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 ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2023-04-26 17:57:41 +0200
committer: Linus Torvalds <torvalds@linux-foundation.org> 2023-04-26 17:57:41 +0200
commit: 0cfcde1fafc23068f57afa50faa3e69487b7cd30 (patch)
tree: 86f9b91f143e39becea74df7db1d3e9cd89dd3ea /fs
parent: Merge tag 'fsverity-for-linus' of git://git.kernel.org/pub/scm/fs/fsverity/linux (diff)
parent: ext4: Add a uapi header for ext4 userspace APIs (diff)
download: linux-0cfcde1fafc23068f57afa50faa3e69487b7cd30.tar.xz
linux-0cfcde1fafc23068f57afa50faa3e69487b7cd30.zip
21 files changed, 1270 insertions, 1423 deletions
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)
 		goto out;
 
 	len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode));
-	kaddr = kmap_atomic(page);
+	BUG_ON(len > PAGE_SIZE);
+	kaddr = kmap_local_folio(folio, 0);
 	ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
-	flush_dcache_page(page);
-	kunmap_atomic(kaddr);
-	zero_user_segment(page, len, PAGE_SIZE);
-	SetPageUptodate(page);
+	flush_dcache_folio(folio);
+	kunmap_local(kaddr);
+	folio_zero_segment(folio, len, folio_size(folio));
+	folio_mark_uptodate(folio);
 	brelse(iloc.bh);
 
 out:
 	return ret;
 }
 
-int ext4_readpage_inline(struct inode *inode, struct page *page)
+int ext4_readpage_inline(struct inode *inode, struct folio *folio)
 {
 	int ret = 0;
 
@@ -515,16 +516,16 @@ int ext4_readpage_inline(struct inode *inode, struct page *page)
 	 * Current inline data can only exist in the 1st page,
 	 * So for all the other pages, just set them uptodate.
 	 */
-	if (!page->index)
-		ret = ext4_read_inline_page(inode, page);
-	else if (!PageUptodate(page)) {
-		zero_user_segment(page, 0, PAGE_SIZE);
-		SetPageUptodate(page);
+	if (!folio->index)
+		ret = ext4_read_inline_folio(inode, folio);
+	else if (!folio_test_uptodate(folio)) {
+		folio_zero_segment(folio, 0, folio_size(folio));
+		folio_mark_uptodate(folio);
 	}
 
 	up_read(&EXT4_I(inode)->xattr_sem);
 
-	unlock_page(page);
+	folio_unlock(folio);
 	return ret >= 0 ? 0 : ret;
 }
 
@@ -534,8 +535,7 @@ static int ext4_convert_inline_data_to_extent(struct address_space *mapping,
 	int ret, needed_blocks, no_expand;
 	handle_t *handle = NULL;
 	int retries = 0, sem_held = 0;
-	struct page *page = NULL;
-	unsigned int flags;
+	struct folio *folio = NULL;
 	unsigned from, to;
 	struct ext4_iloc iloc;
 
@@ -564,10 +564,9 @@ retry:
 
 	/* We cannot recurse into the filesystem as the transaction is already
 	 * started */
-	flags = memalloc_nofs_save();
-	page = grab_cache_page_write_begin(mapping, 0);
-	memalloc_nofs_restore(flags);
-	if (!page) {
+	folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN | FGP_NOFS,
+			mapping_gfp_mask(mapping));
+	if (!folio) {
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -582,8 +581,8 @@ retry:
 
 	from = 0;
 	to = ext4_get_inline_size(inode);
-	if (!PageUptodate(page)) {
-		ret = ext4_read_inline_page(inode, page);
+	if (!folio_test_uptodate(folio)) {
+		ret = ext4_read_inline_folio(inode, folio);
 		if (ret < 0)
 			goto out;
 	}
@@ -593,21 +592,21 @@ retry:
 		goto out;
 
 	if (ext4_should_dioread_nolock(inode)) {
-		ret = __block_write_begin(page, from, to,
+		ret = __block_write_begin(&folio->page, from, to,
 					  ext4_get_block_unwritten);
 	} else
-		ret = __block_write_begin(page, from, to, ext4_get_block);
+		ret = __block_write_begin(&folio->page, from, to, ext4_get_block);
 
 	if (!ret && ext4_should_journal_data(inode)) {
-		ret = ext4_walk_page_buffers(handle, inode, page_buffers(page),
-					     from, to, NULL,
-					     do_journal_get_write_access);
+		ret = ext4_walk_page_buffers(handle, inode,
+					     folio_buffers(folio), from, to,
+					     NULL, do_journal_get_write_access);
 	}
 
 	if (ret) {
-		unlock_page(page);
-		put_page(page);
-		page = NULL;
+		folio_unlock(folio);
+		folio_put(folio);
+		folio = NULL;
 		ext4_orphan_add(handle, inode);
 		ext4_write_unlock_xattr(inode, &no_expand);
 		sem_held = 0;
@@ -627,12 +626,12 @@ retry:
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
 
-	if (page)
-		block_commit_write(page, from, to);
+	if (folio)
+		block_commit_write(&folio->page, from, to);
 out:
-	if (page) {
-		unlock_page(page);
-		put_page(page);
+	if (folio) {
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 	if (sem_held)
 		ext4_write_unlock_xattr(inode, &no_expand);
@@ -655,8 +654,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 {
 	int ret;
 	handle_t *handle;
-	unsigned int flags;
-	struct page *page;
+	struct folio *folio;
 	struct ext4_iloc iloc;
 
 	if (pos + len > ext4_get_max_inline_size(inode))
@@ -693,28 +691,27 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 	if (ret)
 		goto out;
 
-	flags = memalloc_nofs_save();
-	page = grab_cache_page_write_begin(mapping, 0);
-	memalloc_nofs_restore(flags);
-	if (!page) {
+	folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN | FGP_NOFS,
+					mapping_gfp_mask(mapping));
+	if (!folio) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	*pagep = page;
+	*pagep = &folio->page;
 	down_read(&EXT4_I(inode)->xattr_sem);
 	if (!ext4_has_inline_data(inode)) {
 		ret = 0;
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		goto out_up_read;
 	}
 
-	if (!PageUptodate(page)) {
-		ret = ext4_read_inline_page(inode, page);
+	if (!folio_test_uptodate(folio)) {
+		ret = ext4_read_inline_folio(inode, folio);
 		if (ret < 0) {
-			unlock_page(page);
-			put_page(page);
+			folio_unlock(folio);
+			folio_put(folio);
 			goto out_up_read;
 		}
 	}
@@ -735,20 +732,21 @@ convert:
 int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 			       unsigned copied, struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	handle_t *handle = ext4_journal_current_handle();
 	int no_expand;
 	void *kaddr;
 	struct ext4_iloc iloc;
 	int ret = 0, ret2;
 
-	if (unlikely(copied < len) && !PageUptodate(page))
+	if (unlikely(copied < len) && !folio_test_uptodate(folio))
 		copied = 0;
 
 	if (likely(copied)) {
 		ret = ext4_get_inode_loc(inode, &iloc);
 		if (ret) {
-			unlock_page(page);
-			put_page(page);
+			folio_unlock(folio);
+			folio_put(folio);
 			ext4_std_error(inode->i_sb, ret);
 			goto out;
 		}
@@ -762,30 +760,30 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 		 */
 		(void) ext4_find_inline_data_nolock(inode);
 
-		kaddr = kmap_atomic(page);
+		kaddr = kmap_local_folio(folio, 0);
 		ext4_write_inline_data(inode, &iloc, kaddr, pos, copied);
-		kunmap_atomic(kaddr);
-		SetPageUptodate(page);
-		/* clear page dirty so that writepages wouldn't work for us. */
-		ClearPageDirty(page);
+		kunmap_local(kaddr);
+		folio_mark_uptodate(folio);
+		/* clear dirty flag so that writepages wouldn't work for us. */
+		folio_clear_dirty(folio);
 
 		ext4_write_unlock_xattr(inode, &no_expand);
 		brelse(iloc.bh);
 
 		/*
-		 * It's important to update i_size while still holding page
+		 * It's important to update i_size while still holding folio
 		 * lock: page writeout could otherwise come in and zero
 		 * beyond i_size.
 		 */
 		ext4_update_inode_size(inode, pos + copied);
 	}
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	/*
-	 * Don't mark the inode dirty under page lock. First, it unnecessarily
-	 * makes the holding time of page lock longer. Second, it forces lock
-	 * ordering of page lock and transaction start for journaling
+	 * Don't mark the inode dirty under folio lock. First, it unnecessarily
+	 * makes the holding time of folio lock longer. Second, it forces lock
+	 * ordering of folio lock and transaction start for journaling
 	 * filesystems.
 	 */
 	if (likely(copied))
@@ -852,10 +850,11 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
 						 void **fsdata)
 {
 	int ret = 0, inline_size;
-	struct page *page;
+	struct folio *folio;
 
-	page = grab_cache_page_write_begin(mapping, 0);
-	if (!page)
+	folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN,
+					mapping_gfp_mask(mapping));
+	if (!folio)
 		return -ENOMEM;
 
 	down_read(&EXT4_I(inode)->xattr_sem);
@@ -866,32 +865,32 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
 
 	inline_size = ext4_get_inline_size(inode);
 
-	if (!PageUptodate(page)) {
-		ret = ext4_read_inline_page(inode, page);
+	if (!folio_test_uptodate(folio)) {
+		ret = ext4_read_inline_folio(inode, folio);
 		if (ret < 0)
 			goto out;
 	}
 
-	ret = __block_write_begin(page, 0, inline_size,
+	ret = __block_write_begin(&folio->page, 0, inline_size,
 				  ext4_da_get_block_prep);
 	if (ret) {
 		up_read(&EXT4_I(inode)->xattr_sem);
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		ext4_truncate_failed_write(inode);
 		return ret;
 	}
 
-	SetPageDirty(page);
-	SetPageUptodate(page);
+	folio_mark_dirty(folio);
+	folio_mark_uptodate(folio);
 	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
 	*fsdata = (void *)CONVERT_INLINE_DATA;
 
 out:
 	up_read(&EXT4_I(inode)->xattr_sem);
-	if (page) {
-		unlock_page(page);
-		put_page(page);
+	if (folio) {
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 	return ret;
 }
@@ -912,10 +911,9 @@ int ext4_da_write_inline_data_begin(struct address_space *mapping,
 {
 	int ret;
 	handle_t *handle;
-	struct page *page;
+	struct folio *folio;
 	struct ext4_iloc iloc;
 	int retries = 0;
-	unsigned int flags;
 
 	ret = ext4_get_inode_loc(inode, &iloc);
 	if (ret)
@@ -947,10 +945,9 @@ retry_journal:
 	 * We cannot recurse into the filesystem as the transaction
 	 * is already started.
 	 */
-	flags = memalloc_nofs_save();
-	page = grab_cache_page_write_begin(mapping, 0);
-	memalloc_nofs_restore(flags);
-	if (!page) {
+	folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN | FGP_NOFS,
+					mapping_gfp_mask(mapping));
+	if (!folio) {
 		ret = -ENOMEM;
 		goto out_journal;
 	}
@@ -961,8 +958,8 @@ retry_journal:
 		goto out_release_page;
 	}
 
-	if (!PageUptodate(page)) {
-		ret = ext4_read_inline_page(inode, page);
+	if (!folio_test_uptodate(folio)) {
+		ret = ext4_read_inline_folio(inode, folio);
 		if (ret < 0)
 			goto out_release_page;
 	}
@@ -972,13 +969,13 @@ retry_journal:
 		goto out_release_page;
 
 	up_read(&EXT4_I(inode)->xattr_sem);
-	*pagep = page;
+	*pagep = &folio->page;
 	brelse(iloc.bh);
 	return 1;
 out_release_page:
 	up_read(&EXT4_I(inode)->xattr_sem);
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 out_journal:
 	ext4_journal_stop(handle);
 out:
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index bf0b7dea4900..8dbd352e3986 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -136,7 +136,6 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode,
 						   new_size);
 }
 
-static int __ext4_journalled_writepage(struct page *page, unsigned int len);
 static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
 				  int pextents);
 
@@ -180,33 +179,6 @@ void ext4_evict_inode(struct inode *inode)
 	if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
 		ext4_evict_ea_inode(inode);
 	if (inode->i_nlink) {
-		/*
-		 * When journalling data dirty buffers are tracked only in the
-		 * journal. So although mm thinks everything is clean and
-		 * ready for reaping the inode might still have some pages to
-		 * write in the running transaction or waiting to be
-		 * checkpointed. Thus calling jbd2_journal_invalidate_folio()
-		 * (via truncate_inode_pages()) to discard these buffers can
-		 * cause data loss. Also even if we did not discard these
-		 * buffers, we would have no way to find them after the inode
-		 * is reaped and thus user could see stale data if he tries to
-		 * read them before the transaction is checkpointed. So be
-		 * careful and force everything to disk here... We use
-		 * ei->i_datasync_tid to store the newest transaction
-		 * containing inode's data.
-		 *
-		 * Note that directories do not have this problem because they
-		 * don't use page cache.
-		 */
-		if (inode->i_ino != EXT4_JOURNAL_INO &&
-		    ext4_should_journal_data(inode) &&
-		    S_ISREG(inode->i_mode) && inode->i_data.nrpages) {
-			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
-			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
-
-			jbd2_complete_transaction(journal, commit_tid);
-			filemap_write_and_wait(&inode->i_data);
-		}
 		truncate_inode_pages_final(&inode->i_data);
 
 		goto no_delete;
@@ -1005,29 +977,17 @@ int ext4_walk_page_buffers(handle_t *handle, struct inode *inode,
 }
 
 /*
- * To preserve ordering, it is essential that the hole instantiation and
- * the data write be encapsulated in a single transaction.  We cannot
- * close off a transaction and start a new one between the ext4_get_block()
- * and the commit_write().  So doing the jbd2_journal_start at the start of
- * prepare_write() is the right place.
- *
- * Also, this function can nest inside ext4_writepage().  In that case, we
- * *know* that ext4_writepage() has generated enough buffer credits to do the
- * whole page.  So we won't block on the journal in that case, which is good,
- * because the caller may be PF_MEMALLOC.
- *
- * By accident, ext4 can be reentered when a transaction is open via
- * quota file writes.  If we were to commit the transaction while thus
- * reentered, there can be a deadlock - we would be holding a quota
- * lock, and the commit would never complete if another thread had a
- * transaction open and was blocking on the quota lock - a ranking
- * violation.
- *
- * So what we do is to rely on the fact that jbd2_journal_stop/journal_start
- * will _not_ run commit under these circumstances because handle->h_ref
- * is elevated.  We'll still have enough credits for the tiny quotafile
- * write.
+ * Helper for handling dirtying of journalled data. We also mark the folio as
+ * dirty so that writeback code knows about this page (and inode) contains
+ * dirty data. ext4_writepages() then commits appropriate transaction to
+ * make data stable.
  */
+static int ext4_dirty_journalled_data(handle_t *handle, struct buffer_head *bh)
+{
+	folio_mark_dirty(bh->b_folio);
+	return ext4_handle_dirty_metadata(handle, NULL, bh);
+}
+
 int do_journal_get_write_access(handle_t *handle, struct inode *inode,
 				struct buffer_head *bh)
 {
@@ -1050,17 +1010,17 @@ int do_journal_get_write_access(handle_t *handle, struct inode *inode,
 	ret = ext4_journal_get_write_access(handle, inode->i_sb, bh,
 					    EXT4_JTR_NONE);
 	if (!ret && dirty)
-		ret = ext4_handle_dirty_metadata(handle, NULL, bh);
+		ret = ext4_dirty_journalled_data(handle, bh);
 	return ret;
 }
 
 #ifdef CONFIG_FS_ENCRYPTION
-static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
+static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 				  get_block_t *get_block)
 {
 	unsigned from = pos & (PAGE_SIZE - 1);
 	unsigned to = from + len;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	unsigned block_start, block_end;
 	sector_t block;
 	int err = 0;
@@ -1070,22 +1030,24 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 	int nr_wait = 0;
 	int i;
 
-	BUG_ON(!PageLocked(page));
+	BUG_ON(!folio_test_locked(folio));
 	BUG_ON(from > PAGE_SIZE);
 	BUG_ON(to > PAGE_SIZE);
 	BUG_ON(from > to);
 
-	if (!page_has_buffers(page))
-		create_empty_buffers(page, blocksize, 0);
-	head = page_buffers(page);
+	head = folio_buffers(folio);
+	if (!head) {
+		create_empty_buffers(&folio->page, blocksize, 0);
+		head = folio_buffers(folio);
+	}
 	bbits = ilog2(blocksize);
-	block = (sector_t)page->index << (PAGE_SHIFT - bbits);
+	block = (sector_t)folio->index << (PAGE_SHIFT - bbits);
 
 	for (bh = head, block_start = 0; bh != head || !block_start;
 	    block++, block_start = block_end, bh = bh->b_this_page) {
 		block_end = block_start + blocksize;
 		if (block_end <= from || block_start >= to) {
-			if (PageUptodate(page)) {
+			if (folio_test_uptodate(folio)) {
 				set_buffer_uptodate(bh);
 			}
 			continue;
@@ -1098,19 +1060,20 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 			if (err)
 				break;
 			if (buffer_new(bh)) {
-				if (PageUptodate(page)) {
+				if (folio_test_uptodate(folio)) {
 					clear_buffer_new(bh);
 					set_buffer_uptodate(bh);
 					mark_buffer_dirty(bh);
 					continue;
 				}
 				if (block_end > to || block_start < from)
-					zero_user_segments(page, to, block_end,
-							   block_start, from);
+					folio_zero_segments(folio, to,
+							    block_end,
+							    block_start, from);
 				continue;
 			}
 		}
-		if (PageUptodate(page)) {
+		if (folio_test_uptodate(folio)) {
 			set_buffer_uptodate(bh);
 			continue;
 		}
@@ -1130,14 +1093,13 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 			err = -EIO;
 	}
 	if (unlikely(err)) {
-		page_zero_new_buffers(page, from, to);
+		page_zero_new_buffers(&folio->page, from, to);
 	} else if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
 		for (i = 0; i < nr_wait; i++) {
 			int err2;
 
-			err2 = fscrypt_decrypt_pagecache_blocks(page_folio(page),
-								blocksize,
-								bh_offset(wait[i]));
+			err2 = fscrypt_decrypt_pagecache_blocks(folio,
+						blocksize, bh_offset(wait[i]));
 			if (err2) {
 				clear_buffer_uptodate(wait[i]);
 				err = err2;
@@ -1149,6 +1111,13 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 }
 #endif
 
+/*
+ * To preserve ordering, it is essential that the hole instantiation and
+ * the data write be encapsulated in a single transaction.  We cannot
+ * close off a transaction and start a new one between the ext4_get_block()
+ * and the ext4_write_end().  So doing the jbd2_journal_start at the start of
+ * ext4_write_begin() is the right place.
+ */
 static int ext4_write_begin(struct file *file, struct address_space *mapping,
 			    loff_t pos, unsigned len,
 			    struct page **pagep, void **fsdata)
@@ -1157,7 +1126,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	int ret, needed_blocks;
 	handle_t *handle;
 	int retries = 0;
-	struct page *page;
+	struct folio *folio;
 	pgoff_t index;
 	unsigned from, to;
 
@@ -1184,68 +1153,68 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	}
 
 	/*
-	 * grab_cache_page_write_begin() can take a long time if the
-	 * system is thrashing due to memory pressure, or if the page
+	 * __filemap_get_folio() can take a long time if the
+	 * system is thrashing due to memory pressure, or if the folio
 	 * is being written back.  So grab it first before we start
 	 * the transaction handle.  This also allows us to allocate
-	 * the page (if needed) without using GFP_NOFS.
+	 * the folio (if needed) without using GFP_NOFS.
 	 */
 retry_grab:
-	page = grab_cache_page_write_begin(mapping, index);
-	if (!page)
+	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+					mapping_gfp_mask(mapping));
+	if (!folio)
 		return -ENOMEM;
 	/*
 	 * The same as page allocation, we prealloc buffer heads before
 	 * starting the handle.
 	 */
-	if (!page_has_buffers(page))
-		create_empty_buffers(page, inode->i_sb->s_blocksize, 0);
+	if (!folio_buffers(folio))
+		create_empty_buffers(&folio->page, inode->i_sb->s_blocksize, 0);
 
-	unlock_page(page);
+	folio_unlock(folio);
 
 retry_journal:
 	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
 	if (IS_ERR(handle)) {
-		put_page(page);
+		folio_put(folio);
 		return PTR_ERR(handle);
 	}
 
-	lock_page(page);
-	if (page->mapping != mapping) {
-		/* The page got truncated from under us */
-		unlock_page(page);
-		put_page(page);
+	folio_lock(folio);
+	if (folio->mapping != mapping) {
+		/* The folio got truncated from under us */
+		folio_unlock(folio);
+		folio_put(folio);
 		ext4_journal_stop(handle);
 		goto retry_grab;
 	}
-	/* In case writeback began while the page was unlocked */
-	wait_for_stable_page(page);
+	/* 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(page, pos, len,
+		ret = ext4_block_write_begin(folio, pos, len,
 					     ext4_get_block_unwritten);
 	else
-		ret = ext4_block_write_begin(page, pos, len,
-					     ext4_get_block);
+		ret = ext4_block_write_begin(folio, pos, len, ext4_get_block);
 #else
 	if (ext4_should_dioread_nolock(inode))
-		ret = __block_write_begin(page, pos, len,
+		ret = __block_write_begin(&folio->page, pos, len,
 					  ext4_get_block_unwritten);
 	else
-		ret = __block_write_begin(page, pos, len, ext4_get_block);
+		ret = __block_write_begin(&folio->page, pos, len, ext4_get_block);
 #endif
 	if (!ret && ext4_should_journal_data(inode)) {
 		ret = ext4_walk_page_buffers(handle, inode,
-					     page_buffers(page), from, to, NULL,
-					     do_journal_get_write_access);
+					     folio_buffers(folio), from, to,
+					     NULL, do_journal_get_write_access);
 	}
 
 	if (ret) {
 		bool extended = (pos + len > inode->i_size) &&
 				!ext4_verity_in_progress(inode);
 
-		unlock_page(page);
+		folio_unlock(folio);
 		/*
 		 * __block_write_begin may have instantiated a few blocks
 		 * outside i_size.  Trim these off again. Don't need
@@ -1273,10 +1242,10 @@ retry_journal:
 		if (ret == -ENOSPC &&
 		    ext4_should_retry_alloc(inode->i_sb, &retries))
 			goto retry_journal;
-		put_page(page);
+		folio_put(folio);
 		return ret;
 	}
-	*pagep = page;
+	*pagep = &folio->page;
 	return ret;
 }
 
@@ -1288,7 +1257,7 @@ static int write_end_fn(handle_t *handle, struct inode *inode,
 	if (!buffer_mapped(bh) || buffer_freed(bh))
 		return 0;
 	set_buffer_uptodate(bh);
-	ret = ext4_handle_dirty_metadata(handle, NULL, bh);
+	ret = ext4_dirty_journalled_data(handle, bh);
 	clear_buffer_meta(bh);
 	clear_buffer_prio(bh);
 	return ret;
@@ -1306,6 +1275,7 @@ static int ext4_write_end(struct file *file,
 			  loff_t pos, unsigned len, unsigned copied,
 			  struct page *page, void *fsdata)
 {
+	struct folio *folio = page_folio(page);
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
 	loff_t old_size = inode->i_size;
@@ -1321,7 +1291,7 @@ static int ext4_write_end(struct file *file,
 
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
 	/*
-	 * it's important to update i_size while still holding page lock:
+	 * it's important to update i_size while still holding folio lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
 	 *
 	 * If FS_IOC_ENABLE_VERITY is running on this inode, then Merkle tree
@@ -1329,15 +1299,15 @@ static int ext4_write_end(struct file *file,
 	 */
 	if (!verity)
 		i_size_changed = ext4_update_inode_size(inode, pos + copied);
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	if (old_size < pos && !verity)
 		pagecache_isize_extended(inode, old_size, pos);
 	/*
-	 * Don't mark the inode dirty under page lock. First, it unnecessarily
-	 * makes the holding time of page lock longer. Second, it forces lock
-	 * ordering of page lock and transaction start for journaling
+	 * Don't mark the inode dirty under folio lock. First, it unnecessarily
+	 * makes the holding time of folio lock longer. Second, it forces lock
+	 * ordering of folio lock and transaction start for journaling
 	 * filesystems.
 	 */
 	if (i_size_changed)
@@ -1371,28 +1341,28 @@ static int ext4_write_end(struct file *file,
 /*
  * This is a private version of page_zero_new_buffers() which doesn't
  * set the buffer to be dirty, since in data=journalled mode we need
- * to call ext4_handle_dirty_metadata() instead.
+ * to call ext4_dirty_journalled_data() instead.
  */
 static void ext4_journalled_zero_new_buffers(handle_t *handle,
 					    struct inode *inode,
-					    struct page *page,
+					    struct folio *folio,
 					    unsigned from, unsigned to)
 {
 	unsigned int block_start = 0, block_end;
 	struct buffer_head *head, *bh;
 
-	bh = head = page_buffers(page);
+	bh = head = folio_buffers(folio);
 	do {
 		block_end = block_start + bh->b_size;
 		if (buffer_new(bh)) {
 			if (block_end > from && block_start < to) {
-				if (!PageUptodate(page)) {
+				if (!folio_test_uptodate(folio)) {
 					unsigned start, size;
 
 					start = max(from, block_start);
 					size = min(to, block_end) - start;
 
-					zero_user(page, start, size);
+					folio_zero_range(folio, start, size);
 					write_end_fn(handle, inode, bh);
 				}
 				clear_buffer_new(bh);
@@ -1408,6 +1378,7 @@ static int ext4_journalled_write_end(struct file *file,
 				     loff_t pos, unsigned len, unsigned copied,
 				     struct page *page, void *fsdata)
 {
+	struct folio *folio = page_folio(page);
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
 	loff_t old_size = inode->i_size;
@@ -1426,25 +1397,26 @@ static int ext4_journalled_write_end(struct file *file,
 	if (ext4_has_inline_data(inode))
 		return ext4_write_inline_data_end(inode, pos, len, copied, page);
 
-	if (unlikely(copied < len) && !PageUptodate(page)) {
+	if (unlikely(copied < len) && !folio_test_uptodate(folio)) {
 		copied = 0;
-		ext4_journalled_zero_new_buffers(handle, inode, page, from, to);
+		ext4_journalled_zero_new_buffers(handle, inode, folio,
+						 from, to);
 	} else {
 		if (unlikely(copied < len))
-			ext4_journalled_zero_new_buffers(handle, inode, page,
+			ext4_journalled_zero_new_buffers(handle, inode, folio,
 							 from + copied, to);
-		ret = ext4_walk_page_buffers(handle, inode, page_buffers(page),
+		ret = ext4_walk_page_buffers(handle, inode,
+					     folio_buffers(folio),
 					     from, from + copied, &partial,
 					     write_end_fn);
 		if (!partial)
-			SetPageUptodate(page);
+			folio_mark_uptodate(folio);
 	}
 	if (!verity)
 		size_changed = ext4_update_inode_size(inode, pos + copied);
-	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 	EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	if (old_size < pos && !verity)
 		pagecache_isize_extended(inode, old_size, pos);
@@ -1568,6 +1540,7 @@ struct mpage_da_data {
 	struct ext4_io_submit io_submit;	/* IO submission data */
 	unsigned int do_map:1;
 	unsigned int scanned_until_end:1;
+	unsigned int journalled_more_data:1;
 };
 
 static void mpage_release_unused_pages(struct mpage_da_data *mpd,
@@ -1649,12 +1622,6 @@ static void ext4_print_free_blocks(struct inode *inode)
 	return;
 }
 
-static int ext4_bh_delay_or_unwritten(handle_t *handle, struct inode *inode,
-				      struct buffer_head *bh)
-{
-	return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh);
-}
-
 /*
  * ext4_insert_delayed_block - adds a delayed block to the extents status
  *                             tree, incrementing the reserved cluster/block
@@ -1887,249 +1854,41 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 	return 0;
 }
 
-static int __ext4_journalled_writepage(struct page *page,
-				       unsigned int len)
+static void mpage_folio_done(struct mpage_da_data *mpd, struct folio *folio)
 {
-	struct address_space *mapping = page->mapping;
-	struct inode *inode = mapping->host;
-	handle_t *handle = NULL;
-	int ret = 0, err = 0;
-	int inline_data = ext4_has_inline_data(inode);
-	struct buffer_head *inode_bh = NULL;
-	loff_t size;
-
-	ClearPageChecked(page);
-
-	if (inline_data) {
-		BUG_ON(page->index != 0);
-		BUG_ON(len > ext4_get_max_inline_size(inode));
-		inode_bh = ext4_journalled_write_inline_data(inode, len, page);
-		if (inode_bh == NULL)
-			goto out;
-	}
-	/*
-	 * We need to release the page lock before we start the
-	 * journal, so grab a reference so the page won't disappear
-	 * out from under us.
-	 */
-	get_page(page);
-	unlock_page(page);
-
-	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
-				    ext4_writepage_trans_blocks(inode));
-	if (IS_ERR(handle)) {
-		ret = PTR_ERR(handle);
-		put_page(page);
-		goto out_no_pagelock;
-	}
-	BUG_ON(!ext4_handle_valid(handle));
-
-	lock_page(page);
-	put_page(page);
-	size = i_size_read(inode);
-	if (page->mapping != mapping || page_offset(page) > size) {
-		/* The page got truncated from under us */
-		ext4_journal_stop(handle);
-		ret = 0;
-		goto out;
-	}
-
-	if (inline_data) {
-		ret = ext4_mark_inode_dirty(handle, inode);
-	} else {
-		struct buffer_head *page_bufs = page_buffers(page);
-
-		if (page->index == size >> PAGE_SHIFT)
-			len = size & ~PAGE_MASK;
-		else
-			len = PAGE_SIZE;
-
-		ret = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len,
-					     NULL, do_journal_get_write_access);
-
-		err = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len,
-					     NULL, write_end_fn);
-	}
-	if (ret == 0)
-		ret = err;
-	err = ext4_jbd2_inode_add_write(handle, inode, page_offset(page), len);
-	if (ret == 0)
-		ret = err;
-	EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
-	err = ext4_journal_stop(handle);
-	if (!ret)
-		ret = err;
-
-	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
-out:
-	unlock_page(page);
-out_no_pagelock:
-	brelse(inode_bh);
-	return ret;
+	mpd->first_page += folio_nr_pages(folio);
+	folio_unlock(folio);
 }
 
-/*
- * Note that we don't need to start a transaction unless we're journaling data
- * because we should have holes filled from ext4_page_mkwrite(). We even don't
- * need to file the inode to the transaction's list in ordered mode because if
- * we are writing back data added by write(), the inode is already there and if
- * we are writing back data modified via mmap(), no one guarantees in which
- * transaction the data will hit the disk. In case we are journaling data, we
- * cannot start transaction directly because transaction start ranks above page
- * lock so we have to do some magic.
- *
- * This function can get called via...
- *   - ext4_writepages after taking page lock (have journal handle)
- *   - journal_submit_inode_data_buffers (no journal handle)
- *   - shrink_page_list via the kswapd/direct reclaim (no journal handle)
- *   - grab_page_cache when doing write_begin (have journal handle)
- *
- * We don't do any block allocation in this function. If we have page with
- * multiple blocks we need to write those buffer_heads that are mapped. This
- * is important for mmaped based write. So if we do with blocksize 1K
- * truncate(f, 1024);
- * a = mmap(f, 0, 4096);
- * a[0] = 'a';
- * truncate(f, 4096);
- * we have in the page first buffer_head mapped via page_mkwrite call back
- * but other buffer_heads would be unmapped but dirty (dirty done via the
- * do_wp_page). So writepage should write the first block. If we modify
- * the mmap area beyond 1024 we will again get a page_fault and the
- * page_mkwrite callback will do the block allocation and mark the
- * buffer_heads mapped.
- *
- * We redirty the page if we have any buffer_heads that is either delay or
- * unwritten in the page.
- *
- * We can get recursively called as show below.
- *
- *	ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
- *		ext4_writepage()
- *
- * But since we don't do any block allocation we should not deadlock.
- * Page also have the dirty flag cleared so we don't get recurive page_lock.
- */
-static int ext4_writepage(struct page *page,
-			  struct writeback_control *wbc)
+static int mpage_submit_folio(struct mpage_da_data *mpd, struct folio *folio)
 {
-	struct folio *folio = page_folio(page);
-	int ret = 0;
-	loff_t size;
-	unsigned int len;
-	struct buffer_head *page_bufs = NULL;
-	struct inode *inode = page->mapping->host;
-	struct ext4_io_submit io_submit;
-
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
-		folio_invalidate(folio, 0, folio_size(folio));
-		folio_unlock(folio);
-		return -EIO;
-	}
-
-	trace_ext4_writepage(page);
-	size = i_size_read(inode);
-	if (page->index == size >> PAGE_SHIFT &&
-	    !ext4_verity_in_progress(inode))
-		len = size & ~PAGE_MASK;
-	else
-		len = PAGE_SIZE;
-
-	/* Should never happen but for bugs in other kernel subsystems */
-	if (!page_has_buffers(page)) {
-		ext4_warning_inode(inode,
-		   "page %lu does not have buffers attached", page->index);
-		ClearPageDirty(page);
-		unlock_page(page);
-		return 0;
-	}
-
-	page_bufs = page_buffers(page);
-	/*
-	 * We cannot do block allocation or other extent handling in this
-	 * function. If there are buffers needing that, we have to redirty
-	 * the page. But we may reach here when we do a journal commit via
-	 * journal_submit_inode_data_buffers() and in that case we must write
-	 * allocated buffers to achieve data=ordered mode guarantees.
-	 *
-	 * Also, if there is only one buffer per page (the fs block
-	 * size == the page size), if one buffer needs block
-	 * allocation or needs to modify the extent tree to clear the
-	 * unwritten flag, we know that the page can't be written at
-	 * all, so we might as well refuse the write immediately.
-	 * Unfortunately if the block size != page size, we can't as
-	 * easily detect this case using ext4_walk_page_buffers(), but
-	 * for the extremely common case, this is an optimization that
-	 * skips a useless round trip through ext4_bio_write_page().
-	 */
-	if (ext4_walk_page_buffers(NULL, inode, page_bufs, 0, len, NULL,
-				   ext4_bh_delay_or_unwritten)) {
-		redirty_page_for_writepage(wbc, page);
-		if ((current->flags & PF_MEMALLOC) ||
-		    (inode->i_sb->s_blocksize == PAGE_SIZE)) {
-			/*
-			 * For memory cleaning there's no point in writing only
-			 * some buffers. So just bail out. Warn if we came here
-			 * from direct reclaim.
-			 */
-			WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD))
-							== PF_MEMALLOC);
-			unlock_page(page);
-			return 0;
-		}
-	}
-
-	if (PageChecked(page) && ext4_should_journal_data(inode))
-		/*
-		 * It's mmapped pagecache.  Add buffers and journal it.  There
-		 * doesn't seem much point in redirtying the page here.
-		 */
-		return __ext4_journalled_writepage(page, len);
-
-	ext4_io_submit_init(&io_submit, wbc);
-	io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
-	if (!io_submit.io_end) {
-		redirty_page_for_writepage(wbc, page);
-		unlock_page(page);
-		return -ENOMEM;
-	}
-	ret = ext4_bio_write_page(&io_submit, page, len);
-	ext4_io_submit(&io_submit);
-	/* Drop io_end reference we got from init */
-	ext4_put_io_end_defer(io_submit.io_end);
-	return ret;
-}
-
-static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
-{
-	int len;
+	size_t len;
 	loff_t size;
 	int err;
 
-	BUG_ON(page->index != mpd->first_page);
-	clear_page_dirty_for_io(page);
+	BUG_ON(folio->index != mpd->first_page);
+	folio_clear_dirty_for_io(folio);
 	/*
 	 * We have to be very careful here!  Nothing protects writeback path
 	 * against i_size changes and the page can be writeably mapped into
 	 * page tables. So an application can be growing i_size and writing
-	 * data through mmap while writeback runs. clear_page_dirty_for_io()
+	 * data through mmap while writeback runs. folio_clear_dirty_for_io()
 	 * write-protects our page in page tables and the page cannot get
-	 * written to again until we release page lock. So only after
-	 * clear_page_dirty_for_io() we are safe to sample i_size for
-	 * ext4_bio_write_page() to zero-out tail of the written page. We rely
-	 * on the barrier provided by TestClearPageDirty in
-	 * clear_page_dirty_for_io() to make sure i_size is really sampled only
+	 * written to again until we release folio lock. So only after
+	 * folio_clear_dirty_for_io() we are safe to sample i_size for
+	 * ext4_bio_write_folio() to zero-out tail of the written page. We rely
+	 * on the barrier provided by folio_test_clear_dirty() in
+	 * folio_clear_dirty_for_io() to make sure i_size is really sampled only
 	 * after page tables are updated.
 	 */
 	size = i_size_read(mpd->inode);
-	if (page->index == size >> PAGE_SHIFT &&
+	len = folio_size(folio);
+	if (folio_pos(folio) + len > size &&
 	    !ext4_verity_in_progress(mpd->inode))
 		len = size & ~PAGE_MASK;
-	else
-		len = PAGE_SIZE;
-	err = ext4_bio_write_page(&mpd->io_submit, page, len);
+	err = ext4_bio_write_folio(&mpd->io_submit, folio, len);
 	if (!err)
 		mpd->wbc->nr_to_write--;
-	mpd->first_page++;
 
 	return err;
 }
@@ -2240,9 +1999,10 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 	} while (lblk++, (bh = bh->b_this_page) != head);
 	/* So far everything mapped? Submit the page for IO. */
 	if (mpd->map.m_len == 0) {
-		err = mpage_submit_page(mpd, head->b_page);
+		err = mpage_submit_folio(mpd, head->b_folio);
 		if (err < 0)
 			return err;
+		mpage_folio_done(mpd, head->b_folio);
 	}
 	if (lblk >= blocks) {
 		mpd->scanned_until_end = 1;
@@ -2252,21 +2012,22 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 }
 
 /*
- * mpage_process_page - update page buffers corresponding to changed extent and
- *		       may submit fully mapped page for IO
- *
- * @mpd		- description of extent to map, on return next extent to map
- * @m_lblk	- logical block mapping.
- * @m_pblk	- corresponding physical mapping.
- * @map_bh	- determines on return whether this page requires any further
+ * mpage_process_folio - update folio buffers corresponding to changed extent
+ *			 and may submit fully mapped page for IO
+ * @mpd: description of extent to map, on return next extent to map
+ * @folio: Contains these buffers.
+ * @m_lblk: logical block mapping.
+ * @m_pblk: corresponding physical mapping.
+ * @map_bh: determines on return whether this page requires any further
  *		  mapping or not.
- * Scan given page buffers corresponding to changed extent and update buffer
+ *
+ * Scan given folio buffers corresponding to changed extent and update buffer
  * state according to new extent state.
  * We map delalloc buffers to their physical location, clear unwritten bits.
- * If the given page is not fully mapped, we update @map to the next extent in
- * the given page that needs mapping & return @map_bh as true.
+ * If the given folio is not fully mapped, we update @mpd to the next extent in
+ * the given folio that needs mapping & return @map_bh as true.
  */
-static int mpage_process_page(struct mpage_da_data *mpd, struct page *page,
+static int mpage_process_folio(struct mpage_da_data *mpd, struct folio *folio,
 			      ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk,
 			      bool *map_bh)
 {
@@ -2279,14 +2040,14 @@ static int mpage_process_page(struct mpage_da_data *mpd, struct page *page,
 	ssize_t io_end_size = 0;
 	struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end);
 
-	bh = head = page_buffers(page);
+	bh = head = folio_buffers(folio);
 	do {
 		if (lblk < mpd->map.m_lblk)
 			continue;
 		if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
 			/*
 			 * Buffer after end of mapped extent.
-			 * Find next buffer in the page to map.
+			 * Find next buffer in the folio to map.
 			 */
 			mpd->map.m_len = 0;
 			mpd->map.m_flags = 0;
@@ -2359,9 +2120,9 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
 		if (nr == 0)
 			break;
 		for (i = 0; i < nr; i++) {
-			struct page *page = &fbatch.folios[i]->page;
+			struct folio *folio = fbatch.folios[i];
 
-			err = mpage_process_page(mpd, page, &lblk, &pblock,
+			err = mpage_process_folio(mpd, folio, &lblk, &pblock,
 						 &map_bh);
 			/*
 			 * If map_bh is true, means page may require further bh
@@ -2371,9 +2132,10 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
 			if (err < 0 || map_bh)
 				goto out;
 			/* Page fully mapped - let IO run! */
-			err = mpage_submit_page(mpd, page);
+			err = mpage_submit_folio(mpd, folio);
 			if (err < 0)
 				goto out;
+			mpage_folio_done(mpd, folio);
 		}
 		folio_batch_release(&fbatch);
 	}
@@ -2559,17 +2321,45 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
 				MAX_WRITEPAGES_EXTENT_LEN + bpp - 1, bpp);
 }
 
-/* Return true if the page needs to be written as part of transaction commit */
-static bool ext4_page_nomap_can_writeout(struct page *page)
+static int ext4_journal_page_buffers(handle_t *handle, struct page *page,
+				     int len)
 {
-	struct buffer_head *bh, *head;
+	struct buffer_head *page_bufs = page_buffers(page);
+	struct inode *inode = page->mapping->host;
+	int ret, err;
 
-	bh = head = page_buffers(page);
-	do {
-		if (buffer_dirty(bh) && buffer_mapped(bh) && !buffer_delay(bh))
-			return true;
-	} while ((bh = bh->b_this_page) != head);
-	return false;
+	ret = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len,
+				     NULL, do_journal_get_write_access);
+	err = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len,
+				     NULL, write_end_fn);
+	if (ret == 0)
+		ret = err;
+	err = ext4_jbd2_inode_add_write(handle, inode, page_offset(page), len);
+	if (ret == 0)
+		ret = err;
+	EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
+
+	return ret;
+}
+
+static int mpage_journal_page_buffers(handle_t *handle,
+				      struct mpage_da_data *mpd,
+				      struct page *page)
+{
+	struct inode *inode = mpd->inode;
+	loff_t size = i_size_read(inode);
+	int len;
+
+	ClearPageChecked(page);
+	mpd->wbc->nr_to_write--;
+
+	if (page->index == size >> PAGE_SHIFT &&
+	    !ext4_verity_in_progress(inode))
+		len = size & ~PAGE_MASK;
+	else
+		len = PAGE_SIZE;
+
+	return ext4_journal_page_buffers(handle, page, len);
 }
 
 /*
@@ -2597,7 +2387,6 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 	struct address_space *mapping = mpd->inode->i_mapping;
 	struct folio_batch fbatch;
 	unsigned int nr_folios;
-	long left = mpd->wbc->nr_to_write;
 	pgoff_t index = mpd->first_page;
 	pgoff_t end = mpd->last_page;
 	xa_mark_t tag;
@@ -2605,14 +2394,23 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 	int blkbits = mpd->inode->i_blkbits;
 	ext4_lblk_t lblk;
 	struct buffer_head *head;
+	handle_t *handle = NULL;
+	int bpp = ext4_journal_blocks_per_page(mpd->inode);
 
 	if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages)
 		tag = PAGECACHE_TAG_TOWRITE;
 	else
 		tag = PAGECACHE_TAG_DIRTY;
-	folio_batch_init(&fbatch);
+
 	mpd->map.m_len = 0;
 	mpd->next_page = index;
+	if (ext4_should_journal_data(mpd->inode)) {
+		handle = ext4_journal_start(mpd->inode, EXT4_HT_WRITE_PAGE,
+					    bpp);
+		if (IS_ERR(handle))
+			return PTR_ERR(handle);
+	}
+	folio_batch_init(&fbatch);
 	while (index <= end) {
 		nr_folios = filemap_get_folios_tag(mapping, &index, end,
 				tag, &fbatch);
@@ -2630,13 +2428,22 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 			 * newly appeared dirty pages, but have not synced all
 			 * of the old dirty pages.
 			 */
-			if (mpd->wbc->sync_mode == WB_SYNC_NONE && left <= 0)
+			if (mpd->wbc->sync_mode == WB_SYNC_NONE &&
+			    mpd->wbc->nr_to_write <=
+			    mpd->map.m_len >> (PAGE_SHIFT - blkbits))
 				goto out;
 
 			/* If we can't merge this page, we are done. */
 			if (mpd->map.m_len > 0 && mpd->next_page != folio->index)
 				goto out;
 
+			if (handle) {
+				err = ext4_journal_ensure_credits(handle, bpp,
+								  0);
+				if (err < 0)
+					goto out;
+			}
+
 			folio_lock(folio);
 			/*
 			 * If the page is no longer dirty, or its mapping no
@@ -2676,18 +2483,28 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 				mpd->first_page = folio->index;
 			mpd->next_page = folio->index + folio_nr_pages(folio);
 			/*
-			 * Writeout for transaction commit where we cannot
-			 * modify metadata is simple. Just submit the page.
+			 * Writeout when we cannot modify metadata is simple.
+			 * Just submit the page. For data=journal mode we
+			 * first handle writeout of the page for checkpoint and
+			 * only after that handle delayed page dirtying. This
+			 * makes sure current data is checkpointed to the final
+			 * location before possibly journalling it again which
+			 * is desirable when the page is frequently dirtied
+			 * through a pin.
 			 */
 			if (!mpd->can_map) {
-				if (ext4_page_nomap_can_writeout(&folio->page)) {
-					err = mpage_submit_page(mpd, &folio->page);
+				err = mpage_submit_folio(mpd, folio);
+				if (err < 0)
+					goto out;
+				/* Pending dirtying of journalled data? */
+				if (folio_test_checked(folio)) {
+					err = mpage_journal_page_buffers(handle,
+						mpd, &folio->page);
 					if (err < 0)
 						goto out;
-				} else {
-					folio_unlock(folio);
-					mpd->first_page += folio_nr_pages(folio);
+					mpd->journalled_more_data = 1;
 				}
+				mpage_folio_done(mpd, folio);
 			} else {
 				/* Add all dirty buffers to mpd */
 				lblk = ((ext4_lblk_t)folio->index) <<
@@ -2699,24 +2516,21 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 					goto out;
 				err = 0;
 			}
-			left -= folio_nr_pages(folio);
 		}
 		folio_batch_release(&fbatch);
 		cond_resched();
 	}
 	mpd->scanned_until_end = 1;
+	if (handle)
+		ext4_journal_stop(handle);
 	return 0;
 out:
 	folio_batch_release(&fbatch);
+	if (handle)
+		ext4_journal_stop(handle);
 	return err;
 }
 
-static int ext4_writepage_cb(struct folio *folio, struct writeback_control *wbc,
-			     void *data)
-{
-	return ext4_writepage(&folio->page, wbc);
-}
-
 static int ext4_do_writepages(struct mpage_da_data *mpd)
 {
 	struct writeback_control *wbc = mpd->wbc;
@@ -2742,13 +2556,6 @@ static int ext4_do_writepages(struct mpage_da_data *mpd)
 	if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		goto out_writepages;
 
-	if (ext4_should_journal_data(inode)) {
-		blk_start_plug(&plug);
-		ret = write_cache_pages(mapping, wbc, ext4_writepage_cb, NULL);
-		blk_finish_plug(&plug);
-		goto out_writepages;
-	}
-
 	/*
 	 * If the filesystem has aborted, it is read-only, so return
 	 * right away instead of dumping stack traces later on that
@@ -2783,6 +2590,26 @@ static int ext4_do_writepages(struct mpage_da_data *mpd)
 		ext4_journal_stop(handle);
 	}
 
+	/*
+	 * data=journal mode does not do delalloc so we just need to writeout /
+	 * journal already mapped buffers. On the other hand we need to commit
+	 * transaction to make data stable. We expect all the data to be
+	 * already in the journal (the only exception are DMA pinned pages
+	 * dirtied behind our back) so we commit transaction here and run the
+	 * writeback loop to checkpoint them. The checkpointing is not actually
+	 * necessary to make data persistent *but* quite a few places (extent
+	 * shifting operations, fsverity, ...) depend on being able to drop
+	 * pagecache pages after calling filemap_write_and_wait() and for that
+	 * checkpointing needs to happen.
+	 */
+	if (ext4_should_journal_data(inode)) {
+		mpd->can_map = 0;
+		if (wbc->sync_mode == WB_SYNC_ALL)
+			ext4_fc_commit(sbi->s_journal,
+				       EXT4_I(inode)->i_datasync_tid);
+	}
+	mpd->journalled_more_data = 0;
+
 	if (ext4_should_dioread_nolock(inode)) {
 		/*
 		 * We may need to convert up to one extent per block in
@@ -2962,6 +2789,13 @@ static int ext4_writepages(struct address_space *mapping,
 
 	percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem);
 	ret = ext4_do_writepages(&mpd);
+	/*
+	 * For data=journal writeback we could have come across pages marked
+	 * for delayed dirtying (PageChecked) which were just added to the
+	 * running transaction. Try once more to get them to stable storage.
+	 */
+	if (!ret && mpd.journalled_more_data)
+		ret = ext4_do_writepages(&mpd);
 	percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem);
 
 	return ret;
@@ -3043,7 +2877,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 			       struct page **pagep, void **fsdata)
 {
 	int ret, retries = 0;
-	struct page *page;
+	struct folio *folio;
 	pgoff_t index;
 	struct inode *inode = mapping->host;
 
@@ -3070,22 +2904,22 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	}
 
 retry:
-	page = grab_cache_page_write_begin(mapping, index);
-	if (!page)
+	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+			mapping_gfp_mask(mapping));
+	if (!folio)
 		return -ENOMEM;
 
-	/* In case writeback began while the page was unlocked */
-	wait_for_stable_page(page);
+	/* In case writeback began while the folio was unlocked */
+	folio_wait_stable(folio);
 
 #ifdef CONFIG_FS_ENCRYPTION
-	ret = ext4_block_write_begin(page, pos, len,
-				     ext4_da_get_block_prep);
+	ret = ext4_block_write_begin(folio, pos, len, ext4_da_get_block_prep);
 #else
-	ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep);
+	ret = __block_write_begin(&folio->page, pos, len, ext4_da_get_block_prep);
 #endif
 	if (ret < 0) {
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		/*
 		 * block_write_begin may have instantiated a few blocks
 		 * outside i_size.  Trim these off again. Don't need
@@ -3100,7 +2934,7 @@ retry:
 		return ret;
 	}
 
-	*pagep = page;
+	*pagep = &folio->page;
 	return ret;
 }
 
@@ -3159,9 +2993,8 @@ static int ext4_da_write_end(struct file *file,
 	 * i_disksize since writeback will push i_disksize upto i_size
 	 * eventually. If the end of the current write is > i_size and
 	 * inside an allocated block (ext4_da_should_update_i_disksize()
-	 * check), we need to update i_disksize here as neither
-	 * ext4_writepage() nor certain ext4_writepages() paths not
-	 * allocating blocks update i_disksize.
+	 * check), we need to update i_disksize here as certain
+	 * ext4_writepages() paths not allocating blocks update i_disksize.
 	 *
 	 * Note that we defer inode dirtying to generic_write_end() /
 	 * ext4_da_write_inline_data_end().
@@ -3235,9 +3068,7 @@ int ext4_alloc_da_blocks(struct inode *inode)
 static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
 {
 	struct inode *inode = mapping->host;
-	journal_t *journal;
 	sector_t ret = 0;
-	int err;
 
 	inode_lock_shared(inode);
 	/*
@@ -3247,45 +3078,16 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
 		goto out;
 
 	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
-			test_opt(inode->i_sb, DELALLOC)) {
+	    (test_opt(inode->i_sb, DELALLOC) ||
+	     ext4_should_journal_data(inode))) {
 		/*
-		 * With delalloc we want to sync the file
-		 * so that we can make sure we allocate
-		 * blocks for file
+		 * With delalloc or journalled data we want to sync the file so
+		 * that we can make sure we allocate blocks for file and data
+		 * is in place for the user to see it
 		 */
 		filemap_write_and_wait(mapping);
 	}
 
-	if (EXT4_JOURNAL(inode) &&
-	    ext4_test_inode_state(inode, EXT4_STATE_JDATA)) {
-		/*
-		 * This is a REALLY heavyweight approach, but the use of
-		 * bmap on dirty files is expected to be extremely rare:
-		 * only if we run lilo or swapon on a freshly made file
-		 * do we expect this to happen.
-		 *
-		 * (bmap requires CAP_SYS_RAWIO so this does not
-		 * represent an unprivileged user DOS attack --- we'd be
-		 * in trouble if mortal users could trigger this path at
-		 * will.)
-		 *
-		 * NB. EXT4_STATE_JDATA is not set on files other than
-		 * regular files.  If somebody wants to bmap a directory
-		 * or symlink and gets confused because the buffer
-		 * hasn't yet been flushed to disk, they deserve
-		 * everything they get.
-		 */
-
-		ext4_clear_inode_state(inode, EXT4_STATE_JDATA);
-		journal = EXT4_JOURNAL(inode);
-		jbd2_journal_lock_updates(journal);
-		err = jbd2_journal_flush(journal, 0);
-		jbd2_journal_unlock_updates(journal);
-
-		if (err)
-			goto out;
-	}
-
 	ret = iomap_bmap(mapping, block, &ext4_iomap_ops);
 
 out:
@@ -3295,17 +3097,16 @@ out:
 
 static int ext4_read_folio(struct file *file, struct folio *folio)
 {
-	struct page *page = &folio->page;
 	int ret = -EAGAIN;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 
-	trace_ext4_readpage(page);
+	trace_ext4_readpage(&folio->page);
 
 	if (ext4_has_inline_data(inode))
-		ret = ext4_readpage_inline(inode, page);
+		ret = ext4_readpage_inline(inode, folio);
 
 	if (ret == -EAGAIN)
-		return ext4_mpage_readpages(inode, NULL, page);
+		return ext4_mpage_readpages(inode, NULL, folio);
 
 	return ret;
 }
@@ -3686,24 +3487,26 @@ const struct iomap_ops ext4_iomap_report_ops = {
 };
 
 /*
- * Whenever the folio is being dirtied, corresponding buffers should already
- * be attached to the transaction (we take care of this in ext4_page_mkwrite()
- * and ext4_write_begin()). However we cannot move buffers to dirty transaction
- * lists here because ->dirty_folio is called under VFS locks and the folio
- * is not necessarily locked.
- *
- * We cannot just dirty the folio and leave attached buffers clean, because the
- * buffers' dirty state is "definitive".  We cannot just set the buffers dirty
- * or jbddirty because all the journalling code will explode.
- *
- * So what we do is to mark the folio "pending dirty" and next time writepage
- * is called, propagate that into the buffers appropriately.
+ * For data=journal mode, folio should be marked dirty only when it was
+ * writeably mapped. When that happens, it was already attached to the
+ * transaction and marked as jbddirty (we take care of this in
+ * ext4_page_mkwrite()). On transaction commit, we writeprotect page mappings
+ * so we should have nothing to do here, except for the case when someone
+ * had the page pinned and dirtied the page through this pin (e.g. by doing
+ * direct IO to it). In that case we'd need to attach buffers here to the
+ * transaction but we cannot due to lock ordering.  We cannot just dirty the
+ * folio and leave attached buffers clean, because the buffers' dirty state is
+ * "definitive".  We cannot just set the buffers dirty or jbddirty because all
+ * the journalling code will explode.  So what we do is to mark the folio
+ * "pending dirty" and next time ext4_writepages() is called, attach buffers
+ * to the transaction appropriately.
  */
 static bool ext4_journalled_dirty_folio(struct address_space *mapping,
 		struct folio *folio)
 {
 	WARN_ON_ONCE(!folio_buffers(folio));
-	folio_set_checked(folio);
+	if (folio_maybe_dma_pinned(folio))
+		folio_set_checked(folio);
 	return filemap_dirty_folio(mapping, folio);
 }
 
@@ -3809,23 +3612,26 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 	ext4_lblk_t iblock;
 	struct inode *inode = mapping->host;
 	struct buffer_head *bh;
-	struct page *page;
+	struct folio *folio;
 	int err = 0;
 
-	page = find_or_create_page(mapping, from >> PAGE_SHIFT,
-				   mapping_gfp_constraint(mapping, ~__GFP_FS));
-	if (!page)
+	folio = __filemap_get_folio(mapping, from >> PAGE_SHIFT,
+				    FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
+				    mapping_gfp_constraint(mapping, ~__GFP_FS));
+	if (!folio)
 		return -ENOMEM;
 
 	blocksize = inode->i_sb->s_blocksize;
 
 	iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits);
 
-	if (!page_has_buffers(page))
-		create_empty_buffers(page, blocksize, 0);
+	bh = folio_buffers(folio);
+	if (!bh) {
+		create_empty_buffers(&folio->page, blocksize, 0);
+		bh = folio_buffers(folio);
+	}
 
 	/* Find the buffer that contains "offset" */
-	bh = page_buffers(page);
 	pos = blocksize;
 	while (offset >= pos) {
 		bh = bh->b_this_page;
@@ -3847,7 +3653,7 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 	}
 
