[PATCH] vmscan: fix zone_reclaim

- PF_SWAPWRITE needs to be set for RECLAIM_SWAP to be able to write
  out pages to swap. Currently RECLAIM_SWAP may not do that.

- remove setting nr_reclaimed pages after slab reclaim since the slab shrinking
  code does not use that and the nr_reclaimed pages is just right for the
  intended follow up action.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 7 insertions, 3 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1838c15ca4fd..b0af7593d01e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1908,7 +1908,12 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
                 sc.swap_cluster_max = SWAP_CLUSTER_MAX;
 
         cond_resched();
-        p->flags |= PF_MEMALLOC;
+        /*
+         * We need to be able to allocate from the reserves for RECLAIM_SWAP
+         * and we also need to be able to write out pages for RECLAIM_WRITE
+         * and RECLAIM_SWAP.
+         */
+        p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
         reclaim_state.reclaimed_slab = 0;
         p->reclaim_state = &reclaim_state;
 
@@ -1932,11 +1937,10 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
                  * a long time.
                  */
                 shrink_slab(sc.nr_scanned, gfp_mask, order);
-                sc.nr_reclaimed = 1;    /* Avoid getting the off node timeout */
         }
 
         p->reclaim_state = NULL;
-        current->flags &= ~PF_MEMALLOC;
+        current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
 
         if (sc.nr_reclaimed == 0)
                 zone->last_unsuccessful_zone_reclaim = jiffies;