jbd2: add fast commit machinery

This functions adds necessary APIs needed in JBD2 layer for fast
commits.
Signed-off-by: NHarshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-5-harshadshirwadkar@gmail.comSigned-off-by: NTheodore Ts'o <tytso@mit.edu>

fs/ext4/fast_commit.c

@@ -8,11 +8,19 @@
  * Ext4 fast commits routines.
  */
 #include "ext4_jbd2.h"
+/*
+ * Fast commit cleanup routine. This is called after every fast commit and
+ * full commit. full is true if we are called after a full commit.
+ */
+static void ext4_fc_cleanup(journal_t *journal, int full)
+{
+}
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
+	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
 	if (jbd2_fc_init(journal, EXT4_NUM_FC_BLKS)) {
 		pr_warn("Error while enabling fast commits, turning off.");
 		ext4_clear_feature_fast_commit(sb);

fs/jbd2/commit.c

@@ -206,6 +206,30 @@ int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 	return generic_writepages(mapping, &wbc);
 }
 
+/* Send all the data buffers related to an inode */
+int jbd2_submit_inode_data(struct jbd2_inode *jinode)
+{
+
+	if (!jinode || !(jinode->i_flags & JI_WRITE_DATA))
+		return 0;
+
+	trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
+	return jbd2_journal_submit_inode_data_buffers(jinode);
+
+}
+EXPORT_SYMBOL(jbd2_submit_inode_data);
+
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode)
+{
+	if (!jinode || !(jinode->i_flags & JI_WAIT_DATA) ||
+		!jinode->i_vfs_inode || !jinode->i_vfs_inode->i_mapping)
+		return 0;
+	return filemap_fdatawait_range_keep_errors(
+		jinode->i_vfs_inode->i_mapping, jinode->i_dirty_start,
+		jinode->i_dirty_end);
+}
+EXPORT_SYMBOL(jbd2_wait_inode_data);
+
 /*
  * Submit all the data buffers of inode associated with the transaction to
  * disk.
@@ -415,6 +439,20 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	J_ASSERT(journal->j_running_transaction != NULL);
 	J_ASSERT(journal->j_committing_transaction == NULL);
 
+	write_lock(&journal->j_state_lock);
+	journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	while (journal->j_flags & JBD2_FAST_COMMIT_ONGOING) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_fc_wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		write_unlock(&journal->j_state_lock);
+		schedule();
+		write_lock(&journal->j_state_lock);
+		finish_wait(&journal->j_fc_wait, &wait);
+	}
+	write_unlock(&journal->j_state_lock);
+
 	commit_transaction = journal->j_running_transaction;
 
 	trace_jbd2_start_commit(journal, commit_transaction);
@@ -422,6 +460,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			commit_transaction->t_tid);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_fc_off = 0;
 	J_ASSERT(commit_transaction->t_state == T_RUNNING);
 	commit_transaction->t_state = T_LOCKED;
 
@@ -1121,12 +1160,16 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 1);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FULL_COMMIT_ONGOING;
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
 	spin_lock(&journal->j_list_lock);
 	commit_transaction->t_state = T_FINISHED;
 	/* Check if the transaction can be dropped now that we are finished */
@@ -1138,6 +1181,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	spin_unlock(&journal->j_list_lock);
 	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
+	wake_up(&journal->j_fc_wait);
 
 	/*
 	 * Calculate overall stats

fs/jbd2/journal.c

@@ -159,7 +159,9 @@ static void commit_timeout(struct timer_list *t)
  *
  * 1) COMMIT:  Every so often we need to commit the current state of the
  *    filesystem to disk.  The journal thread is responsible for writing
- *    all of the metadata buffers to disk.
+ *    all of the metadata buffers to disk. If a fast commit is ongoing
+ *    journal thread waits until it's done and then continues from
+ *    there on.
  *
  * 2) CHECKPOINT: We cannot reuse a used section of the log file until all
  *    of the data in that part of the log has been rewritten elsewhere on
@@ -716,6 +718,75 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	return err;
 }
 
