Message-Id: <1235344649-18265-7-git-send-email-mel@csn.ul.ie>
Date:	Sun, 22 Feb 2009 23:17:15 +0000
From:	Mel Gorman <mel@....ul.ie>
To:	Mel Gorman <mel@....ul.ie>,
	Linux Memory Management List <linux-mm@...ck.org>
Cc:	Pekka Enberg <penberg@...helsinki.fi>,
	Rik van Riel <riel@...hat.com>,
	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
	Christoph Lameter <cl@...ux-foundation.org>,
	Johannes Weiner <hannes@...xchg.org>,
	Nick Piggin <npiggin@...e.de>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	Lin Ming <ming.m.lin@...el.com>,
	Zhang Yanmin <yanmin_zhang@...ux.intel.com>
Subject: [PATCH 06/20] Break up the allocator entry point into fast and slow paths

The core of the page allocator is one giant function which allocates
memory on the stack and makes calculations that may not be needed for every
allocation. This patch breaks up the allocator path into fast and slow paths.

Signed-off-by: Mel Gorman <mel@....ul.ie>
---
 mm/page_alloc.c |  345 ++++++++++++++++++++++++++++++++++---------------------
 1 files changed, 216 insertions(+), 129 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 99fd538..503d692 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1463,45 +1463,170 @@ try_next_zone:
 	return page;
 }
 
-/*
- * This is the 'heart' of the zoned buddy allocator.
- */
+int
+should_alloc_retry(gfp_t gfp_mask, unsigned int order,
+				unsigned long pages_reclaimed)
+{
+	/* Do not loop if specifically requested */
+	if (gfp_mask & __GFP_NORETRY)
+		return 0;
+	
+	/*
+	 * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
+	 * means __GFP_NOFAIL, but that may not be true in other
+	 * implementations.
+	 */
+	if (order <= PAGE_ALLOC_COSTLY_ORDER)
+		return 1;
+
+	/*
+	 * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
+	 * specified, then we retry until we no longer reclaim any pages
+	 * (above), or we've reclaimed an order of pages at least as
+	 * large as the allocation's order. In both cases, if the
+	 * allocation still fails, we stop retrying.
+	 */
+	if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
+		return 1;
+
+	/*
+	 * Don't let big-order allocations loop unless the caller
+	 * explicitly requests that. 
+	 */
+	if (gfp_mask & __GFP_NOFAIL)
+		return 1;
+
+	return 0;
+}
+
 struct page *
-__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
-			struct zonelist *zonelist, nodemask_t *nodemask)
+__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask)
 {
-	const gfp_t wait = gfp_mask & __GFP_WAIT;
-	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
-	struct zoneref *z;
-	struct zone *zone;
 	struct page *page;
+
+	/* Acquire the OOM killer lock for the zones in zonelist */
+	if (!try_set_zone_oom(zonelist, gfp_mask)) {
+		schedule_timeout_uninterruptible(1);
+		return NULL;
+	}
+
+	/*
+	 * Go through the zonelist yet one more time, keep very high watermark
+	 * here, this is only to catch a parallel oom killing, we must fail if
+	 * we're still under heavy pressure.
+	 */
+	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
+		order, zonelist, high_zoneidx,
+		ALLOC_WMARK_HIGH|ALLOC_CPUSET);
+	if (page)
+		goto out;
+
+	/* The OOM killer will not help higher order allocs */
+	if (order > PAGE_ALLOC_COSTLY_ORDER)
+		goto out;
+
+	/* Exhausted what can be done so it's blamo time */
+	out_of_memory(zonelist, gfp_mask, order);
+
+out:
+	clear_zonelist_oom(zonelist, gfp_mask);
+	return page;
+}
+
+/* The really slow allocator path where we enter direct reclaim */
+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)
+{
+	struct page *page = NULL;
 	struct reclaim_state reclaim_state;
 	struct task_struct *p = current;
-	int do_retry;
-	int alloc_flags;
-	unsigned long did_some_progress;
-	unsigned long pages_reclaimed = 0;
 
-	might_sleep_if(wait);
+	cond_resched();
 
-	if (should_fail_alloc_page(gfp_mask, order))
-		return NULL;
+	/* We now go into synchronous reclaim */
+	cpuset_memory_pressure_bump();
 
-	/* the list of zones suitable for gfp_mask */
-	z = zonelist->_zonerefs;
-	if (unlikely(!z->zone)) {
-		/*
-		 * Happens if we have an empty zonelist as a result of
-		 * GFP_THISNODE being used on a memoryless node
-		 */
-		return NULL;
-	}
+	/*
+	 * The task's cpuset might have expanded its set of allowable nodes
+	 */
+	cpuset_update_task_memory_state();
+	p->flags |= PF_MEMALLOC;
+	reclaim_state.reclaimed_slab = 0;
+	p->reclaim_state = &reclaim_state;
 
-restart:
-	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
-			zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
-	if (page)
-		goto got_pg;
+	*did_some_progress = try_to_free_pages(zonelist, order, gfp_mask);
+
+	p->reclaim_state = NULL;
+	p->flags &= ~PF_MEMALLOC;
+
+	cond_resched();
+
+	if (order != 0)
+		drain_all_pages();
+
+	if (likely(*did_some_progress))
+		page = get_page_from_freelist(gfp_mask, nodemask, order,
+					zonelist, high_zoneidx, alloc_flags);
+	return page;
+}
+
+static inline int is_allocation_high_priority(struct task_struct *p,
+							gfp_t gfp_mask)
+{
+	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
+			&& !in_interrupt())
+		if (!(gfp_mask & __GFP_NOMEMALLOC))
+			return 1;
+	return 0;
+}
+
+/*
+ * This is called in the allocator slow-path if the allocation request is of
+ * sufficient urgency to ignore watermarks and take other desperate measures
+ */
+struct page *
+__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask)
+{
+	struct page *page;
+
+	do {
+		page = get_page_from_freelist(gfp_mask, nodemask, order,
+			zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
+
+		if (!page && gfp_mask & __GFP_NOFAIL)
+			congestion_wait(WRITE, HZ/50);
+	} while (!page && (gfp_mask & __GFP_NOFAIL));
+
+	return page;
+}
+
+static inline
+void wake_all_kswapd(unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx)
+{
+	struct zoneref *z;
+	struct zone *zone;
+
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+		wakeup_kswapd(zone, order);
+}
+
+static struct page * noinline
+__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask)
+{
+	const gfp_t wait = gfp_mask & __GFP_WAIT;
+	struct page *page = NULL;
+	int alloc_flags;
+	unsigned long pages_reclaimed = 0;
+	unsigned long did_some_progress;
+	struct task_struct *p = current;
 
 	/*
 	 * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
@@ -1514,8 +1639,7 @@ restart:
 	if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
-		wakeup_kswapd(zone, order);
+	wake_all_kswapd(order, zonelist, high_zoneidx);
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
@@ -1535,6 +1659,7 @@ restart:
 	if (wait)
 		alloc_flags |= ALLOC_CPUSET;
 
+restart:
 	/*
 	 * Go through the zonelist again. Let __GFP_HIGH and allocations
 	 * coming from realtime tasks go deeper into reserves.
@@ -1548,118 +1673,47 @@ restart:
 	if (page)
 		goto got_pg;
 
-	/* This allocation should allow future memory freeing. */
-
-rebalance:
-	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
-			&& !in_interrupt()) {
-		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
-nofail_alloc:
-			/* go through the zonelist yet again, ignoring mins */
-			page = get_page_from_freelist(gfp_mask, nodemask, order,
-				zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
-			if (page)
-				goto got_pg;
-			if (gfp_mask & __GFP_NOFAIL) {
-				congestion_wait(WRITE, HZ/50);
-				goto nofail_alloc;
-			}
-		}
-		goto nopage;
-	}
+	/* Allocate without watermarks if the context allows */
+	if (is_allocation_high_priority(p, gfp_mask))
+		page = __alloc_pages_high_priority(gfp_mask, order,
+			zonelist, high_zoneidx, nodemask);
+	if (page)
+		goto got_pg;
 
 	/* Atomic allocations - we can't balance anything */
 	if (!wait)
 		goto nopage;
 
-	cond_resched();
+	/* Try direct reclaim and then allocating */
+	page = __alloc_pages_direct_reclaim(gfp_mask, order,
+					zonelist, high_zoneidx,
+					nodemask,
+					alloc_flags, &did_some_progress);
+	if (page)
+		goto got_pg;
 
