Linux 3.14

[~andy/linux] / mm / page_alloc.c

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e3758a09a009747bd17cb75442d0fcae69a74cc4..3bac76ae4b30ec8a62042bdff9644e87ee181d3c 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -369,9 +369,11 @@ void prep_compound_page(struct page *page, unsigned long order)
        __SetPageHead(page);
        for (i = 1; i < nr_pages; i++) {
                struct page *p = page + i;
-               __SetPageTail(p);
                set_page_count(p, 0);
                p->first_page = page;
+               /* Make sure p->first_page is always valid for PageTail() */
+               smp_wmb();
+               __SetPageTail(p);
        }
 }
 
@@ -1236,6 +1238,15 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
        }
        local_irq_restore(flags);
 }
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+       return (gfp_mask & GFP_THISNODE) == GFP_THISNODE;
+}
+#else
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+       return false;
+}
 #endif
 
 /*
@@ -1572,7 +1583,13 @@ again:
                                          get_pageblock_migratetype(page));
        }
 
-       __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+       /*
+        * NOTE: GFP_THISNODE allocations do not partake in the kswapd
+        * aging protocol, so they can't be fair.
+        */
+       if (!gfp_thisnode_allocation(gfp_flags))
+               __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+
        __count_zone_vm_events(PGALLOC, zone, 1 << order);
        zone_statistics(preferred_zone, zone, gfp_flags);
        local_irq_restore(flags);
@@ -1944,8 +1961,12 @@ zonelist_scan:
                 * ultimately fall back to remote zones that do not
                 * partake in the fairness round-robin cycle of this
                 * zonelist.
+                *
+                * NOTE: GFP_THISNODE allocations do not partake in
+                * the kswapd aging protocol, so they can't be fair.
                 */
-               if (alloc_flags & ALLOC_WMARK_LOW) {
+               if ((alloc_flags & ALLOC_WMARK_LOW) &&
+                   !gfp_thisnode_allocation(gfp_mask)) {
                        if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
                                continue;
                        if (!zone_local(preferred_zone, zone))
@@ -2501,8 +2522,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
         * allowed per node queues are empty and that nodes are
         * over allocated.
         */
-       if (IS_ENABLED(CONFIG_NUMA) &&
-                       (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+       if (gfp_thisnode_allocation(gfp_mask))
                goto nopage;
 
 restart: