[PATCH 6.1 13/19] xfs: up(ic_sema) if flushing data device fails

[ Upstream commit 471de20303dda0b67981e06d59cc6c4a83fd2a3c ]

We flush the data device cache before we issue external log IO. If
the flush fails, we shut down the log immediately and return. However,
the iclog->ic_sema is left in a decremented state so let's add an up().
Prior to this patch, xfs/438 would fail consistently when running with
an external log device:

sync
  -> xfs_log_force
  -> xlog_write_iclog
      -> down(&iclog->ic_sema)
      -> blkdev_issue_flush (fail causes us to intiate shutdown)
          -> xlog_force_shutdown
          -> return

unmount
  -> xfs_log_umount
      -> xlog_wait_iclog_completion
          -> down(&iclog->ic_sema) --------> HANG

There is a second early return / shutdown. Make sure the up() happens
for it as well. Also make sure we cleanup the iclog state,
xlog_state_done_syncing, before dropping the iclog lock.

Fixes: b5d721eaae47 ("xfs: external logs need to flush data device")
Fixes: 842a42d126b4 ("xfs: shutdown on failure to add page to log bio")
Fixes: 7d839e325af2 ("xfs: check return codes when flushing block devices")
Signed-off-by: Leah Rumancik <[email protected]>
Reviewed-by: "Darrick J. Wong" <[email protected]>
Signed-off-by: Chandan Babu R <[email protected]>
Signed-off-by: Leah Rumancik <[email protected]>
---
 fs/xfs/xfs_log.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 59c982297503..ce6b303484cf 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1889,13 +1889,11 @@ xlog_write_iclog(
 		 * the log state machine to propagate I/O errors instead of
 		 * doing it here.  We kick of the state machine and unlock
 		 * the buffer manually, the code needs to be kept in sync
 		 * with the I/O completion path.
 		 */
-		xlog_state_done_syncing(iclog);
-		up(&iclog->ic_sema);
-		return;
+		goto sync;
 	}
 
 	/*
 	 * We use REQ_SYNC | REQ_IDLE here to tell the block layer the are more
 	 * IOs coming immediately after this one. This prevents the block layer
@@ -1921,44 +1919,47 @@ xlog_write_iclog(
 		 * writeback from the log succeeded.  Repeating the flush is
 		 * not possible, hence we must shut down with log IO error to
 		 * avoid shutdown re-entering this path and erroring out again.
 		 */
 		if (log->l_targ != log->l_mp->m_ddev_targp &&
-		    blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) {
-			xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
-			return;
-		}
+		    blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev))
+			goto shutdown;
 	}
 	if (iclog->ic_flags & XLOG_ICL_NEED_FUA)
 		iclog->ic_bio.bi_opf |= REQ_FUA;
 
 	iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA);
 
-	if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) {
-		xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
-		return;
-	}
+	if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count))
+		goto shutdown;
+
 	if (is_vmalloc_addr(iclog->ic_data))
 		flush_kernel_vmap_range(iclog->ic_data, count);
 
 	/*
 	 * If this log buffer would straddle the end of the log we will have
 	 * to split it up into two bios, so that we can continue at the start.
 	 */
 	if (bno + BTOBB(count) > log->l_logBBsize) {
 		struct bio *split;
 
 		split = bio_split(&iclog->ic_bio, log->l_logBBsize - bno,
 				  GFP_NOIO, &fs_bio_set);
 		bio_chain(split, &iclog->ic_bio);
 		submit_bio(split);
 
 		/* restart at logical offset zero for the remainder */
 		iclog->ic_bio.bi_iter.bi_sector = log->l_logBBstart;
 	}
 
 	submit_bio(&iclog->ic_bio);
+	return;
+shutdown:
+	xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
+sync:
+	xlog_state_done_syncing(iclog);
+	up(&iclog->ic_sema);
 }
 
 /*
  * We need to bump cycle number for the part of the iclog that is
  * written to the start of the log. Watch out for the header magic
-- 
2.48.1.362.g079036d154-goog