[PATCH] mm: __alloc_pages cleanup

Clean up of __alloc_pages.

Restoration of previous behaviour, plus further cleanups by introducing an
'alloc_flags', removing the last of should_reclaim_zone.
Signed-off-by: Rohit Seth <rohit.seth@intel.com>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/linux/mmzone.h

@@ -329,7 +329,7 @@ void get_zone_counts(unsigned long *active, unsigned long *inactive,
 void build_all_zonelists(void);
 void wakeup_kswapd(struct zone *zone, int order);
 int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
-		int alloc_type, int can_try_harder, gfp_t gfp_high);
+		int classzone_idx, int alloc_flags);
 
 #ifdef CONFIG_HAVE_MEMORY_PRESENT
 void memory_present(int nid, unsigned long start, unsigned long end);

mm/page_alloc.c

@@ -732,9 +732,7 @@ buffered_rmqueue(struct zone *zone, int order, gfp_t gfp_flags)
 		}
 		local_irq_restore(flags);
 		put_cpu();
-	}
-
-	if (page == NULL) {
+	} else {
 		spin_lock_irqsave(&zone->lock, flags);
 		page = __rmqueue(zone, order);
 		spin_unlock_irqrestore(&zone->lock, flags);
@@ -754,20 +752,25 @@ buffered_rmqueue(struct zone *zone, int order, gfp_t gfp_flags)
 	return page;
 }
 
+#define ALLOC_NO_WATERMARKS	0x01 /* don't check watermarks at all */
+#define ALLOC_HARDER		0x02 /* try to alloc harder */
+#define ALLOC_HIGH		0x04 /* __GFP_HIGH set */
+#define ALLOC_CPUSET		0x08 /* check for correct cpuset */
+
 /*
  * 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 classzone_idx, int can_try_harder, gfp_t gfp_high)
+		      int classzone_idx, int alloc_flags)
 {
 	/* free_pages my go negative - that's OK */
 	long min = mark, free_pages = z->free_pages - (1 << order) + 1;
 	int o;
 
-	if (gfp_high)
+	if (alloc_flags & ALLOC_HIGH)
 		min -= min / 2;
-	if (can_try_harder)
+	if (alloc_flags & ALLOC_HARDER)
 		min -= min / 4;
 
 	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
@@ -785,14 +788,40 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	return 1;
 }
 
-static inline int
-should_reclaim_zone(struct zone *z, gfp_t gfp_mask)
+/*
+ * get_page_from_freeliest goes through the zonelist trying to allocate
+ * a page.
+ */
+static struct page *
+get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
+		struct zonelist *zonelist, int alloc_flags)
 {
-	if (!z->reclaim_pages)
-		return 0;
-	if (gfp_mask & __GFP_NORECLAIM)
-		return 0;
-	return 1;
+	struct zone **z = zonelist->zones;
+	struct page *page = NULL;
+	int classzone_idx = zone_idx(*z);
+
+	/*
+	 * Go through the zonelist once, looking for a zone with enough free.
+	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+	 */
+	do {
+		if ((alloc_flags & ALLOC_CPUSET) &&
+				!cpuset_zone_allowed(*z, gfp_mask))
+			continue;
+
+		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
+			if (!zone_watermark_ok(*z, order, (*z)->pages_low,
+				    classzone_idx, alloc_flags))
+				continue;
+		}
+
+		page = buffered_rmqueue(*z, order, gfp_mask);
+		if (page) {
+			zone_statistics(zonelist, *z);
+			break;
+		}
+	} while (*(++z) != NULL);
+	return page;
 }
 
 /*
@@ -803,92 +832,60 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		struct zonelist *zonelist)
 {
 	const gfp_t wait = gfp_mask & __GFP_WAIT;
-	struct zone **zones, *z;
+	struct zone **z;
 	struct page *page;
 	struct reclaim_state reclaim_state;
 	struct task_struct *p = current;
-	int i;
-	int classzone_idx;
 	int do_retry;
-	int can_try_harder;
+	int alloc_flags;
 	int did_some_progress;
 
 	might_sleep_if(wait);
 
-	/*
-	 * The caller may dip into page reserves a bit more if the caller
-	 * cannot run direct reclaim, or is the caller has realtime scheduling
-	 * policy
-	 */
-	can_try_harder = (unlikely(rt_task(p)) && !in_interrupt()) || !wait;
-
-	zones = zonelist->zones;  /* the list of zones suitable for gfp_mask */
+	z = zonelist->zones;  /* the list of zones suitable for gfp_mask */
 
-	if (unlikely(zones[0] == NULL)) {
+	if (unlikely(*z == NULL)) {
 		/* Should this ever happen?? */
 		return NULL;
 	}
+restart:
+	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+				zonelist, ALLOC_CPUSET);
+	if (page)
+		goto got_pg;
 
-	classzone_idx = zone_idx(zones[0]);
+	do
+		wakeup_kswapd(*z, order);
+	while (*(++z));
 