+/*
+ * Start a fast commit. If there's an ongoing fast or full commit wait for
+ * it to complete. Returns 0 if a new fast commit was started. Returns -EALREADY
+ * if a fast commit is not needed, either because there's an already a commit
+ * going on or this tid has already been committed. Returns -EINVAL if no jbd2
+ * commit has yet been performed.
+ */
+int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
+{
+	/*
+	 * Fast commits only allowed if at least one full commit has
+	 * been processed.
+	 */
+	if (!journal->j_stats.ts_tid)
+		return -EINVAL;
+
+	if (tid <= journal->j_commit_sequence)
+		return -EALREADY;
+
+	write_lock(&journal->j_state_lock);
+	if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+	    (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_fc_wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		write_unlock(&journal->j_state_lock);
+		schedule();
+		finish_wait(&journal->j_fc_wait, &wait);
+		return -EALREADY;
+	}
+	journal->j_flags |= JBD2_FAST_COMMIT_ONGOING;
+	write_unlock(&journal->j_state_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_begin_commit);
+
+/*
+ * Stop a fast commit. If fallback is set, this function starts commit of
+ * TID tid before any other fast commit can start.
+ */
+static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
+{
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 0);
+	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
+	if (fallback)
+		journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	write_unlock(&journal->j_state_lock);
+	wake_up(&journal->j_fc_wait);
+	if (fallback)
+		return jbd2_complete_transaction(journal, tid);
+	return 0;
+}
+
+int jbd2_fc_end_commit(journal_t *journal)
+{
+	return __jbd2_fc_end_commit(journal, 0, 0);
+}
+EXPORT_SYMBOL(jbd2_fc_end_commit);
+
+int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid)
+{
+	return __jbd2_fc_end_commit(journal, tid, 1);
+}
+EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
+
 /* Return 1 when transaction with given tid has already committed. */
 int jbd2_transaction_committed(journal_t *journal, tid_t tid)
 {
@@ -784,6 +855,110 @@ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
 	return jbd2_journal_bmap(journal, blocknr, retp);
 }
 
+/* Map one fast commit buffer for use by the file system */
+int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
+{
+	unsigned long long pblock;
+	unsigned long blocknr;
+	int ret = 0;
+	struct buffer_head *bh;
+	int fc_off;
+
+	*bh_out = NULL;
+	write_lock(&journal->j_state_lock);
+
+	if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
+		fc_off = journal->j_fc_off;
+		blocknr = journal->j_fc_first + fc_off;
+		journal->j_fc_off++;
+	} else {
+		ret = -EINVAL;
+	}
+	write_unlock(&journal->j_state_lock);
+
+	if (ret)
+		return ret;
+
+	ret = jbd2_journal_bmap(journal, blocknr, &pblock);
+	if (ret)
+		return ret;
+
+	bh = __getblk(journal->j_dev, pblock, journal->j_blocksize);
+	if (!bh)
+		return -ENOMEM;
+
+	lock_buffer(bh);
+
+	clear_buffer_uptodate(bh);
+	set_buffer_dirty(bh);
+	unlock_buffer(bh);
+	journal->j_fc_wbuf[fc_off] = bh;
+
+	*bh_out = bh;
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_get_buf);
+
+/*
+ * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
+ * for completion.
+ */
+int jbd2_fc_wait_bufs(journal_t *journal, int num_blks)
+{
+	struct buffer_head *bh;
+	int i, j_fc_off;
+
+	read_lock(&journal->j_state_lock);
+	j_fc_off = journal->j_fc_off;
+	read_unlock(&journal->j_state_lock);
+
+	/*
+	 * Wait in reverse order to minimize chances of us being woken up before
+	 * all IOs have completed
+	 */
+	for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) {
+		bh = journal->j_fc_wbuf[i];
+		wait_on_buffer(bh);
+		put_bh(bh);
+		journal->j_fc_wbuf[i] = NULL;
+		if (unlikely(!buffer_uptodate(bh)))
+			return -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_wait_bufs);
+
+/*
+ * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
+ * for completion.
+ */
+int jbd2_fc_release_bufs(journal_t *journal)
+{
+	struct buffer_head *bh;
+	int i, j_fc_off;
+
+	read_lock(&journal->j_state_lock);
+	j_fc_off = journal->j_fc_off;
+	read_unlock(&journal->j_state_lock);
+
+	/*
+	 * Wait in reverse order to minimize chances of us being woken up before
+	 * all IOs have completed
+	 */
+	for (i = j_fc_off - 1; i >= 0; i--) {
+		bh = journal->j_fc_wbuf[i];
+		if (!bh)
+			break;
+		put_bh(bh);
+		journal->j_fc_wbuf[i] = NULL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_release_bufs);
+
 /*
  * Conversion of logical to physical block numbers for the journal
  *
@@ -1142,6 +1317,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	init_waitqueue_head(&journal->j_wait_commit);
 	init_waitqueue_head(&journal->j_wait_updates);
 	init_waitqueue_head(&journal->j_wait_reserved);
+	init_waitqueue_head(&journal->j_fc_wait);
 	mutex_init(&journal->j_abort_mutex);
 	mutex_init(&journal->j_barrier);
 	mutex_init(&journal->j_checkpoint_mutex);
@@ -1495,6 +1671,7 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
 static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 {
 	journal_superblock_t *sb = journal->j_superblock;
+	bool had_fast_commit = false;
 