 	/* Ok, it's mapped. Make sure it's up-to-date */
-	if (PageUptodate(page))
+	if (folio_test_uptodate(folio))
 		set_buffer_uptodate(bh);
 
 	if (!buffer_uptodate(bh)) {
@@ -3857,7 +3663,7 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
 			/* We expect the key to be set. */
 			BUG_ON(!fscrypt_has_encryption_key(inode));
-			err = fscrypt_decrypt_pagecache_blocks(page_folio(page),
+			err = fscrypt_decrypt_pagecache_blocks(folio,
 							       blocksize,
 							       bh_offset(bh));
 			if (err) {
@@ -3873,11 +3679,11 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		if (err)
 			goto unlock;
 	}
-	zero_user(page, offset, length);
+	folio_zero_range(folio, offset, length);
 	BUFFER_TRACE(bh, "zeroed end of block");
 
 	if (ext4_should_journal_data(inode)) {
-		err = ext4_handle_dirty_metadata(handle, inode, bh);
+		err = ext4_dirty_journalled_data(handle, bh);
 	} else {
 		err = 0;
 		mark_buffer_dirty(bh);
@@ -3887,8 +3693,8 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 	}
 
 unlock:
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 	return err;
 }
 
@@ -5385,7 +5191,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
 	 * If the folio is fully truncated, we don't need to wait for any commit
 	 * (and we even should not as __ext4_journalled_invalidate_folio() may
 	 * strip all buffers from the folio but keep the folio dirty which can then
-	 * confuse e.g. concurrent ext4_writepage() seeing dirty folio without
+	 * confuse e.g. concurrent ext4_writepages() seeing dirty folio without
 	 * buffers). Also we don't need to wait for any commit if all buffers in
 	 * the folio remain valid. This is most beneficial for the common case of
 	 * blocksize == PAGESIZE.
@@ -6212,7 +6018,7 @@ static int ext4_bh_unmapped(handle_t *handle, struct inode *inode,
 vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct page *page = vmf->page;
+	struct folio *folio = page_folio(vmf->page);
 	loff_t size;
 	unsigned long len;
 	int err;
@@ -6256,19 +6062,18 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 		goto out_ret;
 	}
 
-	lock_page(page);
+	folio_lock(folio);
 	size = i_size_read(inode);
 	/* Page got truncated from under us? */
-	if (page->mapping != mapping || page_offset(page) > size) {
-		unlock_page(page);
+	if (folio->mapping != mapping || folio_pos(folio) > size) {
+		folio_unlock(folio);
 		ret = VM_FAULT_NOPAGE;
 		goto out;
 	}
 
-	if (page->index == size >> PAGE_SHIFT)
-		len = size & ~PAGE_MASK;
-	else
-		len = PAGE_SIZE;
+	len = folio_size(folio);
+	if (folio_pos(folio) + len > size)
+		len = size - folio_pos(folio);
 	/*
 	 * Return if we have all the buffers mapped. This avoids the need to do
 	 * journal_start/journal_stop which can block and take a long time
@@ -6276,17 +6081,17 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 	 * This cannot be done for data journalling, as we have to add the
 	 * inode to the transaction's list to writeprotect pages on commit.
 	 */
-	if (page_has_buffers(page)) {
-		if (!ext4_walk_page_buffers(NULL, inode, page_buffers(page),
+	if (folio_buffers(folio)) {
+		if (!ext4_walk_page_buffers(NULL, inode, folio_buffers(folio),
 					    0, len, NULL,
 					    ext4_bh_unmapped)) {
 			/* Wait so that we don't change page under IO */
-			wait_for_stable_page(page);
+			folio_wait_stable(folio);
 			ret = VM_FAULT_LOCKED;
 			goto out;
 		}
 	}
-	unlock_page(page);
+	folio_unlock(folio);
 	/* OK, we need to fill the hole... */
 	if (ext4_should_dioread_nolock(inode))
 		get_block = ext4_get_block_unwritten;
@@ -6307,36 +6112,25 @@ retry_alloc:
 	if (!ext4_should_journal_data(inode)) {
 		err = block_page_mkwrite(vma, vmf, get_block);
 	} else {
-		lock_page(page);
+		folio_lock(folio);
 		size = i_size_read(inode);
 		/* Page got truncated from under us? */
-		if (page->mapping != mapping || page_offset(page) > size) {
+		if (folio->mapping != mapping || folio_pos(folio) > size) {
 			ret = VM_FAULT_NOPAGE;
 			goto out_error;
 		}
 
-		if (page->index == size >> PAGE_SHIFT)
-			len = size & ~PAGE_MASK;
-		else
-			len = PAGE_SIZE;
+		len = folio_size(folio);
+		if (folio_pos(folio) + len > size)
+			len = size - folio_pos(folio);
 
-		err = __block_write_begin(page, 0, len, ext4_get_block);
+		err = __block_write_begin(&folio->page, 0, len, ext4_get_block);
 		if (!err) {
 			ret = VM_FAULT_SIGBUS;
-			if (ext4_walk_page_buffers(handle, inode,
-					page_buffers(page), 0, len, NULL,
-					do_journal_get_write_access))
+			if (ext4_journal_page_buffers(handle, &folio->page, len))
 				goto out_error;
-			if (ext4_walk_page_buffers(handle, inode,
-					page_buffers(page), 0, len, NULL,
-					write_end_fn))
-				goto out_error;
-			if (ext4_jbd2_inode_add_write(handle, inode,
-						      page_offset(page), len))
-				goto out_error;
-			ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 		} else {
-			unlock_page(page);
+			folio_unlock(folio);
 		}
 	}
 	ext4_journal_stop(handle);
@@ -6349,7 +6143,7 @@ out:
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 out_error:
-	unlock_page(page);
+	folio_unlock(folio);
 	ext4_journal_stop(handle);
 	goto out;
 }
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 5b2ae37a8b80..78259bddbc4d 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1168,10 +1168,8 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 	if (groups_per_page > 1) {
 		i = sizeof(struct buffer_head *) * groups_per_page;
 		bh = kzalloc(i, gfp);
-		if (bh == NULL) {
-			err = -ENOMEM;
-			goto out;
-		}
+		if (bh == NULL)
+			return -ENOMEM;
 	} else
 		bh = &bhs;
 
@@ -1489,7 +1487,13 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
 			put_page(page);
 		page = find_or_create_page(inode->i_mapping, pnum, gfp);
 		if (page) {
-			BUG_ON(page->mapping != inode->i_mapping);
+			if (WARN_RATELIMIT(page->mapping != inode->i_mapping,
+	"ext4: bitmap's paging->mapping != inode->i_mapping\n")) {
+				/* should never happen */
+				unlock_page(page);
+				ret = -EINVAL;
+				goto err;
+			}
 			if (!PageUptodate(page)) {
 				ret = ext4_mb_init_cache(page, NULL, gfp);
 				if (ret) {
@@ -1525,7 +1529,13 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
 			put_page(page);
 		page = find_or_create_page(inode->i_mapping, pnum, gfp);
 		if (page) {
-			BUG_ON(page->mapping != inode->i_mapping);
+			if (WARN_RATELIMIT(page->mapping != inode->i_mapping,
+	"ext4: buddy bitmap's page->mapping != inode->i_mapping\n")) {
+				/* should never happen */
+				unlock_page(page);
+				ret = -EINVAL;
+				goto err;
+			}
 			if (!PageUptodate(page)) {
 				ret = ext4_mb_init_cache(page, e4b->bd_bitmap,
 							 gfp);
@@ -1557,8 +1567,7 @@ err:
 		put_page(page);
 	if (e4b->bd_bitmap_page)
 		put_page(e4b->bd_bitmap_page);
-	if (e4b->bd_buddy_page)
-		put_page(e4b->bd_buddy_page);
+
 	e4b->bd_buddy = NULL;
 	e4b->bd_bitmap = NULL;
 	return ret;
@@ -1721,7 +1730,8 @@ static void mb_buddy_mark_free(struct ext4_buddy *e4b, int first, int last)
 			break;
 		order++;
 
-		if (first == last || !(buddy2 = mb_find_buddy(e4b, order, &max))) {
+		buddy2 = mb_find_buddy(e4b, order, &max);
+		if (!buddy2) {
 			mb_clear_bits(buddy, first, last - first + 1);
 			e4b->bd_info->bb_counters[order - 1] += last - first + 1;
 			break;
@@ -2021,8 +2031,6 @@ static void ext4_mb_check_limits(struct ext4_allocation_context *ac,
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_free_extent *bex = &ac->ac_b_ex;
 	struct ext4_free_extent *gex = &ac->ac_g_ex;
-	struct ext4_free_extent ex;
-	int max;
 
 	if (ac->ac_status == AC_STATUS_FOUND)
 		return;
@@ -2041,17 +2049,8 @@ static void ext4_mb_check_limits(struct ext4_allocation_context *ac,
 	if (bex->fe_len < gex->fe_len)
 		return;
 
-	if ((finish_group || ac->ac_found > sbi->s_mb_min_to_scan)
-			&& bex->fe_group == e4b->bd_group) {
-		/* recheck chunk's availability - we don't know
-		 * when it was found (within this lock-unlock
-		 * period or not) */
-		max = mb_find_extent(e4b, bex->fe_start, gex->fe_len, &ex);
-		if (max >= gex->fe_len) {
-			ext4_mb_use_best_found(ac, e4b);
-			return;
-		}
-	}
+	if (finish_group)
+		ext4_mb_use_best_found(ac, e4b);
 }
 
 /*
@@ -2124,7 +2123,7 @@ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac,
 }
 
 static noinline_for_stack
-int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
+void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 					struct ext4_buddy *e4b)
 {
 	struct ext4_free_extent ex = ac->ac_b_ex;
@@ -2135,7 +2134,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 	BUG_ON(ex.fe_len <= 0);
 	err = ext4_mb_load_buddy(ac->ac_sb, group, e4b);
 	if (err)
-		return err;
+		return;
 
 	ext4_lock_group(ac->ac_sb, group);
 	max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex);
@@ -2147,8 +2146,6 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 
 	ext4_unlock_group(ac->ac_sb, group);
 	ext4_mb_unload_buddy(e4b);
-
-	return 0;
 }
 
 static noinline_for_stack
@@ -2162,7 +2159,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
 	struct ext4_free_extent ex;
 
-	if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL))
+	if (!(ac->ac_flags & (EXT4_MB_HINT_TRY_GOAL | EXT4_MB_HINT_GOAL_ONLY)))
 		return 0;
 	if (grp->bb_free == 0)
 		return 0;
@@ -2236,7 +2233,9 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
 			continue;
 
 		buddy = mb_find_buddy(e4b, i, &max);
-		BUG_ON(buddy == NULL);
+		if (WARN_RATELIMIT(buddy == NULL,
+			 "ext4: mb_simple_scan_group: mb_find_buddy failed, (%d)\n", i))
+			continue;
 
 		k = mb_find_next_zero_bit(buddy, max, 0);
 		if (k >= max) {
@@ -2569,14 +2568,14 @@ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group,
 void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group,
 			   unsigned int nr)
 {
-	while (nr-- > 0) {
-		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group,
-								  NULL);
-		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	struct ext4_group_desc *gdp;
+	struct ext4_group_info *grp;
 
+	while (nr-- > 0) {
 		if (!group)
 			group = ext4_get_groups_count(sb);
 		group--;
+		gdp = ext4_get_group_desc(sb, group, NULL);
 		grp = ext4_get_group_info(sb, group);
 
 		if (EXT4_MB_GRP_NEED_INIT(grp) &&
@@ -3084,7 +3083,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 		if (meta_group_info == NULL) {
 			ext4_msg(sb, KERN_ERR, "can't allocate mem "
 				 "for a buddy group");
-			goto exit_meta_group_info;
+			return -ENOMEM;
 		}
 		rcu_read_lock();
 		rcu_dereference(sbi->s_group_info)[idx] = meta_group_info;
@@ -3138,7 +3137,6 @@ exit_group_info:
 		group_info[idx] = NULL;
 		rcu_read_unlock();
 	}
-exit_meta_group_info:
 	return -ENOMEM;
 } /* ext4_mb_add_groupinfo */
 
@@ -3419,7 +3417,6 @@ int ext4_mb_init(struct super_block *sb)
 	sbi->s_mb_stats = MB_DEFAULT_STATS;
 	sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD;
 	sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS;
-	sbi->s_mb_max_inode_prealloc = MB_DEFAULT_MAX_INODE_PREALLOC;
 	/*
 	 * The default group preallocation is 512, which for 4k block
 	 * sizes translates to 2 megabytes.  However for bigalloc file
@@ -3606,7 +3603,7 @@ static void ext4_free_data_in_buddy(struct super_block *sb,
 {
 	struct ext4_buddy e4b;
 	struct ext4_group_info *db;
-	int err, count = 0, count2 = 0;
+	int err, count = 0;
 
 	mb_debug(sb, "gonna free %u blocks in group %u (0x%p):",
 		 entry->efd_count, entry->efd_group, entry);
@@ -3622,7 +3619,6 @@ static void ext4_free_data_in_buddy(struct super_block *sb,
 	db = e4b.bd_info;
 	/* there are blocks to put in buddy to make them really free */
 	count += entry->efd_count;
-	count2++;
 	ext4_lock_group(sb, entry->efd_group);
 	/* Take it out of per group rb tree */
 	rb_erase(&entry->efd_node, &(db->bb_free_root));
@@ -3647,8 +3643,7 @@ static void ext4_free_data_in_buddy(struct super_block *sb,
 	ext4_unlock_group(sb, entry->efd_group);
 	ext4_mb_unload_buddy(&e4b);
 
-	mb_debug(sb, "freed %d blocks in %d structures\n", count,
-		 count2);
+	mb_debug(sb, "freed %d blocks in 1 structures\n", count);
 }
 
 /*
@@ -3757,9 +3752,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 
 	bitmap_bh = ext4_read_block_bitmap(sb, ac->ac_b_ex.fe_group);
 	if (IS_ERR(bitmap_bh)) {
-		err = PTR_ERR(bitmap_bh);
-		bitmap_bh = NULL;
-		goto out_err;
+		return PTR_ERR(bitmap_bh);
 	}
 
 	BUFFER_TRACE(bitmap_bh, "getting write access");
@@ -3822,7 +3815,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	}
 	len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len;
 	ext4_free_group_clusters_set(sb, gdp, len);
-	ext4_block_bitmap_csum_set(sb, ac->ac_b_ex.fe_group, gdp, bitmap_bh);
+	ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh);
 	ext4_group_desc_csum_set(sb, ac->ac_b_ex.fe_group, gdp);
 
 	ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
@@ -3929,7 +3922,7 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 			clen = ext4_free_group_clusters(sb, gdp) + clen_changed;
 
 		ext4_free_group_clusters_set(sb, gdp, clen);
-		ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+		ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh);
 		ext4_group_desc_csum_set(sb, group, gdp);
 
 		ext4_unlock_group(sb, group);
@@ -3985,6 +3978,197 @@ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac)
 }
 
 /*
+ * This function returns the next element to look at during inode
+ * PA rbtree walk. We assume that we have held the inode PA rbtree lock
+ * (ei->i_prealloc_lock)
+ *
+ * new_start	The start of the range we want to compare
+ * cur_start	The existing start that we are comparing against
+ * node	The node of the rb_tree
+ */
+static inline struct rb_node*
+ext4_mb_pa_rb_next_iter(ext4_lblk_t new_start, ext4_lblk_t cur_start, struct rb_node *node)
+{
+	if (new_start < cur_start)
+		return node->rb_left;
+	else
+		return node->rb_right;
+}
+
+static inline void
+ext4_mb_pa_assert_overlap(struct ext4_allocation_context *ac,
+			  ext4_lblk_t start, ext4_lblk_t end)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
+	struct ext4_prealloc_space *tmp_pa;
+	ext4_lblk_t tmp_pa_start, tmp_pa_end;
+	struct rb_node *iter;
+
+	read_lock(&ei->i_prealloc_lock);
+	for (iter = ei->i_prealloc_node.rb_node; iter;
+	     iter = ext4_mb_pa_rb_next_iter(start, tmp_pa_start, iter)) {
+		tmp_pa = rb_entry(iter, struct ext4_prealloc_space,
+				  pa_node.inode_node);
+		tmp_pa_start = tmp_pa->pa_lstart;
+		tmp_pa_end = tmp_pa->pa_lstart + EXT4_C2B(sbi, tmp_pa->pa_len);
+
+		spin_lock(&tmp_pa->pa_lock);
+		if (tmp_pa->pa_deleted == 0)
+			BUG_ON(!(start >= tmp_pa_end || end <= tmp_pa_start));
+		spin_unlock(&tmp_pa->pa_lock);
+	}
+	read_unlock(&ei->i_prealloc_lock);
+}
+
+/*
+ * Given an allocation context "ac" and a range "start", "end", check
+ * and adjust boundaries if the range overlaps with any of the existing
+ * preallocatoins stored in the corresponding inode of the allocation context.
+ *
+ * Parameters:
+ *	ac			allocation context
+ *	start			start of the new range
+ *	end			end of the new range
+ */
+static inline void
+ext4_mb_pa_adjust_overlap(struct ext4_allocation_context *ac,
+			  ext4_lblk_t *start, ext4_lblk_t *end)
+{
+	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+	struct ext4_prealloc_space *tmp_pa = NULL, *left_pa = NULL, *right_pa = NULL;
+	struct rb_node *iter;
+	ext4_lblk_t new_start, new_end;
+	ext4_lblk_t tmp_pa_start, tmp_pa_end, left_pa_end = -1, right_pa_start = -1;
+
+	new_start = *start;
+	new_end = *end;
+
+	/*
+	 * Adjust the normalized range so that it doesn't overlap with any
+	 * existing preallocated blocks(PAs). Make sure to hold the rbtree lock
+	 * so it doesn't change underneath us.
+	 */
+	read_lock(&ei->i_prealloc_lock);
+
+	/* Step 1: find any one immediate neighboring PA of the normalized range */
+	for (iter = ei->i_prealloc_node.rb_node; iter;
+	     iter = ext4_mb_pa_rb_next_iter(ac->ac_o_ex.fe_logical,
+					    tmp_pa_start, iter)) {
+		tmp_pa = rb_entry(iter, struct ext4_prealloc_space,
+				  pa_node.inode_node);
+		tmp_pa_start = tmp_pa->pa_lstart;
+		tmp_pa_end = tmp_pa->pa_lstart + EXT4_C2B(sbi, tmp_pa->pa_len);
+
+		/* PA must not overlap original request */
+		spin_lock(&tmp_pa->pa_lock);
+		if (tmp_pa->pa_deleted == 0)
+			BUG_ON(!(ac->ac_o_ex.fe_logical >= tmp_pa_end ||
+				 ac->ac_o_ex.fe_logical < tmp_pa_start));
+		spin_unlock(&tmp_pa->pa_lock);
+	}
+
+	/*
+	 * Step 2: check if the found PA is left or right neighbor and
+	 * get the other neighbor
+	 */
+	if (tmp_pa) {
+		if (tmp_pa->pa_lstart < ac->ac_o_ex.fe_logical) {
+			struct rb_node *tmp;
+
+			left_pa = tmp_pa;
+			tmp = rb_next(&left_pa->pa_node.inode_node);
+			if (tmp) {
+				right_pa = rb_entry(tmp,
+						    struct ext4_prealloc_space,
+						    pa_node.inode_node);
+			}
+		} else {
+			struct rb_node *tmp;
+
+			right_pa = tmp_pa;
+			tmp = rb_prev(&right_pa->pa_node.inode_node);
+			if (tmp) {
+				left_pa = rb_entry(tmp,
+						   struct ext4_prealloc_space,
+						   pa_node.inode_node);
+			}
+		}
+	}
+
+	/* Step 3: get the non deleted neighbors */
+	if (left_pa) {
+		for (iter = &left_pa->pa_node.inode_node;;
+		     iter = rb_prev(iter)) {
+			if (!iter) {
+				left_pa = NULL;
+				break;
+			}
+
+			tmp_pa = rb_entry(iter, struct ext4_prealloc_space,
+					  pa_node.inode_node);
+			left_pa = tmp_pa;
+			spin_lock(&tmp_pa->pa_lock);
+			if (tmp_pa->pa_deleted == 0) {
+				spin_unlock(&tmp_pa->pa_lock);
+				break;
+			}
+			spin_unlock(&tmp_pa->pa_lock);
+		}
+	}
+
+	if (right_pa) {
+		for (iter = &right_pa->pa_node.inode_node;;
+		     iter = rb_next(iter)) {
+			if (!iter) {
+				right_pa = NULL;
+				break;
+			}
+
+			tmp_pa = rb_entry(iter, struct ext4_prealloc_space,
+					  pa_node.inode_node);
+			right_pa = tmp_pa;
+			spin_lock(&tmp_pa->pa_lock);
+			if (tmp_pa->pa_deleted == 0) {
+				spin_unlock(&tmp_pa->pa_lock);
+				break;
+			}
+			spin_unlock(&tmp_pa->pa_lock);
+		}
+	}
+
+	if (left_pa) {
+		left_pa_end =
+			left_pa->pa_lstart + EXT4_C2B(sbi, left_pa->pa_len);
+		BUG_ON(left_pa_end > ac->ac_o_ex.fe_logical);
+	}
+
+	if (right_pa) {
+		right_pa_start = right_pa->pa_lstart;
+		BUG_ON(right_pa_start <= ac->ac_o_ex.fe_logical);
+	}
+
+	/* Step 4: trim our normalized range to not overlap with the neighbors */
+	if (left_pa) {
+		if (left_pa_end > new_start)
+			new_start = left_pa_end;
+	}
+
+	if (right_pa) {
+		if (right_pa_start < new_end)
+			new_end = right_pa_start;
+	}
+	read_unlock(&ei->i_prealloc_lock);
+
+	/* XXX: extra loop to check we really don't overlap preallocations */
+	ext4_mb_pa_assert_overlap(ac, new_start, new_end);
+
+	*start = new_start;
+	*end = new_end;
+}
+
+/*
  * Normalization means making request better in terms of
  * size and alignment
  */
@@ -3993,13 +4177,12 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 				struct ext4_allocation_request *ar)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+	struct ext4_super_block *es = sbi->s_es;
 	int bsbits, max;
 	ext4_lblk_t end;
 	loff_t size, start_off;
 	loff_t orig_size __maybe_unused;
 	ext4_lblk_t start;
-	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
-	struct ext4_prealloc_space *pa;
 
