From 8b9132388964df2cfe151a88fd1dd8219dabf23c Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 10 Jul 2017 15:48:47 -0700 Subject: mm: unify new_node_page and alloc_migrate_target Commit 394e31d2ceb4 ("mem-hotplug: alloc new page from a nearest neighbor node when mem-offline") has duplicated a large part of alloc_migrate_target with some hotplug specific special casing. To be more precise it tried to enfore the allocation from a different node than the original page. As a result the two function diverged in their shared logic, e.g. the hugetlb allocation strategy. Let's unify the two and express different NUMA requirements by the given nodemask. new_node_page will simply exclude the node it doesn't care about and alloc_migrate_target will use all the available nodes. alloc_migrate_target will then learn to migrate hugetlb pages more sanely and use preallocated pool when possible. Please note that alloc_migrate_target used to call alloc_page resp. alloc_pages_current so the memory policy of the current context which is quite strange when we consider that it is used in the context of alloc_contig_range which just tries to migrate pages which stand in the way. Link: http://lkml.kernel.org/r/20170608074553.22152-4-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Naoya Horiguchi Cc: Xishi Qiu Cc: zhong jiang Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux/migrate.h') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 48e24844b3c5..d9675b665cc4 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -4,6 +4,7 @@ #include #include #include +#include typedef struct page *new_page_t(struct page *page, unsigned long private, int **reason); @@ -30,6 +31,21 @@ enum migrate_reason { /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ extern char *migrate_reason_names[MR_TYPES]; +static inline struct page *new_page_nodemask(struct page *page, + int preferred_nid, nodemask_t *nodemask) +{ + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + + if (PageHuge(page)) + return alloc_huge_page_nodemask(page_hstate(compound_head(page)), + nodemask); + + if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) + gfp_mask |= __GFP_HIGHMEM; + + return __alloc_pages_nodemask(gfp_mask, 0, preferred_nid, nodemask); +} + #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); -- cgit v1.2.3 From 3e59fcb0e8c1c40aecb60fa4c2d1543d6a097184 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 10 Jul 2017 15:49:11 -0700 Subject: hugetlb: add support for preferred node to alloc_huge_page_nodemask alloc_huge_page_nodemask tries to allocate from any numa node in the allowed node mask starting from lower numa nodes. This might lead to filling up those low NUMA nodes while others are not used. We can reduce this risk by introducing a concept of the preferred node similar to what we have in the regular page allocator. We will start allocating from the preferred nid and then iterate over all allowed nodes in the zonelist order until we try them all. This is mimicing the page allocator logic except it operates on per-node mempools. dequeue_huge_page_vma already does this so distill the zonelist logic into a more generic dequeue_huge_page_nodemask and use it in alloc_huge_page_nodemask. This will allow us to use proper per numa distance fallback also for alloc_huge_page_node which can use alloc_huge_page_nodemask now and we can get rid of alloc_huge_page_node helper which doesn't have any user anymore. Link: http://lkml.kernel.org/r/20170622193034.28972-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Reviewed-by: Mike Kravetz Tested-by: Mike Kravetz Cc: Naoya Horiguchi Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/migrate.h') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index d9675b665cc4..4634da521238 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -38,7 +38,7 @@ static inline struct page *new_page_nodemask(struct page *page, if (PageHuge(page)) return alloc_huge_page_nodemask(page_hstate(compound_head(page)), - nodemask); + preferred_nid, nodemask); if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) gfp_mask |= __GFP_HIGHMEM; -- cgit v1.2.3 From 0f55685627d6dd2beda55a82abc02297f0f8e5c2 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 12 Jul 2017 14:36:58 -0700 Subject: mm, migration: do not trigger OOM killer when migrating memory Page migration (for memory hotplug, soft_offline_page or mbind) needs to allocate a new memory. This can trigger an oom killer if the target memory is depleated. Although quite unlikely, still possible, especially for the memory hotplug (offlining of memoery). Up to now we didn't really have reasonable means to back off. __GFP_NORETRY can fail just too easily and __GFP_THISNODE sticks to a single node and that is not suitable for all callers. But now that we have __GFP_RETRY_MAYFAIL we should use it. It is preferable to fail the migration than disrupt the system by killing some processes. Link: http://lkml.kernel.org/r/20170623085345.11304-7-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Belits Cc: Chris Wilson Cc: Christoph Hellwig Cc: Darrick J. Wong Cc: David Daney Cc: Johannes Weiner Cc: Mel Gorman Cc: NeilBrown Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/migrate.h') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4634da521238..3e0d405dc842 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -34,7 +34,7 @@ extern char *migrate_reason_names[MR_TYPES]; static inline struct page *new_page_nodemask(struct page *page, int preferred_nid, nodemask_t *nodemask) { - gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; if (PageHuge(page)) return alloc_huge_page_nodemask(page_hstate(compound_head(page)), -- cgit v1.2.3