commit 5ffac122dbda89fbb29885f35a5d47b0edb8936d
author Kent Overstreet <koverstreet@google.com> Thu May 09 15:36:07 2013 -0700
committer Benjamin LaHaise <bcrl@kvack.org> Tue Jul 30 11:53:11 2013 -0400
tree 35c6ee1e0b439983ba6d163e37d7cc66783fef9f
parent bec68faaf3ba74ed0dcd5dc3a881b30aec542973

aio: Don't use ctx->tail unnecessarily

aio_complete() (arguably) needs to keep its own trusted copy of the tail
pointer, but io_getevents() doesn't have to use it - it's already using
the head pointer from the ring buffer.

So convert it to use the tail from the ring buffer so it touches fewer
cachelines and doesn't contend with the cacheline aio_complete() needs.

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>
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>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Signed-off-by: Benjamin LaHaise <bcrl@kvack.org>

fs/aio.c

diff --git a/fs/aio.c b/fs/aio.c
index 12b3768..57b0279 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -406,7 +406,8 @@
 	struct kioctx *ctx = container_of(work, struct kioctx, free_work);
 	struct aio_ring *ring;
 	struct kiocb *req;
-	unsigned cpu, head, avail;
+	unsigned cpu, avail;
+	DEFINE_WAIT(wait);
 
 	spin_lock_irq(&ctx->ctx_lock);
 
@@ -427,22 +428,24 @@
 		kcpu->reqs_available = 0;
 	}
 
-	ring = kmap_atomic(ctx->ring_pages[0]);
-	head = ring->head;
-	kunmap_atomic(ring);
+	while (1) {
+		prepare_to_wait(&ctx->wait, &wait, TASK_UNINTERRUPTIBLE);
 
-	while (atomic_read(&ctx->reqs_available) < ctx->nr_events - 1) {
-		wait_event(ctx->wait,
-			   (head != ctx->tail) ||
-			   (atomic_read(&ctx->reqs_available) >=
-			    ctx->nr_events - 1));
-
-		avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
+		ring = kmap_atomic(ctx->ring_pages[0]);
+		avail = (ring->head <= ring->tail)
+			 ? ring->tail - ring->head
+			 : ctx->nr_events - ring->head + ring->tail;
 
 		atomic_add(avail, &ctx->reqs_available);
-		head += avail;
-		head %= ctx->nr_events;
+		ring->head = ring->tail;
+		kunmap_atomic(ring);
+
+		if (atomic_read(&ctx->reqs_available) >= ctx->nr_events - 1)
+			break;
+
+		schedule();
 	}
+	finish_wait(&ctx->wait, &wait);
 
 	WARN_ON(atomic_read(&ctx->reqs_available) > ctx->nr_events - 1);
 
@@ -869,7 +872,7 @@
 				 struct io_event __user *event, long nr)
 {
 	struct aio_ring *ring;
-	unsigned head, pos;
+	unsigned head, tail, pos;
 	long ret = 0;
 	int copy_ret;
 
@@ -877,11 +880,12 @@
 
 	ring = kmap_atomic(ctx->ring_pages[0]);
 	head = ring->head;
+	tail = ring->tail;
 	kunmap_atomic(ring);
 
-	pr_debug("h%u t%u m%u\n", head, ctx->tail, ctx->nr_events);
+	pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events);
 
-	if (head == ctx->tail)
+	if (head == tail)
 		goto out;
 
 	while (ret < nr) {
@@ -889,8 +893,8 @@
 		struct io_event *ev;
 		struct page *page;
 
-		avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
-		if (head == ctx->tail)
+		avail = (head <= tail ?  tail : ctx->nr_events) - head;
+		if (head == tail)
 			break;
 
 		avail = min(avail, nr - ret);
@@ -921,7 +925,7 @@
 	kunmap_atomic(ring);
 	flush_dcache_page(ctx->ring_pages[0]);
 
-	pr_debug("%li  h%u t%u\n", ret, head, ctx->tail);
+	pr_debug("%li  h%u t%u\n", ret, head, tail);
 
 	put_reqs_available(ctx, ret);
 out: