From 743162013d40ca612b4cb53d3a200dff2d9ab26e Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Jul 2014 15:16:04 +1000 Subject: sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown Acked-by: David Howells (fscache, keys) Acked-by: Steven Whitehouse (gfs2) Acked-by: Peter Zijlstra Cc: Oleg Nesterov Cc: Steve French Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar --- include/linux/wait.h | 115 +++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 111 insertions(+), 4 deletions(-) (limited to 'include/linux/wait.h') diff --git a/include/linux/wait.h b/include/linux/wait.h index bd68819f081..73960ff09e5 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -854,11 +854,14 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); (wait)->flags = 0; \ } while (0) + +extern int bit_wait(void *); +extern int bit_wait_io(void *); + /** * wait_on_bit - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This @@ -867,9 +870,62 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); * call wait_on_bit() in threads waiting for the bit to clear. * One uses wait_on_bit() where one is waiting for the bit to clear, * but has no intention of setting it. + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit(void *word, int bit, unsigned mode) +{ + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait, + mode); +} + +/** + * wait_on_bit_io - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), but calls + * io_schedule() instead of schedule() for the actual waiting. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit_io(void *word, int bit, unsigned mode) +{ + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait_io, + mode); +} + +/** + * wait_on_bit_action - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared, and allow the waiting action to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. */ static inline int -wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode) +wait_on_bit_action(void *word, int bit, int (*action)(void *), unsigned mode) { if (!test_bit(bit, word)) return 0; @@ -880,7 +936,6 @@ wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode) * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This @@ -891,9 +946,61 @@ wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode) * wait_on_bit() in threads waiting to be able to set the bit. * One uses wait_on_bit_lock() where one is waiting for the bit to * clear with the intention of setting it, and when done, clearing it. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock(void *word, int bit, unsigned mode) +{ + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); +} + +/** + * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to atomically set it. This is similar + * to wait_on_bit(), but calls io_schedule() instead of schedule() + * for the actual waiting. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock_io(void *word, int bit, unsigned mode) +{ + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); +} + +/** + * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to set it, and allow the waiting action + * to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. */ static inline int -wait_on_bit_lock(void *word, int bit, int (*action)(void *), unsigned mode) +wait_on_bit_lock_action(void *word, int bit, int (*action)(void *), unsigned mode) { if (!test_and_set_bit(bit, word)) return 0; -- cgit v1.2.3-70-g09d2 From c1221321b7c25b53204447cff9949a6d5a7ddddc Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Jul 2014 15:16:04 +1000 Subject: sched: Allow wait_on_bit_action() functions to support a timeout It is currently not possible for various wait_on_bit functions to implement a timeout. While the "action" function that is called to do the waiting could certainly use schedule_timeout(), there is no way to carry forward the remaining timeout after a false wake-up. As false-wakeups a clearly possible at least due to possible hash collisions in bit_waitqueue(), this is a real problem. The 'action' function is currently passed a pointer to the word containing the bit being waited on. No current action functions use this pointer. So changing it to something else will be a little noisy but will have no immediate effect. This patch changes the 'action' function to take a pointer to the "struct wait_bit_key", which contains a pointer to the word containing the bit so nothing is really lost. It also adds a 'private' field to "struct wait_bit_key", which is initialized to zero. An action function can now implement a timeout with something like static int timed_out_waiter(struct wait_bit_key *key) { unsigned long waited; if (key->private == 0) { key->private = jiffies; if (key->private == 0) key->private -= 1; } waited = jiffies - key->private; if (waited > 10 * HZ) return -EAGAIN; schedule_timeout(waited - 10 * HZ); return 0; } If any other need for context in a waiter were found it would be easy to use ->private for some other purpose, or even extend "struct wait_bit_key". My particular need is to support timeouts in nfs_release_page() to avoid deadlocks with loopback mounted NFS. While wait_on_bit_timeout() would be a cleaner interface, it will not meet my need. I need the timeout to be sensitive to the state of the connection with the server, which could change. So I need to use an 'action' interface. Signed-off-by: NeilBrown Acked-by: Peter Zijlstra Cc: Oleg Nesterov Cc: Steve French Cc: David Howells Cc: Steven Whitehouse Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20140707051604.28027.41257.stgit@notabene.brown Signed-off-by: Ingo Molnar --- fs/cifs/inode.c | 2 +- fs/nfs/inode.c | 2 +- fs/nfs/internal.h | 2 +- fs/nfs/pagelist.c | 2 +- include/linux/sunrpc/sched.h | 2 +- include/linux/wait.h | 18 ++++++++++-------- kernel/sched/wait.c | 16 ++++++++-------- net/sunrpc/sched.c | 4 ++-- 8 files changed, 25 insertions(+), 23 deletions(-) (limited to 'include/linux/wait.h') diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 213c4580b4e..41de3935caa 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1780,7 +1780,7 @@ cifs_invalidate_mapping(struct inode *inode) * @word: long word containing the bit lock */ static int -cifs_wait_bit_killable(void *word) +cifs_wait_bit_killable(struct wait_bit_key *key) { if (fatal_signal_pending(current)) return -ERESTARTSYS; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b7b710e7d08..abd37a38053 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -75,7 +75,7 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks * @word: long word containing the bit lock */ -int nfs_wait_bit_killable(void *word) +int nfs_wait_bit_killable(struct wait_bit_key *key) { if (fatal_signal_pending(current)) return -ERESTARTSYS; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 82ddbf46660..e0193d63630 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -347,7 +347,7 @@ extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); void nfs_zap_acl_cache(struct inode *inode); -extern int nfs_wait_bit_killable(void *word); +extern int nfs_wait_bit_killable(struct wait_bit_key *key); /* super.c */ extern const struct super_operations nfs_sops; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6104d3500b4..745a612dbe2 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -117,7 +117,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c) set_bit(NFS_IO_INPROGRESS, &c->flags); if (atomic_read(&c->io_count) == 0) break; - ret = nfs_wait_bit_killable(&c->flags); + ret = nfs_wait_bit_killable(&q.key); } while (atomic_read(&c->io_count) != 0); finish_wait(wq, &q.wait); return ret; diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index ad7dbe2cfec..1a8959944c5 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -236,7 +236,7 @@ void * rpc_malloc(struct rpc_task *, size_t); void rpc_free(void *); int rpciod_up(void); void rpciod_down(void); -int __rpc_wait_for_completion_task(struct rpc_task *task, int (*)(void *)); +int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *); #ifdef RPC_DEBUG struct net; void rpc_show_tasks(struct net *); diff --git a/include/linux/wait.h b/include/linux/wait.h index 73960ff09e5..6fb1ba5f9b2 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -25,6 +25,7 @@ struct wait_bit_key { void *flags; int bit_nr; #define WAIT_ATOMIC_T_BIT_NR -1 + unsigned long private; }; struct wait_bit_queue { @@ -141,18 +142,19 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) list_del(&old->task_list); } +typedef int wait_bit_action_f(struct wait_bit_key *); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_bit(wait_queue_head_t *, void *, int); -int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); -int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); +int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); +int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); void wake_up_bit(void *, int); void wake_up_atomic_t(atomic_t *); -int out_of_line_wait_on_bit(void *, int, int (*)(void *), unsigned); -int out_of_line_wait_on_bit_lock(void *, int, int (*)(void *), unsigned); +int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned); +int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned); int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned); wait_queue_head_t *bit_waitqueue(void *, int); @@ -855,8 +857,8 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); } while (0) -extern int bit_wait(void *); -extern int bit_wait_io(void *); +extern int bit_wait(struct wait_bit_key *); +extern int bit_wait_io(struct wait_bit_key *); /** * wait_on_bit - wait for a bit to be cleared @@ -925,7 +927,7 @@ wait_on_bit_io(void *word, int bit, unsigned mode) * on that signal. */ static inline int -wait_on_bit_action(void *word, int bit, int (*action)(void *), unsigned mode) +wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode) { if (!test_bit(bit, word)) return 0; @@ -1000,7 +1002,7 @@ wait_on_bit_lock_io(void *word, int bit, unsigned mode) * the @mode allows that signal to wake the process. */ static inline int -wait_on_bit_lock_action(void *word, int bit, int (*action)(void *), unsigned mode) +wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode) { if (!test_and_set_bit(bit, word)) return 0; diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index a104879e88f..15cab1a4f84 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -319,14 +319,14 @@ EXPORT_SYMBOL(wake_bit_function); */ int __sched __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { int ret = 0; do { prepare_to_wait(wq, &q->wait, mode); if (test_bit(q->key.bit_nr, q->key.flags)) - ret = (*action)(q->key.flags); + ret = (*action)(&q->key); } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); finish_wait(wq, &q->wait); return ret; @@ -334,7 +334,7 @@ __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, EXPORT_SYMBOL(__wait_on_bit); int __sched out_of_line_wait_on_bit(void *word, int bit, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { wait_queue_head_t *wq = bit_waitqueue(word, bit); DEFINE_WAIT_BIT(wait, word, bit); @@ -345,7 +345,7 @@ EXPORT_SYMBOL(out_of_line_wait_on_bit); int __sched __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { do { int ret; @@ -353,7 +353,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, prepare_to_wait_exclusive(wq, &q->wait, mode); if (!test_bit(q->key.bit_nr, q->key.flags)) continue; - ret = action(q->key.flags); + ret = action(&q->key); if (!ret) continue; abort_exclusive_wait(wq, &q->wait, mode, &q->key); @@ -365,7 +365,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, EXPORT_SYMBOL(__wait_on_bit_lock); int __sched out_of_line_wait_on_bit_lock(void *word, int bit, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { wait_queue_head_t *wq = bit_waitqueue(word, bit); DEFINE_WAIT_BIT(wait, word, bit); @@ -503,7 +503,7 @@ void wake_up_atomic_t(atomic_t *p) } EXPORT_SYMBOL(wake_up_atomic_t); -__sched int bit_wait(void *word) +__sched int bit_wait(struct wait_bit_key *word) { if (signal_pending_state(current->state, current)) return 1; @@ -512,7 +512,7 @@ __sched int bit_wait(void *word) } EXPORT_SYMBOL(bit_wait); -__sched int bit_wait_io(void *word) +__sched int bit_wait_io(struct wait_bit_key *word) { if (signal_pending_state(current->state, current)) return 1; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index c0365c14b85..9358c79fd58 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -250,7 +250,7 @@ void rpc_destroy_wait_queue(struct rpc_wait_queue *queue) } EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); -static int rpc_wait_bit_killable(void *word) +static int rpc_wait_bit_killable(struct wait_bit_key *key) { if (fatal_signal_pending(current)) return -ERESTARTSYS; @@ -309,7 +309,7 @@ static int rpc_complete_task(struct rpc_task *task) * to enforce taking of the wq->lock and hence avoid races with * rpc_complete_task(). */ -int __rpc_wait_for_completion_task(struct rpc_task *task, int (*action)(void *)) +int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *action) { if (action == NULL) action = rpc_wait_bit_killable; -- cgit v1.2.3-70-g09d2