2 files changed, 22 insertions, 7 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6965be064a31..0a502e99ee22 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1461,7 +1461,8 @@ __alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
         struct task_struct *p = current;
         int do_retry;
         int alloc_flags;
-        int did_some_progress;
+        unsigned long did_some_progress;
+        unsigned long pages_reclaimed = 0;
 
         might_sleep_if(wait);
 
@@ -1611,15 +1612,26 @@ nofail_alloc:
          * Don't let big-order allocations loop unless the caller explicitly
          * requests that.  Wait for some write requests to complete then retry.
          *
-         * In this implementation, either order <= PAGE_ALLOC_COSTLY_ORDER or
-         * __GFP_REPEAT mean __GFP_NOFAIL, but that may not be true in other
+         * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
+         * means __GFP_NOFAIL, but that may not be true in other
          * implementations.
+         *
+         * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
+         * specified, then we retry until we no longer reclaim any pages
+         * (above), or we've reclaimed an order of pages at least as
+         * large as the allocation's order. In both cases, if the
+         * allocation still fails, we stop retrying.
          */
+        pages_reclaimed += did_some_progress;
         do_retry = 0;
         if (!(gfp_mask & __GFP_NORETRY)) {
-                if ((order <= PAGE_ALLOC_COSTLY_ORDER) ||
-                                                (gfp_mask & __GFP_REPEAT))
+                if (order <= PAGE_ALLOC_COSTLY_ORDER) {
                         do_retry = 1;
+                } else {
+                        if (gfp_mask & __GFP_REPEAT &&
+                                pages_reclaimed < (1 << order))
+                                        do_retry = 1;
+                }
                 if (gfp_mask & __GFP_NOFAIL)
                         do_retry = 1;
         }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eceac9f9032f..12e8627c9747 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1299,6 +1299,9 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
  * hope that some of these pages can be written.  But if the allocating task
  * holds filesystem locks which prevent writeout this might not work, and the
  * allocation attempt will fail.
+ *
+ * returns:     0, if no pages reclaimed
+ *              else, the number of pages reclaimed
  */
 static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
                                         struct scan_control *sc)
@@ -1347,7 +1350,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
                 }
                 total_scanned += sc->nr_scanned;
                 if (nr_reclaimed >= sc->swap_cluster_max) {
-                        ret = 1;
+                        ret = nr_reclaimed;
                         goto out;
                 }
 
@@ -1370,7 +1373,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
         }
         /* top priority shrink_caches still had more to do? don't OOM, then */
         if (!sc->all_unreclaimable && scan_global_lru(sc))
-                ret = 1;
+                ret = nr_reclaimed;
 out:
         /*
          * Now that we've scanned all the zones at this priority level, note