lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1341391138-9547-2-git-send-email-laijs@cn.fujitsu.com>
Date:	Wed, 4 Jul 2012 16:38:56 +0800
From:	Lai Jiangshan <laijs@...fujitsu.com>
To:	Mel Gorman <mel@....ul.ie>
Cc:	Chris Metcalf <cmetcalf@...era.com>, Len Brown <lenb@...nel.org>,
	Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
	Andi Kleen <andi@...stfloor.org>, Julia Lawall <julia@...u.dk>,
	David Howells <dhowells@...hat.com>,
	Lai Jiangshan <laijs@...fujitsu.com>,
	Benjamin Herrenschmidt <benh@...nel.crashing.org>,
	Kay Sievers <kay.sievers@...y.org>,
	Ingo Molnar <mingo@...e.hu>,
	Paul Gortmaker <paul.gortmaker@...driver.com>,
	Daniel Kiper <dkiper@...-space.pl>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>,
	Michal Hocko <mhocko@...e.cz>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>,
	Minchan Kim <minchan@...nel.org>,
	Michal Nazarewicz <mina86@...a86.com>,
	Marek Szyprowski <m.szyprowski@...sung.com>,
	Rik van Riel <riel@...hat.com>,
	Bjorn Helgaas <bhelgaas@...gle.com>,
	Christoph Lameter <cl@...ux.com>,
	David Rientjes <rientjes@...gle.com>,
	linux-kernel@...r.kernel.org, linux-acpi@...r.kernel.org,
	linux-mm@...ck.org
Subject: [RFC PATCH 1/3 V1 resend] mm, page_alloc: use __rmqueue_smallest when borrow memory from MIGRATE_CMA

The pages of MIGRATE_CMA can't not be changed to the other type,
nor be moved to the other free list. 

==>
So when we use __rmqueue_fallback() to borrow memory from MIGRATE_CMA,
one of the highest order page is borrowed and it is split.
But the free pages resulted by splitting can NOT
be moved to MIGRATE_MOVABLE.

==>
So in the next time of allocation, we NEED to borrow again,
another one of the highest order page is borrowed from CMA and it is split.
and results some other new split free pages.

==>
So when __rmqueue_fallback() borrows (highest order)memory from MIGRATE_CMA,
it introduces fragments at the same time and may waste tlb(only one page is used in
a pageblock).

Conclusion:
We should borrows the smallest order memory from MIGRATE_CMA in such case

Result(good):
1) use __rmqueue_smallest when borrow memory from MIGRATE_CMA
2) __rmqueue_fallback() don't handle CMA, it becomes much simpler
Result(bad):
__rmqueue_smallest() can't not be inlined to avoid function call overhead.

Signed-off-by: Lai Jiangshan <laijs@...fujitsu.com>
---
 include/linux/mmzone.h |    1 +
 mm/page_alloc.c        |   63 ++++++++++++++++--------------------------------
 2 files changed, 22 insertions(+), 42 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index bf3404e..979c333 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -40,6 +40,7 @@ enum {
 	MIGRATE_RECLAIMABLE,
 	MIGRATE_MOVABLE,
 	MIGRATE_PCPTYPES,	/* the number of types on the pcp lists */
+	MIGRATE_PRIME_TYPES = MIGRATE_PCPTYPES,
 	MIGRATE_RESERVE = MIGRATE_PCPTYPES,
 #ifdef CONFIG_CMA
 	/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 476ae3e..efc327f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -893,17 +893,10 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
  * This array describes the order lists are fallen back to when
  * the free lists for the desirable migrate type are depleted
  */
-static int fallbacks[MIGRATE_TYPES][4] = {
-	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,     MIGRATE_RESERVE },
-	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,     MIGRATE_RESERVE },
-#ifdef CONFIG_CMA
-	[MIGRATE_MOVABLE]     = { MIGRATE_CMA,         MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
-	[MIGRATE_CMA]         = { MIGRATE_RESERVE }, /* Never used */
-#else
-	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE,   MIGRATE_RESERVE },
-#endif
-	[MIGRATE_RESERVE]     = { MIGRATE_RESERVE }, /* Never used */
-	[MIGRATE_ISOLATE]     = { MIGRATE_RESERVE }, /* Never used */
+static int fallbacks[MIGRATE_PRIME_TYPES][2] = {
+	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE   },
+	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE   },
+	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE },
 };
 
