@@ -610,7 +610,9 @@ static inline void __free_one_page(struct page *page,
unsigned long combined_idx;
unsigned long uninitialized_var(buddy_idx);
struct page *buddy;
- int max_order = MAX_ORDER;
+ unsigned int max_order;
+
+ max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
VM_BUG_ON(!zone_is_initialized(zone));
@@ -619,28 +621,20 @@ static inline void __free_one_page(struct page *page,
return;
VM_BUG_ON(migratetype == -1);
- if (is_migrate_isolate(migratetype)) {
- /*
- * We restrict max order of merging to prevent merge
- * between freepages on isolate pageblock and normal
- * pageblock. Without this, pageblock isolation
- * could cause incorrect freepage accounting.
- */
- max_order = min(MAX_ORDER, pageblock_order + 1);
- } else {
+ if (likely(!is_migrate_isolate(migratetype)))
__mod_zone_freepage_state(zone, 1 << order, migratetype);
- }
- page_idx = pfn & ((1 << max_order) - 1);
+ page_idx = pfn & ((1 << MAX_ORDER) - 1);
VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
VM_BUG_ON_PAGE(bad_range(zone, page), page);
+continue_merging:
while (order < max_order - 1) {
buddy_idx = __find_buddy_index(page_idx, order);
buddy = page + (buddy_idx - page_idx);
if (!page_is_buddy(page, buddy, order))
- break;
+ goto done_merging;
/*
* Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
* merge with it and move up one order.
@@ -657,6 +651,32 @@ static inline void __free_one_page(struct page *page,
page_idx = combined_idx;
order++;
}
+ if (max_order < MAX_ORDER) {
+ /* If we are here, it means order is >= pageblock_order.
+ * We want to prevent merge between freepages on isolate
+ * pageblock and normal pageblock. Without this, pageblock
+ * isolation could cause incorrect freepage or CMA accounting.
+ *
+ * We don't want to hit this code for the more frequent
+ * low-order merging.
+ */
+ if (unlikely(has_isolate_pageblock(zone))) {
+ int buddy_mt;
+
+ buddy_idx = __find_buddy_index(page_idx, order);
+ buddy = page + (buddy_idx - page_idx);
+ buddy_mt = get_pageblock_migratetype(buddy);
+
+ if (migratetype != buddy_mt
+ && (is_migrate_isolate(migratetype) ||
+ is_migrate_isolate(buddy_mt)))
+ goto done_merging;
+ }
+ max_order++;
+ goto continue_merging;
+ }
+
+done_merging:
set_page_order(page, order);
/*
This is a note to let you know that I have just added a patch titled mm/page_alloc: prevent merging between isolated and other pageblocks to the linux-3.19.y-queue branch of the 3.19.y-ckt extended stable tree which can be found at: http://kernel.ubuntu.com/git/ubuntu/linux.git/log/?h=linux-3.19.y-queue This patch is scheduled to be released in version 3.19.8-ckt18. If you, or anyone else, feels it should not be added to this tree, please reply to this email. For more information about the 3.19.y-ckt tree, see https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable Thanks. -Kamal ---8<------------------------------------------------------------ From da0a1206b63f23716e1fa8f3f688678161a6fff1 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka <vbabka@suse.cz> Date: Fri, 25 Mar 2016 14:21:50 -0700 Subject: mm/page_alloc: prevent merging between isolated and other pageblocks commit d9dddbf556674bf125ecd925b24e43a5cf2a568a upstream. Hanjun Guo has reported that a CMA stress test causes broken accounting of CMA and free pages: > Before the test, I got: > -bash-4.3# cat /proc/meminfo | grep Cma > CmaTotal: 204800 kB > CmaFree: 195044 kB > > > After running the test: > -bash-4.3# cat /proc/meminfo | grep Cma > CmaTotal: 204800 kB > CmaFree: 6602584 kB > > So the freed CMA memory is more than total.. > > Also the the MemFree is more than mem total: > > -bash-4.3# cat /proc/meminfo > MemTotal: 16342016 kB > MemFree: 22367268 kB > MemAvailable: 22370528 kB Laura Abbott has confirmed the issue and suspected the freepage accounting rewrite around 3.18/4.0 by Joonsoo Kim. Joonsoo had a theory that this is caused by unexpected merging between MIGRATE_ISOLATE and MIGRATE_CMA pageblocks: > CMA isolates MAX_ORDER aligned blocks, but, during the process, > partialy isolated block exists. If MAX_ORDER is 11 and > pageblock_order is 9, two pageblocks make up MAX_ORDER > aligned block and I can think following scenario because pageblock > (un)isolation would be done one by one. > > (each character means one pageblock. 'C', 'I' means MIGRATE_CMA, > MIGRATE_ISOLATE, respectively. > > CC -> IC -> II (Isolation) > II -> CI -> CC (Un-isolation) > > If some pages are freed at this intermediate state such as IC or CI, > that page could be merged to the other page that is resident on > different type of pageblock and it will cause wrong freepage count. This was supposed to be prevented by CMA operating on MAX_ORDER blocks, but since it doesn't hold the zone->lock between pageblocks, a race window does exist. It's also likely that unexpected merging can occur between MIGRATE_ISOLATE and non-CMA pageblocks. This should be prevented in __free_one_page() since commit 3c605096d315 ("mm/page_alloc: restrict max order of merging on isolated pageblock"). However, we only check the migratetype of the pageblock where buddy merging has been initiated, not the migratetype of the buddy pageblock (or group of pageblocks) which can be MIGRATE_ISOLATE. Joonsoo has suggested checking for buddy migratetype as part of page_is_buddy(), but that would add extra checks in allocator hotpath and bloat-o-meter has shown significant code bloat (the function is inline). This patch reduces the bloat at some expense of more complicated code. The buddy-merging while-loop in __free_one_page() is initially bounded to pageblock_border and without any migratetype checks. The checks are placed outside, bumping the max_order if merging is allowed, and returning to the while-loop with a statement which can't be possibly considered harmful. This fixes the accounting bug and also removes the arguably weird state in the original commit 3c605096d315 where buddies could be left unmerged. Fixes: 3c605096d315 ("mm/page_alloc: restrict max order of merging on isolated pageblock") Link: https://lkml.org/lkml/2016/3/2/280 Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Hanjun Guo <guohanjun@huawei.com> Tested-by: Hanjun Guo <guohanjun@huawei.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Debugged-by: Laura Abbott <labbott@redhat.com> Debugged-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> [ kamal: backport to 4.2-stable: context ] Signed-off-by: Kamal Mostafa <kamal@canonical.com> --- mm/page_alloc.c | 46 +++++++++++++++++++++++++++++++++------------- 1 file changed, 33 insertions(+), 13 deletions(-) -- 2.7.4