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

Pull btrfs fixes from Chris Mason:
 "These are assorted fixes, mostly from Josef nailing down xfstests
  runs.  Zach also has a long standing fix for problems with readdir
  wrapping f_pos (or ctx->pos)

  These patches were spread out over different bases, so I rebased
  things on top of rc4 and retested overnight"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  btrfs: don't loop on large offsets in readdir
  Btrfs: check to see if root_list is empty before adding it to dead roots
  Btrfs: release both paths before logging dir/changed extents
  Btrfs: allow splitting of hole em's when dropping extent cache
  Btrfs: make sure the backref walker catches all refs to our extent
  Btrfs: fix backref walking when we hit a compressed extent
  Btrfs: do not offset physical if we're compressed
  Btrfs: fix extent buffer leak after backref walking
  Btrfs: fix a bug of snapshot-aware defrag to make it work on partial extents
  btrfs: fix file truncation if FALLOC_FL_KEEP_SIZE is specified

8 files changed, 119 insertions, 68 deletions

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index eaf133384a8f..8bc5e8ccb091 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -36,16 +36,23 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb,
 				u64 extent_item_pos,
 				struct extent_inode_elem **eie)
 {
-	u64 data_offset;
-	u64 data_len;
+	u64 offset = 0;
 	struct extent_inode_elem *e;
 
-	data_offset = btrfs_file_extent_offset(eb, fi);
-	data_len = btrfs_file_extent_num_bytes(eb, fi);
+	if (!btrfs_file_extent_compression(eb, fi) &&
+	    !btrfs_file_extent_encryption(eb, fi) &&
+	    !btrfs_file_extent_other_encoding(eb, fi)) {
+		u64 data_offset;
+		u64 data_len;
 
-	if (extent_item_pos < data_offset ||
-	    extent_item_pos >= data_offset + data_len)
-		return 1;
+		data_offset = btrfs_file_extent_offset(eb, fi);
+		data_len = btrfs_file_extent_num_bytes(eb, fi);
+
+		if (extent_item_pos < data_offset ||
+		    extent_item_pos >= data_offset + data_len)
+			return 1;
+		offset = extent_item_pos - data_offset;
+	}
 
 	e = kmalloc(sizeof(*e), GFP_NOFS);
 	if (!e)
@@ -53,7 +60,7 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb,
 
 	e->next = *eie;
 	e->inum = key->objectid;
-	e->offset = key->offset + (extent_item_pos - data_offset);
+	e->offset = key->offset + offset;
 	*eie = e;
 
 	return 0;
@@ -189,7 +196,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 	struct extent_buffer *eb;
 	struct btrfs_key key;
 	struct btrfs_file_extent_item *fi;
-	struct extent_inode_elem *eie = NULL;
+	struct extent_inode_elem *eie = NULL, *old = NULL;
 	u64 disk_byte;
 
 	if (level != 0) {
@@ -223,6 +230,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 
 		if (disk_byte == wanted_disk_byte) {
 			eie = NULL;
+			old = NULL;
 			if (extent_item_pos) {
 				ret = check_extent_in_eb(&key, eb, fi,
 						*extent_item_pos,
@@ -230,18 +238,20 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 				if (ret < 0)
 					break;
 			}
-			if (!ret) {
-				ret = ulist_add(parents, eb->start,
-						(uintptr_t)eie, GFP_NOFS);
-				if (ret < 0)
-					break;
-				if (!extent_item_pos) {
-					ret = btrfs_next_old_leaf(root, path,
-							time_seq);
-					continue;
-				}
+			if (ret > 0)
+				goto next;
+			ret = ulist_add_merge(parents, eb->start,
+					      (uintptr_t)eie,
+					      (u64 *)&old, GFP_NOFS);
+			if (ret < 0)
+				break;
+			if (!ret && extent_item_pos) {
+				while (old->next)
+					old = old->next;
+				old->next = eie;
 			}
 		}
+next:
 		ret = btrfs_next_old_item(root, path, time_seq);
 	}
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 5bf4c39e2ad6..ed504607d8ec 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1271,7 +1271,6 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 		BUG_ON(!eb_rewin);
 	}
 
-	extent_buffer_get(eb_rewin);
 	btrfs_tree_read_unlock(eb);
 	free_extent_buffer(eb);
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 583d98bd065e..fe443fece851 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4048,7 +4048,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	}
 
 	while (!end) {
-		u64 offset_in_extent;
+		u64 offset_in_extent = 0;
 
