diff mbox series

[v3,04/13] jbd2: fast-commit commit path new APIs

Message ID 20191001074101.256523-5-harshadshirwadkar@gmail.com
State Changes Requested
Headers show
Series ext4: add fast commit support | expand

Commit Message

harshad shirwadkar Oct. 1, 2019, 7:40 a.m. UTC 
This patch adds new helper APIs that ext4 needs for fast
commits. These new fast commit APIs are used by subsequent fast commit
patches to implement fast commits. Following new APIs are added:

/*
 * Returns when either a full commit or a fast commit
 * completes
 */
int jbd2_fc_complete_commit(journal_tc *journal, tid_t tid,
			                tid_t subtid)

/* Send all the data buffers related to an inode */
int journal_submit_inode_data(journal_t *journal,
			                  struct jbd2_inode *jinode)

/* Map one fast commit buffer for use by the file system */
int jbd2_map_fc_buf(journal_t *journal, struct buffer_head **bh_out)

/* Wait on fast commit buffers to complete IO */
jbd2_wait_on_fc_bufs(journal_t *journal, int num_bufs)

/*
 * Returns 1 if transaction identified by tid:subtid is already
 * committed.
 */
int jbd2_commit_check(journal_t *journal, tid_t tid, tid_t subtid)

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
---
 fs/jbd2/commit.c     |  32 +++++++++++++
 fs/jbd2/journal.c    | 110 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/jbd2.h |   8 ++++
 3 files changed, 150 insertions(+)

Comments

Theodore Ts'o Oct. 16, 2019, 5:20 p.m. UTC | #1 
On Tue, Oct 01, 2019 at 12:40:53AM -0700, Harshad Shirwadkar wrote:
> This patch adds new helper APIs that ext4 needs for fast
> commits. These new fast commit APIs are used by subsequent fast commit
> patches to implement fast commits. Following new APIs are added:
> 
> /*
>  * Returns when either a full commit or a fast commit
>  * completes
>  */
> int jbd2_fc_complete_commit(journal_tc *journal, tid_t tid,
> 			                tid_t subtid)
> 
> /* Send all the data buffers related to an inode */
> int journal_submit_inode_data(journal_t *journal,
> 			                  struct jbd2_inode *jinode)
> 
> /* Map one fast commit buffer for use by the file system */
> int jbd2_map_fc_buf(journal_t *journal, struct buffer_head **bh_out)
> 
> /* Wait on fast commit buffers to complete IO */
> jbd2_wait_on_fc_bufs(journal_t *journal, int num_bufs)
> 
> /*
>  * Returns 1 if transaction identified by tid:subtid is already
>  * committed.
>  */
> int jbd2_commit_check(journal_t *journal, tid_t tid, tid_t subtid)

Please move these commits into the code, before each function.  This
documentation is going to be useful long after the patch gets merged,
and people will be looking for them in the source code, and not
necessarily in the commit description.

> 
> diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
> index 7db3e2b6336d..e85f51e1cc70 100644
> --- a/fs/jbd2/commit.c
> +++ b/fs/jbd2/commit.c
> @@ -202,6 +202,38 @@ static int journal_submit_inode_data_buffers(struct address_space *mapping,
>  	return ret;
>  }
>  
> +int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode)

This code was pulled out of journal_submit_data_buffers(), but given
how it was called, there were locking assumptions that were broken as
a result.

> +{
> +	struct address_space *mapping;
> +	loff_t dirty_start = jinode->i_dirty_start;
> +	loff_t dirty_end = jinode->i_dirty_end;
> +	int ret;
> +
> +	if (!jinode)
> +		return 0;
> +
> +	if (!(jinode->i_flags & JI_WRITE_DATA))
> +		return 0;

Originally in journal_submit_data_buffers() we were holding onto
j_list_lock, and that's needed to safely reference jinode->i_flags

> +
> +	dirty_start = jinode->i_dirty_start;
> +	dirty_end = jinode->i_dirty_end;
> +
> +	mapping = jinode->i_vfs_inode->i_mapping;
> +	jinode->i_flags |= JI_COMMIT_RUNNING;

Originally there was a spin_uinlock(&journal->j_list_lock) here.  And
that's important since there was a memory barrier there which we
needed in order to make sure other CPU's would see the
JI_COMMIT_RUNNING flag.

It's not clear we need to worry about this, if this is only going to
be used in the async fast commit context.  This is another example of
how trying to do the fast commit in the userspace (or nfs server's)
process context is much simpler, since the the JI_COMMIT_RUNNING flag
is needed to make sure there isn't a race with the inode getting
evicted and jbd2_journal_release_jbd_inode.

And if we're calling this function from ext4_jbd2.c, where the inode's
ref count is elevated and there is no risk of the inode getting
evicted from memory, then this particular race is not a problem, and
so messing with JI_COMMIT_RUNNING and the call to wake_up_bit is all
not necessary.

By the way, this function only submits the data to be written out.  It
does not wait for the writeout to be completed.  For that, you need
the equivalent of journal_finish_inode_data_buffers(), and I don't see
that equivalent functionality in the fast commit code path?

     			      	     - Ted
diff mbox series

Patch

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 7db3e2b6336d..e85f51e1cc70 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -202,6 +202,38 @@  static int journal_submit_inode_data_buffers(struct address_space *mapping,
 	return ret;
 }
 
+int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode)
+{
+	struct address_space *mapping;
+	loff_t dirty_start = jinode->i_dirty_start;
+	loff_t dirty_end = jinode->i_dirty_end;
+	int ret;
+
+	if (!jinode)
+		return 0;
+
+	if (!(jinode->i_flags & JI_WRITE_DATA))
+		return 0;
+
+	dirty_start = jinode->i_dirty_start;
+	dirty_end = jinode->i_dirty_end;
+
+	mapping = jinode->i_vfs_inode->i_mapping;
+	jinode->i_flags |= JI_COMMIT_RUNNING;
+
+	trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
+	ret = journal_submit_inode_data_buffers(mapping, dirty_start,
+						dirty_end);
+
+	jinode->i_flags &= ~JI_COMMIT_RUNNING;
+	/* Protect JI_COMMIT_RUNNING flag */
+	smp_mb();
+	wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
+
+	return ret;
+}
+EXPORT_SYMBOL(jbd2_submit_inode_data);
+
 /*
  * Submit all the data buffers of inode associated with the transaction to
  * disk.
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 6853064605ff..14d549445418 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -781,6 +781,18 @@  int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	return __jbd2_log_wait_commit(journal, tid, 0);
 }
 
+int jbd2_commit_check(journal_t *journal, tid_t tid, tid_t subtid)
+{
+	if (journal->j_commit_sequence >= tid)
+		return 1;
+	if (!journal->j_running_transaction)
+		return 0;
+	if (journal->j_running_transaction->t_tid > tid)
+		return 1;
+	if (journal->j_running_transaction->t_subtid > subtid)
+		return 1;
+	return 0;
+}
 
 /* Return 1 when transaction with given tid has already committed. */
 int jbd2_transaction_committed(journal_t *journal, tid_t tid)
@@ -830,6 +842,33 @@  int jbd2_complete_transaction(journal_t *journal, tid_t tid)
 }
 EXPORT_SYMBOL(jbd2_complete_transaction);
 
+int jbd2_fc_complete_commit(journal_t *journal, tid_t tid, tid_t subtid)
+{
+	int	need_to_wait = 1;
+
+	read_lock(&journal->j_state_lock);
+	if (journal->j_running_transaction &&
+	    journal->j_running_transaction->t_tid == tid) {
+		/* Check if fast commit was already done */
+		if (tid_geq(journal->j_fc_sequence, subtid))
+			need_to_wait = 0;
+		if (journal->j_commit_request != tid) {
+			/* transaction not yet started, so request it */
+			read_unlock(&journal->j_state_lock);
+			jbd2_log_start_commit_fast(journal, tid);
+			goto wait_commit;
+		}
+	} else if (!(journal->j_committing_transaction &&
+		     journal->j_committing_transaction->t_tid == tid))
+		need_to_wait = 0;
+	read_unlock(&journal->j_state_lock);
+	if (!need_to_wait)
+		return 0;
+wait_commit:
+	return __jbd2_log_wait_commit(journal, tid, subtid);
+}
+EXPORT_SYMBOL(jbd2_fc_complete_commit);
+
 /*
  * Log buffer allocation routines:
  */
@@ -850,6 +889,77 @@  int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
 	return jbd2_journal_bmap(journal, blocknr, retp);
 }
 
+int jbd2_map_fc_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;
+	journal_header_t *jhdr;
+
+	write_lock(&journal->j_state_lock);
+
+	if (journal->j_fc_off + journal->j_first_fc < journal->j_last_fc) {
+		fc_off = journal->j_fc_off;
+		blocknr = journal->j_first_fc + 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);
+	jhdr = (journal_header_t *)bh->b_data;
+	jhdr->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
+	jhdr->h_blocktype = cpu_to_be32(JBD2_FC_BLOCK);
+	jhdr->h_sequence = cpu_to_be32(journal->j_running_transaction->t_tid);
+
+	set_buffer_uptodate(bh);
+	unlock_buffer(bh);
+	journal->j_fc_wbuf[fc_off] = bh;
+
+	*bh_out = bh;
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_map_fc_buf);
+
+int jbd2_wait_on_fc_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);
+		if (unlikely(!buffer_uptodate(bh)))
+			return -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_wait_on_fc_bufs);
+
 /*
  * Conversion of logical to physical block numbers for the journal
  *
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 41315f648c0f..c6a2b82de4cf 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -124,6 +124,7 @@  typedef struct journal_s	journal_t;	/* Journal control structure */
 #define JBD2_SUPERBLOCK_V1	3
 #define JBD2_SUPERBLOCK_V2	4
 #define JBD2_REVOKE_BLOCK	5
+#define JBD2_FC_BLOCK		6
 
 /*
  * Standard header for all descriptor blocks:
@@ -1579,6 +1580,7 @@  int jbd2_transaction_committed(journal_t *journal, tid_t tid);
 int jbd2_complete_transaction(journal_t *journal, tid_t tid);
 int jbd2_log_do_checkpoint(journal_t *journal);
 int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid);
+int jbd2_fc_complete_commit(journal_t *journal, tid_t tid, tid_t subtid);
 
 void __jbd2_log_wait_for_space(journal_t *journal);
 extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
@@ -1729,6 +1731,12 @@  static inline tid_t  jbd2_get_latest_transaction(journal_t *journal)
 	return tid;
 }
 
+/* Fast commit related APIs */
+int jbd2_map_fc_buf(journal_t *journal, struct buffer_head **bh_out);
+int jbd2_wait_on_fc_bufs(journal_t *journal, int num_blks);
+int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode);
+int jbd2_commit_check(journal_t *journal, tid_t tid, tid_t subtid);
+
 #ifdef __KERNEL__
 
 #define buffer_trace_init(bh)	do {} while (0)