mm: fix GFP_THISNODE callers and clarify

GFP_THISNODE is for callers that implement their own clever fallback to
remote nodes. It restricts the allocation to the specified node and
does not invoke reclaim, assuming that the caller will take care of it
when the fallback fails, e.g. through a subsequent allocation request
without GFP_THISNODE set.

However, many current GFP_THISNODE users only want the node exclusive
aspect of the flag, without actually implementing their own fallback or
triggering reclaim if necessary. This results in things like page
migration failing prematurely even when there is easily reclaimable
memory available, unless kswapd happens to be running already or a
concurrent allocation attempt triggers the necessary reclaim.

Convert all callsites that don't implement their own fallback strategy
to __GFP_THISNODE. This restricts the allocation a single node too, but
at the same time allows the allocator to enter the slowpath, wake
kswapd, and invoke direct reclaim if necessary, to make the allocation
happen when memory is full.

Signed-off-by: Johannes Weiner <[e-mail]>
Acked-by: Rik van Riel <[e-mail]>
Cc: Jan Stancek <[e-mail]>
Cc: Mel Gorman <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

arch/ia64/kernel/uncached.c

···
 	/* attempt to allocate a granule's worth of cached memory pages */
 
 	page = alloc_pages_exact_node(nid,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				IA64_GRANULE_SHIFT-PAGE_SHIFT);
 	if (!page) {
 		mutex_unlock(&uc_pool->add_chunk_mutex);

arch/powerpc/platforms/cell/ras.c

···
 
 	area->nid = nid;
 	area->order = order;
-	area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE,
+	area->pages = alloc_pages_exact_node(area->nid,
+						GFP_KERNEL|__GFP_THISNODE,
 						area->order);
 
 	if (!area->pages) {

drivers/misc/sgi-xp/xpc_uv.c

···
 
 	nid = cpu_to_node(cpu);
 	page = alloc_pages_exact_node(nid,
-				      GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				      GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				      pg_order);
 	if (page == NULL) {
 		dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to alloc %d "

include/linux/gfp.h

···
 			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
 			 __GFP_NO_KSWAPD)
 
+/*
+ * GFP_THISNODE does not perform any reclaim, you most likely want to
+ * use __GFP_THISNODE to allocate from a given node without fallback!
+ */
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE	(__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
 #else

include/linux/mmzone.h

···
 
 /*
  * The NUMA zonelists are doubled because we need zonelists that restrict the
- * allocations to a single node for GFP_THISNODE.
+ * allocations to a single node for __GFP_THISNODE.
  *
  * [0]	: Zonelist with fallback
- * [1]	: No fallback (GFP_THISNODE)
+ * [1]	: No fallback (__GFP_THISNODE)
  */
 #define MAX_ZONELISTS 2
 

include/linux/slab.h

···
  *
  * %GFP_NOWAIT - Allocation will not sleep.
  *
- * %GFP_THISNODE - Allocate node-local memory only.
+ * %__GFP_THISNODE - Allocate node-local memory only.
  *
  * %GFP_DMA - Allocation suitable for DMA.
  *   Should only be used for kmalloc() caches. Otherwise, use a

kernel/profile.c

···
 		struct page *page;
 
 		page = alloc_pages_exact_node(node,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;
 		per_cpu(cpu_profile_hits, cpu)[1]
 				= (struct profile_hit *)page_address(page);
 		page = alloc_pages_exact_node(node,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;

mm/migrate.c

···
 					pm->node);
 	else
 		return alloc_pages_exact_node(pm->node,
-				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
+				GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0);
 }
 
 /*
···
 	struct page *newpage;
 
 	newpage = alloc_pages_exact_node(nid,
-					 (GFP_HIGHUSER_MOVABLE | GFP_THISNODE |
-					  __GFP_NOMEMALLOC | __GFP_NORETRY |
-					  __GFP_NOWARN) &
+					 (GFP_HIGHUSER_MOVABLE |
+					  __GFP_THISNODE | __GFP_NOMEMALLOC |
+					  __GFP_NORETRY | __GFP_NOWARN) &
 					 ~GFP_IOFS, 0);
 
 	return newpage;
···
 		goto out_dropref;
 
 	new_page = alloc_pages_node(node,
-		(GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
+		(GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT,
+		HPAGE_PMD_ORDER);
 	if (!new_page)
 		goto out_fail;