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, 307 insertions, 45 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8b2736283481..03373471131c 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -141,27 +141,115 @@ MODULE_ALIAS_FS("ext3");
 MODULE_ALIAS("ext3");
 #define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
 
+
+static inline void __ext4_read_bh(struct buffer_head *bh, int op_flags,
+				  bh_end_io_t *end_io)
+{
+	/*
+	 * buffer's verified bit is no longer valid after reading from
+	 * disk again due to write out error, clear it to make sure we
+	 * recheck the buffer contents.
+	 */
+	clear_buffer_verified(bh);
+
+	bh->b_end_io = end_io ? end_io : end_buffer_read_sync;
+	get_bh(bh);
+	submit_bh(REQ_OP_READ, op_flags, bh);
+}
+
+void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
+			 bh_end_io_t *end_io)
+{
+	BUG_ON(!buffer_locked(bh));
+
+	if (ext4_buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return;
+	}
+	__ext4_read_bh(bh, op_flags, end_io);
+}
+
+int ext4_read_bh(struct buffer_head *bh, int op_flags, bh_end_io_t *end_io)
+{
+	BUG_ON(!buffer_locked(bh));
+
+	if (ext4_buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return 0;
+	}
+
+	__ext4_read_bh(bh, op_flags, end_io);
+
+	wait_on_buffer(bh);
+	if (buffer_uptodate(bh))
+		return 0;
+	return -EIO;
+}
+
+int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait)
+{
+	if (trylock_buffer(bh)) {
+		if (wait)
+			return ext4_read_bh(bh, op_flags, NULL);
+		ext4_read_bh_nowait(bh, op_flags, NULL);
+		return 0;
+	}
+	if (wait) {
+		wait_on_buffer(bh);
+		if (buffer_uptodate(bh))
+			return 0;
+		return -EIO;
+	}
+	return 0;
+}
+
 /*
- * This works like sb_bread() except it uses ERR_PTR for error
+ * This works like __bread_gfp() except it uses ERR_PTR for error
  * returns.  Currently with sb_bread it's impossible to distinguish
  * between ENOMEM and EIO situations (since both result in a NULL
  * return.
  */
-struct buffer_head *
-ext4_sb_bread(struct super_block *sb, sector_t block, int op_flags)
+static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb,
+					       sector_t block, int op_flags,
+					       gfp_t gfp)
 {
-	struct buffer_head *bh = sb_getblk(sb, block);
+	struct buffer_head *bh;
+	int ret;
 
+	bh = sb_getblk_gfp(sb, block, gfp);
 	if (bh == NULL)
 		return ERR_PTR(-ENOMEM);
 	if (ext4_buffer_uptodate(bh))
 		return bh;
-	ll_rw_block(REQ_OP_READ, REQ_META | op_flags, 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 | op_flags, true);
+	if (ret) {
+		put_bh(bh);
+		return ERR_PTR(ret);
+	}
+	return bh;
+}
+
+struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block,
+				   int op_flags)
+{
+	return __ext4_sb_bread_gfp(sb, block, op_flags, __GFP_MOVABLE);
+}
+
+struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
+					    sector_t block)
+{
+	return __ext4_sb_bread_gfp(sb, block, 0, 0);
+}
+
+void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block)
+{
+	struct buffer_head *bh = sb_getblk_gfp(sb, block, 0);
+
+	if (likely(bh)) {
+		ext4_read_bh_lock(bh, REQ_RAHEAD, false);
+		brelse(bh);
+	}
 }
 
 static int ext4_verify_csum_type(struct super_block *sb,
@@ -201,7 +289,18 @@ void ext4_superblock_csum_set(struct super_block *sb)
 	if (!ext4_has_metadata_csum(sb))
 		return;
 
+	/*
+	 * Locking the superblock prevents the scenario
+	 * where:
+	 *  1) a first thread pauses during checksum calculation.
+	 *  2) a second thread updates the superblock, recalculates
+	 *     the checksum, and updates s_checksum
+	 *  3) the first thread resumes and finishes its checksum calculation
+	 *     and updates s_checksum with a potentially stale or torn value.
+	 */
+	lock_buffer(EXT4_SB(sb)->s_sbh);
 	es->s_checksum = ext4_superblock_csum(sb, es);
+	unlock_buffer(EXT4_SB(sb)->s_sbh);
 }
 
 ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
@@ -472,6 +571,89 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 	spin_unlock(&sbi->s_md_lock);
 }
 
+/*
+ * This writepage callback for write_cache_pages()
+ * takes care of a few cases after page cleaning.
+ *
+ * write_cache_pages() already checks for dirty pages
+ * and calls clear_page_dirty_for_io(), which we want,
+ * to write protect the pages.
+ *
+ * However, we may have to redirty a page (see below.)
+ */
+static int ext4_journalled_writepage_callback(struct page *page,
+					      struct writeback_control *wbc,
+					      void *data)
+{
+	transaction_t *transaction = (transaction_t *) data;
+	struct buffer_head *bh, *head;
+	struct journal_head *jh;
+
+	bh = head = page_buffers(page);
+	do {
+		/*
+		 * We have to redirty a page in these cases:
+		 * 1) If buffer is dirty, it means the page was dirty because it
+		 * contains a buffer that needs checkpointing. So the dirty bit
+		 * needs to be preserved so that checkpointing writes the buffer
+		 * properly.
+		 * 2) If buffer is not part of the committing transaction
+		 * (we may have just accidentally come across this buffer because
+		 * inode range tracking is not exact) or if the currently running
+		 * transaction already contains this buffer as well, dirty bit
+		 * needs to be preserved so that the buffer gets writeprotected
+		 * properly on running transaction's commit.
+		 */
+		jh = bh2jh(bh);
+		if (buffer_dirty(bh) ||
+		    (jh && (jh->b_transaction != transaction ||
+			    jh->b_next_transaction))) {
+			redirty_page_for_writepage(wbc, page);
+			goto out;
+		}
+	} while ((bh = bh->b_this_page) != head);
+
+out:
+	return AOP_WRITEPAGE_ACTIVATE;
+}
+
+static int ext4_journalled_submit_inode_data_buffers(struct jbd2_inode *jinode)
+{
+	struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
+	struct writeback_control wbc = {
+		.sync_mode =  WB_SYNC_ALL,
+		.nr_to_write = LONG_MAX,
+		.range_start = jinode->i_dirty_start,
+		.range_end = jinode->i_dirty_end,
+        };
+
+	return write_cache_pages(mapping, &wbc,
+				 ext4_journalled_writepage_callback,
+				 jinode->i_transaction);
+}
+
+static int ext4_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
+{
+	int ret;
+
+	if (ext4_should_journal_data(jinode->i_vfs_inode))
+		ret = ext4_journalled_submit_inode_data_buffers(jinode);
+	else
+		ret = jbd2_journal_submit_inode_data_buffers(jinode);
+
+	return ret;
+}
+
+static int ext4_journal_finish_inode_data_buffers(struct jbd2_inode *jinode)
+{
+	int ret = 0;
+
+	if (!ext4_should_journal_data(jinode->i_vfs_inode))
+		ret = jbd2_journal_finish_inode_data_buffers(jinode);
+
+	return ret;
+}
+
 static bool system_going_down(void)
 {
 	return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF
@@ -939,10 +1121,10 @@ static void ext4_blkdev_put(struct block_device *bdev)
 static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
 {
 	struct block_device *bdev;
-	bdev = sbi->journal_bdev;
+	bdev = sbi->s_journal_bdev;
 	if (bdev) {
 		ext4_blkdev_put(bdev);
-		sbi->journal_bdev = NULL;
+		sbi->s_journal_bdev = NULL;
 	}
 }
 
@@ -1073,14 +1255,14 @@ static void ext4_put_super(struct super_block *sb)
 
 	sync_blockdev(sb->s_bdev);
 	invalidate_bdev(sb->s_bdev);
-	if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
+	if (sbi->s_journal_bdev && sbi->s_journal_bdev != sb->s_bdev) {
 		/*
 		 * Invalidate the journal device's buffers.  We don't want them
 		 * floating about in memory - the physical journal device may
 		 * hotswapped, and it breaks the `ro-after' testing code.
 		 */
-		sync_blockdev(sbi->journal_bdev);
-		invalidate_bdev(sbi->journal_bdev);
+		sync_blockdev(sbi->s_journal_bdev);
+		invalidate_bdev(sbi->s_journal_bdev);
 		ext4_blkdev_remove(sbi);
 	}
 
@@ -1149,6 +1331,8 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_unwritten, 0);
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
+	ext4_fc_init_inode(&ei->vfs_inode);
+	mutex_init(&ei->i_fc_lock);
 	return &ei->vfs_inode;
 }
 
@@ -1166,6 +1350,10 @@ static int ext4_drop_inode(struct inode *inode)
 static void ext4_free_in_core_inode(struct inode *inode)
 {
 	fscrypt_free_inode(inode);
+	if (!list_empty(&(EXT4_I(inode)->i_fc_list))) {
+		pr_warn("%s: inode %ld still in fc list",
+			__func__, inode->i_ino);
+	}
 	kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
 }
 
@@ -1191,6 +1379,7 @@ static void init_once(void *foo)
 	init_rwsem(&ei->i_data_sem);
 	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
+	ext4_fc_init_inode(&ei->vfs_inode);
 }
 
 static int __init init_inodecache(void)
@@ -1219,6 +1408,7 @@ static void destroy_inodecache(void)
 
 void ext4_clear_inode(struct inode *inode)
 {
+	ext4_fc_del(inode);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	ext4_discard_preallocations(inode, 0);
@@ -1526,7 +1716,11 @@ 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_prefetch_block_bitmaps, Opt_no_fc,
+#ifdef CONFIG_EXT4_DEBUG
+	Opt_fc_debug_max_replay,
+#endif
+	Opt_fc_debug_force
 };
 
 static const match_table_t tokens = {
@@ -1613,6 +1807,11 @@ 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_max_replay, "fc_debug_max_replay=%u"},
+#endif
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
@@ -1739,6 +1938,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
 #define MOPT_EXT4_ONLY	(MOPT_NO_EXT2 | MOPT_NO_EXT3)
 #define MOPT_STRING	0x0400
 #define MOPT_SKIP	0x0800
+#define	MOPT_2		0x1000
 
 static const struct mount_opts {
 	int	token;
@@ -1839,6 +2039,13 @@ 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},
+	{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}
 };
 
@@ -2048,6 +2255,10 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		sbi->s_li_wait_mult = arg;
 	} else if (token == Opt_max_dir_size_kb) {
 		sbi->s_max_dir_size_kb = arg;
+#ifdef CONFIG_EXT4_DEBUG
+	} else if (token == Opt_fc_debug_max_replay) {
+		sbi->s_fc_debug_max_replay = arg;
+#endif
 	} else if (token == Opt_stripe) {
 		sbi->s_stripe = arg;
 	} else if (token == Opt_resuid) {
@@ -2216,10 +2427,17 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			WARN_ON(1);
 			return -1;
 		}
-		if (arg != 0)
-			sbi->s_mount_opt |= m->mount_opt;
-		else
-			sbi->s_mount_opt &= ~m->mount_opt;
+		if (m->flags & MOPT_2) {
+			if (arg != 0)
+				sbi->s_mount_opt2 |= m->mount_opt;
+			else
+				sbi->s_mount_opt2 &= ~m->mount_opt;
+		} else {
+			if (arg != 0)
+				sbi->s_mount_opt |= m->mount_opt;
+			else
+				sbi->s_mount_opt &= ~m->mount_opt;
+		}
 	}
 	return 1;
 }
@@ -2436,6 +2654,9 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PUTS("dax=inode");
 	}
 
+	if (test_opt2(sb, JOURNAL_FAST_COMMIT))
+		SEQ_OPTS_PUTS("fast_commit");
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -3754,7 +3975,7 @@ int ext4_calculate_overhead(struct super_block *sb)
 	 * Add the internal journal blocks whether the journal has been
 	 * loaded or not
 	 */
-	if (sbi->s_journal && !sbi->journal_bdev)
+	if (sbi->s_journal && !sbi->s_journal_bdev)
 		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
 	else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
 		/* j_inum for internal journal is non-zero */
@@ -3868,8 +4089,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		logical_sb_block = sb_block;
 	}
 
-	if (!(bh = sb_bread_unmovable(sb, logical_sb_block))) {
+	bh = ext4_sb_bread_unmovable(sb, logical_sb_block);
+	if (IS_ERR(bh)) {
 		ext4_msg(sb, KERN_ERR, "unable to read superblock");
+		ret = PTR_ERR(bh);
+		bh = NULL;
 		goto out_fail;
 	}
 	/*
@@ -3936,6 +4160,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
+	if (ext4_has_feature_fast_commit(sb))
+		set_opt2(sb, JOURNAL_FAST_COMMIT);
 	/* don't forget to enable journal_csum when metadata_csum is enabled. */
 	if (ext4_has_metadata_csum(sb))
 		set_opt(sb, JOURNAL_CHECKSUM);
@@ -4265,10 +4491,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		brelse(bh);
 		logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
 		offset = do_div(logical_sb_block, blocksize);
-		bh = sb_bread_unmovable(sb, logical_sb_block);
-		if (!bh) {
+		bh = ext4_sb_bread_unmovable(sb, logical_sb_block);
+		if (IS_ERR(bh)) {
 			ext4_msg(sb, KERN_ERR,
 			       "Can't read superblock on 2nd try");
+			ret = PTR_ERR(bh);
+			bh = NULL;
 			goto failed_mount;
 		}
 		es = (struct ext4_super_block *)(bh->b_data + offset);
@@ -4480,18 +4708,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/* Pre-read the descriptors into the buffer cache */
 	for (i = 0; i < db_count; i++) {
 		block = descriptor_loc(sb, logical_sb_block, i);
-		sb_breadahead_unmovable(sb, block);
+		ext4_sb_breadahead_unmovable(sb, block);
 	}
 
 	for (i = 0; i < db_count; i++) {
 		struct buffer_head *bh;
 
 		block = descriptor_loc(sb, logical_sb_block, i);
-		bh = sb_bread_unmovable(sb, block);
-		if (!bh) {
+		bh = ext4_sb_bread_unmovable(sb, block);
+		if (IS_ERR(bh)) {
 			ext4_msg(sb, KERN_ERR,
 			       "can't read group descriptor %d", i);
 			db_count = i;
+			ret = PTR_ERR(bh);
+			bh = NULL;
 			goto failed_mount2;
 		}
 		rcu_read_lock();
@@ -4539,6 +4769,26 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
 
+	/* Initialize fast commit stuff */
+	atomic_set(&sbi->s_fc_subtid, 0);
+	atomic_set(&sbi->s_fc_ineligible_updates, 0);
+	INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_MAIN]);
+	INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_STAGING]);
+	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_state &= ~EXT4_FC_INELIGIBLE;
+	sbi->s_mount_state &= ~EXT4_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;
+	sbi->s_fc_replay_state.fc_regions_size = 0;
+	sbi->s_fc_replay_state.fc_regions_used = 0;
+	sbi->s_fc_replay_state.fc_regions_valid = 0;
+	sbi->s_fc_replay_state.fc_modified_inodes = NULL;
+	sbi->s_fc_replay_state.fc_modified_inodes_size = 0;
+	sbi->s_fc_replay_state.fc_modified_inodes_used = 0;
+
 	sb->s_root = NULL;
 
 	needs_recovery = (es->s_last_orphan != 0 ||
@@ -4588,6 +4838,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM;
 		clear_opt(sb, JOURNAL_CHECKSUM);
 		clear_opt(sb, DATA_FLAGS);
+		clear_opt2(sb, JOURNAL_FAST_COMMIT);
 		sbi->s_journal = NULL;
 		needs_recovery = 0;
 		goto no_journal;
@@ -4646,6 +4897,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 
 	sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
+	sbi->s_journal->j_submit_inode_data_buffers =
+		ext4_journal_submit_inode_data_buffers;
+	sbi->s_journal->j_finish_inode_data_buffers =
+		ext4_journal_finish_inode_data_buffers;
 
 no_journal:
 	if (!test_opt(sb, NO_MBCACHE)) {
@@ -4748,6 +5003,7 @@ no_journal:
 			goto failed_mount4a;
 		}
 	}
+	ext4_fc_replay_cleanup(sb);
 
 	ext4_ext_init(sb);
 	err = ext4_mb_init(sb);
@@ -4814,9 +5070,8 @@ no_journal:
 	 * used to detect the metadata async write error.
 	 */
 	spin_lock_init(&sbi->s_bdev_wb_lock);
-	if (!sb_rdonly(sb))
-		errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
-					 &sbi->s_bdev_wb_err);
+	errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
+				 &sbi->s_bdev_wb_err);
 	sb->s_bdev->bd_super = sb;
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
@@ -4872,6 +5127,7 @@ cantfind_ext4:
 
 failed_mount8:
 	ext4_unregister_sysfs(sb);
+	kobject_put(&sbi->s_kobj);
 failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
@@ -4960,6 +5216,7 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
 	journal->j_commit_interval = sbi->s_commit_interval;
 	journal->j_min_batch_time = sbi->s_min_batch_time;
 	journal->j_max_batch_time = sbi->s_max_batch_time;
+	ext4_fc_init(sb, journal);
 
 	write_lock(&journal->j_state_lock);
 	if (test_opt(sb, BARRIER))
@@ -5102,9 +5359,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 		goto out_bdev;
 	}
 	journal->j_private = sb;
-	ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &journal->j_sb_buffer);
-	wait_on_buffer(journal->j_sb_buffer);
-	if (!buffer_uptodate(journal->j_sb_buffer)) {
+	if (ext4_read_bh_lock(journal->j_sb_buffer, REQ_META | REQ_PRIO, true)) {
 		ext4_msg(sb, KERN_ERR, "I/O error on journal device");
 		goto out_journal;
 	}
@@ -5114,7 +5369,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 			be32_to_cpu(journal->j_superblock->s_nr_users));
 		goto out_journal;
 	}
-	EXT4_SB(sb)->journal_bdev = bdev;
+	EXT4_SB(sb)->s_journal_bdev = bdev;
 	ext4_init_journal_params(sb, journal);
 	return journal;
 
@@ -5708,14 +5963,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			}
 
 			/*
-			 * Update the original bdev mapping's wb_err value
-			 * which could be used to detect the metadata async
-			 * write error.
-			 */
-			errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
-						 &sbi->s_bdev_wb_err);
-
-			/*
 			 * Mounting a RDONLY partition read-write, so reread
 			 * and store the current valid flag.  (It may have
 			 * been changed by e2fsck since we originally mounted
@@ -5760,7 +6007,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	 * Releasing of existing data is done when we are sure remount will
 	 * succeed.
 	 */
-	if (test_opt(sb, BLOCK_VALIDITY) && !sbi->system_blks) {
+	if (test_opt(sb, BLOCK_VALIDITY) && !sbi->s_system_blks) {
 		err = ext4_setup_system_zone(sb);
 		if (err)
 			goto restore_opts;
@@ -5786,7 +6033,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		}
 	}
 #endif
-	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks)
+	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks)
 		ext4_release_system_zone(sb);
 
 	/*
@@ -5809,7 +6056,7 @@ restore_opts:
 	sbi->s_commit_interval = old_opts.s_commit_interval;
 	sbi->s_min_batch_time = old_opts.s_min_batch_time;
 	sbi->s_max_batch_time = old_opts.s_max_batch_time;
-	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks)
+	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks)
 		ext4_release_system_zone(sb);
 #ifdef CONFIG_QUOTA
 	sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
@@ -6042,6 +6289,11 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 	/* Quotafile not on the same filesystem? */
 	if (path->dentry->d_sb != sb)
 		return -EXDEV;
+
+	/* Quota already enabled for this file? */
+	if (IS_NOQUOTA(d_inode(path->dentry)))
+		return -EBUSY;
+
 	/* Journaling quota? */
 	if (EXT4_SB(sb)->s_qf_names[type]) {
 		/* Quotafile not in fs root? */
@@ -6309,6 +6561,10 @@ 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);
@@ -6437,6 +6693,11 @@ static int __init ext4_init_fs(void)
 	err = init_inodecache();
 	if (err)
 		goto out1;
+
+	err = ext4_fc_init_dentry_cache();
+	if (err)
+		goto out05;
+
 	register_as_ext3();
 	register_as_ext2();
 	err = register_filesystem(&ext4_fs_type);
@@ -6447,6 +6708,7 @@ static int __init ext4_init_fs(void)
 out:
 	unregister_as_ext2();
 	unregister_as_ext3();
+out05:
 	destroy_inodecache();
 out1:
 	ext4_exit_mballoc();