Lots of cleanups and bug fixes this cycle, primarily in the block

allocation, extent management, fast commit, and journalling.
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEK2m5VNv+CHkogTfJ8vlZVpUNgaMFAmbsGRcACgkQ8vlZVpUN
 gaP+pwgAop3LUpOFQ9dPRTR3+37AJI8adfabfLIDkEkoVA7lyYY/6Q8pcQ0rklq3
 wE1WxrJ7MaE1GaFCwRIDIL6TP+uYRK0pPjqbFBxGakhDc+WXrTcALOWWofb7J7PL
 FLwP264lRRfKfpMHdK8bx6YHnEN8425PR+ZNXGVPsw+wjo72mmnq54w+ct1iOKiw
 dKfIrwwCGKlBsNdYHS/XsSx7MMK8e7nsKoSq0UtpJ4PqF11/asOtlYYODc4hd27U
 E3I3UDKuntmz+meAscDejOJqQk5FT184HIt/Y5JfetKU2zpUFj9IKqXDzMjijdaj
 vGn9RkTXfJdxMPm1ouF2R6KIRJollg==
 =V7+A
 -----END PGP SIGNATURE-----

Merge tag 'ext4_for_linus-6.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Lots of cleanups and bug fixes this cycle, primarily in the block
  allocation, extent management, fast commit, and journalling"

* tag 'ext4_for_linus-6.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (93 commits)
  ext4: convert EXT4_B2C(sbi->s_stripe) users to EXT4_NUM_B2C
  ext4: check stripe size compatibility on remount as well
  ext4: fix i_data_sem unlock order in ext4_ind_migrate()
  ext4: remove the special buffer dirty handling in do_journal_get_write_access
  ext4: fix a potential assertion failure due to improperly dirtied buffer
  ext4: hoist ext4_block_write_begin and replace the __block_write_begin
  ext4: persist the new uptodate buffers in ext4_journalled_zero_new_buffers
  ext4: dax: keep orphan list before truncate overflow allocated blocks
  ext4: fix error message when rejecting the default hash
  ext4: save unnecessary indentation in ext4_ext_create_new_leaf()
  ext4: make some fast commit functions reuse extents path
  ext4: refactor ext4_swap_extents() to reuse extents path
  ext4: get rid of ppath in convert_initialized_extent()
  ext4: get rid of ppath in ext4_ext_handle_unwritten_extents()
  ext4: get rid of ppath in ext4_ext_convert_to_initialized()
  ext4: get rid of ppath in ext4_convert_unwritten_extents_endio()
  ext4: get rid of ppath in ext4_split_convert_extents()
  ext4: get rid of ppath in ext4_split_extent()
  ext4: get rid of ppath in ext4_force_split_extent_at()
  ext4: get rid of ppath in ext4_split_extent_at()
  ...

Documentation/admin-guide/ext4.rst

@@ -212,16 +212,6 @@ When mounting an ext4 filesystem, the following option are accepted:
         that ext4's inode table readahead algorithm will pre-read into the
         buffer cache.  The default value is 32 blocks.
 
-  nouser_xattr
-        Disables Extended User Attributes.  See the attr(5) manual page for
-        more information about extended attributes.
-
-  noacl
-        This option disables POSIX Access Control List support. If ACL support
-        is enabled in the kernel configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL
-        is enabled by default on mount. See the acl(5) manual page for more
-        information about acl.
-
   bsddf	(*)
         Make 'df' act like BSD.
 

fs/ext4/bitmap.c

@@ -18,15 +18,17 @@ unsigned int ext4_count_free(char *bitmap, unsigned int numchars)
 
 int ext4_inode_bitmap_csum_verify(struct super_block *sb,
 				  struct ext4_group_desc *gdp,
-				  struct buffer_head *bh, int sz)
+				  struct buffer_head *bh)
 {
 	__u32 hi;
 	__u32 provided, calculated;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int sz;
 
 	if (!ext4_has_metadata_csum(sb))
 		return 1;
 
+	sz = EXT4_INODES_PER_GROUP(sb) >> 3;
 	provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo);
 	calculated = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
 	if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) {
@@ -40,14 +42,16 @@ int ext4_inode_bitmap_csum_verify(struct super_block *sb,
 
 void ext4_inode_bitmap_csum_set(struct super_block *sb,
 				struct ext4_group_desc *gdp,
-				struct buffer_head *bh, int sz)
+				struct buffer_head *bh)
 {
 	__u32 csum;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int sz;
 
 	if (!ext4_has_metadata_csum(sb))
 		return;
 
+	sz = EXT4_INODES_PER_GROUP(sb) >> 3;
 	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
 	gdp->bg_inode_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF);
 	if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END)

fs/ext4/dir.c

@@ -280,12 +280,20 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 					struct fscrypt_str de_name =
 							FSTR_INIT(de->name,
 								de->name_len);
+					u32 hash;
+					u32 minor_hash;
+
+					if (IS_CASEFOLDED(inode)) {
+						hash = EXT4_DIRENT_HASH(de);
+						minor_hash = EXT4_DIRENT_MINOR_HASH(de);
+					} else {
+						hash = 0;
+						minor_hash = 0;
+					}
 
 					/* Directory is encrypted */
 					err = fscrypt_fname_disk_to_usr(inode,
-						EXT4_DIRENT_HASH(de),
+						hash, minor_hash, &de_name, &fstr);
-						EXT4_DIRENT_MINOR_HASH(de),
-						&de_name, &fstr);
 					de_name = fstr;
 					fstr.len = save_len;
 					if (err)

fs/ext4/ext4.h

@@ -1058,6 +1058,7 @@ struct ext4_inode_info {
 
 	/* Number of ongoing updates on this inode */
 	atomic_t  i_fc_updates;
+	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
 
 	/* Fast commit wait queue for this inode */
 	wait_queue_head_t i_fc_wait;
@@ -1106,6 +1107,10 @@ struct ext4_inode_info {
 
 	/* mballoc */
 	atomic_t i_prealloc_active;
+
+	/* allocation reservation info for delalloc */
+	/* In case of bigalloc, this refer to clusters rather than blocks */
+	unsigned int i_reserved_data_blocks;
 	struct rb_root i_prealloc_node;
 	rwlock_t i_prealloc_lock;
 
@@ -1122,10 +1127,6 @@ struct ext4_inode_info {
 	/* ialloc */
 	ext4_group_t	i_last_alloc_group;
 
-	/* allocation reservation info for delalloc */
-	/* In case of bigalloc, this refer to clusters rather than blocks */
-	unsigned int i_reserved_data_blocks;
-
 	/* pending cluster reservations for bigalloc file systems */
 	struct ext4_pending_tree i_pending_tree;
 
@@ -1149,7 +1150,6 @@ struct ext4_inode_info {
 	 */
 	struct list_head i_rsv_conversion_list;
 	struct work_struct i_rsv_conversion_work;
-	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
 
 	spinlock_t i_block_reservation_lock;
 
@@ -2338,9 +2338,9 @@ struct ext4_dir_entry_2 {
 	((struct ext4_dir_entry_hash *) \
 		(((void *)(entry)) + \
 		((8 + (entry)->name_len + EXT4_DIR_ROUND) & ~EXT4_DIR_ROUND)))
-#define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(de)->hash)
+#define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(entry)->hash)
 #define EXT4_DIRENT_MINOR_HASH(entry) \
-		le32_to_cpu(EXT4_DIRENT_HASHES(de)->minor_hash)
+		le32_to_cpu(EXT4_DIRENT_HASHES(entry)->minor_hash)
 
 static inline bool ext4_hash_in_dirent(const struct inode *inode)
 {
@@ -2462,6 +2462,7 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
 #define DX_HASH_HALF_MD4_UNSIGNED	4
 #define DX_HASH_TEA_UNSIGNED		5
 #define DX_HASH_SIPHASH			6
+#define DX_HASH_LAST 			DX_HASH_SIPHASH
 
 static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
 			      const void *address, unsigned int length)
@@ -2695,10 +2696,10 @@ struct mmpd_data {
 extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
 void ext4_inode_bitmap_csum_set(struct super_block *sb,
 				struct ext4_group_desc *gdp,
-				struct buffer_head *bh, int sz);
+				struct buffer_head *bh);
 int ext4_inode_bitmap_csum_verify(struct super_block *sb,
 				  struct ext4_group_desc *gdp,
-				  struct buffer_head *bh, int sz);
+				  struct buffer_head *bh);
 void ext4_block_bitmap_csum_set(struct super_block *sb,
 				struct ext4_group_desc *gdp,
 				struct buffer_head *bh);
@@ -3712,11 +3713,12 @@ extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
 extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
 						   int num,
 						   struct ext4_ext_path *path);
-extern int ext4_ext_insert_extent(handle_t *, struct inode *,
+extern struct ext4_ext_path *ext4_ext_insert_extent(
-				  struct ext4_ext_path **,
+				handle_t *handle, struct inode *inode,
-				  struct ext4_extent *, int);
+				struct ext4_ext_path *path,
+				struct ext4_extent *newext, int gb_flags);
 extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
-					      struct ext4_ext_path **,
+					      struct ext4_ext_path *,
 					      int flags);
 extern void ext4_free_ext_path(struct ext4_ext_path *);
 extern int ext4_ext_check_inode(struct inode *inode);
@@ -3853,6 +3855,9 @@ static inline int ext4_buffer_uptodate(struct buffer_head *bh)
 	return buffer_uptodate(bh);
 }
 
+extern int ext4_block_write_begin(handle_t *handle, struct folio *folio,
+				  loff_t pos, unsigned len,
+				  get_block_t *get_block);
 #endif	/* __KERNEL__ */
 
 #define EFSBADCRC	EBADMSG		/* Bad CRC detected */

fs/ext4/extents_status.c

@@ -558,8 +558,8 @@ static int ext4_es_can_be_merged(struct extent_status *es1,
 	if (ext4_es_is_hole(es1))
 		return 1;
 
-	/* we need to check delayed extent is without unwritten status */
+	/* we need to check delayed extent */
-	if (ext4_es_is_delayed(es1) && !ext4_es_is_unwritten(es1))
+	if (ext4_es_is_delayed(es1))
 		return 1;
 
 	return 0;
@@ -848,11 +848,12 @@ out:
  */
 void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 			   ext4_lblk_t len, ext4_fsblk_t pblk,
-			   unsigned int status)
+			   unsigned int status, int flags)
 {
 	struct extent_status newes;
 	ext4_lblk_t end = lblk + len - 1;
 	int err1 = 0, err2 = 0, err3 = 0;
+	int resv_used = 0, pending = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct extent_status *es1 = NULL;
 	struct extent_status *es2 = NULL;
@@ -862,21 +863,14 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
 
-	es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n",
+	es_debug("add [%u/%u) %llu %x %x to extent status tree of inode %lu\n",
-		 lblk, len, pblk, status, inode->i_ino);
+		 lblk, len, pblk, status, flags, inode->i_ino);
 
 	if (!len)
 		return;
 
 	BUG_ON(end < lblk);
-
+	WARN_ON_ONCE(status & EXTENT_STATUS_DELAYED);
-	if ((status & EXTENT_STATUS_DELAYED) &&
-	    (status & EXTENT_STATUS_WRITTEN)) {
-		ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as "
-				" delayed and written which can potentially "
-				" cause data loss.", lblk, len);
-		WARN_ON(1);
-	}
 
 	newes.es_lblk = lblk;
 	newes.es_len = len;
@@ -894,11 +888,11 @@ retry:
 		es1 = __es_alloc_extent(true);
 	if ((err1 || err2) && !es2)
 		es2 = __es_alloc_extent(true);
-	if ((err1 || err2 || err3) && revise_pending && !pr)
+	if ((err1 || err2 || err3 < 0) && revise_pending && !pr)
 		pr = __alloc_pending(true);
 	write_lock(&EXT4_I(inode)->i_es_lock);
 
-	err1 = __es_remove_extent(inode, lblk, end, NULL, es1);
+	err1 = __es_remove_extent(inode, lblk, end, &resv_used, es1);
 	if (err1 != 0)
 		goto error;
 	/* Free preallocated extent if it didn't get used. */
@@ -922,16 +916,38 @@ retry:
 
 	if (revise_pending) {
 		err3 = __revise_pending(inode, lblk, len, &pr);
-		if (err3 != 0)
+		if (err3 < 0)
 			goto error;
 		if (pr) {
 			__free_pending(pr);
 			pr = NULL;
 		}
+		pending = err3;
 	}
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
-	if (err1 || err2 || err3)
+	/*
+	 * Reduce the reserved cluster count to reflect successful deferred
+	 * allocation of delayed allocated clusters or direct allocation of
+	 * clusters discovered to be delayed allocated.  Once allocated, a
+	 * cluster is not included in the reserved count.
+	 *
+	 * When direct allocating (from fallocate, filemap, DIO, or clusters
+	 * allocated when delalloc has been disabled by ext4_nonda_switch())
+	 * an extent either 1) contains delayed blocks but start with
+	 * non-delayed allocated blocks (e.g. hole) or 2) contains non-delayed
+	 * allocated blocks which belong to delayed allocated clusters when
+	 * bigalloc feature is enabled, quota has already been claimed by
+	 * ext4_mb_new_blocks(), so release the quota reservations made for
+	 * any previously delayed allocated clusters instead of claim them
+	 * again.
+	 */
+	resv_used += pending;
+	if (resv_used)
+		ext4_da_update_reserve_space(inode, resv_used,
+				flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+
+	if (err1 || err2 || err3 < 0)
 		goto retry;
 
 	ext4_es_print_tree(inode);
@@ -1051,7 +1067,7 @@ out:
 }
 
 struct rsvd_count {
-	int ndelonly;
+	int ndelayed;
 	bool first_do_lblk_found;
 	ext4_lblk_t first_do_lblk;
 	ext4_lblk_t last_do_lblk;
@@ -1077,10 +1093,10 @@ static void init_rsvd(struct inode *inode, ext4_lblk_t lblk,
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct rb_node *node;
 
-	rc->ndelonly = 0;
+	rc->ndelayed = 0;
 
 	/*
-	 * for bigalloc, note the first delonly block in the range has not
+	 * for bigalloc, note the first delayed block in the range has not
 	 * been found, record the extent containing the block to the left of
 	 * the region to be removed, if any, and note that there's no partial
 	 * cluster to track
@@ -1100,9 +1116,8 @@ static void init_rsvd(struct inode *inode, ext4_lblk_t lblk,
 }
 
 /*
- * count_rsvd - count the clusters containing delayed and not unwritten
+ * count_rsvd - count the clusters containing delayed blocks in a range
- *		(delonly) blocks in a range within an extent and add to
+ *	        within an extent and add to the running tally in rsvd_count
- *	        the running tally in rsvd_count
  *
  * @inode - file containing extent
  * @lblk - first block in range
@@ -1119,13 +1134,13 @@ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len,
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	ext4_lblk_t i, end, nclu;
 
-	if (!ext4_es_is_delonly(es))
+	if (!ext4_es_is_delayed(es))
 		return;
 
 	WARN_ON(len <= 0);
 
 	if (sbi->s_cluster_ratio == 1) {
-		rc->ndelonly += (int) len;
+		rc->ndelayed += (int) len;
 		return;
 	}
 
@@ -1135,7 +1150,7 @@ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len,
 	end = lblk + (ext4_lblk_t) len - 1;
 	end = (end > ext4_es_end(es)) ? ext4_es_end(es) : end;
 
-	/* record the first block of the first delonly extent seen */
+	/* record the first block of the first delayed extent seen */
 	if (!rc->first_do_lblk_found) {
 		rc->first_do_lblk = i;
 		rc->first_do_lblk_found = true;
@@ -1149,7 +1164,7 @@ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len,
 	 * doesn't start with it, count it and stop tracking
 	 */
 	if (rc->partial && (rc->lclu != EXT4_B2C(sbi, i))) {
-		rc->ndelonly++;
+		rc->ndelayed++;
 		rc->partial = false;
 	}
 
@@ -1159,7 +1174,7 @@ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len,
 	 */
 	if (EXT4_LBLK_COFF(sbi, i) != 0) {
 		if (end >= EXT4_LBLK_CFILL(sbi, i)) {
-			rc->ndelonly++;
+			rc->ndelayed++;
 			rc->partial = false;
 			i = EXT4_LBLK_CFILL(sbi, i) + 1;
 		}
@@ -1167,11 +1182,11 @@ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len,
 
 	/*
 	 * if the current cluster starts on a cluster boundary, count the
-	 * number of whole delonly clusters in the extent
+	 * number of whole delayed clusters in the extent
 	 */
 	if ((i + sbi->s_cluster_ratio - 1) <= end) {
 		nclu = (end - i + 1) >> sbi->s_cluster_bits;
-		rc->ndelonly += nclu;
+		rc->ndelayed += nclu;
 		i += nclu << sbi->s_cluster_bits;
 	}
 
@@ -1231,10 +1246,9 @@ static struct pending_reservation *__pr_tree_search(struct rb_root *root,
  * @rc - pointer to reserved count data
  *
  * The number of reservations to be released is equal to the number of
- * clusters containing delayed and not unwritten (delonly) blocks within
+ * clusters containing delayed blocks within the range, minus the number of
- * the range, minus the number of clusters still containing delonly blocks
+ * clusters still containing delayed blocks at the ends of the range, and
- * at the ends of the range, and minus the number of pending reservations
+ * minus the number of pending reservations within the range.
- * within the range.
  */
 static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
 			     struct extent_status *right_es,
@@ -1245,33 +1259,33 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
 	struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree;
 	struct rb_node *node;
 	ext4_lblk_t first_lclu, last_lclu;
-	bool left_delonly, right_delonly, count_pending;
+	bool left_delayed, right_delayed, count_pending;
 	struct extent_status *es;
 
 	if (sbi->s_cluster_ratio > 1) {
 		/* count any remaining partial cluster */
 		if (rc->partial)
-			rc->ndelonly++;
+			rc->ndelayed++;
 
-		if (rc->ndelonly == 0)
+		if (rc->ndelayed == 0)
 			return 0;
 
 		first_lclu = EXT4_B2C(sbi, rc->first_do_lblk);
 		last_lclu = EXT4_B2C(sbi, rc->last_do_lblk);
 
 		/*
-		 * decrease the delonly count by the number of clusters at the
+		 * decrease the delayed count by the number of clusters at the
-		 * ends of the range that still contain delonly blocks -
+		 * ends of the range that still contain delayed blocks -
 		 * these clusters still need to be reserved
 		 */
-		left_delonly = right_delonly = false;
+		left_delayed = right_delayed = false;
 
 		es = rc->left_es;
 		while (es && ext4_es_end(es) >=
 		       EXT4_LBLK_CMASK(sbi, rc->first_do_lblk)) {
-			if (ext4_es_is_delonly(es)) {
+			if (ext4_es_is_delayed(es)) {
-				rc->ndelonly--;
+				rc->ndelayed--;
-				left_delonly = true;
+				left_delayed = true;
 				break;
 			}
 			node = rb_prev(&es->rb_node);
@@ -1279,7 +1293,7 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
 				break;
 			es = rb_entry(node, struct extent_status, rb_node);
 		}
-		if (right_es && (!left_delonly || first_lclu != last_lclu)) {
+		if (right_es && (!left_delayed || first_lclu != last_lclu)) {
 			if (end < ext4_es_end(right_es)) {
 				es = right_es;
 			} else {
@@ -1289,9 +1303,9 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
 			}
 			while (es && es->es_lblk <=
 			       EXT4_LBLK_CFILL(sbi, rc->last_do_lblk)) {
-				if (ext4_es_is_delonly(es)) {
+				if (ext4_es_is_delayed(es)) {
-					rc->ndelonly--;
+					rc->ndelayed--;
-					right_delonly = true;
+					right_delayed = true;
 					break;
 				}
 				node = rb_next(&es->rb_node);
@@ -1305,21 +1319,21 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
 		/*
 		 * Determine the block range that should be searched for
 		 * pending reservations, if any.  Clusters on the ends of the
-		 * original removed range containing delonly blocks are
+		 * original removed range containing delayed blocks are
 		 * excluded.  They've already been accounted for and it's not
 		 * possible to determine if an associated pending reservation
 		 * should be released with the information available in the
 		 * extents status tree.
 		 */
 		if (first_lclu == last_lclu) {
-			if (left_delonly | right_delonly)
+			if (left_delayed | right_delayed)
 				count_pending = false;
 			else
 				count_pending = true;
 		} else {
-			if (left_delonly)
+			if (left_delayed)
 				first_lclu++;
-			if (right_delonly)
+			if (right_delayed)
 				last_lclu--;
 			if (first_lclu <= last_lclu)
 				count_pending = true;
@@ -1330,13 +1344,13 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
 		/*
 		 * a pending reservation found between first_lclu and last_lclu
 		 * represents an allocated cluster that contained at least one
-		 * delonly block, so the delonly total must be reduced by one
+		 * delayed block, so the delayed total must be reduced by one
 		 * for each pending reservation found and released
 		 */
 		if (count_pending) {
 			pr = __pr_tree_search(&tree->root, first_lclu);
 			while (pr && pr->lclu <= last_lclu) {
-				rc->ndelonly--;
+				rc->ndelayed--;
 				node = rb_next(&pr->rb_node);
 				rb_erase(&pr->rb_node, &tree->root);
 				__free_pending(pr);
@@ -1347,7 +1361,7 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
 			}
 		}
 	}
-	return rc->ndelonly;
+	return rc->ndelayed;
 }
 
 
@@ -1940,7 +1954,7 @@ static struct pending_reservation *__get_pending(struct inode *inode,
  * @lblk - logical block in the cluster to be added
  * @prealloc - preallocated pending entry
  *
- * Returns 0 on successful insertion and -ENOMEM on failure.  If the
+ * Returns 1 on successful insertion and -ENOMEM on failure.  If the
  * pending reservation is already in the set, returns successfully.
  */
 static int __insert_pending(struct inode *inode, ext4_lblk_t lblk,
@@ -1984,6 +1998,7 @@ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk,
 
 	rb_link_node(&pr->rb_node, parent, p);
 	rb_insert_color(&pr->rb_node, &tree->root);
+	ret = 1;
 
 out:
 	return ret;
@@ -2105,7 +2120,7 @@ retry:
 		es1 = __es_alloc_extent(true);
 	if ((err1 || err2) && !es2)
 		es2 = __es_alloc_extent(true);
-	if (err1 || err2 || err3) {
+	if (err1 || err2 || err3 < 0) {
 		if (lclu_allocated && !pr1)
 			pr1 = __alloc_pending(true);
 		if (end_allocated && !pr2)
@@ -2135,7 +2150,7 @@ retry:
 
 	if (lclu_allocated) {
 		err3 = __insert_pending(inode, lblk, &pr1);
-		if (err3 != 0)
+		if (err3 < 0)
 			goto error;
 		if (pr1) {
 			__free_pending(pr1);
@@ -2144,7 +2159,7 @@ retry:
 	}
 	if (end_allocated) {
 		err3 = __insert_pending(inode, end, &pr2);
-		if (err3 != 0)
+		if (err3 < 0)
 			goto error;
 		if (pr2) {
 			__free_pending(pr2);
@@ -2153,7 +2168,7 @@ retry:
 	}
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
-	if (err1 || err2 || err3)
+	if (err1 || err2 || err3 < 0)
 		goto retry;
 