 	/* do normalize only data requests, metadata requests
 	   do not need preallocation */
@@ -4068,7 +4251,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 		size = 8 * 1024 * 1024;
 	} else {
 		start_off = (loff_t) ac->ac_o_ex.fe_logical << bsbits;
-		size	  = (loff_t) EXT4_C2B(EXT4_SB(ac->ac_sb),
+		size	  = (loff_t) EXT4_C2B(sbi,
 					      ac->ac_o_ex.fe_len) << bsbits;
 	}
 	size = size >> bsbits;
@@ -4100,61 +4283,10 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 
 	end = start + size;
 
-	/* check we don't cross already preallocated blocks */
-	rcu_read_lock();
-	list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
-		ext4_lblk_t pa_end;
+	ext4_mb_pa_adjust_overlap(ac, &start, &end);
 
-		if (pa->pa_deleted)
-			continue;
-		spin_lock(&pa->pa_lock);
-		if (pa->pa_deleted) {
-			spin_unlock(&pa->pa_lock);
-			continue;
-		}
-
-		pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb),
-						  pa->pa_len);
-
-		/* PA must not overlap original request */
-		BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end ||
-			ac->ac_o_ex.fe_logical < pa->pa_lstart));
-
-		/* skip PAs this normalized request doesn't overlap with */
-		if (pa->pa_lstart >= end || pa_end <= start) {
-			spin_unlock(&pa->pa_lock);
-			continue;
-		}
-		BUG_ON(pa->pa_lstart <= start && pa_end >= end);
-
-		/* adjust start or end to be adjacent to this pa */
-		if (pa_end <= ac->ac_o_ex.fe_logical) {
-			BUG_ON(pa_end < start);
-			start = pa_end;
-		} else if (pa->pa_lstart > ac->ac_o_ex.fe_logical) {
-			BUG_ON(pa->pa_lstart > end);
-			end = pa->pa_lstart;
-		}
-		spin_unlock(&pa->pa_lock);
-	}
-	rcu_read_unlock();
 	size = end - start;
 
-	/* XXX: extra loop to check we really don't overlap preallocations */
-	rcu_read_lock();
-	list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
-		ext4_lblk_t pa_end;
-
-		spin_lock(&pa->pa_lock);
-		if (pa->pa_deleted == 0) {
-			pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb),
-							  pa->pa_len);
-			BUG_ON(!(start >= pa_end || end <= pa->pa_lstart));
-		}
-		spin_unlock(&pa->pa_lock);
-	}
-	rcu_read_unlock();
-
 	/*
 	 * In this function "start" and "size" are normalized for better
 	 * alignment and length such that we could preallocate more blocks.
@@ -4165,7 +4297,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	 * provide gurantee on number of contiguous blocks allocation since that
 	 * depends upon free space left, etc).
 	 * In case of inode pa, later we use the allocated blocks
-	 * [pa_start + fe_logical - pa_lstart, fe_len/size] from the preallocated
+	 * [pa_pstart + fe_logical - pa_lstart, fe_len/size] from the preallocated
 	 * range of goal/best blocks [start, size] to put it at the
 	 * ac_o_ex.fe_logical extent of this inode.
 	 * (See ext4_mb_use_inode_pa() for more details)
@@ -4188,18 +4320,21 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size);
 
 	/* define goal start in order to merge */
-	if (ar->pright && (ar->lright == (start + size))) {
+	if (ar->pright && (ar->lright == (start + size)) &&
+	    ar->pright >= size &&
+	    ar->pright - size >= le32_to_cpu(es->s_first_data_block)) {
 		/* merge to the right */
 		ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size,
-						&ac->ac_f_ex.fe_group,
-						&ac->ac_f_ex.fe_start);
+						&ac->ac_g_ex.fe_group,
+						&ac->ac_g_ex.fe_start);
 		ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL;
 	}
-	if (ar->pleft && (ar->lleft + 1 == start)) {
+	if (ar->pleft && (ar->lleft + 1 == start) &&
+	    ar->pleft + 1 < ext4_blocks_count(es)) {
 		/* merge to the left */
 		ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1,
-						&ac->ac_f_ex.fe_group,
-						&ac->ac_f_ex.fe_start);
+						&ac->ac_g_ex.fe_group,
+						&ac->ac_g_ex.fe_start);
 		ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL;
 	}
 
@@ -4247,15 +4382,14 @@ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
 		if (ac->ac_f_ex.fe_len == 0)
 			return;
 		err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b);
-		if (err) {
+		if (WARN_RATELIMIT(err,
+				   "ext4: mb_load_buddy failed (%d)", err))
 			/*
 			 * This should never happen since we pin the
 			 * pages in the ext4_allocation_context so
 			 * ext4_mb_load_buddy() should never fail.
 			 */
-			WARN(1, "mb_load_buddy failed (%d)", err);
 			return;
-		}
 		ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
 		mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start,
 			       ac->ac_f_ex.fe_len);
@@ -4263,8 +4397,11 @@ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
 		ext4_mb_unload_buddy(&e4b);
 		return;
 	}
-	if (pa->pa_type == MB_INODE_PA)
+	if (pa->pa_type == MB_INODE_PA) {
+		spin_lock(&pa->pa_lock);
 		pa->pa_free += ac->ac_b_ex.fe_len;
+		spin_unlock(&pa->pa_lock);
+	}
 }
 
 /*
@@ -4292,6 +4429,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
 	BUG_ON(start < pa->pa_pstart);
 	BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len));
 	BUG_ON(pa->pa_free < len);
+	BUG_ON(ac->ac_b_ex.fe_len <= 0);
 	pa->pa_free -= len;
 
 	mb_debug(ac->ac_sb, "use %llu/%d from inode pa %p\n", start, len, pa);
@@ -4312,14 +4450,14 @@ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac,
 	ac->ac_status = AC_STATUS_FOUND;
 	ac->ac_pa = pa;
 
-	/* we don't correct pa_pstart or pa_plen here to avoid
+	/* we don't correct pa_pstart or pa_len here to avoid
 	 * possible race when the group is being loaded concurrently
 	 * instead we correct pa later, after blocks are marked
 	 * in on-disk bitmap -- see ext4_mb_release_context()
 	 * Other CPUs are prevented from allocating from this pa by lg_mutex
 	 */
 	mb_debug(ac->ac_sb, "use %u/%u from group pa %p\n",
-		 pa->pa_lstart-len, len, pa);
+		 pa->pa_lstart, len, pa);
 }
 
 /*
@@ -4361,7 +4499,9 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 	int order, i;
 	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
 	struct ext4_locality_group *lg;
-	struct ext4_prealloc_space *pa, *cpa = NULL;
+	struct ext4_prealloc_space *tmp_pa, *cpa = NULL;
+	ext4_lblk_t tmp_pa_start, tmp_pa_end;
+	struct rb_node *iter;
 	ext4_fsblk_t goal_block;
 
 	/* only data can be preallocated */
@@ -4369,35 +4509,47 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 		return false;
 
 	/* first, try per-file preallocation */
-	rcu_read_lock();
-	list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
+	read_lock(&ei->i_prealloc_lock);
+	for (iter = ei->i_prealloc_node.rb_node; iter;
+	     iter = ext4_mb_pa_rb_next_iter(ac->ac_o_ex.fe_logical,
+					    tmp_pa_start, iter)) {
+		tmp_pa = rb_entry(iter, struct ext4_prealloc_space,
+				  pa_node.inode_node);
 
 		/* all fields in this condition don't change,
 		 * so we can skip locking for them */
-		if (ac->ac_o_ex.fe_logical < pa->pa_lstart ||
-		    ac->ac_o_ex.fe_logical >= (pa->pa_lstart +
-					       EXT4_C2B(sbi, pa->pa_len)))
+		tmp_pa_start = tmp_pa->pa_lstart;
+		tmp_pa_end = tmp_pa->pa_lstart + EXT4_C2B(sbi, tmp_pa->pa_len);
+
+		/* original request start doesn't lie in this PA */
+		if (ac->ac_o_ex.fe_logical < tmp_pa_start ||
+		    ac->ac_o_ex.fe_logical >= tmp_pa_end)
 			continue;
 
 		/* non-extent files can't have physical blocks past 2^32 */
 		if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
-		    (pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len) >
-		     EXT4_MAX_BLOCK_FILE_PHYS))
-			continue;
+		    (tmp_pa->pa_pstart + EXT4_C2B(sbi, tmp_pa->pa_len) >
+		     EXT4_MAX_BLOCK_FILE_PHYS)) {
+			/*
+			 * Since PAs don't overlap, we won't find any
+			 * other PA to satisfy this.
+			 */
+			break;
+		}
 
 		/* found preallocated blocks, use them */
-		spin_lock(&pa->pa_lock);
-		if (pa->pa_deleted == 0 && pa->pa_free) {
-			atomic_inc(&pa->pa_count);
-			ext4_mb_use_inode_pa(ac, pa);
-			spin_unlock(&pa->pa_lock);
+		spin_lock(&tmp_pa->pa_lock);
+		if (tmp_pa->pa_deleted == 0 && tmp_pa->pa_free) {
+			atomic_inc(&tmp_pa->pa_count);
+			ext4_mb_use_inode_pa(ac, tmp_pa);
+			spin_unlock(&tmp_pa->pa_lock);
 			ac->ac_criteria = 10;
-			rcu_read_unlock();
+			read_unlock(&ei->i_prealloc_lock);
 			return true;
 		}
-		spin_unlock(&pa->pa_lock);
+		spin_unlock(&tmp_pa->pa_lock);
 	}
-	rcu_read_unlock();
+	read_unlock(&ei->i_prealloc_lock);
 
 	/* can we use group allocation? */
 	if (!(ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC))
@@ -4419,16 +4571,16 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 	 */
 	for (i = order; i < PREALLOC_TB_SIZE; i++) {
 		rcu_read_lock();
-		list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[i],
-					pa_inode_list) {
-			spin_lock(&pa->pa_lock);
-			if (pa->pa_deleted == 0 &&
-					pa->pa_free >= ac->ac_o_ex.fe_len) {
+		list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[i],
+					pa_node.lg_list) {
+			spin_lock(&tmp_pa->pa_lock);
+			if (tmp_pa->pa_deleted == 0 &&
+					tmp_pa->pa_free >= ac->ac_o_ex.fe_len) {
 
 				cpa = ext4_mb_check_group_pa(goal_block,
-								pa, cpa);
+								tmp_pa, cpa);
 			}
-			spin_unlock(&pa->pa_lock);
+			spin_unlock(&tmp_pa->pa_lock);
 		}
 		rcu_read_unlock();
 	}
@@ -4525,16 +4677,22 @@ static void ext4_mb_mark_pa_deleted(struct super_block *sb,
 	}
 }
 
-static void ext4_mb_pa_callback(struct rcu_head *head)
+static inline void ext4_mb_pa_free(struct ext4_prealloc_space *pa)
 {
-	struct ext4_prealloc_space *pa;
-	pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu);
-
+	BUG_ON(!pa);
 	BUG_ON(atomic_read(&pa->pa_count));
 	BUG_ON(pa->pa_deleted == 0);
 	kmem_cache_free(ext4_pspace_cachep, pa);
 }
 
+static void ext4_mb_pa_callback(struct rcu_head *head)
+{
+	struct ext4_prealloc_space *pa;
+
+	pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu);
+	ext4_mb_pa_free(pa);
+}
+
 /*
  * drops a reference to preallocated space descriptor
  * if this was the last reference and the space is consumed
@@ -4544,6 +4702,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
 {
 	ext4_group_t grp;
 	ext4_fsblk_t grp_blk;
+	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
 
 	/* in this short window concurrent discard can set pa_deleted */
 	spin_lock(&pa->pa_lock);
@@ -4588,11 +4747,42 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
 	list_del(&pa->pa_group_list);
 	ext4_unlock_group(sb, grp);
 
-	spin_lock(pa->pa_obj_lock);
-	list_del_rcu(&pa->pa_inode_list);
-	spin_unlock(pa->pa_obj_lock);
+	if (pa->pa_type == MB_INODE_PA) {
+		write_lock(pa->pa_node_lock.inode_lock);
+		rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node);
+		write_unlock(pa->pa_node_lock.inode_lock);
+		ext4_mb_pa_free(pa);
+	} else {
+		spin_lock(pa->pa_node_lock.lg_lock);
+		list_del_rcu(&pa->pa_node.lg_list);
+		spin_unlock(pa->pa_node_lock.lg_lock);
+		call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
+	}
+}
+
+static void ext4_mb_pa_rb_insert(struct rb_root *root, struct rb_node *new)
+{
+	struct rb_node **iter = &root->rb_node, *parent = NULL;
+	struct ext4_prealloc_space *iter_pa, *new_pa;
+	ext4_lblk_t iter_start, new_start;
+
+	while (*iter) {
+		iter_pa = rb_entry(*iter, struct ext4_prealloc_space,
+				   pa_node.inode_node);
+		new_pa = rb_entry(new, struct ext4_prealloc_space,
+				   pa_node.inode_node);
+		iter_start = iter_pa->pa_lstart;
+		new_start = new_pa->pa_lstart;
+
+		parent = *iter;
+		if (new_start < iter_start)
+			iter = &((*iter)->rb_left);
+		else
+			iter = &((*iter)->rb_right);
+	}
 
-	call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
+	rb_link_node(new, parent, iter);
+	rb_insert_color(new, root);
 }
 
 /*
@@ -4616,10 +4806,8 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 	pa = ac->ac_pa;
 
 	if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) {
-		int winl;
-		int wins;
-		int win;
-		int offs;
+		int new_bex_start;
+		int new_bex_end;
 
 		/* we can't allocate as much as normalizer wants.
 		 * so, found space must get proper lstart
@@ -4627,38 +4815,47 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 		BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical);
 		BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len);
 
-		/* we're limited by original request in that
-		 * logical block must be covered any way
-		 * winl is window we can move our chunk within */
-		winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical;
+		/*
+		 * Use the below logic for adjusting best extent as it keeps
+		 * fragmentation in check while ensuring logical range of best
+		 * extent doesn't overflow out of goal extent:
+		 *
+		 * 1. Check if best ex can be kept at end of goal and still
+		 *    cover original start
+		 * 2. Else, check if best ex can be kept at start of goal and
+		 *    still cover original start
+		 * 3. Else, keep the best ex at start of original request.
+		 */
+		new_bex_end = ac->ac_g_ex.fe_logical +
+			EXT4_C2B(sbi, ac->ac_g_ex.fe_len);
+		new_bex_start = new_bex_end - EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
+		if (ac->ac_o_ex.fe_logical >= new_bex_start)
+			goto adjust_bex;
 
-		/* also, we should cover whole original request */
-		wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len);
+		new_bex_start = ac->ac_g_ex.fe_logical;
+		new_bex_end =
+			new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
+		if (ac->ac_o_ex.fe_logical < new_bex_end)
+			goto adjust_bex;
 
-		/* the smallest one defines real window */
-		win = min(winl, wins);
+		new_bex_start = ac->ac_o_ex.fe_logical;
+		new_bex_end =
+			new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
 
-		offs = ac->ac_o_ex.fe_logical %
-			EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
-		if (offs && offs < win)
-			win = offs;
+adjust_bex:
+		ac->ac_b_ex.fe_logical = new_bex_start;
 
-		ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical -
-			EXT4_NUM_B2C(sbi, win);
 		BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
 		BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
+		BUG_ON(new_bex_end > (ac->ac_g_ex.fe_logical +
+				      EXT4_C2B(sbi, ac->ac_g_ex.fe_len)));
 	}
 
-	/* preallocation can change ac_b_ex, thus we store actually
-	 * allocated blocks for history */
-	ac->ac_f_ex = ac->ac_b_ex;
-
 	pa->pa_lstart = ac->ac_b_ex.fe_logical;
 	pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
 	pa->pa_len = ac->ac_b_ex.fe_len;
 	pa->pa_free = pa->pa_len;
 	spin_lock_init(&pa->pa_lock);
-	INIT_LIST_HEAD(&pa->pa_inode_list);
 	INIT_LIST_HEAD(&pa->pa_group_list);
 	pa->pa_deleted = 0;
 	pa->pa_type = MB_INODE_PA;
@@ -4667,20 +4864,20 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 		 pa->pa_len, pa->pa_lstart);
 	trace_ext4_mb_new_inode_pa(ac, pa);
 
-	ext4_mb_use_inode_pa(ac, pa);
 	atomic_add(pa->pa_free, &sbi->s_mb_preallocated);
+	ext4_mb_use_inode_pa(ac, pa);
 
 	ei = EXT4_I(ac->ac_inode);
 	grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group);
 
-	pa->pa_obj_lock = &ei->i_prealloc_lock;
+	pa->pa_node_lock.inode_lock = &ei->i_prealloc_lock;
 	pa->pa_inode = ac->ac_inode;
 
 	list_add(&pa->pa_group_list, &grp->bb_prealloc_list);
 
