Add __GFP_THISNODE to avoid fallback to other nodes and cpuset/memory policy restrictions.

Add a new gfp flag __GFP_THISNODE to avoid fallback to other nodes. This flag
is essential if a kernel component requires memory to be located on a
certain node. It will be needed for alloc_pages_node() to force allocation
on the indicated node and for alloc_pages() to force allocation on the
current node.

Signed-off-by: Christoph Lameter <clameter@sgi.com>

Index: linux-2.6.18-rc1/mm/page_alloc.c
===================================================================
--- linux-2.6.18-rc1.orig/mm/page_alloc.c	2006-07-13 10:27:12.534765446 -0700
+++ linux-2.6.18-rc1/mm/page_alloc.c	2006-07-13 10:27:16.481786427 -0700
@@ -878,9 +878,12 @@ get_page_from_freelist(gfp_t gfp_mask, u
 	 */
 	do {
 		zone = *z;
+		if (unlikely((gfp_mask & __GFP_THISNODE) &&
+			zone->zone_pgdat != zonelist->zones[0]->zone_pgdat))
+				break;
 		if ((alloc_flags & ALLOC_CPUSET) &&
-				!cpuset_zone_allowed(zone, gfp_mask))
-			continue;
+			!cpuset_zone_allowed(zone, gfp_mask))
+				continue;
 
 		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
 			unsigned long mark;
Index: linux-2.6.18-rc1/include/linux/gfp.h
===================================================================
--- linux-2.6.18-rc1.orig/include/linux/gfp.h	2006-07-05 21:09:49.000000000 -0700
+++ linux-2.6.18-rc1/include/linux/gfp.h	2006-07-13 10:28:45.794610139 -0700
@@ -46,6 +46,7 @@ struct vm_area_struct;
 #define __GFP_ZERO	((__force gfp_t)0x8000u)/* Return zeroed page on success */
 #define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */
 #define __GFP_HARDWALL   ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */
+#define __GFP_THISNODE	((__force gfp_t)0x40000u)/* No fallback, no policies */
 
 #define __GFP_BITS_SHIFT 20	/* Room for 20 __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
Index: linux-2.6.18-rc1/mm/mempolicy.c
===================================================================
--- linux-2.6.18-rc1.orig/mm/mempolicy.c	2006-07-05 21:09:49.000000000 -0700
+++ linux-2.6.18-rc1/mm/mempolicy.c	2006-07-13 10:34:14.781057331 -0700
@@ -1277,7 +1277,7 @@ struct page *alloc_pages_current(gfp_t g
 
 	if ((gfp & __GFP_WAIT) && !in_interrupt())
 		cpuset_update_task_memory_state();
-	if (!pol || in_interrupt())
+	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
 		pol = &default_policy;
 	if (pol->policy == MPOL_INTERLEAVE)
 		return alloc_page_interleave(gfp, order, interleave_nodes(pol));
Index: linux-2.6.18-rc1/kernel/cpuset.c
===================================================================
--- linux-2.6.18-rc1.orig/kernel/cpuset.c	2006-07-05 21:09:49.000000000 -0700
+++ linux-2.6.18-rc1/kernel/cpuset.c	2006-07-13 10:34:09.245267571 -0700
@@ -2265,7 +2265,7 @@ int __cpuset_zone_allowed(struct zone *z
 	const struct cpuset *cs;	/* current cpuset ancestors */
 	int allowed;			/* is allocation in zone z allowed? */
 
-	if (in_interrupt())
+	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
 		return 1;
 	node = z->zone_pgdat->node_id;
 	might_sleep_if(!(gfp_mask & __GFP_HARDWALL));