-	/* We now go into synchronous reclaim */
-	cpuset_memory_pressure_bump();
 	/*
-	 * The task's cpuset might have expanded its set of allowable nodes
+	 * If we failed to make any progress reclaiming, then we are
+	 * running out of options and have to consider going OOM
 	 */
-	cpuset_update_task_memory_state();
-	p->flags |= PF_MEMALLOC;
-	reclaim_state.reclaimed_slab = 0;
-	p->reclaim_state = &reclaim_state;
-
-	did_some_progress = try_to_free_pages(zonelist, order, gfp_mask);
-
-	p->reclaim_state = NULL;
-	p->flags &= ~PF_MEMALLOC;
-
-	cond_resched();
-
-	if (order != 0)
-		drain_all_pages();
+	if (!did_some_progress) {
+		if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+			page = __alloc_pages_may_oom(gfp_mask, order,
+					zonelist, high_zoneidx,
+					nodemask);
+			if (page)
+				goto got_pg;
 
-	if (likely(did_some_progress)) {
-		page = get_page_from_freelist(gfp_mask, nodemask, order,
-					zonelist, high_zoneidx, alloc_flags);
-		if (page)
-			goto got_pg;
-	} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
-		if (!try_set_zone_oom(zonelist, gfp_mask)) {
-			schedule_timeout_uninterruptible(1);
 			goto restart;
 		}
-
-		/*
-		 * Go through the zonelist yet one more time, keep
-		 * very high watermark here, this is only to catch
-		 * a parallel oom killing, we must fail if we're still
-		 * under heavy pressure.
-		 */
-		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
-			order, zonelist, high_zoneidx,
-			ALLOC_WMARK_HIGH|ALLOC_CPUSET);
-		if (page) {
-			clear_zonelist_oom(zonelist, gfp_mask);
-			goto got_pg;
-		}
-
-		/* The OOM killer will not help higher order allocs so fail */
-		if (order > PAGE_ALLOC_COSTLY_ORDER) {
-			clear_zonelist_oom(zonelist, gfp_mask);
-			goto nopage;
-		}
-
-		out_of_memory(zonelist, gfp_mask, order);
-		clear_zonelist_oom(zonelist, gfp_mask);
-		goto restart;
 	}
 
-	/*
-	 * Don't let big-order allocations loop unless the caller explicitly
-	 * requests that.  Wait for some write requests to complete then retry.
-	 *
-	 * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
-	 * means __GFP_NOFAIL, but that may not be true in other
-	 * implementations.
-	 *
-	 * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
-	 * specified, then we retry until we no longer reclaim any pages
-	 * (above), or we've reclaimed an order of pages at least as
-	 * large as the allocation's order. In both cases, if the
-	 * allocation still fails, we stop retrying.
-	 */
+	/* Check if we should retry the allocation */
 	pages_reclaimed += did_some_progress;
-	do_retry = 0;
-	if (!(gfp_mask & __GFP_NORETRY)) {
-		if (order <= PAGE_ALLOC_COSTLY_ORDER) {
-			do_retry = 1;
-		} else {
-			if (gfp_mask & __GFP_REPEAT &&
-				pages_reclaimed < (1 << order))
-					do_retry = 1;
-		}
-		if (gfp_mask & __GFP_NOFAIL)
-			do_retry = 1;
-	}
-	if (do_retry) {
+	if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
+		/* Wait for some write requests to complete then retry */
 		congestion_wait(WRITE, HZ/50);
-		goto rebalance;
+		goto restart;
 	}
 
 nopage:
@@ -1672,6 +1726,39 @@ nopage:
 	}
 got_pg:
 	return page;
+
+}
+
+/*
+ * This is the 'heart' of the zoned buddy allocator.
+ */
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+			struct zonelist *zonelist, nodemask_t *nodemask)
+{
+	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+	struct page *page;
+
+	might_sleep_if(gfp_mask & __GFP_WAIT);
+
+	if (should_fail_alloc_page(gfp_mask, order))
+		return NULL;
+
+	/*
+	 * Check the zones suitable for the gfp_mask contain at least one
+	 * valid zone. It's possible to have an empty zonelist as a result
+	 * of GFP_THISNODE and a memoryless node
+	 */
+	if (unlikely(!zonelist->_zonerefs->zone))
+		return NULL;
+
+	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
+			zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+	if (unlikely(!page))
+		page = __alloc_pages_slowpath(gfp_mask, order,
+				zonelist, high_zoneidx, nodemask);
+
+	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
 
-- 
1.5.6.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists