From 327c0e968645f2601a43f5ea7c19c7b3a5fa0a34 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 31 Mar 2009 15:23:31 -0700 Subject: [PATCH] vmscan: fix it to take care of nodemask try_to_free_pages() is used for the direct reclaim of up to SWAP_CLUSTER_MAX pages when watermarks are low. The caller to alloc_pages_nodemask() can specify a nodemask of nodes that are allowed to be used but this is not passed to try_to_free_pages(). This can lead to unnecessary reclaim of pages that are unusable by the caller and int the worst case lead to allocation failure as progress was not been make where it is needed. This patch passes the nodemask used for alloc_pages_nodemask() to try_to_free_pages(). Reviewed-by: KOSAKI Motohiro Acked-by: Mel Gorman Signed-off-by: KAMEZAWA Hiroyuki Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 2 +- include/linux/swap.h | 2 +- mm/page_alloc.c | 3 ++- mm/vmscan.c | 13 +++++++++++-- 4 files changed, 15 insertions(+), 5 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index 0c14f8d..c77b848 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -290,7 +290,7 @@ static void free_more_memory(void) &zone); if (zone) try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0, - GFP_NOFS); + GFP_NOFS, NULL); } } diff --git a/include/linux/swap.h b/include/linux/swap.h index d302155..b8b0c4c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -212,7 +212,7 @@ static inline void lru_cache_add_active_file(struct page *page) /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, - gfp_t gfp_mask); + gfp_t gfp_mask, nodemask_t *mask); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, unsigned int swappiness); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cbd5321..0284e52 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1582,7 +1582,8 @@ nofail_alloc: reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; - did_some_progress = try_to_free_pages(zonelist, order, gfp_mask); + did_some_progress = try_to_free_pages(zonelist, order, + gfp_mask, nodemask); p->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); diff --git a/mm/vmscan.c b/mm/vmscan.c index f4619c6..06e7269 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -78,6 +78,12 @@ struct scan_control { /* Which cgroup do we reclaim from */ struct mem_cgroup *mem_cgroup; + /* + * Nodemask of nodes allowed by the caller. If NULL, all nodes + * are scanned. + */ + nodemask_t *nodemask; + /* Pluggable isolate pages callback */ unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst, unsigned long *scanned, int order, int mode, @@ -1538,7 +1544,8 @@ static void shrink_zones(int priority, struct zonelist *zonelist, struct zone *zone; sc->all_unreclaimable = 1; - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { + for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, + sc->nodemask) { if (!populated_zone(zone)) continue; /* @@ -1683,7 +1690,7 @@ out: } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, - gfp_t gfp_mask) + gfp_t gfp_mask, nodemask_t *nodemask) { struct scan_control sc = { .gfp_mask = gfp_mask, @@ -1694,6 +1701,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .order = order, .mem_cgroup = NULL, .isolate_pages = isolate_pages_global, + .nodemask = nodemask, }; return do_try_to_free_pages(zonelist, &sc); @@ -1714,6 +1722,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, .order = 0, .mem_cgroup = mem_cont, .isolate_pages = mem_cgroup_isolate_pages, + .nodemask = NULL, /* we don't care the placement */ }; struct zonelist *zonelist; -- 1.8.2.3