From: Dave Chinner <dchinner@redhat.com>
Date: Fri, 8 Jul 2011 04:14:35 +0000 (+1000)
Subject: vmscan: shrinker->nr updates race and go wrong
X-Git-Url: http://git.cdn.openwrt.org/?a=commitdiff_plain;h=acf92b485cccf028177f46918e045c0c4e80ee10;p=openwrt%2Fstaging%2Fblogic.git

vmscan: shrinker->nr updates race and go wrong

shrink_slab() allows shrinkers to be called in parallel so the
struct shrinker can be updated concurrently. It does not provide any
exclusio for such updates, so we can get the shrinker->nr value
increasing or decreasing incorrectly.

As a result, when a shrinker repeatedly returns a value of -1 (e.g.
a VFS shrinker called w/ GFP_NOFS), the shrinker->nr goes haywire,
sometimes updating with the scan count that wasn't used, sometimes
losing it altogether. Worse is when a shrinker does work and that
update is lost due to racy updates, which means the shrinker will do
the work again!

Fix this by making the total_scan calculations independent of
shrinker->nr, and making the shrinker->nr updates atomic w.r.t. to
other updates via cmpxchg loops.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 255226554a3d..2f7c6ae8fae0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -251,17 +251,29 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 		unsigned long total_scan;
 		unsigned long max_pass;
 		int shrink_ret = 0;
+		long nr;
+		long new_nr;
 
+		/*
+		 * copy the current shrinker scan count into a local variable
+		 * and zero it so that other concurrent shrinker invocations
+		 * don't also do this scanning work.
+		 */
+		do {
+			nr = shrinker->nr;
+		} while (cmpxchg(&shrinker->nr, nr, 0) != nr);
+
+		total_scan = nr;
 		max_pass = do_shrinker_shrink(shrinker, shrink, 0);
 		delta = (4 * nr_pages_scanned) / shrinker->seeks;
 		delta *= max_pass;
 		do_div(delta, lru_pages + 1);
-		shrinker->nr += delta;
-		if (shrinker->nr < 0) {
+		total_scan += delta;
+		if (total_scan < 0) {
 			printk(KERN_ERR "shrink_slab: %pF negative objects to "
 			       "delete nr=%ld\n",
-			       shrinker->shrink, shrinker->nr);
-			shrinker->nr = max_pass;
+			       shrinker->shrink, total_scan);
+			total_scan = max_pass;
 		}
 
 		/*
@@ -269,13 +281,10 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 		 * never try to free more than twice the estimate number of
 		 * freeable entries.
 		 */
-		if (shrinker->nr > max_pass * 2)
-			shrinker->nr = max_pass * 2;
-
-		total_scan = shrinker->nr;
-		shrinker->nr = 0;
+		if (total_scan > max_pass * 2)
+			total_scan = max_pass * 2;
 
-		trace_mm_shrink_slab_start(shrinker, shrink, total_scan,
+		trace_mm_shrink_slab_start(shrinker, shrink, nr,
 					nr_pages_scanned, lru_pages,
 					max_pass, delta, total_scan);
 
@@ -296,9 +305,19 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 			cond_resched();
 		}
 
-		shrinker->nr += total_scan;
-		trace_mm_shrink_slab_end(shrinker, shrink_ret, total_scan,
-					 shrinker->nr);
+		/*
+		 * move the unused scan count back into the shrinker in a
+		 * manner that handles concurrent updates. If we exhausted the
+		 * scan, there is no need to do an update.
+		 */
+		do {
+			nr = shrinker->nr;
+			new_nr = total_scan + nr;
+			if (total_scan <= 0)
+				break;
+		} while (cmpxchg(&shrinker->nr, nr, new_nr) != nr);
+
+		trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
 	}
 	up_read(&shrinker_rwsem);
 out: