1 files changed, 149 insertions, 121 deletions

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2cc2972eedaf..d954b71c4f9c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -204,8 +204,16 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 
 #ifdef CONFIG_THP_SWAP
 #define SWAPFILE_CLUSTER	HPAGE_PMD_NR
+
+#define swap_entry_size(size)	(size)
 #else
 #define SWAPFILE_CLUSTER	256
+
+/*
+ * Define swap_entry_size() as constant to let compiler to optimize
+ * out some code if !CONFIG_THP_SWAP
+ */
+#define swap_entry_size(size)	1
 #endif
 #define LATENCY_LIMIT		256
 
@@ -269,7 +277,9 @@ static inline void cluster_set_null(struct swap_cluster_info *info)
 
 static inline bool cluster_is_huge(struct swap_cluster_info *info)
 {
-	return info->flags & CLUSTER_FLAG_HUGE;
+	if (IS_ENABLED(CONFIG_THP_SWAP))
+		return info->flags & CLUSTER_FLAG_HUGE;
+	return false;
 }
 
 static inline void cluster_clear_huge(struct swap_cluster_info *info)
@@ -296,13 +306,18 @@ static inline void unlock_cluster(struct swap_cluster_info *ci)
 		spin_unlock(&ci->lock);
 }
 
+/*
+ * Determine the locking method in use for this device.  Return
+ * swap_cluster_info if SSD-style cluster-based locking is in place.
+ */
 static inline struct swap_cluster_info *lock_cluster_or_swap_info(
-	struct swap_info_struct *si,
-	unsigned long offset)
+		struct swap_info_struct *si, unsigned long offset)
 {
 	struct swap_cluster_info *ci;
 
+	/* Try to use fine-grained SSD-style locking if available: */
 	ci = lock_cluster(si, offset);
+	/* Otherwise, fall back to traditional, coarse locking: */
 	if (!ci)
 		spin_lock(&si->lock);
 
@@ -863,7 +878,6 @@ no_page:
 	return n_ret;
 }
 
-#ifdef CONFIG_THP_SWAP
 static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
 {
 	unsigned long idx;
@@ -871,6 +885,15 @@ static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
 	unsigned long offset, i;
 	unsigned char *map;
 
+	/*
+	 * Should not even be attempting cluster allocations when huge
+	 * page swap is disabled.  Warn and fail the allocation.
+	 */
+	if (!IS_ENABLED(CONFIG_THP_SWAP)) {
+		VM_WARN_ON_ONCE(1);
+		return 0;
+	}
+
 	if (cluster_list_empty(&si->free_clusters))
 		return 0;
 
@@ -901,13 +924,6 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
 	unlock_cluster(ci);
 	swap_range_free(si, offset, SWAPFILE_CLUSTER);
 }
-#else
-static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
-{
-	VM_WARN_ON_ONCE(1);
-	return 0;
-}
-#endif /* CONFIG_THP_SWAP */
 
 static unsigned long scan_swap_map(struct swap_info_struct *si,
 				   unsigned char usage)
@@ -924,18 +940,18 @@ static unsigned long scan_swap_map(struct swap_info_struct *si,
 
 }
 
-int get_swap_pages(int n_goal, bool cluster, swp_entry_t swp_entries[])
+int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
 {
-	unsigned long nr_pages = cluster ? SWAPFILE_CLUSTER : 1;
+	unsigned long size = swap_entry_size(entry_size);
 	struct swap_info_struct *si, *next;
 	long avail_pgs;
 	int n_ret = 0;
 	int node;
 
 	/* Only single cluster request supported */
-	WARN_ON_ONCE(n_goal > 1 && cluster);
+	WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
 
-	avail_pgs = atomic_long_read(&nr_swap_pages) / nr_pages;
+	avail_pgs = atomic_long_read(&nr_swap_pages) / size;
 	if (avail_pgs <= 0)
 		goto noswap;
 
@@ -945,7 +961,7 @@ int get_swap_pages(int n_goal, bool cluster, swp_entry_t swp_entries[])
 	if (n_goal > avail_pgs)
 		n_goal = avail_pgs;
 
-	atomic_long_sub(n_goal * nr_pages, &nr_swap_pages);
+	atomic_long_sub(n_goal * size, &nr_swap_pages);
 
 	spin_lock(&swap_avail_lock);
 
@@ -972,14 +988,14 @@ start_over:
 			spin_unlock(&si->lock);
 			goto nextsi;
 		}
-		if (cluster) {
+		if (size == SWAPFILE_CLUSTER) {
 			if (!(si->flags & SWP_FILE))
 				n_ret = swap_alloc_cluster(si, swp_entries);
 		} else
 			n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
 						    n_goal, swp_entries);
 		spin_unlock(&si->lock);
-		if (n_ret || cluster)
+		if (n_ret || size == SWAPFILE_CLUSTER)
 			goto check_out;
 		pr_debug("scan_swap_map of si %d failed to find offset\n",
 			si->type);
@@ -1005,7 +1021,7 @@ nextsi:
 
 check_out:
 	if (n_ret < n_goal)
-		atomic_long_add((long)(n_goal - n_ret) * nr_pages,
+		atomic_long_add((long)(n_goal - n_ret) * size,
 				&nr_swap_pages);
 noswap:
 	return n_ret;
@@ -1107,16 +1123,13 @@ static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry,
 	return p;
 }
 
-static unsigned char __swap_entry_free(struct swap_info_struct *p,
-				       swp_entry_t entry, unsigned char usage)
+static unsigned char __swap_entry_free_locked(struct swap_info_struct *p,
+					      unsigned long offset,
+					      unsigned char usage)
 {
-	struct swap_cluster_info *ci;
-	unsigned long offset = swp_offset(entry);
 	unsigned char count;
 	unsigned char has_cache;
 
-	ci = lock_cluster_or_swap_info(p, offset);
-
 	count = p->swap_map[offset];
 
 	has_cache = count & SWAP_HAS_CACHE;
@@ -1144,6 +1157,17 @@ static unsigned char __swap_entry_free(struct swap_info_struct *p,
 	usage = count | has_cache;
 	p->swap_map[offset] = usage ? : SWAP_HAS_CACHE;
 
+	return usage;
+}
+
+static unsigned char __swap_entry_free(struct swap_info_struct *p,
+				       swp_entry_t entry, unsigned char usage)
+{
+	struct swap_cluster_info *ci;
+	unsigned long offset = swp_offset(entry);
+
+	ci = lock_cluster_or_swap_info(p, offset);
+	usage = __swap_entry_free_locked(p, offset, usage);
 	unlock_cluster_or_swap_info(p, ci);
 
 	return usage;
@@ -1184,19 +1208,7 @@ void swap_free(swp_entry_t entry)
 /*
  * Called after dropping swapcache to decrease refcnt to swap entries.
  */
-static void swapcache_free(swp_entry_t entry)
-{
-	struct swap_info_struct *p;
-
-	p = _swap_info_get(entry);
-	if (p) {
-		if (!__swap_entry_free(p, entry, SWAP_HAS_CACHE))
-			free_swap_slot(entry);
-	}
-}
-
-#ifdef CONFIG_THP_SWAP
-static void swapcache_free_cluster(swp_entry_t entry)
+void put_swap_page(struct page *page, swp_entry_t entry)
 {
 	unsigned long offset = swp_offset(entry);
 	unsigned long idx = offset / SWAPFILE_CLUSTER;
@@ -1205,42 +1217,48 @@ static void swapcache_free_cluster(swp_entry_t entry)
 	unsigned char *map;
 	unsigned int i, free_entries = 0;
 	unsigned char val;
+	int size = swap_entry_size(hpage_nr_pages(page));
 
 	si = _swap_info_get(entry);
 	if (!si)
 		return;
 
-	ci = lock_cluster(si, offset);
-	VM_BUG_ON(!cluster_is_huge(ci));
-	map = si->swap_map + offset;
-	for (i = 0; i < SWAPFILE_CLUSTER; i++) {
-		val = map[i];
-		VM_BUG_ON(!(val & SWAP_HAS_CACHE));
-		if (val == SWAP_HAS_CACHE)
-			free_entries++;
-	}
-	if (!free_entries) {
-		for (i = 0; i < SWAPFILE_CLUSTER; i++)
-			map[i] &= ~SWAP_HAS_CACHE;
+	ci = lock_cluster_or_swap_info(si, offset);
+	if (size == SWAPFILE_CLUSTER) {
+		VM_BUG_ON(!cluster_is_huge(ci));
+		map = si->swap_map + offset;
+		for (i = 0; i < SWAPFILE_CLUSTER; i++) {
+			val = map[i];
+			VM_BUG_ON(!(val & SWAP_HAS_CACHE));
+			if (val == SWAP_HAS_CACHE)
+				free_entries++;
+		}
+		cluster_clear_huge(ci);
+		if (free_entries == SWAPFILE_CLUSTER) {
+			unlock_cluster_or_swap_info(si, ci);
+			spin_lock(&si->lock);
+			ci = lock_cluster(si, offset);
+			memset(map, 0, SWAPFILE_CLUSTER);
+			unlock_cluster(ci);
+			mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER);
+			swap_free_cluster(si, idx);
+			spin_unlock(&si->lock);
+			return;
+		}
 	}
-	cluster_clear_huge(ci);
-	unlock_cluster(ci);
-	if (free_entries == SWAPFILE_CLUSTER) {
-		spin_lock(&si->lock);
-		ci = lock_cluster(si, offset);
-		memset(map, 0, SWAPFILE_CLUSTER);
-		unlock_cluster(ci);
-		mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER);
-		swap_free_cluster(si, idx);
-		spin_unlock(&si->lock);
-	} else if (free_entries) {
-		for (i = 0; i < SWAPFILE_CLUSTER; i++, entry.val++) {
-			if (!__swap_entry_free(si, entry, SWAP_HAS_CACHE))
-				free_swap_slot(entry);
+	for (i = 0; i < size; i++, entry.val++) {
+		if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) {
+			unlock_cluster_or_swap_info(si, ci);
+			free_swap_slot(entry);
+			if (i == size - 1)
+				return;
+			lock_cluster_or_swap_info(si, offset);
 		}
 	}
+	unlock_cluster_or_swap_info(si, ci);
 }
 
+#ifdef CONFIG_THP_SWAP
 int split_swap_cluster(swp_entry_t entry)
 {
 	struct swap_info_struct *si;
@@ -1255,19 +1273,7 @@ int split_swap_cluster(swp_entry_t entry)
 	unlock_cluster(ci);
 	return 0;
 }
-#else
-static inline void swapcache_free_cluster(swp_entry_t entry)
-{
-}
-#endif /* CONFIG_THP_SWAP */
-
-void put_swap_page(struct page *page, swp_entry_t entry)
-{
-	if (!PageTransHuge(page))
-		swapcache_free(entry);
-	else
-		swapcache_free_cluster(entry);
-}
+#endif
 
 static int swp_entry_cmp(const void *ent1, const void *ent2)
 {
@@ -1409,7 +1415,6 @@ out:
 	return count;
 }
 
-#ifdef CONFIG_THP_SWAP
 static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
 					 swp_entry_t entry)
 {
@@ -1422,12 +1427,12 @@ static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
 
 	ci = lock_cluster_or_swap_info(si, offset);
 	if (!ci || !cluster_is_huge(ci)) {
-		if (map[roffset] != SWAP_HAS_CACHE)
+		if (swap_count(map[roffset]))
 			ret = true;
 		goto unlock_out;
 	}
 	for (i = 0; i < SWAPFILE_CLUSTER; i++) {
-		if (map[offset + i] != SWAP_HAS_CACHE) {
+		if (swap_count(map[offset + i])) {
 			ret = true;
 			break;
 		}
@@ -1442,7 +1447,7 @@ static bool page_swapped(struct page *page)
 	swp_entry_t entry;
 	struct swap_info_struct *si;
 
-	if (likely(!PageTransCompound(page)))
+	if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page)))
 		return page_swapcount(page) != 0;
 
 	page = compound_head(page);
@@ -1466,10 +1471,8 @@ static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount,
 	/* hugetlbfs shouldn't call it */
 	VM_BUG_ON_PAGE(PageHuge(page), page);
 
-	if (likely(!PageTransCompound(page))) {
-		mapcount = atomic_read(&page->_mapcount) + 1;
-		if (total_mapcount)
-			*total_mapcount = mapcount;
+	if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) {
+		mapcount = page_trans_huge_mapcount(page, total_mapcount);
 		if (PageSwapCache(page))
 			swapcount = page_swapcount(page);
 		if (total_swapcount)
@@ -1516,26 +1519,6 @@ static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount,
 
 	return map_swapcount;
 }
-#else
-#define swap_page_trans_huge_swapped(si, entry)	swap_swapcount(si, entry)
-#define page_swapped(page)			(page_swapcount(page) != 0)
-
-static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount,
-					 int *total_swapcount)
-{
-	int mapcount, swapcount = 0;
-
-	/* hugetlbfs shouldn't call it */
-	VM_BUG_ON_PAGE(PageHuge(page), page);
-
-	mapcount = page_trans_huge_mapcount(page, total_mapcount);
-	if (PageSwapCache(page))
-		swapcount = page_swapcount(page);
-	if (total_swapcount)
-		*total_swapcount = swapcount;
-	return mapcount + swapcount;
-}
-#endif
 
 /*
  * We can write to an anon page without COW if there are no other references
@@ -2909,6 +2892,35 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 	return 0;
 }
 
+
+/*
+ * Find out how many pages are allowed for a single swap device. There
+ * are two limiting factors:
+ * 1) the number of bits for the swap offset in the swp_entry_t type, and
+ * 2) the number of bits in the swap pte, as defined by the different
+ * architectures.
+ *
+ * In order to find the largest possible bit mask, a swap entry with
+ * swap type 0 and swap offset ~0UL is created, encoded to a swap pte,
+ * decoded to a swp_entry_t again, and finally the swap offset is
+ * extracted.
+ *
+ * This will mask all the bits from the initial ~0UL mask that can't
+ * be encoded in either the swp_entry_t or the architecture definition
+ * of a swap pte.
+ */
+unsigned long generic_max_swapfile_size(void)
+{
+	return swp_offset(pte_to_swp_entry(
+			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+}
+
+/* Can be overridden by an architecture for additional checks. */
+__weak unsigned long max_swapfile_size(void)
+{
+	return generic_max_swapfile_size();
+}
+
 static unsigned long read_swap_header(struct swap_info_struct *p,
 					union swap_header *swap_header,
 					struct inode *inode)
@@ -2944,22 +2956,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 	p->cluster_next = 1;
 	p->cluster_nr = 0;
 
-	/*
-	 * Find out how many pages are allowed for a single swap
-	 * device. There are two limiting factors: 1) the number
-	 * of bits for the swap offset in the swp_entry_t type, and
-	 * 2) the number of bits in the swap pte as defined by the
-	 * different architectures. In order to find the
-	 * largest possible bit mask, a swap entry with swap type 0
-	 * and swap offset ~0UL is created, encoded to a swap pte,
-	 * decoded to a swp_entry_t again, and finally the swap
-	 * offset is extracted. This will mask all the bits from
-	 * the initial ~0UL mask that can't be encoded in either
-	 * the swp_entry_t or the architecture definition of a
-	 * swap pte.
-	 */
-	maxpages = swp_offset(pte_to_swp_entry(
-			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+	maxpages = max_swapfile_size();
 	last_page = swap_header->info.last_page;
 	if (!last_page) {
 		pr_warn("Empty swap-file\n");
@@ -3731,6 +3728,37 @@ static void free_swap_count_continuations(struct swap_info_struct *si)
 	}
 }
 
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
+				  gfp_t gfp_mask)
+{
+	struct swap_info_struct *si, *next;
+	if (!(gfp_mask & __GFP_IO) || !memcg)
+		return;
+
+	if (!blk_cgroup_congested())
+		return;
+
+	/*
+	 * We've already scheduled a throttle, avoid taking the global swap
+	 * lock.
+	 */
+	if (current->throttle_queue)
+		return;
+
+	spin_lock(&swap_avail_lock);
+	plist_for_each_entry_safe(si, next, &swap_avail_heads[node],
+				  avail_lists[node]) {
+		if (si->bdev) {
+			blkcg_schedule_throttle(bdev_get_queue(si->bdev),
+						true);
+			break;
+		}
+	}
+	spin_unlock(&swap_avail_lock);
+}
+#endif
+
 static int __init swapfile_init(void)
 {
 	int nid;