path: root/fs/ext4/fast_commit.c

// SPDX-License-Identifier: GPL-2.0

/*
 * fs/ext4/fast_commit.c
 *
 * Written by Harshad Shirwadkar <harshadshirwadkar@gmail.com>
 *
 * Ext4 fast commits routines.
 */
#include "ext4.h"
#include "ext4_jbd2.h"
#include "ext4_extents.h"
#include "mballoc.h"

/*
 * Ext4 Fast Commits
 * -----------------
 *
 * Ext4 fast commits implement fine grained journalling for Ext4.
 *
 * Fast commits are organized as a log of tag-length-value (TLV) structs. (See
 * struct ext4_fc_tl). Each TLV contains some delta that is replayed TLV by
 * TLV during the recovery phase. For the scenarios for which we currently
 * don't have replay code, fast commit falls back to full commits.
 * Fast commits record delta in one of the following three categories.
 *
 * (A) Directory entry updates:
 *
 * - EXT4_FC_TAG_UNLINK		- records directory entry unlink
 * - EXT4_FC_TAG_LINK		- records directory entry link
 * - EXT4_FC_TAG_CREAT		- records inode and directory entry creation
 *
 * (B) File specific data range updates:
 *
 * - EXT4_FC_TAG_ADD_RANGE	- records addition of new blocks to an inode
 * - EXT4_FC_TAG_DEL_RANGE	- records deletion of blocks from an inode
 *
 * (C) Inode metadata (mtime / ctime etc):
 *
 * - EXT4_FC_TAG_INODE		- record the inode that should be replayed
 *				  during recovery. Note that iblocks field is
 *				  not replayed and instead derived during
 *				  replay.
 * Commit Operation
 * ----------------
 * With fast commits, we maintain all the directory entry operations in the
 * order in which they are issued in an in-memory queue. This queue is flushed
 * to disk during the commit operation. We also maintain a list of inodes
 * that need to be committed during a fast commit in another in memory queue of
 * inodes. During the commit operation, we commit in the following order:
 *
 * [1] Lock inodes for any further data updates by setting COMMITTING state
 * [2] Submit data buffers of all the inodes
 * [3] Wait for [2] to complete
 * [4] Commit all the directory entry updates in the fast commit space
 * [5] Commit all the changed inode structures
 * [6] Write tail tag (this tag ensures the atomicity, please read the following
 *     section for more details).
 * [7] Wait for [4], [5] and [6] to complete.
 *
 * All the inode updates must call ext4_fc_start_update() before starting an
 * update. If such an ongoing update is present, fast commit waits for it to
 * complete. The completion of such an update is marked by
 * ext4_fc_stop_update().
 *
 * Fast Commit Ineligibility
 * -------------------------
 * Not all operations are supported by fast commits today (e.g extended
 * attributes). Fast commit ineligiblity is marked by calling one of the
 * two following functions:
 *
 * - ext4_fc_mark_ineligible(): This makes next fast commit operation to fall
 *   back to full commit. This is useful in case of transient errors.
 *
 * - ext4_fc_start_ineligible() and ext4_fc_stop_ineligible() - This makes all
 *   the fast commits happening between ext4_fc_start_ineligible() and
 *   ext4_fc_stop_ineligible() and one fast commit after the call to
 *   ext4_fc_stop_ineligible() to fall back to full commits. It is important to
 *   make one more fast commit to fall back to full commit after stop call so
 *   that it guaranteed that the fast commit ineligible operation contained
 *   within ext4_fc_start_ineligible() and ext4_fc_stop_ineligible() is
 *   followed by at least 1 full commit.
 *
 * Atomicity of commits
 * --------------------
 * In order to gaurantee atomicity during the commit operation, fast commit
 * uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail
 * tag contains CRC of the contents and TID of the transaction after which
 * this fast commit should be applied. Recovery code replays fast commit
 * logs only if there's at least 1 valid tail present. For every fast commit
 * operation, there is 1 tail. This means, we may end up with multiple tails
 * in the fast commit space. Here's an example:
 *
 * - Create a new file A and remove existing file B
 * - fsync()
 * - Append contents to file A
 * - Truncate file A
 * - fsync()
 *
 * The fast commit space at the end of above operations would look like this:
 *      [HEAD] [CREAT A] [UNLINK B] [TAIL] [ADD_RANGE A] [DEL_RANGE A] [TAIL]
 *             |<---  Fast Commit 1   --->|<---      Fast Commit 2     ---->|
 *
 * Replay code should thus check for all the valid tails in the FC area.
 *
 * TODOs
 * -----
 * 1) Make fast commit atomic updates more fine grained. Today, a fast commit
 *    eligible update must be protected within ext4_fc_start_update() and
 *    ext4_fc_stop_update(). These routines are called at much higher
 *    routines. This can be made more fine grained by combining with
 *    ext4_journal_start().
 *
 * 2) Same above for ext4_fc_start_ineligible() and ext4_fc_stop_ineligible()
 *
 * 3) Handle more ineligible cases.
 */

#include <trace/events/ext4.h>
static struct kmem_cache *ext4_fc_dentry_cachep;

static void ext4_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
{
	BUFFER_TRACE(bh, "");
	if (uptodate) {
		ext4_debug("%s: Block %lld up-to-date",
			   __func__, bh->b_blocknr);
		set_buffer_uptodate(bh);
	} else {
		ext4_debug("%s: Block %lld not up-to-date",
			   __func__, bh->b_blocknr);
		clear_buffer_uptodate(bh);
	}

	unlock_buffer(bh);
}

static inline void ext4_fc_reset_inode(struct inode *inode)
{
	struct ext4_inode_info *ei = EXT4_I(inode);

	ei->i_fc_lblk_start = 0;
	ei->i_fc_lblk_len = 0;
}

void ext4_fc_init_inode(struct inode *inode)
{
	struct ext4_inode_info *ei = EXT4_I(inode);

	ext4_fc_reset_inode(inode);
	ext4_clear_inode_state(inode, EXT4_STATE_FC_COMMITTING);
	INIT_LIST_HEAD(&ei->i_fc_list);
	init_waitqueue_head(&ei->i_fc_wait);
	atomic_set(&ei->i_fc_updates, 0);
	ei->i_fc_committed_subtid = 0;
}

/*
 * Inform Ext4's fast about start of an inode update
 *
 * This function is called by the high level call VFS callbacks before
 * performing any inode update. This function blocks if there's an ongoing
 * fast commit on the inode in question.
 */
void ext4_fc_start_update(struct inode *inode)
{
	struct ext4_inode_info *ei = EXT4_I(inode);

	if (!test_opt2(inode->i_sb, JOURNAL_FAST_CO