Merge tag 'xfs-5.7-merge-12' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull more xfs updates from Darrick Wong:
 "As promised last week, this batch changes how xfs interacts with
  memory reclaim; how the log batches and throttles log items; how hard
  writes near ENOSPC will try to squeeze more space out of the
  filesystem; and hopefully fix the last of the umount hangs after a
  catastrophic failure.

  Summary:

   - Validate the realtime geometry in the superblock when mounting

   - Refactor a bunch of tricky flag handling in the log code

   - Flush the CIL more judiciously so that we don't wait until there
     are millions of log items consuming a lot of memory.

   - Throttle transaction commits to prevent the xfs frontend from
     flooding the CIL with too many log items.

   - Account metadata buffers correctly for memory reclaim.

   - Mark slabs properly for memory reclaim. These should help reclaim
     run more effectively when XFS is using a lot of memory.

   - Don't write a garbage log record at unmount time if we're trying to
     trigger summary counter recalculation at next mount.

   - Don't block the AIL on locked dquot/inode buffers; instead trigger
     its backoff mechanism to give the lock holder a chance to finish
     up.

   - Ratelimit writeback flushing when buffered writes encounter ENOSPC.

   - Other minor cleanups.

   - Make reflink a synchronous operation when the fs is mounted with
     wsync or sync, which means that now we force the log to disk to
     record the changes"

* tag 'xfs-5.7-merge-12' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (26 commits)
  xfs: reflink should force the log out if mounted with wsync
  xfs: factor out a new xfs_log_force_inode helper
  xfs: fix inode number overflow in ifree cluster helper
  xfs: remove redundant variable assignment in xfs_symlink()
  xfs: ratelimit inode flush on buffered write ENOSPC
  xfs: return locked status of inode buffer on xfsaild push
  xfs: trylock underlying buffer on dquot flush
  xfs: remove unnecessary ternary from xfs_create
  xfs: don't write a corrupt unmount record to force summary counter recalc
  xfs: factor inode lookup from xfs_ifree_cluster
  xfs: tail updates only need to occur when LSN changes
  xfs: factor common AIL item deletion code
  xfs: correctly acount for reclaimable slabs
  xfs: Improve metadata buffer reclaim accountability
  xfs: don't allow log IO to be throttled
  xfs: Throttle commits on delayed background CIL push
  xfs: Lower CIL flush limit for large logs
  xfs: remove some stale comments from the log code
  xfs: refactor unmount record writing
  xfs: merge xlog_commit_record with xlog_write_done
  ...

1 files changed, 44 insertions, 11 deletions

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 64cc0bf2ab3b..b43f0e8f43f2 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -669,6 +669,11 @@ xlog_cil_push_work(
 	ASSERT(push_seq <= ctx->sequence);
 
 	/*
+	 * Wake up any background push waiters now this context is being pushed.
+	 */
+	wake_up_all(&ctx->push_wait);
+
+	/*
 	 * Check if we've anything to push. If there is nothing, then we don't
 	 * move on to a new sequence number and so we have to be able to push
 	 * this sequence again later.
@@ -744,6 +749,7 @@ xlog_cil_push_work(
 	 */
 	INIT_LIST_HEAD(&new_ctx->committing);
 	INIT_LIST_HEAD(&new_ctx->busy_extents);
+	init_waitqueue_head(&new_ctx->push_wait);
 	new_ctx->sequence = ctx->sequence + 1;
 	new_ctx->cil = cil;
 	cil->xc_ctx = new_ctx;
@@ -801,7 +807,7 @@ xlog_cil_push_work(
 	lvhdr.lv_iovecp = &lhdr;
 	lvhdr.lv_next = ctx->lv_chain;
 
-	error = xlog_write(log, &lvhdr, tic, &ctx->start_lsn, NULL, 0);
+	error = xlog_write(log, &lvhdr, tic, &ctx->start_lsn, NULL, 0, true);
 	if (error)
 		goto out_abort_free_ticket;
 
@@ -839,10 +845,11 @@ restart:
 	}
 	spin_unlock(&cil->xc_push_lock);
 
-	/* xfs_log_done always frees the ticket on error. */
-	commit_lsn = xfs_log_done(log->l_mp, tic, &commit_iclog, false);
-	if (commit_lsn == -1)
-		goto out_abort;
+	error = xlog_commit_record(log, tic, &commit_iclog, &commit_lsn);
+	if (error)
+		goto out_abort_free_ticket;
+
+	xfs_log_ticket_ungrant(log, tic);
 
 	spin_lock(&commit_iclog->ic_callback_lock);
 	if (commit_iclog->ic_state == XLOG_STATE_IOERROR) {
@@ -875,7 +882,7 @@ out_skip:
 	return;
 
 out_abort_free_ticket:
-	xfs_log_ticket_put(tic);
+	xfs_log_ticket_ungrant(log, tic);
 out_abort:
 	ASSERT(XLOG_FORCED_SHUTDOWN(log));
 	xlog_cil_committed(ctx);
@@ -890,7 +897,7 @@ out_abort:
  */
 static void
 xlog_cil_push_background(
-	struct xlog	*log)
+	struct xlog	*log) __releases(cil->xc_ctx_lock)
 {
 	struct xfs_cil	*cil = log->l_cilp;
 
@@ -904,14 +911,36 @@ xlog_cil_push_background(
 	 * don't do a background push if we haven't used up all the
 	 * space available yet.
 	 */
-	if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log))
+	if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log)) {
+		up_read(&cil->xc_ctx_lock);
 		return;
+	}
 
 	spin_lock(&cil->xc_push_lock);
 	if (cil->xc_push_seq < cil->xc_current_sequence) {
 		cil->xc_push_seq = cil->xc_current_sequence;
 		queue_work(log->l_mp->m_cil_workqueue, &cil->xc_push_work);
 	}
+
+	/*
+	 * Drop the context lock now, we can't hold that if we need to sleep
+	 * because we are over the blocking threshold. The push_lock is still
+	 * held, so blocking threshold sleep/wakeup is still correctly
+	 * serialised here.
+	 */
+	up_read(&cil->xc_ctx_lock);
+
+	/*
+	 * If we are well over the space limit, throttle the work that is being
+	 * done until the push work on this context has begun.
+	 */
+	if (cil->xc_ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) {
+		trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket);
+		ASSERT(cil->xc_ctx->space_used < log->l_logsize);
+		xlog_wait(&cil->xc_ctx->push_wait, &cil->xc_push_lock);
+		return;
+	}
+
 	spin_unlock(&cil->xc_push_lock);
 
 }
@@ -1007,7 +1036,10 @@ xfs_log_commit_cil(
 	if (commit_lsn)
 		*commit_lsn = xc_commit_lsn;
 
-	xfs_log_done(mp, tp->t_ticket, NULL, regrant);
+	if (regrant && !XLOG_FORCED_SHUTDOWN(log))
+		xfs_log_ticket_regrant(log, tp->t_ticket);
+	else
+		xfs_log_ticket_ungrant(log, tp->t_ticket);
 	tp->t_ticket = NULL;
 	xfs_trans_unreserve_and_mod_sb(tp);
 
@@ -1028,9 +1060,9 @@ xfs_log_commit_cil(
 		if (lip->li_ops->iop_committing)
 			lip->li_ops->iop_committing(lip, xc_commit_lsn);
 	}
-	xlog_cil_push_background(log);
 
-	up_read(&cil->xc_ctx_lock);
+	/* xlog_cil_push_background() releases cil->xc_ctx_lock */
+	xlog_cil_push_background(log);
 }
 
 /*
@@ -1189,6 +1221,7 @@ xlog_cil_init(
 
 	INIT_LIST_HEAD(&ctx->committing);
 	INIT_LIST_HEAD(&ctx->busy_extents);
+	init_waitqueue_head(&ctx->push_wait);
 	ctx->sequence = 1;
 	ctx->cil = cil;
 	cil->xc_ctx = ctx;