Merge branch 'master' into for-next

Conflicts:
	include/linux/mmzone.h

Synced with Linus' tree so that trivial patch can be applied
on top of up-to-date code properly.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>

1 files changed, 39 insertions, 267 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3d1365c1786..8deb5f4da4d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -53,24 +53,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/vmscan.h>
 
-/*
- * reclaim_mode determines how the inactive list is shrunk
- * RECLAIM_MODE_SINGLE: Reclaim only order-0 pages
- * RECLAIM_MODE_ASYNC:  Do not block
- * RECLAIM_MODE_SYNC:   Allow blocking e.g. call wait_on_page_writeback
- * RECLAIM_MODE_LUMPYRECLAIM: For high-order allocations, take a reference
- *			page from the LRU and reclaim all pages within a
- *			naturally aligned range
- * RECLAIM_MODE_COMPACTION: For high-order allocations, reclaim a number of
- *			order-0 pages and then compact the zone
- */
-typedef unsigned __bitwise__ reclaim_mode_t;
-#define RECLAIM_MODE_SINGLE		((__force reclaim_mode_t)0x01u)
-#define RECLAIM_MODE_ASYNC		((__force reclaim_mode_t)0x02u)
-#define RECLAIM_MODE_SYNC		((__force reclaim_mode_t)0x04u)
-#define RECLAIM_MODE_LUMPYRECLAIM	((__force reclaim_mode_t)0x08u)
-#define RECLAIM_MODE_COMPACTION		((__force reclaim_mode_t)0x10u)
-
 struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
@@ -97,12 +79,6 @@ struct scan_control {
 	int order;
 
 	/*
-	 * Intend to reclaim enough continuous memory rather than reclaim
-	 * enough amount of memory. i.e, mode for high order allocation.
-	 */
-	reclaim_mode_t reclaim_mode;
-
-	/*
 	 * The memory cgroup that hit its limit and as a result is the
 	 * primary target of this reclaim invocation.
 	 */
@@ -164,35 +140,22 @@ static bool global_reclaim(struct scan_control *sc)
 {
 	return !sc->target_mem_cgroup;
 }
-
-static bool scanning_global_lru(struct mem_cgroup_zone *mz)
-{
-	return !mz->mem_cgroup;
-}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
 	return true;
 }
-
-static bool scanning_global_lru(struct mem_cgroup_zone *mz)
-{
-	return true;
-}
 #endif
 
 static struct zone_reclaim_stat *get_reclaim_stat(struct mem_cgroup_zone *mz)
 {
-	if (!scanning_global_lru(mz))
-		return mem_cgroup_get_reclaim_stat(mz->mem_cgroup, mz->zone);
-
-	return &mz->zone->reclaim_stat;
+	return &mem_cgroup_zone_lruvec(mz->zone, mz->mem_cgroup)->reclaim_stat;
 }
 
 static unsigned long zone_nr_lru_pages(struct mem_cgroup_zone *mz,
 				       enum lru_list lru)
 {
-	if (!scanning_global_lru(mz))
+	if (!mem_cgroup_disabled())
 		return mem_cgroup_zone_nr_lru_pages(mz->mem_cgroup,
 						    zone_to_nid(mz->zone),
 						    zone_idx(mz->zone),
@@ -364,39 +327,6 @@ out:
 	return ret;
 }
 
-static void set_reclaim_mode(int priority, struct scan_control *sc,
-				   bool sync)
-{
-	reclaim_mode_t syncmode = sync ? RECLAIM_MODE_SYNC : RECLAIM_MODE_ASYNC;
-
-	/*
-	 * Initially assume we are entering either lumpy reclaim or
-	 * reclaim/compaction.Depending on the order, we will either set the
-	 * sync mode or just reclaim order-0 pages later.
-	 */
-	if (COMPACTION_BUILD)
-		sc->reclaim_mode = RECLAIM_MODE_COMPACTION;
-	else
-		sc->reclaim_mode = RECLAIM_MODE_LUMPYRECLAIM;
-
-	/*
-	 * Avoid using lumpy reclaim or reclaim/compaction if possible by
-	 * restricting when its set to either costly allocations or when
-	 * under memory pressure
-	 */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		sc->reclaim_mode |= syncmode;
-	else if (sc->order && priority < DEF_PRIORITY - 2)
-		sc->reclaim_mode |= syncmode;
-	else
-		sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC;
-}
-
-static void reset_reclaim_mode(struct scan_control *sc)
-{
-	sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC;
-}
-
 static inline int is_page_cache_freeable(struct page *page)
 {
 	/*
@@ -416,10 +346,6 @@ static int may_write_to_queue(struct backing_dev_info *bdi,
 		return 1;
 	if (bdi == current->backing_dev_info)
 		return 1;
-
-	/* lumpy reclaim for hugepage often need a lot of write */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		return 1;
 	return 0;
 }
 
@@ -523,8 +449,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 			/* synchronous write or broken a_ops? */
 			ClearPageReclaim(page);
 		}
-		trace_mm_vmscan_writepage(page,
-			trace_reclaim_flags(page, sc->reclaim_mode));
+		trace_mm_vmscan_writepage(page, trace_reclaim_flags(page));
 		inc_zone_page_state(page, NR_VMSCAN_WRITE);
 		return PAGE_SUCCESS;
 	}
@@ -707,13 +632,10 @@ static enum page_references page_check_references(struct page *page,
 	int referenced_ptes, referenced_page;
 	unsigned long vm_flags;
 
-	referenced_ptes = page_referenced(page, 1, mz->mem_cgroup, &vm_flags);
+	referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
+					  &vm_flags);
 	referenced_page = TestClearPageReferenced(page);
 
-	/* Lumpy reclaim - ignore references */
-	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
-		return PAGEREF_RECLAIM;
-
 	/*
 	 * Mlock lost the isolation race with us.  Let try_to_unmap()
 	 * move the page to the unevictable list.
@@ -722,7 +644,7 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_RECLAIM;
 
 	if (referenced_ptes) {
-		if (PageAnon(page))
+		if (PageSwapBacked(page))
 			return PAGEREF_ACTIVATE;
 		/*
 		 * All mapped pages start out with page table
@@ -813,19 +735,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 		if (PageWriteback(page)) {
 			nr_writeback++;
-			/*
-			 * Synchronous reclaim cannot queue pages for
-			 * writeback due to the possibility of stack overflow
-			 * but if it encounters a page under writeback, wait
-			 * for the IO to complete.
-			 */
-			if ((sc->reclaim_mode & RECLAIM_MODE_SYNC) &&
-			    may_enter_fs)
-				wait_on_page_writeback(page);
-			else {
-				unlock_page(page);
-				goto keep_lumpy;
-			}
+			unlock_page(page);
+			goto keep;
 		}
 
 		references = page_check_references(page, mz, sc);
@@ -908,7 +819,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto activate_locked;
 			case PAGE_SUCCESS:
 				if (PageWriteback(page))
-					goto keep_lumpy;
+					goto keep;
 				if (PageDirty(page))
 					goto keep;
 
@@ -994,7 +905,6 @@ cull_mlocked:
 			try_to_free_swap(page);
 		unlock_page(page);
 		putback_lru_page(page);
-		reset_reclaim_mode(sc);
 		continue;
 
 activate_locked:
@@ -1007,8 +917,6 @@ activate_locked:
 keep_locked:
 		unlock_page(page);
 keep:
-		reset_reclaim_mode(sc);
-keep_lumpy:
 		list_add(&page->lru, &ret_pages);
 		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
 	}
@@ -1064,11 +972,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file)
 	if (!all_lru_mode && !!page_is_file_cache(page) != file)
 		return ret;
 
-	/*
-	 * When this function is being called for lumpy reclaim, we
-	 * initially look into all LRU pages, active, inactive and
-	 * unevictable; only give shrink_page_list evictable pages.
-	 */
+	/* Do not give back unevictable pages for compaction */
 	if (PageUnevictable(page))
 		return ret;
 
@@ -1153,9 +1057,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	struct lruvec *lruvec;
 	struct list_head *src;
 	unsigned long nr_taken = 0;
-	unsigned long nr_lumpy_taken = 0;
-	unsigned long nr_lumpy_dirty = 0;
-	unsigned long nr_lumpy_failed = 0;
 	unsigned long scan;
 	int lru = LRU_BASE;
 
@@ -1168,10 +1069,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
 		struct page *page;
-		unsigned long pfn;
-		unsigned long end_pfn;
-		unsigned long page_pfn;
-		int zone_id;
 
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);
@@ -1193,84 +1090,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		default:
 			BUG();
 		}
-
-		if (!sc->order || !(sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM))
-			continue;
-
-		/*
-		 * Attempt to take all pages in the order aligned region
-		 * surrounding the tag page.  Only take those pages of
-		 * the same active state as that tag page.  We may safely
-		 * round the target page pfn down to the requested order
-		 * as the mem_map is guaranteed valid out to MAX_ORDER,
-		 * where that page is in a different zone we will detect
-		 * it from its zone id and abort this block scan.
-		 */
-		zone_id = page_zone_id(page);
-		page_pfn = page_to_pfn(page);
-		pfn = page_pfn & ~((1 << sc->order) - 1);
-		end_pfn = pfn + (1 << sc->order);
-		for (; pfn < end_pfn; pfn++) {
-			struct page *cursor_page;
-
-			/* The target page is in the block, ignore it. */
-			if (unlikely(pfn == page_pfn))
-				continue;
-
-			/* Avoid holes within the zone. */
-			if (unlikely(!pfn_valid_within(pfn)))
-				break;
-
-			cursor_page = pfn_to_page(pfn);
-
-			/* Check that we have not crossed a zone boundary. */
-			if (unlikely(page_zone_id(cursor_page) != zone_id))
-				break;
-
-			/*
-			 * If we don't have enough swap space, reclaiming of
-			 * anon page which don't already have a swap slot is
-			 * pointless.
-			 */
-			if (nr_swap_pages <= 0 && PageSwapBacked(cursor_page) &&
-			    !PageSwapCache(cursor_page))
-				break;
-
-			if (__isolate_lru_page(cursor_page, mode, file) == 0) {
-				unsigned int isolated_pages;
-
-				mem_cgroup_lru_del(cursor_page);
-				list_move(&cursor_page->lru, dst);
-				isolated_pages = hpage_nr_pages(cursor_page);
-				nr_taken += isolated_pages;
-				nr_lumpy_taken += isolated_pages;
-				if (PageDirty(cursor_page))
-					nr_lumpy_dirty += isolated_pages;
-				scan++;
-				pfn += isolated_pages - 1;
-			} else {
-				/*
-				 * Check if the page is freed already.
-				 *
-				 * We can't use page_count() as that
-				 * requires compound_head and we don't
-				 * have a pin on the page here. If a
-				 * page is tail, we may or may not
-				 * have isolated the head, so assume
-				 * it's not free, it'd be tricky to
-				 * track the head status without a
-				 * page pin.
-				 */
-				if (!PageTail(cursor_page) &&
-				    !atomic_read(&cursor_page->_count))
-					continue;
-				break;
-			}
-		}
-
-		/* If we break out of the loop above, lumpy reclaim failed */
-		if (pfn < end_pfn)
-			nr_lumpy_failed++;
 	}
 
 	*nr_scanned = scan;
@@ -1278,7 +1097,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	trace_mm_vmscan_lru_isolate(sc->order,
 			nr_to_scan, scan,
 			nr_taken,
-			nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed,
 			mode, file);
 	return nr_taken;
 }
@@ -1454,47 +1272,6 @@ update_isolated_counts(struct mem_cgroup_zone *mz,
 }
 
