Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs fixes from Chris Mason:
 "The big ones here are a memory leak we introduced in rc1, and a
  scheduling while atomic if the transid on disk doesn't match the
  transid we expected.  This happens for corrupt blocks, or out of date
  disks.

  It also fixes up the ioctl definition for our ioctl to resolve logical
  inode numbers.  The __u32 was a merging error and doesn't match what
  we ship in the progs."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  Btrfs: avoid sleeping in verify_parent_transid while atomic
  Btrfs: fix crash in scrub repair code when device is missing
  btrfs: Fix mismatching struct members in ioctl.h
  Btrfs: fix page leak when allocing extent buffers
  Btrfs: Add properly locking around add_root_to_dirty_list

Author: torvalds

fs/btrfs/ctree.c

@@ -220,10 +220,12 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
  */
 static void add_root_to_dirty_list(struct btrfs_root *root)
 {
+	spin_lock(&root->fs_info->trans_lock);
 	if (root->track_dirty && list_empty(&root->dirty_list)) {
 		list_add(&root->dirty_list,
 			 &root->fs_info->dirty_cowonly_roots);
 	}
+	spin_unlock(&root->fs_info->trans_lock);
 }
 
 /*
@@ -723,7 +725,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 
 		cur = btrfs_find_tree_block(root, blocknr, blocksize);
 		if (cur)
-			uptodate = btrfs_buffer_uptodate(cur, gen);
+			uptodate = btrfs_buffer_uptodate(cur, gen, 0);
 		else
 			uptodate = 0;
 		if (!cur || !uptodate) {
@@ -1358,15 +1360,20 @@ static noinline int reada_for_balance(struct btrfs_root *root,
 		block1 = btrfs_node_blockptr(parent, slot - 1);
 		gen = btrfs_node_ptr_generation(parent, slot - 1);
 		eb = btrfs_find_tree_block(root, block1, blocksize);
-		if (eb && btrfs_buffer_uptodate(eb, gen))
+		/*
+		 * if we get -eagain from btrfs_buffer_uptodate, we
+		 * don't want to return eagain here.  That will loop
+		 * forever
+		 */
+		if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0)
 			block1 = 0;
 		free_extent_buffer(eb);
 	}
 	if (slot + 1 < nritems) {
 		block2 = btrfs_node_blockptr(parent, slot + 1);
 		gen = btrfs_node_ptr_generation(parent, slot + 1);
 		eb = btrfs_find_tree_block(root, block2, blocksize);
-		if (eb && btrfs_buffer_uptodate(eb, gen))
+		if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0)
 			block2 = 0;
 		free_extent_buffer(eb);
 	}
@@ -1504,8 +1511,9 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 
 	tmp = btrfs_find_tree_block(root, blocknr, blocksize);
 	if (tmp) {
-		if (btrfs_buffer_uptodate(tmp, 0)) {
-			if (btrfs_buffer_uptodate(tmp, gen)) {
+		/* first we do an atomic uptodate check */
+		if (btrfs_buffer_uptodate(tmp, 0, 1) > 0) {
+			if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
 				/*
 				 * we found an up to date block without
 				 * sleeping, return
@@ -1523,8 +1531,9 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 			free_extent_buffer(tmp);
 			btrfs_set_path_blocking(p);
 
+			/* now we're allowed to do a blocking uptodate check */
 			tmp = read_tree_block(root, blocknr, blocksize, gen);
-			if (tmp && btrfs_buffer_uptodate(tmp, gen)) {
+			if (tmp && btrfs_buffer_uptodate(tmp, gen, 0) > 0) {
 				*eb_ret = tmp;
 				return 0;
 			}
@@ -1559,7 +1568,7 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 		 * and give up so that our caller doesn't loop forever
 		 * on our EAGAINs.
 		 */
-		if (!btrfs_buffer_uptodate(tmp, 0))
+		if (!btrfs_buffer_uptodate(tmp, 0, 0))
 			ret = -EIO;
 		free_extent_buffer(tmp);
 	}
@@ -4043,7 +4052,7 @@ int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
 			tmp = btrfs_find_tree_block(root, blockptr,
 					    btrfs_level_size(root, level - 1));
 
-			if (tmp && btrfs_buffer_uptodate(tmp, gen)) {
+			if (tmp && btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
 				free_extent_buffer(tmp);
 				break;
 			}
@@ -4166,7 +4175,8 @@ int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path,
 				struct extent_buffer *cur;
 				cur = btrfs_find_tree_block(root, blockptr,
 					    btrfs_level_size(root, level - 1));
-				if (!cur || !btrfs_buffer_uptodate(cur, gen)) {
+				if (!cur ||
+				    btrfs_buffer_uptodate(cur, gen, 1) <= 0) {
 					slot++;
 					if (cur)
 						free_extent_buffer(cur);

fs/btrfs/disk-io.c

@@ -323,14 +323,18 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
  * in the wrong place.
  */
 static int verify_parent_transid(struct extent_io_tree *io_tree,
-				 struct extent_buffer *eb, u64 parent_transid)
+				 struct extent_buffer *eb, u64 parent_transid,
+				 int atomic)
 {
 	struct extent_state *cached_state = NULL;
 	int ret;
 
 	if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
 		return 0;
 
