[PATCH] mempool: NOMEMALLOC and NORETRY

Mempools have 2 problems.

The first is that mempool_alloc can possibly get stuck in __alloc_pages
when they should opt to fail, and take an element from their reserved pool.

The second is that it will happily eat emergency PF_MEMALLOC reserves
instead of going to their reserved pools.

Fix the first by passing __GFP_NORETRY in the allocation calls in
mempool_alloc.  Fix the second by introducing a __GFP_MEMPOOL flag which
directs the page allocator not to allocate from the reserve pool.

Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 23 insertions, 12 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 848a1baac07..af7407e8cfc 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -38,14 +38,16 @@ struct vm_area_struct;
 #define __GFP_NO_GROW   0x2000u /* Slab internal usage */
 #define __GFP_COMP      0x4000u /* Add compound page metadata */
 #define __GFP_ZERO      0x8000u /* Return zeroed page on success */
+#define __GFP_NOMEMALLOC 0x10000u /* Don't use emergency reserves */
 
-#define __GFP_BITS_SHIFT 16     /* Room for 16 __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 20     /* Room for 20 __GFP_FOO bits */
 #define __GFP_BITS_MASK ((1 << __GFP_BITS_SHIFT) - 1)
 
 /* if you forget to add the bitmask here kernel will crash, period */
 #define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \
                         __GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \
-                        __GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP)
+                        __GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP| \
+                        __GFP_NOMEMALLOC)
 
 #define GFP_ATOMIC      (__GFP_HIGH)
 #define GFP_NOIO        (__GFP_WAIT)
diff --git a/mm/mempool.c b/mm/mempool.c
index b014ffeaa41..d691b5cb802 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -198,11 +198,16 @@ void * mempool_alloc(mempool_t *pool, unsigned int __nocast gfp_mask)
         void *element;
         unsigned long flags;
         DEFINE_WAIT(wait);
-        int gfp_nowait = gfp_mask & ~(__GFP_WAIT | __GFP_IO);
+        int gfp_nowait;
+
+        gfp_mask |= __GFP_NOMEMALLOC;   /* don't allocate emergency reserves */
+        gfp_mask |= __GFP_NORETRY;      /* don't loop in __alloc_pages */
+        gfp_mask |= __GFP_NOWARN;       /* failures are OK */
+        gfp_nowait = gfp_mask & ~(__GFP_WAIT | __GFP_IO);
 
         might_sleep_if(gfp_mask & __GFP_WAIT);
 repeat_alloc:
-        element = pool->alloc(gfp_nowait|__GFP_NOWARN, pool->pool_data);
+        element = pool->alloc(gfp_nowait, pool->pool_data);
         if (likely(element != NULL))
                 return element;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 08e8627361a..04a35b3d326 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -799,14 +799,18 @@ __alloc_pages(unsigned int __nocast gfp_mask, unsigned int order,
         }
 
         /* This allocation should allow future memory freeing. */
-        if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE))) && !in_interrupt()) {
-                /* go through the zonelist yet again, ignoring mins */
-                for (i = 0; (z = zones[i]) != NULL; i++) {
-                        if (!cpuset_zone_allowed(z))
-                                continue;
-                        page = buffered_rmqueue(z, order, gfp_mask);
-                        if (page)
-                                goto got_pg;
+
+        if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
+                        && !in_interrupt()) {
+                if (!(gfp_mask & __GFP_NOMEMALLOC)) {
+                        /* go through the zonelist yet again, ignoring mins */
+                        for (i = 0; (z = zones[i]) != NULL; i++) {
+                                if (!cpuset_zone_allowed(z))
+                                        continue;
+                                page = buffered_rmqueue(z, order, gfp_mask);
+                                if (page)
+                                        goto got_pg;
+                        }
                 }
                 goto nopage;
         }