page allocator: use allocation flags as an index to the zone watermark

ALLOC_WMARK_MIN, ALLOC_WMARK_LOW and ALLOC_WMARK_HIGH determin whether
pages_min, pages_low or pages_high is used as the zone watermark when
allocating the pages.  Two branches in the allocator hotpath determine
which watermark to use.

This patch uses the flags as an array index into a watermark array that is
indexed with WMARK_* defines accessed via helpers.  All call sites that
use zone->pages_* are updated to use the helpers for accessing the values
and the array offsets for setting.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
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>

1 files changed, 26 insertions, 25 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8485735fc690..abe26003124d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1150,10 +1150,15 @@ failed:
 	return NULL;
 }
 
-#define ALLOC_NO_WATERMARKS	0x01 /* don't check watermarks at all */
-#define ALLOC_WMARK_MIN		0x02 /* use pages_min watermark */
-#define ALLOC_WMARK_LOW		0x04 /* use pages_low watermark */
-#define ALLOC_WMARK_HIGH	0x08 /* use pages_high watermark */
+/* The ALLOC_WMARK bits are used as an index to zone->watermark */
+#define ALLOC_WMARK_MIN		WMARK_MIN
+#define ALLOC_WMARK_LOW		WMARK_LOW
+#define ALLOC_WMARK_HIGH	WMARK_HIGH
+#define ALLOC_NO_WATERMARKS	0x04 /* don't check watermarks at all */
+
+/* Mask to get the watermark bits */
+#define ALLOC_WMARK_MASK	(ALLOC_NO_WATERMARKS-1)
+
 #define ALLOC_HARDER		0x10 /* try to alloc harder */
 #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
 #define ALLOC_CPUSET		0x40 /* check for correct cpuset */
@@ -1440,14 +1445,10 @@ zonelist_scan:
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
 				goto try_next_zone;
 
+		BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
 		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
 			unsigned long mark;
-			if (alloc_flags & ALLOC_WMARK_MIN)
-				mark = zone->pages_min;
-			else if (alloc_flags & ALLOC_WMARK_LOW)
-				mark = zone->pages_low;
-			else
-				mark = zone->pages_high;
+			mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
 			if (!zone_watermark_ok(zone, order, mark,
 				    classzone_idx, alloc_flags)) {
 				if (!zone_reclaim_mode ||
@@ -1959,7 +1960,7 @@ static unsigned int nr_free_zone_pages(int offset)
 
 	for_each_zone_zonelist(zone, z, zonelist, offset) {
 		unsigned long size = zone->present_pages;
-		unsigned long high = zone->pages_high;
+		unsigned long high = high_wmark_pages(zone);
 		if (size > high)
 			sum += size - high;
 	}
@@ -2096,9 +2097,9 @@ void show_free_areas(void)
 			"\n",
 			zone->name,
 			K(zone_page_state(zone, NR_FREE_PAGES)),
-			K(zone->pages_min),
-			K(zone->pages_low),
-			K(zone->pages_high),
+			K(min_wmark_pages(zone)),
+			K(low_wmark_pages(zone)),
+			K(high_wmark_pages(zone)),
 			K(zone_page_state(zone, NR_ACTIVE_ANON)),
 			K(zone_page_state(zone, NR_INACTIVE_ANON)),
 			K(zone_page_state(zone, NR_ACTIVE_FILE)),
@@ -2702,8 +2703,8 @@ static inline unsigned long wait_table_bits(unsigned long size)
 
 /*
  * Mark a number of pageblocks as MIGRATE_RESERVE. The number
- * of blocks reserved is based on zone->pages_min. The memory within the
- * reserve will tend to store contiguous free pages. Setting min_free_kbytes
+ * of blocks reserved is based on min_wmark_pages(zone). The memory within
+ * the reserve will tend to store contiguous free pages. Setting min_free_kbytes
  * higher will lead to a bigger reserve which will get freed as contiguous
  * blocks as reclaim kicks in
  */
@@ -2716,7 +2717,7 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 	/* Get the start pfn, end pfn and the number of blocks to reserve */
 	start_pfn = zone->zone_start_pfn;
 	end_pfn = start_pfn + zone->spanned_pages;
-	reserve = roundup(zone->pages_min, pageblock_nr_pages) >>
+	reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
 							pageblock_order;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
@@ -4319,8 +4320,8 @@ static void calculate_totalreserve_pages(void)
 					max = zone->lowmem_reserve[j];
 			}
 
-			/* we treat pages_high as reserved pages. */
-			max += zone->pages_high;
+			/* we treat the high watermark as reserved pages. */
+			max += high_wmark_pages(zone);
 
 			if (max > zone->present_pages)
 				max = zone->present_pages;
@@ -4400,7 +4401,7 @@ void setup_per_zone_pages_min(void)
 			 * need highmem pages, so cap pages_min to a small
 			 * value here.
 			 *
-			 * The (pages_high-pages_low) and (pages_low-pages_min)
+			 * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
 			 * deltas controls asynch page reclaim, and so should
 			 * not be capped for highmem.
 			 */
@@ -4411,17 +4412,17 @@ void setup_per_zone_pages_min(void)
 				min_pages = SWAP_CLUSTER_MAX;
 			if (min_pages > 128)
 				min_pages = 128;
-			zone->pages_min = min_pages;
+			zone->watermark[WMARK_MIN] = min_pages;
 		} else {
 			/*
 			 * If it's a lowmem zone, reserve a number of pages
 			 * proportionate to the zone's size.
 			 */
-			zone->pages_min = tmp;
+			zone->watermark[WMARK_MIN] = tmp;
 		}
 
-		zone->pages_low   = zone->pages_min + (tmp >> 2);
-		zone->pages_high  = zone->pages_min + (tmp >> 1);
+		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
+		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
 		setup_zone_migrate_reserve(zone);
 		spin_unlock_irqrestore(&zone->lock, flags);
 	}
@@ -4566,7 +4567,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
  *	whenever sysctl_lowmem_reserve_ratio changes.
  *
  * The reserve ratio obviously has absolutely no relation with the
- * pages_min watermarks. The lowmem reserve ratio can only make sense
+ * minimum watermarks. The lowmem reserve ratio can only make sense
  * if in function of the boot time zone sizes.
  */
 int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,