page allocator: calculate the preferred zone for allocation only once
get_page_from_freelist() can be called multiple times for an allocation.
Part of this calculates the preferred_zone which is the first usable zone
in the zonelist but the zone depends on the GFP flags specified at the
beginning of the allocation call. This patch calculates preferred_zone
once. It's safe to do this because if preferred_zone is NULL at the start
of the call, no amount of direct reclaim or other actions will change the
fact the allocation will fail.
[akpm@linux-foundation.org: remove (void) casts]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b098596..8fc6d1f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1388,26 +1388,21 @@
*/
static struct page *
get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
- struct zonelist *zonelist, int high_zoneidx, int alloc_flags)
+ struct zonelist *zonelist, int high_zoneidx, int alloc_flags,
+ struct zone *preferred_zone)
{
struct zoneref *z;
struct page *page = NULL;
int classzone_idx;
- struct zone *zone, *preferred_zone;
+ struct zone *zone;
nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
int zlc_active = 0; /* set if using zonelist_cache */
int did_zlc_setup = 0; /* just call zlc_setup() one time */
- (void)first_zones_zonelist(zonelist, high_zoneidx, nodemask,
- &preferred_zone);
- if (!preferred_zone)
- return NULL;
-
- classzone_idx = zone_idx(preferred_zone);
-
if (WARN_ON_ONCE(order >= MAX_ORDER))
return NULL;
+ classzone_idx = zone_idx(preferred_zone);
zonelist_scan:
/*
* Scan zonelist, looking for a zone with enough free.
@@ -1500,7 +1495,7 @@
static inline struct page *
__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
- nodemask_t *nodemask)
+ nodemask_t *nodemask, struct zone *preferred_zone)
{
struct page *page;
@@ -1517,7 +1512,8 @@
*/
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
order, zonelist, high_zoneidx,
- ALLOC_WMARK_HIGH|ALLOC_CPUSET);
+ ALLOC_WMARK_HIGH|ALLOC_CPUSET,
+ preferred_zone);
if (page)
goto out;
@@ -1537,7 +1533,8 @@
static inline struct page *
__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
- nodemask_t *nodemask, int alloc_flags, unsigned long *did_some_progress)
+ nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
+ unsigned long *did_some_progress)
{
struct page *page = NULL;
struct reclaim_state reclaim_state;
@@ -1569,7 +1566,8 @@
if (likely(*did_some_progress))
page = get_page_from_freelist(gfp_mask, nodemask, order,
- zonelist, high_zoneidx, alloc_flags);
+ zonelist, high_zoneidx,
+ alloc_flags, preferred_zone);
return page;
}
@@ -1589,13 +1587,14 @@
static inline struct page *
__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
- nodemask_t *nodemask)
+ nodemask_t *nodemask, struct zone *preferred_zone)
{
struct page *page;
do {
page = get_page_from_freelist(gfp_mask, nodemask, order,
- zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
+ zonelist, high_zoneidx, ALLOC_NO_WATERMARKS,
+ preferred_zone);
if (!page && gfp_mask & __GFP_NOFAIL)
congestion_wait(WRITE, HZ/50);
@@ -1618,7 +1617,7 @@
static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
- nodemask_t *nodemask)
+ nodemask_t *nodemask, struct zone *preferred_zone)
{
const gfp_t wait = gfp_mask & __GFP_WAIT;
struct page *page = NULL;
@@ -1668,7 +1667,8 @@
* See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
- high_zoneidx, alloc_flags);
+ high_zoneidx, alloc_flags,
+ preferred_zone);
if (page)
goto got_pg;
@@ -1678,7 +1678,7 @@
/* Do not dip into emergency reserves if specified */
if (!(gfp_mask & __GFP_NOMEMALLOC)) {
page = __alloc_pages_high_priority(gfp_mask, order,
- zonelist, high_zoneidx, nodemask);
+ zonelist, high_zoneidx, nodemask, preferred_zone);
if (page)
goto got_pg;
}
@@ -1695,7 +1695,8 @@
page = __alloc_pages_direct_reclaim(gfp_mask, order,
zonelist, high_zoneidx,
nodemask,
- alloc_flags, &did_some_progress);
+ alloc_flags, preferred_zone,
+ &did_some_progress);
if (page)
goto got_pg;
@@ -1707,7 +1708,7 @@
if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
page = __alloc_pages_may_oom(gfp_mask, order,
zonelist, high_zoneidx,
- nodemask);
+ nodemask, preferred_zone);
if (page)
goto got_pg;
@@ -1752,6 +1753,7 @@
struct zonelist *zonelist, nodemask_t *nodemask)
{
enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+ struct zone *preferred_zone;
struct page *page;
lockdep_trace_alloc(gfp_mask);
@@ -1769,11 +1771,19 @@
if (unlikely(!zonelist->_zonerefs->zone))
return NULL;
+ /* The preferred zone is used for statistics later */
+ first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone);
+ if (!preferred_zone)
+ return NULL;
+
+ /* First allocation attempt */
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
- zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+ zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET,
+ preferred_zone);
if (unlikely(!page))
page = __alloc_pages_slowpath(gfp_mask, order,
- zonelist, high_zoneidx, nodemask);
+ zonelist, high_zoneidx, nodemask,
+ preferred_zone);
return page;
}