 /*
- * Returns true if a direct reclaim should wait on pages under writeback.
- *
- * If we are direct reclaiming for contiguous pages and we do not reclaim
- * everything in the list, try again and wait for writeback IO to complete.
- * This will stall high-order allocations noticeably. Only do that when really
- * need to free the pages under high memory pressure.
- */
-static inline bool should_reclaim_stall(unsigned long nr_taken,
-					unsigned long nr_freed,
-					int priority,
-					struct scan_control *sc)
-{
-	int lumpy_stall_priority;
-
-	/* kswapd should not stall on sync IO */
-	if (current_is_kswapd())
-		return false;
-
-	/* Only stall on lumpy reclaim */
-	if (sc->reclaim_mode & RECLAIM_MODE_SINGLE)
-		return false;
-
-	/* If we have reclaimed everything on the isolated list, no stall */
-	if (nr_freed == nr_taken)
-		return false;
-
-	/*
-	 * For high-order allocations, there are two stall thresholds.
-	 * High-cost allocations stall immediately where as lower
-	 * order allocations such as stacks require the scanning
-	 * priority to be much higher before stalling.
-	 */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		lumpy_stall_priority = DEF_PRIORITY;
-	else
-		lumpy_stall_priority = DEF_PRIORITY / 3;
-
-	return priority <= lumpy_stall_priority;
-}
-
-/*
  * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
  * of reclaimed pages
  */
@@ -1522,10 +1299,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 			return SWAP_CLUSTER_MAX;
 	}
 
-	set_reclaim_mode(priority, sc, false);
-	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
-		isolate_mode |= ISOLATE_ACTIVE;
-
 	lru_add_drain();
 
 	if (!sc->may_unmap)
@@ -1556,13 +1329,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 	nr_reclaimed = shrink_page_list(&page_list, mz, sc, priority,
 						&nr_dirty, &nr_writeback);
 
-	/* Check if we should syncronously wait for writeback */
-	if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) {
-		set_reclaim_mode(priority, sc, true);
-		nr_reclaimed += shrink_page_list(&page_list, mz, sc,
-					priority, &nr_dirty, &nr_writeback);
-	}
-
 	spin_lock_irq(&zone->lru_lock);
 
 	reclaim_stat->recent_scanned[0] += nr_anon;
@@ -1616,7 +1382,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 		zone_idx(zone),
 		nr_scanned, nr_reclaimed,
 		priority,
-		trace_shrink_flags(file, sc->reclaim_mode));
+		trace_shrink_flags(file));
 	return nr_reclaimed;
 }
 
@@ -1695,8 +1461,6 @@ static void shrink_active_list(unsigned long nr_to_scan,
 
 	lru_add_drain();
 
-	reset_reclaim_mode(sc);
-
 	if (!sc->may_unmap)
 		isolate_mode |= ISOLATE_UNMAPPED;
 	if (!sc->may_writepage)
@@ -1737,7 +1501,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
 			}
 		}
 
-		if (page_referenced(page, 0, mz->mem_cgroup, &vm_flags)) {
+		if (page_referenced(page, 0, sc->target_mem_cgroup,
+				    &vm_flags)) {
 			nr_rotated += hpage_nr_pages(page);
 			/*
 			 * Identify referenced, file-backed active pages and
@@ -1811,7 +1576,7 @@ static int inactive_anon_is_low(struct mem_cgroup_zone *mz)
 	if (!total_swap_pages)
 		return 0;
 
-	if (!scanning_global_lru(mz))
+	if (!mem_cgroup_disabled())
 		return mem_cgroup_inactive_anon_is_low(mz->mem_cgroup,
 						       mz->zone);
 
@@ -1850,7 +1615,7 @@ static int inactive_file_is_low_global(struct zone *zone)
  */
 static int inactive_file_is_low(struct mem_cgroup_zone *mz)
 {
-	if (!scanning_global_lru(mz))
+	if (!mem_cgroup_disabled())
 		return mem_cgroup_inactive_file_is_low(mz->mem_cgroup,
 						       mz->zone);
 
