Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "The first major feature for ext4 this merge window is the largedir
  feature, which allows ext4 directories to support over 2 billion
  directory entries (assuming ~64 byte file names; in practice, users
  will run into practical performance limits first.) This feature was
  originally written by the Lustre team, and credit goes to Artem
  Blagodarenko from Seagate for getting this feature upstream.

  The second major major feature allows ext4 to support extended
  attribute values up to 64k. This feature was also originally from
  Lustre, and has been enhanced by Tahsin Erdogan from Google with a
  deduplication feature so that if multiple files have the same xattr
  value (for example, Windows ACL's stored by Samba), only one copy will
  be stored on disk for encoding and caching efficiency.

  We also have the usual set of bug fixes, cleanups, and optimizations"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (47 commits)
  ext4: fix spelling mistake: "prellocated" -> "preallocated"
  ext4: fix __ext4_new_inode() journal credits calculation
  ext4: skip ext4_init_security() and encryption on ea_inodes
  fs: generic_block_bmap(): initialize all of the fields in the temp bh
  ext4: change fast symlink test to not rely on i_blocks
  ext4: require key for truncate(2) of encrypted file
  ext4: don't bother checking for encryption key in ->mmap()
  ext4: check return value of kstrtoull correctly in reserved_clusters_store
  ext4: fix off-by-one fsmap error on 1k block filesystems
  ext4: return EFSBADCRC if a bad checksum error is found in ext4_find_entry()
  ext4: return EIO on read error in ext4_find_entry
  ext4: forbid encrypting root directory
  ext4: send parallel discards on commit completions
  ext4: avoid unnecessary stalls in ext4_evict_inode()
  ext4: add nombcache mount option
  ext4: strong binding of xattr inode references
  ext4: eliminate xattr entry e_hash recalculation for removes
  ext4: reserve space for xattr entries/names
  quota: add get_inode_usage callback to transfer multi-inode charges
  ext4: xattr inode deduplication
  ...

1 files changed, 89 insertions, 42 deletions

diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 404256caf9cf..13f0cadb1238 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -513,7 +513,7 @@ ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize)
 
 static inline ext4_lblk_t dx_get_block(struct dx_entry *entry)
 {
-	return le32_to_cpu(entry->block) & 0x00ffffff;
+	return le32_to_cpu(entry->block) & 0x0fffffff;
 }
 
 static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value)
@@ -739,6 +739,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
 	struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR);
 	u32 hash;
 
+	memset(frame_in, 0, EXT4_HTREE_LEVEL * sizeof(frame_in[0]));
 	frame->bh = ext4_read_dirblock(dir, 0, INDEX);
 	if (IS_ERR(frame->bh))
 		return (struct dx_frame *) frame->bh;
@@ -768,9 +769,15 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
 	}
 
 	indirect = root->info.indirect_levels;
-	if (indirect > 1) {
-		ext4_warning_inode(dir, "Unimplemented hash depth: %#06x",
-				   root->info.indirect_levels);
+	if (indirect >= ext4_dir_htree_level(dir->i_sb)) {
+		ext4_warning(dir->i_sb,
+			     "Directory (ino: %lu) htree depth %#06x exceed"
+			     "supported value", dir->i_ino,
+			     ext4_dir_htree_level(dir->i_sb));
+		if (ext4_dir_htree_level(dir->i_sb) < EXT4_HTREE_LEVEL) {
+			ext4_warning(dir->i_sb, "Enable large directory "
+						"feature to access it");
+		}
 		goto fail;
 	}
 
@@ -859,12 +866,19 @@ fail:
 
 static void dx_release(struct dx_frame *frames)
 {
+	struct dx_root_info *info;
+	int i;
+
 	if (frames[0].bh == NULL)
 		return;
 
-	if (((struct dx_root *)frames[0].bh->b_data)->info.indirect_levels)
-		brelse(frames[1].bh);
-	brelse(frames[0].bh);
+	info = &((struct dx_root *)frames[0].bh->b_data)->info;
+	for (i = 0; i <= info->indirect_levels; i++) {
+		if (frames[i].bh == NULL)
+			break;
+		brelse(frames[i].bh);
+		frames[i].bh = NULL;
+	}
 }
 
 /*
@@ -1050,7 +1064,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 {
 	struct dx_hash_info hinfo;
 	struct ext4_dir_entry_2 *de;
-	struct dx_frame frames[2], *frame;
+	struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
 	struct inode *dir;
 	ext4_lblk_t block;
 	int count = 0;
@@ -1428,11 +1442,11 @@ restart:
 			goto next;
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
-			/* read error, skip block & hope for the best */
 			EXT4_ERROR_INODE(dir, "reading directory lblock %lu",
 					 (unsigned long) block);
 			brelse(bh);
-			goto next;
+			ret = ERR_PTR(-EIO);
+			goto cleanup_and_exit;
 		}
 		if (!buffer_verified(bh) &&
 		    !is_dx_internal_node(dir, block,
@@ -1442,7 +1456,8 @@ restart:
 			EXT4_ERROR_INODE(dir, "checksumming directory "
 					 "block %lu", (unsigned long)block);
 			brelse(bh);
-			goto next;
+			ret = ERR_PTR(-EFSBADCRC);
+			goto cleanup_and_exit;
 		}
 		set_buffer_verified(bh);
 		i = search_dirblock(bh, dir, &fname,
@@ -1485,7 +1500,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
 			struct ext4_dir_entry_2 **res_dir)
 {
 	struct super_block * sb = dir->i_sb;
-	struct dx_frame frames[2], *frame;
+	struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
 	struct buffer_head *bh;
 	ext4_lblk_t block;
 	int retval;
@@ -1889,7 +1904,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
 	 */
 	dir->i_mtime = dir->i_ctime = current_time(dir);
 	ext4_update_dx_flag(dir);
-	dir->i_version++;
+	inode_inc_iversion(dir);
 	ext4_mark_inode_dirty(handle, dir);
 	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
 	err = ext4_handle_dirty_dirent_node(handle, dir, bh);
@@ -1908,7 +1923,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
 {
 	struct buffer_head *bh2;
 	struct dx_root	*root;
-	struct dx_frame	frames[2], *frame;
+	struct dx_frame	frames[EXT4_HTREE_LEVEL], *frame;
 	struct dx_entry *entries;
 	struct ext4_dir_entry_2	*de, *de2;
 	struct ext4_dir_entry_tail *t;
@@ -2127,13 +2142,16 @@ out:
 static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 			     struct inode *dir, struct inode *inode)
 {
-	struct dx_frame frames[2], *frame;
+	struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
 	struct dx_entry *entries, *at;
 	struct buffer_head *bh;
 	struct super_block *sb = dir->i_sb;
 	struct ext4_dir_entry_2 *de;
+	int restart;
 	int err;
 
+again:
+	restart = 0;
 	frame = dx_probe(fname, dir, NULL, frames);
 	if (IS_ERR(frame))
 		return PTR_ERR(frame);
@@ -2155,24 +2173,44 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 	if (err != -ENOSPC)
 		goto cleanup;
 
+	err = 0;
 	/* Block full, should compress but for now just split */
 	dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n",
 		       dx_get_count(entries), dx_get_limit(entries)));
 	/* Need to split index? */
 	if (dx_get_count(entries) == dx_get_limit(entries)) {
 		ext4_lblk_t newblock;
-		unsigned icount = dx_get_count(entries);
-		int levels = frame - frames;
+		int levels = frame - frames + 1;
+		unsigned int icount;
+		int add_level = 1;
 		struct dx_entry *entries2;
 		struct dx_node *node2;
 		struct buffer_head *bh2;
 
-		if (levels && (dx_get_count(frames->entries) ==
-			       dx_get_limit(frames->entries))) {
-			ext4_warning_inode(dir, "Directory index full!");
+		while (frame > frames) {
+			if (dx_get_count((frame - 1)->entries) <
+			    dx_get_limit((frame - 1)->entries)) {
+				add_level = 0;
+				break;
+			}
+			frame--; /* split higher index block */
+			at = frame->at;
+			entries = frame->entries;
+			restart = 1;
+		}
+		if (add_level && levels == ext4_dir_htree_level(sb)) {
+			ext4_warning(sb, "Directory (ino: %lu) index full, "
+					 "reach max htree level :%d",
+					 dir->i_ino, levels);
+			if (ext4_dir_htree_level(sb) < EXT4_HTREE_LEVEL) {
+				ext4_warning(sb, "Large directory feature is "
+						 "not enabled on this "
+						 "filesystem");
+			}
 			err = -ENOSPC;
 			goto cleanup;
 		}
+		icount = dx_get_count(entries);
 		bh2 = ext4_append(handle, dir, &newblock);
 		if (IS_ERR(bh2)) {
 			err = PTR_ERR(bh2);
@@ -2187,7 +2225,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 		err = ext4_journal_get_write_access(handle, frame->bh);
 		if (err)
 			goto journal_error;
-		if (levels) {
+		if (!add_level) {
 			unsigned icount1 = icount/2, icount2 = icount - icount1;
 			unsigned hash2 = dx_get_hash(entries + icount1);
 			dxtrace(printk(KERN_DEBUG "Split index %i/%i\n",
@@ -2195,7 +2233,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 
 			BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */
 			err = ext4_journal_get_write_access(handle,
-							     frames[0].bh);
+							     (frame - 1)->bh);
 			if (err)
 				goto journal_error;
 
@@ -2211,17 +2249,25 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 				frame->entries = entries = entries2;
 				swap(frame->bh, bh2);
 			}
-			dx_insert_block(frames + 0, hash2, newblock);
-			dxtrace(dx_show_index("node", frames[1].entries));
+			dx_insert_block((frame - 1), hash2, newblock);
+			dxtrace(dx_show_index("node", frame->entries));
 			dxtrace(dx_show_index("node",
 			       ((struct dx_node *) bh2->b_data)->entries));
 			err = ext4_handle_dirty_dx_node(handle, dir, bh2);
 			if (err)
 				goto journal_error;
 			brelse (bh2);
+			err = ext4_handle_dirty_dx_node(handle, dir,
+						   (frame - 1)->bh);
+			if (err)
+				goto journal_error;
+			if (restart) {
+				err = ext4_handle_dirty_dx_node(handle, dir,
+							   frame->bh);
+				goto journal_error;
+			}
 		} else {
-			dxtrace(printk(KERN_DEBUG
-				       "Creating second level index...\n"));
+			struct dx_root *dxroot;
 			memcpy((char *) entries2, (char *) entries,
 			       icount * sizeof(struct dx_entry));
 			dx_set_limit(entries2, dx_node_limit(dir));
@@ -2229,22 +2275,18 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 			/* Set up root */
 			dx_set_count(entries, 1);
 			dx_set_block(entries + 0, newblock);
-			((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels = 1;
-
-			/* Add new access path frame */
-			frame = frames + 1;
-			frame->at = at = at - entries + entries2;
-			frame->entries = entries = entries2;
-			frame->bh = bh2;
-			err = ext4_journal_get_write_access(handle,
-							     frame->bh);
+			dxroot = (struct dx_root *)frames[0].bh->b_data;
+			dxroot->info.indirect_levels += 1;
+			dxtrace(printk(KERN_DEBUG
+				       "Creating %d level index...\n",
+				       info->indirect_levels));
+			err = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
 			if (err)
 				goto journal_error;
-		}
-		err = ext4_handle_dirty_dx_node(handle, dir, frames[0].bh);
-		if (err) {
-			ext4_std_error(inode->i_sb, err);
-			goto cleanup;
+			err = ext4_handle_dirty_dx_node(handle, dir, bh2);
+			brelse(bh2);
+			restart = 1;
+			goto journal_error;
 		}
 	}
 	de = do_split(handle, dir, &bh, frame, &fname->hinfo);
@@ -2256,10 +2298,15 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 	goto cleanup;
 
 journal_error:
-	ext4_std_error(dir->i_sb, err);
+	ext4_std_error(dir->i_sb, err); /* this is a no-op if err == 0 */
 cleanup:
 	brelse(bh);
 	dx_release(frames);
+	/* @restart is true means htree-path has been changed, we need to
+	 * repeat dx_probe() to find out valid htree-path
+	 */
+	if (restart && err == 0)
+		goto again;
 	return err;
 }
 
@@ -2296,7 +2343,7 @@ int ext4_generic_delete_entry(handle_t *handle,
 					blocksize);
 			else
 				de->inode = 0;
-			dir->i_version++;
+			inode_inc_iversion(dir);
 			return 0;
 		}
 		i += ext4_rec_len_from_disk(de->rec_len, blocksize);