aio: fix io_destroy() regression by using call_rcu()

There was a regression introduced by 36f5588905c1 ("aio: refcounting
cleanup"), reported by Jens Axboe - the refcounting cleanup switched to
using RCU in the shutdown path, but the synchronize_rcu() was done in
the context of the io_destroy() syscall greatly increasing the time it
could block.

This patch switches it to call_rcu() and makes shutdown asynchronous
(more asynchronous than it was originally; before the refcount changes
io_destroy() would still wait on pending kiocbs).

Note that there's a global quota on the max outstanding kiocbs, and that
quota must be manipulated synchronously; otherwise io_setup() could
return -EAGAIN when there isn't quota available, and userspace won't
have any way of waiting until shutdown of the old kioctxs has finished
(besides busy looping).

So we release our quota before kioctx shutdown has finished, which
should be fine since the quota never corresponded to anything real
anyways.

Signed-off-by: Kent Overstreet <koverstreet@google.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>
Reported-by: Jens Axboe <axboe@kernel.dk>
Tested-by: 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>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Benjamin LaHaise <bcrl@kvack.org>
Tested-by: Benjamin LaHaise <bcrl@kvack.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 16 insertions, 20 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 7fe5bdee163..2bbcacf74d0 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -141,9 +141,6 @@ static void aio_free_ring(struct kioctx *ctx)
 	for (i = 0; i < ctx->nr_pages; i++)
 		put_page(ctx->ring_pages[i]);
 
-	if (ctx->mmap_size)
-		vm_munmap(ctx->mmap_base, ctx->mmap_size);
-
 	if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages)
 		kfree(ctx->ring_pages);
 }
@@ -322,11 +319,6 @@ static void free_ioctx(struct kioctx *ctx)
 
 	aio_free_ring(ctx);
 
-	spin_lock(&aio_nr_lock);
-	BUG_ON(aio_nr - ctx->max_reqs > aio_nr);
-	aio_nr -= ctx->max_reqs;
-	spin_unlock(&aio_nr_lock);
-
 	pr_debug("freeing %p\n", ctx);
 
 	/*
@@ -435,17 +427,24 @@ static void kill_ioctx(struct kioctx *ctx)
 {
 	if (!atomic_xchg(&ctx->dead, 1)) {
 		hlist_del_rcu(&ctx->list);
-		/* Between hlist_del_rcu() and dropping the initial ref */
-		synchronize_rcu();
 
 		/*
-		 * We can't punt to workqueue here because put_ioctx() ->
-		 * free_ioctx() will unmap the ringbuffer, and that has to be
-		 * done in the original process's context. kill_ioctx_rcu/work()
-		 * exist for exit_aio(), as in that path free_ioctx() won't do
-		 * the unmap.
+		 * It'd be more correct to do this in free_ioctx(), after all
+		 * the outstanding kiocbs have finished - but by then io_destroy
+		 * has already returned, so io_setup() could potentially return
+		 * -EAGAIN with no ioctxs actually in use (as far as userspace
+		 *  could tell).
 		 */
-		kill_ioctx_work(&ctx->rcu_work);
+		spin_lock(&aio_nr_lock);
+		BUG_ON(aio_nr - ctx->max_reqs > aio_nr);
+		aio_nr -= ctx->max_reqs;
+		spin_unlock(&aio_nr_lock);
+
+		if (ctx->mmap_size)
+			vm_munmap(ctx->mmap_base, ctx->mmap_size);
+
+		/* Between hlist_del_rcu() and dropping the initial ref */
+		call_rcu(&ctx->rcu_head, kill_ioctx_rcu);
 	}
 }
 
@@ -495,10 +494,7 @@ void exit_aio(struct mm_struct *mm)
 		 */
 		ctx->mmap_size = 0;
 
-		if (!atomic_xchg(&ctx->dead, 1)) {
-			hlist_del_rcu(&ctx->list);
-			call_rcu(&ctx->rcu_head, kill_ioctx_rcu);
-		}
+		kill_ioctx(ctx);
 	}
 }