ext4: main fast-commit commit path

This patch adds main fast commit commit path handlers. The overall
patch can be divided into two inter-related parts:

(A) Metadata updates tracking

    This part consists of helper functions to track changes that need
    to be committed during a commit operation. These updates are
    maintained by Ext4 in different in-memory queues. Following are
    the APIs and their short description that are implemented in this
    patch:

    - ext4_fc_track_link/unlink/creat() - Track unlink. link and creat
      operations
    - ext4_fc_track_range() - Track changed logical block offsets
      inodes
    - ext4_fc_track_inode() - Track inodes
    - ext4_fc_mark_ineligible() - Mark file system fast commit
      ineligible()
    - ext4_fc_start_update() / ext4_fc_stop_update() /
      ext4_fc_start_ineligible() / ext4_fc_stop_ineligible() These
      functions are useful for co-ordinating inode updates with
      commits.

(B) Main commit Path

    This part consists of functions to convert updates tracked in
    in-memory data structures into on-disk commits. Function
    ext4_fc_commit() is the main entry point to commit path.

Reported-by: kernel test robot <[email protected]>
Signed-off-by: Harshad Shirwadkar <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Theodore Ts'o <[email protected]>

Author: harshadjs

fs/ext4/acl.c

@@ -242,6 +242,7 @@ ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
+	ext4_fc_start_update(inode);
 
 	if ((type == ACL_TYPE_ACCESS) && acl) {
 		error = posix_acl_update_mode(inode, &mode, &acl);
@@ -259,6 +260,7 @@ ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	}
 out_stop:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_update(inode);
 	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
 	return error;

fs/ext4/ext4.h

@@ -1021,6 +1021,31 @@ struct ext4_inode_info {
 
 	struct list_head i_orphan;	/* unlinked but open inodes */
 
+	/* Fast commit related info */
+
+	struct list_head i_fc_list;	/*
+					 * inodes that need fast commit
+					 * protected by sbi->s_fc_lock.
+					 */
+
+	/* Fast commit subtid when this inode was committed */
+	unsigned int i_fc_committed_subtid;
+
+	/* Start of lblk range that needs to be committed in this fast commit */
+	ext4_lblk_t i_fc_lblk_start;
+
+	/* End of lblk range that needs to be committed in this fast commit */
+	ext4_lblk_t i_fc_lblk_len;
+
+	/* Number of ongoing updates on this inode */
+	atomic_t  i_fc_updates;
+
+	/* Fast commit wait queue for this inode */
+	wait_queue_head_t i_fc_wait;
+
+	/* Protect concurrent accesses on i_fc_lblk_start, i_fc_lblk_len */
+	struct mutex i_fc_lock;
+
 	/*
 	 * i_disksize keeps track of what the inode size is ON DISK, not
 	 * in memory.  During truncate, i_size is set to the new size by
@@ -1141,6 +1166,10 @@ struct ext4_inode_info {
 #define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
 #define	EXT4_ERROR_FS			0x0002	/* Errors detected */
 #define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
+#define EXT4_FC_INELIGIBLE		0x0008	/* Fast commit ineligible */
+#define EXT4_FC_COMMITTING		0x0010	/* File system underoing a fast
+						 * commit.
+						 */
 
 /*
  * Misc. filesystem flags
@@ -1613,6 +1642,30 @@ struct ext4_sb_info {
 	/* Record the errseq of the backing block device */
 	errseq_t s_bdev_wb_err;
 	spinlock_t s_bdev_wb_lock;
+
+	/* Ext4 fast commit stuff */
+	atomic_t s_fc_subtid;
+	atomic_t s_fc_ineligible_updates;
+	/*
+	 * After commit starts, the main queue gets locked, and the further
+	 * updates get added in the staging queue.
+	 */
+#define FC_Q_MAIN	0
+#define FC_Q_STAGING	1
+	struct list_head s_fc_q[2];	/* Inodes staged for fast commit
+					 * that have data changes in them.
+					 */
+	struct list_head s_fc_dentry_q[2];	/* directory entry updates */
+	unsigned int s_fc_bytes;
+	/*
+	 * Main fast commit lock. This lock protects accesses to the
+	 * following fields:
+	 * ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh.
+	 */
+	spinlock_t s_fc_lock;
+	struct buffer_head *s_fc_bh;
+	struct ext4_fc_stats s_fc_stats;
+	u64 s_fc_avg_commit_time;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1723,6 +1776,7 @@ enum {
 	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
 	EXT4_STATE_LUSTRE_EA_INODE,	/* Lustre-style ea_inode */
 	EXT4_STATE_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
+	EXT4_STATE_FC_COMMITTING,	/* Fast commit ongoing */
 };
 
