mm/hugetlb: add mempolicy check in the reservation routine

[linux-2.6-microblaze.git] / mm / hugetlb.c

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e52c878..dffafb5 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3458,13 +3458,21 @@ static int __init default_hugepagesz_setup(char *s)
 }
 __setup("default_hugepagesz=", default_hugepagesz_setup);
 
-static unsigned int cpuset_mems_nr(unsigned int *array)
+static unsigned int allowed_mems_nr(struct hstate *h)
 {
        int node;
        unsigned int nr = 0;
+       nodemask_t *mpol_allowed;
+       unsigned int *array = h->free_huge_pages_node;
+       gfp_t gfp_mask = htlb_alloc_mask(h);
+
+       mpol_allowed = policy_nodemask_current(gfp_mask);
 
-       for_each_node_mask(node, cpuset_current_mems_allowed)
-               nr += array[node];
+       for_each_node_mask(node, cpuset_current_mems_allowed) {
+               if (!mpol_allowed ||
+                   (mpol_allowed && node_isset(node, *mpol_allowed)))
+                       nr += array[node];
+       }
 
        return nr;
 }
@@ -3643,12 +3651,18 @@ static int hugetlb_acct_memory(struct hstate *h, long delta)
         * we fall back to check against current free page availability as
         * a best attempt and hopefully to minimize the impact of changing
         * semantics that cpuset has.
+        *
+        * Apart from cpuset, we also have memory policy mechanism that
+        * also determines from which node the kernel will allocate memory
+        * in a NUMA system. So similar to cpuset, we also should consider
+        * the memory policy of the current task. Similar to the description
+        * above.
         */
        if (delta > 0) {
                if (gather_surplus_pages(h, delta) < 0)
                        goto out;
 
-               if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
+               if (delta > allowed_mems_nr(h)) {
                        return_unused_surplus_pages(h, delta);
                        goto out;
                }