Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:
 "Fix a number of ext4 bugs in fast_commit, inline data, and delayed
  allocation.

  Also fix error handling code paths in ext4_dx_readdir() and
  ext4_fill_super().

  Finally, avoid a grabbing a journal head in the delayed allocation
  write in the common cases where we are overwriting a pre-existing
  block or appending to an inode"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: recheck buffer uptodate bit under buffer lock
  ext4: fix potential infinite loop in ext4_dx_readdir()
  ext4: flush s_error_work before journal destroy in ext4_fill_super
  ext4: fix loff_t overflow in ext4_max_bitmap_size()
  ext4: fix reserved space counter leakage
  ext4: limit the number of blocks in one ADD_RANGE TLV
  ext4: enforce buffer head state assertion in ext4_da_map_blocks
  ext4: remove extent cache entries when truncating inline data
  ext4: drop unnecessary journal handle in delalloc write
  ext4: factor out write end code of inline file
  ext4: correct the error path of ext4_write_inline_data_end()
  ext4: check and update i_disksize properly
  ext4: add error checking to ext4_ext_replay_set_iblocks()

fs/ext4/dir.c

@@ -551,7 +551,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx)
 	struct dir_private_info *info = file->private_data;
 	struct inode *inode = file_inode(file);
 	struct fname *fname;
-	int	ret;
+	int ret = 0;
 
 	if (!info) {
 		info = ext4_htree_create_dir_info(file, ctx->pos);
@@ -599,7 +599,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx)
 						   info->curr_minor_hash,
 						   &info->next_hash);
 			if (ret < 0)
-				return ret;
+				goto finished;
 			if (ret == 0) {
 				ctx->pos = ext4_get_htree_eof(file);
 				break;
@@ -630,7 +630,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx)
 	}
 finished:
 	info->last_pos = ctx->pos;
-	return 0;
+	return ret < 0 ? ret : 0;
 }
 
 static int ext4_release_dir(struct inode *inode, struct file *filp)

fs/ext4/ext4.h

@@ -3593,9 +3593,6 @@ extern int ext4_da_write_inline_data_begin(struct address_space *mapping,
 					   unsigned flags,
 					   struct page **pagep,
 					   void **fsdata);
-extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
-					 unsigned len, unsigned copied,
-					 struct page *page);
 extern int ext4_try_add_inline_entry(handle_t *handle,
 				     struct ext4_filename *fname,
 				     struct inode *dir, struct inode *inode);

fs/ext4/extents.c

@@ -5916,7 +5916,7 @@ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end)
 }
 
 /* Check if *cur is a hole and if it is, skip it */
-static void skip_hole(struct inode *inode, ext4_lblk_t *cur)
+static int skip_hole(struct inode *inode, ext4_lblk_t *cur)
 {
 	int ret;
 	struct ext4_map_blocks map;
@@ -5925,9 +5925,12 @@ static void skip_hole(struct inode *inode, ext4_lblk_t *cur)
 	map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur;
 
 	ret = ext4_map_blocks(NULL, inode, &map, 0);
+	if (ret < 0)
+		return ret;
 	if (ret != 0)
-		return;
+		return 0;
 	*cur = *cur + map.m_len;
+	return 0;
 }
 
 /* Count number of blocks used by this inode and update i_blocks */
@@ -5976,7 +5979,9 @@ int ext4_ext_replay_set_iblocks(struct inode *inode)
 	 * iblocks by total number of differences found.
 	 */
 	cur = 0;
-	skip_hole(inode, &cur);
+	ret = skip_hole(inode, &cur);
+	if (ret < 0)
+		goto out;
 	path = ext4_find_extent(inode, cur, NULL, 0);
 	if (IS_ERR(path))
 		goto out;
@@ -5995,8 +6000,12 @@ int ext4_ext_replay_set_iblocks(struct inode *inode)
 		}
 		cur = max(cur + 1, le32_to_cpu(ex->ee_block) +
 					ext4_ext_get_actual_len(ex));
-		skip_hole(inode, &cur);
-
+		ret = skip_hole(inode, &cur);
+		if (ret < 0) {
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			break;
+		}
 		path2 = ext4_find_extent(inode, cur, NULL, 0);
 		if (IS_ERR(path2)) {
 			ext4_ext_drop_refs(path);

fs/ext4/fast_commit.c

@@ -892,6 +892,12 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc)
 					    sizeof(lrange), (u8 *)&lrange, crc))
 				return -ENOSPC;
 		} else {
+			unsigned int max = (map.m_flags & EXT4_MAP_UNWRITTEN) ?
+				EXT_UNWRITTEN_MAX_LEN : EXT_INIT_MAX_LEN;
+
+			/* Limit the number of blocks in one extent */
+			map.m_len = min(max, map.m_len);
+
 			fc_ext.fc_ino = cpu_to_le32(inode->i_ino);
 			ex = (struct ext4_extent *)&fc_ext.fc_ex;
 			ex->ee_block = cpu_to_le32(map.m_lblk);

fs/ext4/inline.c

@@ -7,6 +7,7 @@
 #include <linux/iomap.h>
 #include <linux/fiemap.h>
 #include <linux/iversion.h>
+#include <linux/backing-dev.h>
 
 #include "ext4_jbd2.h"
 #include "ext4.h"
@@ -733,45 +734,83 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 			       unsigned copied, struct page *page)
 {
-	int ret, no_expand;
+	handle_t *handle = ext4_journal_current_handle();
+	int no_expand;
 	void *kaddr;
 	struct ext4_iloc iloc;
+	int ret = 0, ret2;
+
+	if (unlikely(copied < len) && !PageUptodate(page))
+		copied = 0;
 
-	if (unlikely(copied < len)) {
-		if (!PageUptodate(page)) {
-			copied = 0;
+	if (likely(copied)) {
+		ret = ext4_get_inode_loc(inode, &iloc);
+		if (ret) {
+			unlock_page(page);
+			put_page(page);
+			ext4_std_error(inode->i_sb, ret);
 			goto out;
 		}
-	}
+		ext4_write_lock_xattr(inode, &no_expand);
+		BUG_ON(!ext4_has_inline_data(inode));
 
-	ret = ext4_get_inode_loc(inode, &iloc);
-	if (ret) {
-		ext4_std_error(inode->i_sb, ret);
-		copied = 0;
-		goto out;
-	}
+		/*
+		 * ei->i_inline_off may have changed since
+		 * ext4_write_begin() called
+		 * ext4_try_to_write_inline_data()
+		 */
+		(void) ext4_find_inline_data_nolock(inode);
 
-	ext4_write_lock_xattr(inode, &no_expand);
-	BUG_ON(!ext4_has_inline_data(inode));
+		kaddr = kmap_atomic(page);
+		ext4_write_inline_data(inode, &iloc, kaddr, pos, copied);
+		kunmap_atomic(kaddr);
+		SetPageUptodate(page);
+		/* clear page dirty so that writepages wouldn't work for us. */
+		ClearPageDirty(page);
 
-	/*
-	 * ei->i_inline_off may have changed since ext4_write_begin()
-	 * called ext4_try_to_write_inline_data()
-	 */
-	(void) ext4_find_inline_data_nolock(inode);
+		ext4_write_unlock_xattr(inode, &no_expand);
+		brelse(iloc.bh);
 
-	kaddr = kmap_atomic(page);
-	ext4_write_inline_data(inode, &iloc, kaddr, pos, len);
-	kunmap_atomic(kaddr);
-	SetPageUptodate(page);
-	/* clear page dirty so that writepages wouldn't work for us. */
-	ClearPageDirty(page);
+		/*
+		 * It's important to update i_size while still holding page
+		 * lock: page writeout could otherwise come in and zero
+		 * beyond i_size.
+		 */
+		ext4_update_inode_size(inode, pos + copied);
+	}
+	unlock_page(page);
+	put_page(page);
 
-	ext4_write_unlock_xattr(inode, &no_expand);
-	brelse(iloc.bh);
-	mark_inode_dirty(inode);
+	/*
+	 * Don't mark the inode dirty under page lock. First, it unnecessarily
+	 * makes the holding time of page lock longer. Second, it forces lock
+	 * ordering of page lock and transaction start for journaling
+	 * filesystems.
+	 */
+	if (likely(copied))
+		mark_inode_dirty(inode);
 out:
-	return copied;
+	/*
+	 * If we didn't copy as much data as expected, we need to trim back
+	 * size of xattr containing inline data.
+	 */
+	if (pos + len > inode->i_size && ext4_can_truncate(inode))
+		ext4_orphan_add(handle, inode);
+
+	ret2 = ext4_journal_stop(handle);
+	if (!ret)
+		ret = ret2;
+	if (pos + len > inode->i_size) {
+		ext4_truncate_failed_write(inode);
+		/*
+		 * If truncate failed early the inode might still be
+		 * on the orphan list; we need to make sure the inode
+		 * is removed from the orphan list in that case.
+		 */
+		if (inode->i_nlink)
+			ext4_orphan_del(NULL, inode);
+	}
+	return ret ? ret : copied;
 }
 
 struct buffer_head *
@@ -953,43 +992,6 @@ int ext4_da_write_inline_data_begin(struct address_space *mapping,
 	return ret;
 }
 
-int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
-				  unsigned len, unsigned copied,
-				  struct page *page)
-{
-	int ret;
-
-	ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
-	if (ret < 0) {
-		unlock_page(page);
-		put_page(page);
-		return ret;
-	}
-	copied = ret;
-
-	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold i_mutex.
-	 *
-	 * But it's important to update i_size while still holding page lock:
-	 * page writeout could otherwise come in and zero beyond i_size.
-	 */
-	if (pos+copied > inode->i_size)
-		i_size_write(inode, pos+copied);
-	unlock_page(page);
-	put_page(page);
-
-	/*
-	 * Don't mark the inode dirty under page lock. First, it unnecessarily
-	 * makes the holding time of page lock longer. Second, it forces lock
-	 * ordering of page lock and transaction start for journaling
-	 * filesystems.
-	 */
-	mark_inode_dirty(inode);
-
-	return copied;
-}
-
 #ifdef INLINE_DIR_DEBUG
 void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh,
 			  void *inline_start, int inline_size)
@@ -1917,6 +1919,24 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 	EXT4_I(inode)->i_disksize = i_size;
 
 	if (i_size < inline_size) {
+		/*
+		 * if there's inline data to truncate and this file was
+		 * converted to extents after that inline data was written,
+		 * the extent status cache must be cleared to avoid leaving
+		 * behind stale delayed allocated extent entries
+		 */
+		if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
+retry:
+			err = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
+			if (err == -ENOMEM) {
+				cond_resched();
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				goto retry;
+			}
+			if (err)
+				goto out_error;
+		}
+
 		/* Clear the content in the xattr space. */
 		if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) {
 			if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0)

fs/ext4/super.c

@@ -658,7 +658,7 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
 		 * constraints, it may not be safe to do it right here so we
 		 * defer superblock flushing to a workqueue.
 		 */
-		if (continue_fs)
+		if (continue_fs && journal)
 			schedule_work(&EXT4_SB(sb)->s_error_work);
 		else
 			ext4_commit_super(sb);
@@ -1350,6 +1350,12 @@ static void ext4_destroy_inode(struct inode *inode)
 				true);
 		dump_stack();
 	}
+
+	if (EXT4_I(inode)->i_reserved_data_blocks)
+		ext4_msg(inode->i_sb, KERN_ERR,
+			 "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!",
+			 inode->i_ino, EXT4_I(inode),
+			 EXT4_I(inode)->i_reserved_data_blocks);
 }
 
 static void init_once(void *foo)
@@ -3021,17 +3027,17 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files)
  */
 static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
 {
-	loff_t res = EXT4_NDIR_BLOCKS;
+	unsigned long long upper_limit, res = EXT4_NDIR_BLOCKS;
 	int meta_blocks;
-	loff_t upper_limit;
-	/* This is calculated to be the largest file size for a dense, block
+
+	/*
+	 * This is calculated to be the largest file size for a dense, block
 	 * mapped file such that the file's total number of 512-byte sectors,
 	 * including data and all indirect blocks, does not exceed (2^48 - 1).
 	 *
 	 * __u32 i_blocks_lo and _u16 i_blocks_high represent the total
 	 * number of 512-byte sectors of the file.
 	 */
-
 	if (!has_huge_files) {
 		/*
 		 * !has_huge_files or implies that the inode i_block field
@@ -3074,7 +3080,7 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
 	if (res > MAX_LFS_FILESIZE)
 		res = MAX_LFS_FILESIZE;
 
-	return res;
+	return (loff_t)res;
 }
 
 static ext4_fsblk_t descriptor_loc(struct super_block *sb,
@@ -5042,12 +5048,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_ea_block_cache = NULL;
 
 	if (sbi->s_journal) {
+		/* flush s_error_work before journal destroy. */
+		flush_work(&sbi->s_error_work);
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
 	}
 failed_mount3a:
 	ext4_es_unregister_shrinker(sbi);
 failed_mount3:
+	/* flush s_error_work before sbi destroy */
 	flush_work(&sbi->s_error_work);
 	del_timer_sync(&sbi->s_err_report);
 	ext4_stop_mmpd(sbi);