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

Pull ext4 updates from Ted Ts'o:
 "Improvements to ext4's block allocator performance for very large file
  systems, especially when the file system or files which are highly
  fragmented. There is a new mount option, prefetch_block_bitmaps which
  will pull in the block bitmaps and set up the in-memory buddy bitmaps
  when the file system is initially mounted.

  Beyond that, a lot of bug fixes and cleanups. In particular, a number
  of changes to make ext4 more robust in the face of write errors or
  file system corruptions"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (46 commits)
  ext4: limit the length of per-inode prealloc list
  ext4: reorganize if statement of ext4_mb_release_context()
  ext4: add mb_debug logging when there are lost chunks
  ext4: Fix comment typo "the the".
  jbd2: clean up checksum verification in do_one_pass()
  ext4: change to use fallthrough macro
  ext4: remove unused parameter of ext4_generic_delete_entry function
  mballoc: replace seq_printf with seq_puts
  ext4: optimize the implementation of ext4_mb_good_group()
  ext4: delete invalid comments near ext4_mb_check_limits()
  ext4: fix typos in ext4_mb_regular_allocator() comment
  ext4: fix checking of directory entry validity for inline directories
  fs: prevent BUG_ON in submit_bh_wbc()
  ext4: correctly restore system zone info when remount fails
  ext4: handle add_system_zone() failure in ext4_setup_system_zone()
  ext4: fold ext4_data_block_valid_rcu() into the caller
  ext4: check journal inode extents more carefully
  ext4: don't allow overlapping system zones
  ext4: handle error of ext4_setup_system_zone() on remount
  ext4: delete the invalid BUGON in ext4_mb_load_buddy_gfp()
  ...

1 files changed, 189 insertions, 79 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0907f907c47d..ea425b49b345 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -66,10 +66,10 @@ static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
 static int ext4_show_options(struct seq_file *seq, struct dentry *root);
 static int ext4_commit_super(struct super_block *sb, int sync);
-static void ext4_mark_recovery_complete(struct super_block *sb,
+static int ext4_mark_recovery_complete(struct super_block *sb,
 					struct ext4_super_block *es);
-static void ext4_clear_journal_err(struct super_block *sb,
-				   struct ext4_super_block *es);
+static int ext4_clear_journal_err(struct super_block *sb,
+				  struct ext4_super_block *es);
 static int ext4_sync_fs(struct super_block *sb, int wait);
 static int ext4_remount(struct super_block *sb, int *flags, char *data);
 static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
@@ -744,6 +744,7 @@ void __ext4_msg(struct super_block *sb,
 	struct va_format vaf;
 	va_list args;
 
+	atomic_inc(&EXT4_SB(sb)->s_msg_count);
 	if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs"))
 		return;
 
@@ -754,9 +755,12 @@ void __ext4_msg(struct super_block *sb,
 	va_end(args);
 }
 
-#define ext4_warning_ratelimit(sb)					\
-		___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),	\
-			     "EXT4-fs warning")
+static int ext4_warning_ratelimit(struct super_block *sb)
+{
+	atomic_inc(&EXT4_SB(sb)->s_warning_count);
+	return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),
+			    "EXT4-fs warning");
+}
 
 void __ext4_warning(struct super_block *sb, const char *function,
 		    unsigned int line, const char *fmt, ...)
@@ -1123,6 +1127,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	inode_set_iversion(&ei->vfs_inode, 1);
 	spin_lock_init(&ei->i_raw_lock);
 	INIT_LIST_HEAD(&ei->i_prealloc_list);
+	atomic_set(&ei->i_prealloc_active, 0);
 	spin_lock_init(&ei->i_prealloc_lock);
 	ext4_es_init_tree(&ei->i_es_tree);
 	rwlock_init(&ei->i_es_lock);
@@ -1216,7 +1221,7 @@ void ext4_clear_inode(struct inode *inode)
 {
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 	dquot_drop(inode);
 	if (EXT4_I(inode)->jinode) {
@@ -1288,8 +1293,8 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
 	if (!page_has_buffers(page))
 		return 0;
 	if (journal)
-		return jbd2_journal_try_to_free_buffers(journal, page,
-						wait & ~__GFP_DIRECT_RECLAIM);
+		return jbd2_journal_try_to_free_buffers(journal, page);
+
 	return try_to_free_buffers(page);
 }
 
@@ -1522,6 +1527,7 @@ 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,
 };
 
 static const match_table_t tokens = {
@@ -1614,6 +1620,7 @@ static const match_table_t tokens = {
 	{Opt_inlinecrypt, "inlinecrypt"},
 	{Opt_nombcache, "nombcache"},
 	{Opt_nombcache, "no_mbcache"},	/* for backward compatibility */
+	{Opt_prefetch_block_bitmaps, "prefetch_block_bitmaps"},
 	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
 	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
 	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
@@ -1831,6 +1838,8 @@ static const struct mount_opts {
 	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
 	{Opt_test_dummy_encryption, 0, MOPT_STRING},
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
+	{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
+	 MOPT_SET},
 	{Opt_err, 0, 0}
 };
 
@@ -3213,15 +3222,34 @@ static void print_daily_error_info(struct timer_list *t)
 static int ext4_run_li_request(struct ext4_li_request *elr)
 {
 	struct ext4_group_desc *gdp = NULL;
-	ext4_group_t group, ngroups;
-	struct super_block *sb;
+	struct super_block *sb = elr->lr_super;
+	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t group = elr->lr_next_group;
 	unsigned long timeout = 0;
+	unsigned int prefetch_ios = 0;
 	int ret = 0;
 
-	sb = elr->lr_super;
-	ngroups = EXT4_SB(sb)->s_groups_count;
+	if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) {
+		elr->lr_next_group = ext4_mb_prefetch(sb, group,
+				EXT4_SB(sb)->s_mb_prefetch, &prefetch_ios);
+		if (prefetch_ios)
+			ext4_mb_prefetch_fini(sb, elr->lr_next_group,
+					      prefetch_ios);
+		trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group,
+					    prefetch_ios);
+		if (group >= elr->lr_next_group) {
+			ret = 1;
+			if (elr->lr_first_not_zeroed != ngroups &&
+			    !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) {
+				elr->lr_next_group = elr->lr_first_not_zeroed;
+				elr->lr_mode = EXT4_LI_MODE_ITABLE;
+				ret = 0;
+			}
+		}
+		return ret;
+	}
 
-	for (group = elr->lr_next_group; group < ngroups; group++) {
+	for (; group < ngroups; group++) {
 		gdp = ext4_get_group_desc(sb, group, NULL);
 		if (!gdp) {
 			ret = 1;
@@ -3239,9 +3267,10 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
 		timeout = jiffies;
 		ret = ext4_init_inode_table(sb, group,
 					    elr->lr_timeout ? 0 : 1);
+		trace_ext4_lazy_itable_init(sb, group);
 		if (elr->lr_timeout == 0) {
 			timeout = (jiffies - timeout) *
-				  elr->lr_sbi->s_li_wait_mult;
+				EXT4_SB(elr->lr_super)->s_li_wait_mult;
 			elr->lr_timeout = timeout;
 		}
 		elr->lr_next_sched = jiffies + elr->lr_timeout;
@@ -3256,15 +3285,11 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
  */
 static void ext4_remove_li_request(struct ext4_li_request *elr)
 {
-	struct ext4_sb_info *sbi;
-
 	if (!elr)
 		return;
 
-	sbi = elr->lr_sbi;
-
 	list_del(&elr->lr_request);
-	sbi->s_li_request = NULL;
+	EXT4_SB(elr->lr_super)->s_li_request = NULL;
 	kfree(elr);
 }
 
@@ -3473,7 +3498,6 @@ static int ext4_li_info_new(void)
 static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
 					    ext4_group_t start)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_li_request *elr;
 
 	elr = kzalloc(sizeof(*elr), GFP_KERNEL);
@@ -3481,8 +3505,13 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
 		return NULL;
 
 	elr->lr_super = sb;
-	elr->lr_sbi = sbi;
-	elr->lr_next_group = start;
+	elr->lr_first_not_zeroed = start;
+	if (test_opt(sb, PREFETCH_BLOCK_BITMAPS))
+		elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP;
+	else {
+		elr->lr_mode = EXT4_LI_MODE_ITABLE;
+		elr->lr_next_group = start;
+	}
 
 	/*
 	 * Randomize first schedule time of the request to
@@ -3512,8 +3541,9 @@ int ext4_register_li_request(struct super_block *sb,
 		goto out;
 	}
 
-	if (first_not_zeroed == ngroups || sb_rdonly(sb) ||
-	    !test_opt(sb, INIT_INODE_TABLE))
+	if (!test_opt(sb, PREFETCH_BLOCK_BITMAPS) &&
+	    (first_not_zeroed == ngroups || sb_rdonly(sb) ||
+	     !test_opt(sb, INIT_INODE_TABLE)))
 		goto out;
 
 	elr = ext4_li_request_new(sb, first_not_zeroed);
@@ -4710,11 +4740,13 @@ no_journal:
 
 	ext4_set_resv_clusters(sb);
 
-	err = ext4_setup_system_zone(sb);
-	if (err) {
-		ext4_msg(sb, KERN_ERR, "failed to initialize system "
-			 "zone (%d)", err);
-		goto failed_mount4a;
+	if (test_opt(sb, BLOCK_VALIDITY)) {
+		err = ext4_setup_system_zone(sb);
+		if (err) {
+			ext4_msg(sb, KERN_ERR, "failed to initialize system "
+				 "zone (%d)", err);
+			goto failed_mount4a;
+		}
 	}
 
 	ext4_ext_init(sb);
@@ -4777,12 +4809,23 @@ no_journal:
 	}
 #endif  /* CONFIG_QUOTA */
 
+	/*
+	 * Save the original bdev mapping's wb_err value which could be
+	 * 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);
+	sb->s_bdev->bd_super = sb;
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
 	EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
 	if (needs_recovery) {
 		ext4_msg(sb, KERN_INFO, "recovery complete");
-		ext4_mark_recovery_complete(sb, es);
+		err = ext4_mark_recovery_complete(sb, es);
+		if (err)
+			goto failed_mount8;
 	}
 	if (EXT4_SB(sb)->s_journal) {
 		if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
@@ -4816,6 +4859,8 @@ no_journal:
 	ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10);
 	ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10);
 	ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
+	atomic_set(&sbi->s_warning_count, 0);
+	atomic_set(&sbi->s_msg_count, 0);
 
 	kfree(orig_data);
 	return 0;
@@ -4825,10 +4870,8 @@ cantfind_ext4:
 		ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
 	goto failed_mount;
 
-#ifdef CONFIG_QUOTA
 failed_mount8:
 	ext4_unregister_sysfs(sb);
-#endif
 failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
@@ -4968,7 +5011,8 @@ static journal_t *ext4_get_journal(struct super_block *sb,
 	struct inode *journal_inode;
 	journal_t *journal;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return NULL;
 
 	journal_inode = ext4_get_journal_inode(sb, journal_inum);
 	if (!journal_inode)
@@ -4998,7 +5042,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 	struct ext4_super_block *es;
 	struct block_device *bdev;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return NULL;
 
 	bdev = ext4_blkdev_get(j_dev, sb);
 	if (bdev == NULL)
@@ -5089,8 +5134,10 @@ static int ext4_load_journal(struct super_block *sb,
 	dev_t journal_dev;
 	int err = 0;
 	int really_read_only;
+	int journal_dev_ro;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return -EFSCORRUPTED;
 
 	if (journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
@@ -5100,7 +5147,31 @@ static int ext4_load_journal(struct super_block *sb,
 	} else
 		journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
 
-	really_read_only = bdev_read_only(sb->s_bdev);
+	if (journal_inum && journal_dev) {
+		ext4_msg(sb, KERN_ERR,
+			 "filesystem has both journal inode and journal device!");
+		return -EINVAL;
+	}
+
+	if (journal_inum) {
+		journal = ext4_get_journal(sb, journal_inum);
+		if (!journal)
+			return -EINVAL;
+	} else {
+		journal = ext4_get_dev_journal(sb, journal_dev);
+		if (!journal)
+			return -EINVAL;
+	}
+
+	journal_dev_ro = bdev_read_only(journal->j_dev);
+	really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro;
+
+	if (journal_dev_ro && !sb_rdonly(sb)) {
+		ext4_msg(sb, KERN_ERR,
+			 "journal device read-only, try mounting with '-o ro'");
+		err = -EROFS;
+		goto err_out;
+	}
 
 	/*
 	 * Are we loading a blank journal or performing recovery after a
@@ -5115,27 +5186,14 @@ static int ext4_load_journal(struct super_block *sb,
 				ext4_msg(sb, KERN_ERR, "write access "
 					"unavailable, cannot proceed "
 					"(try mounting with noload)");
-				return -EROFS;
+				err = -EROFS;
+				goto err_out;
 			}
 			ext4_msg(sb, KERN_INFO, "write access will "
 			       "be enabled during recovery");
 		}
 	}
 
-	if (journal_inum && journal_dev) {
-		ext4_msg(sb, KERN_ERR, "filesystem has both journal "
-		       "and inode journals!");
-		return -EINVAL;
-	}
-
-	if (journal_inum) {
-		if (!(journal = ext4_get_journal(sb, journal_inum)))
-			return -EINVAL;
-	} else {
-		if (!(journal = ext4_get_dev_journal(sb, journal_dev)))
-			return -EINVAL;
-	}
-
 	if (!(journal->j_flags & JBD2_BARRIER))
 		ext4_msg(sb, KERN_INFO, "barriers disabled");
 
@@ -5155,12 +5213,16 @@ static int ext4_load_journal(struct super_block *sb,
 
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "error loading journal");
-		jbd2_journal_destroy(journal);
-		return err;
+		goto err_out;
 	}
 
 	EXT4_SB(sb)->s_journal = journal;
-	ext4_clear_journal_err(sb, es);
+	err = ext4_clear_journal_err(sb, es);
+	if (err) {
+		EXT4_SB(sb)->s_journal = NULL;
+		jbd2_journal_destroy(journal);
+		return err;
+	}
 
 	if (!really_read_only && journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
@@ -5171,6 +5233,10 @@ static int ext4_load_journal(struct super_block *sb,
 	}
 
 	return 0;
+
+err_out:
+	jbd2_journal_destroy(journal);
+	return err;
 }
 
 static int ext4_commit_super(struct super_block *sb, int sync)
@@ -5183,13 +5249,6 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 		return error;
 
 	/*
-	 * The superblock bh should be mapped, but it might not be if the
-	 * device was hot-removed. Not much we can do but fail the I/O.
-	 */
-	if (!buffer_mapped(sbh))
-		return error;
-
-	/*
 	 * If the file system is mounted read-only, don't update the
 	 * superblock write time.  This avoids updating the superblock
 	 * write time when we are mounting the root file system
@@ -5256,26 +5315,32 @@ static int ext4_commit_super(struct super_block *sb, int sync)
  * remounting) the filesystem readonly, then we will end up with a
  * consistent fs on disk.  Record that fact.
  */
-static void ext4_mark_recovery_complete(struct super_block *sb,
-					struct ext4_super_block *es)
+static int ext4_mark_recovery_complete(struct super_block *sb,
+				       struct ext4_super_block *es)
 {
+	int err;
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 
 	if (!ext4_has_feature_journal(sb)) {
-		BUG_ON(journal != NULL);
-		return;
+		if (journal != NULL) {
+			ext4_error(sb, "Journal got removed while the fs was "
+				   "mounted!");
+			return -EFSCORRUPTED;
+		}
+		return 0;
 	}
 	jbd2_journal_lock_updates(journal);
-	if (jbd2_journal_flush(journal) < 0)
+	err = jbd2_journal_flush(journal);
+	if (err < 0)
 		goto out;
 
 	if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) {
 		ext4_clear_feature_journal_needs_recovery(sb);
 		ext4_commit_super(sb, 1);
 	}
-
 out:
 	jbd2_journal_unlock_updates(journal);
+	return err;
 }
 
 /*
@@ -5283,14 +5348,17 @@ out:
  * has recorded an error from a previous lifetime, move that error to the
  * main filesystem now.
  */
-static void ext4_clear_journal_err(struct super_block *sb,
+static int ext4_clear_journal_err(struct super_block *sb,
 				   struct ext4_super_block *es)
 {
 	journal_t *journal;
 	int j_errno;
 	const char *errstr;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (!ext4_has_feature_journal(sb)) {
+		ext4_error(sb, "Journal got removed while the fs was mounted!");
+		return -EFSCORRUPTED;
+	}
 
 	journal = EXT4_SB(sb)->s_journal;
 
@@ -5315,6 +5383,7 @@ static void ext4_clear_journal_err(struct super_block *sb,
 		jbd2_journal_clear_err(journal);
 		jbd2_journal_update_sb_errno(journal);
 	}
+	return 0;
 }
 
 /*
@@ -5457,7 +5526,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct ext4_super_block *es;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	unsigned long old_sb_flags;
+	unsigned long old_sb_flags, vfs_flags;
 	struct ext4_mount_options old_opts;
 	int enable_quota = 0;
 	ext4_group_t g;
@@ -5500,6 +5569,14 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	if (sbi->s_journal && sbi->s_journal->j_task->io_context)
 		journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
 
+	/*
+	 * Some options can be enabled by ext4 and/or by VFS mount flag
+	 * either way we need to make sure it matches in both *flags and
+	 * s_flags. Copy those selected flags from *flags to s_flags
+	 */
+	vfs_flags = SB_LAZYTIME | SB_I_VERSION;
+	sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags);
+
 	if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) {
 		err = -EINVAL;
 		goto restore_opts;
@@ -5553,9 +5630,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 	}
 
-	if (*flags & SB_LAZYTIME)
-		sb->s_flags |= SB_LAZYTIME;
-
 	if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
 		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
 			err = -EROFS;
@@ -5585,8 +5659,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			    (sbi->s_mount_state & EXT4_VALID_FS))
 				es->s_state = cpu_to_le16(sbi->s_mount_state);
 
-			if (sbi->s_journal)
+			if (sbi->s_journal) {
+				/*
+				 * We let remount-ro finish even if marking fs
+				 * as clean failed...
+				 */
 				ext4_mark_recovery_complete(sb, es);
+			}
 			if (sbi->s_mmp_tsk)
 				kthread_stop(sbi->s_mmp_tsk);
 		} else {
@@ -5629,13 +5708,24 @@ 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
 			 * the partition.)
 			 */
-			if (sbi->s_journal)
-				ext4_clear_journal_err(sb, es);
+			if (sbi->s_journal) {
+				err = ext4_clear_journal_err(sb, es);
+				if (err)
+					goto restore_opts;
+			}
 			sbi->s_mount_state = le16_to_cpu(es->s_state);
 
 			err = ext4_setup_super(sb, es, 0);
@@ -5665,7 +5755,17 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		ext4_register_li_request(sb, first_not_zeroed);
 	}
 
-	ext4_setup_system_zone(sb);
+	/*
+	 * Handle creation of system zone data early because it can fail.
+	 * Releasing of existing data is done when we are sure remount will
+	 * succeed.
+	 */
+	if (test_opt(sb, BLOCK_VALIDITY) && !sbi->system_blks) {
+		err = ext4_setup_system_zone(sb);
+		if (err)
+			goto restore_opts;
+	}
+
 	if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) {
 		err = ext4_commit_super(sb, 1);
 		if (err)
@@ -5686,8 +5786,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		}
 	}
 #endif
+	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks)
+		ext4_release_system_zone(sb);
+
+	/*
+	 * Some options can be enabled by ext4 and/or by VFS mount flag
+	 * either way we need to make sure it matches in both *flags and
+	 * s_flags. Copy those selected flags from s_flags to *flags
+	 */
+	*flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags);
 
-	*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
 	ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
 	kfree(orig_data);
 	return 0;
@@ -5701,6 +5809,8 @@ 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)
+		ext4_release_system_zone(sb);
 #ifdef CONFIG_QUOTA
 	sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
 	for (i = 0; i < EXT4_MAXQUOTAS; i++) {