 		/* break if the extent we found is outside the range */
 		if (em->start >= max || extent_map_end(em) < off)
@@ -4064,9 +4064,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 		/*
 		 * record the offset from the start of the extent
-		 * for adjusting the disk offset below
+		 * for adjusting the disk offset below.  Only do this if the
+		 * extent isn't compressed since our in ram offset may be past
+		 * what we have actually allocated on disk.
 		 */
-		offset_in_extent = em_start - em->start;
+		if (!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+			offset_in_extent = em_start - em->start;
 		em_end = extent_map_end(em);
 		em_len = em_end - em_start;
 		emflags = em->flags;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a005fe2c072a..8e686a427ce2 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -596,20 +596,29 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 		if (no_splits)
 			goto next;
 
-		if (em->block_start < EXTENT_MAP_LAST_BYTE &&
-		    em->start < start) {
+		if (em->start < start) {
 			split->start = em->start;
 			split->len = start - em->start;
-			split->orig_start = em->orig_start;
-			split->block_start = em->block_start;
 
-			if (compressed)
-				split->block_len = em->block_len;
-			else
-				split->block_len = split->len;
-			split->ram_bytes = em->ram_bytes;
-			split->orig_block_len = max(split->block_len,
-						    em->orig_block_len);
+			if (em->block_start < EXTENT_MAP_LAST_BYTE) {
+				split->orig_start = em->orig_start;
+				split->block_start = em->block_start;
+
+				if (compressed)
+					split->block_len = em->block_len;
+				else
+					split->block_len = split->len;
+				split->orig_block_len = max(split->block_len,
+						em->orig_block_len);
+				split->ram_bytes = em->ram_bytes;
+			} else {
+				split->orig_start = split->start;
+				split->block_len = 0;
+				split->block_start = em->block_start;
+				split->orig_block_len = 0;
+				split->ram_bytes = split->len;
+			}
+
 			split->generation = gen;
 			split->bdev = em->bdev;
 			split->flags = flags;
@@ -620,8 +629,7 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			split = split2;
 			split2 = NULL;
 		}
-		if (em->block_start < EXTENT_MAP_LAST_BYTE &&
-		    testend && em->start + em->len > start + len) {
+		if (testend && em->start + em->len > start + len) {
 			u64 diff = start + len - em->start;
 
 			split->start = start + len;
@@ -630,18 +638,28 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			split->flags = flags;
 			split->compress_type = em->compress_type;
 			split->generation = gen;
-			split->orig_block_len = max(em->block_len,
+
+			if (em->block_start < EXTENT_MAP_LAST_BYTE) {
+				split->orig_block_len = max(em->block_len,
 						    em->orig_block_len);
-			split->ram_bytes = em->ram_bytes;
 
-			if (compressed) {
-				split->block_len = em->block_len;
-				split->block_start = em->block_start;
-				split->orig_start = em->orig_start;
+				split->ram_bytes = em->ram_bytes;
+				if (compressed) {
+					split->block_len = em->block_len;
+					split->block_start = em->block_start;
+					split->orig_start = em->orig_start;
+				} else {
+					split->block_len = split->len;
+					split->block_start = em->block_start
+						+ diff;
+					split->orig_start = em->orig_start;
+				}
 			} else {
-				split->block_len = split->len;
-				split->block_start = em->block_start + diff;
-				split->orig_start = em->orig_start;
+				split->ram_bytes = split->len;
+				split->orig_start = split->start;
+				split->block_len = 0;
+				split->block_start = em->block_start;
+				split->orig_block_len = 0;
 			}
 
 			ret = add_extent_mapping(em_tree, split, modified);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6d1b93c8aafb..021694c08181 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2166,16 +2166,23 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id,
 		if (btrfs_file_extent_disk_bytenr(leaf, extent) != old->bytenr)
 			continue;
 
-		extent_offset = btrfs_file_extent_offset(leaf, extent);
-		if (key.offset - extent_offset != offset)
+		/*
+		 * 'offset' refers to the exact key.offset,
+		 * NOT the 'offset' field in btrfs_extent_data_ref, ie.
+		 * (key.offset - extent_offset).
+		 */
+		if (key.offset != offset)
 			continue;
 
+		extent_offset = btrfs_file_extent_offset(leaf, extent);
 		num_bytes = btrfs_file_extent_num_bytes(leaf, extent);
+
 		if (extent_offset >= old->extent_offset + old->offset +
 		    old->len || extent_offset + num_bytes <=
 		    old->extent_offset + old->offset)
 			continue;
 
