Merge branches 'pm-core', 'pm-clk', 'pm-domains' and 'pm-pci'

[deliverable/linux.git] / mm / page_alloc.c

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f8f3bfc435eec5bf0144798f6b890e6deacee0f6..8b3e1341b7544608cac4777a37bbd424432488e1 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -286,7 +286,9 @@ static inline void reset_deferred_meminit(pg_data_t *pgdat)
 /* Returns true if the struct page for the pfn is uninitialised */
 static inline bool __meminit early_page_uninitialised(unsigned long pfn)
 {
-       if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn)
+       int nid = early_pfn_to_nid(pfn);
+
+       if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
                return true;
 
        return false;
@@ -656,6 +658,9 @@ static inline void set_page_guard(struct zone *zone, struct page *page,
                return;
 
        page_ext = lookup_page_ext(page);
+       if (unlikely(!page_ext))
+               return;
+
        __set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 
        INIT_LIST_HEAD(&page->lru);
@@ -673,6 +678,9 @@ static inline void clear_page_guard(struct zone *zone, struct page *page,
                return;
 
        page_ext = lookup_page_ext(page);
+       if (unlikely(!page_ext))
+               return;
+
        __clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 
        set_page_private(page, 0);
@@ -1267,7 +1275,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn)
        spin_lock(&early_pfn_lock);
        nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
        if (nid < 0)
-               nid = 0;
+               nid = first_online_node;
        spin_unlock(&early_pfn_lock);
 
        return nid;
@@ -2609,11 +2617,12 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
                                page = list_last_entry(list, struct page, lru);
                        else
                                page = list_first_entry(list, struct page, lru);
-               } while (page && check_new_pcp(page));
 
-               __dec_zone_state(zone, NR_ALLOC_BATCH);
-               list_del(&page->lru);
-               pcp->count--;
+                       __dec_zone_state(zone, NR_ALLOC_BATCH);
+                       list_del(&page->lru);
+                       pcp->count--;
+
+               } while (check_new_pcp(page));
        } else {
                /*
                 * We most definitely don't want callers attempting to
@@ -3023,6 +3032,7 @@ reset_fair:
                apply_fair = false;
                fair_skipped = false;
                reset_alloc_batches(ac->preferred_zoneref->zone);
+               z = ac->preferred_zoneref;
                goto zonelist_scan;
        }
 
@@ -3596,6 +3606,17 @@ 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);
@@ -3604,12 +3625,6 @@ 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)
@@ -3808,7 +3823,11 @@ 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) {