From e46e7b77c9096eb2f4d6bcb9ca0b64c9338465ee Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 3 Jun 2016 14:56:01 -0700 Subject: mm, page_alloc: recalculate the preferred zoneref if the context can ignore memory policies The optimistic fast path may use cpuset_current_mems_allowed instead of of a NULL nodemask supplied by the caller for cpuset allocations. The preferred zone is calculated on this basis for statistic purposes and as a starting point in the zonelist iterator. However, if the context can ignore memory policies due to being atomic or being able to ignore watermarks then the starting point in the zonelist iterator is no longer correct. This patch resets the zonelist iterator in the allocator slowpath if the context can ignore memory policies. This will alter the zone used for statistics but only after it is known that it makes sense for that context. Resetting it before entering the slowpath would potentially allow an ALLOC_CPUSET allocation to be accounted for against the wrong zone. Note that while nodemask is not explicitly set to the original nodemask, it would only have been overwritten if cpuset_enabled() and it was reset before the slowpath was entered. Link: http://lkml.kernel.org/r/20160602103936.GU2527@techsingularity.net Fixes: c33d6c06f60f710 ("mm, page_alloc: avoid looking up the first zone in a zonelist twice") Signed-off-by: Mel Gorman Reported-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Acked-by: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 62d1ea3f2f5a..6903b695ebae 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3604,6 +3604,17 @@ retry: */ alloc_flags = gfp_to_alloc_flags(gfp_mask); + /* + * Reset the zonelist iterators if memory policies can be ignored. + * These allocations are high priority and system rather than user + * orientated. + */ + if ((alloc_flags & ALLOC_NO_WATERMARKS) || !(alloc_flags & ALLOC_CPUSET)) { + ac->zonelist = node_zonelist(numa_node_id(), gfp_mask); + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->high_zoneidx, ac->nodemask); + } + /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, order, alloc_flags & ~ALLOC_NO_WATERMARKS, ac); @@ -3612,12 +3623,6 @@ retry: /* Allocate without watermarks if the context allows */ if (alloc_flags & ALLOC_NO_WATERMARKS) { - /* - * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds - * the allocation is high priority and these type of - * allocations are system rather than user orientated - */ - ac->zonelist = node_zonelist(numa_node_id(), gfp_mask); page = get_page_from_freelist(gfp_mask, order, ALLOC_NO_WATERMARKS, ac); if (page) @@ -3816,7 +3821,11 @@ retry_cpuset: /* Dirty zone balancing only done in the fast path */ ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE); - /* The preferred zone is used for statistics later */ + /* + * The preferred zone is used for statistics but crucially it is + * also used as the starting point for the zonelist iterator. It + * may get reset for allocations that ignore memory policies. + */ ac.preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx, ac.nodemask); if (!ac.preferred_zoneref) { -- cgit v1.2.3