 	ext4_es_print_tree(inode);
@@ -2161,94 +2176,6 @@ error:
 	return;
 }
 
-/*
- * __es_delayed_clu - count number of clusters containing blocks that
- *                    are delayed only
- *
- * @inode - file containing block range
- * @start - logical block defining start of range
- * @end - logical block defining end of range
- *
- * Returns the number of clusters containing only delayed (not delayed
- * and unwritten) blocks in the range specified by @start and @end.  Any
- * cluster or part of a cluster within the range and containing a delayed
- * and not unwritten block within the range is counted as a whole cluster.
- */
-static unsigned int __es_delayed_clu(struct inode *inode, ext4_lblk_t start,
-				     ext4_lblk_t end)
-{
-	struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
-	struct extent_status *es;
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	struct rb_node *node;
-	ext4_lblk_t first_lclu, last_lclu;
-	unsigned long long last_counted_lclu;
-	unsigned int n = 0;
-
-	/* guaranteed to be unequal to any ext4_lblk_t value */
-	last_counted_lclu = ~0ULL;
-
-	es = __es_tree_search(&tree->root, start);
-
-	while (es && (es->es_lblk <= end)) {
-		if (ext4_es_is_delonly(es)) {
-			if (es->es_lblk <= start)
-				first_lclu = EXT4_B2C(sbi, start);
-			else
-				first_lclu = EXT4_B2C(sbi, es->es_lblk);
-
-			if (ext4_es_end(es) >= end)
-				last_lclu = EXT4_B2C(sbi, end);
-			else
-				last_lclu = EXT4_B2C(sbi, ext4_es_end(es));
-
-			if (first_lclu == last_counted_lclu)
-				n += last_lclu - first_lclu;
-			else
-				n += last_lclu - first_lclu + 1;
-			last_counted_lclu = last_lclu;
-		}
-		node = rb_next(&es->rb_node);
-		if (!node)
-			break;
-		es = rb_entry(node, struct extent_status, rb_node);
-	}
-
-	return n;
-}
-
-/*
- * ext4_es_delayed_clu - count number of clusters containing blocks that
- *                       are both delayed and unwritten
- *
- * @inode - file containing block range
- * @lblk - logical block defining start of range
- * @len - number of blocks in range
- *
- * Locking for external use of __es_delayed_clu().
- */
-unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk,
-				 ext4_lblk_t len)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	ext4_lblk_t end;
-	unsigned int n;
-
-	if (len == 0)
-		return 0;
-
-	end = lblk + len - 1;
-	WARN_ON(end < lblk);
-
-	read_lock(&ei->i_es_lock);
-
-	n = __es_delayed_clu(inode, lblk, end);
-
-	read_unlock(&ei->i_es_lock);
-
-	return n;
-}
-
 /*
  * __revise_pending - makes, cancels, or leaves unchanged pending cluster
  *                    reservations for a specified block range depending
@@ -2263,7 +2190,9 @@ unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk,
  *
  * Used after a newly allocated extent is added to the extents status tree.
  * Requires that the extents in the range have either written or unwritten
- * status.  Must be called while holding i_es_lock.
+ * status.  Must be called while holding i_es_lock. Returns number of new
+ * inserts pending cluster on insert pendings, returns 0 on remove pendings,
+ * return -ENOMEM on failure.
  */
 static int __revise_pending(struct inode *inode, ext4_lblk_t lblk,
 			    ext4_lblk_t len,
@@ -2273,6 +2202,7 @@ static int __revise_pending(struct inode *inode, ext4_lblk_t lblk,
 	ext4_lblk_t end = lblk + len - 1;
 	ext4_lblk_t first, last;
 	bool f_del = false, l_del = false;
+	int pendings = 0;
 	int ret = 0;
 
 	if (len == 0)
@@ -2294,49 +2224,53 @@ static int __revise_pending(struct inode *inode, ext4_lblk_t lblk,
 	if (EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) {
 		first = EXT4_LBLK_CMASK(sbi, lblk);
 		if (first != lblk)
-			f_del = __es_scan_range(inode, &ext4_es_is_delonly,
+			f_del = __es_scan_range(inode, &ext4_es_is_delayed,
 						first, lblk - 1);
 		if (f_del) {
 			ret = __insert_pending(inode, first, prealloc);
 			if (ret < 0)
 				goto out;
+			pendings += ret;
 		} else {
 			last = EXT4_LBLK_CMASK(sbi, end) +
 			       sbi->s_cluster_ratio - 1;
 			if (last != end)
 				l_del = __es_scan_range(inode,
-							&ext4_es_is_delonly,
+							&ext4_es_is_delayed,
 							end + 1, last);
 			if (l_del) {
 				ret = __insert_pending(inode, last, prealloc);
 				if (ret < 0)
 					goto out;
+				pendings += ret;
 			} else
 				__remove_pending(inode, last);
 		}
 	} else {
 		first = EXT4_LBLK_CMASK(sbi, lblk);
 		if (first != lblk)
-			f_del = __es_scan_range(inode, &ext4_es_is_delonly,
+			f_del = __es_scan_range(inode, &ext4_es_is_delayed,
 						first, lblk - 1);
 		if (f_del) {
 			ret = __insert_pending(inode, first, prealloc);
 			if (ret < 0)
 				goto out;
+			pendings += ret;
 		} else
 			__remove_pending(inode, first);
 
 		last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1;
 		if (last != end)
-			l_del = __es_scan_range(inode, &ext4_es_is_delonly,
+			l_del = __es_scan_range(inode, &ext4_es_is_delayed,
 						end + 1, last);
 		if (l_del) {
 			ret = __insert_pending(inode, last, prealloc);
 			if (ret < 0)
 				goto out;
+			pendings += ret;
 		} else
 			__remove_pending(inode, last);
 	}
 out:
-	return ret;
+	return (ret < 0) ? ret : pendings;
 }

fs/ext4/extents_status.h

@@ -42,6 +42,10 @@ enum {
 #define ES_SHIFT (sizeof(ext4_fsblk_t)*8 - ES_FLAGS)
 #define ES_MASK (~((ext4_fsblk_t)0) << ES_SHIFT)
 
+/*
+ * Besides EXTENT_STATUS_REFERENCED, all these extent type masks
+ * are exclusive, only one type can be set at a time.
+ */
 #define EXTENT_STATUS_WRITTEN	(1 << ES_WRITTEN_B)
 #define EXTENT_STATUS_UNWRITTEN (1 << ES_UNWRITTEN_B)
 #define EXTENT_STATUS_DELAYED	(1 << ES_DELAYED_B)
@@ -51,7 +55,9 @@ enum {
 #define ES_TYPE_MASK	((ext4_fsblk_t)(EXTENT_STATUS_WRITTEN | \
 			  EXTENT_STATUS_UNWRITTEN | \
 			  EXTENT_STATUS_DELAYED | \
-			  EXTENT_STATUS_HOLE) << ES_SHIFT)
+			  EXTENT_STATUS_HOLE))
+
+#define ES_TYPE_VALID(type)	((type) && !((type) & ((type) - 1)))
 
 struct ext4_sb_info;
 struct ext4_extent;
@@ -129,7 +135,7 @@ extern void ext4_es_init_tree(struct ext4_es_tree *tree);
 
 extern void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 				  ext4_lblk_t len, ext4_fsblk_t pblk,
-				  unsigned int status);
+				  unsigned int status, int flags);
 extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
 				 ext4_lblk_t len, ext4_fsblk_t pblk,
 				 unsigned int status);
@@ -156,7 +162,7 @@ static inline unsigned int ext4_es_status(struct extent_status *es)
 
 static inline unsigned int ext4_es_type(struct extent_status *es)
 {
-	return (es->es_pblk & ES_TYPE_MASK) >> ES_SHIFT;
+	return (es->es_pblk >> ES_SHIFT) & ES_TYPE_MASK;
 }
 
 static inline int ext4_es_is_written(struct extent_status *es)
@@ -184,11 +190,6 @@ static inline int ext4_es_is_mapped(struct extent_status *es)
 	return (ext4_es_is_written(es) || ext4_es_is_unwritten(es));
 }
 
-static inline int ext4_es_is_delonly(struct extent_status *es)
-{
-	return (ext4_es_is_delayed(es) && !ext4_es_is_unwritten(es));
-}
-
 static inline void ext4_es_set_referenced(struct extent_status *es)
 {
 	es->es_pblk |= ((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT;
@@ -224,17 +225,12 @@ static inline void ext4_es_store_pblock(struct extent_status *es,
 	es->es_pblk = block;
 }
 
-static inline void ext4_es_store_status(struct extent_status *es,
-					unsigned int status)
-{
-	es->es_pblk = (((ext4_fsblk_t)status << ES_SHIFT) & ES_MASK) |
-		      (es->es_pblk & ~ES_MASK);
-}
-
 static inline void ext4_es_store_pblock_status(struct extent_status *es,
 					       ext4_fsblk_t pb,
 					       unsigned int status)
 {
+	WARN_ON_ONCE(!ES_TYPE_VALID(status & ES_TYPE_MASK));
+
 	es->es_pblk = (((ext4_fsblk_t)status << ES_SHIFT) & ES_MASK) |
 		      (pb & ~ES_MASK);
 }
@@ -252,8 +248,6 @@ extern bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk);
 extern void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
 					  ext4_lblk_t len, bool lclu_allocated,
 					  bool end_allocated);
-extern unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk,
-					ext4_lblk_t len);
 extern void ext4_clear_inode_es(struct inode *inode);
 
 #endif /* _EXT4_EXTENTS_STATUS_H */

fs/ext4/fast_commit.c

@@ -339,22 +339,29 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	tid_t tid;
+	bool has_transaction = true;
+	bool is_ineligible;
 
 	if (ext4_fc_disabled(sb))
 		return;
 
-	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	if (handle && !IS_ERR(handle))
 		tid = handle->h_transaction->t_tid;
 	else {
 		read_lock(&sbi->s_journal->j_state_lock);
-		tid = sbi->s_journal->j_running_transaction ?
+		if (sbi->s_journal->j_running_transaction)
-				sbi->s_journal->j_running_transaction->t_tid : 0;
+			tid = sbi->s_journal->j_running_transaction->t_tid;
+		else
+			has_transaction = false;
 		read_unlock(&sbi->s_journal->j_state_lock);
 	}
 	spin_lock(&sbi->s_fc_lock);
-	if (tid_gt(tid, sbi->s_fc_ineligible_tid))
+	is_ineligible = ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+	if (has_transaction &&
+	    (!is_ineligible ||
+	     (is_ineligible && tid_gt(tid, sbi->s_fc_ineligible_tid))))
 		sbi->s_fc_ineligible_tid = tid;
+	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	spin_unlock(&sbi->s_fc_lock);
 	WARN_ON(reason >= EXT4_FC_REASON_MAX);
 	sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
@@ -1288,8 +1295,21 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
 		list_del_init(&iter->i_fc_list);
 		ext4_clear_inode_state(&iter->vfs_inode,
 				       EXT4_STATE_FC_COMMITTING);
-		if (tid_geq(tid, iter->i_sync_tid))
+		if (tid_geq(tid, iter->i_sync_tid)) {
 			ext4_fc_reset_inode(&iter->vfs_inode);
+		} else if (full) {
+			/*
+			 * We are called after a full commit, inode has been
+			 * modified while the commit was running. Re-enqueue
+			 * the inode into STAGING, which will then be splice
+			 * back into MAIN. This cannot happen during
+			 * fastcommit because the journal is locked all the
+			 * time in that case (and tid doesn't increase so
+			 * tid check above isn't reliable).
+			 */
+			list_add_tail(&EXT4_I(&iter->vfs_inode)->i_fc_list,
+				      &sbi->s_fc_q[FC_Q_STAGING]);
+		}
 		/* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
 		smp_mb();
 #if (BITS_PER_LONG < 64)
@@ -1772,7 +1792,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
 
 		if (ret == 0) {
 			/* Range is not mapped */
-			path = ext4_find_extent(inode, cur, NULL, 0);
+			path = ext4_find_extent(inode, cur, path, 0);
 			if (IS_ERR(path))
 				goto out;
 			memset(&newex, 0, sizeof(newex));
@@ -1783,11 +1803,10 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
 			if (ext4_ext_is_unwritten(ex))
 				ext4_ext_mark_unwritten(&newex);
 			down_write(&EXT4_I(inode)->i_data_sem);
-			ret = ext4_ext_insert_extent(
+			path = ext4_ext_insert_extent(NULL, inode,
-				NULL, inode, &path, &newex, 0);
+						      path, &newex, 0);
 			up_write((&EXT4_I(inode)->i_data_sem));
-			ext4_free_ext_path(path);
+			if (IS_ERR(path))
-			if (ret)
 				goto out;
 			goto next;
 		}
@@ -1836,6 +1855,7 @@ next:
 	ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >>
 					sb->s_blocksize_bits);
 out:
+	ext4_free_ext_path(path);
 	iput(inode);
 	return 0;
 }
@@ -1936,12 +1956,13 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
 				break;
 
 			if (ret > 0) {
-				path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
+				path = ext4_find_extent(inode, map.m_lblk, path, 0);
 				if (!IS_ERR(path)) {
 					for (j = 0; j < path->p_depth; j++)
 						ext4_mb_mark_bb(inode->i_sb,
 							path[j].p_block, 1, true);
-					ext4_free_ext_path(path);
+				} else {
+					path = NULL;
 				}
 				cur += ret;
 				ext4_mb_mark_bb(inode->i_sb, map.m_pblk,
@@ -1952,6 +1973,8 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
 		}
 		iput(inode);
 	}
+
+	ext4_free_ext_path(path);
 }
 
 /*

fs/ext4/file.c

@@ -306,7 +306,7 @@ out:
 }
 
 static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
-					   ssize_t count)
+					   ssize_t written, ssize_t count)
 {
 	handle_t *handle;
 
@@ -315,7 +315,7 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
-	if (ext4_update_inode_size(inode, offset + count)) {
+	if (ext4_update_inode_size(inode, offset + written)) {
 		int ret = ext4_mark_inode_dirty(handle, inode);
 		if (unlikely(ret)) {
 			ext4_journal_stop(handle);
@@ -323,21 +323,21 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
 		}
 	}
 
-	if (inode->i_nlink)
+	if ((written == count) && inode->i_nlink)
 		ext4_orphan_del(handle, inode);
 	ext4_journal_stop(handle);
 
-	return count;
+	return written;
 }
 
 /*
  * Clean up the inode after DIO or DAX extending write has completed and the
  * inode size has been updated using ext4_handle_inode_extension().
  */
-static void ext4_inode_extension_cleanup(struct inode *inode, ssize_t count)
+static void ext4_inode_extension_cleanup(struct inode *inode, bool need_trunc)
 {
 	lockdep_assert_held_write(&inode->i_rwsem);
-	if (count < 0) {
+	if (need_trunc) {
 		ext4_truncate_failed_write(inode);
 		/*
 		 * If the truncate operation failed early, then the inode may
@@ -393,7 +393,7 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
 	if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) &&
 	    pos + size <= i_size_read(inode))
 		return size;
-	return ext4_handle_inode_extension(inode, pos, size);
+	return ext4_handle_inode_extension(inode, pos, size, size);
 }
 
 static const struct iomap_dio_ops ext4_dio_write_ops = {
@@ -586,7 +586,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		 * writeback of delalloc blocks.
 		 */
 		WARN_ON_ONCE(ret == -EIOCBQUEUED);
-		ext4_inode_extension_cleanup(inode, ret);
+		ext4_inode_extension_cleanup(inode, ret < 0);
 	}
 
 out:
@@ -669,8 +669,8 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
 
 	if (extend) {
-		ret = ext4_handle_inode_extension(inode, offset, ret);
+		ret = ext4_handle_inode_extension(inode, offset, ret, count);
-		ext4_inode_extension_cleanup(inode, ret);
+		ext4_inode_extension_cleanup(inode, ret < (ssize_t)count);
 	}
 out:
 	inode_unlock(inode);

fs/ext4/ialloc.c

@@ -87,10 +87,10 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
 		return 0;
 
-	grp = ext4_get_group_info(sb, block_group);
-
 	if (buffer_verified(bh))
 		return 0;
+
+	grp = ext4_get_group_info(sb, block_group);
 	if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
 		return -EFSCORRUPTED;
 
@@ -98,8 +98,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 	if (buffer_verified(bh))
 		goto verified;
 	blk = ext4_inode_bitmap(sb, desc);
-	if (!ext4_inode_bitmap_csum_verify(sb, desc, bh,
+	if (!ext4_inode_bitmap_csum_verify(sb, desc, bh) ||
-					   EXT4_INODES_PER_GROUP(sb) / 8) ||
 	    ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_CRC)) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
@@ -327,8 +326,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 		if (percpu_counter_initialized(&sbi->s_dirs_counter))
 			percpu_counter_dec(&sbi->s_dirs_counter);
 	}
-	ext4_inode_bitmap_csum_set(sb, gdp, bitmap_bh,
+	ext4_inode_bitmap_csum_set(sb, gdp, bitmap_bh);
-				   EXT4_INODES_PER_GROUP(sb) / 8);
 	ext4_group_desc_csum_set(sb, block_group, gdp);
 	ext4_unlock_group(sb, block_group);
 
@@ -514,6 +512,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 	if (min_inodes < 1)
 		min_inodes = 1;
 	min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4;
+	if (min_clusters < 0)
+		min_clusters = 0;
 
 	/*
 	 * Start looking in the flex group where we last allocated an
@@ -755,10 +755,10 @@ int ext4_mark_inode_used(struct super_block *sb, int ino)
 	struct ext4_group_desc *gdp;
 	ext4_group_t group;
 	int bit;
-	int err = -EFSCORRUPTED;
+	int err;
 
 	if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
-		goto out;
+		return -EFSCORRUPTED;
 
 	group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
 	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
@@ -772,7 +772,7 @@ int ext4_mark_inode_used(struct super_block *sb, int ino)
 	}
 
 	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
-	if (!gdp || !group_desc_bh) {
+	if (!gdp) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -851,8 +851,7 @@ int ext4_mark_inode_used(struct super_block *sb, int ino)
 
 	ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
 	if (ext4_has_group_desc_csum(sb)) {
-		ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh,
+		ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh);
-					   EXT4_INODES_PER_GROUP(sb) / 8);
 		ext4_group_desc_csum_set(sb, group, gdp);
 	}
 
@@ -860,6 +859,7 @@ int ext4_mark_inode_used(struct super_block *sb, int ino)
 	err = ext4_handle_dirty_metadata(NULL, NULL, group_desc_bh);
 	sync_dirty_buffer(group_desc_bh);
 out:
+	brelse(inode_bitmap_bh);
 	return err;
 }
 
@@ -1053,14 +1053,14 @@ got_group:
 		brelse(inode_bitmap_bh);
 		inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
 		/* Skip groups with suspicious inode tables */
-		if (((!(sbi->s_mount_state & EXT4_FC_REPLAY))
+		if (IS_ERR(inode_bitmap_bh)) {
-		     && EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) ||
-		    IS_ERR(inode_bitmap_bh)) {
 			inode_bitmap_bh = NULL;
 			goto next_group;
 		}
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY) &&
+		    EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
+			goto next_group;
 
-repeat_in_this_group:
 		ret2 = find_inode_bit(sb, group, inode_bitmap_bh, &ino);
 		if (!ret2)
 			goto next_group;
@@ -1110,8 +1110,6 @@ repeat_in_this_group:
 		if (!ret2)
 			goto got; /* we grabbed the inode! */
 
-		if (ino < EXT4_INODES_PER_GROUP(sb))
-			goto repeat_in_this_group;
 next_group:
 		if (++group == ngroups)
 			group = 0;
@@ -1224,8 +1222,7 @@ got:
 		}
 	}
 	if (ext4_has_group_desc_csum(sb)) {
-		ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh,
+		ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh);
-					   EXT4_INODES_PER_GROUP(sb) / 8);
 		ext4_group_desc_csum_set(sb, group, gdp);
 	}
 	ext4_unlock_group(sb, group);

fs/ext4/indirect.c

@@ -652,13 +652,6 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 	ext4_update_inode_fsync_trans(handle, inode, 1);
 	count = ar.len;
 
-	/*
-	 * Update reserved blocks/metadata blocks after successful block
-	 * allocation which had been deferred till now.
-	 */
-	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
-		ext4_da_update_reserve_space(inode, count, 1);
-
 got_it:
 	map->m_flags |= EXT4_MAP_MAPPED;
 	map->m_pblk = le32_to_cpu(chain[depth-1].key);

fs/ext4/inline.c

@@ -601,10 +601,11 @@ retry:
 		goto out;
 
 	if (ext4_should_dioread_nolock(inode)) {
-		ret = __block_write_begin(folio, from, to,
+		ret = ext4_block_write_begin(handle, folio, from, to,
-					  ext4_get_block_unwritten);
+					     ext4_get_block_unwritten);
 	} else
-		ret = __block_write_begin(folio, from, to, ext4_get_block);
+		ret = ext4_block_write_begin(handle, folio, from, to,
+					     ext4_get_block);
 
 	if (!ret && ext4_should_journal_data(inode)) {
 		ret = ext4_walk_page_buffers(handle, inode,
@@ -856,8 +857,8 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
 			goto out;
 	}
 
-	ret = __block_write_begin(folio, 0, inline_size,
+	ret = ext4_block_write_begin(NULL, folio, 0, inline_size,
-				  ext4_da_get_block_prep);
+				     ext4_da_get_block_prep);
 	if (ret) {
 		up_read(&EXT4_I(inode)->xattr_sem);
 		folio_unlock(folio);
@@ -1665,24 +1666,36 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 					struct ext4_dir_entry_2 **res_dir,
 					int *has_inline_data)
 {
+	struct ext4_xattr_ibody_find is = {
+		.s = { .not_found = -ENODATA, },
+	};
+	struct ext4_xattr_info i = {
+		.name_index = EXT4_XATTR_INDEX_SYSTEM,
+		.name = EXT4_XATTR_SYSTEM_DATA,
+	};
 	int ret;
-	struct ext4_iloc iloc;
 	void *inline_start;
 	int inline_size;
 
-	if (ext4_get_inode_loc(dir, &iloc))
+	ret = ext4_get_inode_loc(dir, &is.iloc);
-		return NULL;
+	if (ret)
+		return ERR_PTR(ret);
 
 	down_read(&EXT4_I(dir)->xattr_sem);
+
+	ret = ext4_xattr_ibody_find(dir, &i, &is);
+	if (ret)
+		goto out;
+
 	if (!ext4_has_inline_data(dir)) {
 		*has_inline_data = 0;
 		goto out;
 	}
 
-	inline_start = (void *)ext4_raw_inode(&iloc)->i_block +
+	inline_start = (void *)ext4_raw_inode(&is.iloc)->i_block +
 						EXT4_INLINE_DOTDOT_SIZE;
 	inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
-	ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
+	ret = ext4_search_dir(is.iloc.bh, inline_start, inline_size,
 			      dir, fname, 0, res_dir);
 	if (ret == 1)
 		goto out_find;
@@ -1692,20 +1705,23 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 	if (ext4_get_inline_size(dir) == EXT4_MIN_INLINE_DATA_SIZE)
 		goto out;
 
-	inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
+	inline_start = ext4_get_inline_xattr_pos(dir, &is.iloc);
 	inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE;
 
-	ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
+	ret = ext4_search_dir(is.iloc.bh, inline_start, inline_size,
 			      dir, fname, 0, res_dir);
 	if (ret == 1)
 		goto out_find;
 
 out:
-	brelse(iloc.bh);
+	brelse(is.iloc.bh);
-	iloc.bh = NULL;
+	if (ret < 0)
+		is.iloc.bh = ERR_PTR(ret);
+	else
+		is.iloc.bh = NULL;
 out_find:
 	up_read(&EXT4_I(dir)->xattr_sem);
-	return iloc.bh;
+	return is.iloc.bh;
 }
 
 int ext4_delete_inline_entry(handle_t *handle,

fs/ext4/inode.c

@@ -49,6 +49,11 @@
 
 #include <trace/events/ext4.h>
 
+static void ext4_journalled_zero_new_buffers(handle_t *handle,
+					    struct inode *inode,
+					    struct folio *folio,
+					    unsigned from, unsigned to);
+
 static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 			      struct ext4_inode_info *ei)
 {
@@ -478,7 +483,89 @@ static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
 	status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 			EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 	ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
-			      map->m_pblk, status);
+			      map->m_pblk, status, 0);
+	return retval;
+}
+
+static int ext4_map_create_blocks(handle_t *handle, struct inode *inode,
+				  struct ext4_map_blocks *map, int flags)
+{
+	struct extent_status es;
+	unsigned int status;
+	int err, retval = 0;
+
+	/*
+	 * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE
+	 * indicates that the blocks and quotas has already been
+	 * checked when the data was copied into the page cache.
+	 */
+	if (map->m_flags & EXT4_MAP_DELAYED)
+		flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
+
+	/*
+	 * Here we clear m_flags because after allocating an new extent,
+	 * it will be set again.
+	 */
+	map->m_flags &= ~EXT4_MAP_FLAGS;
+
+	/*
+	 * We need to check for EXT4 here because migrate could have
+	 * changed the inode type in between.
+	 */
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		retval = ext4_ext_map_blocks(handle, inode, map, flags);
+	} else {
+		retval = ext4_ind_map_blocks(handle, inode, map, flags);
+
+		/*
+		 * We allocated new blocks which will result in i_data's
+		 * format changing. Force the migrate to fail by clearing
+		 * migrate flags.
+		 */
+		if (retval > 0 && map->m_flags & EXT4_MAP_NEW)
+			ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
+	}
+	if (retval <= 0)
+		return retval;
+
+	if (unlikely(retval != map->m_len)) {
+		ext4_warning(inode->i_sb,
+			     "ES len assertion failed for inode %lu: "
+			     "retval %d != map->m_len %d",
+			     inode->i_ino, retval, map->m_len);
+		WARN_ON(1);
+	}
+
+	/*
+	 * We have to zeroout blocks before inserting them into extent
+	 * status tree. Otherwise someone could look them up there and
+	 * use them before they are really zeroed. We also have to
+	 * unmap metadata before zeroing as otherwise writeback can
+	 * overwrite zeros with stale data from block device.
+	 */
+	if (flags & EXT4_GET_BLOCKS_ZERO &&
+	    map->m_flags & EXT4_MAP_MAPPED && map->m_flags & EXT4_MAP_NEW) {
+		err = ext4_issue_zeroout(inode, map->m_lblk, map->m_pblk,
+					 map->m_len);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * If the extent has been zeroed out, we don't need to update
+	 * extent status tree.
+	 */
+	if (flags & EXT4_GET_BLOCKS_PRE_IO &&
+	    ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+		if (ext4_es_is_written(&es))
+			return retval;
+	}
+
+	status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+			EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+	ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+			      map->m_pblk, status, flags);
+
 	return retval;
 }
 
@@ -576,32 +663,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	 * file system block.
 	 */
 	down_read(&EXT4_I(inode)->i_data_sem);
-	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+	retval = ext4_map_query_blocks(handle, inode, map);
-		retval = ext4_ext_map_blocks(handle, inode, map, 0);
-	} else {
-		retval = ext4_ind_map_blocks(handle, inode, map, 0);
-	}
-	if (retval > 0) {
-		unsigned int status;
-
-		if (unlikely(retval != map->m_len)) {
-			ext4_warning(inode->i_sb,
-				     "ES len assertion failed for inode "
-				     "%lu: retval %d != map->m_len %d",
-				     inode->i_ino, retval, map->m_len);
-			WARN_ON(1);
-		}
-
-		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
-				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
-		if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
-		    !(status & EXTENT_STATUS_WRITTEN) &&
-		    ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk,
-				       map->m_lblk + map->m_len - 1))
-			status |= EXTENT_STATUS_DELAYED;
-		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
-				      map->m_pblk, status);
-	}
 	up_read((&EXT4_I(inode)->i_data_sem));
 
 found:
@@ -630,12 +692,6 @@ found:
 		if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN))
 			return retval;
 
-	/*
-	 * Here we clear m_flags because after allocating an new extent,
-	 * it will be set again.
-	 */
-	map->m_flags &= ~EXT4_MAP_FLAGS;
-
 	/*
 	 * New blocks allocate and/or writing to unwritten extent
 	 * will possibly result in updating i_data, so we take
@@ -643,76 +699,7 @@ found:
 	 * with create == 1 flag.
 	 */
 	down_write(&EXT4_I(inode)->i_data_sem);
-
+	retval = ext4_map_create_blocks(handle, inode, map, flags);
-	/*
-	 * We need to check for EXT4 here because migrate
-	 * could have changed the inode type in between
-	 */
-	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
-		retval = ext4_ext_map_blocks(handle, inode, map, flags);
-	} else {
-		retval = ext4_ind_map_blocks(handle, inode, map, flags);
-
-		if (retval > 0 && map->m_flags & EXT4_MAP_NEW) {
-			/*
-			 * We allocated new blocks which will result in
-			 * i_data's format changing.  Force the migrate
-			 * to fail by clearing migrate flags
-			 */
-			ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
-		}
-	}
-
-	if (retval > 0) {
-		unsigned int status;
-
-		if (unlikely(retval != map->m_len)) {
-			ext4_warning(inode->i_sb,
-				     "ES len assertion failed for inode "
-				     "%lu: retval %d != map->m_len %d",
-				     inode->i_ino, retval, map->m_len);
-			WARN_ON(1);
-		}
-
-		/*
-		 * We have to zeroout blocks before inserting them into extent
-		 * status tree. Otherwise someone could look them up there and
-		 * use them before they are really zeroed. We also have to
-		 * unmap metadata before zeroing as otherwise writeback can
-		 * overwrite zeros with stale data from block device.
-		 */
-		if (flags & EXT4_GET_BLOCKS_ZERO &&
-		    map->m_flags & EXT4_MAP_MAPPED &&
-		    map->m_flags & EXT4_MAP_NEW) {
-			ret = ext4_issue_zeroout(inode, map->m_lblk,
-						 map->m_pblk, map->m_len);
-			if (ret) {
-				retval = ret;
-				goto out_sem;
-			}
-		}
-
-		/*
-		 * If the extent has been zeroed out, we don't need to update
-		 * extent status tree.
-		 */
-		if ((flags & EXT4_GET_BLOCKS_PRE_IO) &&
-		    ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
-			if (ext4_es_is_written(&es))
-				goto out_sem;
-		}
-		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
-				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
-		if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
-		    !(status & EXTENT_STATUS_WRITTEN) &&
-		    ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk,
-				       map->m_lblk + map->m_len - 1))
-			status |= EXTENT_STATUS_DELAYED;
-		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
-				      map->m_pblk, status);
-	}
-
-out_sem:
 	up_write((&EXT4_I(inode)->i_data_sem));
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
 		ret = check_block_validity(inode, map);
@@ -1018,32 +1005,16 @@ static int ext4_dirty_journalled_data(handle_t *handle, struct buffer_head *bh)
 int do_journal_get_write_access(handle_t *handle, struct inode *inode,
 				struct buffer_head *bh)
 {
-	int dirty = buffer_dirty(bh);
-	int ret;
-
 	if (!buffer_mapped(bh) || buffer_freed(bh))
 		return 0;
-	/*
-	 * __block_write_begin() could have dirtied some buffers. Clean
-	 * the dirty bit as jbd2_journal_get_write_access() could complain
-	 * otherwise about fs integrity issues. Setting of the dirty bit
-	 * by __block_write_begin() isn't a real problem here as we clear
-	 * the bit before releasing a page lock and thus writeback cannot
-	 * ever write the buffer.
-	 */
-	if (dirty)
-		clear_buffer_dirty(bh);
 	BUFFER_TRACE(bh, "get write access");
-	ret = ext4_journal_get_write_access(handle, inode->i_sb, bh,
+	return ext4_journal_get_write_access(handle, inode->i_sb, bh,
 					    EXT4_JTR_NONE);
-	if (!ret && dirty)
-		ret = ext4_dirty_journalled_data(handle, bh);
-	return ret;
 }
 
-#ifdef CONFIG_FS_ENCRYPTION
+int ext4_block_write_begin(handle_t *handle, struct folio *folio,
-static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
+			   loff_t pos, unsigned len,
-				  get_block_t *get_block)
+			   get_block_t *get_block)
 {
 	unsigned from = pos & (PAGE_SIZE - 1);
 	unsigned to = from + len;
@@ -1056,6 +1027,7 @@ static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 	struct buffer_head *bh, *head, *wait[2];
 	int nr_wait = 0;
 	int i;
+	bool should_journal_data = ext4_should_journal_data(inode);
 
 	BUG_ON(!folio_test_locked(folio));
 	BUG_ON(from > PAGE_SIZE);
@@ -1085,10 +1057,22 @@ static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 			if (err)
 				break;
 			if (buffer_new(bh)) {
+				/*
+				 * We may be zeroing partial buffers or all new
+				 * buffers in case of failure. Prepare JBD2 for
+				 * that.
+				 */
+				if (should_journal_data)
+					do_journal_get_write_access(handle,
+								    inode, bh);
 				if (folio_test_uptodate(folio)) {
-					clear_buffer_new(bh);
+					/*
+					 * Unlike __block_write_begin() we leave
+					 * dirtying of new uptodate buffers to
+					 * ->write_end() time or
+					 * folio_zero_new_buffers().
+					 */
 					set_buffer_uptodate(bh);
-					mark_buffer_dirty(bh);
 					continue;
 				}
 				if (block_end > to || block_start < from)
@@ -1118,7 +1102,11 @@ static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 			err = -EIO;
 	}
 	if (unlikely(err)) {
-		folio_zero_new_buffers(folio, from, to);
+		if (should_journal_data)
+			ext4_journalled_zero_new_buffers(handle, inode, folio,
+							 from, to);
+		else
+			folio_zero_new_buffers(folio, from, to);
 	} else if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
 		for (i = 0; i < nr_wait; i++) {
 			int err2;
@@ -1134,7 +1122,6 @@ static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 
 	return err;
 }
-#endif
 
 /*
  * To preserve ordering, it is essential that the hole instantiation and
@@ -1216,19 +1203,12 @@ retry_journal:
 	/* In case writeback began while the folio was unlocked */
 	folio_wait_stable(folio);
 
-#ifdef CONFIG_FS_ENCRYPTION
 	if (ext4_should_dioread_nolock(inode))
-		ret = ext4_block_write_begin(folio, pos, len,
+		ret = ext4_block_write_begin(handle, folio, pos, len,
 					     ext4_get_block_unwritten);
 	else
-		ret = ext4_block_write_begin(folio, pos, len, ext4_get_block);
+		ret = ext4_block_write_begin(handle, folio, pos, len,
-#else
+					     ext4_get_block);
-	if (ext4_should_dioread_nolock(inode))
-		ret = __block_write_begin(folio, pos, len,
-					  ext4_get_block_unwritten);
-	else
-		ret = __block_write_begin(folio, pos, len, ext4_get_block);
-#endif
 	if (!ret && ext4_should_journal_data(inode)) {
 		ret = ext4_walk_page_buffers(handle, inode,
 					     folio_buffers(folio), from, to,
@@ -1241,7 +1221,7 @@ retry_journal:
 
 		folio_unlock(folio);
 		/*
-		 * __block_write_begin may have instantiated a few blocks
+		 * ext4_block_write_begin may have instantiated a few blocks
 		 * outside i_size.  Trim these off again. Don't need
 		 * i_size_read because we hold i_rwsem.
 		 *
@@ -1388,9 +1368,9 @@ static void ext4_journalled_zero_new_buffers(handle_t *handle,
 					size = min(to, block_end) - start;
 
 					folio_zero_range(folio, start, size);
-					write_end_fn(handle, inode, bh);
 				}
 				clear_buffer_new(bh);
+				write_end_fn(handle, inode, bh);
 			}
 		}
 		block_start = block_end;
@@ -1661,7 +1641,7 @@ static int ext4_clu_alloc_state(struct inode *inode, ext4_lblk_t lblk)
 	int ret;
 
 	/* Has delalloc reservation? */
-	if (ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk))
+	if (ext4_es_scan_clu(inode, &ext4_es_is_delayed, lblk))
 		return 1;
 
 	/* Already been allocated? */
@@ -1782,7 +1762,7 @@ found:
 		 * Delayed extent could be allocated by fallocate.
 		 * So we need to check it.
 		 */
-		if (ext4_es_is_delonly(&es)) {
+		if (ext4_es_is_delayed(&es)) {
 			map->m_flags |= EXT4_MAP_DELAYED;
 			return 0;
 		}
@@ -2217,11 +2197,6 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 	 * writeback and there is nothing we can do about it so it might result
 	 * in data loss.  So use reserved blocks to allocate metadata if
 	 * possible.
-	 *
-	 * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE if
-	 * the blocks in question are delalloc blocks.  This indicates
-	 * that the blocks and quotas has already been checked when
-	 * the data was copied into the page cache.
 	 */
 	get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
 			   EXT4_GET_BLOCKS_METADATA_NOFAIL |
@@ -2229,8 +2204,6 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 	dioread_nolock = ext4_should_dioread_nolock(inode);
 	if (dioread_nolock)
 		get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
-	if (map->m_flags & BIT(BH_Delay))
-		get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
 
 	err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
 	if (err < 0)
@@ -2959,11 +2932,8 @@ retry:
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
-#ifdef CONFIG_FS_ENCRYPTION
+	ret = ext4_block_write_begin(NULL, folio, pos, len,
-	ret = ext4_block_write_begin(folio, pos, len, ext4_da_get_block_prep);
+				     ext4_da_get_block_prep);
-#else
-	ret = __block_write_begin(folio, pos, len, ext4_da_get_block_prep);
-#endif
 	if (ret < 0) {
 		folio_unlock(folio);
 		folio_put(folio);
@@ -4067,7 +4037,7 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 						    stop_block);
 
 		ext4_es_insert_extent(inode, first_block, hole_len, ~0,
-				      EXTENT_STATUS_HOLE);
+				      EXTENT_STATUS_HOLE, 0);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	ext4_fc_track_range(handle, inode, first_block, stop_block);
@@ -5276,8 +5246,9 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
 {
 	unsigned offset;
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
-	tid_t commit_tid = 0;
+	tid_t commit_tid;
 	int ret;
+	bool has_transaction;
 
 	offset = inode->i_size & (PAGE_SIZE - 1);
 	/*
@@ -5302,12 +5273,14 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
 		folio_put(folio);
 		if (ret != -EBUSY)
 			return;
-		commit_tid = 0;
+		has_transaction = false;
 		read_lock(&journal->j_state_lock);
-		if (journal->j_committing_transaction)
+		if (journal->j_committing_transaction) {
 			commit_tid = journal->j_committing_transaction->t_tid;
+			has_transaction = true;
+		}
 		read_unlock(&journal->j_state_lock);
-		if (commit_tid)
+		if (has_transaction)
 			jbd2_log_wait_commit(journal, commit_tid);
 	}
 }
@@ -6216,7 +6189,8 @@ retry_alloc:
 		if (folio_pos(folio) + len > size)
 			len = size - folio_pos(folio);
 
-		err = __block_write_begin(folio, 0, len, ext4_get_block);
+		err = ext4_block_write_begin(handle, folio, 0, len,
+					     ext4_get_block);
 		if (!err) {
 			ret = VM_FAULT_SIGBUS;
 			if (ext4_journal_folio_buffers(handle, folio, len))

fs/ext4/mballoc.c

@@ -2356,7 +2356,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 	ex.fe_logical = 0xDEADFA11; /* debug value */
 
 	if (max >= ac->ac_g_ex.fe_len &&
-	    ac->ac_g_ex.fe_len == EXT4_B2C(sbi, sbi->s_stripe)) {
+	    ac->ac_g_ex.fe_len == EXT4_NUM_B2C(sbi, sbi->s_stripe)) {
 		ext4_fsblk_t start;
 
 		start = ext4_grp_offs_to_block(ac->ac_sb, &ex);
@@ -2553,7 +2553,7 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
 	do_div(a, sbi->s_stripe);
 	i = (a * sbi->s_stripe) - first_group_block;
 
-	stripe = EXT4_B2C(sbi, sbi->s_stripe);
+	stripe = EXT4_NUM_B2C(sbi, sbi->s_stripe);
 	i = EXT4_B2C(sbi, i);
 	while (i < EXT4_CLUSTERS_PER_GROUP(sb)) {
 		if (!mb_test_bit(i, bitmap)) {
@@ -2928,9 +2928,11 @@ repeat:
 			if (cr == CR_POWER2_ALIGNED)
 				ext4_mb_simple_scan_group(ac, &e4b);
 			else {
-				bool is_stripe_aligned = sbi->s_stripe &&
+				bool is_stripe_aligned =
+					(sbi->s_stripe >=
+					 sbi->s_cluster_ratio) &&
 					!(ac->ac_g_ex.fe_len %
-					  EXT4_B2C(sbi, sbi->s_stripe));
+					  EXT4_NUM_B2C(sbi, sbi->s_stripe));
 
 				if ((cr == CR_GOAL_LEN_FAST ||
 				     cr == CR_BEST_AVAIL_LEN) &&
@@ -3075,8 +3077,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	seq_puts(seq, " ]");
 	if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info))
 		seq_puts(seq, " Block bitmap corrupted!");
-	seq_puts(seq, "\n");
+	seq_putc(seq, '\n');
-
 	return 0;
 }
 
@@ -3707,7 +3708,7 @@ int ext4_mb_init(struct super_block *sb)
 	 */
 	if (sbi->s_stripe > 1) {
 		sbi->s_mb_group_prealloc = roundup(
-			sbi->s_mb_group_prealloc, EXT4_B2C(sbi, sbi->s_stripe));
+			sbi->s_mb_group_prealloc, EXT4_NUM_B2C(sbi, sbi->s_stripe));
 	}
 
 	sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
@@ -3887,11 +3888,8 @@ static void ext4_free_data_in_buddy(struct super_block *sb,
 	/*
 	 * Clear the trimmed flag for the group so that the next
 	 * ext4_trim_fs can trim it.
-	 * If the volume is mounted with -o discard, online discard
-	 * is supported and the free blocks will be trimmed online.
 	 */
-	if (!test_opt(sb, DISCARD))
+	EXT4_MB_GRP_CLEAR_TRIMMED(db);
-		EXT4_MB_GRP_CLEAR_TRIMMED(db);
 
 	if (!db->bb_free_root.rb_node) {
 		/* No more items in the per group rb tree
@@ -6515,8 +6513,9 @@ do_more:
 					 " group:%u block:%d count:%lu failed"
 					 " with %d", block_group, bit, count,
 					 err);
-		} else
+		}
-			EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
+
+		EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
 
 		ext4_lock_group(sb, block_group);
 		mb_free_blocks(inode, &e4b, bit, count_clusters);

fs/ext4/migrate.c

@@ -37,7 +37,6 @@ static int finish_range(handle_t *handle, struct inode *inode,
 	path = ext4_find_extent(inode, lb->first_block, NULL, 0);
 	if (IS_ERR(path)) {
 		retval = PTR_ERR(path);
-		path = NULL;
 		goto err_out;
 	}
 
@@ -53,7 +52,9 @@ static int finish_range(handle_t *handle, struct inode *inode,
 	retval = ext4_datasem_ensure_credits(handle, inode, needed, needed, 0);
 	if (retval < 0)
 		goto err_out;
-	retval = ext4_ext_insert_extent(handle, inode, &path, &newext, 0);
+	path = ext4_ext_insert_extent(handle, inode, path, &newext, 0);
+	if (IS_ERR(path))
+		retval = PTR_ERR(path);
 err_out:
 	up_write((&EXT4_I(inode)->i_data_sem));
 	ext4_free_ext_path(path);
@@ -663,8 +664,8 @@ int ext4_ind_migrate(struct inode *inode)
 	if (unlikely(ret2 && !ret))
 		ret = ret2;
 errout:
-	ext4_journal_stop(handle);
 	up_write(&EXT4_I(inode)->i_data_sem);
+	ext4_journal_stop(handle);
 out_unlock:
 	ext4_writepages_up_write(inode->i_sb, alloc_ctx);
 	return ret;

fs/ext4/move_extent.c

@@ -17,27 +17,23 @@
  * get_ext_path() - Find an extent path for designated logical block number.
  * @inode:	inode to be searched
  * @lblock:	logical block number to find an extent path
- * @ppath:	pointer to an extent path pointer (for output)
+ * @path:	pointer to an extent path
  *
- * ext4_find_extent wrapper. Return 0 on success, or a negative error value
+ * ext4_find_extent wrapper. Return an extent path pointer on success,
- * on failure.
+ * or an error pointer on failure.
  */
-static inline int
+static inline struct ext4_ext_path *
 get_ext_path(struct inode *inode, ext4_lblk_t lblock,
-		struct ext4_ext_path **ppath)
+	     struct ext4_ext_path *path)
 {
-	struct ext4_ext_path *path;
+	path = ext4_find_extent(inode, lblock, path, EXT4_EX_NOCACHE);
-
-	path = ext4_find_extent(inode, lblock, ppath, EXT4_EX_NOCACHE);
 	if (IS_ERR(path))
-		return PTR_ERR(path);
+		return path;
 	if (path[ext_depth(inode)].p_ext == NULL) {
 		ext4_free_ext_path(path);
-		*ppath = NULL;
+		return ERR_PTR(-ENODATA);
-		return -ENODATA;
 	}
-	*ppath = path;
+	return path;
-	return 0;
 }
 
 /**
@@ -95,9 +91,11 @@ mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
 	int ret = 0;
 	ext4_lblk_t last = from + count;
 	while (from < last) {
-		*err = get_ext_path(inode, from, &path);
+		path = get_ext_path(inode, from, path);
-		if (*err)
+		if (IS_ERR(path)) {
-			goto out;
+			*err = PTR_ERR(path);
+			return ret;
+		}
 		ext = path[ext_depth(inode)].p_ext;
 		if (unwritten != ext4_ext_is_unwritten(ext))
 			goto out;
@@ -166,15 +164,16 @@ mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
 	return 0;
 }
 
-/* Force page buffers uptodate w/o dropping page's lock */
+/* Force folio buffers uptodate w/o dropping folio's lock */
-static int
+static int mext_page_mkuptodate(struct folio *folio, size_t from, size_t to)
-mext_page_mkuptodate(struct folio *folio, unsigned from, unsigned to)
 {
 	struct inode *inode = folio->mapping->host;
 	sector_t block;
-	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
+	struct buffer_head *bh, *head;
 	unsigned int blocksize, block_start, block_end;
-	int i, err,  nr = 0, partial = 0;
+	int nr = 0;
+	bool partial = false;
+
 	BUG_ON(!folio_test_locked(folio));
 	BUG_ON(folio_test_writeback(folio));
 
@@ -186,19 +185,21 @@ mext_page_mkuptodate(struct folio *folio, unsigned from, unsigned to)
 	if (!head)
 		head = create_empty_buffers(folio, blocksize, 0);
 
-	block = (sector_t)folio->index << (PAGE_SHIFT - inode->i_blkbits);
+	block = folio_pos(folio) >> inode->i_blkbits;
-	for (bh = head, block_start = 0; bh != head || !block_start;
+	block_end = 0;
-	     block++, block_start = block_end, bh = bh->b_this_page) {
+	bh = head;
+	do {
+		block_start = block_end;
 		block_end = block_start + blocksize;
 		if (block_end <= from || block_start >= to) {
 			if (!buffer_uptodate(bh))
-				partial = 1;
+				partial = true;
 			continue;
 		}
 		if (buffer_uptodate(bh))
 			continue;
 		if (!buffer_mapped(bh)) {
-			err = ext4_get_block(inode, block, bh, 0);
+			int err = ext4_get_block(inode, block, bh, 0);
 			if (err)
 				return err;
 			if (!buffer_mapped(bh)) {
@@ -207,21 +208,30 @@ mext_page_mkuptodate(struct folio *folio, unsigned from, unsigned to)
 				continue;
 			}
 		}
-		BUG_ON(nr >= MAX_BUF_PER_PAGE);
+		lock_buffer(bh);
-		arr[nr++] = bh;
+		if (buffer_uptodate(bh)) {
-	}
+			unlock_buffer(bh);
+			continue;
+		}
+		ext4_read_bh_nowait(bh, 0, NULL);
+		nr++;
+	} while (block++, (bh = bh->b_this_page) != head);
+
 	/* No io required */
 	if (!nr)
 		goto out;
 
-	for (i = 0; i < nr; i++) {
+	bh = head;
-		bh = arr[i];
+	do {
-		if (!bh_uptodate_or_lock(bh)) {
+		if (bh_offset(bh) + blocksize <= from)
-			err = ext4_read_bh(bh, 0, NULL);
+			continue;
-			if (err)
+		if (bh_offset(bh) > to)
-				return err;
+			break;
-		}
+		wait_on_buffer(bh);
-	}
+		if (buffer_uptodate(bh))
+			continue;
+		return -EIO;
+	} while ((bh = bh->b_this_page) != head);
 out:
 	if (!partial)
 		folio_mark_uptodate(folio);
@@ -624,9 +634,11 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		int offset_in_page;
 		int unwritten, cur_len;
 
-		ret = get_ext_path(orig_inode, o_start, &path);
+		path = get_ext_path(orig_inode, o_start, path);
-		if (ret)
+		if (IS_ERR(path)) {
+			ret = PTR_ERR(path);
 			goto out;
+		}
 		ex = path[path->p_depth].p_ext;
 		cur_blk = le32_to_cpu(ex->ee_block);
 		cur_len = ext4_ext_get_actual_len(ex);

fs/ext4/namei.c

@@ -1482,7 +1482,7 @@ static bool ext4_match(struct inode *parent,
 }
 
 /*
- * Returns 0 if not found, -1 on failure, and 1 on success
+ * Returns 0 if not found, -EFSCORRUPTED on failure, and 1 on success
  */
 int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 		    struct inode *dir, struct ext4_filename *fname,
@@ -1503,7 +1503,7 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 			 * a full check */
 			if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf,
 						 buf_size, offset))
-				return -1;
+				return -EFSCORRUPTED;
 			*res_dir = de;
 			return 1;
 		}
@@ -1511,7 +1511,7 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 		de_len = ext4_rec_len_from_disk(de->rec_len,
 						dir->i_sb->s_blocksize);
 		if (de_len <= 0)
-			return -1;
+			return -EFSCORRUPTED;
 		offset += de_len;
 		de = (struct ext4_dir_entry_2 *) ((char *) de + de_len);
 	}
@@ -1574,7 +1574,7 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir,
 					     &has_inline_data);
 		if (inlined)
 			*inlined = has_inline_data;
-		if (has_inline_data)
+		if (has_inline_data || IS_ERR(ret))
 			goto cleanup_and_exit;
 	}
 
@@ -1663,8 +1663,10 @@ restart:
 			goto cleanup_and_exit;
 		} else {
 			brelse(bh);
-			if (i < 0)
+			if (i < 0) {
+				ret = ERR_PTR(i);
 				goto cleanup_and_exit;
+			}
 		}
 	next:
 		if (++block >= nblocks)
@@ -1758,7 +1760,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
 		if (retval == 1)
 			goto success;
 		brelse(bh);
-		if (retval == -1) {
+		if (retval < 0) {
 			bh = ERR_PTR(ERR_BAD_DX_DIR);
 			goto errout;
 		}
@@ -1999,7 +2001,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 		split = count/2;
 
 	hash2 = map[split].hash;
-	continued = hash2 == map[split - 1].hash;
+	continued = split > 0 ? hash2 == map[split - 1].hash : 0;
 	dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
 			(unsigned long)dx_get_block(frame->at),
 					hash2, split, count-split));

fs/ext4/readpage.c

@@ -221,7 +221,7 @@ int ext4_mpage_readpages(struct inode *inode,
 	sector_t block_in_file;
 	sector_t last_block;
 	sector_t last_block_in_file;
-	sector_t blocks[MAX_BUF_PER_PAGE];
+	sector_t first_block;
 	unsigned page_block;
 	struct block_device *bdev = inode->i_sb->s_bdev;
 	int length;
@@ -263,6 +263,7 @@ int ext4_mpage_readpages(struct inode *inode,
 			unsigned map_offset = block_in_file - map.m_lblk;
 			unsigned last = map.m_len - map_offset;
 
+			first_block = map.m_pblk + map_offset;
 			for (relative_block = 0; ; relative_block++) {
 				if (relative_block == last) {
 					/* needed? */
@@ -271,8 +272,6 @@ int ext4_mpage_readpages(struct inode *inode,
 				}
 				if (page_block == blocks_per_page)
 					break;
-				blocks[page_block] = map.m_pblk + map_offset +
-					relative_block;
 				page_block++;
 				block_in_file++;
 			}
@@ -307,7 +306,9 @@ int ext4_mpage_readpages(struct inode *inode,
 				goto confused;		/* hole -> non-hole */
 
 			/* Contiguous blocks? */
-			if (page_block && blocks[page_block-1] != map.m_pblk-1)
+			if (!page_block)
+				first_block = map.m_pblk;
+			else if (first_block + page_block != map.m_pblk)
 				goto confused;
 			for (relative_block = 0; ; relative_block++) {
 				if (relative_block == map.m_len) {
@@ -316,7 +317,6 @@ int ext4_mpage_readpages(struct inode *inode,
 					break;
 				} else if (page_block == blocks_per_page)
 					break;
-				blocks[page_block] = map.m_pblk+relative_block;
 				page_block++;
 				block_in_file++;
 			}
@@ -339,7 +339,7 @@ int ext4_mpage_readpages(struct inode *inode,
 		 * This folio will go to BIO.  Do we need to send this
 		 * BIO off first?
 		 */
-		if (bio && (last_block_in_bio != blocks[0] - 1 ||
+		if (bio && (last_block_in_bio != first_block - 1 ||
 			    !fscrypt_mergeable_bio(bio, inode, next_block))) {
 		submit_and_realloc:
 			submit_bio(bio);
@@ -355,7 +355,7 @@ int ext4_mpage_readpages(struct inode *inode,
 			fscrypt_set_bio_crypt_ctx(bio, inode, next_block,
 						  GFP_KERNEL);
 			ext4_set_bio_post_read_ctx(bio, inode, folio->index);
-			bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
+			bio->bi_iter.bi_sector = first_block << (blkbits - 9);
 			bio->bi_end_io = mpage_end_io;
 			if (rac)
 				bio->bi_opf |= REQ_RAHEAD;
@@ -371,7 +371,7 @@ int ext4_mpage_readpages(struct inode *inode,
 			submit_bio(bio);
 			bio = NULL;
 		} else
-			last_block_in_bio = blocks[blocks_per_page - 1];
+			last_block_in_bio = first_block + blocks_per_page - 1;
 		continue;
 	confused:
 		if (bio) {

fs/ext4/resize.c

@@ -1319,8 +1319,7 @@ static int ext4_set_bitmap_checksums(struct super_block *sb,
 	bh = ext4_get_bitmap(sb, group_data->inode_bitmap);
 	if (!bh)
 		return -EIO;
-	ext4_inode_bitmap_csum_set(sb, gdp, bh,
+	ext4_inode_bitmap_csum_set(sb, gdp, bh);
-				   EXT4_INODES_PER_GROUP(sb) / 8);
 	brelse(bh);
 
 	bh = ext4_get_bitmap(sb, group_data->block_bitmap);

fs/ext4/super.c

@@ -735,11 +735,12 @@ 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
+	 * EXT4_FLAGS_SHUTDOWN was set which stops all filesystem
-	 * ->s_flags update
+	 * 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)
@@ -3045,7 +3046,7 @@ 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;
 }
 
@@ -5087,16 +5088,27 @@ 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)
@@ -5114,6 +5126,7 @@ 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)
@@ -5165,6 +5178,18 @@ 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;
@@ -5249,7 +5274,9 @@ 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)
@@ -5272,13 +5299,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		goto failed_mount3;
 
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
-	/*
+	if (ext4_is_stripe_incompatible(sb, sbi->s_stripe)) {
-	 * 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) {
 		ext4_msg(sb, KERN_WARNING,
 			 "stripe (%lu) is not aligned with cluster size (%u), "
 			 "stripe is disabled",
@@ -5313,6 +5334,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *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_fast_commit_init(sb);
 
 	sb->s_root = NULL;
@@ -5534,7 +5557,6 @@ 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_mapping->wb_err,
 				 &sbi->s_bdev_wb_err);
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
@@ -5614,8 +5636,8 @@ 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)
@@ -6441,6 +6463,15 @@ 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

fs/ext4/xattr.c

@@ -458,7 +458,7 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino,
 		ext4_set_inode_state(inode, EXT4_STATE_LUSTRE_EA_INODE);
 		ext4_xattr_inode_set_ref(inode, 1);
 	} else {
-		inode_lock(inode);
+		inode_lock_nested(inode, I_MUTEX_XATTR);
 		inode->i_flags |= S_NOQUOTA;
 		inode_unlock(inode);
 	}
@@ -1039,7 +1039,7 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
 	s64 ref_count;
 	int ret;
 
-	inode_lock(ea_inode);
+	inode_lock_nested(ea_inode, I_MUTEX_XATTR);
 
 	ret = ext4_reserve_inode_write(handle, ea_inode, &iloc);
 	if (ret)
@@ -2879,33 +2879,31 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
 	if (*ea_inode_array == NULL) {
 		/*
 		 * Start with 15 inodes, so it fits into a power-of-two size.
-		 * If *ea_inode_array is NULL, this is essentially offsetof()
 		 */
-		(*ea_inode_array) =
+		(*ea_inode_array) = kmalloc(
-			kmalloc(offsetof(struct ext4_xattr_inode_array,
+			struct_size(*ea_inode_array, inodes, EIA_MASK),
-					 inodes[EIA_MASK]),
+			GFP_NOFS);
-				GFP_NOFS);
 		if (*ea_inode_array == NULL)
 			return -ENOMEM;
 		(*ea_inode_array)->count = 0;
 	} else if (((*ea_inode_array)->count & EIA_MASK) == EIA_MASK) {
 		/* expand the array once all 15 + n * 16 slots are full */
 		struct ext4_xattr_inode_array *new_array = NULL;
-		int count = (*ea_inode_array)->count;
 
-		/* if new_array is NULL, this is essentially offsetof() */
 		new_array = kmalloc(
-				offsetof(struct ext4_xattr_inode_array,
+			struct_size(*ea_inode_array, inodes,
-					 inodes[count + EIA_INCR]),
+				    (*ea_inode_array)->count + EIA_INCR),
-				GFP_NOFS);
+			GFP_NOFS);
 		if (new_array == NULL)
 			return -ENOMEM;
 		memcpy(new_array, *ea_inode_array,
-		       offsetof(struct ext4_xattr_inode_array, inodes[count]));
+		       struct_size(*ea_inode_array, inodes,
+				   (*ea_inode_array)->count));
 		kfree(*ea_inode_array);
 		*ea_inode_array = new_array;
 	}
-	(*ea_inode_array)->inodes[(*ea_inode_array)->count++] = inode;
+	(*ea_inode_array)->count++;
+	(*ea_inode_array)->inodes[(*ea_inode_array)->count - 1] = inode;
 	return 0;
 }
 
@@ -3036,8 +3034,6 @@ void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *ea_inode_array)
  *
  * Create a new entry in the extended attribute block cache, and insert
  * it unless such an entry is already in the cache.
- *
- * Returns 0, or a negative error number on failure.
  */
 static void
 ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache,
@@ -3065,8 +3061,7 @@ ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache,
  *
  * Compare two extended attribute blocks for equality.
  *
- * Returns 0 if the blocks are equal, 1 if they differ, and
+ * Returns 0 if the blocks are equal, 1 if they differ.
- * a negative error number on errors.
  */
 static int
 ext4_xattr_cmp(struct ext4_xattr_header *header1,

fs/ext4/xattr.h

@@ -32,8 +32,7 @@ struct ext4_xattr_header {
 	__le32	h_refcount;	/* reference count */
 	__le32	h_blocks;	/* number of disk blocks used */
 	__le32	h_hash;		/* hash value of all attributes */
-	__le32	h_checksum;	/* crc32c(uuid+id+xattrblock) */
+	__le32	h_checksum;	/* crc32c(uuid+blknum+xattrblock) */
-				/* id = inum if refcount=1, blknum otherwise */
 	__u32	h_reserved[3];	/* zero right now */
 };
 
@@ -130,8 +129,8 @@ struct ext4_xattr_ibody_find {
 };
 
 struct ext4_xattr_inode_array {
-	unsigned int count;		/* # of used items in the array */
+	unsigned int count;
-	struct inode *inodes[];
+	struct inode *inodes[] __counted_by(count);
 };
 
 extern const struct xattr_handler ext4_xattr_user_handler;

fs/jbd2/checkpoint.c

@@ -79,17 +79,23 @@ __releases(&journal->j_state_lock)
 		if (space_left < nblocks) {
 			int chkpt = journal->j_checkpoint_transactions != NULL;
 			tid_t tid = 0;
+			bool has_transaction = false;
 
-			if (journal->j_committing_transaction)
+			if (journal->j_committing_transaction) {
 				tid = journal->j_committing_transaction->t_tid;
+				has_transaction = true;
+			}
 			spin_unlock(&journal->j_list_lock);
 			write_unlock(&journal->j_state_lock);
 			if (chkpt) {
 				jbd2_log_do_checkpoint(journal);
-			} else if (jbd2_cleanup_journal_tail(journal) == 0) {
+			} else if (jbd2_cleanup_journal_tail(journal) <= 0) {
-				/* We were able to recover space; yay! */
+				/*
+				 * We were able to recover space or the
+				 * journal was aborted due to an error.
+				 */
 				;
-			} else if (tid) {
+			} else if (has_transaction) {
 				/*
 				 * jbd2_journal_commit_transaction() may want
 				 * to take the checkpoint_mutex if JBD2_FLUSHED
@@ -407,6 +413,7 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
 	tid_t tid = 0;
 	unsigned long nr_freed = 0;
 	unsigned long freed;
+	bool first_set = false;
 
 again:
 	spin_lock(&journal->j_list_lock);
@@ -426,8 +433,10 @@ again:
 	else
 		transaction = journal->j_checkpoint_transactions;
 
-	if (!first_tid)
+	if (!first_set) {
 		first_tid = transaction->t_tid;
+		first_set = true;
+	}
 	last_transaction = journal->j_checkpoint_transactions->t_cpprev;
 	next_transaction = transaction;
 	last_tid = last_transaction->t_tid;
@@ -457,7 +466,7 @@ again:
 	spin_unlock(&journal->j_list_lock);
 	cond_resched();
 
-	if (*nr_to_scan && next_tid)
+	if (*nr_to_scan && journal->j_shrink_transaction)
 		goto again;
 out:
 	trace_jbd2_shrink_checkpoint_list(journal, first_tid, tid, last_tid,

fs/jbd2/journal.c

@@ -281,6 +281,16 @@ static void journal_kill_thread(journal_t *journal)
 	write_unlock(&journal->j_state_lock);
 }
 
+static inline bool jbd2_data_needs_escaping(char *data)
+{
+	return *((__be32 *)data) == cpu_to_be32(JBD2_MAGIC_NUMBER);
+}
+
+static inline void jbd2_data_do_escape(char *data)
+{
+	*((unsigned int *)data) = 0;
+}
+
 /*
  * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal.
  *
@@ -318,9 +328,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 				  struct buffer_head **bh_out,
 				  sector_t blocknr)
 {
-	int done_copy_out = 0;
 	int do_escape = 0;
-	char *mapped_data;
 	struct buffer_head *new_bh;
 	struct folio *new_folio;
 	unsigned int new_offset;
@@ -349,37 +357,33 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	 * we use that version of the data for the commit.
 	 */
 	if (jh_in->b_frozen_data) {
-		done_copy_out = 1;
 		new_folio = virt_to_folio(jh_in->b_frozen_data);
 		new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data);
+		do_escape = jbd2_data_needs_escaping(jh_in->b_frozen_data);
+		if (do_escape)
+			jbd2_data_do_escape(jh_in->b_frozen_data);
 	} else {
+		char *tmp;
+		char *mapped_data;
+
 		new_folio = bh_in->b_folio;
 		new_offset = offset_in_folio(new_folio, bh_in->b_data);
-	}
+		mapped_data = kmap_local_folio(new_folio, new_offset);
-
+		/*
-	mapped_data = kmap_local_folio(new_folio, new_offset);
+		 * Fire data frozen trigger if data already wasn't frozen. Do
-	/*
+		 * this before checking for escaping, as the trigger may modify
-	 * Fire data frozen trigger if data already wasn't frozen.  Do this
+		 * the magic offset.  If a copy-out happens afterwards, it will
-	 * before checking for escaping, as the trigger may modify the magic
+		 * have the correct data in the buffer.
-	 * offset.  If a copy-out happens afterwards, it will have the correct
+		 */
-	 * data in the buffer.
-	 */
-	if (!done_copy_out)
 		jbd2_buffer_frozen_trigger(jh_in, mapped_data,
 					   jh_in->b_triggers);
-
+		do_escape = jbd2_data_needs_escaping(mapped_data);
-	/*
+		kunmap_local(mapped_data);
-	 * Check for escaping
+		/*
-	 */
+		 * Do we need to do a data copy?
-	if (*((__be32 *)mapped_data) == cpu_to_be32(JBD2_MAGIC_NUMBER))
+		 */
-		do_escape = 1;
+		if (!do_escape)
-	kunmap_local(mapped_data);
+			goto escape_done;
-
-	/*
-	 * Do we need to do a data copy?
-	 */
-	if (do_escape && !done_copy_out) {
-		char *tmp;
 
 		spin_unlock(&jh_in->b_state_lock);
 		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
@@ -406,18 +410,10 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 copy_done:
 		new_folio = virt_to_folio(jh_in->b_frozen_data);
 		new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data);
-		done_copy_out = 1;
+		jbd2_data_do_escape(jh_in->b_frozen_data);
 	}
 
-	/*
+escape_done:
-	 * Did we need to do an escaping?  Now we've done all the
-	 * copying, we can finally do so.
-	 * b_frozen_data is from jbd2_alloc() which always provides an
-	 * address from the direct kernels mapping.
-	 */
-	if (do_escape)
-		*((unsigned int *)jh_in->b_frozen_data) = 0;
-
 	folio_set_bh(new_bh, new_folio, new_offset);
 	new_bh->b_size = bh_in->b_size;
 	new_bh->b_bdev = journal->j_dev;
@@ -710,7 +706,7 @@ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
 		return -EINVAL;
 
 	write_lock(&journal->j_state_lock);
-	if (tid <= journal->j_commit_sequence) {
+	if (tid_geq(journal->j_commit_sequence, tid)) {
 		write_unlock(&journal->j_state_lock);
 		return -EALREADY;
 	}
@@ -740,9 +736,9 @@ EXPORT_SYMBOL(jbd2_fc_begin_commit);
  */
 static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
 {
-	jbd2_journal_unlock_updates(journal);
 	if (journal->j_fc_cleanup_callback)
 		journal->j_fc_cleanup_callback(journal, 0, tid);
+	jbd2_journal_unlock_updates(journal);
 	write_lock(&journal->j_state_lock);
 	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
 	if (fallback)
@@ -841,17 +837,12 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
 
 	*bh_out = NULL;
 
-	if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
+	if (journal->j_fc_off + journal->j_fc_first >= journal->j_fc_last)
-		fc_off = journal->j_fc_off;
+		return -EINVAL;
-		blocknr = journal->j_fc_first + fc_off;
-		journal->j_fc_off++;
-	} else {
-		ret = -EINVAL;
-	}
-
-	if (ret)
-		return ret;
 
+	fc_off = journal->j_fc_off;
+	blocknr = journal->j_fc_first + fc_off;
+	journal->j_fc_off++;
 	ret = jbd2_journal_bmap(journal, blocknr, &pblock);
 	if (ret)
 		return ret;
@@ -860,7 +851,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
 	if (!bh)
 		return -ENOMEM;
 
-
 	journal->j_fc_wbuf[fc_off] = bh;
 
 	*bh_out = bh;
@@ -903,7 +893,7 @@ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks)
 }
 EXPORT_SYMBOL(jbd2_fc_wait_bufs);
 
-int jbd2_fc_release_bufs(journal_t *journal)
+void jbd2_fc_release_bufs(journal_t *journal)
 {
 	struct buffer_head *bh;
 	int i, j_fc_off;
@@ -917,8 +907,6 @@ int jbd2_fc_release_bufs(journal_t *journal)
 		put_bh(bh);
 		journal->j_fc_wbuf[i] = NULL;
 	}
-
-	return 0;
 }
 EXPORT_SYMBOL(jbd2_fc_release_bufs);
 
@@ -1944,7 +1932,7 @@ static void jbd2_mark_journal_empty(journal_t *journal, blk_opf_t write_flags)
 	if (had_fast_commit)
 		jbd2_set_feature_fast_commit(journal);
 
-	/* Log is no longer empty */
+	/* Log is empty */
 	write_lock(&journal->j_state_lock);
 	journal->j_flags |= JBD2_FLUSHED;
 	write_unlock(&journal->j_state_lock);
@@ -2866,8 +2854,7 @@ static struct journal_head *journal_alloc_journal_head(void)
 		ret = kmem_cache_zalloc(jbd2_journal_head_cache,
 				GFP_NOFS | __GFP_NOFAIL);
 	}
-	if (ret)
+	spin_lock_init(&ret->b_state_lock);
-		spin_lock_init(&ret->b_state_lock);
 	return ret;
 }
 

include/linux/jbd2.h

@@ -1086,7 +1086,7 @@ struct journal_s
 	int			j_revoke_records_per_block;
 
 	/**
-	 * @j_transaction_overhead:
+	 * @j_transaction_overhead_buffers:
 	 *
 	 * Number of blocks each transaction needs for its own bookkeeping
 	 */
@@ -1675,7 +1675,7 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
 int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode);
 int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
 int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
-int jbd2_fc_release_bufs(journal_t *journal);
+void jbd2_fc_release_bufs(journal_t *journal);
 
 /*
  * is_journal_abort