1 files changed, 110 insertions, 64 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7acd0afdfc2a..a6c5d0b28321 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -88,9 +88,6 @@ struct scan_control {
 	/* Can pages be swapped as part of reclaim? */
 	unsigned int may_swap:1;
 
-	/* e.g. boosted watermark reclaim leaves slabs alone */
-	unsigned int may_shrinkslab:1;
-
 	/*
 	 * Cgroups are not reclaimed below their configured memory.low,
 	 * unless we threaten to OOM. If any cgroups are skipped due to
@@ -131,6 +128,9 @@ struct scan_control {
 		unsigned int file_taken;
 		unsigned int taken;
 	} nr;
+
+	/* for recording the reclaimed slab by now */
+	struct reclaim_state reclaim_state;
 };
 
 #ifdef ARCH_HAS_PREFETCH
@@ -238,6 +238,18 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker)
 }
 #endif /* CONFIG_MEMCG_KMEM */
 
+static void set_task_reclaim_state(struct task_struct *task,
+				   struct reclaim_state *rs)
+{
+	/* Check for an overwrite */
+	WARN_ON_ONCE(rs && task->reclaim_state);
+
+	/* Check for the nulling of an already-nulled member */
+	WARN_ON_ONCE(!rs && !task->reclaim_state);
+
+	task->reclaim_state = rs;
+}
+
 #ifdef CONFIG_MEMCG
 static bool global_reclaim(struct scan_control *sc)
 {
@@ -684,7 +696,14 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 	unsigned long ret, freed = 0;
 	struct shrinker *shrinker;
 
-	if (!mem_cgroup_is_root(memcg))
+	/*
+	 * The root memcg might be allocated even though memcg is disabled
+	 * via "cgroup_disable=memory" boot parameter.  This could make
+	 * mem_cgroup_is_root() return false, then just run memcg slab
+	 * shrink, but skip global shrink.  This may result in premature
+	 * oom.
+	 */
+	if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
 		return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
 
 	if (!down_read_trylock(&shrinker_rwsem))
@@ -1118,6 +1137,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		int may_enter_fs;
 		enum page_references references = PAGEREF_RECLAIM_CLEAN;
 		bool dirty, writeback;
+		unsigned int nr_pages;
 
 		cond_resched();
 
@@ -1129,7 +1149,10 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 		VM_BUG_ON_PAGE(PageActive(page), page);
 
-		sc->nr_scanned++;
+		nr_pages = 1 << compound_order(page);
+
+		/* Account the number of base pages even though THP */
+		sc->nr_scanned += nr_pages;
 
 		if (unlikely(!page_evictable(page)))
 			goto activate_locked;
@@ -1137,11 +1160,6 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (!sc->may_unmap && page_mapped(page))
 			goto keep_locked;
 
-		/* Double the slab pressure for mapped and swapcache pages */
-		if ((page_mapped(page) || PageSwapCache(page)) &&
-		    !(PageAnon(page) && !PageSwapBacked(page)))
-			sc->nr_scanned++;
-
 		may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
 			(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
 
@@ -1255,7 +1273,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		case PAGEREF_ACTIVATE:
 			goto activate_locked;
 		case PAGEREF_KEEP:
-			stat->nr_ref_keep++;
+			stat->nr_ref_keep += nr_pages;
 			goto keep_locked;
 		case PAGEREF_RECLAIM:
 		case PAGEREF_RECLAIM_CLEAN:
@@ -1287,7 +1305,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				}
 				if (!add_to_swap(page)) {
 					if (!PageTransHuge(page))
-						goto activate_locked;
+						goto activate_locked_split;
 					/* Fallback to swap normal pages */
 					if (split_huge_page_to_list(page,
 								    page_list))
@@ -1296,7 +1314,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 					count_vm_event(THP_SWPOUT_FALLBACK);
 #endif
 					if (!add_to_swap(page))
-						goto activate_locked;
+						goto activate_locked_split;
 				}
 
 				may_enter_fs = 1;
@@ -1311,6 +1329,18 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		}
 
 		/*
+		 * THP may get split above, need minus tail pages and update
+		 * nr_pages to avoid accounting tail pages twice.
+		 *
+		 * The tail pages that are added into swap cache successfully
+		 * reach here.
+		 */
+		if ((nr_pages > 1) && !PageTransHuge(page)) {
+			sc->nr_scanned -= (nr_pages - 1);
+			nr_pages = 1;
+		}
+
+		/*
 		 * The page is mapped into the page tables of one or more
 		 * processes. Try to unmap it here.
 		 */
@@ -1320,7 +1350,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			if (unlikely(PageTransHuge(page)))
 				flags |= TTU_SPLIT_HUGE_PMD;
 			if (!try_to_unmap(page, flags)) {
-				stat->nr_unmap_fail++;
+				stat->nr_unmap_fail += nr_pages;
 				goto activate_locked;
 			}
 		}
@@ -1447,7 +1477,11 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 		unlock_page(page);
 free_it:
-		nr_reclaimed++;
+		/*
+		 * THP may get swapped out in a whole, need account
+		 * all base pages.
+		 */
+		nr_reclaimed += nr_pages;
 
 		/*
 		 * Is there need to periodically free_page_list? It would
@@ -1460,6 +1494,15 @@ free_it:
 			list_add(&page->lru, &free_pages);
 		continue;
 
+activate_locked_split:
+		/*
+		 * The tail pages that are failed to add into swap cache
+		 * reach here.  Fixup nr_scanned and nr_pages.
+		 */
+		if (nr_pages > 1) {
+			sc->nr_scanned -= (nr_pages - 1);
+			nr_pages = 1;
+		}
 activate_locked:
 		/* Not a candidate for swapping, so reclaim swap space. */
 		if (PageSwapCache(page) && (mem_cgroup_swap_full(page) ||
@@ -1469,8 +1512,7 @@ activate_locked:
 		if (!PageMlocked(page)) {
 			int type = page_is_file_cache(page);
 			SetPageActive(page);
-			pgactivate++;
-			stat->nr_activate[type] += hpage_nr_pages(page);
+			stat->nr_activate[type] += nr_pages;
 			count_memcg_page_event(page, PGACTIVATE);
 		}
 keep_locked:
@@ -1480,6 +1522,8 @@ keep:
 		VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
 	}
 
+	pgactivate = stat->nr_activate[0] + stat->nr_activate[1];
+
 	mem_cgroup_uncharge_list(&free_pages);
 	try_to_unmap_flush();
 	free_unref_page_list(&free_pages);
@@ -1505,7 +1549,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
 		if (page_is_file_cache(page) && !PageDirty(page) &&
-		    !__PageMovable(page)) {
+		    !__PageMovable(page) && !PageUnevictable(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
@@ -1651,10 +1695,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	LIST_HEAD(pages_skipped);
 	isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED);
 
+	total_scan = 0;
 	scan = 0;
-	for (total_scan = 0;
-	     scan < nr_to_scan && nr_taken < nr_to_scan && !list_empty(src);
-	     total_scan++) {
+	while (scan < nr_to_scan && !list_empty(src)) {
 		struct page *page;
 
 		page = lru_to_page(src);
@@ -1662,9 +1705,12 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 		VM_BUG_ON_PAGE(!PageLRU(page), page);
 
+		nr_pages = 1 << compound_order(page);
+		total_scan += nr_pages;
+
 		if (page_zonenum(page) > sc->reclaim_idx) {
 			list_move(&page->lru, &pages_skipped);
-			nr_skipped[page_zonenum(page)]++;
+			nr_skipped[page_zonenum(page)] += nr_pages;
 			continue;
 		}
 
@@ -1673,11 +1719,14 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		 * return with no isolated pages if the LRU mostly contains
 		 * ineligible pages.  This causes the VM to not reclaim any
 		 * pages, triggering a premature OOM.
+		 *
+		 * Account all tail pages of THP.  This would not cause
+		 * premature OOM since __isolate_lru_page() returns -EBUSY
+		 * only when the page is being freed somewhere else.
 		 */
-		scan++;
+		scan += nr_pages;
 		switch (__isolate_lru_page(page, mode)) {
 		case 0:
-			nr_pages = hpage_nr_pages(page);
 			nr_taken += nr_pages;
 			nr_zone_taken[page_zonenum(page)] += nr_pages;
 			list_move(&page->lru, dst);
@@ -1953,8 +2002,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	if (global_reclaim(sc))
 		__count_vm_events(item, nr_reclaimed);
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
-	reclaim_stat->recent_rotated[0] = stat.nr_activate[0];
-	reclaim_stat->recent_rotated[1] = stat.nr_activate[1];
+	reclaim_stat->recent_rotated[0] += stat.nr_activate[0];
+	reclaim_stat->recent_rotated[1] += stat.nr_activate[1];
 
 	move_pages_to_lru(lruvec, &page_list);
 
@@ -2125,7 +2174,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
  *   10TB     320        32GB
  */
 static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
-				 struct scan_control *sc, bool actual_reclaim)
+				 struct scan_control *sc, bool trace)
 {
 	enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
@@ -2151,7 +2200,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	 * rid of the stale workingset quickly.
 	 */
 	refaults = lruvec_page_state_local(lruvec, WORKINGSET_ACTIVATE);
-	if (file && actual_reclaim && lruvec->refaults != refaults) {
+	if (file && lruvec->refaults != refaults) {
 		inactive_ratio = 0;
 	} else {
 		gb = (inactive + active) >> (30 - PAGE_SHIFT);
@@ -2161,7 +2210,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 			inactive_ratio = 1;
 	}
 
-	if (actual_reclaim)
+	if (trace)
 		trace_mm_vmscan_inactive_list_is_low(pgdat->node_id, sc->reclaim_idx,
 			lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive,
 			lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active,
@@ -2662,10 +2711,8 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
 			node_lru_pages += lru_pages;
 
-			if (sc->may_shrinkslab) {
-				shrink_slab(sc->gfp_mask, pgdat->node_id,
-				    memcg, sc->priority);
-			}
+			shrink_slab(sc->gfp_mask, pgdat->node_id, memcg,
+					sc->priority);
 
 			/* Record the group's reclaim efficiency */
 			vmpressure(sc->gfp_mask, memcg, false,
@@ -3142,7 +3189,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = 1,
-		.may_shrinkslab = 1,
 	};
 
 	/*
@@ -3161,17 +3207,20 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask))
 		return 1;
 
+	set_task_reclaim_state(current, &sc.reclaim_state);
 	trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask);
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
 	trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
+	set_task_reclaim_state(current, NULL);
 
 	return nr_reclaimed;
 }
 
 #ifdef CONFIG_MEMCG
 
+/* Only used by soft limit reclaim. Do not reuse for anything else. */
 unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 						gfp_t gfp_mask, bool noswap,
 						pg_data_t *pgdat,
@@ -3184,10 +3233,11 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 		.may_unmap = 1,
 		.reclaim_idx = MAX_NR_ZONES - 1,
 		.may_swap = !noswap,
-		.may_shrinkslab = 1,
 	};
 	unsigned long lru_pages;
 
+	WARN_ON_ONCE(!current->reclaim_state);
+
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
 
@@ -3206,6 +3256,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
 
 	*nr_scanned = sc.nr_scanned;
+
 	return sc.nr_reclaimed;
 }
 
@@ -3229,9 +3280,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = may_swap,
-		.may_shrinkslab = 1,
 	};
 
+	set_task_reclaim_state(current, &sc.reclaim_state);
 	/*
 	 * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
 	 * take care of from where we get pages. So the node where we start the
@@ -3252,6 +3303,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 	psi_memstall_leave(&pflags);
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
+	set_task_reclaim_state(current, NULL);
 
 	return nr_reclaimed;
 }
@@ -3453,6 +3505,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		.may_unmap = 1,
 	};
 
+	set_task_reclaim_state(current, &sc.reclaim_state);
 	psi_memstall_enter(&pflags);
 	__fs_reclaim_acquire();
 
@@ -3538,7 +3591,6 @@ restart:
 		 */
 		sc.may_writepage = !laptop_mode && !nr_boost_reclaim;
 		sc.may_swap = !nr_boost_reclaim;
-		sc.may_shrinkslab = !nr_boost_reclaim;
 
 		/*
 		 * Do some background aging of the anon list, to give
@@ -3634,6 +3686,8 @@ out:
 	snapshot_refaults(NULL, pgdat);
 	__fs_reclaim_release();
 	psi_memstall_leave(&pflags);
+	set_task_reclaim_state(current, NULL);
+
 	/*
 	 * Return the order kswapd stopped reclaiming at as
 	 * prepare_kswapd_sleep() takes it into account. If another caller
@@ -3644,19 +3698,18 @@ out:
 }
 
 /*
- * pgdat->kswapd_classzone_idx is the highest zone index that a recent
- * allocation request woke kswapd for. When kswapd has not woken recently,
- * the value is MAX_NR_ZONES which is not a valid index. This compares a
- * given classzone and returns it or the highest classzone index kswapd
- * was recently woke for.
+ * The pgdat->kswapd_classzone_idx is used to pass the highest zone index to be
+ * reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is not
+ * a valid index then either kswapd runs for first time or kswapd couldn't sleep
+ * after previous reclaim attempt (node is still unbalanced). In that case
+ * return the zone index of the previous kswapd reclaim cycle.
  */
 static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
-					   enum zone_type classzone_idx)
+					   enum zone_type prev_classzone_idx)
 {
 	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		return classzone_idx;
-
-	return max(pgdat->kswapd_classzone_idx, classzone_idx);
+		return prev_classzone_idx;
+	return pgdat->kswapd_classzone_idx;
 }
 
 static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
@@ -3758,15 +3811,10 @@ static int kswapd(void *p)
 	unsigned int classzone_idx = MAX_NR_ZONES - 1;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
-
-	struct reclaim_state reclaim_state = {
-		.reclaimed_slab = 0,
-	};
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
 	if (!cpumask_empty(cpumask))
 		set_cpus_allowed_ptr(tsk, cpumask);
-	current->reclaim_state = &reclaim_state;
 
 	/*
 	 * Tell the memory management that we're a "memory allocator",
@@ -3797,7 +3845,7 @@ kswapd_try_sleep:
 
 		/* Read the new order and classzone_idx */
 		alloc_order = reclaim_order = pgdat->kswapd_order;
-		classzone_idx = kswapd_classzone_idx(pgdat, 0);
+		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
 		pgdat->kswapd_order = 0;
 		pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
 
@@ -3828,7 +3876,6 @@ kswapd_try_sleep:
 	}
 
 	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
-	current->reclaim_state = NULL;
 
 	return 0;
 }
@@ -3851,8 +3898,12 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
 	if (!cpuset_zone_allowed(zone, gfp_flags))
 		return;
 	pgdat = zone->zone_pgdat;
-	pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat,
-							   classzone_idx);
+
+	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
+		pgdat->kswapd_classzone_idx = classzone_idx;
+	else
+		pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx,
+						  classzone_idx);
 	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
@@ -3889,7 +3940,6 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
  */
 unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 {
-	struct reclaim_state reclaim_state;
 	struct scan_control sc = {
 		.nr_to_reclaim = nr_to_reclaim,
 		.gfp_mask = GFP_HIGHUSER_MOVABLE,
@@ -3901,18 +3951,16 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 		.hibernation_mode = 1,
 	};
 	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
-	struct task_struct *p = current;
 	unsigned long nr_reclaimed;
 	unsigned int noreclaim_flag;
 
 	fs_reclaim_acquire(sc.gfp_mask);
 	noreclaim_flag = memalloc_noreclaim_save();
-	reclaim_state.reclaimed_slab = 0;
-	p->reclaim_state = &reclaim_state;
+	set_task_reclaim_state(current, &sc.reclaim_state);
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
-	p->reclaim_state = NULL;
+	set_task_reclaim_state(current, NULL);
 	memalloc_noreclaim_restore(noreclaim_flag);
 	fs_reclaim_release(sc.gfp_mask);
 
@@ -4077,7 +4125,6 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	/* Minimum pages needed in order to stay on node */
 	const unsigned long nr_pages = 1 << order;
 	struct task_struct *p = current;
-	struct reclaim_state reclaim_state;
 	unsigned int noreclaim_flag;
 	struct scan_control sc = {
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
@@ -4102,8 +4149,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	 */
 	noreclaim_flag = memalloc_noreclaim_save();
 	p->flags |= PF_SWAPWRITE;
-	reclaim_state.reclaimed_slab = 0;
-	p->reclaim_state = &reclaim_state;
+	set_task_reclaim_state(p, &sc.reclaim_state);
 
 	if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) {
 		/*
@@ -4115,7 +4161,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 		} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
 	}
 
-	p->reclaim_state = NULL;
+	set_task_reclaim_state(p, NULL);
 	current->flags &= ~PF_SWAPWRITE;
 	memalloc_noreclaim_restore(noreclaim_flag);
 	fs_reclaim_release(sc.gfp_mask);