[PATCH] VM: add __GFP_NORECLAIM

When using the early zone reclaim, it was noticed that allocating new pages
that should be spread across the whole system caused eviction of local pages.

This adds a new GFP flag to prevent early reclaim from happening during
certain allocation attempts.  The example that is implemented here is for page
cache pages.  We want page cache pages to be spread across the whole system,
and we don't want page cache pages to evict other pages to get local memory.

Signed-off-by:  Martin Hicks <mort@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 6 insertions, 3 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index af7407e8cfc5..208535fd4832 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -39,6 +39,7 @@ struct vm_area_struct;
 #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_NORECLAIM  0x20000u /* No realy zone reclaim during allocation */
 
 #define __GFP_BITS_SHIFT 20     /* Room for 20 __GFP_FOO bits */
 #define __GFP_BITS_MASK ((1 << __GFP_BITS_SHIFT) - 1)
@@ -47,7 +48,7 @@ struct vm_area_struct;
 #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_NOMEMALLOC)
+                        __GFP_NOMEMALLOC|__GFP_NORECLAIM)
 
 #define GFP_ATOMIC      (__GFP_HIGH)
 #define GFP_NOIO        (__GFP_WAIT)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 0422031161ba..d9a25647a295 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -52,12 +52,12 @@ void release_pages(struct page **pages, int nr, int cold);
 
 static inline struct page *page_cache_alloc(struct address_space *x)
 {
-        return alloc_pages(mapping_gfp_mask(x), 0);
+        return alloc_pages(mapping_gfp_mask(x)|__GFP_NORECLAIM, 0);
 }
 
 static inline struct page *page_cache_alloc_cold(struct address_space *x)
 {
-        return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0);
+        return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD|__GFP_NORECLAIM, 0);
 }
 
 typedef int filler_t(void *, struct page *);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3c0f69ded6b5..a9da20bc2ed0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -729,6 +729,8 @@ should_reclaim_zone(struct zone *z, unsigned int gfp_mask)
 {
         if (!z->reclaim_pages)
                 return 0;
+        if (gfp_mask & __GFP_NORECLAIM)
+                return 0;
         return 1;
 }