-	spin_lock(pa->pa_obj_lock);
-	list_add_rcu(&pa->pa_inode_list, &ei->i_prealloc_list);
-	spin_unlock(pa->pa_obj_lock);
+	write_lock(pa->pa_node_lock.inode_lock);
+	ext4_mb_pa_rb_insert(&ei->i_prealloc_node, &pa->pa_node.inode_node);
+	write_unlock(pa->pa_node_lock.inode_lock);
 	atomic_inc(&ei->i_prealloc_active);
 }
 
@@ -4703,16 +4900,12 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
 
 	pa = ac->ac_pa;
 
-	/* preallocation can change ac_b_ex, thus we store actually
-	 * allocated blocks for history */
-	ac->ac_f_ex = ac->ac_b_ex;
-
 	pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
 	pa->pa_lstart = pa->pa_pstart;
 	pa->pa_len = ac->ac_b_ex.fe_len;
 	pa->pa_free = pa->pa_len;
 	spin_lock_init(&pa->pa_lock);
-	INIT_LIST_HEAD(&pa->pa_inode_list);
+	INIT_LIST_HEAD(&pa->pa_node.lg_list);
 	INIT_LIST_HEAD(&pa->pa_group_list);
 	pa->pa_deleted = 0;
 	pa->pa_type = MB_GROUP_PA;
@@ -4728,7 +4921,7 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
 	lg = ac->ac_lg;
 	BUG_ON(lg == NULL);
 
-	pa->pa_obj_lock = &lg->lg_prealloc_lock;
+	pa->pa_node_lock.lg_lock = &lg->lg_prealloc_lock;
 	pa->pa_inode = NULL;
 
 	list_add(&pa->pa_group_list, &grp->bb_prealloc_list);
@@ -4846,6 +5039,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
 	struct ext4_prealloc_space *pa, *tmp;
 	struct list_head list;
 	struct ext4_buddy e4b;
+	struct ext4_inode_info *ei;
 	int err;
 	int free = 0;
 
@@ -4904,17 +5098,26 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
 	list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) {
 
 		/* remove from object (inode or locality group) */
-		spin_lock(pa->pa_obj_lock);
-		list_del_rcu(&pa->pa_inode_list);
-		spin_unlock(pa->pa_obj_lock);
+		if (pa->pa_type == MB_GROUP_PA) {
+			spin_lock(pa->pa_node_lock.lg_lock);
+			list_del_rcu(&pa->pa_node.lg_list);
+			spin_unlock(pa->pa_node_lock.lg_lock);
+		} else {
+			write_lock(pa->pa_node_lock.inode_lock);
+			ei = EXT4_I(pa->pa_inode);
+			rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node);
+			write_unlock(pa->pa_node_lock.inode_lock);
+		}
 
-		if (pa->pa_type == MB_GROUP_PA)
+		list_del(&pa->u.pa_tmp_list);
+
+		if (pa->pa_type == MB_GROUP_PA) {
 			ext4_mb_release_group_pa(&e4b, pa);
-		else
+			call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
+		} else {
 			ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa);
-
-		list_del(&pa->u.pa_tmp_list);
-		call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
+			ext4_mb_pa_free(pa);
+		}
 	}
 
 	ext4_unlock_group(sb, group);
@@ -4944,10 +5147,10 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 	ext4_group_t group = 0;
 	struct list_head list;
 	struct ext4_buddy e4b;
+	struct rb_node *iter;
 	int err;
 
 	if (!S_ISREG(inode->i_mode)) {
-		/*BUG_ON(!list_empty(&ei->i_prealloc_list));*/
 		return;
 	}
 
@@ -4966,17 +5169,19 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 
 repeat:
 	/* first, collect all pa's in the inode */
-	spin_lock(&ei->i_prealloc_lock);
-	while (!list_empty(&ei->i_prealloc_list) && needed) {
-		pa = list_entry(ei->i_prealloc_list.prev,
-				struct ext4_prealloc_space, pa_inode_list);
-		BUG_ON(pa->pa_obj_lock != &ei->i_prealloc_lock);
+	write_lock(&ei->i_prealloc_lock);
+	for (iter = rb_first(&ei->i_prealloc_node); iter && needed;
+	     iter = rb_next(iter)) {
+		pa = rb_entry(iter, struct ext4_prealloc_space,
+			      pa_node.inode_node);
+		BUG_ON(pa->pa_node_lock.inode_lock != &ei->i_prealloc_lock);
+
 		spin_lock(&pa->pa_lock);
 		if (atomic_read(&pa->pa_count)) {
 			/* this shouldn't happen often - nobody should
 			 * use preallocation while we're discarding it */
 			spin_unlock(&pa->pa_lock);
-			spin_unlock(&ei->i_prealloc_lock);
+			write_unlock(&ei->i_prealloc_lock);
 			ext4_msg(sb, KERN_ERR,
 				 "uh-oh! used pa while discarding");
 			WARN_ON(1);
@@ -4987,7 +5192,7 @@ repeat:
 		if (pa->pa_deleted == 0) {
 			ext4_mb_mark_pa_deleted(sb, pa);
 			spin_unlock(&pa->pa_lock);
-			list_del_rcu(&pa->pa_inode_list);
+			rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node);
 			list_add(&pa->u.pa_tmp_list, &list);
 			needed--;
 			continue;
@@ -4995,7 +5200,7 @@ repeat:
 
 		/* someone is deleting pa right now */
 		spin_unlock(&pa->pa_lock);
-		spin_unlock(&ei->i_prealloc_lock);
+		write_unlock(&ei->i_prealloc_lock);
 
 		/* we have to wait here because pa_deleted
 		 * doesn't mean pa is already unlinked from
@@ -5012,7 +5217,7 @@ repeat:
 		schedule_timeout_uninterruptible(HZ);
 		goto repeat;
 	}
-	spin_unlock(&ei->i_prealloc_lock);
+	write_unlock(&ei->i_prealloc_lock);
 
 	list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) {
 		BUG_ON(pa->pa_type != MB_INODE_PA);
@@ -5044,7 +5249,7 @@ repeat:
 		put_bh(bitmap_bh);
 
 		list_del(&pa->u.pa_tmp_list);
-		call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
+		ext4_mb_pa_free(pa);
 	}
 }
 
@@ -5061,14 +5266,20 @@ static int ext4_mb_pa_alloc(struct ext4_allocation_context *ac)
 	return 0;
 }
 
-static void ext4_mb_pa_free(struct ext4_allocation_context *ac)
+static void ext4_mb_pa_put_free(struct ext4_allocation_context *ac)
 {
 	struct ext4_prealloc_space *pa = ac->ac_pa;
 
 	BUG_ON(!pa);
 	ac->ac_pa = NULL;
 	WARN_ON(!atomic_dec_and_test(&pa->pa_count));
-	kmem_cache_free(ext4_pspace_cachep, pa);
+	/*
+	 * current function is only called due to an error or due to
+	 * len of found blocks < len of requested blocks hence the PA has not
+	 * been added to grp->bb_prealloc_list. So we don't need to lock it
+	 */
+	pa->pa_deleted = 1;
+	ext4_mb_pa_free(pa);
 }
 
 #ifdef CONFIG_EXT4_DEBUG
@@ -5271,7 +5482,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
 
 	spin_lock(&lg->lg_prealloc_lock);
 	list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order],
-				pa_inode_list,
+				pa_node.lg_list,
 				lockdep_is_held(&lg->lg_prealloc_lock)) {
 		spin_lock(&pa->pa_lock);
 		if (atomic_read(&pa->pa_count)) {
@@ -5294,7 +5505,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
 		ext4_mb_mark_pa_deleted(sb, pa);
 		spin_unlock(&pa->pa_lock);
 
-		list_del_rcu(&pa->pa_inode_list);
+		list_del_rcu(&pa->pa_node.lg_list);
 		list_add(&pa->u.pa_tmp_list, &discard_list);
 
 		total_entries--;
@@ -5355,7 +5566,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 	/* Add the prealloc space to lg */
 	spin_lock(&lg->lg_prealloc_lock);
 	list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order],
-				pa_inode_list,
+				pa_node.lg_list,
 				lockdep_is_held(&lg->lg_prealloc_lock)) {
 		spin_lock(&tmp_pa->pa_lock);
 		if (tmp_pa->pa_deleted) {
@@ -5364,8 +5575,8 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 		}
 		if (!added && pa->pa_free < tmp_pa->pa_free) {
 			/* Add to the tail of the previous entry */
-			list_add_tail_rcu(&pa->pa_inode_list,
-						&tmp_pa->pa_inode_list);
+			list_add_tail_rcu(&pa->pa_node.lg_list,
+						&tmp_pa->pa_node.lg_list);
 			added = 1;
 			/*
 			 * we want to count the total
@@ -5376,7 +5587,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 		lg_prealloc_count++;
 	}
 	if (!added)
-		list_add_tail_rcu(&pa->pa_inode_list,
+		list_add_tail_rcu(&pa->pa_node.lg_list,
 					&lg->lg_prealloc_list[order]);
 	spin_unlock(&lg->lg_prealloc_lock);
 
@@ -5390,29 +5601,10 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 }
 
 /*
- * if per-inode prealloc list is too long, trim some PA
- */
-static void ext4_mb_trim_inode_pa(struct inode *inode)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	int count, delta;
-
-	count = atomic_read(&ei->i_prealloc_active);
-	delta = (sbi->s_mb_max_inode_prealloc >> 2) + 1;
-	if (count > sbi->s_mb_max_inode_prealloc + delta) {
-		count -= sbi->s_mb_max_inode_prealloc;
-		ext4_discard_preallocations(inode, count);
-	}
-}
-
-/*
  * release all resource we used in allocation
  */
 static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 {
-	struct inode *inode = ac->ac_inode;
-	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_prealloc_space *pa = ac->ac_pa;
 	if (pa) {
@@ -5432,23 +5624,13 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 			 * doesn't grow big.
 			 */
 			if (likely(pa->pa_free)) {
-				spin_lock(pa->pa_obj_lock);
-				list_del_rcu(&pa->pa_inode_list);
-				spin_unlock(pa->pa_obj_lock);
+				spin_lock(pa->pa_node_lock.lg_lock);
+				list_del_rcu(&pa->pa_node.lg_list);
+				spin_unlock(pa->pa_node_lock.lg_lock);
 				ext4_mb_add_n_trim(ac);
 			}
 		}
 
-		if (pa->pa_type == MB_INODE_PA) {
-			/*
-			 * treat per-inode prealloc list as a lru list, then try
-			 * to trim the least recently used PA.
-			 */
-			spin_lock(pa->pa_obj_lock);
-			list_move(&pa->pa_inode_list, &ei->i_prealloc_list);
-			spin_unlock(pa->pa_obj_lock);
-		}
-
 		ext4_mb_put_pa(ac, ac->ac_sb, pa);
 	}
 	if (ac->ac_bitmap_page)
@@ -5458,7 +5640,6 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
 		mutex_unlock(&ac->ac_lg->lg_mutex);
 	ext4_mb_collect_stats(ac);
-	ext4_mb_trim_inode_pa(inode);
 	return 0;
 }
 
@@ -5611,13 +5792,13 @@ repeat:
 		 * So we have to free this pa here itself.
 		 */
 		if (*errp) {
-			ext4_mb_pa_free(ac);
+			ext4_mb_pa_put_free(ac);
 			ext4_discard_allocated_blocks(ac);
 			goto errout;
 		}
 		if (ac->ac_status == AC_STATUS_FOUND &&
 			ac->ac_o_ex.fe_len >= ac->ac_f_ex.fe_len)
-			ext4_mb_pa_free(ac);
+			ext4_mb_pa_put_free(ac);
 	}
 	if (likely(ac->ac_status == AC_STATUS_FOUND)) {
 		*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
@@ -5636,20 +5817,19 @@ repeat:
 		 * If block allocation fails then the pa allocated above
 		 * needs to be freed here itself.
 		 */
-		ext4_mb_pa_free(ac);
+		ext4_mb_pa_put_free(ac);
 		*errp = -ENOSPC;
 	}
 
-errout:
 	if (*errp) {
+errout:
 		ac->ac_b_ex.fe_len = 0;
 		ar->len = 0;
 		ext4_mb_show_ac(ac);
 	}
 	ext4_mb_release_context(ac);
+	kmem_cache_free(ext4_ac_cachep, ac);
 out:
-	if (ac)
-		kmem_cache_free(ext4_ac_cachep, ac);
 	if (inquota && ar->len < inquota)
 		dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len));
 	if (!ar->len) {
@@ -5693,7 +5873,7 @@ static void ext4_try_merge_freed_extent(struct ext4_sb_info *sbi,
 	kmem_cache_free(ext4_free_data_cachep, entry);
 }
 
-static noinline_for_stack int
+static noinline_for_stack void
 ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 		      struct ext4_free_data *new_entry)
 {
@@ -5736,7 +5916,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 				EXT4_C2B(sbi, cluster),
 				"Block already on to-be-freed list");
 			kmem_cache_free(ext4_free_data_cachep, new_entry);
-			return 0;
+			return;
 		}
 	}
 
@@ -5762,7 +5942,6 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list);
 	sbi->s_mb_free_pending += clusters;
 	spin_unlock(&sbi->s_md_lock);
-	return 0;
 }
 
 /*
@@ -5797,9 +5976,6 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
 			return 0;
 		}
 
-		ext4_get_group_no_and_offset(sb,
-			max(ext4_group_first_block_no(sb, group), goal),
-			NULL, &blkoff);
 		while (1) {
 			i = mb_find_next_zero_bit(bitmap_bh->b_data, max,
 						blkoff);
@@ -5814,6 +5990,8 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
 		brelse(bitmap_bh);
 		if (i < max)
 			break;
+
+		blkoff = 0;
 	}
 
 	if (group >= ext4_get_groups_count(sb) || i >= max) {
@@ -5842,13 +6020,12 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
 	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
 	bitmap_bh = ext4_read_block_bitmap(sb, group);
 	if (IS_ERR(bitmap_bh)) {
-		err = PTR_ERR(bitmap_bh);
 		pr_warn("Failed to read block bitmap\n");
 		return;
 	}
 	gdp = ext4_get_group_desc(sb, group, &gdp_bh);
 	if (!gdp)
-		return;
+		goto err_out;
 
 	for (i = 0; i < count; i++) {
 		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data))
@@ -5857,15 +6034,17 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
 	mb_clear_bits(bitmap_bh->b_data, blkoff, count);
 	err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
 	if (err)
-		return;
+		goto err_out;
 	ext4_free_group_clusters_set(
 		sb, gdp, ext4_free_group_clusters(sb, gdp) +
 		count - already_freed);
-	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+	ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh);
 	ext4_group_desc_csum_set(sb, group, gdp);
 	ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
 	sync_dirty_buffer(bitmap_bh);
 	sync_dirty_buffer(gdp_bh);
+
+err_out:
 	brelse(bitmap_bh);
 }
 
@@ -6023,7 +6202,7 @@ do_more:
 
 	ret = ext4_free_group_clusters(sb, gdp) + count_clusters;
 	ext4_free_group_clusters_set(sb, gdp, ret);
-	ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh);
+	ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh);
 	ext4_group_desc_csum_set(sb, block_group, gdp);
 	ext4_unlock_group(sb, block_group);
 
@@ -6280,7 +6459,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 	free_clusters_count = clusters_freed +
 		ext4_free_group_clusters(sb, desc);
 	ext4_free_group_clusters_set(sb, desc, free_clusters_count);
-	ext4_block_bitmap_csum_set(sb, block_group, desc, bitmap_bh);
+	ext4_block_bitmap_csum_set(sb, desc, bitmap_bh);
 	ext4_group_desc_csum_set(sb, block_group, desc);
 	ext4_unlock_group(sb, block_group);
 	percpu_counter_add(&sbi->s_freeclusters_counter,
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index dcda2a943cee..6d85ee8674a6 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -74,11 +74,6 @@
 #define MB_DEFAULT_GROUP_PREALLOC	512
 
 /*
- * maximum length of inode prealloc list
- */
-#define MB_DEFAULT_MAX_INODE_PREALLOC	512
-
-/*
  * Number of groups to search linearly before performing group scanning
  * optimization.
  */
@@ -114,7 +109,10 @@ struct ext4_free_data {
 };
 
 struct ext4_prealloc_space {
-	struct list_head	pa_inode_list;
+	union {
+		struct rb_node	inode_node;		/* for inode PA rbtree */
+		struct list_head	lg_list;	/* for lg PAs */
+	} pa_node;
 	struct list_head	pa_group_list;
 	union {
 		struct list_head pa_tmp_list;
@@ -128,8 +126,11 @@ struct ext4_prealloc_space {
 	ext4_grpblk_t		pa_len;		/* len of preallocated chunk */
 	ext4_grpblk_t		pa_free;	/* how many blocks are free */
 	unsigned short		pa_type;	/* pa type. inode or group */
-	spinlock_t		*pa_obj_lock;
-	struct inode		*pa_inode;	/* hack, for history only */
+	union {
+		rwlock_t		*inode_lock;	/* locks the rbtree holding this PA */
+		spinlock_t		*lg_lock;	/* locks the lg list holding this PA */
+	} pa_node_lock;
+	struct inode		*pa_inode;	/* used to get the inode during group discard */
 };
 
 enum {
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 2de9829aed63..e509c22a21ed 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -126,7 +126,6 @@ mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
 {
 	struct address_space *mapping[2];
 	unsigned int flags;
-	unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
 
 	BUG_ON(!inode1 || !inode2);
 	if (inode1 < inode2) {
@@ -139,14 +138,14 @@ mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
 	}
 
 	flags = memalloc_nofs_save();
-	folio[0] = __filemap_get_folio(mapping[0], index1, fgp_flags,
+	folio[0] = __filemap_get_folio(mapping[0], index1, FGP_WRITEBEGIN,
 			mapping_gfp_mask(mapping[0]));
 	if (!folio[0]) {
 		memalloc_nofs_restore(flags);
 		return -ENOMEM;
 	}
 
-	folio[1] = __filemap_get_folio(mapping[1], index2, fgp_flags,
+	folio[1] = __filemap_get_folio(mapping[1], index2, FGP_WRITEBEGIN,
 			mapping_gfp_mask(mapping[1]));
 	memalloc_nofs_restore(flags);
 	if (!folio[1]) {
@@ -169,25 +168,27 @@ mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
 
 /* Force page buffers uptodate w/o dropping page's lock */
 static int
-mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
+mext_page_mkuptodate(struct folio *folio, unsigned from, unsigned to)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	sector_t block;
 	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
 	unsigned int blocksize, block_start, block_end;
 	int i, err,  nr = 0, partial = 0;
-	BUG_ON(!PageLocked(page));
-	BUG_ON(PageWriteback(page));
+	BUG_ON(!folio_test_locked(folio));
+	BUG_ON(folio_test_writeback(folio));
 
-	if (PageUptodate(page))
+	if (folio_test_uptodate(folio))
 		return 0;
 
 	blocksize = i_blocksize(inode);
-	if (!page_has_buffers(page))
-		create_empty_buffers(page, blocksize, 0);
+	head = folio_buffers(folio);
+	if (!head) {
+		create_empty_buffers(&folio->page, blocksize, 0);
+		head = folio_buffers(folio);
+	}
 
