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
  ...

Documentation/admin-guide/ext4.rst

@@ -489,9 +489,6 @@ Files in /sys/fs/ext4/<devname>:
         multiple of this tuning parameter if the stripe size is not set in the
         ext4 superblock
 
-  mb_max_inode_prealloc
-        The maximum length of per-inode ext4_prealloc_space list.
-
   mb_max_to_scan
         The maximum number of extents the multiblock allocator will search to
         find the best extent.

MAINTAINERS

@@ -7745,6 +7745,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git
 F:	Documentation/filesystems/ext4/
 F:	fs/ext4/
 F:	include/trace/events/ext4.h
+F:	include/uapi/linux/ext4.h
 
 Extended Verification Module (EVM)
 M:	Mimi Zohar <zohar@linux.ibm.com>

block/bio.c

@@ -1159,6 +1159,7 @@ bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len,
 		return false;
 	return bio_add_page(bio, &folio->page, len, off) > 0;
 }
+EXPORT_SYMBOL(bio_add_folio);
 
 void __bio_release_pages(struct bio *bio, bool mark_dirty)
 {

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;
 
 	/*
-	 * 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.
+	 * 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, 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) {
+		/*
+		 * 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++;
-			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;
-			}
-			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);
+		if (err) {
 			ext4_unlock_group(sb, block_group);
 			unlock_buffer(bh);
-		if (err) {
 			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)) {
@@ -842,9 +845,6 @@ 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;
 }
 
@@ -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);
 }

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)
 {

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);
 

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)) {

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);
 

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 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
 			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 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
 		}
 	}
 	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);
 	}

fs/ext4/mballoc.h

@@ -73,11 +73,6 @@
  */
 #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 {

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 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 		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;
 

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 @@ static void io_submit_add_bh(struct ext4_io_submit *io,
 	}
 	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;
 }

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);

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;

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),

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);
+		if (IS_ERR(folio))
+			return PTR_ERR(folio);
 
-		memcpy_from_page(buf, page, offset_in_page(pos), n);
-
-		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,

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)

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;
 		}
 		/*

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;

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;

include/linux/fscrypt.h

@@ -273,6 +273,16 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page)
 	return (struct page *)page_private(bounce_page);
 }
 
+static inline bool fscrypt_is_bounce_folio(struct folio *folio)
+{
+	return folio->mapping == NULL;
+}
+
+static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio)
+{
+	return bounce_folio->private;
+}
+
 void fscrypt_free_bounce_page(struct page *bounce_page);
 
 /* policy.c */
@@ -446,6 +456,17 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page)
 	return ERR_PTR(-EINVAL);
 }
 
+static inline bool fscrypt_is_bounce_folio(struct folio *folio)
+{
+	return false;
+}
+
+static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio)
+{
+	WARN_ON_ONCE(1);
+	return ERR_PTR(-EINVAL);
+}
+
 static inline void fscrypt_free_bounce_page(struct page *bounce_page)
 {
 }

include/linux/page-flags.h

@@ -762,11 +762,6 @@ bool set_page_writeback(struct page *page);
 #define folio_start_writeback_keepwrite(folio)	\
 	__folio_start_writeback(folio, true)
 
-static inline void set_page_writeback_keepwrite(struct page *page)
-{
-	folio_start_writeback_keepwrite(page_folio(page));
-}
-
 static inline bool test_set_page_writeback(struct page *page)
 {
 	return set_page_writeback(page);

include/linux/pagemap.h

@@ -507,6 +507,8 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
 #define FGP_ENTRY		0x00000080
 #define FGP_STABLE		0x00000100
 
+#define FGP_WRITEBEGIN		(FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE)
+
 struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		int fgp_flags, gfp_t gfp);
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,

include/trace/events/ext4.h

@@ -584,13 +584,6 @@ DECLARE_EVENT_CLASS(ext4__page_op,
 		  (unsigned long) __entry->index)
 );
 
-DEFINE_EVENT(ext4__page_op, ext4_writepage,
-
-	TP_PROTO(struct page *page),
-
-	TP_ARGS(page)
-);
-
 DEFINE_EVENT(ext4__page_op, ext4_readpage,
 
 	TP_PROTO(struct page *page),

include/uapi/linux/ext4.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_LINUX_EXT4_H
+#define _UAPI_LINUX_EXT4_H
+#include <linux/fiemap.h>
+#include <linux/fs.h>
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/*
+ * ext4-specific 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)
+
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT4_IOC32_GETVERSION		_IOR('f', 3, int)
+#define EXT4_IOC32_SETVERSION		_IOW('f', 4, int)
+#define EXT4_IOC32_GETRSVSZ		_IOR('f', 5, int)
+#define EXT4_IOC32_SETRSVSZ		_IOW('f', 6, int)
+#define EXT4_IOC32_GROUP_EXTEND		_IOW('f', 7, unsigned int)
+#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
+#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
+#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
+
+/*
+ * 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[];
+};
+
+/*
+ * Structure for EXT4_IOC_MOVE_EXT
+ */
+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 */
+};
+
+/*
+ * Flags used by EXT4_IOC_SHUTDOWN
+ */
+#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 */
+
+/* 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;
+};
+
+/*
+ * 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
+
+#endif /* _UAPI_LINUX_EXT4_H */

mm/folio-compat.c

@@ -106,9 +106,7 @@ EXPORT_SYMBOL(pagecache_get_page);
 struct page *grab_cache_page_write_begin(struct address_space *mapping,
 					pgoff_t index)
 {
-	unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
-
-	return pagecache_get_page(mapping, index, fgp_flags,
+	return pagecache_get_page(mapping, index, FGP_WRITEBEGIN,
 			mapping_gfp_mask(mapping));
 }
 EXPORT_SYMBOL(grab_cache_page_write_begin);