, struct inode *dir) kmap(page); base = (char*)page_address(page); - memset(base, 0, PAGE_CACHE_SIZE); + memset(base, 0, PAGE_SIZE); de = (struct ufs_dir_entry *) base; @@ -594,7 +594,7 @@ int ufs_make_empty(struct inode * inode, struct inode *dir) err = ufs_commit_chunk(page, 0, chunk_size); fail: - page_cache_release(page); + put_page(page); return err; } diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index d897e169ab9c..9f49431e798d 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -1051,13 +1051,13 @@ static int ufs_alloc_lastblock(struct inode *inode, loff_t size) lastfrag--; lastpage = ufs_get_locked_page(mapping, lastfrag >> - (PAGE_CACHE_SHIFT - inode->i_blkbits)); + (PAGE_SHIFT - inode->i_blkbits)); if (IS_ERR(lastpage)) { err = -EIO; goto out; } - end = lastfrag & ((1 << (PAGE_CACHE_SHIFT - inode->i_blkbits)) - 1); + end = lastfrag & ((1 << (PAGE_SHIFT - inode->i_blkbits)) - 1); bh = page_buffers(lastpage); for (i = 0; i < end; ++i) bh = bh->b_this_page; diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index acf4a3b61b81..a1559f762805 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -305,7 +305,7 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry, ufs_set_link(old_inode, dir_de, dir_page, new_dir, 0); else { kunmap(dir_page); - page_cache_release(dir_page); + put_page(dir_page); } inode_dec_link_count(old_dir); } @@ -315,11 +315,11 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry, out_dir: if (dir_de) { kunmap(dir_page); - page_cache_release(dir_page); + put_page(dir_page); } out_old: kunmap(old_page); - page_cache_release(old_page); + put_page(old_page); out: return err; } diff --git a/fs/ufs/util.c b/fs/ufs/util.c index b6c2f94e041e..a409e3e7827a 100644 --- a/fs/ufs/util.c +++ b/fs/ufs/util.c @@ -261,14 +261,14 @@ struct page *ufs_get_locked_page(struct address_space *mapping, if (unlikely(page->mapping == NULL)) { /* Truncate got there first */ unlock_page(page); - page_cache_release(page); + put_page(page); page = NULL; goto out; } if (!PageUptodate(page) || PageError(page)) { unlock_page(page); - page_cache_release(page); + put_page(page); printk(KERN_ERR "ufs_change_blocknr: " "can not read page: ino %lu, index: %lu\n", diff --git a/fs/ufs/util.h b/fs/ufs/util.h index 954175928240..b7fbf53dbc81 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -283,7 +283,7 @@ extern struct page *ufs_get_locked_page(struct address_space *mapping, static inline void ufs_put_locked_page(struct page *page) { unlock_page(page); - page_cache_release(page); + put_page(page); } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 041b6948aecc..ce41d7fe753c 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3742,11 +3742,11 @@ xfs_bmap_btalloc( args.prod = align; if ((args.mod = (xfs_extlen_t)do_mod(ap->offset, args.prod))) args.mod = (xfs_extlen_t)(args.prod - args.mod); - } else if (mp->m_sb.sb_blocksize >= PAGE_CACHE_SIZE) { + } else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) { args.prod = 1; args.mod = 0; } else { - args.prod = PAGE_CACHE_SIZE >> mp->m_sb.sb_blocklog; + args.prod = PAGE_SIZE >> mp->m_sb.sb_blocklog; if ((args.mod = (xfs_extlen_t)(do_mod(ap->offset, args.prod)))) args.mod = (xfs_extlen_t)(args.prod - args.mod); } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index d445a64b979e..5b8ae03ba855 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -704,7 +704,7 @@ next_buffer: xfs_iunlock(ip, XFS_ILOCK_EXCL); out_invalidate: - xfs_vm_invalidatepage(page, 0, PAGE_CACHE_SIZE); + xfs_vm_invalidatepage(page, 0, PAGE_SIZE); return; } @@ -925,9 +925,9 @@ xfs_do_writepage( * ---------------------------------^------------------| */ offset = i_size_read(inode); - end_index = offset >> PAGE_CACHE_SHIFT; + end_index = offset >> PAGE_SHIFT; if (page->index < end_index) - end_offset = (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT; + end_offset = (xfs_off_t)(page->index + 1) << PAGE_SHIFT; else { /* * Check whether the page to write out is beyond or straddles @@ -940,7 +940,7 @@ xfs_do_writepage( * | | Straddles | * ---------------------------------^-----------|--------| */ - unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1); + unsigned offset_into_page = offset & (PAGE_SIZE - 1); /* * Skip the page if it is fully outside i_size, e.g. due to a @@ -971,7 +971,7 @@ xfs_do_writepage( * memory is zeroed when mapped, and writes to that region are * not written out to the file." */ - zero_user_segment(page, offset_into_page, PAGE_CACHE_SIZE); + zero_user_segment(page, offset_into_page, PAGE_SIZE); /* Adjust the end_offset to the end of file */ end_offset = offset; @@ -1475,7 +1475,7 @@ xfs_vm_write_failed( loff_t block_offset; loff_t block_start; loff_t block_end; - loff_t from = pos & (PAGE_CACHE_SIZE - 1); + loff_t from = pos & (PAGE_SIZE - 1); loff_t to = from + len; struct buffer_head *bh, *head; struct xfs_mount *mp = XFS_I(inode)->i_mount; @@ -1491,7 +1491,7 @@ xfs_vm_write_failed( * start of the page by using shifts rather than masks the mismatch * problem. */ - block_offset = (pos >> PAGE_CACHE_SHIFT) << PAGE_CACHE_SHIFT; + block_offset = (pos >> PAGE_SHIFT) << PAGE_SHIFT; ASSERT(block_offset + from == pos); @@ -1558,7 +1558,7 @@ xfs_vm_write_begin( struct page **pagep, void **fsdata) { - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int status; struct xfs_mount *mp = XFS_I(mapping->host)->i_mount; @@ -1592,7 +1592,7 @@ xfs_vm_write_begin( truncate_pagecache_range(inode, start, pos + len); } - page_cache_release(page); + put_page(page); page = NULL; } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index a32c1dcae2ff..3b6309865c65 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1237,7 +1237,7 @@ xfs_free_file_space( /* wait for the completion of any pending DIOs */ inode_dio_wait(VFS_I(ip)); - rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE); + rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_SIZE); ioffset = round_down(offset, rounding); iendoffset = round_up(offset + len, rounding) - 1; error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, ioffset, @@ -1466,7 +1466,7 @@ xfs_shift_file_space( if (error) return error; error = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, - offset >> PAGE_CACHE_SHIFT, -1); + offset >> PAGE_SHIFT, -1); if (error) return error; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ac0fd32de31e..569938a4a357 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -106,8 +106,8 @@ xfs_iozero( unsigned offset, bytes; void *fsdata; - offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */ - bytes = PAGE_CACHE_SIZE - offset; + offset = (pos & (PAGE_SIZE -1)); /* Within page */ + bytes = PAGE_SIZE - offset; if (bytes > count) bytes = count; @@ -799,8 +799,8 @@ xfs_file_dio_aio_write( /* see generic_file_direct_write() for why this is necessary */ if (mapping->nrpages) { invalidate_inode_pages2_range(mapping, - pos >> PAGE_CACHE_SHIFT, - end >> PAGE_CACHE_SHIFT); + pos >> PAGE_SHIFT, + end >> PAGE_SHIFT); } if (ret > 0) { @@ -1207,9 +1207,9 @@ xfs_find_get_desired_pgoff( pagevec_init(&pvec, 0); - index = startoff >> PAGE_CACHE_SHIFT; + index = startoff >> PAGE_SHIFT; endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount); - end = endoff >> PAGE_CACHE_SHIFT; + end = endoff >> PAGE_SHIFT; do { int want; unsigned nr_pages; diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index ec0e239a0fa9..a8192dc797dc 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -135,7 +135,7 @@ typedef __u32 xfs_nlink_t; * Size of block device i/o is parameterized here. * Currently the system supports page-sized i/o. */ -#define BLKDEV_IOSHIFT PAGE_CACHE_SHIFT +#define BLKDEV_IOSHIFT PAGE_SHIFT #define BLKDEV_IOSIZE (1<sb_blocklog >= BBSHIFT); /* Limited by ULONG_MAX of page cache index */ - if (nblocks >> (PAGE_CACHE_SHIFT - sbp->sb_blocklog) > ULONG_MAX) + if (nblocks >> (PAGE_SHIFT - sbp->sb_blocklog) > ULONG_MAX) return -EFBIG; return 0; } diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index bac6b3435591..eafe257b357a 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -231,12 +231,12 @@ static inline unsigned long xfs_preferred_iosize(xfs_mount_t *mp) { if (mp->m_flags & XFS_MOUNT_COMPAT_IOSIZE) - return PAGE_CACHE_SIZE; + return PAGE_SIZE; return (mp->m_swidth ? (mp->m_swidth << mp->m_sb.sb_blocklog) : ((mp->m_flags & XFS_MOUNT_DFLT_IOSIZE) ? (1 << (int)MAX(mp->m_readio_log, mp->m_writeio_log)) : - PAGE_CACHE_SIZE)); + PAGE_SIZE)); } #define XFS_LAST_UNMOUNT_WAS_CLEAN(mp) \ diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index ade236e90bb3..51ddaf2c2b8c 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -293,8 +293,8 @@ xfs_fs_commit_blocks( * Make sure reads through the pagecache see the new data. */ error = invalidate_inode_pages2_range(inode->i_mapping, - start >> PAGE_CACHE_SHIFT, - (end - 1) >> PAGE_CACHE_SHIFT); + start >> PAGE_SHIFT, + (end - 1) >> PAGE_SHIFT); WARN_ON_ONCE(error); error = xfs_iomap_write_unwritten(ip, start, length); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index d760934109b5..6082f54e0557 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -570,10 +570,10 @@ xfs_max_file_offset( #if BITS_PER_LONG == 32 # if defined(CONFIG_LBDAF) ASSERT(sizeof(sector_t) == 8); - pagefactor = PAGE_CACHE_SIZE; + pagefactor = PAGE_SIZE; bitshift = BITS_PER_LONG; # else - pagefactor = PAGE_CACHE_SIZE >> (PAGE_CACHE_SHIFT - blockshift); + pagefactor = PAGE_SIZE >> (PAGE_SHIFT - blockshift); # endif #endif diff --git a/include/linux/bio.h b/include/linux/bio.h index 88bc64f00bb5..6b7481f62218 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -41,7 +41,7 @@ #endif #define BIO_MAX_PAGES 256 -#define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_CACHE_SHIFT) +#define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_SHIFT) #define BIO_MAX_SECTORS (BIO_MAX_SIZE >> 9) /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7e5d7e018bea..669e419d6234 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1372,7 +1372,7 @@ unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *); static inline void put_dev_sector(Sector p) { - page_cache_release(p.v); + put_page(p.v); } static inline bool __bvec_gap_to_prev(struct request_queue *q, diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index c67f052cc5e5..d48daa3f6f20 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -43,7 +43,7 @@ enum bh_state_bits { */ }; -#define MAX_BUF_PER_PAGE (PAGE_CACHE_SIZE / 512) +#define MAX_BUF_PER_PAGE (PAGE_SIZE / 512) struct page; struct buffer_head; @@ -263,7 +263,7 @@ void buffer_init(void); static inline void attach_page_buffers(struct page *page, struct buffer_head *head) { - page_cache_get(page); + get_page(page); SetPagePrivate(page); set_page_private(page, (unsigned long)head); } diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index e7975e4681e1..db92a8d4926e 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -176,8 +176,8 @@ extern void ceph_put_snap_context(struct ceph_snap_context *sc); */ static inline int calc_pages_for(u64 off, u64 len) { - return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) - - (off >> PAGE_CACHE_SHIFT); + return ((off+len+PAGE_SIZE-1) >> PAGE_SHIFT) - + (off >> PAGE_SHIFT); } extern struct kmem_cache *ceph_inode_cachep; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 9eb215a155e0..b90e9bdbd1dd 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -262,7 +262,7 @@ struct f2fs_node { /* * For NAT entries */ -#define NAT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_nat_entry)) +#define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry)) struct f2fs_nat_entry { __u8 version; /* latest version of cached nat entry */ @@ -282,7 +282,7 @@ struct f2fs_nat_block { * Not allow to change this. */ #define SIT_VBLOCK_MAP_SIZE 64 -#define SIT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_sit_entry)) +#define SIT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_sit_entry)) /* * Note that f2fs_sit_entry->vblocks has the following bit-field information. diff --git a/include/linux/fs.h b/include/linux/fs.h index 14a97194b34b..304991a80e23 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -929,7 +929,7 @@ static inline struct file *get_file(struct file *f) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 -#define MAX_LFS_FILESIZE (((loff_t)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) +#define MAX_LFS_FILESIZE (((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL) #endif @@ -2067,7 +2067,7 @@ extern int generic_update_time(struct inode *, struct timespec *, int); /* /sys/fs */ extern struct kobject *fs_kobj; -#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK) +#define MAX_RW_COUNT (INT_MAX & PAGE_MASK) #ifdef CONFIG_MANDATORY_FILE_LOCKING extern int locks_mandatory_locked(struct file *); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index f2f650f136ee..efada239205e 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -184,7 +184,7 @@ nfs_list_entry(struct list_head *head) static inline loff_t req_offset(struct nfs_page *req) { - return (((loff_t)req->wb_index) << PAGE_CACHE_SHIFT) + req->wb_offset; + return (((loff_t)req->wb_index) << PAGE_SHIFT) + req->wb_offset; } #endif /* _LINUX_NFS_PAGE_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1ebd65c91422..f396ccb900cc 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -390,13 +390,13 @@ static inline pgoff_t page_to_pgoff(struct page *page) return page->index << compound_order(page); if (likely(!PageTransTail(page))) - return page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + return page->index; /* * We don't initialize ->index for tail pages: calculate based on * head page */ - pgoff = compound_head(page)->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff = compound_head(page)->index; pgoff += page - compound_head(page); return pgoff; } @@ -406,12 +406,12 @@ static inline pgoff_t page_to_pgoff(struct page *page) */ static inline loff_t page_offset(struct page *page) { - return ((loff_t)page->index) << PAGE_CACHE_SHIFT; + return ((loff_t)page->index) << PAGE_SHIFT; } static inline loff_t page_file_offset(struct page *page) { - return ((loff_t)page_file_index(page)) << PAGE_CACHE_SHIFT; + return ((loff_t)page_file_index(page)) << PAGE_SHIFT; } extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, @@ -425,7 +425,7 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, return linear_hugepage_index(vma, address); pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; - return pgoff >> (PAGE_CACHE_SHIFT - PAGE_SHIFT); + return pgoff; } extern void __lock_page(struct page *page); @@ -671,8 +671,8 @@ static inline int add_to_page_cache(struct page *page, static inline unsigned long dir_pages(struct inode *inode) { - return (unsigned long)(inode->i_size + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> + PAGE_SHIFT; } #endif /* _LINUX_PAGEMAP_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index d18b65c53dbb..3d980ea1c946 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -435,7 +435,7 @@ struct backing_dev_info; /* only sparc can not include linux/pagemap.h in this file * so leave page_cache_release and release_pages undeclared... */ #define free_page_and_swap_cache(page) \ - page_cache_release(page) + put_page(page) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr), false); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 781c1399c6a3..ade739f67f1d 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -307,8 +307,8 @@ static int mqueue_fill_super(struct super_block *sb, void *data, int silent) struct inode *inode; struct ipc_namespace *ns = data; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = MQUEUE_MAGIC; sb->s_op = &mqueue_super_ops; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 220fc17b9718..7edc95edfaee 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -321,7 +321,7 @@ retry: copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); ret = __replace_page(vma, vaddr, old_page, new_page); - page_cache_release(new_page); + put_page(new_page); put_old: put_page(old_page); @@ -539,14 +539,14 @@ static int __copy_insn(struct address_space *mapping, struct file *filp, * see uprobe_register(). */ if (mapping->a_ops->readpage) - page = read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT, filp); + page = read_mapping_page(mapping, offset >> PAGE_SHIFT, filp); else - page = shmem_read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT); + page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) return PTR_ERR(page); copy_from_page(page, offset, insn, nbytes); - page_cache_release(page); + put_page(page); return 0; } diff --git a/mm/fadvise.c b/mm/fadvise.c index b8a5bc66b0c0..b8024fa7101d 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -97,8 +97,8 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) break; case POSIX_FADV_WILLNEED: /* First and last PARTIAL page! */ - start_index = offset >> PAGE_CACHE_SHIFT; - end_index = endbyte >> PAGE_CACHE_SHIFT; + start_index = offset >> PAGE_SHIFT; + end_index = endbyte >> PAGE_SHIFT; /* Careful about overflow on the "+1" */ nrpages = end_index - start_index + 1; @@ -124,8 +124,8 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) * preserved on the expectation that it is better to preserve * needed memory than to discard unneeded memory. */ - start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT; - end_index = (endbyte >> PAGE_CACHE_SHIFT); + start_index = (offset+(PAGE_SIZE-1)) >> PAGE_SHIFT; + end_index = (endbyte >> PAGE_SHIFT); if (end_index >= start_index) { unsigned long count = invalidate_mapping_pages(mapping, diff --git a/mm/filemap.c b/mm/filemap.c index a8c69c8c0a90..f2479af09da9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -265,7 +265,7 @@ void delete_from_page_cache(struct page *page) if (freepage) freepage(page); - page_cache_release(page); + put_page(page); } EXPORT_SYMBOL(delete_from_page_cache); @@ -352,8 +352,8 @@ EXPORT_SYMBOL(filemap_flush); static int __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { - pgoff_t index = start_byte >> PAGE_CACHE_SHIFT; - pgoff_t end = end_byte >> PAGE_CACHE_SHIFT; + pgoff_t index = start_byte >> PAGE_SHIFT; + pgoff_t end = end_byte >> PAGE_SHIFT; struct pagevec pvec; int nr_pages; int ret = 0; @@ -550,7 +550,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) pgoff_t offset = old->index; freepage = mapping->a_ops->freepage; - page_cache_get(new); + get_page(new); new->mapping = mapping; new->index = offset; @@ -572,7 +572,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) radix_tree_preload_end(); if (freepage) freepage(old); - page_cache_release(old); + put_page(old); } return error; @@ -651,7 +651,7 @@ static int __add_to_page_cache_locked(struct page *page, return error; } - page_cache_get(page); + get_page(page); page->mapping = mapping; page->index = offset; @@ -675,7 +675,7 @@ err_insert: spin_unlock_irq(&mapping->tree_lock); if (!huge) mem_cgroup_cancel_charge(page, memcg, false); - page_cache_release(page); + put_page(page); return error; } @@ -1083,7 +1083,7 @@ repeat: * include/linux/pagemap.h for details. */ if (unlikely(page != *pagep)) { - page_cache_release(page); + put_page(page); goto repeat; } } @@ -1121,7 +1121,7 @@ repeat: /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); - page_cache_release(page); + put_page(page); goto repeat; } VM_BUG_ON_PAGE(page->index != offset, page); @@ -1168,7 +1168,7 @@ repeat: if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!trylock_page(page)) { - page_cache_release(page); + put_page(page); return NULL; } } else { @@ -1178,7 +1178,7 @@ repeat: /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); - page_cache_release(page); + put_page(page); goto repeat; } VM_BUG_ON_PAGE(page->index != offset, page); @@ -1209,7 +1209,7 @@ no_page: err = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_RECLAIM_MASK); if (unlikely(err)) { - page_cache_release(page); + put_page(page); page = NULL; if (err == -EEXIST) goto repeat; @@ -1278,7 +1278,7 @@ repeat: /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(page); goto repeat; } export: @@ -1343,7 +1343,7 @@ repeat: /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(page); goto repeat; } @@ -1405,7 +1405,7 @@ repeat: /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(page); goto repeat; } @@ -1415,7 +1415,7 @@ repeat: * negatives, which is just confusing to the caller. */ if (page->mapping == NULL || page->index != iter.index) { - page_cache_release(page); + put_page(page); break; } @@ -1482,7 +1482,7 @@ repeat: /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(page); goto repeat; } @@ -1549,7 +1549,7 @@ repeat: /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(page); goto repeat; } export: @@ -1610,11 +1610,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos, unsigned int prev_offset; int error = 0; - index = *ppos >> PAGE_CACHE_SHIFT; - prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT; - prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1); - last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; - offset = *ppos & ~PAGE_CACHE_MASK; + index = *ppos >> PAGE_SHIFT; + prev_index = ra->prev_pos >> PAGE_SHIFT; + prev_offset = ra->prev_pos & (PAGE_SIZE-1); + last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT; + offset = *ppos & ~PAGE_MASK; for (;;) { struct page *page; @@ -1648,7 +1648,7 @@ find_page: if (PageUptodate(page)) goto page_ok; - if (inode->i_blkbits == PAGE_CACHE_SHIFT || + if (inode->i_blkbits == PAGE_SHIFT || !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; if (!trylock_page(page)) @@ -1672,18 +1672,18 @@ page_ok: */ isize = i_size_read(inode); - end_index = (isize - 1) >> PAGE_CACHE_SHIFT; + end_index = (isize - 1) >> PAGE_SHIFT; if (unlikely(!isize || index > end_index)) { - page_cache_release(page); + put_page(page); goto out; } /* nr is the maximum number of bytes to copy from this page */ - nr = PAGE_CACHE_SIZE; + nr = PAGE_SIZE; if (index == end_index) { - nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; + nr = ((isize - 1) & ~PAGE_MASK) + 1; if (nr <= offset) { - page_cache_release(page); + put_page(page); goto out; } } @@ -1711,11 +1711,11 @@ page_ok: ret = copy_page_to_iter(page, offset, nr, iter); offset += ret; - index += offset >> PAGE_CACHE_SHIFT; - offset &= ~PAGE_CACHE_MASK; + index += offset >> PAGE_SHIFT; + offset &= ~PAGE_MASK; prev_offset = offset; - page_cache_release(page); + put_page(page); written += ret; if (!iov_iter_count(iter)) goto out; @@ -1735,7 +1735,7 @@ page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); - page_cache_release(page); + put_page(page); continue; } @@ -1757,7 +1757,7 @@ readpage: if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { - page_cache_release(page); + put_page(page); error = 0; goto find_page; } @@ -1774,7 +1774,7 @@ readpage: * invalidate_mapping_pages got it */ unlock_page(page); - page_cache_release(page); + put_page(page); goto find_page; } unlock_page(page); @@ -1789,7 +1789,7 @@ readpage: readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ - page_cache_release(page); + put_page(page); goto out; no_cached_page: @@ -1805,7 +1805,7 @@ no_cached_page: error = add_to_page_cache_lru(page, mapping, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error) { - page_cache_release(page); + put_page(page); if (error == -EEXIST) { error = 0; goto find_page; @@ -1817,10 +1817,10 @@ no_cached_page: out: ra->prev_pos = prev_index; - ra->prev_pos <<= PAGE_CACHE_SHIFT; + ra->prev_pos <<= PAGE_SHIFT; ra->prev_pos |= prev_offset; - *ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset; + *ppos = ((loff_t)index << PAGE_SHIFT) + offset; file_accessed(filp); return written ? written : error; } @@ -1912,7 +1912,7 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask) else if (ret == -EEXIST) ret = 0; /* losing race to add is OK */ - page_cache_release(page); + put_page(page); } while (ret == AOP_TRUNCATED_PAGE); @@ -2022,8 +2022,8 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) loff_t size; int ret = 0; - size = round_up(i_size_read(inode), PAGE_CACHE_SIZE); - if (offset >= size >> PAGE_CACHE_SHIFT) + size = round_up(i_size_read(inode), PAGE_SIZE); + if (offset >= size >> PAGE_SHIFT) return VM_FAULT_SIGBUS; /* @@ -2049,7 +2049,7 @@ retry_find: } if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) { - page_cache_release(page); + put_page(page); return ret | VM_FAULT_RETRY; } @@ -2072,10 +2072,10 @@ retry_find: * Found the page and have a reference on it. * We must recheck i_size under page lock. */ - size = round_up(i_size_read(inode), PAGE_CACHE_SIZE); - if (unlikely(offset >= size >> PAGE_CACHE_SHIFT)) { + size = round_up(i_size_read(inode), PAGE_SIZE); + if (unlikely(offset >= size >> PAGE_SHIFT)) { unlock_page(page); - page_cache_release(page); + put_page(page); return VM_FAULT_SIGBUS; } @@ -2120,7 +2120,7 @@ page_not_uptodate: if (!PageUptodate(page)) error = -EIO; } - page_cache_release(page); + put_page(page); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; @@ -2164,7 +2164,7 @@ repeat: /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(page); goto repeat; } @@ -2178,8 +2178,8 @@ repeat: if (page->mapping != mapping || !PageUptodate(page)) goto unlock; - size = round_up(i_size_read(mapping->host), PAGE_CACHE_SIZE); - if (page->index >= size >> PAGE_CACHE_SHIFT) + size = round_up(i_size_read(mapping->host), PAGE_SIZE); + if (page->index >= size >> PAGE_SHIFT) goto unlock; pte = vmf->pte + page->index - vmf->pgoff; @@ -2195,7 +2195,7 @@ repeat: unlock: unlock_page(page); skip: - page_cache_release(page); + put_page(page); next: if (iter.index == vmf->max_pgoff) break; @@ -2278,7 +2278,7 @@ static struct page *wait_on_page_read(struct page *page) if (!IS_ERR(page)) { wait_on_page_locked(page); if (!PageUptodate(page)) { - page_cache_release(page); + put_page(page); page = ERR_PTR(-EIO); } } @@ -2301,7 +2301,7 @@ repeat: return ERR_PTR(-ENOMEM); err = add_to_page_cache_lru(page, mapping, index, gfp); if (unlikely(err)) { - page_cache_release(page); + put_page(page); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for radix tree node */ @@ -2311,7 +2311,7 @@ repeat: filler: err = filler(data, page); if (err < 0) { - page_cache_release(page); + put_page(page); return ERR_PTR(err); } @@ -2364,7 +2364,7 @@ filler: /* Case c or d, restart the operation */ if (!page->mapping) { unlock_page(page); - page_cache_release(page); + put_page(page); goto repeat; } @@ -2511,7 +2511,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) struct iov_iter data; write_len = iov_iter_count(from); - end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT; + end = (pos + write_len - 1) >> PAGE_SHIFT; written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); if (written) @@ -2525,7 +2525,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) */ if (mapping->nrpages) { written = invalidate_inode_pages2_range(mapping, - pos >> PAGE_CACHE_SHIFT, end); + pos >> PAGE_SHIFT, end); /* * If a page can not be invalidated, return 0 to fall back * to buffered write. @@ -2550,7 +2550,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) */ if (mapping->nrpages) { invalidate_inode_pages2_range(mapping, - pos >> PAGE_CACHE_SHIFT, end); + pos >> PAGE_SHIFT, end); } if (written > 0) { @@ -2611,8 +2611,8 @@ ssize_t generic_perform_write(struct file *file, size_t copied; /* Bytes copied from user */ void *fsdata; - offset = (pos & (PAGE_CACHE_SIZE - 1)); - bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset, + offset = (pos & (PAGE_SIZE - 1)); + bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_count(i)); again: @@ -2665,7 +2665,7 @@ again: * because not all segments in the iov can be copied at * once without a pagefault. */ - bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset, + bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_single_seg_count(i)); goto again; } @@ -2752,8 +2752,8 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) iocb->ki_pos = endbyte + 1; written += status; invalidate_mapping_pages(mapping, - pos >> PAGE_CACHE_SHIFT, - endbyte >> PAGE_CACHE_SHIFT); + pos >> PAGE_SHIFT, + endbyte >> PAGE_SHIFT); } else { /* * We don't know how much we wrote, so just return diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 06058eaa173b..19d0d08b396f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3346,7 +3346,7 @@ retry_avoidcopy: old_page != pagecache_page) outside_reserve = 1; - page_cache_get(old_page); + get_page(old_page); /* * Drop page table lock as buddy allocator may be called. It will @@ -3364,7 +3364,7 @@ retry_avoidcopy: * may get SIGKILLed if it later faults. */ if (outside_reserve) { - page_cache_release(old_page); + put_page(old_page); BUG_ON(huge_pte_none(pte)); unmap_ref_private(mm, vma, old_page, address); BUG_ON(huge_pte_none(pte)); @@ -3425,9 +3425,9 @@ retry_avoidcopy: spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); out_release_all: - page_cache_release(new_page); + put_page(new_page); out_release_old: - page_cache_release(old_page); + put_page(old_page); spin_lock(ptl); /* Caller expects lock to be held */ return ret; diff --git a/mm/madvise.c b/mm/madvise.c index a01147359f3b..07427d3fcead 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -170,7 +170,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, vma, index); if (page) - page_cache_release(page); + put_page(page); } return 0; @@ -204,14 +204,14 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, page = find_get_entry(mapping, index); if (!radix_tree_exceptional_entry(page)) { if (page) - page_cache_release(page); + put_page(page); continue; } swap = radix_to_swp_entry(page); page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE, NULL, 0); if (page) - page_cache_release(page); + put_page(page); } lru_add_drain(); /* Push any new pages onto the LRU now */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 5a544c6c0717..78f5f2641b91 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -538,7 +538,7 @@ static int delete_from_lru_cache(struct page *p) /* * drop the page count elevated by isolate_lru_page() */ - page_cache_release(p); + put_page(p); return 0; } return -EIO; diff --git a/mm/memory.c b/mm/memory.c index 098f00d05461..07a420488cda 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2054,7 +2054,7 @@ static inline int wp_page_reuse(struct mm_struct *mm, VM_BUG_ON_PAGE(PageAnon(page), page); mapping = page->mapping; unlock_page(page); - page_cache_release(page); + put_page(page); if ((dirtied || page_mkwrite) && mapping) { /* @@ -2188,7 +2188,7 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, } if (new_page) - page_cache_release(new_page); + put_page(new_page); pte_unmap_unlock(page_table, ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); @@ -2203,14 +2203,14 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, munlock_vma_page(old_page); unlock_page(old_page); } - page_cache_release(old_page); + put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; oom_free_new: - page_cache_release(new_page); + put_page(new_page); oom: if (old_page) - page_cache_release(old_page); + put_page(old_page); return VM_FAULT_OOM; } @@ -2258,7 +2258,7 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, { int page_mkwrite = 0; - page_cache_get(old_page); + get_page(old_page); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { int tmp; @@ -2267,7 +2267,7 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, tmp = do_page_mkwrite(vma, old_page, address); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { - page_cache_release(old_page); + put_page(old_page); return tmp; } /* @@ -2281,7 +2281,7 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, if (!pte_same(*page_table, orig_pte)) { unlock_page(old_page); pte_unmap_unlock(page_table, ptl); - page_cache_release(old_page); + put_page(old_page); return 0; } page_mkwrite = 1; @@ -2341,7 +2341,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, */ if (PageAnon(old_page) && !PageKsm(old_page)) { if (!trylock_page(old_page)) { - page_cache_get(old_page); + get_page(old_page); pte_unmap_unlock(page_table, ptl); lock_page(old_page); page_table = pte_offset_map_lock(mm, pmd, address, @@ -2349,10 +2349,10 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, if (!pte_same(*page_table, orig_pte)) { unlock_page(old_page); pte_unmap_unlock(page_table, ptl); - page_cache_release(old_page); + put_page(old_page); return 0; } - page_cache_release(old_page); + put_page(old_page); } if (reuse_swap_page(old_page)) { /* @@ -2375,7 +2375,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, /* * Ok, we need to copy. Oh, well.. */ - page_cache_get(old_page); + get_page(old_page); pte_unmap_unlock(page_table, ptl); return wp_page_copy(mm, vma, address, page_table, pmd, @@ -2619,7 +2619,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, * parallel locked swapcache. */ unlock_page(swapcache); - page_cache_release(swapcache); + put_page(swapcache); } if (flags & FAULT_FLAG_WRITE) { @@ -2641,10 +2641,10 @@ out_nomap: out_page: unlock_page(page); out_release: - page_cache_release(page); + put_page(page); if (page != swapcache) { unlock_page(swapcache); - page_cache_release(swapcache); + put_page(swapcache); } return ret; } @@ -2752,7 +2752,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (userfaultfd_missing(vma)) { pte_unmap_unlock(page_table, ptl); mem_cgroup_cancel_charge(page, memcg, false); - page_cache_release(page); + put_page(page); return handle_userfault(vma, address, flags, VM_UFFD_MISSING); } @@ -2771,10 +2771,10 @@ unlock: return 0; release: mem_cgroup_cancel_charge(page, memcg, false); - page_cache_release(page); + put_page(page); goto unlock; oom_free_page: - page_cache_release(page); + put_page(page); oom: return VM_FAULT_OOM; } @@ -2807,7 +2807,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, if (unlikely(PageHWPoison(vmf.page))) { if (ret & VM_FAULT_LOCKED) unlock_page(vmf.page); - page_cache_release(vmf.page); + put_page(vmf.page); return VM_FAULT_HWPOISON; } @@ -2996,7 +2996,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(!pte_same(*pte, orig_pte))) { pte_unmap_unlock(pte, ptl); unlock_page(fault_page); - page_cache_release(fault_page); + put_page(fault_page); return ret; } do_set_pte(vma, address, fault_page, pte, false, false); @@ -3024,7 +3024,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_OOM; if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) { - page_cache_release(new_page); + put_page(new_page); return VM_FAULT_OOM; } @@ -3041,7 +3041,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); if (fault_page) { unlock_page(fault_page); - page_cache_release(fault_page); + put_page(fault_page); } else { /* * The fault handler has no page to lock, so it holds @@ -3057,7 +3057,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); if (fault_page) { unlock_page(fault_page); - page_cache_release(fault_page); + put_page(fault_page); } else { /* * The fault handler has no page to lock, so it holds @@ -3068,7 +3068,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, return ret; uncharge_out: mem_cgroup_cancel_charge(new_page, memcg, false); - page_cache_release(new_page); + put_page(new_page); return ret; } @@ -3096,7 +3096,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, tmp = do_page_mkwrite(vma, fault_page, address); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { - page_cache_release(fault_page); + put_page(fault_page); return tmp; } } @@ -3105,7 +3105,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(!pte_same(*pte, orig_pte))) { pte_unmap_unlock(pte, ptl); unlock_page(fault_page); - page_cache_release(fault_page); + put_page(fault_page); return ret; } do_set_pte(vma, address, fault_page, pte, true, false); @@ -3736,7 +3736,7 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, buf, maddr + offset, bytes); } kunmap(page); - page_cache_release(page); + put_page(page); } len -= bytes; buf += bytes; diff --git a/mm/mincore.c b/mm/mincore.c index 563f32045490..0eed23d50adb 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -75,7 +75,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) #endif if (page) { present = PageUptodate(page); - page_cache_release(page); + put_page(page); } return present; @@ -226,7 +226,7 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len, unsigned char *tmp; /* Check the start address: needs to be page-aligned.. */ - if (start & ~PAGE_CACHE_MASK) + if (start & ~PAGE_MASK) return -EINVAL; /* ..and we need to be passed a valid user-space range */ diff --git a/mm/nommu.c b/mm/nommu.c index de8b6b6580c1..102e257cc6c3 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -141,7 +141,7 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (pages) { pages[i] = virt_to_page(start); if (pages[i]) - page_cache_get(pages[i]); + get_page(pages[i]); } if (vmas) vmas[i] = vma; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 11ff8f758631..999792d35ccc 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2176,8 +2176,8 @@ int write_cache_pages(struct address_space *mapping, cycled = 0; end = -1; } else { - index = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + index = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ @@ -2382,14 +2382,14 @@ int write_one_page(struct page *page, int wait) wait_on_page_writeback(page); if (clear_page_dirty_for_io(page)) { - page_cache_get(page); + get_page(page); ret = mapping->a_ops->writepage(page, &wbc); if (ret == 0 && wait) { wait_on_page_writeback(page); if (PageError(page)) ret = -EIO; } - page_cache_release(page); + put_page(page); } else { unlock_page(page); } @@ -2431,7 +2431,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) __inc_zone_page_state(page, NR_DIRTIED); __inc_wb_stat(wb, WB_RECLAIMABLE); __inc_wb_stat(wb, WB_DIRTIED); - task_io_account_write(PAGE_CACHE_SIZE); + task_io_account_write(PAGE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); } @@ -2450,7 +2450,7 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY); dec_zone_page_state(page, NR_FILE_DIRTY); dec_wb_stat(wb, WB_RECLAIMABLE); - task_io_account_cancelled_write(PAGE_CACHE_SIZE); + task_io_account_cancelled_write(PAGE_SIZE); } } diff --git a/mm/page_io.c b/mm/page_io.c index 18aac7819cc9..cd92e3d67a32 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -252,7 +252,7 @@ out: static sector_t swap_page_sector(struct page *page) { - return (sector_t)__page_file_index(page) << (PAGE_CACHE_SHIFT - 9); + return (sector_t)__page_file_index(page) << (PAGE_SHIFT - 9); } int __swap_writepage(struct page *page, struct writeback_control *wbc, diff --git a/mm/readahead.c b/mm/readahead.c index 20e58e820e44..40be3ae0afe3 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -47,11 +47,11 @@ static void read_cache_pages_invalidate_page(struct address_space *mapping, if (!trylock_page(page)) BUG(); page->mapping = mapping; - do_invalidatepage(page, 0, PAGE_CACHE_SIZE); + do_invalidatepage(page, 0, PAGE_SIZE); page->mapping = NULL; unlock_page(page); } - page_cache_release(page); + put_page(page); } /* @@ -93,14 +93,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, read_cache_pages_invalidate_page(mapping, page); continue; } - page_cache_release(page); + put_page(page); ret = filler(data, page); if (unlikely(ret)) { read_cache_pages_invalidate_pages(mapping, pages); break; } - task_io_account_read(PAGE_CACHE_SIZE); + task_io_account_read(PAGE_SIZE); } return ret; } @@ -130,7 +130,7 @@ static int read_pages(struct address_space *mapping, struct file *filp, mapping_gfp_constraint(mapping, GFP_KERNEL))) { mapping->a_ops->readpage(filp, page); } - page_cache_release(page); + put_page(page); } ret = 0; @@ -163,7 +163,7 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, if (isize == 0) goto out; - end_index = ((isize - 1) >> PAGE_CACHE_SHIFT); + end_index = ((isize - 1) >> PAGE_SHIFT); /* * Preallocate as many pages as we will need. @@ -216,7 +216,7 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, while (nr_to_read) { int err; - unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_CACHE_SIZE; + unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; @@ -425,7 +425,7 @@ ondemand_readahead(struct address_space *mapping, * trivial case: (offset - prev_offset) == 1 * unaligned reads: (offset - prev_offset) == 0 */ - prev_offset = (unsigned long long)ra->prev_pos >> PAGE_CACHE_SHIFT; + prev_offset = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; if (offset - prev_offset <= 1UL) goto initial_readahead; @@ -558,8 +558,8 @@ SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) if (f.file) { if (f.file->f_mode & FMODE_READ) { struct address_space *mapping = f.file->f_mapping; - pgoff_t start = offset >> PAGE_CACHE_SHIFT; - pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT; + pgoff_t start = offset >> PAGE_SHIFT; + pgoff_t end = (offset + count - 1) >> PAGE_SHIFT; unsigned long len = end - start + 1; ret = do_readahead(mapping, f.file, start, len); } diff --git a/mm/rmap.c b/mm/rmap.c index c399a0d41b31..525b92f866a7 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1555,7 +1555,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, discard: page_remove_rmap(page, PageHuge(page)); - page_cache_release(page); + put_page(page); out_unmap: pte_unmap_unlock(pte, ptl); diff --git a/mm/shmem.c b/mm/shmem.c index 9428c51ab2d6..719bd6b88d98 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -75,8 +75,8 @@ static struct vfsmount *shm_mnt; #include "internal.h" -#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) -#define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT) +#define BLOCKS_PER_PAGE (PAGE_SIZE/512) +#define VM_ACCT(size) (PAGE_ALIGN(size) >> PAGE_SHIFT) /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 @@ -176,13 +176,13 @@ static inline int shmem_reacct_size(unsigned long flags, static inline int shmem_acct_block(unsigned long flags) { return (flags & VM_NORESERVE) ? - security_vm_enough_memory_mm(current->mm, VM_ACCT(PAGE_CACHE_SIZE)) : 0; + security_vm_enough_memory_mm(current->mm, VM_ACCT(PAGE_SIZE)) : 0; } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { if (flags & VM_NORESERVE) - vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE)); + vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } static const struct super_operations shmem_ops; @@ -300,7 +300,7 @@ static int shmem_add_to_page_cache(struct page *page, VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); - page_cache_get(page); + get_page(page); page->mapping = mapping; page->index = index; @@ -318,7 +318,7 @@ static int shmem_add_to_page_cache(struct page *page, } else { page->mapping = NULL; spin_unlock_irq(&mapping->tree_lock); - page_cache_release(page); + put_page(page); } return error; } @@ -338,7 +338,7 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) __dec_zone_page_state(page, NR_FILE_PAGES); __dec_zone_page_state(page, NR_SHMEM); spin_unlock_irq(&mapping->tree_lock); - page_cache_release(page); + put_page(page); BUG_ON(error); } @@ -474,10 +474,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); - pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - pgoff_t end = (lend + 1) >> PAGE_CACHE_SHIFT; - unsigned int partial_start = lstart & (PAGE_CACHE_SIZE - 1); - unsigned int partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1); + pgoff_t start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgoff_t end = (lend + 1) >> PAGE_SHIFT; + unsigned int partial_start = lstart & (PAGE_SIZE - 1); + unsigned int partial_end = (lend + 1) & (PAGE_SIZE - 1); struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; long nr_swaps_freed = 0; @@ -530,7 +530,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, struct page *page = NULL; shmem_getpage(inode, start - 1, &page, SGP_READ, NULL); if (page) { - unsigned int top = PAGE_CACHE_SIZE; + unsigned int top = PAGE_SIZE; if (start > end) { top = partial_end; partial_end = 0; @@ -538,7 +538,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, zero_user_segment(page, partial_start, top); set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); } } if (partial_end) { @@ -548,7 +548,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, zero_user_segment(page, 0, partial_end); set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); } } if (start >= end) @@ -833,7 +833,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page) mem_cgroup_commit_charge(page, memcg, true, false); out: unlock_page(page); - page_cache_release(page); + put_page(page); return error; } @@ -1080,7 +1080,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, if (!newpage) return -ENOMEM; - page_cache_get(newpage); + get_page(newpage); copy_highpage(newpage, oldpage); flush_dcache_page(newpage); @@ -1120,8 +1120,8 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, set_page_private(oldpage, 0); unlock_page(oldpage); - page_cache_release(oldpage); - page_cache_release(oldpage); + put_page(oldpage); + put_page(oldpage); return error; } @@ -1145,7 +1145,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, int once = 0; int alloced = 0; - if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT)) + if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; repeat: swap.val = 0; @@ -1156,7 +1156,7 @@ repeat: } if (sgp != SGP_WRITE && sgp != SGP_FALLOC && - ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { error = -EINVAL; goto unlock; } @@ -1169,7 +1169,7 @@ repeat: if (sgp != SGP_READ) goto clear; unlock_page(page); - page_cache_release(page); + put_page(page); page = NULL; } if (page || (sgp == SGP_READ && !swap.val)) { @@ -1327,7 +1327,7 @@ clear: /* Perhaps the file has been truncated since we checked */ if (sgp != SGP_WRITE && sgp != SGP_FALLOC && - ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { if (alloced) { ClearPageDirty(page); delete_from_page_cache(page); @@ -1355,7 +1355,7 @@ failed: unlock: if (page) { unlock_page(page); - page_cache_release(page); + put_page(page); } if (error == -ENOSPC && !once++) { info = SHMEM_I(inode); @@ -1577,7 +1577,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping, { struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; /* i_mutex is held by caller */ if (unlikely(info->seals)) { @@ -1601,16 +1601,16 @@ shmem_write_end(struct file *file, struct address_space *mapping, i_size_write(inode, pos + copied); if (!PageUptodate(page)) { - if (copied < PAGE_CACHE_SIZE) { - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + if (copied < PAGE_SIZE) { + unsigned from = pos & (PAGE_SIZE - 1); zero_user_segments(page, 0, from, - from + copied, PAGE_CACHE_SIZE); + from + copied, PAGE_SIZE); } SetPageUptodate(page); } set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); return copied; } @@ -1635,8 +1635,8 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (!iter_is_iovec(to)) sgp = SGP_DIRTY; - index = *ppos >> PAGE_CACHE_SHIFT; - offset = *ppos & ~PAGE_CACHE_MASK; + index = *ppos >> PAGE_SHIFT; + offset = *ppos & ~PAGE_MASK; for (;;) { struct page *page = NULL; @@ -1644,11 +1644,11 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) unsigned long nr, ret; loff_t i_size = i_size_read(inode); - end_index = i_size >> PAGE_CACHE_SHIFT; + end_index = i_size >> PAGE_SHIFT; if (index > end_index) break; if (index == end_index) { - nr = i_size & ~PAGE_CACHE_MASK; + nr = i_size & ~PAGE_MASK; if (nr <= offset) break; } @@ -1666,14 +1666,14 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) * We must evaluate after, since reads (unlike writes) * are called without i_mutex protection against truncate */ - nr = PAGE_CACHE_SIZE; + nr = PAGE_SIZE; i_size = i_size_read(inode); - end_index = i_size >> PAGE_CACHE_SHIFT; + end_index = i_size >> PAGE_SHIFT; if (index == end_index) { - nr = i_size & ~PAGE_CACHE_MASK; + nr = i_size & ~PAGE_MASK; if (nr <= offset) { if (page) - page_cache_release(page); + put_page(page); break; } } @@ -1694,7 +1694,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) mark_page_accessed(page); } else { page = ZERO_PAGE(0); - page_cache_get(page); + get_page(page); } /* @@ -1704,10 +1704,10 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) ret = copy_page_to_iter(page, offset, nr, to); retval += ret; offset += ret; - index += offset >> PAGE_CACHE_SHIFT; - offset &= ~PAGE_CACHE_MASK; + index += offset >> PAGE_SHIFT; + offset &= ~PAGE_MASK; - page_cache_release(page); + put_page(page); if (!iov_iter_count(to)) break; if (ret < nr) { @@ -1717,7 +1717,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) cond_resched(); } - *ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset; + *ppos = ((loff_t) index << PAGE_SHIFT) + offset; file_accessed(file); return retval ? retval : error; } @@ -1755,9 +1755,9 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, if (splice_grow_spd(pipe, &spd)) return -ENOMEM; - index = *ppos >> PAGE_CACHE_SHIFT; - loff = *ppos & ~PAGE_CACHE_MASK; - req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + index = *ppos >> PAGE_SHIFT; + loff = *ppos & ~PAGE_MASK; + req_pages = (len + loff + PAGE_SIZE - 1) >> PAGE_SHIFT; nr_pages = min(req_pages, spd.nr_pages_max); spd.nr_pages = find_get_pages_contig(mapping, index, @@ -1774,7 +1774,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, index++; } - index = *ppos >> PAGE_CACHE_SHIFT; + index = *ppos >> PAGE_SHIFT; nr_pages = spd.nr_pages; spd.nr_pages = 0; @@ -1784,7 +1784,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, if (!len) break; - this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff); + this_len = min_t(unsigned long, len, PAGE_SIZE - loff); page = spd.pages[page_nr]; if (!PageUptodate(page) || page->mapping != mapping) { @@ -1793,19 +1793,19 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, if (error) break; unlock_page(page); - page_cache_release(spd.pages[page_nr]); + put_page(spd.pages[page_nr]); spd.pages[page_nr] = page; } isize = i_size_read(inode); - end_index = (isize - 1) >> PAGE_CACHE_SHIFT; + end_index = (isize - 1) >> PAGE_SHIFT; if (unlikely(!isize || index > end_index)) break; if (end_index == index) { unsigned int plen; - plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; + plen = ((isize - 1) & ~PAGE_MASK) + 1; if (plen <= loff) break; @@ -1822,7 +1822,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, } while (page_nr < nr_pages) - page_cache_release(spd.pages[page_nr++]); + put_page(spd.pages[page_nr++]); if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); @@ -1904,10 +1904,10 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) else if (offset >= inode->i_size) offset = -ENXIO; else { - start = offset >> PAGE_CACHE_SHIFT; - end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + start = offset >> PAGE_SHIFT; + end = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; new_offset = shmem_seek_hole_data(mapping, start, end, whence); - new_offset <<= PAGE_CACHE_SHIFT; + new_offset <<= PAGE_SHIFT; if (new_offset > offset) { if (new_offset < inode->i_size) offset = new_offset; @@ -2203,8 +2203,8 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, goto out; } - start = offset >> PAGE_CACHE_SHIFT; - end = (offset + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + start = offset >> PAGE_SHIFT; + end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Try to avoid a swapstorm if len is impossible to satisfy */ if (sbinfo->max_blocks && end - start > sbinfo->max_blocks) { error = -ENOSPC; @@ -2237,8 +2237,8 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, if (error) { /* Remove the !PageUptodate pages we added */ shmem_undo_range(inode, - (loff_t)start << PAGE_CACHE_SHIFT, - (loff_t)index << PAGE_CACHE_SHIFT, true); + (loff_t)start << PAGE_SHIFT, + (loff_t)index << PAGE_SHIFT, true); goto undone; } @@ -2259,7 +2259,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, */ set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); cond_resched(); } @@ -2280,7 +2280,7 @@ static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb); buf->f_type = TMPFS_MAGIC; - buf->f_bsize = PAGE_CACHE_SIZE; + buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; if (sbinfo->max_blocks) { buf->f_blocks = sbinfo->max_blocks; @@ -2523,7 +2523,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s struct shmem_inode_info *info; len = strlen(symname) + 1; - if (len > PAGE_CACHE_SIZE) + if (len > PAGE_SIZE) return -ENAMETOOLONG; inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE); @@ -2562,7 +2562,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s SetPageUptodate(page); set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); } dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = CURRENT_TIME; @@ -2835,7 +2835,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, if (*rest) goto bad_val; sbinfo->max_blocks = - DIV_ROUND_UP(size, PAGE_CACHE_SIZE); + DIV_ROUND_UP(size, PAGE_SIZE); } else if (!strcmp(this_char,"nr_blocks")) { sbinfo->max_blocks = memparse(value, &rest); if (*rest) @@ -2940,7 +2940,7 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) if (sbinfo->max_blocks != shmem_default_max_blocks()) seq_printf(seq, ",size=%luk", - sbinfo->max_blocks << (PAGE_CACHE_SHIFT - 10)); + sbinfo->max_blocks << (PAGE_SHIFT - 10)); if (sbinfo->max_inodes != shmem_default_max_inodes()) seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes); if (sbinfo->mode != (S_IRWXUGO | S_ISVTX)) @@ -3082,8 +3082,8 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent) sbinfo->free_inodes = sbinfo->max_inodes; sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = TMPFS_MAGIC; sb->s_op = &shmem_ops; sb->s_time_gran = 1; diff --git a/mm/swap.c b/mm/swap.c index 09fe5e97714a..ea641e247033 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -114,7 +114,7 @@ void put_pages_list(struct list_head *pages) victim = list_entry(pages->prev, struct page, lru); list_del(&victim->lru); - page_cache_release(victim); + put_page(victim); } } EXPORT_SYMBOL(put_pages_list); @@ -142,7 +142,7 @@ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, return seg; pages[seg] = kmap_to_page(kiov[seg].iov_base); - page_cache_get(pages[seg]); + get_page(pages[seg]); } return seg; @@ -236,7 +236,7 @@ void rotate_reclaimable_page(struct page *page) struct pagevec *pvec; unsigned long flags; - page_cache_get(page); + get_page(page); local_irq_save(flags); pvec = this_cpu_ptr(&lru_rotate_pvecs); if (!pagevec_add(pvec, page)) @@ -294,7 +294,7 @@ void activate_page(struct page *page) if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); - page_cache_get(page); + get_page(page); if (!pagevec_add(pvec, page)) pagevec_lru_move_fn(pvec, __activate_page, NULL); put_cpu_var(activate_page_pvecs); @@ -389,7 +389,7 @@ static void __lru_cache_add(struct page *page) { struct pagevec *pvec = &get_cpu_var(lru_add_pvec); - page_cache_get(page); + get_page(page); if (!pagevec_space(pvec)) __pagevec_lru_add(pvec); pagevec_add(pvec, page); @@ -646,7 +646,7 @@ void deactivate_page(struct page *page) if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); - page_cache_get(page); + get_page(page); if (!pagevec_add(pvec, page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); put_cpu_var(lru_deactivate_pvecs); diff --git a/mm/swap_state.c b/mm/swap_state.c index 69cb2464e7dc..366ce3518703 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -85,7 +85,7 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry) VM_BUG_ON_PAGE(PageSwapCache(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); - page_cache_get(page); + get_page(page); SetPageSwapCache(page); set_page_private(page, entry.val); @@ -109,7 +109,7 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry) VM_BUG_ON(error == -EEXIST); set_page_private(page, 0UL); ClearPageSwapCache(page); - page_cache_release(page); + put_page(page); } return error; @@ -226,7 +226,7 @@ void delete_from_swap_cache(struct page *page) spin_unlock_irq(&address_space->tree_lock); swapcache_free(entry); - page_cache_release(page); + put_page(page); } /* @@ -252,7 +252,7 @@ static inline void free_swap_cache(struct page *page) void free_page_and_swap_cache(struct page *page) { free_swap_cache(page); - page_cache_release(page); + put_page(page); } /* @@ -380,7 +380,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, } while (err != -ENOMEM); if (new_page) - page_cache_release(new_page); + put_page(new_page); return found_page; } @@ -495,7 +495,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, continue; if (offset != entry_offset) SetPageReadahead(page); - page_cache_release(page); + put_page(page); } blk_finish_plug(&plug); diff --git a/mm/swapfile.c b/mm/swapfile.c index 560ad380634c..83874eced5bf 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -119,7 +119,7 @@ __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) ret = try_to_free_swap(page); unlock_page(page); } - page_cache_release(page); + put_page(page); return ret; } @@ -1000,7 +1000,7 @@ int free_swap_and_cache(swp_entry_t entry) page = find_get_page(swap_address_space(entry), entry.val); if (page && !trylock_page(page)) { - page_cache_release(page); + put_page(page); page = NULL; } } @@ -1017,7 +1017,7 @@ int free_swap_and_cache(swp_entry_t entry) SetPageDirty(page); } unlock_page(page); - page_cache_release(page); + put_page(page); } return p != NULL; } @@ -1518,7 +1518,7 @@ int try_to_unuse(unsigned int type, bool frontswap, } if (retval) { unlock_page(page); - page_cache_release(page); + put_page(page); break; } @@ -1570,7 +1570,7 @@ int try_to_unuse(unsigned int type, bool frontswap, */ SetPageDirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); /* * Make sure that we aren't completely killing @@ -2574,7 +2574,7 @@ bad_swap: out: if (page && !IS_ERR(page)) { kunmap(page); - page_cache_release(page); + put_page(page); } if (name) putname(name); diff --git a/mm/truncate.c b/mm/truncate.c index 7598b552ae03..b00272810871 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -118,7 +118,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page) return -EIO; if (page_has_private(page)) - do_invalidatepage(page, 0, PAGE_CACHE_SIZE); + do_invalidatepage(page, 0, PAGE_SIZE); /* * Some filesystems seem to re-dirty the page even after @@ -159,8 +159,8 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) { if (page_mapped(page)) { unmap_mapping_range(mapping, - (loff_t)page->index << PAGE_CACHE_SHIFT, - PAGE_CACHE_SIZE, 0); + (loff_t)page->index << PAGE_SHIFT, + PAGE_SIZE, 0); } return truncate_complete_page(mapping, page); } @@ -241,8 +241,8 @@ void truncate_inode_pages_range(struct address_space *mapping, return; /* Offsets within partial pages */ - partial_start = lstart & (PAGE_CACHE_SIZE - 1); - partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1); + partial_start = lstart & (PAGE_SIZE - 1); + partial_end = (lend + 1) & (PAGE_SIZE - 1); /* * 'start' and 'end' always covers the range of pages to be fully @@ -250,7 +250,7 @@ void truncate_inode_pages_range(struct address_space *mapping, * start of the range and 'partial_end' at the end of the range. * Note that 'end' is exclusive while 'lend' is inclusive. */ - start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; if (lend == -1) /* * lend == -1 indicates end-of-file so we have to set 'end' @@ -259,7 +259,7 @@ void truncate_inode_pages_range(struct address_space *mapping, */ end = -1; else - end = (lend + 1) >> PAGE_CACHE_SHIFT; + end = (lend + 1) >> PAGE_SHIFT; pagevec_init(&pvec, 0); index = start; @@ -298,7 +298,7 @@ void truncate_inode_pages_range(struct address_space *mapping, if (partial_start) { struct page *page = find_lock_page(mapping, start - 1); if (page) { - unsigned int top = PAGE_CACHE_SIZE; + unsigned int top = PAGE_SIZE; if (start > end) { /* Truncation within a single page */ top = partial_end; @@ -311,7 +311,7 @@ void truncate_inode_pages_range(struct address_space *mapping, do_invalidatepage(page, partial_start, top - partial_start); unlock_page(page); - page_cache_release(page); + put_page(page); } } if (partial_end) { @@ -324,7 +324,7 @@ void truncate_inode_pages_range(struct address_space *mapping, do_invalidatepage(page, 0, partial_end); unlock_page(page); - page_cache_release(page); + put_page(page); } } /* @@ -538,7 +538,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) if (mapping->a_ops->freepage) mapping->a_ops->freepage(page); - page_cache_release(page); /* pagecache ref */ + put_page(page); /* pagecache ref */ return 1; failed: spin_unlock_irqrestore(&mapping->tree_lock, flags); @@ -608,18 +608,18 @@ int invalidate_inode_pages2_range(struct address_space *mapping, * Zap the rest of the file in one hit. */ unmap_mapping_range(mapping, - (loff_t)index << PAGE_CACHE_SHIFT, + (loff_t)index << PAGE_SHIFT, (loff_t)(1 + end - index) - << PAGE_CACHE_SHIFT, - 0); + << PAGE_SHIFT, + 0); did_range_unmap = 1; } else { /* * Just zap this page */ unmap_mapping_range(mapping, - (loff_t)index << PAGE_CACHE_SHIFT, - PAGE_CACHE_SIZE, 0); + (loff_t)index << PAGE_SHIFT, + PAGE_SIZE, 0); } } BUG_ON(page_mapped(page)); @@ -744,14 +744,14 @@ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) WARN_ON(to > inode->i_size); - if (from >= to || bsize == PAGE_CACHE_SIZE) + if (from >= to || bsize == PAGE_SIZE) return; /* Page straddling @from will not have any hole block created? */ rounded_from = round_up(from, bsize); - if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1))) + if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) return; - index = from >> PAGE_CACHE_SHIFT; + index = from >> PAGE_SHIFT; page = find_lock_page(inode->i_mapping, index); /* Page not cached? Nothing to do */ if (!page) @@ -763,7 +763,7 @@ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) if (page_mkclean(page)) set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); } EXPORT_SYMBOL(pagecache_isize_extended); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 9f3a0290b273..af817e5060fb 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -93,7 +93,7 @@ out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); mem_cgroup_cancel_charge(page, memcg, false); out_release: - page_cache_release(page); + put_page(page); goto out; } @@ -287,7 +287,7 @@ out_unlock: up_read(&dst_mm->mmap_sem); out: if (page) - page_cache_release(page); + put_page(page); BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); diff --git a/mm/zswap.c b/mm/zswap.c index bf14508afd64..91dad80d068b 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -869,7 +869,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) case ZSWAP_SWAPCACHE_EXIST: /* page is already in the swap cache, ignore for now */ - page_cache_release(page); + put_page(page); ret = -EEXIST; goto fail; @@ -897,7 +897,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) /* start writeback */ __swap_writepage(page, &wbc, end_swap_bio_write); - page_cache_release(page); + put_page(page); zswap_written_back_pages++; spin_lock(&tree->lock); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 1831f6353622..a5502898ea33 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -269,7 +269,7 @@ static void _ceph_msgr_exit(void) } BUG_ON(zero_page == NULL); - page_cache_release(zero_page); + put_page(zero_page); zero_page = NULL; ceph_msgr_slab_exit(); @@ -282,7 +282,7 @@ int ceph_msgr_init(void) BUG_ON(zero_page != NULL); zero_page = ZERO_PAGE(0); - page_cache_get(zero_page); + get_page(zero_page); /* * The number of active work items is limited by the number of @@ -1602,7 +1602,7 @@ static int write_partial_skip(struct ceph_connection *con) dout("%s %p %d left\n", __func__, con, con->out_skip); while (con->out_skip > 0) { - size_t size = min(con->out_skip, (int) PAGE_CACHE_SIZE); + size_t size = min(con->out_skip, (int) PAGE_SIZE); ret = ceph_tcp_sendpage(con->sock, zero_page, 0, size, true); if (ret <= 0) diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c index c7c220a736e5..6864007e64fc 100644 --- a/net/ceph/pagelist.c +++ b/net/ceph/pagelist.c @@ -56,7 +56,7 @@ int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len) size_t bit = pl->room; int ret; - memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), + memcpy(pl->mapped_tail + (pl->length & ~PAGE_MASK), buf, bit); pl->length += bit; pl->room -= bit; @@ -67,7 +67,7 @@ int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len) return ret; } - memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len); + memcpy(pl->mapped_tail + (pl->length & ~PAGE_MASK), buf, len); pl->length += len; pl->room -= len; return 0; diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index 10297f7a89ba..00d2601407c5 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -95,19 +95,19 @@ int ceph_copy_user_to_page_vector(struct page **pages, loff_t off, size_t len) { int i = 0; - int po = off & ~PAGE_CACHE_MASK; + int po = off & ~PAGE_MASK; int left = len; int l, bad; while (left > 0) { - l = min_t(int, PAGE_CACHE_SIZE-po, left); + l = min_t(int, PAGE_SIZE-po, left); bad = copy_from_user(page_address(pages[i]) + po, data, l); if (bad == l) return -EFAULT; data += l - bad; left -= l - bad; po += l - bad; - if (po == PAGE_CACHE_SIZE) { + if (po == PAGE_SIZE) { po = 0; i++; } @@ -121,17 +121,17 @@ void ceph_copy_to_page_vector(struct page **pages, loff_t off, size_t len) { int i = 0; - size_t po = off & ~PAGE_CACHE_MASK; + size_t po = off & ~PAGE_MASK; size_t left = len; while (left > 0) { - size_t l = min_t(size_t, PAGE_CACHE_SIZE-po, left); + size_t l = min_t(size_t, PAGE_SIZE-po, left); memcpy(page_address(pages[i]) + po, data, l); data += l; left -= l; po += l; - if (po == PAGE_CACHE_SIZE) { + if (po == PAGE_SIZE) { po = 0; i++; } @@ -144,17 +144,17 @@ void ceph_copy_from_page_vector(struct page **pages, loff_t off, size_t len) { int i = 0; - size_t po = off & ~PAGE_CACHE_MASK; + size_t po = off & ~PAGE_MASK; size_t left = len; while (left > 0) { - size_t l = min_t(size_t, PAGE_CACHE_SIZE-po, left); + size_t l = min_t(size_t, PAGE_SIZE-po, left); memcpy(data, page_address(pages[i]) + po, l); data += l; left -= l; po += l; - if (po == PAGE_CACHE_SIZE) { + if (po == PAGE_SIZE) { po = 0; i++; } @@ -168,25 +168,25 @@ EXPORT_SYMBOL(ceph_copy_from_page_vector); */ void ceph_zero_page_vector_range(int off, int len, struct page **pages) { - int i = off >> PAGE_CACHE_SHIFT; + int i = off >> PAGE_SHIFT; - off &= ~PAGE_CACHE_MASK; + off &= ~PAGE_MASK; dout("zero_page_vector_page %u~%u\n", off, len); /* leading partial page? */ if (off) { - int end = min((int)PAGE_CACHE_SIZE, off + len); + int end = min((int)PAGE_SIZE, off + len); dout("zeroing %d %p head from %d\n", i, pages[i], (int)off); zero_user_segment(pages[i], off, end); len -= (end - off); i++; } - while (len >= PAGE_CACHE_SIZE) { + while (len >= PAGE_SIZE) { dout("zeroing %d %p len=%d\n", i, pages[i], len); - zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE); - len -= PAGE_CACHE_SIZE; + zero_user_segment(pages[i], 0, PAGE_SIZE); + len -= PAGE_SIZE; i++; } /* trailing partial page? */ diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 8c6bc795f060..15612ffa8d57 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1728,8 +1728,8 @@ alloc_enc_pages(struct rpc_rqst *rqstp) return 0; } - first = snd_buf->page_base >> PAGE_CACHE_SHIFT; - last = (snd_buf->page_base + snd_buf->page_len - 1) >> PAGE_CACHE_SHIFT; + first = snd_buf->page_base >> PAGE_SHIFT; + last = (snd_buf->page_base + snd_buf->page_len - 1) >> PAGE_SHIFT; rqstp->rq_enc_pages_num = last - first + 1 + 1; rqstp->rq_enc_pages = kmalloc(rqstp->rq_enc_pages_num * sizeof(struct page *), @@ -1775,10 +1775,10 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, status = alloc_enc_pages(rqstp); if (status) return status; - first = snd_buf->page_base >> PAGE_CACHE_SHIFT; + first = snd_buf->page_base >> PAGE_SHIFT; inpages = snd_buf->pages + first; snd_buf->pages = rqstp->rq_enc_pages; - snd_buf->page_base -= first << PAGE_CACHE_SHIFT; + snd_buf->page_base -= first << PAGE_SHIFT; /* * Give the tail its own page, in case we need extra space in the * head when wrapping: diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index d94a8e1e9f05..045e11ecd332 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -465,7 +465,7 @@ encryptor(struct scatterlist *sg, void *data) page_pos = desc->pos - outbuf->head[0].iov_len; if (page_pos >= 0 && page_pos < outbuf->page_len) { /* pages are not in place: */ - int i = (page_pos + outbuf->page_base) >> PAGE_CACHE_SHIFT; + int i = (page_pos + outbuf->page_base) >> PAGE_SHIFT; in_page = desc->pages[i]; } else { in_page = sg_page(sg); diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 765088e4ad84..a737c2da0837 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -79,9 +79,9 @@ gss_krb5_remove_padding(struct xdr_buf *buf, int blocksize) len -= buf->head[0].iov_len; if (len <= buf->page_len) { unsigned int last = (buf->page_base + len - 1) - >>PAGE_CACHE_SHIFT; + >>PAGE_SHIFT; unsigned int offset = (buf->page_base + len - 1) - & (PAGE_CACHE_SIZE - 1); + & (PAGE_SIZE - 1); ptr = kmap_atomic(buf->pages[last]); pad = *(ptr + offset); kunmap_atomic(ptr); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 008c25d1b9f9..553bf95f7003 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -881,7 +881,7 @@ static ssize_t cache_downcall(struct address_space *mapping, char *kaddr; ssize_t ret = -ENOMEM; - if (count >= PAGE_CACHE_SIZE) + if (count >= PAGE_SIZE) goto out_slow; page = find_or_create_page(mapping, 0, GFP_KERNEL); @@ -892,7 +892,7 @@ static ssize_t cache_downcall(struct address_space *mapping, ret = cache_do_downcall(kaddr, buf, count, cd); kunmap(page); unlock_page(page); - page_cache_release(page); + put_page(page); return ret; out_slow: return cache_slow_downcall(buf, count, cd); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 31789ef3e614..fc48eca21fd2 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1390,8 +1390,8 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); int err; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = RPCAUTH_GSSMAGIC; sb->s_op = &s_ops; sb->s_d_op = &simple_dentry_operations; diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index 2df87f78e518..de70c78025d7 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -96,8 +96,8 @@ ssize_t xdr_partial_copy_from_skb(struct xdr_buf *xdr, unsigned int base, struct if (base || xdr->page_base) { pglen -= base; base += xdr->page_base; - ppage += base >> PAGE_CACHE_SHIFT; - base &= ~PAGE_CACHE_MASK; + ppage += base >> PAGE_SHIFT; + base &= ~PAGE_MASK; } do { char *kaddr; @@ -113,7 +113,7 @@ ssize_t xdr_partial_copy_from_skb(struct xdr_buf *xdr, unsigned int base, struct } } - len = PAGE_CACHE_SIZE; + len = PAGE_SIZE; kaddr = kmap_atomic(*ppage); if (base) { len -= base; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 4439ac4c1b53..1e6aba0501a1 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -181,20 +181,20 @@ _shift_data_right_pages(struct page **pages, size_t pgto_base, pgto_base += len; pgfrom_base += len; - pgto = pages + (pgto_base >> PAGE_CACHE_SHIFT); - pgfrom = pages + (pgfrom_base >> PAGE_CACHE_SHIFT); + pgto = pages + (pgto_base >> PAGE_SHIFT); + pgfrom = pages + (pgfrom_base >> PAGE_SHIFT); - pgto_base &= ~PAGE_CACHE_MASK; - pgfrom_base &= ~PAGE_CACHE_MASK; + pgto_base &= ~PAGE_MASK; + pgfrom_base &= ~PAGE_MASK; do { /* Are any pointers crossing a page boundary? */ if (pgto_base == 0) { - pgto_base = PAGE_CACHE_SIZE; + pgto_base = PAGE_SIZE; pgto--; } if (pgfrom_base == 0) { - pgfrom_base = PAGE_CACHE_SIZE; + pgfrom_base = PAGE_SIZE; pgfrom--; } @@ -236,11 +236,11 @@ _copy_to_pages(struct page **pages, size_t pgbase, const char *p, size_t len) char *vto; size_t copy; - pgto = pages + (pgbase >> PAGE_CACHE_SHIFT); - pgbase &= ~PAGE_CACHE_MASK; + pgto = pages + (pgbase >> PAGE_SHIFT); + pgbase &= ~PAGE_MASK; for (;;) { - copy = PAGE_CACHE_SIZE - pgbase; + copy = PAGE_SIZE - pgbase; if (copy > len) copy = len; @@ -253,7 +253,7 @@ _copy_to_pages(struct page **pages, size_t pgbase, const char *p, size_t len) break; pgbase += copy; - if (pgbase == PAGE_CACHE_SIZE) { + if (pgbase == PAGE_SIZE) { flush_dcache_page(*pgto); pgbase = 0; pgto++; @@ -280,11 +280,11 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len) char *vfrom; size_t copy; - pgfrom = pages + (pgbase >> PAGE_CACHE_SHIFT); - pgbase &= ~PAGE_CACHE_MASK; + pgfrom = pages + (pgbase >> PAGE_SHIFT); + pgbase &= ~PAGE_MASK; do { - copy = PAGE_CACHE_SIZE - pgbase; + copy = PAGE_SIZE - pgbase; if (copy > len) copy = len; @@ -293,7 +293,7 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len) kunmap_atomic(vfrom); pgbase += copy; - if (pgbase == PAGE_CACHE_SIZE) { + if (pgbase == PAGE_SIZE) { pgbase = 0; pgfrom++; } @@ -1038,8 +1038,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, if (base < buf->page_len) { subbuf->page_len = min(buf->page_len - base, len); base += buf->page_base; - subbuf->page_base = base & ~PAGE_CACHE_MASK; - subbuf->pages = &buf->pages[base >> PAGE_CACHE_SHIFT]; + subbuf->page_base = base & ~PAGE_MASK; + subbuf->pages = &buf->pages[base >> PAGE_SHIFT]; len -= subbuf->page_len; base = 0; } else { @@ -1297,9 +1297,9 @@ xdr_xcode_array2(struct xdr_buf *buf, unsigned int base, todo -= avail_here; base += buf->page_base; - ppages = buf->pages + (base >> PAGE_CACHE_SHIFT); - base &= ~PAGE_CACHE_MASK; - avail_page = min_t(unsigned int, PAGE_CACHE_SIZE - base, + ppages = buf->pages + (base >> PAGE_SHIFT); + base &= ~PAGE_MASK; + avail_page = min_t(unsigned int, PAGE_SIZE - base, avail_here); c = kmap(*ppages) + base; @@ -1383,7 +1383,7 @@ xdr_xcode_array2(struct xdr_buf *buf, unsigned int base, } avail_page = min(avail_here, - (unsigned int) PAGE_CACHE_SIZE); + (unsigned int) PAGE_SIZE); } base = buf->page_len; /* align to start of tail */ } @@ -1479,9 +1479,9 @@ xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, if (page_len > len) page_len = len; len -= page_len; - page_offset = (offset + buf->page_base) & (PAGE_CACHE_SIZE - 1); - i = (offset + buf->page_base) >> PAGE_CACHE_SHIFT; - thislen = PAGE_CACHE_SIZE - page_offset; + page_offset = (offset + buf->page_base) & (PAGE_SIZE - 1); + i = (offset + buf->page_base) >> PAGE_SHIFT; + thislen = PAGE_SIZE - page_offset; do { if (thislen > page_len) thislen = page_len; @@ -1492,7 +1492,7 @@ xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, page_len -= thislen; i++; page_offset = 0; - thislen = PAGE_CACHE_SIZE; + thislen = PAGE_SIZE; } while (page_len != 0); offset = 0; } -- cgit v1.2.3