-	head = page_buffers(page);
-	block = (sector_t)page->index << (PAGE_SHIFT - inode->i_blkbits);
+	block = (sector_t)folio->index << (PAGE_SHIFT - inode->i_blkbits);
 	for (bh = head, block_start = 0; bh != head || !block_start;
 	     block++, block_start = block_end, bh = bh->b_this_page) {
 		block_end = block_start + blocksize;
@@ -201,11 +202,11 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
 		if (!buffer_mapped(bh)) {
 			err = ext4_get_block(inode, block, bh, 0);
 			if (err) {
-				SetPageError(page);
+				folio_set_error(folio);
 				return err;
 			}
 			if (!buffer_mapped(bh)) {
-				zero_user(page, block_start, blocksize);
+				folio_zero_range(folio, block_start, blocksize);
 				set_buffer_uptodate(bh);
 				continue;
 			}
@@ -227,7 +228,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
 	}
 out:
 	if (!partial)
-		SetPageUptodate(page);
+		folio_mark_uptodate(folio);
 	return 0;
 }
 
@@ -355,7 +356,7 @@ again:
 		goto unlock_folios;
 	}
 data_copy:
-	*err = mext_page_mkuptodate(&folio[0]->page, from, from + replaced_size);
+	*err = mext_page_mkuptodate(folio[0], from, from + replaced_size);
 	if (*err)
 		goto unlock_folios;
 
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 1e4db96a04e6..3621f29ec671 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -99,30 +99,30 @@ static void buffer_io_error(struct buffer_head *bh)
 
 static void ext4_finish_bio(struct bio *bio)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct folio_iter fi;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
-		struct page *bounce_page = NULL;
+	bio_for_each_folio_all(fi, bio) {
+		struct folio *folio = fi.folio;
+		struct folio *io_folio = NULL;
 		struct buffer_head *bh, *head;
-		unsigned bio_start = bvec->bv_offset;
-		unsigned bio_end = bio_start + bvec->bv_len;
+		size_t bio_start = fi.offset;
+		size_t bio_end = bio_start + fi.length;
 		unsigned under_io = 0;
 		unsigned long flags;
 
-		if (fscrypt_is_bounce_page(page)) {
-			bounce_page = page;
-			page = fscrypt_pagecache_page(bounce_page);
+		if (fscrypt_is_bounce_folio(folio)) {
+			io_folio = folio;
+			folio = fscrypt_pagecache_folio(folio);
 		}
 
 		if (bio->bi_status) {
-			SetPageError(page);
-			mapping_set_error(page->mapping, -EIO);
+			int err = blk_status_to_errno(bio->bi_status);
+			folio_set_error(folio);
+			mapping_set_error(folio->mapping, err);
 		}
-		bh = head = page_buffers(page);
+		bh = head = folio_buffers(folio);
 		/*
-		 * We check all buffers in the page under b_uptodate_lock
+		 * We check all buffers in the folio under b_uptodate_lock
 		 * to avoid races with other end io clearing async_write flags
 		 */
 		spin_lock_irqsave(&head->b_uptodate_lock, flags);
@@ -141,8 +141,8 @@ static void ext4_finish_bio(struct bio *bio)
 		} while ((bh = bh->b_this_page) != head);
 		spin_unlock_irqrestore(&head->b_uptodate_lock, flags);
 		if (!under_io) {
-			fscrypt_free_bounce_page(bounce_page);
-			end_page_writeback(page);
+			fscrypt_free_bounce_page(&io_folio->page);
+			folio_end_writeback(folio);
 		}
 	}
 }
@@ -409,12 +409,10 @@ static void io_submit_init_bio(struct ext4_io_submit *io,
 
 static void io_submit_add_bh(struct ext4_io_submit *io,
 			     struct inode *inode,
-			     struct page *pagecache_page,
-			     struct page *bounce_page,
+			     struct folio *folio,
+			     struct folio *io_folio,
 			     struct buffer_head *bh)
 {
-	int ret;
-
 	if (io->io_bio && (bh->b_blocknr != io->io_next_block ||
 			   !fscrypt_mergeable_bio_bh(io->io_bio, bh))) {
 submit_and_retry:
@@ -422,20 +420,17 @@ submit_and_retry:
 	}
 	if (io->io_bio == NULL)
 		io_submit_init_bio(io, bh);
-	ret = bio_add_page(io->io_bio, bounce_page ?: pagecache_page,
-			   bh->b_size, bh_offset(bh));
-	if (ret != bh->b_size)
+	if (!bio_add_folio(io->io_bio, io_folio, bh->b_size, bh_offset(bh)))
 		goto submit_and_retry;
-	wbc_account_cgroup_owner(io->io_wbc, pagecache_page, bh->b_size);
+	wbc_account_cgroup_owner(io->io_wbc, &folio->page, bh->b_size);
 	io->io_next_block++;
 }
 
-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 *folio,
+		size_t len)
 {
-	struct page *bounce_page = NULL;
-	struct inode *inode = page->mapping->host;
+	struct folio *io_folio = folio;
+	struct inode *inode = folio->mapping->host;
 	unsigned block_start;
 	struct buffer_head *bh, *head;
 	int ret = 0;
@@ -443,30 +438,30 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	struct writeback_control *wbc = io->io_wbc;
 	bool keep_towrite = false;
 
-	BUG_ON(!PageLocked(page));
-	BUG_ON(PageWriteback(page));
+	BUG_ON(!folio_test_locked(folio));
+	BUG_ON(folio_test_writeback(folio));
 
-	ClearPageError(page);
+	folio_clear_error(folio);
 
 	/*
 	 * Comments copied from block_write_full_page:
 	 *
-	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * The folio straddles i_size.  It must be zeroed out on each and every
 	 * writepage invocation because it may be mmapped.  "A file is mapped
 	 * in multiples of the page size.  For a file that is not a multiple of
 	 * the page size, the remaining memory is zeroed when mapped, and
 	 * writes to that region are not written out to the file."
 	 */
-	if (len < PAGE_SIZE)
-		zero_user_segment(page, len, PAGE_SIZE);
+	if (len < folio_size(folio))
+		folio_zero_segment(folio, len, folio_size(folio));
 	/*
 	 * In the first loop we prepare and mark buffers to submit. We have to
-	 * mark all buffers in the page before submitting so that
-	 * end_page_writeback() cannot be called from ext4_end_bio() when IO
+	 * mark all buffers in the folio before submitting so that
+	 * folio_end_writeback() cannot be called from ext4_end_bio() when IO
 	 * on the first buffer finishes and we are still working on submitting
 	 * the second buffer.
 	 */
-	bh = head = page_buffers(page);
+	bh = head = folio_buffers(folio);
 	do {
 		block_start = bh_offset(bh);
 		if (block_start >= len) {
@@ -481,14 +476,16 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 				clear_buffer_dirty(bh);
 			/*
 			 * Keeping dirty some buffer we cannot write? Make sure
-			 * to redirty the page and keep TOWRITE tag so that
-			 * racing WB_SYNC_ALL writeback does not skip the page.
+			 * to redirty the folio and keep TOWRITE tag so that
+			 * racing WB_SYNC_ALL writeback does not skip the folio.
 			 * This happens e.g. when doing writeout for
-			 * transaction commit.
+			 * transaction commit or when journalled data is not
+			 * yet committed.
 			 */
-			if (buffer_dirty(bh)) {
-				if (!PageDirty(page))
-					redirty_page_for_writepage(wbc, page);
+			if (buffer_dirty(bh) ||
+			    (buffer_jbd(bh) && buffer_jbddirty(bh))) {
+				if (!folio_test_dirty(folio))
+					folio_redirty_for_writepage(wbc, folio);
 				keep_towrite = true;
 			}
 			continue;
@@ -500,11 +497,11 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 		nr_to_submit++;
 	} while ((bh = bh->b_this_page) != head);
 
-	/* Nothing to submit? Just unlock the page... */
+	/* Nothing to submit? Just unlock the folio... */
 	if (!nr_to_submit)
-		goto unlock;
+		return 0;
 
-	bh = head = page_buffers(page);
+	bh = head = folio_buffers(folio);
 
 	/*
 	 * If any blocks are being written to an encrypted file, encrypt them
@@ -513,9 +510,10 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	 * (e.g. holes) to be unnecessarily encrypted, but this is rare and
 	 * can't happen in the common case of blocksize == PAGE_SIZE.
 	 */
-	if (fscrypt_inode_uses_fs_layer_crypto(inode) && nr_to_submit) {
+	if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
 		gfp_t gfp_flags = GFP_NOFS;
 		unsigned int enc_bytes = round_up(len, i_blocksize(inode));
+		struct page *bounce_page;
 
 		/*
 		 * Since bounce page allocation uses a mempool, we can only use
@@ -525,8 +523,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 		if (io->io_bio)
 			gfp_flags = GFP_NOWAIT | __GFP_NOWARN;
 	retry_encrypt:
-		bounce_page = fscrypt_encrypt_pagecache_blocks(page, enc_bytes,
-							       0, gfp_flags);
+		bounce_page = fscrypt_encrypt_pagecache_blocks(&folio->page,
+					enc_bytes, 0, gfp_flags);
 		if (IS_ERR(bounce_page)) {
 			ret = PTR_ERR(bounce_page);
 			if (ret == -ENOMEM &&
@@ -542,7 +540,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 			}
 
 			printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret);
-			redirty_page_for_writepage(wbc, page);
+			folio_redirty_for_writepage(wbc, folio);
 			do {
 				if (buffer_async_write(bh)) {
 					clear_buffer_async_write(bh);
@@ -550,22 +548,20 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 				}
 				bh = bh->b_this_page;
 			} while (bh != head);
-			goto unlock;
+
+			return ret;
 		}
+		io_folio = page_folio(bounce_page);
 	}
 
-	if (keep_towrite)
-		set_page_writeback_keepwrite(page);
-	else
-		set_page_writeback(page);
+	__folio_start_writeback(folio, keep_towrite);
 
 	/* Now submit buffers to write */
 	do {
 		if (!buffer_async_write(bh))
 			continue;
-		io_submit_add_bh(io, inode, page, bounce_page, bh);
+		io_submit_add_bh(io, inode, folio, io_folio, bh);
 	} while ((bh = bh->b_this_page) != head);
-unlock:
-	unlock_page(page);
-	return ret;
+
+	return 0;
 }
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index c61dc8a7c014..6f46823fba61 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -68,18 +68,16 @@ struct bio_post_read_ctx {
 
 static void __read_end_io(struct bio *bio)
 {
-	struct page *page;
-	struct bio_vec *bv;
-	struct bvec_iter_all iter_all;
+	struct folio_iter fi;
 
-	bio_for_each_segment_all(bv, bio, iter_all) {
-		page = bv->bv_page;
+	bio_for_each_folio_all(fi, bio) {
+		struct folio *folio = fi.folio;
 
 		if (bio->bi_status)
-			ClearPageUptodate(page);
+			folio_clear_uptodate(folio);
 		else
-			SetPageUptodate(page);
-		unlock_page(page);
+			folio_mark_uptodate(folio);
+		folio_unlock(folio);
 	}
 	if (bio->bi_private)
 		mempool_free(bio->bi_private, bio_post_read_ctx_pool);
@@ -218,7 +216,7 @@ static inline loff_t ext4_readpage_limit(struct inode *inode)
 }
 
 int ext4_mpage_readpages(struct inode *inode,
-		struct readahead_control *rac, struct page *page)
+		struct readahead_control *rac, struct folio *folio)
 {
 	struct bio *bio = NULL;
 	sector_t last_block_in_bio = 0;
@@ -247,16 +245,15 @@ int ext4_mpage_readpages(struct inode *inode,
 		int fully_mapped = 1;
 		unsigned first_hole = blocks_per_page;
 
-		if (rac) {
-			page = readahead_page(rac);
-			prefetchw(&page->flags);
-		}
+		if (rac)
+			folio = readahead_folio(rac);
+		prefetchw(&folio->flags);
 
-		if (page_has_buffers(page))
+		if (folio_buffers(folio))
 			goto confused;
 
 		block_in_file = next_block =
-			(sector_t)page->index << (PAGE_SHIFT - blkbits);
+			(sector_t)folio->index << (PAGE_SHIFT - blkbits);
 		last_block = block_in_file + nr_pages * blocks_per_page;
 		last_block_in_file = (ext4_readpage_limit(inode) +
 				      blocksize - 1) >> blkbits;
@@ -290,7 +287,7 @@ int ext4_mpage_readpages(struct inode *inode,
 
 		/*
 		 * Then do more ext4_map_blocks() calls until we are
-		 * done with this page.
+		 * done with this folio.
 		 */
 		while (page_block < blocks_per_page) {
 			if (block_in_file < last_block) {
@@ -299,10 +296,10 @@ int ext4_mpage_readpages(struct inode *inode,
 
 				if (ext4_map_blocks(NULL, inode, &map, 0) < 0) {
 				set_error_page:
-					SetPageError(page);
-					zero_user_segment(page, 0,
-							  PAGE_SIZE);
-					unlock_page(page);
+					folio_set_error(folio);
+					folio_zero_segment(folio, 0,
+							  folio_size(folio));
+					folio_unlock(folio);
 					goto next_page;
 				}
 			}
@@ -333,22 +330,22 @@ int ext4_mpage_readpages(struct inode *inode,
 			}
 		}
 		if (first_hole != blocks_per_page) {
-			zero_user_segment(page, first_hole << blkbits,
-					  PAGE_SIZE);
+			folio_zero_segment(folio, first_hole << blkbits,
+					  folio_size(folio));
 			if (first_hole == 0) {
-				if (ext4_need_verity(inode, page->index) &&
-				    !fsverity_verify_page(page))
+				if (ext4_need_verity(inode, folio->index) &&
+				    !fsverity_verify_page(&folio->page))
 					goto set_error_page;
-				SetPageUptodate(page);
-				unlock_page(page);
-				goto next_page;
+				folio_mark_uptodate(folio);
+				folio_unlock(folio);
+				continue;
 			}
 		} else if (fully_mapped) {
-			SetPageMappedToDisk(page);
+			folio_set_mappedtodisk(folio);
 		}
 
 		/*
-		 * This page will go to BIO.  Do we need to send this
+		 * This folio will go to BIO.  Do we need to send this
 		 * BIO off first?
 		 */
 		if (bio && (last_block_in_bio != blocks[0] - 1 ||
@@ -366,7 +363,7 @@ int ext4_mpage_readpages(struct inode *inode,
 					REQ_OP_READ, GFP_KERNEL);
 			fscrypt_set_bio_crypt_ctx(bio, inode, next_block,
 						  GFP_KERNEL);
-			ext4_set_bio_post_read_ctx(bio, inode, page->index);
+			ext4_set_bio_post_read_ctx(bio, inode, folio->index);
 			bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
 			bio->bi_end_io = mpage_end_io;
 			if (rac)
@@ -374,7 +371,7 @@ int ext4_mpage_readpages(struct inode *inode,
 		}
 
 		length = first_hole << blkbits;
-		if (bio_add_page(bio, page, length, 0) < length)
+		if (!bio_add_folio(bio, folio, length, 0))
 			goto submit_and_realloc;
 
 		if (((map.m_flags & EXT4_MAP_BOUNDARY) &&
@@ -384,19 +381,18 @@ int ext4_mpage_readpages(struct inode *inode,
 			bio = NULL;
 		} else
 			last_block_in_bio = blocks[blocks_per_page - 1];
-		goto next_page;
+		continue;
 	confused:
 		if (bio) {
 			submit_bio(bio);
 			bio = NULL;
 		}
-		if (!PageUptodate(page))
-			block_read_full_folio(page_folio(page), ext4_get_block);
+		if (!folio_test_uptodate(folio))
+			block_read_full_folio(folio, ext4_get_block);
 		else
-			unlock_page(page);
-	next_page:
-		if (rac)
-			put_page(page);
+			folio_unlock(folio);
+next_page:
+		; /* A label shall be followed by a statement until C23 */
 	}
 	if (bio)
 		submit_bio(bio);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 6b91443d6bf3..0361c20910de 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1306,7 +1306,6 @@ static struct buffer_head *ext4_get_bitmap(struct super_block *sb, __u64 block)
 }
 
 static int ext4_set_bitmap_checksums(struct super_block *sb,
-				     ext4_group_t group,
 				     struct ext4_group_desc *gdp,
 				     struct ext4_new_group_data *group_data)
 {
@@ -1318,14 +1317,14 @@ 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, group, 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);
 	if (!bh)
 		return -EIO;
-	ext4_block_bitmap_csum_set(sb, group, gdp, bh);
+	ext4_block_bitmap_csum_set(sb, gdp, bh);
 	brelse(bh);
 
 	return 0;
@@ -1363,7 +1362,7 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb,
 		memset(gdp, 0, EXT4_DESC_SIZE(sb));
 		ext4_block_bitmap_set(sb, gdp, group_data->block_bitmap);
 		ext4_inode_bitmap_set(sb, gdp, group_data->inode_bitmap);
-		err = ext4_set_bitmap_checksums(sb, group, gdp, group_data);
+		err = ext4_set_bitmap_checksums(sb, gdp, group_data);
 		if (err) {
 			ext4_std_error(sb, err);
 			break;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 76d1ef0efbf4..d03bf0ecf505 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1183,12 +1183,81 @@ static inline void ext4_quota_off_umount(struct super_block *sb)
 }
 #endif
 
+static int ext4_percpu_param_init(struct ext4_sb_info *sbi)
+{
+	ext4_fsblk_t block;
+	int err;
+
+	block = ext4_count_free_clusters(sbi->s_sb);
+	ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block));
+	err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
+				  GFP_KERNEL);
+	if (!err) {
+		unsigned long freei = ext4_count_free_inodes(sbi->s_sb);
+		sbi->s_es->s_free_inodes_count = cpu_to_le32(freei);
+		err = percpu_counter_init(&sbi->s_freeinodes_counter, freei,
+					  GFP_KERNEL);
+	}
+	if (!err)
+		err = percpu_counter_init(&sbi->s_dirs_counter,
+					  ext4_count_dirs(sbi->s_sb), GFP_KERNEL);
+	if (!err)
+		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
+					  GFP_KERNEL);
+	if (!err)
+		err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0,
+					  GFP_KERNEL);
+	if (!err)
+		err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
+
+	if (err)
+		ext4_msg(sbi->s_sb, KERN_ERR, "insufficient memory");
+
+	return err;
+}
+
+static void ext4_percpu_param_destroy(struct ext4_sb_info *sbi)
+{
+	percpu_counter_destroy(&sbi->s_freeclusters_counter);
+	percpu_counter_destroy(&sbi->s_freeinodes_counter);
+	percpu_counter_destroy(&sbi->s_dirs_counter);
+	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
+	percpu_free_rwsem(&sbi->s_writepages_rwsem);
+}
+
+static void ext4_group_desc_free(struct ext4_sb_info *sbi)
+{
+	struct buffer_head **group_desc;
+	int i;
+
+	rcu_read_lock();
+	group_desc = rcu_dereference(sbi->s_group_desc);
+	for (i = 0; i < sbi->s_gdb_count; i++)
+		brelse(group_desc[i]);
+	kvfree(group_desc);
+	rcu_read_unlock();
+}
+
+static void ext4_flex_groups_free(struct ext4_sb_info *sbi)
+{
+	struct flex_groups **flex_groups;
+	int i;
+
+	rcu_read_lock();
+	flex_groups = rcu_dereference(sbi->s_flex_groups);
+	if (flex_groups) {
+		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
+			kvfree(flex_groups[i]);
+		kvfree(flex_groups);
+	}
+	rcu_read_unlock();
+}
+
 static void ext4_put_super(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
-	struct buffer_head **group_desc;
-	struct flex_groups **flex_groups;
 	int aborted = 0;
 	int i, err;
 
