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 <lkp@intel.com>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-6-harshadshirwadkar@gmail.comSigned-off-by: Theodore Ts'o <tytso@mit.edu>

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,
+		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:

fs/ext4/fast_commit.h

@@ -6,4 +6,114 @@
 /* Number of blocks in journal area to allocate for fast commits */
 #define EXT4_NUM_FC_BLKS		256
 
+/* Fast commit tags */
+#define EXT4_FC_TAG_ADD_RANGE		0x0001
+#define EXT4_FC_TAG_DEL_RANGE		0x0002
+#define EXT4_FC_TAG_CREAT		0x0003
+#define EXT4_FC_TAG_LINK		0x0004
+#define EXT4_FC_TAG_UNLINK		0x0005
+#define EXT4_FC_TAG_INODE		0x0006
+#define EXT4_FC_TAG_PAD			0x0007
+#define EXT4_FC_TAG_TAIL		0x0008
+#define EXT4_FC_TAG_HEAD		0x0009
+
+#define EXT4_FC_SUPPORTED_FEATURES	0x0
+
+/* On disk fast commit tlv value structures */
+
+/* Fast commit on disk tag length structure */
+struct ext4_fc_tl {
+	__le16 fc_tag;
+	__le16 fc_len;
+};
+
+/* Value structure for tag EXT4_FC_TAG_HEAD. */
+struct ext4_fc_head {
+	__le32 fc_features;
+	__le32 fc_tid;
+};
+
+/* Value structure for EXT4_FC_TAG_ADD_RANGE. */
+struct ext4_fc_add_range {
+	__le32 fc_ino;
+	__u8 fc_ex[12];
+};
+
+/* Value structure for tag EXT4_FC_TAG_DEL_RANGE. */
+struct ext4_fc_del_range {
+	__le32 fc_ino;
+	__le32 fc_lblk;
+	__le32 fc_len;
+};
+
+/*
+ * This is the value structure for tags EXT4_FC_TAG_CREAT, EXT4_FC_TAG_LINK
+ * and EXT4_FC_TAG_UNLINK.
+ */
+struct ext4_fc_dentry_info {
+	__le32 fc_parent_ino;
+	__le32 fc_ino;
+	u8 fc_dname[0];
+};
+
+/* Value structure for EXT4_FC_TAG_INODE and EXT4_FC_TAG_INODE_PARTIAL. */
+struct ext4_fc_inode {
+	__le32 fc_ino;
+	__u8 fc_raw_inode[0];
+};
+
+/* Value structure for tag EXT4_FC_TAG_TAIL. */
+struct ext4_fc_tail {
+	__le32 fc_tid;
+	__le32 fc_crc;
+};
+
+/*
+ * In memory list of dentry updates that are performed on the file
+ * system used by fast commit code.
+ */
+struct ext4_fc_dentry_update {
+	int fcd_op;		/* Type of update create / unlink / link */
+	int fcd_parent;		/* Parent inode number */
+	int fcd_ino;		/* Inode number */
+	struct qstr fcd_name;	/* Dirent name */
+	unsigned char fcd_iname[DNAME_INLINE_LEN];	/* Dirent name string */
+	struct list_head fcd_list;
+};
+
+/*
+ * Fast commit reason codes
+ */
+enum {
+	/*
+	 * Commit status codes:
+	 */
+	EXT4_FC_REASON_OK = 0,
+	EXT4_FC_REASON_INELIGIBLE,
+	EXT4_FC_REASON_ALREADY_COMMITTED,
+	EXT4_FC_REASON_FC_START_FAILED,
+	EXT4_FC_REASON_FC_FAILED,
+
+	/*
+	 * Fast commit ineligiblity reasons:
+	 */
+	EXT4_FC_REASON_XATTR = 0,
+	EXT4_FC_REASON_CROSS_RENAME,
+	EXT4_FC_REASON_JOURNAL_FLAG_CHANGE,
+	EXT4_FC_REASON_MEM,
+	EXT4_FC_REASON_SWAP_BOOT,
+	EXT4_FC_REASON_RESIZE,
+	EXT4_FC_REASON_RENAME_DIR,
+	EXT4_FC_REASON_FALLOC_RANGE,
+	EXT4_FC_COMMIT_FAILED,
+	EXT4_FC_REASON_MAX
+};
+
+struct ext4_fc_stats {
+	unsigned int fc_ineligible_reason_count[EXT4_FC_REASON_MAX];
+	unsigned long fc_num_commits;
+	unsigned long fc_ineligible_commits;
+	unsigned long fc_numblks;
+};
+
 #endif /* __FAST_COMMIT_H__ */

fs/ext4/file.c

@@ -260,6 +260,7 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		return -EOPNOTSUPP;
 
+	ext4_fc_start_update(inode);
 	inode_lock(inode);
 	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
@@ -271,6 +272,7 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
 
 out:
 	inode_unlock(inode);
+	ext4_fc_stop_update(inode);
 	if (likely(ret > 0)) {
 		iocb->ki_pos += ret;
 		ret = generic_write_sync(iocb, ret);
@@ -534,7 +536,9 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			goto out;
 		}
 
+		ext4_fc_start_update(inode);
 		ret = ext4_orphan_add(handle, inode);
+		ext4_fc_stop_update(inode);
 		if (ret) {
 			ext4_journal_stop(handle);
 			goto out;
@@ -656,7 +660,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 #endif
 	if (iocb->ki_flags & IOCB_DIRECT)
 		return ext4_dio_write_iter(iocb, from);
-
+	else
 		return ext4_buffered_write_iter(iocb, from);
 }
 
@@ -757,6 +761,7 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!daxdev_mapping_supported(vma, dax_dev))
 		return -EOPNOTSUPP;
 
+	ext4_fc_start_update(inode);
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
@@ -764,6 +769,7 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	} else {
 		vma->vm_ops = &ext4_file_vm_ops;
 	}
+	ext4_fc_stop_update(inode);
 	return 0;
 }
 

fs/ext4/fsync.c

@@ -112,7 +112,7 @@ static int ext4_fsync_journal(struct inode *inode, bool datasync,
 	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
 		*needs_barrier = true;
 
-	return jbd2_complete_transaction(journal, commit_tid);
+	return ext4_fc_commit(journal, commit_tid);
 }
 
 /*

fs/ext4/inode.c

@@ -729,6 +729,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 			if (ret)
 				return ret;
 		}
+		ext4_fc_track_range(inode, map->m_lblk,
+			    map->m_lblk + map->m_len - 1);
 	}
 
 	if (retval < 0)
@@ -3300,9 +3302,14 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 {
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 
-	if (journal)
-		return !jbd2_transaction_committed(journal,
-					EXT4_I(inode)->i_datasync_tid);
+	if (journal) {
+		if (jbd2_transaction_committed(journal,
+					EXT4_I(inode)->i_datasync_tid))
+			return true;
+		return atomic_read(&EXT4_SB(inode->i_sb)->s_fc_subtid) >=
+			EXT4_I(inode)->i_fc_committed_subtid;
+	}
+
 	/* Any metadata buffers to write? */
 	if (!list_empty(&inode->i_mapping->private_list))
 		return true;
@@ -4097,6 +4104,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
+	ext4_fc_track_range(inode, first_block, stop_block);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
@@ -4716,6 +4724,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	for (block = 0; block < EXT4_N_BLOCKS; block++)
 		ei->i_data[block] = raw_inode->i_block[block];
 	INIT_LIST_HEAD(&ei->i_orphan);
+	ext4_fc_init_inode(&ei->vfs_inode);
 
 	/*
 	 * Set transaction id's of transactions that have to be committed
@@ -5162,7 +5171,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
 		if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
 			return 0;
 
-		err = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
+		err = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
 						EXT4_I(inode)->i_sync_tid);
 	} else {
 		struct ext4_iloc iloc;
@@ -5291,6 +5300,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		if (error)
 			return error;
 	}
+	ext4_fc_start_update(inode);
 	if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
 	    (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
 		handle_t *handle;
@@ -5314,6 +5324,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 
 		if (error) {
 			ext4_journal_stop(handle);
+			ext4_fc_stop_update(inode);
 			return error;
 		}
 		/* Update corresponding info in inode so that everything is in
@@ -5336,11 +5347,15 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
-			if (attr->ia_size > sbi->s_bitmap_maxbytes)
+			if (attr->ia_size > sbi->s_bitmap_maxbytes) {
+				ext4_fc_stop_update(inode);
 				return -EFBIG;
 			}
-		if (!S_ISREG(inode->i_mode))
+		}
+		if (!S_ISREG(inode->i_mode)) {
+			ext4_fc_stop_update(inode);
 			return -EINVAL;
+		}
 
 		if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
 			inode_inc_iversion(inode);
@@ -5364,7 +5379,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		rc = ext4_break_layouts(inode);
 		if (rc) {
 			up_write(&EXT4_I(inode)->i_mmap_sem);
-			return rc;
+			goto err_out;
 		}
 
 		if (attr->ia_size != inode->i_size) {
@@ -5385,6 +5400,21 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				inode->i_mtime = current_time(inode);
 				inode->i_ctime = inode->i_mtime;
 			}
+
+			if (shrink)
+				ext4_fc_track_range(inode,
+					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits,
+					(oldsize > 0 ? oldsize - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits);
+			else
+				ext4_fc_track_range(
+					inode,
+					(oldsize > 0 ? oldsize - 1 : oldsize) >>
+					inode->i_sb->s_blocksize_bits,
+					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits);
+
 			down_write(&EXT4_I(inode)->i_data_sem);
 			EXT4_I(inode)->i_disksize = attr->ia_size;
 			rc = ext4_mark_inode_dirty(handle, inode);
@@ -5443,9 +5473,11 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		rc = posix_acl_chmod(inode, inode->i_mode);
 
 err_out:
+	if  (error)
 		ext4_std_error(inode->i_sb, error);
 	if (!error)
 		error = rc;
+	ext4_fc_stop_update(inode);
 	return error;
 }
 
@@ -5627,6 +5659,8 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 		put_bh(iloc->bh);
 		return -EIO;
 	}
+	ext4_fc_track_inode(inode);
+
 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
 
@@ -5950,6 +5984,8 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
+	ext4_fc_mark_ineligible(inode->i_sb,
+		EXT4_FC_REASON_JOURNAL_FLAG_CHANGE);
 	err = ext4_mark_inode_dirty(handle, inode);
 	ext4_handle_sync(handle);
 	ext4_journal_stop(handle);

fs/ext4/ioctl.c

@@ -165,6 +165,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 		err = -EINVAL;
 		goto err_out;
 	}
+	ext4_fc_start_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT);
 
 	/* Protect extent tree against block allocations via delalloc */
 	ext4_double_down_write_data_sem(inode, inode_bl);
@@ -247,6 +248,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 
 err_out1:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_ineligible(sb);
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
 err_out:
@@ -807,7 +809,7 @@ static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg)
 	return error;
 }
 
-long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	struct super_block *sb = inode->i_sb;
@@ -1074,6 +1076,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 		err = ext4_resize_fs(sb, n_blocks_count);
 		if (EXT4_SB(sb)->s_journal) {
+			ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE);
 			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
 			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
@@ -1308,6 +1311,17 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 }
 
+long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	long ret;
+
+	ext4_fc_start_update(file_inode(filp));
+	ret = __ext4_ioctl(filp, cmd, arg);
+	ext4_fc_stop_update(file_inode(filp));
+
+	return ret;
+}
+
 #ifdef CONFIG_COMPAT
 long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {

fs/ext4/namei.c

@@ -2611,7 +2611,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		       bool excl)
 {
 	handle_t *handle;
-	struct inode *inode;
+	struct inode *inode, *inode_save;
 	int err, credits, retries = 0;
 
 	err = dquot_initialize(dir);
@@ -2629,7 +2629,11 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		inode->i_op = &ext4_file_inode_operations;
 		inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
+		inode_save = inode;
+		ihold(inode_save);
 		err = ext4_add_nondir(handle, dentry, &inode);
+		ext4_fc_track_create(inode_save, dentry);
+		iput(inode_save);
 	}
 	if (handle)
 		ext4_journal_stop(handle);
@@ -2644,7 +2648,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry,
 		      umode_t mode, dev_t rdev)
 {
 	handle_t *handle;
-	struct inode *inode;
+	struct inode *inode, *inode_save;
 	int err, credits, retries = 0;
 
 	err = dquot_initialize(dir);
@@ -2661,7 +2665,12 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry,
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
 		inode->i_op = &ext4_special_inode_operations;
+		inode_save = inode;
+		ihold(inode_save);
 		err = ext4_add_nondir(handle, dentry, &inode);
+		if (!err)
+			ext4_fc_track_create(inode_save, dentry);
+		iput(inode_save);
 	}
 	if (handle)
 		ext4_journal_stop(handle);
@@ -2825,7 +2834,9 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		iput(inode);
 		goto out_retry;
 	}
+	ext4_fc_track_create(inode, dentry);
 	ext4_inc_count(dir);
+
 	ext4_update_dx_flag(dir);
 	err = ext4_mark_inode_dirty(handle, dir);
 	if (err)
@@ -3165,6 +3176,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 		goto end_rmdir;
 	ext4_dec_count(dir);
 	ext4_update_dx_flag(dir);
+	ext4_fc_track_unlink(inode, dentry);
 	retval = ext4_mark_inode_dirty(handle, dir);
 
 #ifdef CONFIG_UNICODE
@@ -3251,6 +3263,8 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	inode->i_ctime = current_time(inode);
 	retval = ext4_mark_inode_dirty(handle, inode);
 
+	if (!retval)
+		ext4_fc_track_unlink(d_inode(dentry), dentry);
 #ifdef CONFIG_UNICODE
 	/* VFS negative dentries are incompatible with Encoding and
 	 * Case-insensitiveness. Eventually we'll want avoid
@@ -3872,6 +3886,22 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	retval = ext4_mark_inode_dirty(handle, old.dir);
 	if (unlikely(retval))
 		goto end_rename;
+
+	if (S_ISDIR(old.inode->i_mode)) {
+		/*
+		 * We disable fast commits here that's because the
+		 * replay code is not yet capable of changing dot dot
+		 * dirents in directories.
+		 */
+		ext4_fc_mark_ineligible(old.inode->i_sb,
+			EXT4_FC_REASON_RENAME_DIR);
+	} else {
+		if (new.inode)
+			ext4_fc_track_unlink(new.inode, new.dentry);
+		ext4_fc_track_link(old.inode, new.dentry);
+		ext4_fc_track_unlink(old.inode, old.dentry);
+	}
+
 	if (new.inode) {
 		retval = ext4_mark_inode_dirty(handle, new.inode);
 		if (unlikely(retval))
@@ -4015,7 +4045,8 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	retval = ext4_mark_inode_dirty(handle, new.inode);
 	if (unlikely(retval))
 		goto end_rename;
-
+	ext4_fc_mark_ineligible(new.inode->i_sb,
+				EXT4_FC_REASON_CROSS_RENAME);
 	if (old.dir_bh) {
 		retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
 		if (retval)

fs/ext4/super.c

@@ -1331,6 +1331,8 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_unwritten, 0);
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
+	ext4_fc_init_inode(&ei->vfs_inode);
+	mutex_init(&ei->i_fc_lock);
 	return &ei->vfs_inode;
 }
 
@@ -1348,6 +1350,10 @@ static int ext4_drop_inode(struct inode *inode)
 static void ext4_free_in_core_inode(struct inode *inode)
 {
 	fscrypt_free_inode(inode);
+	if (!list_empty(&(EXT4_I(inode)->i_fc_list))) {
+		pr_warn("%s: inode %ld still in fc list",
+			__func__, inode->i_ino);
+	}
 	kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
 }
 
