Merge tag 'ext4_for_linus_6.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Major ext4 changes for 6.17:

   - Better scalability for ext4 block allocation

   - Fix insufficient credits when writing back large folios

  Miscellaneous bug fixes, especially when handling exteded attriutes,
  inline data, and fast commit"

* tag 'ext4_for_linus_6.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (39 commits)
  ext4: do not BUG when INLINE_DATA_FL lacks system.data xattr
  ext4: implement linear-like traversal across order xarrays
  ext4: refactor choose group to scan group
  ext4: convert free groups order lists to xarrays
  ext4: factor out ext4_mb_scan_group()
  ext4: factor out ext4_mb_might_prefetch()
  ext4: factor out __ext4_mb_scan_group()
  ext4: fix largest free orders lists corruption on mb_optimize_scan switch
  ext4: fix zombie groups in average fragment size lists
  ext4: merge freed extent with existing extents before insertion
  ext4: convert sbi->s_mb_free_pending to atomic_t
  ext4: fix typo in CR_GOAL_LEN_SLOW comment
  ext4: get rid of some obsolete EXT4_MB_HINT flags
  ext4: utilize multiple global goals to reduce contention
  ext4: remove unnecessary s_md_lock on update s_mb_last_group
  ext4: remove unnecessary s_mb_last_start
  ext4: separate stream goal hits from s_bal_goals for better tracking
  ext4: add ext4_try_lock_group() to skip busy groups
  ext4: initialize superblock fields in the kballoc-test.c kunit tests
  ext4: refactor the inline directory conversion and new directory codepaths
  ...

14 files changed, 861 insertions, 681 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index c48fd36b2d74..c9329ed5c094 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -703,7 +703,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 	 * possible we just missed a transaction commit that did so
 	 */
 	smp_mb();
-	if (sbi->s_mb_free_pending == 0) {
+	if (atomic_read(&sbi->s_mb_free_pending) == 0) {
 		if (test_opt(sb, DISCARD)) {
 			atomic_inc(&sbi->s_retry_alloc_pending);
 			flush_work(&sbi->s_discard_work);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 7d962e7f388a..01a6e2de7fc3 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -157,7 +157,7 @@ enum criteria {
 
 	/*
 	 * Reads each block group sequentially, performing disk IO if
-	 * necessary, to find find_suitable block group. Tries to
+	 * necessary, to find suitable block group. Tries to
 	 * allocate goal length but might trim the request if nothing
 	 * is found after enough tries.
 	 */
@@ -185,14 +185,8 @@ enum criteria {
 
 /* prefer goal again. length */
 #define EXT4_MB_HINT_MERGE		0x0001
-/* blocks already reserved */
-#define EXT4_MB_HINT_RESERVED		0x0002
-/* metadata is being allocated */
-#define EXT4_MB_HINT_METADATA		0x0004
 /* first blocks in the file */
 #define EXT4_MB_HINT_FIRST		0x0008
-/* search for the best chunk */
-#define EXT4_MB_HINT_BEST		0x0010
 /* data is being allocated */
 #define EXT4_MB_HINT_DATA		0x0020
 /* don't preallocate (for tails) */
@@ -213,15 +207,6 @@ enum criteria {
 #define EXT4_MB_USE_RESERVED		0x2000
 /* Do strict check for free blocks while retrying block allocation */
 #define EXT4_MB_STRICT_CHECK		0x4000
-/* Large fragment size list lookup succeeded at least once for
- * CR_POWER2_ALIGNED */
-#define EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED		0x8000
-/* Avg fragment size rb tree lookup succeeded at least once for
- * CR_GOAL_LEN_FAST */
-#define EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED		0x00010000
-/* Avg fragment size rb tree lookup succeeded at least once for
- * CR_BEST_AVAIL_LEN */
-#define EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED		0x00020000
 
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
@@ -1608,16 +1593,14 @@ struct ext4_sb_info {
 	unsigned short *s_mb_offsets;
 	unsigned int *s_mb_maxs;
 	unsigned int s_group_info_size;
-	unsigned int s_mb_free_pending;
+	atomic_t s_mb_free_pending;
 	struct list_head s_freed_data_list[2];	/* List of blocks to be freed
 						   after commit completed */
 	struct list_head s_discard_list;
 	struct work_struct s_discard_work;
 	atomic_t s_retry_alloc_pending;
-	struct list_head *s_mb_avg_fragment_size;
-	rwlock_t *s_mb_avg_fragment_size_locks;
-	struct list_head *s_mb_largest_free_orders;
-	rwlock_t *s_mb_largest_free_orders_locks;
+	struct xarray *s_mb_avg_fragment_size;
+	struct xarray *s_mb_largest_free_orders;
 
 	/* tunables */
 	unsigned long s_stripe;
@@ -1629,15 +1612,16 @@ struct ext4_sb_info {
 	unsigned int s_mb_order2_reqs;
 	unsigned int s_mb_group_prealloc;
 	unsigned int s_max_dir_size_kb;
-	/* where last allocation was done - for stream allocation */
-	unsigned long s_mb_last_group;
-	unsigned long s_mb_last_start;
 	unsigned int s_mb_prefetch;
 	unsigned int s_mb_prefetch_limit;
 	unsigned int s_mb_best_avail_max_trim_order;
 	unsigned int s_sb_update_sec;
 	unsigned int s_sb_update_kb;
 
+	/* where last allocation was done - for stream allocation */
+	ext4_group_t *s_mb_last_groups;
+	unsigned int s_mb_nr_global_goals;
+
 	/* stats for buddy allocator */
 	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
 	atomic_t s_bal_success;	/* we found long enough chunks */
@@ -1646,12 +1630,10 @@ struct ext4_sb_info {
 	atomic_t s_bal_cX_ex_scanned[EXT4_MB_NUM_CRS];	/* total extents scanned */
 	atomic_t s_bal_groups_scanned;	/* number of groups scanned */
 	atomic_t s_bal_goals;	/* goal hits */
+	atomic_t s_bal_stream_goals;	/* stream allocation global goal hits */
 	atomic_t s_bal_len_goals;	/* len goal hits */
 	atomic_t s_bal_breaks;	/* too long searches */
 	atomic_t s_bal_2orders;	/* 2^order hits */
-	atomic_t s_bal_p2_aligned_bad_suggestions;
-	atomic_t s_bal_goal_fast_bad_suggestions;
-	atomic_t s_bal_best_avail_bad_suggestions;
 	atomic64_t s_bal_cX_groups_considered[EXT4_MB_NUM_CRS];
 	atomic64_t s_bal_cX_hits[EXT4_MB_NUM_CRS];
 	atomic64_t s_bal_cX_failed[EXT4_MB_NUM_CRS];		/* cX loop didn't find blocks */
@@ -3020,7 +3002,7 @@ int ext4_walk_page_buffers(handle_t *handle,
 				     struct buffer_head *bh));
 int do_journal_get_write_access(handle_t *handle, struct inode *inode,
 				struct buffer_head *bh);
-bool ext4_should_enable_large_folio(struct inode *inode);
+void ext4_set_inode_mapping_order(struct inode *inode);
 #define FALL_BACK_TO_NONDELALLOC 1
 #define CONVERT_INLINE_DATA	 2
 
@@ -3064,9 +3046,9 @@ extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
 extern void ext4_set_inode_flags(struct inode *, bool init);
 extern int ext4_alloc_da_blocks(struct inode *inode);
 extern void ext4_set_aops(struct inode *inode);
-extern int ext4_writepage_trans_blocks(struct inode *);
 extern int ext4_normal_submit_inode_data_buffers(struct jbd2_inode *jinode);
 extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
+extern int ext4_chunk_trans_extent(struct inode *inode, int nrblocks);
 extern int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
 				  int pextents);
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
@@ -3489,8 +3471,6 @@ struct ext4_group_info {
 	void            *bb_bitmap;
 #endif
 	struct rw_semaphore alloc_sem;
-	struct list_head bb_avg_fragment_size_node;
-	struct list_head bb_largest_free_order_node;
 	ext4_grpblk_t	bb_counters[];	/* Nr of free power-of-two-block
 					 * regions, index is order.
 					 * bb_counters[3] = 5 means
@@ -3541,23 +3521,28 @@ static inline int ext4_fs_is_busy(struct ext4_sb_info *sbi)
 	return (atomic_read(&sbi->s_lock_busy) > EXT4_CONTENTION_THRESHOLD);
 }
 
+static inline bool ext4_try_lock_group(struct super_block *sb, ext4_group_t group)
+{
+	if (!spin_trylock(ext4_group_lock_ptr(sb, group)))
+		return false;
+	/*
+	 * We're able to grab the lock right away, so drop the lock
+	 * contention counter.
+	 */
+	atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, -1, 0);
+	return true;
+}
+
 static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
 {
-	spinlock_t *lock = ext4_group_lock_ptr(sb, group);
-	if (spin_trylock(lock))
-		/*
-		 * We're able to grab the lock right away, so drop the
-		 * lock contention counter.
-		 */
-		atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, -1, 0);
-	else {
+	if (!ext4_try_lock_group(sb, group)) {
 		/*
 		 * The lock is busy, so bump the contention counter,
 		 * and then wait on the spin lock.
 		 */
 		atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, 1,
 				  EXT4_MAX_CONTENTION);
-		spin_lock(lock);
+		spin_lock(ext4_group_lock_ptr(sb, group));
 	}
 }
 
@@ -3612,6 +3597,7 @@ extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
 extern int ext4_get_max_inline_size(struct inode *inode);
 extern int ext4_find_inline_data_nolock(struct inode *inode);
 extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
+extern void ext4_update_final_de(void *de_buf, int old_size, int new_size);
 
 int ext4_readpage_inline(struct inode *inode, struct folio *folio);
 extern int ext4_try_to_write_inline_data(struct address_space *mapping,
@@ -3671,10 +3657,10 @@ static inline int ext4_has_inline_data(struct inode *inode)
 extern const struct inode_operations ext4_dir_inode_operations;
 extern const struct inode_operations ext4_special_inode_operations;
 extern struct dentry *ext4_get_parent(struct dentry *child);
-extern struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode,
-				 struct ext4_dir_entry_2 *de,
-				 int blocksize, int csum_size,
-				 unsigned int parent_ino, int dotdot_real_len);
+extern int ext4_init_dirblock(handle_t *handle, struct inode *inode,
+			      struct buffer_head *dir_block,
+			      unsigned int parent_ino, void *inline_buf,
+			      int inline_size);
 extern void ext4_initialize_dirent_tail(struct buffer_head *bh,
 					unsigned int blocksize);
 extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 26435f3a3094..c484125d963f 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -31,13 +31,6 @@
 #define CHECK_BINSEARCH__
 
 /*
- * If EXT_STATS is defined then stats numbers are collected.
- * These number will be displayed at umount time.
- */
-#define EXT_STATS_
-
-
-/*
  * ext4_inode has i_block array (60 bytes total).
  * The first 12 bytes store ext4_extent_header;
  * the remainder stores an array of ext4_extent.
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index b43aa82c1b39..ca5499e9412b 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5215,7 +5215,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
 				credits = depth + 2;
 			}
 
-			restart_credits = ext4_writepage_trans_blocks(inode);
+			restart_credits = ext4_chunk_trans_extent(inode, 0);
 			err = ext4_datasem_ensure_credits(handle, inode, credits,
 					restart_credits, 0);
 			if (err) {
@@ -5475,7 +5475,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
 
 	truncate_pagecache(inode, start);
 
-	credits = ext4_writepage_trans_blocks(inode);
+	credits = ext4_chunk_trans_extent(inode, 0);
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
@@ -5571,7 +5571,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
 
 	truncate_pagecache(inode, start);
 
-	credits = ext4_writepage_trans_blocks(inode);
+	credits = ext4_chunk_trans_extent(inode, 0);
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 79aa3df8d019..df4051613b29 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1335,8 +1335,7 @@ got:
 		}
 	}
 
-	if (ext4_should_enable_large_folio(inode))
-		mapping_set_large_folios(inode->i_mapping);
+	ext4_set_inode_mapping_order(inode);
 
 	ext4_update_inode_fsync_trans(handle, inode, 1);
 
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index a1bbcdf40824..1b094a4f3866 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -303,7 +303,11 @@ static int ext4_create_inline_data(handle_t *handle,
 	if (error)
 		goto out;
 
-	BUG_ON(!is.s.not_found);
+	if (!is.s.not_found) {
+		EXT4_ERROR_INODE(inode, "unexpected inline data xattr");
+		error = -EFSCORRUPTED;
+		goto out;
+	}
 
 	error = ext4_xattr_ibody_set(handle, inode, &i, &is);
 	if (error) {
@@ -354,7 +358,11 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
 	if (error)
 		goto out;
 
-	BUG_ON(is.s.not_found);
+	if (is.s.not_found) {
+		EXT4_ERROR_INODE(inode, "missing inline data xattr");
+		error = -EFSCORRUPTED;
+		goto out;
+	}
 
 	len -= EXT4_MIN_INLINE_DATA_SIZE;
 	value = kzalloc(len, GFP_NOFS);
@@ -562,7 +570,7 @@ static int ext4_convert_inline_data_to_extent(struct address_space *mapping,
 		return 0;
 	}
 
-	needed_blocks = ext4_writepage_trans_blocks(inode);
+	needed_blocks = ext4_chunk_trans_extent(inode, 1);
 
 	ret = ext4_get_inode_loc(inode, &iloc);
 	if (ret)
@@ -612,6 +620,7 @@ retry:
 	} else
 		ret = ext4_block_write_begin(handle, folio, from, to,
 					     ext4_get_block);
+	clear_buffer_new(folio_buffers(folio));
 
 	if (!ret && ext4_should_journal_data(inode)) {
 		ret = ext4_walk_page_buffers(handle, inode,
@@ -891,6 +900,7 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
 		return ret;
 	}
 
+	clear_buffer_new(folio_buffers(folio));
 	folio_mark_dirty(folio);
 	folio_mark_uptodate(folio);
 	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
@@ -995,7 +1005,7 @@ static void *ext4_get_inline_xattr_pos(struct inode *inode,
 }
 
 /* Set the final de to cover the whole block. */
-static void ext4_update_final_de(void *de_buf, int old_size, int new_size)
+void ext4_update_final_de(void *de_buf, int old_size, int new_size)
 {
 	struct ext4_dir_entry_2 *de, *prev_de;
 	void *limit;
@@ -1059,51 +1069,6 @@ static void ext4_restore_inline_data(handle_t *handle, struct inode *inode,
 	ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
 }
 
-static int ext4_finish_convert_inline_dir(handle_t *handle,
-					  struct inode *inode,
-					  struct buffer_head *dir_block,
-					  void *buf,
-					  int inline_size)
-{
-	int err, csum_size = 0, header_size = 0;
-	struct ext4_dir_entry_2 *de;
-	void *target = dir_block->b_data;
-
-	/*
-	 * First create "." and ".." and then copy the dir information
-	 * back to the block.
-	 */
-	de = target;
-	de = ext4_init_dot_dotdot(inode, de,
-		inode->i_sb->s_blocksize, csum_size,
-		le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), 1);
-	header_size = (void *)de - target;
-
-	memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE,
-		inline_size - EXT4_INLINE_DOTDOT_SIZE);
-
-	if (ext4_has_feature_metadata_csum(inode->i_sb))
-		csum_size = sizeof(struct ext4_dir_entry_tail);
-
-	inode->i_size = inode->i_sb->s_blocksize;
-	i_size_write(inode, inode->i_sb->s_blocksize);
-	EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
-	ext4_update_final_de(dir_block->b_data,
-			inline_size - EXT4_INLINE_DOTDOT_SIZE + header_size,
-			inode->i_sb->s_blocksize - csum_size);
-
-	if (csum_size)
-		ext4_initialize_dirent_tail(dir_block,
-					    inode->i_sb->s_blocksize);
-	set_buffer_uptodate(dir_block);
-	unlock_buffer(dir_block);
-	err = ext4_handle_dirty_dirblock(handle, inode, dir_block);
-	if (err)
-		return err;
-	set_buffer_verified(dir_block);
-	return ext4_mark_inode_dirty(handle, inode);
-}
-
 static int ext4_convert_inline_data_nolock(handle_t *handle,
 					   struct inode *inode,
 					   struct ext4_iloc *iloc)
@@ -1175,8 +1140,17 @@ static int ext4_convert_inline_data_nolock(handle_t *handle,
 		error = ext4_handle_dirty_metadata(handle,
 						   inode, data_bh);
 	} else {
-		error = ext4_finish_convert_inline_dir(handle, inode, data_bh,
-						       buf, inline_size);
+		unlock_buffer(data_bh);
+		inode->i_size = inode->i_sb->s_blocksize;
+		i_size_write(inode, inode->i_sb->s_blocksize);
+		EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
+
+		error = ext4_init_dirblock(handle, inode, data_bh,
+			  le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode),
+			  buf + EXT4_INLINE_DOTDOT_SIZE,
+			  inline_size - EXT4_INLINE_DOTDOT_SIZE);
+		if (!error)
+			error = ext4_mark_inode_dirty(handle, inode);
 	}
 
 out_restore:
@@ -1315,7 +1289,7 @@ int ext4_inlinedir_to_tree(struct file *dir_file,
 		if (pos == 0) {
 			fake.inode = cpu_to_le32(inode->i_ino);
 			fake.name_len = 1;
-			strcpy(fake.name, ".");
+			memcpy(fake.name, ".", 2);
 			fake.rec_len = ext4_rec_len_to_disk(
 					  ext4_dir_rec_len(fake.name_len, NULL),
 					  inline_size);
@@ -1325,7 +1299,7 @@ int ext4_inlinedir_to_tree(struct file *dir_file,
 		} else if (pos == EXT4_INLINE_DOTDOT_OFFSET) {
 			fake.inode = cpu_to_le32(parent_ino);
 			fake.name_len = 2;
-			strcpy(fake.name, "..");
+			memcpy(fake.name, "..", 3);
 			fake.rec_len = ext4_rec_len_to_disk(
 					  ext4_dir_rec_len(fake.name_len, NULL),
 					  inline_size);
@@ -1864,7 +1838,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 	};
 
 
-	needed_blocks = ext4_writepage_trans_blocks(inode);
+	needed_blocks = ext4_chunk_trans_extent(inode, 1);
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
@@ -1903,7 +1877,12 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 			if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0)
 				goto out_error;
 
-			BUG_ON(is.s.not_found);
+			if (is.s.not_found) {
+				EXT4_ERROR_INODE(inode,
+						 "missing inline data xattr");
+				err = -EFSCORRUPTED;
+				goto out_error;
+			}
 
 			value_len = le32_to_cpu(is.s.here->e_value_size);
 			value = kmalloc(value_len, GFP_NOFS);
@@ -1979,7 +1958,7 @@ int ext4_convert_inline_data(struct inode *inode)
 			return 0;
 	}
 
-	needed_blocks = ext4_writepage_trans_blocks(inode);
+	needed_blocks = ext4_chunk_trans_extent(inode, 1);
 
 	iloc.bh = NULL;
 	error = ext4_get_inode_loc(inode, &iloc);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5c7024051f1e..ed54c4d0f2f9 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -723,8 +723,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		ext4_check_map_extents_env(inode);
 
 	/* Lookup extent status tree firstly */
-	if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) &&
-	    ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
 		if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
 			map->m_pblk = ext4_es_pblock(&es) +
 					map->m_lblk - es.es_lblk;
@@ -757,8 +756,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 				orig_mlen == map->m_len)
 			goto found;
 
-		if (flags & EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF)
-			map->m_len = orig_mlen;
+		map->m_len = orig_mlen;
 	}
 	/*
 	 * In the query cache no-wait mode, nothing we can do more if we
@@ -877,6 +875,26 @@ static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
 	} while (unlikely(!try_cmpxchg(&bh->b_state, &old_state, new_state)));
 }
 
+/*
+ * Make sure that the current journal transaction has enough credits to map
+ * one extent. Return -EAGAIN if it cannot extend the current running
+ * transaction.
+ */
+static inline int ext4_journal_ensure_extent_credits(handle_t *handle,
+						     struct inode *inode)
+{
+	int credits;
+	int ret;
+
+	/* Called from ext4_da_write_begin() which has no handle started? */
+	if (!handle)
+		return 0;
+
+	credits = ext4_chunk_trans_blocks(inode, 1);
+	ret = __ext4_journal_ensure_credits(handle, credits, credits, 0);
+	return ret <= 0 ? ret : -EAGAIN;
+}
+
 static int _ext4_get_block(struct inode *inode, sector_t iblock,
 			   struct buffer_head *bh, int flags)
 {
@@ -1171,11 +1189,13 @@ int ext4_block_write_begin(handle_t *handle, struct folio *folio,
 			}
 			continue;
 		}
-		if (buffer_new(bh))
+		if (WARN_ON_ONCE(buffer_new(bh)))
 			clear_buffer_new(bh);
 		if (!buffer_mapped(bh)) {
 			WARN_ON(bh->b_size != blocksize);
-			err = get_block(inode, block, bh, 1);
+			err = ext4_journal_ensure_extent_credits(handle, inode);
+			if (!err)
+				err = get_block(inode, block, bh, 1);
 			if (err)
 				break;
 			if (buffer_new(bh)) {
@@ -1274,7 +1294,8 @@ static int ext4_write_begin(const struct kiocb *iocb,
 	 * Reserve one block more for addition to orphan list in case
 	 * we allocate blocks but write fails for some reason
 	 */
-	needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
+	needed_blocks = ext4_chunk_trans_extent(inode,
+			ext4_journal_blocks_per_folio(inode)) + 1;
 	index = pos >> PAGE_SHIFT;
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
@@ -1372,8 +1393,9 @@ retry_journal:
 				ext4_orphan_del(NULL, inode);
 		}
 
