Linux-libre 4.2-gnu

1 files changed, 69 insertions, 50 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4dbac2008..8286938c7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -154,11 +154,42 @@ static bool global_reclaim(struct scan_control *sc)
 {
 	return !sc->target_mem_cgroup;
 }
+
+/**
+ * sane_reclaim - is the usual dirty throttling mechanism operational?
+ * @sc: scan_control in question
+ *
+ * The normal page dirty throttling mechanism in balance_dirty_pages() is
+ * completely broken with the legacy memcg and direct stalling in
+ * shrink_page_list() is used for throttling instead, which lacks all the
+ * niceties such as fairness, adaptive pausing, bandwidth proportional
+ * allocation and configurability.
+ *
+ * This function tests whether the vmscan currently in progress can assume
+ * that the normal dirty throttling mechanism is operational.
+ */
+static bool sane_reclaim(struct scan_control *sc)
+{
+	struct mem_cgroup *memcg = sc->target_mem_cgroup;
+
+	if (!memcg)
+		return true;
+#ifdef CONFIG_CGROUP_WRITEBACK
+	if (cgroup_on_dfl(mem_cgroup_css(memcg)->cgroup))
+		return true;
+#endif
+	return false;
+}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
 	return true;
 }
+
+static bool sane_reclaim(struct scan_control *sc)
+{
+	return true;
+}
 #endif
 
 static unsigned long zone_reclaimable_pages(struct zone *zone)
@@ -452,14 +483,13 @@ static inline int is_page_cache_freeable(struct page *page)
 	return page_count(page) - page_has_private(page) == 2;
 }
 
-static int may_write_to_queue(struct backing_dev_info *bdi,
-			      struct scan_control *sc)
+static int may_write_to_inode(struct inode *inode, struct scan_control *sc)
 {
 	if (current->flags & PF_SWAPWRITE)
 		return 1;
-	if (!bdi_write_congested(bdi))
+	if (!inode_write_congested(inode))
 		return 1;
-	if (bdi == current->backing_dev_info)
+	if (inode_to_bdi(inode) == current->backing_dev_info)
 		return 1;
 	return 0;
 }
@@ -538,7 +568,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 	}
 	if (mapping->a_ops->writepage == NULL)
 		return PAGE_ACTIVATE;
-	if (!may_write_to_queue(inode_to_bdi(mapping->host), sc))
+	if (!may_write_to_inode(mapping->host, sc))
 		return PAGE_KEEP;
 
 	if (clear_page_dirty_for_io(page)) {
@@ -579,10 +609,14 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 static int __remove_mapping(struct address_space *mapping, struct page *page,
 			    bool reclaimed)
 {
+	unsigned long flags;
+	struct mem_cgroup *memcg;
+
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
 
-	spin_lock_irq(&mapping->tree_lock);
+	memcg = mem_cgroup_begin_page_stat(page);
+	spin_lock_irqsave(&mapping->tree_lock, flags);
 	/*
 	 * The non racy check for a busy page.
 	 *
@@ -620,7 +654,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		swp_entry_t swap = { .val = page_private(page) };
 		mem_cgroup_swapout(page, swap);
 		__delete_from_swap_cache(page);
-		spin_unlock_irq(&mapping->tree_lock);
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
+		mem_cgroup_end_page_stat(memcg);
 		swapcache_free(swap);
 	} else {
 		void (*freepage)(struct page *);
@@ -640,8 +675,9 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		if (reclaimed && page_is_file_cache(page) &&
 		    !mapping_exiting(mapping))
 			shadow = workingset_eviction(mapping, page);
-		__delete_from_page_cache(page, shadow);
-		spin_unlock_irq(&mapping->tree_lock);
+		__delete_from_page_cache(page, shadow, memcg);
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
+		mem_cgroup_end_page_stat(memcg);
 
 		if (freepage != NULL)
 			freepage(page);
@@ -650,7 +686,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	return 1;
 
 cannot_free:
-	spin_unlock_irq(&mapping->tree_lock);
+	spin_unlock_irqrestore(&mapping->tree_lock, flags);
+	mem_cgroup_end_page_stat(memcg);
 	return 0;
 }
 
@@ -917,7 +954,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 */
 		mapping = page_mapping(page);
 		if (((dirty || writeback) && mapping &&
-		     bdi_write_congested(inode_to_bdi(mapping->host))) ||
+		     inode_write_congested(mapping->host)) ||
 		    (writeback && PageReclaim(page)))
 			nr_congested++;
 
@@ -935,11 +972,11 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 *    note that the LRU is being scanned too quickly and the
 		 *    caller can stall after page list has been processed.
 		 *
-		 * 2) Global reclaim encounters a page, memcg encounters a
-		 *    page that is not marked for immediate reclaim or
-		 *    the caller does not have __GFP_FS (or __GFP_IO if it's
-		 *    simply going to swap, not to fs). In this case mark
-		 *    the page for immediate reclaim and continue scanning.
+		 * 2) Global or new memcg reclaim encounters a page that is
+		 *    not marked for immediate reclaim, or the caller does not
+		 *    have __GFP_FS (or __GFP_IO if it's simply going to swap,
+		 *    not to fs). In this case mark the page for immediate
+		 *    reclaim and continue scanning.
 		 *
 		 *    Require may_enter_fs because we would wait on fs, which
 		 *    may not have submitted IO yet. And the loop driver might
@@ -948,7 +985,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 *    __GFP_IO|__GFP_FS for this reason); but more thought
 		 *    would probably show more reasons.
 		 *
-		 * 3) memcg encounters a page that is not already marked
+		 * 3) Legacy memcg encounters a page that is not already marked
 		 *    PageReclaim. memcg does not have any dirty pages
 		 *    throttling so we could easily OOM just because too many
 		 *    pages are in writeback and there is nothing else to
@@ -963,7 +1000,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto keep_locked;
 
 			/* Case 2 above */
-			} else if (global_reclaim(sc) ||
+			} else if (sane_reclaim(sc) ||
 			    !PageReclaim(page) || !may_enter_fs) {
 				/*
 				 * This is slightly racy - end_page_writeback()
@@ -1409,10 +1446,10 @@ static int too_many_isolated(struct zone *zone, int file,
 {
 	unsigned long inactive, isolated;
 
-	if (current_is_kswapd() || sc->hibernation_mode)
+	if (current_is_kswapd())
 		return 0;
 
-	if (!global_reclaim(sc))
+	if (!sane_reclaim(sc))
 		return 0;
 
 	if (file) {
@@ -1604,10 +1641,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		set_bit(ZONE_WRITEBACK, &zone->flags);
 
 	/*
-	 * memcg will stall in page writeback so only consider forcibly
-	 * stalling for global reclaim
+	 * Legacy memcg will stall in page writeback so avoid forcibly
+	 * stalling here.
 	 */
-	if (global_reclaim(sc)) {
+	if (sane_reclaim(sc)) {
 		/*
 		 * Tag a zone as congested if all the dirty pages scanned were
 		 * backed by a congested BDI and wait_iff_congested will stall.
@@ -2258,9 +2295,6 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	unsigned long pages_for_compaction;
 	unsigned long inactive_lru_pages;
 
-	if (nr_reclaimed && nr_scanned && sc->nr_to_reclaim >= sc->nr_reclaimed)
-		return true;
-
 	/* If not in reclaim/compaction mode, stop */
 	if (!in_reclaim_compaction(sc))
 		return false;
@@ -2571,12 +2605,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	unsigned long total_scanned = 0;
 	unsigned long writeback_threshold;
 	bool zones_reclaimable;
-
-#ifdef CONFIG_FREEZER
-	if (unlikely(pm_freezing && !sc->hibernation_mode))
-		return 0;
-#endif
-
 retry:
 	delayacct_freepages_start();
 
@@ -2651,7 +2679,8 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
-		if (!populated_zone(zone))
+		if (!populated_zone(zone) ||
+		    zone_reclaimable_pages(zone) == 0)
 			continue;
 
 		pfmemalloc_reserve += min_wmark_pages(zone);
@@ -3459,11 +3488,6 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	if (!populated_zone(zone))
 		return;
 
-#ifdef CONFIG_FREEZER
-	if (pm_freezing)
-		return;
-#endif
-
 	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
 		return;
 	pgdat = zone->zone_pgdat;
@@ -3489,7 +3513,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
  * LRU order by reclaiming preferentially
  * inactive > active > active referenced > active mapped
  */
-unsigned long shrink_memory_mask(unsigned long nr_to_reclaim, gfp_t mask)
+unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 {
 	struct reclaim_state reclaim_state;
 	struct scan_control sc = {
@@ -3518,11 +3542,6 @@ unsigned long shrink_memory_mask(unsigned long nr_to_reclaim, gfp_t mask)
 
 	return nr_reclaimed;
 }
-
-unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
-{
-	return shrink_memory_mask(nr_to_reclaim, GFP_HIGHUSER_MOVABLE);
-}
 #endif /* CONFIG_HIBERNATION */
 
 /* It's optimal to keep kswapds on the same CPUs as their memory, but
@@ -3611,7 +3630,7 @@ int zone_reclaim_mode __read_mostly;
 #define RECLAIM_OFF 0
 #define RECLAIM_ZONE (1<<0)	/* Run shrink_inactive_list on the zone */
 #define RECLAIM_WRITE (1<<1)	/* Writeout pages during reclaim */
-#define RECLAIM_SWAP (1<<2)	/* Swap pages out during reclaim */
+#define RECLAIM_UNMAP (1<<2)	/* Unmap pages during reclaim */
 
 /*
  * Priority for ZONE_RECLAIM. This determines the fraction of pages
@@ -3653,12 +3672,12 @@ static long zone_pagecache_reclaimable(struct zone *zone)
 	long delta = 0;
 
 	/*
-	 * If RECLAIM_SWAP is set, then all file pages are considered
+	 * If RECLAIM_UNMAP is set, then all file pages are considered
 	 * potentially reclaimable. Otherwise, we have to worry about
 	 * pages like swapcache and zone_unmapped_file_pages() provides
 	 * a better estimate
 	 */
-	if (zone_reclaim_mode & RECLAIM_SWAP)
+	if (zone_reclaim_mode & RECLAIM_UNMAP)
 		nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES);
 	else
 		nr_pagecache_reclaimable = zone_unmapped_file_pages(zone);
@@ -3689,15 +3708,15 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.order = order,
 		.priority = ZONE_RECLAIM_PRIORITY,
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
-		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+		.may_unmap = !!(zone_reclaim_mode & RECLAIM_UNMAP),
 		.may_swap = 1,
 	};
 
 	cond_resched();
 	/*
-	 * We need to be able to allocate from the reserves for RECLAIM_SWAP
+	 * We need to be able to allocate from the reserves for RECLAIM_UNMAP
 	 * and we also need to be able to write out pages for RECLAIM_WRITE
-	 * and RECLAIM_SWAP.
+	 * and RECLAIM_UNMAP.
 	 */
 	p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
 	lockdep_set_current_reclaim_state(gfp_mask);