From 950e6380aa78e990416bbe8afc3ecb055301e4c8 Mon Sep 17 00:00:00 2001
From: Aaron Lu <aaron.lu@intel.com>
Date: Fri, 2 Mar 2018 11:11:07 +0000
Subject: [PATCH] mm/free_pcppages_bulk: do not hold lock when picking pages to
free
References: bnc#971975 VM performance -- page allocator
Patch-mainline: v4.17-rc1
Git-commit: 0a5f4e5b45625e75db85b4968fc4c232d8091143
When freeing a batch of pages from Per-CPU-Pages(PCP) back to buddy, the
zone->lock is held and then pages are chosen from PCP's migratetype list.
While there is actually no need to do this 'choose part' under lock since
it's PCP pages, the only CPU that can touch them is us and irq is also
disabled.
Moving this part outside could reduce lock held time and improve
performance. Test with will-it-scale/page_fault1 full load:
kernel Broadwell(2S) Skylake(2S) Broadwell(4S) Skylake(4S)
v4.16-rc2+ 9034215 7971818 13667135 15677465
this patch 9536374 +5.6% 8314710 +4.3% 14070408 +3.0% 16675866 +6.4%
What the test does is: starts $nr_cpu processes and each will repeatedly
do the following for 5 minutes:
1 mmap 128M anonymouse space;
2 write access to that space;
3 munmap.
The score is the aggregated iteration.
https://github.com/antonblanchard/will-it-scale/blob/master/tests/page_fault1.c
Link: http://lkml.kernel.org/r/20180301062845.26038-3-aaron.lu@intel.com
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Kemi Wang <kemi.wang@intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
mm/page_alloc.c | 39 +++++++++++++++++++++++----------------
1 file changed, 23 insertions(+), 16 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 787958f28993..2be4da141744 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1113,12 +1113,10 @@ static void free_pcppages_bulk(struct zone *zone, int count,
int migratetype = 0;
int batch_free = 0;
bool isolated_pageblocks;
-
- spin_lock(&zone->lock);
- isolated_pageblocks = has_isolate_pageblock(zone);
+ struct page *page, *tmp;
+ LIST_HEAD(head);
while (count) {
- struct page *page;
struct list_head *list;
/*
@@ -1140,27 +1138,36 @@ static void free_pcppages_bulk(struct zone *zone, int count,
batch_free = count;
do {
- int mt; /* migratetype of the to-be-freed page */
-
page = list_last_entry(list, struct page, lru);
- /* must delete as __free_one_page list manipulates */
+ /* must delete to avoid corrupting pcp list */
list_del(&page->lru);
pcp->count--;
- mt = get_pcppage_migratetype(page);
- /* MIGRATE_ISOLATE page should not go to pcplists */
- VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
- /* Pageblock could have been isolated meanwhile */
- if (unlikely(isolated_pageblocks))
- mt = get_pageblock_migratetype(page);
-
if (bulkfree_pcp_prepare(page))
continue;
- __free_one_page(page, page_to_pfn(page), zone, 0, mt);
- trace_mm_page_pcpu_drain(page, 0, mt);
+ list_add_tail(&page->lru, &head);
} while (--count && --batch_free && !list_empty(list));
}
+
+ spin_lock(&zone->lock);
+ isolated_pageblocks = has_isolate_pageblock(zone);
+
+ /*
+ * Use safe version since after __free_one_page(),
+ * page->lru.next will not point to original list.
+ */
+ list_for_each_entry_safe(page, tmp, &head, lru) {
+ int mt = get_pcppage_migratetype(page);
+ /* MIGRATE_ISOLATE page should not go to pcplists */
+ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
+ /* Pageblock could have been isolated meanwhile */
+ if (unlikely(isolated_pageblocks))
+ mt = get_pageblock_migratetype(page);
+
+ __free_one_page(page, page_to_pfn(page), zone, 0, mt);
+ trace_mm_page_pcpu_drain(page, 0, mt);
+ }
spin_unlock(&zone->lock);
}