@@ -1373,6 +1379,7 @@ static void init_once(void *foo)
 	init_rwsem(&ei->i_data_sem);
 	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
+	ext4_fc_init_inode(&ei->vfs_inode);
 }
 
 static int __init init_inodecache(void)
@@ -1401,6 +1408,7 @@ static void destroy_inodecache(void)
 
 void ext4_clear_inode(struct inode *inode)
 {
+	ext4_fc_del(inode);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	ext4_discard_preallocations(inode, 0);
@@ -4744,6 +4752,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
 
+	/* Initialize fast commit stuff */
+	atomic_set(&sbi->s_fc_subtid, 0);
+	atomic_set(&sbi->s_fc_ineligible_updates, 0);
+	INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_MAIN]);
+	INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_STAGING]);
+	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]);
+	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]);
+	sbi->s_fc_bytes = 0;
+	sbi->s_mount_state &= ~EXT4_FC_INELIGIBLE;
+	sbi->s_mount_state &= ~EXT4_FC_COMMITTING;
+	spin_lock_init(&sbi->s_fc_lock);
+	memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
+
 	sb->s_root = NULL;
 
 	needs_recovery = (es->s_last_orphan != 0 ||
@@ -6515,6 +6536,10 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 	brelse(bh);
 out:
 	if (inode->i_size < off + len) {
+		ext4_fc_track_range(inode,
+			(inode->i_size > 0 ? inode->i_size - 1 : 0)
+				>> inode->i_sb->s_blocksize_bits,
+			(off + len) >> inode->i_sb->s_blocksize_bits);
 		i_size_write(inode, off + len);
 		EXT4_I(inode)->i_disksize = inode->i_size;
 		err2 = ext4_mark_inode_dirty(handle, inode);
@@ -6643,6 +6668,11 @@ static int __init ext4_init_fs(void)
 	err = init_inodecache();
 	if (err)
 		goto out1;
+
+	err = ext4_fc_init_dentry_cache();
+	if (err)
+		goto out05;
+
 	register_as_ext3();
 	register_as_ext2();
 	err = register_filesystem(&ext4_fs_type);
@@ -6653,6 +6683,7 @@ static int __init ext4_init_fs(void)
 out:
 	unregister_as_ext2();
 	unregister_as_ext3();
+out05:
 	destroy_inodecache();
 out1:
 	ext4_exit_mballoc();

fs/ext4/xattr.c

@@ -2419,6 +2419,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		if (IS_SYNC(inode))
 			ext4_handle_sync(handle);
 	}
+	ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
 
 cleanup:
 	brelse(is.iloc.bh);
@@ -2496,6 +2497,7 @@ ext4_xattr_set(struct inode *inode, int name_index, const char *name,
 		if (error == 0)
 			error = error2;
 	}
+	ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
 
 	return error;
 }
@@ -2928,6 +2930,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
 					 error);
 			goto cleanup;
 		}
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
 	}
 	error = 0;
 cleanup:

include/trace/events/ext4.h

@@ -95,6 +95,16 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B);
 	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"},	\
 	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 
+#define show_fc_reason(reason)						\
+	__print_symbolic(reason,					\
+		{ EXT4_FC_REASON_XATTR,		"XATTR"},		\
+		{ EXT4_FC_REASON_CROSS_RENAME,	"CROSS_RENAME"},	\
+		{ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \
+		{ EXT4_FC_REASON_MEM,	"NO_MEM"},			\
+		{ EXT4_FC_REASON_SWAP_BOOT,	"SWAP_BOOT"},		\
+		{ EXT4_FC_REASON_RESIZE,	"RESIZE"},		\
+		{ EXT4_FC_REASON_RENAME_DIR,	"RENAME_DIR"},		\
+		{ EXT4_FC_REASON_FALLOC_RANGE,	"FALLOC_RANGE"})
 
 TRACE_EVENT(ext4_other_inode_update_time,
 	TP_PROTO(struct inode *inode, ino_t orig_ino),
@@ -2791,6 +2801,168 @@ TRACE_EVENT(ext4_lazy_itable_init,
 		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group)
 );
 
+TRACE_EVENT(ext4_fc_commit_start,
+	TP_PROTO(struct super_block *sb),
+
+	TP_ARGS(sb),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+	),
+
+	TP_printk("fast_commit started on dev %d,%d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev))
+);
+
+TRACE_EVENT(ext4_fc_commit_stop,
+	    TP_PROTO(struct super_block *sb, int nblks, int reason),
+
+	TP_ARGS(sb, nblks, reason),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, nblks)
+		__field(int, reason)
+		__field(int, num_fc)
+		__field(int, num_fc_ineligible)
+		__field(int, nblks_agg)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->nblks = nblks;
+		__entry->reason = reason;
+		__entry->num_fc = EXT4_SB(sb)->s_fc_stats.fc_num_commits;
+		__entry->num_fc_ineligible =
+			EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits;
+		__entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks;
+	),
+
+	TP_printk("fc on [%d,%d] nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nblks, __entry->reason, __entry->num_fc,
+		  __entry->num_fc_ineligible, __entry->nblks_agg)
+);
+
+#define FC_REASON_NAME_STAT(reason)					\
+	show_fc_reason(reason),						\
+	__entry->sbi->s_fc_stats.fc_ineligible_reason_count[reason]
+
+TRACE_EVENT(ext4_fc_stats,
+	    TP_PROTO(struct super_block *sb),
+
+	    TP_ARGS(sb),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(struct ext4_sb_info *, sbi)
+		    __field(int, count)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = sb->s_dev;
+		    __entry->sbi = EXT4_SB(sb);
+		    ),
+
+	    TP_printk("dev %d:%d fc ineligible reasons:\n"
+		      "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; "
+		      "num_commits:%ld, ineligible: %ld, numblks: %ld",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE),
+		      __entry->sbi->s_fc_stats.fc_num_commits,
+		      __entry->sbi->s_fc_stats.fc_ineligible_commits,
+		      __entry->sbi->s_fc_stats.fc_numblks)
+
+);
+
+#define DEFINE_TRACE_DENTRY_EVENT(__type)				\
+	TRACE_EVENT(ext4_fc_track_##__type,				\
+	    TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), \
+									\
+	    TP_ARGS(inode, dentry, ret),				\
+									\
+	    TP_STRUCT__entry(						\
+		    __field(dev_t, dev)					\
+		    __field(int, ino)					\
+		    __field(int, error)					\
+		    ),							\
+									\
+	    TP_fast_assign(						\
+		    __entry->dev = inode->i_sb->s_dev;			\
+		    __entry->ino = inode->i_ino;			\
+		    __entry->error = ret;				\
+		    ),							\
+									\
+	    TP_printk("dev %d:%d, inode %d, error %d, fc_%s",		\
+		      MAJOR(__entry->dev), MINOR(__entry->dev),		\
+		      __entry->ino, __entry->error,			\
+		      #__type)						\
+	)
+
+DEFINE_TRACE_DENTRY_EVENT(create);
+DEFINE_TRACE_DENTRY_EVENT(link);
+DEFINE_TRACE_DENTRY_EVENT(unlink);
+
+TRACE_EVENT(ext4_fc_track_inode,
+	    TP_PROTO(struct inode *inode, int ret),
+
+	    TP_ARGS(inode, ret),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(int, ino)
+		    __field(int, error)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = inode->i_sb->s_dev;
+		    __entry->ino = inode->i_ino;
+		    __entry->error = ret;
+		    ),
+
+	    TP_printk("dev %d:%d, inode %d, error %d",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      __entry->ino, __entry->error)
+	);
+
+TRACE_EVENT(ext4_fc_track_range,
+	    TP_PROTO(struct inode *inode, long start, long end, int ret),
+
+	    TP_ARGS(inode, start, end, ret),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(int, ino)
+		    __field(long, start)
+		    __field(long, end)
+		    __field(int, error)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = inode->i_sb->s_dev;
+		    __entry->ino = inode->i_ino;
+		    __entry->start = start;
+		    __entry->end = end;
+		    __entry->error = ret;
+		    ),
+
+	    TP_printk("dev %d:%d, inode %d, error %d, start %ld, end %ld",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      __entry->ino, __entry->error, __entry->start,
+		      __entry->end)
+	);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */