[PATCH] mm: higher order watermarks

Move the watermark checking code into a single function.  Extend it to
account for the order of the allocation and the number of free pages that
could satisfy such a request.

From: Marcelo Tosatti <marcelo.tosatti@cyclades.com>

Fix typo in Nick's kswapd-high-order awareness patch
Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/linux/mmzone.h

@@ -280,6 +280,8 @@ void get_zone_counts(unsigned long *active, unsigned long *inactive,
 			unsigned long *free);
 void build_all_zonelists(void);
 void wakeup_kswapd(struct zone *zone);
+int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		int alloc_type, int can_try_harder, int gfp_high);
 
 /*
  * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc.

mm/page_alloc.c

@@ -585,6 +585,37 @@ buffered_rmqueue(struct zone *zone, int order, int gfp_flags)
 	return page;
 }
 
+/*
+ * Return 1 if free pages are above 'mark'. This takes into account the order
+ * of the allocation.
+ */
+int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		int alloc_type, int can_try_harder, int gfp_high)
+{
+	/* free_pages my go negative - that's OK */
+	long min = mark, free_pages = z->free_pages - (1 << order) + 1;
+	int o;
+
+	if (gfp_high)
+		min -= min / 2;
+	if (can_try_harder)
+		min -= min / 4;
+
+	if (free_pages <= min + z->protection[alloc_type])
+		return 0;
+	for (o = 0; o < order; o++) {
+		/* At the next order, this order's pages become unavailable */
+		free_pages -= z->free_area[o].nr_free << o;
+
+		/* Require fewer higher order pages to be free */
+		min >>= 1;
+
+		if (free_pages <= min)
+			return 0;
+	}
+	return 1;
+}
+
 /*
  * This is the 'heart' of the zoned buddy allocator.
  *
@@ -606,7 +637,6 @@ __alloc_pages(unsigned int gfp_mask, unsigned int order,
 		struct zonelist *zonelist)
 {
 	const int wait = gfp_mask & __GFP_WAIT;
-	unsigned long min;
 	struct zone **zones, *z;
 	struct page *page;
 	struct reclaim_state reclaim_state;
@@ -636,9 +666,9 @@ __alloc_pages(unsigned int gfp_mask, unsigned int order,
 
 	/* Go through the zonelist once, looking for a zone with enough free */
 	for (i = 0; (z = zones[i]) != NULL; i++) {
-		min = z->pages_low + (1<<order) + z->protection[alloc_type];
 
-		if (z->free_pages < min)
+		if (!zone_watermark_ok(z, order, z->pages_low,
+				alloc_type, 0, 0))
 			continue;
 
 		page = buffered_rmqueue(z, order, gfp_mask);
@@ -654,14 +684,9 @@ __alloc_pages(unsigned int gfp_mask, unsigned int order,
 	 * coming from realtime tasks to go deeper into reserves
 	 */
 	for (i = 0; (z = zones[i]) != NULL; i++) {
-		min = z->pages_min;
-		if (gfp_mask & __GFP_HIGH)
-			min /= 2;
-		if (can_try_harder)
-			min -= min / 4;
-		min += (1<<order) + z->protection[alloc_type];
-
-		if (z->free_pages < min)
+		if (!zone_watermark_ok(z, order, z->pages_min,
+				alloc_type, can_try_harder,
+				gfp_mask & __GFP_HIGH))
 			continue;
 
 		page = buffered_rmqueue(z, order, gfp_mask);
@@ -697,14 +722,9 @@ __alloc_pages(unsigned int gfp_mask, unsigned int order,
 
 	/* go through the zonelist yet one more time */
 	for (i = 0; (z = zones[i]) != NULL; i++) {
-		min = z->pages_min;
-		if (gfp_mask & __GFP_HIGH)
-			min /= 2;
-		if (can_try_harder)
-			min -= min / 4;
-		min += (1<<order) + z->protection[alloc_type];
-
-		if (z->free_pages < min)
+		if (!zone_watermark_ok(z, order, z->pages_min,
+				alloc_type, can_try_harder,
+				gfp_mask & __GFP_HIGH))
 			continue;
 
 		page = buffered_rmqueue(z, order, gfp_mask);