1 files changed, 222 insertions, 174 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0f931d0c227d..a50e5c31b937 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -161,8 +161,14 @@ MODULE_ALIAS("ext3");
 
 
 static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
-				  bh_end_io_t *end_io)
+				  bh_end_io_t *end_io, bool simu_fail)
 {
+	if (simu_fail) {
+		clear_buffer_uptodate(bh);
+		unlock_buffer(bh);
+		return;
+	}
+
 	/*
 	 * buffer's verified bit is no longer valid after reading from
 	 * disk again due to write out error, clear it to make sure we
@@ -176,7 +182,7 @@ static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
 }
 
 void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
-			 bh_end_io_t *end_io)
+			 bh_end_io_t *end_io, bool simu_fail)
 {
 	BUG_ON(!buffer_locked(bh));
 
@@ -184,10 +190,11 @@ void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
 		unlock_buffer(bh);
 		return;
 	}
-	__ext4_read_bh(bh, op_flags, end_io);
+	__ext4_read_bh(bh, op_flags, end_io, simu_fail);
 }
 
-int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io)
+int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
+		 bh_end_io_t *end_io, bool simu_fail)
 {
 	BUG_ON(!buffer_locked(bh));
 
@@ -196,7 +203,7 @@ int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io
 		return 0;
 	}
 
-	__ext4_read_bh(bh, op_flags, end_io);
+	__ext4_read_bh(bh, op_flags, end_io, simu_fail);
 
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
@@ -208,10 +215,10 @@ int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait)
 {
 	lock_buffer(bh);
 	if (!wait) {
-		ext4_read_bh_nowait(bh, op_flags, NULL);
+		ext4_read_bh_nowait(bh, op_flags, NULL, false);
 		return 0;
 	}
-	return ext4_read_bh(bh, op_flags, NULL);
+	return ext4_read_bh(bh, op_flags, NULL, false);
 }
 
 /*
@@ -244,7 +251,7 @@ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb,
 struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block,
 				   blk_opf_t op_flags)
 {
-	gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_inode->i_mapping,
+	gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping,
 			~__GFP_FS) | __GFP_MOVABLE;
 
 	return __ext4_sb_bread_gfp(sb, block, op_flags, gfp);
@@ -253,7 +260,7 @@ struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block,
 struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
 					    sector_t block)
 {
-	gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_inode->i_mapping,
+	gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping,
 			~__GFP_FS);
 
 	return __ext4_sb_bread_gfp(sb, block, 0, gfp);
@@ -266,7 +273,7 @@ void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block)
 
 	if (likely(bh)) {
 		if (trylock_buffer(bh))
-			ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL);
+			ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL, false);
 		brelse(bh);
 	}
 }
@@ -346,9 +353,9 @@ __u32 ext4_free_group_clusters(struct super_block *sb,
 __u32 ext4_free_inodes_count(struct super_block *sb,
 			      struct ext4_group_desc *bg)
 {
-	return le16_to_cpu(bg->bg_free_inodes_count_lo) |
+	return le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_lo)) |
 		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
-		 (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
+		 (__u32)le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_hi)) << 16 : 0);
 }
 
 __u32 ext4_used_dirs_count(struct super_block *sb,
@@ -402,9 +409,9 @@ void ext4_free_group_clusters_set(struct super_block *sb,
 void ext4_free_inodes_set(struct super_block *sb,
 			  struct ext4_group_desc *bg, __u32 count)
 {
-	bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
+	WRITE_ONCE(bg->bg_free_inodes_count_lo, cpu_to_le16((__u16)count));
 	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
-		bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
+		WRITE_ONCE(bg->bg_free_inodes_count_hi, cpu_to_le16(count >> 16));
 }
 
 void ext4_used_dirs_set(struct super_block *sb,
@@ -492,22 +499,6 @@ static void ext4_maybe_update_superblock(struct super_block *sb)
 		schedule_work(&EXT4_SB(sb)->s_sb_upd_work);
 }
 
-/*
- * The del_gendisk() function uninitializes the disk-specific data
- * structures, including the bdi structure, without telling anyone
- * else.  Once this happens, any attempt to call mark_buffer_dirty()
- * (for example, by ext4_commit_super), will cause a kernel OOPS.
- * This is a kludge to prevent these oops until we can put in a proper
- * hook in del_gendisk() to inform the VFS and file system layers.
- */
-static int block_device_ejected(struct super_block *sb)
-{
-	struct inode *bd_inode = sb->s_bdev->bd_inode;
-	struct backing_dev_info *bdi = inode_to_bdi(bd_inode);
-
-	return bdi->dev == NULL;
-}
-
 static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 {
 	struct super_block		*sb = journal->j_private;
@@ -751,11 +742,12 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
 
 	ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 	/*
-	 * Make sure updated value of ->s_mount_flags will be visible before
-	 * ->s_flags update
+	 * EXT4_FLAGS_SHUTDOWN was set which stops all filesystem
+	 * modifications. We don't set SB_RDONLY because that requires
+	 * sb->s_umount semaphore and setting it without proper remount
+	 * procedure is confusing code such as freeze_super() leading to
+	 * deadlocks and other problems.
 	 */
-	smp_wmb();
-	sb->s_flags |= SB_RDONLY;
 }
 
 static void update_super_work(struct work_struct *work)
@@ -1343,6 +1335,9 @@ static void ext4_put_super(struct super_block *sb)
 
 	ext4_group_desc_free(sbi);
 	ext4_flex_groups_free(sbi);
+
+	WARN_ON_ONCE(!(sbi->s_mount_state & EXT4_ERROR_FS) &&
+		     percpu_counter_sum(&sbi->s_dirtyclusters_counter));
 	ext4_percpu_param_destroy(sbi);
 #ifdef CONFIG_QUOTA
 	for (int i = 0; i < EXT4_MAXQUOTAS; i++)
@@ -1359,14 +1354,14 @@ static void ext4_put_super(struct super_block *sb)
 
 	sync_blockdev(sb->s_bdev);
 	invalidate_bdev(sb->s_bdev);
-	if (sbi->s_journal_bdev_handle) {
+	if (sbi->s_journal_bdev_file) {
 		/*
 		 * 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->s_journal_bdev_handle->bdev);
-		invalidate_bdev(sbi->s_journal_bdev_handle->bdev);
+		sync_blockdev(file_bdev(sbi->s_journal_bdev_file));
+		invalidate_bdev(file_bdev(sbi->s_journal_bdev_file));
 	}
 
 	ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
@@ -1385,8 +1380,6 @@ static void ext4_put_super(struct super_block *sb)
 	 */
 	kobject_put(&sbi->s_kobj);
 	wait_for_completion(&sbi->s_kobj_unregister);
-	if (sbi->s_chksum_driver)
-		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->s_blockgroup_lock);
 	fs_put_dax(sbi->s_daxdev, NULL);
 	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
@@ -1473,7 +1466,8 @@ static void ext4_destroy_inode(struct inode *inode)
 		dump_stack();
 	}
 
-	if (EXT4_I(inode)->i_reserved_data_blocks)
+	if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ERROR_FS) &&
+	    WARN_ON_ONCE(EXT4_I(inode)->i_reserved_data_blocks))
 		ext4_msg(inode->i_sb, KERN_ERR,
 			 "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!",
 			 inode->i_ino, EXT4_I(inode),
@@ -1500,8 +1494,7 @@ static int __init init_inodecache(void)
 {
 	ext4_inode_cachep = kmem_cache_create_usercopy("ext4_inode_cache",
 				sizeof(struct ext4_inode_info), 0,
-				(SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
-					SLAB_ACCOUNT),
+				SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
 				offsetof(struct ext4_inode_info, i_data),
 				sizeof_field(struct ext4_inode_info, i_data),
 				init_once);
@@ -1600,7 +1593,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
 			     unsigned int flags);
 
-static struct dquot **ext4_get_dquots(struct inode *inode)
+static struct dquot __rcu **ext4_get_dquots(struct inode *inode)
 {
 	return EXT4_I(inode)->i_dquot;
 }
@@ -1724,10 +1717,6 @@ static const struct constant_table ext4_param_dax[] = {
 	{}
 };
 
-/* String parameter that allows empty argument */
-#define fsparam_string_empty(NAME, OPT) \
-	__fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL)
-
 /*
  * Mount option specification
  * We don't use fsparam_flag_no because of the way we set the
@@ -1742,8 +1731,8 @@ static const struct fs_parameter_spec ext4_param_specs[] = {
 	fsparam_flag	("bsdgroups",		Opt_grpid),
 	fsparam_flag	("nogrpid",		Opt_nogrpid),
 	fsparam_flag	("sysvgroups",		Opt_nogrpid),
-	fsparam_u32	("resgid",		Opt_resgid),
-	fsparam_u32	("resuid",		Opt_resuid),
+	fsparam_gid	("resgid",		Opt_resgid),
+	fsparam_uid	("resuid",		Opt_resuid),
 	fsparam_u32	("sb",			Opt_sb),
 	fsparam_enum	("errors",		Opt_errors, ext4_param_errors),
 	fsparam_flag	("nouid32",		Opt_nouid32),
@@ -2079,8 +2068,7 @@ static int unnote_qf_name(struct fs_context *fc, int qtype)
 {
 	struct ext4_fs_context *ctx = fc->fs_private;
 
-	if (ctx->s_qf_names[qtype])
-		kfree(ctx->s_qf_names[qtype]);
+	kfree(ctx->s_qf_names[qtype]);
 
 	ctx->s_qf_names[qtype] = NULL;
 	ctx->qname_spec |= 1 << qtype;
@@ -2113,16 +2101,16 @@ static int ext4_parse_test_dummy_encryption(const struct fs_parameter *param,
 }
 
 #define EXT4_SET_CTX(name)						\
-static inline void ctx_set_##name(struct ext4_fs_context *ctx,		\
-				  unsigned long flag)			\
+static inline __maybe_unused						\
+void ctx_set_##name(struct ext4_fs_context *ctx, unsigned long flag)	\
 {									\
 	ctx->mask_s_##name |= flag;					\
 	ctx->vals_s_##name |= flag;					\
 }
 
 #define EXT4_CLEAR_CTX(name)						\
-static inline void ctx_clear_##name(struct ext4_fs_context *ctx,	\
-				    unsigned long flag)			\
+static inline __maybe_unused						\
+void ctx_clear_##name(struct ext4_fs_context *ctx, unsigned long flag)	\
 {									\
 	ctx->mask_s_##name |= flag;					\
 	ctx->vals_s_##name &= ~flag;					\
@@ -2149,8 +2137,6 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	struct fs_parse_result result;
 	const struct mount_opts *m;
 	int is_remount;
-	kuid_t uid;
-	kgid_t gid;
 	int token;
 
 	token = fs_parse(fc, ext4_param_specs, param, &result);
@@ -2292,23 +2278,11 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		ctx->spec |= EXT4_SPEC_s_stripe;
 		return 0;
 	case Opt_resuid:
-		uid = make_kuid(current_user_ns(), result.uint_32);
-		if (!uid_valid(uid)) {
-			ext4_msg(NULL, KERN_ERR, "Invalid uid value %d",
-				 result.uint_32);
-			return -EINVAL;
-		}
-		ctx->s_resuid = uid;
+		ctx->s_resuid = result.uid;
 		ctx->spec |= EXT4_SPEC_s_resuid;
 		return 0;
 	case Opt_resgid:
-		gid = make_kgid(current_user_ns(), result.uint_32);
-		if (!gid_valid(gid)) {
-			ext4_msg(NULL, KERN_ERR, "Invalid gid value %d",
-				 result.uint_32);
-			return -EINVAL;
-		}
-		ctx->s_resgid = gid;
+		ctx->s_resgid = result.gid;
 		ctx->spec |= EXT4_SPEC_s_resgid;
 		return 0;
 	case Opt_journal_dev:
@@ -2485,8 +2459,7 @@ static int parse_options(struct fs_context *fc, char *options)
 			param.size = v_len;
 
 			ret = ext4_parse_param(fc, &param);
-			if (param.string)
-				kfree(param.string);
+			kfree(param.string);
 			if (ret < 0)
 				return ret;
 		}
@@ -3062,6 +3035,9 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PUTS("mb_optimize_scan=1");
 	}
 
+	if (nodefs && !test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS))
+		SEQ_OPTS_PUTS("prefetch_block_bitmaps");
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -3078,7 +3054,7 @@ int ext4_seq_options_show(struct seq_file *seq, void *offset)
 
 	seq_puts(seq, sb_rdonly(sb) ? "ro" : "rw");
 	rc = _ext4_show_options(seq, sb, 1);
-	seq_puts(seq, "\n");
+	seq_putc(seq, '\n');
 	return rc;
 }
 
@@ -3609,14 +3585,12 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly)
 		return 0;
 	}
 
-#if !IS_ENABLED(CONFIG_UNICODE)
-	if (ext4_has_feature_casefold(sb)) {
+	if (!IS_ENABLED(CONFIG_UNICODE) && ext4_has_feature_casefold(sb)) {
 		ext4_msg(sb, KERN_ERR,
 			 "Filesystem with casefold feature cannot be "
 			 "mounted without CONFIG_UNICODE");
 		return 0;
 	}
-#endif
 
 	if (readonly)
 		return 1;
@@ -3743,12 +3717,12 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
 		ret = 1;
 
 	if (!ret) {
-		start_time = ktime_get_real_ns();
+		start_time = ktime_get_ns();
 		ret = ext4_init_inode_table(sb, group,
 					    elr->lr_timeout ? 0 : 1);
 		trace_ext4_lazy_itable_init(sb, group);
 		if (elr->lr_timeout == 0) {
-			elr->lr_timeout = nsecs_to_jiffies((ktime_get_real_ns() - start_time) *
+			elr->lr_timeout = nsecs_to_jiffies((ktime_get_ns() - start_time) *
 				EXT4_SB(elr->lr_super)->s_li_wait_mult);
 		}
 		elr->lr_next_sched = jiffies + elr->lr_timeout;
@@ -3808,8 +3782,9 @@ static int ext4_lazyinit_thread(void *arg)
 
 cont_thread:
 	while (true) {
-		next_wakeup = MAX_JIFFY_OFFSET;
+		bool next_wakeup_initialized = false;
 
+		next_wakeup = 0;
 		mutex_lock(&eli->li_list_mtx);
 		if (list_empty(&eli->li_request_list)) {
 			mutex_unlock(&eli->li_list_mtx);
@@ -3822,8 +3797,11 @@ cont_thread:
 					 lr_request);
 
 			if (time_before(jiffies, elr->lr_next_sched)) {
-				if (time_before(elr->lr_next_sched, next_wakeup))
+				if (!next_wakeup_initialized ||
+				    time_before(elr->lr_next_sched, next_wakeup)) {
 					next_wakeup = elr->lr_next_sched;
+					next_wakeup_initialized = true;
+				}
 				continue;
 			}
 			if (down_read_trylock(&elr->lr_super->s_umount)) {
@@ -3851,16 +3829,18 @@ cont_thread:
 				elr->lr_next_sched = jiffies +
 					get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ);
 			}
-			if (time_before(elr->lr_next_sched, next_wakeup))
+			if (!next_wakeup_initialized ||
+			    time_before(elr->lr_next_sched, next_wakeup)) {
 				next_wakeup = elr->lr_next_sched;
+				next_wakeup_initialized = true;
+			}
 		}
 		mutex_unlock(&eli->li_list_mtx);
 
 		try_to_freeze();
 
 		cur = jiffies;
-		if ((time_after_eq(cur, next_wakeup)) ||
-		    (MAX_JIFFY_OFFSET == next_wakeup)) {
+		if (!next_wakeup_initialized || time_after_eq(cur, next_wakeup)) {
 			cond_resched();
 			continue;
 		}
@@ -4233,7 +4213,7 @@ 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->s_journal_bdev_handle)
+	if (sbi->s_journal && !sbi->s_journal_bdev_file)
 		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 */
@@ -4422,22 +4402,6 @@ static int ext4_handle_clustersize(struct super_block *sb)
 		}
 		sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
 			le32_to_cpu(es->s_log_block_size);
-		sbi->s_clusters_per_group =
-			le32_to_cpu(es->s_clusters_per_group);
-		if (sbi->s_clusters_per_group > sb->s_blocksize * 8) {
-			ext4_msg(sb, KERN_ERR,
-				 "#clusters per group too big: %lu",
-				 sbi->s_clusters_per_group);
-			return -EINVAL;
-		}
-		if (sbi->s_blocks_per_group !=
-		    (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) {
-			ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and "
-				 "clusters per group (%lu) inconsistent",
-				 sbi->s_blocks_per_group,
-				 sbi->s_clusters_per_group);
-			return -EINVAL;
-		}
 	} else {
 		if (clustersize != sb->s_blocksize) {
 			ext4_msg(sb, KERN_ERR,
@@ -4451,9 +4415,21 @@ static int ext4_handle_clustersize(struct super_block *sb)
 				 sbi->s_blocks_per_group);
 			return -EINVAL;
 		}
-		sbi->s_clusters_per_group = sbi->s_blocks_per_group;
 		sbi->s_cluster_bits = 0;
 	}
+	sbi->s_clusters_per_group = le32_to_cpu(es->s_clusters_per_group);
+	if (sbi->s_clusters_per_group > sb->s_blocksize * 8) {
+		ext4_msg(sb, KERN_ERR, "#clusters per group too big: %lu",
+			 sbi->s_clusters_per_group);
+		return -EINVAL;
+	}
+	if (sbi->s_blocks_per_group !=
+	    (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) {
+		ext4_msg(sb, KERN_ERR,
+			 "blocks per group (%lu) and clusters per group (%lu) inconsistent",
+			 sbi->s_blocks_per_group, sbi->s_clusters_per_group);
+		return -EINVAL;
+	}
 	sbi->s_cluster_ratio = clustersize / sb->s_blocksize;
 
 	/* Do we have standard group size of clustersize * 8 blocks ? */
@@ -4463,6 +4439,36 @@ static int ext4_handle_clustersize(struct super_block *sb)
 	return 0;
 }
 
+/*
+ * ext4_atomic_write_init: Initializes filesystem min & max atomic write units.
+ * @sb: super block
+ * TODO: Later add support for bigalloc
+ */
+static void ext4_atomic_write_init(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct block_device *bdev = sb->s_bdev;
+
+	if (!bdev_can_atomic_write(bdev))
+		return;
+
+	if (!ext4_has_feature_extents(sb))
+		return;
+
+	sbi->s_awu_min = max(sb->s_blocksize,
+			      bdev_atomic_write_unit_min_bytes(bdev));
+	sbi->s_awu_max = min(sb->s_blocksize,
+			      bdev_atomic_write_unit_max_bytes(bdev));
+	if (sbi->s_awu_min && sbi->s_awu_max &&
+	    sbi->s_awu_min <= sbi->s_awu_max) {
+		ext4_msg(sb, KERN_NOTICE, "Supports (experimental) DIO atomic writes awu_min: %u, awu_max: %u",
+			 sbi->s_awu_min, sbi->s_awu_max);
+	} else {
+		sbi->s_awu_min = 0;
+		sbi->s_awu_max = 0;
+	}
+}
+
 static void ext4_fast_commit_init(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -4626,15 +4632,6 @@ static int ext4_init_metadata_csum(struct super_block *sb, struct ext4_super_blo
 	ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE,
 				ext4_orphan_file_block_trigger);
 
-	/* Load the checksum driver */
-	sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
-	if (IS_ERR(sbi->s_chksum_driver)) {
-		int ret = PTR_ERR(sbi->s_chksum_driver);
-		ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver.");
-		sbi->s_chksum_driver = NULL;
-		return ret;
-	}
-
 	/* Check superblock checksum */
 	if (!ext4_superblock_csum_verify(sb, es)) {
 		ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with "
@@ -5126,16 +5123,27 @@ out:
 	return ret;
 }
 
-static void ext4_hash_info_init(struct super_block *sb)
+static int ext4_hash_info_init(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
 	unsigned int i;
 
+	sbi->s_def_hash_version = es->s_def_hash_version;
+
+	if (sbi->s_def_hash_version > DX_HASH_LAST) {
+		ext4_msg(sb, KERN_ERR,
+			 "Invalid default hash set in the superblock");
+		return -EINVAL;
+	} else if (sbi->s_def_hash_version == DX_HASH_SIPHASH) {
+		ext4_msg(sb, KERN_ERR,
+			 "SIPHASH is not a valid default hash value");
+		return -EINVAL;
+	}
+
 	for (i = 0; i < 4; i++)
 		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
 
-	sbi->s_def_hash_version = es->s_def_hash_version;
 	if (ext4_has_feature_dir_index(sb)) {
 		i = le32_to_cpu(es->s_flags);
 		if (i & EXT2_FLAGS_UNSIGNED_HASH)
@@ -5153,6 +5161,7 @@ static void ext4_hash_info_init(struct super_block *sb)
 #endif
 		}
 	}
+	return 0;
 }
 
 static int ext4_block_group_meta_init(struct super_block *sb, int silent)
@@ -5204,6 +5213,18 @@ static int ext4_block_group_meta_init(struct super_block *sb, int silent)
 	return 0;
 }
 
+/*
+ * It's hard to get stripe aligned blocks if stripe is not aligned with
+ * cluster, just disable stripe and alert user to simplify code and avoid
+ * stripe aligned allocation which will rarely succeed.
+ */
+static bool ext4_is_stripe_incompatible(struct super_block *sb, unsigned long stripe)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	return (stripe > 0 && sbi->s_cluster_ratio > 1 &&
+		stripe % sbi->s_cluster_ratio != 0);
+}
+
 static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 {
 	struct ext4_super_block *es = NULL;
@@ -5280,6 +5301,9 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	/* i_version is always enabled now */
 	sb->s_flags |= SB_I_VERSION;
 
+	/* HSM events are allowed by default. */
+	sb->s_iflags |= SB_I_ALLOW_HSM;
+
 	err = ext4_check_feature_compatibility(sb, es, silent);
 	if (err)
 		goto failed_mount;
@@ -5288,7 +5312,9 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	if (err)
 		goto failed_mount;
 
-	ext4_hash_info_init(sb);
+	err = ext4_hash_info_init(sb);
+	if (err)
+		goto failed_mount;
 
 	err = ext4_handle_clustersize(sb);
 	if (err)
@@ -5311,13 +5337,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		goto failed_mount3;
 
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
-	/*
-	 * It's hard to get stripe aligned blocks if stripe is not aligned with
-	 * cluster, just disable stripe and alert user to simpfy code and avoid
-	 * stripe aligned allocation which will rarely successes.
-	 */
-	if (sbi->s_stripe > 0 && sbi->s_cluster_ratio > 1 &&
-	    sbi->s_stripe % sbi->s_cluster_ratio != 0) {
+	if (ext4_is_stripe_incompatible(sb, sbi->s_stripe)) {
 		ext4_msg(sb, KERN_WARNING,
 			 "stripe (%lu) is not aligned with cluster size (%u), "
 			 "stripe is disabled",
@@ -5346,11 +5366,15 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		sb->s_qcop = &ext4_qctl_operations;
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
 #endif
-	memcpy(&sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
+	super_set_uuid(sb, es->s_uuid, sizeof(es->s_uuid));
+	super_set_sysfs_name_bdev(sb);
 
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
 
+	spin_lock_init(&sbi->s_bdev_wb_lock);
+
+	ext4_atomic_write_init(sb);
 	ext4_fast_commit_init(sb);
 
 	sb->s_root = NULL;
@@ -5484,6 +5508,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		goto failed_mount4;
 	}
 
+	generic_set_sb_d_ops(sb);
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		ext4_msg(sb, KERN_ERR, "get root dentry failed");
@@ -5555,19 +5580,15 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	if (err)
 		goto failed_mount6;
 
-	err = ext4_register_sysfs(sb);
-	if (err)
-		goto failed_mount7;
-
 	err = ext4_init_orphan_info(sb);
 	if (err)
-		goto failed_mount8;
+		goto failed_mount7;
 #ifdef CONFIG_QUOTA
 	/* Enable quota usage during mount. */
 	if (ext4_has_feature_quota(sb) && !sb_rdonly(sb)) {
 		err = ext4_enable_quotas(sb);
 		if (err)
-			goto failed_mount9;
+			goto failed_mount8;
 	}
 #endif  /* CONFIG_QUOTA */
 
@@ -5575,8 +5596,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	 * 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);
-	errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
+	errseq_check_and_advance(&sb->s_bdev->bd_mapping->wb_err,
 				 &sbi->s_bdev_wb_err);
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
@@ -5593,7 +5613,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		ext4_msg(sb, KERN_INFO, "recovery complete");
 		err = ext4_mark_recovery_complete(sb, es);
 		if (err)
-			goto failed_mount10;
+			goto failed_mount9;
 	}
 
 	if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev))
@@ -5610,15 +5630,17 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	atomic_set(&sbi->s_warning_count, 0);
 	atomic_set(&sbi->s_msg_count, 0);
 
+	/* Register sysfs after all initializations are complete. */
+	err = ext4_register_sysfs(sb);
+	if (err)
+		goto failed_mount9;
+
 	return 0;
 
-failed_mount10:
+failed_mount9:
 	ext4_quotas_off(sb, EXT4_MAXQUOTAS);
-failed_mount9: __maybe_unused
+failed_mount8: __maybe_unused
 	ext4_release_orphan_info(sb);
-failed_mount8:
-	ext4_unregister_sysfs(sb);
-	kobject_put(&sbi->s_kobj);
 failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
@@ -5653,13 +5675,10 @@ failed_mount3a:
 failed_mount3:
 	/* flush s_sb_upd_work before sbi destroy */
 	flush_work(&sbi->s_sb_upd_work);
-	del_timer_sync(&sbi->s_err_report);
 	ext4_stop_mmpd(sbi);
+	del_timer_sync(&sbi->s_err_report);
 	ext4_group_desc_free(sbi);
 failed_mount:
-	if (sbi->s_chksum_driver)
-		crypto_free_shash(sbi->s_chksum_driver);
-
 #if IS_ENABLED(CONFIG_UNICODE)
 	utf8_unload(sb->s_encoding);
 #endif
@@ -5670,9 +5689,9 @@ failed_mount:
 #endif
 	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
 	brelse(sbi->s_sbh);
-	if (sbi->s_journal_bdev_handle) {
-		invalidate_bdev(sbi->s_journal_bdev_handle->bdev);
-		bdev_release(sbi->s_journal_bdev_handle);
+	if (sbi->s_journal_bdev_file) {
+		invalidate_bdev(file_bdev(sbi->s_journal_bdev_file));
+		bdev_fput(sbi->s_journal_bdev_file);
 	}
 out_fail:
 	invalidate_bdev(sb->s_bdev);
@@ -5842,30 +5861,30 @@ static journal_t *ext4_open_inode_journal(struct super_block *sb,
 	return journal;
 }
 
-static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb,
+static struct file *ext4_get_journal_blkdev(struct super_block *sb,
 					dev_t j_dev, ext4_fsblk_t *j_start,
 					ext4_fsblk_t *j_len)
 {
 	struct buffer_head *bh;
 	struct block_device *bdev;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int hblock, blocksize;
 	ext4_fsblk_t sb_block;
 	unsigned long offset;
 	struct ext4_super_block *es;
 	int errno;
 
-	bdev_handle = bdev_open_by_dev(j_dev,
+	bdev_file = bdev_file_open_by_dev(j_dev,
 		BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
 		sb, &fs_holder_ops);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		ext4_msg(sb, KERN_ERR,
 			 "failed to open journal device unknown-block(%u,%u) %ld",
-			 MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_handle));
-		return bdev_handle;
+			 MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_file));
+		return bdev_file;
 	}
 
-	bdev = bdev_handle->bdev;
+	bdev = file_bdev(bdev_file);
 	blocksize = sb->s_blocksize;
 	hblock = bdev_logical_block_size(bdev);
 	if (blocksize < hblock) {
@@ -5877,7 +5896,7 @@ static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb,
 
 	sb_block = EXT4_MIN_BLOCK_SIZE / blocksize;
 	offset = EXT4_MIN_BLOCK_SIZE % blocksize;
-	set_blocksize(bdev, blocksize);
+	set_blocksize(bdev_file, blocksize);
 	bh = __bread(bdev, sb_block, blocksize);
 	if (!bh) {
 		ext4_msg(sb, KERN_ERR, "couldn't read superblock of "
@@ -5912,12 +5931,12 @@ static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb,
 	*j_start = sb_block + 1;
 	*j_len = ext4_blocks_count(es);
 	brelse(bh);
-	return bdev_handle;
+	return bdev_file;
 
 out_bh:
 	brelse(bh);
 out_bdev:
-	bdev_release(bdev_handle);
+	bdev_fput(bdev_file);
 	return ERR_PTR(errno);
 }
 
@@ -5927,14 +5946,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb,
 	journal_t *journal;
 	ext4_fsblk_t j_start;
 	ext4_fsblk_t j_len;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int errno = 0;
 
-	bdev_handle = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len);
-	if (IS_ERR(bdev_handle))
-		return ERR_CAST(bdev_handle);
+	bdev_file = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len);
+	if (IS_ERR(bdev_file))
+		return ERR_CAST(bdev_file);
 
-	journal = jbd2_journal_init_dev(bdev_handle->bdev, sb->s_bdev, j_start,
+	journal = jbd2_journal_init_dev(file_bdev(bdev_file), sb->s_bdev, j_start,
 					j_len, sb->s_blocksize);
 	if (IS_ERR(journal)) {
 		ext4_msg(sb, KERN_ERR, "failed to create device journal");
@@ -5949,14 +5968,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb,
 		goto out_journal;
 	}
 	journal->j_private = sb;
-	EXT4_SB(sb)->s_journal_bdev_handle = bdev_handle;
+	EXT4_SB(sb)->s_journal_bdev_file = bdev_file;
 	ext4_init_journal_params(sb, journal);
 	return journal;
 
 out_journal:
 	jbd2_journal_destroy(journal);
 out_bdev:
-	bdev_release(bdev_handle);
+	bdev_fput(bdev_file);
 	return ERR_PTR(errno);
 }
 
@@ -6134,8 +6153,8 @@ static void ext4_update_super(struct super_block *sb)
 			__ext4_update_tstamp(&es->s_first_error_time,
 					     &es->s_first_error_time_hi,
 					     sbi->s_first_error_time);
-			strncpy(es->s_first_error_func, sbi->s_first_error_func,
-				sizeof(es->s_first_error_func));
+			strtomem_pad(es->s_first_error_func,
+				     sbi->s_first_error_func, 0);
 			es->s_first_error_line =
 				cpu_to_le32(sbi->s_first_error_line);
 			es->s_first_error_ino =
@@ -6148,8 +6167,7 @@ static void ext4_update_super(struct super_block *sb)
 		__ext4_update_tstamp(&es->s_last_error_time,
 				     &es->s_last_error_time_hi,
 				     sbi->s_last_error_time);
-		strncpy(es->s_last_error_func, sbi->s_last_error_func,
-			sizeof(es->s_last_error_func));
+		strtomem_pad(es->s_last_error_func, sbi->s_last_error_func, 0);
 		es->s_last_error_line = cpu_to_le32(sbi->s_last_error_line);
 		es->s_last_error_ino = cpu_to_le32(sbi->s_last_error_ino);
 		es->s_last_error_block = cpu_to_le64(sbi->s_last_error_block);
@@ -6176,8 +6194,6 @@ static int ext4_commit_super(struct super_block *sb)
 
 	if (!sbh)
 		return -EINVAL;
-	if (block_device_ejected(sb))
-		return -ENODEV;
 
 	ext4_update_super(sb);
 
@@ -6321,7 +6337,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (unlikely(ext4_forced_shutdown(sb)))
-		return 0;
+		return -EIO;
 
 	trace_ext4_sync_fs(sb, wait);
 	flush_workqueue(sbi->rsv_conversion_wq);
@@ -6483,6 +6499,15 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 
 	}
 
+	if ((ctx->spec & EXT4_SPEC_s_stripe) &&
+	    ext4_is_stripe_incompatible(sb, ctx->s_stripe)) {
+		ext4_msg(sb, KERN_WARNING,
+			 "stripe (%lu) is not aligned with cluster size (%u), "
+			 "stripe is disabled",
+			 ctx->s_stripe, sbi->s_cluster_ratio);
+		ctx->s_stripe = 0;
+	}
+
 	/*
 	 * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause
 	 * two calls to ext4_should_dioread_nolock() to return inconsistent
@@ -6529,8 +6554,12 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 		goto restore_opts;
 	}
 
-	if (test_opt2(sb, ABORT))
-		ext4_abort(sb, ESHUTDOWN, "Abort forced by user");
+	if ((old_opts.s_mount_opt & EXT4_MOUNT_DELALLOC) &&
+	    !test_opt(sb, DELALLOC)) {
+		ext4_msg(sb, KERN_ERR, "can't disable delalloc during remount");
+		err = -EINVAL;
+		goto restore_opts;
+	}
 
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
 		(test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
@@ -6700,6 +6729,14 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 	if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb))
 		ext4_stop_mmpd(sbi);
 
+	/*
+	 * Handle aborting the filesystem as the last thing during remount to
+	 * avoid obsure errors during remount when some option changes fail to
+	 * apply due to shutdown filesystem.
+	 */
+	if (test_opt2(sb, ABORT))
+		ext4_abort(sb, ESHUTDOWN, "Abort forced by user");
+
 	return 0;
 
 restore_opts:
@@ -6864,6 +6901,10 @@ static int ext4_write_dquot(struct dquot *dquot)
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 	ret = dquot_commit(dquot);
+	if (ret < 0)
+		ext4_error_err(dquot->dq_sb, -ret,
+			       "Failed to commit dquot type %d",
+			       dquot->dq_id.type);
 	err = ext4_journal_stop(handle);
 	if (!ret)
 		ret = err;
@@ -6880,6 +6921,10 @@ static int ext4_acquire_dquot(struct dquot *dquot)
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 	ret = dquot_acquire(dquot);
+	if (ret < 0)
+		ext4_error_err(dquot->dq_sb, -ret,
+			      "Failed to acquire dquot type %d",
+			      dquot->dq_id.type);
 	err = ext4_journal_stop(handle);
 	if (!ret)
 		ret = err;
@@ -6899,6 +6944,10 @@ static int ext4_release_dquot(struct dquot *dquot)
 		return PTR_ERR(handle);
 	}
 	ret = dquot_release(dquot);
+	if (ret < 0)
+		ext4_error_err(dquot->dq_sb, -ret,
+			       "Failed to release dquot type %d",
+			       dquot->dq_id.type);
 	err = ext4_journal_stop(handle);
 	if (!ret)
 		ret = err;
@@ -7314,12 +7363,12 @@ static inline int ext3_feature_set_ok(struct super_block *sb)
 static void ext4_kill_sb(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct bdev_handle *handle = sbi ? sbi->s_journal_bdev_handle : NULL;
+	struct file *bdev_file = sbi ? sbi->s_journal_bdev_file : NULL;
 
 	kill_block_super(sb);
 
-	if (handle)
-		bdev_release(handle);
+	if (bdev_file)
+		bdev_fput(bdev_file);
 }
 
 static struct file_system_type ext4_fs_type = {
@@ -7328,7 +7377,7 @@ static struct file_system_type ext4_fs_type = {
 	.init_fs_context	= ext4_init_fs_context,
 	.parameters		= ext4_param_specs,
 	.kill_sb		= ext4_kill_sb,
-	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
+	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
 };
 MODULE_ALIAS_FS("ext4");
 
@@ -7434,6 +7483,5 @@ static void __exit ext4_exit_fs(void)
 MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
 MODULE_DESCRIPTION("Fourth Extended Filesystem");
 MODULE_LICENSE("GPL");
-MODULE_SOFTDEP("pre: crc32c");
 module_init(ext4_init_fs)
 module_exit(ext4_exit_fs)