[PATCH] GFP_THISNODE for the slab allocator

This patch insures that the slab node lists in the NUMA case only contain
slabs that belong to that specific node.  All slab allocations use
GFP_THISNODE when calling into the page allocator.  If an allocation fails
then we fall back in the slab allocator according to the zonelists appropriate
for a certain context.

This allows a replication of the behavior of alloc_pages and alloc_pages node
in the slab layer.

Currently allocations requested from the page allocator may be redirected via
cpusets to other nodes.  This results in remote pages on nodelists and that in
turn results in interrupt latency issues during cache draining.  Plus the slab
is handing out memory as local when it is really remote.

Fallback for slab memory allocations will occur within the slab allocator and
not in the page allocator.  This is necessary in order to be able to use the
existing pools of objects on the nodes that we fall back to before adding more
pages to a slab.

The fallback function insures that the nodes we fall back to obey cpuset
restrictions of the current context.  We do not allocate objects from outside
of the current cpuset context like before.

Note that the implementation of locality constraints within the slab allocator
requires importing logic from the page allocator.  This is a mischmash that is
not that great.  Other allocators (uncached allocator, vmalloc, huge pages)
face similar problems and have similar minimal reimplementations of the basic
fallback logic of the page allocator.  There is another way of implementing a
slab by avoiding per node lists (see modular slab) but this wont work within
the existing slab.

V1->V2:
- Use NUMA_BUILD to avoid #ifdef CONFIG_NUMA
- Exploit GFP_THISNODE being 0 in the NON_NUMA case to avoid another
  #ifdef

[akpm@osdl.org: build fix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/mm/slab.c b/mm/slab.c
index 69e11c4..792bfe3 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -972,7 +972,39 @@
 	return nr;
 }
 
-#ifdef CONFIG_NUMA
+#ifndef CONFIG_NUMA
+
+#define drain_alien_cache(cachep, alien) do { } while (0)
+#define reap_alien(cachep, l3) do { } while (0)
+
+static inline struct array_cache **alloc_alien_cache(int node, int limit)
+{
+	return (struct array_cache **)BAD_ALIEN_MAGIC;
+}
+
+static inline void free_alien_cache(struct array_cache **ac_ptr)
+{
+}
+
+static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
+{
+	return 0;
+}
+
+static inline void *alternate_node_alloc(struct kmem_cache *cachep,
+		gfp_t flags)
+{
+	return NULL;
+}
+
+static inline void *__cache_alloc_node(struct kmem_cache *cachep,
+		 gfp_t flags, int nodeid)
+{
+	return NULL;
+}
+
+#else	/* CONFIG_NUMA */
+
 static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int);
 static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
 
@@ -1101,26 +1133,6 @@
 	}
 	return 1;
 }
-
-#else
-
-#define drain_alien_cache(cachep, alien) do { } while (0)
-#define reap_alien(cachep, l3) do { } while (0)
-
-static inline struct array_cache **alloc_alien_cache(int node, int limit)
-{
-	return (struct array_cache **)BAD_ALIEN_MAGIC;
-}
-
-static inline void free_alien_cache(struct array_cache **ac_ptr)
-{
-}
-
-static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
-{
-	return 0;
-}
-
 #endif
 
 static int __cpuinit cpuup_callback(struct notifier_block *nfb,
@@ -1564,7 +1576,13 @@
 	 */
 	flags |= __GFP_COMP;
 #endif
-	flags |= cachep->gfpflags;
+
+	/*
+	 * Under NUMA we want memory on the indicated node. We will handle
+	 * the needed fallback ourselves since we want to serve from our
+	 * per node object lists first for other nodes.
+	 */
+	flags |= cachep->gfpflags | GFP_THISNODE;
 
 	page = alloc_pages_node(nodeid, flags, cachep->gfporder);
 	if (!page)
@@ -3051,13 +3069,18 @@
 
 	local_irq_save(save_flags);
 
-#ifdef CONFIG_NUMA
-	if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY)))
+	if (unlikely(NUMA_BUILD &&
+			current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY)))
 		objp = alternate_node_alloc(cachep, flags);
-#endif
 
 	if (!objp)
 		objp = ____cache_alloc(cachep, flags);
+	/*
+	 * We may just have run out of memory on the local node.
+	 * __cache_alloc_node() knows how to locate memory on other nodes
+	 */
+ 	if (NUMA_BUILD && !objp)
+ 		objp = __cache_alloc_node(cachep, flags, numa_node_id());
 	local_irq_restore(save_flags);
 	objp = cache_alloc_debugcheck_after(cachep, flags, objp,
 					    caller);
@@ -3076,7 +3099,7 @@
 {
 	int nid_alloc, nid_here;
 
-	if (in_interrupt())
+	if (in_interrupt() || (flags & __GFP_THISNODE))
 		return NULL;
 	nid_alloc = nid_here = numa_node_id();
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
@@ -3089,6 +3112,28 @@
 }
 
 /*
+ * Fallback function if there was no memory available and no objects on a
+ * certain node and we are allowed to fall back. We mimick the behavior of
+ * the page allocator. We fall back according to a zonelist determined by
+ * the policy layer while obeying cpuset constraints.
+ */
+void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
+{
+	struct zonelist *zonelist = &NODE_DATA(slab_node(current->mempolicy))
+					->node_zonelists[gfp_zone(flags)];
+	struct zone **z;
+	void *obj = NULL;
+
+	for (z = zonelist->zones; *z && !obj; z++)
+		if (zone_idx(*z) <= ZONE_NORMAL &&
+				cpuset_zone_allowed(*z, flags))
+			obj = __cache_alloc_node(cache,
+					flags | __GFP_THISNODE,
+					zone_to_nid(*z));
+	return obj;
+}
+
+/*
  * A interface to enable slab creation on nodeid
  */
 static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
@@ -3141,11 +3186,15 @@
 must_grow:
 	spin_unlock(&l3->list_lock);
 	x = cache_grow(cachep, flags, nodeid);
+	if (x)
+		goto retry;
 
-	if (!x)
-		return NULL;
+	if (!(flags & __GFP_THISNODE))
+		/* Unable to grow the cache. Fall back to other nodes. */
+		return fallback_alloc(cachep, flags);
 
-	goto retry;
+	return NULL;
+
 done:
 	return obj;
 }