[PATCH] mm: __GFP_NOFAIL fix

In __alloc_pages():

if ((p->flags & (PF_MEMALLOC | PF_MEMDIE)) && !in_interrupt()) {
         /* go through the zonelist yet again, ignoring mins */
         for (i = 0; zones[i] != NULL; i++) {
                 struct zone *z = zones[i];

                 page = buffered_rmqueue(z, order, gfp_mask);
                 if (page) {
                         zone_statistics(zonelist, z);
                         goto got_pg;
                 }
         }
         goto nopage;                <<<< HERE!!! FAIL...
}

kswapd (which has PF_MEMALLOC flag) can fail to allocate memory even when
it allocates it with __GFP_NOFAIL flag.

Signed-Off-By: Pavel Emelianov <xemul@sw.ru>
Signed-Off-By: Denis Lunev <den@sw.ru>
Signed-Off-By: Kirill Korotaev <dev@sw.ru>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 987225bdd661c33cffa0674e3fae7245a6b85a1f..b37dc0f78d077834a8839f92ca0ad93f4f49c971 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -895,6 +895,7 @@ zone_reclaim_retry:
        if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
                        && !in_interrupt()) {
                if (!(gfp_mask & __GFP_NOMEMALLOC)) {
+nofail_alloc:
                        /* go through the zonelist yet again, ignoring mins */
                        for (i = 0; (z = zones[i]) != NULL; i++) {
                                if (!cpuset_zone_allowed(z, gfp_mask))
@@ -903,6 +904,10 @@ zone_reclaim_retry:
                                if (page)
                                        goto got_pg;
                        }
+                       if (gfp_mask & __GFP_NOFAIL) {
+                               blk_congestion_wait(WRITE, HZ/50);
+                               goto nofail_alloc;
+                       }
                }
                goto nopage;
        }