1 files changed, 290 insertions, 114 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c668f6b42374..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);
@@ -522,9 +522,6 @@ static void ext4_handle_error(struct super_block *sb)
 		smp_wmb();
 		sb->s_flags |= SB_RDONLY;
 	} else if (test_opt(sb, ERRORS_PANIC)) {
-		if (EXT4_SB(sb)->s_journal &&
-		  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
-			return;
 		panic("EXT4-fs (device %s): panic forced after error\n",
 			sb->s_id);
 	}
@@ -725,23 +722,20 @@ void __ext4_abort(struct super_block *sb, const char *function,
 	va_end(args);
 
 	if (sb_rdonly(sb) == 0) {
-		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		if (EXT4_SB(sb)->s_journal)
+			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+
+		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		/*
 		 * Make sure updated value of ->s_mount_flags will be visible
 		 * before ->s_flags update
 		 */
 		smp_wmb();
 		sb->s_flags |= SB_RDONLY;
-		if (EXT4_SB(sb)->s_journal)
-			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 	}
-	if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) {
-		if (EXT4_SB(sb)->s_journal &&
-		  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
-			return;
+	if (test_opt(sb, ERRORS_PANIC) && !system_going_down())
 		panic("EXT4-fs panic from previous error\n");
-	}
 }
 
 void __ext4_msg(struct super_block *sb,
@@ -750,6 +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;
 
@@ -760,9 +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, ...)
@@ -1129,6 +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);
@@ -1222,7 +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) {
@@ -1294,8 +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);
 }
 
@@ -1324,6 +1323,9 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 	if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode)))
 		return -EINVAL;
 
+	if (ext4_test_inode_flag(inode, EXT4_INODE_DAX))
+		return -EOPNOTSUPP;
+
 	res = ext4_convert_inline_data(inode);
 	if (res)
 		return res;
@@ -1349,7 +1351,7 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 			 * Update inode->i_flags - S_ENCRYPTED will be enabled,
 			 * S_DAX may be disabled
 			 */
-			ext4_set_inode_flags(inode);
+			ext4_set_inode_flags(inode, false);
 		}
 		return res;
 	}
@@ -1376,7 +1378,7 @@ retry:
 		 * Update inode->i_flags - S_ENCRYPTED will be enabled,
 		 * S_DAX may be disabled
 		 */
-		ext4_set_inode_flags(inode);
+		ext4_set_inode_flags(inode, false);
 		res = ext4_mark_inode_dirty(handle, inode);
 		if (res)
 			EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
@@ -1511,10 +1513,12 @@ enum {
 	Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
 	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
 	Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption,
+	Opt_inlinecrypt,
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
-	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
+	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version,
+	Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
 	Opt_nowarn_on_error, Opt_mblk_io_submit,
 	Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
@@ -1523,6 +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 = {
@@ -1581,6 +1586,9 @@ static const match_table_t tokens = {
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_i_version, "i_version"},
 	{Opt_dax, "dax"},
+	{Opt_dax_always, "dax=always"},
+	{Opt_dax_inode, "dax=inode"},
+	{Opt_dax_never, "dax=never"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
 	{Opt_warn_on_error, "warn_on_error"},
@@ -1609,8 +1617,10 @@ static const match_table_t tokens = {
 	{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"},
+	{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 */
@@ -1729,6 +1739,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
 #define MOPT_NO_EXT3	0x0200
 #define MOPT_EXT4_ONLY	(MOPT_NO_EXT2 | MOPT_NO_EXT3)
 #define MOPT_STRING	0x0400
+#define MOPT_SKIP	0x0800
 
 static const struct mount_opts {
 	int	token;
@@ -1778,7 +1789,13 @@ static const struct mount_opts {
 	{Opt_min_batch_time, 0, MOPT_GTE0},
 	{Opt_inode_readahead_blks, 0, MOPT_GTE0},
 	{Opt_init_itable, 0, MOPT_GTE0},
-	{Opt_dax, EXT4_MOUNT_DAX, MOPT_SET},
+	{Opt_dax, EXT4_MOUNT_DAX_ALWAYS, MOPT_SET | MOPT_SKIP},
+	{Opt_dax_always, EXT4_MOUNT_DAX_ALWAYS,
+		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
+	{Opt_dax_inode, EXT4_MOUNT2_DAX_INODE,
+		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
+	{Opt_dax_never, EXT4_MOUNT2_DAX_NEVER,
+		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
 	{Opt_stripe, 0, MOPT_GTE0},
 	{Opt_resuid, 0, MOPT_GTE0},
 	{Opt_resgid, 0, MOPT_GTE0},
@@ -1821,6 +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}
 };
 
@@ -1938,6 +1957,13 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 	case Opt_nolazytime:
 		sb->s_flags &= ~SB_LAZYTIME;
 		return 1;
+	case Opt_inlinecrypt:
+#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
+		sb->s_flags |= SB_INLINECRYPT;
+#else
+		ext4_msg(sb, KERN_ERR, "inline encryption not supported");
+#endif
+		return 1;
 	}
 
 	for (m = ext4_mount_opts; m->token != Opt_err; m++)
@@ -2123,13 +2149,56 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		}
 		sbi->s_jquota_fmt = m->mount_opt;
 #endif
-	} else if (token == Opt_dax) {
+	} else if (token == Opt_dax || token == Opt_dax_always ||
+		   token == Opt_dax_inode || token == Opt_dax_never) {
 #ifdef CONFIG_FS_DAX
-		ext4_msg(sb, KERN_WARNING,
-		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
-		sbi->s_mount_opt |= m->mount_opt;
+		switch (token) {
+		case Opt_dax:
+		case Opt_dax_always:
+			if (is_remount &&
+			    (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) ||
+			     (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) {
+			fail_dax_change_remount:
+				ext4_msg(sb, KERN_ERR, "can't change "
+					 "dax mount option while remounting");
+				return -1;
+			}
+			if (is_remount &&
+			    (test_opt(sb, DATA_FLAGS) ==
+			     EXT4_MOUNT_JOURNAL_DATA)) {
+				    ext4_msg(sb, KERN_ERR, "can't mount with "
+					     "both data=journal and dax");
+				    return -1;
+			}
+			ext4_msg(sb, KERN_WARNING,
+				"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+			sbi->s_mount_opt |= EXT4_MOUNT_DAX_ALWAYS;
+			sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER;
+			break;
+		case Opt_dax_never:
+			if (is_remount &&
+			    (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) ||
+			     (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS)))
+				goto fail_dax_change_remount;
+			sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
+			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
+			break;
+		case Opt_dax_inode:
+			if (is_remount &&
+			    ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) ||
+			     (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) ||
+			     !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE)))
+				goto fail_dax_change_remount;
+			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
+			sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER;
+			/* Strictly for printing options */
+			sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_INODE;
+			break;
+		}
 #else
 		ext4_msg(sb, KERN_INFO, "dax option not supported");
+		sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
+		sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
 		return -1;
 #endif
 	} else if (token == Opt_data_err_abort) {
@@ -2293,7 +2362,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 	for (m = ext4_mount_opts; m->token != Opt_err; m++) {
 		int want_set = m->flags & MOPT_SET;
 		if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) ||
-		    (m->flags & MOPT_CLEAR_ERR))
+		    (m->flags & MOPT_CLEAR_ERR) || m->flags & MOPT_SKIP)
 			continue;
 		if (!nodefs && !(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt)))
 			continue; /* skip if same as the default */
@@ -2353,6 +2422,20 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 
 	fscrypt_show_test_dummy_encryption(seq, sep, sb);
 
+	if (sb->s_flags & SB_INLINECRYPT)
+		SEQ_OPTS_PUTS("inlinecrypt");
+
+	if (test_opt(sb, DAX_ALWAYS)) {
+		if (IS_EXT2_SB(sb))
+			SEQ_OPTS_PUTS("dax");
+		else
+			SEQ_OPTS_PUTS("dax=always");
+	} else if (test_opt2(sb, DAX_NEVER)) {
+		SEQ_OPTS_PUTS("dax=never");
+	} else if (test_opt2(sb, DAX_INODE)) {
+		SEQ_OPTS_PUTS("dax=inode");
+	}
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -2383,6 +2466,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		ext4_msg(sb, KERN_ERR, "revision level too high, "
 			 "forcing read-only mode");
 		err = -EROFS;
+		goto done;
 	}
 	if (read_only)
 		goto done;
@@ -3138,15 +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;
@@ -3164,9 +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;
@@ -3181,15 +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);
 }
 
@@ -3398,7 +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);
@@ -3406,8 +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
@@ -3437,8 +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);
@@ -4017,7 +4122,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "both data=journal and delalloc");
 			goto failed_mount;
 		}
-		if (test_opt(sb, DAX)) {
+		if (test_opt(sb, DAX_ALWAYS)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
 				 "both data=journal and dax");
 			goto failed_mount;
@@ -4127,13 +4232,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
-	if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
+	if (bdev_dax_supported(sb->s_bdev, blocksize))
+		set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+
+	if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
 		if (ext4_has_feature_inline_data(sb)) {
 			ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem"
 					" that may contain inline data");
 			goto failed_mount;
 		}
-		if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
+		if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) {
 			ext4_msg(sb, KERN_ERR,
 				"DAX unsupported by block device.");
 			goto failed_mount;
@@ -4632,11 +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);
@@ -4699,12 +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)
@@ -4738,6 +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;
@@ -4747,10 +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:
@@ -4890,7 +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)
@@ -4920,7 +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)
@@ -5011,8 +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)) {
@@ -5022,7 +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
@@ -5037,27 +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");
 
@@ -5077,12 +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)) {
@@ -5093,6 +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)
@@ -5105,13 +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
@@ -5178,26 +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;
 }
 
 /*
@@ -5205,14 +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;
 
@@ -5237,6 +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;
 }
 
 /*
@@ -5379,7 +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;
@@ -5422,6 +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;
@@ -5447,12 +5602,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			err = -EINVAL;
 			goto restore_opts;
 		}
-		if (test_opt(sb, DAX)) {
-			ext4_msg(sb, KERN_ERR, "can't mount with "
-				 "both data=journal and dax");
-			err = -EINVAL;
-			goto restore_opts;
-		}
 	} else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) {
 		if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
@@ -5468,12 +5617,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
-	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
-		ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
-			"dax flag with busy inodes while remounting");
-		sbi->s_mount_opt ^= EXT4_MOUNT_DAX;
-	}
-
 	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
 		ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user");
 
@@ -5487,9 +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;
@@ -5519,8 +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 {
@@ -5563,13 +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);
@@ -5599,7 +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)
@@ -5620,8 +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;
@@ -5635,6 +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++) {