-		if (ret == -ENOSPC &&
-		    ext4_should_retry_alloc(inode->i_sb, &retries))
+		if (ret == -EAGAIN ||
+		    (ret == -ENOSPC &&
+		     ext4_should_retry_alloc(inode->i_sb, &retries)))
 			goto retry_journal;
 		folio_put(folio);
 		return ret;
@@ -1393,6 +1415,7 @@ static int write_end_fn(handle_t *handle, struct inode *inode,
 	ret = ext4_dirty_journalled_data(handle, bh);
 	clear_buffer_meta(bh);
 	clear_buffer_prio(bh);
+	clear_buffer_new(bh);
 	return ret;
 }
 
@@ -1665,11 +1688,12 @@ struct mpage_da_data {
 	unsigned int can_map:1;	/* Can writepages call map blocks? */
 
 	/* These are internal state of ext4_do_writepages() */
-	pgoff_t first_page;	/* The first page to write */
-	pgoff_t next_page;	/* Current page to examine */
-	pgoff_t last_page;	/* Last page to examine */
+	loff_t start_pos;	/* The start pos to write */
+	loff_t next_pos;	/* Current pos to examine */
+	loff_t end_pos;		/* Last pos to examine */
+
 	/*
-	 * Extent to map - this can be after first_page because that can be
+	 * Extent to map - this can be after start_pos because that can be
 	 * fully mapped. We somewhat abuse m_flags to store whether the extent
 	 * is delalloc or unwritten.
 	 */
@@ -1689,38 +1713,38 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
 	struct inode *inode = mpd->inode;
 	struct address_space *mapping = inode->i_mapping;
 
-	/* This is necessary when next_page == 0. */
-	if (mpd->first_page >= mpd->next_page)
+	/* This is necessary when next_pos == 0. */
+	if (mpd->start_pos >= mpd->next_pos)
 		return;
 
 	mpd->scanned_until_end = 0;
-	index = mpd->first_page;
-	end   = mpd->next_page - 1;
 	if (invalidate) {
 		ext4_lblk_t start, last;
-		start = index << (PAGE_SHIFT - inode->i_blkbits);
-		last = end << (PAGE_SHIFT - inode->i_blkbits);
+		start = EXT4_B_TO_LBLK(inode, mpd->start_pos);
+		last = mpd->next_pos >> inode->i_blkbits;
 
 		/*
 		 * avoid racing with extent status tree scans made by
 		 * ext4_insert_delayed_block()
 		 */
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_es_remove_extent(inode, start, last - start + 1);
+		ext4_es_remove_extent(inode, start, last - start);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 
 	folio_batch_init(&fbatch);
-	while (index <= end) {
-		nr = filemap_get_folios(mapping, &index, end, &fbatch);
+	index = mpd->start_pos >> PAGE_SHIFT;
+	end = mpd->next_pos >> PAGE_SHIFT;
+	while (index < end) {
+		nr = filemap_get_folios(mapping, &index, end - 1, &fbatch);
 		if (nr == 0)
 			break;
 		for (i = 0; i < nr; i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			if (folio->index < mpd->first_page)
+			if (folio_pos(folio) < mpd->start_pos)
 				continue;
-			if (folio_next_index(folio) - 1 > end)
+			if (folio_next_index(folio) > end)
 				continue;
 			BUG_ON(!folio_test_locked(folio));
 			BUG_ON(folio_test_writeback(folio));
@@ -2022,7 +2046,8 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 
 static void mpage_folio_done(struct mpage_da_data *mpd, struct folio *folio)
 {
-	mpd->first_page += folio_nr_pages(folio);
+	mpd->start_pos += folio_size(folio);
+	mpd->wbc->nr_to_write -= folio_nr_pages(folio);
 	folio_unlock(folio);
 }
 
@@ -2032,7 +2057,7 @@ static int mpage_submit_folio(struct mpage_da_data *mpd, struct folio *folio)
 	loff_t size;
 	int err;
 
-	BUG_ON(folio->index != mpd->first_page);
+	WARN_ON_ONCE(folio_pos(folio) != mpd->start_pos);
 	folio_clear_dirty_for_io(folio);
 	/*
 	 * We have to be very careful here!  Nothing protects writeback path
@@ -2053,8 +2078,6 @@ static int mpage_submit_folio(struct mpage_da_data *mpd, struct folio *folio)
 	    !ext4_verity_in_progress(mpd->inode))
 		len = size & (len - 1);
 	err = ext4_bio_write_folio(&mpd->io_submit, folio, len);
-	if (!err)
-		mpd->wbc->nr_to_write -= folio_nr_pages(folio);
 
 	return err;
 }
@@ -2321,6 +2344,11 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 	int get_blocks_flags;
 	int err, dioread_nolock;
 
+	/* Make sure transaction has enough credits for this extent */
+	err = ext4_journal_ensure_extent_credits(handle, inode);
+	if (err < 0)
+		return err;
+
 	trace_ext4_da_write_pages_extent(inode, map);
 	/*
 	 * Call ext4_map_blocks() to allocate any delayed allocation blocks, or
@@ -2360,6 +2388,47 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 }
 
 /*
+ * This is used to submit mapped buffers in a single folio that is not fully
+ * mapped for various reasons, such as insufficient space or journal credits.
+ */
+static int mpage_submit_partial_folio(struct mpage_da_data *mpd)
+{
+	struct inode *inode = mpd->inode;
+	struct folio *folio;
+	loff_t pos;
+	int ret;
+
+	folio = filemap_get_folio(inode->i_mapping,
+				  mpd->start_pos >> PAGE_SHIFT);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
+	/*
+	 * The mapped position should be within the current processing folio
+	 * but must not be the folio start position.
+	 */
+	pos = ((loff_t)mpd->map.m_lblk) << inode->i_blkbits;
+	if (WARN_ON_ONCE((folio_pos(folio) == pos) ||
+			 !folio_contains(folio, pos >> PAGE_SHIFT)))
+		return -EINVAL;
+
+	ret = mpage_submit_folio(mpd, folio);
+	if (ret)
+		goto out;
+	/*
+	 * Update start_pos to prevent this folio from being released in
+	 * mpage_release_unused_pages(), it will be reset to the aligned folio
+	 * pos when this folio is written again in the next round. Additionally,
+	 * do not update wbc->nr_to_write here, as it will be updated once the
+	 * entire folio has finished processing.
+	 */
+	mpd->start_pos = pos;
+out:
+	folio_unlock(folio);
+	folio_put(folio);
+	return ret;
+}
+
+/*
  * mpage_map_and_submit_extent - map extent starting at mpd->lblk of length
  *				 mpd->len and submit pages underlying it for IO
  *
@@ -2407,10 +2476,18 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 			 * In the case of ENOSPC, if ext4_count_free_blocks()
 			 * is non-zero, a commit should free up blocks.
 			 */
-			if ((err == -ENOMEM) ||
+			if ((err == -ENOMEM) || (err == -EAGAIN) ||
 			    (err == -ENOSPC && ext4_count_free_clusters(sb))) {
-				if (progress)
+				/*
+				 * We may have already allocated extents for
+				 * some bhs inside the folio, issue the
+				 * corresponding data to prevent stale data.
+				 */
+				if (progress) {
+					if (mpage_submit_partial_folio(mpd))
+						goto invalidate_dirty_pages;
 					goto update_disksize;
+				}
 				return err;
 			}
 			ext4_msg(sb, KERN_CRIT,
@@ -2444,7 +2521,7 @@ update_disksize:
 	 * Update on-disk size after IO is submitted.  Races with
 	 * truncate are avoided by checking i_size under i_data_sem.
 	 */
-	disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT;
+	disksize = mpd->start_pos;
 	if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) {
 		int err2;
 		loff_t i_size;
@@ -2468,21 +2545,6 @@ update_disksize:
 	return err;
 }
 
