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 <neilb@suse.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steve French <sfrench@samba.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140707051604.28027.41257.stgit@notabene.brown
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 213c4580b4e32bba71235f97b653d6b7de917032..41de3935caa0cff86e58e8c4a0db829e4ca88a7e 100644 (file)
--- 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 b7b710e7d08ecde0e116ebe97883c0703819d56d..abd37a3805359c17fe4c557dfe82c9c6cda49f84 100644 (file)
--- 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 82ddbf46660e3c1be7d499f2ca014ce619da8603..e0193d63630c9bfb5de1cfea03797195577bf195 100644 (file)
--- 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 6104d3500b493b84f3f47163ef4a2429dec49873..745a612dbe227c356ecf955bb2d3ab11daf95566 100644 (file)
--- 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 ad7dbe2cfecd840e8174fb3fe2e49e774c772d9b..1a8959944c5f4d56038acb386110cc2c1390903e 100644 (file)
--- 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 73960ff09e56ba48188d2980896b0c2ed5186c31..6fb1ba5f9b2f41f1fd4d6e4210f5128b662ff9ba 100644 (file)
--- 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 a104879e88f2751478caaf7268a261ea1b6d4665..15cab1a4f84ed383e1ca5df7bd5600c0af722df8 100644 (file)
--- 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 c0365c14b858711d7e579308aa3452e4d94701c6..9358c79fd5893eacc94e3ba3969d72b6c11b0845 100644 (file)
--- 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;