More fixes and cleanups for the new fast_commit features, but also a

few other miscellaneous bug fixes and a cleanup for the MAINTAINERS file. -----BEGIN PGP SIGNATURE----- iQEzBAABCAAdFiEEK2m5VNv+CHkogTfJ8vlZVpUNgaMFAl+pfIoACgkQ8vlZVpUN gaMGFAf9FP9DoKQp10zp98LphiPRzMAqt9/ghUWcpz1bkXy33+NHivEi1tOTFcrZ hetvtOi/YnMlcD8f5IMf2vyOvj96ubI9fgsN3CIGNzU6kQm5E1s/h14PdQ2OkJbb Kn/BpmaWcTZRj0OXt9CcnEqAYIGrRMaHgZLcDoMwOCr+WgUTJD9Sk7mMLDRBkh8u QXnfRG2Ahsip8ZUdNTxB7fWPC8BkQAhkLnUe+9mMzIQEMDNs7kfPhnuN+ka334KV 62rc99lYvy3jWV34Iahd/pwS8VOYb0x4EHtcqD28bePy/WR9GU54bdbqMDV33bsx D+gnQLfwgoW92+3/2TTXvpG4WPWeqQ== =Y2bI -----END PGP SIGNATURE----- Merge tag 'ext4_for_linus_cleanups' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4 Pull ext4 fixes and cleanups from Ted Ts'o: "More fixes and cleanups for the new fast_commit features, but also a few other miscellaneous bug fixes and a cleanup for the MAINTAINERS file" * tag 'ext4_for_linus_cleanups' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (28 commits) jbd2: fix up sparse warnings in checkpoint code ext4: fix sparse warnings in fast_commit code ext4: cleanup fast commit mount options jbd2: don't start fast commit on aborted journal ext4: make s_mount_flags modifications atomic ext4: issue fsdev cache flush before starting fast commit ext4: disable fast commit with data journalling ext4: fix inode dirty check in case of fast commits ext4: remove unnecessary fast commit calls from ext4_file_mmap ext4: mark buf dirty before submitting fast commit buffer ext4: fix code documentatioon ext4: dedpulicate the code to wait on inode that's being committed jbd2: don't read journal->j_commit_sequence without taking a lock jbd2: don't touch buffer state until it is filled jbd2: add todo for a fast commit performance optimization jbd2: don't pass tid to jbd2_fc_end_commit_fallback() jbd2: don't use state lock during commit path jbd2: drop jbd2_fc_init documentation ext4: clean up the JBD2 API that initializes fast commits jbd2: rename j_maxlen to j_total_len and add jbd2_journal_max_txn_bufs ...
2020-11-09 12:36:58 -08:00 · 2020-11-09 12:36:58 -08:00 · 91808cd6c2
parent df3319a548 05d5233df8
commit 91808cd6c2
24 changed files with 343 additions and 272 deletions
--- a/Documentation/filesystems/ext4/journal.rst
+++ b/Documentation/filesystems/ext4/journal.rst
@ -256,6 +256,10 @@ which is 1024 bytes long:
     - s\_padding2
     -
   * - 0x54
+     - \_\_be32
+     - s\_num\_fc\_blocks
+     - Number of fast commit blocks in the journal.
+   * - 0x58
     - \_\_u32
     - s\_padding[42]
     -
@ -310,6 +314,8 @@ The journal incompat features are any combination of the following:
     - This journal uses v3 of the checksum on-disk format. This is the same as
       v2, but the journal block tag size is fixed regardless of the size of
       block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3)
+   * - 0x20
+     - Journal has fast commit blocks. (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT)

 .. _jbd2_checksum_type:

--- a/Documentation/filesystems/ext4/super.rst
+++ b/Documentation/filesystems/ext4/super.rst
@ -596,6 +596,13 @@ following:
     - Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs
       points to the two block groups that contain backup superblocks
       (COMPAT\_SPARSE\_SUPER2).
+   * - 0x400
+     - Fast commits supported. Although fast commits blocks are
+       backward incompatible, fast commit blocks are not always
+       present in the journal. If fast commit blocks are present in
+       the journal, JBD2 incompat feature
+       (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) gets
+       set (COMPAT\_FAST\_COMMIT).

 .. _super_incompat:

--- a/Documentation/filesystems/journalling.rst
+++ b/Documentation/filesystems/journalling.rst
@ -136,10 +136,8 @@ Fast commits
 ~~~~~~~~~~~~

 JBD2 to also allows you to perform file-system specific delta commits known as
-fast commits. In order to use fast commits, you first need to call
-:c:func:`jbd2_fc_init` and tell how many blocks at the end of journal
-area should be reserved for fast commits. Along with that, you will also need
-to set following callbacks that perform correspodning work:
+fast commits. In order to use fast commits, you will need to set following
+callbacks that perform correspodning work:

 `journal->j_fc_cleanup_cb`: Cleanup function called after every full commit and
 fast commit.
--- a/1
+++ b/1
@ -6614,6 +6614,7 @@ Q:	http://patchwork.ozlabs.org/project/linux-ext4/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git
 F:	Documentation/filesystems/ext4/
 F:	fs/ext4/
+F:	include/trace/events/ext4.h

 Extended Verification Module (EVM)
 M:	Mimi Zohar <zohar@linux.ibm.com>
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@ -1028,9 +1028,6 @@ struct ext4_inode_info {
 					 * protected by sbi->s_fc_lock.
 					 */

-	/* Fast commit subtid when this inode was committed */
-	unsigned int i_fc_committed_subtid;
-
 	/* Start of lblk range that needs to be committed in this fast commit */
 	ext4_lblk_t i_fc_lblk_start;

@ -1422,16 +1419,6 @@ struct ext4_super_block {

 #ifdef __KERNEL__

-/*
- * run-time mount flags
- */
-#define EXT4_MF_MNTDIR_SAMPLED		0x0001
-#define EXT4_MF_FS_ABORTED		0x0002	/* Fatal error detected */
-#define EXT4_MF_FC_INELIGIBLE		0x0004	/* Fast commit ineligible */
-#define EXT4_MF_FC_COMMITTING		0x0008	/* File system underoing a fast
-						 * commit.
-						 */
-
 #ifdef CONFIG_FS_ENCRYPTION
 #define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL)
 #else
@ -1466,7 +1453,7 @@ struct ext4_sb_info {
 	struct buffer_head * __rcu *s_group_desc;
 	unsigned int s_mount_opt;
 	unsigned int s_mount_opt2;
-	unsigned int s_mount_flags;
+	unsigned long s_mount_flags;
 	unsigned int s_def_mount_opt;
 	ext4_fsblk_t s_sb_block;
 	atomic64_t s_resv_clusters;
@ -1694,6 +1681,34 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 	_v;								   \
 })

+/*
+ * run-time mount flags
+ */
+enum {
+	EXT4_MF_MNTDIR_SAMPLED,
+	EXT4_MF_FS_ABORTED,	/* Fatal error detected */
+	EXT4_MF_FC_INELIGIBLE,	/* Fast commit ineligible */
+	EXT4_MF_FC_COMMITTING	/* File system underoing a fast
+				 * commit.
+				 */
+};
+
+static inline void ext4_set_mount_flag(struct super_block *sb, int bit)
+{
+	set_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+static inline void ext4_clear_mount_flag(struct super_block *sb, int bit)
+{
+	clear_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+static inline int ext4_test_mount_flag(struct super_block *sb, int bit)
+{
+	return test_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+
 /*
 * Simulate_fail codes
 */
@ -1863,6 +1878,13 @@ static inline bool ext4_verity_in_progress(struct inode *inode)
 #define EXT4_FEATURE_COMPAT_RESIZE_INODE	0x0010
 #define EXT4_FEATURE_COMPAT_DIR_INDEX		0x0020
 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
+/*
+ * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes
+ * incompatible only if fast commit blocks are present in the FS. Since we
+ * clear the journal (and thus the fast commit blocks), we don't mark FS as
+ * incompatible. We also have a JBD2 incompat feature, which gets set when
+ * there are fast commit blocks present in the journal.
+ */
 #define EXT4_FEATURE_COMPAT_FAST_COMMIT		0x0400
 #define EXT4_FEATURE_COMPAT_STABLE_INODES	0x0800

@ -2731,12 +2753,16 @@ extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
 int ext4_fc_info_show(struct seq_file *seq, void *v);
 void ext4_fc_init(struct super_block *sb, journal_t *journal);
 void ext4_fc_init_inode(struct inode *inode);
-void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
 			 ext4_lblk_t end);
-void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_link(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_create(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_inode(struct inode *inode);
+void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode,
+	struct dentry *dentry);
+void __ext4_fc_track_link(handle_t *handle, struct inode *inode,
+	struct dentry *dentry);
+void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
 void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
 void ext4_fc_start_ineligible(struct super_block *sb, int reason);
 void ext4_fc_stop_ineligible(struct super_block *sb);
@ -3452,7 +3478,7 @@ extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
 extern int ext4_ci_compare(const struct inode *parent,
 			   const struct qstr *fname,
 			   const struct qstr *entry, bool quick);
-extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
 			 struct inode *inode);
 extern int __ext4_link(struct inode *dir, struct inode *inode,
 		       struct dentry *dentry);
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@ -3724,7 +3724,6 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 out:
 	ext4_ext_show_leaf(inode, path);
-	ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
 	return err;
 }

@ -3796,7 +3795,6 @@ convert_initialized_extent(handle_t *handle, struct inode *inode,
 	if (*allocated > map->m_len)
 		*allocated = map->m_len;
 	map->m_len = *allocated;
-	ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
 	return 0;
 }

@ -4329,7 +4327,6 @@ got_allocated_blocks:
 	map->m_len = ar.len;
 	allocated = map->m_len;
 	ext4_ext_show_leaf(inode, path);
-	ext4_fc_track_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1);
 out:
 	ext4_ext_drop_refs(path);
 	kfree(path);
@ -4602,7 +4599,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	ret = ext4_mark_inode_dirty(handle, inode);
 	if (unlikely(ret))
 		goto out_handle;
-	ext4_fc_track_range(inode, offset >> inode->i_sb->s_blocksize_bits,
+	ext4_fc_track_range(handle, inode, offset >> inode->i_sb->s_blocksize_bits,
 			(offset + len - 1) >> inode->i_sb->s_blocksize_bits);
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
@ -4651,8 +4648,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
 		     FALLOC_FL_INSERT_RANGE))
 		return -EOPNOTSUPP;
-	ext4_fc_track_range(inode, offset >> blkbits,
-			(offset + len - 1) >> blkbits);

 	ext4_fc_start_update(inode);

--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@ -83,7 +83,7 @@
 *
 * Atomicity of commits
 * --------------------
- * In order to gaurantee atomicity during the commit operation, fast commit
+ * In order to guarantee atomicity during the commit operation, fast commit
 * uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail
 * tag contains CRC of the contents and TID of the transaction after which
 * this fast commit should be applied. Recovery code replays fast commit
@ -152,7 +152,31 @@ void ext4_fc_init_inode(struct inode *inode)
 	INIT_LIST_HEAD(&ei->i_fc_list);
 	init_waitqueue_head(&ei->i_fc_wait);
 	atomic_set(&ei->i_fc_updates, 0);
-	ei->i_fc_committed_subtid = 0;
+}
+
+/* This function must be called with sbi->s_fc_lock held. */
+static void ext4_fc_wait_committing_inode(struct inode *inode)
+__releases(&EXT4_SB(inode->i_sb)->s_fc_lock)
+{
+	wait_queue_head_t *wq;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+#if (BITS_PER_LONG < 64)
+	DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
+			EXT4_STATE_FC_COMMITTING);
+	wq = bit_waitqueue(&ei->i_state_flags,
+				EXT4_STATE_FC_COMMITTING);
+#else
+	DEFINE_WAIT_BIT(wait, &ei->i_flags,
+			EXT4_STATE_FC_COMMITTING);
+	wq = bit_waitqueue(&ei->i_flags,
+				EXT4_STATE_FC_COMMITTING);
+#endif
+	lockdep_assert_held(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+	spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	schedule();
+	finish_wait(wq, &wait.wq_entry);
 }

 /*
@ -176,22 +200,7 @@ restart:
 		goto out;

 	if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
-		wait_queue_head_t *wq;
-#if (BITS_PER_LONG < 64)
-		DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
-				EXT4_STATE_FC_COMMITTING);
-		wq = bit_waitqueue(&ei->i_state_flags,
-				   EXT4_STATE_FC_COMMITTING);
-#else
-		DEFINE_WAIT_BIT(wait, &ei->i_flags,
-				EXT4_STATE_FC_COMMITTING);
-		wq = bit_waitqueue(&ei->i_flags,
-				   EXT4_STATE_FC_COMMITTING);
-#endif
-		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
-		spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
-		schedule();
-		finish_wait(wq, &wait.wq_entry);
+		ext4_fc_wait_committing_inode(inode);
 		goto restart;
 	}
 out:
@ -234,26 +243,10 @@ restart:
 	}

 	if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
-		wait_queue_head_t *wq;
-#if (BITS_PER_LONG < 64)
-		DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
-				EXT4_STATE_FC_COMMITTING);
-		wq = bit_waitqueue(&ei->i_state_flags,
-				   EXT4_STATE_FC_COMMITTING);
-#else
-		DEFINE_WAIT_BIT(wait, &ei->i_flags,
-				EXT4_STATE_FC_COMMITTING);
-		wq = bit_waitqueue(&ei->i_flags,
-				   EXT4_STATE_FC_COMMITTING);
-#endif
-		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
-		spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
-		schedule();
-		finish_wait(wq, &wait.wq_entry);
+		ext4_fc_wait_committing_inode(inode);
 		goto restart;
 	}
-	if (!list_empty(&ei->i_fc_list))
-		list_del_init(&ei->i_fc_list);
+	list_del_init(&ei->i_fc_list);
 	spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
 }

@ -269,7 +262,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason)
 	    (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
 		return;

-	sbi->s_mount_flags |= EXT4_MF_FC_INELIGIBLE;
+	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	WARN_ON(reason >= EXT4_FC_REASON_MAX);
 	sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
 }
@ -302,14 +295,14 @@ void ext4_fc_stop_ineligible(struct super_block *sb)
 	    (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
 		return;

-	EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FC_INELIGIBLE;
+	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates);
 }

 static inline int ext4_fc_is_ineligible(struct super_block *sb)
 {
-	return (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FC_INELIGIBLE) ||
-		atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates);
+	return (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE) ||
+		atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates));
 }

 /*
@ -323,13 +316,14 @@ static inline int ext4_fc_is_ineligible(struct super_block *sb)
 * If enqueue is set, this function enqueues the inode in fast commit list.
 */
 static int ext4_fc_track_template(
-	struct inode *inode, int (*__fc_track_fn)(struct inode *, void *, bool),
+	handle_t *handle, struct inode *inode,
+	int (*__fc_track_fn)(struct inode *, void *, bool),
 	void *args, int enqueue)
 {
-	tid_t running_txn_tid;
 	bool update = false;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	tid_t tid = 0;
 	int ret;

 	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
@ -339,15 +333,13 @@ static int ext4_fc_track_template(
 	if (ext4_fc_is_ineligible(inode->i_sb))
 		return -EINVAL;

-	running_txn_tid = sbi->s_journal ?
-		sbi->s_journal->j_commit_sequence + 1 : 0;
-
+	tid = handle->h_transaction->t_tid;
 	mutex_lock(&ei->i_fc_lock);
-	if (running_txn_tid == ei->i_sync_tid) {
+	if (tid == ei->i_sync_tid) {
 		update = true;
 	} else {
 		ext4_fc_reset_inode(inode);
-		ei->i_sync_tid = running_txn_tid;
+		ei->i_sync_tid = tid;
 	}
 	ret = __fc_track_fn(inode, args, update);
 	mutex_unlock(&ei->i_fc_lock);
@ -358,7 +350,7 @@ static int ext4_fc_track_template(
 	spin_lock(&sbi->s_fc_lock);
 	if (list_empty(&EXT4_I(inode)->i_fc_list))
 		list_add_tail(&EXT4_I(inode)->i_fc_list,
-				(sbi->s_mount_flags & EXT4_MF_FC_COMMITTING) ?
+				(ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ?
 				&sbi->s_fc_q[FC_Q_STAGING] :
 				&sbi->s_fc_q[FC_Q_MAIN]);
 	spin_unlock(&sbi->s_fc_lock);
@ -384,7 +376,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
 	mutex_unlock(&ei->i_fc_lock);
 	node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS);
 	if (!node) {
-		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_MEM);
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
 		mutex_lock(&ei->i_fc_lock);
 		return -ENOMEM;
 	}
@ -397,7 +389,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
 		if (!node->fcd_name.name) {
 			kmem_cache_free(ext4_fc_dentry_cachep, node);
 			ext4_fc_mark_ineligible(inode->i_sb,
-				EXT4_FC_REASON_MEM);
+				EXT4_FC_REASON_NOMEM);
 			mutex_lock(&ei->i_fc_lock);
 			return -ENOMEM;
 		}
@ -411,7 +403,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
 	node->fcd_name.len = dentry->d_name.len;

 	spin_lock(&sbi->s_fc_lock);
-	if (sbi->s_mount_flags & EXT4_MF_FC_COMMITTING)
+	if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING))
 		list_add_tail(&node->fcd_list,
 				&sbi->s_fc_dentry_q[FC_Q_STAGING]);
 	else
@ -422,7 +414,8 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
 	return 0;
 }

-void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry)
+void __ext4_fc_track_unlink(handle_t *handle,
+		struct inode *inode, struct dentry *dentry)
 {
 	struct __track_dentry_update_args args;
 	int ret;
@ -430,12 +423,18 @@ void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry)
 	args.dentry = dentry;
 	args.op = EXT4_FC_TAG_UNLINK;

-	ret = ext4_fc_track_template(inode, __track_dentry_update,
+	ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
 					(void *)&args, 0);
 	trace_ext4_fc_track_unlink(inode, dentry, ret);
 }

-void ext4_fc_track_link(struct inode *inode, struct dentry *dentry)
+void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry)
+{
+	__ext4_fc_track_unlink(handle, d_inode(dentry), dentry);
+}
+
+void __ext4_fc_track_link(handle_t *handle,
+	struct inode *inode, struct dentry *dentry)
 {
 	struct __track_dentry_update_args args;
 	int ret;
@ -443,20 +442,26 @@ void ext4_fc_track_link(struct inode *inode, struct dentry *dentry)
 	args.dentry = dentry;
 	args.op = EXT4_FC_TAG_LINK;

-	ret = ext4_fc_track_template(inode, __track_dentry_update,
+	ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
 					(void *)&args, 0);
 	trace_ext4_fc_track_link(inode, dentry, ret);
 }

-void ext4_fc_track_create(struct inode *inode, struct dentry *dentry)
+void ext4_fc_track_link(handle_t *handle, struct dentry *dentry)
+{
+	__ext4_fc_track_link(handle, d_inode(dentry), dentry);
+}
+
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
 {
 	struct __track_dentry_update_args args;
+	struct inode *inode = d_inode(dentry);
 	int ret;

 	args.dentry = dentry;
 	args.op = EXT4_FC_TAG_CREAT;

-	ret = ext4_fc_track_template(inode, __track_dentry_update,
+	ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
 					(void *)&args, 0);
 	trace_ext4_fc_track_create(inode, dentry, ret);
 }
@ -472,14 +477,20 @@ static int __track_inode(struct inode *inode, void *arg, bool update)
 	return 0;
 }

-void ext4_fc_track_inode(struct inode *inode)
+void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
 {
 	int ret;

 	if (S_ISDIR(inode->i_mode))
 		return;

-	ret = ext4_fc_track_template(inode, __track_inode, NULL, 1);
+	if (ext4_should_journal_data(inode)) {
+		ext4_fc_mark_ineligible(inode->i_sb,
+					EXT4_FC_REASON_INODE_JOURNAL_DATA);
+		return;
+	}
+
+	ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1);
 	trace_ext4_fc_track_inode(inode, ret);
 }

@ -515,7 +526,7 @@ static int __track_range(struct inode *inode, void *arg, bool update)
 	return 0;
 }

-void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
 			 ext4_lblk_t end)
 {
 	struct __track_range_args args;
@ -527,7 +538,7 @@ void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
 	args.start = start;
 	args.end = end;

-	ret = ext4_fc_track_template(inode,  __track_range, &args, 1);
+	ret = ext4_fc_track_template(handle, inode,  __track_range, &args, 1);

 	trace_ext4_fc_track_range(inode, start, end, ret);
 }
@ -537,10 +548,11 @@ static void ext4_fc_submit_bh(struct super_block *sb)
 	int write_flags = REQ_SYNC;
 	struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;

+	/* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */
 	if (test_opt(sb, BARRIER))
 		write_flags |= REQ_FUA | REQ_PREFLUSH;
 	lock_buffer(bh);
-	clear_buffer_dirty(bh);
+	set_buffer_dirty(bh);
 	set_buffer_uptodate(bh);
 	bh->b_end_io = ext4_end_buffer_io_sync;
 	submit_bh(REQ_OP_WRITE, write_flags, bh);
@ -846,7 +858,7 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal)
 	int ret = 0;

 	spin_lock(&sbi->s_fc_lock);
-	sbi->s_mount_flags |= EXT4_MF_FC_COMMITTING;
+	ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING);
 	list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) {
 		ei = list_entry(pos, struct ext4_inode_info, i_fc_list);
 		ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
@ -900,6 +912,8 @@ static int ext4_fc_wait_inode_data_all(journal_t *journal)

 /* Commit all the directory entry updates */
 static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc)
+__acquires(&sbi->s_fc_lock)
+__releases(&sbi->s_fc_lock)
 {
 	struct super_block *sb = (struct super_block *)(journal->j_private);
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@ -996,6 +1010,13 @@ static int ext4_fc_perform_commit(journal_t *journal)
 	if (ret)
 		return ret;

+	/*
+	 * If file system device is different from journal device, issue a cache
+	 * flush before we start writing fast commit blocks.
+	 */
+	if (journal->j_fs_dev != journal->j_dev)
+		blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS);
+
 	blk_start_plug(&plug);
 	if (sbi->s_fc_bytes == 0) {
 		/*
@ -1031,8 +1052,6 @@ static int ext4_fc_perform_commit(journal_t *journal)
 		if (ret)
 			goto out;
 		spin_lock(&sbi->s_fc_lock);
-		EXT4_I(inode)->i_fc_committed_subtid =
-			atomic_read(&sbi->s_fc_subtid);
 	}
 	spin_unlock(&sbi->s_fc_lock);

@ -1131,7 +1150,7 @@ out:
 		"Fast commit ended with blks = %d, reason = %d, subtid - %d",
 		nblks, reason, subtid);
 	if (reason == EXT4_FC_REASON_FC_FAILED)
-		return jbd2_fc_end_commit_fallback(journal, commit_tid);
+		return jbd2_fc_end_commit_fallback(journal);
 	if (reason == EXT4_FC_REASON_FC_START_FAILED ||
 		reason == EXT4_FC_REASON_INELIGIBLE)
 		return jbd2_complete_transaction(journal, commit_tid);
@ -1190,8 +1209,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
 	list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
 				&sbi->s_fc_q[FC_Q_STAGING]);

-	sbi->s_mount_flags &= ~EXT4_MF_FC_COMMITTING;
-	sbi->s_mount_flags &= ~EXT4_MF_FC_INELIGIBLE;
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);

 	if (full)
 		sbi->s_fc_bytes = 0;
@ -1263,7 +1282,7 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl)
 		return 0;
 	}

-	ret = __ext4_unlink(old_parent, &entry, inode);
+	ret = __ext4_unlink(NULL, old_parent, &entry, inode);
 	/* -ENOENT ok coz it might not exist anymore. */
 	if (ret == -ENOENT)
 		ret = 0;
@ -2079,8 +2098,6 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,

 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
-	int num_fc_blocks;
-
 	/*
 	 * We set replay callback even if fast commit disabled because we may
 	 * could still have fast commit blocks that need to be replayed even if
@ -2090,21 +2107,9 @@ void ext4_fc_init(struct super_block *sb, journal_t *journal)
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
 	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
-	if (!buffer_uptodate(journal->j_sb_buffer)
-		&& ext4_read_bh_lock(journal->j_sb_buffer, REQ_META | REQ_PRIO,
-					true)) {
-		ext4_msg(sb, KERN_ERR, "I/O error on journal");
-		return;
-	}
-	num_fc_blocks = be32_to_cpu(journal->j_superblock->s_num_fc_blks);
-	if (jbd2_fc_init(journal, num_fc_blocks ? num_fc_blocks :
-					EXT4_NUM_FC_BLKS)) {
-		pr_warn("Error while enabling fast commits, turning off.");
-		ext4_clear_feature_fast_commit(sb);
-	}
 }

-const char *fc_ineligible_reasons[] = {
+static const char *fc_ineligible_reasons[] = {
 	"Extended attributes changed",
 	"Cross rename",
 	"Journal flag changed",
@ -2113,6 +2118,7 @@ const char *fc_ineligible_reasons[] = {
 	"Resize",
 	"Dir renamed",
 	"Falloc range op",
+	"Data journalling",
 	"FC Commit Failed"
 };

--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@ -3,9 +3,6 @@
 #ifndef __FAST_COMMIT_H__
 #define __FAST_COMMIT_H__

-/* Number of blocks in journal area to allocate for fast commits */
-#define EXT4_NUM_FC_BLKS		256
-
 /* Fast commit tags */
 #define EXT4_FC_TAG_ADD_RANGE		0x0001
 #define EXT4_FC_TAG_DEL_RANGE		0x0002
@ -100,11 +97,12 @@ enum {
 	EXT4_FC_REASON_XATTR = 0,
 	EXT4_FC_REASON_CROSS_RENAME,
 	EXT4_FC_REASON_JOURNAL_FLAG_CHANGE,
-	EXT4_FC_REASON_MEM,
+	EXT4_FC_REASON_NOMEM,
 	EXT4_FC_REASON_SWAP_BOOT,
 	EXT4_FC_REASON_RESIZE,
 	EXT4_FC_REASON_RENAME_DIR,
 	EXT4_FC_REASON_FALLOC_RANGE,
+	EXT4_FC_REASON_INODE_JOURNAL_DATA,
 	EXT4_FC_COMMIT_FAILED,
 	EXT4_FC_REASON_MAX
 };
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@ -761,7 +761,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!daxdev_mapping_supported(vma, dax_dev))
 		return -EOPNOTSUPP;

-	ext4_fc_start_update(inode);
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
@ -769,7 +768,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	} else {
 		vma->vm_ops = &ext4_file_vm_ops;
 	}
-	ext4_fc_stop_update(inode);
 	return 0;
 }

@ -782,13 +780,13 @@ static int ext4_sample_last_mounted(struct super_block *sb,
 	handle_t *handle;
 	int err;

-	if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
+	if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED)))
 		return 0;

 	if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
 		return 0;

-	sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
+	ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED);
 	/*
 	 * Sample where the filesystem has been mounted and
 	 * store it in the superblock for sysadmin convenience
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@ -280,7 +280,7 @@ static int ext4_getfsmap_logdev(struct super_block *sb, struct ext4_fsmap *keys,

 	/* Fabricate an rmap entry for the external log device. */
 	irec.fmr_physical = journal->j_blk_offset;
-	irec.fmr_length = journal->j_maxlen;
+	irec.fmr_length = journal->j_total_len;
 	irec.fmr_owner = EXT4_FMR_OWN_LOG;
 	irec.fmr_flags = 0;

--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@ -143,7 +143,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (sb_rdonly(inode->i_sb)) {
 		/* Make sure that we read updated s_mount_flags value */
 		smp_rmb();
-		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
+		if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))
 			ret = -EROFS;
 		goto out;
 	}
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@ -1880,6 +1880,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline)

 	ext4_write_lock_xattr(inode, &no_expand);
 	if (!ext4_has_inline_data(inode)) {
+		ext4_write_unlock_xattr(inode, &no_expand);
 		*has_inline = 0;
 		ext4_journal_stop(handle);
 		return 0;
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@ -327,6 +327,8 @@ stop_handle:
 	ext4_xattr_inode_array_free(ea_inode_array);
 	return;
 no_delete:
+	if (!list_empty(&EXT4_I(inode)->i_fc_list))
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
 	ext4_clear_inode(inode);	/* We must guarantee clearing of inode... */
 }

@ -730,7 +732,7 @@ out_sem:
 			if (ret)
 				return ret;
 		}
-		ext4_fc_track_range(inode, map->m_lblk,
+		ext4_fc_track_range(handle, inode, map->m_lblk,
 			    map->m_lblk + map->m_len - 1);
 	}

@ -2440,7 +2442,7 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 			struct super_block *sb = inode->i_sb;

 			if (ext4_forced_shutdown(EXT4_SB(sb)) ||
-			    EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+			    ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
 				goto invalidate_dirty_pages;
 			/*
 			 * Let the uper layers retry transient errors.
@ -2674,7 +2676,7 @@ static int ext4_writepages(struct address_space *mapping,
 	 * the stack trace.
 	 */
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
-		     sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+		     ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) {
 		ret = -EROFS;
 		goto out_writepages;
 	}
@ -3310,8 +3312,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 			EXT4_I(inode)->i_datasync_tid))
 			return false;
 		if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
-			return atomic_read(&EXT4_SB(inode->i_sb)->s_fc_subtid) <
-				EXT4_I(inode)->i_fc_committed_subtid;
+			return !list_empty(&EXT4_I(inode)->i_fc_list);
 		return true;
 	}

@ -4109,7 +4110,7 @@ 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);
+	ext4_fc_track_range(handle, inode, first_block, stop_block);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);

@ -5442,14 +5443,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 			}

 			if (shrink)
-				ext4_fc_track_range(inode,
+				ext4_fc_track_range(handle, 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,
+					handle, inode,
 					(oldsize > 0 ? oldsize - 1 : oldsize) >>
 					inode->i_sb->s_blocksize_bits,
 					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
@ -5699,7 +5700,7 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 		put_bh(iloc->bh);
 		return -EIO;
 	}
-	ext4_fc_track_inode(inode);
+	ext4_fc_track_inode(handle, inode);

 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@ -4477,7 +4477,7 @@ static inline void ext4_mb_show_pa(struct super_block *sb)
 {
 	ext4_group_t i, ngroups;

-	if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+	if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
 		return;

 	ngroups = ext4_get_groups_count(sb);
@ -4508,7 +4508,7 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
 {
 	struct super_block *sb = ac->ac_sb;

-	if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+	if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
 		return;

 	mb_debug(sb, "Can't allocate:"
@ -5167,7 +5167,7 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
 	struct super_block *sb = ar->inode->i_sb;
 	ext4_group_t group;
 	ext4_grpblk_t blkoff;
-	int  i;
+	int i = sb->s_blocksize;
 	ext4_fsblk_t goal, block;
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;

--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@ -2606,7 +2606,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		       bool excl)
 {
 	handle_t *handle;
-	struct inode *inode, *inode_save;
+	struct inode *inode;
 	int err, credits, retries = 0;

 	err = dquot_initialize(dir);
@ -2624,11 +2624,9 @@ retry:
 		inode->i_op = &ext4_file_inode_operations;
 		inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
-		inode_save = inode;
-		ihold(inode_save);
 		err = ext4_add_nondir(handle, dentry, &inode);
-		ext4_fc_track_create(inode_save, dentry);
-		iput(inode_save);
+		if (!err)
+			ext4_fc_track_create(handle, dentry);
 	}
 	if (handle)
 		ext4_journal_stop(handle);
@ -2643,7 +2641,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry,
 		      umode_t mode, dev_t rdev)
 {
 	handle_t *handle;
-	struct inode *inode, *inode_save;
+	struct inode *inode;
 	int err, credits, retries = 0;

 	err = dquot_initialize(dir);
@ -2660,12 +2658,9 @@ retry:
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
 		inode->i_op = &ext4_special_inode_operations;
-		inode_save = inode;
-		ihold(inode_save);
 		err = ext4_add_nondir(handle, dentry, &inode);
 		if (!err)
-			ext4_fc_track_create(inode_save, dentry);
-		iput(inode_save);
+			ext4_fc_track_create(handle, dentry);
 	}
 	if (handle)
 		ext4_journal_stop(handle);
@ -2829,7 +2824,6 @@ out_clear_inode:
 		iput(inode);
 		goto out_retry;
 	}
-	ext4_fc_track_create(inode, dentry);
 	ext4_inc_count(dir);

 	ext4_update_dx_flag(dir);
@ -2837,6 +2831,7 @@ out_clear_inode:
 	if (err)
 		goto out_clear_inode;
 	d_instantiate_new(dentry, inode);
+	ext4_fc_track_create(handle, dentry);
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);

@ -3171,7 +3166,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 		goto end_rmdir;
 	ext4_dec_count(dir);
 	ext4_update_dx_flag(dir);
-	ext4_fc_track_unlink(inode, dentry);
+	ext4_fc_track_unlink(handle, dentry);
 	retval = ext4_mark_inode_dirty(handle, dir);

 #ifdef CONFIG_UNICODE
@ -3192,13 +3187,12 @@ end_rmdir:
 	return retval;
 }

-int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
 		  struct inode *inode)
 {
 	int retval = -ENOENT;
 	struct buffer_head *bh;
 	struct ext4_dir_entry_2 *de;
-	handle_t *handle = NULL;
 	int skip_remove_dentry = 0;

 	bh = ext4_find_entry(dir, d_name, &de, NULL);
@ -3217,14 +3211,7 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
 		if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
 			skip_remove_dentry = 1;
 		else
-			goto out_bh;
-	}
-
-	handle = ext4_journal_start(dir, EXT4_HT_DIR,
-				    EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
-	if (IS_ERR(handle)) {
-		retval = PTR_ERR(handle);
-		goto out_bh;
+			goto out;
 	}

 	if (IS_DIRSYNC(dir))
@ -3233,12 +3220,12 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
 	if (!skip_remove_dentry) {
 		retval = ext4_delete_entry(handle, dir, de, bh);
 		if (retval)
-			goto out_handle;
+			goto out;
 		dir->i_ctime = dir->i_mtime = current_time(dir);
 		ext4_update_dx_flag(dir);
 		retval = ext4_mark_inode_dirty(handle, dir);
 		if (retval)
-			goto out_handle;
+			goto out;
 	} else {
 		retval = 0;
 	}
@ -3252,15 +3239,14 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
 	inode->i_ctime = current_time(inode);
 	retval = ext4_mark_inode_dirty(handle, inode);

-out_handle:
-	ext4_journal_stop(handle);
-out_bh:
+out:
 	brelse(bh);
 	return retval;
 }

 static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 {
+	handle_t *handle;
 	int retval;

 	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
@ -3278,9 +3264,16 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	if (retval)
 		goto out_trace;

-	retval = __ext4_unlink(dir, &dentry->d_name, d_inode(dentry));
+	handle = ext4_journal_start(dir, EXT4_HT_DIR,
+				    EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
+	if (IS_ERR(handle)) {
+		retval = PTR_ERR(handle);
+		goto out_trace;
+	}
+
+	retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry));
 	if (!retval)
-		ext4_fc_track_unlink(d_inode(dentry), dentry);
+		ext4_fc_track_unlink(handle, dentry);
 #ifdef CONFIG_UNICODE
 	/* VFS negative dentries are incompatible with Encoding and
 	 * Case-insensitiveness. Eventually we'll want avoid
@ -3291,6 +3284,8 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	if (IS_CASEFOLDED(dir))
 		d_invalidate(dentry);
 #endif
+	if (handle)
+		ext4_journal_stop(handle);

 out_trace:
 	trace_ext4_unlink_exit(dentry, retval);
@ -3447,7 +3442,6 @@ retry:

 	err = ext4_add_entry(handle, dentry, inode);
 	if (!err) {
-		ext4_fc_track_link(inode, dentry);
 		err = ext4_mark_inode_dirty(handle, inode);
 		/* this can happen only for tmpfile being
 		 * linked the first time
@ -3455,6 +3449,7 @@ retry:
 		if (inode->i_nlink == 1)
 			ext4_orphan_del(handle, inode);
 		d_instantiate(dentry, inode);
+		ext4_fc_track_link(handle, dentry);
 	} else {
 		drop_nlink(inode);
 		iput(inode);
@ -3915,9 +3910,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 			EXT4_FC_REASON_RENAME_DIR);
 	} else {
 		if (new.inode)
-			ext4_fc_track_unlink(new.inode, new.dentry);
-		ext4_fc_track_link(old.inode, new.dentry);
-		ext4_fc_track_unlink(old.inode, old.dentry);
+			ext4_fc_track_unlink(handle, new.dentry);
+		__ext4_fc_track_link(handle, old.inode, new.dentry);
+		__ext4_fc_track_unlink(handle, old.inode, old.dentry);
 	}

 	if (new.inode) {
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@ -686,7 +686,7 @@ static void ext4_handle_error(struct super_block *sb)
 	if (!test_opt(sb, ERRORS_CONT)) {
 		journal_t *journal = EXT4_SB(sb)->s_journal;

-		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
 		if (journal)
 			jbd2_journal_abort(journal, -EIO);
 	}
@ -904,7 +904,7 @@ void __ext4_abort(struct super_block *sb, const char *function,
 	va_end(args);

 	if (sb_rdonly(sb) == 0) {
-		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
 		if (EXT4_SB(sb)->s_journal)
 			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);

@ -1716,11 +1716,10 @@ enum {
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
-	Opt_prefetch_block_bitmaps, Opt_no_fc,
+	Opt_prefetch_block_bitmaps,
 #ifdef CONFIG_EXT4_DEBUG
-	Opt_fc_debug_max_replay,
+	Opt_fc_debug_max_replay, Opt_fc_debug_force
 #endif
-	Opt_fc_debug_force
 };

 static const match_table_t tokens = {
@ -1807,9 +1806,8 @@ static const match_table_t tokens = {
 	{Opt_init_itable, "init_itable=%u"},
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
-	{Opt_no_fc, "no_fc"},
-	{Opt_fc_debug_force, "fc_debug_force"},
 #ifdef CONFIG_EXT4_DEBUG
+	{Opt_fc_debug_force, "fc_debug_force"},
 	{Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"},
 #endif
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
@ -2027,8 +2025,8 @@ static const struct mount_opts {
 	{Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
 		       EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA),
 							MOPT_CLEAR | MOPT_Q},
-	{Opt_usrjquota, 0, MOPT_Q},
-	{Opt_grpjquota, 0, MOPT_Q},
+	{Opt_usrjquota, 0, MOPT_Q | MOPT_STRING},
+	{Opt_grpjquota, 0, MOPT_Q | MOPT_STRING},
 	{Opt_offusrjquota, 0, MOPT_Q},
 	{Opt_offgrpjquota, 0, MOPT_Q},
 	{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
@ -2039,11 +2037,9 @@ static const struct mount_opts {
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
 	{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
 	 MOPT_SET},
-	{Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
-	 MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY},
+#ifdef CONFIG_EXT4_DEBUG
 	{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
 	 MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
-#ifdef CONFIG_EXT4_DEBUG
 	{Opt_fc_debug_max_replay, 0, MOPT_GTE0},
 #endif
 	{Opt_err, 0, 0}
@ -2153,7 +2149,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt);
 		return 1;
 	case Opt_abort:
-		sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
 		return 1;
 	case Opt_i_version:
 		sb->s_flags |= SB_I_VERSION;
@ -3976,7 +3972,7 @@ int ext4_calculate_overhead(struct super_block *sb)
 	 * loaded or not
 	 */
 	if (sbi->s_journal && !sbi->s_journal_bdev)
-		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
+		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len);
 	else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
 		/* j_inum for internal journal is non-zero */
 		j_inode = ext4_get_journal_inode(sb, j_inum);
@ -4340,9 +4336,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #endif

 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
-		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n");
+		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, O_DIRECT and fast_commit support!\n");
 		/* can't mount with both data=journal and dioread_nolock. */
 		clear_opt(sb, DIOREAD_NOLOCK);
+		clear_opt2(sb, JOURNAL_FAST_COMMIT);
 		if (test_opt2(sb, EXPLICIT_DELALLOC)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
 				 "both data=journal and delalloc");
@ -4777,8 +4774,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]);
 	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]);
 	sbi->s_fc_bytes = 0;
-	sbi->s_mount_flags &= ~EXT4_MF_FC_INELIGIBLE;
-	sbi->s_mount_flags &= ~EXT4_MF_FC_COMMITTING;
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
 	spin_lock_init(&sbi->s_fc_lock);
 	memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
 	sbi->s_fc_replay_state.fc_regions = NULL;
@ -4857,6 +4854,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount_wq;
 	}

+	if (test_opt2(sb, JOURNAL_FAST_COMMIT) &&
+		!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
+					  JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) {
+		ext4_msg(sb, KERN_ERR,
+			"Failed to set fast commit journal feature");
+		goto failed_mount_wq;
+	}
+
 	/* We have now updated the journal if required, so we can
 	 * validate the data journaling mode. */
 	switch (test_opt(sb, DATA_FLAGS)) {
@ -5872,7 +5877,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}

-	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
+	if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
 		ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user");

 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
@ -5886,7 +5891,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	}

 	if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
-		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
+		if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) {
 			err = -EROFS;
 			goto restore_opts;
 		}
@ -6560,10 +6565,6 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 	brelse(bh);
 out:
 	if (inode->i_size < off + len) {
-		ext4_fc_track_range(inode,
-			(inode->i_size > 0 ? inode->i_size - 1 : 0)
-				>> inode->i_sb->s_blocksize_bits,
-			(off + len) >> inode->i_sb->s_blocksize_bits);
 		i_size_write(inode, off + len);
 		EXT4_I(inode)->i_disksize = inode->i_size;
 		err2 = ext4_mark_inode_dirty(handle, inode);
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@ -106,6 +106,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
 * for a checkpoint to free up some space in the log.
 */
 void __jbd2_log_wait_for_space(journal_t *journal)
+__acquires(&journal->j_state_lock)
+__releases(&journal->j_state_lock)
 {
 	int nblocks, space_left;
 	/* assert_spin_locked(&journal->j_state_lock); */
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@ -450,6 +450,15 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		schedule();
 		write_lock(&journal->j_state_lock);
 		finish_wait(&journal->j_fc_wait, &wait);
+		/*
+		 * TODO: by blocking fast commits here, we are increasing
+		 * fsync() latency slightly. Strictly speaking, we don't need
+		 * to block fast commits until the transaction enters T_FLUSH
+		 * state. So an optimization is possible where we block new fast
+		 * commits here and wait for existing ones to complete
+		 * just before we enter T_FLUSH. That way, the existing fast
+		 * commits and this full commit can proceed parallely.
+		 */
 	}
 	write_unlock(&journal->j_state_lock);

@ -801,7 +810,7 @@ start_journal_io:
 		if (first_block < journal->j_tail)
 			freed += journal->j_last - journal->j_first;
 		/* Update tail only if we free significant amount of space */
-		if (freed < journal->j_maxlen / 4)
+		if (freed < jbd2_journal_get_max_txn_bufs(journal))
 			update_tail = 0;
 	}
 	J_ASSERT(commit_transaction->t_state == T_COMMIT);
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@ -727,6 +727,8 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 */
 int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
 {
+	if (unlikely(is_journal_aborted(journal)))
+		return -EIO;
 	/*
 	 * Fast commits only allowed if at least one full commit has
 	 * been processed.
@ -734,10 +736,12 @@ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
 	if (!journal->j_stats.ts_tid)
 		return -EINVAL;

-	if (tid <= journal->j_commit_sequence)
-		return -EALREADY;
-
 	write_lock(&journal->j_state_lock);
+	if (tid <= journal->j_commit_sequence) {
+		write_unlock(&journal->j_state_lock);
+		return -EALREADY;
+	}
+
 	if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
 	    (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) {
 		DEFINE_WAIT(wait);
@ -777,13 +781,19 @@ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)

 int jbd2_fc_end_commit(journal_t *journal)
 {
-	return __jbd2_fc_end_commit(journal, 0, 0);
+	return __jbd2_fc_end_commit(journal, 0, false);
 }
 EXPORT_SYMBOL(jbd2_fc_end_commit);

-int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid)
+int jbd2_fc_end_commit_fallback(journal_t *journal)
 {
-	return __jbd2_fc_end_commit(journal, tid, 1);
+	tid_t tid;
+
+	read_lock(&journal->j_state_lock);
+	tid = journal->j_running_transaction ?
+		journal->j_running_transaction->t_tid : 0;
+	read_unlock(&journal->j_state_lock);
+	return __jbd2_fc_end_commit(journal, tid, true);
 }
 EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);

@ -865,7 +875,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
 	int fc_off;

 	*bh_out = NULL;
-	write_lock(&journal->j_state_lock);

 	if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
 		fc_off = journal->j_fc_off;
@ -874,7 +883,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
 	} else {
 		ret = -EINVAL;
 	}
-	write_unlock(&journal->j_state_lock);

 	if (ret)
 		return ret;
@ -887,11 +895,7 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
 	if (!bh)
 		return -ENOMEM;

-	lock_buffer(bh);

-	clear_buffer_uptodate(bh);
-	set_buffer_dirty(bh);
-	unlock_buffer(bh);
 	journal->j_fc_wbuf[fc_off] = bh;

 	*bh_out = bh;
@ -909,9 +913,7 @@ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks)
 	struct buffer_head *bh;
 	int i, j_fc_off;

-	read_lock(&journal->j_state_lock);
 	j_fc_off = journal->j_fc_off;
-	read_unlock(&journal->j_state_lock);

 	/*
 	 * Wait in reverse order to minimize chances of us being woken up before
@ -939,9 +941,7 @@ int jbd2_fc_release_bufs(journal_t *journal)
 	struct buffer_head *bh;
 	int i, j_fc_off;

-	read_lock(&journal->j_state_lock);
 	j_fc_off = journal->j_fc_off;
-	read_unlock(&journal->j_state_lock);

 	/*
 	 * Wait in reverse order to minimize chances of us being woken up before
@ -1348,23 +1348,16 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	journal->j_dev = bdev;
 	journal->j_fs_dev = fs_dev;
 	journal->j_blk_offset = start;
-	journal->j_maxlen = len;
+	journal->j_total_len = len;
 	/* We need enough buffers to write out full descriptor block. */
 	n = journal->j_blocksize / jbd2_min_tag_size();
 	journal->j_wbufsize = n;
+	journal->j_fc_wbuf = NULL;
 	journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
 					GFP_KERNEL);
 	if (!journal->j_wbuf)
 		goto err_cleanup;

-	if (journal->j_fc_wbufsize > 0) {
-		journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
-					sizeof(struct buffer_head *),
-					GFP_KERNEL);
-		if (!journal->j_fc_wbuf)
-			goto err_cleanup;
-	}
-
 	bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
 	if (!bh) {
 		pr_err("%s: Cannot get buffer for journal superblock\n",
@ -1378,23 +1371,11 @@ static journal_t *journal_init_common(struct block_device *bdev,

 err_cleanup:
 	kfree(journal->j_wbuf);
-	kfree(journal->j_fc_wbuf);
 	jbd2_journal_destroy_revoke(journal);
 	kfree(journal);
 	return NULL;
 }

-int jbd2_fc_init(journal_t *journal, int num_fc_blks)
-{
-	journal->j_fc_wbufsize = num_fc_blks;
-	journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
-				sizeof(struct buffer_head *), GFP_KERNEL);
-	if (!journal->j_fc_wbuf)
-		return -ENOMEM;
-	return 0;
-}
-EXPORT_SYMBOL(jbd2_fc_init);
-
 /* jbd2_journal_init_dev and jbd2_journal_init_inode:
 *
 * Create a journal structure assigned some fixed set of disk blocks to
@ -1512,16 +1493,7 @@ static int journal_reset(journal_t *journal)
 	}

 	journal->j_first = first;
-
-	if (jbd2_has_feature_fast_commit(journal) &&
-	    journal->j_fc_wbufsize > 0) {
-		journal->j_fc_last = last;
-		journal->j_last = last - journal->j_fc_wbufsize;
-		journal->j_fc_first = journal->j_last + 1;
-		journal->j_fc_off = 0;
-	} else {
-		journal->j_last = last;
-	}
+	journal->j_last = last;

 	journal->j_head = journal->j_first;
 	journal->j_tail = journal->j_first;
@ -1531,7 +1503,14 @@ static int journal_reset(journal_t *journal)
 	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
 	journal->j_commit_request = journal->j_commit_sequence;

-	journal->j_max_transaction_buffers = journal->j_maxlen / 4;
+	journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal);
+
+	/*
+	 * Now that journal recovery is done, turn fast commits off here. This
+	 * way, if fast commit was enabled before the crash but if now FS has
+	 * disabled it, we don't enable fast commits.
+	 */
+	jbd2_clear_feature_fast_commit(journal);

 	/*
 	 * As a special case, if the on-disk copy is already marked as needing
@ -1792,15 +1771,15 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}

-	if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
-		journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
-	else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
+	if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len)
+		journal->j_total_len = be32_to_cpu(sb->s_maxlen);
+	else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) {
 		printk(KERN_WARNING "JBD2: journal file too short\n");
 		goto out;
 	}

 	if (be32_to_cpu(sb->s_first) == 0 ||
-	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+	    be32_to_cpu(sb->s_first) >= journal->j_total_len) {
 		printk(KERN_WARNING
 			"JBD2: Invalid start block of journal: %u\n",
 			be32_to_cpu(sb->s_first));
@ -1872,6 +1851,7 @@ static int load_superblock(journal_t *journal)
 {
 	int err;
 	journal_superblock_t *sb;
+	int num_fc_blocks;

 	err = journal_get_superblock(journal);
 	if (err)
@ -1883,15 +1863,17 @@ static int load_superblock(journal_t *journal)
 	journal->j_tail = be32_to_cpu(sb->s_start);
 	journal->j_first = be32_to_cpu(sb->s_first);
 	journal->j_errno = be32_to_cpu(sb->s_errno);
+	journal->j_last = be32_to_cpu(sb->s_maxlen);

-	if (jbd2_has_feature_fast_commit(journal) &&
-	    journal->j_fc_wbufsize > 0) {
+	if (jbd2_has_feature_fast_commit(journal)) {
 		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
-		journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize;
+		num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks);
+		if (!num_fc_blocks)
+			num_fc_blocks = JBD2_MIN_FC_BLOCKS;
+		if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS)
+			journal->j_last = journal->j_fc_last - num_fc_blocks;
 		journal->j_fc_first = journal->j_last + 1;
 		journal->j_fc_off = 0;
-	} else {
-		journal->j_last = be32_to_cpu(sb->s_maxlen);
 	}

 	return 0;
@ -1954,9 +1936,6 @@ int jbd2_journal_load(journal_t *journal)
 	 */
 	journal->j_flags &= ~JBD2_ABORT;

-	if (journal->j_fc_wbufsize > 0)
-		jbd2_journal_set_features(journal, 0, 0,
-					  JBD2_FEATURE_INCOMPAT_FAST_COMMIT);
 	/* OK, we've finished with the dynamic journal bits:
 	 * reinitialise the dynamic contents of the superblock in memory
 	 * and reset them on disk. */
@ -2040,8 +2019,7 @@ int jbd2_journal_destroy(journal_t *journal)
 		jbd2_journal_destroy_revoke(journal);
 	if (journal->j_chksum_driver)
 		crypto_free_shash(journal->j_chksum_driver);
-	if (journal->j_fc_wbufsize > 0)
-		kfree(journal->j_fc_wbuf);
+	kfree(journal->j_fc_wbuf);
 	kfree(journal->j_wbuf);
 	kfree(journal);

@ -2116,6 +2094,37 @@ int jbd2_journal_check_available_features(journal_t *journal, unsigned long comp
 	return 0;
 }

+static int
+jbd2_journal_initialize_fast_commit(journal_t *journal)
+{
+	journal_superblock_t *sb = journal->j_superblock;
+	unsigned long long num_fc_blks;
+
+	num_fc_blks = be32_to_cpu(sb->s_num_fc_blks);
+	if (num_fc_blks == 0)
+		num_fc_blks = JBD2_MIN_FC_BLOCKS;
+	if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS)
+		return -ENOSPC;
+
+	/* Are we called twice? */
+	WARN_ON(journal->j_fc_wbuf != NULL);
+	journal->j_fc_wbuf = kmalloc_array(num_fc_blks,
+				sizeof(struct buffer_head *), GFP_KERNEL);
+	if (!journal->j_fc_wbuf)
+		return -ENOMEM;
+
+	journal->j_fc_wbufsize = num_fc_blks;
+	journal->j_fc_last = journal->j_last;
+	journal->j_last = journal->j_fc_last - num_fc_blks;
+	journal->j_fc_first = journal->j_last + 1;
+	journal->j_fc_off = 0;
+	journal->j_free = journal->j_last - journal->j_first;
+	journal->j_max_transaction_buffers =
+		jbd2_journal_get_max_txn_bufs(journal);
+
+	return 0;
+}
+
 /**
 * int jbd2_journal_set_features() - Mark a given journal feature in the superblock
 * @journal: Journal to act on.
@ -2159,6 +2168,13 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat,

 	sb = journal->j_superblock;

+	if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) {
+		if (jbd2_journal_initialize_fast_commit(journal)) {
+			pr_err("JBD2: Cannot enable fast commits.\n");
+			return 0;
+		}
+	}
+
 	/* Load the checksum driver if necessary */
 	if ((journal->j_chksum_driver == NULL) &&
 	    INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@ -74,8 +74,8 @@ static int do_readahead(journal_t *journal, unsigned int start)

 	/* Do up to 128K of readahead */
 	max = start + (128 * 1024 / journal->j_blocksize);
-	if (max > journal->j_maxlen)
-		max = journal->j_maxlen;
+	if (max > journal->j_total_len)
+		max = journal->j_total_len;

 	/* Do the readahead itself.  We'll submit MAXBUF buffer_heads at
 	 * a time to the block device IO layer. */
@ -134,7 +134,7 @@ static int jread(struct buffer_head **bhp, journal_t *journal,

 	*bhp = NULL;

-	if (offset >= journal->j_maxlen) {
+	if (offset >= journal->j_total_len) {
 		printk(KERN_ERR "JBD2: corrupted journal superblock\n");
 		return -EFSCORRUPTED;
 	}
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@ -195,8 +195,10 @@ static void wait_transaction_switching(journal_t *journal)
 	DEFINE_WAIT(wait);

 	if (WARN_ON(!journal->j_running_transaction ||
-		    journal->j_running_transaction->t_state != T_SWITCH))
+		    journal->j_running_transaction->t_state != T_SWITCH)) {
+		read_unlock(&journal->j_state_lock);
 		return;
+	}
 	prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
 			TASK_UNINTERRUPTIBLE);
 	read_unlock(&journal->j_state_lock);
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@ -877,7 +877,7 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
 		goto done;
 	}

-	trace_ocfs2_journal_init_maxlen(j_journal->j_maxlen);
+	trace_ocfs2_journal_init_maxlen(j_journal->j_total_len);

 	*dirty = (le32_to_cpu(di->id1.journal1.ij_flags) &
 		  OCFS2_JOURNAL_DIRTY_FL);
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@ -68,6 +68,7 @@ extern void *jbd2_alloc(size_t size, gfp_t flags);
 extern void jbd2_free(void *ptr, size_t size);

 #define JBD2_MIN_JOURNAL_BLOCKS 1024
+#define JBD2_MIN_FC_BLOCKS	256

 #ifdef __KERNEL__

@ -944,8 +945,9 @@ struct journal_s
 	/**
 	 * @j_fc_off:
 	 *
-	 * Number of fast commit blocks currently allocated.
-	 * [j_state_lock].
+	 * Number of fast commit blocks currently allocated. Accessed only
+	 * during fast commit. Currently only process can do fast commit, so
+	 * this field is not protected by any lock.
 	 */
 	unsigned long		j_fc_off;

@ -988,9 +990,9 @@ struct journal_s
 	struct block_device	*j_fs_dev;

 	/**
-	 * @j_maxlen: Total maximum capacity of the journal region on disk.
+	 * @j_total_len: Total maximum capacity of the journal region on disk.
 	 */
-	unsigned int		j_maxlen;
+	unsigned int		j_total_len;

 	/**
 	 * @j_reserved_credits:
@ -1108,8 +1110,9 @@ struct journal_s
 	struct buffer_head	**j_wbuf;

 	/**
-	 * @j_fc_wbuf: Array of fast commit bhs for
-	 * jbd2_journal_commit_transaction.
+	 * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only
+	 * during a fast commit. Currently only process can do fast commit, so
+	 * this field is not protected by any lock.
 	 */
 	struct buffer_head	**j_fc_wbuf;

@ -1614,16 +1617,20 @@ extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
 extern int jbd2_cleanup_journal_tail(journal_t *);

 /* Fast commit related APIs */
-int jbd2_fc_init(journal_t *journal, int num_fc_blks);
 int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
 int jbd2_fc_end_commit(journal_t *journal);
-int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid);
+int jbd2_fc_end_commit_fallback(journal_t *journal);
 int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
 int jbd2_submit_inode_data(struct jbd2_inode *jinode);
 int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
 int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
 int jbd2_fc_release_bufs(journal_t *journal);

+static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal)
+{
+	return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
+}
+
 /*
 * is_journal_abort
 *
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@ -100,11 +100,12 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B);
 		{ EXT4_FC_REASON_XATTR,		"XATTR"},		\
 		{ EXT4_FC_REASON_CROSS_RENAME,	"CROSS_RENAME"},	\
 		{ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \
-		{ EXT4_FC_REASON_MEM,	"NO_MEM"},			\
+		{ EXT4_FC_REASON_NOMEM,	"NO_MEM"},			\
 		{ EXT4_FC_REASON_SWAP_BOOT,	"SWAP_BOOT"},		\
 		{ EXT4_FC_REASON_RESIZE,	"RESIZE"},		\
 		{ EXT4_FC_REASON_RENAME_DIR,	"RENAME_DIR"},		\
-		{ EXT4_FC_REASON_FALLOC_RANGE,	"FALLOC_RANGE"})
+		{ EXT4_FC_REASON_FALLOC_RANGE,	"FALLOC_RANGE"},	\
+		{ EXT4_FC_REASON_INODE_JOURNAL_DATA,	"INODE_JOURNAL_DATA"})

 TRACE_EVENT(ext4_other_inode_update_time,
 	TP_PROTO(struct inode *inode, ino_t orig_ino),
@ -2917,17 +2918,18 @@ TRACE_EVENT(ext4_fc_stats,
 		    ),

 	    TP_printk("dev %d:%d fc ineligible reasons:\n"
-		      "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; "
+		      "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d; "
 		      "num_commits:%ld, ineligible: %ld, numblks: %ld",
 		      MAJOR(__entry->dev), MINOR(__entry->dev),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE),
-		      FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA),
 		      __entry->sbi->s_fc_stats.fc_num_commits,
 		      __entry->sbi->s_fc_stats.fc_ineligible_commits,
 		      __entry->sbi->s_fc_stats.fc_numblks)