-/*
- * Calculate the total number of credits to reserve for one writepages
- * iteration. This is called from ext4_writepages(). We map an extent of
- * up to MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping
- * the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN +
- * bpp - 1 blocks in bpp different extents.
- */
-static int ext4_da_writepages_trans_blocks(struct inode *inode)
-{
-	int bpp = ext4_journal_blocks_per_folio(inode);
-
-	return ext4_meta_trans_blocks(inode,
-				MAX_WRITEPAGES_EXTENT_LEN + bpp - 1, bpp);
-}
-
 static int ext4_journal_folio_buffers(handle_t *handle, struct folio *folio,
 				     size_t len)
 {
@@ -2547,8 +2609,8 @@ 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;
-	pgoff_t index = mpd->first_page;
-	pgoff_t end = mpd->last_page;
+	pgoff_t index = mpd->start_pos >> PAGE_SHIFT;
+	pgoff_t end = mpd->end_pos >> PAGE_SHIFT;
 	xa_mark_t tag;
 	int i, err = 0;
 	int blkbits = mpd->inode->i_blkbits;
@@ -2563,7 +2625,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 		tag = PAGECACHE_TAG_DIRTY;
 
 	mpd->map.m_len = 0;
-	mpd->next_page = index;
+	mpd->next_pos = mpd->start_pos;
 	if (ext4_should_journal_data(mpd->inode)) {
 		handle = ext4_journal_start(mpd->inode, EXT4_HT_WRITE_PAGE,
 					    bpp);
@@ -2594,7 +2656,8 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 				goto out;
 
 			/* If we can't merge this page, we are done. */
-			if (mpd->map.m_len > 0 && mpd->next_page != folio->index)
+			if (mpd->map.m_len > 0 &&
+			    mpd->next_pos != folio_pos(folio))
 				goto out;
 
 			if (handle) {
@@ -2640,8 +2703,8 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 			}
 
 			if (mpd->map.m_len == 0)
-				mpd->first_page = folio->index;
-			mpd->next_page = folio_next_index(folio);
+				mpd->start_pos = folio_pos(folio);
+			mpd->next_pos = folio_pos(folio) + folio_size(folio);
 			/*
 			 * Writeout when we cannot modify metadata is simple.
 			 * Just submit the page. For data=journal mode we
@@ -2769,12 +2832,12 @@ static int ext4_do_writepages(struct mpage_da_data *mpd)
 	mpd->journalled_more_data = 0;
 
 	if (ext4_should_dioread_nolock(inode)) {
+		int bpf = ext4_journal_blocks_per_folio(inode);
 		/*
 		 * We may need to convert up to one extent per block in
-		 * the page and we may dirty the inode.
+		 * the folio and we may dirty the inode.
 		 */
-		rsv_blocks = 1 + ext4_chunk_trans_blocks(inode,
-						PAGE_SIZE >> inode->i_blkbits);
+		rsv_blocks = 1 + ext4_ext_index_trans_blocks(inode, bpf);
 	}
 
 	if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
@@ -2784,18 +2847,18 @@ static int ext4_do_writepages(struct mpage_da_data *mpd)
 		writeback_index = mapping->writeback_index;
 		if (writeback_index)
 			cycled = 0;
-		mpd->first_page = writeback_index;
-		mpd->last_page = -1;
+		mpd->start_pos = writeback_index << PAGE_SHIFT;
+		mpd->end_pos = LLONG_MAX;
 	} else {
-		mpd->first_page = wbc->range_start >> PAGE_SHIFT;
-		mpd->last_page = wbc->range_end >> PAGE_SHIFT;
+		mpd->start_pos = wbc->range_start;
+		mpd->end_pos = wbc->range_end;
 	}
 
 	ext4_io_submit_init(&mpd->io_submit, wbc);
 retry:
 	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
-		tag_pages_for_writeback(mapping, mpd->first_page,
-					mpd->last_page);
+		tag_pages_for_writeback(mapping, mpd->start_pos >> PAGE_SHIFT,