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

Pull ext4 updates from Ted Ts'o:
 "There are a number of major cleanups in ext4 this cycle:

   - The data=journal writepath has been significantly cleaned up and
     simplified, and reduces a large number of data=journal special
     cases by Jan Kara.

   - Ojaswin Muhoo has replaced linked list used to track extents that
     have been used for inode preallocation with a red-black tree in the
     multi-block allocator. This improves performance for workloads
     which do a large number of random allocating writes.

   - Thanks to Kemeng Shi for a lot of cleanup and bug fixes in the
     multi-block allocator.

   - Matthew wilcox has converted the code paths for reading and writing
     ext4 pages to use folios.

   - Jason Yan has continued to factor out ext4_fill_super() into
     smaller functions for improve ease of maintenance and
     comprehension.

   - Josh Triplett has created an uapi header for ext4 userspace API's"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (105 commits)
  ext4: Add a uapi header for ext4 userspace APIs
  ext4: remove useless conditional branch code
  ext4: remove unneeded check of nr_to_submit
  ext4: move dax and encrypt checking into ext4_check_feature_compatibility()
  ext4: factor out ext4_block_group_meta_init()
  ext4: move s_reserved_gdt_blocks and addressable checking into ext4_check_geometry()
  ext4: rename two functions with 'check'
  ext4: factor out ext4_flex_groups_free()
  ext4: use ext4_group_desc_free() in ext4_put_super() to save some duplicated code
  ext4: factor out ext4_percpu_param_init() and ext4_percpu_param_destroy()
  ext4: factor out ext4_hash_info_init()
  Revert "ext4: Fix warnings when freezing filesystem with journaled data"
  ext4: Update comment in mpage_prepare_extent_to_map()
  ext4: Simplify handling of journalled data in ext4_bmap()
  ext4: Drop special handling of journalled data from ext4_quota_on()
  ext4: Drop special handling of journalled data from ext4_evict_inode()
  ext4: Fix special handling of journalled data from extent zeroing
  ext4: Drop special handling of journalled data from extent shifting operations
  ext4: Drop special handling of journalled data from ext4_sync_file()
  ext4: Commit transaction before writing back pages in data=journal mode
  ...

30 files changed, 1413 insertions, 1441 deletions

diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst
index 4c559e08d11e..5740d85439ff 100644
--- a/Documentation/admin-guide/ext4.rst
+++ b/Documentation/admin-guide/ext4.rst
@@ -489,9 +489,6 @@ Files in /sys/fs/ext4/<devname>:
         multiple of this tuning parameter if the stripe size is not set in the
         ext4 superblock
 
-  mb_max_inode_prealloc
-        The maximum length of per-inode ext4_prealloc_space list.
-
   mb_max_to_scan
         The maximum number of extents the multiblock allocator will search to
         find the best extent.
diff --git a/MAINTAINERS b/MAINTAINERS
index cd69cdfc23a2..731dbf5e6ec9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7745,6 +7745,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git
 F:	Documentation/filesystems/ext4/
 F:	fs/ext4/
 F:	include/trace/events/ext4.h
+F:	include/uapi/linux/ext4.h
 
 Extended Verification Module (EVM)
 M:	Mimi Zohar <zohar@linux.ibm.com>
diff --git a/block/bio.c b/block/bio.c
index fd11614bba4d..043944fd46eb 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1159,6 +1159,7 @@ bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len,
 		return false;
 	return bio_add_page(bio, &folio->page, len, off) > 0;
 }
+EXPORT_SYMBOL(bio_add_folio);
 
 void __bio_release_pages(struct bio *bio, bool mark_dirty)
 {
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 8ff4b9192a9f..094269488183 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -80,32 +80,56 @@ static inline int ext4_block_in_group(struct super_block *sb,
 	return (actual_group == block_group) ? 1 : 0;
 }
 
-/* Return the number of clusters used for file system metadata; this
+/*
+ * Return the number of clusters used for file system metadata; this
  * represents the overhead needed by the file system.
  */
 static unsigned ext4_num_overhead_clusters(struct super_block *sb,
 					   ext4_group_t block_group,
 					   struct ext4_group_desc *gdp)
 {
-	unsigned num_clusters;
-	int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c;
+	unsigned base_clusters, num_clusters;
+	int block_cluster = -1, inode_cluster;
+	int itbl_cluster_start = -1, itbl_cluster_end = -1;
 	ext4_fsblk_t start = ext4_group_first_block_no(sb, block_group);
-	ext4_fsblk_t itbl_blk;
+	ext4_fsblk_t end = start + EXT4_BLOCKS_PER_GROUP(sb) - 1;
+	ext4_fsblk_t itbl_blk_start, itbl_blk_end;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	/* This is the number of clusters used by the superblock,
 	 * block group descriptors, and reserved block group
 	 * descriptor blocks */
-	num_clusters = ext4_num_base_meta_clusters(sb, block_group);
+	base_clusters = ext4_num_base_meta_clusters(sb, block_group);
+	num_clusters = base_clusters;
+
+	/*
+	 * Account and record inode table clusters if any cluster
+	 * is in the block group, or inode table cluster range is
+	 * [-1, -1] and won't overlap with block/inode bitmap cluster
+	 * accounted below.
+	 */
+	itbl_blk_start = ext4_inode_table(sb, gdp);
+	itbl_blk_end = itbl_blk_start + sbi->s_itb_per_group - 1;
+	if (itbl_blk_start <= end && itbl_blk_end >= start) {
+		itbl_blk_start = itbl_blk_start >= start ?
+			itbl_blk_start : start;
+		itbl_blk_end = itbl_blk_end <= end ?
+			itbl_blk_end : end;
+
+		itbl_cluster_start = EXT4_B2C(sbi, itbl_blk_start - start);
+		itbl_cluster_end = EXT4_B2C(sbi, itbl_blk_end - start);
+
+		num_clusters += itbl_cluster_end - itbl_cluster_start + 1;
+		/* check if border cluster is overlapped */
+		if (itbl_cluster_start == base_clusters - 1)
+			num_clusters--;
+	}
 
 	/*
-	 * For the allocation bitmaps and inode table, we first need
-	 * to check to see if the block is in the block group.  If it
-	 * is, then check to see if the cluster is already accounted
-	 * for in the clusters used for the base metadata cluster, or
-	 * if we can increment the base metadata cluster to include
-	 * that block.  Otherwise, we will have to track the cluster
-	 * used for the allocation bitmap or inode table explicitly.
+	 * For the allocation bitmaps, we first need to check to see
+	 * if the block is in the block group.  If it is, then check
+	 * to see if the cluster is already accounted for in the clusters
+	 * used for the base metadata cluster and inode tables cluster.
 	 * Normally all of these blocks are contiguous, so the special
 	 * case handling shouldn't be necessary except for *very*
 	 * unusual file system layouts.
@@ -113,46 +137,26 @@ static unsigned ext4_num_overhead_clusters(struct super_block *sb,
 	if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) {
 		block_cluster = EXT4_B2C(sbi,
 					 ext4_block_bitmap(sb, gdp) - start);
-		if (block_cluster < num_clusters)
-			block_cluster = -1;
-		else if (block_cluster == num_clusters) {
+		if (block_cluster >= base_clusters &&
+		    (block_cluster < itbl_cluster_start ||
+		    block_cluster > itbl_cluster_end))
 			num_clusters++;
-			block_cluster = -1;
-		}
 	}
 