@@ -1984,10 +1749,10 @@ static void get_scan_count(struct mem_cgroup_zone *mz, struct scan_control *sc,
 	 * proportional to the fraction of recently scanned pages on
 	 * each list that were recently referenced and in active use.
 	 */
-	ap = (anon_prio + 1) * (reclaim_stat->recent_scanned[0] + 1);
+	ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1);
 	ap /= reclaim_stat->recent_rotated[0] + 1;
 
-	fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
+	fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
 	fp /= reclaim_stat->recent_rotated[1] + 1;
 	spin_unlock_irq(&mz->zone->lru_lock);
 
@@ -2000,7 +1765,7 @@ out:
 		unsigned long scan;
 
 		scan = zone_nr_lru_pages(mz, lru);
-		if (priority || noswap) {
+		if (priority || noswap || !vmscan_swappiness(mz, sc)) {
 			scan >>= priority;
 			if (!scan && force_scan)
 				scan = SWAP_CLUSTER_MAX;
@@ -2010,23 +1775,35 @@ out:
 	}
 }
 
+/* Use reclaim/compaction for costly allocs or under memory pressure */
+static bool in_reclaim_compaction(int priority, struct scan_control *sc)
+{
+	if (COMPACTION_BUILD && sc->order &&
+			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
+			 priority < DEF_PRIORITY - 2))
+		return true;
+
+	return false;
+}
+
 /*
- * Reclaim/compaction depends on a number of pages being freed. To avoid
- * disruption to the system, a small number of order-0 pages continue to be
- * rotated and reclaimed in the normal fashion. However, by the time we get
- * back to the allocator and call try_to_compact_zone(), we ensure that
- * there are enough free pages for it to be likely successful
+ * Reclaim/compaction is used for high-order allocation requests. It reclaims
+ * order-0 pages before compacting the zone. should_continue_reclaim() returns
+ * true if more pages should be reclaimed such that when the page allocator
+ * calls try_to_compact_zone() that it will have enough free pages to succeed.
+ * It will give up earlier than that if there is difficulty reclaiming pages.
  */
 static inline bool should_continue_reclaim(struct mem_cgroup_zone *mz,
 					unsigned long nr_reclaimed,
 					unsigned long nr_scanned,
+					int priority,
 					struct scan_control *sc)
 {
 	unsigned long pages_for_compaction;
 	unsigned long inactive_lru_pages;
 
 	/* If not in reclaim/compaction mode, stop */
-	if (!(sc->reclaim_mode & RECLAIM_MODE_COMPACTION))
+	if (!in_reclaim_compaction(priority, sc))
 		return false;
 
 	/* Consider stopping depending on scan and reclaim activity */
@@ -2128,7 +1905,8 @@ restart:
 
 	/* reclaim/compaction might need reclaim to continue */
 	if (should_continue_reclaim(mz, nr_reclaimed,
-					sc->nr_scanned - nr_scanned, sc))
+					sc->nr_scanned - nr_scanned,
+					priority, sc))
 		goto restart;
 
 	throttle_vm_writeout(sc->gfp_mask);
@@ -2353,8 +2131,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		sc->nr_scanned = 0;
-		if (!priority)
-			disable_swap_token(sc->target_mem_cgroup);
 		aborted_reclaim = shrink_zones(priority, zonelist, sc);
 
 		/*
@@ -2705,10 +2481,6 @@ loop_again:
 		unsigned long lru_pages = 0;
 		int has_under_min_watermark_zone = 0;
 
-		/* The swap token gets in the way of swapout... */
-		if (!priority)
-			disable_swap_token(NULL);
-
 		all_zones_ok = 1;
 		balanced = 0;
 
@@ -3537,7 +3309,7 @@ int page_evictable(struct page *page, struct vm_area_struct *vma)
 	if (mapping_unevictable(page_mapping(page)))
 		return 0;
 
-	if (PageMlocked(page) || (vma && is_mlocked_vma(vma, page)))
+	if (PageMlocked(page) || (vma && mlocked_vma_newpage(vma, page)))
 		return 0;
 
 	return 1;