+		ret = 0;
 		break;
 	}
 
@@ -2187,7 +2194,7 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id,
 
 	backref->root_id = root_id;
 	backref->inum = inum;
-	backref->file_pos = offset + extent_offset;
+	backref->file_pos = offset;
 	backref->num_bytes = num_bytes;
 	backref->extent_offset = extent_offset;
 	backref->generation = btrfs_file_extent_generation(leaf, extent);
@@ -2210,7 +2217,8 @@ static noinline bool record_extent_backrefs(struct btrfs_path *path,
 	new->path = path;
 
 	list_for_each_entry_safe(old, tmp, &new->head, list) {
-		ret = iterate_inodes_from_logical(old->bytenr, fs_info,
+		ret = iterate_inodes_from_logical(old->bytenr +
+						  old->extent_offset, fs_info,
 						  path, record_one_backref,
 						  old);
 		BUG_ON(ret < 0 && ret != -ENOENT);
@@ -4391,9 +4399,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 	int mask = attr->ia_valid;
 	int ret;
 
-	if (newsize == oldsize)
-		return 0;
-
 	/*
 	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
 	 * special case where we need to update the times despite not having
@@ -5165,14 +5170,31 @@ next:
 	}
 
 	/* Reached end of directory/root. Bump pos past the last item. */
-	if (key_type == BTRFS_DIR_INDEX_KEY)
-		/*
-		 * 32-bit glibc will use getdents64, but then strtol -
-		 * so the last number we can serve is this.
-		 */
-		ctx->pos = 0x7fffffff;
-	else
-		ctx->pos++;
+	ctx->pos++;
+
+	/*
+	 * Stop new entries from being returned after we return the last
+	 * entry.
+	 *
+	 * New directory entries are assigned a strictly increasing
+	 * offset.  This means that new entries created during readdir
+	 * are *guaranteed* to be seen in the future by that readdir.
+	 * This has broken buggy programs which operate on names as
+	 * they're returned by readdir.  Until we re-use freed offsets
+	 * we have this hack to stop new entries from being returned
+	 * under the assumption that they'll never reach this huge
+	 * offset.
+	 *
+	 * This is being careful not to overflow 32bit loff_t unless the
+	 * last entry requires it because doing so has broken 32bit apps
+	 * in the past.
+	 */
+	if (key_type == BTRFS_DIR_INDEX_KEY) {
+		if (ctx->pos >= INT_MAX)
+			ctx->pos = LLONG_MAX;
+		else
+			ctx->pos = INT_MAX;
+	}
 nopos:
 	ret = 0;
 err:
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index d58cce77fc6c..af1931a5960d 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -983,12 +983,12 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
  * a dirty root struct and adds it into the list of dead roots that need to
  * be deleted
  */
-int btrfs_add_dead_root(struct btrfs_root *root)
+void btrfs_add_dead_root(struct btrfs_root *root)
 {
 	spin_lock(&root->fs_info->trans_lock);
-	list_add_tail(&root->root_list, &root->fs_info->dead_roots);
+	if (list_empty(&root->root_list))
+		list_add_tail(&root->root_list, &root->fs_info->dead_roots);
 	spin_unlock(&root->fs_info->trans_lock);
-	return 0;
 }
 
 /*
@@ -1925,7 +1925,7 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root)
 	}
 	root = list_first_entry(&fs_info->dead_roots,
 			struct btrfs_root, root_list);
-	list_del(&root->root_list);
+	list_del_init(&root->root_list);
 	spin_unlock(&fs_info->trans_lock);
 
 	pr_debug("btrfs: cleaner removing %llu\n",
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 005b0375d18c..defbc4269897 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -143,7 +143,7 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid);
 int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root);
 
-int btrfs_add_dead_root(struct btrfs_root *root);
+void btrfs_add_dead_root(struct btrfs_root *root);
 int btrfs_defrag_root(struct btrfs_root *root);
 int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root);
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2c6791493637..ff60d8978ae2 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3746,8 +3746,9 @@ next_slot:
 	}
 
 log_extents:
+	btrfs_release_path(path);
+	btrfs_release_path(dst_path);
 	if (fast_search) {
-		btrfs_release_path(dst_path);
 		ret = btrfs_log_changed_extents(trans, root, inode, dst_path);
 		if (ret) {
 			err = ret;
@@ -3764,8 +3765,6 @@ log_extents:
 	}
 
 	if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) {
-		btrfs_release_path(path);
-		btrfs_release_path(dst_path);
 		ret = log_directory_changes(trans, root, inode, path, dst_path);
 		if (ret) {
 			err = ret;