1 files changed, 129 insertions, 78 deletions

diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 595abb9e7d74..9b5b8951afb4 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -144,9 +144,11 @@
 static struct kmem_cache *ext4_es_cachep;
 static struct kmem_cache *ext4_pending_cachep;
 
-static int __es_insert_extent(struct inode *inode, struct extent_status *newes);
+static int __es_insert_extent(struct inode *inode, struct extent_status *newes,
+			      struct extent_status *prealloc);
 static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
-			      ext4_lblk_t end, int *reserved);
+			      ext4_lblk_t end, int *reserved,
+			      struct extent_status *prealloc);
 static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan);
 static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
 		       struct ext4_inode_info *locked_ei);
@@ -446,22 +448,36 @@ static void ext4_es_list_del(struct inode *inode)
 	spin_unlock(&sbi->s_es_lock);
 }
 
-static struct extent_status *
-ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
-		     ext4_fsblk_t pblk)
+/*
+ * Returns true if we cannot fail to allocate memory for this extent_status
+ * entry and cannot reclaim it until its status changes.
+ */
+static inline bool ext4_es_must_keep(struct extent_status *es)
+{
+	/* fiemap, bigalloc, and seek_data/hole need to use it. */
+	if (ext4_es_is_delayed(es))
+		return true;
+
+	return false;
+}
+
+static inline struct extent_status *__es_alloc_extent(bool nofail)
+{
+	if (!nofail)
+		return kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC);
+
+	return kmem_cache_zalloc(ext4_es_cachep, GFP_KERNEL | __GFP_NOFAIL);
+}
+
+static void ext4_es_init_extent(struct inode *inode, struct extent_status *es,
+		ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk)
 {
-	struct extent_status *es;
-	es = kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC);
-	if (es == NULL)
-		return NULL;
 	es->es_lblk = lblk;
 	es->es_len = len;
 	es->es_pblk = pblk;
 
-	/*
-	 * We don't count delayed extent because we never try to reclaim them
-	 */
-	if (!ext4_es_is_delayed(es)) {
+	/* We never try to reclaim a must kept extent, so we don't count it. */
+	if (!ext4_es_must_keep(es)) {
 		if (!EXT4_I(inode)->i_es_shk_nr++)
 			ext4_es_list_add(inode);
 		percpu_counter_inc(&EXT4_SB(inode->i_sb)->
@@ -470,8 +486,11 @@ ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
 
 	EXT4_I(inode)->i_es_all_nr++;
 	percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
+}
 
-	return es;
+static inline void __es_free_extent(struct extent_status *es)
+{
+	kmem_cache_free(ext4_es_cachep, es);
 }
 
 static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
@@ -479,8 +498,8 @@ static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
 	EXT4_I(inode)->i_es_all_nr--;
 	percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
 
-	/* Decrease the shrink counter when this es is not delayed */
-	if (!ext4_es_is_delayed(es)) {
+	/* Decrease the shrink counter when we can reclaim the extent. */
+	if (!ext4_es_must_keep(es)) {
 		BUG_ON(EXT4_I(inode)->i_es_shk_nr == 0);
 		if (!--EXT4_I(inode)->i_es_shk_nr)
 			ext4_es_list_del(inode);
@@ -488,7 +507,7 @@ static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
 					s_es_stats.es_stats_shk_cnt);
 	}
 
-	kmem_cache_free(ext4_es_cachep, es);
+	__es_free_extent(es);
 }
 
 /*
@@ -749,7 +768,8 @@ static inline void ext4_es_insert_extent_check(struct inode *inode,
 }
 #endif
 
-static int __es_insert_extent(struct inode *inode, struct extent_status *newes)
+static int __es_insert_extent(struct inode *inode, struct extent_status *newes,
+			      struct extent_status *prealloc)
 {
 	struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
 	struct rb_node **p = &tree->root.rb_node;
@@ -789,10 +809,15 @@ static int __es_insert_extent(struct inode *inode, struct extent_status *newes)
 		}
 	}
 
-	es = ext4_es_alloc_extent(inode, newes->es_lblk, newes->es_len,
-				  newes->es_pblk);
+	if (prealloc)
+		es = prealloc;
+	else
+		es = __es_alloc_extent(false);
 	if (!es)
 		return -ENOMEM;
+	ext4_es_init_extent(inode, es, newes->es_lblk, newes->es_len,
+			    newes->es_pblk);
+
 	rb_link_node(&es->rb_node, parent, p);
 	rb_insert_color(&es->rb_node, &tree->root);
 
@@ -804,26 +829,27 @@ out:
 /*
  * ext4_es_insert_extent() adds information to an inode's extent
  * status tree.
- *
- * Return 0 on success, error code on failure.
  */
-int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
-			  ext4_lblk_t len, ext4_fsblk_t pblk,
-			  unsigned int status)
+void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
+			   ext4_lblk_t len, ext4_fsblk_t pblk,
+			   unsigned int status)
 {
 	struct extent_status newes;
 	ext4_lblk_t end = lblk + len - 1;
-	int err = 0;
+	int err1 = 0;
+	int err2 = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	struct extent_status *es1 = NULL;
+	struct extent_status *es2 = NULL;
 
 	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
-		return 0;
+		return;
 
 	es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n",
 		 lblk, len, pblk, status, inode->i_ino);
 
 	if (!len)
-		return 0;
+		return;
 
 	BUG_ON(end < lblk);
 
@@ -842,29 +868,40 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 
 	ext4_es_insert_extent_check(inode, &newes);
 
+retry:
+	if (err1 && !es1)
+		es1 = __es_alloc_extent(true);
+	if ((err1 || err2) && !es2)
+		es2 = __es_alloc_extent(true);
 	write_lock(&EXT4_I(inode)->i_es_lock);
-	err = __es_remove_extent(inode, lblk, end, NULL);
-	if (err != 0)
+
+	err1 = __es_remove_extent(inode, lblk, end, NULL, es1);
+	if (err1 != 0)
+		goto error;
+
+	err2 = __es_insert_extent(inode, &newes, es2);
+	if (err2 == -ENOMEM && !ext4_es_must_keep(&newes))
+		err2 = 0;
+	if (err2 != 0)
 		goto error;
-retry:
-	err = __es_insert_extent(inode, &newes);
-	if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb),
-					  128, EXT4_I(inode)))
-		goto retry;
-	if (err == -ENOMEM && !ext4_es_is_delayed(&newes))
-		err = 0;
 
 	if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) &&
 	    (status & EXTENT_STATUS_WRITTEN ||
 	     status & EXTENT_STATUS_UNWRITTEN))
 		__revise_pending(inode, lblk, len);
 
+	/* es is pre-allocated but not used, free it. */
+	if (es1 && !es1->es_len)
+		__es_free_extent(es1);
+	if (es2 && !es2->es_len)
+		__es_free_extent(es2);
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
+	if (err1 || err2)
+		goto retry;
 
 	ext4_es_print_tree(inode);
-
-	return err;
+	return;
 }
 
 /*
@@ -897,7 +934,7 @@ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
 
 	es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk);
 	if (!es || es->es_lblk > end)
-		__es_insert_extent(inode, &newes);
+		__es_insert_extent(inode, &newes, NULL);
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 }
 
@@ -1287,6 +1324,7 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
  * @lblk - first block in range
  * @end - last block in range
  * @reserved - number of cluster reservations released
+ * @prealloc - pre-allocated es to avoid memory allocation failures
  *
  * If @reserved is not NULL and delayed allocation is enabled, counts
  * block/cluster reservations freed by removing range and if bigalloc
@@ -1294,7 +1332,8 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
  * error code on failure.
  */
 static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
-			      ext4_lblk_t end, int *reserved)
+			      ext4_lblk_t end, int *reserved,
+			      struct extent_status *prealloc)
 {
 	struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
 	struct rb_node *node;
@@ -1302,14 +1341,12 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 	struct extent_status orig_es;
 	ext4_lblk_t len1, len2;
 	ext4_fsblk_t block;
-	int err;
+	int err = 0;
 	bool count_reserved = true;
 	struct rsvd_count rc;
 
 	if (reserved == NULL || !test_opt(inode->i_sb, DELALLOC))
 		count_reserved = false;
-retry:
-	err = 0;
 
 	es = __es_tree_search(&tree->root, lblk);
 	if (!es)
@@ -1343,14 +1380,13 @@ retry:
 					orig_es.es_len - len2;
 			ext4_es_store_pblock_status(&newes, block,
 						    ext4_es_status(&orig_es));
-			err = __es_insert_extent(inode, &newes);
+			err = __es_insert_extent(inode, &newes, prealloc);
 			if (err) {
+				if (!ext4_es_must_keep(&newes))
+					return 0;
+
 				es->es_lblk = orig_es.es_lblk;
 				es->es_len = orig_es.es_len;
-				if ((err == -ENOMEM) &&
-				    __es_shrink(EXT4_SB(inode->i_sb),
-							128, EXT4_I(inode)))
-					goto retry;
 				goto out;
 			}
 		} else {
@@ -1422,39 +1458,48 @@ out:
  * @len - number of blocks to remove
  *
  * Reduces block/cluster reservation count and for bigalloc cancels pending
- * reservations as needed. Returns 0 on success, error code on failure.
+ * reservations as needed.
  */
-int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
-			  ext4_lblk_t len)
+void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
+			   ext4_lblk_t len)
 {
 	ext4_lblk_t end;
 	int err = 0;
 	int reserved = 0;
+	struct extent_status *es = NULL;
 
 	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
-		return 0;
+		return;
 
 	trace_ext4_es_remove_extent(inode, lblk, len);
 	es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
 		 lblk, len, inode->i_ino);
 
 	if (!len)
-		return err;
+		return;
 
 	end = lblk + len - 1;
 	BUG_ON(end < lblk);
 
+retry:
+	if (err && !es)
+		es = __es_alloc_extent(true);
 	/*
 	 * ext4_clear_inode() depends on us taking i_es_lock unconditionally
 	 * so that we are sure __es_shrink() is done with the inode before it
 	 * is reclaimed.
 	 */
 	write_lock(&EXT4_I(inode)->i_es_lock);
-	err = __es_remove_extent(inode, lblk, end, &reserved);
+	err = __es_remove_extent(inode, lblk, end, &reserved, es);
+	if (es && !es->es_len)
+		__es_free_extent(es);
 	write_unlock(&EXT4_I(inode)->i_es_lock);
+	if (err)
+		goto retry;
+
 	ext4_es_print_tree(inode);
 	ext4_da_release_space(inode, reserved);
-	return err;
+	return;
 }
 
 static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
@@ -1702,11 +1747,8 @@ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end,
 
 		(*nr_to_scan)--;
 		node = rb_next(&es->rb_node);
-		/*
-		 * We can't reclaim delayed extent from status tree because
-		 * fiemap, bigallic, and seek_data/hole need to use it.
-		 */
-		if (ext4_es_is_delayed(es))
+
+		if (ext4_es_must_keep(es))
 			goto next;
 		if (ext4_es_is_referenced(es)) {
 			ext4_es_clear_referenced(es);
@@ -1770,7 +1812,7 @@ void ext4_clear_inode_es(struct inode *inode)
 	while (node) {
 		es = rb_entry(node, struct extent_status, rb_node);
 		node = rb_next(node);
-		if (!ext4_es_is_delayed(es)) {
+		if (!ext4_es_must_keep(es)) {
 			rb_erase(&es->rb_node, &tree->root);
 			ext4_es_free_extent(inode, es);
 		}
@@ -1972,17 +2014,18 @@ bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk)
  * @lblk - logical block to be added
  * @allocated - indicates whether a physical cluster has been allocated for
  *              the logical cluster that contains the block
- *
- * Returns 0 on success, negative error code on failure.
  */
-int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
-				 bool allocated)
+void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
+				  bool allocated)
 {
 	struct extent_status newes;
-	int err = 0;
+	int err1 = 0;
+	int err2 = 0;
+	struct extent_status *es1 = NULL;
+	struct extent_status *es2 = NULL;
 
 	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
-		return 0;
+		return;
 
 	es_debug("add [%u/1) delayed to extent status tree of inode %lu\n",
 		 lblk, inode->i_ino);
@@ -1994,29 +2037,37 @@ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
 
 	ext4_es_insert_extent_check(inode, &newes);
 
+retry:
+	if (err1 && !es1)
+		es1 = __es_alloc_extent(true);
+	if ((err1 || err2) && !es2)
+		es2 = __es_alloc_extent(true);
 	write_lock(&EXT4_I(inode)->i_es_lock);
 
-	err = __es_remove_extent(inode, lblk, lblk, NULL);
-	if (err != 0)
+	err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1);
+	if (err1 != 0)
 		goto error;
-retry:
-	err = __es_insert_extent(inode, &newes);
-	if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb),
-					  128, EXT4_I(inode)))
-		goto retry;
-	if (err != 0)
+
+	err2 = __es_insert_extent(inode, &newes, es2);
+	if (err2 != 0)
 		goto error;
 
 	if (allocated)
 		__insert_pending(inode, lblk);
 
+	/* es is pre-allocated but not used, free it. */
+	if (es1 && !es1->es_len)
+		__es_free_extent(es1);
+	if (es2 && !es2->es_len)
+		__es_free_extent(es2);
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
+	if (err1 || err2)
+		goto retry;
 
 	ext4_es_print_tree(inode);
 	ext4_print_pending_tree(inode);
-
-	return err;
+	return;
 }
 
 /*