[PATCH] Add NUMA policy support for huge pages.

[linux-2.6] / mm / page_alloc.c

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b257720edfc83ce4d025159d05c82354b9dd220b..1e49dc7cd61969c49cef5185ff1e424be11b6815 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -903,8 +903,7 @@ restart:
                alloc_flags |= ALLOC_HARDER;
        if (gfp_mask & __GFP_HIGH)
                alloc_flags |= ALLOC_HIGH;
-       if (wait)
-               alloc_flags |= ALLOC_CPUSET;
+       alloc_flags |= ALLOC_CPUSET;
 
        /*
         * Go through the zonelist again. Let __GFP_HIGH and allocations
@@ -926,7 +925,7 @@ restart:
 nofail_alloc:
                        /* go through the zonelist yet again, ignoring mins */
                        page = get_page_from_freelist(gfp_mask, order,
-                               zonelist, ALLOC_NO_WATERMARKS|ALLOC_CPUSET);
+                               zonelist, ALLOC_NO_WATERMARKS);
                        if (page)
                                goto got_pg;
                        if (gfp_mask & __GFP_NOFAIL) {
@@ -1772,16 +1771,16 @@ static int __devinit zone_batchsize(struct zone *zone)
                batch = 1;
 
        /*
-        * We will be trying to allcoate bigger chunks of contiguous
-        * memory of the order of fls(batch).  This should result in
-        * better cache coloring.
+        * Clamp the batch to a 2^n - 1 value. Having a power
+        * of 2 value was found to be more likely to have
+        * suboptimal cache aliasing properties in some cases.
         *
-        * A sanity check also to ensure that batch is still in limits.
+        * For example if 2 tasks are alternately allocating
+        * batches of pages, one task can end up with a lot
+        * of pages of one half of the possible page colors
+        * and the other with pages of the other colors.
         */
-       batch = (1 << fls(batch + batch/2));
-
-       if (fls(batch) >= (PAGE_SHIFT + MAX_ORDER - 2))
-               batch = PAGE_SHIFT + ((MAX_ORDER - 1 - PAGE_SHIFT)/2);
+       batch = (1 << (fls(batch + batch/2)-1)) - 1;
 
        return batch;
 }
@@ -1896,7 +1895,7 @@ static int __devinit pageset_cpuup_callback(struct notifier_block *nfb,
 static struct notifier_block pageset_notifier =
        { &pageset_cpuup_callback, NULL, 0 };
 
-void __init setup_per_cpu_pageset()
+void __init setup_per_cpu_pageset(void)
 {
        int err;