 /*
@@ -995,16 +988,15 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 	struct page *page;
 	int migratetype, i;
 
+	if (WARN_ON_ONCE(start_migratetype >= MIGRATE_PRIME_TYPES))
+		start_migratetype = MIGRATE_UNMOVABLE;
+
 	/* Find the largest possible block of pages in the other list */
 	for (current_order = MAX_ORDER-1; current_order >= order;
 						--current_order) {
-		for (i = 0;; i++) {
+		for (i = 0; i < ARRAY_SIZE(fallbacks[0]); i++) {
 			migratetype = fallbacks[start_migratetype][i];
 
-			/* MIGRATE_RESERVE handled later if necessary */
-			if (migratetype == MIGRATE_RESERVE)
-				break;
-
 			area = &(zone->free_area[current_order]);
 			if (list_empty(&area->free_list[migratetype]))
 				continue;
@@ -1018,17 +1010,10 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 			 * pages to the preferred allocation list. If falling
 			 * back for a reclaimable kernel allocation, be more
 			 * aggressive about taking ownership of free pages
-			 *
-			 * On the other hand, never change migration
-			 * type of MIGRATE_CMA pageblocks nor move CMA
-			 * pages on different free lists. We don't
-			 * want unmovable pages to be allocated from
-			 * MIGRATE_CMA areas.
 			 */
-			if (!is_migrate_cma(migratetype) &&
-			    (unlikely(current_order >= pageblock_order / 2) ||
-			     start_migratetype == MIGRATE_RECLAIMABLE ||
-			     page_group_by_mobility_disabled)) {
+			if (unlikely(current_order >= pageblock_order / 2) ||
+			    start_migratetype == MIGRATE_RECLAIMABLE ||
+			    page_group_by_mobility_disabled) {
 				int pages;
 				pages = move_freepages_block(zone, page,
 								start_migratetype);
@@ -1047,14 +1032,12 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 			rmv_page_order(page);
 
 			/* Take ownership for orders >= pageblock_order */
-			if (current_order >= pageblock_order &&
-			    !is_migrate_cma(migratetype))
+			if (current_order >= pageblock_order)
 				change_pageblock_range(page, current_order,
 							start_migratetype);
 
 			expand(zone, page, order, current_order, area,
-			       is_migrate_cma(migratetype)
-			     ? migratetype : start_migratetype);
+			       start_migratetype);
 
 			trace_mm_page_alloc_extfrag(page, order, current_order,
 				start_migratetype, migratetype);
@@ -1075,22 +1058,18 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order,
 {
 	struct page *page;
 
-retry_reserve:
 	page = __rmqueue_smallest(zone, order, migratetype);
 
-	if (unlikely(!page) && migratetype != MIGRATE_RESERVE) {
+#ifdef CONFIG_CMA
+	if (unlikely(!page) && migratetype == MIGRATE_MOVABLE)
+		page = __rmqueue_smallest(zone, order, MIGRATE_CMA);
+#endif
+
+	if (unlikely(!page))
 		page = __rmqueue_fallback(zone, order, migratetype);
 
-		/*
-		 * Use MIGRATE_RESERVE rather than fail an allocation. goto
-		 * is used because __rmqueue_smallest is an inline function
-		 * and we want just one call site
-		 */
-		if (!page) {
-			migratetype = MIGRATE_RESERVE;
-			goto retry_reserve;
-		}
-	}
+	if (unlikely(!page))
+		page = __rmqueue_smallest(zone, order, MIGRATE_RESERVE);
 
 	trace_mm_page_alloc_zone_locked(page, order, migratetype);
 	return page;
-- 
1.7.4.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