aio: remove retry-based AIO

This removes the retry-based AIO infrastructure now that nothing in tree
is using it.

We want to remove retry-based AIO because it is fundemantally unsafe.
It retries IO submission from a kernel thread that has only assumed the
mm of the submitting task.  All other task_struct references in the IO
submission path will see the kernel thread, not the submitting task.
This design flaw means that nothing of any meaningful complexity can use
retry-based AIO.

This removes all the code and data associated with the retry machinery.
The most significant benefit of this is the removal of the locking
around the unused run list in the submission path.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Kent Overstreet <koverstreet@google.com>
Signed-off-by: Zach Brown <zab@redhat.com>
Cc: Zach Brown <zab@redhat.com>
Cc: Felipe Balbi <balbi@ti.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Asai Thambi S P <asamymuthupa@micron.com>
Cc: Selvan Mani <smani@micron.com>
Cc: Sam Bradshaw <sbradshaw@micron.com>
Acked-by: Jeff Moyer <jmoyer@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Reviewed-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/ocfs2/dlmglue.c

@@ -2322,7 +2322,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 	status = __ocfs2_cluster_lock(osb, lockres, level, dlm_flags,
 				      arg_flags, subclass, _RET_IP_);
 	if (status < 0) {
-		if (status != -EAGAIN && status != -EIOCBRETRY)
+		if (status != -EAGAIN)
 			mlog_errno(status);
 		goto bail;
 	}

fs/read_write.c

@@ -329,16 +329,6 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count
 	return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
 }
 
-static void wait_on_retry_sync_kiocb(struct kiocb *iocb)
-{
-	set_current_state(TASK_UNINTERRUPTIBLE);
-	if (!kiocbIsKicked(iocb))
-		schedule();
-	else
-		kiocbClearKicked(iocb);
-	__set_current_state(TASK_RUNNING);
-}
-
 ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
 {
 	struct iovec iov = { .iov_base = buf, .iov_len = len };
@@ -350,13 +340,7 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp
 	kiocb.ki_left = len;
 	kiocb.ki_nbytes = len;
 
-	for (;;) {
 	ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
-		if (ret != -EIOCBRETRY)
-			break;
-		wait_on_retry_sync_kiocb(&kiocb);
-	}
-
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&kiocb);
 	*ppos = kiocb.ki_pos;
@@ -406,13 +390,7 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof
 	kiocb.ki_left = len;
 	kiocb.ki_nbytes = len;
 
-	for (;;) {
 	ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
-		if (ret != -EIOCBRETRY)
-			break;
-		wait_on_retry_sync_kiocb(&kiocb);
-	}
-
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&kiocb);
 	*ppos = kiocb.ki_pos;
@@ -592,13 +570,7 @@ static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
 	kiocb.ki_left = len;
 	kiocb.ki_nbytes = len;
 
-	for (;;) {
 	ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
-		if (ret != -EIOCBRETRY)
-			break;
-		wait_on_retry_sync_kiocb(&kiocb);
-	}
-
 	if (ret == -EIOCBQUEUED)
 		ret = wait_on_sync_kiocb(&kiocb);
 	*ppos = kiocb.ki_pos;

include/linux/aio.h

@@ -14,18 +14,12 @@ struct kioctx;
 #define KIOCB_SYNC_KEY		(~0U)
 
 /* ki_flags bits */
-#define KIF_KICKED		1
 #define KIF_CANCELLED		2
 
-#define kiocbTryKick(iocb)	test_and_set_bit(KIF_KICKED, &(iocb)->ki_flags)
-
-#define kiocbSetKicked(iocb)	set_bit(KIF_KICKED, &(iocb)->ki_flags)
 #define kiocbSetCancelled(iocb)	set_bit(KIF_CANCELLED, &(iocb)->ki_flags)
 
-#define kiocbClearKicked(iocb)	clear_bit(KIF_KICKED, &(iocb)->ki_flags)
 #define kiocbClearCancelled(iocb)	clear_bit(KIF_CANCELLED, &(iocb)->ki_flags)
 
-#define kiocbIsKicked(iocb)	test_bit(KIF_KICKED, &(iocb)->ki_flags)
 #define kiocbIsCancelled(iocb)	test_bit(KIF_CANCELLED, &(iocb)->ki_flags)
 
 /* is there a better place to document function pointer methods? */
@@ -52,18 +46,8 @@ struct kioctx;
  * not ask the method again -- ki_retry must ensure forward progress.
  * aio_complete() must be called once and only once in the future, multiple
  * calls may result in undefined behaviour.
- *
- * If ki_retry returns -EIOCBRETRY it has made a promise that kick_iocb()
- * will be called on the kiocb pointer in the future.  This may happen
- * through generic helpers that associate kiocb->ki_wait with a wait
- * queue head that ki_retry uses via current->io_wait.  It can also happen
- * with custom tracking and manual calls to kick_iocb(), though that is
- * discouraged.  In either case, kick_iocb() must be called once and only
- * once.  ki_retry must ensure forward progress, the AIO core will wait
- * indefinitely for kick_iocb() to be called.
  */
 struct kiocb {
-	struct list_head	ki_run_list;
 	unsigned long		ki_flags;
 	int			ki_users;
 	unsigned		ki_key;		/* id of this request */
@@ -160,7 +144,6 @@ static inline unsigned aio_ring_avail(struct aio_ring_info *info,
 struct kioctx {
 	atomic_t		users;
 	int			dead;
-	struct mm_struct	*mm;
 
 	/* This needs improving */
 	unsigned long		user_id;
@@ -172,15 +155,12 @@ struct kioctx {
 
 	int			reqs_active;
 	struct list_head	active_reqs;	/* used for cancellation */
-	struct list_head	run_list;	/* used for kicked reqs */
 
 	/* sys_io_setup currently limits this to an unsigned int */
 	unsigned		max_reqs;
 
 	struct aio_ring_info	ring_info;
 
-	struct delayed_work	wq;
-
 	struct rcu_head		rcu_head;
 };
 
@@ -188,7 +168,6 @@ struct kioctx {
 #ifdef CONFIG_AIO
 extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb);
 extern int aio_put_req(struct kiocb *iocb);
-extern void kick_iocb(struct kiocb *iocb);
 extern int aio_complete(struct kiocb *iocb, long res, long res2);
 struct mm_struct;
 extern void exit_aio(struct mm_struct *mm);
@@ -197,7 +176,6 @@ extern long do_io_submit(aio_context_t ctx_id, long nr,
 #else
 static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; }
 static inline int aio_put_req(struct kiocb *iocb) { return 0; }
-static inline void kick_iocb(struct kiocb *iocb) { }
 static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; }
 struct mm_struct;
 static inline void exit_aio(struct mm_struct *mm) { }

include/linux/errno.h

@@ -28,6 +28,5 @@
 #define EBADTYPE	527	/* Type not supported by server */
 #define EJUKEBOX	528	/* Request initiated, but will not complete before timeout */
 #define EIOCBQUEUED	529	/* iocb queued, will get completion event */
-#define EIOCBRETRY	530	/* iocb queued, will trigger a retry */
 
 #endif