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 	lock_buffer(journal->j_sb_buffer);
@@ -1508,9 +1685,20 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 
 	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
 	sb->s_start    = cpu_to_be32(0);
+	if (jbd2_has_feature_fast_commit(journal)) {
+		/*
+		 * When journal is clean, no need to commit fast commit flag and
+		 * make file system incompatible with older kernels.
+		 */
+		jbd2_clear_feature_fast_commit(journal);
+		had_fast_commit = true;
+	}
 
 	jbd2_write_superblock(journal, write_op);
 
+	if (had_fast_commit)
+		jbd2_set_feature_fast_commit(journal);
+
 	/* Log is no longer empty */
 	write_lock(&journal->j_state_lock);
 	journal->j_flags |= JBD2_FLUSHED;

include/linux/jbd2.h

@@ -861,6 +861,13 @@ struct journal_s
 	 */
 	wait_queue_head_t	j_wait_reserved;
 
+	/**
+	 * @j_fc_wait:
+	 *
+	 * Wait queue to wait for completion of async fast commits.
+	 */
+	wait_queue_head_t	j_fc_wait;
+
 	/**
 	 * @j_checkpoint_mutex:
 	 *
@@ -1232,6 +1239,15 @@ struct journal_s
 	 */
 	struct lockdep_map	j_trans_commit_map;
 #endif
+
+	/**
+	 * @j_fc_cleanup_callback:
+	 *
+	 * Clean-up after fast commit or full commit. JBD2 calls this function
+	 * after every commit operation.
+	 */
+	void (*j_fc_cleanup_callback)(struct journal_s *journal, int);
+
 };
 
 #define jbd2_might_wait_for_commit(j) \
@@ -1316,6 +1332,8 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 #define JBD2_ABORT_ON_SYNCDATA_ERR	0x040	/* Abort the journal on file
 						 * data write error in ordered
 						 * mode */
+#define JBD2_FAST_COMMIT_ONGOING	0x100	/* Fast commit is ongoing */
+#define JBD2_FULL_COMMIT_ONGOING	0x200	/* Full commit is ongoing */
 
 /*
  * Function declarations for the journaling transaction and buffer
@@ -1574,6 +1592,15 @@ extern int jbd2_cleanup_journal_tail(journal_t *);
 
 /* Fast commit related APIs */
 int jbd2_fc_init(journal_t *journal, int num_fc_blks);
+int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
+int jbd2_fc_end_commit(journal_t *journal);
+int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid);
+int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
+int jbd2_submit_inode_data(struct jbd2_inode *jinode);
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
+int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
+int jbd2_fc_release_bufs(journal_t *journal);
+
 /*
  * is_journal_abort
  *