mm, page_alloc: allow hugepage fallback to remote nodes when madvised

[linux-2.6-block.git] / mm / page_alloc.c

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 272c6de1bf4ead31c22aca202940da00bc8eaf8b..87cbd92065e53cd45d1412b200f96e8769896aaf 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2238,27 +2238,12 @@ static int move_freepages(struct zone *zone,
        unsigned int order;
        int pages_moved = 0;
 
-#ifndef CONFIG_HOLES_IN_ZONE
-       /*
-        * page_zone is not safe to call in this context when
-        * CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant
-        * anyway as we check zone boundaries in move_freepages_block().
-        * Remove at a later date when no bug reports exist related to
-        * grouping pages by mobility
-        */
-       VM_BUG_ON(pfn_valid(page_to_pfn(start_page)) &&
-                 pfn_valid(page_to_pfn(end_page)) &&
-                 page_zone(start_page) != page_zone(end_page));
-#endif
        for (page = start_page; page <= end_page;) {
                if (!pfn_valid_within(page_to_pfn(page))) {
                        page++;
                        continue;
                }
 
-               /* Make sure we are not inadvertently changing nodes */
-               VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
-
                if (!PageBuddy(page)) {
                        /*
                         * We assume that pages that could be isolated for
@@ -2273,6 +2258,10 @@ static int move_freepages(struct zone *zone,
                        continue;
                }
 
+               /* Make sure we are not inadvertently changing nodes */
+               VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
+               VM_BUG_ON_PAGE(page_zone(page) != zone, page);
+
                order = page_order(page);
                move_to_free_area(page, &zone->free_area[order], migratetype);
                page += 1 << order;
@@ -4469,6 +4458,28 @@ retry_cpuset:
                if (page)
                        goto got_pg;
 
+                if (order >= pageblock_order && (gfp_mask & __GFP_IO)) {
+                       /*
+                        * If allocating entire pageblock(s) and compaction
+                        * failed because all zones are below low watermarks
+                        * or is prohibited because it recently failed at this
+                        * order, fail immediately.
+                        *
+                        * Reclaim is
+                        *  - potentially very expensive because zones are far
+                        *    below their low watermarks or this is part of very
+                        *    bursty high order allocations,
+                        *  - not guaranteed to help because isolate_freepages()
+                        *    may not iterate over freed pages as part of its
+                        *    linear scan, and
+                        *  - unlikely to make entire pageblocks free on its
+                        *    own.
+                        */
+                       if (compact_result == COMPACT_SKIPPED ||
+                           compact_result == COMPACT_DEFERRED)
+                               goto nopage;
+               }
+
                /*
                 * Checks for costly allocations with __GFP_NORETRY, which
                 * includes THP page fault allocations