-restart:
 	/*
-	 * Go through the zonelist once, looking for a zone with enough free.
-	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+	 * OK, we're below the kswapd watermark and have kicked background
+	 * reclaim. Now things get more complex, so set up alloc_flags according
+	 * to how we want to proceed.
+	 *
+	 * The caller may dip into page reserves a bit more if the caller
+	 * cannot run direct reclaim, or if the caller has realtime scheduling
+	 * policy.
 	 */
-	for (i = 0; (z = zones[i]) != NULL; i++) {
-		int do_reclaim = should_reclaim_zone(z, gfp_mask);
-
-		if (!cpuset_zone_allowed(z, __GFP_HARDWALL))
-			continue;
-
-		/*
-		 * If the zone is to attempt early page reclaim then this loop
-		 * will try to reclaim pages and check the watermark a second
-		 * time before giving up and falling back to the next zone.
-		 */
-zone_reclaim_retry:
-		if (!zone_watermark_ok(z, order, z->pages_low,
-				       classzone_idx, 0, 0)) {
-			if (!do_reclaim)
-				continue;
-			else {
-				zone_reclaim(z, gfp_mask, order);
-				/* Only try reclaim once */
-				do_reclaim = 0;
-				goto zone_reclaim_retry;
-			}
-		}
-
-		page = buffered_rmqueue(z, order, gfp_mask);
-		if (page)
-			goto got_pg;
-	}
-
-	for (i = 0; (z = zones[i]) != NULL; i++)
-		wakeup_kswapd(z, order);
+	alloc_flags = 0;
+	if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
+		alloc_flags |= ALLOC_HARDER;
+	if (gfp_mask & __GFP_HIGH)
+		alloc_flags |= ALLOC_HIGH;
+	if (wait)
+		alloc_flags |= ALLOC_CPUSET;
 
 	/*
 	 * Go through the zonelist again. Let __GFP_HIGH and allocations
-	 * coming from realtime tasks to go deeper into reserves
+	 * coming from realtime tasks go deeper into reserves.
 	 *
 	 * This is the last chance, in general, before the goto nopage.
 	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
 	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
-	for (i = 0; (z = zones[i]) != NULL; i++) {
-		if (!zone_watermark_ok(z, order, z->pages_min,
-				       classzone_idx, can_try_harder,
-				       gfp_mask & __GFP_HIGH))
-			continue;
-
-		if (wait && !cpuset_zone_allowed(z, gfp_mask))
-			continue;
-
-		page = buffered_rmqueue(z, order, gfp_mask);
-		if (page)
-			goto got_pg;
-	}
+	page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);
+	if (page)
+		goto got_pg;
 
 	/* This allocation should allow future memory freeing. */
 
@@ -897,13 +894,10 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
 nofail_alloc:
 			/* go through the zonelist yet again, ignoring mins */
-			for (i = 0; (z = zones[i]) != NULL; i++) {
-				if (!cpuset_zone_allowed(z, gfp_mask))
-					continue;
-				page = buffered_rmqueue(z, order, gfp_mask);
-				if (page)
-					goto got_pg;
-			}
+			page = get_page_from_freelist(gfp_mask, order,
+				zonelist, ALLOC_NO_WATERMARKS|ALLOC_CPUSET);
+			if (page)
+				goto got_pg;
 			if (gfp_mask & __GFP_NOFAIL) {
 				blk_congestion_wait(WRITE, HZ/50);
 				goto nofail_alloc;
@@ -924,7 +918,7 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	did_some_progress = try_to_free_pages(zones, gfp_mask);
+	did_some_progress = try_to_free_pages(zonelist->zones, gfp_mask);
 
 	p->reclaim_state = NULL;
 	p->flags &= ~PF_MEMALLOC;
@@ -932,19 +926,10 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	cond_resched();
 
 	if (likely(did_some_progress)) {
-		for (i = 0; (z = zones[i]) != NULL; i++) {
-			if (!zone_watermark_ok(z, order, z->pages_min,
-					       classzone_idx, can_try_harder,
-					       gfp_mask & __GFP_HIGH))
-				continue;
-
-			if (!cpuset_zone_allowed(z, gfp_mask))
-				continue;
-
-			page = buffered_rmqueue(z, order, gfp_mask);
-			if (page)
-				goto got_pg;
-		}
+		page = get_page_from_freelist(gfp_mask, order,
+						zonelist, alloc_flags);
+		if (page)
+			goto got_pg;
 	} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
 		/*
 		 * Go through the zonelist yet one more time, keep
@@ -952,18 +937,10 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		 * a parallel oom killing, we must fail if we're still
 		 * under heavy pressure.
 		 */
-		for (i = 0; (z = zones[i]) != NULL; i++) {
-			if (!zone_watermark_ok(z, order, z->pages_high,
-					       classzone_idx, 0, 0))
-				continue;
-
-			if (!cpuset_zone_allowed(z, __GFP_HARDWALL))
-				continue;
-
-			page = buffered_rmqueue(z, order, gfp_mask);
-			if (page)
-				goto got_pg;
-		}
+		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+						zonelist, ALLOC_CPUSET);
+		if (page)
+			goto got_pg;
 
 		out_of_memory(gfp_mask, order);
 		goto restart;
@@ -996,9 +973,7 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		dump_stack();
 		show_mem();
 	}
-	return NULL;
 got_pg:
-	zone_statistics(zonelist, z);
 	return page;
 }
 

mm/vmscan.c

@@ -1074,7 +1074,7 @@ static int balance_pgdat(pg_data_t *pgdat, int nr_pages, int order)
 					continue;
 
 				if (!zone_watermark_ok(zone, order,
-						zone->pages_high, 0, 0, 0)) {
+						zone->pages_high, 0, 0)) {
 					end_zone = i;
 					goto scan;
 				}
@@ -1111,7 +1111,7 @@ static int balance_pgdat(pg_data_t *pgdat, int nr_pages, int order)
 
 			if (nr_pages == 0) {	/* Not software suspend */
 				if (!zone_watermark_ok(zone, order,
-						zone->pages_high, end_zone, 0, 0))
+						zone->pages_high, end_zone, 0))
 					all_zones_ok = 0;
 			}
 			zone->temp_priority = priority;
@@ -1259,7 +1259,7 @@ void wakeup_kswapd(struct zone *zone, int order)
 		return;
 
 	pgdat = zone->zone_pgdat;
-	if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0, 0))
+	if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
 		return;
 	if (pgdat->kswapd_max_order < order)
 		pgdat->kswapd_max_order = order;