mm: filter based on a nodemask as well as a gfp_mask

The MPOL_BIND policy creates a zonelist that is used for allocations
controlled by that mempolicy.  As the per-node zonelist is already being
filtered based on a zone id, this patch adds a version of __alloc_pages() that
takes a nodemask for further filtering.  This eliminates the need for
MPOL_BIND to create a custom zonelist.

A positive benefit of this is that allocations using MPOL_BIND now use the
local node's distance-ordered zonelist instead of a custom node-id-ordered
zonelist.  I.e., pages will be allocated from the closest allowed node with
available memory.

[Lee.Schermerhorn@hp.com: Mempolicy: update stale documentation and comments]
[Lee.Schermerhorn@hp.com: Mempolicy: make dequeue_huge_page_vma() obey MPOL_BIND nodemask]
[Lee.Schermerhorn@hp.com: Mempolicy: make dequeue_huge_page_vma() obey MPOL_BIND nodemask rework]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 12 insertions, 7 deletions

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 69160dc32d48..b8b3da7a3315 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -54,19 +54,20 @@ struct mm_struct;
  * mmap_sem.
  *
  * Freeing policy:
- * When policy is MPOL_BIND v.zonelist is kmalloc'ed and must be kfree'd.
- * All other policies don't have any external state. mpol_free() handles this.
+ * Mempolicy objects are reference counted.  A mempolicy will be freed when
+ * mpol_free() decrements the reference count to zero.
  *
  * Copying policy objects:
- * For MPOL_BIND the zonelist must be always duplicated. mpol_clone() does this.
+ * mpol_copy() allocates a new mempolicy and copies the specified mempolicy
+ * to the new storage.  The reference count of the new object is initialized
+ * to 1, representing the caller of mpol_copy().
  */
 struct mempolicy {
         atomic_t refcnt;
         short policy;   /* See MPOL_* above */
         union {
-                struct zonelist  *zonelist;     /* bind */
                 short            preferred_node; /* preferred */
-                nodemask_t       nodes;         /* interleave */
+                nodemask_t       nodes;         /* interleave/bind */
                 /* undefined for default */
         } v;
         nodemask_t cpuset_mems_allowed; /* mempolicy relative to these nodes */
@@ -151,7 +152,8 @@ extern void mpol_fix_fork_child_flag(struct task_struct *p);
 
 extern struct mempolicy default_policy;
 extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
-                unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol);
+                                unsigned long addr, gfp_t gfp_flags,
+                                struct mempolicy **mpol, nodemask_t **nodemask);
 extern unsigned slab_node(struct mempolicy *policy);
 
 extern enum zone_type policy_zone;
@@ -239,8 +241,11 @@ static inline void mpol_fix_fork_child_flag(struct task_struct *p)
 }
 
 static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
-                unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol)
+                                unsigned long addr, gfp_t gfp_flags,
+                                struct mempolicy **mpol, nodemask_t **nodemask)
 {
+        *mpol = NULL;
+        *nodemask = NULL;
         return node_zonelist(0, gfp_flags);
 }