hugetlb: fix pool shrinking while in restricted cpuset

[pandora-kernel.git] / mm / hugetlb.c

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 89e6286..dcacc81 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -71,7 +71,25 @@ static void enqueue_huge_page(struct page *page)
        free_huge_pages_node[nid]++;
 }
 
-static struct page *dequeue_huge_page(struct vm_area_struct *vma,
+static struct page *dequeue_huge_page(void)
+{
+       int nid;
+       struct page *page = NULL;
+
+       for (nid = 0; nid < MAX_NUMNODES; ++nid) {
+               if (!list_empty(&hugepage_freelists[nid])) {
+                       page = list_entry(hugepage_freelists[nid].next,
+                                         struct page, lru);
+                       list_del(&page->lru);
+                       free_huge_pages--;
+                       free_huge_pages_node[nid]--;
+                       break;
+               }
+       }
+       return page;
+}
+
+static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
                                unsigned long address)
 {
        int nid;
@@ -296,8 +314,10 @@ static int gather_surplus_pages(int delta)
        int needed, allocated;
 
        needed = (resv_huge_pages + delta) - free_huge_pages;
-       if (needed <= 0)
+       if (needed <= 0) {
+               resv_huge_pages += delta;
                return 0;
+       }
 
        allocated = 0;
        INIT_LIST_HEAD(&surplus_list);
@@ -335,9 +355,12 @@ retry:
         * The surplus_list now contains _at_least_ the number of extra pages
         * needed to accomodate the reservation.  Add the appropriate number
         * of pages to the hugetlb pool and free the extras back to the buddy
-        * allocator.
+        * allocator.  Commit the entire reservation here to prevent another
+        * process from stealing the pages as they are added to the pool but
+        * before they are reserved.
         */
        needed += allocated;
+       resv_huge_pages += delta;
        ret = 0;
 free:
        list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
@@ -371,6 +394,9 @@ static void return_unused_surplus_pages(unsigned long unused_resv_pages)
        struct page *page;
        unsigned long nr_pages;
 
+       /* Uncommit the reservation */
+       resv_huge_pages -= unused_resv_pages;
+
        nr_pages = min(unused_resv_pages, surplus_huge_pages);
 
        while (nr_pages) {
@@ -402,7 +428,7 @@ static struct page *alloc_huge_page_shared(struct vm_area_struct *vma,
        struct page *page;
 
        spin_lock(&hugetlb_lock);
-       page = dequeue_huge_page(vma, addr);
+       page = dequeue_huge_page_vma(vma, addr);
        spin_unlock(&hugetlb_lock);
        return page ? page : ERR_PTR(-VM_FAULT_OOM);
 }
@@ -417,7 +443,7 @@ static struct page *alloc_huge_page_private(struct vm_area_struct *vma,
 
        spin_lock(&hugetlb_lock);
        if (free_huge_pages > resv_huge_pages)
-               page = dequeue_huge_page(vma, addr);
+               page = dequeue_huge_page_vma(vma, addr);
        spin_unlock(&hugetlb_lock);
        if (!page) {
                page = alloc_buddy_huge_page(vma, addr);
@@ -570,7 +596,7 @@ static unsigned long set_max_huge_pages(unsigned long count)
        min_count = max(count, min_count);
        try_to_free_low(min_count);
        while (min_count < persistent_huge_pages) {
-               struct page *page = dequeue_huge_page(NULL, 0);
+               struct page *page = dequeue_huge_page();
                if (!page)
                        break;
                update_and_free_page(page);
@@ -1205,12 +1231,13 @@ static int hugetlb_acct_memory(long delta)
                if (gather_surplus_pages(delta) < 0)
                        goto out;
 
-               if (delta > cpuset_mems_nr(free_huge_pages_node))
+               if (delta > cpuset_mems_nr(free_huge_pages_node)) {
+                       return_unused_surplus_pages(delta);
                        goto out;
+               }
        }
 
        ret = 0;
-       resv_huge_pages += delta;
        if (delta < 0)
                return_unused_surplus_pages((unsigned long) -delta);