1 files changed, 13 insertions, 29 deletions

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 767c386ed4ce..ba57323bfdce 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -705,11 +705,21 @@ xlog_cil_set_ctx_write_state(
 		 * The LSN we need to pass to the log items on transaction
 		 * commit is the LSN reported by the first log vector write, not
 		 * the commit lsn. If we use the commit record lsn then we can
-		 * move the tail beyond the grant write head.
+		 * move the grant write head beyond the tail LSN and overwrite
+		 * it.
 		 */
 		ctx->start_lsn = lsn;
 		wake_up_all(&cil->xc_start_wait);
 		spin_unlock(&cil->xc_push_lock);
+
+		/*
+		 * Make sure the metadata we are about to overwrite in the log
+		 * has been flushed to stable storage before this iclog is
+		 * issued.
+		 */
+		spin_lock(&cil->xc_log->l_icloglock);
+		iclog->ic_flags |= XLOG_ICL_NEED_FLUSH;
+		spin_unlock(&cil->xc_log->l_icloglock);
 		return;
 	}
 
@@ -888,10 +898,7 @@ xlog_cil_push_work(
 	struct xfs_trans_header thdr;
 	struct xfs_log_iovec	lhdr;
 	struct xfs_log_vec	lvhdr = { NULL };
-	xfs_lsn_t		preflush_tail_lsn;
 	xfs_csn_t		push_seq;
-	struct bio		bio;
-	DECLARE_COMPLETION_ONSTACK(bdev_flush);
 	bool			push_commit_stable;
 
 	new_ctx = xlog_cil_ctx_alloc();
@@ -962,23 +969,6 @@ xlog_cil_push_work(
 	spin_unlock(&cil->xc_push_lock);
 
 	/*
-	 * The CIL is stable at this point - nothing new will be added to it
-	 * because we hold the flush lock exclusively. Hence we can now issue
-	 * a cache flush to ensure all the completed metadata in the journal we
-	 * are about to overwrite is on stable storage.
-	 *
-	 * Because we are issuing this cache flush before we've written the
-	 * tail lsn to the iclog, we can have metadata IO completions move the
-	 * tail forwards between the completion of this flush and the iclog
-	 * being written. In this case, we need to re-issue the cache flush
-	 * before the iclog write. To detect whether the log tail moves, sample
-	 * the tail LSN *before* we issue the flush.
-	 */
-	preflush_tail_lsn = atomic64_read(&log->l_tail_lsn);
-	xfs_flush_bdev_async(&bio, log->l_mp->m_ddev_targp->bt_bdev,
-				&bdev_flush);
-
-	/*
 	 * Pull all the log vectors off the items in the CIL, and remove the
 	 * items from the CIL. We don't need the CIL lock here because it's only
 	 * needed on the transaction commit side which is currently locked out
@@ -1054,12 +1044,6 @@ xlog_cil_push_work(
 	lvhdr.lv_iovecp = &lhdr;
 	lvhdr.lv_next = ctx->lv_chain;
 
-	/*
-	 * Before we format and submit the first iclog, we have to ensure that
-	 * the metadata writeback ordering cache flush is complete.
-	 */
-	wait_for_completion(&bdev_flush);
-
 	error = xlog_cil_write_chain(ctx, &lvhdr);
 	if (error)
 		goto out_abort_free_ticket;
@@ -1118,7 +1102,7 @@ xlog_cil_push_work(
 	if (push_commit_stable &&
 	    ctx->commit_iclog->ic_state == XLOG_STATE_ACTIVE)
 		xlog_state_switch_iclogs(log, ctx->commit_iclog, 0);
-	xlog_state_release_iclog(log, ctx->commit_iclog, preflush_tail_lsn);
+	xlog_state_release_iclog(log, ctx->commit_iclog);
 
 	/* Not safe to reference ctx now! */
 
@@ -1139,7 +1123,7 @@ out_abort_free_ticket:
 		return;
 	}
 	spin_lock(&log->l_icloglock);
-	xlog_state_release_iclog(log, ctx->commit_iclog, 0);
+	xlog_state_release_iclog(log, ctx->commit_iclog);
 	/* Not safe to reference ctx now! */
 	spin_unlock(&log->l_icloglock);
 }