@@ -1238,24 +1307,9 @@ static void ext4_put_super(struct super_block *sb)
 	if (!sb_rdonly(sb))
 		ext4_commit_super(sb);
 
-	rcu_read_lock();
-	group_desc = rcu_dereference(sbi->s_group_desc);
-	for (i = 0; i < sbi->s_gdb_count; i++)
-		brelse(group_desc[i]);
-	kvfree(group_desc);
-	flex_groups = rcu_dereference(sbi->s_flex_groups);
-	if (flex_groups) {
-		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
-			kvfree(flex_groups[i]);
-		kvfree(flex_groups);
-	}
-	rcu_read_unlock();
-	percpu_counter_destroy(&sbi->s_freeclusters_counter);
-	percpu_counter_destroy(&sbi->s_freeinodes_counter);
-	percpu_counter_destroy(&sbi->s_dirs_counter);
-	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
-	percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
-	percpu_free_rwsem(&sbi->s_writepages_rwsem);
+	ext4_group_desc_free(sbi);
+	ext4_flex_groups_free(sbi);
+	ext4_percpu_param_destroy(sbi);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(get_qf_name(sb, sbi, i));
@@ -1325,9 +1379,9 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	inode_set_iversion(&ei->vfs_inode, 1);
 	ei->i_flags = 0;
 	spin_lock_init(&ei->i_raw_lock);
-	INIT_LIST_HEAD(&ei->i_prealloc_list);
+	ei->i_prealloc_node = RB_ROOT;
 	atomic_set(&ei->i_prealloc_active, 0);
-	spin_lock_init(&ei->i_prealloc_lock);
+	rwlock_init(&ei->i_prealloc_lock);
 	ext4_es_init_tree(&ei->i_es_tree);
 	rwlock_init(&ei->i_es_lock);
 	INIT_LIST_HEAD(&ei->i_es_list);
@@ -4587,6 +4641,8 @@ static int ext4_check_feature_compatibility(struct super_block *sb,
 					    struct ext4_super_block *es,
 					    int silent)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
 	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
 	    (ext4_has_compat_features(sb) ||
 	     ext4_has_ro_compat_features(sb) ||
@@ -4656,14 +4712,59 @@ static int ext4_check_feature_compatibility(struct super_block *sb,
 	if (!ext4_feature_set_ok(sb, (sb_rdonly(sb))))
 		return -EINVAL;
 
+	if (sbi->s_daxdev) {
+		if (sb->s_blocksize == PAGE_SIZE)
+			set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+		else
+			ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n");
+	}
+
+	if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
+		if (ext4_has_feature_inline_data(sb)) {
+			ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem"
+					" that may contain inline data");
+			return -EINVAL;
+		}
+		if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) {
+			ext4_msg(sb, KERN_ERR,
+				"DAX unsupported by block device.");
+			return -EINVAL;
+		}
+	}
+
+	if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) {
+		ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d",
+			 es->s_encryption_level);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
-static int ext4_geometry_check(struct super_block *sb,
+static int ext4_check_geometry(struct super_block *sb,
 			       struct ext4_super_block *es)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	__u64 blocks_count;
+	int err;
+
+	if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (sb->s_blocksize / 4)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Number of reserved GDT blocks insanely large: %d",
+			 le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks));
+		return -EINVAL;
+	}
+	/*
+	 * Test whether we have more sectors than will fit in sector_t,
+	 * and whether the max offset is addressable by the page cache.
+	 */
+	err = generic_check_addressable(sb->s_blocksize_bits,
+					ext4_blocks_count(es));
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "filesystem"
+			 " too large to mount safely on this system");
+		return err;
+	}
 
 	/* check blocks count against device size */
 	blocks_count = sb_bdev_nr_blocks(sb);
@@ -4719,19 +4820,6 @@ static int ext4_geometry_check(struct super_block *sb,
 	return 0;
 }
 
-static void ext4_group_desc_free(struct ext4_sb_info *sbi)
-{
-	struct buffer_head **group_desc;
-	int i;
-
-	rcu_read_lock();
-	group_desc = rcu_dereference(sbi->s_group_desc);
-	for (i = 0; i < sbi->s_gdb_count; i++)
-		brelse(group_desc[i]);
-	kvfree(group_desc);
-	rcu_read_unlock();
-}
-
 static int ext4_group_desc_init(struct super_block *sb,
 				struct ext4_super_block *es,
 				ext4_fsblk_t logical_sb_block,
@@ -4881,7 +4969,7 @@ out:
 	return -EINVAL;
 }
 
-static int ext4_journal_data_mode_check(struct super_block *sb)
+static int ext4_check_journal_data_mode(struct super_block *sb)
 {
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
 		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with "
@@ -5024,17 +5112,93 @@ out:
 	return ret;
 }
 
+static void 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;
+
+	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)
+			sbi->s_hash_unsigned = 3;
+		else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+#ifdef __CHAR_UNSIGNED__
+			if (!sb_rdonly(sb))
+				es->s_flags |=
+					cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+			sbi->s_hash_unsigned = 3;
+#else
+			if (!sb_rdonly(sb))
+				es->s_flags |=
+					cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+#endif
+		}
+	}
+}
+
+static int ext4_block_group_meta_init(struct super_block *sb, int silent)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	int has_huge_files;
+
+	has_huge_files = ext4_has_feature_huge_file(sb);
+	sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits,
+						      has_huge_files);
+	sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
+
+	sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
+	if (ext4_has_feature_64bit(sb)) {
+		if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
+		    sbi->s_desc_size > EXT4_MAX_DESC_SIZE ||
+		    !is_power_of_2(sbi->s_desc_size)) {
+			ext4_msg(sb, KERN_ERR,
+			       "unsupported descriptor size %lu",
+			       sbi->s_desc_size);
+			return -EINVAL;
+		}
+	} else
+		sbi->s_desc_size = EXT4_MIN_DESC_SIZE;
+
+	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
+	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
+
+	sbi->s_inodes_per_block = sb->s_blocksize / EXT4_INODE_SIZE(sb);
+	if (sbi->s_inodes_per_block == 0 || sbi->s_blocks_per_group == 0) {
+		if (!silent)
+			ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
+		return -EINVAL;
+	}
+	if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
+	    sbi->s_inodes_per_group > sb->s_blocksize * 8) {
+		ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n",
+			 sbi->s_inodes_per_group);
+		return -EINVAL;
+	}
+	sbi->s_itb_per_group = sbi->s_inodes_per_group /
+					sbi->s_inodes_per_block;
+	sbi->s_desc_per_block = sb->s_blocksize / EXT4_DESC_SIZE(sb);
+	sbi->s_mount_state = le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY;
+	sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
+	sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
+
+	return 0;
+}
+
 static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 {
 	struct ext4_super_block *es = NULL;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct flex_groups **flex_groups;
-	ext4_fsblk_t block;
 	ext4_fsblk_t logical_sb_block;
 	struct inode *root;
 	int ret = -ENOMEM;
 	unsigned int i;
-	int needs_recovery, has_huge_files;
+	int needs_recovery;
 	int err = 0;
 	ext4_group_t first_not_zeroed;
 	struct ext4_fs_context *ctx = fc->fs_private;
@@ -5094,7 +5258,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	if (ext4_encoding_init(sb, es))
 		goto failed_mount;
 
-	if (ext4_journal_data_mode_check(sb))
+	if (ext4_check_journal_data_mode(sb))
 		goto failed_mount;
 
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
@@ -5106,116 +5270,15 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	if (ext4_check_feature_compatibility(sb, es, silent))
 		goto failed_mount;
 
-	if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (sb->s_blocksize / 4)) {
-		ext4_msg(sb, KERN_ERR,
-			 "Number of reserved GDT blocks insanely large: %d",
-			 le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks));
+	if (ext4_block_group_meta_init(sb, silent))
 		goto failed_mount;
-	}
 
-	if (sbi->s_daxdev) {
-		if (sb->s_blocksize == PAGE_SIZE)
-			set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
-		else
-			ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n");
-	}
-
-	if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
-		if (ext4_has_feature_inline_data(sb)) {
-			ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem"
-					" that may contain inline data");
-			goto failed_mount;
-		}
-		if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) {
-			ext4_msg(sb, KERN_ERR,
-				"DAX unsupported by block device.");
-			goto failed_mount;
-		}
-	}
-
-	if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) {
-		ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d",
-			 es->s_encryption_level);
-		goto failed_mount;
-	}
-
-	has_huge_files = ext4_has_feature_huge_file(sb);
-	sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits,
-						      has_huge_files);
-	sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
-
-	sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
-	if (ext4_has_feature_64bit(sb)) {
-		if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
-		    sbi->s_desc_size > EXT4_MAX_DESC_SIZE ||
-		    !is_power_of_2(sbi->s_desc_size)) {
-			ext4_msg(sb, KERN_ERR,
-			       "unsupported descriptor size %lu",
-			       sbi->s_desc_size);
-			goto failed_mount;
-		}
-	} else
-		sbi->s_desc_size = EXT4_MIN_DESC_SIZE;
-
-	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
-	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
-
-	sbi->s_inodes_per_block = sb->s_blocksize / EXT4_INODE_SIZE(sb);
-	if (sbi->s_inodes_per_block == 0 || sbi->s_blocks_per_group == 0) {
-		if (!silent)
-			ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
-		goto failed_mount;
-	}
-	if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
-	    sbi->s_inodes_per_group > sb->s_blocksize * 8) {
-		ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n",
-			 sbi->s_inodes_per_group);
-		goto failed_mount;
-	}
-	sbi->s_itb_per_group = sbi->s_inodes_per_group /
-					sbi->s_inodes_per_block;
-	sbi->s_desc_per_block = sb->s_blocksize / EXT4_DESC_SIZE(sb);
-	sbi->s_mount_state = le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY;
-	sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
-	sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
-
-	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)
-			sbi->s_hash_unsigned = 3;
-		else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
-#ifdef __CHAR_UNSIGNED__
-			if (!sb_rdonly(sb))
-				es->s_flags |=
-					cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
-			sbi->s_hash_unsigned = 3;
-#else
-			if (!sb_rdonly(sb))
-				es->s_flags |=
-					cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
-#endif
-		}
-	}
+	ext4_hash_info_init(sb);
 
 	if (ext4_handle_clustersize(sb))
 		goto failed_mount;
 
-	/*
-	 * Test whether we have more sectors than will fit in sector_t,
-	 * and whether the max offset is addressable by the page cache.
-	 */
-	err = generic_check_addressable(sb->s_blocksize_bits,
-					ext4_blocks_count(es));
-	if (err) {
-		ext4_msg(sb, KERN_ERR, "filesystem"
-			 " too large to mount safely on this system");
-		goto failed_mount;
-	}
-
-	if (ext4_geometry_check(sb, es))
+	if (ext4_check_geometry(sb, es))
 		goto failed_mount;
 
 	timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
@@ -5440,33 +5503,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		sbi->s_journal->j_commit_callback =
 			ext4_journal_commit_callback;
 
-	block = ext4_count_free_clusters(sb);
-	ext4_free_blocks_count_set(sbi->s_es,
-				   EXT4_C2B(sbi, block));
-	err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
-				  GFP_KERNEL);
-	if (!err) {
-		unsigned long freei = ext4_count_free_inodes(sb);
-		sbi->s_es->s_free_inodes_count = cpu_to_le32(freei);
-		err = percpu_counter_init(&sbi->s_freeinodes_counter, freei,
-					  GFP_KERNEL);
-	}
-	if (!err)
-		err = percpu_counter_init(&sbi->s_dirs_counter,
-					  ext4_count_dirs(sb), GFP_KERNEL);
-	if (!err)
-		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
-					  GFP_KERNEL);
-	if (!err)
-		err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0,
-					  GFP_KERNEL);
-	if (!err)
-		err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
-
-	if (err) {
-		ext4_msg(sb, KERN_ERR, "insufficient memory");
+	if (ext4_percpu_param_init(sbi))
 		goto failed_mount6;
-	}
 
 	if (ext4_has_feature_flex_bg(sb))
 		if (!ext4_fill_flex_info(sb)) {
@@ -5548,20 +5586,8 @@ failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
 	ext4_mb_release(sb);
-	rcu_read_lock();
-	flex_groups = rcu_dereference(sbi->s_flex_groups);
-	if (flex_groups) {
-		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
-			kvfree(flex_groups[i]);
-		kvfree(flex_groups);
-	}
-	rcu_read_unlock();
-	percpu_counter_destroy(&sbi->s_freeclusters_counter);
-	percpu_counter_destroy(&sbi->s_freeinodes_counter);
-	percpu_counter_destroy(&sbi->s_dirs_counter);
-	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
-	percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
-	percpu_free_rwsem(&sbi->s_writepages_rwsem);
+	ext4_flex_groups_free(sbi);
+	ext4_percpu_param_destroy(sbi);
 failed_mount5:
 	ext4_ext_release(sb);
 	ext4_release_system_zone(sb);
@@ -6870,23 +6896,6 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 		sb_dqopt(sb)->flags &= ~DQUOT_NOLIST_DIRTY;
 	}
 
-	/*
-	 * When we journal data on quota file, we have to flush journal to see
-	 * all updates to the file when we bypass pagecache...
-	 */
-	if (EXT4_SB(sb)->s_journal &&
-	    ext4_should_journal_data(d_inode(path->dentry))) {
-		/*
-		 * We don't need to lock updates but journal_flush() could
-		 * otherwise be livelocked...
-		 */
-		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-		err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
-		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
-		if (err)
-			return err;
-	}
-
 	lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA);
 	err = dquot_quota_on(sb, type, format_id, path);
 	if (!err) {
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 12d6252e3e22..3042bc605bbf 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -214,7 +214,6 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
 EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
 EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
 EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
-EXT4_RW_ATTR_SBI_UI(mb_max_inode_prealloc, s_mb_max_inode_prealloc);
 EXT4_RW_ATTR_SBI_UI(mb_max_linear_groups, s_mb_max_linear_groups);
 EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
 EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error);
@@ -264,7 +263,6 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(mb_order2_req),
 	ATTR_LIST(mb_stream_req),
 	ATTR_LIST(mb_group_prealloc),
-	ATTR_LIST(mb_max_inode_prealloc),
 	ATTR_LIST(mb_max_linear_groups),
 	ATTR_LIST(max_writeback_mb_bump),
 	ATTR_LIST(extent_max_zeroout_kb),
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index e4da1704438e..3b01247066dd 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -42,18 +42,16 @@ static int pagecache_read(struct inode *inode, void *buf, size_t count,
 			  loff_t pos)
 {
 	while (count) {
-		size_t n = min_t(size_t, count,
-				 PAGE_SIZE - offset_in_page(pos));
-		struct page *page;
+		struct folio *folio;
+		size_t n;
 
-		page = read_mapping_page(inode->i_mapping, pos >> PAGE_SHIFT,
+		folio = read_mapping_folio(inode->i_mapping, pos >> PAGE_SHIFT,
 					 NULL);
-		if (IS_ERR(page))
-			return PTR_ERR(page);
-
-		memcpy_from_page(buf, page, offset_in_page(pos), n);
+		if (IS_ERR(folio))
+			return PTR_ERR(folio);
 
-		put_page(page);
+		n = memcpy_from_file_folio(buf, folio, pos, count);
+		folio_put(folio);
 
 		buf += n;
 		pos += n;
@@ -363,21 +361,21 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode,
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
 {
-	struct page *page;
+	struct folio *folio;
 
 	index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT;
 
-	page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED);
-	if (!page || !PageUptodate(page)) {
+	folio = __filemap_get_folio(inode->i_mapping, index, FGP_ACCESSED, 0);
+	if (!folio || !folio_test_uptodate(folio)) {
 		DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index);
 
-		if (page)
-			put_page(page);
+		if (folio)
+			folio_put(folio);
 		else if (num_ra_pages > 1)
 			page_cache_ra_unbounded(&ractl, num_ra_pages, 0);
-		page = read_mapping_page(inode->i_mapping, index, NULL);
+		folio = read_mapping_folio(inode->i_mapping, index, NULL);
 	}
-	return page;
+	return folio_file_page(folio, index);
 }
 
 static int ext4_write_merkle_tree_block(struct inode *inode, const void *buf,
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 6f4c97a6d7e9..10a203515583 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -467,7 +467,7 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
  */
 struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos)
 {
-	unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS;
+	unsigned fgp = FGP_WRITEBEGIN | FGP_NOFS;
 	struct folio *folio;
 
 	if (iter->flags & IOMAP_NOWAIT)
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 15de1385012e..18611241f451 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2387,6 +2387,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 			spin_unlock(&jh->b_state_lock);
 			write_unlock(&journal->j_state_lock);
 			jbd2_journal_put_journal_head(jh);
+			/* Already zapped buffer? Nothing to do... */
+			if (!bh->b_bdev)
+				return 0;
 			return -EBUSY;
 		}
 		/*
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 7679a68e8193..e3d754a9e1b0 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -341,14 +341,13 @@ int netfs_write_begin(struct netfs_inode *ctx,
 {
 	struct netfs_io_request *rreq;
 	struct folio *folio;
-	unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
 	pgoff_t index = pos >> PAGE_SHIFT;
 	int ret;
 
 	DEFINE_READAHEAD(ractl, file, NULL, mapping, index);
 
 retry:
-	folio = __filemap_get_folio(mapping, index, fgp_flags,
+	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
 				    mapping_gfp_mask(mapping));
 	if (!folio)
 		return -ENOMEM;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 893625eacab9..2474cbc30712 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -306,15 +306,6 @@ static bool nfs_want_read_modify_write(struct file *file, struct folio *folio,
 	return false;
 }
 
-static struct folio *
-nfs_folio_grab_cache_write_begin(struct address_space *mapping, pgoff_t index)
-{
-	unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
-
-	return __filemap_get_folio(mapping, index, fgp_flags,
-				   mapping_gfp_mask(mapping));
-}
-
 /*
  * This does the "real" work of the write. We must allocate and lock the
  * page to be sent back to the generic routine, which then copies the
@@ -335,7 +326,8 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
 		file, mapping->host->i_ino, len, (long long) pos);
 
 start:
-	folio = nfs_folio_grab_cache_write_begin(mapping, pos >> PAGE_SHIFT);
+	folio = __filemap_get_folio(mapping, pos >> PAGE_SHIFT, FGP_WRITEBEGIN,
+				    mapping_gfp_mask(mapping));
 	if (!folio)
 		return -ENOMEM;
 	*pagep = &folio->page;
author	Linus Torvalds <torvalds@linux-foundation.org>	2023-04-26 17:57:41 +0200
committer	Linus Torvalds <torvalds@linux-foundation.org>	2023-04-26 17:57:41 +0200
commit	0cfcde1fafc23068f57afa50faa3e69487b7cd30 (patch)
tree	86f9b91f143e39becea74df7db1d3e9cd89dd3ea /fs
parent	Merge tag 'fsverity-for-linus' of git://git.kernel.org/pub/scm/fs/fsverity/linux (diff)
parent	ext4: Add a uapi header for ext4 userspace APIs (diff)
download	linux-0cfcde1fafc23068f57afa50faa3e69487b7cd30.tar.xz linux-0cfcde1fafc23068f57afa50faa3e69487b7cd30.zip