Subject: [merged] mm-page_alloc-insert-memory-barriers-to-allow-async-update-of-pcp-batch-and-high.patch removed from -mm tree To: cody@xxxxxxxxxxxxxxxxxx,gilad@xxxxxxxxxxxxx,kosaki.motohiro@xxxxxxxxx,mgorman@xxxxxxx,penberg@xxxxxxxxxx,mm-commits@xxxxxxxxxxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Mon, 08 Jul 2013 12:24:13 -0700 The patch titled Subject: mm/page_alloc: insert memory barriers to allow async update of pcp batch and high has been removed from the -mm tree. Its filename was mm-page_alloc-insert-memory-barriers-to-allow-async-update-of-pcp-batch-and-high.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Cody P Schafer <cody@xxxxxxxxxxxxxxxxxx> Subject: 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@xxxxxxxxxxxxxxxxxx> Reviewed-by: Gilad Ben-Yossef <gilad@xxxxxxxxxxxxx> Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxx> Cc: Mel Gorman <mgorman@xxxxxxx> Cc: Pekka Enberg <penberg@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/page_alloc.c | 41 ++++++++++++++++++++++++++++++++--------- 1 file changed, 32 insertions(+), 9 deletions(-) diff -puN mm/page_alloc.c~mm-page_alloc-insert-memory-barriers-to-allow-async-update-of-pcp-batch-and-high mm/page_alloc.c --- a/mm/page_alloc.c~mm-page_alloc-insert-memory-barriers-to-allow-async-update-of-pcp-batch-and-high +++ a/mm/page_alloc.c @@ -4035,12 +4035,37 @@ static int __meminit zone_batchsize(stru #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 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) _ Patches currently in -mm which might be from cody@xxxxxxxxxxxxxxxxxx are origin.patch zbud-add-to-mm.patch zswap-add-to-mm.patch zswap-add-documentation.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html