 #define EXT4_INODE_BIT_FNS(name, field, offset)				\
@@ -2682,6 +2736,22 @@ extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
 /* fast_commit.c */
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal);
+void ext4_fc_init_inode(struct inode *inode);
+void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+			 ext4_lblk_t end);
+void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry);
+void ext4_fc_track_link(struct inode *inode, struct dentry *dentry);
+void ext4_fc_track_create(struct inode *inode, struct dentry *dentry);
+void ext4_fc_track_inode(struct inode *inode);
+void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
+void ext4_fc_start_ineligible(struct super_block *sb, int reason);
+void ext4_fc_stop_ineligible(struct super_block *sb);
+void ext4_fc_start_update(struct inode *inode);
+void ext4_fc_stop_update(struct inode *inode);
+void ext4_fc_del(struct inode *inode);
+int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
+int __init ext4_fc_init_dentry_cache(void);
+
 /* mballoc.c */
 extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern long ext4_mb_stats;

fs/ext4/extents.c

@@ -3723,6 +3723,7 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 out:
 	ext4_ext_show_leaf(inode, path);
+	ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
 	return err;
 }
 
@@ -3794,6 +3795,7 @@ convert_initialized_extent(handle_t *handle, struct inode *inode,
 	if (*allocated > map->m_len)
 		*allocated = map->m_len;
 	map->m_len = *allocated;
+	ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
 	return 0;
 }
 
@@ -4327,7 +4329,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	map->m_len = ar.len;
 	allocated = map->m_len;
 	ext4_ext_show_leaf(inode, path);
-
+	ext4_fc_track_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1);
 out:
 	ext4_ext_drop_refs(path);
 	kfree(path);
@@ -4600,7 +4602,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	ret = ext4_mark_inode_dirty(handle, inode);
 	if (unlikely(ret))
 		goto out_handle;
-
+	ext4_fc_track_range(inode, offset >> inode->i_sb->s_blocksize_bits,
+			(offset + len - 1) >> inode->i_sb->s_blocksize_bits);
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
 	if (ret >= 0)
@@ -4648,23 +4651,34 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
 		     FALLOC_FL_INSERT_RANGE))
 		return -EOPNOTSUPP;
+	ext4_fc_track_range(inode, offset >> blkbits,
+			(offset + len - 1) >> blkbits);
 
-	if (mode & FALLOC_FL_PUNCH_HOLE)
-		return ext4_punch_hole(inode, offset, len);
+	ext4_fc_start_update(inode);
+
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		ret = ext4_punch_hole(inode, offset, len);
+		goto exit;
+	}
 
 	ret = ext4_convert_inline_data(inode);
 	if (ret)
-		return ret;
+		goto exit;
 
-	if (mode & FALLOC_FL_COLLAPSE_RANGE)
-		return ext4_collapse_range(inode, offset, len);
-
-	if (mode & FALLOC_FL_INSERT_RANGE)
-		return ext4_insert_range(inode, offset, len);
+	if (mode & FALLOC_FL_COLLAPSE_RANGE) {
+		ret = ext4_collapse_range(inode, offset, len);
+		goto exit;
+	}
 
-	if (mode & FALLOC_FL_ZERO_RANGE)
-		return ext4_zero_range(file, offset, len, mode);
+	if (mode & FALLOC_FL_INSERT_RANGE) {
+		ret = ext4_insert_range(inode, offset, len);
+		goto exit;
+	}
 
+	if (mode & FALLOC_FL_ZERO_RANGE) {
+		ret = ext4_zero_range(file, offset, len, mode);
+		goto exit;
+	}
 	trace_ext4_fallocate_enter(inode, offset, len, mode);
 	lblk = offset >> blkbits;
 
@@ -4698,12 +4712,14 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		goto out;
 
 	if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) {
-		ret = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
-						EXT4_I(inode)->i_sync_tid);
+		ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
+					EXT4_I(inode)->i_sync_tid);
 	}
 out:
 	inode_unlock(inode);
 	trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
+exit:
+	ext4_fc_stop_update(inode);
 	return ret;
 }
 
@@ -5291,6 +5307,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		ret = PTR_ERR(handle);
 		goto out_mmap;
 	}
+	ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ext4_discard_preallocations(inode, 0);
@@ -5329,6 +5346,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_ineligible(sb);
 out_mmap:
 	up_write(&EXT4_I(inode)->i_mmap_sem);
 out_mutex:
@@ -5429,6 +5447,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 		ret = PTR_ERR(handle);
 		goto out_mmap;
 	}
+	ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
 
 	/* Expand file to avoid data loss if there is error while shifting */
 	inode->i_size += len;
@@ -5503,6 +5522,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_ineligible(sb);
 out_mmap:
 	up_write(&EXT4_I(inode)->i_mmap_sem);
 out_mutex: