1 files changed, 31 insertions, 0 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 88e708be1f64..eb7180db3033 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -174,6 +174,17 @@ static int __init hugetlb_setup(char *s)
 }
 __setup("hugepages=", hugetlb_setup);
 
+static unsigned int cpuset_mems_nr(unsigned int *array)
+{
+        int node;
+        unsigned int nr = 0;
+
+        for_each_node_mask(node, cpuset_current_mems_allowed)
+                nr += array[node];
+
+        return nr;
+}
+
 #ifdef CONFIG_SYSCTL
 static void update_and_free_page(struct page *page)
 {
@@ -819,6 +830,26 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to)
         chg = region_chg(&inode->i_mapping->private_list, from, to);
         if (chg < 0)
                 return chg;
+        /*
+         * When cpuset is configured, it breaks the strict hugetlb page
+         * reservation as the accounting is done on a global variable. Such
+         * reservation is completely rubbish in the presence of cpuset because
+         * the reservation is not checked against page availability for the
+         * current cpuset. Application can still potentially OOM'ed by kernel
+         * with lack of free htlb page in cpuset that the task is in.
+         * Attempt to enforce strict accounting with cpuset is almost
+         * impossible (or too ugly) because cpuset is too fluid that
+         * task or memory node can be dynamically moved between cpusets.
+         *
+         * The change of semantics for shared hugetlb mapping with cpuset is
+         * undesirable. However, in order to preserve some of the semantics,
+         * 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.
+         */
+        if (chg > cpuset_mems_nr(free_huge_pages_node))
+                return -ENOMEM;
+
         ret = hugetlb_acct_memory(chg);
         if (ret < 0)
                 return ret;