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

Pull ext4 updates from Ted Ts'o:
 "Various cleanups and bug fixes in ext4's extent status tree,
  journalling, and block allocator subsystems.

  Also improve performance for parallel DIO overwrites"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (55 commits)
  ext4: avoid updating the superblock on a r/o mount if not needed
  jbd2: skip reading super block if it has been verified
  ext4: fix to check return value of freeze_bdev() in ext4_shutdown()
  ext4: refactoring to use the unified helper ext4_quotas_off()
  ext4: turn quotas off if mount failed after enabling quotas
  ext4: update doc about journal superblock description
  ext4: add journal cycled recording support
  jbd2: continue to record log between each mount
  jbd2: remove j_format_version
  jbd2: factor out journal initialization from journal_get_superblock()
  jbd2: switch to check format version in superblock directly
  jbd2: remove unused feature macros
  ext4: ext4_put_super: Remove redundant checking for 'sbi->s_journal_bdev'
  ext4: Fix reusing stale buffer heads from last failed mounting
  ext4: allow concurrent unaligned dio overwrites
  ext4: clean up mballoc criteria comments
  ext4: make ext4_zeroout_es() return void
  ext4: make ext4_es_insert_extent() return void
  ext4: make ext4_es_insert_delayed_block() return void
  ext4: make ext4_es_remove_extent() return void
  ...

Author: torvalds

Documentation/filesystems/ext4/journal.rst

@@ -260,8 +260,13 @@ which is 1024 bytes long:
      - s_num_fc_blocks
      - Number of fast commit blocks in the journal.
    * - 0x58
+     - __be32
+     - s_head
+     - Block number of the head (first unused block) of the journal, only
+       up-to-date when the journal is empty.
+   * - 0x5C
      - __u32
-     - s_padding[42]
+     - s_padding[40]
      -
    * - 0xFC
      - __be32

fs/ext4/ext4.h

@@ -127,6 +127,58 @@ enum SHIFT_DIRECTION {
 	SHIFT_RIGHT,
 };
 
+/*
+ * For each criteria, mballoc has slightly different way of finding
+ * the required blocks nad usually, higher the criteria the slower the
+ * allocation.  We start at lower criterias and keep falling back to
+ * higher ones if we are not able to find any blocks.  Lower (earlier)
+ * criteria are faster.
+ */
+enum criteria {
+	/*
+	 * Used when number of blocks needed is a power of 2. This
+	 * doesn't trigger any disk IO except prefetch and is the
+	 * fastest criteria.
+	 */
+	CR_POWER2_ALIGNED,
+
+	/*
+	 * Tries to lookup in-memory data structures to find the most
+	 * suitable group that satisfies goal request. No disk IO
+	 * except block prefetch.
+	 */
+	CR_GOAL_LEN_FAST,
+
+        /*
+	 * Same as CR_GOAL_LEN_FAST but is allowed to reduce the goal
+         * length to the best available length for faster allocation.
+	 */
+	CR_BEST_AVAIL_LEN,
+
+	/*
+	 * Reads each block group sequentially, performing disk IO if
+	 * necessary, to find find_suitable block group. Tries to
+	 * allocate goal length but might trim the request if nothing
+	 * is found after enough tries.
+	 */
+	CR_GOAL_LEN_SLOW,
+
+	/*
+	 * Finds the first free set of blocks and allocates
+	 * those. This is only used in rare cases when
+	 * CR_GOAL_LEN_SLOW also fails to allocate anything.
+	 */
+	CR_ANY_FREE,
+
+	/*
+	 * Number of criterias defined.
+	 */
+	EXT4_MB_NUM_CRS
+};
+
+/* criteria below which we use fast block scanning and avoid unnecessary IO */
+#define CR_FAST CR_GOAL_LEN_SLOW
+
 /*
  * Flags used in mballoc's allocation_context flags field.
  *
@@ -165,9 +217,12 @@ enum SHIFT_DIRECTION {
 /* 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 = 0 */
-#define EXT4_MB_CR0_OPTIMIZED		0x8000
+#define EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED		0x8000
 /* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */
-#define EXT4_MB_CR1_OPTIMIZED		0x00010000
+#define EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED		0x00010000
+/* Avg fragment size rb tree lookup succeeded at least once for cr = 1.5 */
+#define EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED		0x00020000
+
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
 	struct inode *inode;
@@ -1532,21 +1587,25 @@ struct ext4_sb_info {
 	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;
 
 	/* 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 */
 	atomic_t s_bal_allocated;	/* in blocks */
 	atomic_t s_bal_ex_scanned;	/* total extents scanned */
+	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_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_cr0_bad_suggestions;
-	atomic_t s_bal_cr1_bad_suggestions;
-	atomic64_t s_bal_cX_groups_considered[4];
-	atomic64_t s_bal_cX_hits[4];
-	atomic64_t s_bal_cX_failed[4];		/* cX loop didn't find blocks */
+	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 */
 	atomic_t s_mb_buddies_generated;	/* number of buddies generated */
 	atomic64_t s_mb_generation_time;
 	atomic_t s_mb_lost_chunks;
@@ -2632,10 +2691,6 @@ extern void ext4_get_group_no_and_offset(struct super_block *sb,
 extern ext4_group_t ext4_get_group_number(struct super_block *sb,
 					  ext4_fsblk_t block);
 
-extern unsigned int ext4_block_group(struct super_block *sb,
-			ext4_fsblk_t blocknr);
-extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
-			ext4_fsblk_t blocknr);
 extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
 extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
 			ext4_group_t group);
@@ -2841,8 +2896,6 @@ int ext4_fc_record_regions(struct super_block *sb, int ino,
 /* mballoc.c */
 extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern const struct seq_operations ext4_mb_seq_structs_summary_ops;
-extern long ext4_mb_stats;
-extern long ext4_mb_max_to_scan;
 extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset);
 extern int ext4_mb_init(struct super_block *);
 extern int ext4_mb_release(struct super_block *);
@@ -3481,14 +3534,8 @@ extern int ext4_try_to_write_inline_data(struct address_space *mapping,
 					 struct inode *inode,
 					 loff_t pos, unsigned len,
 					 struct page **pagep);
-extern int ext4_write_inline_data_end(struct inode *inode,
-				      loff_t pos, unsigned len,
-				      unsigned copied,
-				      struct page *page);
-extern struct buffer_head *
-ext4_journalled_write_inline_data(struct inode *inode,
-				  unsigned len,
-				  struct page *page);
+int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
+			       unsigned copied, struct folio *folio);
 extern int ext4_da_write_inline_data_begin(struct address_space *mapping,
 					   struct inode *inode,
 					   loff_t pos, unsigned len,

fs/ext4/extents.c

@@ -3123,7 +3123,7 @@ void ext4_ext_release(struct super_block *sb)
 #endif
 }
 
-static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
+static void ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
 {
 	ext4_lblk_t  ee_block;
 	ext4_fsblk_t ee_pblock;
@@ -3134,10 +3134,10 @@ static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
 	ee_pblock = ext4_ext_pblock(ex);
 
 	if (ee_len == 0)
-		return 0;
+		return;
 
-	return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
-				     EXTENT_STATUS_WRITTEN);
+	ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
+			      EXTENT_STATUS_WRITTEN);
 }
 
 /* FIXME!! we need to try to merge to left or right after zero-out  */
@@ -3287,7 +3287,7 @@ static int ext4_split_extent_at(handle_t *handle,
 			err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 			if (!err)
 				/* update extent status tree */
-				err = ext4_zeroout_es(inode, &zero_ex);
+				ext4_zeroout_es(inode, &zero_ex);
 			/* If we failed at this point, we don't know in which
 			 * state the extent tree exactly is so don't try to fix
 			 * length of the original extent as it may do even more
@@ -3640,9 +3640,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 out:
 	/* If we have gotten a failure, don't zero out status tree */
 	if (!err) {
-		err = ext4_zeroout_es(inode, &zero_ex1);
-		if (!err)
-			err = ext4_zeroout_es(inode, &zero_ex2);
+		ext4_zeroout_es(inode, &zero_ex1);
+		ext4_zeroout_es(inode, &zero_ex2);
 	}
 	return err ? err : allocated;
 }
@@ -4403,15 +4402,8 @@ int ext4_ext_truncate(handle_t *handle, struct inode *inode)
 
 	last_block = (inode->i_size + sb->s_blocksize - 1)
 			>> EXT4_BLOCK_SIZE_BITS(sb);
-retry:
-	err = ext4_es_remove_extent(inode, last_block,
-				    EXT_MAX_BLOCKS - last_block);
-	if (err == -ENOMEM) {
-		memalloc_retry_wait(GFP_ATOMIC);
-		goto retry;
-	}
-	if (err)
-		return err;
+	ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block);
+
 retry_remove_space:
 	err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
 	if (err == -ENOMEM) {
@@ -5363,13 +5355,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ext4_discard_preallocations(inode, 0);
-
-	ret = ext4_es_remove_extent(inode, punch_start,
-				    EXT_MAX_BLOCKS - punch_start);
-	if (ret) {
-		up_write(&EXT4_I(inode)->i_data_sem);
-		goto out_stop;
-	}
+	ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start);
 
 	ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
 	if (ret) {
@@ -5547,12 +5533,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
 		ext4_free_ext_path(path);
 	}
 
-	ret = ext4_es_remove_extent(inode, offset_lblk,
-			EXT_MAX_BLOCKS - offset_lblk);
-	if (ret) {
-		up_write(&EXT4_I(inode)->i_data_sem);
-		goto out_stop;
-	}
+	ext4_es_remove_extent(inode, offset_lblk, EXT_MAX_BLOCKS - offset_lblk);
 
 	/*
 	 * if offset_lblk lies in a hole which is at start of file, use
@@ -5610,12 +5591,8 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1,
 	BUG_ON(!inode_is_locked(inode1));
 	BUG_ON(!inode_is_locked(inode2));
 
-	*erp = ext4_es_remove_extent(inode1, lblk1, count);
-	if (unlikely(*erp))
-		return 0;
-	*erp = ext4_es_remove_extent(inode2, lblk2, count);
-	if (unlikely(*erp))
-		return 0;
+	ext4_es_remove_extent(inode1, lblk1, count);
+	ext4_es_remove_extent(inode2, lblk2, count);
 
 	while (count) {
 		struct ext4_extent *ex1, *ex2, tmp_ex;