mm/page_alloc: insert memory barriers to allow async update of pcp batch and high

Introduce pageset_update() to perform a safe transision from one set of
pcp->{batch,high} to a new set using memory barriers.

This ensures that batch is always set to a safe value (1) prior to
updating high, and ensure that high is fully updated before setting the
real value of batch.  It avoids ->batch ever rising above ->high.

Suggested by Gilad Ben-Yossef in these threads:

	https://lkml.org/lkml/2013/4/9/23
	https://lkml.org/lkml/2013/4/10/49

Also reproduces his proposed comment.

Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Reviewed-by: Gilad Ben-Yossef <gilad@benyossef.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8d4335779633f46d4d6a0ac067648029407f1961..eaaef2a094249d1e7f68ff249bdb840365e5ae91 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4035,12 +4035,37 @@ static int __meminit zone_batchsize(struct zone *zone)
 #endif
 }
 
+/*
+ * pcp->high and pcp->batch values are related and dependent on one another:
+ * ->batch must never be higher then ->high.
+ * The following function updates them in a safe manner without read side
+ * locking.
+ *
+ * Any new users of pcp->batch and pcp->high should ensure they can cope with
+ * those fields changing asynchronously (acording the the above rule).
+ *
+ * mutex_is_locked(&pcp_batch_high_lock) required when calling this function
+ * outside of boot time (or some other assurance that no concurrent updaters
+ * exist).
+ */
+static void pageset_update(struct per_cpu_pages *pcp, unsigned long high,
+               unsigned long batch)
+{
+       /* start with a fail safe value for batch */
+       pcp->batch = 1;
+       smp_wmb();
+
+       /* Update high, then batch, in order */
+       pcp->high = high;
+       smp_wmb();
+
+       pcp->batch = batch;
+}
+
 /* a companion to setup_pagelist_highmark() */
 static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch)
 {
-       struct per_cpu_pages *pcp = &p->pcp;
-       pcp->high = 6 * batch;
-       pcp->batch = max(1UL, 1 * batch);
+       pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch));
 }
 
 static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
@@ -4064,13 +4089,11 @@ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
 static void setup_pagelist_highmark(struct per_cpu_pageset *p,
                                unsigned long high)
 {
-       struct per_cpu_pages *pcp;
+       unsigned long batch = max(1UL, high / 4);
+       if ((high / 4) > (PAGE_SHIFT * 8))
+               batch = PAGE_SHIFT * 8;
 
-       pcp = &p->pcp;
-       pcp->high = high;
-       pcp->batch = max(1UL, high/4);
-       if ((high/4) > (PAGE_SHIFT * 8))
-               pcp->batch = PAGE_SHIFT * 8;
+       pageset_update(&p->pcp, high, batch);
 }
 
 static void __meminit setup_zone_pageset(struct zone *zone)