Merge branch 'linus' into x86/bootmem

[karo-tx-linux.git] / mm / page_alloc.c

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 90c1439549fdf221ab1813b14ae0d5dc74adce45..887ce3bd823daa353326eeff654ec97c8ca3f11c 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1088,8 +1088,10 @@ static void drain_pages(unsigned int cpu)
                pset = per_cpu_ptr(zone->pageset, cpu);
 
                pcp = &pset->pcp;
-               free_pcppages_bulk(zone, pcp->count, pcp);
-               pcp->count = 0;
+               if (pcp->count) {
+                       free_pcppages_bulk(zone, pcp->count, pcp);
+                       pcp->count = 0;
+               }
                local_irq_restore(flags);
        }
 }
@@ -2034,6 +2036,14 @@ restart:
         */
        alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
+       /*
+        * Find the true preferred zone if the allocation is unconstrained by
+        * cpusets.
+        */
+       if (!(alloc_flags & ALLOC_CPUSET) && !nodemask)
+               first_zones_zonelist(zonelist, high_zoneidx, NULL,
+                                       &preferred_zone);
+
        /* This is the last chance, in general, before the goto nopage. */
        page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
                        high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -2192,7 +2202,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 
        get_mems_allowed();
        /* The preferred zone is used for statistics later */
-       first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone);
+       first_zones_zonelist(zonelist, high_zoneidx,
+                               nodemask ? : &cpuset_current_mems_allowed,
+                               &preferred_zone);
        if (!preferred_zone) {
                put_mems_allowed();
                return NULL;
@@ -3604,6 +3616,34 @@ static int __meminit next_active_region_index_in_nid(int index, int nid)
        return -1;
 }
 
+/*
+ * Basic iterator support. Return the last range of PFNs for a node
+ * Note: nid == MAX_NUMNODES returns last region regardless of node
+ */
+static int __meminit last_active_region_index_in_nid(int nid)
+{
+       int i;
+
+       for (i = nr_nodemap_entries - 1; i >= 0; i--)
+               if (nid == MAX_NUMNODES || early_node_map[i].nid == nid)
+                       return i;
+
+       return -1;
+}
+
+/*
+ * Basic iterator support. Return the previous active range of PFNs for a node
+ * Note: nid == MAX_NUMNODES returns next region regardless of node
+ */
+static int __meminit previous_active_region_index_in_nid(int index, int nid)
+{
+       for (index = index - 1; index >= 0; index--)
+               if (nid == MAX_NUMNODES || early_node_map[index].nid == nid)
+                       return index;
+
+       return -1;
+}
+
 #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
 /*
  * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
@@ -3655,6 +3695,10 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
        for (i = first_active_region_index_in_nid(nid); i != -1; \
                                i = next_active_region_index_in_nid(i, nid))
 
+#define for_each_active_range_index_in_nid_reverse(i, nid) \
+       for (i = last_active_region_index_in_nid(nid); i != -1; \
+                               i = previous_active_region_index_in_nid(i, nid))
+
 /**
  * free_bootmem_with_active_regions - Call free_bootmem_node for each active range
  * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed.
@@ -3693,7 +3737,7 @@ u64 __init find_memory_core_early(int nid, u64 size, u64 align,
        int i;
 
        /* Need to go over early_node_map to find out good range for node */
-       for_each_active_range_index_in_nid(i, nid) {
+       for_each_active_range_index_in_nid_reverse(i, nid) {
                u64 addr;
                u64 ei_start, ei_last;
                u64 final_start, final_end;