 	if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) {
 		inode_cluster = EXT4_B2C(sbi,
 					 ext4_inode_bitmap(sb, gdp) - start);
-		if (inode_cluster < num_clusters)
-			inode_cluster = -1;
-		else if (inode_cluster == num_clusters) {
-			num_clusters++;
-			inode_cluster = -1;
-		}
-	}
-
-	itbl_blk = ext4_inode_table(sb, gdp);
-	for (i = 0; i < sbi->s_itb_per_group; i++) {
-		if (ext4_block_in_group(sb, itbl_blk + i, block_group)) {
-			c = EXT4_B2C(sbi, itbl_blk + i - start);
-			if ((c < num_clusters) || (c == inode_cluster) ||
-			    (c == block_cluster) || (c == itbl_cluster))
-				continue;
-			if (c == num_clusters) {
-				num_clusters++;
-				continue;
-			}
+		/*
+		 * Additional check if inode bitmap is in just accounted
+		 * block_cluster
+		 */
+		if (inode_cluster != block_cluster &&
+		    inode_cluster >= base_clusters &&
+		    (inode_cluster < itbl_cluster_start ||
+		    inode_cluster > itbl_cluster_end))
 			num_clusters++;
-			itbl_cluster = c;
-		}
 	}
 
-	if (block_cluster != -1)
-		num_clusters++;
-	if (inode_cluster != -1)
-		num_clusters++;
-
 	return num_clusters;
 }
 
@@ -187,8 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 
 	ASSERT(buffer_locked(bh));
 
-	/* If checksum is bad mark all blocks used to prevent allocation
-	 * essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
 		ext4_mark_group_bitmap_corrupted(sb, block_group,
 					EXT4_GROUP_INFO_BBITMAP_CORRUPT |
@@ -350,13 +352,13 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
 	blk = ext4_inode_table(sb, desc);
 	offset = blk - group_first_block;
 	if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
-	    EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= max_bit)
+	    EXT4_B2C(sbi, offset + sbi->s_itb_per_group - 1) >= max_bit)
 		return blk;
 	next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
-			EXT4_B2C(sbi, offset + sbi->s_itb_per_group),
+			EXT4_B2C(sbi, offset + sbi->s_itb_per_group - 1) + 1,
 			EXT4_B2C(sbi, offset));
 	if (next_zero_bit <
-	    EXT4_B2C(sbi, offset + sbi->s_itb_per_group))
+	    EXT4_B2C(sbi, offset + sbi->s_itb_per_group - 1) + 1)
 		/* bad bitmap for inode tables */
 		return blk;
 	return 0;
@@ -383,8 +385,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 	ext4_lock_group(sb, block_group);
 	if (buffer_verified(bh))
 		goto verified;
-	if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
-						    desc, bh) ||
+	if (unlikely(!ext4_block_bitmap_csum_verify(sb, desc, bh) ||
 		     ext4_simulate_fail(sb, EXT4_SIM_BBITMAP_CRC))) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
@@ -474,17 +475,19 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group,
 			goto out;
 		}
 		err = ext4_init_block_bitmap(sb, bh, block_group, desc);
-		set_bitmap_uptodate(bh);
-		set_buffer_uptodate(bh);
-		set_buffer_verified(bh);
-		ext4_unlock_group(sb, block_group);
-		unlock_buffer(bh);
 		if (err) {
+			ext4_unlock_group(sb, block_group);
+			unlock_buffer(bh);
 			ext4_error(sb, "Failed to init block bitmap for group "
 				   "%u: %d", block_group, err);
 			goto out;
 		}
-		goto verify;
+		set_bitmap_uptodate(bh);
+		set_buffer_uptodate(bh);
+		set_buffer_verified(bh);
+		ext4_unlock_group(sb, block_group);
+		unlock_buffer(bh);
+		return bh;
 	}
 	ext4_unlock_group(sb, block_group);
 	if (buffer_uptodate(bh)) {
@@ -842,10 +845,7 @@ static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb,
 	if (!ext4_bg_has_super(sb, group))
 		return 0;
 
-	if (ext4_has_feature_meta_bg(sb))
-		return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
-	else
-		return EXT4_SB(sb)->s_gdb_count;
+	return EXT4_SB(sb)->s_gdb_count;
 }
 
 /**
@@ -887,11 +887,11 @@ static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
 	    block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
 			  sbi->s_desc_per_block) {
 		if (num) {
-			num += ext4_bg_num_gdb(sb, block_group);
+			num += ext4_bg_num_gdb_nometa(sb, block_group);
 			num += le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
 		}
 	} else { /* For META_BG_BLOCK_GROUPS */
-		num += ext4_bg_num_gdb(sb, block_group);
+		num += ext4_bg_num_gdb_meta(sb, block_group);
 	}
 	return EXT4_NUM_B2C(sbi, num);
 }
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index f63e028c638c..cd725bebe69e 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -16,7 +16,7 @@ unsigned int ext4_count_free(char *bitmap, unsigned int numchars)
 	return numchars * BITS_PER_BYTE - memweight(bitmap, numchars);
 }
 
-int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
+int ext4_inode_bitmap_csum_verify(struct super_block *sb,
 				  struct ext4_group_desc *gdp,
 				  struct buffer_head *bh, int sz)
 {
@@ -38,7 +38,7 @@ int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 	return provided == calculated;
 }
 
-void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
+void ext4_inode_bitmap_csum_set(struct super_block *sb,
 				struct ext4_group_desc *gdp,
 				struct buffer_head *bh, int sz)
 {
@@ -54,7 +54,7 @@ void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
 		gdp->bg_inode_bitmap_csum_hi = cpu_to_le16(csum >> 16);
 }
 
-int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
+int ext4_block_bitmap_csum_verify(struct super_block *sb,
 				  struct ext4_group_desc *gdp,
 				  struct buffer_head *bh)
 {
@@ -74,13 +74,10 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 	} else
 		calculated &= 0xFFFF;
 
-	if (provided == calculated)
-		return 1;
-
-	return 0;
+	return provided == calculated;
 }
 
-void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
+void ext4_block_bitmap_csum_set(struct super_block *sb,
 				struct ext4_group_desc *gdp,
 				struct buffer_head *bh)
 {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 08b29c289da4..18cb2680dc39 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -40,6 +40,7 @@
 #ifdef __KERNEL__
 #include <linux/compat.h>
 #endif
+#include <uapi/linux/ext4.h>
 
 #include <linux/fscrypt.h>
 #include <linux/fsverity.h>
@@ -591,17 +592,6 @@ static inline void ext4_check_flag_values(void)
 	CHECK_FLAG_VALUE(RESERVED);
 }
 
-/* Used to pass group descriptor data when online resize is done */
-struct ext4_new_group_input {
-	__u32 group;		/* Group number for this data */
-	__u64 block_bitmap;	/* Absolute block number of block bitmap */
-	__u64 inode_bitmap;	/* Absolute block number of inode bitmap */
-	__u64 inode_table;	/* Absolute block number of inode table start */
-	__u32 blocks_count;	/* Total number of blocks in this group */
-	__u16 reserved_blocks;	/* Number of reserved blocks in this group */
-	__u16 unused;
-};
-
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 struct compat_ext4_new_group_input {
 	u32 group;
@@ -698,70 +688,6 @@ enum {
 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
 #define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER      0x0040
 
-/*
- * ioctl commands
- */
-#define	EXT4_IOC_GETVERSION		_IOR('f', 3, long)
-#define	EXT4_IOC_SETVERSION		_IOW('f', 4, long)
-#define	EXT4_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
-#define	EXT4_IOC_SETVERSION_OLD		FS_IOC_SETVERSION
-#define EXT4_IOC_GETRSVSZ		_IOR('f', 5, long)
-#define EXT4_IOC_SETRSVSZ		_IOW('f', 6, long)
-#define EXT4_IOC_GROUP_EXTEND		_IOW('f', 7, unsigned long)
-#define EXT4_IOC_GROUP_ADD		_IOW('f', 8, struct ext4_new_group_input)
-#define EXT4_IOC_MIGRATE		_IO('f', 9)
- /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
- /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
-#define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
-#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
-#define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
-#define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
-#define EXT4_IOC_PRECACHE_EXTENTS	_IO('f', 18)
-/* ioctl codes 19--39 are reserved for fscrypt */
-#define EXT4_IOC_CLEAR_ES_CACHE		_IO('f', 40)
-#define EXT4_IOC_GETSTATE		_IOW('f', 41, __u32)
-#define EXT4_IOC_GET_ES_CACHE		_IOWR('f', 42, struct fiemap)
-#define EXT4_IOC_CHECKPOINT		_IOW('f', 43, __u32)
-#define EXT4_IOC_GETFSUUID		_IOR('f', 44, struct fsuuid)
-#define EXT4_IOC_SETFSUUID		_IOW('f', 44, struct fsuuid)
-
-#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
-
-/*
- * Flags for going down operation
- */
-#define EXT4_GOING_FLAGS_DEFAULT		0x0	/* going down */
-#define EXT4_GOING_FLAGS_LOGFLUSH		0x1	/* flush log but not data */
-#define EXT4_GOING_FLAGS_NOLOGFLUSH		0x2	/* don't flush log nor data */
-
-/*
- * Flags returned by EXT4_IOC_GETSTATE
- *
- * We only expose to userspace a subset of the state flags in
- * i_state_flags
- */
-#define EXT4_STATE_FLAG_EXT_PRECACHED	0x00000001
-#define EXT4_STATE_FLAG_NEW		0x00000002
-#define EXT4_STATE_FLAG_NEWENTRY	0x00000004
-#define EXT4_STATE_FLAG_DA_ALLOC_CLOSE	0x00000008
-
-/* flags for ioctl EXT4_IOC_CHECKPOINT */
-#define EXT4_IOC_CHECKPOINT_FLAG_DISCARD	0x1
-#define EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT	0x2
-#define EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN	0x4
-#define EXT4_IOC_CHECKPOINT_FLAG_VALID		(EXT4_IOC_CHECKPOINT_FLAG_DISCARD | \
-						EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT | \
-						EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN)
-
-/*
- * Structure for EXT4_IOC_GETFSUUID/EXT4_IOC_SETFSUUID
- */
-struct fsuuid {
-	__u32       fsu_len;
-	__u32       fsu_flags;
-	__u8        fsu_uuid[];
-};
-
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
  * ioctl commands in 32 bit emulation
@@ -776,12 +702,6 @@ struct fsuuid {
 #define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
 #endif
 
-/*
- * Returned by EXT4_IOC_GET_ES_CACHE as an additional possible flag.
- * It indicates that the entry in extent status cache is for a hole.
- */
-#define EXT4_FIEMAP_EXTENT_HOLE		0x08000000
-
 /* Max physical block we can address w/o extents */
 #define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF
 
@@ -852,15 +772,6 @@ struct ext4_inode {
 	__le32	i_projid;	/* Project ID */
 };
 
-struct move_extent {
-	__u32 reserved;		/* should be zero */
-	__u32 donor_fd;		/* donor file descriptor */
-	__u64 orig_start;	/* logical start offset in block for orig */
-	__u64 donor_start;	/* logical start offset in block for donor */
-	__u64 len;		/* block length to be moved */
-	__u64 moved_len;	/* moved block length */
-};
-
 #define EXT4_EPOCH_BITS 2
 #define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
 #define EXT4_NSEC_MASK  (~0UL << EXT4_EPOCH_BITS)
@@ -1120,8 +1031,8 @@ struct ext4_inode_info {
 
 	/* mballoc */
 	atomic_t i_prealloc_active;
-	struct list_head i_prealloc_list;
-	spinlock_t i_prealloc_lock;
+	struct rb_root i_prealloc_node;
+	rwlock_t i_prealloc_lock;
 
 	/* extents status tree */
 	struct ext4_es_tree i_es_tree;
@@ -1613,7 +1524,6 @@ struct ext4_sb_info {
 	unsigned int s_mb_stats;
 	unsigned int s_mb_order2_reqs;
 	unsigned int s_mb_group_prealloc;
-	unsigned int s_mb_max_inode_prealloc;
 	unsigned int s_max_dir_size_kb;
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
@@ -1887,7 +1797,6 @@ static inline void ext4_simulate_fail_bh(struct super_block *sb,
  * Inode dynamic state flags
  */
 enum {
-	EXT4_STATE_JDATA,		/* journaled data exists */
 	EXT4_STATE_NEW,			/* inode is newly created */
 	EXT4_STATE_XATTR,		/* has in-inode xattrs */
 	EXT4_STATE_NO_EXPAND,		/* No space for expansion */
@@ -2676,16 +2585,16 @@ struct mmpd_data {
 
 /* bitmap.c */
 extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
-void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
+void ext4_inode_bitmap_csum_set(struct super_block *sb,
 				struct ext4_group_desc *gdp,
 				struct buffer_head *bh, int sz);
-int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
+int ext4_inode_bitmap_csum_verify(struct super_block *sb,
 				  struct ext4_group_desc *gdp,
 				  struct buffer_head *bh, int sz);
-void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
+void ext4_block_bitmap_csum_set(struct super_block *sb,
 				struct ext4_group_desc *gdp,
 				struct buffer_head *bh);
-int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
+int ext4_block_bitmap_csum_verify(struct super_block *sb,
 				  struct ext4_group_desc *gdp,
 				  struct buffer_head *bh);
 
@@ -3550,7 +3459,7 @@ extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
 				 unsigned int len);
 extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
 
-extern int ext4_readpage_inline(struct inode *inode, struct page *page);
+int ext4_readpage_inline(struct inode *inode, struct folio *folio);
 extern int ext4_try_to_write_inline_data(struct address_space *mapping,
 					 struct inode *inode,
 					 loff_t pos, unsigned len,
@@ -3647,7 +3556,7 @@ static inline void ext4_set_de_type(struct super_block *sb,
 
 /* readpages.c */
 extern int ext4_mpage_readpages(struct inode *inode,
-		struct readahead_control *rac, struct page *page);
+		struct readahead_control *rac, struct folio *folio);
 extern int __init ext4_init_post_read_processing(void);
 extern void ext4_exit_post_read_processing(void);
 
@@ -3757,9 +3666,8 @@ extern void ext4_io_submit_init(struct ext4_io_submit *io,
 				struct writeback_control *wbc);
 extern void ext4_end_io_rsv_work(struct work_struct *work);
 extern void ext4_io_submit(struct ext4_io_submit *io);
-extern int ext4_bio_write_page(struct ext4_io_submit *io,
-			       struct page *page,
-			       int len);
+int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *page,
+		size_t len);
 extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end);
 extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end);
 
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 3559ea6b0781..e79c767cc5e0 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4526,13 +4526,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 	trace_ext4_zero_range(inode, offset, len, mode);
 
-	/* Call ext4_force_commit to flush all data in case of data=journal. */
-	if (ext4_should_journal_data(inode)) {
-		ret = ext4_force_commit(inode->i_sb);
-		if (ret)
-			return ret;
-	}
-
 	/*
 	 * Round up offset. This is not fallocate, we need to zero out
 	 * blocks, so convert interior block aligned part of the range to
@@ -4616,6 +4609,20 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 			filemap_invalidate_unlock(mapping);
 			goto out_mutex;
 		}
+
+		/*
+		 * For journalled data we need to write (and checkpoint) pages
+		 * before discarding page cache to avoid inconsitent data on
+		 * disk in case of crash before zeroing trans is committed.
+		 */
+		if (ext4_should_journal_data(inode)) {
+			ret = filemap_write_and_wait_range(mapping, start, end);
+			if (ret) {
+				filemap_invalidate_unlock(mapping);
+				goto out_mutex;
+			}
+		}
+
 		/* Now release the pages and zero block aligned part of pages */
 		truncate_pagecache_range(inode, start, end - 1);
 		inode->i_mtime = inode->i_ctime = current_time(inode);
@@ -5290,13 +5297,6 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
 	punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb);
 	punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb);
 
-	/* Call ext4_force_commit to flush all data in case of data=journal. */
-	if (ext4_should_journal_data(inode)) {
-		ret = ext4_force_commit(inode->i_sb);
-		if (ret)
-			return ret;
-	}
-
 	inode_lock(inode);
 	/*
 	 * There is no need to overlap collapse range with EOF, in which case
@@ -5443,13 +5443,6 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
 	offset_lblk = offset >> EXT4_BLOCK_SIZE_BITS(sb);
 	len_lblk = len >> EXT4_BLOCK_SIZE_BITS(sb);
 
-	/* Call ext4_force_commit to flush all data in case of data=journal */
-	if (ext4_should_journal_data(inode)) {
-		ret = ext4_force_commit(inode->i_sb);
-		if (ret)
-			return ret;
-	}
-
 	inode_lock(inode);
 	/* Currently just for extent based files */
 	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 027a7d7037a0..f65fdb27ce14 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -153,23 +153,12 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		goto out;
 
 	/*
-	 * data=writeback,ordered:
 	 *  The caller's filemap_fdatawrite()/wait will sync the data.
 	 *  Metadata is in the journal, we wait for proper transaction to
 	 *  commit here.
-	 *
-	 * data=journal:
-	 *  filemap_fdatawrite won't do anything (the buffers are clean).
-	 *  ext4_force_commit will write the file data into the journal and
-	 *  will wait on that.
-	 *  filemap_fdatawait() will encounter a ton of newly-dirtied pages
-	 *  (they were dirtied by commit).  But that's OK - the blocks are
-	 *  safe in-journal, which is all fsync() needs to ensure.
 	 */
 	if (!sbi->s_journal)
 		ret = ext4_fsync_nojournal(inode, datasync, &needs_barrier);
-	else if (ext4_should_journal_data(inode))
-		ret = ext4_force_commit(inode->i_sb);
 	else
 		ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
 
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 157663031f8c..787ab89c2c26 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -98,7 +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, block_group, 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);
@@ -327,7 +327,7 @@ 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, block_group, 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);
@@ -813,8 +813,7 @@ int ext4_mark_inode_used(struct super_block *sb, int ino)
 			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 			ext4_free_group_clusters_set(sb, gdp,
 				ext4_free_clusters_after_init(sb, group, gdp));
-			ext4_block_bitmap_csum_set(sb, group, gdp,
-						   block_bitmap_bh);
+			ext4_block_bitmap_csum_set(sb, gdp, block_bitmap_bh);
 			ext4_group_desc_csum_set(sb, group, gdp);
 		}
 		ext4_unlock_group(sb, group);
@@ -852,7 +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, group, 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);
 	}
@@ -1165,8 +1164,7 @@ got:
 			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 			ext4_free_group_clusters_set(sb, gdp,
 				ext4_free_clusters_after_init(sb, group, gdp));
-			ext4_block_bitmap_csum_set(sb, group, gdp,
-						   block_bitmap_bh);
+			ext4_block_bitmap_csum_set(sb, gdp, block_bitmap_bh);
 			ext4_group_desc_csum_set(sb, group, gdp);
 		}
 		ext4_unlock_group(sb, group);
@@ -1222,7 +1220,7 @@ got:
 		}
 	}
 	if (ext4_has_group_desc_csum(sb)) {
-		ext4_inode_bitmap_csum_set(sb, group, 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);
 	}
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 1602d74b5eeb..b9fb1177fff6 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -467,16 +467,16 @@ out:
 	return error;
 }
 
-static int ext4_read_inline_page(struct inode *inode, struct page *page)
+static int ext4_read_inline_folio(struct inode *inode, struct folio *folio)
 {
 	void *kaddr;
 	int ret = 0;
 	size_t len;
 	struct ext4_iloc iloc;
 
-	BUG_ON(!PageLocked(page));
+	BUG_ON(!folio_test_locked(folio));
 	BUG_ON(!ext4_has_inline_data(inode));
-	BUG_ON(page->index);
+	BUG_ON(folio->index);
 
 	if (!EXT4_I(inode)->i_inline_off) {
 		ext4_warning(inode->i_sb, "inode %lu doesn't have inline data.",
@@ -489,19 +489,20 @@ static int ext4_read_inline_page(struct inode *inode, struct page *page)