btrfs: introduce BTRFS_NESTING_COW for cow'ing blocks

When we COW a block we are holding a lock on the original block, and
then we lock the new COW block.  Because our lockdep maps are based on
root + level, this will make lockdep complain.  We need a way to
indicate a subclass for locking the COW'ed block, so plumb through our
btrfs_lock_nesting from btrfs_cow_block down to the btrfs_init_buffer,
and then introduce BTRFS_NESTING_COW to be used for cow'ing blocks.

The reason I've added all this extra infrastructure is because there
will be need of different nesting classes in follow up patches.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

8 files changed, 66 insertions, 36 deletions

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 71e3fa30082c..48178fd8740f 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -198,7 +198,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 		btrfs_node_key(buf, &disk_key, 0);
 
 	cow = btrfs_alloc_tree_block(trans, root, 0, new_root_objectid,
-			&disk_key, level, buf->start, 0);
+			&disk_key, level, buf->start, 0, BTRFS_NESTING_NORMAL);
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
@@ -957,7 +957,8 @@ static struct extent_buffer *alloc_tree_block_no_bg_flush(
 					  const struct btrfs_disk_key *disk_key,
 					  int level,
 					  u64 hint,
-					  u64 empty_size)
+					  u64 empty_size,
+					  enum btrfs_lock_nesting nest)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *ret;
@@ -986,7 +987,7 @@ static struct extent_buffer *alloc_tree_block_no_bg_flush(
 
 	ret = btrfs_alloc_tree_block(trans, root, parent_start,
 				     root->root_key.objectid, disk_key, level,
-				     hint, empty_size);
+				     hint, empty_size, nest);
 	trans->can_flush_pending_bgs = true;
 
 	return ret;
@@ -1009,7 +1010,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 			     struct extent_buffer *buf,
 			     struct extent_buffer *parent, int parent_slot,
 			     struct extent_buffer **cow_ret,
-			     u64 search_start, u64 empty_size)
+			     u64 search_start, u64 empty_size,
+			     enum btrfs_lock_nesting nest)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_disk_key disk_key;
@@ -1040,7 +1042,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		parent_start = parent->start;
 
 	cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key,
-					   level, search_start, empty_size);
+					   level, search_start, empty_size, nest);
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
@@ -1446,7 +1448,8 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
 noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		    struct btrfs_root *root, struct extent_buffer *buf,
 		    struct extent_buffer *parent, int parent_slot,
-		    struct extent_buffer **cow_ret)
+		    struct extent_buffer **cow_ret,
+		    enum btrfs_lock_nesting nest)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 search_start;
@@ -1485,7 +1488,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 	 */
 	btrfs_qgroup_trace_subtree_after_cow(trans, root, buf);
 	ret = __btrfs_cow_block(trans, root, buf, parent,
-				 parent_slot, cow_ret, search_start, 0);
+				 parent_slot, cow_ret, search_start, 0, nest);
 
 	trace_btrfs_cow_block(root, buf, *cow_ret);
 
@@ -1657,7 +1660,8 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 		err = __btrfs_cow_block(trans, root, cur, parent, i,
 					&cur, search_start,
 					min(16 * blocksize,
-					    (end_slot - i) * blocksize));
+					    (end_slot - i) * blocksize),
+					BTRFS_NESTING_COW);
 		if (err) {
 			btrfs_tree_unlock(cur);
 			free_extent_buffer(cur);
@@ -1855,7 +1859,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 		btrfs_tree_lock(child);
 		btrfs_set_lock_blocking_write(child);
-		ret = btrfs_cow_block(trans, root, child, mid, 0, &child);
+		ret = btrfs_cow_block(trans, root, child, mid, 0, &child,
+				      BTRFS_NESTING_COW);
 		if (ret) {
 			btrfs_tree_unlock(child);
 			free_extent_buffer(child);
@@ -1894,7 +1899,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		btrfs_tree_lock(left);
 		btrfs_set_lock_blocking_write(left);
 		wret = btrfs_cow_block(trans, root, left,
-				       parent, pslot - 1, &left);
+				       parent, pslot - 1, &left,
+				       BTRFS_NESTING_COW);
 		if (wret) {
 			ret = wret;
 			goto enospc;
@@ -1909,7 +1915,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		btrfs_tree_lock(right);
 		btrfs_set_lock_blocking_write(right);
 		wret = btrfs_cow_block(trans, root, right,
-				       parent, pslot + 1, &right);
+				       parent, pslot + 1, &right,
+				       BTRFS_NESTING_COW);
 		if (wret) {
 			ret = wret;
 			goto enospc;
@@ -2077,7 +2084,8 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
 			wret = 1;
 		} else {
 			ret = btrfs_cow_block(trans, root, left, parent,
-					      pslot - 1, &left);
+					      pslot - 1, &left,
+					      BTRFS_NESTING_COW);
 			if (ret)
 				wret = 1;
 			else {
@@ -2132,7 +2140,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
 		} else {
 			ret = btrfs_cow_block(trans, root, right,
 					      parent, pslot + 1,
-					      &right);
+					      &right, BTRFS_NESTING_COW);
 			if (ret)
 				wret = 1;
 			else {
@@ -2740,11 +2748,13 @@ again:
 			btrfs_set_path_blocking(p);
 			if (last_level)
 				err = btrfs_cow_block(trans, root, b, NULL, 0,
-						      &b);
+						      &b,
+						      BTRFS_NESTING_COW);
 			else
 				err = btrfs_cow_block(trans, root, b,
 						      p->nodes[level + 1],
-						      p->slots[level + 1], &b);
+						      p->slots[level + 1], &b,
+						      BTRFS_NESTING_COW);
 			if (err) {
 				ret = err;
 				goto done;
@@ -3396,7 +3406,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 		btrfs_node_key(lower, &lower_key, 0);
 
 	c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level,
-					 root->node->start, 0);
+					 root->node->start, 0,
+					 BTRFS_NESTING_NORMAL);
 	if (IS_ERR(c))
 		return PTR_ERR(c);
 
@@ -3526,7 +3537,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 	btrfs_node_key(c, &disk_key, mid);
 
 	split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level,
-					     c->start, 0);
+					     c->start, 0, BTRFS_NESTING_NORMAL);
 	if (IS_ERR(split))
 		return PTR_ERR(split);
 
@@ -3804,7 +3815,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
 
 	/* cow and double check */
 	ret = btrfs_cow_block(trans, root, right, upper,
-			      slot + 1, &right);
+			      slot + 1, &right, BTRFS_NESTING_COW);
 	if (ret)
 		goto out_unlock;
 
@@ -4045,7 +4056,8 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
 
 	/* cow and double check */
 	ret = btrfs_cow_block(trans, root, left,
-			      path->nodes[1], slot - 1, &left);
+			      path->nodes[1], slot - 1, &left,
+			      BTRFS_NESTING_COW);
 	if (ret) {
 		/* we hit -ENOSPC, but it isn't fatal here */
 		if (ret == -ENOSPC)
@@ -4312,7 +4324,7 @@ again:
 		btrfs_item_key(l, &disk_key, mid);
 
 	right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0,
-					     l->start, 0);
+					     l->start, 0, BTRFS_NESTING_NORMAL);
 	if (IS_ERR(right))
 		return PTR_ERR(right);
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 1339e390a757..b4d3a4d82053 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2526,7 +2526,8 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 					     u64 parent, u64 root_objectid,
 					     const struct btrfs_disk_key *key,
 					     int level, u64 hint,
-					     u64 empty_size);
+					     u64 empty_size,
+					     enum btrfs_lock_nesting nest);
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct extent_buffer *buf,
@@ -2667,7 +2668,8 @@ struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent,
 int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		    struct btrfs_root *root, struct extent_buffer *buf,
 		    struct extent_buffer *parent, int parent_slot,
-		    struct extent_buffer **cow_ret);
+		    struct extent_buffer **cow_ret,
+		    enum btrfs_lock_nesting nest);
 int btrfs_copy_root(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root,
 		      struct extent_buffer *buf,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4eb56f00ee81..ed887242f348 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1205,7 +1205,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
 	root->root_key.offset = 0;
 
-	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
+	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0,
+				      BTRFS_NESTING_NORMAL);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
 		leaf = NULL;
@@ -1277,7 +1278,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	 */
 
 	leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
-			NULL, 0, 0, 0);
+			NULL, 0, 0, 0, BTRFS_NESTING_NORMAL);
 	if (IS_ERR(leaf)) {
 		btrfs_put_root(root);
 		return ERR_CAST(leaf);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 7b61b7b5122f..3b21fee13e77 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4656,7 +4656,8 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 
 static struct extent_buffer *
 btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		      u64 bytenr, int level, u64 owner)
+		      u64 bytenr, int level, u64 owner,
+		      enum btrfs_lock_nesting nest)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *buf;
@@ -4679,7 +4680,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	}
 
 	btrfs_set_buffer_lockdep_class(owner, buf, level);
-	btrfs_tree_lock(buf);
+	__btrfs_tree_lock(buf, nest);
 	btrfs_clean_tree_block(buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
 
@@ -4725,7 +4726,8 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 					     u64 parent, u64 root_objectid,
 					     const struct btrfs_disk_key *key,
 					     int level, u64 hint,
-					     u64 empty_size)
+					     u64 empty_size,
+					     enum btrfs_lock_nesting nest)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_key ins;
@@ -4741,7 +4743,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	if (btrfs_is_testing(fs_info)) {
 		buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr,
-					    level, root_objectid);
+					    level, root_objectid, nest);
 		if (!IS_ERR(buf))
 			root->alloc_bytenr += blocksize;
 		return buf;
@@ -4758,7 +4760,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		goto out_unuse;
 
 	buf = btrfs_init_new_buffer(trans, root, ins.objectid, level,
-				    root_objectid);
+				    root_objectid, nest);
 	if (IS_ERR(buf)) {
 		ret = PTR_ERR(buf);
 		goto out_free_reserved;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 3779a6c12184..b91444e810a5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -628,7 +628,8 @@ static noinline int create_subvol(struct inode *dir,
 	if (ret)
 		goto fail;
 
-	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
+	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0,
+				      BTRFS_NESTING_NORMAL);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
 		goto fail;
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index 5fabda8f0a80..8b47ba34fb03 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -25,6 +25,14 @@ enum btrfs_lock_nesting {
 	BTRFS_NESTING_NORMAL,
 
 	/*
+	 * When we COW a block we are holding the lock on the original block,
+	 * and since our lockdep maps are rootid+level, this confuses lockdep
+	 * when we lock the newly allocated COW'd block.  Handle this by having
+	 * a subclass for COW'ed blocks so that lockdep doesn't complain.
+	 */
+	BTRFS_NESTING_COW,
+
+	/*
 	 * We are limited to MAX_LOCKDEP_SUBLCLASSES number of subclasses, so
 	 * add this in here and add a static_assert to keep us from going over
 	 * the limit.  As of this writing we're limited to 8, and we're
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 4ba1ab9cc76d..3602806d71bd 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1206,7 +1206,8 @@ again:
 	}
 
 	if (cow) {
-		ret = btrfs_cow_block(trans, dest, eb, NULL, 0, &eb);
+		ret = btrfs_cow_block(trans, dest, eb, NULL, 0, &eb,
+				      BTRFS_NESTING_COW);
 		BUG_ON(ret);
 	}
 	btrfs_set_lock_blocking_write(eb);
@@ -1274,7 +1275,8 @@ again:
 			btrfs_tree_lock(eb);
 			if (cow) {
 				ret = btrfs_cow_block(trans, dest, eb, parent,
-						      slot, &eb);
+						      slot, &eb,
+						      BTRFS_NESTING_COW);
 				BUG_ON(ret);
 			}
 			btrfs_set_lock_blocking_write(eb);
@@ -1781,7 +1783,8 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 	 * relocated and the block is tree root.
 	 */
 	leaf = btrfs_lock_root_node(root);
-	ret = btrfs_cow_block(trans, root, leaf, NULL, 0, &leaf);
+	ret = btrfs_cow_block(trans, root, leaf, NULL, 0, &leaf,
+			      BTRFS_NESTING_COW);
 	btrfs_tree_unlock(leaf);
 	free_extent_buffer(leaf);
 	if (ret < 0)
@@ -2308,7 +2311,7 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 
 		if (!node->eb) {
 			ret = btrfs_cow_block(trans, root, eb, upper->eb,
-					      slot, &eb);
+					      slot, &eb, BTRFS_NESTING_COW);
 			btrfs_tree_unlock(eb);
 			free_extent_buffer(eb);
 			if (ret < 0) {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index f8265dbec9c3..52ada47aff50 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1184,7 +1184,7 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans)
 
 	eb = btrfs_lock_root_node(fs_info->tree_root);
 	ret = btrfs_cow_block(trans, fs_info->tree_root, eb, NULL,
-			      0, &eb);
+			      0, &eb, BTRFS_NESTING_COW);
 	btrfs_tree_unlock(eb);
 	free_extent_buffer(eb);
 
@@ -1589,7 +1589,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_set_root_otransid(new_root_item, trans->transid);
 
 	old = btrfs_lock_root_node(root);
-	ret = btrfs_cow_block(trans, root, old, NULL, 0, &old);
+	ret = btrfs_cow_block(trans, root, old, NULL, 0, &old,
+			      BTRFS_NESTING_COW);
 	if (ret) {
 		btrfs_tree_unlock(old);
 		free_extent_buffer(old);