[058/155] mm: swap: use smp_mb__after_atomic() to order LRU bit set

Commit Message

Andrew Morton April 2, 2020, 4:06 a.m. UTC

From: Yang Shi <[e-mail]>
Subject: mm: swap: use smp_mb__after_atomic() to order LRU bit set

Memory barrier is needed after setting LRU bit, but smp_mb() is too
strong.  Some architectures, i.e.  x86, imply memory barrier with atomic
operations, so replacing it with smp_mb__after_atomic() sounds better,
which is nop on strong ordered machines, and full memory barriers on
others.  With this change the vm-scalability cases would perform better on
x86, I saw total 6% improvement with this patch and previous inline fix.

The test data (lru-file-readtwice throughput) against v5.6-rc4:
	mainline	w/ inline fix	w/ both (adding this)
	150MB		154MB		159MB

Link: http://lkml.kernel.org/r/[e-mail]
Fixes: 9c4e6b1a7027 ("mm, mlock, vmscan: no more skipping pagevecs")
Signed-off-by: Yang Shi <[e-mail]>
Acked-by: Vlastimil Babka <[e-mail]>
Reviewed-by: Shakeel Butt <[e-mail]>
Tested-by: Shakeel Butt <[e-mail]>
Acked-by: Johannes Weiner <[e-mail]>
Cc: Matthew Wilcox (Oracle) <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
---

 mm/swap.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Patch

--- a/mm/swap.c~mm-swap-use-smp_mb__after_atomic-to-order-lru-bit-set
+++ a/mm/swap.c
@@ -931,7 +931,6 @@  static void __pagevec_lru_add_fn(struct
 
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 
-	SetPageLRU(page);
 	/*
 	 * Page becomes evictable in two ways:
 	 * 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()].
@@ -958,7 +957,8 @@  static void __pagevec_lru_add_fn(struct
 	 * looking at the same page) and the evictable page will be stranded
 	 * in an unevictable LRU.
 	 */
-	smp_mb();
+	SetPageLRU(page);
+	smp_mb__after_atomic();
 
 	if (page_evictable(page)) {
 		lru = page_lru(page);