+	if (atomic)
+		return -EAGAIN;
+
 	lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
 			 0, &cached_state);
 	if (extent_buffer_uptodate(eb) &&
@@ -372,7 +376,8 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 		ret = read_extent_buffer_pages(io_tree, eb, start,
 					       WAIT_COMPLETE,
 					       btree_get_extent, mirror_num);
-		if (!ret && !verify_parent_transid(io_tree, eb, parent_transid))
+		if (!ret && !verify_parent_transid(io_tree, eb,
+						   parent_transid, 0))
 			break;
 
 		/*
@@ -1202,7 +1207,7 @@ static int __must_check find_and_setup_root(struct btrfs_root *tree_root,
 	root->commit_root = NULL;
 	root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
 				     blocksize, generation);
-	if (!root->node || !btrfs_buffer_uptodate(root->node, generation)) {
+	if (!root->node || !btrfs_buffer_uptodate(root->node, generation, 0)) {
 		free_extent_buffer(root->node);
 		root->node = NULL;
 		return -EIO;
@@ -3143,7 +3148,8 @@ int close_ctree(struct btrfs_root *root)
 	return 0;
 }
 
-int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid)
+int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
+			  int atomic)
 {
 	int ret;
 	struct inode *btree_inode = buf->pages[0]->mapping->host;
@@ -3153,7 +3159,9 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid)
 		return ret;
 
 	ret = verify_parent_transid(&BTRFS_I(btree_inode)->io_tree, buf,
-				    parent_transid);
+				    parent_transid, atomic);
+	if (ret == -EAGAIN)
+		return ret;
 	return !ret;
 }
 

fs/btrfs/disk-io.h

@@ -66,7 +66,8 @@ void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
 void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
 void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root);
 void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
-int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid);
+int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
+			  int atomic);
 int btrfs_set_buffer_uptodate(struct extent_buffer *buf);
 int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid);
 u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len);

fs/btrfs/extent-tree.c

@@ -6568,7 +6568,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 			goto skip;
 	}
 
-	if (!btrfs_buffer_uptodate(next, generation)) {
+	if (!btrfs_buffer_uptodate(next, generation, 0)) {
 		btrfs_tree_unlock(next);
 		free_extent_buffer(next);
 		next = NULL;

fs/btrfs/extent_io.c

@@ -4120,6 +4120,7 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 			if (atomic_inc_not_zero(&exists->refs)) {
 				spin_unlock(&mapping->private_lock);
 				unlock_page(p);
+				page_cache_release(p);
 				mark_extent_buffer_accessed(exists);
 				goto free_eb;
 			}
@@ -4199,8 +4200,7 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 			unlock_page(eb->pages[i]);
 	}
 
-	if (!atomic_dec_and_test(&eb->refs))
-		return exists;
+	WARN_ON(!atomic_dec_and_test(&eb->refs));
 	btrfs_release_extent_buffer(eb);
 	return exists;
 }

fs/btrfs/ioctl.h

@@ -252,15 +252,15 @@ struct btrfs_data_container {
 
 struct btrfs_ioctl_ino_path_args {
 	__u64				inum;		/* in */
-	__u32				size;		/* in */
+	__u64				size;		/* in */
 	__u64				reserved[4];
 	/* struct btrfs_data_container	*fspath;	   out */
 	__u64				fspath;		/* out */
 };
 
 struct btrfs_ioctl_logical_ino_args {
 	__u64				logical;	/* in */
-	__u32				size;		/* in */
+	__u64				size;		/* in */
 	__u64				reserved[4];
 	/* struct btrfs_data_container	*inodes;	out   */
 	__u64				inodes;

fs/btrfs/scrub.c

@@ -998,6 +998,7 @@ static int scrub_setup_recheck_block(struct scrub_dev *sdev,
 			page = sblock->pagev + page_index;
 			page->logical = logical;
 			page->physical = bbio->stripes[mirror_index].physical;
+			/* for missing devices, bdev is NULL */
 			page->bdev = bbio->stripes[mirror_index].dev->bdev;
 			page->mirror_num = mirror_index + 1;
 			page->page = alloc_page(GFP_NOFS);
@@ -1042,6 +1043,12 @@ static int scrub_recheck_block(struct btrfs_fs_info *fs_info,
 		struct scrub_page *page = sblock->pagev + page_num;
 		DECLARE_COMPLETION_ONSTACK(complete);
 
+		if (page->bdev == NULL) {
+			page->io_error = 1;
+			sblock->no_io_error_seen = 0;
+			continue;
+		}
+
 		BUG_ON(!page->page);
 		bio = bio_alloc(GFP_NOFS, 1);
 		if (!bio)

fs/btrfs/tree-log.c

@@ -279,7 +279,7 @@ static int process_one_buffer(struct btrfs_root *log,
 						log->fs_info->extent_root,
 						eb->start, eb->len);
 
-	if (btrfs_buffer_uptodate(eb, gen)) {
+	if (btrfs_buffer_uptodate(eb, gen, 0)) {
 		if (wc->write)
 			btrfs_write_tree_block(eb);
 		if (wc->wait)