The function __alloc_pages_direct_compact() sets PF_MEMALLOC to prevent
deadlock during page migration by lock_page() (see the comment in
__unmap_and_move()). Then it unconditionally clears the flag, which can clear a
pre-existing PF_MEMALLOC flag and result in recursive reclaim. This was not a
problem until commit a8161d1ed609 ("mm, page_alloc: restructure direct
compaction handling in slowpath"), because direct compation was called only
after direct reclaim, which was skipped when PF_MEMALLOC flag was set.
Even now it's only a theoretical issue, as the new callsite of
__alloc_pages_direct_compact() is reached only for costly orders and when
gfp_pfmemalloc_allowed() is true, which means either __GFP_NOMEMALLOC is in
gfp_flags or in_interrupt() is true. There is no such known context, but let's
play it safe and make __alloc_pages_direct_compact() robust for cases where
PF_MEMALLOC is already set.
Fixes: a8161d1ed609 ("mm, page_alloc: restructure direct compaction handling in
slowpath")
Reported-by: Andrey Ryabinin <aryabi...@virtuozzo.com>
Signed-off-by: Vlastimil Babka <vba...@suse.cz>
Cc: <sta...@vger.kernel.org>
---
mm/page_alloc.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3589f8be53be..b84e6ffbe756 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3288,6 +3288,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int
order,
enum compact_priority prio, enum compact_result *compact_result)
{
struct page *page;
+ unsigned int noreclaim_flag = current->flags & PF_MEMALLOC;
if (!order)
return NULL;
@@ -3295,7 +3296,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int
order,
current->flags |= PF_MEMALLOC;
*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
prio);
- current->flags &= ~PF_MEMALLOC;
+ current->flags = (current->flags & ~PF_MEMALLOC) | noreclaim_flag;
if (*compact_result <= COMPACT_INACTIVE)
return NULL;
--
2.12.2
