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 siginificant new ext4 feature this time around is Harshad's new
  fast_commit mode.

  In addition, thanks to Mauricio for fixing a race where mmap'ed pages
  that are being changed in parallel with a data=journal transaction
  commit could result in bad checksums in the failure that could cause
  journal replays to fail.

  Also notable is Ritesh's buffered write optimization which can result
  in significant improvements on parallel write workloads. (The kernel
  test robot reported a 330.6% improvement on fio.write_iops on a 96
  core system using DAX)

  Besides that, we have the usual miscellaneous cleanups and bug fixes"

Link: https://lore.kernel.org/r/20200925071217.GO28663@shao2-debian

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (46 commits)
  ext4: fix invalid inode checksum
  ext4: add fast commit stats in procfs
  ext4: add a mount opt to forcefully turn fast commits on
  ext4: fast commit recovery path
  jbd2: fast commit recovery path
  ext4: main fast-commit commit path
  jbd2: add fast commit machinery
  ext4 / jbd2: add fast commit initialization
  ext4: add fast_commit feature and handling for extended mount options
  doc: update ext4 and journalling docs to include fast commit feature
  ext4: Detect already used quota file early
  jbd2: avoid transaction reuse after reformatting
  ext4: use the normal helper to get the actual inode
  ext4: fix bs < ps issue reported with dioread_nolock mount opt
  ext4: data=journal: write-protect pages on j_submit_inode_data_buffers()
  ext4: data=journal: fixes for ext4_page_mkwrite()
  jbd2, ext4, ocfs2: introduce/use journal callbacks j_submit|finish_inode_data_buffers()
  jbd2: introduce/export functions jbd2_journal_submit|finish_inode_data_buffers()
  ext4: introduce ext4_sb_bread_unmovable() to replace sb_bread_unmovable()
  ext4: use ext4_sb_bread() instead of sb_bread()
  ...

1 files changed, 209 insertions, 81 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index bf596467c234..03c2253005f0 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -101,8 +101,8 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw,
 	return provided == calculated;
 }
 
-static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
-				struct ext4_inode_info *ei)
+void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
+			 struct ext4_inode_info *ei)
 {
 	__u32 csum;
 
@@ -514,7 +514,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		return -EFSCORRUPTED;
 
 	/* Lookup extent status tree firstly */
-	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+	if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) &&
+	    ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
 		if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
 			map->m_pblk = ext4_es_pblock(&es) +
 					map->m_lblk - es.es_lblk;
@@ -729,6 +730,8 @@ out_sem:
 			if (ret)
 				return ret;
 		}
+		ext4_fc_track_range(inode, map->m_lblk,
+			    map->m_lblk + map->m_len - 1);
 	}
 
 	if (retval < 0)
@@ -825,7 +828,8 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 	int create = map_flags & EXT4_GET_BLOCKS_CREATE;
 	int err;
 
-	J_ASSERT(handle != NULL || create == 0);
+	J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		 || handle != NULL || create == 0);
 
 	map.m_lblk = block;
 	map.m_len = 1;
@@ -841,7 +845,8 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 		return ERR_PTR(-ENOMEM);
 	if (map.m_flags & EXT4_MAP_NEW) {
 		J_ASSERT(create != 0);
-		J_ASSERT(handle != NULL);
+		J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+			 || (handle != NULL));
 
 		/*
 		 * Now that we do not always journal data, we should
@@ -878,18 +883,20 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
 			       ext4_lblk_t block, int map_flags)
 {
 	struct buffer_head *bh;
+	int ret;
 
 	bh = ext4_getblk(handle, inode, block, map_flags);
 	if (IS_ERR(bh))
 		return bh;
 	if (!bh || ext4_buffer_uptodate(bh))
 		return bh;
-	ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bh);
-	wait_on_buffer(bh);
-	if (buffer_uptodate(bh))
-		return bh;
-	put_bh(bh);
-	return ERR_PTR(-EIO);
+
+	ret = ext4_read_bh_lock(bh, REQ_META | REQ_PRIO, true);
+	if (ret) {
+		put_bh(bh);
+		return ERR_PTR(ret);
+	}
+	return bh;
 }
 
 /* Read a contiguous batch of blocks. */
@@ -910,8 +917,7 @@ int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count,
 	for (i = 0; i < bh_count; i++)
 		/* Note that NULL bhs[i] is valid because of holes. */
 		if (bhs[i] && !ext4_buffer_uptodate(bhs[i]))
-			ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1,
-				    &bhs[i]);
+			ext4_read_bh_lock(bhs[i], REQ_META | REQ_PRIO, false);
 
 	if (!wait)
 		return 0;
@@ -1081,7 +1087,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
 		    !buffer_unwritten(bh) &&
 		    (block_start < from || block_end > to)) {
-			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+			ext4_read_bh_lock(bh, 0, false);
 			wait[nr_wait++] = bh;
 		}
 	}
@@ -1912,6 +1918,9 @@ static int __ext4_journalled_writepage(struct page *page,
 	}
 	if (ret == 0)
 		ret = err;
+	err = ext4_jbd2_inode_add_write(handle, inode, 0, len);
+	if (ret == 0)
+		ret = err;
 	EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
 	err = ext4_journal_stop(handle);
 	if (!ret)
@@ -2254,7 +2263,7 @@ static int mpage_process_page(struct mpage_da_data *mpd, struct page *page,
 					err = PTR_ERR(io_end_vec);
 					goto out;
 				}
-				io_end_vec->offset = mpd->map.m_lblk << blkbits;
+				io_end_vec->offset = (loff_t)mpd->map.m_lblk << blkbits;
 			}
 			*map_bh = true;
 			goto out;
@@ -2785,7 +2794,7 @@ retry:
 		 * ext4_journal_stop() can wait for transaction commit
 		 * to finish which may depend on writeback of pages to
 		 * complete or on page lock to be released.  In that
-		 * case, we have to wait until after after we have
+		 * case, we have to wait until after we have
 		 * submitted all the IO, released page locks we hold,
 		 * and dropped io_end reference (for extent conversion
 		 * to be able to complete) before stopping the handle.
@@ -3296,9 +3305,14 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 {
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 
-	if (journal)
-		return !jbd2_transaction_committed(journal,
-					EXT4_I(inode)->i_datasync_tid);
+	if (journal) {
+		if (jbd2_transaction_committed(journal,
+					EXT4_I(inode)->i_datasync_tid))
+			return true;
+		return atomic_read(&EXT4_SB(inode->i_sb)->s_fc_subtid) >=
+			EXT4_I(inode)->i_fc_committed_subtid;
+	}
+
 	/* Any metadata buffers to write? */
 	if (!list_empty(&inode->i_mapping->private_list))
 		return true;
@@ -3436,14 +3450,26 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
 			  EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
 
-	if (flags & IOMAP_WRITE)
+	if (flags & IOMAP_WRITE) {
+		/*
+		 * We check here if the blocks are already allocated, then we
+		 * don't need to start a journal txn and we can directly return
+		 * the mapping information. This could boost performance
+		 * especially in multi-threaded overwrite requests.
+		 */
+		if (offset + length <= i_size_read(inode)) {
+			ret = ext4_map_blocks(NULL, inode, &map, 0);
+			if (ret > 0 && (map.m_flags & EXT4_MAP_MAPPED))
+				goto out;
+		}
 		ret = ext4_iomap_alloc(inode, &map, flags);
-	else
+	} else {
 		ret = ext4_map_blocks(NULL, inode, &map, 0);
+	}
 
 	if (ret < 0)
 		return ret;
-
+out:
 	ext4_set_iomap(inode, iomap, &map, offset, length);
 
 	return 0;
@@ -3601,6 +3627,13 @@ static int ext4_set_page_dirty(struct page *page)
 	return __set_page_dirty_buffers(page);
 }
 
+static int ext4_iomap_swap_activate(struct swap_info_struct *sis,
+				    struct file *file, sector_t *span)
+{
+	return iomap_swapfile_activate(sis, file, span,
+				       &ext4_iomap_report_ops);
+}
+
 static const struct address_space_operations ext4_aops = {
 	.readpage		= ext4_readpage,
 	.readahead		= ext4_readahead,
@@ -3616,6 +3649,7 @@ static const struct address_space_operations ext4_aops = {
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
+	.swap_activate		= ext4_iomap_swap_activate,
 };
 
 static const struct address_space_operations ext4_journalled_aops = {
@@ -3632,6 +3666,7 @@ static const struct address_space_operations ext4_journalled_aops = {
 	.direct_IO		= noop_direct_IO,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
+	.swap_activate		= ext4_iomap_swap_activate,
 };
 
 static const struct address_space_operations ext4_da_aops = {
@@ -3649,6 +3684,7 @@ static const struct address_space_operations ext4_da_aops = {
 	.migratepage		= buffer_migrate_page,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
+	.swap_activate		= ext4_iomap_swap_activate,
 };
 
 static const struct address_space_operations ext4_dax_aops = {
@@ -3657,6 +3693,7 @@ static const struct address_space_operations ext4_dax_aops = {
 	.set_page_dirty		= noop_set_page_dirty,
 	.bmap			= ext4_bmap,
 	.invalidatepage		= noop_invalidatepage,
+	.swap_activate		= ext4_iomap_swap_activate,
 };
 
 void ext4_set_aops(struct inode *inode)
@@ -3730,11 +3767,8 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		set_buffer_uptodate(bh);
 
 	if (!buffer_uptodate(bh)) {
-		err = -EIO;
-		ll_rw_block(REQ_OP_READ, 0, 1, &bh);
-		wait_on_buffer(bh);
-		/* Uhhuh. Read error. Complain and punt. */
-		if (!buffer_uptodate(bh))
+		err = ext4_read_bh_lock(bh, 0, true);
+		if (err)
 			goto unlock;
 		if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
 			/* We expect the key to be set. */
@@ -4073,6 +4107,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
+	ext4_fc_track_range(inode, first_block, stop_block);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
@@ -4252,22 +4287,22 @@ out_trace:
  * data in memory that is needed to recreate the on-disk version of this
  * inode.
  */
-static int __ext4_get_inode_loc(struct inode *inode,
-				struct ext4_iloc *iloc, int in_mem)
+static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
+				struct ext4_iloc *iloc, int in_mem,
+				ext4_fsblk_t *ret_block)
 {
 	struct ext4_group_desc	*gdp;
 	struct buffer_head	*bh;
-	struct super_block	*sb = inode->i_sb;
 	ext4_fsblk_t		block;
 	struct blk_plug		plug;
 	int			inodes_per_block, inode_offset;
 
 	iloc->bh = NULL;
-	if (inode->i_ino < EXT4_ROOT_INO ||
-	    inode->i_ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
+	if (ino < EXT4_ROOT_INO ||
+	    ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
 		return -EFSCORRUPTED;
 
-	iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	iloc->block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
 	gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
 	if (!gdp)
 		return -EIO;
@@ -4276,7 +4311,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	 * Figure out the offset within the block group inode table
 	 */
 	inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
-	inode_offset = ((inode->i_ino - 1) %
+	inode_offset = ((ino - 1) %
 			EXT4_INODES_PER_GROUP(sb));
 	block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
 	iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
@@ -4289,16 +4324,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	if (!buffer_uptodate(bh)) {
 		lock_buffer(bh);
 
-		/*
-		 * If the buffer has the write error flag, we have failed
-		 * to write out another inode in the same block.  In this
-		 * case, we don't have to read the block because we may
-		 * read the old inode data successfully.
-		 */
-		if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
-			set_buffer_uptodate(bh);
-
-		if (buffer_uptodate(bh)) {
+		if (ext4_buffer_uptodate(bh)) {
 			/* someone brought it uptodate while we waited */
 			unlock_buffer(bh);
 			goto has_buffer;
@@ -4369,7 +4395,7 @@ make_io:
 			if (end > table)
 				end = table;
 			while (b <= end)
-				sb_breadahead_unmovable(sb, b++);
+				ext4_sb_breadahead_unmovable(sb, b++);
 		}
 
 		/*
@@ -4377,16 +4403,14 @@ make_io:
 		 * has in-inode xattrs, or we don't have this inode in memory.
 		 * Read the block from disk.
 		 */
-		trace_ext4_load_inode(inode);
-		get_bh(bh);
-		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
+		trace_ext4_load_inode(sb, ino);
+		ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL);
 		blk_finish_plug(&plug);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 		simulate_eio:
-			ext4_error_inode_block(inode, block, EIO,
-					       "unable to read itable block");
+			if (ret_block)
+				*ret_block = block;
 			brelse(bh);
 			return -EIO;
 		}
@@ -4396,11 +4420,43 @@ has_buffer:
 	return 0;
 }
 
+static int __ext4_get_inode_loc_noinmem(struct inode *inode,
+					struct ext4_iloc *iloc)
+{
+	ext4_fsblk_t err_blk;
+	int ret;
+
+	ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc, 0,
+					&err_blk);
+
+	if (ret == -EIO)
+		ext4_error_inode_block(inode, err_blk, EIO,
+					"unable to read itable block");
+
+	return ret;
+}
+
 int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 {
+	ext4_fsblk_t err_blk;
+	int ret;
+
 	/* We have all inode data except xattrs in memory here. */
-	return __ext4_get_inode_loc(inode, iloc,
-		!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
+	ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc,
+		!ext4_test_inode_state(inode, EXT4_STATE_XATTR), &err_blk);
+
+	if (ret == -EIO)
+		ext4_error_inode_block(inode, err_blk, EIO,
+					"unable to read itable block");
+
+	return ret;
+}
+
+
+int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
+			  struct ext4_iloc *iloc)
+{
+	return __ext4_get_inode_loc(sb, ino, iloc, 0, NULL);
 }
 
 static bool ext4_should_enable_dax(struct inode *inode)
@@ -4566,7 +4622,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	ei = EXT4_I(inode);
 	iloc.bh = NULL;
 
-	ret = __ext4_get_inode_loc(inode, &iloc, 0);
+	ret = __ext4_get_inode_loc_noinmem(inode, &iloc);
 	if (ret < 0)
 		goto bad_inode;
 	raw_inode = ext4_raw_inode(&iloc);
@@ -4612,10 +4668,11 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 					      sizeof(gen));
 	}
 
-	if (!ext4_inode_csum_verify(inode, raw_inode, ei) ||
-	    ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) {
-		ext4_error_inode_err(inode, function, line, 0, EFSBADCRC,
-				     "iget: checksum invalid");
+	if ((!ext4_inode_csum_verify(inode, raw_inode, ei) ||
+	    ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) &&
+	     (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))) {
+		ext4_error_inode_err(inode, function, line, 0,
+				EFSBADCRC, "iget: checksum invalid");
 		ret = -EFSBADCRC;
 		goto bad_inode;
 	}
@@ -4703,6 +4760,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	for (block = 0; block < EXT4_N_BLOCKS; block++)
 		ei->i_data[block] = raw_inode->i_block[block];
 	INIT_LIST_HEAD(&ei->i_orphan);
+	ext4_fc_init_inode(&ei->vfs_inode);
 
 	/*
 	 * Set transaction id's of transactions that have to be committed
@@ -4768,9 +4826,10 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		goto bad_inode;
 	} else if (!ext4_has_inline_data(inode)) {
 		/* validate the block references in the inode */
-		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-		   (S_ISLNK(inode->i_mode) &&
-		    !ext4_inode_is_fast_symlink(inode))) {
+		if (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
+			(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+			(S_ISLNK(inode->i_mode) &&
+			!ext4_inode_is_fast_symlink(inode)))) {
 			if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 				ret = ext4_ext_check_inode(inode);
 			else
@@ -4971,6 +5030,12 @@ static int ext4_do_update_inode(handle_t *handle,
 	if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
 		memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
 
+	err = ext4_inode_blocks_set(handle, raw_inode, ei);
+	if (err) {
+		spin_unlock(&ei->i_raw_lock);
+		goto out_brelse;
+	}
+
 	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
 	i_uid = i_uid_read(inode);
 	i_gid = i_gid_read(inode);
@@ -5004,11 +5069,6 @@ static int ext4_do_update_inode(handle_t *handle,
 	EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
 	EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
 
-	err = ext4_inode_blocks_set(handle, raw_inode, ei);
-	if (err) {
-		spin_unlock(&ei->i_raw_lock);
-		goto out_brelse;
-	}
 	raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
 	raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
 	if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
@@ -5149,12 +5209,12 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
 		if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
 			return 0;
 
-		err = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
+		err = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
 						EXT4_I(inode)->i_sync_tid);
 	} else {
 		struct ext4_iloc iloc;
 
-		err = __ext4_get_inode_loc(inode, &iloc, 0);
+		err = __ext4_get_inode_loc_noinmem(inode, &iloc);
 		if (err)
 			return err;
 		/*
@@ -5278,6 +5338,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		if (error)
 			return error;
 	}
+	ext4_fc_start_update(inode);
 	if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
 	    (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
 		handle_t *handle;
@@ -5301,6 +5362,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 
 		if (error) {
 			ext4_journal_stop(handle);
+			ext4_fc_stop_update(inode);
 			return error;
 		}
 		/* Update corresponding info in inode so that everything is in
@@ -5323,11 +5385,15 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
-			if (attr->ia_size > sbi->s_bitmap_maxbytes)
+			if (attr->ia_size > sbi->s_bitmap_maxbytes) {
+				ext4_fc_stop_update(inode);
 				return -EFBIG;
+			}
 		}
-		if (!S_ISREG(inode->i_mode))
+		if (!S_ISREG(inode->i_mode)) {
+			ext4_fc_stop_update(inode);
 			return -EINVAL;
+		}
 
 		if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
 			inode_inc_iversion(inode);
@@ -5351,7 +5417,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		rc = ext4_break_layouts(inode);
 		if (rc) {
 			up_write(&EXT4_I(inode)->i_mmap_sem);
-			return rc;
+			goto err_out;
 		}
 
 		if (attr->ia_size != inode->i_size) {
@@ -5372,6 +5438,21 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				inode->i_mtime = current_time(inode);
 				inode->i_ctime = inode->i_mtime;
 			}
+
+			if (shrink)
+				ext4_fc_track_range(inode,
+					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits,
+					(oldsize > 0 ? oldsize - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits);
+			else
+				ext4_fc_track_range(
+					inode,
+					(oldsize > 0 ? oldsize - 1 : oldsize) >>
+					inode->i_sb->s_blocksize_bits,
+					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits);
+
 			down_write(&EXT4_I(inode)->i_data_sem);
 			EXT4_I(inode)->i_disksize = attr->ia_size;
 			rc = ext4_mark_inode_dirty(handle, inode);
@@ -5430,9 +5511,11 @@ out_mmap_sem:
 		rc = posix_acl_chmod(inode, inode->i_mode);
 
 err_out:
-	ext4_std_error(inode->i_sb, error);
+	if  (error)
+		ext4_std_error(inode->i_sb, error);
 	if (!error)
 		error = rc;
+	ext4_fc_stop_update(inode);
 	return error;
 }
 
@@ -5614,6 +5697,8 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 		put_bh(iloc->bh);
 		return -EIO;
 	}
+	ext4_fc_track_inode(inode);
+
 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
 
@@ -5937,6 +6022,8 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
+	ext4_fc_mark_ineligible(inode->i_sb,
+		EXT4_FC_REASON_JOURNAL_FLAG_CHANGE);
 	err = ext4_mark_inode_dirty(handle, inode);
 	ext4_handle_sync(handle);
 	ext4_journal_stop(handle);
@@ -5977,9 +6064,17 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 	if (err)
 		goto out_ret;
 
+	/*
+	 * On data journalling we skip straight to the transaction handle:
+	 * there's no delalloc; page truncated will be checked later; the
+	 * early return w/ all buffers mapped (calculates size/len) can't
+	 * be used; and there's no dioread_nolock, so only ext4_get_block.
+	 */
+	if (ext4_should_journal_data(inode))
+		goto retry_alloc;
+
 	/* Delalloc case is easy... */
 	if (test_opt(inode->i_sb, DELALLOC) &&
-	    !ext4_should_journal_data(inode) &&
 	    !ext4_nonda_switch(inode->i_sb)) {
 		do {
 			err = block_page_mkwrite(vma, vmf,
@@ -6005,6 +6100,9 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 	/*
 	 * Return if we have all the buffers mapped. This avoids the need to do
 	 * journal_start/journal_stop which can block and take a long time
+	 *
+	 * This cannot be done for data journalling, as we have to add the
+	 * inode to the transaction's list to writeprotect pages on commit.
 	 */
 	if (page_has_buffers(page)) {
 		if (!ext4_walk_page_buffers(NULL, page_buffers(page),
@@ -6029,16 +6127,42 @@ retry_alloc:
 		ret = VM_FAULT_SIGBUS;
 		goto out;
 	}
-	err = block_page_mkwrite(vma, vmf, get_block);
-	if (!err && ext4_should_journal_data(inode)) {
-		if (ext4_walk_page_buffers(handle, page_buffers(page), 0,
-			  PAGE_SIZE, NULL, do_journal_get_write_access)) {
-			unlock_page(page);
+	/*
+	 * Data journalling can't use block_page_mkwrite() because it
+	 * will set_buffer_dirty() before do_journal_get_write_access()
+	 * thus might hit warning messages for dirty metadata buffers.
+	 */
+	if (!ext4_should_journal_data(inode)) {
+		err = block_page_mkwrite(vma, vmf, get_block);
+	} else {
+		lock_page(page);
+		size = i_size_read(inode);
+		/* Page got truncated from under us? */
+		if (page->mapping != mapping || page_offset(page) > size) {
+			ret = VM_FAULT_NOPAGE;
+			goto out_error;
+		}
+
+		if (page->index == size >> PAGE_SHIFT)
+			len = size & ~PAGE_MASK;
+		else
+			len = PAGE_SIZE;
+
+		err = __block_write_begin(page, 0, len, ext4_get_block);
+		if (!err) {
 			ret = VM_FAULT_SIGBUS;
-			ext4_journal_stop(handle);
-			goto out;
+			if (ext4_walk_page_buffers(handle, page_buffers(page),
+					0, len, NULL, do_journal_get_write_access))
+				goto out_error;
+			if (ext4_walk_page_buffers(handle, page_buffers(page),
+					0, len, NULL, write_end_fn))
+				goto out_error;
+			if (ext4_jbd2_inode_add_write(handle, inode, 0, len))
+				goto out_error;
+			ext4_set_inode_state(inode, EXT4_STATE_JDATA);
+		} else {
+			unlock_page(page);
 		}
-		ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 	}
 	ext4_journal_stop(handle);
 	if (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -6049,6 +6173,10 @@ out:
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
+out_error:
+	unlock_page(page);
+	ext4_journal_stop(handle);
+	goto out;
 }
 
 vm_fault_t ext4_filemap_fault(struct vm_fault *vmf)